* Re: [PATCH 2/3] init: use static buffers for bootconfig extra command line
From: Masami Hiramatsu @ 2026-04-17 1:44 UTC (permalink / raw)
To: Breno Leitao
Cc: Andrew Morton, oss, paulmck, linux-trace-kernel, linux-kernel,
kernel-team
In-Reply-To: <20260415-bootconfig_earlier-v1-2-cf160175de5e@debian.org>
On Wed, 15 Apr 2026 03:51:11 -0700
Breno Leitao <leitao@debian.org> wrote:
> Replace memblock_alloc/memblock_free in xbc_make_cmdline() with
> static __initdata buffers. This removes the last memblock dependency
> from the bootconfig loading path, completing the prerequisite for
> running bootconfig parsing before memblock is available.
>
> Signed-off-by: Breno Leitao <leitao@debian.org>
> ---
> init/main.c | 24 ++++++++++++------------
> 1 file changed, 12 insertions(+), 12 deletions(-)
>
> diff --git a/init/main.c b/init/main.c
> index 96f93bb06c490..b9feca55e01f9 100644
> --- a/init/main.c
> +++ b/init/main.c
> @@ -369,11 +369,18 @@ static int __init xbc_snprint_cmdline(char *buf, size_t size,
> }
> #undef rest
>
> +/*
> + * Static buffers for bootconfig-generated command line parameters.
> + * Two separate buffers are needed because both "kernel" and "init"
> + * parameters are stored simultaneously.
> + */
> +static char extra_cmdline_buf[COMMAND_LINE_SIZE] __initdata;
> +static char extra_initargs_buf[COMMAND_LINE_SIZE] __initdata;
This is not good to me, since bootconfig supports bigger config file
than COMMAND_LINE_SIZE. Even if we limits the size for embedded
bootconfig file, it should depends on CONFIG_BOOT_CONFIG_EMBED.
Please use XBC_DATA_MAX instead of COMMAND_LINE_SIZE, or calculate
expected data length when compiling kernel.
But if we can do it, should we continue using bootconfig? I mean
it is easy to make a tool (or add a feature in tools/bootconfig)
which converts bootconfig file to command line string and embeds
it in the kernel. Hmm.
Thanks,
> +
> /* Make an extra command line under given key word */
> -static char * __init xbc_make_cmdline(const char *key)
> +static char * __init xbc_make_cmdline(const char *key, char *new_cmdline)
> {
> struct xbc_node *root;
> - char *new_cmdline;
> int ret, len = 0;
>
> root = xbc_find_node(key);
> @@ -382,19 +389,12 @@ static char * __init xbc_make_cmdline(const char *key)
>
> /* Count required buffer size */
> len = xbc_snprint_cmdline(NULL, 0, root);
> - if (len <= 0)
> + if (len <= 0 || len >= COMMAND_LINE_SIZE)
> return NULL;
>
> - new_cmdline = memblock_alloc(len + 1, SMP_CACHE_BYTES);
> - if (!new_cmdline) {
> - pr_err("Failed to allocate memory for extra kernel cmdline.\n");
> - return NULL;
> - }
> -
> ret = xbc_snprint_cmdline(new_cmdline, len + 1, root);
> if (ret < 0 || ret > len) {
> pr_err("Failed to print extra kernel cmdline.\n");
> - memblock_free(new_cmdline, len + 1);
> return NULL;
> }
>
> @@ -467,9 +467,9 @@ static void __init setup_boot_config(void)
> xbc_get_info(&ret, NULL);
> pr_info("Load bootconfig: %ld bytes %d nodes\n", (long)size, ret);
> /* keys starting with "kernel." are passed via cmdline */
> - extra_command_line = xbc_make_cmdline("kernel");
> + extra_command_line = xbc_make_cmdline("kernel", extra_cmdline_buf);
> /* Also, "init." keys are init arguments */
> - extra_init_args = xbc_make_cmdline("init");
> + extra_init_args = xbc_make_cmdline("init", extra_initargs_buf);
> }
> return;
> }
>
> --
> 2.52.0
>
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply
* Re: [PATCH v5 6/7] locking: Factor out __queued_read_unlock()/__queued_write_unlock()
From: Paul E. McKenney @ 2026-04-16 23:55 UTC (permalink / raw)
To: Dmitry Ilvokhin
Cc: Peter Zijlstra, Ingo Molnar, Will Deacon, Boqun Feng, Waiman Long,
Thomas Bogendoerfer, Juergen Gross, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Thomas Gleixner,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Arnd Bergmann,
Dennis Zhou, Tejun Heo, Christoph Lameter, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, linux-kernel, linux-mips,
virtualization, linux-arch, linux-mm, linux-trace-kernel,
kernel-team
In-Reply-To: <eabc9de3347ca042eb0593c9b81c8e48254a4874.1776350944.git.d@ilvokhin.com>
On Thu, Apr 16, 2026 at 03:05:12PM +0000, Dmitry Ilvokhin wrote:
> This is a preparatory refactoring for the next commit, which adds
> contended_release tracepoint instrumentation and needs to call the
> unlock from both traced and non-traced paths.
