* [PATCH v2 15/28] nfsd: use RCU to protect fi_deleg_file
From: Jeff Layton @ 2026-04-16 17:35 UTC (permalink / raw)
To: Alexander Viro, Christian Brauner, Jan Kara, Chuck Lever,
Alexander Aring, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, NeilBrown,
Olga Kornievskaia, Dai Ngo, Tom Talpey, Trond Myklebust,
Anna Schumaker, Amir Goldstein
Cc: Calum Mackay, linux-fsdevel, linux-kernel, linux-trace-kernel,
linux-doc, linux-nfs, Jeff Layton
In-Reply-To: <20260416-dir-deleg-v2-0-851426a550f6@kernel.org>
fi_deleg_file can be NULLed by put_deleg_file() when fi_delegees drops
to zero during delegation teardown (e.g. DELEGRETURN). Concurrent
accesses from workqueue callbacks -- such as CB_NOTIFY -- can
dereference a NULL pointer if they race with this teardown.
Annotate fi_deleg_file with __rcu and convert all accessors to use
proper RCU primitives:
- rcu_assign_pointer() / RCU_INIT_POINTER() for stores
- rcu_dereference_protected() for reads under fi_lock or where
fi_delegees > 0 guarantees stability
This prepares for a subsequent patch that will use rcu_read_lock +
rcu_dereference + nfsd_file_get to safely acquire a reference from
the CB_NOTIFY callback path without holding fi_lock.
Assisted-by: Claude (Anthropic Claude Code)
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4layouts.c | 2 +-
fs/nfsd/nfs4state.c | 40 ++++++++++++++++++++++++----------------
fs/nfsd/state.h | 2 +-
3 files changed, 26 insertions(+), 18 deletions(-)
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 8974e3d85d75..d32cc6b38c23 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -248,7 +248,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
NFSPROC4_CLNT_CB_LAYOUT);
if (parent->sc_type == SC_TYPE_DELEG)
- ls->ls_file = nfsd_file_get(fp->fi_deleg_file);
+ ls->ls_file = nfsd_file_get(rcu_dereference_protected(fp->fi_deleg_file, 1));
else
ls->ls_file = find_any_file(fp);
BUG_ON(!ls->ls_file);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c0046fc3c1b1..ef04e26b4f30 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1212,7 +1212,9 @@ static void put_deleg_file(struct nfs4_file *fp)
spin_lock(&fp->fi_lock);
if (--fp->fi_delegees == 0) {
- swap(nf, fp->fi_deleg_file);
+ nf = rcu_dereference_protected(fp->fi_deleg_file,
+ lockdep_is_held(&fp->fi_lock));
+ rcu_assign_pointer(fp->fi_deleg_file, NULL);
swap(rnf, fp->fi_rdeleg_file);
}
spin_unlock(&fp->fi_lock);
@@ -1295,7 +1297,7 @@ static void nfsd_fsnotify_recalc_mask(struct nfsd_file *nf)
static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp)
{
struct nfs4_file *fp = dp->dl_stid.sc_file;
- struct nfsd_file *nf = fp->fi_deleg_file;
+ struct nfsd_file *nf = rcu_dereference_protected(fp->fi_deleg_file, 1);
WARN_ON_ONCE(!fp->fi_delegees);
@@ -3167,7 +3169,8 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st)
/* XXX: lease time, whether it's being recalled. */
spin_lock(&nf->fi_lock);
- file = nf->fi_deleg_file;
+ file = rcu_dereference_protected(nf->fi_deleg_file,
+ lockdep_is_held(&nf->fi_lock));
if (file) {
seq_puts(s, ", ");
nfs4_show_superblock(s, file);
@@ -4949,7 +4952,7 @@ static void nfsd4_file_init(const struct svc_fh *fh, struct nfs4_file *fp)
INIT_LIST_HEAD(&fp->fi_delegations);
INIT_LIST_HEAD(&fp->fi_clnt_odstate);
fh_copy_shallow(&fp->fi_fhandle, &fh->fh_handle);
- fp->fi_deleg_file = NULL;
+ RCU_INIT_POINTER(fp->fi_deleg_file, NULL);
fp->fi_rdeleg_file = NULL;
fp->fi_had_conflict = false;
fp->fi_share_deny = 0;
@@ -6101,7 +6104,7 @@ static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp, u32
fl->c.flc_type = deleg_is_read(dp->dl_type) ? F_RDLCK : F_WRLCK;
fl->c.flc_owner = (fl_owner_t)dp;
fl->c.flc_pid = current->tgid;
- fl->c.flc_file = dp->dl_stid.sc_file->fi_deleg_file->nf_file;
+ fl->c.flc_file = rcu_dereference_protected(dp->dl_stid.sc_file->fi_deleg_file, 1)->nf_file;
return fl;
}
@@ -6109,7 +6112,7 @@ static int nfsd4_check_conflicting_opens(struct nfs4_client *clp,
struct nfs4_file *fp)
{
struct nfs4_ol_stateid *st;
- struct file *f = fp->fi_deleg_file->nf_file;
+ struct file *f = rcu_dereference_protected(fp->fi_deleg_file, 1)->nf_file;
struct inode *ino = file_inode(f);
int writes;
@@ -6186,7 +6189,7 @@ nfsd4_verify_deleg_dentry(struct nfsd4_open *open, struct nfs4_file *fp,
exp_put(exp);
dput(child);
- if (child != file_dentry(fp->fi_deleg_file->nf_file))
+ if (child != file_dentry(rcu_dereference_protected(fp->fi_deleg_file, 1)->nf_file))
return -EAGAIN;
return 0;
@@ -6292,8 +6295,9 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
status = -EAGAIN;
else if (nfsd4_verify_setuid_write(open, nf))
status = -EAGAIN;
- else if (!fp->fi_deleg_file) {
- fp->fi_deleg_file = nf;
+ else if (!rcu_dereference_protected(fp->fi_deleg_file,
+ lockdep_is_held(&fp->fi_lock))) {
+ rcu_assign_pointer(fp->fi_deleg_file, nf);
/* increment early to prevent fi_deleg_file from being
* cleared */
fp->fi_delegees = 1;
@@ -6318,7 +6322,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
if (!fl)
goto out_clnt_odstate;
- status = kernel_setlease(fp->fi_deleg_file->nf_file,
+ status = kernel_setlease(rcu_dereference_protected(fp->fi_deleg_file, 1)->nf_file,
fl->c.flc_type, &fl, NULL);
if (fl)
locks_free_lease(fl);
@@ -6339,7 +6343,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
* Now that the deleg is set, check again to ensure that nothing
* raced in and changed the mode while we weren't looking.
*/
- status = nfsd4_verify_setuid_write(open, fp->fi_deleg_file);
+ status = nfsd4_verify_setuid_write(open, rcu_dereference_protected(fp->fi_deleg_file, 1));
if (status)
goto out_unlock;
@@ -6360,7 +6364,8 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
return dp;
out_unlock:
- kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp);
+ kernel_setlease(rcu_dereference_protected(fp->fi_deleg_file, 1)->nf_file,
+ F_UNLCK, NULL, (void **)&dp);
out_clnt_odstate:
put_clnt_odstate(dp->dl_clnt_odstate);
nfs4_put_stid(&dp->dl_stid);
@@ -6517,8 +6522,9 @@ nfs4_open_delegation(struct svc_rqst *rqstp, struct nfsd4_open *open,
memcpy(&open->op_delegate_stateid, &dp->dl_stid.sc_stateid, sizeof(dp->dl_stid.sc_stateid));
if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) {
- struct file *f = dp->dl_stid.sc_file->fi_deleg_file->nf_file;
+ struct file *f;
+ f = rcu_dereference_protected(dp->dl_stid.sc_file->fi_deleg_file, 1)->nf_file;
if (!nfsd4_add_rdaccess_to_wrdeleg(rqstp, open, fh, stp) ||
!nfs4_delegation_stat(dp, currentfh, &stat)) {
nfs4_put_stid(&dp->dl_stid);
@@ -9660,8 +9666,9 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
/* existing delegation? */
if (nfs4_delegation_exists(clp, fp)) {
status = -EAGAIN;
- } else if (!fp->fi_deleg_file) {
- fp->fi_deleg_file = nfsd_file_get(nf);
+ } else if (!rcu_dereference_protected(fp->fi_deleg_file,
+ lockdep_is_held(&fp->fi_lock))) {
+ rcu_assign_pointer(fp->fi_deleg_file, nfsd_file_get(nf));
fp->fi_delegees = 1;
} else {
++fp->fi_delegees;
@@ -9713,7 +9720,8 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
}
/* Something failed. Drop the lease and clean up the stid */
- kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp);
+ kernel_setlease(rcu_dereference_protected(fp->fi_deleg_file, 1)->nf_file,
+ F_UNLCK, NULL, (void **)&dp);
out_put_stid:
nfs4_put_stid(&dp->dl_stid);
out_delegees:
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 22c9a1e7d8fd..eb5946b0999e 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -698,7 +698,7 @@ struct nfs4_file {
*/
atomic_t fi_access[2];
u32 fi_share_deny;
- struct nfsd_file *fi_deleg_file;
+ struct nfsd_file __rcu *fi_deleg_file;
struct nfsd_file *fi_rdeleg_file;
int fi_delegees;
struct knfsd_fh fi_fhandle;
--
2.53.0
^ permalink raw reply related
* [PATCH v2 16/28] nfsd: add data structures for handling CB_NOTIFY
From: Jeff Layton @ 2026-04-16 17:35 UTC (permalink / raw)
To: Alexander Viro, Christian Brauner, Jan Kara, Chuck Lever,
Alexander Aring, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, NeilBrown,
Olga Kornievskaia, Dai Ngo, Tom Talpey, Trond Myklebust,
Anna Schumaker, Amir Goldstein
Cc: Calum Mackay, linux-fsdevel, linux-kernel, linux-trace-kernel,
linux-doc, linux-nfs, Jeff Layton
In-Reply-To: <20260416-dir-deleg-v2-0-851426a550f6@kernel.org>
Add the data structures, allocation helpers, and callback operations
needed for directory delegation CB_NOTIFY support:
- struct nfsd_notify_event: carries fsnotify events for CB_NOTIFY
- struct nfsd4_cb_notify: per-delegation state for notification handling
- Union dl_cb_fattr with dl_cb_notify in nfs4_delegation since a
delegation is either a regular file delegation or a directory
delegation, never both
Refactor alloc_init_deleg() into a common __alloc_init_deleg() base
with a pluggable sc_free callback, and add alloc_init_dir_deleg() which
allocates the page array and notify4 buffer needed for CB_NOTIFY
encoding.
Add skeleton nfsd4_cb_notify_ops with done/release handlers that will
be filled in when the notification path is wired up.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4state.c | 117 +++++++++++++++++++++++++++++++++++++++++++++-------
fs/nfsd/state.h | 46 ++++++++++++++++++++-
2 files changed, 147 insertions(+), 16 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index ef04e26b4f30..eefce9e7c628 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -126,6 +126,7 @@ static void free_session(struct nfsd4_session *);
static const struct nfsd4_callback_ops nfsd4_cb_recall_ops;
static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops;
static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops;
+static const struct nfsd4_callback_ops nfsd4_cb_notify_ops;
static struct workqueue_struct *laundry_wq;
@@ -1123,29 +1124,31 @@ static void block_delegations(struct knfsd_fh *fh)
}
static struct nfs4_delegation *
-alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
- struct nfs4_clnt_odstate *odstate, u32 dl_type)
+__alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
+ struct nfs4_clnt_odstate *odstate, u32 dl_type,
+ void (*sc_free)(struct nfs4_stid *))
{
struct nfs4_delegation *dp;
struct nfs4_stid *stid;
long n;
- dprintk("NFSD alloc_init_deleg\n");
+ if (delegation_blocked(&fp->fi_fhandle))
+ return NULL;
+
n = atomic_long_inc_return(&num_delegations);
if (n < 0 || n > max_delegations)
goto out_dec;
- if (delegation_blocked(&fp->fi_fhandle))
- goto out_dec;
- stid = nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg);
+
+ stid = nfs4_alloc_stid(clp, deleg_slab, sc_free);
if (stid == NULL)
goto out_dec;
- dp = delegstateid(stid);
/*
* delegation seqid's are never incremented. The 4.1 special
* meaning of seqid 0 isn't meaningful, really, but let's avoid
- * 0 anyway just for consistency and use 1:
+ * 0 anyway just for consistency and use 1.
*/
+ dp = delegstateid(stid);
dp->dl_stid.sc_stateid.si_generation = 1;
INIT_LIST_HEAD(&dp->dl_perfile);
INIT_LIST_HEAD(&dp->dl_perclnt);
@@ -1155,19 +1158,75 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
dp->dl_type = dl_type;
dp->dl_retries = 1;
dp->dl_recalled = false;
- nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
- &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL);
- nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client,
- &nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR);
- dp->dl_cb_fattr.ncf_file_modified = false;
get_nfs4_file(fp);
dp->dl_stid.sc_file = fp;
+ nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
+ &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL);
return dp;
out_dec:
atomic_long_dec(&num_delegations);
return NULL;
}
+static struct nfs4_delegation *
+alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
+ struct nfs4_clnt_odstate *odstate, u32 dl_type)
+{
+ struct nfs4_delegation *dp;
+
+ dp = __alloc_init_deleg(clp, fp, odstate, dl_type, nfs4_free_deleg);
+ if (!dp)
+ return NULL;
+
+ nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client,
+ &nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR);
+ dp->dl_cb_fattr.ncf_file_modified = false;
+ return dp;
+}
+
+static void nfs4_free_dir_deleg(struct nfs4_stid *stid)
+{
+ struct nfs4_delegation *dp = delegstateid(stid);
+ struct nfsd4_cb_notify *ncn = &dp->dl_cb_notify;
+ int i;
+
+ for (i = 0; i < ncn->ncn_evt_cnt; ++i)
+ nfsd_notify_event_put(ncn->ncn_evt[i]);
+ release_pages(ncn->ncn_pages, NOTIFY4_PAGE_ARRAY_SIZE);
+ kfree(ncn->ncn_nf);
+ nfs4_free_deleg(stid);
+}
+
+static struct nfs4_delegation *
+alloc_init_dir_deleg(struct nfs4_client *clp, struct nfs4_file *fp)
+{
+ struct nfs4_delegation *dp;
+ struct nfsd4_cb_notify *ncn;
+ int npages;
+
+ dp = __alloc_init_deleg(clp, fp, NULL, NFS4_OPEN_DELEGATE_READ, nfs4_free_dir_deleg);
+ if (!dp)
+ return NULL;
+
+ ncn = &dp->dl_cb_notify;
+
+ npages = alloc_pages_bulk(GFP_KERNEL, NOTIFY4_PAGE_ARRAY_SIZE, ncn->ncn_pages);
+ if (npages != NOTIFY4_PAGE_ARRAY_SIZE) {
+ nfs4_put_stid(&dp->dl_stid);
+ return NULL;
+ }
+
+ ncn->ncn_nf = kcalloc(NOTIFY4_EVENT_QUEUE_SIZE, sizeof(*ncn->ncn_nf), GFP_KERNEL);
+ if (!ncn->ncn_nf) {
+ nfs4_put_stid(&dp->dl_stid);
+ return NULL;
+ }
+ spin_lock_init(&ncn->ncn_lock);
+ nfsd4_init_cb(&ncn->ncn_cb, dp->dl_stid.sc_client,
+ &nfsd4_cb_notify_ops, NFSPROC4_CLNT_CB_NOTIFY);
+ return dp;
+}
+
void
nfs4_put_stid(struct nfs4_stid *s)
{
@@ -3389,6 +3448,30 @@ nfsd4_cb_getattr_release(struct nfsd4_callback *cb)
nfs4_put_stid(&dp->dl_stid);
}
+static int
+nfsd4_cb_notify_done(struct nfsd4_callback *cb,
+ struct rpc_task *task)
+{
+ switch (task->tk_status) {
+ case -NFS4ERR_DELAY:
+ rpc_delay(task, 2 * HZ);
+ return 0;
+ default:
+ return 1;
+ }
+}
+
+static void
+nfsd4_cb_notify_release(struct nfsd4_callback *cb)
+{
+ struct nfsd4_cb_notify *ncn =
+ container_of(cb, struct nfsd4_cb_notify, ncn_cb);
+ struct nfs4_delegation *dp =
+ container_of(ncn, struct nfs4_delegation, dl_cb_notify);
+
+ nfs4_put_stid(&dp->dl_stid);
+}
+
static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = {
.done = nfsd4_cb_recall_any_done,
.release = nfsd4_cb_recall_any_release,
@@ -3401,6 +3484,12 @@ static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops = {
.opcode = OP_CB_GETATTR,
};
+static const struct nfsd4_callback_ops nfsd4_cb_notify_ops = {
+ .done = nfsd4_cb_notify_done,
+ .release = nfsd4_cb_notify_release,
+ .opcode = OP_CB_NOTIFY,
+};
+
static void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf)
{
struct nfs4_delegation *dp =
@@ -9683,7 +9772,7 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
/* Try to set up the lease */
status = -ENOMEM;
- dp = alloc_init_deleg(clp, fp, NULL, NFS4_OPEN_DELEGATE_READ);
+ dp = alloc_init_dir_deleg(clp, fp);
if (!dp)
goto out_delegees;
if (cstate->current_fh.fh_export)
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index eb5946b0999e..500e07e47909 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -197,6 +197,44 @@ struct nfs4_cb_fattr {
#define NOTIFY4_EVENT_QUEUE_SIZE 3
#define NOTIFY4_PAGE_ARRAY_SIZE 1
+struct nfsd_notify_event {
+ refcount_t ne_ref; // refcount
+ u32 ne_mask; // FS_* mask from fsnotify callback
+ struct dentry *ne_dentry; // dentry reference to target
+ u32 ne_namelen; // length of ne_name
+ char ne_name[]; // name of dentry being changed
+};
+
+static inline struct nfsd_notify_event *nfsd_notify_event_get(struct nfsd_notify_event *ne)
+{
+ refcount_inc(&ne->ne_ref);
+ return ne;
+}
+
+static inline void nfsd_notify_event_put(struct nfsd_notify_event *ne)
+{
+ if (refcount_dec_and_test(&ne->ne_ref)) {
+ dput(ne->ne_dentry);
+ kfree(ne);
+ }
+}
+
+/*
+ * Represents a directory delegation. The callback is for handling CB_NOTIFYs.
+ * As notifications from fsnotify come in, allocate a new event, take the ncn_lock,
+ * and add it to the ncn_evt queue. The CB_NOTIFY prepare handler will take the
+ * lock, clean out the list and process it.
