* [PATCH bpf-next v6 2/2] selftests/bpf: Add tests for kprobe attachment with duplicate symbols
From: Andrey Grodzovsky @ 2026-04-07 16:51 UTC (permalink / raw)
To: bpf, linux-trace-kernel, jolsa, ihor.solodrai
Cc: ast, daniel, andrii, rostedt, mhiramat, emil, linux-open-source
In-Reply-To: <20260407165145.1651061-1-andrey.grodzovsky@crowdstrike.com>
bpf_fentry_shadow_test exists in both vmlinux (net/bpf/test_run.c) and
bpf_testmod (bpf_testmod.c), creating a duplicate symbol condition when
bpf_testmod is loaded. Add subtests that verify kprobe behavior with
this duplicate symbol:
In attach_probe:
- dup-sym-{default,legacy,perf,link}: unqualified attach succeeds
across all four modes, preferring vmlinux over module shadow.
- dup-sym-module-{default,legacy,perf,link}: MOD:SYM qualification
(bpf_testmod:bpf_fentry_shadow_test) attaches to the module version.
In kprobe_multi_test:
- dup_sym: kprobe_multi attach with kprobe and kretprobe succeeds.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@crowdstrike.com>
---
.../selftests/bpf/prog_tests/attach_probe.c | 68 +++++++++++++++++++
.../bpf/prog_tests/kprobe_multi_test.c | 39 +++++++++++
2 files changed, 107 insertions(+)
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index 12a841afda68..2d52547c395e 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -197,6 +197,65 @@ static void test_attach_kprobe_legacy_by_addr_reject(void)
test_attach_probe_manual__destroy(skel);
}
+/* bpf_fentry_shadow_test exists in both vmlinux (net/bpf/test_run.c) and
+ * bpf_testmod (bpf_testmod.c). When bpf_testmod is loaded the symbol is
+ * duplicated. Test that kprobe attachment handles this correctly:
+ * - Unqualified name ("bpf_fentry_shadow_test") attaches to vmlinux.
+ * - MOD:SYM name ("bpf_testmod:bpf_fentry_shadow_test") attaches to module.
+ *
+ * Note: bpf_fentry_shadow_test is not invoked via test_run, so we only
+ * verify that attach and detach succeed without triggering the probe.
+ */
+static void test_attach_probe_dup_sym(enum probe_attach_mode attach_mode)
+{
+ DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, kprobe_opts);
+ struct bpf_link *kprobe_link, *kretprobe_link;
+ struct test_attach_probe_manual *skel;
+
+ skel = test_attach_probe_manual__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_dup_sym_open_and_load"))
+ return;
+
+ kprobe_opts.attach_mode = attach_mode;
+
+ /* Unqualified: should attach to vmlinux symbol */
+ kprobe_opts.retprobe = false;
+ kprobe_link = bpf_program__attach_kprobe_opts(skel->progs.handle_kprobe,
+ "bpf_fentry_shadow_test",
+ &kprobe_opts);
+ if (!ASSERT_OK_PTR(kprobe_link, "attach_kprobe_vmlinux"))
+ goto cleanup;
+ bpf_link__destroy(kprobe_link);
+
+ kprobe_opts.retprobe = true;
+ kretprobe_link = bpf_program__attach_kprobe_opts(skel->progs.handle_kretprobe,
+ "bpf_fentry_shadow_test",
+ &kprobe_opts);
+ if (!ASSERT_OK_PTR(kretprobe_link, "attach_kretprobe_vmlinux"))
+ goto cleanup;
+ bpf_link__destroy(kretprobe_link);
+
+ /* MOD:SYM qualified: should attach to module symbol */
+ kprobe_opts.retprobe = false;
+ kprobe_link = bpf_program__attach_kprobe_opts(skel->progs.handle_kprobe,
+ "bpf_testmod:bpf_fentry_shadow_test",
+ &kprobe_opts);
+ if (!ASSERT_OK_PTR(kprobe_link, "attach_kprobe_module"))
+ goto cleanup;
+ bpf_link__destroy(kprobe_link);
+
+ kprobe_opts.retprobe = true;
+ kretprobe_link = bpf_program__attach_kprobe_opts(skel->progs.handle_kretprobe,