>
> No functional change.
>
> Signed-off-by: Dmitry Ilvokhin <d@ilvokhin.com>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
> ---
> include/asm-generic/qrwlock.h | 20 +++++++++++++++-----
> 1 file changed, 15 insertions(+), 5 deletions(-)
>
> diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h
> index 75b8f4601b28..4b627bafba8b 100644
> --- a/include/asm-generic/qrwlock.h
> +++ b/include/asm-generic/qrwlock.h
> @@ -101,16 +101,26 @@ static inline void queued_write_lock(struct qrwlock *lock)
> queued_write_lock_slowpath(lock);
> }
>
> +static __always_inline void __queued_read_unlock(struct qrwlock *lock)
> +{
> + /*
> + * Atomically decrement the reader count
> + */
> + (void)atomic_sub_return_release(_QR_BIAS, &lock->cnts);
> +}
> +
> /**
> * queued_read_unlock - release read lock of a queued rwlock
> * @lock : Pointer to queued rwlock structure
> */
> static inline void queued_read_unlock(struct qrwlock *lock)
> {
> - /*
> - * Atomically decrement the reader count
> - */
> - (void)atomic_sub_return_release(_QR_BIAS, &lock->cnts);
> + __queued_read_unlock(lock);
> +}
> +
> +static __always_inline void __queued_write_unlock(struct qrwlock *lock)
> +{
> + smp_store_release(&lock->wlocked, 0);
> }
>
> /**
> @@ -119,7 +129,7 @@ static inline void queued_read_unlock(struct qrwlock *lock)
> */
> static inline void queued_write_unlock(struct qrwlock *lock)
> {
> - smp_store_release(&lock->wlocked, 0);
> + __queued_write_unlock(lock);
> }
>
> /**
> --
> 2.52.0
>
^ permalink raw reply
* Re: [PATCH v5 5/7] locking: Add contended_release tracepoint to qspinlock
From: Paul E. McKenney @ 2026-04-16 23:54 UTC (permalink / raw)
To: Dmitry Ilvokhin
Cc: Peter Zijlstra, Ingo Molnar, Will Deacon, Boqun Feng, Waiman Long,
Thomas Bogendoerfer, Juergen Gross, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Thomas Gleixner,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Arnd Bergmann,
Dennis Zhou, Tejun Heo, Christoph Lameter, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, linux-kernel, linux-mips,
virtualization, linux-arch, linux-mm, linux-trace-kernel,
kernel-team
In-Reply-To: <af285ffefa3fa2f73b73a39e9f06fb176009e047.1776350944.git.d@ilvokhin.com>
On Thu, Apr 16, 2026 at 03:05:11PM +0000, Dmitry Ilvokhin wrote:
> Use the arch-overridable queued_spin_release(), introduced in the
> previous commit, to ensure the tracepoint works correctly across all
> architectures, including those with custom unlock implementations (e.g.
> x86 paravirt).
>
> When the tracepoint is disabled, the only addition to the hot path is a
> single NOP instruction (the static branch). When enabled, the contention
> check, trace call, and unlock are combined in an out-of-line function to
> minimize hot path impact, avoiding the compiler needing to preserve the
> lock pointer in a callee-saved register across the trace call.
>
> Binary size impact (x86_64, defconfig):
> uninlined unlock (common case): +680 bytes (+0.00%)
> inlined unlock (worst case): +83659 bytes (+0.21%)
>
> The inlined unlock case could not be achieved through Kconfig options on
> x86_64 as PREEMPT_BUILD unconditionally selects UNINLINE_SPIN_UNLOCK on
> x86_64. The UNINLINE_SPIN_UNLOCK guards were manually inverted to force
> inline the unlock path and estimate the worst case binary size increase.
