* [PATCH v7 02/10] rust: module: add `THIS_MODULE` const to `ModuleMetadata` trait
From: Alvin Sun @ 2026-06-27 9:28 UTC (permalink / raw)
To: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Luis Chamberlain, Petr Pavlu, Daniel Gomez,
Sami Tolvanen, Aaron Tomlin, Greg Kroah-Hartman,
Rafael J. Wysocki, David Airlie, Simona Vetter, Daniel Almeida,
Arnd Bergmann, Brendan Higgins, David Gow, Rae Moar, Breno Leitao,
Jens Axboe, Dave Ertman, Leon Romanovsky, Igor Korotin,
FUJITA Tomonori, Bjorn Helgaas, Krzysztof Wilczyński,
Arve Hjønnevåg, Todd Kjos, Christian Brauner,
Carlos Llamas
Cc: rust-for-linux, linux-modules, driver-core, dri-devel, nova-gpu,
linux-kselftest, kunit-dev, linux-block, linux-kernel, netdev,
linux-pci, Alvin Sun
In-Reply-To: <20260627-fix-fops-owner-v7-0-33cd3990edf0@linux.dev>
Since `const_refs_to_static` has been stable as of the MSRV bump, a
`ThisModule` pointer can now be used in const contexts.
Add a `THIS_MODULE` const to the `ModuleMetadata` trait so that modules
can provide their `ThisModule` pointer in const contexts such as static
`file_operations`.
Add a `this_module()` helper to retrieve the `THIS_MODULE` pointer of a
given module type, and update `__init` to use it instead of the
`THIS_MODULE` static generated by the `module!` macro.
The `static THIS_MODULE` generated by the `module!` macro is retained
for backwards compatibility with existing users and removed in a later
patch once all references have been migrated.
Assisted-by: opencode:glm-5.2
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Reviewed-by: Gary Guo <gary@garyguo.net>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Signed-off-by: Alvin Sun <alvin.sun@linux.dev>
---
rust/kernel/module.rs | 9 +++++++++
rust/macros/module.rs | 18 +++++++++++++++++-
2 files changed, 26 insertions(+), 1 deletion(-)
diff --git a/rust/kernel/module.rs b/rust/kernel/module.rs
index be242a82e86d2..d713705984477 100644
--- a/rust/kernel/module.rs
+++ b/rust/kernel/module.rs
@@ -42,6 +42,15 @@ fn init(module: &'static ThisModule) -> impl pin_init::PinInit<Self, crate::erro
pub trait ModuleMetadata {
/// The name of the module as specified in the `module!` macro.
const NAME: &'static crate::str::CStr;
+
+ /// The module's `THIS_MODULE` pointer.
+ const THIS_MODULE: ThisModule;
+}
+
+/// Returns a reference to the `THIS_MODULE` of the given module type.
+#[inline]
+pub const fn this_module<M: ModuleMetadata>() -> &'static ThisModule {
+ &M::THIS_MODULE
}
/// Equivalent to `THIS_MODULE` in the C API.
diff --git a/rust/macros/module.rs b/rust/macros/module.rs
index 06c18e2075083..aa9a618d5d19e 100644
--- a/rust/macros/module.rs
+++ b/rust/macros/module.rs
@@ -519,6 +519,22 @@ pub(crate) fn module(info: ModuleInfo) -> Result<TokenStream> {
impl ::kernel::ModuleMetadata for #type_ {
const NAME: &'static ::kernel::str::CStr = #name_cstr;
+
+ #[cfg(MODULE)]
+ const THIS_MODULE: ::kernel::ThisModule = {
+ extern "C" {
+ static __this_module: ::kernel::types::Opaque<::kernel::bindings::module>;
+ }
+
+ // SAFETY: `__this_module` is constructed by the kernel at load time
+ // and lives until the module is unloaded.
+ unsafe { ::kernel::ThisModule::from_ptr(__this_module.get()) }
+ };
+
+ #[cfg(not(MODULE))]
+ const THIS_MODULE: ::kernel::ThisModule = unsafe {
+ ::kernel::ThisModule::from_ptr(::core::ptr::null_mut())
+ };
}
// Double nested modules, since then nobody can access the public items inside.
@@ -616,7 +632,7 @@ pub extern "C" fn #ident_exit() {
/// This function must only be called once.
unsafe fn __init() -> ::kernel::ffi::c_int {
let initer = <super::super::LocalModule as ::kernel::InPlaceModule>::init(
- &super::super::THIS_MODULE
+ ::kernel::module::this_module::<super::super::LocalModule>()
);
// SAFETY: No data race, since `__MOD` can only be accessed by this module
// and there only `__init` and `__exit` access it. These functions are only
--
2.43.0
^ permalink raw reply related
* [PATCH v7 00/10] Fix missing fops.owner in Rust DRM/misc abstractions
From: Alvin Sun @ 2026-06-27 9:28 UTC (permalink / raw)
To: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Luis Chamberlain, Petr Pavlu, Daniel Gomez,
Sami Tolvanen, Aaron Tomlin, Greg Kroah-Hartman,
Rafael J. Wysocki, David Airlie, Simona Vetter, Daniel Almeida,
Arnd Bergmann, Brendan Higgins, David Gow, Rae Moar, Breno Leitao,
Jens Axboe, Dave Ertman, Leon Romanovsky, Igor Korotin,
FUJITA Tomonori, Bjorn Helgaas, Krzysztof Wilczyński,
Arve Hjønnevåg, Todd Kjos, Christian Brauner,
Carlos Llamas
Cc: rust-for-linux, linux-modules, driver-core, dri-devel, nova-gpu,
linux-kselftest, kunit-dev, linux-block, linux-kernel, netdev,
linux-pci, Alvin Sun
During tyr debugfs development, a kernel NULL pointer dereference was
encountered after `rmmod tyr` while gnome-shell still held /dev/card1 open:
```
[158827.868132] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
[158827.868918] Mem abort info:
[158827.869177] ESR = 0x0000000086000004
[158827.869519] EC = 0x21: IABT (current EL), IL = 32 bits
[158827.870000] SET = 0, FnV = 0
[158827.870281] EA = 0, S1PTW = 0
[158827.870571] FSC = 0x04: level 0 translation fault
[158827.871043] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000108dec000
[158827.871623] [0000000000000000] pgd=0000000000000000, p4d=0000000000000000
[158827.872242] Internal error: Oops: 0000000086000004 [#1] SMP
[158827.872246] Modules linked in: tyr sunrpc snd_soc_simple_card rk805_pwrkey snd_soc_simple_card_utils rtw88_8822bu display_connector rtw88_usb rtw88_8822b snd_soc_rockchip_i2s_tdm snd_soc_hdmi_codec
rtw88_core]
[158827.872337] CPU: 4 UID: 1000 PID: 11276 Comm: gnome-s:disk$0 Tainted: G N 7.1.0-rc1+ #331 PREEMPT
[158827.880534] Tainted: [N]=TEST
[158827.880535] Hardware name: FriendlyElec NanoPi R6C/NanoPi R6C, BIOS v1.1 04/09/2025
[158827.880538] pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[158827.880542] pc : 0x0
[158827.880547] lr : _RNvNtCs257m05FHVbX_3tyr2vm8pt_unmap+0x8c/0x12c [tyr]
[158827.880578] sp : ffff800083c236b0
[158827.880579] x29: ffff800083c236d0 x28: ffff00013f8a0000 x27: 0000000000000000
[158827.880585] x26: 000000000000007c x25: ffff000108e6ed80 x24: 0000000000401000
[158827.880590] x23: 0000000000000000 x22: 0000000040000000 x21: 0000000000001000
[158827.880595] x20: ffff00010f778138 x19: 0000000000400000 x18: 00000000ffffffff
[158827.880600] x17: 000000040044ffff x16: 045000f2b5503510 x15: 0720072007200720
[158827.880606] x14: 0720072007200720 x13: 0000000000401000 x12: 0000000000400000
[158827.880611] x11: ffff800083c239d0 x10: ffff000141e4fd88 x9 : 0000000000000000
[158827.880615] x8 : 0000000000000000 x7 : 0000000000000000 x6 : 0000000000400000
[158827.880620] x5 : ffff00013f8a0000 x4 : 0000000000000000 x3 : 0000000000000001
[158827.880625] x2 : 0000000000001000 x1 : 0000000000400000 x0 : ffff00010f778138
[158827.880630] Call trace:
[158827.880632] 0x0 (P)
[158827.880635] _RNvXs6_NtCs257m05FHVbX_3tyr2vmNtB5_9GpuVmDataNtNtNtCsgmSOfgXi5CZ_6kernel3drm5gpuvm11DriverGpuVm13sm_step_unmap+0x3c/0x120 [tyr]
[158827.891166] _RNvMs4_NtNtNtCsgmSOfgXi5CZ_6kernel3drm5gpuvm6sm_opsINtB7_5GpuVmNtNtCs257m05FHVbX_3tyr2vm9GpuVmDataE13sm_step_unmapB13_+0x18/0x34 [tyr]
[158827.891187] op_unmap_cb+0x78/0xb0
[158827.891196] __drm_gpuvm_sm_unmap+0x18c/0x1b4
[158827.891204] drm_gpuvm_sm_unmap+0x38/0x4c
[158827.891209] _RNvMs5_NtCs257m05FHVbX_3tyr2vmNtB5_2Vm7exec_op+0x1cc/0x254 [tyr]
[158827.894085] _RNvMs5_NtCs257m05FHVbX_3tyr2vmNtB5_2Vm11unmap_range+0x124/0x188 [tyr]
[158827.894105] _RINvNtCs5hGKnPbRUFW_4core3ptr13drop_in_placeNtNtCs257m05FHVbX_3tyr3gem8KernelBoEBK_+0x44/0xd8 [tyr]
[158827.894125] _RINvNtCs5hGKnPbRUFW_4core3ptr13drop_in_placeINtNtNtCsgmSOfgXi5CZ_6kernel5alloc4kvec3VecNtNtCs257m05FHVbX_3tyr2fw7SectionNtNtBL_9allocator7KmallocEEB1r_+0x3c/0x100 [tyr]
[158827.894147] _RINvNtCs5hGKnPbRUFW_4core3ptr13drop_in_placeINtNtNtCsgmSOfgXi5CZ_6kernel4sync3arc3ArcNtNtCs257m05FHVbX_3tyr2fw8FirmwareEEB1p_+0x94/0x190 [tyr]
[158827.894167] _RNvMs4_NtNtCsgmSOfgXi5CZ_6kernel3drm6deviceINtB5_6DeviceNtNtCs257m05FHVbX_3tyr6driver12TyrDrmDriverE7releaseBW_+0x30/0x98 [tyr]
[158827.899550] drm_dev_put.part.0+0x88/0xc0
[158827.899557] drm_minor_release+0x18/0x28
[158827.899562] drm_release+0x144/0x170
[158827.899567] __fput+0xe4/0x30c
[158827.899573] ____fput+0x14/0x20
[158827.899579] task_work_run+0x7c/0xe8
[158827.899586] do_exit+0x2a8/0xac4
[158827.899590] do_group_exit+0x34/0x90
[158827.899594] get_signal+0xaac/0xabc
[158827.899599] arch_do_signal_or_restart+0x90/0x3e8
[158827.899606] exit_to_user_mode_loop+0x140/0x1d0
[158827.899613] el0_svc+0x2f4/0x2f8
[158827.899620] el0t_64_sync_handler+0xa0/0xe4
[158827.899627] el0t_64_sync+0x198/0x19c
[158827.899632] ---[ end trace 0000000000000000 ]---
```
The root cause: `fops.owner` was `NULL` in Rust DRM drivers, so the kernel
never blocked module unloading while file descriptors were open. This leads to
use-after-free when drm_release (or other fops) is called on freed module code.
The series moves `THIS_MODULE` into the `ModuleMetadata` as a const, threads it
through `#[vtable]` to set `fops.owner` in DRM/miscdevice, and updates configfs
and rnull to use `this_module::<LocalModule>()`.
Assisted-by: opencode:glm-5.2
Signed-off-by: Alvin Sun <alvin.sun@linux.dev>
---
Changes in v7:
- Use `crate::LocalModule` in `configfs_attrs!` and silence `clippy::crate_in_macro_def`, per Gary's review.
- Link to v6: https://lore.kernel.org/r/20260624-fix-fops-owner-v6-0-5295e333cb3e@linux.dev
Changes in v6:
- Update MAINTAINERS to cover the new `rust/kernel/module.rs`.
- Link to v5: https://lore.kernel.org/r/20260624-fix-fops-owner-v5-0-aa1cba242f05@linux.dev
Changes in v5:
- Add `#[inline]` to the `this_module()` helper.
- Fix configfs doc comment to reference `crate::LocalModule` instead of
bare `LocalModule`.
- Link to v4: https://lore.kernel.org/r/20260623-fix-fops-owner-v4-0-0daf5f077d5c@linux.dev
Changes in v4:
- Move module-related types into a new `rust/kernel/module.rs`.
- Migrate binder from the `module!`-generated `THIS_MODULE` static to
`this_module::<LocalModule>()`.
- Reorganise the series so that every commit builds independently, and
drop the legacy `THIS_MODULE` static once all users are migrated.
- Link to v3: https://lore.kernel.org/r/20260622-fix-fops-owner-v3-0-49d45cb37032@linux.dev
Changes in v3:
- Renamed vtable associated type `ThisModule` to `OwnerModule`
- Added `this_module()` helper for ergonomic `THIS_MODULE` access
- Refined vtable macro implementation: one-liner detection and single `defined_items` set
- Reordered commits to place doctest fallback before vtable auto-insert
- Link to v2: https://lore.kernel.org/r/20260521-fix-fops-owner-v2-0-fd99079c5a04@linux.dev
Changes in v2:
- Merged old `static THIS_MODULE` and v1's `MODULE_PTR` into a single
`ModuleMetadata::THIS_MODULE` const
- `#[vtable]` macro now auto-inserts `type ThisModule`, removing all per-driver
manual patches from v1
- Added configfs & rnull usage site updates and doctest `LocalModule` fallback
- Link to v1: https://lore.kernel.org/r/20260519-fix-fops-owner-v1-0-2ded9830da14@linux.dev
---
Alvin Sun (10):
rust: module: move module types into `module.rs`
rust: module: add `THIS_MODULE` const to `ModuleMetadata` trait
rust: doctest: add LocalModule fallback for #[vtable] ThisModule
rust: macros: auto-insert OwnerModule in #[vtable]
rust: drm: set fops.owner from driver module pointer
rust: miscdevice: set fops.owner from driver module pointer
rust: configfs: use `LocalModule` for `THIS_MODULE`
rust: binder: use `LocalModule` for `THIS_MODULE`
rust: macros: remove `THIS_MODULE` static from `module!`
rust: module: update MAINTAINERS to cover module.rs
MAINTAINERS | 2 +-
drivers/android/binder/rust_binder_main.rs | 3 +-
drivers/block/rnull/configfs.rs | 6 +--
rust/kernel/auxiliary.rs | 2 +-
rust/kernel/configfs.rs | 9 ++--
rust/kernel/drm/device.rs | 3 +-
rust/kernel/drm/gem/mod.rs | 4 +-
rust/kernel/i2c.rs | 2 +-
rust/kernel/lib.rs | 75 +++-------------------------
rust/kernel/miscdevice.rs | 4 +-
rust/kernel/module.rs | 80 ++++++++++++++++++++++++++++++
rust/kernel/net/phy.rs | 6 ++-
rust/kernel/pci.rs | 2 +-
rust/kernel/platform.rs | 2 +-
rust/kernel/usb.rs | 2 +-
rust/macros/lib.rs | 6 +++
rust/macros/module.rs | 34 ++++++-------
rust/macros/vtable.rs | 41 +++++++++++++--
scripts/rustdoc_test_gen.rs | 16 ++++++
19 files changed, 190 insertions(+), 109 deletions(-)
---
base-commit: b7e5ac83cb16f7ffd11dc23736f84276602100ed
change-id: 20260519-fix-fops-owner-e3a77bb27c6c
prerequisite-change-id: 20260519-miscdev-use-format-9ab7e83b1c11:v3
prerequisite-patch-id: 405b334ff0d48ad350014f05a2321bdbaa025400
prerequisite-patch-id: 604b631c81d5423f4ebb2e12ba2d22e9ce371bfc
prerequisite-patch-id: cb550d94cefe01920e0d3ced2b2bcbecd76f3907
prerequisite-patch-id: 3bc830839742591460cb86d9472c04f4686dc600
prerequisite-patch-id: 571058244bc8c7088638d2e3225713011246c7e9
prerequisite-patch-id: 347c5a3c6dbef9832bfce8419fc23e6e08ba477f
prerequisite-patch-id: 3e202d988b56b88446f7535e90d3f00cf5f15701
Best regards,
--
Alvin Sun <alvin.sun@linux.dev>
^ permalink raw reply
* [PATCH v7 01/10] rust: module: move module types into `module.rs`
From: Alvin Sun @ 2026-06-27 9:28 UTC (permalink / raw)
To: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Luis Chamberlain, Petr Pavlu, Daniel Gomez,
Sami Tolvanen, Aaron Tomlin, Greg Kroah-Hartman,
Rafael J. Wysocki, David Airlie, Simona Vetter, Daniel Almeida,
Arnd Bergmann, Brendan Higgins, David Gow, Rae Moar, Breno Leitao,
Jens Axboe, Dave Ertman, Leon Romanovsky, Igor Korotin,
FUJITA Tomonori, Bjorn Helgaas, Krzysztof Wilczyński,
Arve Hjønnevåg, Todd Kjos, Christian Brauner,
Carlos Llamas
Cc: rust-for-linux, linux-modules, driver-core, dri-devel, nova-gpu,
linux-kselftest, kunit-dev, linux-block, linux-kernel, netdev,
linux-pci, Alvin Sun
In-Reply-To: <20260627-fix-fops-owner-v7-0-33cd3990edf0@linux.dev>
Move `Module`, `InPlaceModule`, `ModuleMetadata` and `ThisModule` from
`lib.rs` into a new `rust/kernel/module.rs`. Re-export them from `lib.rs`
to avoid tree-wide changes.
Switch six bus driver registrations from `module.0` to the public
`ThisModule::as_ptr()` accessor, since the field is no longer visible
outside the new `module` submodule.
No functional change.
Assisted-by: opencode:glm-5.2
Acked-by: Danilo Krummrich <dakr@kernel.org>
Signed-off-by: Alvin Sun <alvin.sun@linux.dev>
---
rust/kernel/auxiliary.rs | 2 +-
rust/kernel/i2c.rs | 2 +-
rust/kernel/lib.rs | 75 +++++-------------------------------------------
rust/kernel/module.rs | 71 +++++++++++++++++++++++++++++++++++++++++++++
rust/kernel/net/phy.rs | 6 +++-
rust/kernel/pci.rs | 2 +-
rust/kernel/platform.rs | 2 +-
rust/kernel/usb.rs | 2 +-
8 files changed, 88 insertions(+), 74 deletions(-)
diff --git a/rust/kernel/auxiliary.rs b/rust/kernel/auxiliary.rs
index 93c0db1f66555..4a02f83240be3 100644
--- a/rust/kernel/auxiliary.rs
+++ b/rust/kernel/auxiliary.rs
@@ -63,7 +63,7 @@ unsafe fn register(
// SAFETY: `adrv` is guaranteed to be a valid `DriverType`.
to_result(unsafe {
- bindings::__auxiliary_driver_register(adrv.get(), module.0, name.as_char_ptr())
+ bindings::__auxiliary_driver_register(adrv.get(), module.as_ptr(), name.as_char_ptr())
})
}
diff --git a/rust/kernel/i2c.rs b/rust/kernel/i2c.rs
index 7b908f0c5a58d..24eff08f47123 100644
--- a/rust/kernel/i2c.rs
+++ b/rust/kernel/i2c.rs
@@ -142,7 +142,7 @@ unsafe fn register(
}
// SAFETY: `idrv` is guaranteed to be a valid `DriverType`.