+ "bpf_testmod:bpf_fentry_shadow_test",
+ &kprobe_opts);
+ if (!ASSERT_OK_PTR(kretprobe_link, "attach_kretprobe_module"))
+ goto cleanup;
+ bpf_link__destroy(kretprobe_link);
+
+cleanup:
+ test_attach_probe_manual__destroy(skel);
+}
+
/* attach uprobe/uretprobe long event name testings */
static void test_attach_uprobe_long_event_name(void)
{
@@ -559,6 +618,15 @@ void test_attach_probe(void)
if (test__start_subtest("kprobe-legacy-by-addr-reject"))
test_attach_kprobe_legacy_by_addr_reject();
+ if (test__start_subtest("dup-sym-default"))
+ test_attach_probe_dup_sym(PROBE_ATTACH_MODE_DEFAULT);
+ if (test__start_subtest("dup-sym-legacy"))
+ test_attach_probe_dup_sym(PROBE_ATTACH_MODE_LEGACY);
+ if (test__start_subtest("dup-sym-perf"))
+ test_attach_probe_dup_sym(PROBE_ATTACH_MODE_PERF);
+ if (test__start_subtest("dup-sym-link"))
+ test_attach_probe_dup_sym(PROBE_ATTACH_MODE_LINK);
+
if (test__start_subtest("auto"))
test_attach_probe_auto(skel);
if (test__start_subtest("kprobe-sleepable"))
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index 78c974d4ea33..d89650e31fd3 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -633,6 +633,43 @@ static void test_attach_write_ctx(void)
}
#endif
+/* Test kprobe_multi handles shadow symbols (vmlinux + module duplicate).
+ * bpf_fentry_shadow_test exists in both vmlinux and bpf_testmod.
+ * kprobe_multi resolves via ftrace_lookup_symbols() which finds the
+ * vmlinux symbol first and stops, so this should always succeed.
+ */
+static void test_attach_probe_dup_sym(void)
+{
+ LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+ const char *syms[1] = { "bpf_fentry_shadow_test" };
+ struct kprobe_multi *skel = NULL;
+ struct bpf_link *link1 = NULL, *link2 = NULL;
+
+ skel = kprobe_multi__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "kprobe_multi__open_and_load"))
+ goto cleanup;
+
+ skel->bss->pid = getpid();
+ opts.syms = syms;
+ opts.cnt = ARRAY_SIZE(syms);
+
+ link1 = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
+ NULL, &opts);
+ if (!ASSERT_OK_PTR(link1, "attach_kprobe_multi_dup_sym"))
+ goto cleanup;
+
+ opts.retprobe = true;
+ link2 = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kretprobe_manual,
+ NULL, &opts);
+ if (!ASSERT_OK_PTR(link2, "attach_kretprobe_multi_dup_sym"))
+ goto cleanup;
+
+cleanup:
+ bpf_link__destroy(link2);
+ bpf_link__destroy(link1);
+ kprobe_multi__destroy(skel);
+}
+
void serial_test_kprobe_multi_bench_attach(void)
{
if (test__start_subtest("kernel"))
@@ -676,5 +713,7 @@ void test_kprobe_multi_test(void)
test_unique_match();
if (test__start_subtest("attach_write_ctx"))
test_attach_write_ctx();
+ if (test__start_subtest("dup_sym"))
+ test_attach_probe_dup_sym();
RUN_TESTS(kprobe_multi_verifier);
}
--
2.34.1
^ permalink raw reply related
* Re: [PATCH] selftests/ftrace: Check exact trace_marker_raw payload lengths
From: Cao Ruichuang @ 2026-04-07 16:45 UTC (permalink / raw)
To: rostedt, mhiramat
Cc: mathieu.desnoyers, shuah, linux-kernel, linux-trace-kernel,
linux-kselftest
In-Reply-To: <20260407101245.78988-1-create0818@163.com>
A follow-up on this patch: I am pausing it in its current form.
The exact payload-length checks here were based on my earlier
ring-buffer change, and Steven has rejected that direction because
the ring buffer is meant to keep the allocated size, not the
requested payload size.