>
> In practice, configurations with UNINLINE_SPIN_UNLOCK=n have already
> opted against binary size optimization, so the inlined worst case is
> unlikely to be a concern.
>
> Architectures with fully custom qspinlock implementations (e.g.
> PowerPC) are not covered by this change.
>
> Signed-off-by: Dmitry Ilvokhin <d@ilvokhin.com>
Much nicer split out!
Acked-by: Paul E. McKenney <paulmck@kernel.org>
> ---
> include/asm-generic/qspinlock.h | 18 ++++++++++++++++++
> kernel/locking/qspinlock.c | 8 ++++++++
> 2 files changed, 26 insertions(+)
>
> diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
> index df76f34645a0..915a4c2777f6 100644
> --- a/include/asm-generic/qspinlock.h
> +++ b/include/asm-generic/qspinlock.h
> @@ -41,6 +41,7 @@
>
> #include <asm-generic/qspinlock_types.h>
> #include <linux/atomic.h>
> +#include <linux/tracepoint-defs.h>
>
> #ifndef queued_spin_is_locked
> /**
> @@ -129,12 +130,29 @@ static __always_inline void queued_spin_release(struct qspinlock *lock)
> }
> #endif
>
> +DECLARE_TRACEPOINT(contended_release);
> +
> +extern void queued_spin_release_traced(struct qspinlock *lock);
> +
> /**
> * queued_spin_unlock - unlock a queued spinlock
> * @lock : Pointer to queued spinlock structure
> + *
> + * Generic tracing wrapper around the arch-overridable
> + * queued_spin_release().
> */
> static __always_inline void queued_spin_unlock(struct qspinlock *lock)
> {
> + /*
> + * Trace and release are combined in queued_spin_release_traced() so
> + * the compiler does not need to preserve the lock pointer across the
> + * function call, avoiding callee-saved register save/restore on the
> + * hot path.
> + */
> + if (tracepoint_enabled(contended_release)) {
> + queued_spin_release_traced(lock);
> + return;
> + }
> queued_spin_release(lock);
> }
>
> diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
> index af8d122bb649..c72610980ec7 100644
> --- a/kernel/locking/qspinlock.c
> +++ b/kernel/locking/qspinlock.c
> @@ -104,6 +104,14 @@ static __always_inline u32 __pv_wait_head_or_lock(struct qspinlock *lock,
> #define queued_spin_lock_slowpath native_queued_spin_lock_slowpath
> #endif
>
> +void __lockfunc queued_spin_release_traced(struct qspinlock *lock)
> +{
> + if (queued_spin_is_contended(lock))
> + trace_contended_release(lock);
> + queued_spin_release(lock);
> +}
> +EXPORT_SYMBOL(queued_spin_release_traced);
> +
> #endif /* _GEN_PV_LOCK_SLOWPATH */
>
> /**
> --
> 2.52.0
>
^ permalink raw reply
* Re: [PATCH v2 07/28] fsnotify: add FSNOTIFY_EVENT_RENAME data type
From: Jeff Layton @ 2026-04-16 20:52 UTC (permalink / raw)
To: Amir Goldstein
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: <CAOQ4uxg2jHxCi77A1DGtopjZHsTNg4etdboW2GjL85N3uc_KqQ@mail.gmail.com>
On Thu, 2026-04-16 at 21:24 +0200, Amir Goldstein wrote:
> 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.
>
Yeah, it's not very useful, but the protocol requires it. Unfortunately
RFC5661 was written before anyone had made a real implementation of
directory delegations. If we were rewriting it today, we'd probably
make that info optional.