- to_result(unsafe { bindings::i2c_register_driver(module.0, idrv.get()) })
+ to_result(unsafe { bindings::i2c_register_driver(module.as_ptr(), idrv.get()) })
}
unsafe fn unregister(idrv: &Opaque<Self::DriverType>) {
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index b72b2fbe046d6..040ae85056509 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -93,6 +93,7 @@
pub mod maple_tree;
pub mod miscdevice;
pub mod mm;
+pub mod module;
pub mod module_param;
#[cfg(CONFIG_NET)]
pub mod net;
@@ -139,79 +140,17 @@
#[doc(hidden)]
pub use bindings;
pub use macros;
+pub use module::{
+ InPlaceModule,
+ Module,
+ ModuleMetadata,
+ ThisModule, //
+};
pub use uapi;
/// Prefix to appear before log messages printed from within the `kernel` crate.
const __LOG_PREFIX: &[u8] = b"rust_kernel\0";
-/// The top level entrypoint to implementing a kernel module.
-///
-/// For any teardown or cleanup operations, your type may implement [`Drop`].
-pub trait Module: Sized + Sync + Send {
- /// Called at module initialization time.
- ///
- /// Use this method to perform whatever setup or registration your module
- /// should do.
- ///
- /// Equivalent to the `module_init` macro in the C API.
- fn init(module: &'static ThisModule) -> error::Result<Self>;
-}
-
-/// A module that is pinned and initialised in-place.
-pub trait InPlaceModule: Sync + Send {
- /// Creates an initialiser for the module.
- ///
- /// It is called when the module is loaded.
- fn init(module: &'static ThisModule) -> impl pin_init::PinInit<Self, error::Error>;
-}
-
-impl<T: Module> InPlaceModule for T {
- fn init(module: &'static ThisModule) -> impl pin_init::PinInit<Self, error::Error> {
- let initer = move |slot: *mut Self| {
- let m = <Self as Module>::init(module)?;
-
- // SAFETY: `slot` is valid for write per the contract with `pin_init_from_closure`.
- unsafe { slot.write(m) };
- Ok(())
- };
-
- // SAFETY: On success, `initer` always fully initialises an instance of `Self`.
- unsafe { pin_init::pin_init_from_closure(initer) }
- }
-}
-
-/// Metadata attached to a [`Module`] or [`InPlaceModule`].
-pub trait ModuleMetadata {
- /// The name of the module as specified in the `module!` macro.
- const NAME: &'static crate::str::CStr;
-}
-
-/// Equivalent to `THIS_MODULE` in the C API.
-///
-/// C header: [`include/linux/init.h`](srctree/include/linux/init.h)
-pub struct ThisModule(*mut bindings::module);
-
-// SAFETY: `THIS_MODULE` may be used from all threads within a module.
-unsafe impl Sync for ThisModule {}
-
-impl ThisModule {
- /// Creates a [`ThisModule`] given the `THIS_MODULE` pointer.
- ///
- /// # Safety
- ///
- /// The pointer must be equal to the right `THIS_MODULE`.
- pub const unsafe fn from_ptr(ptr: *mut bindings::module) -> ThisModule {
- ThisModule(ptr)
- }
-
- /// Access the raw pointer for this module.
- ///
- /// It is up to the user to use it correctly.
- pub const fn as_ptr(&self) -> *mut bindings::module {
- self.0
- }
-}
-
#[cfg(not(testlib))]
#[panic_handler]
fn panic(info: &core::panic::PanicInfo<'_>) -> ! {
diff --git a/rust/kernel/module.rs b/rust/kernel/module.rs
new file mode 100644
index 0000000000000..be242a82e86d2
--- /dev/null
+++ b/rust/kernel/module.rs
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Module-related types and helpers.
+
+/// The entrypoint to implementing a kernel module.
+///
+/// For any teardown or cleanup operations, your type may implement [`Drop`].
+pub trait Module: Sized + Sync + Send {
+ /// Called at module initialization time.
+ ///
+ /// Use this method to perform whatever setup or registration your module
+ /// should do.
+ ///
+ /// Equivalent to the `module_init` macro in the C API.
+ fn init(module: &'static ThisModule) -> crate::error::Result<Self>;
+}
+
+/// A module that is pinned and initialised in-place.
+pub trait InPlaceModule: Sync + Send {
+ /// Creates an initialiser for the module.
+ ///
+ /// It is called when the module is loaded.
+ fn init(module: &'static ThisModule) -> impl pin_init::PinInit<Self, crate::error::Error>;
+}
+
+impl<T: Module> InPlaceModule for T {
+ fn init(module: &'static ThisModule) -> impl pin_init::PinInit<Self, crate::error::Error> {
+ let initer = move |slot: *mut Self| {
+ let m = <Self as Module>::init(module)?;
+
+ // SAFETY: `slot` is valid for write per the contract with `pin_init_from_closure`.
+ unsafe { slot.write(m) };
+ Ok(())
+ };
+
+ // SAFETY: On success, `initer` always fully initialises an instance of `Self`.
+ unsafe { pin_init::pin_init_from_closure(initer) }
+ }
+}
+
+/// Metadata attached to a [`Module`] or [`InPlaceModule`].
+pub trait ModuleMetadata {
+ /// The name of the module as specified in the `module!` macro.
+ const NAME: &'static crate::str::CStr;
+}
+
+/// Equivalent to `THIS_MODULE` in the C API.
+///
+/// C header: [`include/linux/init.h`](srctree/include/linux/init.h)
+pub struct ThisModule(*mut crate::bindings::module);
+
+// SAFETY: `THIS_MODULE` may be used from all threads within a module.
+unsafe impl Sync for ThisModule {}
+
+impl ThisModule {
+ /// Creates a [`ThisModule`] given the `THIS_MODULE` pointer.
+ ///
+ /// # Safety
+ ///
+ /// The pointer must be equal to the right `THIS_MODULE`.
+ pub const unsafe fn from_ptr(ptr: *mut crate::bindings::module) -> ThisModule {
+ ThisModule(ptr)
+ }
+
+ /// Access the raw pointer for this module.
+ ///
+ /// It is up to the user to use it correctly.
+ pub const fn as_ptr(&self) -> *mut crate::bindings::module {
+ self.0
+ }
+}
diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs
index 3ca99db5cccf2..8b7036b8fe480 100644
--- a/rust/kernel/net/phy.rs
+++ b/rust/kernel/net/phy.rs
@@ -659,7 +659,11 @@ pub fn register(
// the `drivers` slice are initialized properly. `drivers` will not be moved.
// So it's just an FFI call.
to_result(unsafe {
- bindings::phy_drivers_register(drivers[0].0.get(), drivers.len().try_into()?, module.0)
+ bindings::phy_drivers_register(
+ drivers[0].0.get(),
+ drivers.len().try_into()?,
+ module.as_ptr(),
+ )
})?;
// INVARIANT: The `drivers` slice is successfully registered to the kernel via `phy_drivers_register`.
Ok(Registration { drivers })
diff --git a/rust/kernel/pci.rs b/rust/kernel/pci.rs
index af74ddff6114d..916ed2cb6b70b 100644
--- a/rust/kernel/pci.rs
+++ b/rust/kernel/pci.rs
@@ -86,7 +86,7 @@ unsafe fn register(
// SAFETY: `pdrv` is guaranteed to be a valid `DriverType`.
to_result(unsafe {
- bindings::__pci_register_driver(pdrv.get(), module.0, name.as_char_ptr())
+ bindings::__pci_register_driver(pdrv.get(), module.as_ptr(), name.as_char_ptr())
})
}
diff --git a/rust/kernel/platform.rs b/rust/kernel/platform.rs
index 8917d4ee499fb..9fdbafd53bc21 100644
--- a/rust/kernel/platform.rs
+++ b/rust/kernel/platform.rs
@@ -82,7 +82,7 @@ unsafe fn register(
}
// SAFETY: `pdrv` is guaranteed to be a valid `DriverType`.
- to_result(unsafe { bindings::__platform_driver_register(pdrv.get(), module.0) })
+ to_result(unsafe { bindings::__platform_driver_register(pdrv.get(), module.as_ptr()) })
}
unsafe fn unregister(pdrv: &Opaque<Self::DriverType>) {
diff --git a/rust/kernel/usb.rs b/rust/kernel/usb.rs
index 9c17a672cd275..213db32727c17 100644
--- a/rust/kernel/usb.rs
+++ b/rust/kernel/usb.rs
@@ -63,7 +63,7 @@ unsafe fn register(
// SAFETY: `udrv` is guaranteed to be a valid `DriverType`.
to_result(unsafe {
- bindings::usb_register_driver(udrv.get(), module.0, name.as_char_ptr())
+ bindings::usb_register_driver(udrv.get(), module.as_ptr(), name.as_char_ptr())
})
}
--
2.43.0
^ permalink raw reply related
* [PATCH v7 04/10] rust: macros: auto-insert OwnerModule in #[vtable]
From: Alvin Sun @ 2026-06-27 9:28 UTC (permalink / raw)
To: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Luis Chamberlain, Petr Pavlu, Daniel Gomez,
Sami Tolvanen, Aaron Tomlin, Greg Kroah-Hartman,
Rafael J. Wysocki, David Airlie, Simona Vetter, Daniel Almeida,
Arnd Bergmann, Brendan Higgins, David Gow, Rae Moar, Breno Leitao,
Jens Axboe, Dave Ertman, Leon Romanovsky, Igor Korotin,
FUJITA Tomonori, Bjorn Helgaas, Krzysztof Wilczyński,
Arve Hjønnevåg, Todd Kjos, Christian Brauner,
Carlos Llamas
Cc: rust-for-linux, linux-modules, driver-core, dri-devel, nova-gpu,
linux-kselftest, kunit-dev, linux-block, linux-kernel, netdev,
linux-pci, Alvin Sun
In-Reply-To: <20260627-fix-fops-owner-v7-0-33cd3990edf0@linux.dev>
Auto-add `type OwnerModule: ::kernel::ModuleMetadata;` as a required
associated type on the trait side if not already defined, and
auto-insert `type OwnerModule = crate::LocalModule;` on the impl side
if not explicitly provided, eliminating the need to manually declare
and implement `OwnerModule` in every vtable trait and impl.
Assisted-by: opencode:glm-5.2
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Suggested-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/all/DIMMWHUOLPSH.13JFRHDKDQJGO@garyguo.net
Reviewed-by: Gary Guo <gary@garyguo.net>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Signed-off-by: Alvin Sun <alvin.sun@linux.dev>
---
rust/macros/lib.rs | 6 ++++++
rust/macros/vtable.rs | 41 ++++++++++++++++++++++++++++++++++++-----
2 files changed, 42 insertions(+), 5 deletions(-)
diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs
index 2cfd59e0f9e7c..bc7ded353c5ca 100644
--- a/rust/macros/lib.rs
+++ b/rust/macros/lib.rs
@@ -176,6 +176,12 @@ pub fn module(input: TokenStream) -> TokenStream {
///
/// This macro should not be used when all functions are required.
///
+/// Additionally, this macro automatically handles the `OwnerModule`
+/// associated type: on the trait side, `type OwnerModule: ModuleMetadata;`
+/// is added as a required associated type if not already defined; on the
+/// impl side, `type OwnerModule = LocalModule;` is automatically inserted
+/// if not explicitly defined.
+///
/// # Examples
///
/// ```
diff --git a/rust/macros/vtable.rs b/rust/macros/vtable.rs
index c6510b0c4ea1d..be9a5ed8abe5e 100644
--- a/rust/macros/vtable.rs
+++ b/rust/macros/vtable.rs
@@ -30,6 +30,22 @@ fn handle_trait(mut item: ItemTrait) -> Result<ItemTrait> {
const USE_VTABLE_ATTR: ();
});
+ // Add `type OwnerModule: ModuleMetadata` as a required associated type if
+ // the trait does not already define it.
+ if !item
+ .items
+ .iter()
+ .any(|i| matches!(i, TraitItem::Type(t) if t.ident == "OwnerModule"))
+ {
+ gen_items.push(parse_quote! {
+ /// The module implementing this vtable trait.
+ ///
+ /// Automatically set to `crate::LocalModule` by the `#[vtable]`
+ /// impl macro.
+ type OwnerModule: ::kernel::ModuleMetadata;
+ });
+ }
+
for item in &item.items {
if let TraitItem::Fn(fn_item) = item {
let name = &fn_item.sig.ident;
@@ -57,12 +73,18 @@ fn handle_trait(mut item: ItemTrait) -> Result<ItemTrait> {
fn handle_impl(mut item: ItemImpl) -> Result<ItemImpl> {
let mut gen_items = Vec::new();
- let mut defined_consts = HashSet::new();
+ let mut defined_items = HashSet::new();
- // Iterate over all user-defined constants to gather any possible explicit overrides.
+ // Iterate over all user-defined items to gather any possible explicit overrides.
for item in &item.items {
- if let ImplItem::Const(const_item) = item {
- defined_consts.insert(const_item.ident.clone());
+ match item {
+ ImplItem::Const(const_item) => {
+ defined_items.insert(const_item.ident.clone());
+ }
+ ImplItem::Type(type_item) => {
+ defined_items.insert(type_item.ident.clone());
+ }
+ _ => {}
}
}
@@ -70,6 +92,15 @@ fn handle_impl(mut item: ItemImpl) -> Result<ItemImpl> {
const USE_VTABLE_ATTR: () = ();
});
+ // Auto-insert `type OwnerModule = crate::LocalModule` if not explicitly defined.
+ // `crate::LocalModule` resolves to the real module type (via `module!`) or a
+ // dummy fallback in non-module contexts (e.g., doctests).
+ if !defined_items.contains(&parse_quote!(OwnerModule)) {
+ gen_items.push(parse_quote! {
+ type OwnerModule = crate::LocalModule;
+ });
+ }
+
for item in &item.items {
if let ImplItem::Fn(fn_item) = item {
let name = &fn_item.sig.ident;
@@ -78,7 +109,7 @@ fn handle_impl(mut item: ItemImpl) -> Result<ItemImpl> {
name.span(),
);
// Skip if it's declared already -- this allows user override.
- if defined_consts.contains(&gen_const_name) {
+ if defined_items.contains(&gen_const_name) {
continue;
}
let cfg_attrs = crate::helpers::gather_cfg_attrs(&fn_item.attrs);
--
2.43.0
^ permalink raw reply related
* [PATCH v7 03/10] rust: doctest: add LocalModule fallback for #[vtable] ThisModule
From: Alvin Sun @ 2026-06-27 9:28 UTC (permalink / raw)
To: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Luis Chamberlain, Petr Pavlu, Daniel Gomez,
Sami Tolvanen, Aaron Tomlin, Greg Kroah-Hartman,
Rafael J. Wysocki, David Airlie, Simona Vetter, Daniel Almeida,
Arnd Bergmann, Brendan Higgins, David Gow, Rae Moar, Breno Leitao,
Jens Axboe, Dave Ertman, Leon Romanovsky, Igor Korotin,
FUJITA Tomonori, Bjorn Helgaas, Krzysztof Wilczyński,
Arve Hjønnevåg, Todd Kjos, Christian Brauner,
Carlos Llamas
Cc: rust-for-linux, linux-modules, driver-core, dri-devel, nova-gpu,
linux-kselftest, kunit-dev, linux-block, linux-kernel, netdev,
linux-pci, Alvin Sun
In-Reply-To: <20260627-fix-fops-owner-v7-0-33cd3990edf0@linux.dev>
Add a `LocalModule` struct with a null-pointer `ModuleMetadata` impl
in the doctest harness, so that `crate::LocalModule` (auto-inserted
by `#[vtable]`) resolves correctly when there is no `module!` macro.
Assisted-by: opencode:glm-5.2
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Reviewed-by: Gary Guo <gary@garyguo.net>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Signed-off-by: Alvin Sun <alvin.sun@linux.dev>
---
scripts/rustdoc_test_gen.rs | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/scripts/rustdoc_test_gen.rs b/scripts/rustdoc_test_gen.rs
index ee76e96b41eea..198af4e446c8c 100644
--- a/scripts/rustdoc_test_gen.rs
+++ b/scripts/rustdoc_test_gen.rs
@@ -239,6 +239,22 @@ macro_rules! assert_eq {{
const __LOG_PREFIX: &[u8] = b"rust_doctests_kernel\0";
+/// Dummy module type for doctest context.
+struct LocalModule;
+
+use kernel::{{
+ str::CStr,
+ ModuleMetadata,
+ ThisModule, //
+}};
+use core::ptr::null_mut;
+
+impl ModuleMetadata for LocalModule {{
+ const NAME: &'static CStr = c"rust_doctests_kernel";
+ // SAFETY: `try_module_get`/`module_put` handle null module pointers gracefully.
+ const THIS_MODULE: ThisModule = unsafe {{ ThisModule::from_ptr(null_mut()) }};
+}}
+
{rust_tests}
"#
)
--
2.43.0
^ permalink raw reply related
* [PATCH v7 06/10] rust: miscdevice: set fops.owner from driver module pointer
From: Alvin Sun @ 2026-06-27 9:28 UTC (permalink / raw)
To: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Luis Chamberlain, Petr Pavlu, Daniel Gomez,
Sami Tolvanen, Aaron Tomlin, Greg Kroah-Hartman,
Rafael J. Wysocki, David Airlie, Simona Vetter, Daniel Almeida,
Arnd Bergmann, Brendan Higgins, David Gow, Rae Moar, Breno Leitao,
Jens Axboe, Dave Ertman, Leon Romanovsky, Igor Korotin,
FUJITA Tomonori, Bjorn Helgaas, Krzysztof Wilczyński,
Arve Hjønnevåg, Todd Kjos, Christian Brauner,
Carlos Llamas
Cc: rust-for-linux, linux-modules, driver-core, dri-devel, nova-gpu,
linux-kselftest, kunit-dev, linux-block, linux-kernel, netdev,
linux-pci, Alvin Sun
In-Reply-To: <20260627-fix-fops-owner-v7-0-33cd3990edf0@linux.dev>
Set the miscdevice fops owner field from the driver module pointer
via the `this_module::<T::OwnerModule>()` helper, instead of
defaulting to null.