+ */
+struct nfsd4_cb_notify {
+ spinlock_t ncn_lock; // protects the evt queue and count
+ int ncn_evt_cnt; // count of events in ncn_evt
+ int ncn_nf_cnt; // count of valid entries in ncn_nf
+ struct nfsd_notify_event *ncn_evt[NOTIFY4_EVENT_QUEUE_SIZE]; // list of events
+ struct page *ncn_pages[NOTIFY4_PAGE_ARRAY_SIZE]; // for encoding
+ struct notify4 *ncn_nf; // array of notify4's to be sent
+ struct nfsd4_callback ncn_cb; // notify4 callback
+};
+
/*
* Represents a delegation stateid. The nfs4_client holds references to these
* and they are put when it is being destroyed or when the delegation is
@@ -233,8 +271,12 @@ struct nfs4_delegation {
bool dl_written;
bool dl_setattr;
- /* for CB_GETATTR */
- struct nfs4_cb_fattr dl_cb_fattr;
+ union {
+ /* for CB_GETATTR */
+ struct nfs4_cb_fattr dl_cb_fattr;
+ /* for CB_NOTIFY */
+ struct nfsd4_cb_notify dl_cb_notify;
+ };
/* For delegated timestamps */
struct timespec64 dl_atime;
--
2.53.0
^ permalink raw reply related
* [PATCH v2 17/28] nfsd: add notification handlers for dir events
From: Jeff Layton @ 2026-04-16 17:35 UTC (permalink / raw)
To: Alexander Viro, Christian Brauner, Jan Kara, Chuck Lever,
Alexander Aring, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, NeilBrown,
Olga Kornievskaia, Dai Ngo, Tom Talpey, Trond Myklebust,
Anna Schumaker, Amir Goldstein
Cc: Calum Mackay, linux-fsdevel, linux-kernel, linux-trace-kernel,
linux-doc, linux-nfs, Jeff Layton
In-Reply-To: <20260416-dir-deleg-v2-0-851426a550f6@kernel.org>
Add the necessary parts to accept a fsnotify callback for directory
change event and create a CB_NOTIFY request for it. When a dir nfsd_file
is created set a handle_event callback to handle the notification.
Use that to allocate a nfsd_notify_event object and then hand off a
reference to each delegation's CB_NOTIFY. If anything fails along the
way, recall any affected delegations.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/filecache.c | 70 ++++++++++---
fs/nfsd/nfs4callback.c | 19 +++-
fs/nfsd/nfs4state.c | 268 +++++++++++++++++++++++++++++++++++++++++++++----
fs/nfsd/nfs4xdr.c | 121 ++++++++++++++++++++++
fs/nfsd/state.h | 4 +
fs/nfsd/xdr4.h | 3 +
6 files changed, 443 insertions(+), 42 deletions(-)
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 24511c3208db..be8f6d8a3ba0 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -72,6 +72,7 @@ static struct kmem_cache *nfsd_file_mark_slab;
static struct list_lru nfsd_file_lru;
static unsigned long nfsd_file_flags;
static struct fsnotify_group *nfsd_file_fsnotify_group;
+static struct fsnotify_group *nfsd_dir_fsnotify_group;
static struct delayed_work nfsd_filecache_laundrette;
static struct rhltable nfsd_file_rhltable
____cacheline_aligned_in_smp;
@@ -147,7 +148,7 @@ static void
nfsd_file_mark_put(struct nfsd_file_mark *nfm)
{
if (refcount_dec_and_test(&nfm->nfm_ref)) {
- fsnotify_destroy_mark(&nfm->nfm_mark, nfsd_file_fsnotify_group);
+ fsnotify_destroy_mark(&nfm->nfm_mark, nfm->nfm_mark.group);
fsnotify_put_mark(&nfm->nfm_mark);
}
}
@@ -155,35 +156,37 @@ nfsd_file_mark_put(struct nfsd_file_mark *nfm)
static struct nfsd_file_mark *
nfsd_file_mark_find_or_create(struct inode *inode)
{
- int err;
- struct fsnotify_mark *mark;
struct nfsd_file_mark *nfm = NULL, *new;
+ struct fsnotify_group *group;
+ struct fsnotify_mark *mark;
+ int err;
+
+ group = S_ISDIR(inode->i_mode) ? nfsd_dir_fsnotify_group : nfsd_file_fsnotify_group;
do {
- fsnotify_group_lock(nfsd_file_fsnotify_group);
- mark = fsnotify_find_inode_mark(inode,
- nfsd_file_fsnotify_group);
+ fsnotify_group_lock(group);
+ mark = fsnotify_find_inode_mark(inode, group);
if (mark) {
nfm = nfsd_file_mark_get(container_of(mark,
struct nfsd_file_mark,
nfm_mark));
- fsnotify_group_unlock(nfsd_file_fsnotify_group);
+ fsnotify_group_unlock(group);
if (nfm) {
fsnotify_put_mark(mark);
break;
}
/* Avoid soft lockup race with nfsd_file_mark_put() */
- fsnotify_destroy_mark(mark, nfsd_file_fsnotify_group);
+ fsnotify_destroy_mark(mark, group);
fsnotify_put_mark(mark);
} else {
- fsnotify_group_unlock(nfsd_file_fsnotify_group);
+ fsnotify_group_unlock(group);
}
/* allocate a new nfm */
new = kmem_cache_alloc(nfsd_file_mark_slab, GFP_KERNEL);
if (!new)
return NULL;
- fsnotify_init_mark(&new->nfm_mark, nfsd_file_fsnotify_group);
+ fsnotify_init_mark(&new->nfm_mark, group);
new->nfm_mark.mask = FS_ATTRIB|FS_DELETE_SELF;
refcount_set(&new->nfm_ref, 1);
@@ -812,12 +815,36 @@ nfsd_file_fsnotify_handle_event(struct fsnotify_mark *mark, u32 mask,
return 0;
}
+#ifdef CONFIG_NFSD_V4
+static int
+nfsd_dir_fsnotify_handle_event(struct fsnotify_group *group, u32 mask,
+ const void *data, int data_type, struct inode *dir,
+ const struct qstr *name, u32 cookie,
+ struct fsnotify_iter_info *iter_info)
+{
+ return nfsd_handle_dir_event(mask, dir, data, data_type, name);
+}
+#else
+static int
+nfsd_dir_fsnotify_handle_event(struct fsnotify_group *group, u32 mask,
+ const void *data, int data_type, struct inode *dir,
+ const struct qstr *name, u32 cookie,
+ struct fsnotify_iter_info *iter_info)
+{
+ return 0;
+}
+#endif
static const struct fsnotify_ops nfsd_file_fsnotify_ops = {
.handle_inode_event = nfsd_file_fsnotify_handle_event,
.free_mark = nfsd_file_mark_free,
};
+static const struct fsnotify_ops nfsd_dir_fsnotify_ops = {
+ .handle_event = nfsd_dir_fsnotify_handle_event,
+ .free_mark = nfsd_file_mark_free,
+};
+
int
nfsd_file_cache_init(void)
{
@@ -869,8 +896,7 @@ nfsd_file_cache_init(void)
goto out_shrinker;
}
- nfsd_file_fsnotify_group = fsnotify_alloc_group(&nfsd_file_fsnotify_ops,
- 0);
+ nfsd_file_fsnotify_group = fsnotify_alloc_group(&nfsd_file_fsnotify_ops, 0);
if (IS_ERR(nfsd_file_fsnotify_group)) {
pr_err("nfsd: unable to create fsnotify group: %ld\n",
PTR_ERR(nfsd_file_fsnotify_group));
@@ -879,11 +905,23 @@ nfsd_file_cache_init(void)
goto out_notifier;
}
+ nfsd_dir_fsnotify_group = fsnotify_alloc_group(&nfsd_dir_fsnotify_ops, 0);
+ if (IS_ERR(nfsd_dir_fsnotify_group)) {
+ pr_err("nfsd: unable to create fsnotify group: %ld\n",
+ PTR_ERR(nfsd_dir_fsnotify_group));
+ ret = PTR_ERR(nfsd_dir_fsnotify_group);
+ nfsd_dir_fsnotify_group = NULL;
+ goto out_notify_group;
+ }
+
INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_gc_worker);
out:
if (ret)
clear_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags);
return ret;
+out_notify_group:
+ fsnotify_put_group(nfsd_file_fsnotify_group);
+ nfsd_file_fsnotify_group = NULL;
out_notifier:
lease_unregister_notifier(&nfsd_file_lease_notifier);
out_shrinker:
@@ -1019,6 +1057,8 @@ nfsd_file_cache_shutdown(void)
rcu_barrier();
fsnotify_put_group(nfsd_file_fsnotify_group);
nfsd_file_fsnotify_group = NULL;
+ fsnotify_put_group(nfsd_dir_fsnotify_group);
+ nfsd_dir_fsnotify_group = NULL;
kmem_cache_destroy(nfsd_file_slab);
nfsd_file_slab = NULL;
fsnotify_wait_marks_destroyed();
@@ -1223,10 +1263,8 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net,
open_file:
trace_nfsd_file_alloc(nf);
- if (type == S_IFREG)
- nf->nf_mark = nfsd_file_mark_find_or_create(inode);
-
- if (type != S_IFREG || nf->nf_mark) {
+ nf->nf_mark = nfsd_file_mark_find_or_create(inode);
+ if (nf->nf_mark) {
if (file) {
get_file(file);
nf->nf_file = file;
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index ea3e7deb06fa..1964a213f80e 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -870,21 +870,30 @@ static void nfs4_xdr_enc_cb_notify(struct rpc_rqst *req,
const void *data)
{
const struct nfsd4_callback *cb = data;
+ struct nfsd4_cb_notify *ncn = container_of(cb, struct nfsd4_cb_notify, ncn_cb);
+ struct nfs4_delegation *dp = container_of(ncn, struct nfs4_delegation, dl_cb_notify);
struct nfs4_cb_compound_hdr hdr = {
.ident = 0,
.minorversion = cb->cb_clp->cl_minorversion,
};
- struct CB_NOTIFY4args args = { };
+ struct CB_NOTIFY4args args;
+ __be32 *p;
WARN_ON_ONCE(hdr.minorversion == 0);
encode_cb_compound4args(xdr, &hdr);
encode_cb_sequence4args(xdr, cb, &hdr);
- /*
- * FIXME: get stateid and fh from delegation. Inline the cna_changes
- * buffer, and zero it.
- */
+ p = xdr_reserve_space(xdr, 4);
+ *p = cpu_to_be32(OP_CB_NOTIFY);
+
+ args.cna_stateid.seqid = dp->dl_stid.sc_stateid.si_generation;
+ memcpy(&args.cna_stateid.other, &dp->dl_stid.sc_stateid.si_opaque,
+ ARRAY_SIZE(args.cna_stateid.other));
+ args.cna_fh.len = dp->dl_stid.sc_file->fi_fhandle.fh_size;
+ args.cna_fh.data = dp->dl_stid.sc_file->fi_fhandle.fh_raw;
+ args.cna_changes.count = ncn->ncn_nf_cnt;
+ args.cna_changes.element = ncn->ncn_nf;
WARN_ON_ONCE(!xdrgen_encode_CB_NOTIFY4args(xdr, &args));
hdr.nops++;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index eefce9e7c628..f4d0e64be544 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -55,6 +55,7 @@
#include "netns.h"
#include "pnfs.h"
#include "filecache.h"
+#include "nfs4xdr_gen.h"
#include "trace.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
@@ -3448,19 +3449,131 @@ nfsd4_cb_getattr_release(struct nfsd4_callback *cb)
nfs4_put_stid(&dp->dl_stid);
}
+static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
+{
+ bool queued;
+
+ if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &dp->dl_recall.cb_flags))
+ return;
+
+ /*
+ * We're assuming the state code never drops its reference
+ * without first removing the lease. Since we're in this lease
+ * callback (and since the lease code is serialized by the
+ * flc_lock) we know the server hasn't removed the lease yet, and
+ * we know it's safe to take a reference.
+ */
+ refcount_inc(&dp->dl_stid.sc_count);
+ queued = nfsd4_run_cb(&dp->dl_recall);
+ WARN_ON_ONCE(!queued);
+ if (!queued)
+ refcount_dec(&dp->dl_stid.sc_count);
+}
+
+static bool
+nfsd4_cb_notify_prepare(struct nfsd4_callback *cb)
+{
+ struct nfsd4_cb_notify *ncn = container_of(cb, struct nfsd4_cb_notify, ncn_cb);
+ struct nfs4_delegation *dp = container_of(ncn, struct nfs4_delegation, dl_cb_notify);
+ struct nfsd_notify_event *events[NOTIFY4_EVENT_QUEUE_SIZE];
+ struct xdr_buf xdr = { .buflen = PAGE_SIZE * NOTIFY4_PAGE_ARRAY_SIZE,
+ .pages = ncn->ncn_pages };
+ struct xdr_stream stream;
+ struct nfsd_file *nf;
+ int count, i;
+ bool error = false;
+
+ xdr_init_encode_pages(&stream, &xdr);
+
+ spin_lock(&ncn->ncn_lock);
+ count = ncn->ncn_evt_cnt;
+
+ /* spurious queueing? */
+ if (count == 0) {
+ spin_unlock(&ncn->ncn_lock);
+ return false;
+ }
+
+ /* we can't keep up! */
+ if (count > NOTIFY4_EVENT_QUEUE_SIZE) {
+ spin_unlock(&ncn->ncn_lock);
+ goto out_recall;
+ }
+
+ memcpy(events, ncn->ncn_evt, sizeof(*events) * count);
+ ncn->ncn_evt_cnt = 0;
+ spin_unlock(&ncn->ncn_lock);
+
+ rcu_read_lock();
+ nf = nfsd_file_get(rcu_dereference(dp->dl_stid.sc_file->fi_deleg_file));
+ rcu_read_unlock();
+ if (!nf) {
+ for (i = 0; i < count; ++i)
+ nfsd_notify_event_put(events[i]);
+ goto out_recall;
+ }
+
+ for (i = 0; i < count; ++i) {
+ struct nfsd_notify_event *nne = events[i];
+
+ if (!error) {
+ u32 *maskp = (u32 *)xdr_reserve_space(&stream, sizeof(*maskp));
+ u8 *p;
+
+ if (!maskp) {
+ error = true;
+ goto put_event;
+ }
+
+ p = nfsd4_encode_notify_event(&stream, nne, dp, nf, maskp);
+ if (!p) {
+ pr_notice("Could not generate CB_NOTIFY from fsnotify mask 0x%x\n",
+ nne->ne_mask);
+ error = true;
+ goto put_event;
+ }
+
+ ncn->ncn_nf[i].notify_mask.count = 1;
+ ncn->ncn_nf[i].notify_mask.element = maskp;
+ ncn->ncn_nf[i].notify_vals.data = p;
+ ncn->ncn_nf[i].notify_vals.len = (u8 *)stream.p - p;
+ }
+put_event:
+ nfsd_notify_event_put(nne);
+ }
+ if (!error) {
+ ncn->ncn_nf_cnt = count;
+ nfsd_file_put(nf);
+ return true;
+ }
+ nfsd_file_put(nf);
+out_recall:
+ nfsd_break_one_deleg(dp);
+ return false;
+}
+
static int
nfsd4_cb_notify_done(struct nfsd4_callback *cb,
struct rpc_task *task)
{
+ struct nfsd4_cb_notify *ncn = container_of(cb, struct nfsd4_cb_notify, ncn_cb);
+ struct nfs4_delegation *dp = container_of(ncn, struct nfs4_delegation, dl_cb_notify);
+
switch (task->tk_status) {
case -NFS4ERR_DELAY:
rpc_delay(task, 2 * HZ);
return 0;
default:
+ /* For any other hard error, recall the deleg */
+ nfsd_break_one_deleg(dp);
+ fallthrough;
+ case 0:
return 1;
}
}
+static void nfsd4_run_cb_notify(struct nfsd4_cb_notify *ncn);
+
static void
nfsd4_cb_notify_release(struct nfsd4_callback *cb)
{
@@ -3469,6 +3582,9 @@ nfsd4_cb_notify_release(struct nfsd4_callback *cb)
struct nfs4_delegation *dp =
container_of(ncn, struct nfs4_delegation, dl_cb_notify);
+ /* Drain events that arrived while this callback was in flight */
+ if (ncn->ncn_evt_cnt > 0)
+ nfsd4_run_cb_notify(ncn);
nfs4_put_stid(&dp->dl_stid);
}
@@ -3485,6 +3601,7 @@ static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops = {
};
static const struct nfsd4_callback_ops nfsd4_cb_notify_ops = {
+ .prepare = nfsd4_cb_notify_prepare,
.done = nfsd4_cb_notify_done,
.release = nfsd4_cb_notify_release,
.opcode = OP_CB_NOTIFY,
@@ -5717,27 +5834,6 @@ static const struct nfsd4_callback_ops nfsd4_cb_recall_ops = {
.opcode = OP_CB_RECALL,
};
-static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
-{
- bool queued;
-
- if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &dp->dl_recall.cb_flags))
- return;
-
- /*
- * We're assuming the state code never drops its reference
- * without first removing the lease. Since we're in this lease
- * callback (and since the lease code is serialized by the
- * flc_lock) we know the server hasn't removed the lease yet, and
- * we know it's safe to take a reference.