So this selftest should not move forward as-is. If there is a real
fix, it needs to come from an event-specific change that explicitly
stores the true payload length where needed. I will revisit it only
from that direction.
Thanks,
Cao Ruichuang
^ permalink raw reply
* Re: [PATCH] ring-buffer: Preserve true payload lengths in long data events
From: Cao Ruichuang @ 2026-04-07 16:45 UTC (permalink / raw)
To: rostedt; +Cc: mhiramat, mathieu.desnoyers, linux-kernel, linux-trace-kernel
In-Reply-To: <20260407114812.580c27d5@gandalf.local.home>
Thanks for the clarification.
I understand the design boundary now: the ring buffer metadata is
supposed to describe the allocated record size, not the requested
payload size. Given that, I will stop pushing this ring-buffer
approach.
If there is a valid fix here, it should be done at the event layer
for the users that need the true payload length, not in the generic
ring buffer code.
Thanks,
Cao Ruichuang
^ permalink raw reply
* Re: [PATCH] ring-buffer: Preserve true payload lengths in long data events
From: Steven Rostedt @ 2026-04-07 15:48 UTC (permalink / raw)
To: Cao Ruichuang
Cc: mhiramat, mathieu.desnoyers, linux-kernel, linux-trace-kernel
In-Reply-To: <20260407091550.67963-1-create0818@163.com>
On Tue, 7 Apr 2026 17:15:50 +0800
Cao Ruichuang <create0818@163.com> wrote:
> Long ring buffer data records currently store the aligned in-buffer size in
> their length field. That makes ring_buffer_event_length() report padded
> sizes, and small TRACE_PRINT / TRACE_RAW_DATA records lose their true
> payload length entirely when they use the short type_len encoding.
>
> Teach long data events to keep the true payload size in array[0], and let
> the ring buffer derive the aligned in-buffer size separately when it needs
> to walk or discard records. Then add a long-reserve helper and use it for
> TRACE_PRINT and TRACE_RAW_DATA so their zero-length-array tails always
> preserve the real payload size.
Sorry, I'm against this change. I made a conscious decision to have the
ring buffer meta data record the size allocated and not the size requested.
If an event needs to know the actual size, then it needs to add that
information itself. That's not the job of the ring buffer code.
NAK.
-- Steve
^ permalink raw reply
* Re: [RFC PATCH 3/4] livepatch: Add "replaceable" attribute to klp_patch
From: Petr Mladek @ 2026-04-07 15:08 UTC (permalink / raw)
To: Yafang Shao
Cc: Song Liu, Joe Lawrence, Dylan Hatch, jpoimboe, jikos, mbenes,
rostedt, mhiramat, mathieu.desnoyers, kpsingh, mattbobrowski,
jolsa, ast, daniel, andrii, martin.lau, eddyz87, memxor,
yonghong.song, live-patching, linux-kernel, linux-trace-kernel,
bpf
In-Reply-To: <CALOAHbCxPA0dtsx7L2kYn8wwBdM=krZyOpfRTBiDW9qfA_zmzQ@mail.gmail.com>
On Tue 2026-04-07 17:45:31, Yafang Shao wrote:
> On Tue, Apr 7, 2026 at 11:16 AM Yafang Shao <laoar.shao@gmail.com> wrote:
> >
> > On Tue, Apr 7, 2026 at 10:54 AM Song Liu <song@kernel.org> wrote:
> > >
> > > On Mon, Apr 6, 2026 at 2:12 PM Joe Lawrence <joe.lawrence@redhat.com> wrote:
> > > [...]
> > > > > > > - The regular livepatches are cumulative, have the replace flag; and
> > > > > > > are replaceable.
> > > > > > > - The occasional "off-band" livepatches do not have the replace flag,
> > > > > > > and are not replaceable.
> > > > > > >
> > > > > > > With this setup, for systems with off-band livepatches loaded, we can
> > > > > > > still release a cumulative livepatch to replace the previous cumulative
> > > > > > > livepatch. Is this the expected use case?
> > > > > >
> > > > > > That matches our expected use case.
> > > > >
> > > > > If we really want to serve use cases like this, I think we can introduce
> > > > > some replace tag concept: Each livepatch will have a tag, u32 number.