Assisted-by: opencode:glm-5.2
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Reviewed-by: Gary Guo <gary@garyguo.net>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Signed-off-by: Alvin Sun <alvin.sun@linux.dev>
---
rust/kernel/miscdevice.rs | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/rust/kernel/miscdevice.rs b/rust/kernel/miscdevice.rs
index 83ce50def5ac9..2a4329f98614e 100644
--- a/rust/kernel/miscdevice.rs
+++ b/rust/kernel/miscdevice.rs
@@ -24,12 +24,13 @@
IovIterSource, //
},
mm::virt::VmaNew,
+ module::this_module,
prelude::*,
seq_file::SeqFile,
types::{
ForeignOwnable,
Opaque, //
- },
+ }, //
};
use core::marker::PhantomData;
@@ -430,6 +431,7 @@ impl<T: MiscDevice> MiscdeviceVTable<T> {
} else {
None
},
+ owner: this_module::<T::OwnerModule>().as_ptr(),
..pin_init::zeroed()
};
--
2.43.0
^ permalink raw reply related
* [PATCH v7 05/10] rust: drm: set fops.owner from driver module pointer
From: Alvin Sun @ 2026-06-27 9:28 UTC (permalink / raw)
To: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Luis Chamberlain, Petr Pavlu, Daniel Gomez,
Sami Tolvanen, Aaron Tomlin, Greg Kroah-Hartman,
Rafael J. Wysocki, David Airlie, Simona Vetter, Daniel Almeida,
Arnd Bergmann, Brendan Higgins, David Gow, Rae Moar, Breno Leitao,
Jens Axboe, Dave Ertman, Leon Romanovsky, Igor Korotin,
FUJITA Tomonori, Bjorn Helgaas, Krzysztof Wilczyński,
Arve Hjønnevåg, Todd Kjos, Christian Brauner,
Carlos Llamas
Cc: rust-for-linux, linux-modules, driver-core, dri-devel, nova-gpu,
linux-kselftest, kunit-dev, linux-block, linux-kernel, netdev,
linux-pci, Alvin Sun
In-Reply-To: <20260627-fix-fops-owner-v7-0-33cd3990edf0@linux.dev>
Change `create_fops()` to accept an owner module pointer instead of
hardcoding `null_mut()`, ensuring the kernel correctly tracks the
module owning the DRM device's file operations.
Assisted-by: opencode:glm-5.2
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Reviewed-by: Gary Guo <gary@garyguo.net>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Signed-off-by: Alvin Sun <alvin.sun@linux.dev>
---
rust/kernel/drm/device.rs | 3 ++-
rust/kernel/drm/gem/mod.rs | 4 ++--
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/rust/kernel/drm/device.rs b/rust/kernel/drm/device.rs
index 403fc35353c74..d92cacb665366 100644
--- a/rust/kernel/drm/device.rs
+++ b/rust/kernel/drm/device.rs
@@ -111,7 +111,8 @@ impl<T: drm::Driver> Device<T> {
fops: &Self::GEM_FOPS,
};
- const GEM_FOPS: bindings::file_operations = drm::gem::create_fops();
+ const GEM_FOPS: bindings::file_operations =
+ drm::gem::create_fops(crate::module::this_module::<T::OwnerModule>().as_ptr());
/// Create a new `drm::Device` for a `drm::Driver`.
pub fn new(dev: &device::Device, data: impl PinInit<T::Data, Error>) -> Result<ARef<Self>> {
diff --git a/rust/kernel/drm/gem/mod.rs b/rust/kernel/drm/gem/mod.rs
index 01b5bd47a3332..9a203efc59116 100644
--- a/rust/kernel/drm/gem/mod.rs
+++ b/rust/kernel/drm/gem/mod.rs
@@ -357,10 +357,10 @@ impl<T: DriverObject> AllocImpl for Object<T> {
};
}
-pub(super) const fn create_fops() -> bindings::file_operations {
+pub(super) const fn create_fops(owner: *mut bindings::module) -> bindings::file_operations {
let mut fops: bindings::file_operations = pin_init::zeroed();
- fops.owner = core::ptr::null_mut();
+ fops.owner = owner;
fops.open = Some(bindings::drm_open);
fops.release = Some(bindings::drm_release);
fops.unlocked_ioctl = Some(bindings::drm_ioctl);
--
2.43.0
^ permalink raw reply related
* [PATCH v7 07/10] rust: configfs: use `LocalModule` for `THIS_MODULE`
From: Alvin Sun @ 2026-06-27 9:28 UTC (permalink / raw)
To: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Luis Chamberlain, Petr Pavlu, Daniel Gomez,
Sami Tolvanen, Aaron Tomlin, Greg Kroah-Hartman,
Rafael J. Wysocki, David Airlie, Simona Vetter, Daniel Almeida,
Arnd Bergmann, Brendan Higgins, David Gow, Rae Moar, Breno Leitao,
Jens Axboe, Dave Ertman, Leon Romanovsky, Igor Korotin,
FUJITA Tomonori, Bjorn Helgaas, Krzysztof Wilczyński,
Arve Hjønnevåg, Todd Kjos, Christian Brauner,
Carlos Llamas
Cc: rust-for-linux, linux-modules, driver-core, dri-devel, nova-gpu,
linux-kselftest, kunit-dev, linux-block, linux-kernel, netdev,
linux-pci, Alvin Sun
In-Reply-To: <20260627-fix-fops-owner-v7-0-33cd3990edf0@linux.dev>
Replace the `THIS_MODULE` static reference in the `configfs_attrs!`
macro with `this_module::<LocalModule>()`, and update
rnull to import `LocalModule` instead of `THIS_MODULE`, consistent
with the move of `THIS_MODULE` into the `ModuleMetadata` trait.
Assisted-by: opencode:glm-5.2
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Signed-off-by: Alvin Sun <alvin.sun@linux.dev>
---
drivers/block/rnull/configfs.rs | 6 ++----
rust/kernel/configfs.rs | 9 ++++++---
2 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/drivers/block/rnull/configfs.rs b/drivers/block/rnull/configfs.rs
index c10a55fc58948..b2547ad1e5ddd 100644
--- a/drivers/block/rnull/configfs.rs
+++ b/drivers/block/rnull/configfs.rs
@@ -1,9 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
-use super::{
- NullBlkDevice,
- THIS_MODULE, //
-};
+use super::NullBlkDevice;
+use crate::LocalModule;
use kernel::{
block::mq::gen_disk::{
GenDisk,
diff --git a/rust/kernel/configfs.rs b/rust/kernel/configfs.rs
index 2339c6467325d..cd082b83e9e74 100644
--- a/rust/kernel/configfs.rs
+++ b/rust/kernel/configfs.rs
@@ -875,13 +875,14 @@ fn as_ptr(&self) -> *const bindings::config_item_type {
/// configfs::Subsystem<Configuration>,
/// Configuration
/// >::new_with_child_ctor::<N,Child>(
-/// &THIS_MODULE,
+/// ::kernel::module::this_module::<crate::LocalModule>(),
/// &CONFIGURATION_ATTRS
/// );
///
/// &CONFIGURATION_TPE
/// }
/// ```
+#[allow(clippy::crate_in_macro_def)]
#[macro_export]
macro_rules! configfs_attrs {
(
@@ -1021,7 +1022,8 @@ macro_rules! configfs_attrs {
static [< $data:upper _TPE >] : $crate::configfs::ItemType<$container, $data> =
$crate::configfs::ItemType::<$container, $data>::new::<N>(
- &THIS_MODULE, &[<$ data:upper _ATTRS >]
+ $crate::module::this_module::<crate::LocalModule>(),
+ &[<$ data:upper _ATTRS >]
);
)?
@@ -1030,7 +1032,8 @@ macro_rules! configfs_attrs {
$crate::configfs::ItemType<$container, $data> =
$crate::configfs::ItemType::<$container, $data>::
new_with_child_ctor::<N, $child>(
- &THIS_MODULE, &[<$ data:upper _ATTRS >]
+ $crate::module::this_module::<crate::LocalModule>(),
+ &[<$ data:upper _ATTRS >]
);
)?
--
2.43.0
^ permalink raw reply related
* [PATCH v7 10/10] rust: module: update MAINTAINERS to cover module.rs
From: Alvin Sun @ 2026-06-27 9:28 UTC (permalink / raw)
To: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Luis Chamberlain, Petr Pavlu, Daniel Gomez,
Sami Tolvanen, Aaron Tomlin, Greg Kroah-Hartman,
Rafael J. Wysocki, David Airlie, Simona Vetter, Daniel Almeida,
Arnd Bergmann, Brendan Higgins, David Gow, Rae Moar, Breno Leitao,
Jens Axboe, Dave Ertman, Leon Romanovsky, Igor Korotin,
FUJITA Tomonori, Bjorn Helgaas, Krzysztof Wilczyński,
Arve Hjønnevåg, Todd Kjos, Christian Brauner,
Carlos Llamas
Cc: rust-for-linux, linux-modules, driver-core, dri-devel, nova-gpu,
linux-kselftest, kunit-dev, linux-block, linux-kernel, netdev,
linux-pci, Alvin Sun
In-Reply-To: <20260627-fix-fops-owner-v7-0-33cd3990edf0@linux.dev>
Module types now live in `rust/kernel/module.rs` alongside
`rust/kernel/module_param.rs`. Update the MODULE SUPPORT file pattern
from `rust/kernel/module_param.rs` to `rust/kernel/module*.rs` so both
files are covered.
Assisted-by: opencode:glm-5.2
Link: https://lore.kernel.org/rust-for-linux/8ea21b29-9baf-4926-a16f-7d21c5a1a1b8@suse.com
Signed-off-by: Alvin Sun <alvin.sun@linux.dev>
---
MAINTAINERS | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index e035a3be797c4..74733de3e41ee 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17984,7 +17984,7 @@ F: include/linux/module*.h
F: kernel/module/
F: lib/test_kmod.c
F: lib/tests/module/
-F: rust/kernel/module_param.rs
+F: rust/kernel/module*.rs
F: rust/macros/module.rs
F: scripts/module*
F: tools/testing/selftests/kmod/
--
2.43.0
^ permalink raw reply related
* [PATCH v7 08/10] rust: binder: use `LocalModule` for `THIS_MODULE`
From: Alvin Sun @ 2026-06-27 9:28 UTC (permalink / raw)
To: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Luis Chamberlain, Petr Pavlu, Daniel Gomez,
Sami Tolvanen, Aaron Tomlin, Greg Kroah-Hartman,
Rafael J. Wysocki, David Airlie, Simona Vetter, Daniel Almeida,
Arnd Bergmann, Brendan Higgins, David Gow, Rae Moar, Breno Leitao,
Jens Axboe, Dave Ertman, Leon Romanovsky, Igor Korotin,
FUJITA Tomonori, Bjorn Helgaas, Krzysztof Wilczyński,
Arve Hjønnevåg, Todd Kjos, Christian Brauner,
Carlos Llamas
Cc: rust-for-linux, linux-modules, driver-core, dri-devel, nova-gpu,
linux-kselftest, kunit-dev, linux-block, linux-kernel, netdev,
linux-pci, Alvin Sun
In-Reply-To: <20260627-fix-fops-owner-v7-0-33cd3990edf0@linux.dev>
Replace the `THIS_MODULE` static reference in the binder fops with
`this_module::<LocalModule>()`, consistent with the move of
`THIS_MODULE` into the `ModuleMetadata` trait.
Assisted-by: opencode:glm-5.2
Reviewed-by: Gary Guo <gary@garyguo.net>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Signed-off-by: Alvin Sun <alvin.sun@linux.dev>
---
drivers/android/binder/rust_binder_main.rs | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/android/binder/rust_binder_main.rs b/drivers/android/binder/rust_binder_main.rs
index dc1941cd2407b..d6ceebbd5f94e 100644
--- a/drivers/android/binder/rust_binder_main.rs
+++ b/drivers/android/binder/rust_binder_main.rs
@@ -17,6 +17,7 @@
bindings::{self, seq_file},
fs::File,
list::{ListArc, ListArcSafe, ListLinksSelfPtr, TryNewListArc},
+ module::this_module,
prelude::*,
seq_file::SeqFile,
seq_print,
@@ -318,7 +319,7 @@ unsafe impl<T> Sync for AssertSync<T> {}
let zeroed_ops = unsafe { core::mem::MaybeUninit::zeroed().assume_init() };
let ops = kernel::bindings::file_operations {
- owner: THIS_MODULE.as_ptr(),
+ owner: this_module::<LocalModule>().as_ptr(),
poll: Some(rust_binder_poll),
unlocked_ioctl: Some(rust_binder_ioctl),
compat_ioctl: bindings::compat_ptr_ioctl,
--
2.43.0
^ permalink raw reply related
* [PATCH v7 09/10] rust: macros: remove `THIS_MODULE` static from `module!`
From: Alvin Sun @ 2026-06-27 9:28 UTC (permalink / raw)
To: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Luis Chamberlain, Petr Pavlu, Daniel Gomez,
Sami Tolvanen, Aaron Tomlin, Greg Kroah-Hartman,
Rafael J. Wysocki, David Airlie, Simona Vetter, Daniel Almeida,
Arnd Bergmann, Brendan Higgins, David Gow, Rae Moar, Breno Leitao,
Jens Axboe, Dave Ertman, Leon Romanovsky, Igor Korotin,
FUJITA Tomonori, Bjorn Helgaas, Krzysztof Wilczyński,
Arve Hjønnevåg, Todd Kjos, Christian Brauner,
Carlos Llamas
Cc: rust-for-linux, linux-modules, driver-core, dri-devel, nova-gpu,
linux-kselftest, kunit-dev, linux-block, linux-kernel, netdev,
linux-pci, Alvin Sun
In-Reply-To: <20260627-fix-fops-owner-v7-0-33cd3990edf0@linux.dev>
All users have been migrated to `ModuleMetadata::THIS_MODULE` const or
`this_module::<LocalModule>()` helper. The `static THIS_MODULE`
generated by the `module!` macro is no longer referenced anywhere,
so remove it to avoid having two sources of the same `ThisModule`
pointer.
Assisted-by: opencode:glm-5.2
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Reviewed-by: Gary Guo <gary@garyguo.net>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Signed-off-by: Alvin Sun <alvin.sun@linux.dev>
---
rust/macros/module.rs | 16 ----------------
1 file changed, 16 deletions(-)
diff --git a/rust/macros/module.rs b/rust/macros/module.rs
index aa9a618d5d19e..23b6a1b456b80 100644
--- a/rust/macros/module.rs
+++ b/rust/macros/module.rs
@@ -497,22 +497,6 @@ pub(crate) fn module(info: ModuleInfo) -> Result<TokenStream> {
/// Used by the printing macros, e.g. [`info!`].
const __LOG_PREFIX: &[u8] = #name_cstr.to_bytes_with_nul();
- // SAFETY: `__this_module` is constructed by the kernel at load time and will not be
- // freed until the module is unloaded.
- #[cfg(MODULE)]
- static THIS_MODULE: ::kernel::ThisModule = unsafe {
- extern "C" {
- static __this_module: ::kernel::types::Opaque<::kernel::bindings::module>;
- };
-
- ::kernel::ThisModule::from_ptr(__this_module.get())
- };
-
- #[cfg(not(MODULE))]
- static THIS_MODULE: ::kernel::ThisModule = unsafe {
- ::kernel::ThisModule::from_ptr(::core::ptr::null_mut())
- };
-
/// The `LocalModule` type is the type of the module created by `module!`,
/// `module_pci_driver!`, `module_platform_driver!`, etc.
type LocalModule = #type_;
--
2.43.0
^ permalink raw reply related
* Re: [PATCH v6 07/10] rust: configfs: use `LocalModule` for `THIS_MODULE`
From: Alvin Sun @ 2026-06-27 13:10 UTC (permalink / raw)
To: Gary Guo, Miguel Ojeda, Boqun Feng, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Luis Chamberlain, Petr Pavlu, Daniel Gomez,
Sami Tolvanen, Aaron Tomlin, Greg Kroah-Hartman,
Rafael J. Wysocki, David Airlie, Simona Vetter, Daniel Almeida,
Arnd Bergmann, Brendan Higgins, David Gow, Rae Moar, Breno Leitao,
Jens Axboe, Dave Ertman, Leon Romanovsky, Igor Korotin,
FUJITA Tomonori, Bjorn Helgaas, Krzysztof Wilczyński,
Arve Hjønnevåg, Todd Kjos, Christian Brauner,
Carlos Llamas
Cc: rust-for-linux, linux-modules, driver-core, dri-devel, nova-gpu,
linux-kselftest, kunit-dev, linux-block, linux-kernel, netdev,
linux-pci
In-Reply-To: <DJJ25JJ3TDO9.1UFOP60U0IPX5@garyguo.net>
On 6/26/26 22:41, Gary Guo wrote:
> On Fri Jun 26, 2026 at 3:35 AM BST, Alvin Sun wrote:
>> On 6/25/26 22:40, Gary Guo wrote:
>>> On Wed Jun 24, 2026 at 4:00 PM BST, Alvin Sun wrote:
>>>> Replace the `THIS_MODULE` static reference in the `configfs_attrs!`
>>>> macro with `this_module::<LocalModule>()`, and update
>>>> rnull to import `LocalModule` instead of `THIS_MODULE`, consistent
>>>> with the move of `THIS_MODULE` into the `ModuleMetadata` trait.
>>>>
>>>> Assisted-by: opencode:glm-5.2
>>>> Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
>>>> Acked-by: Danilo Krummrich <dakr@kernel.org>
>>>> Signed-off-by: Alvin Sun <alvin.sun@linux.dev>
>>>> ---
>>>> drivers/block/rnull/configfs.rs | 6 ++----
>>>> rust/kernel/configfs.rs | 8 +++++---
>>>> 2 files changed, 7 insertions(+), 7 deletions(-)
>>>>
>>>> diff --git a/drivers/block/rnull/configfs.rs b/drivers/block/rnull/configfs.rs
>>>> index c10a55fc58948..b2547ad1e5ddd 100644
>>>> --- a/drivers/block/rnull/configfs.rs
>>>> +++ b/drivers/block/rnull/configfs.rs
>>>> @@ -1,9 +1,7 @@
>>>> // SPDX-License-Identifier: GPL-2.0
>>>>
>>>> -use super::{
>>>> - NullBlkDevice,
>>>> - THIS_MODULE, //
>>>> -};
>>>> +use super::NullBlkDevice;
>>>> +use crate::LocalModule;
>>>> use kernel::{
>>>> block::mq::gen_disk::{
>>>> GenDisk,
>>>> diff --git a/rust/kernel/configfs.rs b/rust/kernel/configfs.rs
>>>> index 2339c6467325d..c31d7882e216d 100644
>>>> --- a/rust/kernel/configfs.rs
>>>> +++ b/rust/kernel/configfs.rs
>>>> @@ -875,7 +875,7 @@ fn as_ptr(&self) -> *const bindings::config_item_type {
>>>> /// configfs::Subsystem<Configuration>,
>>>> /// Configuration
>>>> /// >::new_with_child_ctor::<N,Child>(
>>>> -/// &THIS_MODULE,
>>>> +/// ::kernel::module::this_module::<crate::LocalModule>(),
>>>> /// &CONFIGURATION_ATTRS
>>>> /// );
>>>> ///
>>>> @@ -1021,7 +1021,8 @@ macro_rules! configfs_attrs {
>>>>
>>>> static [< $data:upper _TPE >] : $crate::configfs::ItemType<$container, $data> =
>>>> $crate::configfs::ItemType::<$container, $data>::new::<N>(
>>>> - &THIS_MODULE, &[<$ data:upper _ATTRS >]
>>>> + $crate::module::this_module::<LocalModule>(),
>>> ^ You only changed one single place. This is still plain `LocalModule`.
>> Initially I wrote it as `crate::LocalModule`, but clippy warned about it. So
>> instead of putting the crate path in the macro body, I added `use
>> crate::LocalModule` in the calling file.
>>
>> ```
>> warning: `crate` references the macro call's crate
>> --> rust/kernel/configfs.rs:1024:59
>> |
>> 1024 | ... $crate::module::this_module::<crate::LocalModule>(),
>> | ^^^^^ help:
>> to reference the macro definition's crate, use: `$crate`
>> |
>> = help: for further information visit
>> https://rust-lang.github.io/rust-clippy/rust-1.94.0/index.html#crate_in_macro_def
>> = note: `-W clippy::crate-in-macro-def` implied by `-W clippy::all`
>> = help: to override `-W clippy::all` add
>> `#[allow(clippy::crate_in_macro_def)]`
>>
>> warning: 1 warning emitted
>> ```
> Clippy has a point about `crate::` being usually wrong in macros, but it is what
> we actually want here, so obviously you should allow the warning.