> 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
> >
--
Jeff Layton <jlayton@kernel.org>
^ permalink raw reply
* Re: [LSF/MM/BPF TOPIC][RFC PATCH v4 00/27] Private Memory Nodes (w/ Compressed RAM)
From: Gregory Price @ 2026-04-16 20:23 UTC (permalink / raw)
To: Frank van der Linden
Cc: David Hildenbrand (Arm), lsf-pc, linux-kernel, linux-cxl, cgroups,
linux-mm, linux-trace-kernel, damon, kernel-team, gregkh, rafael,
dakr, dave, jonathan.cameron, dave.jiang, alison.schofield,
vishal.l.verma, ira.weiny, dan.j.williams, longman, akpm,
lorenzo.stoakes, Liam.Howlett, vbabka, rppt, surenb, mhocko,
osalvador, ziy, matthew.brost, joshua.hahnjy, rakie.kim,
byungchul, ying.huang, apopple, axelrasmussen, yuanchu, weixugc,
yury.norov, linux, mhiramat, mathieu.desnoyers, tj, hannes,
mkoutny, jackmanb, sj, baolin.wang, npache, ryan.roberts,
dev.jain, baohua, lance.yang, muchun.song, xu.xin16,
chengming.zhou, jannh, linmiaohe, nao.horiguchi, pfalcato,
rientjes, shakeel.butt, riel, harry.yoo, cl, roman.gushchin,
chrisl, kasong, shikemeng, nphamcs, bhe, zhengqi.arch,
terry.bowman
In-Reply-To: <CAPTztWajm_JLpp9BjRcX=h72r25ELrXeGkOXVachybBxLJGS=g@mail.gmail.com>
On Wed, Apr 15, 2026 at 12:47:50PM -0700, Frank van der Linden wrote:
> >
> > > I also have some questions about longterm pinnings, but that's better
> > > discussed in person :)
> > >
> >
> > The longterm pin extention came from auditing existing zone_device
> > filters.
> >
> > tl;dr: informative mechanism - but it probably should be dropped,
> > it makes no sense (it's device memory, pinnings mean nothing?).
> >
> >
... snip ... stitching together some context here
>
> So, looking at having some properties set at the node level makes
> sense to me even in the non-device case. But perhaps that is out of
> scope for the initial discussion.
I think there's an argument burried in this observation (useful for
non-device case) that suggests there could be a world where longterm
pinning on this memory makes sense.
But it doesn't need to be introduced from the start, and it's a 5-10
line change to add it in later, so I think it will get trimmed unless
there's a user out there actively experimenting with it.
~Gregory
^ 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: [RFC PATCH 1/2] kernel/notifier: replace single-linked list with double-linked list for reverse traversal
From: David Laight @ 2026-04-16 19:15 UTC (permalink / raw)
To: Petr Mladek
Cc: chensong_2000, rafael, lenb, mturquette, sboyd, viresh.kumar, agk,
snitzer, mpatocka, bmarzins, song, yukuai, linan122, jason.wessel,
danielt, dianders, horms, davem, edumazet, kuba, pabeni, paulmck,
frederic, mcgrof, petr.pavlu, da.gomez, samitolvanen, atomlin,
jpoimboe, jikos, mbenes, joe.lawrence, rostedt, mhiramat,
mark.rutland, mathieu.desnoyers, linux-modules, linux-kernel,
linux-trace-kernel, linux-acpi, linux-clk, linux-pm,
live-patching, dm-devel, linux-raid, kgdb-bugreport, netdev
In-Reply-To: <aeD4H8P1DiPQoM8V@pathway.suse.cz>
On Thu, 16 Apr 2026 16:54:23 +0200
Petr Mladek <pmladek@suse.com> wrote:
> On Thu 2026-04-16 13:30:04, David Laight wrote:
> > On Wed, 15 Apr 2026 15:01:37 +0800
> > chensong_2000@189.cn wrote:
> >
> > > From: Song Chen <chensong_2000@189.cn>
> > >
> > > The current notifier chain implementation uses a single-linked list
> > > (struct notifier_block *next), which only supports forward traversal
> > > in priority order. This makes it difficult to handle cleanup/teardown
> > > scenarios that require notifiers to be called in reverse priority order.
> >
> > If it is only cleanup/teardown then the list can be order-reversed
> > as part of that process at the same time as the list is deleted.
>
> Interesting idea. But it won't work in all situations.
It is useful for things like locklessy queuing a request to be processed later.
Items can be added with a cmpxchg and the list grabbed by xchg of NULL.
The only downside is that reversing a list isn't cache friendly.
Thinks... although that may not be any worse than accessing the current 'tail'
to add to the end of a doubly linked (or singly linked with a tail ptr) list.
David
>
> Note that the motivation for this update are the module loader
> notifiers which are called several times for each loaded/removed module.