> > > > > Newly loaded livepatch will only replace existing livepatch with the
> > > > > same tag. We can even reuse the existing "bool replace" in klp_patch,
> > > > > and make it u32: replace=0 means no replace; replace > 0 are the
> > > > > replace tag.
> > > > >
> > > > > For current users of cumulative patches, all the livepatch will have the
> > > > > same tag, say 1. For your use case, you can assign each user a
> > > > > unique tag. Then all these users can do atomic upgrades of their
> > > > > own livepatches.
> > > > >
> > > > > We may also need to check whether two livepatches of different tags
> > > > > touch the same kernel function. When that happens, the later
> > > > > livepatch should fail to load.
I still think how to make the hybrid mode more secure:
+ The isolated sets of livepatched functions look like a good rule.
+ What about isolating the shadow variables/states as well?
> > That sounds like a viable solution. I'll look into it and see how we
> > can implement it.
>
> Does the following change look good to you ?
>
> Subject: [PATCH] livepatch: Support scoped atomic replace using replace tags
>
> Extend the replace attribute from a boolean to a u32 to act as a replace
> tag. This introduces the following semantics:
>
> replace = 0: Atomic replace is disabled. However, this patch remains
> eligible to be superseded by others.
> replace > 0: Enables tagged replace (default is 1). A newly loaded
> livepatch will only replace existing patches that share the
> same tag.
>
> To maintain backward compatibility, a patch with replace == 0 does not
> trigger an outgoing atomic replace, but remains eligible to be superseded
> by any incoming patch with a valid replace tag.
>
> diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h
> index ba9e3988c07c..417c67a17b99 100644
> --- a/include/linux/livepatch.h
> +++ b/include/linux/livepatch.h
> @@ -123,7 +123,11 @@ struct klp_state {
> * @mod: reference to the live patch module
> * @objs: object entries for kernel objects to be patched
> * @states: system states that can get modified
> - * @replace: replace all actively used patches
> + * @replace: replace tag:
> + * = 0: Atomic replace is disabled; however, this patch remains
> + * eligible to be superseded by others.
This is weird semantic. Which livepatch tag would be allowed to
supersede it, please?
Do we still need this category?
> + * > 0: Atomic replace is enabled. Only existing patches with a
> + * matching replace tag will be superseded.
> * @list: list node for global list of actively used patches
> * @kobj: kobject for sysfs resources
> * @obj_list: dynamic list of the object entries
> @@ -137,7 +141,7 @@ struct klp_patch {
> struct module *mod;
> struct klp_object *objs;
> struct klp_state *states;
> - bool replace;
> + unsigned int replace;
This already breaks the backward compatibility by changing the type
and semantic of this field. I would also change the name to better
match the new semantic. What about using:
* @replace_set: Livepatch using the same @replace_set will get
atomically replaced, see also conflicts[*].
unsigned int replace_set;
[*] A livepatch module, livepatching an already livepatches function,
can be loaded only when it has the same @replace_set number.
By other words, two livepatches conflict when they have a different
@replace_set number and have at least one livepatched version
in common.
>
> /* internal */
> struct list_head list;
> diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
> index 28d15ba58a26..e4e5c03b0724 100644
> --- a/kernel/livepatch/core.c
> +++ b/kernel/livepatch/core.c
> @@ -793,6 +793,8 @@ void klp_free_replaced_patches_async(struct
> klp_patch *new_patch)
> klp_for_each_patch_safe(old_patch, tmp_patch) {
> if (old_patch == new_patch)
> return;
> + if (old_patch->replace && old_patch->replace !=
> new_patch->replace)
> + continue;
> klp_free_patch_async(old_patch);
> }
> }
> @@ -1194,6 +1196,8 @@ void klp_unpatch_replaced_patches(struct
> klp_patch *new_patch)
> klp_for_each_patch(old_patch) {
> if (old_patch == new_patch)
> return;
> + if (old_patch->replace && old_patch->replace !=
> new_patch->replace)
> + continue;
>
> old_patch->enabled = false;
> klp_unpatch_objects(old_patch);
This handles only the freeing part. More changes will be
necessary:
+ klp_is_patch_compatible() must check also conflicts
between livepatches with different @replace_set.