>
> It is the exact same case in `vtable` macro, just that Clippy is unable to check
> proc macros!
Thanks for the detailed explanation.
I specifically searched for issues related to `crate_in_macro_def`, and
this information is very useful to me.
Best regards,
Alvin
>
> Best,
> Gary
>
>> Alternatively, `#[allow(clippy::crate_in_macro_def)]` could be added on
>> the macro
>> definition. Would you suggest that approach?
^ permalink raw reply
* Re: [PATCH] init/main: Expose built-in initcalls and blacklist status via debugfs
From: Aaron Tomlin @ 2026-06-28 22:58 UTC (permalink / raw)
To: Andrew Morton
Cc: arnd, mcgrof, petr.pavlu, da.gomez, samitolvanen, neelx, sean,
chjohnst, steve, mproche, nick.lane, linux-arch, linux-modules,
linux-kernel
In-Reply-To: <20260625165011.63b47ca601b6f871797d98ac@linux-foundation.org>
On Thu, Jun 25, 2026 at 04:50:11PM -0700, Andrew Morton wrote:
> On Sun, 10 May 2026 02:13:01 -0400 Aaron Tomlin <atomlin@atomlin.com> wrote:
>
> > At present, identifying the correct function name to supply to the
> > "initcall_blacklist=" kernel command-line parameter requires manual
> > inspection of the source code or kernel symbol tables. Furthermore,
> > administrators lack a reliable runtime mechanism to verify whether a
> > specified built-in module has been successfully blacklisted.
>
> I expect nobody has felt a need for this in their day-to-day work, so
> the interest is low.
>
> A detailed description of the use-cases would be of benefit - help
> people better understand the value of this to our users. I suggest you
> add this info and send a v2, if motivated.
Hi Andrew,
Thank you for taking the time to review the patch. I appreciate the
pragmatic feedback.
> > To resolve this, introduce a new debugfs interface at
> > /sys/kernel/debug/modules/builtin_initcalls. This file enumerates all
> > built-in modules alongside their corresponding initialisation callbacks
> > (e.g., those specified by module_init()) in a simple format:
> > "module_name init_callback".
>
> Isn't this information all available at build time?
>
> Can we extract it and put it in some file somewhere which becomes part
> of the distributed kernel package?
It is indeed possible to extract this. We currently generate
modules.builtin, but it only lists module paths, not the corresponding
initcall function names. While a userspace application could theoretically
parse System.map to find these relationships, this approach assumes the
presence of Linux kernel packages on the target server. In some
environments, these files are frequently stripped or omitted entirely.
> > If a built-in module has been actively
> > blacklisted, the entry is explicitly appended with a " [blacklisted]"
> > suffix.
>
> Can this be added to the /proc/modules output in some fashion? Perhaps
> just add TAINT_BLACKLISTED and we get this info almost for free?
Unfortunately, we cannot append this information to /proc/modules. That
interface iterates over the kernel's modules list, which relies on struct
module metadata. Because built-in modules are statically linked into
vmlinux, they lack this runtime structure entirely and are invisible to
/proc/modules.
Petr Pavlu offered excellent advice — extend module_blacklist to also
cover built-in modules [1] — I do like this idea.
[1]: https://lore.kernel.org/lkml/79ace94f-31d3-4a5e-9a47-3fad69304fe5@suse.com/
Kind regards,
--
Aaron Tomlin
^ permalink raw reply
* Re: [PATCH] kbuild: Use --force-group-allocation when linking modules
From: Nathan Chancellor @ 2026-06-30 1:54 UTC (permalink / raw)
To: Petr Pavlu
Cc: Nathan Chancellor, Nicolas Schier, Catalin Marinas, Will Deacon,
Peter Collingbourne, Sami Tolvanen, Daniel Gomez,
Luis Chamberlain, Aaron Tomlin, linux-kbuild, linux-arm-kernel,
linux-modules, linux-kernel
In-Reply-To: <20260612133139.1919042-1-petr.pavlu@suse.com>
On Fri, 12 Jun 2026 15:31:37 +0200, Petr Pavlu <petr.pavlu@suse.com> wrote:
> Specific code, such as outlined KASAN checks, may be placed in
> COMDAT-deduplicated sections. When linking modules as relocatable files,
> the linker by default preserves such groups, potentially leaving multiple
> copies in the resulting modules and unnecessary group metadata.
>
> Use --force-group-allocation to have the linker resolve the COMDAT groups
> and place their members as regular sections. The option is available from
> ld.bfd 2.29 and ld.lld 19.1.0.
>
> [...]
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
--
Cheers,
Nathan
^ permalink raw reply
* [PATCH v5] rust: configfs: add procedural macro for declaring configfs attributes
From: Malte Wechter @ 2026-06-30 13:38 UTC (permalink / raw)
To: Andreas Hindborg, Breno Leitao, Miguel Ojeda, Boqun Feng,
Gary Guo, Björn Roy Baron, Benno Lossin, Alice Ryhl,
Trevor Gross, Danilo Krummrich, Jens Axboe, Luis Chamberlain,
Petr Pavlu, Daniel Gomez, Sami Tolvanen, Aaron Tomlin
Cc: linux-kernel, rust-for-linux, linux-block, linux-modules,
Malte Wechter
Implement `configfs_attrs!` as a procedural macro using `syn`, this
improves readability and maintainability. Remove the old macro and
replace all uses with the new macro. Add the new macro implementation
file to MAINTAINERS.
Signed-off-by: Malte Wechter <maltewechter@gmail.com>
---
Changes in v5:
- Assert during parsing that attribute names are unique (sashiko).
- Update safety comment to include that calls to make_group are serialized on the C side (sashiko)
- Add support for raw identifiers as attribute names (sashiko).
- Link to v4: https://lore.kernel.org/r/20260619-configfs-syn-v4-1-207c39504c1e@gmail.com
Changes in v4:
- Update link path to configfs_attr macro in configfs.rs
- Fix doc strings for configfs_attr in macros/lib.rs
- Fix doc strings for parse_ordered_fields in macros/helpers.rs
- Update title prefix to `rust: configfs:`
- Link to v3: https://lore.kernel.org/r/20260612-configfs-syn-v3-1-3292fbc5cc32@gmail.com
Changes in v3:
- Remove 'make_static_ident' function, make names for static variables simpler
- Move 'parse_ordered_fields' macro from module.rs into helpers
- Use 'parse_ordered_fields' macro for parsing instead of doing it ad-hoc
- Link to v2: https://lore.kernel.org/r/20260603-configfs-syn-v2-1-cb58489c2647@gmail.com
Changes in v2:
- Add a try_parse helper function to macros/helpers.rs
- Fix bug where 'child' configuration gets dropped if trailing comma is missing (sashiko)
- Link to v1: https://lore.kernel.org/r/20260520-configfs-syn-v1-1-6c5b80a9cef2@gmail.com
To: Andreas Hindborg <a.hindborg@kernel.org>
To: Boqun Feng <boqun@kernel.org>
To: Jens Axboe <axboe@kernel.dk>
To: Breno Leitao <leitao@debian.org>
To: Miguel Ojeda <ojeda@kernel.org>
To: Gary Guo <gary@garyguo.net>
To: Björn Roy Baron <bjorn3_gh@protonmail.com>
To: Benno Lossin <lossin@kernel.org>
To: Alice Ryhl <aliceryhl@google.com>
To: Trevor Gross <tmgross@umich.edu>
To: Danilo Krummrich <dakr@kernel.org>
To: Luis Chamberlain <mcgrof@kernel.org>
To: Petr Pavlu <petr.pavlu@suse.com>
To: Daniel Gomez <da.gomez@kernel.org>
To: Sami Tolvanen <samitolvanen@google.com>
To: Aaron Tomlin <atomlin@atomlin.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-block@vger.kernel.org
Cc: rust-for-linux@vger.kernel.org
Cc: linux-modules@vger.kernel.org
---
MAINTAINERS | 1 +
drivers/block/rnull/configfs.rs | 2 +-
rust/kernel/configfs.rs | 263 +---------------------------------------
rust/macros/configfs_attrs.rs | 149 +++++++++++++++++++++++
rust/macros/helpers.rs | 139 +++++++++++++++++++++
rust/macros/lib.rs | 87 +++++++++++++
rust/macros/module.rs | 137 ---------------------
samples/rust/rust_configfs.rs | 2 +-
8 files changed, 384 insertions(+), 396 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 2fb1c75afd16..45f7a1ec93b4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6464,6 +6464,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/a.hindborg/linux.git config
F: fs/configfs/
F: include/linux/configfs.h
F: rust/kernel/configfs.rs
+F: rust/macros/configfs_attrs.rs
F: samples/configfs/
F: samples/rust/rust_configfs.rs
diff --git a/drivers/block/rnull/configfs.rs b/drivers/block/rnull/configfs.rs
index 7c2eb5c0b722..f28ec69d7984 100644
--- a/drivers/block/rnull/configfs.rs
+++ b/drivers/block/rnull/configfs.rs
@@ -4,8 +4,8 @@
use kernel::{
block::mq::gen_disk::{GenDisk, GenDiskBuilder},
configfs::{self, AttributeOperations},
- configfs_attrs,
fmt::{self, Write as _},
+ macros::configfs_attrs,
new_mutex,
page::PAGE_SIZE,
prelude::*,
diff --git a/rust/kernel/configfs.rs b/rust/kernel/configfs.rs
index 2339c6467325..a8995a418136 100644
--- a/rust/kernel/configfs.rs
+++ b/rust/kernel/configfs.rs
@@ -21,7 +21,7 @@
//!
//! ```ignore
//! use kernel::alloc::flags;
-//! use kernel::configfs_attrs;
+//! use macros::configfs_attrs;
//! use kernel::configfs;
//! use kernel::new_mutex;
//! use kernel::page::PAGE_SIZE;
@@ -240,7 +240,7 @@ unsafe fn container_of(group: *const bindings::config_group) -> *const Self {
/// A configfs group.
///
/// To add a subgroup to configfs, pass this type as `ctype` to
-/// [`crate::configfs_attrs`] when creating a group in [`GroupOperations::make_group`].
+/// [`macros::configfs_attrs`] when creating a group in [`GroupOperations::make_group`].
#[pin_data]
pub struct Group<Data> {
#[pin]
@@ -637,7 +637,7 @@ pub const fn new(name: &'static CStr) -> Self {
/// implement `HasGroup<Data>`. The trait must be implemented once for each
/// attribute of the group. The constant type parameter `ID` maps the
/// implementation to a specific `Attribute`. `ID` must be passed when declaring
-/// attributes via the [`kernel::configfs_attrs`] macro, to tie
+/// attributes via the [`macros::configfs_attrs`] macro, to tie
/// `AttributeOperations` implementations to concrete named attributes.
#[vtable]
pub trait AttributeOperations<const ID: u64 = 0> {
@@ -669,13 +669,13 @@ fn store(_data: &Self::Data, _page: &[u8]) -> Result {
/// This type is used to construct a new [`ItemType`]. It represents a list of
/// [`Attribute`] that will appear in the directory representing a [`Group`].
/// Users should not directly instantiate this type, rather they should use the
-/// [`kernel::configfs_attrs`] macro to declare a static set of attributes for a
+/// [`macros::configfs_attrs`] macro to declare a static set of attributes for a
/// group.
///
/// # Note
///
/// Instances of this type are constructed statically at compile by the
-/// [`kernel::configfs_attrs`] macro.
+/// [`macros::configfs_attrs`] macro.
#[repr(transparent)]
pub struct AttributeList<const N: usize, Data>(
/// Null terminated Array of pointers to [`Attribute`]. The type is [`c_void`]
@@ -724,7 +724,7 @@ impl<const N: usize, Data> AttributeList<N, Data> {
/// [`Subsystem`].
///
/// Users should not directly instantiate objects of this type. Rather, they
-/// should use the [`kernel::configfs_attrs`] macro to statically declare the
+/// should use the [`macros::configfs_attrs`] macro to statically declare the
/// shape of a [`Group`] or [`Subsystem`].
#[pin_data]
pub struct ItemType<Container, Data> {
@@ -791,254 +791,3 @@ fn as_ptr(&self) -> *const bindings::config_item_type {
self.item_type.get()
}
}
-
-/// Define a list of configfs attributes statically.
-///
-/// Invoking the macro in the following manner:
-///
-/// ```ignore
-/// let item_type = configfs_attrs! {
-/// container: configfs::Subsystem<Configuration>,
-/// data: Configuration,
-/// child: Child,
-/// attributes: [
-/// message: 0,
-/// bar: 1,
-/// ],
-/// };
-/// ```
-///
-/// Expands the following output:
-///
-/// ```ignore
-/// let item_type = {
-/// static CONFIGURATION_MESSAGE_ATTR: kernel::configfs::Attribute<
-/// 0,
-/// Configuration,
-/// Configuration,
-/// > = unsafe {
-/// kernel::configfs::Attribute::new({
-/// const S: &str = "message\u{0}";
-/// const C: &kernel::str::CStr = match kernel::str::CStr::from_bytes_with_nul(
-/// S.as_bytes()
-/// ) {
-/// Ok(v) => v,
-/// Err(_) => {
-/// core::panicking::panic_fmt(core::const_format_args!(
-/// "string contains interior NUL"
-/// ));
-/// }
-/// };
-/// C
-/// })
-/// };
-///
-/// static CONFIGURATION_BAR_ATTR: kernel::configfs::Attribute<
-/// 1,
-/// Configuration,
-/// Configuration
-/// > = unsafe {
-/// kernel::configfs::Attribute::new({
-/// const S: &str = "bar\u{0}";
-/// const C: &kernel::str::CStr = match kernel::str::CStr::from_bytes_with_nul(
-/// S.as_bytes()
-/// ) {
-/// Ok(v) => v,
-/// Err(_) => {
-/// core::panicking::panic_fmt(core::const_format_args!(
-/// "string contains interior NUL"
-/// ));
-/// }
-/// };
-/// C
-/// })
-/// };
-///
-/// const N: usize = (1usize + (1usize + 0usize)) + 1usize;
-///
-/// static CONFIGURATION_ATTRS: kernel::configfs::AttributeList<N, Configuration> =
-/// unsafe { kernel::configfs::AttributeList::new() };
-///
-/// {
-/// const N: usize = 0usize;
-/// unsafe { CONFIGURATION_ATTRS.add::<N, 0, _>(&CONFIGURATION_MESSAGE_ATTR) };
-/// }
-///
-/// {
-/// const N: usize = (1usize + 0usize);
-/// unsafe { CONFIGURATION_ATTRS.add::<N, 1, _>(&CONFIGURATION_BAR_ATTR) };
-/// }
-///
-/// static CONFIGURATION_TPE:
-/// kernel::configfs::ItemType<configfs::Subsystem<Configuration> ,Configuration>
-/// = kernel::configfs::ItemType::<
-/// configfs::Subsystem<Configuration>,
-/// Configuration
-/// >::new_with_child_ctor::<N,Child>(
-/// &THIS_MODULE,
-/// &CONFIGURATION_ATTRS
-/// );
-///
-/// &CONFIGURATION_TPE
-/// }
-/// ```
-#[macro_export]
-macro_rules! configfs_attrs {
- (
- container: $container:ty,
- data: $data:ty,
- attributes: [
- $($name:ident: $attr:literal),* $(,)?
- ] $(,)?
- ) => {
- $crate::configfs_attrs!(
- count:
- @container($container),
- @data($data),
- @child(),
- @no_child(x),
- @attrs($($name $attr)*),
- @eat($($name $attr,)*),
- @assign(),
- @cnt(0usize),
- )
- };
- (
- container: $container:ty,
- data: $data:ty,
- child: $child:ty,
- attributes: [
- $($name:ident: $attr:literal),* $(,)?
- ] $(,)?
- ) => {
- $crate::configfs_attrs!(
- count:
- @container($container),
- @data($data),
- @child($child),
- @no_child(),
- @attrs($($name $attr)*),
- @eat($($name $attr,)*),
- @assign(),
- @cnt(0usize),
- )
- };
- (count:
- @container($container:ty),
- @data($data:ty),
- @child($($child:ty)?),
- @no_child($($no_child:ident)?),
- @attrs($($aname:ident $aattr:literal)*),
- @eat($name:ident $attr:literal, $($rname:ident $rattr:literal,)*),
- @assign($($assign:block)*),
- @cnt($cnt:expr),
- ) => {
- $crate::configfs_attrs!(
- count:
- @container($container),
- @data($data),
- @child($($child)?),
- @no_child($($no_child)?),
- @attrs($($aname $aattr)*),
- @eat($($rname $rattr,)*),
- @assign($($assign)* {
- const N: usize = $cnt;
- // The following macro text expands to a call to `Attribute::add`.
-
- // SAFETY: By design of this macro, the name of the variable we
- // invoke the `add` method on below, is not visible outside of
- // the macro expansion. The macro does not operate concurrently
- // on this variable, and thus we have exclusive access to the
- // variable.
- unsafe {
- $crate::macros::paste!(
- [< $data:upper _ATTRS >]
- .add::<N, $attr, _>(&[< $data:upper _ $name:upper _ATTR >])
- )
- };
- }),
- @cnt(1usize + $cnt),
- )
- };
- (count:
- @container($container:ty),
- @data($data:ty),
- @child($($child:ty)?),
- @no_child($($no_child:ident)?),
- @attrs($($aname:ident $aattr:literal)*),
- @eat(),
- @assign($($assign:block)*),
- @cnt($cnt:expr),
- ) =>
- {
- $crate::configfs_attrs!(
- final:
- @container($container),
- @data($data),
- @child($($child)?),
- @no_child($($no_child)?),
- @attrs($($aname $aattr)*),
- @assign($($assign)*),
- @cnt($cnt),
- )
- };
- (final:
- @container($container:ty),
- @data($data:ty),
- @child($($child:ty)?),
- @no_child($($no_child:ident)?),
- @attrs($($name:ident $attr:literal)*),
- @assign($($assign:block)*),
- @cnt($cnt:expr),
- ) =>
- {
- $crate::macros::paste!{
- {
- $(
- // SAFETY: We are expanding `configfs_attrs`.
- static [< $data:upper _ $name:upper _ATTR >]:
- $crate::configfs::Attribute<$attr, $data, $data> =
- unsafe {
- $crate::configfs::Attribute::new(
- $crate::c_str!(::core::stringify!($name)),
- )
- };
- )*
-
-
- // We need space for a null terminator.
- const N: usize = $cnt + 1usize;
-
- // SAFETY: We are expanding `configfs_attrs`.
- static [< $data:upper _ATTRS >]:
- $crate::configfs::AttributeList<N, $data> =
- unsafe { $crate::configfs::AttributeList::new() };
-
- $($assign)*
-
- $(
- const [<$no_child:upper>]: bool = true;
-
- static [< $data:upper _TPE >] : $crate::configfs::ItemType<$container, $data> =
- $crate::configfs::ItemType::<$container, $data>::new::<N>(
- &THIS_MODULE, &[<$ data:upper _ATTRS >]
- );
- )?
-
- $(
- static [< $data:upper _TPE >]:
- $crate::configfs::ItemType<$container, $data> =
- $crate::configfs::ItemType::<$container, $data>::
- new_with_child_ctor::<N, $child>(
- &THIS_MODULE, &[<$ data:upper _ATTRS >]
- );
- )?