- */
- refcount_inc(&dp->dl_stid.sc_count);
- queued = nfsd4_run_cb(&dp->dl_recall);
- WARN_ON_ONCE(!queued);
- if (!queued)
- refcount_dec(&dp->dl_stid.sc_count);
-}
-
/* Called from break_lease() with flc_lock held. */
static bool
nfsd_break_deleg_cb(struct file_lease *fl)
@@ -9818,3 +9914,133 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
put_nfs4_file(fp);
return ERR_PTR(status);
}
+
+static void
+nfsd4_run_cb_notify(struct nfsd4_cb_notify *ncn)
+{
+ struct nfs4_delegation *dp = container_of(ncn, struct nfs4_delegation, dl_cb_notify);
+
+ if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &ncn->ncn_cb.cb_flags))
+ return;
+
+ if (!refcount_inc_not_zero(&dp->dl_stid.sc_count))
+ clear_bit(NFSD4_CALLBACK_RUNNING, &ncn->ncn_cb.cb_flags);
+ else
+ nfsd4_run_cb(&ncn->ncn_cb);
+}
+
+static struct nfsd_notify_event *
+alloc_nfsd_notify_event(u32 mask, const struct qstr *q, struct dentry *dentry,
+ struct inode *target)
+{
+ struct nfsd_notify_event *ne;
+
+ ne = kmalloc(sizeof(*ne) + q->len + 1, GFP_KERNEL);
+ if (!ne)
+ return NULL;
+
+ memcpy(&ne->ne_name, q->name, q->len);
+ refcount_set(&ne->ne_ref, 1);
+ ne->ne_mask = mask;
+ ne->ne_name[q->len] = '\0';
+ ne->ne_namelen = q->len;
+ ne->ne_dentry = dget(dentry);
+ ne->ne_target = target;
+ if (ne->ne_target)
+ ihold(ne->ne_target);
+ return ne;
+}
+
+static bool
+should_notify_deleg(u32 mask, struct file_lease *fl)
+{
+ /* Don't notify the client generating the event */
+ if (nfsd_breaker_owns_lease(fl))
+ return false;
+
+ /* Skip if this event wasn't ignored by the lease */
+ if ((mask & FS_DELETE) && !(fl->c.flc_flags & FL_IGN_DIR_DELETE))
+ return false;
+ if ((mask & FS_CREATE) && !(fl->c.flc_flags & FL_IGN_DIR_CREATE))
+ return false;
+ if ((mask & FS_RENAME) && !(fl->c.flc_flags & FL_IGN_DIR_RENAME))
+ return false;
+
+ return true;
+}
+
+static void
+nfsd_recall_all_dir_delegs(const struct inode *dir)
+{
+ struct file_lock_context *ctx = locks_inode_context(dir);
+ struct file_lock_core *flc;
+
+ spin_lock(&ctx->flc_lock);
+ list_for_each_entry(flc, &ctx->flc_lease, flc_list) {
+ struct file_lease *fl = container_of(flc, struct file_lease, c);
+
+ if (fl->fl_lmops == &nfsd_lease_mng_ops)
+ nfsd_break_deleg_cb(fl);
+ }
+ spin_unlock(&ctx->flc_lock);
+}
+
+int
+nfsd_handle_dir_event(u32 mask, const struct inode *dir, const void *data,
+ int data_type, const struct qstr *name)
+{
+ struct dentry *dentry = fsnotify_data_dentry(data, data_type);
+ struct inode *target = fsnotify_data_rename_target(data, data_type);
+ struct file_lock_context *ctx;
+ struct file_lock_core *flc;
+ struct nfsd_notify_event *evt;
+
+ /* Normalize cross-dir rename events to create/delete */
+ if (mask & FS_MOVED_FROM) {
+ mask &= ~FS_MOVED_FROM;
+ mask |= FS_DELETE;
+ }
+ if (mask & FS_MOVED_TO) {
+ mask &= ~FS_MOVED_TO;
+ mask |= FS_CREATE;
+ }
+
+ /* Don't do anything if this is not an expected event */
+ if (!(mask & (FS_CREATE|FS_DELETE|FS_RENAME)))
+ return 0;
+
+ ctx = locks_inode_context(dir);
+ if (!ctx || list_empty(&ctx->flc_lease))
+ return 0;
+
+ evt = alloc_nfsd_notify_event(mask, name, dentry, target);
+ if (!evt) {
+ nfsd_recall_all_dir_delegs(dir);
+ return 0;
+ }
+
+ spin_lock(&ctx->flc_lock);
+ list_for_each_entry(flc, &ctx->flc_lease, flc_list) {
+ struct file_lease *fl = container_of(flc, struct file_lease, c);
+ struct nfs4_delegation *dp = flc->flc_owner;
+ struct nfsd4_cb_notify *ncn = &dp->dl_cb_notify;
+
+ if (!should_notify_deleg(mask, fl))
+ continue;
+
+ spin_lock(&ncn->ncn_lock);
+ if (ncn->ncn_evt_cnt >= NOTIFY4_EVENT_QUEUE_SIZE) {
+ /* We're generating notifications too fast. Recall. */
+ spin_unlock(&ncn->ncn_lock);
+ nfsd_break_deleg_cb(fl);
+ continue;
+ }
+ ncn->ncn_evt[ncn->ncn_evt_cnt++] = nfsd_notify_event_get(evt);
+ spin_unlock(&ncn->ncn_lock);
+
+ nfsd4_run_cb_notify(ncn);
+ }
+ spin_unlock(&ctx->flc_lock);
+ nfsd_notify_event_put(evt);
+ return 0;
+}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 2a0946c630e1..8af1e15e1102 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4098,6 +4098,127 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
goto out;
}
+static bool
+nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
+ struct dentry *dentry, struct nfs4_delegation *dp,
+ struct nfsd_file *nf, char *name, u32 namelen)
+{
+ uint32_t *attrmask;
+
+ /* Reserve space for attrmask */
+ attrmask = xdr_reserve_space(xdr, 3 * sizeof(uint32_t));
+ if (!attrmask)
+ return false;
+
+ ne->ne_file.data = name;
+ ne->ne_file.len = namelen;
+ ne->ne_attrs.attrmask.element = attrmask;
+
+ attrmask[0] = 0;
+ attrmask[1] = 0;
+ attrmask[2] = 0;
+ ne->ne_attrs.attr_vals.data = NULL;
+ ne->ne_attrs.attr_vals.len = 0;
+ ne->ne_attrs.attrmask.count = 1;
+ return true;
+}
+
+/**
+ * nfsd4_encode_notify_event - encode a notify
+ * @xdr: stream to which to encode the fattr4
+ * @nne: nfsd_notify_event to encode
+ * @dp: delegation where the event occurred
+ * @nf: nfsd_file on which event occurred
+ * @notify_mask: pointer to word where notification mask should be set
+ *
+ * Encode @nne into @xdr. Returns a pointer to the start of the event, or NULL if
+ * the event couldn't be encoded. The appropriate bit in the notify_mask will also
+ * be set on success.
+ */
+u8 *nfsd4_encode_notify_event(struct xdr_stream *xdr, struct nfsd_notify_event *nne,
+ struct nfs4_delegation *dp, struct nfsd_file *nf,
+ u32 *notify_mask)
+{
+ u8 *p = NULL;
+
+ *notify_mask = 0;
+
+ if (nne->ne_mask & FS_DELETE) {
+ struct notify_remove4 nr = { };
+
+ if (!nfsd4_setup_notify_entry4(&nr.nrm_old_entry, xdr, nne->ne_dentry, dp,
+ nf, nne->ne_name, nne->ne_namelen))
+ goto out_err;
+ p = (u8 *)xdr->p;
+ if (!xdrgen_encode_notify_remove4(xdr, &nr))
+ goto out_err;
+ *notify_mask |= BIT(NOTIFY4_REMOVE_ENTRY);
+ } else if (nne->ne_mask & FS_CREATE) {
+ struct notify_add4 na = { };
+ struct notify_remove4 old = { };
+
+ if (!nfsd4_setup_notify_entry4(&na.nad_new_entry, xdr, nne->ne_dentry, dp,
+ nf, nne->ne_name, nne->ne_namelen))
+ goto out_err;
+
+ /* If a file was overwritten, report it in nad_old_entry */
+ if (nne->ne_target) {
+ if (!nfsd4_setup_notify_entry4(&old.nrm_old_entry, xdr,
+ NULL, dp, nf,
+ nne->ne_name, nne->ne_namelen))
+ goto out_err;
+ na.nad_old_entry.count = 1;
+ na.nad_old_entry.element = &old;
+ }
+
+ p = (u8 *)xdr->p;
+ if (!xdrgen_encode_notify_add4(xdr, &na))
+ goto out_err;
+
+ *notify_mask |= BIT(NOTIFY4_ADD_ENTRY);
+ } else if (nne->ne_mask & FS_RENAME) {
+ struct notify_rename4 nr = { };
+ struct notify_remove4 old = { };
+ struct name_snapshot n;
+ bool ret;
+
+ /* Don't send any attributes in the old_entry since they're the same in new */
+ if (!nfsd4_setup_notify_entry4(&nr.nrn_old_entry.nrm_old_entry, xdr,
+ NULL, dp, nf, nne->ne_name,
+ nne->ne_namelen))
+ goto out_err;
+
+ take_dentry_name_snapshot(&n, nne->ne_dentry);
+ ret = nfsd4_setup_notify_entry4(&nr.nrn_new_entry.nad_new_entry, xdr,
+ nne->ne_dentry, dp, nf, (char *)n.name.name,
+ n.name.len);
+
+ /* If a file was overwritten, report it in nad_old_entry */
+ if (ret && nne->ne_target) {
+ ret = nfsd4_setup_notify_entry4(&old.nrm_old_entry, xdr,
+ NULL, dp, nf,
+ (char *)n.name.name, n.name.len);
+ if (ret) {
+ nr.nrn_new_entry.nad_old_entry.count = 1;
+ nr.nrn_new_entry.nad_old_entry.element = &old;
+ }
+ }
+
+ if (ret) {
+ p = (u8 *)xdr->p;
+ ret = xdrgen_encode_notify_rename4(xdr, &nr);
+ }
+ release_dentry_name_snapshot(&n);
+ if (!ret)
+ goto out_err;
+ *notify_mask |= BIT(NOTIFY4_RENAME_ENTRY);
+ }
+ return p;
+out_err:
+ pr_warn("nfsd: unable to marshal notify_rename4 to xdr stream\n");
+ return NULL;
+}
+
static void svcxdr_init_encode_from_buffer(struct xdr_stream *xdr,
struct xdr_buf *buf, __be32 *p, int bytes)
{
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 500e07e47909..570d66fc8297 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -201,6 +201,7 @@ struct nfsd_notify_event {
refcount_t ne_ref; // refcount
u32 ne_mask; // FS_* mask from fsnotify callback
struct dentry *ne_dentry; // dentry reference to target
+ struct inode *ne_target; // inode overwritten by rename, or NULL
u32 ne_namelen; // length of ne_name
char ne_name[]; // name of dentry being changed
};
@@ -214,6 +215,7 @@ static inline struct nfsd_notify_event *nfsd_notify_event_get(struct nfsd_notify
static inline void nfsd_notify_event_put(struct nfsd_notify_event *ne)
{
if (refcount_dec_and_test(&ne->ne_ref)) {
+ iput(ne->ne_target);
dput(ne->ne_dentry);
kfree(ne);
}
@@ -897,6 +899,8 @@ bool nfsd4_has_active_async_copies(struct nfs4_client *clp);
extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name,
struct xdr_netobj princhash, struct nfsd_net *nn);
extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn);
+int nfsd_handle_dir_event(u32 mask, const struct inode *dir, const void *data,
+ int data_type, const struct qstr *name);
void put_nfs4_file(struct nfs4_file *fi);
extern void nfs4_put_cpntf_state(struct nfsd_net *nn,
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 417e9ad9fbb3..d276840aca50 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -955,6 +955,9 @@ __be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words,
struct svc_fh *fhp, struct svc_export *exp,
struct dentry *dentry,
u32 *bmval, struct svc_rqst *, int ignore_crossmnt);
+u8 *nfsd4_encode_notify_event(struct xdr_stream *xdr, struct nfsd_notify_event *nne,
+ struct nfs4_delegation *dd, struct nfsd_file *nf,
+ u32 *notify_mask);
extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
struct nfsd4_compound_state *, union nfsd4_op_u *u);
extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
--
2.53.0
^ permalink raw reply related
* [PATCH v2 18/28] nfsd: add tracepoint to dir_event handler
From: Jeff Layton @ 2026-04-16 17:35 UTC (permalink / raw)
To: Alexander Viro, Christian Brauner, Jan Kara, Chuck Lever,
Alexander Aring, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, NeilBrown,
Olga Kornievskaia, Dai Ngo, Tom Talpey, Trond Myklebust,
Anna Schumaker, Amir Goldstein
Cc: Calum Mackay, linux-fsdevel, linux-kernel, linux-trace-kernel,
linux-doc, linux-nfs, Jeff Layton
In-Reply-To: <20260416-dir-deleg-v2-0-851426a550f6@kernel.org>
Add some extra visibility around the fsnotify handlers.
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4state.c | 2 ++
fs/nfsd/trace.h | 22 ++++++++++++++++++++++
2 files changed, 24 insertions(+)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index f4d0e64be544..eba6da1072c0 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -9995,6 +9995,8 @@ nfsd_handle_dir_event(u32 mask, const struct inode *dir, const void *data,
struct file_lock_core *flc;
struct nfsd_notify_event *evt;
+ trace_nfsd_handle_dir_event(mask, dir, name);
+
/* Normalize cross-dir rename events to create/delete */
if (mask & FS_MOVED_FROM) {
mask &= ~FS_MOVED_FROM;
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 60cacf64181c..b9119ff4253a 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -12,6 +12,7 @@
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/xprt.h>
#include <trace/misc/fs.h>
+#include <trace/misc/fsnotify.h>
#include <trace/misc/nfs.h>
#include <trace/misc/sunrpc.h>
@@ -1377,6 +1378,27 @@ TRACE_EVENT(nfsd_file_fsnotify_handle_event,
__entry->nlink, __entry->mode, __entry->mask)
);
+TRACE_EVENT(nfsd_handle_dir_event,
+ TP_PROTO(u32 mask, const struct inode *dir, const struct qstr *name),
+ TP_ARGS(mask, dir, name),
+ TP_STRUCT__entry(
+ __field(u32, mask)
+ __field(dev_t, s_dev)
+ __field(ino_t, i_ino)
+ __string_len(name, name->name, name->len)
+ ),
+ TP_fast_assign(
+ __entry->mask = mask;
+ __entry->s_dev = dir->i_sb->s_dev;
+ __entry->i_ino = dir->i_ino;
+ __assign_str(name);
+ ),
+ TP_printk("inode=0x%x:0x%x:0x%lx mask=%s name=%s",
+ MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
+ __entry->i_ino, show_fsnotify_mask(__entry->mask),
+ __get_str(name))
+);
+
DECLARE_EVENT_CLASS(nfsd_file_gc_class,
TP_PROTO(
const struct nfsd_file *nf
--
2.53.0
^ permalink raw reply related
* [PATCH v4 10/10] ipe: Add BPF program load policy enforcement via Hornet integration
From: Blaise Boscaccy @ 2026-04-16 17:33 UTC (permalink / raw)
To: Blaise Boscaccy, Jonathan Corbet, Paul Moore, James Morris,
Serge E. Hallyn, Mickaël Salaün, Günther Noack,
Dr. David Alan Gilbert, Andrew Morton, James.Bottomley, dhowells,
Fan Wu, Ryan Foster, Randy Dunlap, linux-security-module,
linux-doc, linux-kernel, bpf, Song Liu
In-Reply-To: <20260416173500.176716-1-bboscaccy@linux.microsoft.com>
Add support for the bpf_prog_load_post_integrity LSM hook, enabling IPE
to make policy decisions about BPF program loading based on integrity
verdicts provided by the Hornet LSM.
New policy operation:
op=BPF_PROG_LOAD - Matches BPF program load events
New policy properties:
bpf_signature=NONE - No Verdict
bpf_signature=OK - Program signature and map hashes verified
bpf_signature=UNSIGNED - No signature provided
bpf_signature=PARTIALSIG - Signature OK but no map hash data
bpf_signature=UNKNOWNKEY - Cert not trusted
bpf_signature=UNEXPECTED - An unexpected hash value was encountered
bpf_signature=FAULT - System error during verification
bpf_signature=BADSIG - Signature or map hash verification failed
bpf_keyring=BUILTIN - Program was signed using a builtin keyring
bpf_keyring=SECONDARY - Program was signed using the secondary keyring
bpf_keyring=PLATFORM - Program was signed using the platform keyring
bpf_kernel=TRUE - Program originated from kernelspace
bpf_kernel=FALSE - Program originated from userspace
These properties map directly to the lsm_integrity_verdict enum values
provided by the Hornet LSM through security_bpf_prog_load_post_integrity.
The feature is gated on CONFIG_IPE_PROP_BPF_SIGNATURE which depends on
CONFIG_SECURITY_HORNET.
Example policy for bpf signature enforcement:
DEFAULT op=BPF_PROG_LOAD action=DENY
op=BPF_PROG_LOAD is_kernel=TRUE action=ALLOW
op=BPF_PROG_LOAD bpf_signature=OK action=ALLOW
Signed-off-by: Blaise Boscaccy <bboscaccy@linux.microsoft.com>
---
security/ipe/Kconfig | 14 +++++++
security/ipe/audit.c | 15 ++++++++
security/ipe/eval.c | 73 +++++++++++++++++++++++++++++++++++-
security/ipe/eval.h | 5 +++
security/ipe/hooks.c | 37 ++++++++++++++++++
security/ipe/hooks.h | 11 ++++++
security/ipe/ipe.c | 3 ++
security/ipe/policy.h | 14 +++++++
security/ipe/policy_parser.c | 27 +++++++++++++
9 files changed, 198 insertions(+), 1 deletion(-)
diff --git a/security/ipe/Kconfig b/security/ipe/Kconfig
index a110a6cd848b7..4c1d46847582b 100644
--- a/security/ipe/Kconfig
+++ b/security/ipe/Kconfig
@@ -95,6 +95,20 @@ config IPE_PROP_FS_VERITY_BUILTIN_SIG
if unsure, answer Y.
+config IPE_PROP_BPF_SIGNATURE
+ bool "Enable support for Hornet BPF program signature verification"
+ depends on SECURITY_HORNET
+ help
+ This option enables the 'bpf_signature' and 'bpf_keyring'
+ properties within IPE policies. The 'bpf_signature' property
+ allows IPE to make policy decisions based on the integrity
+ verdict provided by the Hornet LSM when a BPF program is loaded.
+ Verdicts include OK, UNSIGNED, PARTIALSIG, BADSIG, and others.
+ The 'bpf_keyring' property allows policies to match against the
+ keyring specified in bpf_attr (BUILTIN, SECONDARY, PLATFORM).
+
+ If unsure, answer Y.
+
endmenu
config SECURITY_IPE_KUNIT_TEST
diff --git a/security/ipe/audit.c b/security/ipe/audit.c
index 3f0deeb549127..251c6ec2f8423 100644
--- a/security/ipe/audit.c
+++ b/security/ipe/audit.c
@@ -41,6 +41,7 @@ static const char *const audit_op_names[__IPE_OP_MAX + 1] = {
"KEXEC_INITRAMFS",
"POLICY",
"X509_CERT",
+ "BPF_PROG_LOAD",
"UNKNOWN",
};
@@ -51,6 +52,7 @@ static const char *const audit_hook_names[__IPE_HOOK_MAX] = {
"MPROTECT",
"KERNEL_READ",
"KERNEL_LOAD",
+ "BPF_PROG_LOAD",
};
static const char *const audit_prop_names[__IPE_PROP_MAX] = {
@@ -62,6 +64,19 @@ static const char *const audit_prop_names[__IPE_PROP_MAX] = {
"fsverity_digest=",
"fsverity_signature=FALSE",
"fsverity_signature=TRUE",
+ "bpf_signature=NONE",
+ "bpf_signature=OK",
+ "bpf_signature=UNSIGNED",
+ "bpf_signature=PARTIALSIG",
+ "bpf_signature=UNKNOWNKEY",
+ "bpf_signature=UNEXPECTED",
+ "bpf_signature=FAULT",
+ "bpf_signature=BADSIG",
+ "bpf_keyring=BUILTIN",
+ "bpf_keyring=SECONDARY",
+ "bpf_keyring=PLATFORM",
+ "bpf_kernel=FALSE",
+ "bpf_kernel=TRUE",
};
/**
diff --git a/security/ipe/eval.c b/security/ipe/eval.c
index 21439c5be3364..9a6d583fea125 100644
--- a/security/ipe/eval.c
+++ b/security/ipe/eval.c
@@ -11,6 +11,7 @@
#include <linux/rcupdate.h>
#include <linux/moduleparam.h>
#include <linux/fsverity.h>
+#include <linux/verification.h>
#include "ipe.h"
#include "eval.h"
@@ -265,8 +266,52 @@ static bool evaluate_fsv_sig_true(const struct ipe_eval_ctx *const ctx)
}
#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+#ifdef CONFIG_IPE_PROP_BPF_SIGNATURE
+/**
+ * evaluate_bpf_sig() - Evaluate @ctx against a bpf_signature property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ * @expected: The expected lsm_integrity_verdict to match against.
+ *
+ * Return:
+ * * %true - The current @ctx matches the expected verdict
+ * * %false - The current @ctx doesn't match the expected verdict
+ */
+static bool evaluate_bpf_sig(const struct ipe_eval_ctx *const ctx,
+ enum lsm_integrity_verdict expected)
+{
+ return ctx->bpf_verdict == expected;
+}
+#else
+static bool evaluate_bpf_sig(const struct ipe_eval_ctx *const ctx,
+ enum lsm_integrity_verdict expected)
+{
+ return false;
+}
+#endif /* CONFIG_IPE_PROP_BPF_SIGNATURE */
+
+#ifdef CONFIG_IPE_PROP_BPF_SIGNATURE
+/**
+ * evaluate_bpf_keyring() - Evaluate @ctx against a bpf_keyring property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ * @expected: The expected keyring_id to match against.