>
> Best Regards,
> Petr
>
^ permalink raw reply
* [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
* [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 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 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 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 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 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 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 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 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 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 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 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 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 14/28] nfsd: add callback encoding and decoding linkages for 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 routines for encoding and decoding CB_NOTIFY messages. These call
into the code generated by xdrgen to do the actual encoding and
decoding.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4callback.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
fs/nfsd/state.h | 8 ++++++++
fs/nfsd/xdr4cb.h | 12 ++++++++++++
3 files changed, 66 insertions(+)
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 25bbf5b8814d..ea3e7deb06fa 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -865,6 +865,51 @@ static void encode_stateowner(struct xdr_stream *xdr, struct nfs4_stateowner *so
xdr_encode_opaque(p, so->so_owner.data, so->so_owner.len);
}
+static void nfs4_xdr_enc_cb_notify(struct rpc_rqst *req,
+ struct xdr_stream *xdr,
+ const void *data)
+{
+ const struct nfsd4_callback *cb = data;
+ struct nfs4_cb_compound_hdr hdr = {
+ .ident = 0,
+ .minorversion = cb->cb_clp->cl_minorversion,
+ };
+ struct CB_NOTIFY4args args = { };
+
+ 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.
+ */
+ WARN_ON_ONCE(!xdrgen_encode_CB_NOTIFY4args(xdr, &args));
+
+ hdr.nops++;
+ encode_cb_nops(&hdr);
+}
+
+static int nfs4_xdr_dec_cb_notify(struct rpc_rqst *rqstp,
+ struct xdr_stream *xdr,
+ void *data)
+{
+ struct nfsd4_callback *cb = data;
+ struct nfs4_cb_compound_hdr hdr;
+ int status;
+
+ status = decode_cb_compound4res(xdr, &hdr);
+ if (unlikely(status))
+ return status;
+
+ status = decode_cb_sequence4res(xdr, cb);
+ if (unlikely(status || cb->cb_seq_status))
+ return status;
+
+ return decode_cb_op_status(xdr, OP_CB_NOTIFY, &cb->cb_status);
+}
+
static void nfs4_xdr_enc_cb_notify_lock(struct rpc_rqst *req,
struct xdr_stream *xdr,
const void *data)
@@ -1026,6 +1071,7 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = {
#ifdef CONFIG_NFSD_PNFS
PROC(CB_LAYOUT, COMPOUND, cb_layout, cb_layout),
#endif
+ PROC(CB_NOTIFY, COMPOUND, cb_notify, cb_notify),
PROC(CB_NOTIFY_LOCK, COMPOUND, cb_notify_lock, cb_notify_lock),
PROC(CB_OFFLOAD, COMPOUND, cb_offload, cb_offload),
PROC(CB_RECALL_ANY, COMPOUND, cb_recall_any, cb_recall_any),
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 7d2afe7dcc3e..22c9a1e7d8fd 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -190,6 +190,13 @@ struct nfs4_cb_fattr {
u64 ncf_cur_fsize;
};
+/*
+ * FIXME: the current backchannel encoder can't handle a send buffer longer
+ * than a single page (see bc_alloc/bc_free).