-
- & [< $data:upper _TPE >]
- }
- }
- };
-
-}
-
-pub use crate::configfs_attrs;
diff --git a/rust/macros/configfs_attrs.rs b/rust/macros/configfs_attrs.rs
new file mode 100644
index 000000000000..f829a42cece8
--- /dev/null
+++ b/rust/macros/configfs_attrs.rs
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+
+use std::collections::HashSet;
+
+use quote::{
+ format_ident,
+ quote, //
+};
+
+use syn::{
+ bracketed,
+ ext::IdentExt,
+ parse::{
+ Parse,
+ ParseStream, //
+ },
+ punctuated::Punctuated,
+ spanned::Spanned,
+ Error,
+ Ident,
+ LitInt,
+ Token,
+ Type, //
+};
+
+use crate::helpers::parse_ordered_fields;
+
+pub(crate) struct ConfigfsAttrs {
+ container: Type,
+ data: Type,
+ child: Option<Type>,
+ attributes: Vec<(Ident, LitInt)>,
+}
+
+fn parse_attribute_field(stream: ParseStream<'_>) -> syn::Result<(Ident, LitInt)> {
+ let id = stream.parse::<syn::Ident>()?;
+ let _colon = stream.parse::<Token![:]>()?;
+ let v = stream.parse::<LitInt>()?;
+ Ok((id, v))
+}
+
+fn parse_attributes(stream: ParseStream<'_>) -> syn::Result<Vec<(Ident, LitInt)>> {
+ let attr_stream;
+ let _bracket = bracketed!(attr_stream in stream);
+ let attributes = Punctuated::<(Ident, LitInt), Token![,]>::parse_terminated_with(
+ &attr_stream,
+ parse_attribute_field,
+ )?;
+ let mut attr_set = HashSet::new();
+ for attr in attributes.iter() {
+ if !attr_set.insert(attr.0.clone()) {
+ return Err(syn::Error::new(attr.0.span(), "duplicate attribute"));
+ }
+ }
+
+ Ok(attributes.into_iter().collect::<Vec<_>>())
+}
+
+impl Parse for ConfigfsAttrs {
+ fn parse(input: ParseStream<'_>) -> syn::Result<Self> {
+ parse_ordered_fields!(
+ from input;
+ container [required] => (input.parse::<Type>())?,
+ data [required] => (input.parse::<Type>())?,
+ child => (input.parse::<Type>())?,
+ attributes [required] => parse_attributes(input)?,
+ );
+
+ Ok(ConfigfsAttrs {
+ container,
+ data,
+ child,
+ attributes,
+ })
+ }
+}
+
+pub(crate) fn configfs_attrs(cfs_attrs: ConfigfsAttrs) -> proc_macro2::TokenStream {
+ let (container_ty, data_ty) = (&cfs_attrs.container, &cfs_attrs.data);
+
+ let data_tp_ident = Ident::new("DATA_TPE", cfs_attrs.data.span());
+ let data_attr_ident = Ident::new("DATA_ATTR_LIST", cfs_attrs.data.span());
+
+ let n = cfs_attrs.attributes.len() + 1;
+
+ let attr_list = quote! {
+ static #data_attr_ident: kernel::configfs::AttributeList<#n, #data_ty> =
+ // SAFETY: We are expanding `configfs_attrs`.
+ unsafe { kernel::configfs::AttributeList::new() };
+ };
+
+ let mut attrs = Vec::new();
+ for (attr_idx, (name, id)) in cfs_attrs.attributes.iter().enumerate() {
+ let name_with_attr = format_ident!(
+ "{}_ATTR_{}",
+ name.unraw().to_string().to_uppercase(),
+ attr_idx
+ );
+
+ let id: u64 = match id.base10_parse::<u64>() {
+ Ok(v) => v,
+ Err(_) => {
+ return syn::Error::new(id.span(), "Could not parse attribute ID as a u64")
+ .to_compile_error();
+ }
+ };
+
+ attrs.push(quote! {
+ static #name_with_attr: kernel::configfs::Attribute<#id, #data_ty, #data_ty> =
+ // SAFETY: We are expanding `configfs_attrs`.
+ unsafe {
+ kernel::configfs::Attribute::new(kernel::c_str!(::core::stringify!(#name)))
+ };
+
+ // SAFETY: By design of this macro, the name of the variable we
+ // invoke the `add` method on below, is not visible outside of
+ // the macro expansion. The macro does not operate concurrently
+ // on this variable, and thus we have exclusive access to the
+ // variable. Calls to `make_group` are serialized on the C side
+ // by per subsystem mutex.
+ unsafe { #data_attr_ident.add::<#attr_idx, #id, _>(&#name_with_attr) }
+ });
+ }
+
+ let has_child_code = if let Some(child) = cfs_attrs.child {
+ quote! { new_with_child_ctor::<#n, #child>}
+ } else {
+ quote! { new::<#n> }
+ };
+
+ let data_type = quote! {
+ {
+ static #data_tp_ident:
+ kernel::configfs::ItemType<#container_ty, #data_ty> =
+ kernel::configfs::ItemType::<#container_ty, #data_ty>::#has_child_code(
+ &THIS_MODULE, &#data_attr_ident
+ );
+ &#data_tp_ident
+ }
+ };
+
+ quote! {
+ {
+ #attr_list
+ #(#attrs)*
+ #data_type
+ }
+ }
+}
diff --git a/rust/macros/helpers.rs b/rust/macros/helpers.rs
index d18fbf4daa0a..305dcbddf797 100644
--- a/rust/macros/helpers.rs
+++ b/rust/macros/helpers.rs
@@ -58,3 +58,142 @@ pub(crate) fn file() -> String {
pub(crate) fn gather_cfg_attrs(attr: &[Attribute]) -> impl Iterator<Item = &Attribute> + '_ {
attr.iter().filter(|a| a.path().is_ident("cfg"))
}
+
+/// Parse fields that are required to use a specific order.
+///
+/// As fields must follow a specific order, we *could* just parse fields one by one by peeking.
+/// However the error message generated when implementing that way is not very friendly.
+///
+/// So instead we parse fields in an arbitrary order, but only enforce the ordering after parsing,
+/// and if the wrong order is used, the proper order is communicated to the user with error message.
+///
+/// Usage looks like this:
+/// ```ignore
+/// parse_ordered_fields! {
+/// from input;
+///
+/// // This will extract `foo: <field>` into a variable named `foo`.
+/// // The variable will have type `Option<_>`.
+/// foo => <expression that parses the field>,
+///
+/// // If you need the variable name to be different than the key name.
+/// // This extracts `baz: <field>` into a variable named `bar`.
+/// // You might want this if `baz` is a keyword.
+/// baz as bar => <expression that parse the field>,
+///
+/// // You can mark a key as required, and the variable will no longer be `Option`.
+/// // foobar will be of type `Expr` instead of `Option<Expr>`.
+/// foobar [required] => input.parse::<Expr>()?,
+/// }
+/// ```
+macro_rules! parse_ordered_fields {
+ (@gen
+ [$input:expr]
+ [$([$name:ident; $key:ident; $parser:expr])*]
+ [$([$req_name:ident; $req_key:ident])*]
+ ) => {
+ $(let mut $name = None;)*
+
+ const EXPECTED_KEYS: &[&str] = &[$(stringify!($key),)*];
+ const REQUIRED_KEYS: &[&str] = &[$(stringify!($req_key),)*];
+
+ let span = $input.span();
+ let mut seen_keys = Vec::new();
+
+ while !$input.is_empty() {
+ let key = $input.call(Ident::parse_any)?;
+
+ if seen_keys.contains(&key) {
+ Err(Error::new_spanned(
+ &key,
+ format!(r#"duplicated key "{key}". Keys can only be specified once."#),
+ ))?
+ }
+
+ $input.parse::<Token![:]>()?;
+
+ match &*key.to_string() {
+ $(
+ stringify!($key) => $name = Some($parser),
+ )*
+ _ => {
+ Err(Error::new_spanned(
+ &key,
+ format!(r#"unknown key "{key}". Valid keys are: {EXPECTED_KEYS:?}."#),
+ ))?
+ }
+ }
+
+ $input.parse::<Token![,]>()?;
+ seen_keys.push(key);
+ }
+
+ for key in REQUIRED_KEYS {
+ if !seen_keys.iter().any(|e| e == key) {
+ Err(Error::new(span, format!(r#"missing required key "{key}""#)))?
+ }
+ }
+
+ let mut ordered_keys: Vec<&str> = Vec::new();
+ for key in EXPECTED_KEYS {
+ if seen_keys.iter().any(|e| e == key) {
+ ordered_keys.push(key);
+ }
+ }
+
+ if seen_keys != ordered_keys {
+ Err(Error::new(
+ span,
+ format!(r#"keys are not ordered as expected. Order them like: {ordered_keys:?}."#),
+ ))?
+ }
+
+ $(let $req_name = $req_name.expect("required field");)*
+ };
+
+ // Handle required fields.
+ (@gen
+ [$input:expr] [$($tok:tt)*] [$($req:tt)*]
+ $key:ident as $name:ident [required] => $parser:expr,
+ $($rest:tt)*
+ ) => {
+ parse_ordered_fields!(
+ @gen [$input] [$($tok)* [$name; $key; $parser]] [$($req)* [$name; $key]] $($rest)*
+ )
+ };
+ (@gen
+ [$input:expr] [$($tok:tt)*] [$($req:tt)*]
+ $name:ident [required] => $parser:expr,
+ $($rest:tt)*
+ ) => {
+ parse_ordered_fields!(
+ @gen [$input] [$($tok)* [$name; $name; $parser]] [$($req)* [$name; $name]] $($rest)*
+ )
+ };
+
+ // Handle optional fields.
+ (@gen
+ [$input:expr] [$($tok:tt)*] [$($req:tt)*]
+ $key:ident as $name:ident => $parser:expr,
+ $($rest:tt)*
+ ) => {
+ parse_ordered_fields!(
+ @gen [$input] [$($tok)* [$name; $key; $parser]] [$($req)*] $($rest)*
+ )
+ };
+ (@gen
+ [$input:expr] [$($tok:tt)*] [$($req:tt)*]
+ $name:ident => $parser:expr,
+ $($rest:tt)*
+ ) => {
+ parse_ordered_fields!(
+ @gen [$input] [$($tok)* [$name; $name; $parser]] [$($req)*] $($rest)*
+ )
+ };
+
+ (from $input:expr; $($tok:tt)*) => {
+ parse_ordered_fields!(@gen [$input] [] [] $($tok)*)
+ }
+}
+
+pub(crate) use parse_ordered_fields;
diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs
index 2cfd59e0f9e7..ebb41e80ecc7 100644
--- a/rust/macros/lib.rs
+++ b/rust/macros/lib.rs
@@ -15,6 +15,8 @@
#![cfg_attr(not(CONFIG_RUSTC_HAS_SPAN_FILE), feature(proc_macro_span))]
mod concat_idents;
+#[cfg(CONFIG_CONFIGFS_FS)]
+mod configfs_attrs;
mod export;
mod fmt;
mod helpers;
@@ -489,3 +491,88 @@ pub fn kunit_tests(attr: TokenStream, input: TokenStream) -> TokenStream {
.unwrap_or_else(|e| e.into_compile_error())
.into()
}
+
+/// Define a list of configfs attributes statically.
+///
+/// # Examples
+///
+/// ```ignore
+/// let item_type = configfs_attrs! {
+/// container: configfs::Subsystem<Configuration>,
+/// data: Configuration,
+/// child: Child,
+/// attributes: [
+/// message: 0,
+/// bar: 1,
+/// ],
+/// };
+/// ```
+///
+/// Expands the following output:
+///
+/// ```ignore
+/// let item_type = {
+/// static DATA_ATTR_LIST: kernel::configfs::AttributeList<
+/// 3usize,
+/// Configuration,
+/// > = unsafe { kernel::configfs::AttributeList::new() };
+/// static MESSAGE_ATTR_0: kernel::configfs::Attribute<
+/// 0u64,
+/// Configuration,
+/// Configuration,
+/// > = unsafe {
+/// kernel::configfs::Attribute::new({
+/// const S: &str = "message\u{0}";
+/// const C: &kernel::str::CStr = match kernel::str::CStr::from_bytes_with_nul(
+/// S.as_bytes(),
+/// ) {
+/// Ok(v) => v,
+/// Err(_) => {
+/// ::core::panicking::panic_fmt(
+/// format_args!("string contains interior NUL"),
+/// );
+/// }
+/// };
+/// C
+/// })
+/// };
+/// unsafe { DATA_ATTR_LIST.add::<0usize, 0u64, _>(&MESSAGE_ATTR_0) }
+/// static BAR_ATTR_1: kernel::configfs::Attribute<
+/// 1u64,
+/// Configuration,
+/// Configuration,
+/// > = unsafe {
+/// kernel::configfs::Attribute::new({
+/// const S: &str = "bar\u{0}";
+/// const C: &kernel::str::CStr = match kernel::str::CStr::from_bytes_with_nul(
+/// S.as_bytes(),
+/// ) {
+/// Ok(v) => v,
+/// Err(_) => {
+/// ::core::panicking::panic_fmt(
+/// format_args!("string contains interior NUL"),
+/// );
+/// }
+/// };
+/// C
+/// })
+/// };
+/// unsafe { DATA_ATTR_LIST.add::<1usize, 1u64, _>(&BAR_ATTR_1) }
+/// {
+/// static DATA_TPE: kernel::configfs::ItemType<
+/// Subsystem<Configuration>,
+/// Configuration,
+/// > = kernel::configfs::ItemType::<
+/// Subsystem<Configuration>,
+/// Configuration,
+/// >::new_with_child_ctor::<3usize, Child>(&THIS_MODULE, &DATA_ATTR_LIST);
+/// &DATA_TPE
+/// }
+/// };
+/// ```
+#[cfg(CONFIG_CONFIGFS_FS)]
+#[proc_macro]
+pub fn configfs_attrs(input: TokenStream) -> TokenStream {
+ configfs_attrs::configfs_attrs(parse_macro_input!(input as configfs_attrs::ConfigfsAttrs))
+ .into()
+}
diff --git a/rust/macros/module.rs b/rust/macros/module.rs
index 06c18e207508..7ff6ad09b1a2 100644
--- a/rust/macros/module.rs
+++ b/rust/macros/module.rs
@@ -196,143 +196,6 @@ fn param_ops_path(param_type: &str) -> Path {
}
}
-/// Parse fields that are required to use a specific order.
-///
-/// As fields must follow a specific order, we *could* just parse fields one by one by peeking.
-/// However the error message generated when implementing that way is not very friendly.
-///
-/// So instead we parse fields in an arbitrary order, but only enforce the ordering after parsing,
-/// and if the wrong order is used, the proper order is communicated to the user with error message.
-///
-/// Usage looks like this:
-/// ```ignore
-/// parse_ordered_fields! {
-/// from input;
-///
-/// // This will extract "foo: <field>" into a variable named "foo".
-/// // The variable will have type `Option<_>`.
-/// foo => <expression that parses the field>,
-///
-/// // If you need the variable name to be different than the key name.
-/// // This extracts "baz: <field>" into a variable named "bar".
-/// // You might want this if "baz" is a keyword.
-/// baz as bar => <expression that parse the field>,
-///
-/// // You can mark a key as required, and the variable will no longer be `Option`.
-/// // foobar will be of type `Expr` instead of `Option<Expr>`.
-/// foobar [required] => input.parse::<Expr>()?,
-/// }
-/// ```
-macro_rules! parse_ordered_fields {
- (@gen
- [$input:expr]
- [$([$name:ident; $key:ident; $parser:expr])*]
- [$([$req_name:ident; $req_key:ident])*]
- ) => {
- $(let mut $name = None;)*
-
- const EXPECTED_KEYS: &[&str] = &[$(stringify!($key),)*];
- const REQUIRED_KEYS: &[&str] = &[$(stringify!($req_key),)*];
-
- let span = $input.span();
- let mut seen_keys = Vec::new();
-
- while !$input.is_empty() {
- let key = $input.call(Ident::parse_any)?;
-
- if seen_keys.contains(&key) {
- Err(Error::new_spanned(
- &key,
- format!(r#"duplicated key "{key}". Keys can only be specified once."#),
- ))?
- }
-
- $input.parse::<Token![:]>()?;
-
- match &*key.to_string() {
- $(
- stringify!($key) => $name = Some($parser),
- )*
- _ => {
- Err(Error::new_spanned(
- &key,
- format!(r#"unknown key "{key}". Valid keys are: {EXPECTED_KEYS:?}."#),
- ))?
- }
- }
-
- $input.parse::<Token![,]>()?;
- seen_keys.push(key);
- }
-
- for key in REQUIRED_KEYS {
- if !seen_keys.iter().any(|e| e == key) {
- Err(Error::new(span, format!(r#"missing required key "{key}""#)))?
- }
- }
-
- let mut ordered_keys: Vec<&str> = Vec::new();
- for key in EXPECTED_KEYS {
- if seen_keys.iter().any(|e| e == key) {
- ordered_keys.push(key);
- }
- }
-
- if seen_keys != ordered_keys {
- Err(Error::new(
- span,
- format!(r#"keys are not ordered as expected. Order them like: {ordered_keys:?}."#),
- ))?
- }
-
- $(let $req_name = $req_name.expect("required field");)*
- };
-
- // Handle required fields.
- (@gen
- [$input:expr] [$($tok:tt)*] [$($req:tt)*]
- $key:ident as $name:ident [required] => $parser:expr,
- $($rest:tt)*
- ) => {
- parse_ordered_fields!(
- @gen [$input] [$($tok)* [$name; $key; $parser]] [$($req)* [$name; $key]] $($rest)*
- )
- };
- (@gen
- [$input:expr] [$($tok:tt)*] [$($req:tt)*]
- $name:ident [required] => $parser:expr,
- $($rest:tt)*
- ) => {
- parse_ordered_fields!(
- @gen [$input] [$($tok)* [$name; $name; $parser]] [$($req)* [$name; $name]] $($rest)*
- )
- };
-
- // Handle optional fields.
- (@gen
- [$input:expr] [$($tok:tt)*] [$($req:tt)*]
- $key:ident as $name:ident => $parser:expr,
- $($rest:tt)*
- ) => {
- parse_ordered_fields!(
- @gen [$input] [$($tok)* [$name; $key; $parser]] [$($req)*] $($rest)*
- )
- };
- (@gen
- [$input:expr] [$($tok:tt)*] [$($req:tt)*]
- $name:ident => $parser:expr,
- $($rest:tt)*
- ) => {
- parse_ordered_fields!(
- @gen [$input] [$($tok)* [$name; $name; $parser]] [$($req)*] $($rest)*
- )
- };
-
- (from $input:expr; $($tok:tt)*) => {
- parse_ordered_fields!(@gen [$input] [] [] $($tok)*)
- }
-}
-
struct Parameter {
name: Ident,
ptype: Ident,
diff --git a/samples/rust/rust_configfs.rs b/samples/rust/rust_configfs.rs
index a1bd9db6010d..876462f7789d 100644
--- a/samples/rust/rust_configfs.rs
+++ b/samples/rust/rust_configfs.rs
@@ -4,7 +4,7 @@
use kernel::alloc::flags;
use kernel::configfs;
-use kernel::configfs::configfs_attrs;
+use kernel::macros::configfs_attrs;
use kernel::new_mutex;
use kernel::page::PAGE_SIZE;
use kernel::prelude::*;
---
base-commit: 254f49634ee16a731174d2ae34bc50bd5f45e731
change-id: 20260417-configfs-syn-191e07130027
Best regards,
--
Malte Wechter <maltewechter@gmail.com>
^ permalink raw reply related
* Re: [PATCH v5] rust: configfs: add procedural macro for declaring configfs attributes
From: sashiko-bot @ 2026-06-30 13:51 UTC (permalink / raw)
To: Malte Wechter; +Cc: linux-modules, ojeda
In-Reply-To: <20260630-configfs-syn-v5-1-da712975ec1a@gmail.com>
Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
New issues:
- [Medium] Raw identifiers generate incorrect configfs attribute names with an 'r#' prefix.