+ *
+ * Return:
+ * * %true - The current @ctx matches the expected keyring
+ * * %false - The current @ctx doesn't match the expected keyring
+ */
+static bool evaluate_bpf_keyring(const struct ipe_eval_ctx *const ctx,
+ s32 expected)
+{
+ return ctx->bpf_keyring_id == expected;
+}
+#else
+static bool evaluate_bpf_keyring(const struct ipe_eval_ctx *const ctx,
+ s32 expected)
+{
+ return false;
+}
+#endif /* CONFIG_IPE_PROP_BPF_SIGNATURE */
/**
- * evaluate_property() - Analyze @ctx against a rule property.
* @ctx: Supplies a pointer to the context to be evaluated.
* @p: Supplies a pointer to the property to be evaluated.
*
@@ -297,6 +342,32 @@ static bool evaluate_property(const struct ipe_eval_ctx *const ctx,
return evaluate_fsv_sig_false(ctx);
case IPE_PROP_FSV_SIG_TRUE:
return evaluate_fsv_sig_true(ctx);
+ case IPE_PROP_BPF_SIG_NONE:
+ return evaluate_bpf_sig(ctx, LSM_INT_VERDICT_NONE);
+ case IPE_PROP_BPF_SIG_OK:
+ return evaluate_bpf_sig(ctx, LSM_INT_VERDICT_OK);
+ case IPE_PROP_BPF_SIG_UNSIGNED:
+ return evaluate_bpf_sig(ctx, LSM_INT_VERDICT_UNSIGNED);
+ case IPE_PROP_BPF_SIG_PARTIALSIG:
+ return evaluate_bpf_sig(ctx, LSM_INT_VERDICT_PARTIALSIG);
+ case IPE_PROP_BPF_SIG_UNKNOWNKEY:
+ return evaluate_bpf_sig(ctx, LSM_INT_VERDICT_UNKNOWNKEY);
+ case IPE_PROP_BPF_SIG_UNEXPECTED:
+ return evaluate_bpf_sig(ctx, LSM_INT_VERDICT_UNEXPECTED);
+ case IPE_PROP_BPF_SIG_FAULT:
+ return evaluate_bpf_sig(ctx, LSM_INT_VERDICT_FAULT);
+ case IPE_PROP_BPF_SIG_BADSIG:
+ return evaluate_bpf_sig(ctx, LSM_INT_VERDICT_BADSIG);
+ case IPE_PROP_BPF_KEYRING_BUILTIN:
+ return evaluate_bpf_keyring(ctx, 0);
+ case IPE_PROP_BPF_KEYRING_SECONDARY:
+ return evaluate_bpf_keyring(ctx, (s32)(unsigned long)VERIFY_USE_SECONDARY_KEYRING);
+ case IPE_PROP_BPF_KEYRING_PLATFORM:
+ return evaluate_bpf_keyring(ctx, (s32)(unsigned long)VERIFY_USE_PLATFORM_KEYRING);
+ case IPE_PROP_BPF_KERNEL_FALSE:
+ return !ctx->bpf_kernel;
+ case IPE_PROP_BPF_KERNEL_TRUE:
+ return ctx->bpf_kernel;
default:
return false;
}
diff --git a/security/ipe/eval.h b/security/ipe/eval.h
index fef65a36468cb..1578d83bafc10 100644
--- a/security/ipe/eval.h
+++ b/security/ipe/eval.h
@@ -52,6 +52,11 @@ struct ipe_eval_ctx {
#ifdef CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG
const struct ipe_inode *ipe_inode;
#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+#ifdef CONFIG_IPE_PROP_BPF_SIGNATURE
+ enum lsm_integrity_verdict bpf_verdict;
+ s32 bpf_keyring_id;
+ bool bpf_kernel;
+#endif /* CONFIG_IPE_PROP_BPF_SIGNATURE */
};
enum ipe_match {
diff --git a/security/ipe/hooks.c b/security/ipe/hooks.c
index 0ae54a880405a..03541e5bb7f60 100644
--- a/security/ipe/hooks.c
+++ b/security/ipe/hooks.c
@@ -340,3 +340,40 @@ int ipe_inode_setintegrity(const struct inode *inode,
return -EINVAL;
}
#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+
+#ifdef CONFIG_IPE_PROP_BPF_SIGNATURE
+/**
+ * ipe_bpf_prog_load_post_integrity() - ipe security hook for BPF program load.
+ * @prog: Supplies the BPF program being loaded.
+ * @attr: Supplies the bpf syscall attributes.
+ * @token: Supplies the BPF token, if any.
+ * @kernel: Whether the call originated from the kernel.
+ * @lsmid: Supplies the LSM ID of the integrity provider.
+ * @verdict: Supplies the integrity verdict from the provider (e.g. Hornet).
+ *
+ * This LSM hook is called after an integrity verification LSM (such as Hornet)
+ * has evaluated a BPF program's cryptographic signature. IPE uses the verdict
+ * to make a policy-based allow/deny decision.
+ *
+ * Return:
+ * * %0 - Success
+ * * %-EACCES - Did not pass IPE policy
+ */
+int ipe_bpf_prog_load_post_integrity(struct bpf_prog *prog,
+ union bpf_attr *attr,
+ struct bpf_token *token,
+ bool kernel,
+ const struct lsm_id *lsmid,
+ enum lsm_integrity_verdict verdict)
+{
+ struct ipe_eval_ctx ctx = IPE_EVAL_CTX_INIT;
+
+ ctx.op = IPE_OP_BPF_PROG_LOAD;
+ ctx.hook = IPE_HOOK_BPF_PROG_LOAD;
+ ctx.bpf_verdict = verdict;
+ ctx.bpf_keyring_id = attr->keyring_id;
+ ctx.bpf_kernel = kernel;
+
+ return ipe_evaluate_event(&ctx);
+}
+#endif /* CONFIG_IPE_PROP_BPF_SIGNATURE */
diff --git a/security/ipe/hooks.h b/security/ipe/hooks.h
index 07db373327402..95b74f7899750 100644
--- a/security/ipe/hooks.h
+++ b/security/ipe/hooks.h
@@ -10,6 +10,7 @@
#include <linux/security.h>
#include <linux/blk_types.h>
#include <linux/fsverity.h>
+#include <linux/bpf.h>
enum ipe_hook_type {
IPE_HOOK_BPRM_CHECK = 0,
@@ -18,6 +19,7 @@ enum ipe_hook_type {
IPE_HOOK_MPROTECT,
IPE_HOOK_KERNEL_READ,
IPE_HOOK_KERNEL_LOAD,
+ IPE_HOOK_BPF_PROG_LOAD,
__IPE_HOOK_MAX
};
@@ -52,4 +54,13 @@ int ipe_inode_setintegrity(const struct inode *inode, enum lsm_integrity_type ty
const void *value, size_t size);
#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+#ifdef CONFIG_IPE_PROP_BPF_SIGNATURE
+int ipe_bpf_prog_load_post_integrity(struct bpf_prog *prog,
+ union bpf_attr *attr,
+ struct bpf_token *token,
+ bool kernel,
+ const struct lsm_id *lsmid,
+ enum lsm_integrity_verdict verdict);
+#endif /* CONFIG_IPE_PROP_BPF_SIGNATURE */
+
#endif /* _IPE_HOOKS_H */
diff --git a/security/ipe/ipe.c b/security/ipe/ipe.c
index 495bb765de1b8..6502d4ddc641c 100644
--- a/security/ipe/ipe.c
+++ b/security/ipe/ipe.c
@@ -60,6 +60,9 @@ static struct security_hook_list ipe_hooks[] __ro_after_init = {
#ifdef CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG
LSM_HOOK_INIT(inode_setintegrity, ipe_inode_setintegrity),
#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+#ifdef CONFIG_IPE_PROP_BPF_SIGNATURE
+ LSM_HOOK_INIT(bpf_prog_load_post_integrity, ipe_bpf_prog_load_post_integrity),
+#endif /* CONFIG_IPE_PROP_BPF_SIGNATURE */
};
/**
diff --git a/security/ipe/policy.h b/security/ipe/policy.h
index 5bfbdbddeef86..748bea92beb19 100644
--- a/security/ipe/policy.h
+++ b/security/ipe/policy.h
@@ -17,6 +17,7 @@ enum ipe_op_type {
IPE_OP_KEXEC_INITRAMFS,
IPE_OP_POLICY,
IPE_OP_X509,
+ IPE_OP_BPF_PROG_LOAD,
__IPE_OP_MAX,
};
@@ -39,6 +40,19 @@ enum ipe_prop_type {
IPE_PROP_FSV_DIGEST,
IPE_PROP_FSV_SIG_FALSE,
IPE_PROP_FSV_SIG_TRUE,
+ IPE_PROP_BPF_SIG_NONE,
+ IPE_PROP_BPF_SIG_OK,
+ IPE_PROP_BPF_SIG_UNSIGNED,
+ IPE_PROP_BPF_SIG_PARTIALSIG,
+ IPE_PROP_BPF_SIG_UNKNOWNKEY,
+ IPE_PROP_BPF_SIG_UNEXPECTED,
+ IPE_PROP_BPF_SIG_FAULT,
+ IPE_PROP_BPF_SIG_BADSIG,
+ IPE_PROP_BPF_KEYRING_BUILTIN,
+ IPE_PROP_BPF_KEYRING_SECONDARY,
+ IPE_PROP_BPF_KEYRING_PLATFORM,
+ IPE_PROP_BPF_KERNEL_FALSE,
+ IPE_PROP_BPF_KERNEL_TRUE,
__IPE_PROP_MAX
};
diff --git a/security/ipe/policy_parser.c b/security/ipe/policy_parser.c
index 6fa5bebf84714..71f63de56616b 100644
--- a/security/ipe/policy_parser.c
+++ b/security/ipe/policy_parser.c
@@ -237,6 +237,7 @@ static const match_table_t operation_tokens = {
{IPE_OP_KEXEC_INITRAMFS, "op=KEXEC_INITRAMFS"},
{IPE_OP_POLICY, "op=POLICY"},
{IPE_OP_X509, "op=X509_CERT"},
+ {IPE_OP_BPF_PROG_LOAD, "op=BPF_PROG_LOAD"},
{IPE_OP_INVALID, NULL}
};
@@ -281,6 +282,19 @@ static const match_table_t property_tokens = {
{IPE_PROP_FSV_DIGEST, "fsverity_digest=%s"},
{IPE_PROP_FSV_SIG_FALSE, "fsverity_signature=FALSE"},
{IPE_PROP_FSV_SIG_TRUE, "fsverity_signature=TRUE"},
+ {IPE_PROP_BPF_SIG_NONE, "bpf_signature=NONE"},
+ {IPE_PROP_BPF_SIG_OK, "bpf_signature=OK"},
+ {IPE_PROP_BPF_SIG_UNSIGNED, "bpf_signature=UNSIGNED"},
+ {IPE_PROP_BPF_SIG_PARTIALSIG, "bpf_signature=PARTIALSIG"},
+ {IPE_PROP_BPF_SIG_UNKNOWNKEY, "bpf_signature=UNKNOWNKEY"},
+ {IPE_PROP_BPF_SIG_UNEXPECTED, "bpf_signature=UNEXPECTED"},
+ {IPE_PROP_BPF_SIG_FAULT, "bpf_signature=FAULT"},
+ {IPE_PROP_BPF_SIG_BADSIG, "bpf_signature=BADSIG"},
+ {IPE_PROP_BPF_KEYRING_BUILTIN, "bpf_keyring=BUILTIN"},
+ {IPE_PROP_BPF_KEYRING_SECONDARY, "bpf_keyring=SECONDARY"},
+ {IPE_PROP_BPF_KEYRING_PLATFORM, "bpf_keyring=PLATFORM"},
+ {IPE_PROP_BPF_KERNEL_FALSE, "bpf_kernel=FALSE"},
+ {IPE_PROP_BPF_KERNEL_TRUE, "bpf_kernel=TRUE"},
{IPE_PROP_INVALID, NULL}
};
@@ -331,6 +345,19 @@ static int parse_property(char *t, struct ipe_rule *r)
case IPE_PROP_DMV_SIG_TRUE:
case IPE_PROP_FSV_SIG_FALSE:
case IPE_PROP_FSV_SIG_TRUE:
+ case IPE_PROP_BPF_SIG_NONE:
+ case IPE_PROP_BPF_SIG_OK:
+ case IPE_PROP_BPF_SIG_UNSIGNED:
+ case IPE_PROP_BPF_SIG_PARTIALSIG:
+ case IPE_PROP_BPF_SIG_UNKNOWNKEY:
+ case IPE_PROP_BPF_SIG_UNEXPECTED:
+ case IPE_PROP_BPF_SIG_FAULT:
+ case IPE_PROP_BPF_SIG_BADSIG:
+ case IPE_PROP_BPF_KEYRING_BUILTIN:
+ case IPE_PROP_BPF_KEYRING_SECONDARY:
+ case IPE_PROP_BPF_KEYRING_PLATFORM:
+ case IPE_PROP_BPF_KERNEL_FALSE:
+ case IPE_PROP_BPF_KERNEL_TRUE:
p->type = token;
break;
default:
--
2.53.0
^ permalink raw reply related
* [PATCH v2 19/28] nfsd: apply the notify mask to the delegation when requested
From: Jeff Layton @ 2026-04-16 17:35 UTC (permalink / raw)
To: Alexander Viro, Christian Brauner, Jan Kara, Chuck Lever,
Alexander Aring, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, NeilBrown,
Olga Kornievskaia, Dai Ngo, Tom Talpey, Trond Myklebust,
Anna Schumaker, Amir Goldstein
Cc: Calum Mackay, linux-fsdevel, linux-kernel, linux-trace-kernel,
linux-doc, linux-nfs, Jeff Layton
In-Reply-To: <20260416-dir-deleg-v2-0-851426a550f6@kernel.org>
If the client requests a directory delegation with notifications
enabled, set the appropriate return mask in gddr_notification[0]. This
will ensure the lease acquisition sets the appropriate ignore mask.
If the client doesn't set NOTIFY4_GFLAG_EXTEND, then don't offer any
notifications, as nfsd won't provide directory offset information, and
"classic" notifications require them.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4proc.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 2797da8cc950..01e3bf9e1839 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2506,12 +2506,18 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
return status == nfserr_same ? nfs_ok : status;
}
+#define SUPPORTED_NOTIFY_MASK (BIT(NOTIFY4_REMOVE_ENTRY) | \
+ BIT(NOTIFY4_ADD_ENTRY) | \
+ BIT(NOTIFY4_RENAME_ENTRY) | \
+ BIT(NOTIFY4_GFLAG_EXTEND))
+
static __be32
nfsd4_get_dir_delegation(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate,
union nfsd4_op_u *u)
{
struct nfsd4_get_dir_delegation *gdd = &u->get_dir_delegation;
+ u32 requested = gdd->gdda_notification_types[0];
struct nfs4_delegation *dd;
struct nfsd_file *nf;
__be32 status;
@@ -2520,6 +2526,12 @@ nfsd4_get_dir_delegation(struct svc_rqst *rqstp,
if (status != nfs_ok)
return status;
+ /* No notifications if you don't set NOTIFY4_GFLAG_EXTEND! */
+ if (!(requested & BIT(NOTIFY4_GFLAG_EXTEND)))
+ requested = 0;
+
+ gdd->gddr_notification[0] = requested & SUPPORTED_NOTIFY_MASK;
+
/*
* RFC 8881, section 18.39.3 says:
*
--
2.53.0
^ permalink raw reply related
* [PATCH v2 20/28] nfsd: add helper to marshal a fattr4 from completed args
From: Jeff Layton @ 2026-04-16 17:35 UTC (permalink / raw)
To: Alexander Viro, Christian Brauner, Jan Kara, Chuck Lever,
Alexander Aring, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, NeilBrown,
Olga Kornievskaia, Dai Ngo, Tom Talpey, Trond Myklebust,
Anna Schumaker, Amir Goldstein
Cc: Calum Mackay, linux-fsdevel, linux-kernel, linux-trace-kernel,
linux-doc, linux-nfs, Jeff Layton
In-Reply-To: <20260416-dir-deleg-v2-0-851426a550f6@kernel.org>
Break the loop that encodes the actual attr_vals field into a separate
function.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4xdr.c | 44 +++++++++++++++++++++++++-------------------
1 file changed, 25 insertions(+), 19 deletions(-)
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 8af1e15e1102..b9b173ec7421 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3852,6 +3852,22 @@ static const nfsd4_enc_attr nfsd4_enc_fattr4_encode_ops[] = {
#endif
};
+static __be32
+nfsd4_encode_attr_vals(struct xdr_stream *xdr, u32 *attrmask, struct nfsd4_fattr_args *args)
+{
+ DECLARE_BITMAP(attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops));
+ unsigned long bit;
+ __be32 status;
+
+ bitmap_from_arr32(attr_bitmap, attrmask, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops));
+ for_each_set_bit(bit, attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)) {
+ status = nfsd4_enc_fattr4_encode_ops[bit](xdr, args);
+ if (status != nfs_ok)
+ return status;
+ }
+ return nfs_ok;
+}
+
/*
* Note: @fhp can be NULL; in this case, we might have to compose the filehandle
* ourselves.