The conflicts might be in the lists of:
+ livepatched functions
+ state IDs (aka callbacks and shadow variables IDs)
+ klp_add_nops() must skip livepatches with another @replace_set
+ klp_unpatch_replaced_patches() should unpatch only
patches with the same @replace_set
Finally, we would need to update existing selftests
plus add new selftests.
It is possible that I have missed something.
Anyway, you should wait for more feedback before you do too much
coding, especially the selftests are not needed at RFC stage.
Best Regards,
Petr
^ permalink raw reply
* Re: [PATCH v5 0/3] PCI Controller event and LTSSM tracepoint support
From: Manivannan Sadhasivam @ 2026-04-07 14:43 UTC (permalink / raw)
To: Bjorn Helgaas, Shawn Lin
Cc: linux-rockchip, linux-pci, linux-trace-kernel, linux-doc,
Steven Rostedt
In-Reply-To: <1774403912-210670-1-git-send-email-shawn.lin@rock-chips.com>
On Wed, 25 Mar 2026 09:58:29 +0800, Shawn Lin wrote:
> This patch-set adds new pci controller event and LTSSM tracepoint used by host drivers
> which provide LTSSM trace functionality. The first user is pcie-dw-rockchip with a 256
> Bytes FIFO for recording LTSSM transition.
>
> Testing
> =========
>
> [...]
Applied, thanks!
[1/3] PCI: trace: Add PCI controller LTSSM transition tracepoint
commit: d1b7add89c004295cd48d7cd49946ed5cb5cbb55
[2/3] Documentation: tracing: Add PCI controller event documentation
commit: a3966a6f915ea7d1af0941ea26848d921e574c45
[3/3] PCI: dw-rockchip: Add pcie_ltssm_state_transition trace support
commit: a276c0d802d8d2a22088b7919d9e82e936995cf4
Best regards,
--
Manivannan Sadhasivam <mani@kernel.org>
^ permalink raw reply
* Re: [RFC PATCH 3/4] livepatch: Add "replaceable" attribute to klp_patch
From: Petr Mladek @ 2026-04-07 13:52 UTC (permalink / raw)
To: Yafang Shao
Cc: Song Liu, Dylan Hatch, jpoimboe, jikos, mbenes, joe.lawrence,
rostedt, mhiramat, mathieu.desnoyers, kpsingh, mattbobrowski,
jolsa, ast, daniel, andrii, martin.lau, eddyz87, memxor,
yonghong.song, live-patching, linux-kernel, linux-trace-kernel,
bpf
In-Reply-To: <CALOAHbCbcw2jpjk9JD9yyf+SMpQ-s9FAonSaz7Gs4XUeP+w+2g@mail.gmail.com>
On Mon 2026-04-06 19:08:05, Yafang Shao wrote:
> On Sat, Apr 4, 2026 at 5:36 AM Song Liu <song@kernel.org> wrote:
> >
> > On Fri, Apr 3, 2026 at 1:55 PM Dylan Hatch <dylanbhatch@google.com> wrote:
> > [...]
> > > > IIRC, the use case for this change is when multiple users load various
> > > > livepatch modules on the same system. I still don't believe this is the
> > > > right way to manage livepatches. That said, I won't really NACK this
> > > > if other folks think this is a useful option.
> > >
> > > In our production fleet, we apply exactly one cumulative livepatch
> > > module, and we use per-kernel build "livepatch release" branches to
> > > track the contents of these cumulative livepatches. This model has
> > > worked relatively well for us, but there are some painpoints.
> > >
> > > We are often under pressure to selectively deploy a livepatch fix to
> > > certain subpopulations of production. If the subpopulation is running
> > > the same build of everything else, this would require us to introduce
> > > another branching factor to the "livepatch release" branches --
> > > something we do not support due to the added toil and complexity.
> > >
> > > However, if we had the ability to build "off-band" livepatch modules
> > > that were marked as non-replaceable, we could support these selective
> > > patches without the additional branching factor. I will have to
> > > circulate the idea internally, but to me this seems like a very useful
> > > option to have in certain cases.