- [Low] The new macro strictly requires a trailing comma after the last field, reverting a usability fix and breaking compatibility with existing macro invocations.
Pre-existing issues:
- [High] Concurrent configfs directory creations of the same type will cause a data race on the `static` `DATA_ATTR_LIST` array.
--
commit 884f1e9ac3af92759b06d060216464edd49fb53f
Author: Malte Wechter <maltewechter@gmail.com>
rust: configfs: add procedural macro for declaring configfs attributes
Implement `configfs_attrs!` as a procedural macro using `syn`, this
improves readability and maintainability. Remove the old macro and
replace all uses with the new macro. Add the new macro implementation
file to MAINTAINERS.
> diff --git a/rust/macros/configfs_attrs.rs b/rust/macros/configfs_attrs.rs
> new file mode 100644
> index 0000000000000..f829a42cece88
> --- /dev/null
> +++ b/rust/macros/configfs_attrs.rs
[ ... ]
> + attrs.push(quote! {
> + static #name_with_attr: kernel::configfs::Attribute<#id, #data_ty, #data_ty> =
> + // SAFETY: We are expanding `configfs_attrs`.
> + unsafe {
> + kernel::configfs::Attribute::new(kernel::c_str!(::core::stringify!(#name)))
^^^^
[Severity: Medium]
Will this generate incorrect configfs attribute names with an "r#" prefix if
a raw identifier is used? The macro uses unraw() for the Rust static names
earlier, but seems to pass the raw string into stringify!() here.
> + };
> +
> + // SAFETY: By design of this macro, the name of the variable we
> + // invoke the `add` method on below, is not visible outside of
[ ... ]
> + // by per subsystem mutex.
> + unsafe { #data_attr_ident.add::<#attr_idx, #id, _>(&#name_with_attr) }
^^^^
[Severity: High]
This is a pre-existing issue, but does this code cause a data race? If
multiple threads call make_group concurrently (for example, creating
directories in different subsystems that share the same configuration struct),
they would execute this add() concurrently and mutate the static
DATA_ATTR_LIST array without synchronization, leading to undefined behavior.
> + });
> + }
> diff --git a/rust/macros/helpers.rs b/rust/macros/helpers.rs
> index d18fbf4daa0a5..305dcbddf7974 100644
> --- a/rust/macros/helpers.rs
> +++ b/rust/macros/helpers.rs
[ ... ]
> + match &*key.to_string() {
> + $(
> + stringify!($key) => $name = Some($parser),
> + )*
> + _ => {
> + Err(Error::new_spanned(
> + &key,
> + format!(r#"unknown key "{key}". Valid keys are: {EXPECTED_KEYS:?}."#),
> + ))?
> + }
> + }
> +
> + $input.parse::<Token![,]>()?;
^^^^
[Severity: Low]
Does this strictly require a trailing comma after the last field? The
previous declarative macro allowed an optional trailing comma, so
this strict requirement might break compatibility with existing macro
invocations.
> + seen_keys.push(key);
> + }
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260630-configfs-syn-v5-1-da712975ec1a@gmail.com?part=1
^ permalink raw reply
* [PATCH v4 0/5] fix section alignment on i386 when CONFIG_DRM_USE_DYNAMIC_DEBUG=Y
From: Jim Cromie @ 2026-06-30 18:37 UTC (permalink / raw)
To: Arnd Bergmann, Jason Baron, Luis Chamberlain, Petr Pavlu,
Daniel Gomez, Sami Tolvanen, Aaron Tomlin
Cc: linux-kernel, linux-arch, linux-modules, Andrew Morton,
Jim Cromie, Louis Chauvet
This fixes a section misalignement on i386, when CONFIG_DRM=y and
CONFIG_DRM_USE_DYNAMIC_DEBUG=Y
In this config, the __dyndbg_classes section gets a single
struct/record. On i386 this is 28-bytes, breaking the required
ALIGN(8) on the following __dyndbg section.
This breaks dynamic_debug_init() with a NULL pointer dereference; the
section traversal logic encounters padding bytes instead of a valid
descriptor.
the series:
1. moves BOUNDED_SECTION_* macros from vmlinux.lds.h to its own file.
v2- adds note that macros are for vmlinux.lds.h only, not for modules.
2. drops unused HEADERED_SECTION_* macros from that new file
3. adds ALIGN(8) into BOUNDED_SECTION* macros
omission causing NULL ptr on i386
adds,uses BOUNDED_SECTION _ALIGNED variants
4. removes now redundant ALIGN(8)s in vmlinux.lds.h
5. adds dyndbg.lds.S to KEEP sections in modules
follows codetag.lds.h model
Signed-off-by: Jim Cromie <jim.cromie@gmail.com>
---
v3:
- move #includes to top of files,
- drop redundant ALIGN(8) in dydnbg.lds.S: DYNDBG_SECTIONS macro
- add Reviewed-by tag (thx Petr)
v2:
- avoid BOUNDED_SECTION in modules, dont need _start & _end symbols.
- sets 0 address to the sections, not just whatever current is.
---
Jim Cromie (5):
vmlinux.lds.h: refactor BOUNDED_SECTION_* macros into bounded_sections.lds.h
vmlinux.lds.h: drop unused HEADERED_SECTION* macros
vmlinux.lds.h: Fix ALIGN(8) omission causing NULL ptr on i386
vmlinux.lds.h: remove redundant ALIGN(8) directives
dyndbg.lds.S: fix lost dyndbg sections in modules
MAINTAINERS | 1 +
include/asm-generic/bounded_sections.lds.h | 32 ++++++++++++++
include/asm-generic/dyndbg.lds.h | 18 ++++++++
include/asm-generic/vmlinux.lds.h | 68 ++++++------------------------
scripts/module.lds.S | 2 +
5 files changed, 66 insertions(+), 55 deletions(-)
---
base-commit: dc59e4fea9d83f03bad6bddf3fa2e52491777482
change-id: 20260630-fix-align-589738662161
Best regards,
--
Jim Cromie <jim.cromie@gmail.com>
^ permalink raw reply
* [PATCH v4 1/5] vmlinux.lds.h: refactor BOUNDED_SECTION_* macros into bounded_sections.lds.h
From: Jim Cromie @ 2026-06-30 18:37 UTC (permalink / raw)
To: Arnd Bergmann, Jason Baron, Luis Chamberlain, Petr Pavlu,
Daniel Gomez, Sami Tolvanen, Aaron Tomlin
Cc: linux-kernel, linux-arch, linux-modules, Andrew Morton,
Jim Cromie
In-Reply-To: <20260630-fix-align-v4-0-42e6ec883342@gmail.com>
Move BOUNDED_SECTION_* macros to a new helper file:
include/asm-generic/bounded_sections.lds.h and include it back into
vmlinux.lds.h. This allows its reuse later to fix a failure to keep
dyndbg sections in some circumstances.
NOTES:
These macros are only for use in vmlinux.lds.h, where the _start &
_end symbols are needed. Modules keep sections separate in ELF
sections, with their boundaries known, so the _start and _end are not
useful, and may confuse tools not expecting them.
This patch ignores a checkpatch warning, because new file is covered
by "GENERIC INCLUDE/ASM HEADER FILES" in MAINTAINERS
CC: Arnd Bergmann <arnd@arndb.de>
CC: linux-arch@vger.kernel.org
Signed-off-by: Jim Cromie <jim.cromie@gmail.com>
---
v3: move include to top
---
include/asm-generic/bounded_sections.lds.h | 36 ++++++++++++++++++++++++++++++
include/asm-generic/vmlinux.lds.h | 31 +------------------------
2 files changed, 37 insertions(+), 30 deletions(-)
diff --git a/include/asm-generic/bounded_sections.lds.h b/include/asm-generic/bounded_sections.lds.h
new file mode 100644
index 000000000000..8c29293ca7fb
--- /dev/null
+++ b/include/asm-generic/bounded_sections.lds.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _ASM_GENERIC_BOUNDED_SECTIONS_H
+#define _ASM_GENERIC_BOUNDED_SECTIONS_H
+
+#define BOUNDED_SECTION_PRE_LABEL(_sec_, _label_, _BEGIN_, _END_) \
+ _BEGIN_##_label_ = .; \
+ KEEP(*(_sec_)) \
+ _END_##_label_ = .;
+
+#define BOUNDED_SECTION_POST_LABEL(_sec_, _label_, _BEGIN_, _END_) \
+ _label_##_BEGIN_ = .; \
+ KEEP(*(_sec_)) \
+ _label_##_END_ = .;
+
+#define BOUNDED_SECTION_BY(_sec_, _label_) \
+ BOUNDED_SECTION_PRE_LABEL(_sec_, _label_, __start, __stop)
+
+#define BOUNDED_SECTION(_sec) BOUNDED_SECTION_BY(_sec, _sec)
+
+#define HEADERED_SECTION_PRE_LABEL(_sec_, _label_, _BEGIN_, _END_, _HDR_) \
+ _HDR_##_label_ = .; \
+ KEEP(*(.gnu.linkonce.##_sec_)) \
+ BOUNDED_SECTION_PRE_LABEL(_sec_, _label_, _BEGIN_, _END_)
+
+#define HEADERED_SECTION_POST_LABEL(_sec_, _label_, _BEGIN_, _END_, _HDR_) \
+ _label_##_HDR_ = .; \
+ KEEP(*(.gnu.linkonce.##_sec_)) \
+ BOUNDED_SECTION_POST_LABEL(_sec_, _label_, _BEGIN_, _END_)
+
+#define HEADERED_SECTION_BY(_sec_, _label_) \
+ HEADERED_SECTION_PRE_LABEL(_sec_, _label_, __start, __stop)
+
+#define HEADERED_SECTION(_sec) HEADERED_SECTION_BY(_sec, _sec)
+
+#endif /* _ASM_GENERIC_BOUNDED_SECTIONS_H */
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 5659f4b5a125..f5ddf31b7f26 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -50,6 +50,7 @@
* [__nosave_begin, __nosave_end] for the nosave data
*/
+#include <asm-generic/bounded_sections.lds.h>
#include <asm-generic/codetag.lds.h>
#ifndef LOAD_OFFSET
@@ -211,36 +212,6 @@
# endif
#endif
-#define BOUNDED_SECTION_PRE_LABEL(_sec_, _label_, _BEGIN_, _END_) \
- _BEGIN_##_label_ = .; \
- KEEP(*(_sec_)) \
- _END_##_label_ = .;
-
-#define BOUNDED_SECTION_POST_LABEL(_sec_, _label_, _BEGIN_, _END_) \
- _label_##_BEGIN_ = .; \
- KEEP(*(_sec_)) \
- _label_##_END_ = .;
-
-#define BOUNDED_SECTION_BY(_sec_, _label_) \
- BOUNDED_SECTION_PRE_LABEL(_sec_, _label_, __start, __stop)
-
-#define BOUNDED_SECTION(_sec) BOUNDED_SECTION_BY(_sec, _sec)
-
-#define HEADERED_SECTION_PRE_LABEL(_sec_, _label_, _BEGIN_, _END_, _HDR_) \
- _HDR_##_label_ = .; \
- KEEP(*(.gnu.linkonce.##_sec_)) \
- BOUNDED_SECTION_PRE_LABEL(_sec_, _label_, _BEGIN_, _END_)
-
-#define HEADERED_SECTION_POST_LABEL(_sec_, _label_, _BEGIN_, _END_, _HDR_) \
- _label_##_HDR_ = .; \
- KEEP(*(.gnu.linkonce.##_sec_)) \
- BOUNDED_SECTION_POST_LABEL(_sec_, _label_, _BEGIN_, _END_)
-
-#define HEADERED_SECTION_BY(_sec_, _label_) \
- HEADERED_SECTION_PRE_LABEL(_sec_, _label_, __start, __stop)
-
-#define HEADERED_SECTION(_sec) HEADERED_SECTION_BY(_sec, _sec)
-
#ifdef CONFIG_TRACE_BRANCH_PROFILING
#define LIKELY_PROFILE() \
BOUNDED_SECTION_BY(_ftrace_annotated_branch, _annotated_branch_profile)
--
2.54.0
^ permalink raw reply related
* [PATCH v4 2/5] vmlinux.lds.h: drop unused HEADERED_SECTION* macros
From: Jim Cromie @ 2026-06-30 18:37 UTC (permalink / raw)
To: Arnd Bergmann, Jason Baron, Luis Chamberlain, Petr Pavlu,
Daniel Gomez, Sami Tolvanen, Aaron Tomlin
Cc: linux-kernel, linux-arch, linux-modules, Andrew Morton,
Jim Cromie
In-Reply-To: <20260630-fix-align-v4-0-42e6ec883342@gmail.com>
These macros are unused, no point in carrying them any more.
NB: these macros were just moved to bounded_sections.lds.h, from
vmlinux.lds.h, which is the known entity, and therefore more
meaningful in the 1-line summary, so thats what I used as the topic.
Signed-off-by: Jim Cromie <jim.cromie@gmail.com>
---
include/asm-generic/bounded_sections.lds.h | 15 ---------------
1 file changed, 15 deletions(-)
diff --git a/include/asm-generic/bounded_sections.lds.h b/include/asm-generic/bounded_sections.lds.h
index 8c29293ca7fb..268cdc34389b 100644
--- a/include/asm-generic/bounded_sections.lds.h
+++ b/include/asm-generic/bounded_sections.lds.h
@@ -18,19 +18,4 @@
#define BOUNDED_SECTION(_sec) BOUNDED_SECTION_BY(_sec, _sec)
-#define HEADERED_SECTION_PRE_LABEL(_sec_, _label_, _BEGIN_, _END_, _HDR_) \
- _HDR_##_label_ = .; \
- KEEP(*(.gnu.linkonce.##_sec_)) \
- BOUNDED_SECTION_PRE_LABEL(_sec_, _label_, _BEGIN_, _END_)
-
-#define HEADERED_SECTION_POST_LABEL(_sec_, _label_, _BEGIN_, _END_, _HDR_) \
- _label_##_HDR_ = .; \
- KEEP(*(.gnu.linkonce.##_sec_)) \
- BOUNDED_SECTION_POST_LABEL(_sec_, _label_, _BEGIN_, _END_)
-
-#define HEADERED_SECTION_BY(_sec_, _label_) \
- HEADERED_SECTION_PRE_LABEL(_sec_, _label_, __start, __stop)
-
-#define HEADERED_SECTION(_sec) HEADERED_SECTION_BY(_sec, _sec)
-
#endif /* _ASM_GENERIC_BOUNDED_SECTIONS_H */
--
2.54.0
^ permalink raw reply related
* [PATCH v4 3/5] vmlinux.lds.h: Fix ALIGN(8) omission causing NULL ptr on i386
From: Jim Cromie @ 2026-06-30 18:37 UTC (permalink / raw)
To: Arnd Bergmann, Jason Baron, Luis Chamberlain, Petr Pavlu,
Daniel Gomez, Sami Tolvanen, Aaron Tomlin
Cc: linux-kernel, linux-arch, linux-modules, Andrew Morton,
Jim Cromie, Louis Chauvet
In-Reply-To: <20260630-fix-align-v4-0-42e6ec883342@gmail.com>
Almost all uses of the BOUNDED_SECTION macros are ALIGN(8), either
explicitly, or by being below an aligned section containing x*8 byte
objects. The noteworthy exception is BOUNDED_SECTION(__dyndbg), which
immediately follows BOUNDED_SECTION(__dyndbg_classes).
On i386, struct _ddebug_classmap is 28 bytes, so without an explicit
ALIGN(8) in the macro, the following __dyndbg section gets misaligned,
causing a NULL ptr deref in dynamic_debug_init().
So fix this with an explicit ALIGN(8) in the existing BOUNDED_SECTION
macros, and introduce _ALIGNED variants to handle the cases with an
explicit . = ALIGN(x)
Also add explicit alignments for: EXCEPTION_TABLE, ORC_UNWIND_TABLE,
TRACEDATA, INIT_SETUP, and NOTES.
update BOUNDED_SECTION uses inside . = ALIGN(x) stanzas to use
_ALIGNED variants, but keep the outer ALIGNs so the symbols between
them are not "re-aligned".
In particular, scripts/sorttable.c does not tolerate sloppy padding.
At the top of ORC_UNWIND_TABLE, add . = ALIGN(4) to match the struct
orc_header __align() call in the code:
commit b9f174c811e3 ("x86/unwind/orc: Add ELF section with ORC version identifier")
Suggested-by: Louis Chauvet <louis.chauvet@bootlin.com> # _ALIGNED variants.
Link: https://lore.kernel.org/lkml/177402491426.6181.12855763650074831089.b4-review@b4/
Signed-off-by: Jim Cromie <jim.cromie@gmail.com>
---
v3:
sashiko complained about NOTES and .BTF_ids.
gemini asserts that NOTES are natively 4-byte aligned, add comment repeating it.