+ */
+#define NOTIFY4_EVENT_QUEUE_SIZE 3
+#define NOTIFY4_PAGE_ARRAY_SIZE 1
+
/*
* 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
@@ -774,6 +781,7 @@ enum nfsd4_cb_op {
NFSPROC4_CLNT_CB_NOTIFY_LOCK,
NFSPROC4_CLNT_CB_RECALL_ANY,
NFSPROC4_CLNT_CB_GETATTR,
+ NFSPROC4_CLNT_CB_NOTIFY,
};
/* Returns true iff a is later than b: */
diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h
index f4e29c0c701c..b06d0170d7c4 100644
--- a/fs/nfsd/xdr4cb.h
+++ b/fs/nfsd/xdr4cb.h
@@ -33,6 +33,18 @@
cb_sequence_dec_sz + \
op_dec_sz)
+#define NFS4_enc_cb_notify_sz (cb_compound_enc_hdr_sz + \
+ cb_sequence_enc_sz + \
+ 1 + enc_stateid_sz + \
+ enc_nfs4_fh_sz + \
+ 1 + \
+ NOTIFY4_EVENT_QUEUE_SIZE * \
+ (2 + (NFS4_OPAQUE_LIMIT >> 2)))
+
+#define NFS4_dec_cb_notify_sz (cb_compound_dec_hdr_sz + \
+ cb_sequence_dec_sz + \
+ op_dec_sz)
+
#define NFS4_enc_cb_notify_lock_sz (cb_compound_enc_hdr_sz + \
cb_sequence_enc_sz + \
2 + 1 + \
--
2.53.0
^ permalink raw reply related
* [PATCH v2 13/28] nfsd: make nfsd4_callback_ops->prepare operation bool return
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>
For a CB_NOTIFY operation, we need to stop processing the callback
if an allocation fails. Change the ->prepare callback operation to
return true if processing should continue, and false otherwise.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4callback.c | 5 ++++-
fs/nfsd/nfs4layouts.c | 3 ++-
fs/nfsd/nfs4state.c | 6 ++++--
fs/nfsd/state.h | 6 +++---
4 files changed, 13 insertions(+), 7 deletions(-)
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 50827405468d..25bbf5b8814d 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1715,7 +1715,10 @@ nfsd4_run_cb_work(struct work_struct *work)
if (!test_and_clear_bit(NFSD4_CALLBACK_REQUEUE, &cb->cb_flags)) {
if (cb->cb_ops && cb->cb_ops->prepare)
- cb->cb_ops->prepare(cb);
+ if (!cb->cb_ops->prepare(cb)) {
+ nfsd41_destroy_cb(cb);
+ return;
+ }
}
cb->cb_msg.rpc_cred = clp->cl_cb_cred;
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index c550b83f4432..8974e3d85d75 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -654,7 +654,7 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls, struct nfsd_file *file)
}
}
-static void
+static bool
nfsd4_cb_layout_prepare(struct nfsd4_callback *cb)
{
struct nfs4_layout_stateid *ls =
@@ -663,6 +663,7 @@ nfsd4_cb_layout_prepare(struct nfsd4_callback *cb)
mutex_lock(&ls->ls_mutex);
nfs4_inc_and_copy_stateid(&ls->ls_recall_sid, &ls->ls_stid);
mutex_unlock(&ls->ls_mutex);
+ return true;
}
static int
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 6adce94e9fdb..c0046fc3c1b1 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -357,12 +357,13 @@ remove_blocked_locks(struct nfs4_lockowner *lo)
}
}
-static void
+static bool
nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb)
{
struct nfsd4_blocked_lock *nbl = container_of(cb,
struct nfsd4_blocked_lock, nbl_cb);
locks_delete_block(&nbl->nbl_lock);
+ return true;
}
static int
@@ -5553,7 +5554,7 @@ bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, struct inode *inode)
return timeo > 0;
}
-static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb)
+static bool nfsd4_cb_recall_prepare(struct nfsd4_callback *cb)
{
struct nfs4_delegation *dp = cb_to_delegation(cb);
struct nfsd_net *nn = net_generic(dp->dl_stid.sc_client->net,
@@ -5574,6 +5575,7 @@ static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb)
list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru);
}
spin_unlock(&nn->deleg_lock);
+ return true;
}
static int nfsd4_cb_recall_done(struct nfsd4_callback *cb,
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 811c148f36fc..7d2afe7dcc3e 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -98,9 +98,9 @@ struct nfsd4_callback {
};
struct nfsd4_callback_ops {
- void (*prepare)(struct nfsd4_callback *);
- int (*done)(struct nfsd4_callback *, struct rpc_task *);
- void (*release)(struct nfsd4_callback *);
+ bool (*prepare)(struct nfsd4_callback *cb);
+ int (*done)(struct nfsd4_callback *cb, struct rpc_task *task);
+ void (*release)(struct nfsd4_callback *cb);
uint32_t opcode;
};
--
2.53.0
^ permalink raw reply related
* [PATCH v2 12/28] nfsd: update the fsnotify mark when setting or removing a dir delegation
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 a new helper function that will update the mask on the nfsd_file's
fsnotify_mark to be a union of all current directory delegations on an
inode. Call that when directory delegations are added or removed.