> >
> > IIUC, the plan is:
> >
> > - The regular livepatches are cumulative, have the replace flag; and
> > are replaceable.
> > - The occasional "off-band" livepatches do not have the replace flag,
> > and are not replaceable.
> >
> > With this setup, for systems with off-band livepatches loaded, we can
> > still release a cumulative livepatch to replace the previous cumulative
> > livepatch. Is this the expected use case?
>
> That matches our expected use case.
>
> >
> > I think there are a few issues with this:
> > 1. The "off-band" livepatches cannot be replaced atomically. To upgrade
> > "off-band' livepatches, we will have to unload the old version and load
> > the new version later.
>
> Right. That is how the non-atomic-replace patch works.
>
> > 2. Any conflict with the off-band livepatches and regular livepatches will
> > be difficult to manage.
>
> We need to manage this conflict with a complex user script. That said,
> everything can be controlled from userspace.
>
> > IOW, we kind removed the benefit of cumulative
> > livepatches. For example, what shall we do if we really need two fixes
> > to the same kernel functions: one from the original branch, the other
> > from the off-band branch?
>
> We run tens of livepatches on our production servers and have never
> run into this issue. It's an extremely rare case — and if it does
> happen, a user script should be able to handle it just fine.
Could you please share the script? Or at least summarize the situations
when this script detect a conflict and refuse loading a livepatch?
I believe that most/all of these checks can be implemented in the kernel.
And if we agreed to add a hybrid mode than it should be added
together with the checks.
We have already invested a lot of effort into make the kernel
livepatching as safe as possible. From my POV, the most important
parts are:
+ consistency model: Tasks are transitioned separately when they
do not use any livepatched function.
+ atomic replace: Transition all livepatched functions at once.
If we agree to add the hybrid model then we should add it with
some safety belts as well. And it would be nice to get inspiration
about the safety checks from your script.
Best Regards,
Petr
^ permalink raw reply
* [PATCH 24/24] nfsd: add support to CB_NOTIFY for dir attribute changes
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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 c4b6f4d65a47..01a2fb11dc0e 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3470,10 +3470,15 @@ 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);
@@ -3487,7 +3492,7 @@ 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;
}
@@ -3534,6 +3539,22 @@ 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 35646809becb..6e76502ca149 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;
@@ -4283,6 +4291,41 @@ 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 23/24] nfsd: track requested dir attributes
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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 | 7 ++++---
fs/nfsd/nfs4state.c | 14 +++++++++++++-
fs/nfsd/state.h | 2 ++
3 files changed, 19 insertions(+), 4 deletions(-)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index a807a55dddf9..82d7c473e4d3 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
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 59a9b1ca836b..c4b6f4d65a47 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -9795,6 +9795,15 @@ 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
@@ -9864,10 +9873,13 @@ 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 7ca5ef9caafe..56a3cfb12e65 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -284,7 +284,9 @@ 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 22/24] nfsd: properly track requested child attributes
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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 0580c935d804..59a9b1ca836b 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -9780,6 +9780,21 @@ 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
@@ -9849,6 +9864,9 @@ 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 e468cbc087ad..35646809becb 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 d060d70c5820..7ca5ef9caafe 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -282,6 +282,9 @@ 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 21/24] nfsd: add the filehandle to returned attributes in CB_NOTIFY
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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 faf0c3d35dee..e468cbc087ad 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 20/24] nfsd: add a fi_connectable flag to struct nfs4_file
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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 requires
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 f3bf572b0ada..0580c935d804 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5153,6 +5153,7 @@ 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 & EXPORT_FH_CONNECTABLE;
#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 dbeacbb7a5c8..d060d70c5820 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -745,6 +745,7 @@ 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 19/24] nfsd: allow encoding a filehandle into fattr4 without a svc_fh
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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 0cdce460f9c8..faf0c3d35dee 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 18/24] nfsd: send basic file attributes in CB_NOTIFY
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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 49ca24851707..0cdce460f9c8 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 17/24] nfsd: allow nfsd4_encode_fattr4_change() to work with no export