.BTF_ids doesnt use BOUNDED_BY, since start/end isnt needed;
sashiko evidently got confused by immediately preceding usage.
v2:
sashiko picked up 2 cases, added to the explicit list above
https://sashiko.dev/#/patchset/20260515-asm-generic-1-v3-0-680b273666d4%40gmail.com
---
include/asm-generic/bounded_sections.lds.h | 17 ++++++++++++++---
include/asm-generic/vmlinux.lds.h | 18 ++++++++++--------
2 files changed, 24 insertions(+), 11 deletions(-)
diff --git a/include/asm-generic/bounded_sections.lds.h b/include/asm-generic/bounded_sections.lds.h
index 268cdc34389b..8ff3e3420f60 100644
--- a/include/asm-generic/bounded_sections.lds.h
+++ b/include/asm-generic/bounded_sections.lds.h
@@ -3,19 +3,30 @@
#ifndef _ASM_GENERIC_BOUNDED_SECTIONS_H
#define _ASM_GENERIC_BOUNDED_SECTIONS_H
-#define BOUNDED_SECTION_PRE_LABEL(_sec_, _label_, _BEGIN_, _END_) \
+#define BOUNDED_SECTION_PRE_LABEL_ALIGNED(_sec_, _label_, _BEGIN_, _END_, _ALIGNED_) \
+ . = ALIGN(_ALIGNED_); \
_BEGIN_##_label_ = .; \
KEEP(*(_sec_)) \
_END_##_label_ = .;
-#define BOUNDED_SECTION_POST_LABEL(_sec_, _label_, _BEGIN_, _END_) \
+#define BOUNDED_SECTION_PRE_LABEL(_sec_, _label_, _BEGIN_, _END_) \
+ BOUNDED_SECTION_PRE_LABEL_ALIGNED(_sec_, _label_, _BEGIN_, _END_, 8)
+
+#define BOUNDED_SECTION_POST_LABEL_ALIGNED(_sec_, _label_, _BEGIN_, _END_, _ALIGNED_) \
+ . = ALIGN(_ALIGNED_); \
_label_##_BEGIN_ = .; \
KEEP(*(_sec_)) \
_label_##_END_ = .;
+#define BOUNDED_SECTION_POST_LABEL(_sec_, _label_, _BEGIN_, _END_) \
+ BOUNDED_SECTION_POST_LABEL_ALIGNED(_sec_, _label_, _BEGIN_, _END_, 8)
+
#define BOUNDED_SECTION_BY(_sec_, _label_) \
BOUNDED_SECTION_PRE_LABEL(_sec_, _label_, __start, __stop)
-#define BOUNDED_SECTION(_sec) BOUNDED_SECTION_BY(_sec, _sec)
+#define BOUNDED_SECTION_BY_ALIGNED(_sec_, _label_, _ALIGNED_) \
+ BOUNDED_SECTION_PRE_LABEL_ALIGNED(_sec_, _label_, __start, __stop, _ALIGNED_)
+
+#define BOUNDED_SECTION(_sec) BOUNDED_SECTION_BY(_sec, _sec)
#endif /* _ASM_GENERIC_BOUNDED_SECTIONS_H */
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index f5ddf31b7f26..f29fc079e37e 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -640,7 +640,7 @@
#define EXCEPTION_TABLE(align) \
. = ALIGN(align); \
__ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) { \
- BOUNDED_SECTION_BY(__ex_table, ___ex_table) \
+ BOUNDED_SECTION_BY_ALIGNED(__ex_table, ___ex_table, align) \
}
/*
@@ -650,7 +650,7 @@
#define BTF \
. = ALIGN(PAGE_SIZE); \
.BTF : AT(ADDR(.BTF) - LOAD_OFFSET) { \
- BOUNDED_SECTION_BY(.BTF, _BTF) \
+ BOUNDED_SECTION_BY_ALIGNED(.BTF, _BTF, PAGE_SIZE) \
} \
. = ALIGN(PAGE_SIZE); \
.BTF_ids : AT(ADDR(.BTF_ids) - LOAD_OFFSET) { \
@@ -832,16 +832,17 @@
#ifdef CONFIG_UNWINDER_ORC
#define ORC_UNWIND_TABLE \
+ . = ALIGN(4); \
.orc_header : AT(ADDR(.orc_header) - LOAD_OFFSET) { \
- BOUNDED_SECTION_BY(.orc_header, _orc_header) \
+ BOUNDED_SECTION_BY_ALIGNED(.orc_header, _orc_header, 4) \
} \
. = ALIGN(4); \
.orc_unwind_ip : AT(ADDR(.orc_unwind_ip) - LOAD_OFFSET) { \
- BOUNDED_SECTION_BY(.orc_unwind_ip, _orc_unwind_ip) \
+ BOUNDED_SECTION_BY_ALIGNED(.orc_unwind_ip, _orc_unwind_ip, 4)\
} \
. = ALIGN(2); \
.orc_unwind : AT(ADDR(.orc_unwind) - LOAD_OFFSET) { \
- BOUNDED_SECTION_BY(.orc_unwind, _orc_unwind) \
+ BOUNDED_SECTION_BY_ALIGNED(.orc_unwind, _orc_unwind, 2) \
} \
text_size = _etext - _stext; \
. = ALIGN(4); \
@@ -869,7 +870,7 @@
#define TRACEDATA \
. = ALIGN(4); \
.tracedata : AT(ADDR(.tracedata) - LOAD_OFFSET) { \
- BOUNDED_SECTION_POST_LABEL(.tracedata, __tracedata, _start, _end) \
+ BOUNDED_SECTION_POST_LABEL_ALIGNED(.tracedata, __tracedata, _start, _end, 4) \
}
#else
#define TRACEDATA
@@ -898,13 +899,14 @@
*(.note.gnu.property) \
} \
.notes : AT(ADDR(.notes) - LOAD_OFFSET) { \
- BOUNDED_SECTION_BY(.note.*, _notes) \
+ /* *(.note.*) are natively 4-byte aligned */ \
+ BOUNDED_SECTION_BY_ALIGNED(.note.*, _notes, 4) \
} NOTES_HEADERS \
NOTES_HEADERS_RESTORE
#define INIT_SETUP(initsetup_align) \
. = ALIGN(initsetup_align); \
- BOUNDED_SECTION_POST_LABEL(.init.setup, __setup, _start, _end)
+ BOUNDED_SECTION_POST_LABEL_ALIGNED(.init.setup, __setup, _start, _end, initsetup_align)
#define INIT_CALLS_LEVEL(level) \
__initcall##level##_start = .; \
--
2.54.0
^ permalink raw reply related
* [PATCH v4 4/5] vmlinux.lds.h: remove redundant ALIGN(8) directives
From: Jim Cromie @ 2026-06-30 18:37 UTC (permalink / raw)
To: Arnd Bergmann, Jason Baron, Luis Chamberlain, Petr Pavlu,
Daniel Gomez, Sami Tolvanen, Aaron Tomlin
Cc: linux-kernel, linux-arch, linux-modules, Andrew Morton,
Jim Cromie
In-Reply-To: <20260630-fix-align-v4-0-42e6ec883342@gmail.com>
The BOUNDED_SECTION_PRE_LABEL and BOUNDED_SECTION_POST_LABEL macros
were recently updated to inherently enforce an 8-byte alignment. This
makes the explicit '. = ALIGN(8);' statements preceding 'naked' macro
calls in vmlinux.lds.h redundant.
Remove these redundant alignment directives to clean up the file and
clarify that the macros handle their own alignment padding.
Signed-off-by: Jim Cromie <jim.cromie@gmail.com>
---
include/asm-generic/vmlinux.lds.h | 13 -------------
1 file changed, 13 deletions(-)
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index f29fc079e37e..3758a79d0430 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -228,7 +228,6 @@
#ifdef CONFIG_KPROBES
#define KPROBE_BLACKLIST() \
- . = ALIGN(8); \
BOUNDED_SECTION(_kprobe_blacklist)
#else
#define KPROBE_BLACKLIST()
@@ -244,7 +243,6 @@
#ifdef CONFIG_EVENT_TRACING
#define FTRACE_EVENTS() \
- . = ALIGN(8); \
BOUNDED_SECTION(_ftrace_events) \
BOUNDED_SECTION_BY(_ftrace_eval_map, _ftrace_eval_maps)
#else
@@ -261,7 +259,6 @@
#ifdef CONFIG_FTRACE_SYSCALLS
#define TRACE_SYSCALLS() \
- . = ALIGN(8); \
BOUNDED_SECTION_BY(__syscalls_metadata, _syscalls_metadata)
#else
#define TRACE_SYSCALLS()
@@ -276,7 +273,6 @@
#ifdef CONFIG_SERIAL_EARLYCON
#define EARLYCON_TABLE() \
- . = ALIGN(8); \
BOUNDED_SECTION_POST_LABEL(__earlycon_table, __earlycon_table, , _end)
#else
#define EARLYCON_TABLE()
@@ -284,11 +280,9 @@
#ifdef CONFIG_SECURITY
#define LSM_TABLE() \
- . = ALIGN(8); \
BOUNDED_SECTION_PRE_LABEL(.lsm_info.init, _lsm_info, __start, __end)
#define EARLY_LSM_TABLE() \
- . = ALIGN(8); \
BOUNDED_SECTION_PRE_LABEL(.early_lsm_info.init, _early_lsm_info, __start, __end)
#else
#define LSM_TABLE()
@@ -314,7 +308,6 @@
#ifdef CONFIG_ACPI
#define ACPI_PROBE_TABLE(name) \
- . = ALIGN(8); \
BOUNDED_SECTION_POST_LABEL(__##name##_acpi_probe_table, \
__##name##_acpi_probe_table,, _end)
#else
@@ -323,7 +316,6 @@
#ifdef CONFIG_THERMAL
#define THERMAL_TABLE(name) \
- . = ALIGN(8); \
BOUNDED_SECTION_POST_LABEL(__##name##_thermal_table, \
__##name##_thermal_table,, _end)
#else
@@ -403,12 +395,10 @@
__end_init_stack = .;
#define JUMP_TABLE_DATA \
- . = ALIGN(8); \
BOUNDED_SECTION_BY(__jump_table, ___jump_table)
#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
#define STATIC_CALL_DATA \
- . = ALIGN(8); \
BOUNDED_SECTION_BY(.static_call_sites, _static_call_sites) \
BOUNDED_SECTION_BY(.static_call_tramp_key, _static_call_tramp_key)
#else
@@ -453,7 +443,6 @@
*(.rodata) *(.rodata.*) *(.data.rel.ro*) \
SCHED_DATA \
RO_AFTER_INIT_DATA /* Read only after init */ \
- . = ALIGN(8); \
BOUNDED_SECTION_BY(__tracepoints_ptrs, ___tracepoints_ptrs) \
*(__tracepoints_strings)/* Tracepoints: strings */ \
} \
@@ -947,12 +936,10 @@
/* Alignment must be consistent with (kunit_suite *) in include/kunit/test.h */
#define KUNIT_TABLE() \
- . = ALIGN(8); \
BOUNDED_SECTION_POST_LABEL(.kunit_test_suites, __kunit_suites, _start, _end)
/* Alignment must be consistent with (kunit_suite *) in include/kunit/test.h */
#define KUNIT_INIT_TABLE() \
- . = ALIGN(8); \
BOUNDED_SECTION_POST_LABEL(.kunit_init_test_suites, \
__kunit_init_suites, _start, _end)
--
2.54.0
^ permalink raw reply related
* [PATCH v4 5/5] dyndbg.lds.S: fix lost dyndbg sections in modules
From: Jim Cromie @ 2026-06-30 18:37 UTC (permalink / raw)
To: Arnd Bergmann, Jason Baron, Luis Chamberlain, Petr Pavlu,
Daniel Gomez, Sami Tolvanen, Aaron Tomlin
Cc: linux-kernel, linux-arch, linux-modules, Andrew Morton,
Jim Cromie
In-Reply-To: <20260630-fix-align-v4-0-42e6ec883342@gmail.com>
With CONFIG_DRM_USE_DYNAMIC_DEBUG=y, several build configs had
problems with __dyndbg* sections getting lost in drm drivers. Fix
this by following the model demonstrated in codetag.lds.h.
Introduce include/asm-generic/dyndbg.lds.h, to bundle dynamic-debug's
multiple sections together, into 2 macros:
vmlinux.lds.h DATA_DATA: move the 2 BOUNDED_SECTION_BY(__dyndbg*)
calls into dyndbg.lds.h DYNDBG_SECTIONS(). vmlinux.lds.h now includes
the new file and calls the new macro.
MOD_DYNDBG_SECTIONS keeps the 2 sections by name, aligns them and sets
the output address to 0 when the sections are empty.
dyndbg.lds.h includes (reuses) bounded-section.lds.h
scripts/module.lds.S: now calls MOD_DYNDBG_SECTIONS right before the
CODETAG macro (consistent with their placements in vmlinux.lds.h), and
also includes dyndbg.lds.h
This isolates vmlinux.lds.h from further __dyndbg section additions.
CC: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jim Cromie <jim.cromie@gmail.com>
Reviewed-by: Petr Pavlu <petr.pavlu@suse.com>
---
v3: move #includes to top, drop extra ALIGN(8) in DYNDBG_SECTIONS, add RvBy
v2: Address linker script review feedback for relocatable modules.
MOD_DYNDBG_SECTIONS() used the BOUNDED_SECTION_BY() macro, which
proved problematic for kernel modules for two reasons:
1. Unwanted Empty Sections:
BOUNDED_SECTION_BY() automatically generates `__start` and `__stop`
symbols. When applied to `MOD_DYNDBG_SECTIONS()`, the linker assumes
the sections are populated due to the symbol definitions, forcing an
empty `__dyndbg` and `__dyndbg_classes` output section in every
compiled module, even those without dynamic debug configuration.
Since the module loader uses `section_objs()` to locate data via
ELF headers instead of relying on `__start`/`__stop` symbols, these
assignments are completely unnecessary.
2. Non-zero Output Addresses:
During relocatable linking (e.g., `ld.bfd -r`), omitting an explicit
base address causes the section to inherit the current location
counter. This results in non-zero sh_addr values in `.ko` files,
which is confusing, degrades compressibility, and can cause issues
with external tools parsing the ELF.
Fix both issues by dropping `BOUNDED_SECTION_BY()` in favor of a simple
`KEEP(*(...))` constraint and explicitly defining the sections with a `0`
base address: `__dyndbg 0 : ALIGN(8) { ... }`.
fixup-inc-vml
---
MAINTAINERS | 1 +
include/asm-generic/dyndbg.lds.h | 18 ++++++++++++++++++
include/asm-generic/vmlinux.lds.h | 6 ++----
scripts/module.lds.S | 2 ++
4 files changed, 23 insertions(+), 4 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 15011f5752a9..cfc2695d9bbe 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9178,6 +9178,7 @@ DYNAMIC DEBUG
M: Jason Baron <jbaron@akamai.com>
M: Jim Cromie <jim.cromie@gmail.com>
S: Maintained
+F: include/asm-generic/dyndbg.lds.h
F: include/linux/dynamic_debug.h
F: lib/dynamic_debug.c
F: lib/test_dynamic_debug.c
diff --git a/include/asm-generic/dyndbg.lds.h b/include/asm-generic/dyndbg.lds.h
new file mode 100644
index 000000000000..9d8951bef688
--- /dev/null
+++ b/include/asm-generic/dyndbg.lds.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_GENERIC_DYNDBG_LDS_H
+#define __ASM_GENERIC_DYNDBG_LDS_H
+
+#include <asm-generic/bounded_sections.lds.h>
+#define DYNDBG_SECTIONS() \
+ BOUNDED_SECTION_BY(__dyndbg, ___dyndbg) \
+ BOUNDED_SECTION_BY(__dyndbg_classes, ___dyndbg_classes)
+
+#define MOD_DYNDBG_SECTIONS() \
+ __dyndbg 0 : ALIGN(8) { \
+ KEEP(*(__dyndbg)) \
+ } \
+ __dyndbg_classes 0 : ALIGN(8) { \
+ KEEP(*(__dyndbg_classes)) \
+ }
+
+#endif /* __ASM_GENERIC_DYNDBG_LDS_H */
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 3758a79d0430..bd60f278f762 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -52,6 +52,7 @@
#include <asm-generic/bounded_sections.lds.h>
#include <asm-generic/codetag.lds.h>
+#include <asm-generic/dyndbg.lds.h>
#ifndef LOAD_OFFSET
#define LOAD_OFFSET 0
@@ -344,10 +345,7 @@
*(.data..do_once) \
STRUCT_ALIGN(); \
*(__tracepoints) \
- /* implement dynamic printk debug */ \
- . = ALIGN(8); \
- BOUNDED_SECTION_BY(__dyndbg_classes, ___dyndbg_classes) \
- BOUNDED_SECTION_BY(__dyndbg, ___dyndbg) \
+ DYNDBG_SECTIONS() \
CODETAG_SECTIONS() \
LIKELY_PROFILE() \
BRANCH_PROFILE() \
diff --git a/scripts/module.lds.S b/scripts/module.lds.S
index b62683061d79..2e62dc5bd5d4 100644
--- a/scripts/module.lds.S
+++ b/scripts/module.lds.S
@@ -10,6 +10,7 @@
#endif
#include <asm-generic/codetag.lds.h>
+#include <asm-generic/dyndbg.lds.h>
SECTIONS {
/DISCARD/ : {
@@ -61,6 +62,7 @@ SECTIONS {
*(.rodata..L*)
}
+ MOD_DYNDBG_SECTIONS()
MOD_SEPARATE_CODETAG_SECTIONS()
}
--
2.54.0
^ permalink raw reply related
* Re: [PATCH v3 1/7] list: Add mutable iterator variants
From: Kaitao Cheng @ 2026-07-01 11:07 UTC (permalink / raw)
To: Jani Nikula, David Laight, Christian König,
David Hildenbrand (Arm), Alexei Starovoitov
Cc: Andrew Morton, Jens Axboe, Tejun Heo, Alexander Viro,
Christian Brauner, Daniel Borkmann, Andrii Nakryiko,
Johannes Weiner, Peter Zijlstra, Ingo Molnar,
Arnaldo Carvalho de Melo, Namhyung Kim, Thomas Gleixner,
Juri Lelli, Vincent Guittot, Paul Moore, Andy Shevchenko,
Paul E. McKenney, Shakeel Butt, David Howells, Simona Vetter,
Randy Dunlap, Luca Ceresoli, Philipp Stanner, linux-block,
linux-kernel, cgroups, linux-ntfs-dev, linux-fsdevel, io-uring,
audit, bpf, netdev, dri-devel, linux-perf-users,
linux-trace-kernel, kexec, live-patching, linux-modules,
linux-crypto, linux-pm, rcu, sched-ext, linux-mm, virtualization,
damon, llvm, Kaitao Cheng, Muchun Song
In-Reply-To: <734f66ca51485ee3ec9788c0eaaead681e00664b@intel.com>
在 2026/6/25 19:00, Jani Nikula 写道:
> On Thu, 25 Jun 2026, Kaitao Cheng <kaitao.cheng@linux.dev> wrote:
>> 在 2026/6/24 22:23, David Laight 写道:
>>> On Wed, 24 Jun 2026 15:23:47 +0200
>>> Christian König <christian.koenig@amd.com> wrote:
>>>> On 6/24/26 15:14, Kaitao Cheng wrote:
>>>>> 在 2026/6/22 16:42, David Laight 写道:
>>>>>> On Mon, 22 Jun 2026 12:05:31 +0800
>>>>>> Kaitao Cheng <kaitao.cheng@linux.dev> wrote:
>>>>>>
>>>>>>> From: Kaitao Cheng <chengkaitao@kylinos.cn>
>>>>>>>
>>>>>>> The list_for_each*_safe() helpers are used when the loop body may
>>>>>>> remove the current entry. Their API exposes the temporary cursor at
>>>>>>> every call site, even though most users only need it for the iterator
>>>>>>> implementation and never reference it in the loop body.
>>>>>>>
>>>>>>> Add *_mutable() variants for list and hlist iteration. The new helpers
>>>>>>> support both forms: callers may keep passing an explicit temporary cursor
>>>>>>> when they need to inspect or reset it, or omit it and let the helper use
>>>>>>> a unique internal cursor.
>>>>>>
>>>>>> I'm not really sure 'mutable' means anything either.
>>>>>> It is possible to make it valid for the loop body (or even other threads)
>>>>>> to delete arbitrary list items - but that needs significant extra overheads.
>>>>>>
>>>>>> It might be worth doing something that doesn't need the extra variable,
>>>>>> but there is little point doing all the churn just to rename things.
>>>>>>
>>>>>>>
>>>>>>> This makes call sites that only mutate the list through the current entry
>>>>>>> less noisy, while keeping the existing *_safe() helpers available for
>>>>>>> compatibility.
>>>>>>>
>>>>>>> Signed-off-by: Kaitao Cheng <chengkaitao@kylinos.cn>
>>>>>>> ---
>>>>>>> include/linux/list.h | 269 +++++++++++++++++++++++++++++++++++++------
>>>>>>> 1 file changed, 231 insertions(+), 38 deletions(-)
>>>>>>>
>>>>>>> diff --git a/include/linux/list.h b/include/linux/list.h
>>>>>>> index 09d979976b3b..1081def7cea9 100644
>>>>>>> --- a/include/linux/list.h
>>>>>>> +++ b/include/linux/list.h
>>>>>>> @@ -7,6 +7,7 @@
>>>>>>> #include <linux/stddef.h>
>>>>>>> #include <linux/poison.h>
>>>>>>> #include <linux/const.h>
>>>>>>> +#include <linux/args.h>
>>>>>>>
>>>>>>> #include <asm/barrier.h>
>>>>>>>
>>>>>>> @@ -763,28 +764,72 @@ static inline void list_splice_tail_init(struct list_head *list,
>>>>>>> #define list_for_each_prev(pos, head) \
>>>>>>> for (pos = (head)->prev; !list_is_head(pos, (head)); pos = pos->prev)
>>>>>>>
>>>>>>> -/**
>>>>>>> - * list_for_each_safe - iterate over a list safe against removal of list entry
>>>>>>> - * @pos: the &struct list_head to use as a loop cursor.