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4state.c | 33 +++++++++++++++++++++++++++++++++
1 file changed, 33 insertions(+)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index bd7e4f9cdaa5..6adce94e9fdb 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1260,6 +1260,37 @@ static void nfsd4_finalize_deleg_timestamps(struct nfs4_delegation *dp, struct f
}
}
+static void nfsd_fsnotify_recalc_mask(struct nfsd_file *nf)
+{
+ struct fsnotify_mark *mark = &nf->nf_mark->nfm_mark;
+ struct inode *inode = file_inode(nf->nf_file);
+ u32 lease_mask, set = 0, clear = 0;
+
+ /* This is only needed when adding or removing dir delegs */
+ if (!S_ISDIR(inode->i_mode))
+ return;
+
+ /* Set up notifications for any ignored delegation events */
+ lease_mask = inode_lease_ignore_mask(inode);
+
+ if (lease_mask & FL_IGN_DIR_CREATE)
+ set |= FS_CREATE | FS_MOVED_TO;
+ else
+ clear |= FS_CREATE | FS_MOVED_TO;
+
+ if (lease_mask & FL_IGN_DIR_DELETE)
+ set |= FS_DELETE | FS_MOVED_FROM;
+ else
+ clear |= FS_DELETE | FS_MOVED_FROM;
+
+ if (lease_mask & FL_IGN_DIR_RENAME)
+ set |= FS_RENAME;
+ else
+ clear |= FS_RENAME;
+
+ fsnotify_modify_mark_mask(mark, set, clear);
+}
+
static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp)
{
struct nfs4_file *fp = dp->dl_stid.sc_file;
@@ -1269,6 +1300,7 @@ static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp)
nfsd4_finalize_deleg_timestamps(dp, nf->nf_file);
kernel_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp);
+ nfsd_fsnotify_recalc_mask(nf);
put_deleg_file(fp);
}
@@ -9674,6 +9706,7 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
if (!status) {
put_nfs4_file(fp);
+ nfsd_fsnotify_recalc_mask(nf);
return dp;
}
--
2.53.0
^ permalink raw reply related
* [PATCH v2 11/28] nfsd: allow nfsd to get a dir lease with an ignore mask
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 requesting a directory lease, enable the FL_IGN_DIR_* bits that
correspond to the requested notification types.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4state.c | 26 ++++++++++++++++++++------
1 file changed, 20 insertions(+), 6 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 35f5c098717e..bd7e4f9cdaa5 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -6040,7 +6040,22 @@ static bool nfsd4_cb_channel_good(struct nfs4_client *clp)
return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN;
}
-static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp)
+static unsigned int
+nfsd_notify_to_ignore(u32 notify)
+{
+ unsigned int mask = 0;
+
+ if (notify & BIT(NOTIFY4_REMOVE_ENTRY))
+ mask |= FL_IGN_DIR_DELETE;
+ if (notify & BIT(NOTIFY4_ADD_ENTRY))
+ mask |= FL_IGN_DIR_CREATE;
+ if (notify & BIT(NOTIFY4_RENAME_ENTRY))
+ mask |= FL_IGN_DIR_RENAME;
+
+ return mask;
+}
+
+static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp, u32 notify)
{
struct file_lease *fl;
@@ -6048,7 +6063,7 @@ static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp)
if (!fl)
return NULL;
fl->fl_lmops = &nfsd_lease_mng_ops;
- fl->c.flc_flags = FL_DELEG;
+ fl->c.flc_flags = FL_DELEG | nfsd_notify_to_ignore(notify);
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;
@@ -6265,7 +6280,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
if (stp->st_stid.sc_export)
dp->dl_stid.sc_export = exp_get(stp->st_stid.sc_export);
- fl = nfs4_alloc_init_lease(dp);
+ fl = nfs4_alloc_init_lease(dp, 0);
if (!fl)
goto out_clnt_odstate;
@@ -9634,12 +9649,11 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
dp->dl_stid.sc_export =
exp_get(cstate->current_fh.fh_export);
- fl = nfs4_alloc_init_lease(dp);
+ fl = nfs4_alloc_init_lease(dp, gdd->gddr_notification[0]);
if (!fl)
goto out_put_stid;
- status = kernel_setlease(nf->nf_file,
- fl->c.flc_type, &fl, NULL);
+ status = kernel_setlease(nf->nf_file, fl->c.flc_type, &fl, NULL);
if (fl)
locks_free_lease(fl);
if (status)
--
2.53.0
^ 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