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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 2ba3fcadb742..49ca24851707 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 16/24] nfsd: add helper to marshal a fattr4 from completed args
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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 | 46 ++++++++++++++++++++++++++--------------------
1 file changed, 26 insertions(+), 20 deletions(-)
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 9ad13f96c219..2ba3fcadb742 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;
+ return status;
/* 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 15/24] nfsd: apply the notify mask to the delegation when requested
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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 14/24] nfsd: add tracepoint to dir_event handler
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@kernel.org>
Add some extra visibility around the fsnotify handlers.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/nfsd/nfs4state.c | 2 ++
fs/nfsd/trace.h | 20 ++++++++++++++++++++
2 files changed, 22 insertions(+)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 339c3d0bb575..f3bf572b0ada 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -9963,6 +9963,8 @@ 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_file_fsnotify_handle_dir_event(mask, dir, name);
+
/* Don't do anything if this is not an expected event */
if (!(mask & (FS_CREATE|FS_DELETE|FS_RENAME)))
return 0;
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 60cacf64181c..3302cb926254 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -1377,6 +1377,26 @@ TRACE_EVENT(nfsd_file_fsnotify_handle_event,
__entry->nlink, __entry->mode, __entry->mask)
);
+TRACE_EVENT(nfsd_file_fsnotify_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=0x%x name=%s",
+ MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
+ __entry->i_ino, __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 13/24] nfsd: add notification handlers for dir events
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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 | 57 ++++++++----
fs/nfsd/nfs4callback.c | 19 +++-
fs/nfsd/nfs4state.c | 248 ++++++++++++++++++++++++++++++++++++++++++++-----
fs/nfsd/nfs4xdr.c | 96 +++++++++++++++++++
fs/nfsd/state.h | 2 +
fs/nfsd/xdr4.h | 3 +
6 files changed, 383 insertions(+), 42 deletions(-)
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 24511c3208db..56889fca6dca 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 +815,25 @@ nfsd_file_fsnotify_handle_event(struct fsnotify_mark *mark, u32 mask,
return 0;
}
+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);
+}
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 +885,7 @@ 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 +894,23 @@ 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:
@@ -1223,10 +1250,8 @@ 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 b2b8c454fc0f..339c3d0bb575 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
@@ -3440,15 +3441,125 @@ 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("Count 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;
}
}
@@ -3477,6 +3588,7 @@ 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,
@@ -5702,27 +5814,6 @@ 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)
@@ -9796,3 +9887,118 @@ 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 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);
+ return ne;
+}
+
+static bool
+should_notify_deleg(u32 mask, struct file_lease *fl)
+{
+ /* Only nfsd leases */
+ if (fl->fl_lmops != &nfsd_lease_mng_ops)
+ 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 file_lock_context *ctx;
+ struct file_lock_core *flc;
+ struct nfsd_notify_event *evt;
+
+ /* 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);
+ 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..9ad13f96c219 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4098,6 +4098,102 @@ 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
+ * @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 = { };
+
+ if (!nfsd4_setup_notify_entry4(&na.nad_new_entry, xdr, nne->ne_dentry, dp,
+ nf, nne->ne_name, nne->ne_namelen))
+ goto out_err;
+
+ 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 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 (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..dbeacbb7a5c8 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -897,6 +897,8 @@ 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 12/24] nfsd: add data structures for handling CB_NOTIFY
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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 4afe7e68fb51..b2b8c454fc0f 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -124,6 +124,7 @@ 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;
@@ -1121,29 +1122,31 @@ 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);
@@ -1153,19 +1156,75 @@ 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_free_dir_deleg(&dp->dl_stid);
+ return NULL;
+ }
+
+ ncn->ncn_nf = kcalloc(NOTIFY4_EVENT_QUEUE_SIZE, sizeof(*ncn->ncn_nf), GFP_KERNEL);
+ if (!ncn->ncn_nf) {
+ nfs4_free_dir_deleg(&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)
{
@@ -3381,6 +3440,30 @@ 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,
@@ -3393,6 +3476,12 @@ 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 =
@@ -9661,7 +9750,7 @@ 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 11/24] nfsd: use RCU to protect fi_deleg_file
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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.