>>>>>>> - * @n: another &struct list_head to use as temporary storage
>>>>>>> - * @head: the head for your list.
>>>>>>> +/*
>>>>>>> + * list_for_each_safe is an old interface, use list_for_each_mutable instead.
>>>>>>> */
>>>>>>> #define list_for_each_safe(pos, n, head) \
>>>>>>> for (pos = (head)->next, n = pos->next; \
>>>>>>> !list_is_head(pos, (head)); \
>>>>>>> pos = n, n = pos->next)
>>>>>>>
>>>>>>> +#define __list_for_each_mutable_internal(pos, tmp, head) \
>>>>>>> + for (typeof(pos) tmp = (pos = (head)->next)->next; \
>>>>>>
>>>>>> Use auto
>>>>>>
>>>>>>> + !list_is_head(pos, (head)); \
>>>>>>> + pos = tmp, tmp = pos->next)
>>>>>>> +
>>>>>>> +#define __list_for_each_mutable1(pos, head) \
>>>>>>> + __list_for_each_mutable_internal(pos, __UNIQUE_ID(next), head)
>>>>>>> +
>>>>>>> +#define __list_for_each_mutable2(pos, next, head) \
>>>>>>> + list_for_each_safe(pos, next, head)
>>>>>>> +
>>>>>>> /**
>>>>>>> - * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry
>>>>>>> + * list_for_each_mutable - iterate over a list safe against entry removal
>>>>>>> * @pos: the &struct list_head to use as a loop cursor.
>>>>>>> - * @n: another &struct list_head to use as temporary storage
>>>>>>> - * @head: the head for your list.
>>>>>>> + * @...: either (head) or (next, head)
>>>>>>> + *
>>>>>>> + * next: another &struct list_head to use as optional temporary storage.
>>>>>>> + * The temporary cursor is internal unless explicitly supplied by
>>>>>>> + * the caller.
>>>>>>> + * head: the head for your list.
>>>>>>> + */
>>>>>>> +#define list_for_each_mutable(pos, ...) \
>>>>>>> + CONCATENATE(__list_for_each_mutable, COUNT_ARGS(__VA_ARGS__)) \
>>>>>>> + (pos, __VA_ARGS__)
>>>>>>
>>>>>> The variable argument count logic really just slows down compilation.
>>>>>> Maybe there aren't enough copies of this code to make that significant.
>>>>>> But just because you can do it doesn't mean it is a gooD idea.
>>>>>> I'm also not sure it really adds anything to the readability.
>>>>>>
>>>>>> And, it you are going to make the middle argument optional there is
>>>>>> no need to change the macro name.
>>>>>
>>>>> Christian König and Jani Nikula also disagree with the variadic-argument
>>>>> implementation approach. If we abandon that method, it means we will
>>>>> inevitably need to add some new macros. If mutable is not a good name,
>>>>> suggestions for better alternatives would be welcome; coming up with a
>>>>> suitable name is indeed rather tricky.
>>>>
>>>> I don't think you need to add a new macro for the specific use case that people want to modify the next element of the iteration.
>>>>
>>>> If I remember your numbers correctly that is a really corner case and keeping using the existing *_safe() macros for that sounds perfectly fine to me.
>>>
>>> IIRC currently you have a choice of either:
>>> define Item that can't be deleted
>>> list_for_each() The current item.
>>> list_for_each_safe() The next item.
>>> There is also likely to be code that updates the variables to allow
>>> for other scenarios.
>>>
>>> Note that if increase a reference count and release a lock then list_for_each()
>>> is likely safer than list_for_each_safe() :-)
>>>
>>> list.h has 9 variants of the 'safe' loop.
>>> The bloat of another 9 is getting excessive.
>>>
>>> It has to be said that this is one of my least favourite type of list...
>>
>> Hi Christian König, David Laight, Jani Nikula, David Hildenbrand,
>> Andy Shevchenko, Alexei Starovoitov
>>
>> For ease of discussion, I need to summarize the currently possible
>> approaches and briefly describe their respective pros and cons,
>> using the list_for_each_entry* interfaces as examples.
>>
>> 1. Add list_for_each_entry_mutable, while keeping list_for_each_entry
>> and list_for_each_entry_safe unchanged. list_for_each_entry_mutable
>> would be used specifically for safe deletion scenarios that do not
>> need to expose the temporary cursor externally. The code can refer to
>> the v1 version.
>>
>> Pros: Does not depend on immediate per-subsystem adaptation and can be
>> merged directly.
>> Cons: Requires adding a whole set of mutable interfaces, which makes the
>> code somewhat redundant.
>
> Seems fine, and the original _safe naming is ambiguous anyway.
>
>> 2. Directly optimize away the temporary cursor in list_for_each_entry_safe
>> and define it inside the loop instead, changing the interface from four
>> arguments to three.
>>
>> Pros: Does not add redundant interfaces.
>> Cons: (1) Users need to manually update special cases that use the
>> traversal variable of list_for_each_entry_safe, the new
>> list_for_each_entry_safe would no longer apply there and would
>> need to be open-coded.
>> (2) Because the macro arguments changes, all list_for_each_entry_safe
>> callers would need to be modified and merged together, making it
>> difficult to merge such a large amount of code at once.
>
> This won't fly because there are literally thousands of
> list_for_each_entry_safe() users.
>
>> 3. Use a variadic macro approach to optimize list_for_each_entry_safe,
>> so that it supports both three and four arguments.
>>
>> Pros: (1) Does not add redundant interfaces.
>> (2) Does not depend on immediate per-subsystem adaptation and can
>> be merged directly.
>> Cons: (1) Increases compile time.
>> (2) Makes the interface harder for users to use.
>
> Basically I'm against any variadic macro tricks where the optional
> argument is not the last argument. That's just way too surprising, and
> goes against common practice in just about all other languages.
>
>> 4. Optimize list_for_each_entry by defining the temporary cursor internally,
>> making it compatible with the functionality of list_for_each_entry_safe.
>> The code can refer to the v2 version.
>>
>> Pros: (1) Does not add redundant interfaces.
>> (2) The number of externally visible arguments of list_for_each_entry
>> remains unchanged, still three.
>> Cons: (1) list_for_each_entry and list_for_each_entry_safe would be merged
>> into one, and list_for_each_entry_safe would gradually be deprecated.
>> (2) Users need to manually update special cases that use the traversal
>> variable of list_for_each_entry, the new list_for_each_entry would no
>> longer apply there and would need to be open-coded. There are 15 such
>> cases in total.
>
> This sounds good to me, though I take it there's some code size increase
> and/or performance penalty?
>
> Maybe the 15 cases are questionable anyway?
>
>> 5. Use a variadic macro approach to optimize list_for_each_entry, so that
>> it supports both three and four arguments.
>>
>> Pros: (1) Does not add redundant interfaces.
>> (2) Does not depend on immediate per-subsystem adaptation and can be
>> merged directly.
>> Cons: (1) Increases compile time.
>> (2) list_for_each_entry and list_for_each_entry_safe would be merged
>> into one, and list_for_each_entry_safe would gradually be deprecated.
>
> Please don't do the macro tricks.
>
>> 6. Make no changes, keep the current logic unchanged, and close the current
>> email discussion.
>
> I like hiding the temporary stuff when possible.
>
> BR,
> Jani.
Hi all,
If there are no objections, I will make the changes using the first approach.
Hi David Laight,
You previously expressed a different opinion. Do you have any further comments
on the current proposed approach?
--
Thanks
Kaitao Cheng
^ permalink raw reply
* [PATCH v5 00/18] dyndbg: cleanups, refactors in prep for API fix
From: Jim Cromie @ 2026-07-02 16:40 UTC (permalink / raw)
To: Andrew Morton, Jason Baron, Jim Cromie, Jonathan Corbet,
Shuah Khan, Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann,
David Airlie, Simona Vetter, Arnd Bergmann, Luis Chamberlain,
Petr Pavlu, Daniel Gomez, Sami Tolvanen, Aaron Tomlin
Cc: linux-kernel, linux-doc, dri-devel, linux-arch, linux-modules,
Louis Chauvet
This series has cleanups and refactors in preparation for an API
change needed to fix a regression in DRM when it uses dyndbg
classmaps. I split these out for easier review, and to stay under
gmail's 500/day message limit.
Whats here:
. factor ddebug_match_desc out from ddebug_change
separate selecting from altering
. add stub macro for DECLARE_DYNDBG_CLASSMAP
for cleaner patches later
. reword class unknown to class _UNKNOWN_
a more greppable error announcement
. API remove DD_CLASS_TYPE_ DISJOINT LEVEL _NAME
these are unused, just extra untested code.
. drop NUM_TYPE_ARGS - just use ~ARRAY_SIZE
. bump num tokens in a query cmd from 9 to 15
with class keyword, can have 13 words in a query
. reduce verbose debug clutter
7 log-lines to 4, with same info
. lib parser add match_wildcard_hyphen for underscore/hypen equivalence
"module kvm-intel" is same as "module kvm_intel"
. dynamic_debug use KBUILD_MODFILE for unique builtin names
disambiguate init/main from kernel/module/main
. refactor param_set_dyndbg_classes and below
improve selectivity of callchain underneath
. tighten fn sig of ddebug_apply_class_bitmap
make more args const
. replace classmap list with an array slice
section records are directly usable from the array
. macrofy a 2 index for loop pattern - DRY
. pin class param storage to u32
avoid param size ambiguity across arches
this also changes __drm_debug from long unsigned to u32.
. module make proper substructs in _ddebug_info
its just cleaner
. move mod_name down from struct ddebug_table to _ddebug_info
makes mod_name more available where its needed
. hoist classmap filter-by-modname up to ddebug_add_module
closer to where its done for pr-debug descriptors
. change __dynamic_func_call_cls macros into expressions
Xe driver uses it inside an if (cond), do-while-0 cant sit there.
"user visible" changes:
The KBUILD_MODFILE derived name appears in dynamic_debug/control, so
[main] changes to [init/main] etc. The query parser is adjusted so
that "module main" still selects all of the former [main] modules.
It is user visible, but not a behavior change.
If a coder calls __pr_debug_cls(5, "...") but does not register a
classmap for it, that callsite will display in dynamic_debug/control
as "class:_UNKNOWN_ _id:5", not "class unknown, _id:5" as previously.
This is an error case, and has never been seen in the wild.
---
Changes in v5:
moves KBUILD_MODFILE ahead of array-slice, to address sashiko
complaints which were fixed later in V4.
Changes in v4:
Dyndbg previously used KBUILD_MODNAME to provide module-name, this
works well for loadable modules (module loader requires unique module
names), but for builtin modules, is effectively kbasename, and is not
guaranteed unique.
So we get 4 modules named "main": init/main, kernel/power/main,
kernel/base/power/main. This ambiguity is visible in user-space since
the beginning of dyndbg.
Now suppose kernel/{,base}/power/main want to define classmaps to
categorize the various pr-debugs they have. The current code finds a
module's classmaps by strcmp on modname, so init/main will match
against classmaps defined by both kernel/{,base}/power/main.
The current code will also map "main" classes to kernel/*/power/main,
so they will probably work at first, but 2 independent classmaps can
both use class-ids 0-N, but will conflict if they're both used by a
module. Then we have classmap overlaps and unpredictable results.
Changes in v3:
fix some (not all) of sashiko's complaints.
Changes in v2:
https://lore.kernel.org/lkml/20260504-dd-cleanups-2-v1-0-6fdd24040642@gmail.com/
V2 addressed most of sashiko's feedback on V1:
https://sashiko.dev/#/patchset/20260504-dd-cleanups-2-v1-0-6fdd24040642%40gmail.com
---
Jim Cromie (18):
dyndbg: factor ddebug_match_desc out from ddebug_change
dyndbg: add stub macro for DECLARE_DYNDBG_CLASSMAP
dyndbg: reword "class unknown," to "class:_UNKNOWN_"
dyndbg-API: remove DD_CLASS_TYPE_(DISJOINT|LEVEL)_NAMES and code
dyndbg: drop NUM_TYPE_ARGS
dyndbg: bump num-tokens in a query-cmd from 9 to 15
dyndbg: reduce verbose/debug clutter
lib/parser: add match_wildcard_hyphen() for agnostic matching
dyndbg: use KBUILD_MODFILE for unique builtin module names
dyndbg: refactor param_set_dyndbg_classes and below
dyndbg: tighten fn-sig of ddebug_apply_class_bitmap
dyndbg: replace classmap list with an array-slice
dyndbg: macrofy a 2-index for-loop pattern
dyndbg: pin class param storage to u32
dyndbg,module: make proper substructs in _ddebug_info
dyndbg: move mod_name down from struct ddebug_table to _ddebug_info
dyndbg: hoist classmap-filter-by-modname up to ddebug_add_module
dyndbg: change __dynamic_func_call_cls* macros into expressions
Documentation/admin-guide/dynamic-debug-howto.rst | 42 +-
drivers/gpu/drm/drm_print.c | 6 +-
include/asm-generic/dyndbg.lds.h | 14 +-
include/drm/drm_print.h | 2 +-
include/linux/dynamic_debug.h | 130 +++---
include/linux/parser.h | 1 +
kernel/module/main.c | 12 +-
lib/dynamic_debug.c | 494 +++++++++++-----------
lib/parser.c | 58 ++-
lib/test_dynamic_debug.c | 28 +-
10 files changed, 397 insertions(+), 390 deletions(-)
---
base-commit: 4dcdecc52686a3fbd4545e86fc711fdcd15f09cb
change-id: 20260521-dd-maint-2-76c542079420
prerequisite-change-id: 20260630-fix-align-589738662161:v4
prerequisite-patch-id: d6b2b7d254c7e8bbc0aea891d49b15dc1e71eaa4
prerequisite-patch-id: 3dffaa165e78dc58e443469755eddb07972d0ddf
prerequisite-patch-id: 2c4827d84b4159e71df89cca2a03938a534ecdb5
prerequisite-patch-id: 4599f9be1eb06c0d7f2a7c657d4940411635e94b
prerequisite-patch-id: aea9e121b30e3c7f3d76921b49f81ad421b7af51
Best regards,
--
Jim Cromie <jim.cromie@gmail.com>
^ permalink raw reply
* [PATCH v5 01/18] dyndbg: factor ddebug_match_desc out from ddebug_change
From: Jim Cromie @ 2026-07-02 16:40 UTC (permalink / raw)
To: Andrew Morton, Jason Baron, Jim Cromie, Jonathan Corbet,
Shuah Khan, Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann,
David Airlie, Simona Vetter, Arnd Bergmann, Luis Chamberlain,
Petr Pavlu, Daniel Gomez, Sami Tolvanen, Aaron Tomlin
Cc: linux-kernel, linux-doc, dri-devel, linux-arch, linux-modules,
Louis Chauvet
In-Reply-To: <20260702-dd-maint-2-v5-0-24f22b052bf2@gmail.com>
ddebug_change() is a big (~100 lines) function with a nested for loop.
The outer loop walks the per-module ddebug_tables list, and does
module stuff: it filters on a query's "module FOO*" and "class BAR",
failures here skip the entire inner loop.
The inner loop (60 lines) scans a module's descriptors. It starts
with a long block of filters on function, line, format, and the
validated "BAR" class (or the legacy/_DPRINTK_CLASS_DFLT).
These filters "continue" past pr_debugs that don't match the query
criteria, before it falls through the code below that counts matches,
then adjusts the flags and static-keys. This is unnecessarily hard to
think about.
So move the per-descriptor filter-block into a boolean function:
ddebug_match_desc(desc), and change each "continue" to "return false".
This puts a clear interface in place, so any future changes are either
inside, outside, or across this interface.
also fix checkpatch complaints about spaces and braces.
Signed-off-by: Jim Cromie <jim.cromie@gmail.com>
Reviewed-by: Louis Chauvet <louis.chauvet@bootlin.com>
---
v5: check for null format in callsite. shouldnt happen, but pr_debug() isnt illegal
---
lib/dynamic_debug.c | 87 +++++++++++++++++++++++++++++++----------------------
1 file changed, 51 insertions(+), 36 deletions(-)
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index 18a71a9108d3..577a07916072 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -172,6 +172,56 @@ static struct ddebug_class_map *ddebug_find_valid_class(struct ddebug_table cons
* callsites, normally the same as number of changes. If verbose,
* logs the changes. Takes ddebug_lock.
*/
+static bool ddebug_match_desc(const struct ddebug_query *query,
+ struct _ddebug *dp,
+ int valid_class)
+{
+ /* match site against query-class */
+ if (dp->class_id != valid_class)
+ return false;
+
+ /* match against the source filename */
+ if (query->filename &&
+ !match_wildcard(query->filename, dp->filename) &&
+ !match_wildcard(query->filename,
+ kbasename(dp->filename)) &&
+ !match_wildcard(query->filename,
+ trim_prefix(dp->filename)))
+ return false;
+
+ /* match against the function */
+ if (query->function &&
+ !match_wildcard(query->function, dp->function))
+ return false;
+
+ /* match against the format */
+ if (query->format) {
+ if (!dp->format) {
+ pr_info("encountered a NULL format\n");
+ return false;
+ }
+ if (*query->format == '^') {
+ char *p;
+ /* anchored search. match must be at beginning */
+ p = strstr(dp->format, query->format + 1);
+ if (p != dp->format)
+ return false;
+ } else if (!strstr(dp->format, query->format)) {
+ return false;
+ }
+ }
+
+ /* match against the line number range */
+ if (query->first_lineno &&
+ dp->lineno < query->first_lineno)
+ return false;
+ if (query->last_lineno &&
+ dp->lineno > query->last_lineno)
+ return false;
+
+ return true;
+}
+
static int ddebug_change(const struct ddebug_query *query,
struct flag_settings *modifiers)
{
@@ -204,42 +254,7 @@ static int ddebug_change(const struct ddebug_query *query,
for (i = 0; i < dt->num_ddebugs; i++) {
struct _ddebug *dp = &dt->ddebugs[i];
- /* match site against query-class */
- if (dp->class_id != valid_class)
- continue;
-
- /* match against the source filename */
- if (query->filename &&
- !match_wildcard(query->filename, dp->filename) &&
- !match_wildcard(query->filename,
- kbasename(dp->filename)) &&
- !match_wildcard(query->filename,
- trim_prefix(dp->filename)))
- continue;
-
- /* match against the function */
- if (query->function &&
- !match_wildcard(query->function, dp->function))
- continue;
-
- /* match against the format */
- if (query->format) {
- if (*query->format == '^') {
- char *p;
- /* anchored search. match must be at beginning */
- p = strstr(dp->format, query->format+1);
- if (p != dp->format)
- continue;
- } else if (!strstr(dp->format, query->format))
- continue;
- }
-
- /* match against the line number range */
- if (query->first_lineno &&
- dp->lineno < query->first_lineno)
- continue;
- if (query->last_lineno &&
- dp->lineno > query->last_lineno)
+ if (!ddebug_match_desc(query, dp, valid_class))
continue;
nfound++;
--
2.54.0
^ 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