@@ -3862,7 +3878,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
struct dentry *dentry, const u32 *bmval,
int ignore_crossmnt)
{
- DECLARE_BITMAP(attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops));
struct nfs4_delegation *dp = NULL;
struct nfsd4_fattr_args args;
struct svc_fh *tempfh = NULL;
@@ -3877,7 +3892,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
.mnt = exp->ex_path.mnt,
.dentry = dentry,
};
- unsigned long bit;
WARN_ON_ONCE(bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1);
WARN_ON_ONCE(!nfsd_attrs_supported(minorversion, bmval));
@@ -4050,27 +4064,22 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
#endif /* CONFIG_NFSD_V4_POSIX_ACLS */
/* attrmask */
- status = nfsd4_encode_bitmap4(xdr, attrmask[0], attrmask[1],
- attrmask[2]);
+ status = nfsd4_encode_bitmap4(xdr, attrmask[0], attrmask[1], attrmask[2]);
if (status)
goto out;
/* attr_vals */
attrlen_offset = xdr->buf->len;
- if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT)))
- goto out_resource;
- bitmap_from_arr32(attr_bitmap, attrmask,
- ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops));
- for_each_set_bit(bit, attr_bitmap,
- ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)) {
- status = nfsd4_enc_fattr4_encode_ops[bit](xdr, &args);
- if (status != nfs_ok)
- goto out;
+ if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT))) {
+ status = nfserr_resource;
+ goto out;
}
- attrlen = cpu_to_be32(xdr->buf->len - attrlen_offset - XDR_UNIT);
- write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, XDR_UNIT);
- status = nfs_ok;
+ status = nfsd4_encode_attr_vals(xdr, attrmask, &args);
+ if (status == nfs_ok) {
+ attrlen = cpu_to_be32(xdr->buf->len - attrlen_offset - XDR_UNIT);
+ write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, XDR_UNIT);
+ }
out:
#ifdef CONFIG_NFSD_V4_POSIX_ACLS
if (args.dpacl)
@@ -4093,9 +4102,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
out_nfserr:
status = nfserrno(err);
goto out;
-out_resource:
- status = nfserr_resource;
- goto out;
}
static bool
--
2.53.0
^ permalink raw reply related
* [PATCH v2 21/28] nfsd: allow nfsd4_encode_fattr4_change() to work with no export
From: Jeff Layton @ 2026-04-16 17:35 UTC (permalink / raw)
To: Alexander Viro, Christian Brauner, Jan Kara, Chuck Lever,
Alexander Aring, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, NeilBrown,
Olga Kornievskaia, Dai Ngo, Tom Talpey, Trond Myklebust,
Anna Schumaker, Amir Goldstein
Cc: Calum Mackay, linux-fsdevel, linux-kernel, linux-trace-kernel,
linux-doc, linux-nfs, Jeff Layton
In-Reply-To: <20260416-dir-deleg-v2-0-851426a550f6@kernel.org>
In the context of a CB_NOTIFY callback, we may not have easy access to
a svc_export. nfsd will not currently grant a delegation on a the V4 root
however, so this should be safe.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4xdr.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index b9b173ec7421..91681aea9d7f 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3257,7 +3257,7 @@ static __be32 nfsd4_encode_fattr4_change(struct xdr_stream *xdr,
{
const struct svc_export *exp = args->exp;
- if (unlikely(exp->ex_flags & NFSEXP_V4ROOT)) {
+ if (exp && unlikely(exp->ex_flags & NFSEXP_V4ROOT)) {
u32 flush_time = convert_to_wallclock(exp->cd->flush_time);
if (xdr_stream_encode_u32(xdr, flush_time) != XDR_UNIT)
--
2.53.0
^ permalink raw reply related
* [PATCH v2 22/28] nfsd: send basic file attributes in CB_NOTIFY
From: Jeff Layton @ 2026-04-16 17:35 UTC (permalink / raw)
To: Alexander Viro, Christian Brauner, Jan Kara, Chuck Lever,
Alexander Aring, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, NeilBrown,
Olga Kornievskaia, Dai Ngo, Tom Talpey, Trond Myklebust,
Anna Schumaker, Amir Goldstein
Cc: Calum Mackay, linux-fsdevel, linux-kernel, linux-trace-kernel,
linux-doc, linux-nfs, Jeff Layton
In-Reply-To: <20260416-dir-deleg-v2-0-851426a550f6@kernel.org>
In addition to the filename, send attributes about the inode in a
CB_NOTIFY event. This patch just adds a the basic inode information that
can be acquired via GETATTR.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4xdr.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 44 insertions(+)
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 91681aea9d7f..f85581ebbd10 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4104,12 +4104,21 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
goto out;
}
+#define CB_NOTIFY_STATX_REQUEST_MASK (STATX_BASIC_STATS | \
+ STATX_BTIME | \
+ STATX_CHANGE_COOKIE)
+
static bool
nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
struct dentry *dentry, struct nfs4_delegation *dp,
struct nfsd_file *nf, char *name, u32 namelen)
{
+ struct path path = { .mnt = nf->nf_file->f_path.mnt,
+ .dentry = dentry };
+ struct nfsd4_fattr_args args = { };
uint32_t *attrmask;
+ __be32 status;
+ int ret;
/* Reserve space for attrmask */
attrmask = xdr_reserve_space(xdr, 3 * sizeof(uint32_t));
@@ -4120,6 +4129,41 @@ nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
ne->ne_file.len = namelen;
ne->ne_attrs.attrmask.element = attrmask;
+ /* FIXME: d_find_alias for inode ? */
+ if (!path.dentry || !d_inode(path.dentry))
+ goto noattrs;
+
+ /*
+ * It is possible that the client was granted a delegation when a file
+ * was created. Note that we don't issue a CB_GETATTR here since stale
+ * attributes are presumably ok.
+ */
+ ret = vfs_getattr(&path, &args.stat, CB_NOTIFY_STATX_REQUEST_MASK, AT_STATX_SYNC_AS_STAT);
+ if (ret)
+ goto noattrs;
+
+ args.change_attr = nfsd4_change_attribute(&args.stat);
+
+ attrmask[0] = FATTR4_WORD0_TYPE | FATTR4_WORD0_CHANGE |
+ FATTR4_WORD0_SIZE | FATTR4_WORD0_FILEID;
+ attrmask[1] = FATTR4_WORD1_MODE | FATTR4_WORD1_NUMLINKS | FATTR4_WORD1_RAWDEV |
+ FATTR4_WORD1_SPACE_USED | FATTR4_WORD1_TIME_ACCESS |
+ FATTR4_WORD1_TIME_METADATA | FATTR4_WORD1_TIME_MODIFY;
+ attrmask[2] = 0;
+
+ if (args.stat.result_mask & STATX_BTIME)
+ attrmask[1] |= FATTR4_WORD1_TIME_CREATE;
+
+ ne->ne_attrs.attrmask.count = 2;
+ ne->ne_attrs.attr_vals.data = (u8 *)xdr->p;
+
+ status = nfsd4_encode_attr_vals(xdr, attrmask, &args);
+ if (status != nfs_ok)
+ goto noattrs;
+
+ ne->ne_attrs.attr_vals.len = (u8 *)xdr->p - ne->ne_attrs.attr_vals.data;
+ return true;
+noattrs:
attrmask[0] = 0;
attrmask[1] = 0;
attrmask[2] = 0;
--
2.53.0
^ permalink raw reply related
* [PATCH v2 23/28] nfsd: allow encoding a filehandle into fattr4 without a svc_fh
From: Jeff Layton @ 2026-04-16 17:35 UTC (permalink / raw)
To: Alexander Viro, Christian Brauner, Jan Kara, Chuck Lever,
Alexander Aring, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, NeilBrown,
Olga Kornievskaia, Dai Ngo, Tom Talpey, Trond Myklebust,
Anna Schumaker, Amir Goldstein
Cc: Calum Mackay, linux-fsdevel, linux-kernel, linux-trace-kernel,
linux-doc, linux-nfs, Jeff Layton
In-Reply-To: <20260416-dir-deleg-v2-0-851426a550f6@kernel.org>
The current fattr4 encoder requires a svc_fh in order to encode the
filehandle. This is not available in a CB_NOTIFY callback. Add a a new
"fhandle" field to struct nfsd4_fattr_args and copy the filehandle into
there from the svc_fh. CB_NOTIFY will populate it via other means.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4xdr.c | 35 ++++++++++++++++++++---------------
1 file changed, 20 insertions(+), 15 deletions(-)
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index f85581ebbd10..a9cdf7a3f8b3 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2701,7 +2701,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
}
static __be32 nfsd4_encode_nfs_fh4(struct xdr_stream *xdr,
- struct knfsd_fh *fh_handle)
+ const struct knfsd_fh *fh_handle)
{
return nfsd4_encode_opaque(xdr, fh_handle->fh_raw, fh_handle->fh_size);
}
@@ -3144,6 +3144,7 @@ struct nfsd4_fattr_args {
struct svc_fh *fhp;
struct svc_export *exp;
struct dentry *dentry;
+ struct knfsd_fh fhandle;
struct kstat stat;
struct kstatfs statfs;
struct nfs4_acl *acl;
@@ -3359,7 +3360,7 @@ static __be32 nfsd4_encode_fattr4_acl(struct xdr_stream *xdr,
static __be32 nfsd4_encode_fattr4_filehandle(struct xdr_stream *xdr,
const struct nfsd4_fattr_args *args)
{
- return nfsd4_encode_nfs_fh4(xdr, &args->fhp->fh_handle);
+ return nfsd4_encode_nfs_fh4(xdr, &args->fhandle);
}
static __be32 nfsd4_encode_fattr4_fileid(struct xdr_stream *xdr,
@@ -3969,19 +3970,23 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
if (err)
goto out_nfserr;
}
- if ((attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) &&
- !fhp) {
- tempfh = kmalloc_obj(struct svc_fh);
- status = nfserr_jukebox;
- if (!tempfh)
- goto out;
- fh_init(tempfh, NFS4_FHSIZE);
- status = fh_compose(tempfh, exp, dentry, NULL);
- if (status)
- goto out;
- args.fhp = tempfh;
- } else
- args.fhp = fhp;
+
+ args.fhp = fhp;
+ if ((attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID))) {
+ if (!args.fhp) {
+ tempfh = kmalloc_obj(struct svc_fh);
+ status = nfserr_jukebox;
+ if (!tempfh)
+ goto out;
+ fh_init(tempfh, NFS4_FHSIZE);
+ status = fh_compose(tempfh, exp, dentry, NULL);
+ if (status)
+ goto out;
+ args.fhp = tempfh;
+ }
+ if (args.fhp)
+ fh_copy_shallow(&args.fhandle, &args.fhp->fh_handle);
+ }
if (attrmask[0] & FATTR4_WORD0_ACL) {
err = nfsd4_get_nfs4_acl(rqstp, dentry, &args.acl);
--
2.53.0
^ permalink raw reply related
* [PATCH v2 24/28] nfsd: add a fi_connectable flag to struct nfs4_file
From: Jeff Layton @ 2026-04-16 17:35 UTC (permalink / raw)
To: Alexander Viro, Christian Brauner, Jan Kara, Chuck Lever,
Alexander Aring, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, NeilBrown,
Olga Kornievskaia, Dai Ngo, Tom Talpey, Trond Myklebust,
Anna Schumaker, Amir Goldstein
Cc: Calum Mackay, linux-fsdevel, linux-kernel, linux-trace-kernel,
linux-doc, linux-nfs, Jeff Layton
In-Reply-To: <20260416-dir-deleg-v2-0-851426a550f6@kernel.org>
When encoding a filehandle for a CB_NOTIFY, there is no svc_export
available, but the server needs to know whether to encode a connectable
filehandle. Add a flag to the nfs4_file that tells whether the
svc_export under which a directory delegation was acquired has subtree
checking enabled, in which case it needs connectable filehandles.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4state.c | 1 +
fs/nfsd/state.h | 1 +
2 files changed, 2 insertions(+)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index eba6da1072c0..5f848c9910b8 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5166,6 +5166,7 @@ static void nfsd4_file_init(const struct svc_fh *fh, struct nfs4_file *fp)
memset(fp->fi_access, 0, sizeof(fp->fi_access));
fp->fi_aliased = false;
fp->fi_inode = d_inode(fh->fh_dentry);
+ fp->fi_connectable = !(fh->fh_export->ex_flags & NFSEXP_NOSUBTREECHECK);
#ifdef CONFIG_NFSD_PNFS
INIT_LIST_HEAD(&fp->fi_lo_states);
atomic_set(&fp->fi_lo_recalls, 0);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 570d66fc8297..caa3f5f78dc1 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -747,6 +747,7 @@ struct nfs4_file {
int fi_delegees;
struct knfsd_fh fi_fhandle;
bool fi_had_conflict;
+ bool fi_connectable;
#ifdef CONFIG_NFSD_PNFS
struct list_head fi_lo_states;
atomic_t fi_lo_recalls;
--
2.53.0
^ permalink raw reply related
* [PATCH v2 25/28] nfsd: add the filehandle to returned attributes in CB_NOTIFY
From: Jeff Layton @ 2026-04-16 17:35 UTC (permalink / raw)
To: Alexander Viro, Christian Brauner, Jan Kara, Chuck Lever,
Alexander Aring, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, NeilBrown,
Olga Kornievskaia, Dai Ngo, Tom Talpey, Trond Myklebust,
Anna Schumaker, Amir Goldstein
Cc: Calum Mackay, linux-fsdevel, linux-kernel, linux-trace-kernel,
linux-doc, linux-nfs, Jeff Layton
In-Reply-To: <20260416-dir-deleg-v2-0-851426a550f6@kernel.org>
nfsd's usual fh_compose routine requires a svc_export and fills out a
svc_fh. In the context of a CB_NOTIFY there is no such export to
consult.
Add a new routine that composes a filehandle with only a parent
filehandle and nfs4_file. Use that to fill out the fhandle field in the
nfsd4_fattr_args.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4xdr.c | 37 +++++++++++++++++++++++++++++++++++++
1 file changed, 37 insertions(+)
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index a9cdf7a3f8b3..5d7d8545c904 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4109,6 +4109,39 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
goto out;
}
+static bool
+setup_notify_fhandle(struct dentry *dentry, struct nfs4_file *fi,
+ struct nfsd_file *nf, struct nfsd4_fattr_args *args)
+{
+ int fileid_type, fsid_len, maxsize, flags = 0;
+ struct knfsd_fh *fhp = &args->fhandle;
+ struct inode *inode = d_inode(dentry);
+ struct inode *parent = NULL;
+ struct fid *fid;
+
+ fsid_len = key_len(fi->fi_fhandle.fh_fsid_type);
+ fhp->fh_size = 4 + fsid_len;
+
+ /* Copy first 4 bytes + fsid */
+ memcpy(&fhp->fh_raw, &fi->fi_fhandle.fh_raw, fhp->fh_size);
+
+ fid = (struct fid *)(fh_fsid(fhp) + fsid_len/4);
+ maxsize = (NFS4_FHSIZE - fhp->fh_size)/4;
+
+ if (fi->fi_connectable && !S_ISDIR(inode->i_mode)) {
+ parent = d_inode(nf->nf_file->f_path.dentry);
+ flags = EXPORT_FH_CONNECTABLE;
+ }
+
+ fileid_type = exportfs_encode_inode_fh(inode, fid, &maxsize, parent, flags);
+ if (fileid_type < 0)
+ return false;
+
+ fhp->fh_fileid_type = fileid_type;
+ fhp->fh_size += maxsize * 4;
+ return true;
+}
+
#define CB_NOTIFY_STATX_REQUEST_MASK (STATX_BASIC_STATS | \
STATX_BTIME | \
STATX_CHANGE_COOKIE)
@@ -4118,6 +4151,7 @@ nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
struct dentry *dentry, struct nfs4_delegation *dp,
struct nfsd_file *nf, char *name, u32 namelen)
{
+ struct nfs4_file *fi = dp->dl_stid.sc_file;
struct path path = { .mnt = nf->nf_file->f_path.mnt,
.dentry = dentry };
struct nfsd4_fattr_args args = { };
@@ -4156,6 +4190,9 @@ nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
FATTR4_WORD1_TIME_METADATA | FATTR4_WORD1_TIME_MODIFY;
attrmask[2] = 0;
+ if (setup_notify_fhandle(dentry, fi, nf, &args))
+ attrmask[0] |= FATTR4_WORD0_FILEHANDLE;
+
if (args.stat.result_mask & STATX_BTIME)
attrmask[1] |= FATTR4_WORD1_TIME_CREATE;
--
2.53.0
^ permalink raw reply related
* [PATCH v2 26/28] nfsd: properly track requested child attributes
From: Jeff Layton @ 2026-04-16 17:35 UTC (permalink / raw)
To: Alexander Viro, Christian Brauner, Jan Kara, Chuck Lever,
Alexander Aring, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, NeilBrown,
Olga Kornievskaia, Dai Ngo, Tom Talpey, Trond Myklebust,
Anna Schumaker, Amir Goldstein
Cc: Calum Mackay, linux-fsdevel, linux-kernel, linux-trace-kernel,
linux-doc, linux-nfs, Jeff Layton
In-Reply-To: <20260416-dir-deleg-v2-0-851426a550f6@kernel.org>
Track the union of requested and supported child attributes in the
delegation, and only encode the attributes in that union when sending
add/remove/rename updates.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4proc.c | 2 ++
fs/nfsd/nfs4state.c | 18 ++++++++++++++++++
fs/nfsd/nfs4xdr.c | 15 ++++++---------
fs/nfsd/state.h | 3 +++
4 files changed, 29 insertions(+), 9 deletions(-)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 01e3bf9e1839..a807a55dddf9 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2553,6 +2553,8 @@ nfsd4_get_dir_delegation(struct svc_rqst *rqstp,
gdd->gddrnf_status = GDD4_OK;
memcpy(&gdd->gddr_stateid, &dd->dl_stid.sc_stateid, sizeof(gdd->gddr_stateid));
+ gdd->gddr_child_attributes[0] = dd->dl_child_attrs[0];
+ gdd->gddr_child_attributes[1] = dd->dl_child_attrs[1];
nfs4_put_stid(&dd->dl_stid);
return nfs_ok;
}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 5f848c9910b8..28e34f6c95e7 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -9807,6 +9807,21 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry,
return status;
}
+#define GDD_WORD0_CHILD_ATTRS (FATTR4_WORD0_TYPE | \
+ FATTR4_WORD0_CHANGE | \
+ FATTR4_WORD0_SIZE | \
+ FATTR4_WORD0_FILEID | \
+ FATTR4_WORD0_FILEHANDLE)
+
+#define GDD_WORD1_CHILD_ATTRS (FATTR4_WORD1_MODE | \
+ FATTR4_WORD1_NUMLINKS | \
+ FATTR4_WORD1_RAWDEV | \
+ FATTR4_WORD1_SPACE_USED | \
+ FATTR4_WORD1_TIME_ACCESS | \
+ FATTR4_WORD1_TIME_METADATA | \
+ FATTR4_WORD1_TIME_MODIFY | \
+ FATTR4_WORD1_TIME_CREATE)
+
/**
* nfsd_get_dir_deleg - attempt to get a directory delegation
* @cstate: compound state
@@ -9876,6 +9891,9 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
dp->dl_stid.sc_export =
exp_get(cstate->current_fh.fh_export);
+ dp->dl_child_attrs[0] = gdd->gdda_child_attributes[0] & GDD_WORD0_CHILD_ATTRS;
+ dp->dl_child_attrs[1] = gdd->gdda_child_attributes[1] & GDD_WORD1_CHILD_ATTRS;
+
fl = nfs4_alloc_init_lease(dp, gdd->gddr_notification[0]);
if (!fl)
goto out_put_stid;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 5d7d8545c904..bd1142590d2b 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4183,18 +4183,15 @@ nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
args.change_attr = nfsd4_change_attribute(&args.stat);
- attrmask[0] = FATTR4_WORD0_TYPE | FATTR4_WORD0_CHANGE |
- FATTR4_WORD0_SIZE | FATTR4_WORD0_FILEID;