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 fd3d7cd427e1..4afe7e68fb51 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1210,7 +1210,9 @@ 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);
@@ -1293,7 +1295,7 @@ 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);
@@ -3159,7 +3161,8 @@ 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);
@@ -4941,7 +4944,7 @@ 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;
@@ -6082,7 +6085,7 @@ 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;
}
@@ -6090,7 +6093,7 @@ 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;
@@ -6167,7 +6170,7 @@ 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;
@@ -6273,8 +6276,9 @@ 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;
@@ -6299,7 +6303,7 @@ 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);
@@ -6320,7 +6324,7 @@ 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;
@@ -6341,7 +6345,8 @@ 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);
@@ -6498,8 +6503,9 @@ 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);
@@ -9638,8 +9644,9 @@ 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;
@@ -9691,7 +9698,8 @@ 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 10/24] nfsd: add callback encoding and decoding linkages for CB_NOTIFY
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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 09/24] nfsd: make nfsd4_callback_ops->prepare operation bool return
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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 9a4cff08c67d..fd3d7cd427e1 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -355,12 +355,13 @@ 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
@@ -5538,7 +5539,7 @@ 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,
@@ -5559,6 +5560,7 @@ 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 08/24] nfsd: update the fsnotify mark when setting or removing a dir delegation
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@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.
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 c8fb84c38637..9a4cff08c67d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1258,6 +1258,37 @@ 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;
+ else
+ clear |= FS_CREATE;
+
+ if (lease_mask & FL_IGN_DIR_DELETE)
+ set |= FS_DELETE;
+ else
+ clear |= FS_DELETE;
+
+ 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;
@@ -1266,6 +1297,7 @@ static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp)
WARN_ON_ONCE(!fp->fi_delegees);
nfsd4_finalize_deleg_timestamps(dp, nf->nf_file);
+ nfsd_fsnotify_recalc_mask(nf);
kernel_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp);
put_deleg_file(fp);
}
@@ -9652,6 +9684,7 @@ 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 07/24] vfs: add fsnotify_modify_mark_mask()
From: Jeff Layton @ 2026-04-07 13:21 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: <20260407-dir-deleg-v1-0-aaf68c478abd@kernel.org>
nfsd needs to be able to modify the mask on an existing mark when new
directory delegations are set or unset. Add an exported function that
allows the caller to set and clear bits in the mark->mask, and does
the recalculation if something changed.
Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/notify/mark.c | 29 +++++++++++++++++++++++++++++
include/linux/fsnotify_backend.h | 1 +
2 files changed, 30 insertions(+)
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index c2ed5b11b0fe..b1e73c6fd382 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -310,6 +310,35 @@ void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
fsnotify_conn_set_children_dentry_flags(conn);
}
+/**
+ * fsnotify_modify_mark_mask - set and/or clear flags in a mark's mask
+ * @mark: mark to be modified
+ * @set: bits to be set in mask
+ * @clear: bits to be cleared in mask
+ *
+ * Modify a fsnotify_mark mask as directed, and update its associated conn.
+ * The caller is expected to hold a reference to the mark.
+ */
+void fsnotify_modify_mark_mask(struct fsnotify_mark *mark, u32 set, u32 clear)
+{
+ bool recalc = false;
+ u32 mask;
+
+ WARN_ON_ONCE(clear & set);
+
+ spin_lock(&mark->lock);
+ mask = mark->mask;
+ mark->mask |= set;
+ mark->mask &= ~clear;
+ if (mark->mask != mask)
+ recalc = true;
+ spin_unlock(&mark->lock);
+
+ if (recalc)
+ fsnotify_recalc_mask(mark->connector);
+}
+EXPORT_SYMBOL_GPL(fsnotify_modify_mark_mask);
+
/* Free all connectors queued for freeing once SRCU period ends */
static void fsnotify_connector_destroy_workfn(struct work_struct *work)
{
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 95985400d3d8..66e185bd1b1b 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -917,6 +917,7 @@ extern void fsnotify_get_mark(struct fsnotify_mark *mark);
extern void fsnotify_put_mark(struct fsnotify_mark *mark);
extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info);
extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info);
+extern void fsnotify_modify_mark_mask(struct fsnotify_mark *mark, u32 set, u32 clear);
static inline void fsnotify_init_event(struct fsnotify_event *event)
{
--
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