- attrmask[1] = FATTR4_WORD1_MODE | FATTR4_WORD1_NUMLINKS | FATTR4_WORD1_RAWDEV |
- FATTR4_WORD1_SPACE_USED | FATTR4_WORD1_TIME_ACCESS |
- FATTR4_WORD1_TIME_METADATA | FATTR4_WORD1_TIME_MODIFY;
+ attrmask[0] = dp->dl_child_attrs[0];
+ attrmask[1] = dp->dl_child_attrs[1];
attrmask[2] = 0;
- if (setup_notify_fhandle(dentry, fi, nf, &args))
- attrmask[0] |= FATTR4_WORD0_FILEHANDLE;
+ if (!setup_notify_fhandle(dentry, fi, nf, &args))
+ attrmask[0] &= ~FATTR4_WORD0_FILEHANDLE;
- if (args.stat.result_mask & STATX_BTIME)
- attrmask[1] |= FATTR4_WORD1_TIME_CREATE;
+ if (!(args.stat.result_mask & STATX_BTIME))
+ attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE;
ne->ne_attrs.attrmask.count = 2;
ne->ne_attrs.attr_vals.data = (u8 *)xdr->p;
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index caa3f5f78dc1..cb1ac3248fe8 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -284,6 +284,9 @@ struct nfs4_delegation {
struct timespec64 dl_atime;
struct timespec64 dl_mtime;
struct timespec64 dl_ctime;
+
+ /* For dir delegations */
+ uint32_t dl_child_attrs[2];
};
static inline bool deleg_is_read(u32 dl_type)
--
2.53.0
^ permalink raw reply related
* [PATCH v2 27/28] nfsd: track requested dir attributes
From: Jeff Layton @ 2026-04-16 17:35 UTC (permalink / raw)
To: Alexander Viro, Christian Brauner, Jan Kara, Chuck Lever,
Alexander Aring, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, NeilBrown,
Olga Kornievskaia, Dai Ngo, Tom Talpey, Trond Myklebust,
Anna Schumaker, Amir Goldstein
Cc: Calum Mackay, linux-fsdevel, linux-kernel, linux-trace-kernel,
linux-doc, linux-nfs, Jeff Layton
In-Reply-To: <20260416-dir-deleg-v2-0-851426a550f6@kernel.org>
Track the union of requested and supported dir attributes in the
delegation, and only encode the attributes in that union when sending
add/remove/rename updates.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4proc.c | 9 ++++++---
fs/nfsd/nfs4state.c | 14 +++++++++++++-
fs/nfsd/state.h | 2 ++
3 files changed, 21 insertions(+), 4 deletions(-)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index a807a55dddf9..e4717e1e3d93 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2506,9 +2506,10 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
return status == nfserr_same ? nfs_ok : status;
}
-#define SUPPORTED_NOTIFY_MASK (BIT(NOTIFY4_REMOVE_ENTRY) | \
- BIT(NOTIFY4_ADD_ENTRY) | \
- BIT(NOTIFY4_RENAME_ENTRY) | \
+#define SUPPORTED_NOTIFY_MASK (BIT(NOTIFY4_CHANGE_DIR_ATTRS) | \
+ BIT(NOTIFY4_REMOVE_ENTRY) | \
+ BIT(NOTIFY4_ADD_ENTRY) | \
+ BIT(NOTIFY4_RENAME_ENTRY) | \
BIT(NOTIFY4_GFLAG_EXTEND))
static __be32
@@ -2555,6 +2556,8 @@ nfsd4_get_dir_delegation(struct svc_rqst *rqstp,
memcpy(&gdd->gddr_stateid, &dd->dl_stid.sc_stateid, sizeof(gdd->gddr_stateid));
gdd->gddr_child_attributes[0] = dd->dl_child_attrs[0];
gdd->gddr_child_attributes[1] = dd->dl_child_attrs[1];
+ gdd->gddr_dir_attributes[0] = dd->dl_dir_attrs[0];
+ gdd->gddr_dir_attributes[1] = dd->dl_dir_attrs[1];
nfs4_put_stid(&dd->dl_stid);
return nfs_ok;
}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 28e34f6c95e7..32340a0669df 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -9822,6 +9822,15 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry,
FATTR4_WORD1_TIME_MODIFY | \
FATTR4_WORD1_TIME_CREATE)
+#define GDD_WORD0_DIR_ATTRS (FATTR4_WORD0_CHANGE | \
+ FATTR4_WORD0_SIZE)
+
+#define GDD_WORD1_DIR_ATTRS (FATTR4_WORD1_NUMLINKS | \
+ FATTR4_WORD1_SPACE_USED | \
+ FATTR4_WORD1_TIME_ACCESS | \
+ FATTR4_WORD1_TIME_METADATA | \
+ FATTR4_WORD1_TIME_MODIFY)
+
/**
* nfsd_get_dir_deleg - attempt to get a directory delegation
* @cstate: compound state
@@ -9891,10 +9900,13 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
dp->dl_stid.sc_export =
exp_get(cstate->current_fh.fh_export);
+ dp->dl_notify_mask = gdd->gddr_notification[0];
dp->dl_child_attrs[0] = gdd->gdda_child_attributes[0] & GDD_WORD0_CHILD_ATTRS;
dp->dl_child_attrs[1] = gdd->gdda_child_attributes[1] & GDD_WORD1_CHILD_ATTRS;
+ dp->dl_dir_attrs[0] = gdd->gdda_dir_attributes[0] & GDD_WORD0_DIR_ATTRS;
+ dp->dl_dir_attrs[1] = gdd->gdda_dir_attributes[1] & GDD_WORD1_DIR_ATTRS;
- fl = nfs4_alloc_init_lease(dp, gdd->gddr_notification[0]);
+ fl = nfs4_alloc_init_lease(dp, dp->dl_notify_mask);
if (!fl)
goto out_put_stid;
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index cb1ac3248fe8..4c5848285378 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -286,7 +286,9 @@ struct nfs4_delegation {
struct timespec64 dl_ctime;
/* For dir delegations */
+ uint32_t dl_notify_mask;
uint32_t dl_child_attrs[2];
+ uint32_t dl_dir_attrs[2];
};
static inline bool deleg_is_read(u32 dl_type)
--
2.53.0
^ permalink raw reply related
* [PATCH v2 28/28] nfsd: add support to CB_NOTIFY for dir attribute changes
From: Jeff Layton @ 2026-04-16 17:35 UTC (permalink / raw)
To: Alexander Viro, Christian Brauner, Jan Kara, Chuck Lever,
Alexander Aring, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, NeilBrown,
Olga Kornievskaia, Dai Ngo, Tom Talpey, Trond Myklebust,
Anna Schumaker, Amir Goldstein
Cc: Calum Mackay, linux-fsdevel, linux-kernel, linux-trace-kernel,
linux-doc, linux-nfs, Jeff Layton
In-Reply-To: <20260416-dir-deleg-v2-0-851426a550f6@kernel.org>
If the client requested dir attribute change notifications, send those
alongside any set of add/remove/rename events. Note that the server will
still recall the delegation on a SETATTR, so these are only sent for
changes to child dirents.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4state.c | 25 ++++++++++++++++++++--
fs/nfsd/nfs4xdr.c | 61 +++++++++++++++++++++++++++++++++++++++++++++--------
fs/nfsd/xdr4.h | 2 ++
3 files changed, 77 insertions(+), 11 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 32340a0669df..5eca7899c48d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3478,10 +3478,15 @@ nfsd4_cb_notify_prepare(struct nfsd4_callback *cb)
struct nfsd_notify_event *events[NOTIFY4_EVENT_QUEUE_SIZE];
struct xdr_buf xdr = { .buflen = PAGE_SIZE * NOTIFY4_PAGE_ARRAY_SIZE,
.pages = ncn->ncn_pages };
+ int limit = NOTIFY4_EVENT_QUEUE_SIZE;
struct xdr_stream stream;
struct nfsd_file *nf;
- int count, i;
bool error = false;
+ int count, i;
+
+ /* Save a slot for dir attr update if requested */
+ if (dp->dl_notify_mask & BIT(NOTIFY4_CHANGE_DIR_ATTRS))
+ --limit;
xdr_init_encode_pages(&stream, &xdr);
@@ -3495,7 +3500,7 @@ nfsd4_cb_notify_prepare(struct nfsd4_callback *cb)
}
/* we can't keep up! */
- if (count > NOTIFY4_EVENT_QUEUE_SIZE) {
+ if (count > limit) {
spin_unlock(&ncn->ncn_lock);
goto out_recall;
}
@@ -3542,6 +3547,22 @@ nfsd4_cb_notify_prepare(struct nfsd4_callback *cb)
nfsd_notify_event_put(nne);
}
if (!error) {
+ if (dp->dl_notify_mask & BIT(NOTIFY4_CHANGE_DIR_ATTRS)) {
+ u32 *maskp = (u32 *)xdr_reserve_space(&stream, sizeof(*maskp));
+
+ if (maskp) {
+ u8 *p = nfsd4_encode_dir_attr_change(&stream, dp, nf);
+
+ if (p) {
+ *maskp = BIT(NOTIFY4_CHANGE_DIR_ATTRS);
+ ncn->ncn_nf[count].notify_mask.count = 1;
+ ncn->ncn_nf[count].notify_mask.element = maskp;
+ ncn->ncn_nf[count].notify_vals.data = p;
+ ncn->ncn_nf[count].notify_vals.len = (u8 *)stream.p - p;
+ ++count;
+ }
+ }
+ }
ncn->ncn_nf_cnt = count;
nfsd_file_put(nf);
return true;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index bd1142590d2b..73f2fdf929ed 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4152,11 +4152,11 @@ nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
struct nfsd_file *nf, char *name, u32 namelen)
{
struct nfs4_file *fi = dp->dl_stid.sc_file;
- struct path path = { .mnt = nf->nf_file->f_path.mnt,
- .dentry = dentry };
+ struct path path = nf->nf_file->f_path;
struct nfsd4_fattr_args args = { };
uint32_t *attrmask;
__be32 status;
+ bool parent;
int ret;
/* Reserve space for attrmask */
@@ -4168,6 +4168,9 @@ nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
ne->ne_file.len = namelen;
ne->ne_attrs.attrmask.element = attrmask;
+ parent = (dentry == path.dentry);
+ path.dentry = dentry;
+
/* FIXME: d_find_alias for inode ? */
if (!path.dentry || !d_inode(path.dentry))
goto noattrs;
@@ -4183,15 +4186,20 @@ nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
args.change_attr = nfsd4_change_attribute(&args.stat);
- attrmask[0] = dp->dl_child_attrs[0];
- attrmask[1] = dp->dl_child_attrs[1];
- attrmask[2] = 0;
+ if (parent) {
+ attrmask[0] = dp->dl_dir_attrs[0];
+ attrmask[1] = dp->dl_dir_attrs[1];
+ } else {
+ attrmask[0] = dp->dl_child_attrs[0];
+ attrmask[1] = dp->dl_child_attrs[1];
- if (!setup_notify_fhandle(dentry, fi, nf, &args))
- attrmask[0] &= ~FATTR4_WORD0_FILEHANDLE;
+ if (!setup_notify_fhandle(dentry, fi, nf, &args))
+ attrmask[0] &= ~FATTR4_WORD0_FILEHANDLE;
- if (!(args.stat.result_mask & STATX_BTIME))
- attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE;
+ if (!(args.stat.result_mask & STATX_BTIME))
+ attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE;
+ }
+ attrmask[2] = 0;
ne->ne_attrs.attrmask.count = 2;
ne->ne_attrs.attr_vals.data = (u8 *)xdr->p;
@@ -4308,6 +4316,41 @@ u8 *nfsd4_encode_notify_event(struct xdr_stream *xdr, struct nfsd_notify_event *
return NULL;
}
+/**
+ * nfsd4_encode_dir_attr_change
+ * @xdr: stream to which to encode the fattr4
+ * @dp: delegation where the event occurred
+ * @nf: nfsd_file opened on the directory
+ *
+ * Encode a dir attr change event.
+ */
+u8 *nfsd4_encode_dir_attr_change(struct xdr_stream *xdr, struct nfs4_delegation *dp,
+ struct nfsd_file *nf)
+{
+ struct dentry *dentry = nf->nf_file->f_path.dentry;
+ struct notify_attr4 na = { };
+ struct name_snapshot n;
+ bool ret;
+ u8 *p = NULL;
+
+ if (!(dp->dl_notify_mask & BIT(NOTIFY4_CHANGE_DIR_ATTRS)))
+ return NULL;
+
+ take_dentry_name_snapshot(&n, dentry);
+ ret = nfsd4_setup_notify_entry4(&na.na_changed_entry, xdr,
+ dentry, dp, nf, (char *)n.name.name,
+ n.name.len);
+
+ /* Don't bother with the event if we're not encoding attrs */
+ if (ret && na.na_changed_entry.ne_attrs.attr_vals.len) {
+ p = (u8 *)xdr->p;
+ if (!xdrgen_encode_notify_attr4(xdr, &na))
+ p = NULL;
+ }
+ release_dentry_name_snapshot(&n);
+ return p;
+}
+
static void svcxdr_init_encode_from_buffer(struct xdr_stream *xdr,
struct xdr_buf *buf, __be32 *p, int bytes)
{
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index d276840aca50..cf7f0df68d63 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -958,6 +958,8 @@ __be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words,
u8 *nfsd4_encode_notify_event(struct xdr_stream *xdr, struct nfsd_notify_event *nne,
struct nfs4_delegation *dd, struct nfsd_file *nf,
u32 *notify_mask);
+u8 *nfsd4_encode_dir_attr_change(struct xdr_stream *xdr, struct nfs4_delegation *dp,
+ struct nfsd_file *nf);
extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
struct nfsd4_compound_state *, union nfsd4_op_u *u);
extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
--
2.53.0
^ permalink raw reply related
* Re: [PATCH v2 1/2] dt-bindings: hwmon: pmbus: add max20830
From: Guenter Roeck @ 2026-04-16 18:01 UTC (permalink / raw)
To: Conor Dooley
Cc: Alexis Czezar Torreno, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Jonathan Corbet, Shuah Khan, linux-hwmon,
devicetree, linux-kernel, linux-doc
In-Reply-To: <20260416-diaphragm-corrode-494560404ed4@spud>
On Thu, Apr 16, 2026 at 04:51:37PM +0100, Conor Dooley wrote:
> On Thu, Apr 16, 2026 at 03:59:10PM +0800, Alexis Czezar Torreno wrote:
> > Add device tree documentation for MAX20830 step-down DC-DC switching
> > regulator with PMBus interface.
> >
> > Signed-off-by: Alexis Czezar Torreno <alexisczezar.torreno@analog.com>
> > ---
> > .../bindings/hwmon/pmbus/adi,max20830.yaml | 61 ++++++++++++++++++++++
> > MAINTAINERS | 7 +++
> > 2 files changed, 68 insertions(+)
> >
> > diff --git a/Documentation/devicetree/bindings/hwmon/pmbus/adi,max20830.yaml b/Documentation/devicetree/bindings/hwmon/pmbus/adi,max20830.yaml
> > new file mode 100644
> > index 0000000000000000000000000000000000000000..8b3ec1ffa0c9460de2122f6606ce3dcbcdfbbcc7
> > --- /dev/null
> > +++ b/Documentation/devicetree/bindings/hwmon/pmbus/adi,max20830.yaml
> > @@ -0,0 +1,61 @@
> > +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
> > +%YAML 1.2
> > +---
> > +$id: http://devicetree.org/schemas/hwmon/pmbus/adi,max20830.yaml#
> > +$schema: http://devicetree.org/meta-schemas/core.yaml#
> > +
> > +title: Analog Devices MAX20830 Step-Down Switching Regulator with PMBus
> > +
> > +maintainers:
> > + - Alexis Czezar Torreno <alexisczezar.torreno@analog.com>
> > +
> > +description: |
> > + The MAX20830 is a fully integrated step-down DC-DC switching regulator with
> > + PMBus interface. It provides 2.7V to 16V input, 0.4V to 5.8V adjustable
> > + output, and up to 30A output current. It allows monitoring of input/output
> > + voltage, output current and temperature through the PMBus serial interface.
> > + Datasheet:
> > + https://www.analog.com/en/products/max20830.html
> > +
> > +allOf:
> > + - $ref: /schemas/regulator/regulator.yaml#
> > +
> > +properties:
> > + compatible:
> > + const: adi,max20830
> > +
> > + reg:
> > + maxItems: 1
>
> On the previous version, you got an LLM comment about not having the
> interrupts property amongst other things.
> I think the other things got implemented, but I didn't see any reply to
> the bot about that?
> I think the answer is that it shouldn't because the pin it referenced
> doesn't exist, but when looking at the schematic I have to wonder if
I had to look this up in the datasheet. A SMBus chip with no alert pin is
a bit odd, but you are correct.
> there should be an interrupts property for dealing with "pgood"?
>
FWIW, I have never seen that. Normally such pins are used to take devices
out of reset.
Thanks,
Guenter
^ permalink raw reply
* Re: [RFC, PATCH 00/12] userfaultfd: working set tracking for VM guest memory
From: David Hildenbrand (Arm) @ 2026-04-16 18:32 UTC (permalink / raw)
To: Kiryl Shutsemau
Cc: Andrew Morton, Peter Xu, Lorenzo Stoakes, Mike Rapoport,
Suren Baghdasaryan, Vlastimil Babka, Liam R . Howlett, Zi Yan,
Jonathan Corbet, Shuah Khan, Sean Christopherson, Paolo Bonzini,
linux-mm, linux-kernel, linux-doc, linux-kselftest, kvm
In-Reply-To: <aeDoqFWPFxkkNB26@thinkstation>
On 4/16/26 15:49, Kiryl Shutsemau wrote:
> On Tue, Apr 14, 2026 at 06:10:44PM +0100, Kiryl Shutsemau wrote:
>> On Tue, Apr 14, 2026 at 05:37:50PM +0200, David Hildenbrand (Arm) wrote:
>>>
>>> I would rather tackle this from the other direction: it's another form
>>> of protection (like WP), not really a "minor" mode.
>>>
>>> Could we add a UFFDIO_REGISTER_MODE_RWP (or however we would call it)
>>> and support it for anon+shmem, avoiding the zapping for shmem completely?
>>
>> I like this idea.
>>
>> It should be functionally equivalent, but your interface idea fits
>> better with the rest.
>>
>> Thanks! Will give it a try.
>
> Here is an updated version:
>
> https://git.kernel.org/pub/scm/linux/kernel/git/kas/linux.git/log/?h=uffd/rfc-v2
>
> will post after -rc1 is tagged.
>
> I like it more. It got substantially cleaner.
I don't have time to look into the details just yet, but my thinking was
that
a) It would avoid the zap+refault
b) We could reuse the uffd-wp PTE bit + marker to indicate/remember the
protection, making it co-exist with NUMA hinting naturally.
b) obviously means that we cannot use uffd-wp and uffd-rwp at the same
time in the same uffd area. I guess that should be acceptable for the
use cases we you should have in mind?
But I also haven't taken a closer look at this patch set, whether you
would already be using a PTE bit somehow (I suspect not :) )
--
Cheers,
David
^ permalink raw reply
* Re: [PATCH v5 00/21] Virtual Swap Space
From: Kairui Song @ 2026-04-16 18:46 UTC (permalink / raw)
To: Nhat Pham
Cc: Liam.Howlett, akpm, apopple, axelrasmussen, baohua, baolin.wang,
bhe, byungchul, cgroups, chengming.zhou, chrisl, corbet, david,
dev.jain, gourry, hannes, hughd, jannh, joshua.hahnjy, lance.yang,
lenb, linux-doc, linux-kernel, linux-mm, linux-pm,
lorenzo.stoakes, matthew.brost, mhocko, muchun.song, npache,
pavel, peterx, peterz, pfalcato, rafael, rakie.kim,
roman.gushchin, rppt, ryan.roberts, shakeel.butt, shikemeng,
surenb, tglx, vbabka, weixugc, ying.huang, yosry.ahmed, yuanchu,
zhengqi.arch, ziy, kernel-team, riel
In-Reply-To: <CAKEwX=NrUhUrAFx+8BYJEfaVKpCm-H9JhBzYSrqOQb-NW7QRug@mail.gmail.com>
On Wed, Apr 15, 2026 at 1:23 AM Nhat Pham <nphamcs@gmail.com> wrote:
> Hi Kairui,
>
> My apologies if I missed your response, but could you share with me
> your full benchmark suite? It would be hugely useful, not just for
> this series, but for all swap contributions in the future :) We should
> do as much homework ourselves as possible :P
>
> And apologies for the delayed response. I kept having to back and
> forth between regression investigating, and figuring out what was
> going on with the build setups (I missed some of the CONFIGs you had
> originally), reducing variance on hosts, etc.
>
Hello Nhat!
No worries, I was also thinking about submitting some in tree test for
that so testing will be easier, but got really busy with some other
issues, series and the incommong LSFMM, will find some time to do
that.
>
> 1. Kswapd is slower on the vswap side, which shifts work towards
> direct reclaim, and makes compaction have to run harder (which has a
> weird contention through zsmalloc - I can expand further, but this is
> not vswap-specific, just exacerbated by slower kswapd).
It might be related, e.g. could the dynamic alloc and RCU free of
vswap data cause more fragmentation hence more pressure?
> 2. Higher swap readahead (albeit with higher hit rate) - this is more
> of an artifact of the fact that zero swap pages are no longer backed
> by zram swapfile, which skipped readahead in certain paths. We can
> ignore this for now, but worth assessing this for fast swap backends
> in general (zero swap pages, zswap, so on and so forth).
Hmm... That just brought up another question, you can't tell the
backend type or properly do readahead until you look down through the
virtual layer I guess?
> I spent sometimes perf-ing kswapd, and hack the usemem binary a bit so
> that I can perf the free stage of usemem separately. Most of the
> vswap-specific overhead lies in the xarray lookups. Some big offenders
> on top of my mind:
>
> 1. Right now, in the physical swap allocator, whenever we have an
> allocated slot in the range we're checking, we check if that slot is
> swap-cache-only (i.e no swap count), and if so we try to free it (if
> swapfile is almost full etc.). This check is cheap if all swap entry
> metadata live in physical swap layer only, but more expensive when you
> have to go through another layer of indirection :)
>
> I fixed that by just taking one bit in the reverse map to track
> swap-cache-only state, which eliminates this without extra space
> overhead (on top of the existing design).
Isn't that HAS_CACHE :) ?
> 2. On the free path, in swap_pte_batch(), we check cgroup to make sure
> that the range we pass to free_swap_and_cache_nr() belongs to the same
> cgroup, which has a per-PTE overhead for going to the vswap layer. We
This might be helpful:
https://lore.kernel.org/linux-mm/20260417-swap-table-p4-v2-8-17f5d1015428@tencent.com/
I observed a similar but much smaller issue with the current swap too.
Deferring the cgroup lookup to the swap-cache layer, where we already
grab the cluster (in a later commit), should reduce a lot of overhead.
It requires some unification of allocation though as shown in that
series, things will be much easier after that :)
> Anyway, still a small gap. The next idea that I have is inspired by
> TLB, which cache virtual->physical memory address translation. I added
I think this is getting over complex... You got a mandatory virtual
layer, which already comes with some cluster cache inside, and the
lower physical allocator has its own cluster cache, and then a new set
of cache on top of the virtual layer?
>
> Some final remarks:
> * I still think there's a good chance we can *significantly* close the
> gap overall between a design with virtual swap and a design without.
> It's a bit premature to commit to a vswap-optional route (which to be
> completely honest I'm still not confident is possible to satisfy all
> of our requirements).
>
> * Regardless of the direction we take, these are all pitfalls that
> will be problematic for virtual swap design, and more generally some
> of them will affect any dynamic swap design (which has to go through
> some sort of indirection or a dynamic data structure like xarray that
> will induce some amount of lookup overhead). I hope my work here can
> be useful in this sense too, outside of this specific vswap direction
> :)
Glad to know things are getting better! We can definitely work
something out. But besides the problem above, I think there are some
other concerns that need to be solved too. Good part is I think
everyone agrees that some kind of intermediate layer is needed.
^ permalink raw reply
* Re: [PATCH v2 07/28] fsnotify: add FSNOTIFY_EVENT_RENAME data type
From: Amir Goldstein @ 2026-04-16 19:24 UTC (permalink / raw)
To: Jeff Layton
Cc: Alexander Viro, Christian Brauner, Jan Kara, Chuck Lever,
Alexander Aring, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, NeilBrown,
Olga Kornievskaia, Dai Ngo, Tom Talpey, Trond Myklebust,
Anna Schumaker, Calum Mackay, linux-fsdevel, linux-kernel,
linux-trace-kernel, linux-doc, linux-nfs
In-Reply-To: <20260416-dir-deleg-v2-7-851426a550f6@kernel.org>
On Thu, Apr 16, 2026 at 7:35 PM Jeff Layton <jlayton@kernel.org> wrote:
>
> Add a new fsnotify_rename_data struct and FSNOTIFY_EVENT_RENAME data
> type that carries both the moved dentry and the inode that was
> overwritten by the rename (if any).
>
> Update fsnotify_data_inode(), fsnotify_data_dentry(), and
> fsnotify_data_sb() to handle the new type, and add a new
> fsnotify_data_rename_target() helper for extracting the overwritten
> target inode.
>
> Update fsnotify_move() to use the new data type for FS_RENAME and
> FS_MOVED_TO events, passing the overwritten target inode through the
> event data. FS_MOVED_FROM is unchanged since the source directory
> doesn't need overwrite information.
>
> This is done so that fsnotify consumers like nfsd can atomically
> observe the overwritten file when a rename replaces an existing entry,
> without needing a separate FS_DELETE event.
>
> Assisted-by: Claude (Anthropic Claude Code)
> Signed-off-by: Jeff Layton <jlayton@kernel.org>
> ---
> include/linux/fsnotify.h | 8 ++++++--
> include/linux/fsnotify_backend.h | 20 ++++++++++++++++++++
> 2 files changed, 26 insertions(+), 2 deletions(-)
It is strange to me that the NFS protocol needs to report the overwritten
node in the same event of the rename, but oh well, fine by me.
Feel free to add:
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Thanks,
Amir.
>
> diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
> index 079c18bcdbde..bda798bc67bc 100644
> --- a/include/linux/fsnotify.h
> +++ b/include/linux/fsnotify.h
> @@ -257,6 +257,10 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
> __u32 new_dir_mask = FS_MOVED_TO;
> __u32 rename_mask = FS_RENAME;
> const struct qstr *new_name = &moved->d_name;
> + struct fsnotify_rename_data rd = {
> + .moved = moved,
> + .target = target,
> + };
>
> if (isdir) {
> old_dir_mask |= FS_ISDIR;
> @@ -265,12 +269,12 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
> }
>
> /* Event with information about both old and new parent+name */
> - fsnotify_name(rename_mask, moved, FSNOTIFY_EVENT_DENTRY,
> + fsnotify_name(rename_mask, &rd, FSNOTIFY_EVENT_RENAME,
> old_dir, old_name, 0);
>
> fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE,
> old_dir, old_name, fs_cookie);
> - fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE,
> + fsnotify_name(new_dir_mask, &rd, FSNOTIFY_EVENT_RENAME,
> new_dir, new_name, fs_cookie);
>
> if (target)
> diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
> index 66e185bd1b1b..f8c8fb7f34ae 100644
> --- a/include/linux/fsnotify_backend.h
> +++ b/include/linux/fsnotify_backend.h
> @@ -311,6 +311,7 @@ enum fsnotify_data_type {
> FSNOTIFY_EVENT_DENTRY,
> FSNOTIFY_EVENT_MNT,
> FSNOTIFY_EVENT_ERROR,
> + FSNOTIFY_EVENT_RENAME,
> };
>
> struct fs_error_report {
> @@ -335,6 +336,11 @@ struct fsnotify_mnt {
> u64 mnt_id;
> };
>
> +struct fsnotify_rename_data {
> + struct dentry *moved; /* the dentry that was renamed */
> + struct inode *target; /* inode overwritten by rename, or NULL */
> +};
> +
> static inline struct inode *fsnotify_data_inode(const void *data, int data_type)
> {
> switch (data_type) {
> @@ -348,6 +354,8 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type)
> return d_inode(file_range_path(data)->dentry);
> case FSNOTIFY_EVENT_ERROR:
> return ((struct fs_error_report *)data)->inode;
> + case FSNOTIFY_EVENT_RENAME:
> + return d_inode(((const struct fsnotify_rename_data *)data)->moved);
> default:
> return NULL;
> }
> @@ -363,6 +371,8 @@ static inline struct dentry *fsnotify_data_dentry(const void *data, int data_typ
> return ((const struct path *)data)->dentry;
> case FSNOTIFY_EVENT_FILE_RANGE:
> return file_range_path(data)->dentry;
> + case FSNOTIFY_EVENT_RENAME:
> + return ((struct fsnotify_rename_data *)data)->moved;
> default:
> return NULL;
> }
> @@ -395,6 +405,8 @@ static inline struct super_block *fsnotify_data_sb(const void *data,
> return file_range_path(data)->dentry->d_sb;
> case FSNOTIFY_EVENT_ERROR:
> return ((struct fs_error_report *) data)->sb;
> + case FSNOTIFY_EVENT_RENAME:
> + return ((const struct fsnotify_rename_data *)data)->moved->d_sb;
> default:
> return NULL;
> }
> @@ -430,6 +442,14 @@ static inline struct fs_error_report *fsnotify_data_error_report(
> }
> }
>
> +static inline struct inode *fsnotify_data_rename_target(const void *data,
> + int data_type)
> +{
> + if (data_type == FSNOTIFY_EVENT_RENAME)
> + return ((const struct fsnotify_rename_data *)data)->target;
> + return NULL;
> +}
> +
> static inline const struct file_range *fsnotify_data_file_range(
> const void *data,
> int data_type)
>
> --
> 2.53.0
>
^ permalink raw reply
* Re: [PATCH v2] Documentation: sysctl: document net core sysctls
From: Jay Vosburgh @ 2026-04-16 20:11 UTC (permalink / raw)
To: Simon Horman
Cc: Shubham Chakraborty, netdev, davem, edumazet, kuba, pabeni,
kuniyu, corbet, skhan, linux-doc, linux-kernel
In-Reply-To: <20260413164707.GT469338@kernel.org>
Simon Horman <horms@kernel.org> wrote:
>On Thu, Apr 09, 2026 at 11:18:59PM +0530, Shubham Chakraborty wrote:
[...]
>> netdev_budget_usecs
>> ---------------------
>>
>
>The lines above the following hunk are:
>
>netdev_budget_usecs
>---------------------
>
>Maximum number of microseconds in one NAPI polling cycle. Polling
>
>> @@ -297,12 +332,16 @@ Maximum number of microseconds in one NAPI polling cycle. Polling
>> will exit when either netdev_budget_usecs have elapsed during the
>> poll cycle or the number of packets processed reaches netdev_budget.
>>
>> +Default: ``2 * USEC_PER_SEC / HZ`` (2000 when ``HZ`` is 1000)
>> +
>
>Well, that is awkward.
>
>Looking at git history, it seems that this sysctl was added by 7acf8a1e8a28
>("Replace 2 jiffies with sysctl netdev_budget_usecs to enable softirq
>tuning") in 2017. And at that time the unic was us, and the default was 2000 us.
>
>But that was changed by a fix for that commit, a4837980fd9f ("net: revert
>default NAPI poll timeout to 2 jiffies"), in 2020. As a side-effect of
>that commit, the default was changed to what you have documented above,
>and the unit changed to jiffies.
>
>So while what you have is correct it seems nonsensical to me for the unit
>to be jiffies. Because that's not a meaningful unit for users. And because
>the name of the sysctl ends in usecs.
I don't think the units for netdev_budget_usecs are actually
jiffies, even after a4837980fd9f. The default value, for example, is
2000 if HZ is 1000. However, the granularity of the measurement is in
jiffies, via:
static __latent_entropy void net_rx_action(void)
{
struct softnet_data *sd = this_cpu_ptr(&softnet_data);
unsigned long time_limit = jiffies +
usecs_to_jiffies(READ_ONCE(net_hotdata.netdev_budget_usecs));
I'm not sure offhand if usecs_to_jiffies rounds up or down, but
the netdev_budget_usecs looks to be interpreted as usecs.
-J
>But I'm unsure what to do about it. Since changing the unit this would
>represent (another) KABI break.
>
>* Add another knob that shadows this one (But what to call it?)
>* Simply remove this one (KAPI break)
>* Change the unit of this knob (KAPI break)
>
>If the code is left as is, then I think it should be documented that the
>unit is jiffies.
>
>...
>
---
-Jay Vosburgh, jv@jvosburgh.net
^ permalink raw reply
* Re: [PATCH V10 00/10] famfs: port into fuse
From: Gregory Price @ 2026-04-16 20:14 UTC (permalink / raw)
To: Joanne Koong
Cc: John Groves, Darrick J. Wong, Miklos Szeredi, Bernd Schubert,
John Groves, Dan Williams, Bernd Schubert, Alison Schofield,
John Groves, Jonathan Corbet, Shuah Khan, Vishal Verma,
Dave Jiang, Matthew Wilcox, Jan Kara, Alexander Viro,
David Hildenbrand, Christian Brauner, Randy Dunlap, Jeff Layton,
Amir Goldstein, Jonathan Cameron, Stefan Hajnoczi, Josef Bacik,
Bagas Sanjaya, Chen Linxuan, James Morse, Fuad Tabba,
Sean Christopherson, Shivank Garg, Ackerley Tng, Aravind Ramesh,
Ajay Joshi, 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, djbw
In-Reply-To: <CAJnrk1ZWVsKW2dhAWdBkCQskoTE+hmOhPFDhyz4EtExn=GdXGA@mail.gmail.com>
On Thu, Apr 16, 2026 at 08:56:46AM -0700, Joanne Koong wrote:
> On Tue, Apr 14, 2026 at 5:10 PM John Groves <John@groves.net> wrote:
> >
> > There is a FUSE_DAX_FMAP capability that the kernel may advertise or not
> > at init time; this capability "is" the famfs GET_FMAP AND GET_DAXDEV
> > commands. In the future, if we find a way to use BPF (or some other
> > mechanism) to avoid needing those fuse messages, the kernel could be updated
> > to NEVER advertise the FUSE_DAX_FMAP capability. All of the famfs-specific
> > code could be taken out of kernels that never advertise that capability.
>
> I’m not sure the capability bit can be used like that (though I am
> hoping it can!). As I understand it, once the kernel advertises a
> capability, it must continue supporting it in future kernels else
> userspace programs that rely on it will break.
>
FUSE_DAX_FMAP is already conditional on CONFIG_FUSE_DAX, the kernel is
not required to continue advertising FUSE_DAX_FMAP in perpetuity.
Setting CONFIG_FUSE_DAX=n does not mean userland "is broken", this would
only be the case if FUSE_DAX_FMAP was advertised but not actually
supported.
If DAX were removed from the kernel (unlikely, but stick with me) this
would be equivalent to permanently changing CONFIG_FUSE_DAX to always
off, and there would be no squabbles over whether that particular
change broke userland (there would be much strife over removing dax).
While not a deprecation method, this is what capability bits are
designed for. Same as cpuid capability bits - just because the bit is
there doesn't mean a processor is required to support it in perpetuity.
They're only required to support it if the bit is turned on.
---
I think the focus here needs to be on whether this interface ACTUALLY
needs to be more generic - and whether that is actually FEASIBLE.
It's not like this is a new problem - and there are real design reasons
why John chose this route.
The additional overhead is not trivial for FAMFS - FAMFS is not doing
i/o. He already has data showing fuse caused a performance hit due to
overhead on open - his concern of overhead on fault being catastrophic
is grounded in data.
For others it's an age old problem of self-describing protocols (parsing
vs giant inflexible binary blobs, pick your poison). It's extremely
unlikely we will find a one-size-fits-all solution that doesn't
eventually run right back into this same problem.
I worry that this discussion is going to turn towards implementing a
solution grounded in parsing arbitrary formats and how to store them,
and that is completely detached from why FAMFS went this route in the
first place.
I question whether the actual issue here lies in the interface APPEARING
more general purpose than it actually is - and therefore inviting
attempts to over-genericize it.
Is there a world here where this is solved by a name change and a
capability bit? I think so.
~Gregory
^ permalink raw reply
* [PATCH v4 0/8] Add support for ZTE zx297520v3
From: Stefan Dösinger @ 2026-04-16 20:19 UTC (permalink / raw)
To: Jonathan Corbet, Shuah Khan, Russell King, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Arnd Bergmann,
Krzysztof Kozlowski, Alexandre Belloni, Linus Walleij,
Drew Fustini, Greg Kroah-Hartman, Jiri Slaby
Cc: linux-doc, linux-kernel, linux-arm-kernel, devicetree, soc,
linux-serial, Stefan Dösinger
Hi,
This is a follow-up on my RFC patches from January [0] for ZTE's
zx297520v3 chipset. This chipset is popular in cheap LTE-to-wifi routers
sold in developing countries. My goal is to run OpenWRT on them. I made
more progress in more work on this SoC and it is time to get serious
about code review and upstreaming.
Since my version in January I managed to get more hardware running: SPI,
I2C, PMIC with real time clock and voltage regulators, Watchdog. LTE is
not working yet, but I am able to start the coprocessor that handles it
and talk to it via mailbox + shared memory. Wifi is working on a few
more devices. Since WiFi, USB and Ethernet are working, the devices can
have actual use with OpenWRT even without LTE.
Another hacker created a free software program to talk to the USB loader
[1] and boot U-Boot and Linux without modifying the on disk files. At
the moment it needs a proprietary blob, so my documentation is
emphasising booting with the on-device U-Boot.
This patchset here is mostly unmodified from the version I sent in
January. It is the bare minimum to get an interactive shell working on
the UART. Future patches can be found on my git repository [2] for those
curious to peek ahead. The first 30 patches are in reasonable shape, but
the further you go the more cleanup is necessary. I expect all of the
patches go require a few rounds of feedback though.
My plan for upstreaming is largly this:
1) This bare minimum boot patchset
2) Add clock and pinctrl drivers
3) Add standard hardware to the device tree
4) Add zx29 specific drivers one by one: Watchdog, spi, i2c, DMA, PMIC,
battery
5) SDIO backend for rtl8xxxu
6) rproc, mailbox and rpmsg
I am willing to maintain support for the SoC within reason. My patches
add myself as maintainer. This is a hobby project for me though, keep
that in mind if you want to ship a commercial product with these SoCs
and upstreaming Linux.
Cheers,
Stefan
0: https://lists.infradead.org/pipermail/linux-arm-kernel/2026-January/1099306.html
1: https://github.com/zx297520v3-mainline/zx297520v3-loader
2: https://gitlab.com/stefandoesinger/zx297520-kernel/
Patch changelog:
v4: rename zx29.yaml to zte.yaml and add board enums
v3: Remove [RFC] tag, add defconfig
v2: checkpatch.pl fixes
Signed-off-by: Stefan Dösinger <stefandoesinger@gmail.com>
---
Stefan Dösinger (8):
ARM: zte: Add zx297520v3 platform support
dt-bindings: arm: Add zx297520v3 board binding
ARM: dts: Add D-Link DWR-932M support
ARM: zte: Add support for zx29 low level debug
ARM: dts: Add an armv7 timer for zx297520v3
ARM: zte: Bring back zx29 UART support
ARM: dts: Declare UART1 on zx297520v3 boards
ARM: defconfig: Add a zx29 defconfig file
Documentation/arch/arm/zte/zx297520v3.rst | 158 +++++++++++++++++++++++++
Documentation/devicetree/bindings/arm/zte.yaml | 25 ++++
MAINTAINERS | 6 +
arch/arm/Kconfig | 2 +
arch/arm/Kconfig.debug | 12 ++
arch/arm/Makefile | 1 +
arch/arm/boot/dts/Makefile | 1 +
arch/arm/boot/dts/zte/Makefile | 3 +
arch/arm/boot/dts/zte/dlink-dwr-932m.dts | 21 ++++
arch/arm/boot/dts/zte/zx297520v3.dtsi | 83 +++++++++++++
arch/arm/configs/zx29_defconfig | 90 ++++++++++++++
arch/arm/include/debug/pl01x.S | 7 ++
arch/arm/mach-zte/Kconfig | 24 ++++
arch/arm/mach-zte/Makefile | 2 +
arch/arm/mach-zte/zx297520v3.c | 19 +++
drivers/tty/serial/amba-pl011.c | 37 ++++++
include/linux/amba/bus.h | 6 +
17 files changed, 497 insertions(+)
---
base-commit: 028ef9c96e96197026887c0f092424679298aae8
change-id: 20260416-send-5c08e095e5c9
Best regards,
--
Stefan Dösinger <stefandoesinger@gmail.com>
^ permalink raw reply
* [PATCH v4 1/8] ARM: zte: Add zx297520v3 platform support
From: Stefan Dösinger @ 2026-04-16 20:19 UTC (permalink / raw)
To: Jonathan Corbet, Shuah Khan, Russell King, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Arnd Bergmann,
Krzysztof Kozlowski, Alexandre Belloni, Linus Walleij,
Drew Fustini, Greg Kroah-Hartman, Jiri Slaby
Cc: linux-doc, linux-kernel, linux-arm-kernel, devicetree, soc,
linux-serial, Stefan Dösinger
In-Reply-To: <20260416-send-v4-0-e19d02b944ec@gmail.com>
This SoC is used in low end LTE-to-WiFi routers, for example some D-Link
DWR 932 revisions, ZTE K10, ZLT S10 4G, but also models that are branded
and sold by ISPs themselves. They are widespread in Africa, China,
Russia and Eastern Europe.
This SoC is a relative of the zx296702 and zx296718 that had some
upstream support until commit 89d4f98ae90d ("ARM: remove zte zx
platform"). My eventual goal is to enable OpenWRT to run on these
devices.
Signed-off-by: Stefan Dösinger <stefandoesinger@gmail.com>
---
Documentation/arch/arm/zte/zx297520v3.rst | 158 ++++++++++++++++++++++++++++++
MAINTAINERS | 4 +
arch/arm/Kconfig | 2 +
arch/arm/Makefile | 1 +
arch/arm/mach-zte/Kconfig | 24 +++++
arch/arm/mach-zte/Makefile | 2 +
arch/arm/mach-zte/zx297520v3.c | 19 ++++
7 files changed, 210 insertions(+)
diff --git a/Documentation/arch/arm/zte/zx297520v3.rst b/Documentation/arch/arm/zte/zx297520v3.rst
new file mode 100644
index 000000000000..a0f25ade0a3d
--- /dev/null
+++ b/Documentation/arch/arm/zte/zx297520v3.rst
@@ -0,0 +1,158 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====================================
+Booting Linux on ZTE zx297520v3 SoCs
+====================================
+
+...............................................................................
+
+Author: Stefan Dösinger
+
+Date : 27 Jan 2026
+
+1. Hardware description
+---------------------------
+Zx297520v3 SoCs use a 64 bit capable Cortex-A53 CPU and GICv3, although they
+run in aarch32 mode only. The CPU has support EL3, but no hypervisor (EL2) and
+it seems to lack VFP and NEON.
+
+The SoC is used in a number of cheap LTE to Wifi routers, both battery powered
+MiFis and stationary CPEs. In addition to the CPU these devices usually have
+64 MB Ram (although some is shared with the LTE chip), 128 MB NAND flash, an
+SDIO connected RTL8192-type Wifi chip limited to 2.4 ghz operation, USB 2,
+and buttons. Devices with as low as 32 MB or as high as 128 MB ram exist, as
+do devices with 8 or 16 MB of NOR flash.
+
+Some devices, especially the stationary ones, have 100 mbit Ethernet and an
+Ethernet switch.
+
+Usually the devices have LEDs for status indication, although some have SPI or
+i2c connected displays
+
+Some have an SD card slot. If it exists, it is a better choice for the root
+file system because it easily outperforms the built-in NAND.
+
+The LTE interface runs on a separate DSP called ZSP880. It is probably derived
+from LSI ZSPs and has an undocumented instruction set. The ZSP communicates
+with the main CPU via SRAM and DRAM and a mailbox hardware that can generate
+IRQs on either ends.
+
+There is also a Cortex M0 CPU, which is responsible for early HW initialization
+and starting the Cortex A53 CPU. It does not have any essential purpose once
+U-Boot is started. A SRAM-Based handover protocol exists to run custom code on
+this CPU.
+
+2. Booting via USB
+---------------------------
+
+The Boot ROM has support for booting custom code via USB. This mode can be
+entered by connecting a Boot PIN to GND or by modifying the third byte on NAND
+(set it to anything other than 0x5A aka 'Z'). A free software tool to start
+custom uboot and kernels can be found here:
+
+https://github.com/zx297520v3-mainline/zx297520v3-loader
+
+If USB download mode is entered but no boot commands are sent through USB, the
+device will proceed to boot normally after a few seconds. It is therefore
+possible to enable USB boot permanently and still leave the default boot files
+in place.
+
+3. Building for built-in U-Boot
+---------------------------
+The devices come with an ancient U-Boot that loads legacy uImages from NAND and
+boots them without a chance for the user to interrupt. The images are stored in
+files ap_cpuap.bin and ap_recovery.bin on a jffs2 partition named imagefs,
+usually mtd4. A file named "fotaflag" switches between the two modes.
+
+In addition to the uImage header, those files have a 384 byte signature header,
+which is used for authenticating the images on some devices. Most devices have
+this authentication disabled and it is enough to pad the uImage files with 384
+zero bytes.
+
+Builtin U-Boot also poorly sets up the CPU. Read the next section for details
+on this. It has no support for loading DTBs, so CONFIG_ARM_APPENDED_DTB is
+needed.
+
+So to build an image that boots from NAND the following steps are necessary:
+
+1) Patch the assembly code from section 3 into arch/arm/kernel/head.S.
+2) make zx29_defconfig
+3) make [-j x]
+4) cat arch/arm/boot/zImage arch/arm/boot/dts/zte/[device].dtb > kernel+dtb
+5) mkimage -A arm -O linux -T kernel -C none -a 0x20008000 -d kernel+dtb uimg
+6) dd if=/dev/zero bs=1 count=384 of=ap_recovery.bin
+7) cat uimg >> ap_recovery.bin
+8) Place this file onto imagefs on the device. Delete ap_cpuap.bin if the
+free space is not enough.
+9) Create the file fotaflag: echo -n FOTA-RECOVERY > fotaflag
+
+For development, booting ap_recovery.bin is recommended because the normal boot
+mode arms the watchdog before starting the kernel.
+
+4. CPU and GIC Setup
+---------------------------
+
+Generally CPU and GICv3 need to be set up according to the requirements spelled
+out in Documentation/arch/arm64/booting.rst. For zx297520v3 this means:
+
+1. GICD_CTLR.DS=1 to disable GIC security
+2. Enable access to ICC_SRE
+3. Disable trapping IRQs into monitor mode
+4. Configure EL2 and below to run in insecure mode.
+5. Configure timer PPIs to active-low.
+
+The kernel sources provided by ZTE do not boot either (interrupts do not work
+at all). They are incomplete in other aspects too, so it is assumed that there
+is some workaround similar to the one described in this document somewhere in
+the binary blobs.
+
+The assembly code below is given as an example of how to achieve this:
+
+```
+#include <linux/irqchip/arm-gic-v3.h>
+#include <asm/assembler.h>
+#include <asm/cp15.h>
+
+@ This allows EL1 to handle ints hat are normally handled by EL2/3.
+ldr r3, =0xf2000000
+ldr r4, =#(GICD_CTLR_ARE_NS | GICD_CTLR_DS)
+str r4, [r3]
+
+cps #MON_MODE
+
+@ Work in non-secure physical address space: SCR_EL3.NS = 1. At least the UART
+@ seems to respond only to non-secure addresses. I have taken insipiration from
+@ Raspberry pi's armstub7.S here.
+@
+@ ARM docs say modify this bit in monitor mode only...
+mov r3, #0x131 @ non-secure, Make F, A bits in CPSR writeable
+ @ Allow hypervisor call.
+mcr p15, 0, r3, c1, c1, 0
+
+@ AP_PPI_MODE_REG: Configure timer PPIs (10, 11, 13, 14) to active-low.
+ldr r3, =0xF22020a8
+ldr r4, =0x50
+str r4, [r3]
+ldr r3, =0xF22020ac
+ldr r4, =0x14
+str r4, [r3]
+
+@ Enable EL2 access to ICC_SRE (bit 3, ICC_SRE_EL3.Enable). Enable system reg
+@ access to GICv3 registers (bit 0, ICC_SRE_EL3.SRE) for EL1 and EL3.
+mrc p15, 6, r3, c12, c12, 5 @ ICC_SRE_EL3
+orr r3, #0x9 @ FIXME: No defines for SRE_EL3 values?
+mcr p15, 6, r3, c12, c12, 5
+mrc p15, 0, r3, c12, c12, 5 @ ICC_SRE_EL1
+orr r3, #(ICC_SRE_EL1_SRE)
+mcr p15, 0, r3, c12, c12, 5
+
+@ Like ICC_SRE_EL3, enable EL1 access to ICC_SRE and system register access
+@ for EL2.
+mrc p15, 4, r3, c12, c9, 5 @ ICC_SRE_EL2 aka ICC_HSRE
+orr r3, r3, #(ICC_SRE_EL2_ENABLE | ICC_SRE_EL2_SRE)
+mcr p15, 4, r3, c12, c9, 5
+isb
+
+@ Back to SVC mode. TODO: Doesn't safe_svcmode_maskall do this for us anyway?
+cps #SVC_MODE
+```
diff --git a/MAINTAINERS b/MAINTAINERS
index d1cc0e12fe1f..974d7a98956a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -29200,6 +29200,10 @@ F: include/linux/zswap.h
F: mm/zswap.c
F: tools/testing/selftests/cgroup/test_zswap.c
+ZX29
+M: Stefan Dösinger <stefandoesinger@gmail.com>
+F: arch/arm/mach-zte/
+
SENARYTECH AUDIO CODEC DRIVER
M: bo liu <bo.liu@senarytech.com>
S: Maintained
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index ec33376f8e2b..4217ed704e48 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -464,6 +464,8 @@ source "arch/arm/mach-versatile/Kconfig"
source "arch/arm/mach-vt8500/Kconfig"
+source "arch/arm/mach-zte/Kconfig"
+
source "arch/arm/mach-zynq/Kconfig"
# ARMv7-M architecture
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index b7de4b6b284c..573813ef5e77 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -223,6 +223,7 @@ machine-$(CONFIG_ARCH_SUNXI) += sunxi
machine-$(CONFIG_ARCH_TEGRA) += tegra
machine-$(CONFIG_ARCH_U8500) += ux500
machine-$(CONFIG_ARCH_VT8500) += vt8500
+machine-$(CONFIG_ARCH_ZTE) += zte
machine-$(CONFIG_ARCH_ZYNQ) += zynq
machine-$(CONFIG_PLAT_VERSATILE) += versatile
machine-$(CONFIG_PLAT_SPEAR) += spear
diff --git a/arch/arm/mach-zte/Kconfig b/arch/arm/mach-zte/Kconfig
new file mode 100644
index 000000000000..24699256863b
--- /dev/null
+++ b/arch/arm/mach-zte/Kconfig
@@ -0,0 +1,24 @@
+# SPDX-License-Identifier: GPL-2.0
+menuconfig ARCH_ZTE
+ bool "ZTE zx family"
+ depends on ARCH_MULTI_V7
+ help
+ Support for ZTE zx-based family of processors.
+
+if ARCH_ZTE
+
+config SOC_ZX297520V3
+ default y if ARCH_ZTE
+ bool "ZX297520v3"
+ select ARM_GIC_V3
+ select ARM_AMBA
+ select HAVE_ARM_ARCH_TIMER
+ select PM_GENERIC_DOMAINS if PM
+ help
+ Support for ZTE zx297520v3 SoC. It a single core SoC used in cheap LTE to WiFi routers.
+ These devices can be Identified by the occurrence of the string "zx297520v3" in the boot
+ output and /proc/cpuinfo of their stock firmware.
+
+ Please read Documentation/arch/arm/zte/zx297520v3.rst on how to boot the kernel.
+
+endif
diff --git a/arch/arm/mach-zte/Makefile b/arch/arm/mach-zte/Makefile
new file mode 100644
index 000000000000..1bfe4fddd6af
--- /dev/null
+++ b/arch/arm/mach-zte/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_SOC_ZX297520V3) += zx297520v3.o
diff --git a/arch/arm/mach-zte/zx297520v3.c b/arch/arm/mach-zte/zx297520v3.c
new file mode 100644
index 000000000000..c11c7e836f91
--- /dev/null
+++ b/arch/arm/mach-zte/zx297520v3.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2026 Stefan Dösinger
+ */
+
+#include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+
+static const char *const zx297520v3_dt_compat[] __initconst = {
+ "zte,zx297520v3",
+ NULL,
+};
+
+DT_MACHINE_START(ZX, "ZTE zx297520v3 (Device Tree)")
+ .dt_compat = zx297520v3_dt_compat,
+MACHINE_END
--
2.52.0
^ permalink raw reply related
* [PATCH v4 2/8] dt-bindings: arm: Add zx297520v3 board binding
From: Stefan Dösinger @ 2026-04-16 20:19 UTC (permalink / raw)
To: Jonathan Corbet, Shuah Khan, Russell King, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Arnd Bergmann,
Krzysztof Kozlowski, Alexandre Belloni, Linus Walleij,
Drew Fustini, Greg Kroah-Hartman, Jiri Slaby
Cc: linux-doc, linux-kernel, linux-arm-kernel, devicetree, soc,
linux-serial, Stefan Dösinger
In-Reply-To: <20260416-send-v4-0-e19d02b944ec@gmail.com>
Add a compatible for boards based on the ZTE zx297520v3 SoC.
Signed-off-by: Stefan Dösinger <stefandoesinger@gmail.com>
---
The list of devices is the devices I have access to for testing. There
are many more devices based on this board and it is not always easy to
identify them. Often they are sold without any branding ("4G home
router") or with mobile carrier branding.
---
Documentation/devicetree/bindings/arm/zte.yaml | 25 +++++++++++++++++++++++++
MAINTAINERS | 1 +
2 files changed, 26 insertions(+)
diff --git a/Documentation/devicetree/bindings/arm/zte.yaml b/Documentation/devicetree/bindings/arm/zte.yaml
new file mode 100644
index 000000000000..6eba09edd2c5
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/zte.yaml
@@ -0,0 +1,25 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/arm/zte.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ZTE zx29
+
+maintainers:
+ - Stefan Dösinger <stefandoesinger@gmail.com>
+
+properties:
+ $nodename:
+ const: "/"
+ compatible:
+ oneOf:
+ - items:
+ - enum:
+ - dlink,dwr932m
+ - hgsd,r310
+ - tecno,tr118
+ - zte,k10
+ - const: zte,zx297520v3
+
+additionalProperties: true
diff --git a/MAINTAINERS b/MAINTAINERS
index 974d7a98956a..bcade90ca14e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -29202,6 +29202,7 @@ F: tools/testing/selftests/cgroup/test_zswap.c
ZX29
M: Stefan Dösinger <stefandoesinger@gmail.com>
+F: Documentation/devicetree/bindings/arm/zte.yaml
F: arch/arm/mach-zte/
SENARYTECH AUDIO CODEC DRIVER
--
2.52.0
^ permalink raw reply related
* [PATCH v4 3/8] ARM: dts: Add D-Link DWR-932M support
From: Stefan Dösinger @ 2026-04-16 20:19 UTC (permalink / raw)
To: Jonathan Corbet, Shuah Khan, Russell King, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Arnd Bergmann,
Krzysztof Kozlowski, Alexandre Belloni, Linus Walleij,
Drew Fustini, Greg Kroah-Hartman, Jiri Slaby
Cc: linux-doc, linux-kernel, linux-arm-kernel, devicetree, soc,
linux-serial, Stefan Dösinger
In-Reply-To: <20260416-send-v4-0-e19d02b944ec@gmail.com>
This adds DT bindings for zx297520v3 and one board that consumes it.
Signed-off-by: Stefan Dösinger <stefandoesinger@gmail.com>
---
MAINTAINERS | 1 +
arch/arm/boot/dts/Makefile | 1 +
arch/arm/boot/dts/zte/Makefile | 3 +++
arch/arm/boot/dts/zte/dlink-dwr-932m.dts | 21 ++++++++++++++++++
arch/arm/boot/dts/zte/zx297520v3.dtsi | 37 ++++++++++++++++++++++++++++++++
5 files changed, 63 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index bcade90ca14e..f7ca0d478e81 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -29203,6 +29203,7 @@ F: tools/testing/selftests/cgroup/test_zswap.c
ZX29
M: Stefan Dösinger <stefandoesinger@gmail.com>
F: Documentation/devicetree/bindings/arm/zte.yaml
+F: arch/arm/boot/dts/zte
F: arch/arm/mach-zte/
SENARYTECH AUDIO CODEC DRIVER
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index efe38eb25301..28fba538d552 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -39,3 +39,4 @@ subdir-y += unisoc
subdir-y += vt8500
subdir-y += xen
subdir-y += xilinx
+subdir-y += zte
diff --git a/arch/arm/boot/dts/zte/Makefile b/arch/arm/boot/dts/zte/Makefile
new file mode 100644
index 000000000000..416c24a489cd
--- /dev/null
+++ b/arch/arm/boot/dts/zte/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+dtb-$(CONFIG_SOC_ZX297520V3) += \
+ dlink-dwr-932m.dtb
diff --git a/arch/arm/boot/dts/zte/dlink-dwr-932m.dts b/arch/arm/boot/dts/zte/dlink-dwr-932m.dts
new file mode 100644
index 000000000000..7b2a26aaaecb
--- /dev/null
+++ b/arch/arm/boot/dts/zte/dlink-dwr-932m.dts
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * D-Link DWR-932M Board
+ *
+ * (C) Copyright 2026 Stefan Dösinger
+ *
+ */
+
+/dts-v1/;
+
+#include "zx297520v3.dtsi"
+
+/ {
+ model = "D-Link DWR-932M";
+ compatible = "dlink,dwr932m", "zte,zx297520v3";
+
+ memory@20000000 {
+ device_type = "memory";
+ reg = <0x20000000 0x04000000>;
+ };
+};
diff --git a/arch/arm/boot/dts/zte/zx297520v3.dtsi b/arch/arm/boot/dts/zte/zx297520v3.dtsi
new file mode 100644
index 000000000000..d6c71d52b26c
--- /dev/null
+++ b/arch/arm/boot/dts/zte/zx297520v3.dtsi
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a53";
+ reg = <0>;
+ };
+ };
+
+ soc {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "simple-bus";
+ interrupt-parent = <&gic>;
+ ranges;
+
+ gic: interrupt-controller@f2000000 {
+ compatible = "arm,gic-v3";
+ interrupt-controller;
+ #interrupt-cells = <3>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ reg = <0xf2000000 0x10000>,
+ <0xf2040000 0x20000>;
+ };
+ };
+};
--
2.52.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox