- Linux-kselftest-mirror - lists.linaro.org

[PATCH net-next] selftests: drv-net: fix merge conflicts resolution

by Matthieu Baerts (NGI0)

After the recent merge between net-next and net, I got some conflicts on my side because the merge resolution was different from Stephen's one [1] I applied on my side in the MPTCP tree. It looks like the code that is now in net-next is using the old way to retrieve the local and remote addresses. This patch is now using the new way, like what was in Stephen's email [1]. Also, in get_interface_info(), there were no conflicts in this area, because that was new code from 'net', but a small adaptation was needed there as well to get the remote address. Fixes: 941defcea7e1 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net") Link: https://lore.kernel.org/20250311115758.17a1d414@canb.auug.org.au [1] Suggested-by: Stephen Rothwell <sfr(a)canb.auug.org.au> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- tools/testing/selftests/drivers/net/ping.py | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py index 7a1026a073681d159202015fc6945e91368863fe..79f07e0510ecc14d3bc2716e14f49f9381bb919f 100755 --- a/tools/testing/selftests/drivers/net/ping.py +++ b/tools/testing/selftests/drivers/net/ping.py @@ -15,18 +15,18 @@ no_sleep=False def _test_v4(cfg) -> None: cfg.require_ipver("4") - cmd(f"ping -c 1 -W0.5 {cfg.remote_v4}") - cmd(f"ping -c 1 -W0.5 {cfg.v4}", host=cfg.remote) - cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.remote_v4}") - cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.v4}", host=cfg.remote) + cmd("ping -c 1 -W0.5 " + cfg.remote_addr_v["4"]) + cmd("ping -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote) + cmd("ping -s 65000 -c 1 -W0.5 " + cfg.remote_addr_v["4"]) + cmd("ping -s 65000 -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote) def _test_v6(cfg) -> None: cfg.require_ipver("6") - cmd(f"ping -c 1 -W5 {cfg.remote_v6}") - cmd(f"ping -c 1 -W5 {cfg.v6}", host=cfg.remote) - cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.remote_v6}") - cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.v6}", host=cfg.remote) + cmd("ping -c 1 -W5 " + cfg.remote_addr_v["6"]) + cmd("ping -c 1 -W5 " + cfg.addr_v["6"], host=cfg.remote) + cmd("ping -s 65000 -c 1 -W0.5 " + cfg.remote_addr_v["6"]) + cmd("ping -s 65000 -c 1 -W0.5 " + cfg.addr_v["6"], host=cfg.remote) def _test_tcp(cfg) -> None: cfg.require_cmd("socat", remote=True) @@ -120,7 +120,7 @@ def get_interface_info(cfg) -> None: global remote_ifname global no_sleep - remote_info = cmd(f"ip -4 -o addr show to {cfg.remote_v4} | awk '{{print $2}}'", shell=True, host=cfg.remote).stdout + remote_info = cmd(f"ip -4 -o addr show to {cfg.remote_addr_v['4']} | awk '{{print $2}}'", shell=True, host=cfg.remote).stdout remote_ifname = remote_info.rstrip('\n') if remote_ifname == "": raise KsftFailEx('Can not get remote interface') --- base-commit: 941defcea7e11ad7ff8f0d4856716dd637d757dd change-id: 20250314-net-next-drv-net-ping-fix-merge-b303167fde16 Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

4 months

3
2
0 0

[PATCH 3/3] rust: replace `addr_of[_mut]!` with `&raw [mut]`

by Antonio Hickey

Replacing all occurrences of `addr_of!(place)` with `&raw place`, and all occurrences of `addr_of_mut!(place)` with `&raw mut place`. Utilizing the new feature will allow us to reduce macro complexity, and improve consistency with existing reference syntax as `&raw`, `&raw mut` is very similar to `&`, `&mut` making it fit more naturally with other existing code. Depends on: Patch 1/3 0001-rust-enable-raw_ref_op-feature.patch Suggested-by: Benno Lossin <y86-dev(a)protonmail.com> Link: https://github.com/Rust-for-Linux/linux/issues/1148 Signed-off-by: Antonio Hickey <contact(a)antoniohickey.com> --- rust/kernel/block/mq/request.rs | 4 ++-- rust/kernel/faux.rs | 4 ++-- rust/kernel/fs/file.rs | 2 +- rust/kernel/init.rs | 8 ++++---- rust/kernel/init/macros.rs | 28 +++++++++++++------------- rust/kernel/jump_label.rs | 4 ++-- rust/kernel/kunit.rs | 4 ++-- rust/kernel/list.rs | 2 +- rust/kernel/list/impl_list_item_mod.rs | 6 +++--- rust/kernel/net/phy.rs | 4 ++-- rust/kernel/pci.rs | 4 ++-- rust/kernel/platform.rs | 4 +--- rust/kernel/rbtree.rs | 22 ++++++++++---------- rust/kernel/sync/arc.rs | 2 +- rust/kernel/task.rs | 4 ++-- rust/kernel/workqueue.rs | 8 ++++---- 16 files changed, 54 insertions(+), 56 deletions(-) diff --git a/rust/kernel/block/mq/request.rs b/rust/kernel/block/mq/request.rs index 7943f43b9575..4a5b7ec914ef 100644 --- a/rust/kernel/block/mq/request.rs +++ b/rust/kernel/block/mq/request.rs @@ -12,7 +12,7 @@ }; use core::{ marker::PhantomData, - ptr::{addr_of_mut, NonNull}, + ptr::NonNull, sync::atomic::{AtomicU64, Ordering}, }; @@ -187,7 +187,7 @@ pub(crate) fn refcount(&self) -> &AtomicU64 { pub(crate) unsafe fn refcount_ptr(this: *mut Self) -> *mut AtomicU64 { // SAFETY: Because of the safety requirements of this function, the // field projection is safe. - unsafe { addr_of_mut!((*this).refcount) } + unsafe { &raw mut (*this).refcount } } } diff --git a/rust/kernel/faux.rs b/rust/kernel/faux.rs index 5acc0c02d451..52ac554c1119 100644 --- a/rust/kernel/faux.rs +++ b/rust/kernel/faux.rs @@ -7,7 +7,7 @@ //! C header: [`include/linux/device/faux.h`] use crate::{bindings, device, error::code::*, prelude::*}; -use core::ptr::{addr_of_mut, null, null_mut, NonNull}; +use core::ptr::{null, null_mut, NonNull}; /// The registration of a faux device. /// @@ -45,7 +45,7 @@ impl AsRef<device::Device> for Registration { fn as_ref(&self) -> &device::Device { // SAFETY: The underlying `device` in `faux_device` is guaranteed by the C API to be // a valid initialized `device`. - unsafe { device::Device::as_ref(addr_of_mut!((*self.as_raw()).dev)) } + unsafe { device::Device::as_ref((&raw mut (*self.as_raw()).dev)) } } } diff --git a/rust/kernel/fs/file.rs b/rust/kernel/fs/file.rs index ed57e0137cdb..7ee4830b67f3 100644 --- a/rust/kernel/fs/file.rs +++ b/rust/kernel/fs/file.rs @@ -331,7 +331,7 @@ pub fn flags(&self) -> u32 { // SAFETY: The file is valid because the shared reference guarantees a nonzero refcount. // // FIXME(read_once): Replace with `read_once` when available on the Rust side. - unsafe { core::ptr::addr_of!((*self.as_ptr()).f_flags).read_volatile() } + unsafe { (&raw const (*self.as_ptr()).f_flags).read_volatile() } } } diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index 7fd1ea8265a5..a8fac6558671 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -122,7 +122,7 @@ //! ```rust //! # #![expect(unreachable_pub, clippy::disallowed_names)] //! use kernel::{init, types::Opaque}; -//! use core::{ptr::addr_of_mut, marker::PhantomPinned, pin::Pin}; +//! use core::{marker::PhantomPinned, pin::Pin}; //! # mod bindings { //! # #![expect(non_camel_case_types)] //! # #![expect(clippy::missing_safety_doc)] @@ -159,7 +159,7 @@ //! unsafe { //! init::pin_init_from_closure(move |slot: *mut Self| { //! // `slot` contains uninit memory, avoid creating a reference. -//! let foo = addr_of_mut!((*slot).foo); +//! let foo = &raw mut (*slot).foo; //! //! // Initialize the `foo` //! bindings::init_foo(Opaque::raw_get(foo)); @@ -541,7 +541,7 @@ macro_rules! stack_try_pin_init { /// /// ```rust /// # use kernel::{macros::{Zeroable, pin_data}, pin_init}; -/// # use core::{ptr::addr_of_mut, marker::PhantomPinned}; +/// # use core::marker::PhantomPinned; /// #[pin_data] /// #[derive(Zeroable)] /// struct Buf { @@ -554,7 +554,7 @@ macro_rules! stack_try_pin_init { /// pin_init!(&this in Buf { /// buf: [0; 64], /// // SAFETY: TODO. -/// ptr: unsafe { addr_of_mut!((*this.as_ptr()).buf).cast() }, +/// ptr: unsafe { &raw mut (*this.as_ptr()).buf.cast() }, /// pin: PhantomPinned, /// }); /// pin_init!(Buf { diff --git a/rust/kernel/init/macros.rs b/rust/kernel/init/macros.rs index 1fd146a83241..af525fbb2f01 100644 --- a/rust/kernel/init/macros.rs +++ b/rust/kernel/init/macros.rs @@ -244,25 +244,25 @@ //! struct __InitOk; //! // This is the expansion of `t,`, which is syntactic sugar for `t: t,`. //! { -//! unsafe { ::core::ptr::write(::core::addr_of_mut!((*slot).t), t) }; +//! unsafe { ::core::ptr::write(&raw mut (*slot).t, t) }; //! } //! // Since initialization could fail later (not in this case, since the //! // error type is `Infallible`) we will need to drop this field if there //! // is an error later. This `DropGuard` will drop the field when it gets //! // dropped and has not yet been forgotten. //! let __t_guard = unsafe { -//! ::pinned_init::__internal::DropGuard::new(::core::addr_of_mut!((*slot).t)) +//! ::pinned_init::__internal::DropGuard::new(&raw mut (*slot).t) //! }; //! // Expansion of `x: 0,`: //! // Since this can be an arbitrary expression we cannot place it inside //! // of the `unsafe` block, so we bind it here. //! { //! let x = 0; -//! unsafe { ::core::ptr::write(::core::addr_of_mut!((*slot).x), x) }; +//! unsafe { ::core::ptr::write(&raw mut (*slot).x, x) }; //! } //! // We again create a `DropGuard`. //! let __x_guard = unsafe { -//! ::kernel::init::__internal::DropGuard::new(::core::addr_of_mut!((*slot).x)) +//! ::kernel::init::__internal::DropGuard::new(&raw mut (*slot).x) //! }; //! // Since initialization has successfully completed, we can now forget //! // the guards. This is not `mem::forget`, since we only have @@ -459,15 +459,15 @@ //! { //! struct __InitOk; //! { -//! unsafe { ::core::ptr::write(::core::addr_of_mut!((*slot).a), a) }; +//! unsafe { ::core::ptr::write(&raw mut (*slot).a, a) }; //! } //! let __a_guard = unsafe { -//! ::kernel::init::__internal::DropGuard::new(::core::addr_of_mut!((*slot).a)) +//! ::kernel::init::__internal::DropGuard::new(&raw mut (*slot).a) //! }; //! let init = Bar::new(36); -//! unsafe { data.b(::core::addr_of_mut!((*slot).b), b)? }; +//! unsafe { data.b(&raw mut (*slot).b, b)? }; //! let __b_guard = unsafe { -//! ::kernel::init::__internal::DropGuard::new(::core::addr_of_mut!((*slot).b)) +//! ::kernel::init::__internal::DropGuard::new(&raw mut (*slot).b) //! }; //! ::core::mem::forget(__b_guard); //! ::core::mem::forget(__a_guard); @@ -1210,7 +1210,7 @@ fn assert_zeroable<T: $crate::init::Zeroable>(_: *mut T) {} // SAFETY: `slot` is valid, because we are inside of an initializer closure, we // return when an error/panic occurs. // We also use the `data` to require the correct trait (`Init` or `PinInit`) for `$field`. - unsafe { $data.$field(::core::ptr::addr_of_mut!((*$slot).$field), init)? }; + unsafe { $data.$field(&raw mut (*$slot).$field, init)? }; // Create the drop guard: // // We rely on macro hygiene to make it impossible for users to access this local variable. @@ -1218,7 +1218,7 @@ fn assert_zeroable<T: $crate::init::Zeroable>(_: *mut T) {} ::kernel::macros::paste! { // SAFETY: We forget the guard later when initialization has succeeded. let [< __ $field _guard >] = unsafe { - $crate::init::__internal::DropGuard::new(::core::ptr::addr_of_mut!((*$slot).$field)) + $crate::init::__internal::DropGuard::new(&raw mut (*$slot).$field) }; $crate::__init_internal!(init_slot($use_data): @@ -1241,7 +1241,7 @@ fn assert_zeroable<T: $crate::init::Zeroable>(_: *mut T) {} // // SAFETY: `slot` is valid, because we are inside of an initializer closure, we // return when an error/panic occurs. - unsafe { $crate::init::Init::__init(init, ::core::ptr::addr_of_mut!((*$slot).$field))? }; + unsafe { $crate::init::Init::__init(init, &raw mut (*$slot).$field)? }; // Create the drop guard: // // We rely on macro hygiene to make it impossible for users to access this local variable. @@ -1249,7 +1249,7 @@ fn assert_zeroable<T: $crate::init::Zeroable>(_: *mut T) {} ::kernel::macros::paste! { // SAFETY: We forget the guard later when initialization has succeeded. let [< __ $field _guard >] = unsafe { - $crate::init::__internal::DropGuard::new(::core::ptr::addr_of_mut!((*$slot).$field)) + $crate::init::__internal::DropGuard::new(&raw mut (*$slot).$field) }; $crate::__init_internal!(init_slot(): @@ -1272,7 +1272,7 @@ fn assert_zeroable<T: $crate::init::Zeroable>(_: *mut T) {} // Initialize the field. // // SAFETY: The memory at `slot` is uninitialized. - unsafe { ::core::ptr::write(::core::ptr::addr_of_mut!((*$slot).$field), $field) }; + unsafe { ::core::ptr::write(&raw mut (*$slot).$field, $field) }; } // Create the drop guard: // @@ -1281,7 +1281,7 @@ fn assert_zeroable<T: $crate::init::Zeroable>(_: *mut T) {} ::kernel::macros::paste! { // SAFETY: We forget the guard later when initialization has succeeded. let [< __ $field _guard >] = unsafe { - $crate::init::__internal::DropGuard::new(::core::ptr::addr_of_mut!((*$slot).$field)) + $crate::init::__internal::DropGuard::new(&raw mut (*$slot).$field) }; $crate::__init_internal!(init_slot($($use_data)?): diff --git a/rust/kernel/jump_label.rs b/rust/kernel/jump_label.rs index 4e974c768dbd..05d4564714c7 100644 --- a/rust/kernel/jump_label.rs +++ b/rust/kernel/jump_label.rs @@ -20,8 +20,8 @@ #[macro_export] macro_rules! static_branch_unlikely { ($key:path, $keytyp:ty, $field:ident) => {{ - let _key: *const $keytyp = ::core::ptr::addr_of!($key); - let _key: *const $crate::bindings::static_key_false = ::core::ptr::addr_of!((*_key).$field); + let _key: *const $keytyp = &raw $key; + let _key: *const $crate::bindings::static_key_false = &raw (*_key).$field; let _key: *const $crate::bindings::static_key = _key.cast(); #[cfg(not(CONFIG_JUMP_LABEL))] diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs index 824da0e9738a..18357dd782ed 100644 --- a/rust/kernel/kunit.rs +++ b/rust/kernel/kunit.rs @@ -128,9 +128,9 @@ unsafe impl Sync for UnaryAssert {} unsafe { $crate::bindings::__kunit_do_failed_assertion( kunit_test, - core::ptr::addr_of!(LOCATION.0), + &raw LOCATION.0, $crate::bindings::kunit_assert_type_KUNIT_ASSERTION, - core::ptr::addr_of!(ASSERTION.0.assert), + &raw ASSERTION.0.assert, Some($crate::bindings::kunit_unary_assert_format), core::ptr::null(), ); diff --git a/rust/kernel/list.rs b/rust/kernel/list.rs index c0ed227b8a4f..e98f0820f002 100644 --- a/rust/kernel/list.rs +++ b/rust/kernel/list.rs @@ -176,7 +176,7 @@ pub fn new() -> impl PinInit<Self> { #[inline] unsafe fn fields(me: *mut Self) -> *mut ListLinksFields { // SAFETY: The caller promises that the pointer is valid. - unsafe { Opaque::raw_get(ptr::addr_of!((*me).inner)) } + unsafe { Opaque::raw_get(&raw const (*me).inner) } } /// # Safety diff --git a/rust/kernel/list/impl_list_item_mod.rs b/rust/kernel/list/impl_list_item_mod.rs index a0438537cee1..014b6713d59d 100644 --- a/rust/kernel/list/impl_list_item_mod.rs +++ b/rust/kernel/list/impl_list_item_mod.rs @@ -49,7 +49,7 @@ macro_rules! impl_has_list_links { // SAFETY: The implementation of `raw_get_list_links` only compiles if the field has the // right type. // - // The behavior of `raw_get_list_links` is not changed since the `addr_of_mut!` macro is + // The behavior of `raw_get_list_links` is not changed since the `&raw mut` op is // equivalent to the pointer offset operation in the trait definition. unsafe impl$(<$($implarg),*>)? $crate::list::HasListLinks$(<$id>)? for $self $(<$($selfarg),*>)? @@ -61,7 +61,7 @@ unsafe fn raw_get_list_links(ptr: *mut Self) -> *mut $crate::list::ListLinks$(<$ // SAFETY: The caller promises that the pointer is not dangling. We know that this // expression doesn't follow any pointers, as the `offset_of!` invocation above // would otherwise not compile. - unsafe { ::core::ptr::addr_of_mut!((*ptr)$(.$field)*) } + unsafe { &raw mut (*ptr)$(.$field)* } } } )*}; @@ -103,7 +103,7 @@ macro_rules! impl_has_list_links_self_ptr { unsafe fn raw_get_list_links(ptr: *mut Self) -> *mut $crate::list::ListLinks$(<$id>)? { // SAFETY: The caller promises that the pointer is not dangling. let ptr: *mut $crate::list::ListLinksSelfPtr<$item_type $(, $id)?> = - unsafe { ::core::ptr::addr_of_mut!((*ptr).$field) }; + unsafe { &raw mut (*ptr).$field }; ptr.cast() } } diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs index a59469c785e3..757db052cc09 100644 --- a/rust/kernel/net/phy.rs +++ b/rust/kernel/net/phy.rs @@ -7,7 +7,7 @@ //! C headers: [`include/linux/phy.h`](srctree/include/linux/phy.h). use crate::{error::*, prelude::*, types::Opaque}; -use core::{marker::PhantomData, ptr::addr_of_mut}; +use core::marker::PhantomData; pub mod reg; @@ -285,7 +285,7 @@ impl AsRef<kernel::device::Device> for Device { fn as_ref(&self) -> &kernel::device::Device { let phydev = self.0.get(); // SAFETY: The struct invariant ensures that `mdio.dev` is valid. - unsafe { kernel::device::Device::as_ref(addr_of_mut!((*phydev).mdio.dev)) } + unsafe { kernel::device::Device::as_ref(&raw mut (*phydev).mdio.dev) } } } diff --git a/rust/kernel/pci.rs b/rust/kernel/pci.rs index f7b2743828ae..6cb9ed1e7cbf 100644 --- a/rust/kernel/pci.rs +++ b/rust/kernel/pci.rs @@ -17,7 +17,7 @@ types::{ARef, ForeignOwnable, Opaque}, ThisModule, }; -use core::{ops::Deref, ptr::addr_of_mut}; +use core::ops::Deref; use kernel::prelude::*; /// An adapter for the registration of PCI drivers. @@ -60,7 +60,7 @@ extern "C" fn probe_callback( ) -> kernel::ffi::c_int { // SAFETY: The PCI bus only ever calls the probe callback with a valid pointer to a // `struct pci_dev`. - let dev = unsafe { device::Device::get_device(addr_of_mut!((*pdev).dev)) }; + let dev = unsafe { device::Device::get_device(&raw mut (*pdev).dev) }; // SAFETY: `dev` is guaranteed to be embedded in a valid `struct pci_dev` by the call // above. let mut pdev = unsafe { Device::from_dev(dev) }; diff --git a/rust/kernel/platform.rs b/rust/kernel/platform.rs index 1297f5292ba9..344875ad7b82 100644 --- a/rust/kernel/platform.rs +++ b/rust/kernel/platform.rs @@ -14,8 +14,6 @@ ThisModule, }; -use core::ptr::addr_of_mut; - /// An adapter for the registration of platform drivers. pub struct Adapter<T: Driver>(T); @@ -55,7 +53,7 @@ unsafe fn unregister(pdrv: &Opaque<Self::RegType>) { impl<T: Driver + 'static> Adapter<T> { extern "C" fn probe_callback(pdev: *mut bindings::platform_device) -> kernel::ffi::c_int { // SAFETY: The platform bus only ever calls the probe callback with a valid `pdev`. - let dev = unsafe { device::Device::get_device(addr_of_mut!((*pdev).dev)) }; + let dev = unsafe { device::Device::get_device(&raw mut (*pdev).dev) }; // SAFETY: `dev` is guaranteed to be embedded in a valid `struct platform_device` by the // call above. let mut pdev = unsafe { Device::from_dev(dev) }; diff --git a/rust/kernel/rbtree.rs b/rust/kernel/rbtree.rs index 1ea25c7092fb..b0ad35663cb0 100644 --- a/rust/kernel/rbtree.rs +++ b/rust/kernel/rbtree.rs @@ -11,7 +11,7 @@ cmp::{Ord, Ordering}, marker::PhantomData, mem::MaybeUninit, - ptr::{addr_of_mut, from_mut, NonNull}, + ptr::{from_mut, NonNull}, }; /// A red-black tree with owned nodes. @@ -238,7 +238,7 @@ pub fn values_mut(&mut self) -> impl Iterator<Item = &'_ mut V> { /// Returns a cursor over the tree nodes, starting with the smallest key. pub fn cursor_front(&mut self) -> Option<Cursor<'_, K, V>> { - let root = addr_of_mut!(self.root); + let root = &raw mut self.root; // SAFETY: `self.root` is always a valid root node let current = unsafe { bindings::rb_first(root) }; NonNull::new(current).map(|current| { @@ -253,7 +253,7 @@ pub fn cursor_front(&mut self) -> Option<Cursor<'_, K, V>> { /// Returns a cursor over the tree nodes, starting with the largest key. pub fn cursor_back(&mut self) -> Option<Cursor<'_, K, V>> { - let root = addr_of_mut!(self.root); + let root = &raw mut self.root; // SAFETY: `self.root` is always a valid root node let current = unsafe { bindings::rb_last(root) }; NonNull::new(current).map(|current| { @@ -459,7 +459,7 @@ pub fn cursor_lower_bound(&mut self, key: &K) -> Option<Cursor<'_, K, V>> let best = best_match?; // SAFETY: `best` is a non-null node so it is valid by the type invariants. - let links = unsafe { addr_of_mut!((*best.as_ptr()).links) }; + let links = unsafe { &raw mut (*best.as_ptr()).links }; NonNull::new(links).map(|current| { // INVARIANT: @@ -767,7 +767,7 @@ pub fn remove_current(self) -> (Option<Self>, RBTreeNode<K, V>) { let node = RBTreeNode { node }; // SAFETY: The reference to the tree used to create the cursor outlives the cursor, so // the tree cannot change. By the tree invariant, all nodes are valid. - unsafe { bindings::rb_erase(&mut (*this).links, addr_of_mut!(self.tree.root)) }; + unsafe { bindings::rb_erase(&mut (*this).links, &raw mut self.tree.root) }; let current = match (prev, next) { (_, Some(next)) => next, @@ -803,7 +803,7 @@ fn remove_neighbor(&mut self, direction: Direction) -> Option<RBTreeNode<K, V>> let neighbor = neighbor.as_ptr(); // SAFETY: The reference to the tree used to create the cursor outlives the cursor, so // the tree cannot change. By the tree invariant, all nodes are valid. - unsafe { bindings::rb_erase(neighbor, addr_of_mut!(self.tree.root)) }; + unsafe { bindings::rb_erase(neighbor, &raw mut self.tree.root) }; // SAFETY: By the type invariant of `Self`, all non-null `rb_node` pointers stored in `self` // point to the links field of `Node<K, V>` objects. let this = unsafe { container_of!(neighbor, Node<K, V>, links) }.cast_mut(); @@ -918,7 +918,7 @@ unsafe fn to_key_value_raw<'b>(node: NonNull<bindings::rb_node>) -> (&'b K, *mut let k = unsafe { &(*this).key }; // SAFETY: The passed `node` is the current node or a non-null neighbor, // thus `this` is valid by the type invariants. - let v = unsafe { addr_of_mut!((*this).value) }; + let v = unsafe { &raw mut (*this).value }; (k, v) } } @@ -1027,7 +1027,7 @@ fn next(&mut self) -> Option<Self::Item> { self.next = unsafe { bindings::rb_next(self.next) }; // SAFETY: By the same reasoning above, it is safe to dereference the node. - Some(unsafe { (addr_of_mut!((*cur).key), addr_of_mut!((*cur).value)) }) + Some(unsafe { (&raw mut (*cur).key, &raw mut (*cur).value) }) } } @@ -1170,7 +1170,7 @@ fn insert(self, node: RBTreeNode<K, V>) -> &'a mut V { // SAFETY: `node` is valid at least until we call `Box::from_raw`, which only happens when // the node is removed or replaced. - let node_links = unsafe { addr_of_mut!((*node).links) }; + let node_links = unsafe { &raw mut (*node).links }; // INVARIANT: We are linking in a new node, which is valid. It remains valid because we // "forgot" it with `Box::into_raw`. @@ -1178,7 +1178,7 @@ fn insert(self, node: RBTreeNode<K, V>) -> &'a mut V { unsafe { bindings::rb_link_node(node_links, self.parent, self.child_field_of_parent) }; // SAFETY: All pointers are valid. `node` has just been inserted into the tree. - unsafe { bindings::rb_insert_color(node_links, addr_of_mut!((*self.rbtree).root)) }; + unsafe { bindings::rb_insert_color(node_links, &raw mut (*self.rbtree).root) }; // SAFETY: The node is valid until we remove it from the tree. unsafe { &mut (*node).value } @@ -1261,7 +1261,7 @@ fn replace(self, node: RBTreeNode<K, V>) -> RBTreeNode<K, V> { // SAFETY: `node` is valid at least until we call `Box::from_raw`, which only happens when // the node is removed or replaced. - let new_node_links = unsafe { addr_of_mut!((*node).links) }; + let new_node_links = unsafe { &raw mut (*node).links }; // SAFETY: This updates the pointers so that `new_node_links` is in the tree where // `self.node_links` used to be. diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs index 3cefda7a4372..81d8b0f84957 100644 --- a/rust/kernel/sync/arc.rs +++ b/rust/kernel/sync/arc.rs @@ -243,7 +243,7 @@ pub fn into_raw(self) -> *const T { let ptr = self.ptr.as_ptr(); core::mem::forget(self); // SAFETY: The pointer is valid. - unsafe { core::ptr::addr_of!((*ptr).data) } + unsafe { &raw const (*ptr).data } } /// Recreates an [`Arc`] instance previously deconstructed via [`Arc::into_raw`]. diff --git a/rust/kernel/task.rs b/rust/kernel/task.rs index 49012e711942..b2ac768eed23 100644 --- a/rust/kernel/task.rs +++ b/rust/kernel/task.rs @@ -257,7 +257,7 @@ pub fn as_ptr(&self) -> *mut bindings::task_struct { pub fn group_leader(&self) -> &Task { // SAFETY: The group leader of a task never changes after initialization, so reading this // field is not a data race. - let ptr = unsafe { *ptr::addr_of!((*self.as_ptr()).group_leader) }; + let ptr = unsafe { *(&raw const (*self.as_ptr()).group_leader) }; // SAFETY: The lifetime of the returned task reference is tied to the lifetime of `self`, // and given that a task has a reference to its group leader, we know it must be valid for @@ -269,7 +269,7 @@ pub fn group_leader(&self) -> &Task { pub fn pid(&self) -> Pid { // SAFETY: The pid of a task never changes after initialization, so reading this field is // not a data race. - unsafe { *ptr::addr_of!((*self.as_ptr()).pid) } + unsafe { *(&raw const (*self.as_ptr()).pid) } } /// Returns the UID of the given task. diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs index 0cd100d2aefb..34e8abb38974 100644 --- a/rust/kernel/workqueue.rs +++ b/rust/kernel/workqueue.rs @@ -401,9 +401,9 @@ pub fn new(name: &'static CStr, key: &'static LockClassKey) -> impl PinInit<Self pub unsafe fn raw_get(ptr: *const Self) -> *mut bindings::work_struct { // SAFETY: The caller promises that the pointer is aligned and not dangling. // - // A pointer cast would also be ok due to `#[repr(transparent)]`. We use `addr_of!` so that - // the compiler does not complain that the `work` field is unused. - unsafe { Opaque::raw_get(core::ptr::addr_of!((*ptr).work)) } + // A pointer cast would also be ok due to `#[repr(transparent)]`. We use `&raw const (*ptr).work` + // so that the compiler does not complain that the `work` field is unused. + unsafe { Opaque::raw_get(&raw const (*ptr).work) } } } @@ -510,7 +510,7 @@ macro_rules! impl_has_work { unsafe fn raw_get_work(ptr: *mut Self) -> *mut $crate::workqueue::Work<$work_type $(, $id)?> { // SAFETY: The caller promises that the pointer is not dangling. unsafe { - ::core::ptr::addr_of_mut!((*ptr).$field) + &raw mut (*ptr).$field } } } -- 2.48.1

4 months

2
1
0 0

[PATCH v2 3/3] rust: replace `addr_of[_mut]!` with `&raw [const | mut]`

by Antonio Hickey

Replacing all occurrences of `addr_of!(place)` with `&raw const place`, and all occurrences of `addr_of_mut!(place)` with `&raw mut place`. Utilizing the new feature will allow us to reduce macro complexity, and improve consistency with existing reference syntax as `&raw const`, `&raw mut` is very similar to `&`, `&mut` making it fit more naturally with other existing code than the previously used macros. Suggested-by: Benno Lossin <benno.lossin(a)proton.me> Link: https://github.com/Rust-for-Linux/linux/issues/1148 Signed-off-by: Antonio Hickey <contact(a)antoniohickey.com> --- rust/kernel/block/mq/request.rs | 4 ++-- rust/kernel/faux.rs | 4 ++-- rust/kernel/fs/file.rs | 2 +- rust/kernel/init.rs | 8 ++++---- rust/kernel/init/macros.rs | 28 +++++++++++++------------- rust/kernel/jump_label.rs | 4 ++-- rust/kernel/kunit.rs | 4 ++-- rust/kernel/list.rs | 2 +- rust/kernel/list/impl_list_item_mod.rs | 6 +++--- rust/kernel/net/phy.rs | 4 ++-- rust/kernel/pci.rs | 4 ++-- rust/kernel/platform.rs | 4 +--- rust/kernel/rbtree.rs | 22 ++++++++++---------- rust/kernel/sync/arc.rs | 2 +- rust/kernel/task.rs | 4 ++-- rust/kernel/workqueue.rs | 8 ++++---- 16 files changed, 54 insertions(+), 56 deletions(-) diff --git a/rust/kernel/block/mq/request.rs b/rust/kernel/block/mq/request.rs index 7943f43b9575..4a5b7ec914ef 100644 --- a/rust/kernel/block/mq/request.rs +++ b/rust/kernel/block/mq/request.rs @@ -12,7 +12,7 @@ }; use core::{ marker::PhantomData, - ptr::{addr_of_mut, NonNull}, + ptr::NonNull, sync::atomic::{AtomicU64, Ordering}, }; @@ -187,7 +187,7 @@ pub(crate) fn refcount(&self) -> &AtomicU64 { pub(crate) unsafe fn refcount_ptr(this: *mut Self) -> *mut AtomicU64 { // SAFETY: Because of the safety requirements of this function, the // field projection is safe. - unsafe { addr_of_mut!((*this).refcount) } + unsafe { &raw mut (*this).refcount } } } diff --git a/rust/kernel/faux.rs b/rust/kernel/faux.rs index 5acc0c02d451..52ac554c1119 100644 --- a/rust/kernel/faux.rs +++ b/rust/kernel/faux.rs @@ -7,7 +7,7 @@ //! C header: [`include/linux/device/faux.h`] use crate::{bindings, device, error::code::*, prelude::*}; -use core::ptr::{addr_of_mut, null, null_mut, NonNull}; +use core::ptr::{null, null_mut, NonNull}; /// The registration of a faux device. /// @@ -45,7 +45,7 @@ impl AsRef<device::Device> for Registration { fn as_ref(&self) -> &device::Device { // SAFETY: The underlying `device` in `faux_device` is guaranteed by the C API to be // a valid initialized `device`. - unsafe { device::Device::as_ref(addr_of_mut!((*self.as_raw()).dev)) } + unsafe { device::Device::as_ref((&raw mut (*self.as_raw()).dev)) } } } diff --git a/rust/kernel/fs/file.rs b/rust/kernel/fs/file.rs index ed57e0137cdb..7ee4830b67f3 100644 --- a/rust/kernel/fs/file.rs +++ b/rust/kernel/fs/file.rs @@ -331,7 +331,7 @@ pub fn flags(&self) -> u32 { // SAFETY: The file is valid because the shared reference guarantees a nonzero refcount. // // FIXME(read_once): Replace with `read_once` when available on the Rust side. - unsafe { core::ptr::addr_of!((*self.as_ptr()).f_flags).read_volatile() } + unsafe { (&raw const (*self.as_ptr()).f_flags).read_volatile() } } } diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index 7fd1ea8265a5..a8fac6558671 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -122,7 +122,7 @@ //! ```rust //! # #![expect(unreachable_pub, clippy::disallowed_names)] //! use kernel::{init, types::Opaque}; -//! use core::{ptr::addr_of_mut, marker::PhantomPinned, pin::Pin}; +//! use core::{marker::PhantomPinned, pin::Pin}; //! # mod bindings { //! # #![expect(non_camel_case_types)] //! # #![expect(clippy::missing_safety_doc)] @@ -159,7 +159,7 @@ //! unsafe { //! init::pin_init_from_closure(move |slot: *mut Self| { //! // `slot` contains uninit memory, avoid creating a reference. -//! let foo = addr_of_mut!((*slot).foo); +//! let foo = &raw mut (*slot).foo; //! //! // Initialize the `foo` //! bindings::init_foo(Opaque::raw_get(foo)); @@ -541,7 +541,7 @@ macro_rules! stack_try_pin_init { /// /// ```rust /// # use kernel::{macros::{Zeroable, pin_data}, pin_init}; -/// # use core::{ptr::addr_of_mut, marker::PhantomPinned}; +/// # use core::marker::PhantomPinned; /// #[pin_data] /// #[derive(Zeroable)] /// struct Buf { @@ -554,7 +554,7 @@ macro_rules! stack_try_pin_init { /// pin_init!(&this in Buf { /// buf: [0; 64], /// // SAFETY: TODO. -/// ptr: unsafe { addr_of_mut!((*this.as_ptr()).buf).cast() }, +/// ptr: unsafe { &raw mut (*this.as_ptr()).buf.cast() }, /// pin: PhantomPinned, /// }); /// pin_init!(Buf { diff --git a/rust/kernel/init/macros.rs b/rust/kernel/init/macros.rs index 1fd146a83241..af525fbb2f01 100644 --- a/rust/kernel/init/macros.rs +++ b/rust/kernel/init/macros.rs @@ -244,25 +244,25 @@ //! struct __InitOk; //! // This is the expansion of `t,`, which is syntactic sugar for `t: t,`. //! { -//! unsafe { ::core::ptr::write(::core::addr_of_mut!((*slot).t), t) }; +//! unsafe { ::core::ptr::write(&raw mut (*slot).t, t) }; //! } //! // Since initialization could fail later (not in this case, since the //! // error type is `Infallible`) we will need to drop this field if there //! // is an error later. This `DropGuard` will drop the field when it gets //! // dropped and has not yet been forgotten. //! let __t_guard = unsafe { -//! ::pinned_init::__internal::DropGuard::new(::core::addr_of_mut!((*slot).t)) +//! ::pinned_init::__internal::DropGuard::new(&raw mut (*slot).t) //! }; //! // Expansion of `x: 0,`: //! // Since this can be an arbitrary expression we cannot place it inside //! // of the `unsafe` block, so we bind it here. //! { //! let x = 0; -//! unsafe { ::core::ptr::write(::core::addr_of_mut!((*slot).x), x) }; +//! unsafe { ::core::ptr::write(&raw mut (*slot).x, x) }; //! } //! // We again create a `DropGuard`. //! let __x_guard = unsafe { -//! ::kernel::init::__internal::DropGuard::new(::core::addr_of_mut!((*slot).x)) +//! ::kernel::init::__internal::DropGuard::new(&raw mut (*slot).x) //! }; //! // Since initialization has successfully completed, we can now forget //! // the guards. This is not `mem::forget`, since we only have @@ -459,15 +459,15 @@ //! { //! struct __InitOk; //! { -//! unsafe { ::core::ptr::write(::core::addr_of_mut!((*slot).a), a) }; +//! unsafe { ::core::ptr::write(&raw mut (*slot).a, a) }; //! } //! let __a_guard = unsafe { -//! ::kernel::init::__internal::DropGuard::new(::core::addr_of_mut!((*slot).a)) +//! ::kernel::init::__internal::DropGuard::new(&raw mut (*slot).a) //! }; //! let init = Bar::new(36); -//! unsafe { data.b(::core::addr_of_mut!((*slot).b), b)? }; +//! unsafe { data.b(&raw mut (*slot).b, b)? }; //! let __b_guard = unsafe { -//! ::kernel::init::__internal::DropGuard::new(::core::addr_of_mut!((*slot).b)) +//! ::kernel::init::__internal::DropGuard::new(&raw mut (*slot).b) //! }; //! ::core::mem::forget(__b_guard); //! ::core::mem::forget(__a_guard); @@ -1210,7 +1210,7 @@ fn assert_zeroable<T: $crate::init::Zeroable>(_: *mut T) {} // SAFETY: `slot` is valid, because we are inside of an initializer closure, we // return when an error/panic occurs. // We also use the `data` to require the correct trait (`Init` or `PinInit`) for `$field`. - unsafe { $data.$field(::core::ptr::addr_of_mut!((*$slot).$field), init)? }; + unsafe { $data.$field(&raw mut (*$slot).$field, init)? }; // Create the drop guard: // // We rely on macro hygiene to make it impossible for users to access this local variable. @@ -1218,7 +1218,7 @@ fn assert_zeroable<T: $crate::init::Zeroable>(_: *mut T) {} ::kernel::macros::paste! { // SAFETY: We forget the guard later when initialization has succeeded. let [< __ $field _guard >] = unsafe { - $crate::init::__internal::DropGuard::new(::core::ptr::addr_of_mut!((*$slot).$field)) + $crate::init::__internal::DropGuard::new(&raw mut (*$slot).$field) }; $crate::__init_internal!(init_slot($use_data): @@ -1241,7 +1241,7 @@ fn assert_zeroable<T: $crate::init::Zeroable>(_: *mut T) {} // // SAFETY: `slot` is valid, because we are inside of an initializer closure, we // return when an error/panic occurs. - unsafe { $crate::init::Init::__init(init, ::core::ptr::addr_of_mut!((*$slot).$field))? }; + unsafe { $crate::init::Init::__init(init, &raw mut (*$slot).$field)? }; // Create the drop guard: // // We rely on macro hygiene to make it impossible for users to access this local variable. @@ -1249,7 +1249,7 @@ fn assert_zeroable<T: $crate::init::Zeroable>(_: *mut T) {} ::kernel::macros::paste! { // SAFETY: We forget the guard later when initialization has succeeded. let [< __ $field _guard >] = unsafe { - $crate::init::__internal::DropGuard::new(::core::ptr::addr_of_mut!((*$slot).$field)) + $crate::init::__internal::DropGuard::new(&raw mut (*$slot).$field) }; $crate::__init_internal!(init_slot(): @@ -1272,7 +1272,7 @@ fn assert_zeroable<T: $crate::init::Zeroable>(_: *mut T) {} // Initialize the field. // // SAFETY: The memory at `slot` is uninitialized. - unsafe { ::core::ptr::write(::core::ptr::addr_of_mut!((*$slot).$field), $field) }; + unsafe { ::core::ptr::write(&raw mut (*$slot).$field, $field) }; } // Create the drop guard: // @@ -1281,7 +1281,7 @@ fn assert_zeroable<T: $crate::init::Zeroable>(_: *mut T) {} ::kernel::macros::paste! { // SAFETY: We forget the guard later when initialization has succeeded. let [< __ $field _guard >] = unsafe { - $crate::init::__internal::DropGuard::new(::core::ptr::addr_of_mut!((*$slot).$field)) + $crate::init::__internal::DropGuard::new(&raw mut (*$slot).$field) }; $crate::__init_internal!(init_slot($($use_data)?): diff --git a/rust/kernel/jump_label.rs b/rust/kernel/jump_label.rs index 4e974c768dbd..ca10abae0eee 100644 --- a/rust/kernel/jump_label.rs +++ b/rust/kernel/jump_label.rs @@ -20,8 +20,8 @@ #[macro_export] macro_rules! static_branch_unlikely { ($key:path, $keytyp:ty, $field:ident) => {{ - let _key: *const $keytyp = ::core::ptr::addr_of!($key); - let _key: *const $crate::bindings::static_key_false = ::core::ptr::addr_of!((*_key).$field); + let _key: *const $keytyp = &raw const $key; + let _key: *const $crate::bindings::static_key_false = &raw const (*_key).$field; let _key: *const $crate::bindings::static_key = _key.cast(); #[cfg(not(CONFIG_JUMP_LABEL))] diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs index 824da0e9738a..a17ef3b2e860 100644 --- a/rust/kernel/kunit.rs +++ b/rust/kernel/kunit.rs @@ -128,9 +128,9 @@ unsafe impl Sync for UnaryAssert {} unsafe { $crate::bindings::__kunit_do_failed_assertion( kunit_test, - core::ptr::addr_of!(LOCATION.0), + &raw const LOCATION.0, $crate::bindings::kunit_assert_type_KUNIT_ASSERTION, - core::ptr::addr_of!(ASSERTION.0.assert), + &raw const ASSERTION.0.assert, Some($crate::bindings::kunit_unary_assert_format), core::ptr::null(), ); diff --git a/rust/kernel/list.rs b/rust/kernel/list.rs index c0ed227b8a4f..e98f0820f002 100644 --- a/rust/kernel/list.rs +++ b/rust/kernel/list.rs @@ -176,7 +176,7 @@ pub fn new() -> impl PinInit<Self> { #[inline] unsafe fn fields(me: *mut Self) -> *mut ListLinksFields { // SAFETY: The caller promises that the pointer is valid. - unsafe { Opaque::raw_get(ptr::addr_of!((*me).inner)) } + unsafe { Opaque::raw_get(&raw const (*me).inner) } } /// # Safety diff --git a/rust/kernel/list/impl_list_item_mod.rs b/rust/kernel/list/impl_list_item_mod.rs index a0438537cee1..014b6713d59d 100644 --- a/rust/kernel/list/impl_list_item_mod.rs +++ b/rust/kernel/list/impl_list_item_mod.rs @@ -49,7 +49,7 @@ macro_rules! impl_has_list_links { // SAFETY: The implementation of `raw_get_list_links` only compiles if the field has the // right type. // - // The behavior of `raw_get_list_links` is not changed since the `addr_of_mut!` macro is + // The behavior of `raw_get_list_links` is not changed since the `&raw mut` op is // equivalent to the pointer offset operation in the trait definition. unsafe impl$(<$($implarg),*>)? $crate::list::HasListLinks$(<$id>)? for $self $(<$($selfarg),*>)? @@ -61,7 +61,7 @@ unsafe fn raw_get_list_links(ptr: *mut Self) -> *mut $crate::list::ListLinks$(<$ // SAFETY: The caller promises that the pointer is not dangling. We know that this // expression doesn't follow any pointers, as the `offset_of!` invocation above // would otherwise not compile. - unsafe { ::core::ptr::addr_of_mut!((*ptr)$(.$field)*) } + unsafe { &raw mut (*ptr)$(.$field)* } } } )*}; @@ -103,7 +103,7 @@ macro_rules! impl_has_list_links_self_ptr { unsafe fn raw_get_list_links(ptr: *mut Self) -> *mut $crate::list::ListLinks$(<$id>)? { // SAFETY: The caller promises that the pointer is not dangling. let ptr: *mut $crate::list::ListLinksSelfPtr<$item_type $(, $id)?> = - unsafe { ::core::ptr::addr_of_mut!((*ptr).$field) }; + unsafe { &raw mut (*ptr).$field }; ptr.cast() } } diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs index a59469c785e3..757db052cc09 100644 --- a/rust/kernel/net/phy.rs +++ b/rust/kernel/net/phy.rs @@ -7,7 +7,7 @@ //! C headers: [`include/linux/phy.h`](srctree/include/linux/phy.h). use crate::{error::*, prelude::*, types::Opaque}; -use core::{marker::PhantomData, ptr::addr_of_mut}; +use core::marker::PhantomData; pub mod reg; @@ -285,7 +285,7 @@ impl AsRef<kernel::device::Device> for Device { fn as_ref(&self) -> &kernel::device::Device { let phydev = self.0.get(); // SAFETY: The struct invariant ensures that `mdio.dev` is valid. - unsafe { kernel::device::Device::as_ref(addr_of_mut!((*phydev).mdio.dev)) } + unsafe { kernel::device::Device::as_ref(&raw mut (*phydev).mdio.dev) } } } diff --git a/rust/kernel/pci.rs b/rust/kernel/pci.rs index f7b2743828ae..6cb9ed1e7cbf 100644 --- a/rust/kernel/pci.rs +++ b/rust/kernel/pci.rs @@ -17,7 +17,7 @@ types::{ARef, ForeignOwnable, Opaque}, ThisModule, }; -use core::{ops::Deref, ptr::addr_of_mut}; +use core::ops::Deref; use kernel::prelude::*; /// An adapter for the registration of PCI drivers. @@ -60,7 +60,7 @@ extern "C" fn probe_callback( ) -> kernel::ffi::c_int { // SAFETY: The PCI bus only ever calls the probe callback with a valid pointer to a // `struct pci_dev`. - let dev = unsafe { device::Device::get_device(addr_of_mut!((*pdev).dev)) }; + let dev = unsafe { device::Device::get_device(&raw mut (*pdev).dev) }; // SAFETY: `dev` is guaranteed to be embedded in a valid `struct pci_dev` by the call // above. let mut pdev = unsafe { Device::from_dev(dev) }; diff --git a/rust/kernel/platform.rs b/rust/kernel/platform.rs index 1297f5292ba9..344875ad7b82 100644 --- a/rust/kernel/platform.rs +++ b/rust/kernel/platform.rs @@ -14,8 +14,6 @@ ThisModule, }; -use core::ptr::addr_of_mut; - /// An adapter for the registration of platform drivers. pub struct Adapter<T: Driver>(T); @@ -55,7 +53,7 @@ unsafe fn unregister(pdrv: &Opaque<Self::RegType>) { impl<T: Driver + 'static> Adapter<T> { extern "C" fn probe_callback(pdev: *mut bindings::platform_device) -> kernel::ffi::c_int { // SAFETY: The platform bus only ever calls the probe callback with a valid `pdev`. - let dev = unsafe { device::Device::get_device(addr_of_mut!((*pdev).dev)) }; + let dev = unsafe { device::Device::get_device(&raw mut (*pdev).dev) }; // SAFETY: `dev` is guaranteed to be embedded in a valid `struct platform_device` by the // call above. let mut pdev = unsafe { Device::from_dev(dev) }; diff --git a/rust/kernel/rbtree.rs b/rust/kernel/rbtree.rs index 1ea25c7092fb..b0ad35663cb0 100644 --- a/rust/kernel/rbtree.rs +++ b/rust/kernel/rbtree.rs @@ -11,7 +11,7 @@ cmp::{Ord, Ordering}, marker::PhantomData, mem::MaybeUninit, - ptr::{addr_of_mut, from_mut, NonNull}, + ptr::{from_mut, NonNull}, }; /// A red-black tree with owned nodes. @@ -238,7 +238,7 @@ pub fn values_mut(&mut self) -> impl Iterator<Item = &'_ mut V> { /// Returns a cursor over the tree nodes, starting with the smallest key. pub fn cursor_front(&mut self) -> Option<Cursor<'_, K, V>> { - let root = addr_of_mut!(self.root); + let root = &raw mut self.root; // SAFETY: `self.root` is always a valid root node let current = unsafe { bindings::rb_first(root) }; NonNull::new(current).map(|current| { @@ -253,7 +253,7 @@ pub fn cursor_front(&mut self) -> Option<Cursor<'_, K, V>> { /// Returns a cursor over the tree nodes, starting with the largest key. pub fn cursor_back(&mut self) -> Option<Cursor<'_, K, V>> { - let root = addr_of_mut!(self.root); + let root = &raw mut self.root; // SAFETY: `self.root` is always a valid root node let current = unsafe { bindings::rb_last(root) }; NonNull::new(current).map(|current| { @@ -459,7 +459,7 @@ pub fn cursor_lower_bound(&mut self, key: &K) -> Option<Cursor<'_, K, V>> let best = best_match?; // SAFETY: `best` is a non-null node so it is valid by the type invariants. - let links = unsafe { addr_of_mut!((*best.as_ptr()).links) }; + let links = unsafe { &raw mut (*best.as_ptr()).links }; NonNull::new(links).map(|current| { // INVARIANT: @@ -767,7 +767,7 @@ pub fn remove_current(self) -> (Option<Self>, RBTreeNode<K, V>) { let node = RBTreeNode { node }; // SAFETY: The reference to the tree used to create the cursor outlives the cursor, so // the tree cannot change. By the tree invariant, all nodes are valid. - unsafe { bindings::rb_erase(&mut (*this).links, addr_of_mut!(self.tree.root)) }; + unsafe { bindings::rb_erase(&mut (*this).links, &raw mut self.tree.root) }; let current = match (prev, next) { (_, Some(next)) => next, @@ -803,7 +803,7 @@ fn remove_neighbor(&mut self, direction: Direction) -> Option<RBTreeNode<K, V>> let neighbor = neighbor.as_ptr(); // SAFETY: The reference to the tree used to create the cursor outlives the cursor, so // the tree cannot change. By the tree invariant, all nodes are valid. - unsafe { bindings::rb_erase(neighbor, addr_of_mut!(self.tree.root)) }; + unsafe { bindings::rb_erase(neighbor, &raw mut self.tree.root) }; // SAFETY: By the type invariant of `Self`, all non-null `rb_node` pointers stored in `self` // point to the links field of `Node<K, V>` objects. let this = unsafe { container_of!(neighbor, Node<K, V>, links) }.cast_mut(); @@ -918,7 +918,7 @@ unsafe fn to_key_value_raw<'b>(node: NonNull<bindings::rb_node>) -> (&'b K, *mut let k = unsafe { &(*this).key }; // SAFETY: The passed `node` is the current node or a non-null neighbor, // thus `this` is valid by the type invariants. - let v = unsafe { addr_of_mut!((*this).value) }; + let v = unsafe { &raw mut (*this).value }; (k, v) } } @@ -1027,7 +1027,7 @@ fn next(&mut self) -> Option<Self::Item> { self.next = unsafe { bindings::rb_next(self.next) }; // SAFETY: By the same reasoning above, it is safe to dereference the node. - Some(unsafe { (addr_of_mut!((*cur).key), addr_of_mut!((*cur).value)) }) + Some(unsafe { (&raw mut (*cur).key, &raw mut (*cur).value) }) } } @@ -1170,7 +1170,7 @@ fn insert(self, node: RBTreeNode<K, V>) -> &'a mut V { // SAFETY: `node` is valid at least until we call `Box::from_raw`, which only happens when // the node is removed or replaced. - let node_links = unsafe { addr_of_mut!((*node).links) }; + let node_links = unsafe { &raw mut (*node).links }; // INVARIANT: We are linking in a new node, which is valid. It remains valid because we // "forgot" it with `Box::into_raw`. @@ -1178,7 +1178,7 @@ fn insert(self, node: RBTreeNode<K, V>) -> &'a mut V { unsafe { bindings::rb_link_node(node_links, self.parent, self.child_field_of_parent) }; // SAFETY: All pointers are valid. `node` has just been inserted into the tree. - unsafe { bindings::rb_insert_color(node_links, addr_of_mut!((*self.rbtree).root)) }; + unsafe { bindings::rb_insert_color(node_links, &raw mut (*self.rbtree).root) }; // SAFETY: The node is valid until we remove it from the tree. unsafe { &mut (*node).value } @@ -1261,7 +1261,7 @@ fn replace(self, node: RBTreeNode<K, V>) -> RBTreeNode<K, V> { // SAFETY: `node` is valid at least until we call `Box::from_raw`, which only happens when // the node is removed or replaced. - let new_node_links = unsafe { addr_of_mut!((*node).links) }; + let new_node_links = unsafe { &raw mut (*node).links }; // SAFETY: This updates the pointers so that `new_node_links` is in the tree where // `self.node_links` used to be. diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs index 3cefda7a4372..81d8b0f84957 100644 --- a/rust/kernel/sync/arc.rs +++ b/rust/kernel/sync/arc.rs @@ -243,7 +243,7 @@ pub fn into_raw(self) -> *const T { let ptr = self.ptr.as_ptr(); core::mem::forget(self); // SAFETY: The pointer is valid. - unsafe { core::ptr::addr_of!((*ptr).data) } + unsafe { &raw const (*ptr).data } } /// Recreates an [`Arc`] instance previously deconstructed via [`Arc::into_raw`]. diff --git a/rust/kernel/task.rs b/rust/kernel/task.rs index 49012e711942..b2ac768eed23 100644 --- a/rust/kernel/task.rs +++ b/rust/kernel/task.rs @@ -257,7 +257,7 @@ pub fn as_ptr(&self) -> *mut bindings::task_struct { pub fn group_leader(&self) -> &Task { // SAFETY: The group leader of a task never changes after initialization, so reading this // field is not a data race. - let ptr = unsafe { *ptr::addr_of!((*self.as_ptr()).group_leader) }; + let ptr = unsafe { *(&raw const (*self.as_ptr()).group_leader) }; // SAFETY: The lifetime of the returned task reference is tied to the lifetime of `self`, // and given that a task has a reference to its group leader, we know it must be valid for @@ -269,7 +269,7 @@ pub fn group_leader(&self) -> &Task { pub fn pid(&self) -> Pid { // SAFETY: The pid of a task never changes after initialization, so reading this field is // not a data race. - unsafe { *ptr::addr_of!((*self.as_ptr()).pid) } + unsafe { *(&raw const (*self.as_ptr()).pid) } } /// Returns the UID of the given task. diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs index 0cd100d2aefb..34e8abb38974 100644 --- a/rust/kernel/workqueue.rs +++ b/rust/kernel/workqueue.rs @@ -401,9 +401,9 @@ pub fn new(name: &'static CStr, key: &'static LockClassKey) -> impl PinInit<Self pub unsafe fn raw_get(ptr: *const Self) -> *mut bindings::work_struct { // SAFETY: The caller promises that the pointer is aligned and not dangling. // - // A pointer cast would also be ok due to `#[repr(transparent)]`. We use `addr_of!` so that - // the compiler does not complain that the `work` field is unused. - unsafe { Opaque::raw_get(core::ptr::addr_of!((*ptr).work)) } + // A pointer cast would also be ok due to `#[repr(transparent)]`. We use `&raw const (*ptr).work` + // so that the compiler does not complain that the `work` field is unused. + unsafe { Opaque::raw_get(&raw const (*ptr).work) } } } @@ -510,7 +510,7 @@ macro_rules! impl_has_work { unsafe fn raw_get_work(ptr: *mut Self) -> *mut $crate::workqueue::Work<$work_type $(, $id)?> { // SAFETY: The caller promises that the pointer is not dangling. unsafe { - ::core::ptr::addr_of_mut!((*ptr).$field) + &raw mut (*ptr).$field } } } -- 2.48.1

4 months

1
0
0 0

[RFC PATCH v1 0/2] mseal: allow noop mprotect

by jeffxu＠chromium.org

From: Jeff Xu <jeffxu(a)chromium.org> Initially, when mseal was introduced in 6.10, semantically, when a VMA within the specified address range is sealed, the mprotect will be rejected, leaving all of VMA unmodified. However, adding an extra loop to check the mseal flag for every VMA slows things down a bit, therefore in 6.12, this issue was solved by removing can_modify_mm and checking each VMA’s mseal flag directly without an extra loop [1]. This is a semantic change, i.e. partial update is allowed, VMAs can be updated until a sealed VMA is found. The new semantic also means, we could allow mprotect on a sealed VMA if the new attribute of VMA remains the same as the old one. Relaxing this avoids unnecessary impacts for applications that want to seal a particular mapping. Doing this also has no security impact. The mseal_test is also modified by this patch to adapt to the new semantic. Please note, mseal_test is currently undergoing refactoring, and eventually will be replaced with a new memory sealing selftest. In this patch, I only make a minimum change to make it pass. I considered adding a new testcase in mseal_test to cover this new behavior, however, the existing mseal_test is using wrong patterns and won’t pass the review. Such a new test is better to be added in the new refactored memory sealing tests. The refactoring is currently pending review [2]. [1] https://lore.kernel.org/all/20240817-mseal-depessimize-v3-0-d8d2e037df30@gm… [2] https://lore.kernel.org/all/20241211053311.245636-1-jeffxu@google.com/ Jeff Xu (2): selftests/mm: mseal_test: avoid using no-op mprotect mseal: allow noop mprotect mm/mprotect.c | 6 +++--- tools/testing/selftests/mm/mseal_test.c | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) -- 2.49.0.rc0.332.g42c0ae87b1-goog

4 months

5
10
0 0

[PATCH] selftests/bpf: Fix sockopt selftest failure on powerpc

by Saket Kumar Bhaskar

The SO_RCVLOWAT option is defined as 18 in the selftest header, which matches the generic definition. However, on powerpc, SO_RCVLOWAT is defined as 16. This discrepancy causes sol_socket_sockopt() to fail with the default switch case on powerpc. This commit fixes by defining SO_RCVLOWAT as 16 for powerpc. Signed-off-by: Saket Kumar Bhaskar <skb99(a)linux.ibm.com> --- tools/testing/selftests/bpf/progs/bpf_tracing_net.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index 59843b430f76..bcd44d5018bf 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -15,7 +15,11 @@ #define SO_KEEPALIVE 9 #define SO_PRIORITY 12 #define SO_REUSEPORT 15 +#if defined(__TARGET_ARCH_powerpc) +#define SO_RCVLOWAT 16 +#else #define SO_RCVLOWAT 18 +#endif #define SO_BINDTODEVICE 25 #define SO_MARK 36 #define SO_MAX_PACING_RATE 47 -- 2.43.5

4 months

3
2
0 0

Error during --arch x86_64 kunit test run

by Shuah Khan

David, Brendan, Rae, I am seeing the following error when I run ./tools/testing/kunit/kunit.py run --arch x86_64 ERROR:root:ld:arch/x86/realmode/rm/realmode.lds:236: undefined symbol `sev_es_trampoline_start' referenced in expression I isolated it to dependency on CONFIG_AMD_MEM_ENCRYPT I added the option using --kconfig_add ./tools/testing/kunit/kunit.py run --arch x86_64 --kconfig_add CONFIG_AMD_MEM_ENCRYPT=y I see the following RROR:root:Not all Kconfig options selected in kunitconfig were in the generated .config. This is probably due to unsatisfied dependencies. Missing: CONFIG_AMD_MEM_ENCRYPT=y Is there a better way to fix the dependencies? Does kunit default config need changing for x86_64? thanks, -- Shuah

4 months

2
4
0 0

[PATCH v6 0/3] printf: convert self-test to KUnit

by Tamir Duberstein

This is one of just 3 remaining "Test Module" kselftests (the others being bitmap and scanf), the rest having been converted to KUnit. I tested this using: $ tools/testing/kunit/kunit.py run --arch arm64 --make_options LLVM=1 printf I have also sent out a series converting scanf[0]. Link: https://lore.kernel.org/all/20250204-scanf-kunit-convert-v3-0-386d7c3ee714@… [0] Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- Changes in v6: - Use __printf correctly on `__test`. (Petr Mladek) - Rebase on linux-next. - Remove leftover references to `printf.sh`. - Update comment in `hash_pointer`. (Petr Mladek) - Avoid overrun in `KUNIT_EXPECT_MEMNEQ`. (Petr Mladek) - Restore trailing newlines on printk strings and add some missing ones. (Petr Mladek) - Use `kunit_skip` on not-yet-initialized crng. (Petr Mladek) - Link to v5: https://lore.kernel.org/r/20250221-printf-kunit-convert-v5-0-5db840301730@g… Changes in v5: - Update `do_test` `__printf` annotation (Rasmus Villemoes). - Link to v4: https://lore.kernel.org/r/20250214-printf-kunit-convert-v4-0-c254572f1565@g… Changes in v4: - Add patch "implicate test line in failure messages". - Rebase on linux-next, move scanf_kunit.c into lib/tests/. - Link to v3: https://lore.kernel.org/r/20250210-printf-kunit-convert-v3-0-ee6ac5500f5e@g… Changes in v3: - Remove extraneous trailing newlines from failure messages. - Replace `pr_warn` with `kunit_warn`. - Drop arch changes. - Remove KUnit boilerplate from CONFIG_PRINTF_KUNIT_TEST help text. - Restore `total_tests` counting. - Remove tc_fail macro in last patch. - Link to v2: https://lore.kernel.org/r/20250207-printf-kunit-convert-v2-0-057b23860823@g… Changes in v2: - Incorporate code review from prior work[0] by Arpitha Raghunandan. - Link to v1: https://lore.kernel.org/r/20250204-printf-kunit-convert-v1-0-ecf1b846a4de@g… Link: https://lore.kernel.org/lkml/20200817043028.76502-1-98.arpi@gmail.com/t/#u [0] --- Tamir Duberstein (3): printf: convert self-test to KUnit printf: break kunit into test cases printf: implicate test line in failure messages Documentation/core-api/printk-formats.rst | 4 +- Documentation/dev-tools/kselftest.rst | 2 +- MAINTAINERS | 2 +- lib/Kconfig.debug | 12 +- lib/Makefile | 1 - lib/tests/Makefile | 1 + lib/{test_printf.c => tests/printf_kunit.c} | 442 ++++++++++++---------------- tools/testing/selftests/kselftest/module.sh | 2 +- tools/testing/selftests/lib/Makefile | 2 +- tools/testing/selftests/lib/config | 1 - tools/testing/selftests/lib/printf.sh | 4 - 11 files changed, 207 insertions(+), 266 deletions(-) --- base-commit: 7ec162622e66a4ff886f8f28712ea1b13069e1aa change-id: 20250131-printf-kunit-convert-fd4012aa2ec6 Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

4 months

3
9
0 0

[PATCH v4 0/6] Fix some issues related to an interrupt type in pci_endpoint_test

by Kunihiko Hayashi

This series solves some issues about global "irq_type" that is used for indicating the current type for users. In addition, avoid an unexpected warning that occur due to interrupts remaining after displaying an error caused by devm_request_irq(). Patch 1 includes adding GET_IRQTYPE test (check for failure). Patch 2-4 include fixes for stable kernels that have global "irq_type". Patch 5-6 include improvements for the latest. Changes since v3: - Add GET_IRQTYPE check to pci_endpoint test in selftests - Add the reason why global variables aren't necessary (patch 5/6) - Add Reviewed-by: lines (patch {2, 4, 6}/6) Changes since v2: - Rebase to v6.14-rc1 - Update message to clarify, and add result of call trace (patch 1/5) - Add Reviewed-by: lines (patch 2/5) - Add new patch to remove global "irq_type" variable (patch 4/5) - Add new patch to replace "devm" version of IRQ functions (patch 5/5) Changes since v1: - Divide original patch into two - Add an error message example - Add "pcitest" display example - Add a patch to fix an interrupt remaining issue Kunihiko Hayashi (6): selftests: pci_endpoint: Add GET_IRQTYPE checks to each interrupt test misc: pci_endpoint_test: Avoid issue of interrupts remaining after request_irq error misc: pci_endpoint_test: Fix displaying irq_type after request_irq error misc: pci_endpoint_test: Fix irq_type to convey the correct type misc: pci_endpoint_test: Remove global 'irq_type' and 'no_msi' misc: pci_endpoint_test: Do not use managed irq functions drivers/misc/pci_endpoint_test.c | 31 +++++++------------ .../pci_endpoint/pci_endpoint_test.c | 11 ++++++- 2 files changed, 21 insertions(+), 21 deletions(-) -- 2.25.1

4 months

4
11
0 0

[PATCH v10 0/8] Buddy allocator like (or non-uniform) folio split

by Zi Yan

Hi all, This patchset adds a new buddy allocator like (or non-uniform) large folio split from a order-n folio to order-m with m < n. It reduces 1. the total number of after-split folios from 2^(n-m) to n-m+1; 2. the amount of memory needed for multi-index xarray split from 2^(n/6-m/6) to n/6-m/6, assuming XA_CHUNK_SHIFT=6; 3. keep more large folios after a split from all order-m folios to order-(n-1) to order-m folios. For example, to split an order-9 to order-0, folio split generates 10 (or 11 for anonymous memory) folios instead of 512, allocates 1 xa_node instead of 8, and leaves 1 order-8, 1 order-7, ..., 1 order-1 and 2 order-0 folios (or 4 order-0 for anonymous memory) instead of 512 order-0 folios. Instead of duplicating existing split_huge_page*() code, __folio_split() is introduced as the shared backend code for both split_huge_page_to_list_to_order() and folio_split(). __folio_split() can support both uniform split and buddy allocator like (or non-uniform) split. All existing split_huge_page*() users can be gradually converted to use folio_split() if possible. In this patchset, I converted truncate_inode_partial_folio() to use folio_split(). xfstests quick group passed for both tmpfs and xfs. I also semi-replicated Hugh's test[12] and ran it without any issue for almost 24 hours. It is on top of mm-everything-2025-03-07-07-55. It is ready to be merged. Changelog === From V9[13] 1. Incorporated Hugh's fixes[14] (Thanks Hugh): a) moved folio_set_order() in __split_folio_to_order() to be called only once for the input folio, b) used folio_test_swapcache() to catch both anon and shmem in swap cache cases, c) moved folio_next() out of for(;;), d) used mapping instead of origin_folio->mapping. 2. Added a TODO in __folio_split(), since large in-swap-cache shmem folio split is not supported yet. 3. Changed __split_folio_to_order() based on David Hildenbrand's MM owner tracking for large folios patchset[15], due to rebasing. From V8[11]: 1. Removed gfp parameter from xas_try_split() and GFP_NOWAIT is used all the time. (per Baolin Wang) 2. Used __xas_init_node_for_split() instead of __xas_alloc_node_for_split() and moved node allocation out. It fixed a bug when xa_node is pre-allocated by xas_nomem() before xas_try_split() is called without being initialized for split. From V7[9]: 1. Fixed a wrong function name in lib/test_xarray.c. 2. Made __split_folio_to_order() never fail, since the old order check is already done in __folio_split(). (per David Hildenbrand) 3. Fixed an issue reported by syzbot[10] by not dropping the original folio during truncate. 4. Fixed a WARNING when READ_ONLY_THP_FOR_FS is enabled. (Thank David Hildenbrand for reporting the issue) 5. Used two separate struct page* parameters, split_at and lock_at, to specify at which subpage the non-uniform split happens and which subpage to keep locked after the split, respectively. It improves code readability. From V6[8]: 1. Added an xarray function xas_try_split() to support iterative folio split, removing the need of using xas_split_alloc() and xas_split(). The function guarantees that at most one xa_node is allocated for each call. 2. Added concrete numbers of after-split folios and xa_node savings to cover letter, commit log. (per Andrew) From V5[7]: 1. Split shmem to any lower order patches are in mm tree, so dropped from this series. 2. Rename split_folio_at() to try_folio_split() to clarify that non-uniform split will not be used if it is not supported. From V4[6]: 1. Enabled shmem support in both uniform and buddy allocator like split and added selftests for it. 2. Added functions to check if uniform split and buddy allocator like split are supported for the given folio and order. 3. Made truncate fall back to uniform split if buddy allocator split is not supported (CONFIG_READ_ONLY_THP_FOR_FS and FS without large folio). 4. Added the missing folio_clear_has_hwpoisoned() to __split_unmapped_folio(). From V3[5]: 1. Used xas_split_alloc(GFP_NOWAIT) instead of xas_nomem(), since extra operations inside xas_split_alloc() are needed for correctness. 2. Enabled folio_split() for shmem and no issue was found with xfstests quick test group. 3. Split both ends of a truncate range in truncate_inode_partial_folio() to avoid wasting memory in shmem truncate (per David Hildenbrand). 4. Removed page_in_folio_offset() since page_folio() does the same thing. 5. Finished truncate related tests from xfstests quick test group on XFS and tmpfs without issues. 6. Disabled buddy allocator like split on CONFIG_READ_ONLY_THP_FOR_FS and FS without large folio. This check was missed in the prior versions. From V2[3]: 1. Incorporated all the feedback from Kirill[4]. 2. Used GFP_NOWAIT for xas_nomem(). 3. Tested the code path when xas_nomem() fails. 4. Added selftests for folio_split(). 5. Fixed no THP config build error. From V1[2]: 1. Split the original patch 1 into multiple ones for easy review (per Kirill). 2. Added xas_destroy() to avoid memory leak. 3. Fixed nr_dropped not used error (per kernel test robot). 4. Added proper error handling when xas_nomem() fails to allocate memory for xas_split() during buddy allocator like split. From RFC[1]: 1. Merged backend code of split_huge_page_to_list_to_order() and folio_split(). The same code is used for both uniform split and buddy allocator like split. 2. Use xas_nomem() instead of xas_split_alloc() for folio_split(). 3. folio_split() now leaves the first after-split folio unlocked, instead of the one containing the given page, since the caller of truncate_inode_partial_folio() locks and unlocks the first folio. 4. Extended split_huge_page debugfs to use folio_split(). 5. Added truncate_inode_partial_folio() as first user of folio_split(). Design === folio_split() splits a large folio in the same way as buddy allocator splits a large free page for allocation. The purpose is to minimize the number of folios after the split. For example, if user wants to free the 3rd subpage in a order-9 folio, folio_split() will split the order-9 folio as: O-0, O-0, O-0, O-0, O-2, O-3, O-4, O-5, O-6, O-7, O-8 if it is anon O-1, O-0, O-0, O-2, O-3, O-4, O-5, O-6, O-7, O-9 if it is pagecache Since anon folio does not support order-1 yet. The split process is similar to existing approach: 1. Unmap all page mappings (split PMD mappings if exist); 2. Split meta data like memcg, page owner, page alloc tag; 3. Copy meta data in struct folio to sub pages, but instead of spliting the whole folio into multiple smaller ones with the same order in a shot, this approach splits the folio iteratively. Taking the example above, this approach first splits the original order-9 into two order-8, then splits left part of order-8 to two order-7 and so on; 4. Post-process split folios, like write mapping->i_pages for pagecache, adjust folio refcounts, add split folios to corresponding list; 5. Remap split folios 6. Unlock split folios. __split_unmapped_folio() and __split_folio_to_order() replace __split_huge_page() and __split_huge_page_tail() respectively. __split_unmapped_folio() uses different approaches to perform uniform split and buddy allocator like split: 1. uniform split: one single call to __split_folio_to_order() is used to uniformly split the given folio. All resulting folios are put back to the list after split. The folio containing the given page is left to caller to unlock and others are unlocked. 2. buddy allocator like (or non-uniform) split: (old_order - new_order) calls to __split_folio_to_order() are used to split the given folio at order N to order N-1. After each call, the target folio is changed to the one containing the page, which is given as a folio_split() parameter. After each call, folios not containing the page are put back to the list. The folio containing the page is put back to the list when its order is new_order. All folios are unlocked except the first folio, which is left to caller to unlock. Patch Overview === 1. Patch 1 added a new xarray function xas_try_split() to perform iterative xarray split. 2. Patch 2 added __split_unmapped_folio() and __split_folio_to_order() to prepare for moving to new backend split code. 3. Patch 3 moved common code in split_huge_page_to_list_to_order() to __folio_split(). 4. Patch 4 added new folio_split() and made split_huge_page_to_list_to_order() share the new __split_unmapped_folio() with folio_split(). 5. Patch 5 removed no longer used __split_huge_page() and __split_huge_page_tail(). 6. Patch 6 added a new in_folio_offset to split_huge_page debugfs for folio_split() test. 7. Patch 7 used try_folio_split() for truncate operation. 8. Patch 8 added folio_split() tests. Any comments and/or suggestions are welcome. Thanks. [1] https://lore.kernel.org/linux-mm/20241008223748.555845-1-ziy@nvidia.com/ [2] https://lore.kernel.org/linux-mm/20241028180932.1319265-1-ziy@nvidia.com/ [3] https://lore.kernel.org/linux-mm/20241101150357.1752726-1-ziy@nvidia.com/ [4] https://lore.kernel.org/linux-mm/e6ppwz5t4p4kvir6eqzoto4y5fmdjdxdyvxvtw43nc… [5] https://lore.kernel.org/linux-mm/20241205001839.2582020-1-ziy@nvidia.com/ [6] https://lore.kernel.org/linux-mm/20250106165513.104899-1-ziy@nvidia.com/ [7] https://lore.kernel.org/linux-mm/20250116211042.741543-1-ziy@nvidia.com/ [8] https://lore.kernel.org/linux-mm/20250205031417.1771278-1-ziy@nvidia.com/ [9] https://lore.kernel.org/linux-mm/20250211155034.268962-1-ziy@nvidia.com/ [10] https://lore.kernel.org/all/67af65cb.050a0220.21dd3.004a.GAE@google.com/ [11] https://lore.kernel.org/linux-mm/20250218235012.1542225-1-ziy@nvidia.com/ [12] https://lore.kernel.org/linux-mm/D45D4F01-E5A5-47E6-8724-01610CC192CC@nvidi… [13] https://lore.kernel.org/linux-mm/20250226210032.2044041-1-ziy@nvidia.com/ [14] https://lore.kernel.org/linux-mm/2fae27fe-6e2e-3587-4b68-072118d80cf8@googl… [15] https://lore.kernel.org/all/20250303163014.1128035-4-david@redhat.com/ Zi Yan (8): xarray: add xas_try_split() to split a multi-index entry mm/huge_memory: add two new (not yet used) functions for folio_split() mm/huge_memory: move folio split common code to __folio_split() mm/huge_memory: add buddy allocator like (non-uniform) folio_split() mm/huge_memory: remove the old, unused __split_huge_page() mm/huge_memory: add folio_split() to debugfs testing interface mm/truncate: use folio_split() in truncate operation selftests/mm: add tests for folio_split(), buddy allocator like split Documentation/core-api/xarray.rst | 14 +- include/linux/huge_mm.h | 36 + include/linux/xarray.h | 6 + lib/test_xarray.c | 52 ++ lib/xarray.c | 132 ++- mm/huge_memory.c | 786 ++++++++++++------ mm/truncate.c | 37 +- tools/testing/radix-tree/Makefile | 1 + .../selftests/mm/split_huge_page_test.c | 34 +- 9 files changed, 809 insertions(+), 289 deletions(-) -- 2.47.2

4 months

2
16
0 0

[PATCH net 7/7] selftests: net: test for lwtunnel dst ref loops

by Justin Iurman

As recently specified by commit 0ea09cbf8350 ("docs: netdev: add a note on selftest posting") in net-next, the selftest is therefore shipped in this series. However, this selftest does not really test this series. It needs this series to avoid crashing the kernel. What it really tests, thanks to kmemleak, is what was fixed by the following commits: - commit c71a192976de ("net: ipv6: fix dst refleaks in rpl, seg6 and ioam6 lwtunnels") - commit 92191dd10730 ("net: ipv6: fix dst ref loops in rpl, seg6 and ioam6 lwtunnels") - commit c64a0727f9b1 ("net: ipv6: fix dst ref loop on input in seg6 lwt") - commit 13e55fbaec17 ("net: ipv6: fix dst ref loop on input in rpl lwt") - commit 0e7633d7b95b ("net: ipv6: fix dst ref loop in ila lwtunnel") - commit 5da15a9c11c1 ("net: ipv6: fix missing dst ref drop in ila lwtunnel") Cc: Shuah Khan <shuah(a)kernel.org> Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Justin Iurman <justin.iurman(a)uliege.be> --- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/config | 2 + .../selftests/net/lwt_dst_cache_ref_loop.sh | 250 ++++++++++++++++++ 3 files changed, 253 insertions(+) create mode 100755 tools/testing/selftests/net/lwt_dst_cache_ref_loop.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 73ee88d6b043..8f32b4f01aee 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -100,6 +100,7 @@ TEST_PROGS += vlan_bridge_binding.sh TEST_PROGS += bpf_offload.py TEST_PROGS += ipv6_route_update_soft_lockup.sh TEST_PROGS += busy_poll_test.sh +TEST_PROGS += lwt_dst_cache_ref_loop.sh # YNL files, must be before "include ..lib.mk" YNL_GEN_FILES := busy_poller netlink-dumps diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 5b9baf708950..61e5116987f3 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -107,3 +107,5 @@ CONFIG_XFRM_INTERFACE=m CONFIG_XFRM_USER=m CONFIG_IP_NF_MATCH_RPFILTER=m CONFIG_IP6_NF_MATCH_RPFILTER=m +CONFIG_IPV6_ILA=m +CONFIG_IPV6_RPL_LWTUNNEL=y diff --git a/tools/testing/selftests/net/lwt_dst_cache_ref_loop.sh b/tools/testing/selftests/net/lwt_dst_cache_ref_loop.sh new file mode 100755 index 000000000000..9161f16154a5 --- /dev/null +++ b/tools/testing/selftests/net/lwt_dst_cache_ref_loop.sh @@ -0,0 +1,250 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Author: Justin Iurman <justin.iurman(a)uliege.be> +# +# WARNING +# ------- +# This is just a dummy script that triggers encap cases with possible dst cache +# reference loops in affected lwt users (see list below). Some cases are +# pathological configurations for simplicity, others are valid. Overall, we +# don't want this issue to happen, no matter what. In order to catch any +# reference loops, kmemleak MUST be used. The results alone are always blindly +# successful, don't rely on them. Note that the following tests may crash the +# kernel if the fix to prevent lwtunnel_{input|output|xmit}() reentry loops is +# not present. +# +# Affected lwt users so far (please update accordingly if needed): +# - ila_lwt (output only) +# - ioam6_iptunnel (output only) +# - rpl_iptunnel (both input and output) +# - seg6_iptunnel (both input and output) + +source lib.sh + +check_compatibility() +{ + setup_ns tmp_node &>/dev/null + if [ $? != 0 ] + then + echo "SKIP: Cannot create netns." + exit $ksft_skip + fi + + ip link add name veth0 netns $tmp_node type veth \ + peer name veth1 netns $tmp_node &>/dev/null + local ret=$? + + ip -netns $tmp_node link set veth0 up &>/dev/null + ret=$((ret + $?)) + + ip -netns $tmp_node link set veth1 up &>/dev/null + ret=$((ret + $?)) + + if [ $ret != 0 ] + then + echo "SKIP: Cannot configure links." + cleanup_ns $tmp_node + exit $ksft_skip + fi + + lsmod 2>/dev/null | grep -q "ila" + ila_lsmod=$? + [ $ila_lsmod != 0 ] && modprobe ila &>/dev/null + + ip -netns $tmp_node route add 2001:db8:1::/64 \ + encap ila 1:2:3:4 csum-mode no-action ident-type luid hook-type output \ + dev veth0 &>/dev/null + + ip -netns $tmp_node route add 2001:db8:2::/64 \ + encap ioam6 trace prealloc type 0x800000 ns 0 size 4 dev veth0 &>/dev/null + + ip -netns $tmp_node route add 2001:db8:3::/64 \ + encap rpl segs 2001:db8:3::1 dev veth0 &>/dev/null + + ip -netns $tmp_node route add 2001:db8:4::/64 \ + encap seg6 mode inline segs 2001:db8:4::1 dev veth0 &>/dev/null + + ip -netns $tmp_node -6 route 2>/dev/null | grep -q "encap ila" + skip_ila=$? + + ip -netns $tmp_node -6 route 2>/dev/null | grep -q "encap ioam6" + skip_ioam6=$? + + ip -netns $tmp_node -6 route 2>/dev/null | grep -q "encap rpl" + skip_rpl=$? + + ip -netns $tmp_node -6 route 2>/dev/null | grep -q "encap seg6" + skip_seg6=$? + + cleanup_ns $tmp_node +} + +setup() +{ + setup_ns alpha beta gamma &>/dev/null + + ip link add name veth-alpha netns $alpha type veth \ + peer name veth-betaL netns $beta &>/dev/null + ip link add name veth-betaR netns $beta type veth \ + peer name veth-gamma netns $gamma &>/dev/null + + ip -netns $alpha link set veth-alpha name veth0 &>/dev/null + ip -netns $beta link set veth-betaL name veth0 &>/dev/null + ip -netns $beta link set veth-betaR name veth1 &>/dev/null + ip -netns $gamma link set veth-gamma name veth0 &>/dev/null + + ip -netns $alpha addr add 2001:db8:1::2/64 dev veth0 &>/dev/null + ip -netns $alpha link set veth0 up &>/dev/null + ip -netns $alpha link set lo up &>/dev/null + ip -netns $alpha route add 2001:db8:2::/64 \ + via 2001:db8:1::1 dev veth0 &>/dev/null + + ip -netns $beta addr add 2001:db8:1::1/64 dev veth0 &>/dev/null + ip -netns $beta addr add 2001:db8:2::1/64 dev veth1 &>/dev/null + ip -netns $beta link set veth0 up &>/dev/null + ip -netns $beta link set veth1 up &>/dev/null + ip -netns $beta link set lo up &>/dev/null + ip -netns $beta route del 2001:db8:2::/64 + ip -netns $beta route add 2001:db8:2::/64 dev veth1 + ip netns exec $beta sysctl -wq net.ipv6.conf.all.forwarding=1 &>/dev/null + + ip -netns $gamma addr add 2001:db8:2::2/64 dev veth0 &>/dev/null + ip -netns $gamma link set veth0 up &>/dev/null + ip -netns $gamma link set lo up &>/dev/null + ip -netns $gamma route add 2001:db8:1::/64 \ + via 2001:db8:2::1 dev veth0 &>/dev/null + + sleep 1 + + ip netns exec $alpha ping6 -c 5 -W 1 2001:db8:2::2 &>/dev/null + if [ $? != 0 ] + then + echo "SKIP: Setup failed." + cleanup + exit $ksft_skip + fi + + sleep 1 +} + +cleanup() +{ + cleanup_ns $alpha $beta $gamma + [ $ila_lsmod != 0 ] && modprobe -r ila &>/dev/null +} + +run_ila() +{ + if [ $skip_ila != 0 ] + then + echo "SKIP: ila (output)" + return + fi + + ip -netns $beta route del 2001:db8:2::/64 + + ip -netns $beta route add 2001:db8:2:0:0:0:0:2/128 \ + encap ila 2001:db8:2:0 csum-mode no-action ident-type luid hook-type output \ + dev veth1 &>/dev/null + sleep 1 + + echo "TEST: ila (output)" + ip netns exec $beta ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null + sleep 1 + + ip -netns $beta route del 2001:db8:2:0:0:0:0:2/128 + ip -netns $beta route add 2001:db8:2::/64 dev veth1 + sleep 1 +} + +run_ioam6() +{ + if [ $skip_ioam6 != 0 ] + then + echo "SKIP: ioam6 (output)" + return + fi + + ip -netns $beta route change 2001:db8:2::/64 \ + encap ioam6 trace prealloc type 0x800000 ns 1 size 4 \ + dev veth1 &>/dev/null + sleep 1 + + echo "TEST: ioam6 (output)" + ip netns exec $beta ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null + sleep 1 +} + +run_rpl() +{ + if [ $skip_rpl != 0 ] + then + echo "SKIP: rpl (input)" + echo "SKIP: rpl (output)" + return + fi + + ip -netns $beta route change 2001:db8:2::/64 \ + encap rpl segs 2001:db8:2::2 \ + dev veth1 &>/dev/null + sleep 1 + + echo "TEST: rpl (input)" + ip netns exec $alpha ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null + sleep 1 + + echo "TEST: rpl (output)" + ip netns exec $beta ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null + sleep 1 +} + +run_seg6() +{ + if [ $skip_seg6 != 0 ] + then + echo "SKIP: seg6 (input)" + echo "SKIP: seg6 (output)" + return + fi + + ip -netns $beta route change 2001:db8:2::/64 \ + encap seg6 mode inline segs 2001:db8:2::2 \ + dev veth1 &>/dev/null + sleep 1 + + echo "TEST: seg6 (input)" + ip netns exec $alpha ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null + sleep 1 + + echo "TEST: seg6 (output)" + ip netns exec $beta ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null + sleep 1 +} + +run() +{ + run_ila + run_ioam6 + run_rpl + run_seg6 +} + +if [ "$(id -u)" -ne 0 ] +then + echo "SKIP: Need root privileges." + exit $ksft_skip +fi + +if [ ! -x "$(command -v ip)" ] +then + echo "SKIP: Could not run test without ip tool." + exit $ksft_skip +fi + +check_compatibility +setup +run +cleanup + +exit $ksft_pass -- 2.34.1

4 months

2
1
0 0

Re: [PATCH 3/3] rust: replace `addr_of[_mut]!` with `&raw [mut]`

by Benno Lossin

On Thu Mar 13, 2025 at 6:33 AM CET, Antonio Hickey wrote: > Replacing all occurrences of `addr_of!(place)` with `&raw place`, and > all occurrences of `addr_of_mut!(place)` with `&raw mut place`. > > Utilizing the new feature will allow us to reduce macro complexity, and > improve consistency with existing reference syntax as `&raw`, `&raw mut` > is very similar to `&`, `&mut` making it fit more naturally with other > existing code. > > Depends on: Patch 1/3 0001-rust-enable-raw_ref_op-feature.patch This information shouldn't be in the commit message. You can put it below the `---` (that won't end up in the commit message). But since you sent this as part of a series, you don't need to mention it. > Suggested-by: Benno Lossin <y86-dev(a)protonmail.com> > Link: https://github.com/Rust-for-Linux/linux/issues/1148 > Signed-off-by: Antonio Hickey <contact(a)antoniohickey.com> > --- > rust/kernel/block/mq/request.rs | 4 ++-- > rust/kernel/faux.rs | 4 ++-- > rust/kernel/fs/file.rs | 2 +- > rust/kernel/init.rs | 8 ++++---- > rust/kernel/init/macros.rs | 28 +++++++++++++------------- > rust/kernel/jump_label.rs | 4 ++-- > rust/kernel/kunit.rs | 4 ++-- > rust/kernel/list.rs | 2 +- > rust/kernel/list/impl_list_item_mod.rs | 6 +++--- > rust/kernel/net/phy.rs | 4 ++-- > rust/kernel/pci.rs | 4 ++-- > rust/kernel/platform.rs | 4 +--- > rust/kernel/rbtree.rs | 22 ++++++++++---------- > rust/kernel/sync/arc.rs | 2 +- > rust/kernel/task.rs | 4 ++-- > rust/kernel/workqueue.rs | 8 ++++---- > 16 files changed, 54 insertions(+), 56 deletions(-) [...] > diff --git a/rust/kernel/jump_label.rs b/rust/kernel/jump_label.rs > index 4e974c768dbd..05d4564714c7 100644 > --- a/rust/kernel/jump_label.rs > +++ b/rust/kernel/jump_label.rs > @@ -20,8 +20,8 @@ > #[macro_export] > macro_rules! static_branch_unlikely { > ($key:path, $keytyp:ty, $field:ident) => {{ > - let _key: *const $keytyp = ::core::ptr::addr_of!($key); > - let _key: *const $crate::bindings::static_key_false = ::core::ptr::addr_of!((*_key).$field); > + let _key: *const $keytyp = &raw $key; This should be `&raw const $key`. I wrote that wrongly in the issue. > + let _key: *const $crate::bindings::static_key_false = &raw (*_key).$field; Same here. > let _key: *const $crate::bindings::static_key = _key.cast(); > > #[cfg(not(CONFIG_JUMP_LABEL))] > diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs > index 824da0e9738a..18357dd782ed 100644 > --- a/rust/kernel/kunit.rs > +++ b/rust/kernel/kunit.rs > @@ -128,9 +128,9 @@ unsafe impl Sync for UnaryAssert {} > unsafe { > $crate::bindings::__kunit_do_failed_assertion( > kunit_test, > - core::ptr::addr_of!(LOCATION.0), > + &raw LOCATION.0, And here. > $crate::bindings::kunit_assert_type_KUNIT_ASSERTION, > - core::ptr::addr_of!(ASSERTION.0.assert), > + &raw ASSERTION.0.assert, Lastly here as well. --- Cheers, Benno

4 months

1
0
0 0

arm64: Kernel crash at devm_kmalloc include/linux/device.h: drivers/base/devres.c

by Naresh Kamboju

Regression on arm64 FVP and rock-pi-4-b while booting the Linux next-20250312 and next-20250313. the following crash noticed with KVM Kconfigs. First seen on next-20250312. Good: next-20250311 Bad: 6.14.0-rc6-next-20250312 and 6.14.0-rc6-next-20250313 Boot regression: arm64 devm_kmalloc rk_iommu_of_xlate kernel panic Reported-by: Linux Kernel Functional Testing <lkft(a)linaro.org> ## Boot log [ 0.000000] Booting Linux on physical CPU 0x0000000000 [0x410fd034] [ 0.000000] Linux version 6.14.0-rc6-next-20250313 (tuxmake@tuxmake) (aarch64-linux-gnu-gcc (Debian 13.3.0-12) 13.3.0, GNU ld (GNU Binutils for Debian) 2.44) #1 SMP PREEMPT @1741850074 [ 0.000000] KASLR disabled due to lack of seed [ 0.000000] Machine model: Radxa ROCK Pi 4B <trim> [ 1.028830] SuperH (H)SCI(F) driver initialized [ 1.030168] STM32 USART driver initialized [ 1.052086] Unable to handle kernel NULL pointer dereference at virtual address 00000000000002a0 [ 1.052877] Mem abort info: [ 1.053137] ESR = 0x0000000096000004 [ 1.053481] EC = 0x25: DABT (current EL), IL = 32 bits [ 1.053960] SET = 0, FnV = 0 [ 1.054241] EA = 0, S1PTW = 0 [ 1.054530] FSC = 0x04: level 0 translation fault [ 1.054971] Data abort info: [ 1.055236] ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 [ 1.055760] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [ 1.056216] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 1.056693] [00000000000002a0] user address but active_mm is swapper [ 1.057264] Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP [ 1.057821] Modules linked in: [ 1.058105] CPU: 4 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.14.0-rc6-next-20250313 #1 [ 1.058823] Hardware name: Radxa ROCK Pi 4B (DT) [ 1.059236] pstate: 00000005 (nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 1.059854] pc : devm_kmalloc (include/linux/device.h:805 drivers/base/devres.c:853) [ 1.060225] lr : rk_iommu_of_xlate (drivers/iommu/rockchip-iommu.c:1152) [ 1.060614] sp : ffff80008306b7c0 [ 1.060913] x29: ffff80008306b7c0 x28: ffff8000825a9068 x27: ffff80008225ce00 [ 1.061560] x26: 0000000000000001 x25: ffff80008225e188 x24: ffff000000eafa80 [ 1.062206] x23: 0000000000000000 x22: ffff800081af6a98 x21: 0000000000000000 [ 1.062850] x20: 0000000000000010 x19: 0000000000000000 x18: 00000000ffffffff [ 1.063493] x17: ffff0000019abc00 x16: ffff000001985400 x15: ffff80008306b820 [ 1.064136] x14: ffff000002736a1c x13: ffff00000273627c x12: 0101010101010101 [ 1.064780] x11: 7f7f7f7f7f7f7f7f x10: 000000000016f8a0 x9 : ffff800080b65870 [ 1.065424] x8 : ffff80008306b718 x7 : 0000000000000000 x6 : 0000000000000001 [ 1.066066] x5 : ffff800082890000 x4 : ffff8000828905f0 x3 : 0000000000000000 [ 1.066708] x2 : 0000000000000dc0 x1 : 0000000000000010 x0 : 0000000000000090 [ 1.067351] Call trace: [ 1.067576] devm_kmalloc (include/linux/device.h:805 drivers/base/devres.c:853) (P) [ 1.067937] rk_iommu_of_xlate (drivers/iommu/rockchip-iommu.c:1152) [ 1.068295] of_iommu_xlate (drivers/iommu/of_iommu.c:39) [ 1.068629] of_iommu_configure (drivers/iommu/of_iommu.c:71 drivers/iommu/of_iommu.c:98 drivers/iommu/of_iommu.c:149) [ 1.069008] of_dma_configure_id (drivers/of/device.c:161) [ 1.069392] platform_dma_configure (drivers/base/platform.c:1455) [ 1.069796] __iommu_probe_device (drivers/iommu/iommu.c:430 drivers/iommu/iommu.c:569) [ 1.070194] probe_iommu_group (drivers/iommu/iommu.c:1722) [ 1.070553] bus_for_each_dev (drivers/base/bus.c:370) [ 1.070906] iommu_device_register (drivers/iommu/iommu.c:1875 drivers/iommu/iommu.c:276) [ 1.071304] rk_iommu_probe (drivers/iommu/rockchip-iommu.c:1263) [ 1.071652] platform_probe (drivers/base/platform.c:1404) [ 1.071986] really_probe (drivers/base/dd.c:579 drivers/base/dd.c:658) [ 1.072316] __driver_probe_device (drivers/base/dd.c:800) [ 1.072716] driver_probe_device (drivers/base/dd.c:830) [ 1.073100] __driver_attach (drivers/base/dd.c:1217) [ 1.073453] bus_for_each_dev (drivers/base/bus.c:370) [ 1.073805] driver_attach (drivers/base/dd.c:1235) [ 1.074135] bus_add_driver (drivers/base/bus.c:678) [ 1.074488] driver_register (drivers/base/driver.c:249) [ 1.074836] __platform_driver_register (drivers/base/platform.c:868) [ 1.075261] rk_iommu_driver_init (drivers/iommu/rockchip-iommu.c:1380) [ 1.075644] do_one_initcall (init/main.c:1257) [ 1.075996] kernel_init_freeable (init/main.c:1318 (discriminator 1) init/main.c:1335 (discriminator 1) init/main.c:1354 (discriminator 1) init/main.c:1567 (discriminator 1)) [ 1.076393] kernel_init (init/main.c:1461) [ 1.076720] ret_from_fork (arch/arm64/kernel/entry.S:863) [ 1.077053] Code: aa0003f5 b1020020 a90153f3 aa0103f4 (b942a2b7) All code ======== 0: aa0003f5 mov x21, x0 4: b1020020 adds x0, x1, #0x80 8: a90153f3 stp x19, x20, [sp, #16] c: aa0103f4 mov x20, x1 10:* b942a2b7 ldr w23, [x21, #672] <-- trapping instruction Code starting with the faulting instruction =========================================== 0: b942a2b7 ldr w23, [x21, #672] [ 1.077594] ---[ end trace 0000000000000000 ]--- [ 1.078059] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b [ 1.078736] SMP: stopping secondary CPUs [ 1.079099] Kernel Offset: disabled [ 1.079412] CPU features: 0x0400,00041058,01000400,8200421b [ 1.079909] Memory Limit: none [ 1.080188] ---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b ]--- ## Source * Kernel version: 6.14.0-rc6-next-20250313 * Git tree: https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git * Git sha: 613af589b566093ce7388bf3202fca70d742c166 * Git describe: 6.14.0-rc6-next-20250313 * Project details: https://qa-reports.linaro.org/lkft/linux-next-master/build/next-20250305/ * Architectures: arm64 * Compilers: gcc-13 ## Test data * Test log: https://qa-reports.linaro.org/lkft/linux-next-master/build/next-20250313/te… * Test history: https://qa-reports.linaro.org/lkft/linux-next-master/build/next-20250313/te… * Test details: https://qa-reports.linaro.org/lkft/linux-next-master/build/next-20250313/te… * Build link: https://storage.tuxsuite.com/public/linaro/lkft/builds/2uFgT27J8KGNrdNXzKgU… * Kernel config: https://storage.tuxsuite.com/public/linaro/lkft/builds/2uFgT27J8KGNrdNXzKgU… -- Linaro LKFT https://lkft.linaro.org

4 months

2
1
0 0

[PATCH net-next] selftests: net: bump GRO timeout for gro/setup_veth

by Jakub Kicinski

Commit 51bef03e1a71 ("selftests/net: deflake GRO tests") recently switched to NAPI suspension, and lowered the timeout from 1ms to 100us. This started causing flakes in netdev-run CI. Let's bump it to 200us. In a quick test of a debug kernel I see failures with 100us, with 200us in 5 runs I see 2 completely clean runs and 3 with a single retry (GRO test will retry up to 5 times). Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: krakauer(a)google.com CC: willemb(a)google.com CC: shuah(a)kernel.org CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/net/setup_veth.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh index eb3182066d12..152bf4c65747 100644 --- a/tools/testing/selftests/net/setup_veth.sh +++ b/tools/testing/selftests/net/setup_veth.sh @@ -11,7 +11,7 @@ setup_veth_ns() { local -r ns_mac="$4" [[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}" - echo 100000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" + echo 200000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" echo 1 > "/sys/class/net/${ns_dev}/napi_defer_hard_irqs" ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535 ip -netns "${ns_name}" link set dev "${ns_dev}" up -- 2.48.1

4 months

3
2
0 0

[PATCH net-next v22 00/23] Introducing OpenVPN Data Channel Offload

by Antonio Quartulli

Notable changes since v21: * accessed crypto_slot->primary_idx via READ/WRITE_ONCE * made ovpn_aead_init() static * converted link tx/rx packet counters from u32 to to uint * ensured all u32 NL attributes are read by nla_get_u32() * ensured all u32 NL attrivutes are written by nla_put_u32() * reset cache upon float or local endpoint change * dropped check for delta > 0 in keepalive worker scheduling * improved comments in update endpoints logic * converted local_ip to void* to avoid useless casts Please note that some patches were already reviewed/tested by a few people. These patches have retained the tags as they have hardly been touched. The latest code can also be found at: https://github.com/OpenVPN/ovpn-net-next Thanks a lot! Best Regards, Antonio Quartulli OpenVPN Inc. --- Changes in v21: - EDITME: describe what is new in this series revision. - EDITME: use bulletpoints and terse descriptions. - Link to v20: https://lore.kernel.org/r/20250227-b4-ovpn-v20-0-93f363310834@openvpn.net --- Antonio Quartulli (23): net: introduce OpenVPN Data Channel Offload (ovpn) ovpn: add basic netlink support ovpn: add basic interface creation/destruction/management routines ovpn: keep carrier always on for MP interfaces ovpn: introduce the ovpn_peer object ovpn: introduce the ovpn_socket object ovpn: implement basic TX path (UDP) ovpn: implement basic RX path (UDP) ovpn: implement packet processing ovpn: store tunnel and transport statistics ovpn: implement TCP transport skb: implement skb_send_sock_locked_with_flags() ovpn: add support for MSG_NOSIGNAL in tcp_sendmsg ovpn: implement multi-peer support ovpn: implement peer lookup logic ovpn: implement keepalive mechanism ovpn: add support for updating local or remote UDP endpoint ovpn: implement peer add/get/dump/delete via netlink ovpn: implement key add/get/del/swap via netlink ovpn: kill key and notify userspace in case of IV exhaustion ovpn: notify userspace when a peer is deleted ovpn: add basic ethtool support testing/selftests: add test tool and scripts for ovpn module Documentation/netlink/specs/ovpn.yaml | 367 +++ Documentation/netlink/specs/rt_link.yaml | 16 + MAINTAINERS | 11 + drivers/net/Kconfig | 15 + drivers/net/Makefile | 1 + drivers/net/ovpn/Makefile | 22 + drivers/net/ovpn/bind.c | 55 + drivers/net/ovpn/bind.h | 101 + drivers/net/ovpn/crypto.c | 211 ++ drivers/net/ovpn/crypto.h | 145 ++ drivers/net/ovpn/crypto_aead.c | 409 ++++ drivers/net/ovpn/crypto_aead.h | 29 + drivers/net/ovpn/io.c | 462 ++++ drivers/net/ovpn/io.h | 34 + drivers/net/ovpn/main.c | 339 +++ drivers/net/ovpn/main.h | 14 + drivers/net/ovpn/netlink-gen.c | 213 ++ drivers/net/ovpn/netlink-gen.h | 41 + drivers/net/ovpn/netlink.c | 1249 ++++++++++ drivers/net/ovpn/netlink.h | 18 + drivers/net/ovpn/ovpnpriv.h | 57 + drivers/net/ovpn/peer.c | 1367 +++++++++++ drivers/net/ovpn/peer.h | 163 ++ drivers/net/ovpn/pktid.c | 129 ++ drivers/net/ovpn/pktid.h | 87 + drivers/net/ovpn/proto.h | 118 + drivers/net/ovpn/skb.h | 61 + drivers/net/ovpn/socket.c | 244 ++ drivers/net/ovpn/socket.h | 49 + drivers/net/ovpn/stats.c | 21 + drivers/net/ovpn/stats.h | 47 + drivers/net/ovpn/tcp.c | 592 +++++ drivers/net/ovpn/tcp.h | 36 + drivers/net/ovpn/udp.c | 442 ++++ drivers/net/ovpn/udp.h | 25 + include/linux/skbuff.h | 2 + include/uapi/linux/if_link.h | 15 + include/uapi/linux/ovpn.h | 109 + include/uapi/linux/udp.h | 1 + net/core/skbuff.c | 18 +- net/ipv6/af_inet6.c | 1 + net/ipv6/udp.c | 1 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/net/ovpn/.gitignore | 2 + tools/testing/selftests/net/ovpn/Makefile | 31 + tools/testing/selftests/net/ovpn/common.sh | 92 + tools/testing/selftests/net/ovpn/config | 10 + tools/testing/selftests/net/ovpn/data64.key | 5 + tools/testing/selftests/net/ovpn/ovpn-cli.c | 2395 ++++++++++++++++++++ tools/testing/selftests/net/ovpn/tcp_peers.txt | 5 + .../testing/selftests/net/ovpn/test-chachapoly.sh | 9 + .../selftests/net/ovpn/test-close-socket-tcp.sh | 9 + .../selftests/net/ovpn/test-close-socket.sh | 45 + tools/testing/selftests/net/ovpn/test-float.sh | 9 + tools/testing/selftests/net/ovpn/test-tcp.sh | 9 + tools/testing/selftests/net/ovpn/test.sh | 113 + tools/testing/selftests/net/ovpn/udp_peers.txt | 5 + 57 files changed, 10072 insertions(+), 5 deletions(-) --- base-commit: 40587f749df216889163dd6e02d88ad53e759e66 change-id: 20241002-b4-ovpn-eeee35c694a2 Best regards, -- Antonio Quartulli <antonio(a)openvpn.net>

4 months

2
24
0 0

[PATCH v7 00/10] iommufd: Add vIOMMU infrastructure (Part-2: vDEVICE)

by Nicolin Chen

Following the previous vIOMMU series, this adds another vDEVICE structure, representing the association from an iommufd_device to an iommufd_viommu. This gives the whole architecture a new "v" layer: _______________________________________________________________________ | iommufd (with vIOMMU/vDEVICE) | | _____________ _____________ | | | | | | | | |----------------| vIOMMU |<---| vDEVICE |<------| | | | | | |_____________| | | | | ______ | | _____________ ___|____ | | | | | | | | | | | | | | | IOAS |<---|(HWPT_PAGING)|<---| HWPT_NESTED |<--| DEVICE | | | | |______| |_____________| |_____________| |________| | |______|________|______________|__________________|_______________|_____| | | | | | ______v_____ | ______v_____ ______v_____ ___v__ | struct | | PFN | (paging) | | (nested) | |struct| |iommu_device| |------>|iommu_domain|<----|iommu_domain|<----|device| |____________| storage|____________| |____________| |______| This vDEVICE object is used to collect and store all vIOMMU-related device information/attributes in a VM. As an initial series for vDEVICE, add only the virt_id to the vDEVICE, which is a vIOMMU specific device ID in a VM: e.g. vSID of ARM SMMUv3, vDeviceID of AMD IOMMU, and vRID of Intel VT-d to a Context Table. This virt_id helps IOMMU drivers to link the vID to a pID of the device against the physical IOMMU instance. This is essential for a vIOMMU-based invalidation, where the request contains a device's vID for a device cache flush, e.g. ATC invalidation. Therefore, with this vDEVICE object, support a vIOMMU-based invalidation, by reusing IOMMUFD_CMD_HWPT_INVALIDATE for a vIOMMU object to flush cache with a given driver data. As for the implementation of the series, add driver support in ARM SMMUv3 for a real world use case. This series is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_viommu_p2-v7 (QEMU branch for testing will be provided in Jason's nesting series) Changelog v7 * Added "Reviewed-by" from Jason * Corrected a line of comments in iommufd_vdevice_destroy() v6 https://lore.kernel.org/all/cover.1730313494.git.nicolinc@nvidia.com/ * Fixed kdoc in the uAPI header * Fixed indentations in iommufd.rst * Replaced vdev->idev with vdev->dev * Added "Reviewed-by" from Kevin and Jason * Updated kdoc of struct iommu_vdevice_alloc * Fixed lockdep function call in iommufd_viommu_find_dev * Added missing iommu_dev validation between viommu and idev * Skipped SMMUv3 driver changes (to post in a separate series) * Replaced !cache_invalidate_user in WARN_ON of the allocation path with cache_invalidate_user validation in iommufd_hwpt_invalidate v5 https://lore.kernel.org/all/cover.1729897278.git.nicolinc@nvidia.com/ * Dropped driver-allocated vDEVICE support * Changed vdev_to_dev helper to iommufd_viommu_find_dev v4 https://lore.kernel.org/all/cover.1729555967.git.nicolinc@nvidia.com/ * Added missing brackets in switch-case * Fixed the unreleased idev refcount issue * Reworked the iommufd_vdevice_alloc allocator * Dropped support for IOMMU_VIOMMU_TYPE_DEFAULT * Added missing TEST_LENGTH and fail_nth coverages * Added a verification to the driver-allocated vDEVICE object * Added an iommufd_vdevice_abort for a missing mutex protection * Added a u64 structure arm_vsmmu_invalidation_cmd for user command conversion v3 https://lore.kernel.org/all/cover.1728491532.git.nicolinc@nvidia.com/ * Added Jason's Reviewed-by * Split this invalidation part out of the part-1 series * Repurposed VDEV_ID ioctl to a wider vDEVICE structure and ioctl * Reduced viommu_api functions by allowing drivers to access viommu and vdevice structure directly * Dropped vdevs_rwsem by using xa_lock instead * Dropped arm_smmu_cache_invalidate_user v2 https://lore.kernel.org/all/cover.1724776335.git.nicolinc@nvidia.com/ * Limited vdev_id to one per idev * Added a rw_sem to protect the vdev_id list * Reworked driver-level APIs with proper lockings * Added a new viommu_api file for IOMMUFD_DRIVER config * Dropped useless iommu_dev point from the viommu structure * Added missing index numnbers to new types in the uAPI header * Dropped IOMMU_VIOMMU_INVALIDATE uAPI; Instead, reuse the HWPT one * Reworked mock_viommu_cache_invalidate() using the new iommu helper * Reordered details of set/unset_vdev_id handlers for proper lockings v1 https://lore.kernel.org/all/cover.1723061377.git.nicolinc@nvidia.com/ Thanks! Nicolin Jason Gunthorpe (1): iommu: Add iommu_copy_struct_from_full_user_array helper Nicolin Chen (9): iommufd/viommu: Add IOMMUFD_OBJ_VDEVICE and IOMMU_VDEVICE_ALLOC ioctl iommufd/selftest: Add IOMMU_VDEVICE_ALLOC test coverage iommu/viommu: Add cache_invalidate to iommufd_viommu_ops iommufd: Allow hwpt_id to carry viommu_id for IOMMU_HWPT_INVALIDATE iommufd/viommu: Add iommufd_viommu_find_dev helper iommufd/selftest: Add mock_viommu_cache_invalidate iommufd/selftest: Add IOMMU_TEST_OP_DEV_CHECK_CACHE test command iommufd/selftest: Add vIOMMU coverage for IOMMU_HWPT_INVALIDATE ioctl Documentation: userspace-api: iommufd: Update vDEVICE drivers/iommu/iommufd/iommufd_private.h | 18 ++ drivers/iommu/iommufd/iommufd_test.h | 30 +++ include/linux/iommu.h | 48 ++++- include/linux/iommufd.h | 22 ++ include/uapi/linux/iommufd.h | 31 ++- tools/testing/selftests/iommu/iommufd_utils.h | 83 +++++++ drivers/iommu/iommufd/driver.c | 13 ++ drivers/iommu/iommufd/hw_pagetable.c | 40 +++- drivers/iommu/iommufd/main.c | 6 + drivers/iommu/iommufd/selftest.c | 98 ++++++++- drivers/iommu/iommufd/viommu.c | 76 +++++++ tools/testing/selftests/iommu/iommufd.c | 204 +++++++++++++++++- .../selftests/iommu/iommufd_fail_nth.c | 4 + Documentation/userspace-api/iommufd.rst | 41 +++- 14 files changed, 688 insertions(+), 26 deletions(-) base-commit: 0780dd4af09a5360392f5c376c35ffc2599a9c0e -- 2.43.0

4 months

4
14
0 0

[PATCHv5 net 0/3] bond: fix xfrm offload issues

by Hangbin Liu

The first patch fixes the incorrect locks using in bond driver. The second patch fixes the xfrm offload feature during setup active-backup mode. The third patch add a ipsec offload testing. v5: use list_for_each_entry_safe() when del item in list (Nikolay Aleksandrov) do not call spin_lock_bh in sleep function xdo_dev_state_free (Nikolay Aleksandrov) set xso.real_dev = NULL to avoid __xfrm_state_delete() is called in parallel() (Cosmin Ratiu) remove spin lock in bond_ipsec_add_sa_all() as it doesn't resolve the race condition. v4: hold xs->lock for bond_ipsec_{del, add}_sa_all (Cosmin Ratiu) use the defer helpers in lib.sh for selftest (Petr Machata) v3: move the ipsec deletion to bond_ipsec_free_sa (Cosmin Ratiu) v2: do not turn carrier on if bond change link failed (Nikolay Aleksandrov) move the mutex lock to a work queue (Cosmin Ratiu) Hangbin Liu (3): bonding: fix calling sleeping function in spin lock and some race conditions bonding: fix xfrm offload feature setup on active-backup mode selftests: bonding: add ipsec offload test drivers/net/bonding/bond_main.c | 71 +++++--- drivers/net/bonding/bond_netlink.c | 16 +- include/net/bonding.h | 1 + .../selftests/drivers/net/bonding/Makefile | 3 +- .../drivers/net/bonding/bond_ipsec_offload.sh | 154 ++++++++++++++++++ .../selftests/drivers/net/bonding/config | 4 + 6 files changed, 222 insertions(+), 27 deletions(-) create mode 100755 tools/testing/selftests/drivers/net/bonding/bond_ipsec_offload.sh -- 2.46.0

4 months

5
13
0 0

[PATCH] selftests/mm/cow: Fix the incorrect error handling

by Cyan Yang

There are two error handlings did not check the correct return value. This patch will fix them. Fixes: f4b5fd6946e244cdedc3bbb9a1f24c8133b2077a ("selftests/vm: anon_cow: THP tests") Signed-off-by: Cyan Yang <cyan.yang(a)sifive.com> --- tools/testing/selftests/mm/cow.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 9446673645eb..16fcadc090a4 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -876,13 +876,13 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize) mremap_size = thpsize / 2; mremap_mem = mmap(NULL, mremap_size, PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); - if (mem == MAP_FAILED) { + if (mremap_mem == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); goto munmap; } tmp = mremap(mem + mremap_size, mremap_size, mremap_size, MREMAP_MAYMOVE | MREMAP_FIXED, mremap_mem); - if (tmp != mremap_mem) { + if (tmp == MAP_FAILED) { ksft_test_result_fail("mremap() failed\n"); goto munmap; } -- 2.39.5 (Apple Git-154)

4 months

3
4
0 0

[PATCH] selftest/powerpc/mm/pkey: fix build-break introduced by commit 00894c3fc917

by Madhavan Srinivasan

Build break was reported in the powerpc mailing list for next-20250218 with below errors make[1]: Nothing to be done for 'all'. BUILD_TARGET=/root/venkat/linux-next/tools/testing/selftests/powerpc/mm; mkdir -p $BUILD_TARGET; make OUTPUT=$BUILD_TARGET -k -C mm all CC pkey_exec_prot In file included from pkey_exec_prot.c:18: /root/venkat/linux-next/tools/testing/selftests/powerpc/include/pkeys.h: In function ‘pkeys_unsupported’: /root/venkat/linux-next/tools/testing/selftests/powerpc/include/pkeys.h:96:34: error: ‘PKEY_UNRESTRICTED’ undeclared (first use in this function) 96 | pkey = sys_pkey_alloc(0, PKEY_UNRESTRICTED); | ^~~~~~~~~~~~~~~~~ https://lore.kernel.org/all/20250113170619.484698-2-yury.khrustalev@arm.com/ patchset has been queued to arm64/for-next/pkey_unrestricted which is causing a build break in the selftest/powerpc builds. Commit 6d61527d931ba ("mm/pkey: Add PKEY_UNRESTRICTED macro") added a macro PKEY_UNRESTRICTED to handle implicit literal value of 0x0 (which is "unrestricted"). Add the same to selftest/powerpc/pkeys.h to fix the reported build break. Reported-by: Venkat Rao Bagalkote <venkat88(a)linux.ibm.com> Closes: https://lore.kernel.org/lkml/3267ea6e-5a1a-4752-96ef-8351c912d386@linux.ibm… Tested-by: Venkat Rao Bagalkote <venkat88(a)linux.ibm.com> Signed-off-by: Madhavan Srinivasan <maddy(a)linux.ibm.com> --- Catalin, can you take this fix via arm64/for-next/pkey_unrestricted? Patch applies clean on top of arm64/for-next/pkey_unrestricted tools/testing/selftests/powerpc/include/pkeys.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/testing/selftests/powerpc/include/pkeys.h b/tools/testing/selftests/powerpc/include/pkeys.h index c6d4063dd4f6..d6deb6ffa1b9 100644 --- a/tools/testing/selftests/powerpc/include/pkeys.h +++ b/tools/testing/selftests/powerpc/include/pkeys.h @@ -24,6 +24,9 @@ #undef PKEY_DISABLE_EXECUTE #define PKEY_DISABLE_EXECUTE 0x4 +#undef PKEY_UNRESTRICTED +#define PKEY_UNRESTRICTED 0x0 + /* Older versions of libc do not define this */ #ifndef SEGV_PKUERR #define SEGV_PKUERR 4 -- 2.48.1

4 months

2
2
0 0

[PATCH 6.1.y] selftests/vm: fix undefined reference of the `default_huge_page_size`

by Andrey Kalachev

The commit a584c7734a4d ("selftests: mm: fix map_hugetlb failure on 64K page size systems") backported the fix from v6.8 to stable v6.1. The patch uses default_huge_page_size() function, which definition moved into vm_util.[ch] by commit bd4d67e76f699 ("selftests/mm: merge default_huge_page_size() into one") merged to upsream since v6.4. However, in v6.1 common definition/declaration for the default_huge_page_size() we doesn't have, the following build error is seen: map_hugetlb.c:79:25: warning: implicit declaration of function ‘default_huge_page_size’ [-Wimplicit-function-declaration] 79 | hugepage_size = default_huge_page_size(); | ^~~~~~~~~~~~~~~~~~~~~~ /usr/bin/ld: /tmp/ccx95BZz.o: in function `main': map_hugetlb.c:(.text+0x104): undefined reference to `default_huge_page_size' Place default_huge_page_size() function body into map_hugetlb.c to fix this issue. Fixes: a584c7734a4d ("selftests: mm: fix map_hugetlb failure on 64K page size systems") Signed-off-by: Andrey Kalachev <kalachev(a)swemel.ru> --- tools/testing/selftests/vm/map_hugetlb.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/tools/testing/selftests/vm/map_hugetlb.c b/tools/testing/selftests/vm/map_hugetlb.c index c65c55b7a789..5826c50b6736 100644 --- a/tools/testing/selftests/vm/map_hugetlb.c +++ b/tools/testing/selftests/vm/map_hugetlb.c @@ -67,6 +67,30 @@ static int read_bytes(char *addr, size_t length) return 0; } +/* + * default_huge_page_size copied from mlock2-tests.c + */ +unsigned long default_huge_page_size(void) +{ + unsigned long hps = 0; + char *line = NULL; + size_t linelen = 0; + FILE *f = fopen("/proc/meminfo", "r"); + + if (!f) + return 0; + while (getline(&line, &linelen, f) > 0) { + if (sscanf(line, "Hugepagesize: %lu kB", &hps) == 1) { + hps <<= 10; + break; + } + } + + free(line); + fclose(f); + return hps; +} + int main(int argc, char **argv) { void *addr; -- 2.39.5

4 months

1
0
0 0

[PATCH 00/11] selftests: ublk: bug fixes & consolidation

by Ming Lei

Hello Jens and guys, This patchset fixes several issues(1, 2, 4) and consolidate & improve the tests in the following ways: - support shellcheck and fixes all warning - misc cleanup - improve cleanup code path(module load/unload, cleanup temp files) - help to reuse the same test source code and scripts for other projects(liburing[1], blktest, ...) - add two stress tests for covering IO workloads vs. removing device & killing ublk server, given buffer lifetime is one big thing for ublk-zc [1] https://github.com/ming1/liburing/commits/ublk-zc - just need one line change for overriding skip_code, libring uses 77 and kselftests takes 4 Ming Lei (11): selftests: ublk: make ublk_stop_io_daemon() more reliable selftests: ublk: fix build failure selftests: ublk: add --foreground command line selftests: ublk: fix parsing '-a' argument selftests: ublk: support shellcheck and fix all warning selftests: ublk: don't pass ${dev_id} to _cleanup_test() selftests: ublk: move zero copy feature check into _add_ublk_dev() selftests: ublk: load/unload ublk_drv when preparing & cleaning up tests selftests: ublk: add one stress test for covering IO vs. removing device selftests: ublk: add stress test for covering IO vs. killing ublk server selftests: ublk: improve test usability tools/testing/selftests/ublk/Makefile | 6 + tools/testing/selftests/ublk/kublk.c | 43 +++-- tools/testing/selftests/ublk/kublk.h | 2 + tools/testing/selftests/ublk/test_common.sh | 167 ++++++++++++++---- tools/testing/selftests/ublk/test_loop_01.sh | 13 +- tools/testing/selftests/ublk/test_loop_02.sh | 14 +- tools/testing/selftests/ublk/test_loop_03.sh | 16 +- tools/testing/selftests/ublk/test_loop_04.sh | 14 +- tools/testing/selftests/ublk/test_null_01.sh | 9 +- .../testing/selftests/ublk/test_stress_01.sh | 47 +++++ .../testing/selftests/ublk/test_stress_02.sh | 47 +++++ 11 files changed, 300 insertions(+), 78 deletions(-) create mode 100755 tools/testing/selftests/ublk/test_stress_01.sh create mode 100755 tools/testing/selftests/ublk/test_stress_02.sh -- 2.47.0

4 months

3
20
0 0

[PATCH v4 00/12] selftests/mm: Some cleanups from trying to run them

by Brendan Jackman

I never had much luck running mm selftests so I spent a few hours digging into why. Looks like most of the reason is missing SKIP checks, so this series is just adding a bunch of those that I found. I did not do anything like all of them, just the ones I spotted in gup_longterm, gup_test, mmap, userfaultfd and memfd_secret. It's a bit unfortunate to have to skip those tests when ftruncate() fails, but I don't have time to dig deep enough into it to actually make them pass. I have observed the issue on 9pfs and heard rumours that NFS has a similar problem. I'm now able to run these test groups successfully: - mmap - gup_test - compaction - migration - page_frag - userfaultfd - mlock I've never gone past "Waiting for hugetlb memory to get depleted", in the hugetlb tests. I don't know if they are stuck or if they would eventually work if I was patient enough (testing on a 1G machine). I have not investigated further. I had some issues with mlock tests failing due to -ENOSRCH from mlock2(), I can no longer reproduce that though, things work OK now. Of the remaining tests there may be others that work fine, but there's no convenient way to survey the whole output of run_vmtests.sh so I'm just going test by test here. In my spare moments I am slowly chipping away at a setup to run these tests continuously in a reasonably hermetic QEMU environment via virtme-ng: https://github.com/bjackman/linux/blob/5fad4b9c592290f38e0f8bc73c9abb9c99d8… Hopefully that will eventually offer a way to provide a "canned" environment where the tests are known to work, which can be fairly easily reproduced by any developer. Signed-off-by: Brendan Jackman <jackmanb(a)google.com> --- Changes in v4: - NOT ADDRESSED: still using errno==ENOENT as a hacky way to detect buggy filesystems: https://lore.kernel.org/all/CA+i-1C3srkh44tN8dMQ5aD-jhoksUkdEpa+mMfdDtDrPAU… - Added some incomplete cleanups for the mlock tests. - Fixed divide-by-zero error when running uffd-stress on <32cpu systems. - Fixed misnamed nr_threads variable (now nr_parallel). - Fixed reporting io_uring errors (retval instead of errno). - Link to v3: https://lore.kernel.org/r/20250228-mm-selftests-v3-0-958e3b6f0203@google.com Changes in v3: - Added fix for userfaultfd tests. - Dropped attempts to use sudo. - Fixed garbage printf in uffd-stress. (Added EXTRA_CFLAGS=-Werror FORCE_TARGETS=1 to my scripts to prevent such errors happening again). - Fixed missing newlines in ksft_test_result_skip() calls. - Link to v2: https://lore.kernel.org/r/20250221-mm-selftests-v2-0-28c4d66383c5@google.com Changes in v2 (Thanks to Dev for the reviews): - Improve and cleanup some error messages - Add some extra SKIPs - Fix misnaming of nr_cpus variable in uffd tests - Link to v1: https://lore.kernel.org/r/20250220-mm-selftests-v1-0-9bbf57d64463@google.com --- Brendan Jackman (12): selftests/mm: Report errno when things fail in gup_longterm selftests/mm: Skip uffd-stress if userfaultfd not available selftests/mm: Skip uffd-wp-mremap if userfaultfd not available selftests/mm/uffd: Rename nr_cpus -> nr_parallel selftests/mm: Print some details when uffd-stress gets bad params selftests/mm: Don't fail uffd-stress if too many CPUs selftests/mm: Skip map_populate on weird filesystems selftests/mm: Skip gup_longterm tests on weird filesystems selftests/mm: Drop unnecessary sudo usage selftests/mm: Ensure uffd-wp-mremap gets pages of each size selftests/mm: Skip mlock tests if nobody user can't read it selftests/mm/mlock: Print error on failure tools/testing/selftests/mm/gup_longterm.c | 45 +++++++++++++++++--------- tools/testing/selftests/mm/map_populate.c | 7 ++++ tools/testing/selftests/mm/mlock-random-test.c | 4 +-- tools/testing/selftests/mm/mlock2.h | 8 ++++- tools/testing/selftests/mm/run_vmtests.sh | 27 ++++++++++++++-- tools/testing/selftests/mm/uffd-common.c | 8 ++--- tools/testing/selftests/mm/uffd-common.h | 2 +- tools/testing/selftests/mm/uffd-stress.c | 42 +++++++++++++++--------- tools/testing/selftests/mm/uffd-unit-tests.c | 2 +- tools/testing/selftests/mm/uffd-wp-mremap.c | 5 ++- 10 files changed, 105 insertions(+), 45 deletions(-) --- base-commit: dcb38e6757f1b7944af9347ce6b54263d3666478 change-id: 20250220-mm-selftests-2d7d0542face Best regards, -- Brendan Jackman <jackmanb(a)google.com>

4 months

1
12
0 0

[PATCHv4 net 0/2] bonding: fix incorrect mac address setting

by Hangbin Liu

The mac address on backup slave should be convert from Solicited-Node Multicast address, not from bonding unicast target address. v4: no change, just repost. v3: also fix the mac setting for slave_set_ns_maddr. (Jay) Add function description for slave_set_ns_maddr/slave_set_ns_maddrs (Jay) v2: fix patch 01's subject Hangbin Liu (2): bonding: fix incorrect MAC address setting to receive NS messages selftests: bonding: fix incorrect mac address drivers/net/bonding/bond_options.c | 55 ++++++++++++++++--- .../drivers/net/bonding/bond_options.sh | 4 +- 2 files changed, 49 insertions(+), 10 deletions(-) -- 2.46.0

4 months

3
5
0 0

[PATCH v7 bpf-next 0/2] security: Propagate caller information in bpf hooks

by Blaise Boscaccy

Hello, While trying to implement an eBPF gatekeeper program, we ran into an issue whereas the LSM hooks are missing some relevant data. Certain subcommands passed to the bpf() syscall can be invoked from either the kernel or userspace. Additionally, some fields in the bpf_attr struct contain pointers, and depending on where the subcommand was invoked, they could point to either user or kernel memory. One example of this is the bpf_prog_load subcommand and its fd_array. This data is made available and used by the verifier but not made available to the LSM subsystem. This patchset simply exposes that information to applicable LSM hooks. Change list: - v6 -> v7 - use gettid/pid in lieu of getpid/tgid in test condition - v5 -> v6 - fix regression caused by is_kernel renaming - simplify test logic - v4 -> v5 - merge v4 selftest breakout patch back into a single patch - change "is_kernel" to "kernel" - add selftest using new kernel flag - v3 -> v4 - split out selftest changes into a separate patch - v2 -> v3 - reorder params so that the new boolean flag is the last param - fixup function signatures in bpf selftests - v1 -> v2 - Pass a boolean flag in lieu of bpfptr_t Revisions: - v6 https://lore.kernel.org/bpf/20250308013314.719150-1-bboscaccy@linux.microso… - v5 https://lore.kernel.org/bpf/20250307213651.3065714-1-bboscaccy@linux.micros… - v4 https://lore.kernel.org/bpf/20250304203123.3935371-1-bboscaccy@linux.micros… - v3 https://lore.kernel.org/bpf/20250303222416.3909228-1-bboscaccy@linux.micros… - v2 https://lore.kernel.org/bpf/20250228165322.3121535-1-bboscaccy@linux.micros… - v1 https://lore.kernel.org/bpf/20250226003055.1654837-1-bboscaccy@linux.micros… Blaise Boscaccy (2): security: Propagate caller information in bpf hooks selftests/bpf: Add a kernel flag test for LSM bpf hook include/linux/lsm_hook_defs.h | 6 +-- include/linux/security.h | 12 +++--- kernel/bpf/syscall.c | 10 ++--- security/security.c | 15 ++++--- security/selinux/hooks.c | 6 +-- .../selftests/bpf/prog_tests/kernel_flag.c | 43 +++++++++++++++++++ .../selftests/bpf/progs/rcu_read_lock.c | 3 +- .../bpf/progs/test_cgroup1_hierarchy.c | 4 +- .../selftests/bpf/progs/test_kernel_flag.c | 28 ++++++++++++ .../bpf/progs/test_kfunc_dynptr_param.c | 6 +-- .../selftests/bpf/progs/test_lookup_key.c | 2 +- .../selftests/bpf/progs/test_ptr_untrusted.c | 2 +- .../bpf/progs/test_task_under_cgroup.c | 2 +- .../bpf/progs/test_verify_pkcs7_sig.c | 2 +- 14 files changed, 108 insertions(+), 33 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/kernel_flag.c create mode 100644 tools/testing/selftests/bpf/progs/test_kernel_flag.c -- 2.48.1

4 months

4
5
0 0

[PATCH net-next 4/4] tools/testing/selftests/cgroup: add test for SO_PEERCGROUPID

by Alexander Mikhalitsyn

Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Cc: netdev(a)vger.kernel.org Cc: cgroups(a)vger.kernel.org Cc: "David S. Miller" <davem(a)davemloft.net> Cc: Eric Dumazet <edumazet(a)google.com> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Paolo Abeni <pabeni(a)redhat.com> Cc: Willem de Bruijn <willemb(a)google.com> Cc: Leon Romanovsky <leon(a)kernel.org> Cc: Arnd Bergmann <arnd(a)arndb.de> Cc: Christian Brauner <brauner(a)kernel.org> Cc: Kuniyuki Iwashima <kuniyu(a)amazon.com> Cc: Lennart Poettering <mzxreary(a)0pointer.de> Cc: Luca Boccassi <bluca(a)debian.org> Cc: Tejun Heo <tj(a)kernel.org> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: "Michal Koutný" <mkoutny(a)suse.com> Cc: Shuah Khan <shuah(a)kernel.org> Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn(a)canonical.com> --- tools/testing/selftests/cgroup/Makefile | 2 + .../selftests/cgroup/test_so_peercgroupid.c | 308 ++++++++++++++++++ 2 files changed, 310 insertions(+) create mode 100644 tools/testing/selftests/cgroup/test_so_peercgroupid.c diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile index 1b897152bab6..a932ff068081 100644 --- a/tools/testing/selftests/cgroup/Makefile +++ b/tools/testing/selftests/cgroup/Makefile @@ -16,6 +16,7 @@ TEST_GEN_PROGS += test_kill TEST_GEN_PROGS += test_kmem TEST_GEN_PROGS += test_memcontrol TEST_GEN_PROGS += test_pids +TEST_GEN_PROGS += test_so_peercgroupid TEST_GEN_PROGS += test_zswap LOCAL_HDRS += $(selfdir)/clone3/clone3_selftests.h $(selfdir)/pidfd/pidfd.h @@ -31,4 +32,5 @@ $(OUTPUT)/test_kill: cgroup_util.c $(OUTPUT)/test_kmem: cgroup_util.c $(OUTPUT)/test_memcontrol: cgroup_util.c $(OUTPUT)/test_pids: cgroup_util.c +$(OUTPUT)/test_so_peercgroupid: cgroup_util.c $(OUTPUT)/test_zswap: cgroup_util.c diff --git a/tools/testing/selftests/cgroup/test_so_peercgroupid.c b/tools/testing/selftests/cgroup/test_so_peercgroupid.c new file mode 100644 index 000000000000..2bf1f00a45c7 --- /dev/null +++ b/tools/testing/selftests/cgroup/test_so_peercgroupid.c @@ -0,0 +1,308 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +#define _GNU_SOURCE +#include <error.h> +#include <inttypes.h> +#include <limits.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/socket.h> +#include <linux/socket.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> +#include <sys/un.h> +#include <sys/signal.h> +#include <sys/types.h> +#include <sys/wait.h> + +#include "../kselftest_harness.h" +#include "cgroup_util.h" + +#define clean_errno() (errno == 0 ? "None" : strerror(errno)) +#define log_err(MSG, ...) \ + fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", __FILE__, __LINE__, \ + clean_errno(), ##__VA_ARGS__) + +#ifndef SO_PEERCGROUPID +#define SO_PEERCGROUPID 83 +#endif + +static void child_die() +{ + exit(1); +} + +struct sock_addr { + char sock_name[32]; + struct sockaddr_un listen_addr; + socklen_t addrlen; +}; + +FIXTURE(so_peercgroupid) +{ + int server; + pid_t client_pid; + int sync_sk[2]; + struct sock_addr server_addr; + struct sock_addr *client_addr; + char cgroup_root[PATH_MAX]; + char *test_cgroup1; + char *test_cgroup2; +}; + +FIXTURE_VARIANT(so_peercgroupid) +{ + int type; + bool abstract; +}; + +FIXTURE_VARIANT_ADD(so_peercgroupid, stream_pathname) +{ + .type = SOCK_STREAM, + .abstract = 0, +}; + +FIXTURE_VARIANT_ADD(so_peercgroupid, stream_abstract) +{ + .type = SOCK_STREAM, + .abstract = 1, +}; + +FIXTURE_VARIANT_ADD(so_peercgroupid, seqpacket_pathname) +{ + .type = SOCK_SEQPACKET, + .abstract = 0, +}; + +FIXTURE_VARIANT_ADD(so_peercgroupid, seqpacket_abstract) +{ + .type = SOCK_SEQPACKET, + .abstract = 1, +}; + +FIXTURE_VARIANT_ADD(so_peercgroupid, dgram_pathname) +{ + .type = SOCK_DGRAM, + .abstract = 0, +}; + +FIXTURE_VARIANT_ADD(so_peercgroupid, dgram_abstract) +{ + .type = SOCK_DGRAM, + .abstract = 1, +}; + +FIXTURE_SETUP(so_peercgroupid) +{ + self->client_addr = mmap(NULL, sizeof(*self->client_addr), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(MAP_FAILED, self->client_addr); + + self->cgroup_root[0] = '\0'; +} + +FIXTURE_TEARDOWN(so_peercgroupid) +{ + close(self->server); + + kill(self->client_pid, SIGKILL); + waitpid(self->client_pid, NULL, 0); + + if (!variant->abstract) { + unlink(self->server_addr.sock_name); + unlink(self->client_addr->sock_name); + } + + if (strlen(self->cgroup_root) > 0) { + cg_enter_current(self->cgroup_root); + + if (self->test_cgroup1) + cg_destroy(self->test_cgroup1); + free(self->test_cgroup1); + + if (self->test_cgroup2) + cg_destroy(self->test_cgroup2); + free(self->test_cgroup2); + } +} + +static void fill_sockaddr(struct sock_addr *addr, bool abstract) +{ + char *sun_path_buf = (char *)&addr->listen_addr.sun_path; + + addr->listen_addr.sun_family = AF_UNIX; + addr->addrlen = offsetof(struct sockaddr_un, sun_path); + snprintf(addr->sock_name, sizeof(addr->sock_name), "so_peercgroupid_%d", getpid()); + addr->addrlen += strlen(addr->sock_name); + if (abstract) { + *sun_path_buf = '\0'; + addr->addrlen++; + sun_path_buf++; + } else { + unlink(addr->sock_name); + } + memcpy(sun_path_buf, addr->sock_name, strlen(addr->sock_name)); +} + +static void client(FIXTURE_DATA(so_peercgroupid) *self, + const FIXTURE_VARIANT(so_peercgroupid) *variant) +{ + int cfd, err; + socklen_t len; + uint64_t peer_cgroup_id = 0, test_cgroup1_id = 0, test_cgroup2_id = 0; + char state; + + cfd = socket(AF_UNIX, variant->type, 0); + if (cfd < 0) { + log_err("socket"); + child_die(); + } + + if (variant->type == SOCK_DGRAM) { + fill_sockaddr(self->client_addr, variant->abstract); + + if (bind(cfd, (struct sockaddr *)&self->client_addr->listen_addr, self->client_addr->addrlen)) { + log_err("bind"); + child_die(); + } + } + + /* negative testcase: no peer for socket yet */ + len = sizeof(peer_cgroup_id); + err = getsockopt(cfd, SOL_SOCKET, SO_PEERCGROUPID, &peer_cgroup_id, &len); + if (!err || (errno != ENODATA)) { + log_err("getsockopt must fail with errno == ENODATA when socket has no peer"); + child_die(); + } + + if (connect(cfd, (struct sockaddr *)&self->server_addr.listen_addr, + self->server_addr.addrlen) != 0) { + log_err("connect"); + child_die(); + } + + state = 'R'; + write(self->sync_sk[1], &state, sizeof(state)); + + read(self->sync_sk[1], &test_cgroup1_id, sizeof(uint64_t)); + read(self->sync_sk[1], &test_cgroup2_id, sizeof(uint64_t)); + + len = sizeof(peer_cgroup_id); + if (getsockopt(cfd, SOL_SOCKET, SO_PEERCGROUPID, &peer_cgroup_id, &len)) { + log_err("Failed to get SO_PEERCGROUPID"); + child_die(); + } + + /* + * There is a difference between connection-oriented sockets + * and connectionless ones from the perspective of SO_PEERCGROUPID. + * + * sk->sk_cgrp_data is getting filled when we allocate struct sock (see call to cgroup_sk_alloc()). + * For DGRAM socket, self->server socket is our peer and by the time when we allocate it, + * parent process sits in a test_cgroup1. Then it changes cgroup to test_cgroup2, but it does not + * affect anything. + * For STREAM/SEQPACKET socket, self->server is not our peer, but that one we get from accept() + * syscall. And by the time when we call accept(), parent process sits in test_cgroup2. + * + * Let's ensure that it works like that and if it get changed then we should detect it + * as it's a clear UAPI change. + */ + if (variant->type == SOCK_DGRAM) { + /* cgroup id from SO_PEERCGROUPID should be equal to the test_cgroup1_id */ + if (peer_cgroup_id != test_cgroup1_id) { + log_err("peer_cgroup_id != test_cgroup1_id: %" PRId64 " != %" PRId64, peer_cgroup_id, test_cgroup1_id); + child_die(); + } + } else { + /* cgroup id from SO_PEERCGROUPID should be equal to the test_cgroup2_id */ + if (peer_cgroup_id != test_cgroup2_id) { + log_err("peer_cgroup_id != test_cgroup2_id: %" PRId64 " != %" PRId64, peer_cgroup_id, test_cgroup2_id); + child_die(); + } + } +} + +TEST_F(so_peercgroupid, test) +{ + uint64_t test_cgroup1_id, test_cgroup2_id; + int err; + int pfd; + char state; + int child_status = 0; + + if (cg_find_unified_root(self->cgroup_root, sizeof(self->cgroup_root), NULL)) + ksft_exit_skip("cgroup v2 isn't mounted\n"); + + self->test_cgroup1 = cg_name(self->cgroup_root, "so_peercgroupid_cg1"); + ASSERT_NE(NULL, self->test_cgroup1); + + self->test_cgroup2 = cg_name(self->cgroup_root, "so_peercgroupid_cg2"); + ASSERT_NE(NULL, self->test_cgroup2); + + err = cg_create(self->test_cgroup1); + ASSERT_EQ(0, err); + + err = cg_create(self->test_cgroup2); + ASSERT_EQ(0, err); + + test_cgroup1_id = cg_get_id(self->test_cgroup1); + ASSERT_LT(0, test_cgroup1_id); + + test_cgroup2_id = cg_get_id(self->test_cgroup2); + ASSERT_LT(0, test_cgroup2_id); + + /* enter test_cgroup1 before allocating a socket */ + err = cg_enter_current(self->test_cgroup1); + ASSERT_EQ(0, err); + + self->server = socket(AF_UNIX, variant->type, 0); + ASSERT_NE(-1, self->server); + + /* enter test_cgroup2 after allocating a socket */ + err = cg_enter_current(self->test_cgroup2); + ASSERT_EQ(0, err); + + fill_sockaddr(&self->server_addr, variant->abstract); + + err = bind(self->server, (struct sockaddr *)&self->server_addr.listen_addr, self->server_addr.addrlen); + ASSERT_EQ(0, err); + + if (variant->type != SOCK_DGRAM) { + err = listen(self->server, 1); + ASSERT_EQ(0, err); + } + + err = socketpair(AF_UNIX, SOCK_DGRAM | SOCK_CLOEXEC, 0, self->sync_sk); + EXPECT_EQ(err, 0); + + self->client_pid = fork(); + ASSERT_NE(-1, self->client_pid); + if (self->client_pid == 0) { + close(self->server); + close(self->sync_sk[0]); + client(self, variant); + exit(0); + } + close(self->sync_sk[1]); + + if (variant->type != SOCK_DGRAM) { + pfd = accept(self->server, NULL, NULL); + ASSERT_NE(-1, pfd); + } else { + pfd = self->server; + } + + /* wait until the child arrives at checkpoint */ + read(self->sync_sk[0], &state, sizeof(state)); + ASSERT_EQ(state, 'R'); + + write(self->sync_sk[0], &test_cgroup1_id, sizeof(uint64_t)); + write(self->sync_sk[0], &test_cgroup2_id, sizeof(uint64_t)); + + close(pfd); + waitpid(self->client_pid, &child_status, 0); + ASSERT_EQ(0, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); +} + +TEST_HARNESS_MAIN -- 2.43.0

4 months

3
2
0 0

[PATCH v12 3/3] selftests/rseq: Add test for mm_cid compaction

by Gabriele Monaco

A task in the kernel (task_mm_cid_work) runs somewhat periodically to compact the mm_cid for each process. Add a test to validate that it runs correctly and timely. The test spawns 1 thread pinned to each CPU, then each thread, including the main one, runs in short bursts for some time. During this period, the mm_cids should be spanning all numbers between 0 and nproc. At the end of this phase, a thread with high enough mm_cid (>= nproc/2) is selected to be the new leader, all other threads terminate. After some time, the only running thread should see 0 as mm_cid, if that doesn't happen, the compaction mechanism didn't work and the test fails. The test never fails if only 1 core is available, in which case, we cannot test anything as the only available mm_cid is 0. Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Signed-off-by: Gabriele Monaco <gmonaco(a)redhat.com> --- tools/testing/selftests/rseq/.gitignore | 1 + tools/testing/selftests/rseq/Makefile | 2 +- .../selftests/rseq/mm_cid_compaction_test.c | 200 ++++++++++++++++++ 3 files changed, 202 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/rseq/mm_cid_compaction_test.c diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore index 16496de5f6ce4..2c89f97e4f737 100644 --- a/tools/testing/selftests/rseq/.gitignore +++ b/tools/testing/selftests/rseq/.gitignore @@ -3,6 +3,7 @@ basic_percpu_ops_test basic_percpu_ops_mm_cid_test basic_test basic_rseq_op_test +mm_cid_compaction_test param_test param_test_benchmark param_test_compare_twice diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 5a3432fceb586..ce1b38f46a355 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -16,7 +16,7 @@ OVERRIDE_TARGETS = 1 TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ param_test_benchmark param_test_compare_twice param_test_mm_cid \ - param_test_mm_cid_benchmark param_test_mm_cid_compare_twice + param_test_mm_cid_benchmark param_test_mm_cid_compare_twice mm_cid_compaction_test TEST_GEN_PROGS_EXTENDED = librseq.so diff --git a/tools/testing/selftests/rseq/mm_cid_compaction_test.c b/tools/testing/selftests/rseq/mm_cid_compaction_test.c new file mode 100644 index 0000000000000..7ddde3b657dd6 --- /dev/null +++ b/tools/testing/selftests/rseq/mm_cid_compaction_test.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include <assert.h> +#include <pthread.h> +#include <sched.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stddef.h> + +#include "../kselftest.h" +#include "rseq.h" + +#define VERBOSE 0 +#define printf_verbose(fmt, ...) \ + do { \ + if (VERBOSE) \ + printf(fmt, ##__VA_ARGS__); \ + } while (0) + +/* 0.5 s */ +#define RUNNER_PERIOD 500000 +/* Number of runs before we terminate or get the token */ +#define THREAD_RUNS 5 + +/* + * Number of times we check that the mm_cid were compacted. + * Checks are repeated every RUNNER_PERIOD. + */ +#define MM_CID_COMPACT_TIMEOUT 10 + +struct thread_args { + int cpu; + int num_cpus; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + pthread_t *tinfo; + struct thread_args *args_head; +}; + +static void __noreturn *thread_runner(void *arg) +{ + struct thread_args *args = arg; + int i, ret, curr_mm_cid; + cpu_set_t cpumask; + + CPU_ZERO(&cpumask); + CPU_SET(args->cpu, &cpumask); + ret = pthread_setaffinity_np(pthread_self(), sizeof(cpumask), &cpumask); + if (ret) { + errno = ret; + perror("Error: failed to set affinity"); + abort(); + } + pthread_barrier_wait(args->barrier); + + for (i = 0; i < THREAD_RUNS; i++) + usleep(RUNNER_PERIOD); + curr_mm_cid = rseq_current_mm_cid(); + /* + * We select one thread with high enough mm_cid to be the new leader. + * All other threads (including the main thread) will terminate. + * After some time, the mm_cid of the only remaining thread should + * converge to 0, if not, the test fails. + */ + if (curr_mm_cid >= args->num_cpus / 2 && + !pthread_mutex_trylock(args->token)) { + printf_verbose( + "cpu%d has mm_cid=%d and will be the new leader.\n", + sched_getcpu(), curr_mm_cid); + for (i = 0; i < args->num_cpus; i++) { + if (args->tinfo[i] == pthread_self()) + continue; + ret = pthread_join(args->tinfo[i], NULL); + if (ret) { + errno = ret; + perror("Error: failed to join thread"); + abort(); + } + } + pthread_barrier_destroy(args->barrier); + free(args->tinfo); + free(args->token); + free(args->barrier); + free(args->args_head); + + for (i = 0; i < MM_CID_COMPACT_TIMEOUT; i++) { + curr_mm_cid = rseq_current_mm_cid(); + printf_verbose("run %d: mm_cid=%d on cpu%d.\n", i, + curr_mm_cid, sched_getcpu()); + if (curr_mm_cid == 0) + exit(EXIT_SUCCESS); + usleep(RUNNER_PERIOD); + } + exit(EXIT_FAILURE); + } + printf_verbose("cpu%d has mm_cid=%d and is going to terminate.\n", + sched_getcpu(), curr_mm_cid); + pthread_exit(NULL); +} + +int test_mm_cid_compaction(void) +{ + cpu_set_t affinity; + int i, j, ret = 0, num_threads; + pthread_t *tinfo; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + struct thread_args *args; + + sched_getaffinity(0, sizeof(affinity), &affinity); + num_threads = CPU_COUNT(&affinity); + tinfo = calloc(num_threads, sizeof(*tinfo)); + if (!tinfo) { + perror("Error: failed to allocate tinfo"); + return -1; + } + args = calloc(num_threads, sizeof(*args)); + if (!args) { + perror("Error: failed to allocate args"); + ret = -1; + goto out_free_tinfo; + } + token = malloc(sizeof(*token)); + if (!token) { + perror("Error: failed to allocate token"); + ret = -1; + goto out_free_args; + } + barrier = malloc(sizeof(*barrier)); + if (!barrier) { + perror("Error: failed to allocate barrier"); + ret = -1; + goto out_free_token; + } + if (num_threads == 1) { + fprintf(stderr, "Cannot test on a single cpu. " + "Skipping mm_cid_compaction test.\n"); + /* only skipping the test, this is not a failure */ + goto out_free_barrier; + } + pthread_mutex_init(token, NULL); + ret = pthread_barrier_init(barrier, NULL, num_threads); + if (ret) { + errno = ret; + perror("Error: failed to initialise barrier"); + goto out_free_barrier; + } + for (i = 0, j = 0; i < CPU_SETSIZE && j < num_threads; i++) { + if (!CPU_ISSET(i, &affinity)) + continue; + args[j].num_cpus = num_threads; + args[j].tinfo = tinfo; + args[j].token = token; + args[j].barrier = barrier; + args[j].cpu = i; + args[j].args_head = args; + if (!j) { + /* The first thread is the main one */ + tinfo[0] = pthread_self(); + ++j; + continue; + } + ret = pthread_create(&tinfo[j], NULL, thread_runner, &args[j]); + if (ret) { + errno = ret; + perror("Error: failed to create thread"); + abort(); + } + ++j; + } + printf_verbose("Started %d threads.\n", num_threads); + + /* Also main thread will terminate if it is not selected as leader */ + thread_runner(&args[0]); + + /* only reached in case of errors */ +out_free_barrier: + free(barrier); +out_free_token: + free(token); +out_free_args: + free(args); +out_free_tinfo: + free(tinfo); + + return ret; +} + +int main(int argc, char **argv) +{ + if (!rseq_mm_cid_available()) { + fprintf(stderr, "Error: rseq_mm_cid unavailable\n"); + return -1; + } + if (test_mm_cid_compaction()) + return -1; + return 0; +} -- 2.48.1

4 months

1
0
0 0

[PATCH v8 net-next 0/3] DUALPI2 patch

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find DUALPI2 patch v8. v8 - Fix warning messages in v7 v7 - Separate into 3 patches to avoid mixing changes of documentation, selftest, and code. (Cong Wang <xiyou.wangcong(a)gmail.com>) v6 - Add modprobe for dulapi2 in tc-testing script tc-testing/tdc.sh (Jakub Kicinski <kuba(a)kernel.org>) - Update test cases in dualpi2.json - Update commit message v5 - A comparison was done between MQ + DUALPI2, MQ + FQ_PIE, MQ + FQ_CODEL: Unshaped 1gigE with 4 download streams test: - Summary of tcp_4down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 1.19 1.34 ms 349 TCP download avg : 235.42 N/A Mbits/s 349 TCP download sum : 941.68 N/A Mbits/s 349 TCP download::1 : 235.19 235.39 Mbits/s 349 TCP download::2 : 235.03 235.35 Mbits/s 349 TCP download::3 : 236.89 235.44 Mbits/s 349 TCP download::4 : 234.57 235.19 Mbits/s 349 - Summary of tcp_4down run 'MQ + FQ_PIE' avg median # data pts Ping (ms) ICMP : 1.21 1.37 ms 350 TCP download avg : 235.42 N/A Mbits/s 350 TCP download sum : 941.61 N/A Mbits/s 350 TCP download::1 : 232.54 233.13 Mbits/s 350 TCP download::2 : 232.52 232.80 Mbits/s 350 TCP download::3 : 233.14 233.78 Mbits/s 350 TCP download::4 : 243.41 241.48 Mbits/s 350 - Summary of tcp_4down run 'MQ + DUALPI2' avg median # data pts Ping (ms) ICMP : 1.19 1.34 ms 349 TCP download avg : 235.42 N/A Mbits/s 349 TCP download sum : 941.68 N/A Mbits/s 349 TCP download::1 : 235.19 235.39 Mbits/s 349 TCP download::2 : 235.03 235.35 Mbits/s 349 TCP download::3 : 236.89 235.44 Mbits/s 349 TCP download::4 : 234.57 235.19 Mbits/s 349 Unshaped 1gigE with 128 download streams test: - Summary of tcp_128down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 Unshaped 10gigE with 4 download streams test: - Summary of tcp_4down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 0.22 0.23 ms 350 TCP download avg : 2354.08 N/A Mbits/s 350 TCP download sum : 9416.31 N/A Mbits/s 350 TCP download::1 : 2353.65 2352.81 Mbits/s 350 TCP download::2 : 2354.54 2354.21 Mbits/s 350 TCP download::3 : 2353.56 2353.78 Mbits/s 350 TCP download::4 : 2354.56 2354.45 Mbits/s 350 - Summary of tcp_4down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 0.20 0.19 ms 350 TCP download avg : 2354.76 N/A Mbits/s 350 TCP download sum : 9419.04 N/A Mbits/s 350 TCP download::1 : 2354.77 2353.89 Mbits/s 350 TCP download::2 : 2353.41 2354.29 Mbits/s 350 TCP download::3 : 2356.18 2354.19 Mbits/s 350 TCP download::4 : 2354.68 2353.15 Mbits/s 350 - Summary of tcp_4down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 0.24 0.24 ms 350 TCP download avg : 2354.11 N/A Mbits/s 350 TCP download sum : 9416.43 N/A Mbits/s 350 TCP download::1 : 2354.75 2353.93 Mbits/s 350 TCP download::2 : 2353.15 2353.75 Mbits/s 350 TCP download::3 : 2353.49 2353.72 Mbits/s 350 TCP download::4 : 2355.04 2353.73 Mbits/s 350 Unshaped 10gigE with 128 download streams test: - Summary of tcp_128down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 7.57 8.69 ms 350 TCP download avg : 73.97 N/A Mbits/s 350 TCP download sum : 9467.82 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 7.82 8.91 ms 350 TCP download avg : 73.97 N/A Mbits/s 350 TCP download sum : 9468.42 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 6.87 7.93 ms 350 TCP download avg : 73.95 N/A Mbits/s 350 TCP download sum : 9465.87 N/A Mbits/s 350 From the results shown above, we see small differences between combinations. - Update commit message to include results of no_split_gso and split_gso (Dave Taht <dave.taht(a)gmail.com> and Paolo Abeni <pabeni(a)redhat.com>) - Add memlimit in dualpi2 attribute, and add memory_used, max_memory_used, memory_limit in dualpi2 stats (Dave Taht <dave.taht(a)gmail.com>) - Update note in sch_dualpi2.c related to BBRv3 status (Dave Taht <dave.taht(a)gmail.com>) - Update license identifier (Dave Taht <dave.taht(a)gmail.com>) - Add selftest in tools/testing/selftests/tc-testing (Cong Wang <xiyou.wangcong(a)gmail.com>) - Use netlink policies for parameter checks (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Modify texts & fix typos in Documentation/netlink/specs/tc.yaml (Dave Taht <dave.taht(a)gmail.com>) - Add dscsriptions of packet counter statistics and reset function of sch_dualpi2.c - Fix step_thresh in packets - Update code comments in sch_dualpi2.c v4 - Update statement in Kconfig for DualPI2 (Stephen Hemminger <stephen(a)networkplumber.org>) - Put a blank line after #define in sch_dualpi2.c (Stephen Hemminger <stephen(a)networkplumber.org>) - Fix line length warning v3 - Fix compilaiton error - Update Documentation/netlink/specs/tc.yaml (Jakub Kicinski <kuba(a)kernel.org>) v2 - Add Documentation/netlink/specs/tc.yaml (Jakub Kicinski <kuba(a)kernel.org>) - Use dualpi2 instead of skb prefix (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Replace nla_parse_nested_deprecated with nla_parse_nested (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Fix line length warning For more details of DualPI2, plesae refer IETF RFC9332 (https://datatracker.ietf.org/doc/html/rfc9332). Best regards, Chia-Yu Chia-Yu Chang (2): Documentation: netlink: specs: tc: Add DualPI2 specification selftests/tc-testing: Add selftests for qdisc DualPI2 Koen De Schepper (1): sched: Add dualpi2 qdisc Documentation/netlink/specs/tc.yaml | 140 +++ include/linux/netdevice.h | 1 + include/uapi/linux/pkt_sched.h | 38 + net/sched/Kconfig | 12 + net/sched/Makefile | 1 + net/sched/sch_dualpi2.c | 1082 +++++++++++++++++ tools/testing/selftests/tc-testing/config | 1 + .../tc-testing/tc-tests/qdiscs/dualpi2.json | 149 +++ tools/testing/selftests/tc-testing/tdc.sh | 1 + 9 files changed, 1425 insertions(+) create mode 100644 net/sched/sch_dualpi2.c create mode 100644 tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json -- 2.34.1

4 months

2
4
0 0

[PATCH] selftests/bpf: Convert comma to semicolon

by Chen Ni

Replace comma between expressions with semicolons. Using a ',' in place of a ';' can have unintended side effects. Although that is not the case here, it is seems best to use ';' unless ',' is intended. Found by inspection. No functional change intended. Compile tested only. Signed-off-by: Chen Ni <nichen(a)iscas.ac.cn> --- tools/testing/selftests/bpf/prog_tests/fd_array.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c index a1d52e73fb16..9add890c2d37 100644 --- a/tools/testing/selftests/bpf/prog_tests/fd_array.c +++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c @@ -83,8 +83,8 @@ static inline int bpf_prog_get_map_ids(int prog_fd, __u32 *nr_map_ids, __u32 *ma int err; memset(&info, 0, len); - info.nr_map_ids = *nr_map_ids, - info.map_ids = ptr_to_u64(map_ids), + info.nr_map_ids = *nr_map_ids; + info.map_ids = ptr_to_u64(map_ids); err = bpf_prog_get_info_by_fd(prog_fd, &info, &len); if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd")) -- 2.25.1

4 months

3
2
0 0

[PATCH v21 00/24] Introducing OpenVPN Data Channel Offload

by Antonio Quartulli

Notable changes since v20: * removed newline at the end of message in NL_SET_ERR_MSG_FMT_MOD * dropped udp_init() and related build_protos() and directly use .encap_destroy [instead of overriding sk->close()] * defered peer_del() call to worker in case of transport errors, as we may be in non-sleepable context * used kfree() instead of kfree_rcu() when releasing socket as we just invoked synchronize_rcu() * fix comment in ovpn_tcp_parse() * invoked peer->tcp.sk_cb.prot->release_cb instead of explicitly calling tcp_release_cb. This way we don't need to export it again * moved call to peer_put() after call to peer->tcp.sk_cb.prot->close * moved switch(mode) inside ovpn_peers_free() * simplified skip logic in ovpn_peers_free() * fixed check to avoid passing a negative delay to keepalive's schedule_work() Please note that some patches were already reviewed/tested by a few people. These patches have retained the tags as they have hardly been touched. The latest code can also be found at: https://github.com/OpenVPN/ovpn-net-next Thanks a lot! Best Regards, Antonio Quartulli OpenVPN Inc. To: netdev(a)vger.kernel.org To: Eric Dumazet <edumazet(a)google.com> To: Jakub Kicinski <kuba(a)kernel.org> To: Paolo Abeni <pabeni(a)redhat.com> To: Donald Hunter <donald.hunter(a)gmail.com> To: Antonio Quartulli <antonio(a)openvpn.net> To: Shuah Khan <shuah(a)kernel.org> To: sd(a)queasysnail.net To: ryazanov.s.a(a)gmail.com To: Andrew Lunn <andrew+netdev(a)lunn.ch> Cc: Simon Horman <horms(a)kernel.org> Cc: linux-kernel(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Cc: Xiao Liang <shaw.leon(a)gmail.com> Signed-off-by: Antonio Quartulli <antonio(a)openvpn.net> --- Antonio Quartulli (24): net: introduce OpenVPN Data Channel Offload (ovpn) ovpn: add basic netlink support ovpn: add basic interface creation/destruction/management routines ovpn: keep carrier always on for MP interfaces ovpn: introduce the ovpn_peer object ovpn: introduce the ovpn_socket object ovpn: implement basic TX path (UDP) ovpn: implement basic RX path (UDP) ovpn: implement packet processing ovpn: store tunnel and transport statistics ovpn: implement TCP transport skb: implement skb_send_sock_locked_with_flags() ovpn: add support for MSG_NOSIGNAL in tcp_sendmsg ovpn: implement multi-peer support ovpn: implement peer lookup logic ovpn: implement keepalive mechanism ovpn: add support for updating local UDP endpoint ovpn: add support for peer floating ovpn: implement peer add/get/dump/delete via netlink ovpn: implement key add/get/del/swap via netlink ovpn: kill key and notify userspace in case of IV exhaustion ovpn: notify userspace when a peer is deleted ovpn: add basic ethtool support testing/selftests: add test tool and scripts for ovpn module Documentation/netlink/specs/ovpn.yaml | 371 +++ Documentation/netlink/specs/rt_link.yaml | 16 + MAINTAINERS | 11 + drivers/net/Kconfig | 15 + drivers/net/Makefile | 1 + drivers/net/ovpn/Makefile | 22 + drivers/net/ovpn/bind.c | 55 + drivers/net/ovpn/bind.h | 101 + drivers/net/ovpn/crypto.c | 211 ++ drivers/net/ovpn/crypto.h | 145 ++ drivers/net/ovpn/crypto_aead.c | 408 ++++ drivers/net/ovpn/crypto_aead.h | 33 + drivers/net/ovpn/io.c | 462 ++++ drivers/net/ovpn/io.h | 34 + drivers/net/ovpn/main.c | 339 +++ drivers/net/ovpn/main.h | 14 + drivers/net/ovpn/netlink-gen.c | 213 ++ drivers/net/ovpn/netlink-gen.h | 41 + drivers/net/ovpn/netlink.c | 1249 ++++++++++ drivers/net/ovpn/netlink.h | 18 + drivers/net/ovpn/ovpnpriv.h | 57 + drivers/net/ovpn/peer.c | 1352 +++++++++++ drivers/net/ovpn/peer.h | 163 ++ drivers/net/ovpn/pktid.c | 129 ++ drivers/net/ovpn/pktid.h | 87 + drivers/net/ovpn/proto.h | 118 + drivers/net/ovpn/skb.h | 61 + drivers/net/ovpn/socket.c | 244 ++ drivers/net/ovpn/socket.h | 49 + drivers/net/ovpn/stats.c | 21 + drivers/net/ovpn/stats.h | 47 + drivers/net/ovpn/tcp.c | 592 +++++ drivers/net/ovpn/tcp.h | 36 + drivers/net/ovpn/udp.c | 442 ++++ drivers/net/ovpn/udp.h | 25 + include/linux/skbuff.h | 2 + include/uapi/linux/if_link.h | 15 + include/uapi/linux/ovpn.h | 110 + include/uapi/linux/udp.h | 1 + net/core/skbuff.c | 18 +- net/ipv6/af_inet6.c | 1 + net/ipv6/udp.c | 1 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/net/ovpn/.gitignore | 2 + tools/testing/selftests/net/ovpn/Makefile | 31 + tools/testing/selftests/net/ovpn/common.sh | 92 + tools/testing/selftests/net/ovpn/config | 10 + tools/testing/selftests/net/ovpn/data64.key | 5 + tools/testing/selftests/net/ovpn/ovpn-cli.c | 2395 ++++++++++++++++++++ tools/testing/selftests/net/ovpn/tcp_peers.txt | 5 + .../testing/selftests/net/ovpn/test-chachapoly.sh | 9 + .../selftests/net/ovpn/test-close-socket-tcp.sh | 9 + .../selftests/net/ovpn/test-close-socket.sh | 45 + tools/testing/selftests/net/ovpn/test-float.sh | 9 + tools/testing/selftests/net/ovpn/test-tcp.sh | 9 + tools/testing/selftests/net/ovpn/test.sh | 113 + tools/testing/selftests/net/ovpn/udp_peers.txt | 5 + 57 files changed, 10065 insertions(+), 5 deletions(-) --- base-commit: fb05579a176f7bccc8d279665fc0e46dfed43dfb change-id: 20250304-b4-ovpn-tmp-153379e78603 Best regards, -- Antonio Quartulli <antonio(a)openvpn.net>

4 months

2
45
0 0

[PATCH v15 00/15] PCI: EP: Add RC-to-EP doorbell with platform MSI controller

by Frank Li

┌────────────┐ ┌───────────────────────────────────┐ ┌────────────────┐ │ │ │ │ │ │ │ │ │ PCI Endpoint │ │ PCI Host │ │ │ │ │ │ │ │ │◄──┤ 1.platform_msi_domain_alloc_irqs()│ │ │ │ │ │ │ │ │ │ MSI ├──►│ 2.write_msi_msg() ├──►├─BAR<n> │ │ Controller │ │ update doorbell register address│ │ │ │ │ │ for BAR │ │ │ │ │ │ │ │ 3. Write BAR<n>│ │ │◄──┼───────────────────────────────────┼───┤ │ │ │ │ │ │ │ │ ├──►│ 4.Irq Handle │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ └────────────┘ └───────────────────────────────────┘ └────────────────┘ This patches based on old https://lore.kernel.org/imx/20221124055036.1630573-1-Frank.Li@nxp.com/ Original patch only target to vntb driver. But actually it is common method. This patches add new API to pci-epf-core, so any EP driver can use it. Previous v2 discussion here. https://lore.kernel.org/imx/20230911220920.1817033-1-Frank.Li@nxp.com/ Changes in v15: - rebase to v6.14-rc1 - fix build issue find by kernel test robot - Link to v14: https://lore.kernel.org/r/20250207-ep-msi-v14-0-9671b136f2b8@nxp.com Changes in v14: Marc Zyngier raised concerns about adding DOMAIN_BUS_DEVICE_PCI_EP_MSI. As a result, the approach has been reverted to the v9 method. However, there are several improvements: MSI now supports msi-map in addition to msi-parent. - The struct device: id is used as the endpoint function (EPF) device identity to map to the stream ID (sideband information). - The EPC device tree source (DTS) utilizes msi-map to provide such information. - The EPF device's of_node is set to the EPC controller’s node. This approach is commonly used for multi-function device (MFD) platform child devices, allowing them to inherit properties from the MFD device’s DTS, such as reset-cells and gpio-cells. This method is well-suited for the current case, as the EPF is inherently created/binded to the EPC and should inherit the EPC’s DTS node properties. Additionally: Since the basic IMX95 LUT support has already been merged into the mainline, a DTS and driver increment patch is added to complete the solution. The patch is rebased onto the latest linux-next tree and aligned with the new pcitest framework. - Link to v13: https://lore.kernel.org/r/20241218-ep-msi-v13-0-646e2192dc24@nxp.com Changes in v13: - Change to use DOMAIN_BUS_PCI_DEVICE_EP_MSI - Change request id as func | vfunc << 3 - Remove IRQ_DOMAIN_MSI_IMMUTABLE Thomas Gleixner: I hope capture all your points in review comments. If missed, let me know. - Link to v12: https://lore.kernel.org/r/20241211-ep-msi-v12-0-33d4532fa520@nxp.com Changes in v12: - Change to use IRQ_DOMAIN_MSI_IMMUTABLE and add help function irq_domain_msi_is_immuatble(). - split PCI: endpoint: pci-ep-msi: Add MSI address/data pair mutable check to 3 patches - Link to v11: https://lore.kernel.org/r/20241209-ep-msi-v11-0-7434fa8397bd@nxp.com Changes in v11: - Change to use MSI_FLAG_MSG_IMMUTABLE - Link to v10: https://lore.kernel.org/r/20241204-ep-msi-v10-0-87c378dbcd6d@nxp.com Changes in v10: Thomas Gleixner: There are big change in pci-ep-msi.c. I am sure if go on the corrent path. The key improvement is remove only 1 function devices's limitation. I use new patch for imutable check, which relative additional feature compared to base enablement patch. - Remove patch Add msi_remove_device_irq_domain() in platform_device_msi_free_irqs_all() - Add new patch irqchip/gic-v3-its: Avoid overwriting msi_prepare callback if provided by msi_domain_info - Remove only support 1 endpoint function limiation. - Create one MSI domain for each endpoint function devices. - Use "msi-map" in pci ep controler node, instead of of msi-parent. first argument is (func_no << 8 | vfunc_no) - Link to v9: https://lore.kernel.org/r/20241203-ep-msi-v9-0-a60dbc3f15dd@nxp.com Changes in v9 - Add patch platform-msi: Add msi_remove_device_irq_domain() in platform_device_msi_free_irqs_all() - Remove patch PCI: endpoint: Add pci_epc_get_fn() API for customizable filtering - Remove API pci_epf_align_inbound_addr_lo_hi - Move doorbell_alloc in to doorbell_enable function. - Link to v8: https://lore.kernel.org/r/20241116-ep-msi-v8-0-6f1f68ffd1bb@nxp.com Changes in v8: - update helper function name to pci_epf_align_inbound_addr() - Link to v7: https://lore.kernel.org/r/20241114-ep-msi-v7-0-d4ac7aafbd2c@nxp.com Changes in v7: - Add helper function pci_epf_align_addr(); - Link to v6: https://lore.kernel.org/r/20241112-ep-msi-v6-0-45f9722e3c2a@nxp.com Changes in v6: - change doorbell_addr to doorbell_offset - use round_down() - add Niklas's test by tag - rebase to pci/endpoint - Link to v5: https://lore.kernel.org/r/20241108-ep-msi-v5-0-a14951c0d007@nxp.com Changes in v5: - Move request_irq to epf test function driver for more flexiable user case - Add fixed size bar handler - Some minor improvememtn to see each patches's changelog. - Link to v4: https://lore.kernel.org/r/20241031-ep-msi-v4-0-717da2d99b28@nxp.com Changes in v4: - Remove patch genirq/msi: Add cleanup guard define for msi_lock_descs()/msi_unlock_descs() - Use new method to avoid compatible problem. Add new command DOORBELL_ENABLE and DOORBELL_DISABLE. pcitest -B send DOORBELL_ENABLE first, EP test function driver try to remap one of BAR_N (except test register bar) to ITS MSI MMIO space. Old driver don't support new command, so failure return, not side effect. After test, DOORBELL_DISABLE command send out to recover original map, so pcitest bar test can pass as normal. - Other detail change see each patches's change log - Link to v3: https://lore.kernel.org/r/20241015-ep-msi-v3-0-cedc89a16c1a@nxp.com Change from v2 to v3 - Fixed manivannan's comments - Move common part to pci-ep-msi.c and pci-ep-msi.h - rebase to 6.12-rc1 - use RevID to distingiush old version mkdir /sys/kernel/config/pci_ep/functions/pci_epf_test/func1 echo 16 > /sys/kernel/config/pci_ep/functions/pci_epf_test/func1/msi_interrupts echo 0x080c > /sys/kernel/config/pci_ep/functions/pci_epf_test/func1/deviceid echo 0x1957 > /sys/kernel/config/pci_ep/functions/pci_epf_test/func1/vendorid echo 1 > /sys/kernel/config/pci_ep/functions/pci_epf_test/func1/revid ^^^^^^ to enable platform msi support. ln -s /sys/kernel/config/pci_ep/functions/pci_epf_test/func1 /sys/kernel/config/pci_ep/controllers/4c380000.pcie-ep - use new device ID, which identify support doorbell to avoid broken compatility. Enable doorbell support only for PCI_DEVICE_ID_IMX8_DB, while other devices keep the same behavior as before. EP side RC with old driver RC with new driver PCI_DEVICE_ID_IMX8_DB no probe doorbell enabled Other device ID doorbell disabled* doorbell disabled* * Behavior remains unchanged. Change from v1 to v2 - Add missed patch for endpont/pci-epf-test.c - Move alloc and free to epc driver from epf. - Provide general help function for EPC driver to alloc platform msi irq. - Fixed manivannan's comments. Signed-off-by: Frank Li <Frank.Li(a)nxp.com> --- Frank Li (15): platform-msi: Add msi_remove_device_irq_domain() in platform_device_msi_free_irqs_all() irqdomain: Add IRQ_DOMAIN_FLAG_MSI_IMMUTABLE and irq_domain_is_msi_immutable() irqchip/gic-v3-its: Set IRQ_DOMAIN_FLAG_MSI_IMMUTABLE for ITS irqchip/gic-v3-its: Add support for device tree msi-map and msi-mask PCI: endpoint: Set ID and of_node for function driver PCI: endpoint: Add RC-to-EP doorbell support using platform MSI controller PCI: endpoint: pci-ep-msi: Add MSI address/data pair mutable check PCI: endpoint: Add pci_epf_align_inbound_addr() helper for address alignment PCI: endpoint: pci-epf-test: Add doorbell test support misc: pci_endpoint_test: Add doorbell test case selftests: pci_endpoint: Add doorbell test case pci: imx6: Add helper function imx_pcie_add_lut_by_rid() pci: imx6: Add LUT setting for MSI/IOMMU in Endpoint mode arm64: dts: imx95: Add msi-map for pci-ep device arm64: dts: imx95-19x19-evk: Add PCIe1 endpoint function overlay file arch/arm64/boot/dts/freescale/Makefile | 3 + .../dts/freescale/imx95-19x19-evk-pcie1-ep.dtso | 21 ++++ arch/arm64/boot/dts/freescale/imx95.dtsi | 1 + drivers/base/platform-msi.c | 1 + drivers/irqchip/irq-gic-v3-its-msi-parent.c | 8 ++ drivers/irqchip/irq-gic-v3-its.c | 2 +- drivers/misc/pci_endpoint_test.c | 81 +++++++++++++ drivers/pci/controller/dwc/pci-imx6.c | 25 ++-- drivers/pci/endpoint/Makefile | 1 + drivers/pci/endpoint/functions/pci-epf-test.c | 132 +++++++++++++++++++++ drivers/pci/endpoint/pci-ep-msi.c | 90 ++++++++++++++ drivers/pci/endpoint/pci-epf-core.c | 48 ++++++++ include/linux/irqdomain.h | 7 ++ include/linux/pci-ep-msi.h | 28 +++++ include/linux/pci-epf.h | 21 ++++ include/uapi/linux/pcitest.h | 1 + .../selftests/pci_endpoint/pci_endpoint_test.c | 25 ++++ 17 files changed, 486 insertions(+), 9 deletions(-) --- base-commit: 2014c95afecee3e76ca4a56956a936e23283f05b change-id: 20241010-ep-msi-8b4cab33b1be Best regards, --- Frank Li <Frank.Li(a)nxp.com>

4 months

4
28
0 0

[PATCH v3 net 0/8] eth: bnxt: fix several bugs in the bnxt module

by Taehee Yoo

The first fixes setting incorrect skb->truesize. When xdp-mb prog returns XDP_PASS, skb is allocated and initialized. Currently, The truesize is calculated as BNXT_RX_PAGE_SIZE * sinfo->nr_frags, but sinfo->nr_frags is flushed by napi_build_skb(). So, it stores sinfo before calling napi_build_skb() and then use it for calculate truesize. The second fixes kernel panic in the bnxt_queue_mem_alloc(). The bnxt_queue_mem_alloc() accesses rx ring descriptor. rx ring descriptors are allocated when the interface is up and it's freed when the interface is down. So, if bnxt_queue_mem_alloc() is called when the interface is down, kernel panic occurs. This patch makes the bnxt_queue_mem_alloc() return -ENETDOWN if rx ring descriptors are not allocated. The third patch fixes kernel panic in the bnxt_queue_{start | stop}(). When a queue is restarted bnxt_queue_{start | stop}() are called. These functions set MRU to 0 to stop packet flow and then to set up the remaining things. MRU variable is a member of vnic_info[] the first vnic_info is for default and the second is for ntuple. The first vnic_info is always allocated when interface is up, but the second is allocated only when ntuple is enabled. (ethtool -K eth0 ntuple <on | off>). Currently, the bnxt_queue_{start | stop}() access vnic_info[BNXT_VNIC_NTUPLE] regardless of whether ntuple is enabled or not. So kernel panic occurs. This patch make the bnxt_queue_{start | stop}() use bp->nr_vnics instead of BNXT_VNIC_NTUPLE. The fourth patch fixes a warning due to checksum state. The bnxt_rx_pkt() checks whether skb->ip_summed is not CHECKSUM_NONE before updating ip_summed. if ip_summed is not CHECKSUM_NONE, it WARNS about it. However, the bnxt_xdp_build_skb() is called in XDP-MB-PASS path and it updates ip_summed earlier than bnxt_rx_pkt(). So, in the XDP-MB-PASS path, the bnxt_rx_pkt() always warns about checksum. Updating ip_summed at the bnxt_xdp_build_skb() is unnecessary and duplicate, so it is removed. The fifth patch fixes a kernel panic in the bnxt_get_queue_stats{rx | tx}(). The bnxt_get_queue_stats{rx | tx}() callback functions are called when a queue is resetting. These internally access rx and tx rings without null check, but rings are allocated and initialized when the interface is up. So, these functions are called when the interface is down, it occurs a kernel panic. The sixth patch fixes memory leak in queue reset logic. When a queue is resetting, tpa_info is allocated for the new queue and tpa_info for an old queue is not used anymore. So it should be freed, but not. The seventh patch makes net_devmem_unbind_dmabuf() ignore -ENETDOWN. When devmem socket is closed, net_devmem_unbind_dmabuf() is called to unbind/release resources. If interface is down, the driver returns -ENETDOWN. The -ENETDOWN return value is not an actual error, because the interface will release resources when the interface is down. So, net_devmem_unbind_dmabuf() needs to ignore -ENETDOWN. The last patch adds XDP testcases to tools/testing/selftests/drivers/net/ping.py. v3: - Copy nr_frags instead of full copy. (1/8) - Add Review tags from Somnath. (3/8) - Add new patch for fixing kernel panic in the bnxt_get_queue_stats{rx | tx}(). (5/8) - Add new patch for fixing memory leak in queue reset. (6/8) v2: - Do not use num_frags in the bnxt_xdp_build_skb(). (1/6) - Add Review tags from Somnath and Jakub. (2/6) - Add new patch for fixing checksum warning. (4/6) - Add new patch for fixing warning in net_devmem_unbind_dmabuf(). (5/6) - Add new XDP testcases to ping.py (6/6) Taehee Yoo (8): eth: bnxt: fix truesize for mb-xdp-pass case eth: bnxt: return fail if interface is down in bnxt_queue_mem_alloc() eth: bnxt: do not use BNXT_VNIC_NTUPLE unconditionally in queue restart logic eth: bnxt: do not update checksum in bnxt_xdp_build_skb() eth: bnxt: fix kernel panic in the bnxt_get_queue_stats{rx | tx} eth: bnxt: fix memory leak in queue reset net: devmem: do not WARN conditionally after netdev_rx_queue_restart() selftests: drv-net: add xdp cases for ping.py drivers/net/ethernet/broadcom/bnxt/bnxt.c | 25 ++- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 13 +- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h | 3 +- net/core/devmem.c | 4 +- tools/testing/selftests/drivers/net/ping.py | 200 ++++++++++++++++-- .../testing/selftests/net/lib/xdp_dummy.bpf.c | 6 + 6 files changed, 220 insertions(+), 31 deletions(-) -- 2.34.1

4 months

5
15
0 0

[PATCH v6 bpf-next 0/2] security: Propagate caller information in bpf hooks

by Blaise Boscaccy

Hello, While trying to implement an eBPF gatekeeper program, we ran into an issue whereas the LSM hooks are missing some relevant data. Certain subcommands passed to the bpf() syscall can be invoked from either the kernel or userspace. Additionally, some fields in the bpf_attr struct contain pointers, and depending on where the subcommand was invoked, they could point to either user or kernel memory. One example of this is the bpf_prog_load subcommand and its fd_array. This data is made available and used by the verifier but not made available to the LSM subsystem. This patchset simply exposes that information to applicable LSM hooks. Change list: - v5 -> v6 - fix regression caused by is_kernel renaming - simplify test logic - v4 -> v5 - merge v4 selftest breakout patch back into a single patch - change "is_kernel" to "kernel" - add selftest using new kernel flag - v3 -> v4 - split out selftest changes into a separate patch - v2 -> v3 - reorder params so that the new boolean flag is the last param - fixup function signatures in bpf selftests - v1 -> v2 - Pass a boolean flag in lieu of bpfptr_t Revisions: - v5 https://lore.kernel.org/bpf/20250307213651.3065714-1-bboscaccy@linux.micros… - v4 https://lore.kernel.org/bpf/20250304203123.3935371-1-bboscaccy@linux.micros… - v3 https://lore.kernel.org/bpf/20250303222416.3909228-1-bboscaccy@linux.micros… - v2 https://lore.kernel.org/bpf/20250228165322.3121535-1-bboscaccy@linux.micros… - v1 https://lore.kernel.org/bpf/20250226003055.1654837-1-bboscaccy@linux.micros… Blaise Boscaccy (2): security: Propagate caller information in bpf hooks selftests/bpf: Add a kernel flag test for LSM bpf hook include/linux/lsm_hook_defs.h | 6 +-- include/linux/security.h | 12 +++--- kernel/bpf/syscall.c | 10 ++--- security/security.c | 15 ++++--- security/selinux/hooks.c | 6 +-- .../selftests/bpf/prog_tests/kernel_flag.c | 43 +++++++++++++++++++ .../selftests/bpf/progs/rcu_read_lock.c | 3 +- .../bpf/progs/test_cgroup1_hierarchy.c | 4 +- .../selftests/bpf/progs/test_kernel_flag.c | 28 ++++++++++++ .../bpf/progs/test_kfunc_dynptr_param.c | 6 +-- .../selftests/bpf/progs/test_lookup_key.c | 2 +- .../selftests/bpf/progs/test_ptr_untrusted.c | 2 +- .../bpf/progs/test_task_under_cgroup.c | 2 +- .../bpf/progs/test_verify_pkcs7_sig.c | 2 +- 14 files changed, 108 insertions(+), 33 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/kernel_flag.c create mode 100644 tools/testing/selftests/bpf/progs/test_kernel_flag.c -- 2.48.1

4 months

3
8
0 0

[PATCH 6.1.y] KVM: selftests: Fix build error due to assert in dirty_log_test

by Andrey Kalachev

Hi all. Please apply that forgotten patch to fix v6.1 KVM selftests broken build. Origin of the patch can be founded here [1] Regards, AK [1] https://lore.kernel.org/stable/20240403164230.1722018-1-rananta@google.com/ -- 2.30.2

4 months

1
1
0 0

[PATCH] mm/huge_memory: drop beyond-EOF folios with the right number of refs.

by Zi Yan

When an after-split folio is large and needs to be dropped due to EOF, folio_put_refs(folio, folio_nr_pages(folio)) should be used to drop all page cache refs. Otherwise, the folio will not be freed, causing memory leak. This leak would happen on a filesystem with blocksize > page_size and a truncate is performed, where the blocksize makes folios split to >0 order ones, causing truncated folios not being freed. Fixes: c010d47f107f ("mm: thp: split huge page to any lower order pages") Reported-by: Hugh Dickins <hughd(a)google.com> Closes: https://lore.kernel.org/all/fcbadb7f-dd3e-21df-f9a7-2853b53183c4@google.com/ Cc: stable(a)vger.kernel.org Signed-off-by: Zi Yan <ziy(a)nvidia.com> --- mm/huge_memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 3d3ebdc002d5..373781b21e5c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3304,7 +3304,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, folio_account_cleaned(tail, inode_to_wb(folio->mapping->host)); __filemap_remove_folio(tail, NULL); - folio_put(tail); + folio_put_refs(tail, folio_nr_pages(tail)); } else if (!folio_test_anon(folio)) { __xa_store(&folio->mapping->i_pages, tail->index, tail, 0); -- 2.47.2

4 months

1
0
0 0

[PATCH v9 0/8] Buddy allocator like (or non-uniform) folio split

by Zi Yan

Hi all, This patchset adds a new buddy allocator like (or non-uniform) large folio split from a order-n folio to order-m with m < n. It reduces 1. the total number of after-split folios from 2^(n-m) to n-m+1; 2. the amount of memory needed for multi-index xarray split from 2^(n/6-m/6) to n/6-m/6, assuming XA_CHUNK_SHIFT=6; 3. keep more large folios after a split from all order-m folios to order-(n-1) to order-m folios. For example, to split an order-9 to order-0, folio split generates 10 (or 11 for anonymous memory) folios instead of 512, allocates 1 xa_node instead of 8, and leaves 1 order-8, 1 order-7, ..., 1 order-1 and 2 order-0 folios (or 4 order-0 for anonymous memory) instead of 512 order-0 folios. Instead of duplicating existing split_huge_page*() code, __folio_split() is introduced as the shared backend code for both split_huge_page_to_list_to_order() and folio_split(). __folio_split() can support both uniform split and buddy allocator like (or non-uniform) split. All existing split_huge_page*() users can be gradually converted to use folio_split() if possible. In this patchset, I converted truncate_inode_partial_folio() to use folio_split(). xfstests quick group passed for both tmpfs and xfs. It is on top of mm-everything-2025-02-26-03-56 with V8 reverted. It is ready to be merged. Changelog === From V8[11]: 1. Removed gfp parameter from xas_try_split() and GFP_NOWAIT is used all the time. (per Baolin Wang) 2. Used __xas_init_node_for_split() instead of __xas_alloc_node_for_split() and moved node allocation out. It fixed a bug when xa_node is pre-allocated by xas_nomem() before xas_try_split() is called without being initialized for split. From V7[9]: 1. Fixed a wrong function name in lib/test_xarray.c. 2. Made __split_folio_to_order() never fail, since the old order check is already done in __folio_split(). (per David Hildenbrand) 3. Fixed an issue reported by syzbot[10] by not dropping the original folio during truncate. 4. Fixed a WARNING when READ_ONLY_THP_FOR_FS is enabled. (Thank David Hildenbrand for reporting the issue) 5. Used two separate struct page* parameters, split_at and lock_at, to specify at which subpage the non-uniform split happens and which subpage to keep locked after the split, respectively. It improves code readability. From V6[8]: 1. Added an xarray function xas_try_split() to support iterative folio split, removing the need of using xas_split_alloc() and xas_split(). The function guarantees that at most one xa_node is allocated for each call. 2. Added concrete numbers of after-split folios and xa_node savings to cover letter, commit log. (per Andrew) From V5[7]: 1. Split shmem to any lower order patches are in mm tree, so dropped from this series. 2. Rename split_folio_at() to try_folio_split() to clarify that non-uniform split will not be used if it is not supported. From V4[6]: 1. Enabled shmem support in both uniform and buddy allocator like split and added selftests for it. 2. Added functions to check if uniform split and buddy allocator like split are supported for the given folio and order. 3. Made truncate fall back to uniform split if buddy allocator split is not supported (CONFIG_READ_ONLY_THP_FOR_FS and FS without large folio). 4. Added the missing folio_clear_has_hwpoisoned() to __split_unmapped_folio(). From V3[5]: 1. Used xas_split_alloc(GFP_NOWAIT) instead of xas_nomem(), since extra operations inside xas_split_alloc() are needed for correctness. 2. Enabled folio_split() for shmem and no issue was found with xfstests quick test group. 3. Split both ends of a truncate range in truncate_inode_partial_folio() to avoid wasting memory in shmem truncate (per David Hildenbrand). 4. Removed page_in_folio_offset() since page_folio() does the same thing. 5. Finished truncate related tests from xfstests quick test group on XFS and tmpfs without issues. 6. Disabled buddy allocator like split on CONFIG_READ_ONLY_THP_FOR_FS and FS without large folio. This check was missed in the prior versions. From V2[3]: 1. Incorporated all the feedback from Kirill[4]. 2. Used GFP_NOWAIT for xas_nomem(). 3. Tested the code path when xas_nomem() fails. 4. Added selftests for folio_split(). 5. Fixed no THP config build error. From V1[2]: 1. Split the original patch 1 into multiple ones for easy review (per Kirill). 2. Added xas_destroy() to avoid memory leak. 3. Fixed nr_dropped not used error (per kernel test robot). 4. Added proper error handling when xas_nomem() fails to allocate memory for xas_split() during buddy allocator like split. From RFC[1]: 1. Merged backend code of split_huge_page_to_list_to_order() and folio_split(). The same code is used for both uniform split and buddy allocator like split. 2. Use xas_nomem() instead of xas_split_alloc() for folio_split(). 3. folio_split() now leaves the first after-split folio unlocked, instead of the one containing the given page, since the caller of truncate_inode_partial_folio() locks and unlocks the first folio. 4. Extended split_huge_page debugfs to use folio_split(). 5. Added truncate_inode_partial_folio() as first user of folio_split(). Design === folio_split() splits a large folio in the same way as buddy allocator splits a large free page for allocation. The purpose is to minimize the number of folios after the split. For example, if user wants to free the 3rd subpage in a order-9 folio, folio_split() will split the order-9 folio as: O-0, O-0, O-0, O-0, O-2, O-3, O-4, O-5, O-6, O-7, O-8 if it is anon O-1, O-0, O-0, O-2, O-3, O-4, O-5, O-6, O-7, O-9 if it is pagecache Since anon folio does not support order-1 yet. The split process is similar to existing approach: 1. Unmap all page mappings (split PMD mappings if exist); 2. Split meta data like memcg, page owner, page alloc tag; 3. Copy meta data in struct folio to sub pages, but instead of spliting the whole folio into multiple smaller ones with the same order in a shot, this approach splits the folio iteratively. Taking the example above, this approach first splits the original order-9 into two order-8, then splits left part of order-8 to two order-7 and so on; 4. Post-process split folios, like write mapping->i_pages for pagecache, adjust folio refcounts, add split folios to corresponding list; 5. Remap split folios 6. Unlock split folios. __split_unmapped_folio() and __split_folio_to_order() replace __split_huge_page() and __split_huge_page_tail() respectively. __split_unmapped_folio() uses different approaches to perform uniform split and buddy allocator like split: 1. uniform split: one single call to __split_folio_to_order() is used to uniformly split the given folio. All resulting folios are put back to the list after split. The folio containing the given page is left to caller to unlock and others are unlocked. 2. buddy allocator like (or non-uniform) split: (old_order - new_order) calls to __split_folio_to_order() are used to split the given folio at order N to order N-1. After each call, the target folio is changed to the one containing the page, which is given as a folio_split() parameter. After each call, folios not containing the page are put back to the list. The folio containing the page is put back to the list when its order is new_order. All folios are unlocked except the first folio, which is left to caller to unlock. Patch Overview === 1. Patch 1 added a new xarray function xas_try_split() to perform iterative xarray split. 2. Patch 2 added __split_unmapped_folio() and __split_folio_to_order() to prepare for moving to new backend split code. 3. Patch 3 moved common code in split_huge_page_to_list_to_order() to __folio_split(). 4. Patch 4 added new folio_split() and made split_huge_page_to_list_to_order() share the new __split_unmapped_folio() with folio_split(). 5. Patch 5 removed no longer used __split_huge_page() and __split_huge_page_tail(). 6. Patch 6 added a new in_folio_offset to split_huge_page debugfs for folio_split() test. 7. Patch 7 used try_folio_split() for truncate operation. 8. Patch 8 added folio_split() tests. Any comments and/or suggestions are welcome. Thanks. [1] https://lore.kernel.org/linux-mm/20241008223748.555845-1-ziy@nvidia.com/ [2] https://lore.kernel.org/linux-mm/20241028180932.1319265-1-ziy@nvidia.com/ [3] https://lore.kernel.org/linux-mm/20241101150357.1752726-1-ziy@nvidia.com/ [4] https://lore.kernel.org/linux-mm/e6ppwz5t4p4kvir6eqzoto4y5fmdjdxdyvxvtw43nc… [5] https://lore.kernel.org/linux-mm/20241205001839.2582020-1-ziy@nvidia.com/ [6] https://lore.kernel.org/linux-mm/20250106165513.104899-1-ziy@nvidia.com/ [7] https://lore.kernel.org/linux-mm/20250116211042.741543-1-ziy@nvidia.com/ [8] https://lore.kernel.org/linux-mm/20250205031417.1771278-1-ziy@nvidia.com/ [9] https://lore.kernel.org/linux-mm/20250211155034.268962-1-ziy@nvidia.com/ [10] https://lore.kernel.org/all/67af65cb.050a0220.21dd3.004a.GAE@google.com/ [11] https://lore.kernel.org/linux-mm/20250218235012.1542225-1-ziy@nvidia.com/ Zi Yan (8): xarray: add xas_try_split() to split a multi-index entry mm/huge_memory: add two new (not yet used) functions for folio_split() mm/huge_memory: move folio split common code to __folio_split() mm/huge_memory: add buddy allocator like (non-uniform) folio_split() mm/huge_memory: remove the old, unused __split_huge_page() mm/huge_memory: add folio_split() to debugfs testing interface mm/truncate: use buddy allocator like folio split for truncate operation selftests/mm: add tests for folio_split(), buddy allocator like split Documentation/core-api/xarray.rst | 14 +- include/linux/huge_mm.h | 36 + include/linux/xarray.h | 6 + lib/test_xarray.c | 52 ++ lib/xarray.c | 131 ++- mm/huge_memory.c | 755 ++++++++++++------ mm/truncate.c | 31 +- tools/testing/radix-tree/Makefile | 1 + .../selftests/mm/split_huge_page_test.c | 34 +- 9 files changed, 783 insertions(+), 277 deletions(-) -- 2.47.2

4 months

5
30
0 0

[PATCH bpf-next v2 0/3] bpf: Fix use-after-free of sockmap

by Jiayuan Chen

1. Issue Syzkaller reported this issue [1]. 2. Reproduce We can reproduce this issue by using the test_sockmap_with_close_on_write() test I provided in selftest, also you need to apply the following patch to ensure 100% reproducibility (sleep after checking sock): ''' static void sk_psock_verdict_data_ready(struct sock *sk) { ....... if (unlikely(!sock)) return; + if (!strcmp("test_progs", current->comm)) { + printk("sleep 2s to wait socket freed\n"); + mdelay(2000); + printk("sleep end\n"); + } ops = READ_ONCE(sock->ops); if (!ops || !ops->read_skb) return; } ''' Then running './test_progs -v sockmap_basic', and if the kernel has KASAN enabled [2], you will see the following warning: ''' BUG: KASAN: slab-use-after-free in sk_psock_verdict_data_ready+0x29b/0x2d0 Read of size 8 at addr ffff88813a777020 by task test_progs/47055 Tainted: [O]=OOT_MODULE Call Trace: <TASK> dump_stack_lvl+0x53/0x70 print_address_description.constprop.0+0x30/0x420 ? sk_psock_verdict_data_ready+0x29b/0x2d0 print_report+0xb7/0x270 ? sk_psock_verdict_data_ready+0x29b/0x2d0 ? kasan_addr_to_slab+0xd/0xa0 ? sk_psock_verdict_data_ready+0x29b/0x2d0 kasan_report+0xca/0x100 ? sk_psock_verdict_data_ready+0x29b/0x2d0 sk_psock_verdict_data_ready+0x29b/0x2d0 unix_stream_sendmsg+0x4a6/0xa40 ? __pfx_unix_stream_sendmsg+0x10/0x10 ? fdget+0x2c1/0x3a0 __sys_sendto+0x39c/0x410 ''' 3. Reason ''' CPU0 CPU1 unix_stream_sendmsg(sk): other = unix_peer(sk) other->sk_data_ready(other): socket *sock = sk->sk_socket if (unlikely(!sock)) return; close(other): ... other->close() free(socket) READ_ONCE(sock->ops) ^ use 'sock' after free ''' For TCP, UDP, or other protocols, we have already performed rcu_read_lock() when the network stack receives packets in ip_input.c: ''' ip_local_deliver_finish(): rcu_read_lock() ip_protocol_deliver_rcu() xxx_rcv rcu_read_unlock() ''' However, for Unix sockets, sk_data_ready is called directly from the process context without rcu_read_lock() protection. 4. Solution Based on the fact that the 'struct socket' is released using call_rcu(), We add rcu_read_{un}lock() at the entrance and exit of our sk_data_ready. It will not increase performance overhead, at least for TCP and UDP, they are already in a relatively large critical section. Of course, we can also add a custom callback for Unix sockets and call rcu_read_lock() before calling _verdict_data_ready like this: ''' if (sk_is_unix(sk)) sk->sk_data_ready = sk_psock_verdict_data_ready_rcu; else sk->sk_data_ready = sk_psock_verdict_data_ready; sk_psock_verdict_data_ready_rcu(): rcu_read_lock() sk_psock_verdict_data_ready() rcu_read_unlock() ''' However, this will cause too many branches, and it's not suitable to distinguish network protocols in skmsg.c. [1] https://syzkaller.appspot.com/bug?extid=dd90a702f518e0eac072 [2] https://syzkaller.appspot.com/text?tag=KernelConfig&x=1362a5aee630ff34 --- v1 -> v2: 1. Add Fixes tag. 2. Extend selftest of edge case for TCP/UDP sockets. 3. Add Reviewed-by and Acked-by tag. https://lore.kernel.org/bpf/20250226132242.52663-1-jiayuan.chen@linux.dev/T… Jiayuan Chen (3): bpf, sockmap: avoid using sk_socket after free selftests/bpf: Add socketpair to create_pair to support unix socket selftests/bpf: Add edge case tests for sockmap net/core/skmsg.c | 18 ++++-- .../selftests/bpf/prog_tests/socket_helpers.h | 13 +++- .../selftests/bpf/prog_tests/sockmap_basic.c | 59 +++++++++++++++++++ 3 files changed, 84 insertions(+), 6 deletions(-) -- 2.47.1

4 months

2
7
0 0

[PATCH bpf-next v12 0/5] xsk: TX metadata Launch Time support

by Song Yoong Siang

This series expands the XDP TX metadata framework to allow user applications to pass per packet 64-bit launch time directly to the kernel driver, requesting launch time hardware offload support. The XDP TX metadata framework will not perform any clock conversion or packet reordering. Please note that the role of Tx metadata is just to pass the launch time, not to enable the offload feature. Users will need to enable the launch time hardware offload feature of the device by using the respective command, such as the tc-etf command. Although some devices use the tc-etf command to enable their launch time hardware offload feature, xsk packets will not go through the etf qdisc. Therefore, in my opinion, the launch time should always be based on the PTP Hardware Clock (PHC). Thus, i did not include a clock ID to indicate the clock source. To simplify the test steps, I modified the xdp_hw_metadata bpf self-test tool in such a way that it will set the launch time based on the offset provided by the user and the value of the Receive Hardware Timestamp, which is against the PHC. This will eliminate the need to discipline System Clock with the PHC and then use clock_gettime() to get the time. Please note that AF_XDP lacks a feedback mechanism to inform the application if the requested launch time is invalid. So, users are expected to familiar with the horizon of the launch time of the device they use and not request a launch time that is beyond the horizon. Otherwise, the driver might interpret the launch time incorrectly and react wrongly. For stmmac and igc, where modulo computation is used, a launch time larger than the horizon will cause the device to transmit the packet earlier that the requested launch time. Although there is no feedback mechanism for the launch time request for now, user still can check whether the requested launch time is working or not, by requesting the Transmit Completion Hardware Timestamp. v12: - Fix the comment in include/uapi/linux/if_xdp.h to allign with what is generated by ./tools/net/ynl/ynl-regen.sh to avoid dirty tree error in the netdev/ynl checks. v11: https://lore.kernel.org/netdev/20250216074302.956937-1-yoong.siang.song@int… - regenerate netdev_xsk_flags based on latest netdev.yaml (Jakub) v10: https://lore.kernel.org/netdev/20250207021943.814768-1-yoong.siang.song@int… - use net_err_ratelimited(), instead of net_ratelimit() (Maciej) - accumulate the amount of used descs in local variable and update the igc_metadata_request::used_desc once (Maciej) - Ensure reverse christmas tree rule (Maciej) V9: https://lore.kernel.org/netdev/20250206060408.808325-1-yoong.siang.song@int… - Remove the igc_desc_unused() checking (Maciej) - Ensure that skb allocation and DMA mapping work before proceeding to fill in igc_tx_buffer info, context desc, and data desc (Maciej) - Rate limit the error messages (Maciej) - Update the comment to indicate that the 2 descriptors needed by the empty frame are already taken into consideration (Maciej) - Handle the case where the insertion of an empty frame fails and explain the reason behind (Maciej) - put self SOB tag as last tag (Maciej) V8: https://lore.kernel.org/netdev/20250205024116.798862-1-yoong.siang.song@int… - check the number of used descriptor in xsk_tx_metadata_request() by using used_desc of struct igc_metadata_request, and then decreases the budget with it (Maciej) - submit another bug fix patch to set the buffer type for empty frame (Maciej): https://lore.kernel.org/netdev/20250205023603.798819-1-yoong.siang.song@int… V7: https://lore.kernel.org/netdev/20250204004907.789330-1-yoong.siang.song@int… - split the refactoring code of igc empty packet insertion into a separate commit (Faizal) - add explanation on why the value "4" is used as igc transmit budget (Faizal) - perform a stress test by sending 1000 packets with 10ms interval and launch time set to 500us in the future (Faizal & Yong Liang) V6: https://lore.kernel.org/netdev/20250116155350.555374-1-yoong.siang.song@int… - fix selftest build errors by using asprintf() and realloc(), instead of managing the buffer sizes manually (Daniel, Stanislav) V5: https://lore.kernel.org/netdev/20250114152718.120588-1-yoong.siang.song@int… - change netdev feature name from tx-launch-time to tx-launch-time-fifo to explicitly state the FIFO behaviour (Stanislav) - improve the looping of xdp_hw_metadata app to wait for packet tx completion to be more readable by using clock_gettime() (Stanislav) - add launch time setup steps into xdp_hw_metadata app (Stanislav) V4: https://lore.kernel.org/netdev/20250106135506.9687-1-yoong.siang.song@intel… - added XDP launch time support to the igc driver (Jesper & Florian) - added per-driver launch time limitation on xsk-tx-metadata.rst (Jesper) - added explanation on FIFO behavior on xsk-tx-metadata.rst (Jakub) - added step to enable launch time in the commit message (Jesper & Willem) - explicitly documented the type of launch_time and which clock source it is against (Willem) V3: https://lore.kernel.org/netdev/20231203165129.1740512-1-yoong.siang.song@in… - renamed to use launch time (Jesper & Willem) - changed the default launch time in xdp_hw_metadata apps from 1s to 0.1s because some NICs do not support such a large future time. V2: https://lore.kernel.org/netdev/20231201062421.1074768-1-yoong.siang.song@in… - renamed to use Earliest TxTime First (Willem) - renamed to use txtime (Willem) V1: https://lore.kernel.org/netdev/20231130162028.852006-1-yoong.siang.song@int… Song Yoong Siang (5): xsk: Add launch time hardware offload support to XDP Tx metadata selftests/bpf: Add launch time request to xdp_hw_metadata net: stmmac: Add launch time support to XDP ZC igc: Refactor empty frame insertion for launch time support igc: Add launch time support to XDP ZC Documentation/netlink/specs/netdev.yaml | 4 + Documentation/networking/xsk-tx-metadata.rst | 62 +++++++ drivers/net/ethernet/intel/igc/igc.h | 1 + drivers/net/ethernet/intel/igc/igc_main.c | 143 +++++++++++---- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 2 + .../net/ethernet/stmicro/stmmac/stmmac_main.c | 13 ++ include/net/xdp_sock.h | 10 ++ include/net/xdp_sock_drv.h | 1 + include/uapi/linux/if_xdp.h | 10 ++ include/uapi/linux/netdev.h | 3 + net/core/netdev-genl.c | 2 + net/xdp/xsk.c | 3 + tools/include/uapi/linux/if_xdp.h | 10 ++ tools/include/uapi/linux/netdev.h | 3 + tools/testing/selftests/bpf/xdp_hw_metadata.c | 168 +++++++++++++++++- 15 files changed, 396 insertions(+), 39 deletions(-) -- 2.34.1

4 months

5
10
0 0

[PATCH net-next 3/4] tools/testing/selftests/cgroup/cgroup_util: add cg_get_id helper

by Alexander Mikhalitsyn

Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Cc: netdev(a)vger.kernel.org Cc: cgroups(a)vger.kernel.org Cc: "David S. Miller" <davem(a)davemloft.net> Cc: Eric Dumazet <edumazet(a)google.com> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Paolo Abeni <pabeni(a)redhat.com> Cc: Willem de Bruijn <willemb(a)google.com> Cc: Leon Romanovsky <leon(a)kernel.org> Cc: Arnd Bergmann <arnd(a)arndb.de> Cc: Christian Brauner <brauner(a)kernel.org> Cc: Kuniyuki Iwashima <kuniyu(a)amazon.com> Cc: Lennart Poettering <mzxreary(a)0pointer.de> Cc: Luca Boccassi <bluca(a)debian.org> Cc: Tejun Heo <tj(a)kernel.org> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: "Michal Koutný" <mkoutny(a)suse.com> Cc: Shuah Khan <shuah(a)kernel.org> Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn(a)canonical.com> --- tools/testing/selftests/cgroup/cgroup_util.c | 15 +++++++++++++++ tools/testing/selftests/cgroup/cgroup_util.h | 2 ++ 2 files changed, 17 insertions(+) diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c index 1e2d46636a0c..b60e0e1433f4 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.c +++ b/tools/testing/selftests/cgroup/cgroup_util.c @@ -205,6 +205,21 @@ int cg_open(const char *cgroup, const char *control, int flags) return open(path, flags); } +/* + * Returns cgroup id on success, or -1 on failure. + */ +uint64_t cg_get_id(const char *cgroup) +{ + struct stat st; + int ret; + + ret = stat(cgroup, &st); + if (ret) + return -1; + + return st.st_ino; +} + int cg_write_numeric(const char *cgroup, const char *control, long value) { char buf[64]; diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h index 19b131ee7707..3f2d9676ceda 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.h +++ b/tools/testing/selftests/cgroup/cgroup_util.h @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <stdbool.h> +#include <stdint.h> #include <stdlib.h> #include "../kselftest.h" @@ -39,6 +40,7 @@ long cg_read_key_long(const char *cgroup, const char *control, const char *key); extern long cg_read_lc(const char *cgroup, const char *control); extern int cg_write(const char *cgroup, const char *control, char *buf); extern int cg_open(const char *cgroup, const char *control, int flags); +extern uint64_t cg_get_id(const char *cgroup); int cg_write_numeric(const char *cgroup, const char *control, long value); extern int cg_run(const char *cgroup, int (*fn)(const char *cgroup, void *arg), -- 2.43.0

4 months

1
0
0 0

🎁 Yes, a Truly Free SEO Cleanup Awaits!

by Free Backlinks Clean up

Hi there, I understand the skepticism—“free” offers often come with strings attached. But we’re genuinely committed to supporting webmasters and giving back to the community with no hidden catches. Simply fill out the form, and our team will deliver a comprehensive SEO cleanup within a day—no cost, no commitments. Get Your Free SEO Cleanup Here: https://www.1free-seo.com/get-started/ (https://www.1free-seo.com/get-started/) Cheers, Mike Larson WhatsApp: +1 (833) 854-6783 (https://wa.me/18338546783) Telegram: https://t.me/freeseosupport (https://t.me/freeseosupport) Book appointment: https://1free-seo.com/free-seo-consultaition/ (https://1free-seo.com/free-seo-consultaition/) Unsubscribe (https://clicks.1free-seo.com/?na=u&nk=2080001-9a11fc6fe9&nek=24-) | Manage your subscription (https://clicks.1free-seo.com/?na=p&nk=2080001-9a11fc6fe9&nek=24-) | View online (https://clicks.1free-seo.com/?na=v&nk=2080001-9a11fc6fe9&id=24)

4 months

1
0
0 0

[PATCH v3 0/2] scanf: convert self-test to KUnit

by Tamir Duberstein

This is one of just 3 remaining "Test Module" kselftests (the others being bitmap and printf), the rest having been converted to KUnit. In addition to the enclosed patch, please consider this an RFC on the removal of the "Test Module" kselftest machinery. I tested this using: $ tools/testing/kunit/kunit.py run --arch arm64 --make_options LLVM=1 scanf Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- Changes in v3: - Reduce diff noise in lib/Makefile. (Petr Mladek) - Split `scanf_test` into a few test cases. New output: : =================== scanf (10 subtests) ==================== : [PASSED] numbers_simple : ====================== numbers_list ======================= : [PASSED] delim=" " : [PASSED] delim=":" : [PASSED] delim="," : [PASSED] delim="-" : [PASSED] delim="/" : ================== [PASSED] numbers_list =================== : ============ numbers_list_field_width_typemax ============= : [PASSED] delim=" " : [PASSED] delim=":" : [PASSED] delim="," : [PASSED] delim="-" : [PASSED] delim="/" : ======== [PASSED] numbers_list_field_width_typemax ========= : =========== numbers_list_field_width_val_width ============ : [PASSED] delim=" " : [PASSED] delim=":" : [PASSED] delim="," : [PASSED] delim="-" : [PASSED] delim="/" : ======= [PASSED] numbers_list_field_width_val_width ======== : [PASSED] numbers_slice : [PASSED] numbers_prefix_overflow : [PASSED] test_simple_strtoull : [PASSED] test_simple_strtoll : [PASSED] test_simple_strtoul : [PASSED] test_simple_strtol : ====================== [PASSED] scanf ====================== : ============================================================ : Testing complete. Ran 22 tests: passed: 22 : Elapsed time: 5.517s total, 0.001s configuring, 5.440s building, 0.067s running - Link to v2: https://lore.kernel.org/r/20250203-scanf-kunit-convert-v2-1-277a618d804e@gm… Changes in v2: - Rename lib/{test_scanf.c => scanf_kunit.c}. (Andy Shevchenko) - Link to v1: https://lore.kernel.org/r/20250131-scanf-kunit-convert-v1-1-0976524f0eba@gm… --- Tamir Duberstein (2): scanf: convert self-test to KUnit scanf: break kunit into test cases MAINTAINERS | 2 +- arch/m68k/configs/amiga_defconfig | 1 - arch/m68k/configs/apollo_defconfig | 1 - arch/m68k/configs/atari_defconfig | 1 - arch/m68k/configs/bvme6000_defconfig | 1 - arch/m68k/configs/hp300_defconfig | 1 - arch/m68k/configs/mac_defconfig | 1 - arch/m68k/configs/multi_defconfig | 1 - arch/m68k/configs/mvme147_defconfig | 1 - arch/m68k/configs/mvme16x_defconfig | 1 - arch/m68k/configs/q40_defconfig | 1 - arch/m68k/configs/sun3_defconfig | 1 - arch/m68k/configs/sun3x_defconfig | 1 - arch/powerpc/configs/ppc64_defconfig | 1 - lib/Kconfig.debug | 20 +- lib/Makefile | 2 +- lib/scanf_kunit.c | 800 ++++++++++++++++++++++++++++++++++ lib/test_scanf.c | 814 ----------------------------------- tools/testing/selftests/lib/Makefile | 2 +- tools/testing/selftests/lib/config | 1 - tools/testing/selftests/lib/scanf.sh | 4 - 21 files changed, 820 insertions(+), 838 deletions(-) --- base-commit: a86bf2283d2c9769205407e2b54777c03d012939 change-id: 20250131-scanf-kunit-convert-f70dc33bb34c Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

4 months

3
6
0 0

[PATCH bpf-next 0/2] selftests/bpf: Move test_lwt_seg6local to test_progs

by Bastien Curutchet (eBPF Foundation)

Hi all, This patch series continues the work to migrate the script tests into prog_tests. test_lwt_seg6local.sh tests some bpf_lwt_* helpers. It contains only one test that uses a network topology quite different than the ones that can be found in others prog_tests/lwt_*.c files so I add a new prog_tests/lwt_seg6local.c file. While working on the migration I noticed that some routes present in the script weren't needed so PATCH 1 deletes them and then PATCH 2 migrates the test into the test_progs framework. Signed-off-by: Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com> --- Bastien Curutchet (eBPF Foundation) (2): selftests/bpf: lwt_seg6local: Remove unused routes selftests/bpf: lwt_seg6local: Move test to test_progs tools/testing/selftests/bpf/Makefile | 1 - .../selftests/bpf/prog_tests/lwt_seg6local.c | 176 +++++++++++++++++++++ tools/testing/selftests/bpf/test_lwt_seg6local.sh | 156 ------------------ 3 files changed, 176 insertions(+), 157 deletions(-) --- base-commit: 86eb3a47230a41c6ccf5cdae8ee0a7e7292aa29d change-id: 20250214-seg6local-64bcde44b66e Best regards, -- Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com>

4 months

3
4
0 0

[PATCH v2] kunit: tool: Fix bug in parsing test plan

by Rae Moar

A bug was identified where the KTAP below caused an infinite loop: TAP version 13 ok 4 test_case 1..4 The infinite loop was caused by the parser not parsing a test plan if following a test result line. Fix this bug to correctly parse test plan line. Signed-off-by: Rae Moar <rmoar(a)google.com> --- Changes since v1: - Remove error reported when test plan is missing. tools/testing/kunit/kunit_parser.py | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index 29fc27e8949b..da53a709773a 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -759,7 +759,7 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: # If parsing the main/top-level test, parse KTAP version line and # test plan test.name = "main" - ktap_line = parse_ktap_header(lines, test, printer) + parse_ktap_header(lines, test, printer) test.log.extend(parse_diagnostic(lines)) parse_test_plan(lines, test) parent_test = True @@ -768,13 +768,12 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: # the KTAP version line and/or subtest header line ktap_line = parse_ktap_header(lines, test, printer) subtest_line = parse_test_header(lines, test) + test.log.extend(parse_diagnostic(lines)) + parse_test_plan(lines, test) parent_test = (ktap_line or subtest_line) if parent_test: - # If KTAP version line and/or subtest header is found, attempt - # to parse test plan and print test header - test.log.extend(parse_diagnostic(lines)) - parse_test_plan(lines, test) print_test_header(test, printer) + expected_count = test.expected_count subtests = [] test_num = 1 base-commit: 0619a4868fc1b32b07fb9ed6c69adc5e5cf4e4b2 -- 2.49.0.rc0.332.g42c0ae87b1-goog

4 months

3
2
0 0

[PATCH v5 bpf-next 0/2] security: Propagate caller information in bpf hooks

by Blaise Boscaccy

Hello, While trying to implement an eBPF gatekeeper program, we ran into an issue whereas the LSM hooks are missing some relevant data. Certain subcommands passed to the bpf() syscall can be invoked from either the kernel or userspace. Additionally, some fields in the bpf_attr struct contain pointers, and depending on where the subcommand was invoked, they could point to either user or kernel memory. One example of this is the bpf_prog_load subcommand and its fd_array. This data is made available and used by the verifier but not made available to the LSM subsystem. This patchset simply exposes that information to applicable LSM hooks. Change list: - v4 -> v5 - merge v4 selftest breakout patch back into a single patch - change "is_kernel" to "kernel" - add selftest using new kernel flag - v3 -> v4 - split out selftest changes into a separate patch - v2 -> v3 - reorder params so that the new boolean flag is the last param - fixup function signatures in bpf selftests - v1 -> v2 - Pass a boolean flag in lieu of bpfptr_t Revisions: - v4 https://lore.kernel.org/bpf/20250304203123.3935371-1-bboscaccy@linux.micros… - v3 https://lore.kernel.org/bpf/20250303222416.3909228-1-bboscaccy@linux.micros… - v2 https://lore.kernel.org/bpf/20250228165322.3121535-1-bboscaccy@linux.micros… - v1 https://lore.kernel.org/bpf/20250226003055.1654837-1-bboscaccy@linux.micros… Blaise Boscaccy (2): security: Propagate caller information in bpf hooks selftests/bpf: Add a kernel flag test for LSM bpf hook include/linux/lsm_hook_defs.h | 6 +-- include/linux/security.h | 12 +++--- kernel/bpf/syscall.c | 10 ++--- security/security.c | 15 ++++--- security/selinux/hooks.c | 6 +-- .../selftests/bpf/prog_tests/kernel_flag.c | 43 +++++++++++++++++++ .../selftests/bpf/progs/rcu_read_lock.c | 3 +- .../bpf/progs/test_cgroup1_hierarchy.c | 4 +- .../selftests/bpf/progs/test_kernel_flag.c | 32 ++++++++++++++ .../bpf/progs/test_kfunc_dynptr_param.c | 6 +-- .../selftests/bpf/progs/test_lookup_key.c | 2 +- .../selftests/bpf/progs/test_ptr_untrusted.c | 2 +- .../bpf/progs/test_task_under_cgroup.c | 2 +- .../bpf/progs/test_verify_pkcs7_sig.c | 2 +- 14 files changed, 112 insertions(+), 33 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/kernel_flag.c create mode 100644 tools/testing/selftests/bpf/progs/test_kernel_flag.c -- 2.48.1

4 months

2
3
0 0

[PATCH v5 0/3] printf: convert self-test to KUnit

by Tamir Duberstein

This is one of just 3 remaining "Test Module" kselftests (the others being bitmap and scanf), the rest having been converted to KUnit. I tested this using: $ tools/testing/kunit/kunit.py run --arch arm64 --make_options LLVM=1 printf I have also sent out a series converting scanf[0]. Link: https://lore.kernel.org/all/20250204-scanf-kunit-convert-v3-0-386d7c3ee714@… [0] Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- Changes in v5: - Update `do_test` `__printf` annotation (Rasmus Villemoes). - Link to v4: https://lore.kernel.org/r/20250214-printf-kunit-convert-v4-0-c254572f1565@g… Changes in v4: - Add patch "implicate test line in failure messages". - Rebase on linux-next, move scanf_kunit.c into lib/tests/. - Link to v3: https://lore.kernel.org/r/20250210-printf-kunit-convert-v3-0-ee6ac5500f5e@g… Changes in v3: - Remove extraneous trailing newlines from failure messages. - Replace `pr_warn` with `kunit_warn`. - Drop arch changes. - Remove KUnit boilerplate from CONFIG_PRINTF_KUNIT_TEST help text. - Restore `total_tests` counting. - Remove tc_fail macro in last patch. - Link to v2: https://lore.kernel.org/r/20250207-printf-kunit-convert-v2-0-057b23860823@g… Changes in v2: - Incorporate code review from prior work[0] by Arpitha Raghunandan. - Link to v1: https://lore.kernel.org/r/20250204-printf-kunit-convert-v1-0-ecf1b846a4de@g… Link: https://lore.kernel.org/lkml/20200817043028.76502-1-98.arpi@gmail.com/t/#u [0] --- Tamir Duberstein (3): printf: convert self-test to KUnit printf: break kunit into test cases printf: implicate test line in failure messages Documentation/core-api/printk-formats.rst | 4 +- MAINTAINERS | 2 +- lib/Kconfig.debug | 12 +- lib/Makefile | 1 - lib/tests/Makefile | 1 + lib/{test_printf.c => tests/printf_kunit.c} | 437 ++++++++++++---------------- tools/testing/selftests/lib/config | 1 - tools/testing/selftests/lib/printf.sh | 4 - 8 files changed, 200 insertions(+), 262 deletions(-) --- base-commit: d4b0fd87ff0d4338b259dc79b2b3c6f7e70e8afa change-id: 20250131-printf-kunit-convert-fd4012aa2ec6 Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

4 months

2
16
0 0

[PATCH net-next v8 0/6] tun: Introduce virtio-net hashing feature

by Akihiko Odaki

virtio-net have two usage of hashes: one is RSS and another is hash reporting. Conventionally the hash calculation was done by the VMM. However, computing the hash after the queue was chosen defeats the purpose of RSS. Another approach is to use eBPF steering program. This approach has another downside: it cannot report the calculated hash due to the restrictive nature of eBPF. Introduce the code to compute hashes to the kernel in order to overcome thse challenges. An alternative solution is to extend the eBPF steering program so that it will be able to report to the userspace, but it is based on context rewrites, which is in feature freeze. We can adopt kfuncs, but they will not be UAPIs. We opt to ioctl to align with other relevant UAPIs (KVM and vhost_net). The patches for QEMU to use this new feature was submitted as RFC and is available at: https://patchew.org/QEMU/20240915-hash-v3-0-79cb08d28647@daynix.com/ This work was presented at LPC 2024: https://lpc.events/event/18/contributions/1963/ V1 -> V2: Changed to introduce a new BPF program type. Signed-off-by: Akihiko Odaki <akihiko.odaki(a)daynix.com> --- Changes in v8: - Disabled IPv6 to eliminate noises in tests. - Added a branch in tap to avoid unnecessary dissection when hash reporting is disabled. - Removed unnecessary rtnl_lock(). - Extracted code to handle new ioctls into separate functions to avoid adding extra NULL checks to the code handling other ioctls. - Introduced variable named "fd" to __tun_chr_ioctl(). - s/-/=/g in a patch message to avoid confusing Git. - Link to v7: https://lore.kernel.org/r/20250228-rss-v7-0-844205cbbdd6@daynix.com Changes in v7: - Ensured to set hash_report to VIRTIO_NET_HASH_REPORT_NONE for VHOST_NET_F_VIRTIO_NET_HDR. - s/4/sizeof(u32)/ in patch "virtio_net: Add functions for hashing". - Added tap_skb_cb type. - Rebased. - Link to v6: https://lore.kernel.org/r/20250109-rss-v6-0-b1c90ad708f6@daynix.com Changes in v6: - Extracted changes to fill vnet header holes into another series. - Squashed patches "skbuff: Introduce SKB_EXT_TUN_VNET_HASH", "tun: Introduce virtio-net hash reporting feature", and "tun: Introduce virtio-net RSS" into patch "tun: Introduce virtio-net hash feature". - Dropped the RFC tag. - Link to v5: https://lore.kernel.org/r/20241008-rss-v5-0-f3cf68df005d@daynix.com Changes in v5: - Fixed a compilation error with CONFIG_TUN_VNET_CROSS_LE. - Optimized the calculation of the hash value according to: https://git.dpdk.org/dpdk/commit/?id=3fb1ea032bd6ff8317af5dac9af901f1f324ca… - Added patch "tun: Unify vnet implementation". - Dropped patch "tap: Pad virtio header with zero". - Added patch "selftest: tun: Test vnet ioctls without device". - Reworked selftests to skip for older kernels. - Documented the case when the underlying device is deleted and packets have queue_mapping set by TC. - Reordered test harness arguments. - Added code to handle fragmented packets. - Link to v4: https://lore.kernel.org/r/20240924-rss-v4-0-84e932ec0e6c@daynix.com Changes in v4: - Moved tun_vnet_hash_ext to if_tun.h. - Renamed virtio_net_toeplitz() to virtio_net_toeplitz_calc(). - Replaced htons() with cpu_to_be16(). - Changed virtio_net_hash_rss() to return void. - Reordered variable declarations in virtio_net_hash_rss(). - Removed virtio_net_hdr_v1_hash_from_skb(). - Updated messages of "tap: Pad virtio header with zero" and "tun: Pad virtio header with zero". - Fixed vnet_hash allocation size. - Ensured to free vnet_hash when destructing tun_struct. - Link to v3: https://lore.kernel.org/r/20240915-rss-v3-0-c630015db082@daynix.com Changes in v3: - Reverted back to add ioctl. - Split patch "tun: Introduce virtio-net hashing feature" into "tun: Introduce virtio-net hash reporting feature" and "tun: Introduce virtio-net RSS". - Changed to reuse hash values computed for automq instead of performing RSS hashing when hash reporting is requested but RSS is not. - Extracted relevant data from struct tun_struct to keep it minimal. - Added kernel-doc. - Changed to allow calling TUNGETVNETHASHCAP before TUNSETIFF. - Initialized num_buffers with 1. - Added a test case for unclassified packets. - Fixed error handling in tests. - Changed tests to verify that the queue index will not overflow. - Rebased. - Link to v2: https://lore.kernel.org/r/20231015141644.260646-1-akihiko.odaki@daynix.com --- Akihiko Odaki (6): virtio_net: Add functions for hashing net: flow_dissector: Export flow_keys_dissector_symmetric tun: Introduce virtio-net hash feature selftest: tun: Test vnet ioctls without device selftest: tun: Add tests for virtio-net hashing vhost/net: Support VIRTIO_NET_F_HASH_REPORT Documentation/networking/tuntap.rst | 7 + drivers/net/Kconfig | 1 + drivers/net/tap.c | 67 +++- drivers/net/tun.c | 98 +++++- drivers/net/tun_vnet.h | 159 ++++++++- drivers/vhost/net.c | 49 +-- include/linux/if_tap.h | 2 + include/linux/skbuff.h | 3 + include/linux/virtio_net.h | 188 ++++++++++ include/net/flow_dissector.h | 1 + include/uapi/linux/if_tun.h | 75 ++++ net/core/flow_dissector.c | 3 +- net/core/skbuff.c | 4 + tools/testing/selftests/net/Makefile | 2 +- tools/testing/selftests/net/tun.c | 656 ++++++++++++++++++++++++++++++++++- 15 files changed, 1254 insertions(+), 61 deletions(-) --- base-commit: dd83757f6e686a2188997cb58b5975f744bb7786 change-id: 20240403-rss-e737d89efa77 prerequisite-change-id: 20241230-tun-66e10a49b0c7:v6 prerequisite-patch-id: 871dc5f146fb6b0e3ec8612971a8e8190472c0fb prerequisite-patch-id: 2797ed249d32590321f088373d4055ff3f430a0e prerequisite-patch-id: ea3370c72d4904e2f0536ec76ba5d26784c0cede prerequisite-patch-id: 837e4cf5d6b451424f9b1639455e83a260c4440d prerequisite-patch-id: ea701076f57819e844f5a35efe5cbc5712d3080d prerequisite-patch-id: 701646fb43ad04cc64dd2bf13c150ccbe6f828ce prerequisite-patch-id: 53176dae0c003f5b6c114d43f936cf7140d31bb5 prerequisite-change-id: 20250116-buffers-96e14bf023fc:v2 prerequisite-patch-id: 25fd4f99d4236a05a5ef16ab79f3e85ee57e21cc Best regards, -- Akihiko Odaki <akihiko.odaki(a)daynix.com>

4 months, 1 week

4
9
0 0

[PATCH v2 0/4] RISC-V KVM PMU fix and selftest improvement

by Atish Patra

This series adds a fix for KVM PMU code and improves the pmu selftest by allowing generating precise number of interrupts. It also provided another additional option to the overflow test that allows user to generate custom number of LCOFI interrupts. Signed-off-by: Atish Patra <atishp(a)rivosinc.com> --- Changes in v2: - Initialized the local overflow irq variable to 0 indicate that it's not a allowed value. - Moved the introduction of argument option `n` to the last patch. - Link to v1: https://lore.kernel.org/r/20250226-kvm_pmu_improve-v1-0-74c058c2bf6d@rivosi… --- Atish Patra (4): RISC-V: KVM: Disable the kernel perf counter during configure KVM: riscv: selftests: Do not start the counter in the overflow handler KVM: riscv: selftests: Change command line option KVM: riscv: selftests: Allow number of interrupts to be configurable arch/riscv/kvm/vcpu_pmu.c | 1 + tools/testing/selftests/kvm/riscv/sbi_pmu_test.c | 81 ++++++++++++++++-------- 2 files changed, 57 insertions(+), 25 deletions(-) --- base-commit: 0ad2507d5d93f39619fc42372c347d6006b64319 change-id: 20250225-kvm_pmu_improve-fffd038b2404 -- Regards, Atish patra

4 months, 1 week

3
6
0 0

[PATCH v2 net 0/6] eth: bnxt: fix several bugs in the bnxt module

by Taehee Yoo

The first fixes setting incorrect skb->truesize. When xdp-mb prog returns XDP_PASS, skb is allocated and initialized. Currently, The truesize is calculated as BNXT_RX_PAGE_SIZE * sinfo->nr_frags, but sinfo->nr_frags is flushed by napi_build_skb(). So, it stores sinfo before calling napi_build_skb() and then use it for calculate truesize. The second fixes kernel panic in the bnxt_queue_mem_alloc(). The bnxt_queue_mem_alloc() accesses rx ring descriptor. rx ring descriptors are allocated when the interface is up and it's freed when the interface is down. So, if bnxt_queue_mem_alloc() is called when the interface is down, kernel panic occurs. This patch makes the bnxt_queue_mem_alloc() return -ENETDOWN if rx ring descriptors are not allocated. The third patch fixes kernel panic in the bnxt_queue_{start | stop}(). When a queue is restarted bnxt_queue_{start | stop}() are called. These functions set MRU to 0 to stop packet flow and then to set up the remaining things. MRU variable is a member of vnic_info[] the first vnic_info is for default and the second is for ntuple. The first vnic_info is always allocated when interface is up, but the second is allocated only when ntuple is enabled. (ethtool -K eth0 ntuple <on | off>). Currently, the bnxt_queue_{start | stop}() access vnic_info[BNXT_VNIC_NTUPLE] regardless of whether ntuple is enabled or not. So kernel panic occurs. This patch make the bnxt_queue_{start | stop}() use bp->nr_vnics instead of BNXT_VNIC_NTUPLE. The fourth patch fixes a warning due to checksum state. The bnxt_rx_pkt() checks whether skb->ip_summed is not CHECKSUM_NONE before updating ip_summed. if ip_summed is not CHECKSUM_NONE, it WARNS about it. However, the bnxt_xdp_build_skb() is called in XDP-MB-PASS path and it updates ip_summed earlier than bnxt_rx_pkt(). So, in the XDP-MB-PASS path, the bnxt_rx_pkt() always warns about checksum. Updating ip_summed at the bnxt_xdp_build_skb() is unnecessary and duplicate, so it is removed. The fifth patch makes net_devmem_unbind_dmabuf() ignore -ENETDOWN. When devmem socket is closed, net_devmem_unbind_dmabuf() is called to unbind/release resources. If interface is down, the driver returns -ENETDOWN. The -ENETDOWN return value is not an actual error, because the interface will release resources when the interface is down. So, net_devmem_unbind_dmabuf() needs to ignore -ENETDOWN. The last patch adds XDP testcases to tools/testing/selftests/drivers/net/ping.py. v2: - Do not use num_frags in the bnxt_xdp_build_skb(). (1/6) - Add Review tags from Somnath and Jakub. (2/6) - Add new patch for fixing checksum warning. (4/6) - Add new patch for fixing warning in net_devmem_unbind_dmabuf(). (5/6) - Add new XDP testcases to ping.py (6/6) Taehee Yoo (6): eth: bnxt: fix truesize for mb-xdp-pass case eth: bnxt: return fail if interface is down in bnxt_queue_mem_alloc() eth: bnxt: do not use BNXT_VNIC_NTUPLE unconditionally in queue restart logic eth: bnxt: do not update checksum in bnxt_xdp_build_skb() net: devmem: do not WARN conditionally after netdev_rx_queue_restart() selftests: drv-net: add xdp cases for ping.py drivers/net/ethernet/broadcom/bnxt/bnxt.c | 36 ++-- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 18 +- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h | 6 +- net/core/devmem.c | 4 +- tools/testing/selftests/drivers/net/ping.py | 200 ++++++++++++++++-- .../testing/selftests/net/lib/xdp_dummy.bpf.c | 6 + 6 files changed, 221 insertions(+), 49 deletions(-) -- 2.34.1

4 months, 1 week

3
9
0 0

[PATCHv4 net 0/3] bond: fix xfrm offload issues

by Hangbin Liu

The first patch fixes the incorrect locks using in bond driver. The second patch fixes the xfrm offload feature during setup active-backup mode. The third patch add a ipsec offload testing. v4: hold xs->lock for bond_ipsec_{del, add}_sa_all (Cosmin Ratiu) use the defer helpers in lib.sh for selftest (Petr Machata) v3: move the ipsec deletion to bond_ipsec_free_sa (Cosmin Ratiu) v2: do not turn carrier on if bond change link failed (Nikolay Aleksandrov) move the mutex lock to a work queue (Cosmin Ratiu) Hangbin Liu (3): bonding: move IPsec deletion to bond_ipsec_free_sa bonding: fix xfrm offload feature setup on active-backup mode selftests: bonding: add ipsec offload test drivers/net/bonding/bond_main.c | 55 +++++-- drivers/net/bonding/bond_netlink.c | 16 +- include/net/bonding.h | 1 + .../selftests/drivers/net/bonding/Makefile | 3 +- .../drivers/net/bonding/bond_ipsec_offload.sh | 154 ++++++++++++++++++ .../selftests/drivers/net/bonding/config | 4 + 6 files changed, 208 insertions(+), 25 deletions(-) create mode 100755 tools/testing/selftests/drivers/net/bonding/bond_ipsec_offload.sh -- 2.46.0

4 months, 1 week

4
13
0 0

[PATCH net-next v2 1/2] selftests: drv-net: add path helper for net/lib

by Jakub Kicinski

Looks like a lot of users of recently added env.rpath() actually want to access stuff under net/lib. Add another helper. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- tools/testing/selftests/drivers/net/hds.py | 2 +- tools/testing/selftests/drivers/net/hw/csum.py | 2 +- tools/testing/selftests/drivers/net/lib/py/env.py | 7 +++++++ 3 files changed, 9 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py index 7cc74faed743..def44c10349a 100755 --- a/tools/testing/selftests/drivers/net/hds.py +++ b/tools/testing/selftests/drivers/net/hds.py @@ -20,7 +20,7 @@ from lib.py import defer, ethtool, ip def _xdp_onoff(cfg): - prog = cfg.rpath("../../net/lib/xdp_dummy.bpf.o") + prog = cfg.lpath("xdp_dummy.bpf.o") ip("link set dev %s xdp obj %s sec xdp" % (cfg.ifname, prog)) ip("link set dev %s xdp off" % cfg.ifname) diff --git a/tools/testing/selftests/drivers/net/hw/csum.py b/tools/testing/selftests/drivers/net/hw/csum.py index 701aca1361e0..49ec98aef579 100755 --- a/tools/testing/selftests/drivers/net/hw/csum.py +++ b/tools/testing/selftests/drivers/net/hw/csum.py @@ -88,7 +88,7 @@ from lib.py import bkg, cmd, wait_port_listen with NetDrvEpEnv(__file__, nsim_test=False) as cfg: check_nic_features(cfg) - cfg.bin_local = cfg.rpath("../../../net/lib/csum") + cfg.bin_local = cfg.lpath("csum") cfg.bin_remote = cfg.remote.deploy(cfg.bin_local) cases = [] diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index fd4d674e6c72..2a1f8bd0ec19 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -30,6 +30,13 @@ from .remote import Remote src_dir = Path(self.src_path).parent.resolve() return (src_dir / path).as_posix() + def lpath(self, path): + """ + Similar to rpath, but for files in net/lib TARGET. + """ + lib_dir = (Path(__file__).parent / "../../../../net/lib").resolve() + return (lib_dir / path).as_posix() + def _load_env_file(self): env = os.environ.copy() -- 2.48.1

4 months, 1 week

3
7
0 0

[PATCH net-next] selftests: openvswitch: don't hardcode the drop reason subsys

by Jakub Kicinski

WiFi removed one of their subsys entries from drop reasons, in commit 286e69677065 ("wifi: mac80211: Drop cooked monitor support") SKB_DROP_REASON_SUBSYS_OPENVSWITCH is now 2 not 3. The drop reasons are not uAPI, read the correct value from debug info. We need to enable vmlinux BTF, otherwise pahole needs a few GB of memory to decode the enum name. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: pshelar(a)ovn.org CC: aconole(a)redhat.com CC: amorenoz(a)redhat.com CC: linux-kselftest(a)vger.kernel.org CC: dev(a)openvswitch.org --- tools/testing/selftests/net/config | 2 ++ .../testing/selftests/net/openvswitch/openvswitch.sh | 11 ++++++++--- 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 5b9baf708950..3365bcc35304 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -18,6 +18,8 @@ CONFIG_DUMMY=y CONFIG_BRIDGE_VLAN_FILTERING=y CONFIG_BRIDGE=y CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_DEBUG_INFO_BTF=y +CONFIG_DEBUG_INFO_BTF_MODULES=n CONFIG_VLAN_8021Q=y CONFIG_GENEVE=m CONFIG_IFB=y diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index 960e1ab4dd04..3c8d3455d8e7 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -330,6 +330,11 @@ test_psample() { # - drop packets and verify the right drop reason is reported test_drop_reason() { which perf >/dev/null 2>&1 || return $ksft_skip + which pahole >/dev/null 2>&1 || return $ksft_skip + + ovs_drop_subsys=$(pahole -C skb_drop_reason_subsys | + awk '/OPENVSWITCH/ { print $3; }' | + tr -d ,) sbx_add "test_drop_reason" || return $? @@ -373,7 +378,7 @@ test_drop_reason() { "in_port(2),eth(),eth_type(0x0800),ipv4(src=172.31.110.20,proto=1),icmp()" 'drop' ovs_drop_record_and_run "test_drop_reason" ip netns exec client ping -c 2 172.31.110.20 - ovs_drop_reason_count 0x30001 # OVS_DROP_FLOW_ACTION + ovs_drop_reason_count 0x${ovs_drop_subsys}0001 # OVS_DROP_FLOW_ACTION if [[ "$?" -ne "2" ]]; then info "Did not detect expected drops: $?" return 1 @@ -390,7 +395,7 @@ test_drop_reason() { ovs_drop_record_and_run \ "test_drop_reason" ip netns exec client nc -i 1 -zuv 172.31.110.20 6000 - ovs_drop_reason_count 0x30004 # OVS_DROP_EXPLICIT_ACTION_ERROR + ovs_drop_reason_count 0x${ovs_drop_subsys}0004 # OVS_DROP_EXPLICIT_ACTION_ERROR if [[ "$?" -ne "1" ]]; then info "Did not detect expected explicit error drops: $?" return 1 @@ -398,7 +403,7 @@ test_drop_reason() { ovs_drop_record_and_run \ "test_drop_reason" ip netns exec client nc -i 1 -zuv 172.31.110.20 7000 - ovs_drop_reason_count 0x30003 # OVS_DROP_EXPLICIT_ACTION + ovs_drop_reason_count 0x${ovs_drop_subsys}0003 # OVS_DROP_EXPLICIT_ACTION if [[ "$?" -ne "1" ]]; then info "Did not detect expected explicit drops: $?" return 1 -- 2.48.1

4 months, 1 week

4
3
0 0

[PATCH net-next 1/2] selftests: net: fix error message in bpf_offload

by Jakub Kicinski

We hit a following exception on timeout, nmaps is never set: Test bpftool bound info reporting (own ns)... Traceback (most recent call last): File "/home/virtme/testing-1/tools/testing/selftests/net/./bpf_offload.py", line 1128, in <module> check_dev_info(False, "") File "/home/virtme/testing-1/tools/testing/selftests/net/./bpf_offload.py", line 583, in check_dev_info maps = bpftool_map_list_wait(expected=2, ns=ns) File "/home/virtme/testing-1/tools/testing/selftests/net/./bpf_offload.py", line 215, in bpftool_map_list_wait raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps)) NameError: name 'nmaps' is not defined Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: linux-kselftest(a)vger.kernel.org CC: bpf(a)vger.kernel.org --- tools/testing/selftests/net/bpf_offload.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/bpf_offload.py b/tools/testing/selftests/net/bpf_offload.py index fd0d959914e4..4a9be8c49561 100755 --- a/tools/testing/selftests/net/bpf_offload.py +++ b/tools/testing/selftests/net/bpf_offload.py @@ -207,9 +207,11 @@ netns = [] # net namespaces to be removed raise Exception("Time out waiting for program counts to stabilize want %d, have %d" % (expected, nprogs)) def bpftool_map_list_wait(expected=0, n_retry=20, ns=""): + nmaps = None for i in range(n_retry): maps = bpftool_map_list(ns=ns) - if len(maps) == expected: + nmaps = len(maps) + if nmaps == expected: return maps time.sleep(0.05) raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps)) -- 2.48.1

4 months, 1 week

3
4
0 0

[PATCH net-next v6 0/8] Device memory TCP TX

by Mina Almasry

v6: https://lore.kernel.org/netdev/20250222191517.743530-1-almasrymina@google.c… === v6 has no major changes. Addressed a few issues from Paolo and David, and collected Acks from Stan. Thank you everyone for the review! Changes: - retain behavior to process MSG_FASTOPEN even if the provided cmsg is invalid (Paolo). - Rework the freeing of tx_vec slightly (it now has its own err label). (Paolo). - Squash the commit that makes dmabuf unbinding scheduled work into the same one which implements the TX path so we don't run into future errors on bisecting (Paolo). - Fix/add comments to explain how dmabuf binding refcounting works (David). v5: https://lore.kernel.org/netdev/20250220020914.895431-1-almasrymina@google.c… === v5 has no major changes; it clears up the relatively minor issues pointed out to in v4, and rebases the series on top of net-next to resolve the conflict with a patch that raced to the tree. It also collects the review tags from v4. Changes: - Rebase to net-next - Fix issues in selftest (Stan). - Address comments in the devmem and netmem driver docs (Stan and Bagas) - Fix zerocopy_fill_skb_from_devmem return error code (Stan). v4: https://lore.kernel.org/netdev/20250203223916.1064540-1-almasrymina@google.… === v4 mainly addresses the critical driver support issue surfaced in v3 by Paolo and Stan. Drivers aiming to support netmem_tx should make sure not to pass the netmem dma-addrs to the dma-mapping APIs, as these dma-addrs may come from dma-bufs. Additionally other feedback from v3 is addressed. Major changes: - Add helpers to handle netmem dma-addrs. Add GVE support for netmem_tx. - Fix binding->tx_vec not being freed on error paths during the tx binding. - Add a minimal devmem_tx test to devmem.py. - Clean up everything obsolete from the cover letter (Paolo). v3: https://patchwork.kernel.org/project/netdevbpf/list/?series=929401&state=* === Address minor comments from RFCv2 and fix a few build warnings and ynl-regen issues. No major changes. RFC v2: https://patchwork.kernel.org/project/netdevbpf/list/?series=920056&state=* ======= RFC v2 addresses much of the feedback from RFC v1. I plan on sending something close to this as net-next reopens, sending it slightly early to get feedback if any. Major changes: -------------- - much improved UAPI as suggested by Stan. We now interpret the iov_base of the passed in iov from userspace as the offset into the dmabuf to send from. This removes the need to set iov.iov_base = NULL which may be confusing to users, and enables us to send multiple iovs in the same sendmsg() call. ncdevmem and the docs show a sample use of that. - Removed the duplicate dmabuf iov_iter in binding->iov_iter. I think this is good improvment as it was confusing to keep track of 2 iterators for the same sendmsg, and mistracking both iterators caused a couple of bugs reported in the last iteration that are now resolved with this streamlining. - Improved test coverage in ncdevmem. Now multiple sendmsg() are tested, and sending multiple iovs in the same sendmsg() is tested. - Fixed issue where dmabuf unmapping was happening in invalid context (Stan). ==================================================================== The TX path had been dropped from the Device Memory TCP patch series post RFCv1 [1], to make that series slightly easier to review. This series rebases the implementation of the TX path on top of the net_iov/netmem framework agreed upon and merged. The motivation for the feature is thoroughly described in the docs & cover letter of the original proposal, so I don't repeat the lengthy descriptions here, but they are available in [1]. Full outline on usage of the TX path is detailed in the documentation included with this series. Test example is available via the kselftest included in the series as well. The series is relatively small, as the TX path for this feature largely piggybacks on the existing MSG_ZEROCOPY implementation. Patch Overview: --------------- 1. Documentation & tests to give high level overview of the feature being added. 1. Add netmem refcounting needed for the TX path. 2. Devmem TX netlink API. 3. Devmem TX net stack implementation. 4. Make dma-buf unbinding scheduled work to handle TX cases where it gets freed from contexts where we can't sleep. 5. Add devmem TX documentation. 6. Add scaffolding enabling driver support for netmem_tx. Add helpers, driver feature flag, and docs to enable drivers to declare netmem_tx support. 7. Guard netmem_tx against being enabled against drivers that don't support it. 8. Add devmem_tx selftests. Add TX path to ncdevmem and add a test to devmem.py. Testing: -------- Testing is very similar to devmem TCP RX path. The ncdevmem test used for the RX path is now augemented with client functionality to test TX path. * Test Setup: Kernel: net-next with this RFC and memory provider API cherry-picked locally. Hardware: Google Cloud A3 VMs. NIC: GVE with header split & RSS & flow steering support. Performance results are not included with this version, unfortunately. I'm having issues running the dma-buf exporter driver against the upstream kernel on my test setup. The issues are specific to that dma-buf exporter and do not affect this patch series. I plan to follow up this series with perf fixes if the tests point to issues once they're up and running. Special thanks to Stan who took a stab at rebasing the TX implementation on top of the netmem/net_iov framework merged. Parts of his proposal [2] that are reused as-is are forked off into their own patches to give full credit. [1] https://lore.kernel.org/netdev/20240909054318.1809580-1-almasrymina@google.… [2] https://lore.kernel.org/netdev/20240913150913.1280238-2-sdf@fomichev.me/T/#… Cc: sdf(a)fomichev.me Cc: asml.silence(a)gmail.com Cc: dw(a)davidwei.uk Cc: Jamal Hadi Salim <jhs(a)mojatatu.com> Cc: Victor Nogueira <victor(a)mojatatu.com> Cc: Pedro Tammela <pctammela(a)mojatatu.com> Cc: Samiullah Khawaja <skhawaja(a)google.com> Mina Almasry (7): net: add get_netmem/put_netmem support net: devmem: Implement TX path net: add devmem TCP TX documentation net: enable driver support for netmem TX gve: add netmem TX support to GVE DQO-RDA mode net: check for driver support in netmem TX selftests: ncdevmem: Implement devmem TCP TX Stanislav Fomichev (1): net: devmem: TCP tx netlink api Documentation/netlink/specs/netdev.yaml | 12 + Documentation/networking/devmem.rst | 150 ++++++++- .../networking/net_cachelines/net_device.rst | 1 + Documentation/networking/netdev-features.rst | 5 + Documentation/networking/netmem.rst | 23 +- drivers/net/ethernet/google/gve/gve_main.c | 4 + drivers/net/ethernet/google/gve/gve_tx_dqo.c | 8 +- include/linux/netdevice.h | 2 + include/linux/skbuff.h | 17 +- include/linux/skbuff_ref.h | 4 +- include/net/netmem.h | 23 ++ include/net/sock.h | 1 + include/uapi/linux/netdev.h | 1 + net/core/datagram.c | 48 ++- net/core/dev.c | 3 + net/core/devmem.c | 115 ++++++- net/core/devmem.h | 77 ++++- net/core/netdev-genl-gen.c | 13 + net/core/netdev-genl-gen.h | 1 + net/core/netdev-genl.c | 73 ++++- net/core/skbuff.c | 48 ++- net/core/sock.c | 6 + net/ipv4/ip_output.c | 3 +- net/ipv4/tcp.c | 50 ++- net/ipv6/ip6_output.c | 3 +- net/vmw_vsock/virtio_transport_common.c | 5 +- tools/include/uapi/linux/netdev.h | 1 + .../selftests/drivers/net/hw/devmem.py | 26 +- .../selftests/drivers/net/hw/ncdevmem.c | 300 +++++++++++++++++- 29 files changed, 950 insertions(+), 73 deletions(-) base-commit: 80c4a0015ce249cf0917a04dbb3cc652a6811079 -- 2.48.1.658.g4767266eb4-goog

4 months, 1 week

6
24
0 0

[PATCH] selftests/bpf: Move test_lwt_ip_encap to test_progs

by Bastien Curutchet (eBPF Foundation)

test_lwt_ip_encap.sh isn't used by the BPF CI. Add a new file in the test_progs framework to migrate the tests done by test_lwt_ip_encap.sh. It uses the same network topology and the same BPF programs located in progs/test_lwt_ip_encap.c. Rework the GSO part to avoid using nc and dd. Remove test_lwt_ip_encap.sh and its Makefile entry. Signed-off-by: Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com> --- tools/testing/selftests/bpf/Makefile | 3 +- .../selftests/bpf/prog_tests/lwt_ip_encap.c | 540 +++++++++++++++++++++ tools/testing/selftests/bpf/test_lwt_ip_encap.sh | 476 ------------------ 3 files changed, 541 insertions(+), 478 deletions(-) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index e6a02d5b87d123cef7e6b41bfbc96d34083f38e1..df4814b5200a5a0e732b19ab3a5975957fb7cbc9 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -95,7 +95,7 @@ TEST_GEN_PROGS += test_progs-cpuv4 TEST_INST_SUBDIRS += cpuv4 endif -TEST_GEN_FILES = test_lwt_ip_encap.bpf.o test_tc_edt.bpf.o +TEST_GEN_FILES = test_tc_edt.bpf.o TEST_FILES = xsk_prereqs.sh $(wildcard progs/btf_dump_test_case_*.c) # Order correspond to 'make run_tests' order @@ -104,7 +104,6 @@ TEST_PROGS := test_kmod.sh \ test_lirc_mode2.sh \ test_xdp_vlan_mode_generic.sh \ test_xdp_vlan_mode_native.sh \ - test_lwt_ip_encap.sh \ test_tc_tunnel.sh \ test_tc_edt.sh \ test_xdping.sh \ diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c b/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c new file mode 100644 index 0000000000000000000000000000000000000000..61fcded43b46cab7775237c6d85de07b5df7d87e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c @@ -0,0 +1,540 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <netinet/in.h> + +#include "network_helpers.h" +#include "test_progs.h" + +#define BPF_FILE "test_lwt_ip_encap.bpf.o" + +#define NETNS_NAME_SIZE 32 +#define NETNS_BASE "ns-lwt-ip-encap" + +#define IP4_ADDR_1 "172.16.1.100" +#define IP4_ADDR_2 "172.16.2.100" +#define IP4_ADDR_3 "172.16.3.100" +#define IP4_ADDR_4 "172.16.4.100" +#define IP4_ADDR_5 "172.16.5.100" +#define IP4_ADDR_6 "172.16.6.100" +#define IP4_ADDR_7 "172.16.7.100" +#define IP4_ADDR_8 "172.16.8.100" +#define IP4_ADDR_GRE "172.16.16.100" + +#define IP4_ADDR_SRC IP4_ADDR_1 +#define IP4_ADDR_DST IP4_ADDR_4 + +#define IP6_ADDR_1 "fb01::1" +#define IP6_ADDR_2 "fb02::1" +#define IP6_ADDR_3 "fb03::1" +#define IP6_ADDR_4 "fb04::1" +#define IP6_ADDR_5 "fb05::1" +#define IP6_ADDR_6 "fb06::1" +#define IP6_ADDR_7 "fb07::1" +#define IP6_ADDR_8 "fb08::1" +#define IP6_ADDR_GRE "fb10::1" + +#define IP6_ADDR_SRC IP6_ADDR_1 +#define IP6_ADDR_DST IP6_ADDR_4 + +/* Setup/topology: + * + * NS1 NS2 NS3 + * veth1 <---> veth2 veth3 <---> veth4 (the top route) + * veth5 <---> veth6 veth7 <---> veth8 (the bottom route) + * + * Each vethN gets IP[4|6]_ADDR_N address. + * + * IP*_ADDR_SRC = IP*_ADDR_1 + * IP*_ADDR_DST = IP*_ADDR_4 + * + * All tests test pings from IP*_ADDR__SRC to IP*_ADDR_DST. + * + * By default, routes are configured to allow packets to go + * IP*_ADDR_1 <=> IP*_ADDR_2 <=> IP*_ADDR_3 <=> IP*_ADDR_4 (the top route). + * + * A GRE device is installed in NS3 with IP*_ADDR_GRE, and + * NS1/NS2 are configured to route packets to IP*_ADDR_GRE via IP*_ADDR_8 + * (the bottom route). + * + * Tests: + * + * 1. Routes NS2->IP*_ADDR_DST are brought down, so the only way a ping + * from IP*_ADDR_SRC to IP*_ADDR_DST can work is via IP*_ADDR_GRE. + * + * 2a. In an egress test, a bpf LWT_XMIT program is installed on veth1 + * that encaps the packets with an IP/GRE header to route to IP*_ADDR_GRE. + * + * ping: SRC->[encap at veth1:egress]->GRE:decap->DST + * ping replies go DST->SRC directly + * + * 2b. In an ingress test, a bpf LWT_IN program is installed on veth2 + * that encaps the packets with an IP/GRE header to route to IP*_ADDR_GRE. + * + * ping: SRC->[encap at veth2:ingress]->GRE:decap->DST + * ping replies go DST->SRC directly + */ + +static int create_ns(char *name, size_t name_sz) +{ + if (!name) + goto fail; + + if (!ASSERT_OK(append_tid(name, name_sz), "append TID")) + goto fail; + + SYS(fail, "ip netns add %s", name); + + /* rp_filter gets confused by what these tests are doing, so disable it */ + SYS(fail, "ip netns exec %s sysctl -wq net.ipv4.conf.all.rp_filter=0", name); + SYS(fail, "ip netns exec %s sysctl -wq net.ipv4.conf.default.rp_filter=0", name); + /* Disable IPv6 DAD because it sometimes takes too long and fails tests */ + SYS(fail, "ip netns exec %s sysctl -wq net.ipv6.conf.all.accept_dad=0", name); + SYS(fail, "ip netns exec %s sysctl -wq net.ipv6.conf.default.accept_dad=0", name); + + return 0; +fail: + return -1; +} + +static int set_top_addr(const char *ns1, const char *ns2, const char *ns3) +{ + SYS(fail, "ip -n %s a add %s/24 dev veth1", ns1, IP4_ADDR_1); + SYS(fail, "ip -n %s a add %s/24 dev veth2", ns2, IP4_ADDR_2); + SYS(fail, "ip -n %s a add %s/24 dev veth3", ns2, IP4_ADDR_3); + SYS(fail, "ip -n %s a add %s/24 dev veth4", ns3, IP4_ADDR_4); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth1", ns1, IP6_ADDR_1); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth2", ns2, IP6_ADDR_2); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth3", ns2, IP6_ADDR_3); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth4", ns3, IP6_ADDR_4); + + SYS(fail, "ip -n %s link set dev veth1 up", ns1); + SYS(fail, "ip -n %s link set dev veth2 up", ns2); + SYS(fail, "ip -n %s link set dev veth3 up", ns2); + SYS(fail, "ip -n %s link set dev veth4 up", ns3); + + return 0; +fail: + return 1; +} + +static int set_bottom_addr(const char *ns1, const char *ns2, const char *ns3) +{ + SYS(fail, "ip -n %s a add %s/24 dev veth5", ns1, IP4_ADDR_5); + SYS(fail, "ip -n %s a add %s/24 dev veth6", ns2, IP4_ADDR_6); + SYS(fail, "ip -n %s a add %s/24 dev veth7", ns2, IP4_ADDR_7); + SYS(fail, "ip -n %s a add %s/24 dev veth8", ns3, IP4_ADDR_8); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth5", ns1, IP6_ADDR_5); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth6", ns2, IP6_ADDR_6); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth7", ns2, IP6_ADDR_7); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth8", ns3, IP6_ADDR_8); + + SYS(fail, "ip -n %s link set dev veth5 up", ns1); + SYS(fail, "ip -n %s link set dev veth6 up", ns2); + SYS(fail, "ip -n %s link set dev veth7 up", ns2); + SYS(fail, "ip -n %s link set dev veth8 up", ns3); + + return 0; +fail: + return 1; +} + +static int configure_vrf(const char *ns1, const char *ns2) +{ + if (!ns1 || !ns2) + goto fail; + + SYS(fail, "ip -n %s link add red type vrf table 1001", ns1); + SYS(fail, "ip -n %s link set red up", ns1); + SYS(fail, "ip -n %s route add table 1001 unreachable default metric 8192", ns1); + SYS(fail, "ip -n %s -6 route add table 1001 unreachable default metric 8192", ns1); + SYS(fail, "ip -n %s link set veth1 vrf red", ns1); + SYS(fail, "ip -n %s link set veth5 vrf red", ns1); + + SYS(fail, "ip -n %s link add red type vrf table 1001", ns2); + SYS(fail, "ip -n %s link set red up", ns2); + SYS(fail, "ip -n %s route add table 1001 unreachable default metric 8192", ns2); + SYS(fail, "ip -n %s -6 route add table 1001 unreachable default metric 8192", ns2); + SYS(fail, "ip -n %s link set veth2 vrf red", ns2); + SYS(fail, "ip -n %s link set veth3 vrf red", ns2); + SYS(fail, "ip -n %s link set veth6 vrf red", ns2); + SYS(fail, "ip -n %s link set veth7 vrf red", ns2); + + return 0; +fail: + return -1; +} + +static int configure_ns1(const char *ns1, const char *vrf) +{ + struct nstoken *nstoken = NULL; + + if (!ns1 || !vrf) + goto fail; + + nstoken = open_netns(ns1); + if (!ASSERT_OK_PTR(nstoken, "open ns1")) + goto fail; + + /* Top route */ + SYS(fail, "ip route add %s/32 dev veth1 %s", IP4_ADDR_2, vrf); + SYS(fail, "ip route add default dev veth1 via %s %s", IP4_ADDR_2, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth1 %s", IP6_ADDR_2, vrf); + SYS(fail, "ip -6 route add default dev veth1 via %s %s", IP6_ADDR_2, vrf); + /* Bottom route */ + SYS(fail, "ip route add %s/32 dev veth5 %s", IP4_ADDR_6, vrf); + SYS(fail, "ip route add %s/32 dev veth5 via %s %s", IP4_ADDR_7, IP4_ADDR_6, vrf); + SYS(fail, "ip route add %s/32 dev veth5 via %s %s", IP4_ADDR_8, IP4_ADDR_6, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth5 %s", IP6_ADDR_6, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth5 via %s %s", IP6_ADDR_7, IP6_ADDR_6, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth5 via %s %s", IP6_ADDR_8, IP6_ADDR_6, vrf); + + close_netns(nstoken); + return 0; +fail: + close_netns(nstoken); + return -1; +} + +static int configure_ns2(const char *ns2, const char *vrf) +{ + struct nstoken *nstoken = NULL; + + if (!ns2 || !vrf) + goto fail; + + nstoken = open_netns(ns2); + if (!ASSERT_OK_PTR(nstoken, "open ns2")) + goto fail; + + SYS(fail, "ip netns exec %s sysctl -wq net.ipv4.ip_forward=1", ns2); + SYS(fail, "ip netns exec %s sysctl -wq net.ipv6.conf.all.forwarding=1", ns2); + + /* Top route */ + SYS(fail, "ip route add %s/32 dev veth2 %s", IP4_ADDR_1, vrf); + SYS(fail, "ip route add %s/32 dev veth3 %s", IP4_ADDR_4, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth2 %s", IP6_ADDR_1, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth3 %s", IP6_ADDR_4, vrf); + /* Bottom route */ + SYS(fail, "ip route add %s/32 dev veth6 %s", IP4_ADDR_5, vrf); + SYS(fail, "ip route add %s/32 dev veth7 %s", IP4_ADDR_8, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth6 %s", IP6_ADDR_5, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth7 %s", IP6_ADDR_8, vrf); + + close_netns(nstoken); + return 0; +fail: + close_netns(nstoken); + return -1; +} + +static int configure_ns3(const char *ns3) +{ + struct nstoken *nstoken = NULL; + + if (!ns3) + goto fail; + + nstoken = open_netns(ns3); + if (!ASSERT_OK_PTR(nstoken, "open ns3")) + goto fail; + + /* Top route */ + SYS(fail, "ip route add %s/32 dev veth4", IP4_ADDR_3); + SYS(fail, "ip route add %s/32 dev veth4 via %s", IP4_ADDR_1, IP4_ADDR_3); + SYS(fail, "ip route add %s/32 dev veth4 via %s", IP4_ADDR_2, IP4_ADDR_3); + SYS(fail, "ip -6 route add %s/128 dev veth4", IP6_ADDR_3); + SYS(fail, "ip -6 route add %s/128 dev veth4 via %s", IP6_ADDR_1, IP6_ADDR_3); + SYS(fail, "ip -6 route add %s/128 dev veth4 via %s", IP6_ADDR_2, IP6_ADDR_3); + /* Bottom route */ + SYS(fail, "ip route add %s/32 dev veth8", IP4_ADDR_7); + SYS(fail, "ip route add %s/32 dev veth8 via %s", IP4_ADDR_5, IP4_ADDR_7); + SYS(fail, "ip route add %s/32 dev veth8 via %s", IP4_ADDR_6, IP4_ADDR_7); + SYS(fail, "ip -6 route add %s/128 dev veth8", IP6_ADDR_7); + SYS(fail, "ip -6 route add %s/128 dev veth8 via %s", IP6_ADDR_5, IP6_ADDR_7); + SYS(fail, "ip -6 route add %s/128 dev veth8 via %s", IP6_ADDR_6, IP6_ADDR_7); + + /* Configure IPv4 GRE device */ + SYS(fail, "ip tunnel add gre_dev mode gre remote %s local %s ttl 255", + IP4_ADDR_1, IP4_ADDR_GRE); + SYS(fail, "ip link set gre_dev up"); + SYS(fail, "ip a add %s dev gre_dev", IP4_ADDR_GRE); + + /* Configure IPv6 GRE device */ + SYS(fail, "ip tunnel add gre6_dev mode ip6gre remote %s local %s ttl 255", + IP6_ADDR_1, IP6_ADDR_GRE); + SYS(fail, "ip link set gre6_dev up"); + SYS(fail, "ip a add %s dev gre6_dev", IP6_ADDR_GRE); + + close_netns(nstoken); + return 0; +fail: + close_netns(nstoken); + return -1; +} + +static int setup_network(char *ns1, char *ns2, char *ns3, const char *vrf) +{ + if (!ns1 || !ns2 || !ns3 || !vrf) + goto fail; + + SYS(fail, "ip -n %s link add veth1 type veth peer name veth2 netns %s", ns1, ns2); + SYS(fail, "ip -n %s link add veth3 type veth peer name veth4 netns %s", ns2, ns3); + SYS(fail, "ip -n %s link add veth5 type veth peer name veth6 netns %s", ns1, ns2); + SYS(fail, "ip -n %s link add veth7 type veth peer name veth8 netns %s", ns2, ns3); + + if (vrf[0]) { + if (!ASSERT_OK(configure_vrf(ns1, ns2), "configure vrf")) + goto fail; + } + if (!ASSERT_OK(set_top_addr(ns1, ns2, ns3), "set top addresses")) + goto fail; + + if (!ASSERT_OK(set_bottom_addr(ns1, ns2, ns3), "set bottom addresses")) + goto fail; + + if (!ASSERT_OK(configure_ns1(ns1, vrf), "configure ns1 routes")) + goto fail; + + if (!ASSERT_OK(configure_ns2(ns2, vrf), "configure ns2 routes")) + goto fail; + + if (!ASSERT_OK(configure_ns3(ns3), "configure ns3 routes")) + goto fail; + + /* Link bottom route to the GRE tunnels */ + SYS(fail, "ip -n %s route add %s/32 dev veth5 via %s %s", + ns1, IP4_ADDR_GRE, IP4_ADDR_6, vrf); + SYS(fail, "ip -n %s route add %s/32 dev veth7 via %s %s", + ns2, IP4_ADDR_GRE, IP4_ADDR_8, vrf); + SYS(fail, "ip -n %s -6 route add %s/128 dev veth5 via %s %s", + ns1, IP6_ADDR_GRE, IP6_ADDR_6, vrf); + SYS(fail, "ip -n %s -6 route add %s/128 dev veth7 via %s %s", + ns2, IP6_ADDR_GRE, IP6_ADDR_8, vrf); + + return 0; +fail: + return -1; +} + +int remove_routes_to_gredev(const char *ns1, const char *ns2, const char *vrf) +{ + SYS(fail, "ip -n %s route del %s dev veth5 %s", ns1, IP4_ADDR_GRE, vrf); + SYS(fail, "ip -n %s route del %s dev veth7 %s", ns2, IP4_ADDR_GRE, vrf); + SYS(fail, "ip -n %s -6 route del %s/128 dev veth5 %s", ns1, IP6_ADDR_GRE, vrf); + SYS(fail, "ip -n %s -6 route del %s/128 dev veth7 %s", ns2, IP6_ADDR_GRE, vrf); + + return 0; +fail: + return -1; +} + +int add_unreachable_routes_to_gredev(const char *ns1, const char *ns2, const char *vrf) +{ + SYS(fail, "ip -n %s route add unreachable %s/32 %s", ns1, IP4_ADDR_GRE, vrf); + SYS(fail, "ip -n %s route add unreachable %s/32 %s", ns2, IP4_ADDR_GRE, vrf); + SYS(fail, "ip -n %s -6 route add unreachable %s/128 %s", ns1, IP6_ADDR_GRE, vrf); + SYS(fail, "ip -n %s -6 route add unreachable %s/128 %s", ns2, IP6_ADDR_GRE, vrf); + + return 0; +fail: + return -1; +} + +#define GSO_SIZE 5000 +#define GSO_TCP_PORT 9000 +/* This tests the fix from commit ea0371f78799 ("net: fix GSO in bpf_lwt_push_ip_encap") */ +static int test_gso_fix(const char *ns1, const char *ns3, int family) +{ + const char *ip_addr = family == AF_INET ? IP4_ADDR_DST : IP6_ADDR_DST; + char gso_packet[GSO_SIZE] = {}; + struct nstoken *nstoken = NULL; + int sfd, cfd, afd; + ssize_t bytes; + int ret = -1; + + if (!ns1 || !ns3) + return ret; + + nstoken = open_netns(ns3); + if (!ASSERT_OK_PTR(nstoken, "open ns3")) + return ret; + + sfd = start_server_str(family, SOCK_STREAM, ip_addr, GSO_TCP_PORT, NULL); + if (!ASSERT_OK_FD(sfd, "start server")) + goto close_netns; + + close_netns(nstoken); + + nstoken = open_netns(ns1); + if (!ASSERT_OK_PTR(nstoken, "open ns1")) + goto close_server; + + cfd = connect_to_addr_str(family, SOCK_STREAM, ip_addr, GSO_TCP_PORT, NULL); + if (!ASSERT_OK_FD(cfd, "connect to server")) + goto close_server; + + close_netns(nstoken); + nstoken = NULL; + + afd = accept(sfd, NULL, NULL); + if (!ASSERT_OK_FD(afd, "accept")) + goto close_client; + + /* Send a packet larger than MTU */ + bytes = send(cfd, gso_packet, GSO_SIZE, 0); + if (!ASSERT_EQ(bytes, GSO_SIZE, "send packet")) + goto close_accept; + + /* Verify we received all expected bytes */ + bytes = read(afd, gso_packet, GSO_SIZE); + if (!ASSERT_EQ(bytes, GSO_SIZE, "receive packet")) + goto close_accept; + + ret = 0; + +close_accept: + close(afd); +close_client: + close(cfd); +close_server: + close(sfd); +close_netns: + close_netns(nstoken); + + return ret; +} + +static int check_ping_ok(const char *ns1) +{ + SYS(fail, "ip netns exec %s ping -c 1 -W1 -I veth1 %s > /dev/null", ns1, IP4_ADDR_DST); + SYS(fail, "ip netns exec %s ping6 -c 1 -W1 -I veth1 %s > /dev/null", ns1, IP6_ADDR_DST); + return 0; +fail: + return -1; +} + +static int check_ping_fails(const char *ns1) +{ + int ret; + + ret = SYS_NOFAIL("ip netns exec %s ping -c 1 -W1 -I veth1 %s", ns1, IP4_ADDR_DST); + if (!ret) + return -1; + + ret = SYS_NOFAIL("ip netns exec %s ping6 -c 1 -W1 -I veth1 %s", ns1, IP6_ADDR_DST); + if (!ret) + return -1; + + return 0; +} + +#define EGRESS true +#define INGRESS false +#define IPV4_ENCAP true +#define IPV6_ENCAP false +static void lwt_ip_encap(bool ipv4_encap, bool egress, const char *vrf) +{ + char ns1[NETNS_NAME_SIZE] = NETNS_BASE "-1-"; + char ns2[NETNS_NAME_SIZE] = NETNS_BASE "-2-"; + char ns3[NETNS_NAME_SIZE] = NETNS_BASE "-3-"; + char *sec = ipv4_encap ? "encap_gre" : "encap_gre6"; + + if (!vrf) + return; + + if (!ASSERT_OK(create_ns(ns1, NETNS_NAME_SIZE), "create ns1")) + goto out; + if (!ASSERT_OK(create_ns(ns2, NETNS_NAME_SIZE), "create ns2")) + goto out; + if (!ASSERT_OK(create_ns(ns3, NETNS_NAME_SIZE), "create ns3")) + goto out; + + if (!ASSERT_OK(setup_network(ns1, ns2, ns3, vrf), "setup network")) + goto out; + + /* By default, pings work */ + if (!ASSERT_OK(check_ping_ok(ns1), "ping OK")) + goto out; + + /* Remove NS2->DST routes, ping fails */ + SYS(out, "ip -n %s route del %s/32 dev veth3 %s", ns2, IP4_ADDR_DST, vrf); + SYS(out, "ip -n %s -6 route del %s/128 dev veth3 %s", ns2, IP6_ADDR_DST, vrf); + if (!ASSERT_OK(check_ping_fails(ns1), "ping expected fail")) + goto out; + + /* Install replacement routes (LWT/eBPF), pings succeed */ + if (egress) { + SYS(out, "ip -n %s route add %s encap bpf xmit obj %s sec %s dev veth1 %s", + ns1, IP4_ADDR_DST, BPF_FILE, sec, vrf); + SYS(out, "ip -n %s -6 route add %s encap bpf xmit obj %s sec %s dev veth1 %s", + ns1, IP6_ADDR_DST, BPF_FILE, sec, vrf); + } else { + SYS(out, "ip -n %s route add %s encap bpf in obj %s sec %s dev veth2 %s", + ns2, IP4_ADDR_DST, BPF_FILE, sec, vrf); + SYS(out, "ip -n %s -6 route add %s encap bpf in obj %s sec %s dev veth2 %s", + ns2, IP6_ADDR_DST, BPF_FILE, sec, vrf); + } + + if (!ASSERT_OK(check_ping_ok(ns1), "ping OK")) + goto out; + + /* Skip GSO tests with VRF: VRF routing needs properly assigned + * source IP/device, which is easy to do with ping but hard with TCP. + */ + if (egress && !vrf[0]) { + if (!ASSERT_OK(test_gso_fix(ns1, ns3, AF_INET), "test GSO")) + goto out; + } + + /* Negative test: remove routes to GRE devices: ping fails */ + if (!ASSERT_OK(remove_routes_to_gredev(ns1, ns2, vrf), "remove routes to gredev")) + goto out; + if (!ASSERT_OK(check_ping_fails(ns1), "ping expected fail")) + goto out; + + /* Another negative test */ + if (!ASSERT_OK(add_unreachable_routes_to_gredev(ns1, ns2, vrf), + "add unreachable routes")) + goto out; + ASSERT_OK(check_ping_fails(ns1), "ping expected fail"); + +out: + SYS_NOFAIL("ip netns del %s", ns1); + SYS_NOFAIL("ip netns del %s", ns2); + SYS_NOFAIL("ip netns del %s", ns3); +} + +void test_lwt_ip_encap_vrf_ipv6(void) +{ + if (test__start_subtest("egress")) + lwt_ip_encap(IPV6_ENCAP, EGRESS, "vrf red"); + + if (test__start_subtest("ingress")) + lwt_ip_encap(IPV6_ENCAP, INGRESS, "vrf red"); +} + +void test_lwt_ip_encap_vrf_ipv4(void) +{ + if (test__start_subtest("egress")) + lwt_ip_encap(IPV4_ENCAP, EGRESS, "vrf red"); + + if (test__start_subtest("ingress")) + lwt_ip_encap(IPV4_ENCAP, INGRESS, "vrf red"); +} + +void test_lwt_ip_encap_ipv6(void) +{ + if (test__start_subtest("egress")) + lwt_ip_encap(IPV6_ENCAP, EGRESS, ""); + + if (test__start_subtest("ingress")) + lwt_ip_encap(IPV6_ENCAP, INGRESS, ""); +} + +void test_lwt_ip_encap_ipv4(void) +{ + if (test__start_subtest("egress")) + lwt_ip_encap(IPV4_ENCAP, EGRESS, ""); + + if (test__start_subtest("ingress")) + lwt_ip_encap(IPV4_ENCAP, INGRESS, ""); +} diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh deleted file mode 100755 index 1e565f47aca940d8dc7235d823c48537d7a708b8..0000000000000000000000000000000000000000 --- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh +++ /dev/null @@ -1,476 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# Setup/topology: -# -# NS1 NS2 NS3 -# veth1 <---> veth2 veth3 <---> veth4 (the top route) -# veth5 <---> veth6 veth7 <---> veth8 (the bottom route) -# -# each vethN gets IPv[4|6]_N address -# -# IPv*_SRC = IPv*_1 -# IPv*_DST = IPv*_4 -# -# all tests test pings from IPv*_SRC to IPv*_DST -# -# by default, routes are configured to allow packets to go -# IP*_1 <=> IP*_2 <=> IP*_3 <=> IP*_4 (the top route) -# -# a GRE device is installed in NS3 with IPv*_GRE, and -# NS1/NS2 are configured to route packets to IPv*_GRE via IP*_8 -# (the bottom route) -# -# Tests: -# -# 1. routes NS2->IPv*_DST are brought down, so the only way a ping -# from IP*_SRC to IP*_DST can work is via IPv*_GRE -# -# 2a. in an egress test, a bpf LWT_XMIT program is installed on veth1 -# that encaps the packets with an IP/GRE header to route to IPv*_GRE -# -# ping: SRC->[encap at veth1:egress]->GRE:decap->DST -# ping replies go DST->SRC directly -# -# 2b. in an ingress test, a bpf LWT_IN program is installed on veth2 -# that encaps the packets with an IP/GRE header to route to IPv*_GRE -# -# ping: SRC->[encap at veth2:ingress]->GRE:decap->DST -# ping replies go DST->SRC directly - -BPF_FILE="test_lwt_ip_encap.bpf.o" -if [[ $EUID -ne 0 ]]; then - echo "This script must be run as root" - echo "FAIL" - exit 1 -fi - -readonly NS1="ns1-$(mktemp -u XXXXXX)" -readonly NS2="ns2-$(mktemp -u XXXXXX)" -readonly NS3="ns3-$(mktemp -u XXXXXX)" - -readonly IPv4_1="172.16.1.100" -readonly IPv4_2="172.16.2.100" -readonly IPv4_3="172.16.3.100" -readonly IPv4_4="172.16.4.100" -readonly IPv4_5="172.16.5.100" -readonly IPv4_6="172.16.6.100" -readonly IPv4_7="172.16.7.100" -readonly IPv4_8="172.16.8.100" -readonly IPv4_GRE="172.16.16.100" - -readonly IPv4_SRC=$IPv4_1 -readonly IPv4_DST=$IPv4_4 - -readonly IPv6_1="fb01::1" -readonly IPv6_2="fb02::1" -readonly IPv6_3="fb03::1" -readonly IPv6_4="fb04::1" -readonly IPv6_5="fb05::1" -readonly IPv6_6="fb06::1" -readonly IPv6_7="fb07::1" -readonly IPv6_8="fb08::1" -readonly IPv6_GRE="fb10::1" - -readonly IPv6_SRC=$IPv6_1 -readonly IPv6_DST=$IPv6_4 - -TEST_STATUS=0 -TESTS_SUCCEEDED=0 -TESTS_FAILED=0 - -TMPFILE="" - -process_test_results() -{ - if [[ "${TEST_STATUS}" -eq 0 ]] ; then - echo "PASS" - TESTS_SUCCEEDED=$((TESTS_SUCCEEDED+1)) - else - echo "FAIL" - TESTS_FAILED=$((TESTS_FAILED+1)) - fi -} - -print_test_summary_and_exit() -{ - echo "passed tests: ${TESTS_SUCCEEDED}" - echo "failed tests: ${TESTS_FAILED}" - if [ "${TESTS_FAILED}" -eq "0" ] ; then - exit 0 - else - exit 1 - fi -} - -setup() -{ - set -e # exit on error - TEST_STATUS=0 - - # create devices and namespaces - ip netns add "${NS1}" - ip netns add "${NS2}" - ip netns add "${NS3}" - - # rp_filter gets confused by what these tests are doing, so disable it - ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${NS1} sysctl -wq net.ipv4.conf.default.rp_filter=0 - ip netns exec ${NS2} sysctl -wq net.ipv4.conf.default.rp_filter=0 - ip netns exec ${NS3} sysctl -wq net.ipv4.conf.default.rp_filter=0 - - # disable IPv6 DAD because it sometimes takes too long and fails tests - ip netns exec ${NS1} sysctl -wq net.ipv6.conf.all.accept_dad=0 - ip netns exec ${NS2} sysctl -wq net.ipv6.conf.all.accept_dad=0 - ip netns exec ${NS3} sysctl -wq net.ipv6.conf.all.accept_dad=0 - ip netns exec ${NS1} sysctl -wq net.ipv6.conf.default.accept_dad=0 - ip netns exec ${NS2} sysctl -wq net.ipv6.conf.default.accept_dad=0 - ip netns exec ${NS3} sysctl -wq net.ipv6.conf.default.accept_dad=0 - - ip link add veth1 type veth peer name veth2 - ip link add veth3 type veth peer name veth4 - ip link add veth5 type veth peer name veth6 - ip link add veth7 type veth peer name veth8 - - ip netns exec ${NS2} sysctl -wq net.ipv4.ip_forward=1 - ip netns exec ${NS2} sysctl -wq net.ipv6.conf.all.forwarding=1 - - ip link set veth1 netns ${NS1} - ip link set veth2 netns ${NS2} - ip link set veth3 netns ${NS2} - ip link set veth4 netns ${NS3} - ip link set veth5 netns ${NS1} - ip link set veth6 netns ${NS2} - ip link set veth7 netns ${NS2} - ip link set veth8 netns ${NS3} - - if [ ! -z "${VRF}" ] ; then - ip -netns ${NS1} link add red type vrf table 1001 - ip -netns ${NS1} link set red up - ip -netns ${NS1} route add table 1001 unreachable default metric 8192 - ip -netns ${NS1} -6 route add table 1001 unreachable default metric 8192 - ip -netns ${NS1} link set veth1 vrf red - ip -netns ${NS1} link set veth5 vrf red - - ip -netns ${NS2} link add red type vrf table 1001 - ip -netns ${NS2} link set red up - ip -netns ${NS2} route add table 1001 unreachable default metric 8192 - ip -netns ${NS2} -6 route add table 1001 unreachable default metric 8192 - ip -netns ${NS2} link set veth2 vrf red - ip -netns ${NS2} link set veth3 vrf red - ip -netns ${NS2} link set veth6 vrf red - ip -netns ${NS2} link set veth7 vrf red - fi - - # configure addesses: the top route (1-2-3-4) - ip -netns ${NS1} addr add ${IPv4_1}/24 dev veth1 - ip -netns ${NS2} addr add ${IPv4_2}/24 dev veth2 - ip -netns ${NS2} addr add ${IPv4_3}/24 dev veth3 - ip -netns ${NS3} addr add ${IPv4_4}/24 dev veth4 - ip -netns ${NS1} -6 addr add ${IPv6_1}/128 nodad dev veth1 - ip -netns ${NS2} -6 addr add ${IPv6_2}/128 nodad dev veth2 - ip -netns ${NS2} -6 addr add ${IPv6_3}/128 nodad dev veth3 - ip -netns ${NS3} -6 addr add ${IPv6_4}/128 nodad dev veth4 - - # configure addresses: the bottom route (5-6-7-8) - ip -netns ${NS1} addr add ${IPv4_5}/24 dev veth5 - ip -netns ${NS2} addr add ${IPv4_6}/24 dev veth6 - ip -netns ${NS2} addr add ${IPv4_7}/24 dev veth7 - ip -netns ${NS3} addr add ${IPv4_8}/24 dev veth8 - ip -netns ${NS1} -6 addr add ${IPv6_5}/128 nodad dev veth5 - ip -netns ${NS2} -6 addr add ${IPv6_6}/128 nodad dev veth6 - ip -netns ${NS2} -6 addr add ${IPv6_7}/128 nodad dev veth7 - ip -netns ${NS3} -6 addr add ${IPv6_8}/128 nodad dev veth8 - - ip -netns ${NS1} link set dev veth1 up - ip -netns ${NS2} link set dev veth2 up - ip -netns ${NS2} link set dev veth3 up - ip -netns ${NS3} link set dev veth4 up - ip -netns ${NS1} link set dev veth5 up - ip -netns ${NS2} link set dev veth6 up - ip -netns ${NS2} link set dev veth7 up - ip -netns ${NS3} link set dev veth8 up - - # configure routes: IP*_SRC -> veth1/IP*_2 (= top route) default; - # the bottom route to specific bottom addresses - - # NS1 - # top route - ip -netns ${NS1} route add ${IPv4_2}/32 dev veth1 ${VRF} - ip -netns ${NS1} route add default dev veth1 via ${IPv4_2} ${VRF} # go top by default - ip -netns ${NS1} -6 route add ${IPv6_2}/128 dev veth1 ${VRF} - ip -netns ${NS1} -6 route add default dev veth1 via ${IPv6_2} ${VRF} # go top by default - # bottom route - ip -netns ${NS1} route add ${IPv4_6}/32 dev veth5 ${VRF} - ip -netns ${NS1} route add ${IPv4_7}/32 dev veth5 via ${IPv4_6} ${VRF} - ip -netns ${NS1} route add ${IPv4_8}/32 dev veth5 via ${IPv4_6} ${VRF} - ip -netns ${NS1} -6 route add ${IPv6_6}/128 dev veth5 ${VRF} - ip -netns ${NS1} -6 route add ${IPv6_7}/128 dev veth5 via ${IPv6_6} ${VRF} - ip -netns ${NS1} -6 route add ${IPv6_8}/128 dev veth5 via ${IPv6_6} ${VRF} - - # NS2 - # top route - ip -netns ${NS2} route add ${IPv4_1}/32 dev veth2 ${VRF} - ip -netns ${NS2} route add ${IPv4_4}/32 dev veth3 ${VRF} - ip -netns ${NS2} -6 route add ${IPv6_1}/128 dev veth2 ${VRF} - ip -netns ${NS2} -6 route add ${IPv6_4}/128 dev veth3 ${VRF} - # bottom route - ip -netns ${NS2} route add ${IPv4_5}/32 dev veth6 ${VRF} - ip -netns ${NS2} route add ${IPv4_8}/32 dev veth7 ${VRF} - ip -netns ${NS2} -6 route add ${IPv6_5}/128 dev veth6 ${VRF} - ip -netns ${NS2} -6 route add ${IPv6_8}/128 dev veth7 ${VRF} - - # NS3 - # top route - ip -netns ${NS3} route add ${IPv4_3}/32 dev veth4 - ip -netns ${NS3} route add ${IPv4_1}/32 dev veth4 via ${IPv4_3} - ip -netns ${NS3} route add ${IPv4_2}/32 dev veth4 via ${IPv4_3} - ip -netns ${NS3} -6 route add ${IPv6_3}/128 dev veth4 - ip -netns ${NS3} -6 route add ${IPv6_1}/128 dev veth4 via ${IPv6_3} - ip -netns ${NS3} -6 route add ${IPv6_2}/128 dev veth4 via ${IPv6_3} - # bottom route - ip -netns ${NS3} route add ${IPv4_7}/32 dev veth8 - ip -netns ${NS3} route add ${IPv4_5}/32 dev veth8 via ${IPv4_7} - ip -netns ${NS3} route add ${IPv4_6}/32 dev veth8 via ${IPv4_7} - ip -netns ${NS3} -6 route add ${IPv6_7}/128 dev veth8 - ip -netns ${NS3} -6 route add ${IPv6_5}/128 dev veth8 via ${IPv6_7} - ip -netns ${NS3} -6 route add ${IPv6_6}/128 dev veth8 via ${IPv6_7} - - # configure IPv4 GRE device in NS3, and a route to it via the "bottom" route - ip -netns ${NS3} tunnel add gre_dev mode gre remote ${IPv4_1} local ${IPv4_GRE} ttl 255 - ip -netns ${NS3} link set gre_dev up - ip -netns ${NS3} addr add ${IPv4_GRE} dev gre_dev - ip -netns ${NS1} route add ${IPv4_GRE}/32 dev veth5 via ${IPv4_6} ${VRF} - ip -netns ${NS2} route add ${IPv4_GRE}/32 dev veth7 via ${IPv4_8} ${VRF} - - - # configure IPv6 GRE device in NS3, and a route to it via the "bottom" route - ip -netns ${NS3} -6 tunnel add name gre6_dev mode ip6gre remote ${IPv6_1} local ${IPv6_GRE} ttl 255 - ip -netns ${NS3} link set gre6_dev up - ip -netns ${NS3} -6 addr add ${IPv6_GRE} nodad dev gre6_dev - ip -netns ${NS1} -6 route add ${IPv6_GRE}/128 dev veth5 via ${IPv6_6} ${VRF} - ip -netns ${NS2} -6 route add ${IPv6_GRE}/128 dev veth7 via ${IPv6_8} ${VRF} - - TMPFILE=$(mktemp /tmp/test_lwt_ip_encap.XXXXXX) - - sleep 1 # reduce flakiness - set +e -} - -cleanup() -{ - if [ -f ${TMPFILE} ] ; then - rm ${TMPFILE} - fi - - ip netns del ${NS1} 2> /dev/null - ip netns del ${NS2} 2> /dev/null - ip netns del ${NS3} 2> /dev/null -} - -trap cleanup EXIT - -remove_routes_to_gredev() -{ - ip -netns ${NS1} route del ${IPv4_GRE} dev veth5 ${VRF} - ip -netns ${NS2} route del ${IPv4_GRE} dev veth7 ${VRF} - ip -netns ${NS1} -6 route del ${IPv6_GRE}/128 dev veth5 ${VRF} - ip -netns ${NS2} -6 route del ${IPv6_GRE}/128 dev veth7 ${VRF} -} - -add_unreachable_routes_to_gredev() -{ - ip -netns ${NS1} route add unreachable ${IPv4_GRE}/32 ${VRF} - ip -netns ${NS2} route add unreachable ${IPv4_GRE}/32 ${VRF} - ip -netns ${NS1} -6 route add unreachable ${IPv6_GRE}/128 ${VRF} - ip -netns ${NS2} -6 route add unreachable ${IPv6_GRE}/128 ${VRF} -} - -test_ping() -{ - local readonly PROTO=$1 - local readonly EXPECTED=$2 - local RET=0 - - if [ "${PROTO}" == "IPv4" ] ; then - ip netns exec ${NS1} ping -c 1 -W 1 -I veth1 ${IPv4_DST} 2>&1 > /dev/null - RET=$? - elif [ "${PROTO}" == "IPv6" ] ; then - ip netns exec ${NS1} ping6 -c 1 -W 1 -I veth1 ${IPv6_DST} 2>&1 > /dev/null - RET=$? - else - echo " test_ping: unknown PROTO: ${PROTO}" - TEST_STATUS=1 - fi - - if [ "0" != "${RET}" ]; then - RET=1 - fi - - if [ "${EXPECTED}" != "${RET}" ] ; then - echo " test_ping failed: expected: ${EXPECTED}; got ${RET}" - TEST_STATUS=1 - fi -} - -test_gso() -{ - local readonly PROTO=$1 - local readonly PKT_SZ=5000 - local IP_DST="" - : > ${TMPFILE} # trim the capture file - - # check that nc is present - command -v nc >/dev/null 2>&1 || \ - { echo >&2 "nc is not available: skipping TSO tests"; return; } - - # listen on port 9000, capture TCP into $TMPFILE - if [ "${PROTO}" == "IPv4" ] ; then - IP_DST=${IPv4_DST} - ip netns exec ${NS3} bash -c \ - "nc -4 -l -p 9000 > ${TMPFILE} &" - elif [ "${PROTO}" == "IPv6" ] ; then - IP_DST=${IPv6_DST} - ip netns exec ${NS3} bash -c \ - "nc -6 -l -p 9000 > ${TMPFILE} &" - RET=$? - else - echo " test_gso: unknown PROTO: ${PROTO}" - TEST_STATUS=1 - fi - sleep 1 # let nc start listening - - # send a packet larger than MTU - ip netns exec ${NS1} bash -c \ - "dd if=/dev/zero bs=$PKT_SZ count=1 > /dev/tcp/${IP_DST}/9000 2>/dev/null" - sleep 2 # let the packet get delivered - - # verify we received all expected bytes - SZ=$(stat -c %s ${TMPFILE}) - if [ "$SZ" != "$PKT_SZ" ] ; then - echo " test_gso failed: ${PROTO}" - TEST_STATUS=1 - fi -} - -test_egress() -{ - local readonly ENCAP=$1 - echo "starting egress ${ENCAP} encap test ${VRF}" - setup - - # by default, pings work - test_ping IPv4 0 - test_ping IPv6 0 - - # remove NS2->DST routes, ping fails - ip -netns ${NS2} route del ${IPv4_DST}/32 dev veth3 ${VRF} - ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3 ${VRF} - test_ping IPv4 1 - test_ping IPv6 1 - - # install replacement routes (LWT/eBPF), pings succeed - if [ "${ENCAP}" == "IPv4" ] ; then - ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj \ - ${BPF_FILE} sec encap_gre dev veth1 ${VRF} - ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj \ - ${BPF_FILE} sec encap_gre dev veth1 ${VRF} - elif [ "${ENCAP}" == "IPv6" ] ; then - ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj \ - ${BPF_FILE} sec encap_gre6 dev veth1 ${VRF} - ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj \ - ${BPF_FILE} sec encap_gre6 dev veth1 ${VRF} - else - echo " unknown encap ${ENCAP}" - TEST_STATUS=1 - fi - test_ping IPv4 0 - test_ping IPv6 0 - - # skip GSO tests with VRF: VRF routing needs properly assigned - # source IP/device, which is easy to do with ping and hard with dd/nc. - if [ -z "${VRF}" ] ; then - test_gso IPv4 - test_gso IPv6 - fi - - # a negative test: remove routes to GRE devices: ping fails - remove_routes_to_gredev - test_ping IPv4 1 - test_ping IPv6 1 - - # another negative test - add_unreachable_routes_to_gredev - test_ping IPv4 1 - test_ping IPv6 1 - - cleanup - process_test_results -} - -test_ingress() -{ - local readonly ENCAP=$1 - echo "starting ingress ${ENCAP} encap test ${VRF}" - setup - - # need to wait a bit for IPv6 to autoconf, otherwise - # ping6 sometimes fails with "unable to bind to address" - - # by default, pings work - test_ping IPv4 0 - test_ping IPv6 0 - - # remove NS2->DST routes, pings fail - ip -netns ${NS2} route del ${IPv4_DST}/32 dev veth3 ${VRF} - ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3 ${VRF} - test_ping IPv4 1 - test_ping IPv6 1 - - # install replacement routes (LWT/eBPF), pings succeed - if [ "${ENCAP}" == "IPv4" ] ; then - ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj \ - ${BPF_FILE} sec encap_gre dev veth2 ${VRF} - ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj \ - ${BPF_FILE} sec encap_gre dev veth2 ${VRF} - elif [ "${ENCAP}" == "IPv6" ] ; then - ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj \ - ${BPF_FILE} sec encap_gre6 dev veth2 ${VRF} - ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj \ - ${BPF_FILE} sec encap_gre6 dev veth2 ${VRF} - else - echo "FAIL: unknown encap ${ENCAP}" - TEST_STATUS=1 - fi - test_ping IPv4 0 - test_ping IPv6 0 - - # a negative test: remove routes to GRE devices: ping fails - remove_routes_to_gredev - test_ping IPv4 1 - test_ping IPv6 1 - - # another negative test - add_unreachable_routes_to_gredev - test_ping IPv4 1 - test_ping IPv6 1 - - cleanup - process_test_results -} - -VRF="" -test_egress IPv4 -test_egress IPv6 -test_ingress IPv4 -test_ingress IPv6 - -VRF="vrf red" -test_egress IPv4 -test_egress IPv6 -test_ingress IPv4 -test_ingress IPv6 - -print_test_summary_and_exit --- base-commit: 5fd21aaac37919abc5c5d0df1eb06a9f02518f27 change-id: 20250206-lwt_ip-b6a91d2787bf Best regards, -- Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com>

4 months, 1 week

2
1
0 0

[PATCH] selftests/nolibc: stop testing constructor order

by Thomas Weißschuh

The execution order of constructors in undefined and depends on the toolchain. While recent toolchains seems to have a stable order, it doesn't work for older ones and may also change at any time. Stop validating the order and instead only validate that all constructors are executed. Reported-by: Willy Tarreau <w(a)1wt.eu> Closes: https://lore.kernel.org/lkml/20250301110735.GA18621@1wt.eu/ Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- tools/testing/selftests/nolibc/nolibc-test-linkage.c | 6 +++--- tools/testing/selftests/nolibc/nolibc-test.c | 8 ++++---- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/nolibc/nolibc-test-linkage.c b/tools/testing/selftests/nolibc/nolibc-test-linkage.c index 5ff4c8a1db2a46cf3f8cb55bdabaa5e8819b344c..a7ca8325863face9cd4134a717fe4c7761bdeb7f 100644 --- a/tools/testing/selftests/nolibc/nolibc-test-linkage.c +++ b/tools/testing/selftests/nolibc/nolibc-test-linkage.c @@ -11,16 +11,16 @@ void *linkage_test_errno_addr(void) return &errno; } -int linkage_test_constructor_test_value; +int linkage_test_constructor_test_value = 0; __attribute__((constructor)) static void constructor1(void) { - linkage_test_constructor_test_value = 2; + linkage_test_constructor_test_value |= 1 << 0; } __attribute__((constructor)) static void constructor2(void) { - linkage_test_constructor_test_value *= 3; + linkage_test_constructor_test_value |= 1 << 1; } diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index a5abf16dbfe0f2aed286964fdfc391bc6201ef3b..5884a891c491544050fc35b07322c73a1a9dbaf3 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -692,14 +692,14 @@ int expect_strtox(int llen, void *func, const char *input, int base, intmax_t ex __attribute__((constructor)) static void constructor1(void) { - constructor_test_value = 1; + constructor_test_value |= 1 << 0; } __attribute__((constructor)) static void constructor2(int argc, char **argv, char **envp) { if (argc && argv && envp) - constructor_test_value *= 2; + constructor_test_value |= 1 << 1; } int run_startup(int min, int max) @@ -738,9 +738,9 @@ int run_startup(int min, int max) CASE_TEST(environ_HOME); EXPECT_PTRNZ(1, getenv("HOME")); break; CASE_TEST(auxv_addr); EXPECT_PTRGT(test_auxv != (void *)-1, test_auxv, brk); break; CASE_TEST(auxv_AT_UID); EXPECT_EQ(1, getauxval(AT_UID), getuid()); break; - CASE_TEST(constructor); EXPECT_EQ(is_nolibc, constructor_test_value, 2); break; + CASE_TEST(constructor); EXPECT_EQ(is_nolibc, constructor_test_value, 0x3); break; CASE_TEST(linkage_errno); EXPECT_PTREQ(1, linkage_test_errno_addr(), &errno); break; - CASE_TEST(linkage_constr); EXPECT_EQ(is_nolibc, linkage_test_constructor_test_value, 6); break; + CASE_TEST(linkage_constr); EXPECT_EQ(1, linkage_test_constructor_test_value, 0x3); break; case __LINE__: return ret; /* must be last */ /* note: do not set any defaults so as to permit holes above */ --- base-commit: 6e406202a44a1a37176da0333cec10d5320c4b33 change-id: 20250306-nolibc-constructor-order-6921e8c93591 Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

4 months, 1 week

2
1
0 0

[PATCH v2] selftests: livepatch: test if ftrace can trace a livepatched function

by Filipe Xavier

This new test makes sure that ftrace can trace a function that was introduced by a livepatch. Signed-off-by: Filipe Xavier <felipeaggger(a)gmail.com> --- Changes in v2: - functions.sh: added reset tracing on push and pop_config. - test-ftrace.sh: enabled tracing_on before test init. - nitpick: added double quotations on filenames and fixed some wording. - Link to v1: https://lore.kernel.org/r/20250102-ftrace-selftest-livepatch-v1-1-84880baef… --- tools/testing/selftests/livepatch/functions.sh | 14 ++++++++++ tools/testing/selftests/livepatch/test-ftrace.sh | 33 ++++++++++++++++++++++++ 2 files changed, 47 insertions(+) diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index e5d06fb402335d85959bafe099087effc6ddce12..e6c13514002dae5f8d7461f90b8241ab43024ea4 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -62,6 +62,9 @@ function push_config() { awk -F'[: ]' '{print "file " $1 " line " $2 " " $4}') FTRACE_ENABLED=$(sysctl --values kernel.ftrace_enabled) KPROBE_ENABLED=$(cat "$SYSFS_KPROBES_DIR/enabled") + TRACING_ON=$(cat "$SYSFS_DEBUG_DIR/tracing/tracing_on") + CURRENT_TRACER=$(cat "$SYSFS_DEBUG_DIR/tracing/current_tracer") + FTRACE_FILTER=$(cat "$SYSFS_DEBUG_DIR/tracing/set_ftrace_filter") } function pop_config() { @@ -74,6 +77,17 @@ function pop_config() { if [[ -n "$KPROBE_ENABLED" ]]; then echo "$KPROBE_ENABLED" > "$SYSFS_KPROBES_DIR/enabled" fi + if [[ -n "$TRACING_ON" ]]; then + echo "$TRACING_ON" > "$SYSFS_DEBUG_DIR/tracing/tracing_on" + fi + if [[ -n "$CURRENT_TRACER" ]]; then + echo "$CURRENT_TRACER" > "$SYSFS_DEBUG_DIR/tracing/current_tracer" + fi + if [[ "$FTRACE_FILTER" == *"#"* ]]; then + echo > "$SYSFS_DEBUG_DIR/tracing/set_ftrace_filter" + elif [[ -n "$FTRACE_FILTER" ]]; then + echo "$FTRACE_FILTER" > "$SYSFS_DEBUG_DIR/tracing/set_ftrace_filter" + fi } function set_dynamic_debug() { diff --git a/tools/testing/selftests/livepatch/test-ftrace.sh b/tools/testing/selftests/livepatch/test-ftrace.sh index fe14f248913acbec46fb6c0fec38a2fc84209d39..66af5d726c52e48e5177804e182b4ff31784d5ac 100755 --- a/tools/testing/selftests/livepatch/test-ftrace.sh +++ b/tools/testing/selftests/livepatch/test-ftrace.sh @@ -61,4 +61,37 @@ livepatch: '$MOD_LIVEPATCH': unpatching complete % rmmod $MOD_LIVEPATCH" +# - verify livepatch can load +# - check if traces have a patched function +# - unload livepatch and reset trace + +start_test "trace livepatched function and check that the live patch remains in effect" + +TRACE_FILE="$SYSFS_DEBUG_DIR/tracing/trace" +FUNCTION_NAME="livepatch_cmdline_proc_show" + +load_lp $MOD_LIVEPATCH + +echo 1 > "$SYSFS_DEBUG_DIR/tracing/tracing_on" +echo $FUNCTION_NAME > "$SYSFS_DEBUG_DIR/tracing/set_ftrace_filter" +echo "function" > "$SYSFS_DEBUG_DIR/tracing/current_tracer" +echo "" > "$TRACE_FILE" + +if [[ "$(cat /proc/cmdline)" != "$MOD_LIVEPATCH: this has been live patched" ]] ; then + echo -e "FAIL\n\n" + die "livepatch kselftest(s) failed" +fi + +grep -q $FUNCTION_NAME "$TRACE_FILE" +FOUND=$? + +disable_lp $MOD_LIVEPATCH +unload_lp $MOD_LIVEPATCH + +if [ "$FOUND" -eq 1 ]; then + echo -e "FAIL\n\n" + die "livepatch kselftest(s) failed" +fi + + exit 0 --- base-commit: fc033cf25e612e840e545f8d5ad2edd6ba613ed5 change-id: 20250101-ftrace-selftest-livepatch-161fb77dbed8 Best regards, -- Filipe Xavier <felipeaggger(a)gmail.com>

4 months, 1 week

4
4
0 0

[PATCH v3 1/5] tools/nolibc: add support for openat(2)

by Louis Taylor

openat is useful to avoid needing to construct relative paths, so expose a wrapper for using it directly. Signed-off-by: Louis Taylor <louis(a)kragniz.eu> --- tools/include/nolibc/sys.h | 25 ++++++++++++++++++++ tools/testing/selftests/nolibc/nolibc-test.c | 17 +++++++++++++ 2 files changed, 42 insertions(+) diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index 8f44c33b1213..3cd938f9abda 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -765,6 +765,31 @@ int mount(const char *src, const char *tgt, return __sysret(sys_mount(src, tgt, fst, flags, data)); } +/* + * int openat(int dirfd, const char *path, int flags[, mode_t mode]); + */ + +static __attribute__((unused)) +int sys_openat(int dirfd, const char *path, int flags, mode_t mode) +{ + return my_syscall4(__NR_openat, dirfd, path, flags, mode); +} + +static __attribute__((unused)) +int openat(int dirfd, const char *path, int flags, ...) +{ + mode_t mode = 0; + + if (flags & O_CREAT) { + va_list args; + + va_start(args, flags); + mode = va_arg(args, mode_t); + va_end(args); + } + + return __sysret(sys_openat(dirfd, path, flags, mode)); +} /* * int open(const char *path, int flags[, mode_t mode]); diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index 79c3e6a845f3..e8faddcecf9d 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -1028,6 +1028,22 @@ int test_rlimit(void) return 0; } +int test_openat(void) +{ + int dev, null; + + dev = openat(AT_FDCWD, "/dev", O_DIRECTORY); + if (dev < 0) + return -1; + + null = openat(dev, "null", O_RDONLY); + close(dev); + if (null < 0) + return -1; + + close(null); + return 0; +} /* Run syscall tests between IDs <min> and <max>. * Return 0 on success, non-zero on failure. @@ -1116,6 +1132,7 @@ int run_syscall(int min, int max) CASE_TEST(mmap_munmap_good); EXPECT_SYSZR(1, test_mmap_munmap()); break; CASE_TEST(open_tty); EXPECT_SYSNE(1, tmp = open("/dev/null", 0), -1); if (tmp != -1) close(tmp); break; CASE_TEST(open_blah); EXPECT_SYSER(1, tmp = open("/proc/self/blah", 0), -1, ENOENT); if (tmp != -1) close(tmp); break; + CASE_TEST(openat_dir); EXPECT_SYSZR(1, test_openat()); break; CASE_TEST(pipe); EXPECT_SYSZR(1, test_pipe()); break; CASE_TEST(poll_null); EXPECT_SYSZR(1, poll(NULL, 0, 0)); break; CASE_TEST(poll_stdout); EXPECT_SYSNE(1, ({ struct pollfd fds = { 1, POLLOUT, 0}; poll(&fds, 1, 0); }), -1); break; -- 2.45.2

4 months, 1 week

2
2
0 0

[PATCH bpf-next v5 0/6] XDP metadata support for tun driver

by Marcus Wichelmann

Hi all, this v5 of the patch series is very similar to v4, but rebased onto the bpf-next/net branch instead of bpf-next/master. Because the commit c047e0e0e435 ("selftests/bpf: Optionally open a dedicated namespace to run test in it") is not yet included in this branch, I changed the xdp_context_tuntap test to manually create a namespace to run the test in. Not so successful pipeline: https://github.com/kernel-patches/bpf/actions/runs/13682405154 The CI pipeline failed because of veristat changes in seemingly unrelated eBPF programs. I don't think this has to do with the changes from this patch series, but if it does, please let me know what I may have to do different to make the CI pass. --- v5: - rebase onto bpf-next/net - resolve rebase conflicts - change xdp_context_tuntap test to manually create and open a network namespace using netns_new v4: https://lore.kernel.org/bpf/20250227142330.1605996-1-marcus.wichelmann@hetz… - strip unrelated changes from the selftest patches - extend commit message for "selftests/bpf: refactor xdp_context_functional test and bpf program" - the NOARP flag was not effective to prevent other packets from interfering with the tests, add a filter to the XDP program instead - run xdp_context_tuntap in a separate namespace to avoid conflicts with other tests v3: https://lore.kernel.org/bpf/20250224152909.3911544-1-marcus.wichelmann@hetz… - change the condition to handle xdp_buffs without metadata support, as suggested by Willem de Bruijn <willemb(a)google.com> - add clarifying comment why that condition is needed - set NOARP flag in selftests to ensure that the kernel does not send packets on the test interfaces that may interfere with the tests v2: https://lore.kernel.org/bpf/20250217172308.3291739-1-marcus.wichelmann@hetz… - submit against bpf-next subtree - split commits and improved commit messages - remove redundant metasize check and add clarifying comment instead - use max() instead of ternary operator - add selftest for metadata support in the tun driver v1: https://lore.kernel.org/all/20250130171614.1657224-1-marcus.wichelmann@hetz… Marcus Wichelmann (6): net: tun: enable XDP metadata support net: tun: enable transfer of XDP metadata to skb selftests/bpf: move open_tuntap to network helpers selftests/bpf: refactor xdp_context_functional test and bpf program selftests/bpf: add test for XDP metadata support in tun driver selftests/bpf: fix file descriptor assertion in open_tuntap helper drivers/net/tun.c | 28 +++- tools/testing/selftests/bpf/network_helpers.c | 28 ++++ tools/testing/selftests/bpf/network_helpers.h | 3 + .../selftests/bpf/prog_tests/lwt_helpers.h | 29 ---- .../bpf/prog_tests/xdp_context_test_run.c | 145 +++++++++++++++++- .../selftests/bpf/progs/test_xdp_meta.c | 53 +++++-- 6 files changed, 230 insertions(+), 56 deletions(-) -- 2.43.0

4 months, 1 week

2
7
0 0

[PATCH v2 1/5] tools/nolibc: add support for openat(2)

by Louis Taylor

openat is useful to avoid needing to construct relative paths, so expose a wrapper for using it directly. Signed-off-by: Louis Taylor <louis(a)kragniz.eu> --- tools/include/nolibc/sys.h | 25 ++++++++++++++++++++ tools/testing/selftests/nolibc/nolibc-test.c | 21 ++++++++++++++++ 2 files changed, 46 insertions(+) diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index 8f44c33b1213..3cd938f9abda 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -765,6 +765,31 @@ int mount(const char *src, const char *tgt, return __sysret(sys_mount(src, tgt, fst, flags, data)); } +/* + * int openat(int dirfd, const char *path, int flags[, mode_t mode]); + */ + +static __attribute__((unused)) +int sys_openat(int dirfd, const char *path, int flags, mode_t mode) +{ + return my_syscall4(__NR_openat, dirfd, path, flags, mode); +} + +static __attribute__((unused)) +int openat(int dirfd, const char *path, int flags, ...) +{ + mode_t mode = 0; + + if (flags & O_CREAT) { + va_list args; + + va_start(args, flags); + mode = va_arg(args, mode_t); + va_end(args); + } + + return __sysret(sys_openat(dirfd, path, flags, mode)); +} /* * int open(const char *path, int flags[, mode_t mode]); diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index 79c3e6a845f3..2a1629938dd6 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -1028,6 +1028,26 @@ int test_rlimit(void) return 0; } +static int test_openat(void) +{ + int dev; + int null; + + dev = openat(AT_FDCWD, "/dev", O_DIRECTORY); + if (dev < 0) + return -1; + + null = openat(dev, "null", 0); + if (null < 0) { + close(dev); + return -1; + } + + close(dev); + close(null); + + return 0; +} /* Run syscall tests between IDs <min> and <max>. * Return 0 on success, non-zero on failure. @@ -1116,6 +1136,7 @@ int run_syscall(int min, int max) CASE_TEST(mmap_munmap_good); EXPECT_SYSZR(1, test_mmap_munmap()); break; CASE_TEST(open_tty); EXPECT_SYSNE(1, tmp = open("/dev/null", 0), -1); if (tmp != -1) close(tmp); break; CASE_TEST(open_blah); EXPECT_SYSER(1, tmp = open("/proc/self/blah", 0), -1, ENOENT); if (tmp != -1) close(tmp); break; + CASE_TEST(openat_dir); EXPECT_SYSNE(1, test_openat(), -1); break; CASE_TEST(pipe); EXPECT_SYSZR(1, test_pipe()); break; CASE_TEST(poll_null); EXPECT_SYSZR(1, poll(NULL, 0, 0)); break; CASE_TEST(poll_stdout); EXPECT_SYSNE(1, ({ struct pollfd fds = { 1, POLLOUT, 0}; poll(&fds, 1, 0); }), -1); break; -- 2.45.2

4 months, 1 week

3
8
0 0

[PATCH] kunit: tool: Fix bug in parsing test plan

by Rae Moar

A bug was identified where the KTAP below caused an infinite loop: TAP version 13 ok 4 test_case 1..4 The infinite loop was caused by the parser not parsing a test plan if following a test result line. Fix bug to correctly parse test plan and add error if test plan is missing. Signed-off-by: Rae Moar <rmoar(a)google.com> --- tools/testing/kunit/kunit_parser.py | 12 +++++++----- tools/testing/kunit/kunit_tool_test.py | 5 ++--- 2 files changed, 9 insertions(+), 8 deletions(-) diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index 29fc27e8949b..5dcbc670e1dc 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -761,20 +761,22 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: test.name = "main" ktap_line = parse_ktap_header(lines, test, printer) test.log.extend(parse_diagnostic(lines)) - parse_test_plan(lines, test) + plan_line = parse_test_plan(lines, test) parent_test = True else: # If not the main test, attempt to parse a test header containing # the KTAP version line and/or subtest header line ktap_line = parse_ktap_header(lines, test, printer) subtest_line = parse_test_header(lines, test) + test.log.extend(parse_diagnostic(lines)) + plan_line = parse_test_plan(lines, test) parent_test = (ktap_line or subtest_line) if parent_test: - # If KTAP version line and/or subtest header is found, attempt - # to parse test plan and print test header - test.log.extend(parse_diagnostic(lines)) - parse_test_plan(lines, test) print_test_header(test, printer) + + if parent_test and not plan_line: + test.add_error(printer, 'missing test plan!') + expected_count = test.expected_count subtests = [] test_num = 1 diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 0bcb0cc002f8..e1e142c1a850 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -181,8 +181,7 @@ class KUnitParserTest(unittest.TestCase): result = kunit_parser.parse_run_tests( kunit_parser.extract_tap_lines( file.readlines()), stdout) - # A missing test plan is not an error. - self.assertEqual(result.counts, kunit_parser.TestCounts(passed=10, errors=0)) + self.assertEqual(result.counts, kunit_parser.TestCounts(passed=10, errors=2)) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) def test_no_tests(self): @@ -203,7 +202,7 @@ class KUnitParserTest(unittest.TestCase): self.assertEqual( kunit_parser.TestStatus.NO_TESTS, result.subtests[0].subtests[0].status) - self.assertEqual(result.counts, kunit_parser.TestCounts(passed=1, errors=1)) + self.assertEqual(result.counts, kunit_parser.TestCounts(passed=1, errors=2)) def test_no_kunit_output(self): base-commit: 0619a4868fc1b32b07fb9ed6c69adc5e5cf4e4b2 -- 2.48.1.711.g2feabab25a-goog

4 months, 1 week

3
5
0 0

[PATCH v8 0/4] scanf: convert self-test to KUnit

by Tamir Duberstein

This is one of just 3 remaining "Test Module" kselftests (the others being bitmap and printf), the rest having been converted to KUnit. In addition to the enclosed patch, please consider this an RFC on the removal of the "Test Module" kselftest machinery. I tested this using: $ tools/testing/kunit/kunit.py run --arch arm64 --make_options LLVM=1 scanf Failure output before this series: [ 383.100048] test_scanf: vsscanf("1574 9 64ca 935b 7 142d ff58 0", "%4hx %1hx %4hx %4hx %1hx %4hx %4hx %1hx", ...) expected 2472240330 got 1690959881 [ 383.102843] test_scanf: vsscanf("f12:2:d:2:c166:1:36b:1906", "%3hx:%1hx:%1hx:%1hx:%4hx:%1hx:%3hx:%4hx", ...) expected 131085 got 851970 [ 383.105376] test_scanf: vsscanf("4,b2fe,3,593,6,0,3bde,0", "%1hx,%4hx,%1hx,%3hx,%1hx,%1hx,%4hx,%1hx", ...) expected 93519875 got 242430 [ 383.105659] test_scanf: vsscanf("6-1-2-1-d9e6-f-93e-e567", "%1hx-%1hx-%1hx-%1hx-%4hx-%1hx-%3hx-%4hx", ...) expected 65538 got 131073 [ 383.106127] test_scanf: vsscanf("72d6/35/e88d/1/0/6c8c/7/1", "%4hx/%2hx/%4hx/%1hx/%1hx/%4hx/%1hx/%1hx", ...) expected 125069 got 3901554741 [ 383.106235] test_scanf: vsscanf("c9bea1b8122113e9a168df573", "%4hx%4hx%1hx%4hx%4hx%1hx%4hx%3hx", ...) expected 571539457 got 106936 ... [ 383.106398] test_scanf: failed 6 out of 2545 tests Failure output after this series: # numbers_list_field_width_val_width: ASSERTION FAILED at lib/scanf_kunit.c:94 lib/scanf_kunit.c:555: vsscanf("0 1e 3e43 31f0 0 0 5797 9c70", "%1hx %2hx %4hx %4hx %1hx %1hx %4hx %4hx", ...) expected 837828163 got 1044578334 not ok 1 " " # numbers_list_field_width_val_width: ASSERTION FAILED at lib/scanf_kunit.c:94 lib/scanf_kunit.c:555: vsscanf("dc2:1c:0:3531:2621:5172:1:7", "%3hx:%2hx:%1hx:%4hx:%4hx:%4hx:%1hx:%1hx", ...) expected 892403712 got 28 not ok 2 ":" # numbers_list_field_width_val_width: ASSERTION FAILED at lib/scanf_kunit.c:94 lib/scanf_kunit.c:555: vsscanf("e083,8f6e,b,70ca,1,1,aab1,10e4", "%4hx,%4hx,%1hx,%4hx,%1hx,%1hx,%4hx,%4hx", ...) expected 1892286475 got 757614 not ok 3 "," # numbers_list_field_width_val_width: ASSERTION FAILED at lib/scanf_kunit.c:94 lib/scanf_kunit.c:555: vsscanf("2e72-8435-1-2fc-7cbd-c2f1-7158-2b41", "%4hx-%4hx-%1hx-%3hx-%4hx-%4hx-%4hx-%4hx", ...) expected 50069505 got 99381 not ok 4 "-" # numbers_list_field_width_val_width: ASSERTION FAILED at lib/scanf_kunit.c:94 lib/scanf_kunit.c:555: vsscanf("403/0/17/1/11e7/1/1fe8/34ba", "%3hx/%1hx/%2hx/%1hx/%4hx/%1hx/%4hx/%4hx", ...) expected 65559 got 1507328 not ok 5 "/" Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- Changes in v8: - Expand "scanf: remove redundant debug logs" commit message. (Andy Shevchenko) - Add patch "implicate test line in failure messages". - Rebase on linux-next, move scanf_kunit.c into lib/tests/. - Link to v7: https://lore.kernel.org/r/20250211-scanf-kunit-convert-v7-0-c057f0a3d9d8@gm… Changes in v7: - Remove redundant debug logs. (Petr Mladek) - Drop Petr's Acked-by. - Use original test assertions as KUNIT_*_EQ_MSG produces hard-to-parse messages. The new failure output is: - Link to v6: https://lore.kernel.org/r/20250210-scanf-kunit-convert-v6-0-4d583d07f92d@gm… Changes in v6: - s/at boot/at runtime/ for consistency with the printf series. - Go back to kmalloc. (Geert Uytterhoeven) - Link to v5: https://lore.kernel.org/r/20250210-scanf-kunit-convert-v5-0-8e64f3a7de99@gm… Changes in v5: - Remove extraneous trailing newlines from failure messages. - Replace `pr_debug` with `kunit_printk`. - Use static char arrays instead of kmalloc. - Drop KUnit boilerplate from CONFIG_SCANF_KUNIT_TEST help text. - Drop arch changes. - Link to v4: https://lore.kernel.org/r/20250207-scanf-kunit-convert-v4-0-a23e2afaede8@gm… Changes in v4: - Bake `test` into various macros, greatly reducing diff noise. - Revert control flow changes. - Link to v3: https://lore.kernel.org/r/20250204-scanf-kunit-convert-v3-0-386d7c3ee714@gm… Changes in v3: - Reduce diff noise in lib/Makefile. (Petr Mladek) - Split `scanf_test` into a few test cases. New output: : =================== scanf (10 subtests) ==================== : [PASSED] numbers_simple : ====================== numbers_list ======================= : [PASSED] delim=" " : [PASSED] delim=":" : [PASSED] delim="," : [PASSED] delim="-" : [PASSED] delim="/" : ================== [PASSED] numbers_list =================== : ============ numbers_list_field_width_typemax ============= : [PASSED] delim=" " : [PASSED] delim=":" : [PASSED] delim="," : [PASSED] delim="-" : [PASSED] delim="/" : ======== [PASSED] numbers_list_field_width_typemax ========= : =========== numbers_list_field_width_val_width ============ : [PASSED] delim=" " : [PASSED] delim=":" : [PASSED] delim="," : [PASSED] delim="-" : [PASSED] delim="/" : ======= [PASSED] numbers_list_field_width_val_width ======== : [PASSED] numbers_slice : [PASSED] numbers_prefix_overflow : [PASSED] test_simple_strtoull : [PASSED] test_simple_strtoll : [PASSED] test_simple_strtoul : [PASSED] test_simple_strtol : ====================== [PASSED] scanf ====================== : ============================================================ : Testing complete. Ran 22 tests: passed: 22 : Elapsed time: 5.517s total, 0.001s configuring, 5.440s building, 0.067s running - Link to v2: https://lore.kernel.org/r/20250203-scanf-kunit-convert-v2-1-277a618d804e@gm… Changes in v2: - Rename lib/{test_scanf.c => scanf_kunit.c}. (Andy Shevchenko) - Link to v1: https://lore.kernel.org/r/20250131-scanf-kunit-convert-v1-1-0976524f0eba@gm… --- Tamir Duberstein (4): scanf: implicate test line in failure messages scanf: remove redundant debug logs scanf: convert self-test to KUnit scanf: break kunit into test cases MAINTAINERS | 2 +- lib/Kconfig.debug | 12 +- lib/Makefile | 1 - lib/tests/Makefile | 1 + lib/{test_scanf.c => tests/scanf_kunit.c} | 299 +++++++++++++++--------------- tools/testing/selftests/lib/Makefile | 2 +- tools/testing/selftests/lib/config | 1 - tools/testing/selftests/lib/scanf.sh | 4 - 8 files changed, 160 insertions(+), 162 deletions(-) --- base-commit: 7b7a883c7f4de1ee5040bd1c32aabaafde54d209 change-id: 20250131-scanf-kunit-convert-f70dc33bb34c Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

4 months, 1 week

4
19
0 0

[PATCH net-next v7 0/6] tun: Introduce virtio-net hashing feature

by Akihiko Odaki

virtio-net have two usage of hashes: one is RSS and another is hash reporting. Conventionally the hash calculation was done by the VMM. However, computing the hash after the queue was chosen defeats the purpose of RSS. Another approach is to use eBPF steering program. This approach has another downside: it cannot report the calculated hash due to the restrictive nature of eBPF. Introduce the code to compute hashes to the kernel in order to overcome thse challenges. An alternative solution is to extend the eBPF steering program so that it will be able to report to the userspace, but it is based on context rewrites, which is in feature freeze. We can adopt kfuncs, but they will not be UAPIs. We opt to ioctl to align with other relevant UAPIs (KVM and vhost_net). The patches for QEMU to use this new feature was submitted as RFC and is available at: https://patchew.org/QEMU/20240915-hash-v3-0-79cb08d28647@daynix.com/ This work was presented at LPC 2024: https://lpc.events/event/18/contributions/1963/ V1 -> V2: Changed to introduce a new BPF program type. Signed-off-by: Akihiko Odaki <akihiko.odaki(a)daynix.com> --- Changes in v7: - Ensured to set hash_report to VIRTIO_NET_HASH_REPORT_NONE for VHOST_NET_F_VIRTIO_NET_HDR. - s/4/sizeof(u32)/ in patch "virtio_net: Add functions for hashing". - Added tap_skb_cb type. - Rebased. - Link to v6: https://lore.kernel.org/r/20250109-rss-v6-0-b1c90ad708f6@daynix.com Changes in v6: - Extracted changes to fill vnet header holes into another series. - Squashed patches "skbuff: Introduce SKB_EXT_TUN_VNET_HASH", "tun: Introduce virtio-net hash reporting feature", and "tun: Introduce virtio-net RSS" into patch "tun: Introduce virtio-net hash feature". - Dropped the RFC tag. - Link to v5: https://lore.kernel.org/r/20241008-rss-v5-0-f3cf68df005d@daynix.com Changes in v5: - Fixed a compilation error with CONFIG_TUN_VNET_CROSS_LE. - Optimized the calculation of the hash value according to: https://git.dpdk.org/dpdk/commit/?id=3fb1ea032bd6ff8317af5dac9af901f1f324ca… - Added patch "tun: Unify vnet implementation". - Dropped patch "tap: Pad virtio header with zero". - Added patch "selftest: tun: Test vnet ioctls without device". - Reworked selftests to skip for older kernels. - Documented the case when the underlying device is deleted and packets have queue_mapping set by TC. - Reordered test harness arguments. - Added code to handle fragmented packets. - Link to v4: https://lore.kernel.org/r/20240924-rss-v4-0-84e932ec0e6c@daynix.com Changes in v4: - Moved tun_vnet_hash_ext to if_tun.h. - Renamed virtio_net_toeplitz() to virtio_net_toeplitz_calc(). - Replaced htons() with cpu_to_be16(). - Changed virtio_net_hash_rss() to return void. - Reordered variable declarations in virtio_net_hash_rss(). - Removed virtio_net_hdr_v1_hash_from_skb(). - Updated messages of "tap: Pad virtio header with zero" and "tun: Pad virtio header with zero". - Fixed vnet_hash allocation size. - Ensured to free vnet_hash when destructing tun_struct. - Link to v3: https://lore.kernel.org/r/20240915-rss-v3-0-c630015db082@daynix.com Changes in v3: - Reverted back to add ioctl. - Split patch "tun: Introduce virtio-net hashing feature" into "tun: Introduce virtio-net hash reporting feature" and "tun: Introduce virtio-net RSS". - Changed to reuse hash values computed for automq instead of performing RSS hashing when hash reporting is requested but RSS is not. - Extracted relevant data from struct tun_struct to keep it minimal. - Added kernel-doc. - Changed to allow calling TUNGETVNETHASHCAP before TUNSETIFF. - Initialized num_buffers with 1. - Added a test case for unclassified packets. - Fixed error handling in tests. - Changed tests to verify that the queue index will not overflow. - Rebased. - Link to v2: https://lore.kernel.org/r/20231015141644.260646-1-akihiko.odaki@daynix.com --- Akihiko Odaki (6): virtio_net: Add functions for hashing net: flow_dissector: Export flow_keys_dissector_symmetric tun: Introduce virtio-net hash feature selftest: tun: Test vnet ioctls without device selftest: tun: Add tests for virtio-net hashing vhost/net: Support VIRTIO_NET_F_HASH_REPORT Documentation/networking/tuntap.rst | 7 + drivers/net/Kconfig | 1 + drivers/net/tap.c | 62 +++- drivers/net/tun.c | 89 ++++- drivers/net/tun_vnet.h | 180 +++++++++- drivers/vhost/net.c | 49 +-- include/linux/if_tap.h | 2 + include/linux/skbuff.h | 3 + include/linux/virtio_net.h | 188 +++++++++++ include/net/flow_dissector.h | 1 + include/uapi/linux/if_tun.h | 75 +++++ net/core/flow_dissector.c | 3 +- net/core/skbuff.c | 4 + tools/testing/selftests/net/Makefile | 2 +- tools/testing/selftests/net/tun.c | 627 ++++++++++++++++++++++++++++++++++- 15 files changed, 1231 insertions(+), 62 deletions(-) --- base-commit: dd83757f6e686a2188997cb58b5975f744bb7786 change-id: 20240403-rss-e737d89efa77 prerequisite-change-id: 20241230-tun-66e10a49b0c7:v6 prerequisite-patch-id: 871dc5f146fb6b0e3ec8612971a8e8190472c0fb prerequisite-patch-id: 2797ed249d32590321f088373d4055ff3f430a0e prerequisite-patch-id: ea3370c72d4904e2f0536ec76ba5d26784c0cede prerequisite-patch-id: 837e4cf5d6b451424f9b1639455e83a260c4440d prerequisite-patch-id: ea701076f57819e844f5a35efe5cbc5712d3080d prerequisite-patch-id: 701646fb43ad04cc64dd2bf13c150ccbe6f828ce prerequisite-patch-id: 53176dae0c003f5b6c114d43f936cf7140d31bb5 prerequisite-change-id: 20250116-buffers-96e14bf023fc:v2 prerequisite-patch-id: 25fd4f99d4236a05a5ef16ab79f3e85ee57e21cc Best regards, -- Akihiko Odaki <akihiko.odaki(a)daynix.com>

4 months, 1 week

4
12
0 0

Re: [brauner-github:vfs.all 205/231] WARNING: modpost: vmlinux: section mismatch in reference: initramfs_test_cases+0x0 (section: .data) -> initramfs_test_extract (section: .init.text)

by David Disseldorp

[cc'ing linux-kselftest and kunit-dev] Hi, On Wed, 5 Mar 2025 01:47:55 +0800, kernel test robot wrote: > tree: https://github.com/brauner/linux.git vfs.all > head: ea47e99a3a234837d5fea0d1a20bb2ad1eaa6dd4 > commit: b6736cfccb582b7c016cba6cd484fbcf30d499af [205/231] initramfs_test: kunit tests for initramfs unpacking > config: x86_64-buildonly-randconfig-002-20250304 (https://download.01.org/0day-ci/archive/20250305/202503050109.t5Ab93hX-lkp@…) > compiler: gcc-12 (Debian 12.2.0-14) 12.2.0 > reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250305/202503050109.t5Ab93hX-lkp@…) > > If you fix the issue in a separate patch/commit (i.e. not just a new version of > the same patch/commit), kindly add following tags > | Reported-by: kernel test robot <lkp(a)intel.com> > | Closes: https://lore.kernel.org/oe-kbuild-all/202503050109.t5Ab93hX-lkp@intel.com/ > > All warnings (new ones prefixed by >>, old ones prefixed by <<): > > >> WARNING: modpost: vmlinux: section mismatch in reference: initramfs_test_cases+0x0 (section: .data) -> initramfs_test_extract (section: .init.text) > >> WARNING: modpost: vmlinux: section mismatch in reference: initramfs_test_cases+0x30 (section: .data) -> initramfs_test_fname_overrun (section: .init.text) > >> WARNING: modpost: vmlinux: section mismatch in reference: initramfs_test_cases+0x60 (section: .data) -> initramfs_test_data (section: .init.text) > >> WARNING: modpost: vmlinux: section mismatch in reference: initramfs_test_cases+0x90 (section: .data) -> initramfs_test_csum (section: .init.text) > >> WARNING: modpost: vmlinux: section mismatch in reference: initramfs_test_cases+0xc0 (section: .data) -> initramfs_test_hardlink (section: .init.text) > >> WARNING: modpost: vmlinux: section mismatch in reference: initramfs_test_cases+0xf0 (section: .data) -> initramfs_test_many (section: .init.text) These new warnings are covered in the commit message. The kunit_test_init_section_suites() registered tests aren't in the .init section as debugfs entries are retained for results reporting (without an ability to rerun them). IIUC, the __kunit_init_test_suites->CONCATENATE(..., _probe) suffix is intended to suppress the modpost warning - @kunit-dev: any ideas why this isn't working as intended? Thanks, David

4 months, 1 week

3
3
0 0

[PATCH] selftests: riscv: fix v_exec_initval_nolibc.c

by Ignacio Encinas

Vector registers are zero initialized by the kernel. Stop accepting "all ones" as a clean value. Note that this was not working as expected given that value == 0xff can be assumed to be always false by the compiler as value's range is [-128, 127]. Both GCC (-Wtype-limits) and clang (-Wtautological-constant-out-of-range-compare) warn about this. Signed-off-by: Ignacio Encinas <ignacio(a)iencinas.com> --- I tried looking why "all ones" was previously deemed a "clean" value but couldn't find any information. It looks like the kernel always zero-initializes the vector registers. If "all ones" is still acceptable for any reason, my intention is to spin a v2 changing the types of `value` and `prev_value` to unsigned char. --- tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c index 35c0812e32de0c82a54f84bd52c4272507121e35..b712c4d258a6cb045aa96de4a75299714866f5e6 100644 --- a/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c +++ b/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c @@ -6,7 +6,7 @@ * the values. To further ensure consistency, this file is compiled without * libc and without auto-vectorization. * - * To be "clean" all values must be either all ones or all zeroes. + * To be "clean" all values must be all zeroes. */ #define __stringify_1(x...) #x @@ -46,7 +46,7 @@ int main(int argc, char **argv) : "=r" (value)); \ if (first) { \ first = 0; \ - } else if (value != prev_value || !(value == 0x00 || value == 0xff)) { \ + } else if (value != prev_value || value != 0x00) { \ printf("Register " __stringify(register) \ " values not clean! value: %u\n", value); \ exit(-1); \ --- base-commit: 03d38806a902b36bf364cae8de6f1183c0a35a67 change-id: 20250301-fix-v_exec_initval_nolibc-498d976c372d Best regards, -- Ignacio Encinas <ignacio(a)iencinas.com>

4 months, 1 week

3
3
0 0

[PATCH v4 0/8] initramfs: kunit tests and cleanups

by David Disseldorp

This patchset adds basic kunit test coverage for initramfs unpacking and cleans up some minor buffer handling issues / inefficiencies. Changes since v3: - Drop shared unpack buffer changes + rework into initramfs: allocate heap buffers together (patch 5/8) + extra review complexity wasn't worth the tiny boot-time heap saving - move hardlink hash leak repro into first initramfs_test patch - add note regarding kunit section=.data -> section=.init.text warning Changes since v2 (patch 2 only): - fix !CONFIG_INITRAMFS_PRESERVE_MTIME kunit test checks - add test MODULE_DESCRIPTION(), as suggested by Jeff Johnson - add some missing headers, reported by kernel test robot Changes since v1 (RFC): - rebase atop v6.12-rc6 and filename field overrun fix from https://lore.kernel.org/r/20241030035509.20194-2-ddiss@suse.de - add unit test coverage (new patches 1 and 2) - add patch: fix hardlink hash leak without TRAILER - rework patch: avoid static buffer for error message + drop unnecessary message propagation - drop patch: cpio_buf reuse for built-in and bootloader initramfs + no good justification for the change Feedback appreciated. David Disseldorp (8): init: add initramfs_internal.h initramfs_test: kunit tests for initramfs unpacking vsprintf: add simple_strntoul initramfs: avoid memcpy for hex header fields initramfs: allocate heap buffers together initramfs: reuse name_len for dir mtime tracking initramfs: fix hardlink hash leak without TRAILER initramfs: avoid static buffer for error message include/linux/kstrtox.h | 1 + init/.kunitconfig | 3 + init/Kconfig | 7 + init/Makefile | 1 + init/initramfs.c | 66 ++++---- init/initramfs_internal.h | 8 + init/initramfs_test.c | 407 ++++++++++++++++++++++++++++++++++++++++++++++ lib/vsprintf.c | 7 + 8 files changed, 472 insertions(+), 28 deletions(-) create mode 100644 init/.kunitconfig create mode 100644 init/initramfs_internal.h create mode 100644 init/initramfs_test.c

4 months, 1 week

2
11
0 0

[PATCH] selftests: Override command line in lib.mk

by Akihiko Odaki

Documentation/dev-tools/kselftest.rst says you can use the "TARGETS" variable on the make command line to run only tests targeted for a single subsystem: $ make TARGETS="size timers" kselftest A natural way to narrow down further to a particular test in a subsystem is to specify e.g., TEST_GEN_PROGS: $ make TARGETS=net TEST_PROGS= TEST_GEN_PROGS=tun kselftest However, this does not work well because the following statement in tools/testing/selftests/lib.mk gets ignored: TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) Add the override directive to make it and similar ones will be effective even when TEST_GEN_PROGS and similar variables are specified in the command line. Signed-off-by: Akihiko Odaki <akihiko.odaki(a)daynix.com> --- tools/testing/selftests/lib.mk | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index d6edcfcb5be832ddee4c3d34b5ad221e9295f878..68116e51f97d62376c63f727ba3fd1f616c67562 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -93,9 +93,9 @@ TOOLS_INCLUDES := -isystem $(top_srcdir)/tools/include/uapi # TEST_PROGS are for test shell scripts. # TEST_CUSTOM_PROGS and TEST_PROGS will be run by common run_tests # and install targets. Common clean doesn't touch them. -TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) -TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) -TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) +override TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) +override TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) +override TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) \ $(if $(TEST_GEN_MODS_DIR),gen_mods_dir) --- base-commit: dd83757f6e686a2188997cb58b5975f744bb7786 change-id: 20250306-lib-4ac9711c10a2 Best regards, -- Akihiko Odaki <akihiko.odaki(a)daynix.com>

4 months, 1 week

1
0
0 0

[PATCHv3 net 0/2] bonding: fix incorrect mac address setting

by Hangbin Liu

The mac address on backup slave should be convert from Solicited-Node Multicast address, not from bonding unicast target address. v3: also fix the mac setting for slave_set_ns_maddr. (Jay) Add function description for slave_set_ns_maddr/slave_set_ns_maddrs (Jay) v2: fix patch 01's subject Hangbin Liu (2): bonding: fix incorrect MAC address setting to receive NS messages selftests: bonding: fix incorrect mac address drivers/net/bonding/bond_options.c | 55 ++++++++++++++++--- .../drivers/net/bonding/bond_options.sh | 4 +- 2 files changed, 49 insertions(+), 10 deletions(-) -- 2.46.0

4 months, 1 week

4
9
0 0

[PATCH bpf-next v3] selftests/Makefile: override the srctree for out-of-tree builds

by Li Zhijian

Fixes an issue where out-of-tree kselftest builds fail when building the BPF and bpftools components. The failure occurs because the top-level Makefile passes a relative srctree path to its sub-Makefiles, which leads to errors in locating necessary files. For example, the following error is encountered: ``` $ make V=1 O=$build/ TARGETS=hid kselftest-all ... make -C ../tools/testing/selftests all make[4]: Entering directory '/path/to/linux/tools/testing/selftests/hid' make -C /path/to/linux/tools/testing/selftests/../../../tools/lib/bpf OUTPUT=/path/to/linux/O/kselftest/hid/tools/build/libbpf/ \ EXTRA_CFLAGS='-g -O0' \ DESTDIR=/path/to/linux/O/kselftest/hid/tools prefix= all install_headers make[5]: Entering directory '/path/to/linux/tools/lib/bpf' ... make[5]: Entering directory '/path/to/linux/tools/bpf/bpftool' Makefile:127: ../tools/build/Makefile.feature: No such file or directory make[5]: *** No rule to make target '../tools/build/Makefile.feature'. Stop. ``` To resolve this, override the srctree in the kselftests's top Makefile when performing an out-of-tree build. This ensures that all sub-Makefiles have the correct path to the source tree, preventing directory resolution errors. Cc: Andrii Nakryiko <andrii.nakryiko(a)gmail.com> Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> Tested-by: Quentin Monnet <qmo(a)kernel.org> --- Cc: Masahiro Yamada <masahiroy(a)kernel.org> V3: collected Tested-by and rebased on bpf-next V2: - handle srctree in selftests itself rather than the linux' top Makefile # Masahiro Yamada <masahiroy(a)kernel.org> V1: https://lore.kernel.org/lkml/20241217031052.69744-1-lizhijian@fujitsu.com/ --- tools/testing/selftests/Makefile | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 2401e973c359..f04a3b0003f6 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -154,15 +154,19 @@ override LDFLAGS = override MAKEFLAGS = endif +top_srcdir ?= ../../.. + # Append kselftest to KBUILD_OUTPUT and O to avoid cluttering # KBUILD_OUTPUT with selftest objects and headers installed # by selftests Makefile or lib.mk. +# Override the `srctree` variable to ensure it is correctly resolved in +# sub-Makefiles, such as those within `bpf`, when managing targets like +# `net` and `hid`. ifdef building_out_of_srctree override LDFLAGS = +override srctree := $(top_srcdir) endif -top_srcdir ?= ../../.. - ifeq ("$(origin O)", "command line") KBUILD_OUTPUT := $(O) endif -- 2.44.0

4 months, 1 week

3
2
0 0

[PATCH v9 0/7] mseal system mappings

by jeffxu＠chromium.org

From: Jeff Xu <jeffxu(a)chromium.org> This is V9 version, addressing comments from V8, without code logic change. ------------------------------------------------------------------- As discussed during mseal() upstream process [1], mseal() protects the VMAs of a given virtual memory range against modifications, such as the read/write (RW) and no-execute (NX) bits. For complete descriptions of memory sealing, please see mseal.rst [2]. The mseal() is useful to mitigate memory corruption issues where a corrupted pointer is passed to a memory management system. For example, such an attacker primitive can break control-flow integrity guarantees since read-only memory that is supposed to be trusted can become writable or .text pages can get remapped. The system mappings are readonly only, memory sealing can protect them from ever changing to writable or unmmap/remapped as different attributes. System mappings such as vdso, vvar, vvar_vclock, vectors (arm compat-mode), sigpage (arm compat-mode), are created by the kernel during program initialization, and could be sealed after creation. Unlike the aforementioned mappings, the uprobe mapping is not established during program startup. However, its lifetime is the same as the process's lifetime [3]. It could be sealed from creation. The vsyscall on x86-64 uses a special address (0xffffffffff600000), which is outside the mm managed range. This means mprotect, munmap, and mremap won't work on the vsyscall. Since sealing doesn't enhance the vsyscall's security, it is skipped in this patch. If we ever seal the vsyscall, it is probably only for decorative purpose, i.e. showing the 'sl' flag in the /proc/pid/smaps. For this patch, it is ignored. It is important to note that the CHECKPOINT_RESTORE feature (CRIU) may alter the system mappings during restore operations. UML(User Mode Linux) and gVisor, rr are also known to change the vdso/vvar mappings. Consequently, this feature cannot be universally enabled across all systems. As such, CONFIG_MSEAL_SYSTEM_MAPPINGS is disabled by default. To support mseal of system mappings, architectures must define CONFIG_ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS and update their special mappings calls to pass mseal flag. Additionally, architectures must confirm they do not unmap/remap system mappings during the process lifetime. The existence of this flag for an architecture implies that it does not require the remapping of thest system mappings during process lifetime, so sealing these mappings is safe from a kernel perspective. This version covers x86-64 and arm64 archiecture as minimum viable feature. While no specific CPU hardware features are required for enable this feature on an archiecture, memory sealing requires a 64-bit kernel. Other architectures can choose whether or not to adopt this feature. Currently, I'm not aware of any instances in the kernel code that actively munmap/mremap a system mapping without a request from userspace. The PPC does call munmap when _install_special_mapping fails for vdso; however, it's uncertain if this will ever fail for PPC - this needs to be investigated by PPC in the future [4]. The UML kernel can add this support when KUnit tests require it [5]. In this version, we've improved the handling of system mapping sealing from previous versions, instead of modifying the _install_special_mapping function itself, which would affect all architectures, we now call _install_special_mapping with a sealing flag only within the specific architecture that requires it. This targeted approach offers two key advantages: 1) It limits the code change's impact to the necessary architectures, and 2) It aligns with the software architecture by keeping the core memory management within the mm layer, while delegating the decision of sealing system mappings to the individual architecture, which is particularly relevant since 32-bit architectures never require sealing. Prior to this patch series, we explored sealing special mappings from userspace using glibc's dynamic linker. This approach revealed several issues: - The PT_LOAD header may report an incorrect length for vdso, (smaller than its actual size). The dynamic linker, which relies on PT_LOAD information to determine mapping size, would then split and partially seal the vdso mapping. Since each architecture has its own vdso/vvar code, fixing this in the kernel would require going through each archiecture. Our initial goal was to enable sealing readonly mappings, e.g. .text, across all architectures, sealing vdso from kernel since creation appears to be simpler than sealing vdso at glibc. - The [vvar] mapping header only contains address information, not length information. Similar issues might exist for other special mappings. - Mappings like uprobe are not covered by the dynamic linker, and there is no effective solution for them. This feature's security enhancements will benefit ChromeOS, Android, and other high security systems. Testing: This feature was tested on ChromeOS and Android for both x86-64 and ARM64. - Enable sealing and verify vdso/vvar, sigpage, vector are sealed properly, i.e. "sl" shown in the smaps for those mappings, and mremap is blocked. - Passing various automation tests (e.g. pre-checkin) on ChromeOS and Android to ensure the sealing doesn't affect the functionality of Chromebook and Android phone. I also tested the feature on Ubuntu on x86-64: - With config disabled, vdso/vvar is not sealed, - with config enabled, vdso/vvar is sealed, and booting up Ubuntu is OK, normal operations such as browsing the web, open/edit doc are OK. Link: https://lore.kernel.org/all/20240415163527.626541-1-jeffxu@chromium.org/ [1] Link: Documentation/userspace-api/mseal.rst [2] Link: https://lore.kernel.org/all/CABi2SkU9BRUnqf70-nksuMCQ+yyiWjo3fM4XkRkL-NrCZx… [3] Link: https://lore.kernel.org/all/CABi2SkV6JJwJeviDLsq9N4ONvQ=EFANsiWkgiEOjyT9TQS… [4] Link: https://lore.kernel.org/all/202502251035.239B85A93@keescook/ [5] ------------------------------------------- History: V9: - Add negative test in selftest (Kees Cook) - fx typos in text (Kees Cook) V8: - Change ARCH_SUPPORTS_MSEAL_X to ARCH_SUPPORTS_MSEAL_X (Liam R. Howlett) - Update comments in Kconfig and mseal.rst (Lorenzo Stoakes, Liam R. Howlett) - Change patch header perfix to "mseal sysmap" (Lorenzo Stoakes) - Remove "vm_flags =" (Kees Cook, Liam R. Howlett, Oleg Nesterov) - Drop uml architecture (Lorenzo Stoakes, Kees Cook) - Add a selftest to verify system mappings are sealed (Lorenzo Stoakes) V7: https://lore.kernel.org/all/20250224225246.3712295-1-jeffxu@google.com/ - Remove cover letter from the first patch (Liam R. Howlett) - Change macro name to VM_SEALED_SYSMAP (Liam R. Howlett) - logging and fclose() in selftest (Liam R. Howlett) V6: https://lore.kernel.org/all/20250224174513.3600914-1-jeffxu@google.com/ - mseal.rst: fix a typo (Randy Dunlap) - security/Kconfig: add rr into note (Liam R. Howlett) - remove mseal_system_mappings() and use macro instead (Liam R. Howlett) - mseal.rst: add incompatible userland software (Lorenzo Stoakes) - remove RFC from title (Kees Cook) V5 https://lore.kernel.org/all/20250212032155.1276806-1-jeffxu@google.com/ - Remove kernel cmd line (Lorenzo Stoakes) - Add test info (Lorenzo Stoakes) - Add threat model info (Lorenzo Stoakes) - Fix x86 selftest: test_mremap_vdso - Restrict code change to ARM64/x86-64/UM arch only. - Add userprocess.h to include seal_system_mapping(). - Remove sealing vsyscall. - Split the patch. V4: https://lore.kernel.org/all/20241125202021.3684919-1-jeffxu@google.com/ - ARCH_HAS_SEAL_SYSTEM_MAPPINGS (Lorenzo Stoakes) - test info (Lorenzo Stoakes) - Update mseal.rst (Liam R. Howlett) - Update test_mremap_vdso.c (Liam R. Howlett) - Misc. style, comments, doc update (Liam R. Howlett) V3: https://lore.kernel.org/all/20241113191602.3541870-1-jeffxu@google.com/ - Revert uprobe to v1 logic (Oleg Nesterov) - use CONFIG_SEAL_SYSTEM_MAPPINGS instead of _ALWAYS/_NEVER (Kees Cook) - Move kernel cmd line from fs/exec.c to mm/mseal.c and misc. (Liam R. Howlett) V2: https://lore.kernel.org/all/20241014215022.68530-1-jeffxu@google.com/ - Seal uprobe always (Oleg Nesterov) - Update comments and description (Randy Dunlap, Liam R.Howlett, Oleg Nesterov) - Rebase to linux_main V1: - https://lore.kernel.org/all/20241004163155.3493183-1-jeffxu@google.com/ -------------------------------------------------- Jeff Xu (7): mseal sysmap: kernel config and header change selftests: x86: test_mremap_vdso: skip if vdso is msealed mseal sysmap: enable x86-64 mseal sysmap: enable arm64 mseal sysmap: uprobe mapping mseal sysmap: update mseal.rst selftest: test system mappings are sealed. Documentation/userspace-api/mseal.rst | 20 +++ arch/arm64/Kconfig | 1 + arch/arm64/kernel/vdso.c | 12 +- arch/x86/Kconfig | 1 + arch/x86/entry/vdso/vma.c | 7 +- include/linux/mm.h | 10 ++ init/Kconfig | 22 ++++ kernel/events/uprobes.c | 3 +- security/Kconfig | 21 ++++ tools/testing/selftests/Makefile | 1 + .../mseal_system_mappings/.gitignore | 2 + .../selftests/mseal_system_mappings/Makefile | 6 + .../selftests/mseal_system_mappings/config | 1 + .../mseal_system_mappings/sysmap_is_sealed.c | 119 ++++++++++++++++++ .../testing/selftests/x86/test_mremap_vdso.c | 43 +++++++ 15 files changed, 261 insertions(+), 8 deletions(-) create mode 100644 tools/testing/selftests/mseal_system_mappings/.gitignore create mode 100644 tools/testing/selftests/mseal_system_mappings/Makefile create mode 100644 tools/testing/selftests/mseal_system_mappings/config create mode 100644 tools/testing/selftests/mseal_system_mappings/sysmap_is_sealed.c -- 2.48.1.711.g2feabab25a-goog

4 months, 1 week

5
15
0 0

[PATCH 0/2] kselftest/arm64: mte: Minor fixes to the MTE hugetlb test

by Catalin Marinas

The first patch makes use of the correct terminology for synchronous and asynchronous errors. The second patch checks whether PROT_MTE is supported on hugetlb mappings before continuing with the tests. Such support was added in 6.13 but people tend to use current kselftests on older kernels. Avoid the failure reporting on such kernels, just skip the tests. Catalin Marinas (2): kselftest/arm64: mte: Use the correct naming for tag check modes in check_hugetlb_options.c kselftest/arm64: mte: Skip the hugetlb tests if MTE not supported on such mappings .../arm64/mte/check_hugetlb_options.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-)

4 months, 1 week

3
6
0 0

Re: [PATCH v8 3/4] scanf: convert self-test to KUnit

by Petr Mladek

On Sat 2025-02-15 14:52:22, Tamir Duberstein wrote: > On Sat, Feb 15, 2025 at 1:51 PM kernel test robot <lkp(a)intel.com> wrote: > > > > Hi Tamir, > > > > kernel test robot noticed the following build warnings: > > > > [auto build test WARNING on 7b7a883c7f4de1ee5040bd1c32aabaafde54d209] > > > > url: > https://github.com/intel-lab-lkp/linux/commits/Tamir-Duberstein/scanf-impli… > > base: 7b7a883c7f4de1ee5040bd1c32aabaafde54d209 > > patch link: > https://lore.kernel.org/r/20250214-scanf-kunit-convert-v8-3-5ea50f95f83c%40… > > patch subject: [PATCH v8 3/4] scanf: convert self-test to KUnit > > config: sh-randconfig-002-20250216 ( > https://download.01.org/0day-ci/archive/20250216/202502160245.KUrryBJR-lkp@… > ) > > compiler: sh4-linux-gcc (GCC) 14.2.0 > > reproduce (this is a W=1 build): ( > https://download.01.org/0day-ci/archive/20250216/202502160245.KUrryBJR-lkp@… > ) > > > > If you fix the issue in a separate patch/commit (i.e. not just a new > version of > > the same patch/commit), kindly add following tags > > | Reported-by: kernel test robot <lkp(a)intel.com> > > | Closes: > https://lore.kernel.org/oe-kbuild-all/202502160245.KUrryBJR-lkp@intel.com/ > > > > All warnings (new ones prefixed by >>): > > > > In file included from <command-line>: > > lib/tests/scanf_kunit.c: In function 'numbers_list_ll': > > >> include/linux/compiler.h:197:61: warning: function 'numbers_list_ll' > might be a candidate for 'gnu_scanf' format attribute > [-Wsuggest-attribute=format] > > I am not able to reproduce these warnings with clang 19.1.7. They also > don't obviously make sense to me. I have reproduced the problem with gcc: $> gcc --version gcc (SUSE Linux) 14.2.1 20250220 [revision 9ffecde121af883b60bbe60d00425036bc873048] $> make W=1 lib/test_scanf.ko CALL scripts/checksyscalls.sh DESCEND objtool INSTALL libsubcmd_headers CC [M] lib/test_scanf.o In file included from <command-line>: lib/test_scanf.c: In function ‘numbers_list_ll’: ./include/linux/compiler.h:197:61: warning: function ‘numbers_list_ll’ might be a candidate for ‘gnu_scanf’ format attribute [-Wsuggest-attribute=format] 197 | #define __BUILD_BUG_ON_ZERO_MSG(e, msg) ((int)sizeof(struct {_Static_assert(!(e), msg);})) | ^ [...] It seems that it is a regression introduced by the first patch of this patch set. And the fix is: diff --git a/lib/test_scanf.c b/lib/test_scanf.c index d1664e0d0138..e65b10c3dc11 100644 --- a/lib/test_scanf.c +++ b/lib/test_scanf.c @@ -27,7 +27,7 @@ static struct rnd_state rnd_state __initdata; typedef int (*check_fn)(const char *file, const int line, const void *check_data, const char *string, const char *fmt, int n_args, va_list ap); -static void __scanf(6, 0) __init +static void __scanf(6, 8) __init _test(const char *file, const int line, check_fn fn, const void *check_data, const char *string, const char *fmt, int n_args, ...) { Best Regards, Petr

4 months, 1 week

2
1
0 0

[PATCH 00/32] kselftest harness and nolibc compatibility

by Thomas Weißschuh

Nolibc is useful for selftests as the test programs can be very small, and compiled with just a kernel crosscompiler, without userspace support. Currently nolibc is only usable with kselftest.h, not the more convenient to use kselftest_harness.h This series provides this compatibility by adding new features to nolibc and removing the usage of problematic features from the harness. The first half of the series are changes to the harness, the second one are for nolibc. Both parts are very independent and can go through different trees. The last patch is not meant to be applied and serves as test that everything works correctly. Based on the next branch of the nolibc tree: https://web.git.kernel.org/pub/scm/linux/kernel/git/nolibc/linux-nolibc.git… Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- Thomas Weißschuh (32): selftests: harness: Add harness selftest selftests: harness: Use C89 comment style selftests: harness: Ignore unused variant argument warning selftests: harness: Mark functions without prototypes static selftests: harness: Remove inline qualifier for wrappers selftests: harness: Guard includes on nolibc selftests: harness: Remove dependency on libatomic selftests: harness: Implement test timeouts through pidfd selftests: harness: Don't set setup_completed for fixtureless tests selftests: harness: Always provide "self" and "variant" selftests: harness: Move teardown conditional into test metadata selftests: harness: Add teardown callback to test metadata selftests: harness: Stop using setjmp()/longjmp() tools/nolibc: handle intmax_t/uintmax_t in printf tools/nolibc: use intmax definitions from compiler tools/nolibc: use pselect6_time64 if available tools/nolibc: use ppoll_time64 if available tools/nolibc: add tolower() and toupper() tools/nolibc: add _exit() tools/nolibc: add setpgrp() tools/nolibc: implement waitpid() in terms of waitid() Revert "selftests/nolibc: use waitid() over waitpid()" tools/nolibc: add dprintf() and vdprintf() tools/nolibc: add getopt() tools/nolibc: allow different write callbacks in printf tools/nolibc: allow limiting of printf destination size tools/nolibc: add snprintf() and friends selftests/nolibc: use snprintf() for printf tests selftests/nolibc: rename vfprintf test suite selftests/nolibc: add test for snprintf() truncation tools/nolibc: implement width padding in printf() HACK: selftests/nolibc: demonstrate usage of the kselftest harness tools/include/nolibc/Makefile | 1 + tools/include/nolibc/getopt.h | 105 ++ tools/include/nolibc/nolibc.h | 1 + tools/include/nolibc/stdint.h | 4 +- tools/include/nolibc/stdio.h | 127 +- tools/include/nolibc/string.h | 17 + tools/include/nolibc/sys.h | 102 +- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/kselftest/.gitignore | 1 + tools/testing/selftests/kselftest/Makefile | 6 + .../testing/selftests/kselftest/harness-selftest.c | 129 ++ .../selftests/kselftest/harness-selftest.expected | 62 + .../selftests/kselftest/harness-selftest.sh | 14 + tools/testing/selftests/kselftest_harness.h | 188 +-- tools/testing/selftests/nolibc/Makefile | 17 +- tools/testing/selftests/nolibc/harness-selftest.c | 1 + tools/testing/selftests/nolibc/nolibc-test.c | 1712 +------------------- tools/testing/selftests/nolibc/run-tests.sh | 2 +- 18 files changed, 639 insertions(+), 1851 deletions(-) --- base-commit: cb839e0cc881b4abd4a2e64cd06c2e313987a189 change-id: 20250130-nolibc-kselftest-harness-8b2c8cac43bf Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

4 months, 1 week

2
42
0 0

[PATCH rcu 00/10] Miscellaneous RCU changes for v6.15

by Boqun Feng

Hi, Please find the upcoming miscellaneous RCU changes. The changes can also be found at: git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux.git misc.2025.03.04a Regards, Boqun Paul E. McKenney (6): rcu: Split rcu_report_exp_cpu_mult() mask parameter and use for tracing rcu: Fix get_state_synchronize_rcu_full() GP-start detection rcu-tasks: Move RCU Tasks self-tests to core_initcall() rcu/nocb: Print segment lengths in show_rcu_nocb_gp_state() context_tracking: Make RCU watch ct_kernel_exit_state() warning Flush console log from kernel_power_off() Uladzislau Rezki (Sony) (3): rcutorture: Allow a negative value for nfakewriters rcu: Update TREE05.boot to test normal synchronize_rcu() rcu: Use _full() API to debug synchronize_rcu() Zilin Guan (1): rcu: Remove READ_ONCE() for rdp->gpwrap access in __note_gp_changes() include/linux/printk.h | 6 ++++ include/linux/rcupdate.h | 6 ---- include/linux/rcupdate_wait.h | 3 ++ init/main.c | 1 - kernel/context_tracking.c | 9 +++--- kernel/printk/printk.c | 4 +-- kernel/rcu/rcu.h | 2 +- kernel/rcu/rcutorture.c | 22 ++++++++++---- kernel/rcu/tasks.h | 5 +++- kernel/rcu/tree.c | 29 +++++++++++-------- kernel/rcu/tree_exp.h | 6 ++-- kernel/rcu/tree_nocb.h | 20 +++++++++---- kernel/reboot.c | 1 + .../rcutorture/configs/rcu/TREE05.boot | 6 ++++ 14 files changed, 78 insertions(+), 42 deletions(-) -- 2.48.1

4 months, 1 week

1
10
0 0

[PATCH rcu 00/11] Lazy Preempt changes for v6.15

by Boqun Feng

Hi, Please find the upcoming changes for CONFIG_PREEMPT_LAZY in RCU. The changes can also be found at: git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux.git lazypreempt.2025.02.24a Paul & Ankur, I put patch #7 and #8 (bug fixes in rcutorture) before patch #9 (which is the one that enables non-preemptible RCU in preemptible kernel), because I want to avoid introduce a bug in-between a series, appreciate it if you can double check on this. Thanks! Regards, Boqun Ankur Arora (7): rcu: fix header guard for rcu_all_qs() rcu: rename PREEMPT_AUTO to PREEMPT_LAZY sched: update __cond_resched comment about RCU quiescent states rcu: handle unstable rdp in rcu_read_unlock_strict() rcu: handle quiescent states for PREEMPT_RCU=n, PREEMPT_COUNT=y osnoise: provide quiescent states rcu: limit PREEMPT_RCU configurations Boqun Feng (1): rcutorture: Update ->extendables check for lazy preemption Paul E. McKenney (3): rcutorture: Update rcutorture_one_extend_check() for lazy preemption rcutorture: Make scenario TREE10 build CONFIG_PREEMPT_LAZY=y rcutorture: Make scenario TREE07 build CONFIG_PREEMPT_LAZY=y include/linux/rcupdate.h | 2 +- include/linux/rcutree.h | 2 +- include/linux/srcutiny.h | 2 +- kernel/rcu/Kconfig | 4 +-- kernel/rcu/rcutorture.c | 26 ++++++++++++--- kernel/rcu/srcutiny.c | 14 ++++---- kernel/rcu/tree_plugin.h | 22 ++++++++++--- kernel/sched/core.c | 4 ++- kernel/trace/trace_osnoise.c | 32 +++++++++---------- .../selftests/rcutorture/configs/rcu/TREE07 | 3 +- .../selftests/rcutorture/configs/rcu/TREE10 | 3 +- 11 files changed, 73 insertions(+), 41 deletions(-) -- 2.39.5 (Apple Git-154)

4 months, 1 week

4
15
0 0

[PATCH net-next 1/2] selftests: drv-net: use env.rpath in the HDS test

by Jakub Kicinski

Commit 29b036be1b0b ("selftests: drv-net: test XDP, HDS auto and the ioctl path") added a new test case in the net tree, now that this code has made its way to net-next convert it to use the env.rpath() helper instead of manually computing the relative path. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- tools/testing/selftests/drivers/net/hds.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py index 873f5219e41d..7cc74faed743 100755 --- a/tools/testing/selftests/drivers/net/hds.py +++ b/tools/testing/selftests/drivers/net/hds.py @@ -20,8 +20,7 @@ from lib.py import defer, ethtool, ip def _xdp_onoff(cfg): - test_dir = os.path.dirname(os.path.realpath(__file__)) - prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o" + prog = cfg.rpath("../../net/lib/xdp_dummy.bpf.o") ip("link set dev %s xdp obj %s sec xdp" % (cfg.ifname, prog)) ip("link set dev %s xdp off" % cfg.ifname) -- 2.48.1

4 months, 1 week

3
4
0 0

[PATCH net-next 0/5] mptcp: improve code coverage and small optimisations

by Matthieu Baerts (NGI0)

This small series have various unrelated patches: - Patch 1 and 2: improve code coverage by validating mptcp_diag_dump_one thanks to a new tool displaying MPTCP info for a specific token. - Patch 3: a fix for a commit which is only in net-next. - Patch 4: reduce parameters for one in-kernel PM helper. - Patch 5: exit early when processing an ADD_ADDR echo to avoid unneeded operations. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Gang Yan (2): selftests: mptcp: Add a tool to get specific msk_info selftests: mptcp: add a test for mptcp_diag_dump_one Geliang Tang (2): mptcp: pm: in-kernel: avoid access entry without lock mptcp: pm: in-kernel: reduce parameters of set_flags Matthieu Baerts (NGI0) (1): mptcp: pm: exit early with ADD_ADDR echo if possible net/mptcp/pm.c | 3 + net/mptcp/pm_netlink.c | 15 +- tools/testing/selftests/net/mptcp/Makefile | 2 +- tools/testing/selftests/net/mptcp/diag.sh | 27 +++ tools/testing/selftests/net/mptcp/mptcp_diag.c | 272 +++++++++++++++++++++++++ 5 files changed, 311 insertions(+), 8 deletions(-) --- base-commit: 56794b5862c5a9aefcf2b703257c6fb93f76573e change-id: 20250228-net-next-mptcp-coverage-small-opti-70d8dc1d329d Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

4 months, 1 week

2
6
0 0

[PATCH] selftests/pcie_bwctrl: Add "set_pcie_speed.sh" to TEST_PROGS

by Yi Lai

The test shell script "set_pcie_speed.sh" is not installed in INSTALL_PATH. Attempting to execute set_pcie_cooling_state.sh shows warning: " ./set_pcie_cooling_state.sh: line 119: ./set_pcie_speed.sh: No such file or directory " Add "set_pcie_speed.sh" to TEST_PROGS. Fixes: 838f12c3d551 ("selftests/pcie_bwctrl: Create selftests") Signed-off-by: Yi Lai <yi1.lai(a)intel.com> --- tools/testing/selftests/pcie_bwctrl/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/pcie_bwctrl/Makefile b/tools/testing/selftests/pcie_bwctrl/Makefile index 3e84e26341d1..48ec048f47af 100644 --- a/tools/testing/selftests/pcie_bwctrl/Makefile +++ b/tools/testing/selftests/pcie_bwctrl/Makefile @@ -1,2 +1,2 @@ -TEST_PROGS = set_pcie_cooling_state.sh +TEST_PROGS = set_pcie_cooling_state.sh set_pcie_speed.sh include ../lib.mk -- 2.39.2

4 months, 1 week

2
1
0 0

[PATCH v8 0/7] mseal system mappings

by jeffxu＠chromium.org

From: Jeff Xu <jeffxu(a)google.com> This is V8 version, addressing comments from V7, without code logic change. ------------------------------------------------------------------- As discussed during mseal() upstream process [1], mseal() protects the VMAs of a given virtual memory range against modifications, such as the read/write (RW) and no-execute (NX) bits. For complete descriptions of memory sealing, please see mseal.rst [2]. The mseal() is useful to mitigate memory corruption issues where a corrupted pointer is passed to a memory management system. For example, such an attacker primitive can break control-flow integrity guarantees since read-only memory that is supposed to be trusted can become writable or .text pages can get remapped. The system mappings are readonly only, memory sealing can protect them from ever changing to writable or unmmap/remapped as different attributes. System mappings such as vdso, vvar, vvar_vclock, vectors (arm compact-mode), sigpage (arm compact-mode), are created by the kernel during program initialization, and could be sealed after creation. Unlike the aforementioned mappings, the uprobe mapping is not established during program startup. However, its lifetime is the same as the process's lifetime [3]. It could be sealed from creation. The vsyscall on x86-64 uses a special address (0xffffffffff600000), which is outside the mm managed range. This means mprotect, munmap, and mremap won't work on the vsyscall. Since sealing doesn't enhance the vsyscall's security, it is skipped in this patch. If we ever seal the vsyscall, it is probably only for decorative purpose, i.e. showing the 'sl' flag in the /proc/pid/smaps. For this patch, it is ignored. It is important to note that the CHECKPOINT_RESTORE feature (CRIU) may alter the system mappings during restore operations. UML(User Mode Linux) and gVisor, rr are also known to change the vdso/vvar mappings. Consequently, this feature cannot be universally enabled across all systems. As such, CONFIG_MSEAL_SYSTEM_MAPPINGS is disabled by default. To support mseal of system mappings, architectures must define CONFIG_ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS and update their special mappings calls to pass mseal flag. Additionally, architectures must confirm they do not unmap/remap system mappings during the process lifetime. The existence of this flag for an architecture implies that it does not require the remapping of thest system mappings during process lifetime, so sealing these mappings is safe from a kernel perspective. This version covers x86-64 and arm64 archiecture as minimum viable feature. While no specific CPU hardware features are required for enable this feature on an archiecture, memory sealing requires a 64-bit kernel. Other architectures can choose whether or not to adopt this feature. Currently, I'm not aware of any instances in the kernel code that actively munmap/mremap a system mapping without a request from userspace. The PPC does call munmap when _install_special_mapping fails for vdso; however, it's uncertain if this will ever fail for PPC - this needs to be investigated by PPC in the future [4]. The UML kernel can add this support when KUnit tests require it [5]. In this version, we've improved the handling of system mapping sealing from previous versions, instead of modifying the _install_special_mapping function itself, which would affect all architectures, we now call _install_special_mapping with a sealing flag only within the specific architecture that requires it. This targeted approach offers two key advantages: 1) It limits the code change's impact to the necessary architectures, and 2) It aligns with the software architecture by keeping the core memory management within the mm layer, while delegating the decision of sealing system mappings to the individual architecture, which is particularly relevant since 32-bit architectures never require sealing. Prior to this patch series, we explored sealing special mappings from userspace using glibc's dynamic linker. This approach revealed several issues: - The PT_LOAD header may report an incorrect length for vdso, (smaller than its actual size). The dynamic linker, which relies on PT_LOAD information to determine mapping size, would then split and partially seal the vdso mapping. Since each architecture has its own vdso/vvar code, fixing this in the kernel would require going through each archiecture. Our initial goal was to enable sealing readonly mappings, e.g. .text, across all architectures, sealing vdso from kernel since creation appears to be simpler than sealing vdso at glibc. - The [vvar] mapping header only contains address information, not length information. Similar issues might exist for other special mappings. - Mappings like uprobe are not covered by the dynamic linker, and there is no effective solution for them. This feature's security enhancements will benefit ChromeOS, Android, and other high security systems. Testing: This feature was tested on ChromeOS and Android for both x86-64 and ARM64. - Enable sealing and verify vdso/vvar, sigpage, vector are sealed properly, i.e. "sl" shown in the smaps for those mappings, and mremap is blocked. - Passing various automation tests (e.g. pre-checkin) on ChromeOS and Android to ensure the sealing doesn't affect the functionality of Chromebook and Android phone. I also tested the feature on Ubuntu on x86-64: - With config disabled, vdso/vvar is not sealed, - with config enabled, vdso/vvar is sealed, and booting up Ubuntu is OK, normal operations such as browsing the web, open/edit doc are OK. Link: https://lore.kernel.org/all/20240415163527.626541-1-jeffxu@chromium.org/ [1] Link: Documentation/userspace-api/mseal.rst [2] Link: https://lore.kernel.org/all/CABi2SkU9BRUnqf70-nksuMCQ+yyiWjo3fM4XkRkL-NrCZx… [3] Link: https://lore.kernel.org/all/CABi2SkV6JJwJeviDLsq9N4ONvQ=EFANsiWkgiEOjyT9TQS… [4] Link: https://lore.kernel.org/all/202502251035.239B85A93@keescook/ [5] ------------------------------------------- History: V8: - Change ARCH_SUPPORTS_MSEAL_X to ARCH_SUPPORTS_MSEAL_X (Liam R. Howlett) - Update comments in Kconfig and mseal.rst (Lorenzo Stoakes, Liam R. Howlett) - Change patch header perfix to "mseal sysmap" (Lorenzo Stoakes) - Remove "vm_flags =" (Kees Cook, Liam R. Howlett, Oleg Nesterov) - Drop uml architecture (Lorenzo Stoakes, Kees Cook) - Add a selftest to verify system mappings are sealed (Lorenzo Stoakes) V7: https://lore.kernel.org/all/20250224225246.3712295-1-jeffxu@google.com/ - Remove cover letter from the first patch (Liam R. Howlett) - Change macro name to VM_SEALED_SYSMAP (Liam R. Howlett) - logging and fclose() in selftest (Liam R. Howlett) V6: https://lore.kernel.org/all/20250224174513.3600914-1-jeffxu@google.com/ - mseal.rst: fix a typo (Randy Dunlap) - security/Kconfig: add rr into note (Liam R. Howlett) - remove mseal_system_mappings() and use macro instead (Liam R. Howlett) - mseal.rst: add incompatible userland software (Lorenzo Stoakes) - remove RFC from title (Kees Cook) V5 https://lore.kernel.org/all/20250212032155.1276806-1-jeffxu@google.com/ - Remove kernel cmd line (Lorenzo Stoakes) - Add test info (Lorenzo Stoakes) - Add threat model info (Lorenzo Stoakes) - Fix x86 selftest: test_mremap_vdso - Restrict code change to ARM64/x86-64/UM arch only. - Add userprocess.h to include seal_system_mapping(). - Remove sealing vsyscall. - Split the patch. V4: https://lore.kernel.org/all/20241125202021.3684919-1-jeffxu@google.com/ - ARCH_HAS_SEAL_SYSTEM_MAPPINGS (Lorenzo Stoakes) - test info (Lorenzo Stoakes) - Update mseal.rst (Liam R. Howlett) - Update test_mremap_vdso.c (Liam R. Howlett) - Misc. style, comments, doc update (Liam R. Howlett) V3: https://lore.kernel.org/all/20241113191602.3541870-1-jeffxu@google.com/ - Revert uprobe to v1 logic (Oleg Nesterov) - use CONFIG_SEAL_SYSTEM_MAPPINGS instead of _ALWAYS/_NEVER (Kees Cook) - Move kernel cmd line from fs/exec.c to mm/mseal.c and misc. (Liam R. Howlett) V2: https://lore.kernel.org/all/20241014215022.68530-1-jeffxu@google.com/ - Seal uprobe always (Oleg Nesterov) - Update comments and description (Randy Dunlap, Liam R.Howlett, Oleg Nesterov) - Rebase to linux_main V1: - https://lore.kernel.org/all/20241004163155.3493183-1-jeffxu@google.com/ -------------------------------------------------- Jeff Xu (7): mseal sysmap: kernel config and header change selftests: x86: test_mremap_vdso: skip if vdso is msealed mseal sysmap: enable x86-64 mseal sysmap: enable arm64 mseal sysmap: uprobe mapping mseal sysmap: update mseal.rst selftest: test system mappings are sealed. Documentation/userspace-api/mseal.rst | 20 ++++ arch/arm64/Kconfig | 1 + arch/arm64/kernel/vdso.c | 12 +- arch/x86/Kconfig | 1 + arch/x86/entry/vdso/vma.c | 7 +- include/linux/mm.h | 10 ++ init/Kconfig | 22 ++++ kernel/events/uprobes.c | 3 +- security/Kconfig | 21 ++++ .../mseal_system_mappings/.gitignore | 2 + .../selftests/mseal_system_mappings/Makefile | 6 + .../selftests/mseal_system_mappings/config | 1 + .../mseal_system_mappings/sysmap_is_sealed.c | 113 ++++++++++++++++++ .../testing/selftests/x86/test_mremap_vdso.c | 43 +++++++ 14 files changed, 254 insertions(+), 8 deletions(-) create mode 100644 tools/testing/selftests/mseal_system_mappings/.gitignore create mode 100644 tools/testing/selftests/mseal_system_mappings/Makefile create mode 100644 tools/testing/selftests/mseal_system_mappings/config create mode 100644 tools/testing/selftests/mseal_system_mappings/sysmap_is_sealed.c -- 2.48.1.711.g2feabab25a-goog

4 months, 1 week

6
38
0 0

[PATCH] selftests: proofreading bpf module

by Armin

Fixed multiple spelling issues in the kselftests bpf modules. Signed-off-by: Armin <Armin.Mahdilou(a)gmail.com> --- tools/testing/selftests/bpf/Makefile | 2 +- tools/testing/selftests/bpf/bench.c | 2 +- tools/testing/selftests/bpf/prog_tests/btf_dump.c | 2 +- tools/testing/selftests/bpf/prog_tests/fd_array.c | 2 +- tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c | 2 +- tools/testing/selftests/bpf/prog_tests/reg_bounds.c | 4 ++-- tools/testing/selftests/bpf/progs/bpf_cc_cubic.c | 2 +- tools/testing/selftests/bpf/progs/bpf_dctcp.c | 2 +- .../testing/selftests/bpf/progs/freplace_unreliable_prog.c | 2 +- tools/testing/selftests/bpf/progs/iters_state_safety.c | 2 +- .../testing/selftests/bpf/progs/test_cls_redirect_dynptr.c | 2 +- tools/testing/selftests/bpf/progs/test_tc_dtime.c | 2 +- tools/testing/selftests/bpf/progs/uprobe_multi_verifier.c | 6 +++--- tools/testing/selftests/bpf/progs/uretprobe_stack.c | 2 +- tools/testing/selftests/bpf/progs/verifier_loops1.c | 2 +- tools/testing/selftests/bpf/progs/verifier_scalar_ids.c | 2 +- tools/testing/selftests/bpf/test_lru_map.c | 4 ++-- tools/testing/selftests/bpf/test_lwt_ip_encap.sh | 2 +- tools/testing/selftests/bpf/test_sockmap.c | 2 +- tools/testing/selftests/bpf/verifier/calls.c | 6 +++--- tools/testing/selftests/bpf/xdping.c | 2 +- tools/testing/selftests/bpf/xsk.h | 2 +- 22 files changed, 28 insertions(+), 28 deletions(-) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 87551628e112..a66d9173609d 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -392,7 +392,7 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers endif -# vmlinux.h is first dumped to a temprorary file and then compared to +# vmlinux.h is first dumped to a temporary file and then compared to # the previous version. This helps to avoid unnecessary re-builds of # $(TRUNNER_BPF_OBJS) $(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR) diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index 1bd403a5ef7b..b25db4142126 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -497,7 +497,7 @@ extern const struct bench bench_rename_rawtp; extern const struct bench bench_rename_fentry; extern const struct bench bench_rename_fexit; -/* pure counting benchmarks to establish theoretical lmits */ +/* pure counting benchmarks to establish theoretical limits */ extern const struct bench bench_trig_usermode_count; extern const struct bench bench_trig_syscall_count; extern const struct bench bench_trig_kernel_count; diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c index b293b8501fd6..2b434038d5af 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c @@ -63,7 +63,7 @@ static int test_btf_dump_case(int n, struct btf_dump_test_case *t) /* tests with t->known_ptr_sz have no "long" or "unsigned long" type, * so it's impossible to determine correct pointer size; but if they - * do, it should be 8 regardless of host architecture, becaues BPF + * do, it should be 8 regardless of host architecture, because BPF * target is always 64-bit */ if (!t->known_ptr_sz) { diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c index a1d52e73fb16..ab0fe7add9dc 100644 --- a/tools/testing/selftests/bpf/prog_tests/fd_array.c +++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c @@ -293,7 +293,7 @@ static int get_btf_id_by_fd(int btf_fd, __u32 *id) * 1) Create a new btf, it's referenced only by a file descriptor, so refcnt=1 * 2) Load a BPF prog with fd_array[0] = btf_fd; now btf's refcnt=2 * 3) Close the btf_fd, now refcnt=1 - * Wait and check that BTF stil exists. + * Wait and check that BTF still exists. */ static void check_fd_array_cnt__referenced_btfs(void) { diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index e19ef509ebf8..f377bea0b82d 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -463,7 +463,7 @@ static bool skip_entry(char *name) return false; } -/* Do comparision by ignoring '.llvm.<hash>' suffixes. */ +/* Do comparison by ignoring '.llvm.<hash>' suffixes. */ static int compare_name(const char *name1, const char *name2) { const char *res1, *res2; diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c index 39d42271cc46..de302ecd5f58 100644 --- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c +++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c @@ -609,7 +609,7 @@ static void range_cond(enum num_t t, struct range x, struct range y, *newx = range(t, x.a, x.b); *newy = range(t, y.a + 1, y.b); } else if (x.a == x.b && x.b == y.b) { - /* X is a constant matching rigth side of Y */ + /* X is a constant matching right side of Y */ *newx = range(t, x.a, x.b); *newy = range(t, y.a, y.b - 1); } else if (y.a == y.b && x.a == y.a) { @@ -617,7 +617,7 @@ static void range_cond(enum num_t t, struct range x, struct range y, *newx = range(t, x.a + 1, x.b); *newy = range(t, y.a, y.b); } else if (y.a == y.b && x.b == y.b) { - /* Y is a constant matching rigth side of X */ + /* Y is a constant matching right side of X */ *newx = range(t, x.a, x.b - 1); *newy = range(t, y.a, y.b); } else { diff --git a/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c index 1654a530aa3d..4e51785e7606 100644 --- a/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c +++ b/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c @@ -101,7 +101,7 @@ static void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, tp->snd_cwnd = pkts_in_flight + sndcnt; } -/* Decide wheather to run the increase function of congestion control. */ +/* Decide whether to run the increase function of congestion control. */ static bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) { if (tcp_sk(sk)->reordering > TCP_REORDERING) diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c index 7cd73e75f52a..32c511bcd60b 100644 --- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c +++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ -/* WARNING: This implemenation is not necessarily the same +/* WARNING: This implementation is not necessarily the same * as the tcp_dctcp.c. The purpose is mainly for testing * the kernel BPF logic. */ diff --git a/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c b/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c index 624078abf3de..d7e30ee576c9 100644 --- a/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c +++ b/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c @@ -7,7 +7,7 @@ SEC("freplace/btf_unreliable_kprobe") /* context type is what BPF verifier expects for kprobe context, but target - * program has `stuct whatever *ctx` argument, so freplace operation will be + * program has `struct whatever *ctx` argument, so freplace operation will be * rejected with the following message: * * arg0 replace_btf_unreliable_kprobe(struct pt_regs *) doesn't match btf_unreliable_kprobe(struct whatever *) diff --git a/tools/testing/selftests/bpf/progs/iters_state_safety.c b/tools/testing/selftests/bpf/progs/iters_state_safety.c index f41257eadbb2..b381ac0c736c 100644 --- a/tools/testing/selftests/bpf/progs/iters_state_safety.c +++ b/tools/testing/selftests/bpf/progs/iters_state_safety.c @@ -345,7 +345,7 @@ int __naked read_from_iter_slot_fail(void) "r3 = 1000;" "call %[bpf_iter_num_new];" - /* attemp to leak bpf_iter_num state */ + /* attempt to leak bpf_iter_num state */ "r7 = *(u64 *)(r6 + 0);" "r8 = *(u64 *)(r6 + 8);" diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c index d0f7670351e5..dfd4a2710391 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c @@ -494,7 +494,7 @@ static ret_t get_next_hop(struct bpf_dynptr *dynptr, __u64 *offset, encap_header *offset += sizeof(*next_hop); - /* Skip the remainig next hops (may be zero). */ + /* Skip the remaining next hops (may be zero). */ return skip_next_hops(offset, encap->unigue.hop_count - encap->unigue.next_hop - 1); } diff --git a/tools/testing/selftests/bpf/progs/test_tc_dtime.c b/tools/testing/selftests/bpf/progs/test_tc_dtime.c index ca8e8734d901..f0c58519cab1 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_dtime.c +++ b/tools/testing/selftests/bpf/progs/test_tc_dtime.c @@ -21,7 +21,7 @@ * ns_src | ns_fwd | ns_dst * * ns_src and ns_dst: ENDHOST namespace - * ns_fwd: Fowarding namespace + * ns_fwd: Forwarding namespace */ #define ctx_ptr(field) (void *)(long)(field) diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_verifier.c b/tools/testing/selftests/bpf/progs/uprobe_multi_verifier.c index fe49f2cb5360..d15f49ed93f1 100644 --- a/tools/testing/selftests/bpf/progs/uprobe_multi_verifier.c +++ b/tools/testing/selftests/bpf/progs/uprobe_multi_verifier.c @@ -10,14 +10,14 @@ char _license[] SEC("license") = "GPL"; SEC("uprobe.session") __success -int uprobe_sesison_return_0(struct pt_regs *ctx) +int uprobe_session_return_0(struct pt_regs *ctx) { return 0; } SEC("uprobe.session") __success -int uprobe_sesison_return_1(struct pt_regs *ctx) +int uprobe_session_return_1(struct pt_regs *ctx) { return 1; } @@ -25,7 +25,7 @@ int uprobe_sesison_return_1(struct pt_regs *ctx) SEC("uprobe.session") __failure __msg("At program exit the register R0 has smin=2 smax=2 should have been in [0, 1]") -int uprobe_sesison_return_2(struct pt_regs *ctx) +int uprobe_session_return_2(struct pt_regs *ctx) { return 2; } diff --git a/tools/testing/selftests/bpf/progs/uretprobe_stack.c b/tools/testing/selftests/bpf/progs/uretprobe_stack.c index 9fdcf396b8f4..cbc428a80744 100644 --- a/tools/testing/selftests/bpf/progs/uretprobe_stack.c +++ b/tools/testing/selftests/bpf/progs/uretprobe_stack.c @@ -27,7 +27,7 @@ SEC("uprobe//proc/self/exe:target_1") int BPF_UPROBE(uprobe_1) { /* target_1 is recursive wit depth of 2, so we capture two separate - * stack traces, depending on which occurence it is + * stack traces, depending on which occurrence it is */ static bool recur = false; diff --git a/tools/testing/selftests/bpf/progs/verifier_loops1.c b/tools/testing/selftests/bpf/progs/verifier_loops1.c index e07b43b78fd2..cd4ee4d38cf6 100644 --- a/tools/testing/selftests/bpf/progs/verifier_loops1.c +++ b/tools/testing/selftests/bpf/progs/verifier_loops1.c @@ -261,7 +261,7 @@ l0_%=: r2 += r1; \ SEC("xdp") __success -__naked void not_an_inifinite_loop(void) +__naked void not_an_infinite_loop(void) { asm volatile (" \ call %[bpf_get_prandom_u32]; \ diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c index 7c5e5e6d10eb..dba3ca728f6e 100644 --- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c +++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c @@ -349,7 +349,7 @@ __naked void precision_two_ids(void) SEC("socket") __success __log_level(2) __flag(BPF_F_TEST_STATE_FREQ) -/* check thar r0 and r6 have different IDs after 'if', +/* check that r0 and r6 have different IDs after 'if', * collect_linked_regs() can't tie more than 6 registers for a single insn. */ __msg("8: (25) if r0 > 0x7 goto pc+0 ; R0=scalar(id=1") diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c index fda7589c5023..b80b3bc17575 100644 --- a/tools/testing/selftests/bpf/test_lru_map.c +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -306,7 +306,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) * Update 1 to tgt_free/2 * => The original 1 to tgt_free/2 will be removed due to * the LRU shrink process - * Re-insert 1 to tgt_free/2 again and do a lookup immeidately + * Re-insert 1 to tgt_free/2 again and do a lookup immediately * Insert 1+tgt_free to tgt_free*3/2 * Insert 1+tgt_free*3/2 to tgt_free*5/2 * => Key 1+tgt_free to tgt_free*3/2 @@ -371,7 +371,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) } /* Re-insert 1 to tgt_free/2 again and do a lookup - * immeidately. + * immediately. */ end_key = 1 + batch_size; value[0] = 4321; diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh index 1e565f47aca9..37c31e53cc6e 100755 --- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh +++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh @@ -164,7 +164,7 @@ setup() ip -netns ${NS2} link set veth7 vrf red fi - # configure addesses: the top route (1-2-3-4) + # configure addresses: the top route (1-2-3-4) ip -netns ${NS1} addr add ${IPv4_1}/24 dev veth1 ip -netns ${NS2} addr add ${IPv4_2}/24 dev veth2 ip -netns ${NS2} addr add ${IPv4_3}/24 dev veth3 diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index fd2da2234cc9..76568db7a664 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -1372,7 +1372,7 @@ static int run_options(struct sockmap_options *options, int cg_fd, int test) } else fprintf(stderr, "unknown test\n"); out: - /* Detatch and zero all the maps */ + /* Detach and zero all the maps */ bpf_prog_detach2(bpf_program__fd(progs[3]), cg_fd, BPF_CGROUP_SOCK_OPS); for (i = 0; i < ARRAY_SIZE(links); i++) { diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 18596ae0b0c1..e0ce0a7ed774 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -1375,7 +1375,7 @@ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), /* write into map value */ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), - /* fetch secound map_value_ptr from the stack */ + /* fetch second map_value_ptr from the stack */ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -16), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), /* write into map value */ @@ -1439,7 +1439,7 @@ /* second time with fp-16 */ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), - /* fetch secound map_value_ptr from the stack */ + /* fetch second map_value_ptr from the stack */ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0), /* write into map value */ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), @@ -1493,7 +1493,7 @@ /* second time with fp-16 */ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), - /* fetch secound map_value_ptr from the stack */ + /* fetch second map_value_ptr from the stack */ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0), /* write into map value */ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c index 1503a1d2faa0..9ed8c796645d 100644 --- a/tools/testing/selftests/bpf/xdping.c +++ b/tools/testing/selftests/bpf/xdping.c @@ -155,7 +155,7 @@ int main(int argc, char **argv) } if (!server) { - /* Only supports IPv4; see hints initiailization above. */ + /* Only supports IPv4; see hints initialization above. */ if (getaddrinfo(argv[optind], NULL, &hints, &a) || !a) { fprintf(stderr, "Could not resolve %s\n", argv[optind]); return 1; diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h index 93c2cc413cfc..73d01518bf84 100644 --- a/tools/testing/selftests/bpf/xsk.h +++ b/tools/testing/selftests/bpf/xsk.h @@ -94,7 +94,7 @@ static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb) * cached_cons is r->size bigger than the real consumer pointer so * that this addition can be avoided in the more frequently * executed code that computs free_entries in the beginning of - * this function. Without this optimization it whould have been + * this function. Without this optimization it would have been * free_entries = r->cached_prod - r->cached_cons + r->size. */ r->cached_cons = __atomic_load_n(r->consumer, __ATOMIC_ACQUIRE); -- 2.47.2

4 months, 1 week

2
1
0 0

[PATCH 00/12] kunit: Introduce UAPI testing framework

by Thomas Weißschuh

Currently testing of userspace and in-kernel API use two different frameworks. kselftests for the userspace ones and Kunit for the in-kernel ones. Besides their different scopes, both have different strengths and limitations: Kunit: * Tests are normal kernel code. * They use the regular kernel toolchain. * They can be packaged and distributed as modules conveniently. Kselftests: * Tests are normal userspace code * They need a userspace toolchain. A kernel cross toolchain is likely not enough. * A fair amout of userland is required to run the tests, which means a full distro or handcrafted rootfs. * There is no way to conveniently package and run kselftests with a given kernel image. * The kselftests makefiles are not as powerful as regular kbuild. For example they are missing proper header dependency tracking or more complex compiler option modifications. Therefore kunit is much easier to run against different kernel configurations and architectures. This series aims to combine kselftests and kunit, avoiding both their limitations. It works by compiling the userspace kselftests as part of the regular kernel build, embedding them into the kunit kernel or module and executing them from there. If the kernel toolchain is not fit to produce userspace because of a missing libc, the kernel's own nolibc can be used instead. The structured TAP output from the kselftest is integrated into the kunit KTAP output transparently, the kunit parser can parse the combined logs together. Further room for improvements: * Call each test in its completely dedicated namespace * Handle additional test files besides the test executable through archives. CPIO, cramfs, etc. * Compatibility with kselftest_harness.h (in progress) * Expose the blobs in debugfs * Provide some convience wrappers around compat userprogs * Figure out a migration path/coexistence solution for kunit UAPI and tools/testing/selftests/ Output from the kunit example testcase, note the output of "example_uapi_tests". $ ./tools/testing/kunit/kunit.py run --kunitconfig lib/kunit example ... Running tests with: $ .kunit/linux kunit.filter_glob=example kunit.enable=1 mem=1G console=tty kunit_shutdown=halt [11:53:53] ================== example (10 subtests) =================== [11:53:53] [PASSED] example_simple_test [11:53:53] [SKIPPED] example_skip_test [11:53:53] [SKIPPED] example_mark_skipped_test [11:53:53] [PASSED] example_all_expect_macros_test [11:53:53] [PASSED] example_static_stub_test [11:53:53] [PASSED] example_static_stub_using_fn_ptr_test [11:53:53] [PASSED] example_priv_test [11:53:53] =================== example_params_test =================== [11:53:53] [SKIPPED] example value 3 [11:53:53] [PASSED] example value 2 [11:53:53] [PASSED] example value 1 [11:53:53] [SKIPPED] example value 0 [11:53:53] =============== [PASSED] example_params_test =============== [11:53:53] [PASSED] example_slow_test [11:53:53] ======================= (4 subtests) ======================= [11:53:53] [PASSED] procfs [11:53:53] [PASSED] userspace test 2 [11:53:53] [SKIPPED] userspace test 3: some reason [11:53:53] [PASSED] userspace test 4 [11:53:53] ================ [PASSED] example_uapi_test ================ [11:53:53] ===================== [PASSED] example ===================== [11:53:53] ============================================================ [11:53:53] Testing complete. Ran 16 tests: passed: 11, skipped: 5 [11:53:53] Elapsed time: 67.543s total, 1.823s configuring, 65.655s building, 0.058s running Based on v6.14-rc1 and the series "tools/nolibc: compatibility with -Wmissing-prototypes" [0]. For compatibility with LLVM/clang another series is needed [1]. [0] https://lore.kernel.org/lkml/20250123-nolibc-prototype-v1-0-e1afc5c1999a@we… [1] https://lore.kernel.org/lkml/20250213-kbuild-userprog-fixes-v1-0-f255fb477d… Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- Thomas Weißschuh (12): kconfig: implement CONFIG_HEADERS_INSTALL for Usermode Linux kconfig: introduce CONFIG_ARCH_HAS_NOLIBC kbuild: userprogs: respect CONFIG_WERROR kbuild: userprogs: add nolibc support kbuild: introduce blob framework kunit: tool: Add test for nested test result reporting kunit: tool: Don't overwrite test status based on subtest counts kunit: tool: Parse skipped tests from kselftest.h kunit: Introduce UAPI testing framework kunit: uapi: Add example for UAPI tests kunit: uapi: Introduce preinit executable kunit: uapi: Validate usability of /proc Documentation/kbuild/makefiles.rst | 12 + Makefile | 5 +- include/kunit/uapi.h | 17 ++ include/linux/blob.h | 21 ++ init/Kconfig | 2 + lib/Kconfig.debug | 1 - lib/kunit/Kconfig | 9 + lib/kunit/Makefile | 17 +- lib/kunit/kunit-example-test.c | 17 ++ lib/kunit/kunit-uapi-example.c | 58 +++++ lib/kunit/uapi-preinit.c | 61 +++++ lib/kunit/uapi.c | 250 +++++++++++++++++++++ scripts/Makefile.blobs | 19 ++ scripts/Makefile.build | 6 + scripts/Makefile.clean | 2 +- scripts/Makefile.userprogs | 18 +- scripts/blob-wrap.c | 27 +++ tools/include/nolibc/Kconfig.nolibc | 18 ++ tools/testing/kunit/kunit_parser.py | 13 +- tools/testing/kunit/kunit_tool_test.py | 9 + .../test_is_test_passed-failure-nested.log | 10 + .../test_data/test_is_test_passed-kselftest.log | 3 +- 22 files changed, 584 insertions(+), 11 deletions(-) --- base-commit: 20e952894066214a80793404c9578d72ef89c5e0 change-id: 20241015-kunit-kselftests-56273bc40442 Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

4 months, 1 week

4
17
0 0

[PATCH] selftests/ftrace: add 'poll' binary to gitignore

by Bharadwaj Raju

When building this test, a binary file 'poll' is generated and should be gitignore'd. Signed-off-by: Bharadwaj Raju <bharadwaj.raju777(a)gmail.com> --- tools/testing/selftests/ftrace/.gitignore | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/ftrace/.gitignore b/tools/testing/selftests/ftrace/.gitignore index 2659417cb2c7..4d7fcb828850 100644 --- a/tools/testing/selftests/ftrace/.gitignore +++ b/tools/testing/selftests/ftrace/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only logs +poll -- 2.43.0

4 months, 1 week

3
3
0 0

[PATCH v3 0/2] tools: Unify top-level quiet infrastructure

by Charlie Jenkins

The quiet infrastructure was moved out of Makefile.build to accomidate the new syscall table generation scripts in perf. Syscall table generation wanted to also be able to be quiet, so instead of again copying the code to set the quiet variables, the code was moved into Makefile.perf to be used globally. This was not the right solution. It should have been moved even further upwards in the call chain. Makefile.include is imported in many files so this seems like a proper place to put it. To: Signed-off-by: Charlie Jenkins <charlie(a)rivosinc.com> --- Changes in v3: - Add back erroneously removed "silent=1" (Jiri) - Link to v2: https://lore.kernel.org/r/20250210-quiet_tools-v2-0-b2f18cbf72af@rivosinc.c… Changes in v2: - Fix spacing around Q= (Andrii) - Link to v1: https://lore.kernel.org/r/20250203-quiet_tools-v1-0-d25c8956e59a@rivosinc.c… --- Charlie Jenkins (2): tools: Unify top-level quiet infrastructure tools: Remove redundant quiet setup tools/arch/arm64/tools/Makefile | 6 ----- tools/bpf/Makefile | 6 ----- tools/bpf/bpftool/Documentation/Makefile | 6 ----- tools/bpf/bpftool/Makefile | 6 ----- tools/bpf/resolve_btfids/Makefile | 2 -- tools/bpf/runqslower/Makefile | 5 +--- tools/build/Makefile | 8 +----- tools/lib/bpf/Makefile | 13 ---------- tools/lib/perf/Makefile | 13 ---------- tools/lib/thermal/Makefile | 13 ---------- tools/objtool/Makefile | 6 ----- tools/perf/Makefile.perf | 41 ------------------------------- tools/scripts/Makefile.include | 30 ++++++++++++++++++++++ tools/testing/selftests/bpf/Makefile.docs | 6 ----- tools/testing/selftests/hid/Makefile | 2 -- tools/thermal/lib/Makefile | 13 ---------- tools/tracing/latency/Makefile | 6 ----- tools/tracing/rtla/Makefile | 6 ----- tools/verification/rv/Makefile | 6 ----- 19 files changed, 32 insertions(+), 162 deletions(-) --- base-commit: 2014c95afecee3e76ca4a56956a936e23283f05b change-id: 20250203-quiet_tools-9a6ea9d65a19 -- - Charlie

4 months, 1 week

3
4
0 0

[PATCH net-next v2 0/8] netconsole: Add taskname sysdata support

by Breno Leitao

This patchset introduces a new feature to the netconsole extradata subsystem that enables the inclusion of the current task's name in the sysdata output of netconsole messages. This enhancement is particularly valuable for large-scale deployments, such as Meta's, where netconsole collects messages from millions of servers and stores them in a data warehouse for analysis. Engineers often rely on these messages to investigate issues and assess kernel health. One common challenge we face is determining the context in which a particular message was generated. By including the task name (task->comm) with each message, this feature provides a direct answer to the frequently asked question: "What was running when this message was generated?" This added context will significantly improve our ability to diagnose and troubleshoot issues, making it easier to interpret output of netconsole. The patchset consists of seven patches that implement the following changes: * Refactor CPU number formatting into a separate function * Prefix CPU_NR sysdata feature with SYSDATA_ * Patch to covert a bitwise operation into boolean * Add configfs controls for taskname sysdata feature * Add taskname to extradata entry count * Add support for including task name in netconsole's extra data output * Document the task name feature in Documentation/networking/netconsole.rst * Add test coverage for the task name feature to the existing sysdata selftest script These changes allow users to enable or disable the task name feature via configfs and provide additional context for kernel messages by showing which task generated each console message. I have tested these patches on some servers and they seem to work as expected. Signed-off-by: Breno Leitao <leitao(a)debian.org> --- Changes in v2: - Add an extra patch to convert the comparison more stable. (Paolo) - Changed the argument of a function (Simon) - Removed the warn on `current == NULLL` since it shouldn't be the case. (Simon and Paolo) - Link to v1: https://lore.kernel.org/r/20250221-netcons_current-v1-0-21c86ae8fc0d@debian… --- Breno Leitao (8): netconsole: prefix CPU_NR sysdata feature with SYSDATA_ netconsole: Make boolean comparison consistent netconsole: refactor CPU number formatting into separate function netconsole: add taskname to extradata entry count netconsole: add configfs controls for taskname sysdata feature netconsole: add task name to extra data fields netconsole: docs: document the task name feature netconsole: selftest: add task name append testing Documentation/networking/netconsole.rst | 28 +++++++ drivers/net/netconsole.c | 95 ++++++++++++++++++---- .../selftests/drivers/net/netcons_sysdata.sh | 51 ++++++++++-- 3 files changed, 153 insertions(+), 21 deletions(-) --- base-commit: 56794b5862c5a9aefcf2b703257c6fb93f76573e change-id: 20250217-netcons_current-2c635fa5beda prerequisite-change-id: 20250212-netdevsim-258d2d628175:v3 prerequisite-patch-id: 4ecfdbc58dd599d2358655e4ad742cbb9dde39f3 Best regards, -- Breno Leitao <leitao(a)debian.org>

4 months, 1 week

3
11
0 0

[PATCH net-next 0/7] netconsole: Add taskname sysdata support

by Breno Leitao

This patchset introduces a new feature to the netconsole extradata subsystem that enables the inclusion of the current task's name in the sysdata output of netconsole messages. This enhancement is particularly valuable for large-scale deployments, such as Meta's, where netconsole collects messages from millions of servers and stores them in a data warehouse for analysis. Engineers often rely on these messages to investigate issues and assess kernel health. One common challenge we face is determining the context in which a particular message was generated. By including the task name (task->comm) with each message, this feature provides a direct answer to the frequently asked question: "What was running when this message was generated?" This added context will significantly improve our ability to diagnose and troubleshoot issues, making it easier to interpret output of netconsole. The patchset consists of seven patches that implement the following changes: * Refactor CPU number formatting into a separate function * Prefix CPU_NR sysdata feature with SYSDATA_ * Add configfs controls for taskname sysdata feature * Add taskname to extradata entry count * Add support for including task name in netconsole's extra data output * Document the task name feature in Documentation/networking/netconsole.rst * Add test coverage for the task name feature to the existing sysdata selftest script These changes allow users to enable or disable the task name feature via configfs and provide additional context for kernel messages by showing which task generated each console message. I have tested these patches on some servers and they seem to work as expected. Signed-off-by: Breno Leitao <leitao(a)debian.org> --- Breno Leitao (7): netconsole: prefix CPU_NR sysdata feature with SYSDATA_ netconsole: refactor CPU number formatting into separate function netconsole: add taskname to extradata entry count netconsole: add configfs controls for taskname sysdata feature netconsole: add task name to extra data fields netconsole: docs: document the task name feature netconsole: selftest: add task name append testing Documentation/networking/netconsole.rst | 28 +++++++ drivers/net/netconsole.c | 98 ++++++++++++++++++---- .../selftests/drivers/net/netcons_sysdata.sh | 51 +++++++++-- 3 files changed, 156 insertions(+), 21 deletions(-) --- base-commit: bb3bb6c92e5719c0f5d7adb9d34db7e76705ac33 change-id: 20250217-netcons_current-2c635fa5beda prerequisite-change-id: 20250212-netdevsim-258d2d628175:v3 prerequisite-patch-id: 4ecfdbc58dd599d2358655e4ad742cbb9dde39f3 Best regards, -- Breno Leitao <leitao(a)debian.org>

4 months, 1 week

3
23
0 0

[PATCHv3 net 0/3] bond: fix xfrm offload issues

by Hangbin Liu

The first patch fixes the incorrect locks using in bond driver. The second patch fixes the xfrm offload feature during setup active-backup mode. The third patch add a ipsec offload testing. v3: move the ipsec deletion to bond_ipsec_free_sa (Cosmin Ratiu) v2: do not turn carrier on if bond change link failed (Nikolay Aleksandrov) move the mutex lock to a work queue (Cosmin Ratiu) Hangbin Liu (3): bonding: move IPsec deletion to bond_ipsec_free_sa bonding: fix xfrm offload feature setup on active-backup mode selftests: bonding: add ipsec offload test drivers/net/bonding/bond_main.c | 36 ++-- drivers/net/bonding/bond_netlink.c | 16 +- include/net/bonding.h | 1 + .../selftests/drivers/net/bonding/Makefile | 3 +- .../drivers/net/bonding/bond_ipsec_offload.sh | 155 ++++++++++++++++++ .../selftests/drivers/net/bonding/config | 4 + 6 files changed, 195 insertions(+), 20 deletions(-) create mode 100755 tools/testing/selftests/drivers/net/bonding/bond_ipsec_offload.sh -- 2.46.0

4 months, 1 week

4
15
0 0

[PATCH net-next v8 0/8] Some pktgen fixes/improvments (part II)

by Peter Seiderer

While taking a look at '[PATCH net] pktgen: Avoid out-of-range in get_imix_entries' ([1]) and '[PATCH net v2] pktgen: Avoid out-of-bounds access in get_imix_entries' ([2], [3]) and doing some tests and code review I detected that the /proc/net/pktgen/... parsing logic does not honour the user given buffer bounds (resulting in out-of-bounds access). This can be observed e.g. by the following simple test (sometimes the old/'longer' previous value is re-read from the buffer): $ echo add_device lo@0 > /proc/net/pktgen/kpktgend_0 $ echo "min_pkt_size 12345" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 12345 max_pkt_size: 0 Result: OK: min_pkt_size=12345 $ echo -n "min_pkt_size 123" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 12345 max_pkt_size: 0 Result: OK: min_pkt_size=12345 $ echo "min_pkt_size 123" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 123 max_pkt_size: 0 Result: OK: min_pkt_size=123 So fix the out-of-bounds access (and some minor findings) and add a simple proc_net_pktgen selftest... Patch set splited into part I (now already applied to net-next) - net: pktgen: replace ENOTSUPP with EOPNOTSUPP - net: pktgen: enable 'param=value' parsing - net: pktgen: fix hex32_arg parsing for short reads - net: pktgen: fix 'rate 0' error handling (return -EINVAL) - net: pktgen: fix 'ratep 0' error handling (return -EINVAL) - net: pktgen: fix ctrl interface command parsing - net: pktgen: fix access outside of user given buffer in pktgen_thread_write() nd part II (this one): - net: pktgen: use defines for the various dec/hex number parsing digits lengths - net: pktgen: fix mix of int/long - net: pktgen: remove extra tmp variable (re-use len instead) - net: pktgen: remove some superfluous variable initializing - net: pktgen: fix mpls maximum labels list parsing - net: pktgen: fix access outside of user given buffer in pktgen_if_write() - net: pktgen: fix mpls reset parsing - net: pktgen: remove all superfluous index assignements - selftest: net: add proc_net_pktgen Regards, Peter Changes v7 -> v8: - rebased on actual net-next/main - add rev-by Simon Horman - net: pktgen: fix mpls maximum labels list parsing - slightly rephrase commit message, omit '/16' (suggested by Paolo Abeni) - net: pktgen: fix mpls reset parsing - fix c99 comment (suggested by Paolo Abeni) - selftest: net: add proc_net_pktgen - fix c99 comments (suggested by Paolo Abeni) Changes v6 -> v7: - rebased on actual net-next/main - selftest: net: add proc_net_pktgen - fixed conflict in tools/testing/selftests/net/config Changes v5 -> v6: - add rev-by Simon Horman - drop patch 'net: pktgen: use defines for the various dec/hex number parsing digits lengths' - adjust to dropped patch 'net: pktgen: use defines for the various dec/hex number parsing digits lengths' - net: pktgen: fix mix of int/long - fix line break (suggested by Simon Horman) Changes v4 -> v5: - split up patchset into part i/ii (suggested by Simon Horman) - add rev-by Simon Horman - net: pktgen: align some variable declarations to the most common pattern -> net: pktgen: fix mix of int/long - instead of align to most common pattern (int) adjust all usages to size_t for i and max and ssize_t for len and adjust function signatures of hex32_arg(), count_trail_chars(), num_arg() and strn_len() accordingly - respect reverse xmas tree order for local variable declarations (where possible without too much code churn) - update subject line and patch description - dropped net: pktgen: hex32_arg/num_arg error out in case no characters are available - keep empty hex/num arg is implicit assumed as zero value - dropped net: pktgen: num_arg error out in case no valid character is parsed - keep empty hex/num arg is implicit assumed as zero value - Change patch description ('Fixes:' -> 'Addresses the following:', suggested by Simon Horman) - net: pktgen: remove all superfluous index assignements - new patch (suggested by Simon Horman) - selftest: net: add proc_net_pktgen - addapt to dropped patch 'net: pktgen: hex32_arg/num_arg error out in case no characters are available', empty hex/num arg is now implicit assumed as zero value (instead of failure) Changes v3 -> v4: - add rev-by Simon Horman - new patch 'net: pktgen: use defines for the various dec/hex number parsing digits lengths' (suggested by Simon Horman) - replace C99 comment (suggested by Paolo Abeni) - drop available characters check in strn_len() (suggested by Paolo Abeni) - factored out patch 'net: pktgen: align some variable declarations to the most common pattern' (suggested by Paolo Abeni) - factored out patch 'net: pktgen: remove extra tmp variable (re-use len instead)' (suggested by Paolo Abeni) - factored out patch 'net: pktgen: remove some superfluous variable initializing' (suggested by Paolo Abeni) - factored out patch 'net: pktgen: fix mpls maximum labels list parsing' (suggested by Paolo Abeni) - factored out 'net: pktgen: hex32_arg/num_arg error out in case no characters are available' (suggested by Paolo Abeni) - factored out 'net: pktgen: num_arg error out in case no valid character is parsed' (suggested by Paolo Abeni) Changes v2 -> v3: - new patch: 'net: pktgen: fix ctrl interface command parsing' - new patch: 'net: pktgen: fix mpls reset parsing' - tools/testing/selftests/net/proc_net_pktgen.c: - fix typo in change description ('v1 -> v1' and tyop) - rename some vars to better match usage add_loopback_0 -> thr_cmd_add_loopback_0 rm_loopback_0 -> thr_cmd_rm_loopback_0 wrong_ctrl_cmd -> wrong_thr_cmd legacy_ctrl_cmd -> legacy_thr_cmd ctrl_fd -> thr_fd - add ctrl interface tests Changes v1 -> v2: - new patch: 'net: pktgen: fix hex32_arg parsing for short reads' - new patch: 'net: pktgen: fix 'rate 0' error handling (return -EINVAL)' - new patch: 'net: pktgen: fix 'ratep 0' error handling (return -EINVAL)' - net/core/pktgen.c: additional fix get_imix_entries() and get_labels() - tools/testing/selftests/net/proc_net_pktgen.c: - fix typo not vs. nod (suggested by Jakub Kicinski) - fix misaligned line (suggested by Jakub Kicinski) - enable fomerly commented out CONFIG_XFRM dependent test (command spi), as CONFIG_XFRM is enabled via tools/testing/selftests/net/config CONFIG_XFRM_INTERFACE/CONFIG_XFRM_USER (suggestex by Jakub Kicinski) - add CONFIG_NET_PKTGEN=m to tools/testing/selftests/net/config (suggested by Jakub Kicinski) - add modprobe pktgen to FIXTURE_SETUP() (suggested by Jakub Kicinski) - fix some checkpatch warnings (Missing a blank line after declarations) - shrink line length by re-naming some variables (command -> cmd, device -> dev) - add 'rate 0' testcase - add 'ratep 0' testcase [1] https://lore.kernel.org/netdev/20241006221221.3744995-1-artem.chernyshev@re… [2] https://lore.kernel.org/netdev/20250109083039.14004-1-pchelkin@ispras.ru/ [3] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… Peter Seiderer (8): net: pktgen: fix mix of int/long net: pktgen: remove extra tmp variable (re-use len instead) net: pktgen: remove some superfluous variable initializing net: pktgen: fix mpls maximum labels list parsing net: pktgen: fix access outside of user given buffer in pktgen_if_write() net: pktgen: fix mpls reset parsing net: pktgen: remove all superfluous index assignements selftest: net: add proc_net_pktgen net/core/pktgen.c | 288 ++++---- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/config | 1 + tools/testing/selftests/net/proc_net_pktgen.c | 646 ++++++++++++++++++ 4 files changed, 805 insertions(+), 131 deletions(-) create mode 100644 tools/testing/selftests/net/proc_net_pktgen.c -- 2.48.1

4 months, 1 week

2
9
0 0

[PATCH 0/4] RISC-V KVM PMU fix and selftest improvement

by Atish Patra

This series adds a fix for KVM PMU code and improves the pmu selftest by allowing generating precise number of interrupts. It also provided another additional option to the overflow test that allows user to generate custom number of LCOFI interrupts. Signed-off-by: Atish Patra <atishp(a)rivosinc.com> --- Atish Patra (4): RISC-V: KVM: Disable the kernel perf counter during configure KVM: riscv: selftests: Do not start the counter in the overflow handler KVM: riscv: selftests: Change command line option KVM: riscv: selftests: Allow number of interrupts to be configurable arch/riscv/kvm/vcpu_pmu.c | 1 + tools/testing/selftests/kvm/riscv/sbi_pmu_test.c | 81 ++++++++++++++++-------- 2 files changed, 57 insertions(+), 25 deletions(-) --- base-commit: 0ad2507d5d93f39619fc42372c347d6006b64319 change-id: 20250225-kvm_pmu_improve-fffd038b2404 -- Regards, Atish patra

4 months, 1 week

3
11
0 0

[PATCH net-next] selftests: net: report output format as TAP 13 in Python tests

by Jakub Kicinski

The Python lib based tests report that they are producing "KTAP version 1", but really we aren't making use of any KTAP features, like subtests. Our output is plain TAP. Report TAP 13 instead of KTAP 1, this is what mptcp tests do, and what NIPA knows how to parse best. For HW testing we need precise subtest result tracking. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: petrm(a)nvidia.com CC: matttbe(a)kernel.org CC: willemb(a)google.com CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/drivers/net/README.rst | 4 ++-- tools/testing/selftests/net/lib/py/ksft.py | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/drivers/net/README.rst b/tools/testing/selftests/drivers/net/README.rst index 3b6a29e6564b..eb838ae94844 100644 --- a/tools/testing/selftests/drivers/net/README.rst +++ b/tools/testing/selftests/drivers/net/README.rst @@ -107,7 +107,7 @@ Example 1..1 # timeout set to 45 # selftests: drivers/net: ping.py - # KTAP version 1 + # TAP version 13 # 1..3 # ok 1 ping.test_v4 # ok 2 ping.test_v6 @@ -128,7 +128,7 @@ Example Run the test:: [/root] # ./ksft-net-drv/drivers/net/ping.py - KTAP version 1 + TAP version 13 1..3 ok 1 ping.test_v4 ok 2 ping.test_v6 # SKIP Test requires IPv6 connectivity diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index fd23349fa8ca..3cfad0fd4570 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -207,7 +207,7 @@ KSFT_DISRUPTIVE = True totals = {"pass": 0, "fail": 0, "skip": 0, "xfail": 0} - print("KTAP version 1") + print("TAP version 13") print("1.." + str(len(cases))) global KSFT_RESULT -- 2.48.1

4 months, 1 week

3
3
0 0

[PATCH bpf-next v2 00/10] selftests/bpf: Migrate test_tunnel.sh to test_progs

by Bastien Curutchet (eBPF Foundation)

Hi all, This patch series continues the work to migrate the *.sh tests into prog_tests framework. The test_tunnel.sh script has already been partly migrated to test_progs in prog_tests/test_tunnel.c so I add my work to it. PATCH 1 & 2 create some helpers to avoid code duplication and ease the migration in the following patches. PATCH 3 to 9 migrate the tests of gre, ip6gre, erspan, ip6erspan, geneve, ip6geneve and ip6tnl tunnels. PATCH 10 removes test_tunnel.sh Signed-off-by: Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com> --- Changes in v2: - PATCH 1: Move tc_hook definition to attatch_tc_prog() - PATCH 4: Disable DAD through `ip addr` - Link to v1: https://lore.kernel.org/r/20250227-tunnels-v1-0-33df5c30aa04@bootlin.com --- Bastien Curutchet (eBPF Foundation) (10): selftests/bpf: test_tunnel: Add generic_attach* helpers selftests/bpf: test_tunnel: Add ping helpers selftests/bpf: test_tunnel: Move gre tunnel test to test_progs selftests/bpf: test_tunnel: Move ip6gre tunnel test to test_progs selftests/bpf: test_tunnel: Move erspan tunnel tests to test_progs selftests/bpf: test_tunnel: Move ip6erspan tunnel test to test_progs selftests/bpf: test_tunnel: Move geneve tunnel test to test_progs selftests/bpf: test_tunnel: Move ip6geneve tunnel test to test_progs selftests/bpf: test_tunnel: Move ip6tnl tunnel tests to test_progs selftests/bpf: test_tunnel: Remove test_tunnel.sh tools/testing/selftests/bpf/Makefile | 1 - .../testing/selftests/bpf/prog_tests/test_tunnel.c | 633 ++++++++++++++++---- tools/testing/selftests/bpf/test_tunnel.sh | 645 --------------------- 3 files changed, 530 insertions(+), 749 deletions(-) --- base-commit: 97b4501198b918f1d0adeb8205004d64f780e472 change-id: 20250131-tunnels-59b641ea3f10 Best regards, -- Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com>

4 months, 1 week

3
13
0 0

[PATCH bpf-next v4 0/6] XDP metadata support for tun driver

by Marcus Wichelmann

Hi all, this series contains some improvements for the selftest patches. The other patches remain unchanged. Please check the changelist below. I have reverted the addition of the NOARP flag from the previous version, as it was not effective and the CI was still failing occasionally because of the race condition caused by foreign packets interfering with the veth tests. This series contains an alternative solution by filtering all but the test packets using the attached XDP program. Successful pipeline: https://github.com/kernel-patches/bpf/actions/runs/13552017584 --- v4: - strip unrelated changes from the selftest patches - extend commit message for "selftests/bpf: refactor xdp_context_functional test and bpf program" - the NOARP flag was not effective to prevent other packets from interfering with the tests, add a filter to the XDP program instead - run xdp_context_tuntap in a separate namespace to avoid conflicts with other tests v3: https://lore.kernel.org/bpf/20250224152909.3911544-1-marcus.wichelmann@hetz… - change the condition to handle xdp_buffs without metadata support, as suggested by Willem de Bruijn <willemb(a)google.com> - add clarifying comment why that condition is needed - set NOARP flag in selftests to ensure that the kernel does not send packets on the test interfaces that may interfere with the tests v2: https://lore.kernel.org/bpf/20250217172308.3291739-1-marcus.wichelmann@hetz… - submit against bpf-next subtree - split commits and improved commit messages - remove redundant metasize check and add clarifying comment instead - use max() instead of ternary operator - add selftest for metadata support in the tun driver v1: https://lore.kernel.org/all/20250130171614.1657224-1-marcus.wichelmann@hetz… Marcus Wichelmann (6): net: tun: enable XDP metadata support net: tun: enable transfer of XDP metadata to skb selftests/bpf: move open_tuntap to network helpers selftests/bpf: refactor xdp_context_functional test and bpf program selftests/bpf: add test for XDP metadata support in tun driver selftests/bpf: fix file descriptor assertion in open_tuntap helper drivers/net/tun.c | 28 +++- tools/testing/selftests/bpf/network_helpers.c | 28 ++++ tools/testing/selftests/bpf/network_helpers.h | 3 + .../selftests/bpf/prog_tests/lwt_helpers.h | 29 ---- .../bpf/prog_tests/xdp_context_test_run.c | 138 +++++++++++++++++- .../selftests/bpf/progs/test_xdp_meta.c | 53 +++++-- 6 files changed, 223 insertions(+), 56 deletions(-) -- 2.43.0

4 months, 1 week

5
14
0 0

[PATCH net-next v20 00/25] Introducing OpenVPN Data Channel Offload

by Antonio Quartulli

After some time of struggle trying to fix all hidden bugs that Sabrina has found...here is v20! Notable changes since v19: * copyright years updated to 2025 * rtnl_link_ops.newlink adapted to new signature * removed admindown del-peer-reason attribute from netlink API (it should have gone away in v19 already) * removed asynchronous socket cleanup. All cleanup now happens in the same context as the peer removal. I used a "deferred list" to collect all peers that needed socket release and traversed it after releasing the socket. This wasy there was no need to spawn workers to leave the atomic context. Code looks way more linear now * provided implementation for sk_prot->close() in order to catch when userspace is releasing a socet and act accordingly. This way we can avoid the dangling netns problem discussed in v19 * due to the previous item, it is now expected that the process that created a socket stays alive all time long. * kselftest scripts have been re-arranged as per the previous item in order to keep ovpn-cli processes alive in background during the tests * improved TCP shutdown coordination across involved components * fixed false deadlock reporting by using nested lock class (thanks a lot to Sean Anderson!) * exported udpv6_prot via EXPORT_SYMBOL_GPL * merged patch for exporting inet6_stream_ops with its user * moved TCP code that may sleep during detach out of lock_sock area * reverted tcp_release_cb to EXPORT_SYMBOL * improved kselftest Makefile to allow kselftest_deps.sh to detect all dependencies Please note that some patches were already reviewed/tested by a few people. These patches have retained the tags as they have hardly been touched. (Due to the amount of changes applied to the kselftest scripts, I dropped the Reviewed-by Shuah Khan tag on that specific patch) The latest code can also be found at: https://github.com/OpenVPN/ovpn-net-next Thanks a lot! Best Regards, Antonio Quartulli OpenVPN Inc. --- Antonio Quartulli (25): mailmap: remove unwanted entry for Antonio Quartulli net: introduce OpenVPN Data Channel Offload (ovpn) ovpn: add basic netlink support ovpn: add basic interface creation/destruction/management routines ovpn: keep carrier always on for MP interfaces ovpn: introduce the ovpn_peer object ovpn: introduce the ovpn_socket object ovpn: implement basic TX path (UDP) ovpn: implement basic RX path (UDP) ovpn: implement packet processing ovpn: store tunnel and transport statistics ovpn: implement TCP transport skb: implement skb_send_sock_locked_with_flags() ovpn: add support for MSG_NOSIGNAL in tcp_sendmsg ovpn: implement multi-peer support ovpn: implement peer lookup logic ovpn: implement keepalive mechanism ovpn: add support for updating local UDP endpoint ovpn: add support for peer floating ovpn: implement peer add/get/dump/delete via netlink ovpn: implement key add/get/del/swap via netlink ovpn: kill key and notify userspace in case of IV exhaustion ovpn: notify userspace when a peer is deleted ovpn: add basic ethtool support testing/selftests: add test tool and scripts for ovpn module .mailmap | 1 - Documentation/netlink/specs/ovpn.yaml | 371 +++ Documentation/netlink/specs/rt_link.yaml | 16 + MAINTAINERS | 11 + drivers/net/Kconfig | 15 + drivers/net/Makefile | 1 + drivers/net/ovpn/Makefile | 22 + drivers/net/ovpn/bind.c | 55 + drivers/net/ovpn/bind.h | 101 + drivers/net/ovpn/crypto.c | 211 ++ drivers/net/ovpn/crypto.h | 145 ++ drivers/net/ovpn/crypto_aead.c | 408 ++++ drivers/net/ovpn/crypto_aead.h | 33 + drivers/net/ovpn/io.c | 462 ++++ drivers/net/ovpn/io.h | 34 + drivers/net/ovpn/main.c | 350 +++ drivers/net/ovpn/main.h | 14 + drivers/net/ovpn/netlink-gen.c | 213 ++ drivers/net/ovpn/netlink-gen.h | 41 + drivers/net/ovpn/netlink.c | 1249 ++++++++++ drivers/net/ovpn/netlink.h | 18 + drivers/net/ovpn/ovpnpriv.h | 57 + drivers/net/ovpn/peer.c | 1341 +++++++++++ drivers/net/ovpn/peer.h | 163 ++ drivers/net/ovpn/pktid.c | 129 ++ drivers/net/ovpn/pktid.h | 87 + drivers/net/ovpn/proto.h | 118 + drivers/net/ovpn/skb.h | 61 + drivers/net/ovpn/socket.c | 241 ++ drivers/net/ovpn/socket.h | 53 + drivers/net/ovpn/stats.c | 21 + drivers/net/ovpn/stats.h | 47 + drivers/net/ovpn/tcp.c | 571 +++++ drivers/net/ovpn/tcp.h | 36 + drivers/net/ovpn/udp.c | 478 ++++ drivers/net/ovpn/udp.h | 27 + include/linux/skbuff.h | 2 + include/uapi/linux/if_link.h | 15 + include/uapi/linux/ovpn.h | 110 + include/uapi/linux/udp.h | 1 + net/core/skbuff.c | 18 +- net/ipv4/tcp_output.c | 2 +- net/ipv6/af_inet6.c | 1 + net/ipv6/udp.c | 1 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/net/ovpn/.gitignore | 2 + tools/testing/selftests/net/ovpn/Makefile | 31 + tools/testing/selftests/net/ovpn/common.sh | 92 + tools/testing/selftests/net/ovpn/config | 10 + tools/testing/selftests/net/ovpn/data64.key | 5 + tools/testing/selftests/net/ovpn/ovpn-cli.c | 2395 ++++++++++++++++++++ tools/testing/selftests/net/ovpn/tcp_peers.txt | 5 + .../testing/selftests/net/ovpn/test-chachapoly.sh | 9 + .../selftests/net/ovpn/test-close-socket-tcp.sh | 9 + .../selftests/net/ovpn/test-close-socket.sh | 45 + tools/testing/selftests/net/ovpn/test-float.sh | 9 + tools/testing/selftests/net/ovpn/test-tcp.sh | 9 + tools/testing/selftests/net/ovpn/test.sh | 113 + tools/testing/selftests/net/ovpn/udp_peers.txt | 5 + 59 files changed, 10084 insertions(+), 7 deletions(-) --- base-commit: 91c8d8e4b7a38dc099b26e14b22f814ca4e75089 change-id: 20241002-b4-ovpn-eeee35c694a2 Best regards, -- Antonio Quartulli <antonio(a)openvpn.net>

4 months, 1 week

4
39
0 0

[v3 PATCH 0/2] KVM: guest_memfd: use write for population

by Nikita Kalyazin

This series is rebased on top of Fuad's v4 for shared mapping of guest_memfd [1]. Change since v2 [2]: - David/Mike D: Only compile support for the write syscall if CONFIG_KVM_GMEM_SHARED_MEM introduced in [1] is enabled. In non-CoCo use cases where the host can access guest memory, guest_memfd can be allocated and populated via the write syscall. Even though the same can also be achieved via userspace mapping and memcpy from userspace, write provides a more performant option because it 1) avoids double initialisation as the kernel does not need to zero pages and 2) does not require setting up page tables. Nikita [1] https://lore.kernel.org/kvm/20250218172500.807733-4-tabba@google.com/T/ [2] https://lore.kernel.org/kvm/20241129123929.64790-1-kalyazin@amazon.com/T/ Nikita Kalyazin (2): KVM: guest_memfd: add generic population via write KVM: selftests: update guest_memfd write tests .../testing/selftests/kvm/guest_memfd_test.c | 85 +++++++++++++++-- virt/kvm/guest_memfd.c | 94 ++++++++++++++++++- 2 files changed, 170 insertions(+), 9 deletions(-) base-commit: 005f6404708d430abab7fab9b422d0daf6e0c2fe -- 2.47.1

4 months, 1 week

1
2
0 0

[PATCH v7 0/6] ptrace: introduce PTRACE_SET_SYSCALL_INFO API

by Dmitry V. Levin

PTRACE_SET_SYSCALL_INFO is a generic ptrace API that complements PTRACE_GET_SYSCALL_INFO by letting the ptracer modify details of system calls the tracee is blocked in. This API allows ptracers to obtain and modify system call details in a straightforward and architecture-agnostic way, providing a consistent way of manipulating the system call number and arguments across architectures. As in case of PTRACE_GET_SYSCALL_INFO, PTRACE_SET_SYSCALL_INFO also does not aim to address numerous architecture-specific system call ABI peculiarities, like differences in the number of system call arguments for such system calls as pread64 and preadv. The current implementation supports changing only those bits of system call information that are used by strace system call tampering, namely, syscall number, syscall arguments, and syscall return value. Support of changing additional details returned by PTRACE_GET_SYSCALL_INFO, such as instruction pointer and stack pointer, could be added later if needed, by using struct ptrace_syscall_info.flags to specify the additional details that should be set. Currently, "flags" and "reserved" fields of struct ptrace_syscall_info must be initialized with zeroes; "arch", "instruction_pointer", and "stack_pointer" fields are currently ignored. PTRACE_SET_SYSCALL_INFO currently supports only PTRACE_SYSCALL_INFO_ENTRY, PTRACE_SYSCALL_INFO_EXIT, and PTRACE_SYSCALL_INFO_SECCOMP operations. Other operations could be added later if needed. Ideally, PTRACE_SET_SYSCALL_INFO should have been introduced along with PTRACE_GET_SYSCALL_INFO, but it didn't happen. The last straw that convinced me to implement PTRACE_SET_SYSCALL_INFO was apparent failure to provide an API of changing the first system call argument on riscv architecture [1]. ptrace(2) man page: long ptrace(enum __ptrace_request request, pid_t pid, void *addr, void *data); ... PTRACE_SET_SYSCALL_INFO Modify information about the system call that caused the stop. The "data" argument is a pointer to struct ptrace_syscall_info that specifies the system call information to be set. The "addr" argument should be set to sizeof(struct ptrace_syscall_info)). [1] https://lore.kernel.org/all/59505464-c84a-403d-972f-d4b2055eeaac@gmail.com/ Notes: v7: * csky: Fix typo in comment * mips: syscall_set_arguments: Remove mips_syscall_is_indirect check * mips: syscall_set_nr: Reword comment * mips: Add Reviewed-by * v6: https://lore.kernel.org/all/20250217090834.GA18175@strace.io/ v6: * mips: Submit mips_get_syscall_arg() o32 fix via mips tree to get it merged into v6.14-rc3 * Rebase to v6.14-rc3 * v5: https://lore.kernel.org/all/20250210113336.GA887@strace.io/ v5: * ptrace: Extend the commit message to say that the new API does not aim to address numerous architecture-specific syscall ABI peculiarities * selftests: Add a workaround for s390 16-bit syscall numbers * parisc: Add Acked-by * v4: https://lore.kernel.org/all/20250203065849.GA14120@strace.io/ v4: * Split out syscall_set_return_value() for hexagon into a separate patch * s390: Change the style of syscall_set_arguments() implementation as requested * ptrace: Add Reviewed-by * v3: https://lore.kernel.org/all/20250128091445.GA8257@strace.io/ v3: * powerpc: Submit syscall_set_return_value() fix for "sc" case separately * mips: Do not introduce erroneous argument truncation on mips n32, add a detailed description to the commit message of the mips_get_syscall_arg() change * ptrace: Add explicit padding to the end of struct ptrace_syscall_info, simplify obtaining of user ptrace_syscall_info, do not introduce PTRACE_SYSCALL_INFO_SIZE_VER0 * ptrace: Change the return type of ptrace_set_syscall_info_* functions from "unsigned long" to "int" * ptrace: Add -ERANGE check to ptrace_set_syscall_info_exit(), add comments to -ERANGE checks * ptrace: Update comments about supported syscall stops * selftests: Extend set_syscall_info test, fix for mips n32 * riscv: Add Tested-by and Reviewed-by v2: * Add patch to fix syscall_set_return_value() on powerpc * Add patch to fix mips_get_syscall_arg() on mips * Add syscall_set_return_value() implementation on hexagon * Add syscall_set_return_value() invocation to syscall_set_nr() on arm and arm64. * Fix syscall_set_nr() and mips_set_syscall_arg() on mips * Add a comment to syscall_set_nr() on arc, powerpc, s390, sh, and sparc * Remove redundant ptrace_syscall_info.op assignments in ptrace_get_syscall_info_* * Minor style tweaks in ptrace_get_syscall_info_op() * Remove syscall_set_return_value() invocation from ptrace_set_syscall_info_entry() * Skip syscall_set_arguments() invocation in case of syscall number -1 in ptrace_set_syscall_info_entry() * Split ptrace_syscall_info.reserved into ptrace_syscall_info.reserved and ptrace_syscall_info.flags * Use __kernel_ulong_t instead of unsigned long in set_syscall_info test Dmitry V. Levin (6): hexagon: add syscall_set_return_value() syscall.h: add syscall_set_arguments() syscall.h: introduce syscall_set_nr() ptrace_get_syscall_info: factor out ptrace_get_syscall_info_op ptrace: introduce PTRACE_SET_SYSCALL_INFO request selftests/ptrace: add a test case for PTRACE_SET_SYSCALL_INFO arch/arc/include/asm/syscall.h | 25 + arch/arm/include/asm/syscall.h | 37 ++ arch/arm64/include/asm/syscall.h | 29 + arch/csky/include/asm/syscall.h | 13 + arch/hexagon/include/asm/syscall.h | 21 + arch/loongarch/include/asm/syscall.h | 15 + arch/m68k/include/asm/syscall.h | 7 + arch/microblaze/include/asm/syscall.h | 7 + arch/mips/include/asm/syscall.h | 43 ++ arch/nios2/include/asm/syscall.h | 16 + arch/openrisc/include/asm/syscall.h | 13 + arch/parisc/include/asm/syscall.h | 19 + arch/powerpc/include/asm/syscall.h | 20 + arch/riscv/include/asm/syscall.h | 16 + arch/s390/include/asm/syscall.h | 21 + arch/sh/include/asm/syscall_32.h | 24 + arch/sparc/include/asm/syscall.h | 22 + arch/um/include/asm/syscall-generic.h | 19 + arch/x86/include/asm/syscall.h | 43 ++ arch/xtensa/include/asm/syscall.h | 18 + include/asm-generic/syscall.h | 30 + include/uapi/linux/ptrace.h | 7 +- kernel/ptrace.c | 179 +++++- tools/testing/selftests/ptrace/Makefile | 2 +- .../selftests/ptrace/set_syscall_info.c | 519 ++++++++++++++++++ 25 files changed, 1138 insertions(+), 27 deletions(-) create mode 100644 tools/testing/selftests/ptrace/set_syscall_info.c base-commit: 7eb172143d5508b4da468ed59ee857c6e5e01da6 -- ldv

4 months, 1 week

1
0
0 0

[PATCH] tools/nolibc: add support for openat(2)

by Louis Taylor

openat is useful to avoid needing to construct relative paths, so expose a wrapper for using it directly. Signed-off-by: Louis Taylor <louis(a)kragniz.eu> --- tools/include/nolibc/sys.h | 29 ++++++++++++++++++++ tools/testing/selftests/nolibc/nolibc-test.c | 22 +++++++++++++++ 2 files changed, 51 insertions(+) diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index 8f44c33b1213..e5ff34df4aee 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -765,6 +765,35 @@ int mount(const char *src, const char *tgt, return __sysret(sys_mount(src, tgt, fst, flags, data)); } +/* + * int openat(int dirfd, const char *path, int flags[, mode_t mode]); + */ + +static __attribute__((unused)) +int sys_openat(int dirfd, const char *path, int flags, mode_t mode) +{ +#ifdef __NR_openat + return my_syscall4(__NR_openat, dirfd, path, flags, mode); +#else + return __nolibc_enosys(__func__, dirfd, path, flags, mode); +#endif +} + +static __attribute__((unused)) +int openat(int dirfd, const char *path, int flags, ...) +{ + mode_t mode = 0; + + if (flags & O_CREAT) { + va_list args; + + va_start(args, flags); + mode = va_arg(args, int); + va_end(args); + } + + return __sysret(sys_openat(dirfd, path, flags, mode)); +} /* * int open(const char *path, int flags[, mode_t mode]); diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index 79c3e6a845f3..97ded6c76f99 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -1028,6 +1028,26 @@ int test_rlimit(void) return 0; } +int test_openat(void) +{ + int dev; + int null; + + dev = openat(AT_FDCWD, "/dev", O_DIRECTORY); + if (dev < 0) + return -1; + + null = openat(dev, "null", 0); + if (null < 0) { + close(dev); + return -1; + } + + close(dev); + close(null); + + return 0; +} /* Run syscall tests between IDs <min> and <max>. * Return 0 on success, non-zero on failure. @@ -1116,6 +1136,8 @@ int run_syscall(int min, int max) CASE_TEST(mmap_munmap_good); EXPECT_SYSZR(1, test_mmap_munmap()); break; CASE_TEST(open_tty); EXPECT_SYSNE(1, tmp = open("/dev/null", 0), -1); if (tmp != -1) close(tmp); break; CASE_TEST(open_blah); EXPECT_SYSER(1, tmp = open("/proc/self/blah", 0), -1, ENOENT); if (tmp != -1) close(tmp); break; + CASE_TEST(openat_fdcwd); EXPECT_SYSNE(1, tmp = openat(AT_FDCWD, "/dev/null", 0), -1); if (tmp != -1) close(tmp); break; + CASE_TEST(openat_dir); EXPECT_SYSNE(1, test_openat(), -1); break; CASE_TEST(pipe); EXPECT_SYSZR(1, test_pipe()); break; CASE_TEST(poll_null); EXPECT_SYSZR(1, poll(NULL, 0, 0)); break; CASE_TEST(poll_stdout); EXPECT_SYSNE(1, ({ struct pollfd fds = { 1, POLLOUT, 0}; poll(&fds, 1, 0); }), -1); break; -- 2.45.2

4 months, 1 week

2
3
0 0

[PATCH 0/2] selftests/pidfd: Fix missing headers

by Siddharth Menon

Fix compilation errors caused by missing headers in the pidfd selftest. The errors include: pidfd_fdinfo_test.c:230:13: error: implicit declaration of function ‘mount’ pidfd_setns_test.c:172:54: error: implicit declaration of function ‘ioctl’ Siddharth Menon (2): selftests/pidfd: Fix missing header selftests/pidfd: Fix missing header tools/testing/selftests/pidfd/pidfd_fdinfo_test.c | 1 + tools/testing/selftests/pidfd/pidfd_setns_test.c | 1 + 2 files changed, 2 insertions(+) -- 2.48.1

4 months, 1 week

2
3
0 0

CVE-2024-56741: apparmor: test: Fix memory leak for aa_unpack_strdup()

by Ben Hutchings

Hi all, CVE-2024-56741 is supposed to be fixed by commit 7290f5923191 "apparmor: test: Fix memory leak for aa_unpack_strdup()" but I think this assignment should be rejected. While a user-triggered memory leak may be exploitable for denial-of- service, the code that was fixed here is a part of KUnit tests. KUnit tests usually run a single time at boot, not under user control, and can then later be invoked through debugfs by the root user. Firstly, it is intended that the root user can deny service through the reboot system call, so I don't think additional ways to do this are security flaws. Secondly, the KUnit documentation at <https://docs.kernel.org/dev- tools/kunit/run_manual.html> says: Note: KUnit is not designed for use in a production system. It is possible that tests may reduce the stability or security of the system. so I don't think security issues in KUnit tests generally deserve CVE IDs. (That said, the help text for CONFIG_KUNIT does not have such a warning.) Ben. -- Ben Hutchings Any smoothly functioning technology is indistinguishable from a rigged demo.

4 months, 1 week

2
1
0 0

[PATCH] selftests/dma: Fix bad array reference.

by Liu Ye

dir[directions] should be directions[dir] to correctly index the directions array. Signed-off-by: Liu Ye <liuye(a)kylinos.cn> --- tools/testing/selftests/dma/dma_map_benchmark.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c index b12f1f9babf8..b925756373ce 100644 --- a/tools/testing/selftests/dma/dma_map_benchmark.c +++ b/tools/testing/selftests/dma/dma_map_benchmark.c @@ -118,7 +118,7 @@ int main(int argc, char **argv) } printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s granule: %d\n", - threads, seconds, node, dir[directions], granule); + threads, seconds, node, directions[dir], granule); printf("average map latency(us):%.1f standard deviation:%.1f\n", map.avg_map_100ns/10.0, map.map_stddev/10.0); printf("average unmap latency(us):%.1f standard deviation:%.1f\n", -- 2.25.1

4 months, 1 week

3
3
0 0

[PATCH 0/8] tracing: probes: Fixes and enhancing error logs

by Masami Hiramatsu (Google)

The following series fixes some bugs and adding some error messages which are not handled. This also add some selftests which tests the new error messages. Thank you, --- Masami Hiramatsu (Google) (8): tracing: tprobe-events: Fix a memory leak when tprobe with $retval tracing: tprobe-events: Reject invalid tracepoint name tracing: fprobe-events: Log error for exceeding the number of entry args tracing: probe-events: Log errro for exceeding the number of arguments tracing: probe-events: Remove unused MAX_ARG_BUF_LEN macro selftests/ftrace: Expand the tprobe event test to check wrong format selftests/ftrace: Add new syntax error test selftests/ftrace: Add dynamic events argument limitation test case kernel/trace/trace_eprobe.c | 2 + kernel/trace/trace_fprobe.c | 25 +++++++++++- kernel/trace/trace_kprobe.c | 5 ++ kernel/trace/trace_probe.h | 6 ++- kernel/trace/trace_uprobe.c | 9 +++- .../ftrace/test.d/dynevent/add_remove_tprobe.tc | 14 +++++++ .../ftrace/test.d/dynevent/dynevent_limitations.tc | 42 ++++++++++++++++++++ .../ftrace/test.d/dynevent/fprobe_syntax_errors.tc | 1 8 files changed, 98 insertions(+), 6 deletions(-) create mode 100644 tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc -- Masami Hiramatsu (Google) <mhiramat(a)kernel.org>

4 months, 1 week

4
19
0 0

[PATCH] selftests/nolibc: only run constructor tests on nolibc

by Thomas Weißschuh

The nolibc testsuite can be run against other libcs to test for interoperability. Some aspects of the constructor execution are not standardized and musl does not provide all tested feature, for one it does not provide arguments to the constructors, anymore? Skip the constructor tests on non-nolibc configurations. Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- tools/testing/selftests/nolibc/nolibc-test.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index 798fbdcd3ff8c36b514feb3fa1c7b8d7701cccd7..94db506eca906ff0ce8f518298dee34abf386484 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -738,9 +738,9 @@ int run_startup(int min, int max) CASE_TEST(environ_HOME); EXPECT_PTRNZ(1, getenv("HOME")); break; CASE_TEST(auxv_addr); EXPECT_PTRGT(test_auxv != (void *)-1, test_auxv, brk); break; CASE_TEST(auxv_AT_UID); EXPECT_EQ(1, getauxval(AT_UID), getuid()); break; - CASE_TEST(constructor); EXPECT_EQ(1, constructor_test_value, 2); break; + CASE_TEST(constructor); EXPECT_EQ(is_nolibc, constructor_test_value, 2); break; CASE_TEST(linkage_errno); EXPECT_PTREQ(1, linkage_test_errno_addr(), &errno); break; - CASE_TEST(linkage_constr); EXPECT_EQ(1, linkage_test_constructor_test_value, 6); break; + CASE_TEST(linkage_constr); EXPECT_EQ(is_nolibc, linkage_test_constructor_test_value, 6); break; case __LINE__: return ret; /* must be last */ /* note: do not set any defaults so as to permit holes above */ --- base-commit: 16681bea9a80080765c98b545ad74c17de2d513c change-id: 20250212-nolibc-test-constructor-42491ba71a19 Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

4 months, 1 week

2
6
0 0

[PATCH] kunit: constify return of string literals

by Christian Göttsche

From: Christian Göttsche <cgzones(a)googlemail.com> The function kunit_status_to_ok_not_ok() returns string literals, thus declare the return value as such. Reported by clang: ./include/kunit/test.h:143:10: warning: returning 'const char[3]' from a function with result type 'char *' discards qualifiers [-Wincompatible-pointer-types-discards-qualifiers] 143 | return "ok"; | ^~~~ ./include/kunit/test.h:145:10: warning: returning 'const char[7]' from a function with result type 'char *' discards qualifiers [-Wincompatible-pointer-types-discards-qualifiers] 145 | return "not ok"; | ^~~~~~~~ ./include/kunit/test.h:147:9: warning: returning 'const char[8]' from a function with result type 'char *' discards qualifiers [-Wincompatible-pointer-types-discards-qualifiers] 147 | return "invalid"; | ^~~~~~~~~ Signed-off-by: Christian Göttsche <cgzones(a)googlemail.com> --- include/kunit/test.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/kunit/test.h b/include/kunit/test.h index 34b71e42fb10..ae1b57578476 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -135,7 +135,7 @@ struct kunit_case { struct string_stream *log; }; -static inline char *kunit_status_to_ok_not_ok(enum kunit_status status) +static inline const char *kunit_status_to_ok_not_ok(enum kunit_status status) { switch (status) { case KUNIT_SKIPPED: -- 2.45.2

4 months, 1 week

2
1
0 0

[PATCH 0/2] selftests/nolibc: add armthumb configuration

by Thomas Weißschuh

While nolibc does support ARM Thumb instructions, that support was not tested specifically. Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- Thomas Weißschuh (2): selftests/nolibc: explicitly enable ARM mode selftests/nolibc: add armthumb configuration tools/testing/selftests/nolibc/Makefile | 7 +++++++ tools/testing/selftests/nolibc/run-tests.sh | 5 +++-- 2 files changed, 10 insertions(+), 2 deletions(-) --- base-commit: 3bd53b2fa57d9472d3af63b3f4d26023ba07b579 change-id: 20250228-nolibc-armthumb-372963140267 Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

4 months, 1 week

2
3
0 0

[PATCH V3 0/3] selftests: add ublk selftests

by Ming Lei

Hello Jens, This patchset adds ublk kernel selftests, which is very handy for developer for verifying kernel change, especially ublk heavily depends on io_uring subsystem. Also it provides template for target implementation. Please consider it for v6.15. The 1st patch adds one ublk utility and one entry test. The 2nd patch adds test over file backed ublk. The 3rd patch adds test for ublk zero copy. How to run: - make install - make headers_install INSTALL_HDR_PATH=/usr # in case UAPI is changed - reboot - make -C tools/testing/selftests TARGETS=ublk run_test Thanks, V3: - re-organize code, and move target code into standalone source file - fix one error handling bug - add licence tag - add dma limit for zero copy file backed target - kill checkpatch ERROR V2: - fix one sqe allocation bug, so ublk zero copy with io_link can pass - dump log in case of error - add one more test for mkfs/mount on zero copy Ming Lei (3): selftests: ublk: add kernel selftests for ublk selftests: ublk: add file backed ublk selftests: ublk: add ublk zero copy test MAINTAINERS | 1 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/ublk/.gitignore | 3 + tools/testing/selftests/ublk/Makefile | 16 + tools/testing/selftests/ublk/config | 1 + tools/testing/selftests/ublk/file_backed.c | 220 ++++ tools/testing/selftests/ublk/kublk.c | 1110 ++++++++++++++++++ tools/testing/selftests/ublk/kublk.h | 326 +++++ tools/testing/selftests/ublk/null.c | 38 + tools/testing/selftests/ublk/test_common.sh | 113 ++ tools/testing/selftests/ublk/test_loop_01.sh | 31 + tools/testing/selftests/ublk/test_loop_02.sh | 22 + tools/testing/selftests/ublk/test_loop_03.sh | 33 + tools/testing/selftests/ublk/test_loop_04.sh | 22 + tools/testing/selftests/ublk/test_null_01.sh | 19 + 15 files changed, 1956 insertions(+) create mode 100644 tools/testing/selftests/ublk/.gitignore create mode 100644 tools/testing/selftests/ublk/Makefile create mode 100644 tools/testing/selftests/ublk/config create mode 100644 tools/testing/selftests/ublk/file_backed.c create mode 100644 tools/testing/selftests/ublk/kublk.c create mode 100644 tools/testing/selftests/ublk/kublk.h create mode 100644 tools/testing/selftests/ublk/null.c create mode 100755 tools/testing/selftests/ublk/test_common.sh create mode 100755 tools/testing/selftests/ublk/test_loop_01.sh create mode 100755 tools/testing/selftests/ublk/test_loop_02.sh create mode 100755 tools/testing/selftests/ublk/test_loop_03.sh create mode 100755 tools/testing/selftests/ublk/test_loop_04.sh create mode 100755 tools/testing/selftests/ublk/test_null_01.sh -- 2.47.0

4 months, 1 week

2
7
0 0

[PATCH bpf-next v1 0/3] Optimize bpf selftest to increase CI success rate

by Jiayuan Chen

1. Optimized some static bound port selftests to avoid port occupation when running test_progs -j. 2. Optimized the retry logic for test_maps. Some Failed CI: https://github.com/kernel-patches/bpf/actions/runs/13275542359/job/37064974… https://github.com/kernel-patches/bpf/actions/runs/13549227497/job/37868926… https://github.com/kernel-patches/bpf/actions/runs/13548089029/job/37865812… https://github.com/kernel-patches/bpf/actions/runs/13553536268/job/37883329… (Perhaps it's due to the large number of pull requests requiring CI runs?) Jiayuan Chen (3): selftests/bpf: Allow auto port binding for cgroup connect selftests/bpf: Allow auto port binding for bpf nf selftests/bpf: Fixes for test_maps test tools/testing/selftests/bpf/prog_tests/bpf_nf.c | 9 ++++++--- .../testing/selftests/bpf/prog_tests/cgroup_v1v2.c | 13 +++++++++---- .../testing/selftests/bpf/progs/connect4_dropper.c | 4 +++- tools/testing/selftests/bpf/test_maps.c | 9 +++++---- 4 files changed, 23 insertions(+), 12 deletions(-) -- 2.47.1

4 months, 1 week

4
6
0 0

[PATCH]][next] KVM: selftests: Fix spelling mistake "UFFDIO_CONINUE" -> "UFFDIO_CONTINUE"

by Colin Ian King

There is a spelling mistake in a PER_PAGE_DEBUG debug message. Fix it. Signed-off-by: Colin Ian King <colin.i.king(a)gmail.com> --- tools/testing/selftests/kvm/lib/userfaultfd_util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/lib/userfaultfd_util.c b/tools/testing/selftests/kvm/lib/userfaultfd_util.c index 7c9de8414462..5bde176cedd5 100644 --- a/tools/testing/selftests/kvm/lib/userfaultfd_util.c +++ b/tools/testing/selftests/kvm/lib/userfaultfd_util.c @@ -114,7 +114,7 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay, PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n", is_minor ? "MINOR" : "MISSING", - is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY"); + is_minor ? "UFFDIO_CONTINUE" : "UFFDIO_COPY"); uffd_desc = malloc(sizeof(struct uffd_desc)); TEST_ASSERT(uffd_desc, "Failed to malloc uffd descriptor"); -- 2.47.2

4 months, 1 week

2
1
0 0

[PATCH v6 0/3] Add support for the Idle HLT intercept feature

by Manali Shukla

The upcoming new Idle HLT Intercept feature allows for the HLT instruction execution by a vCPU to be intercepted by the hypervisor only if there are no pending V_INTR and V_NMI events for the vCPU. When the vCPU is expected to service the pending V_INTR and V_NMI events, the Idle HLT intercept won’t trigger. The feature allows the hypervisor to determine if the vCPU is actually idle and reduces wasteful VMEXITs. The Idle HLT intercept feature is used for enlightened guests who wish to securely handle the events. When an enlightened guest does a HLT while an interrupt is pending, hypervisor will not have a way to figure out whether the guest needs to be re-entered or not. The Idle HLT intercept feature allows the HLT execution only if there are no pending V_INTR and V_NMI events. Presence of the Idle HLT Intercept feature is indicated via CPUID function Fn8000_000A_EDX[30]. Document for the Idle HLT intercept feature is available at [1]. This series is based on kvm-x86/next (eb723766b103) + [2]. Testing Done: - Tested the functionality for the Idle HLT intercept feature using selftest ipi_hlt_test. - Tested on normal, SEV, SEV-ES, SEV-SNP guest for the Idle HLT intercept functionality. - Tested the Idle HLT intercept functionality on nested guest. v5 -> v6 - Incorporated Neeraj's review comments on selftest. v4 -> v5 - Incorporated Sean's review comments on nested Idle HLT intercept support. - Make svm_idle_hlt_test independent of the Idle HLT to run on all hardware. v3 -> v4 - Drop the patches to add vcpu_get_stat() into a new series [2]. - Added nested Idle HLT intercept support. v2 -> v3 - Incorporated Andrew's suggestion to structure vcpu_stat_types in a way that each architecture can share the generic types and also provide its own. v1 -> v2 - Did changes in svm_idle_hlt_test based on the review comments from Sean. - Added an enum based approach to get binary stats in vcpu_get_stat() which doesn't use string to get stat data based on the comments from Sean. - Added safe_halt() and cli() helpers based on the comments from Sean. [1]: AMD64 Architecture Programmer's Manual Pub. 24593, April 2024, Vol 2, 15.9 Instruction Intercepts (Table 15-7: IDLE_HLT). https://bugzilla.kernel.org/attachment.cgi?id=306251 [2]: https://lore.kernel.org/kvm/ee027335-f1b9-4637-bc79-27a610c1ab08@amd.com/T/… --- V5: https://lore.kernel.org/kvm/20250103081828.7060-1-manali.shukla@amd.com/ V4: https://lore.kernel.org/kvm/20241022054810.23369-1-manali.shukla@amd.com/ V3: https://lore.kernel.org/kvm/20240528041926.3989-4-manali.shukla@amd.com/T/ V2: https://lore.kernel.org/kvm/20240501145433.4070-1-manali.shukla@amd.com/ V1: https://lore.kernel.org/kvm/20240307054623.13632-1-manali.shukla@amd.com/ Manali Shukla (3): x86/cpufeatures: Add CPUID feature bit for Idle HLT intercept KVM: SVM: Add Idle HLT intercept support KVM: selftests: Add self IPI HLT test arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/svm.h | 1 + arch/x86/include/uapi/asm/svm.h | 2 + arch/x86/kvm/svm/svm.c | 13 ++- tools/testing/selftests/kvm/Makefile.kvm | 1 + .../selftests/kvm/include/x86/processor.h | 1 + tools/testing/selftests/kvm/ipi_hlt_test.c | 81 +++++++++++++++++++ 7 files changed, 97 insertions(+), 3 deletions(-) create mode 100644 tools/testing/selftests/kvm/ipi_hlt_test.c base-commit: eb723766b1030a23c38adf2348b7c3d1409d11f0 prerequisite-patch-id: cb345fc0d814a351df2b5788b76eee0eef9de549 prerequisite-patch-id: 71806f400cffe09f47d6231cb072cbdbd540de1b prerequisite-patch-id: 9ea0412aab7ecd8555fcee3e9609dbfe8456d47b prerequisite-patch-id: 3504df50cdd33958456f2e56139d76867273525c prerequisite-patch-id: 674e56729a56cc487cb85be1a64ef561eb7bac8a prerequisite-patch-id: 48e87354f9d6e6bd121ca32ab73cd0d7f1dce74f prerequisite-patch-id: b32c21df6522a7396baa41d62bcad9479041d97a prerequisite-patch-id: 0ff4b504e982db7c1dfa8ec6ac485c92a89f4af8 prerequisite-patch-id: 509018dc2fc1657debc641544e86f5a92d04bc1a -- 2.34.1

4 months, 1 week

3
15
0 0

[PATCH v2 0/9] selftests/mm: Some cleanups from trying to run them

by Brendan Jackman

I never had much luck running mm selftests so I spent a couple of hours digging into why. Looks like most of the reason is missing SKIP checks, so this series is just adding a bunch of those that I found. I did not do anything like all of them, just the ones I spotted in gup_longterm, gup_test, mmap, userfaultfd and memfd_secret. It's a bit unfortunate to have to skip those tests when ftruncate() fails, but I don't have time to dig deep enough into it to actually make them pass - I observed these issues on both 9p and virtiofs. Probably it requires digging into the filesystem implementation (An alternative might just be to mount a tmpfs in the test script). I am also seeing some failures to allocate hugetlb pages in uffd-mp-mremap that I have not had time to fully understand, you can see those here: https://gist.github.com/bjackman/af74c3a6e60975e6ff0d760cba1e05d2#file-user… Signed-off-by: Brendan Jackman <jackmanb(a)google.com> --- Changes in v2 (Thanks to Dev for the reviews): - Improve and cleanup some error messages - Add some extra SKIPs - Fix misnaming of nr_cpus variable in uffd tests - Link to v1: https://lore.kernel.org/r/20250220-mm-selftests-v1-0-9bbf57d64463@google.com --- Brendan Jackman (9): selftests/mm: Report errno when things fail in gup_longterm selftests/mm: Fix assumption that sudo is present selftests/mm: Skip uffd-stress if userfaultfd not available selftests/mm: Skip uffd-wp-mremap if userfaultfd not available selftests/mm/uffd: Rename nr_cpus -> nr_threads selftests/mm: Print some details when uffd-stress gets bad params selftests/mm: Don't fail uffd-stress if too many CPUs selftests/mm: Skip map_populate on weird filesystems selftests/mm: Skip gup_longerm tests on weird filesystems tools/testing/selftests/mm/gup_longterm.c | 45 ++++++++++++++++++---------- tools/testing/selftests/mm/map_populate.c | 7 +++++ tools/testing/selftests/mm/run_vmtests.sh | 22 +++++++++++--- tools/testing/selftests/mm/uffd-common.c | 8 ++--- tools/testing/selftests/mm/uffd-common.h | 2 +- tools/testing/selftests/mm/uffd-stress.c | 42 ++++++++++++++++---------- tools/testing/selftests/mm/uffd-unit-tests.c | 2 +- tools/testing/selftests/mm/uffd-wp-mremap.c | 5 +++- 8 files changed, 90 insertions(+), 43 deletions(-) --- base-commit: a3daad8215143340c0870c5489e599fd059037e9 change-id: 20250220-mm-selftests-2d7d0542face Best regards, -- Brendan Jackman <jackmanb(a)google.com>

4 months, 1 week

1
12
0 0

[RFC PATCH 00/31] AMD: Add Secure AVIC KVM selftests

by Neeraj Upadhyay

This series adds KVM selftests for Secure AVIC. The Secure AVIC KVM support patch series is at: https://lore.kernel.org/kvm/20250228085115.105648-1-Neeraj.Upadhyay@amd.com… Git tree is available at: https://github.com/AMDESE/linux-kvm/tree/savic-host-latest This series depends on SNP Smoke tests patch series by Pratik: https://lore.kernel.org/lkml/20250123220100.339867-1-prsampat@amd.com/ - Patch 1-6 are taken from Peter Gonda's patch series for GHCB support for SEV-ES guests. GHCB support for SNP guests is added to these patches. https://lore.kernel.org/lkml/Ziln_Spd6KtgVqkr@google.com/T/#m6c0fc7e2b2e35f… Patches 7-8 are fixes on top of Peter's series. - Patch 9 fixes IDT vector for #VC exception (29) which has a valid error code associated with the exception. - Patch 10 adds #VC exception handling for rdmsr/wrmsr accesses of SEV-ES guests. - Patch 11 skips vm_is_gpa_protected() check for APIC MMIO base address in __virt_pg_map() for VMs with protected memory. This is required for xapic tests enablement for SEV VMs. - Patch 12 and 13 are PoC patches to support MMIO #VC handling for SEV-ES guests. They add x86 instruction decoding support. - Patch 14 adds #VC handling for MMIO accesses by SEV-ES guests. - Patch 15 adds movabs instruction decoding for cases where compiler generates movabs for MMIO reads/writes. - Patch 16 adds SEV guests testing support in xapic_state_test. - Patch 17 adds x2apic mode support in xapic_ipi_test. - Patch 18 adds SEV VMs support in xapic_ipi_test. - Patch 19 adds a library for Secure AVIC backing page initialization and enabling Secure AVIC for a SNP guest. - Patch 20 adds support for SVM_EXIT_AVIC_UNACCELERATED_ACCESS #VC exception handling for APIC msr reads/writes by Secure AVIC enabled VM. - Patch 21 adds support for SVM_EXIT_AVIC_INCOMPLETE_IPI #VC error code handling for Secure AVIC enabled VM. - Patch 22 adds args param to kvm_arch_vm_post_create() to pass vmsa features to KVM_SEV_INIT2 ioctl for SEV VMs. - Patch 23 adds an api for passing guest APIC page GPA to Hypervisor. - Patch 24 adds Secure AVIC VM support to xapic_ipi_test test. - Patch 25 adds a test for verifying APIC regs MMIO/msr accesses for a Secure AVIC VM before it enables x2apic mode, in x2apic mode and after enabling Secure AVIC in the Secure AVIC control msr. - Patch 26 adds a msr access test to verify accelerated/unaccelerated msr acceses for Secure AVIC enabled VM. - Patch 27 tests idle hlt for Secure AVIC enabled VM. - Patch 28 adds IOAPIC tests for Secure AVIC enabled VM. - Patch 29 adds cross-vCPU IPI testing with various destination shorthands for Secure AVIC enabled VM. - Patch 30 adds Hypervisor NMI injection and cross-vCPU ICR based NMI for Secure AVIC enabled VM. - Patch 31 adds MSI injection test for Secure AVIC enabled VM. Neeraj Upadhyay (25): KVM: selftests: Fix ghcb_entry returned in ghcb_alloc() KVM: selftests: Make GHCB entry page size aligned KVM: selftests: Add support for #VC in x86 exception handlers KVM: selftests: Add MSR VC handling support for SEV-ES VMs KVM: selftests: Skip vm_is_gpa_protected() call for APIC MMIO base KVM: selftests: Add instruction decoding support KVM: selftests: Add instruction decoding support KVM: selftests: Add MMIO VC exception handling for SEV-ES guests KVM: selftests: Add instruction decoding for movabs instructions KVM: selftests: Add SEV guests support in xapic_state_test KVM: selftests: Add x2apic mode testing in xapic_ipi_test KVM: selftests: Add SEV VM support in xapic_ipi_test KVM: selftests: Add Secure AVIC lib KVM: selftests: Add unaccelerated APIC msrs #VC handling KVM: selftests: Add IPI handling support for Secure AVIC KVM: selftests: Add args param to kvm_arch_vm_post_create() KVM: selftests: Add SAVIC GPA notification GHCB call KVM: selftests: Add Secure AVIC mode to xapic_ipi_test KVM: selftests: Add Secure AVIC APIC regs test KVM: selftests: Add test to verify APIC MSR accesses for SAVIC guest KVM: selftests: Extend savic test with idle halt testing KVM: selftests: Add IOAPIC tests for Secure AVIC KVM: selftests: Add cross-vCPU IPI testing for SAVIC guests KVM: selftests: Add NMI test for SAVIC guests KVM: selftests: Add MSI injection test for SAVIC Peter Gonda (6): Add GHCB with setters and getters Add arch specific additional guest pages Add vm_vaddr_alloc_pages_shared() Add GHCB allocations and helpers Add is_sev_enabled() helpers Add ability for SEV-ES guests to use ucalls via GHCB tools/arch/x86/include/asm/msr-index.h | 4 +- tools/testing/selftests/kvm/.gitignore | 3 +- tools/testing/selftests/kvm/Makefile.kvm | 16 +- .../testing/selftests/kvm/include/kvm_util.h | 14 +- .../testing/selftests/kvm/include/x86/apic.h | 57 + .../selftests/kvm/include/x86/ex_regs.h | 21 + .../selftests/kvm/include/x86/insn-eval.h | 48 + .../selftests/kvm/include/x86/processor.h | 18 +- .../testing/selftests/kvm/include/x86/savic.h | 25 + tools/testing/selftests/kvm/include/x86/sev.h | 15 + tools/testing/selftests/kvm/include/x86/svm.h | 109 ++ tools/testing/selftests/kvm/lib/kvm_util.c | 109 +- .../testing/selftests/kvm/lib/x86/handlers.S | 4 +- .../testing/selftests/kvm/lib/x86/insn-eval.c | 1726 +++++++++++++++++ .../testing/selftests/kvm/lib/x86/processor.c | 24 +- tools/testing/selftests/kvm/lib/x86/savic.c | 490 +++++ tools/testing/selftests/kvm/lib/x86/sev.c | 598 +++++- tools/testing/selftests/kvm/lib/x86/ucall.c | 18 + tools/testing/selftests/kvm/s390/cmma_test.c | 2 +- tools/testing/selftests/kvm/x86/savic_test.c | 1549 +++++++++++++++ .../selftests/kvm/x86/sev_smoke_test.c | 40 +- .../selftests/kvm/x86/xapic_ipi_test.c | 183 +- .../selftests/kvm/x86/xapic_state_test.c | 117 +- 23 files changed, 5084 insertions(+), 106 deletions(-) create mode 100644 tools/testing/selftests/kvm/include/x86/ex_regs.h create mode 100644 tools/testing/selftests/kvm/include/x86/insn-eval.h create mode 100644 tools/testing/selftests/kvm/include/x86/savic.h create mode 100644 tools/testing/selftests/kvm/lib/x86/insn-eval.c create mode 100644 tools/testing/selftests/kvm/lib/x86/savic.c create mode 100644 tools/testing/selftests/kvm/x86/savic_test.c base-commit: f7bafceba76e9ab475b413578c1757ee18c3e44b -- 2.34.1

4 months, 2 weeks

1
31
0 0

[PATCH bpf-next 00/10] selftests/bpf: Migrate test_tunnel.sh to test_progs

by Bastien Curutchet (eBPF Foundation)

Hi all, This patch series continues the work to migrate the *.sh tests into prog_tests framework. The test_tunnel.sh script has already been partly migrated to test_progs in prog_tests/test_tunnel.c so I add my work to it. PATCH 1 & 2 create some helpers to avoid code duplication and ease the migration in the following patches. PATCH 3 to 9 migrate the tests of gre, ip6gre, erspan, ip6erspan, geneve, ip6geneve and ip6tnl tunnels. PATCH 10 removes test_tunnel.sh Signed-off-by: Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com> --- Bastien Curutchet (eBPF Foundation) (10): selftests/bpf: test_tunnel: Add generic_attach* helpers selftests/bpf: test_tunnel: Add ping helpers selftests/bpf: test_tunnel: Move gre tunnel test to test_progs selftests/bpf: test_tunnel: Move ip6gre tunnel test to test_progs selftests/bpf: test_tunnel: Move erspan tunnel tests to test_progs selftests/bpf: test_tunnel: Move ip6erspan tunnel test to test_progs selftests/bpf: test_tunnel: Move geneve tunnel test to test_progs selftests/bpf: test_tunnel: Move ip6geneve tunnel test to test_progs selftests/bpf: test_tunnel: Move ip6tnl tunnel tests to test_progs selftests/bpf: test_tunnel: Remove test_tunnel.sh tools/testing/selftests/bpf/Makefile | 1 - .../testing/selftests/bpf/prog_tests/test_tunnel.c | 627 +++++++++++++++++--- tools/testing/selftests/bpf/test_tunnel.sh | 645 --------------------- 3 files changed, 532 insertions(+), 741 deletions(-) --- base-commit: 16566afa71143757b49fc4b2a331639f487d105a change-id: 20250131-tunnels-59b641ea3f10 Best regards, -- Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com>

4 months, 2 weeks

3
22
0 0

[PATCH bpf-next v1 0/3] bpf: Fix use-after-free of sockmap

by Jiayuan Chen

1. Issue Syzkaller reported this issue [1]. 2. Reproduce We can reproduce this issue by using the test_sockmap_with_close_on_write() test I provided in selftest, also you need to apply the following patch to ensure 100% reproducibility (sleep after checking sock): ''' static void sk_psock_verdict_data_ready(struct sock *sk) { ....... if (unlikely(!sock)) return; + if (!strcmp("test_progs", current->comm)) { + printk("sleep 2s to wait socket freed\n"); + mdelay(2000); + printk("sleep end\n"); + } ops = READ_ONCE(sock->ops); if (!ops || !ops->read_skb) return; } ''' Then running './test_progs -v sockmap_basic', and if the kernel has KASAN enabled [2], you will see the following warning: ''' BUG: KASAN: slab-use-after-free in sk_psock_verdict_data_ready+0x29b/0x2d0 Read of size 8 at addr ffff88813a777020 by task test_progs/47055 Tainted: [O]=OOT_MODULE Call Trace: <TASK> dump_stack_lvl+0x53/0x70 print_address_description.constprop.0+0x30/0x420 ? sk_psock_verdict_data_ready+0x29b/0x2d0 print_report+0xb7/0x270 ? sk_psock_verdict_data_ready+0x29b/0x2d0 ? kasan_addr_to_slab+0xd/0xa0 ? sk_psock_verdict_data_ready+0x29b/0x2d0 kasan_report+0xca/0x100 ? sk_psock_verdict_data_ready+0x29b/0x2d0 sk_psock_verdict_data_ready+0x29b/0x2d0 unix_stream_sendmsg+0x4a6/0xa40 ? __pfx_unix_stream_sendmsg+0x10/0x10 ? fdget+0x2c1/0x3a0 __sys_sendto+0x39c/0x410 ''' 3. Reason ''' CPU0 CPU1 unix_stream_sendmsg(sk): other = unix_peer(sk) other->sk_data_ready(other): socket *sock = sk->sk_socket if (unlikely(!sock)) return; close(other): ... other->close() free(socket) READ_ONCE(sock->ops) ^ use 'sock' after free ''' For TCP, UDP, or other protocols, we have already performed rcu_read_lock() when the network stack receives packets in ip_input.c: ''' ip_local_deliver_finish(): rcu_read_lock() ip_protocol_deliver_rcu() xxx_rcv rcu_read_unlock() ''' However, for Unix sockets, sk_data_ready is called directly from the process context without rcu_read_lock() protection. 4. Solution Based on the fact that the 'struct socket' is released using call_rcu(), We add rcu_read_{un}lock() at the entrance and exit of our sk_data_ready. It will not increase performance overhead, at least for TCP and UDP, they are already in a relatively large critical section. Of course, we can also add a custom callback for Unix sockets and call rcu_read_lock() before calling _verdict_data_ready like this: ''' if (sk_is_unix(sk)) sk->sk_data_ready = sk_psock_verdict_data_ready_rcu; else sk->sk_data_ready = sk_psock_verdict_data_ready; sk_psock_verdict_data_ready_rcu(): rcu_read_lock() sk_psock_verdict_data_ready() rcu_read_unlock() ''' However, this will cause too many branches, and it's not suitable to distinguish network protocols in skmsg.c. [1] https://syzkaller.appspot.com/bug?extid=dd90a702f518e0eac072 [2] https://syzkaller.appspot.com/text?tag=KernelConfig&x=1362a5aee630ff34 Jiayuan Chen (3): bpf, sockmap: avoid using sk_socket after free selftests/bpf: Add socketpair to create_pair to support unix socket selftests/bpf: Add edge case tests for sockmap net/core/skmsg.c | 18 ++++-- .../selftests/bpf/prog_tests/socket_helpers.h | 13 ++++- .../selftests/bpf/prog_tests/sockmap_basic.c | 57 +++++++++++++++++++ 3 files changed, 82 insertions(+), 6 deletions(-) -- 2.47.1

4 months, 2 weeks

4
13
0 0

[PATCH v2 0/3] selftests/net: deflake GRO tests and fix return value and output

by Kevin Krakauer

The GRO selftests can flake and have some confusing behavior. These changes make the output and return value of GRO behave as expected, then deflake the tests. v2: - Split into multiple commits. - Reduced napi_defer_hard_irqs to 1. - Reduced gro_flush_timeout to 100us. - Fixed comment that wasn't updated. v1: https://lore.kernel.org/netdev/20250218164555.1955400-1-krakauer@google.com/ Kevin Krakauer (3): selftests/net: have `gro.sh -t` return a correct exit code selftests/net: only print passing message in GRO tests when tests pass selftests/net: deflake GRO tests tools/testing/selftests/net/gro.c | 8 +++++--- tools/testing/selftests/net/gro.sh | 7 ++++--- tools/testing/selftests/net/setup_veth.sh | 3 ++- 3 files changed, 11 insertions(+), 7 deletions(-) -- 2.48.1.658.g4767266eb4-goog

4 months, 2 weeks

3
10
0 0

[PATCH][next] KVM: selftests: Fix spelling mistake "avaialable" -> "available"

by Colin Ian King

There is a spelling mistake in a ksft_test_result_skip message. Fix it. Signed-off-by: Colin Ian King <colin.i.king(a)gmail.com> --- tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c b/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c index 27255880dabd..aded795d42be 100644 --- a/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c +++ b/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c @@ -291,7 +291,7 @@ int main(int argc, char *argv[]) ksft_test_result_pass("%s\n", testlist[idx].subfunc_name); free(array); } else { - ksft_test_result_skip("%s feature is not avaialable\n", + ksft_test_result_skip("%s feature is not available\n", testlist[idx].subfunc_name); } } -- 2.47.2

4 months, 2 weeks

1
0
0 0

[PATCH v2 0/7] iommu: Add MSI mapping support with nested SMMU (Part-1 core)

by Nicolin Chen

[ Background ] On ARM GIC systems and others, the target address of the MSI is translated by the IOMMU. For GIC, the MSI address page is called "ITS" page. When the IOMMU is disabled, the MSI address is programmed to the physical location of the GIC ITS page (e.g. 0x20200000). When the IOMMU is enabled, the ITS page is behind the IOMMU, so the MSI address is programmed to an allocated IO virtual address (a.k.a IOVA), e.g. 0xFFFF0000, which must be mapped to the physical ITS page: IOVA (0xFFFF0000) ===> PA (0x20200000). When a 2-stage translation is enabled, IOVA will be still used to program the MSI address, though the mappings will be in two stages: IOVA (0xFFFF0000) ===> IPA (e.g. 0x80900000) ===> PA (0x20200000) (IPA stands for Intermediate Physical Address). If the device that generates MSI is attached to an IOMMU_DOMAIN_DMA, the IOVA is dynamically allocated from the top of the IOVA space. If attached to an IOMMU_DOMAIN_UNMANAGED (e.g. a VFIO passthrough device), the IOVA is fixed to an MSI window reported by the IOMMU driver via IOMMU_RESV_SW_MSI, which is hardwired to MSI_IOVA_BASE (IOVA==0x8000000) for ARM IOMMUs. So far, this IOMMU_RESV_SW_MSI works well as kernel is entirely in charge of the IOMMU translation (1-stage translation), since the IOVA for the ITS page is fixed and known by kernel. However, with virtual machine enabling a nested IOMMU translation (2-stage), a guest kernel directly controls the stage-1 translation with an IOMMU_DOMAIN_DMA, mapping a vITS page (at an IPA 0x80900000) onto its own IOVA space (e.g. 0xEEEE0000). Then, the host kernel can't know that guest-level IOVA to program the MSI address. There have been two approaches to solve this problem: 1. Create an identity mapping in the stage-1. VMM could insert a few RMRs (Reserved Memory Regions) in guest's IORT. Then the guest kernel would fetch these RMR entries from the IORT and create an IOMMU_RESV_DIRECT region per iommu group for a direct mapping. Eventually, the mappings would look like: IOVA (0x8000000) === IPA (0x8000000) ===> 0x20200000 This requires an IOMMUFD ioctl for kernel and VMM to agree on the IPA. 2. Forward the guest-level MSI IOVA captured by VMM to the host-level GIC driver, to program the correct MSI IOVA. Forward the VMM-defined vITS page location (IPA) to the kernel for the stage-2 mapping. Eventually: IOVA (0xFFFF0000) ===> IPA (0x80900000) ===> PA (0x20200000) This requires a VFIO ioctl (for IOVA) and an IOMMUFD ioctl (for IPA). Worth mentioning that when Eric Auger was working on the same topic with the VFIO iommu uAPI, he had a solution for approach (2) first, and then switched to approach (1), suggested by Jean-Philippe for the reduction of complexity. Approach (1) basically feels like the existing VFIO passthrough that has a 1-stage mapping for the unmanaged domain, yet only by shifting the MSI mapping from stage 1 (no-viommu case) to stage 2 (has-viommu case). So, it could reuse the existing IOMMU_RESV_SW_MSI piece, by sharing the same idea of "VMM leaving everything to the kernel". Approach (2) is an ideal solution, yet it requires additional effort for kernel to be aware of the stage-1 gIOVAs and the stage-2 IPAs for vITS page(s), which demands VMM to closely cooperate. * It also brings some complicated use cases to the table where the host or/and guest system(s) has/have multiple ITS pages. [ Execution ] Though these two approaches feel very different on the surface, they can share some underlying common infrastructure. Currently, only one pair of sw_msi functions (prepare/compose) are provided by dma-iommu for irqchip drivers to directly use. There could be different versions of functions from different domain owners: for existing VFIO passthrough cases and in- kernel DMA domain cases, reuse the existing dma-iommu's version of sw_msi functions; for nested translation use cases, there can be another version of sw_msi functions to handle mapping and msi_msg(s) differently. As a part-1 series, this refactors the core infrastructure: - Get rid of the duplication in the "compose" function - Introduce a function pointer for the previously "prepare" function - Allow different domain owners to set their own "sw_msi" implementations - Implement an iommufd_sw_msi function to additionally support non-nested use cases and also prepare for a nested translation use case using the approach (1) [ Future Plan ] Part-2 will add support of approach (1), i.e. RMR solution: - Add a pair of IOMMUFD options for a SW_MSI window for kernel and VMM to agree on (for approach 1) Part-3 and beyond will continue the effort of supporting approach (2) i.e. a complete vITS-to-pITS mapping: - Map the phsical ITS page (potentially via IOMMUFD_CMD_IOAS_MAP_MSI) - Convey the IOVAs per-irq (potentially via VFIO_IRQ_SET_ACTION_PREPARE) --- This is a joint effort that includes Jason's rework in irq/iommu/iommufd base level and my additional patches on top of that for new uAPIs. This series is on github: https://github.com/nicolinc/iommufd/commits/iommufd_msi_p1-v2 For testing with nested SMMU (approach 1): https://github.com/nicolinc/iommufd/commits/wip/iommufd_msi_p2-v2 Pairing QEMU branch for testing (approach 1): https://github.com/nicolinc/qemu/commits/wip/for_iommufd_msi_p2-v2-rmr Changelog v2 * Split the iommufd ioctl for approach (1) out of this part-1 * Rebase on Jason's for-next tree (6.14-rc2) for two iommufd patches * Update commit logs in two irqchip patches to make narrative clearer * Keep iommu_dma_compose_msi_msg() in PATCH-1 as a small cleaner step * Improve with some coding style changes: kdoc and 100-char wrapping v1 https://lore.kernel.org/kvm/cover.1739005085.git.nicolinc@nvidia.com/ * Rebase on v6.14-rc1 and iommufd_attach_handle-v1 series https://lore.kernel.org/all/cover.1738645017.git.nicolinc@nvidia.com/ * Correct typos * Replace set_bit with __set_bit * Use a common helper to get iommufd_handle * Add kdoc for iommu_msi_iova/iommu_msi_page_shift * Rename msi_msg_set_msi_addr() to msi_msg_set_addr() * Update selftest for a better coverage for the new options * Change IOMMU_OPTION_SW_MSI_START/SIZE to be per-idev and properly check against device's reserved region list RFCv2 https://lore.kernel.org/kvm/cover.1736550979.git.nicolinc@nvidia.com/ * Rebase on v6.13-rc6 * Drop all the irq/pci patches and rework the compose function instead * Add a new sw_msi op to iommu_domain for a per type implementation and let iommufd core has its own implementation to support both approaches * Add RMR-solution (approach 1) support since it is straightforward and have been used in some out-of-tree projects widely RFCv1 https://lore.kernel.org/kvm/cover.1731130093.git.nicolinc@nvidia.com/ Thanks! Nicolin Jason Gunthorpe (5): genirq/msi: Store the IOMMU IOVA directly in msi_desc instead of iommu_cookie genirq/msi: Refactor iommu_dma_compose_msi_msg() iommu: Make iommu_dma_prepare_msi() into a generic operation irqchip: Have CONFIG_IRQ_MSI_IOMMU be selected by irqchips that need it iommufd: Implement sw_msi support natively Nicolin Chen (2): iommu: Turn fault_data to iommufd private pointer iommu: Turn iova_cookie to dma-iommu private pointer drivers/iommu/Kconfig | 1 - drivers/irqchip/Kconfig | 4 + kernel/irq/Kconfig | 1 + drivers/iommu/iommufd/iommufd_private.h | 23 +++- include/linux/iommu.h | 58 +++++---- include/linux/msi.h | 55 +++++--- drivers/iommu/dma-iommu.c | 63 +++------- drivers/iommu/iommu.c | 29 +++++ drivers/iommu/iommufd/device.c | 160 ++++++++++++++++++++---- drivers/iommu/iommufd/fault.c | 2 +- drivers/iommu/iommufd/hw_pagetable.c | 5 +- drivers/iommu/iommufd/main.c | 9 ++ drivers/irqchip/irq-gic-v2m.c | 5 +- drivers/irqchip/irq-gic-v3-its.c | 13 +- drivers/irqchip/irq-gic-v3-mbi.c | 12 +- drivers/irqchip/irq-ls-scfg-msi.c | 5 +- 16 files changed, 309 insertions(+), 136 deletions(-) base-commit: dc10ba25d43f433ad5d9e8e6be4f4d2bb3cd9ddb prerequisite-patch-id: 0000000000000000000000000000000000000000 -- 2.43.0

4 months, 2 weeks

5
33
0 0

[PATCH] bpf/selftests: test_select_reuseport_kern: remove unused header

by Alexis Lothoré (eBPF Foundation)

test_select_reuseport_kern.c is currently including <stdlib.h>, but it does not use any definition from there. Remove stdlib.h inclusion from test_select_reuseport_kern.c Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore(a)bootlin.com> --- I stumbled upon this specific header include while trying to build selftests on the current bpf-next_base branch, which ended with this error: [...] CLNG-BPF [test_progs-cpuv4] test_select_reuseport_kern.bpf.o In file included from progs/test_select_reuseport_kern.c:4: /usr/include/bits/floatn.h:83:52: error: unsupported machine mode '__TC__' 83 | typedef _Complex float __cfloat128 __attribute__ ((__mode__ (__TC__))); | ^ /usr/include/bits/floatn.h:97:9: error: __float128 is not supported on this target 97 | typedef __float128 _Float128; The exact error (unknown TC mode) is likely rather due to some issues in my local build, in which I am actually cross-compiling selftests (for ARM64 from a x86_64 host, but not through vmtests.sh), and I still have to sort out some other issues. But I guess it is not really right anyway to include stdlib.h from an ebpf program, especially if it is not used, so I am still proposing this small change. --- tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c index 5eb25c6ad75b1a9c61f22e978d817d3dc88b3a2f..a5be3267dbb01372c84bb468e3a48eae69ac5329 100644 --- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018 Facebook */ -#include <stdlib.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/ipv6.h> --- base-commit: 072c40912477ebac2ef98cd0b1532ba9bebda20a change-id: 20250227-remove_wrong_header-02d288d64204 Best regards, -- Alexis Lothoré, Bootlin Embedded Linux and Kernel engineering https://bootlin.com

4 months, 2 weeks

2
1
0 0

[PATCH v3 0/2 RESEND] update kselftest framework to check for required configs

by Siddharth Menon

Currently, kselftests does not have a generalised mechanism to skip compilation and run tests when required kernel configuration options are disabled. This patch series adresses this issue by checking whether all required configs from selftest/<test>/config are enabled in the current kernel Siddharth Menon (2): selftests: Introduce script to validate required dependencies selftests/lib.mk: Introduce check to validate required dependencies .../testing/selftests/check_kselftest_deps.pl | 170 ++++++++++++++++++ tools/testing/selftests/lib.mk | 15 +- 2 files changed, 183 insertions(+), 2 deletions(-) create mode 100755 tools/testing/selftests/check_kselftest_deps.pl -- 2.48.1

4 months, 2 weeks

2
3
0 0

[RFC PATCH 0/9] bpf: Mitigate Spectre v1 using speculation barriers

by Luis Gerhorst

This improves the expressiveness of unprivileged BPF by inserting speculation barriers instead of rejcting the programs. The approach was presented at LPC'24: https://lpc.events/event/18/contributions/1954/ ("Mitigating Spectre-PHT using Speculation Barriers in Linux eBPF") and RAID'24: https://arxiv.org/pdf/2405.00078 ("VeriFence: Lightweight and Precise Spectre Defenses for Untrusted Linux Kernel Extensions") Goal of this RFC is to get feedback on the approach and the structuring into commits. TODOs to be fixed for final version: * actually emit arm64 barrier * fix unexpected_load_success from test_progs for "bpf: Fall back to nospec for sanitization-failures" * use bpf-next as base commit Luis Gerhorst (9): bpf/arm64: Unset bypass_spec_v4() instead of ignoring BPF_NOSPEC bpf: Refactor do_check() if/else into do_check_insn() bpf: Return EFAULT on misconfigurations bpf: Return EFAULT on internal errors bpf: Fall back to nospec if v1 verification fails bpf: Allow nospec-protected var-offset stack access bpf: Refactor push_stack to return error code bpf: Fall back to nospec for sanitization-failures bpf: Cut speculative path verification short arch/arm64/net/bpf_jit_comp.c | 10 +- include/linux/bpf.h | 14 +- include/linux/bpf_verifier.h | 3 +- kernel/bpf/core.c | 17 +- kernel/bpf/verifier.c | 832 ++++++++++-------- .../selftests/bpf/progs/verifier_and.c | 3 +- .../selftests/bpf/progs/verifier_bounds.c | 30 +- .../selftests/bpf/progs/verifier_movsx.c | 6 +- .../selftests/bpf/progs/verifier_unpriv.c | 3 +- .../bpf/progs/verifier_value_ptr_arith.c | 11 +- 10 files changed, 520 insertions(+), 409 deletions(-) base-commit: d082ecbc71e9e0bf49883ee4afd435a77a5101b6 -- 2.48.1

4 months, 2 weeks

1
10
0 0

[PATCH] KVM: selftests: access_tracking_perf_test: add option to skip the sanity check

by Maxim Levitsky

Add an option to skip sanity check of number of still idle pages, and force it on, in case hypervisor or NUMA balancing is detected. Signed-off-by: Maxim Levitsky <mlevitsk(a)redhat.com> --- .../selftests/kvm/access_tracking_perf_test.c | 23 +++++++++++++++++-- .../testing/selftests/kvm/include/test_util.h | 1 + tools/testing/selftests/kvm/lib/test_util.c | 22 ++++++++++++++++++ 3 files changed, 44 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index 3c7defd34f56..eafaecf086c4 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -65,6 +65,8 @@ static int vcpu_last_completed_iteration[KVM_MAX_VCPUS]; /* Whether to overlap the regions of memory vCPUs access. */ static bool overlap_memory_access; +static bool skip_sanity_check; + struct test_params { /* The backing source for the region of memory. */ enum vm_mem_backing_src_type backing_src; @@ -185,7 +187,7 @@ static void mark_vcpu_memory_idle(struct kvm_vm *vm, */ if (still_idle >= pages / 10) { #ifdef __x86_64__ - TEST_ASSERT(this_cpu_has(X86_FEATURE_HYPERVISOR), + TEST_ASSERT(skip_sanity_check, "vCPU%d: Too many pages still idle (%lu out of %lu)", vcpu_idx, still_idle, pages); #endif @@ -342,6 +344,8 @@ static void help(char *name) printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); + printf(" -u: Skip check that after dirtying the guest memory, most (90%%) of\n" + "it is reported as dirty again"); backing_src_help("-s"); puts(""); exit(0); @@ -359,7 +363,7 @@ int main(int argc, char *argv[]) guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hm:b:v:os:")) != -1) { + while ((opt = getopt(argc, argv, "hm:b:v:os:u")) != -1) { switch (opt) { case 'm': guest_modes_cmdline(optarg); @@ -376,6 +380,9 @@ int main(int argc, char *argv[]) case 's': params.backing_src = parse_backing_src_type(optarg); break; + case 'u': + skip_sanity_check = true; + break; case 'h': default: help(argv[0]); @@ -386,6 +393,18 @@ int main(int argc, char *argv[]) page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR); __TEST_REQUIRE(page_idle_fd >= 0, "CONFIG_IDLE_PAGE_TRACKING is not enabled"); + + + if (skip_sanity_check == false) { + if (this_cpu_has(X86_FEATURE_HYPERVISOR)) { + printf("Skipping idle page count sanity check, because the test is run nested\n"); + skip_sanity_check = true; + } else if (is_numa_balancing_enabled()) { + printf("Skipping idle page count sanity check, because NUMA balance is enabled\n"); + skip_sanity_check = true; + } + } + close(page_idle_fd); for_each_guest_mode(run_test, &params); diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index 3e473058849f..1bc9b0a92427 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -153,6 +153,7 @@ bool is_backing_src_hugetlb(uint32_t i); void backing_src_help(const char *flag); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); long get_run_delay(void); +bool is_numa_balancing_enabled(void); /* * Whether or not the given source type is shared memory (as opposed to diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 8ed0b74ae837..1271863613fa 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -163,6 +163,28 @@ size_t get_trans_hugepagesz(void) return size; } + +bool is_numa_balancing_enabled(void) +{ + int ret; + int val; + struct stat statbuf; + FILE *f; + + ret = stat("/proc/sys/kernel/numa_balancing", &statbuf); + TEST_ASSERT(ret == 0 || (ret == -1 && errno == ENOENT), + "Error in stating /proc/sys/kernel/numa_balancing"); + + if (ret != 0) + return false; + + f = fopen("/proc/sys/kernel/numa_balancing", "r"); + ret = fscanf(f, "%d", &val); + + TEST_ASSERT(val == 0 || val == 1, "Unexpected value in /proc/sys/kernel/numa_balancing"); + return val == 1; +} + size_t get_def_hugetlb_pagesz(void) { char buf[64]; -- 2.26.3

4 months, 2 weeks

2
1
0 0

[PATCH net v2] selftests: drv-net: Check if combined-count exists

by Joe Damato

Some drivers, like tg3, do not set combined-count: $ ethtool -l enp4s0f1 Channel parameters for enp4s0f1: Pre-set maximums: RX: 4 TX: 4 Other: n/a Combined: n/a Current hardware settings: RX: 4 TX: 1 Other: n/a Combined: n/a In the case where combined-count is not set, the ethtool netlink code in the kernel elides the value and the code in the test: netnl.channels_get(...) With a tg3 device, the returned dictionary looks like: {'header': {'dev-index': 3, 'dev-name': 'enp4s0f1'}, 'rx-max': 4, 'rx-count': 4, 'tx-max': 4, 'tx-count': 1} Note that the key 'combined-count' is missing. As a result of this missing key the test raises an exception: # Exception| if channels['combined-count'] == 0: # Exception| ~~~~~~~~^^^^^^^^^^^^^^^^^^ # Exception| KeyError: 'combined-count' Change the test to check if 'combined-count' is a key in the dictionary first and if not assume that this means the driver has separate RX and TX queues. With this change, the test now passes successfully on tg3 and mlx5 (which does have a 'combined-count'). Fixes: 1cf270424218 ("net: selftest: add test for netdev netlink queue-get API") Signed-off-by: Joe Damato <jdamato(a)fastly.com> --- v2: - Simplify logic and reduce indentation as suggested by David Wei. Retested on both tg3 and mlx5 and test passes as expected. v1: https://lore.kernel.org/lkml/20250225181455.224309-1-jdamato@fastly.com/ tools/testing/selftests/drivers/net/queues.py | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py index 38303da957ee..8a518905a9f9 100755 --- a/tools/testing/selftests/drivers/net/queues.py +++ b/tools/testing/selftests/drivers/net/queues.py @@ -45,10 +45,9 @@ def addremove_queues(cfg, nl) -> None: netnl = EthtoolFamily() channels = netnl.channels_get({'header': {'dev-index': cfg.ifindex}}) - if channels['combined-count'] == 0: - rx_type = 'rx' - else: - rx_type = 'combined' + rx_type = 'rx' + if channels.get('combined-count', 0) > 0: + rx_type = 'combined' expected = curr_queues - 1 cmd(f"ethtool -L {cfg.dev['ifname']} {rx_type} {expected}", timeout=10) base-commit: 8d52da23b6c68a0f6bad83959ebb61a2cf623c4e -- 2.43.0

4 months, 2 weeks

3
2
0 0

[PATCH v11 3/3] selftests/rseq: Add test for mm_cid compaction

by Gabriele Monaco

A task in the kernel (task_mm_cid_work) runs somewhat periodically to compact the mm_cid for each process. Add a test to validate that it runs correctly and timely. The test spawns 1 thread pinned to each CPU, then each thread, including the main one, runs in short bursts for some time. During this period, the mm_cids should be spanning all numbers between 0 and nproc. At the end of this phase, a thread with high enough mm_cid (>= nproc/2) is selected to be the new leader, all other threads terminate. After some time, the only running thread should see 0 as mm_cid, if that doesn't happen, the compaction mechanism didn't work and the test fails. The test never fails if only 1 core is available, in which case, we cannot test anything as the only available mm_cid is 0. Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Signed-off-by: Gabriele Monaco <gmonaco(a)redhat.com> --- tools/testing/selftests/rseq/.gitignore | 1 + tools/testing/selftests/rseq/Makefile | 2 +- .../selftests/rseq/mm_cid_compaction_test.c | 200 ++++++++++++++++++ 3 files changed, 202 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/rseq/mm_cid_compaction_test.c diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore index 16496de5f6ce4..2c89f97e4f737 100644 --- a/tools/testing/selftests/rseq/.gitignore +++ b/tools/testing/selftests/rseq/.gitignore @@ -3,6 +3,7 @@ basic_percpu_ops_test basic_percpu_ops_mm_cid_test basic_test basic_rseq_op_test +mm_cid_compaction_test param_test param_test_benchmark param_test_compare_twice diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 5a3432fceb586..ce1b38f46a355 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -16,7 +16,7 @@ OVERRIDE_TARGETS = 1 TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ param_test_benchmark param_test_compare_twice param_test_mm_cid \ - param_test_mm_cid_benchmark param_test_mm_cid_compare_twice + param_test_mm_cid_benchmark param_test_mm_cid_compare_twice mm_cid_compaction_test TEST_GEN_PROGS_EXTENDED = librseq.so diff --git a/tools/testing/selftests/rseq/mm_cid_compaction_test.c b/tools/testing/selftests/rseq/mm_cid_compaction_test.c new file mode 100644 index 0000000000000..7ddde3b657dd6 --- /dev/null +++ b/tools/testing/selftests/rseq/mm_cid_compaction_test.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include <assert.h> +#include <pthread.h> +#include <sched.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stddef.h> + +#include "../kselftest.h" +#include "rseq.h" + +#define VERBOSE 0 +#define printf_verbose(fmt, ...) \ + do { \ + if (VERBOSE) \ + printf(fmt, ##__VA_ARGS__); \ + } while (0) + +/* 0.5 s */ +#define RUNNER_PERIOD 500000 +/* Number of runs before we terminate or get the token */ +#define THREAD_RUNS 5 + +/* + * Number of times we check that the mm_cid were compacted. + * Checks are repeated every RUNNER_PERIOD. + */ +#define MM_CID_COMPACT_TIMEOUT 10 + +struct thread_args { + int cpu; + int num_cpus; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + pthread_t *tinfo; + struct thread_args *args_head; +}; + +static void __noreturn *thread_runner(void *arg) +{ + struct thread_args *args = arg; + int i, ret, curr_mm_cid; + cpu_set_t cpumask; + + CPU_ZERO(&cpumask); + CPU_SET(args->cpu, &cpumask); + ret = pthread_setaffinity_np(pthread_self(), sizeof(cpumask), &cpumask); + if (ret) { + errno = ret; + perror("Error: failed to set affinity"); + abort(); + } + pthread_barrier_wait(args->barrier); + + for (i = 0; i < THREAD_RUNS; i++) + usleep(RUNNER_PERIOD); + curr_mm_cid = rseq_current_mm_cid(); + /* + * We select one thread with high enough mm_cid to be the new leader. + * All other threads (including the main thread) will terminate. + * After some time, the mm_cid of the only remaining thread should + * converge to 0, if not, the test fails. + */ + if (curr_mm_cid >= args->num_cpus / 2 && + !pthread_mutex_trylock(args->token)) { + printf_verbose( + "cpu%d has mm_cid=%d and will be the new leader.\n", + sched_getcpu(), curr_mm_cid); + for (i = 0; i < args->num_cpus; i++) { + if (args->tinfo[i] == pthread_self()) + continue; + ret = pthread_join(args->tinfo[i], NULL); + if (ret) { + errno = ret; + perror("Error: failed to join thread"); + abort(); + } + } + pthread_barrier_destroy(args->barrier); + free(args->tinfo); + free(args->token); + free(args->barrier); + free(args->args_head); + + for (i = 0; i < MM_CID_COMPACT_TIMEOUT; i++) { + curr_mm_cid = rseq_current_mm_cid(); + printf_verbose("run %d: mm_cid=%d on cpu%d.\n", i, + curr_mm_cid, sched_getcpu()); + if (curr_mm_cid == 0) + exit(EXIT_SUCCESS); + usleep(RUNNER_PERIOD); + } + exit(EXIT_FAILURE); + } + printf_verbose("cpu%d has mm_cid=%d and is going to terminate.\n", + sched_getcpu(), curr_mm_cid); + pthread_exit(NULL); +} + +int test_mm_cid_compaction(void) +{ + cpu_set_t affinity; + int i, j, ret = 0, num_threads; + pthread_t *tinfo; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + struct thread_args *args; + + sched_getaffinity(0, sizeof(affinity), &affinity); + num_threads = CPU_COUNT(&affinity); + tinfo = calloc(num_threads, sizeof(*tinfo)); + if (!tinfo) { + perror("Error: failed to allocate tinfo"); + return -1; + } + args = calloc(num_threads, sizeof(*args)); + if (!args) { + perror("Error: failed to allocate args"); + ret = -1; + goto out_free_tinfo; + } + token = malloc(sizeof(*token)); + if (!token) { + perror("Error: failed to allocate token"); + ret = -1; + goto out_free_args; + } + barrier = malloc(sizeof(*barrier)); + if (!barrier) { + perror("Error: failed to allocate barrier"); + ret = -1; + goto out_free_token; + } + if (num_threads == 1) { + fprintf(stderr, "Cannot test on a single cpu. " + "Skipping mm_cid_compaction test.\n"); + /* only skipping the test, this is not a failure */ + goto out_free_barrier; + } + pthread_mutex_init(token, NULL); + ret = pthread_barrier_init(barrier, NULL, num_threads); + if (ret) { + errno = ret; + perror("Error: failed to initialise barrier"); + goto out_free_barrier; + } + for (i = 0, j = 0; i < CPU_SETSIZE && j < num_threads; i++) { + if (!CPU_ISSET(i, &affinity)) + continue; + args[j].num_cpus = num_threads; + args[j].tinfo = tinfo; + args[j].token = token; + args[j].barrier = barrier; + args[j].cpu = i; + args[j].args_head = args; + if (!j) { + /* The first thread is the main one */ + tinfo[0] = pthread_self(); + ++j; + continue; + } + ret = pthread_create(&tinfo[j], NULL, thread_runner, &args[j]); + if (ret) { + errno = ret; + perror("Error: failed to create thread"); + abort(); + } + ++j; + } + printf_verbose("Started %d threads.\n", num_threads); + + /* Also main thread will terminate if it is not selected as leader */ + thread_runner(&args[0]); + + /* only reached in case of errors */ +out_free_barrier: + free(barrier); +out_free_token: + free(token); +out_free_args: + free(args); +out_free_tinfo: + free(tinfo); + + return ret; +} + +int main(int argc, char **argv) +{ + if (!rseq_mm_cid_available()) { + fprintf(stderr, "Error: rseq_mm_cid unavailable\n"); + return -1; + } + if (test_mm_cid_compaction()) + return -1; + return 0; +} -- 2.48.1

4 months, 2 weeks

1
0
0 0

[PATCH net-next v7 0/8] Some pktgen fixes/improvments (part II)

by Peter Seiderer

While taking a look at '[PATCH net] pktgen: Avoid out-of-range in get_imix_entries' ([1]) and '[PATCH net v2] pktgen: Avoid out-of-bounds access in get_imix_entries' ([2], [3]) and doing some tests and code review I detected that the /proc/net/pktgen/... parsing logic does not honour the user given buffer bounds (resulting in out-of-bounds access). This can be observed e.g. by the following simple test (sometimes the old/'longer' previous value is re-read from the buffer): $ echo add_device lo@0 > /proc/net/pktgen/kpktgend_0 $ echo "min_pkt_size 12345" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 12345 max_pkt_size: 0 Result: OK: min_pkt_size=12345 $ echo -n "min_pkt_size 123" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 12345 max_pkt_size: 0 Result: OK: min_pkt_size=12345 $ echo "min_pkt_size 123" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 123 max_pkt_size: 0 Result: OK: min_pkt_size=123 So fix the out-of-bounds access (and some minor findings) and add a simple proc_net_pktgen selftest... Patch set splited into part I (now already applied to net-next) - net: pktgen: replace ENOTSUPP with EOPNOTSUPP - net: pktgen: enable 'param=value' parsing - net: pktgen: fix hex32_arg parsing for short reads - net: pktgen: fix 'rate 0' error handling (return -EINVAL) - net: pktgen: fix 'ratep 0' error handling (return -EINVAL) - net: pktgen: fix ctrl interface command parsing - net: pktgen: fix access outside of user given buffer in pktgen_thread_write() And part II (this one): - net: pktgen: use defines for the various dec/hex number parsing digits lengths - net: pktgen: fix mix of int/long - net: pktgen: remove extra tmp variable (re-use len instead) - net: pktgen: remove some superfluous variable initializing - net: pktgen: fix mpls maximum labels list parsing - net: pktgen: fix access outside of user given buffer in pktgen_if_write() - net: pktgen: fix mpls reset parsing - net: pktgen: remove all superfluous index assignements - selftest: net: add proc_net_pktgen Regards, Peter Changes v6 -> v7: - rebased on actual net-next/main - selftest: net: add proc_net_pktgen - fixed conflict in tools/testing/selftests/net/config Changes v5 -> v6: - add rev-by Simon Horman - drop patch 'net: pktgen: use defines for the various dec/hex number parsing digits lengths' - adjust to dropped patch ''net: pktgen: use defines for the various dec/hex number parsing digits lengths' - net: pktgen: fix mix of int/long - fix line break (suggested by Simon Horman) Changes v4 -> v5: - split up patchset into part i/ii (suggested by Simon Horman) - add rev-by Simon Horman - net: pktgen: align some variable declarations to the most common pattern -> net: pktgen: fix mix of int/long - instead of align to most common pattern (int) adjust all usages to size_t for i and max and ssize_t for len and adjust function signatures of hex32_arg(), count_trail_chars(), num_arg() and strn_len() accordingly - respect reverse xmas tree order for local variable declarations (where possible without too much code churn) - update subject line and patch description - dropped net: pktgen: hex32_arg/num_arg error out in case no characters are available - keep empty hex/num arg is implicit assumed as zero value - dropped net: pktgen: num_arg error out in case no valid character is parsed - keep empty hex/num arg is implicit assumed as zero value - Change patch description ('Fixes:' -> 'Addresses the following:', suggested by Simon Horman) - net: pktgen: remove all superfluous index assignements - new patch (suggested by Simon Horman) - selftest: net: add proc_net_pktgen - addapt to dropped patch 'net: pktgen: hex32_arg/num_arg error out in case no characters are available', empty hex/num arg is now implicit assumed as zero value (instead of failure) Changes v3 -> v4: - add rev-by Simon Horman - new patch 'net: pktgen: use defines for the various dec/hex number parsing digits lengths' (suggested by Simon Horman) - replace C99 comment (suggested by Paolo Abeni) - drop available characters check in strn_len() (suggested by Paolo Abeni) - factored out patch 'net: pktgen: align some variable declarations to the most common pattern' (suggested by Paolo Abeni) - factored out patch 'net: pktgen: remove extra tmp variable (re-use len instead)' (suggested by Paolo Abeni) - factored out patch 'net: pktgen: remove some superfluous variable initializing' (suggested by Paolo Abeni) - factored out patch 'net: pktgen: fix mpls maximum labels list parsing' (suggested by Paolo Abeni) - factored out 'net: pktgen: hex32_arg/num_arg error out in case no characters are available' (suggested by Paolo Abeni) - factored out 'net: pktgen: num_arg error out in case no valid character is parsed' (suggested by Paolo Abeni) Changes v2 -> v3: - new patch: 'net: pktgen: fix ctrl interface command parsing' - new patch: 'net: pktgen: fix mpls reset parsing' - tools/testing/selftests/net/proc_net_pktgen.c: - fix typo in change description ('v1 -> v1' and tyop) - rename some vars to better match usage add_loopback_0 -> thr_cmd_add_loopback_0 rm_loopback_0 -> thr_cmd_rm_loopback_0 wrong_ctrl_cmd -> wrong_thr_cmd legacy_ctrl_cmd -> legacy_thr_cmd ctrl_fd -> thr_fd - add ctrl interface tests Changes v1 -> v2: - new patch: 'net: pktgen: fix hex32_arg parsing for short reads' - new patch: 'net: pktgen: fix 'rate 0' error handling (return -EINVAL)' - new patch: 'net: pktgen: fix 'ratep 0' error handling (return -EINVAL)' - net/core/pktgen.c: additional fix get_imix_entries() and get_labels() - tools/testing/selftests/net/proc_net_pktgen.c: - fix tyop not vs. nod (suggested by Jakub Kicinski) - fix misaligned line (suggested by Jakub Kicinski) - enable fomerly commented out CONFIG_XFRM dependent test (command spi), as CONFIG_XFRM is enabled via tools/testing/selftests/net/config CONFIG_XFRM_INTERFACE/CONFIG_XFRM_USER (suggestex by Jakub Kicinski) - add CONFIG_NET_PKTGEN=m to tools/testing/selftests/net/config (suggested by Jakub Kicinski) - add modprobe pktgen to FIXTURE_SETUP() (suggested by Jakub Kicinski) - fix some checkpatch warnings (Missing a blank line after declarations) - shrink line length by re-naming some variables (command -> cmd, device -> dev) - add 'rate 0' testcase - add 'ratep 0' testcase [1] https://lore.kernel.org/netdev/20241006221221.3744995-1-artem.chernyshev@re… [2] https://lore.kernel.org/netdev/20250109083039.14004-1-pchelkin@ispras.ru/ [3] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… Peter Seiderer (8): net: pktgen: fix mix of int/long net: pktgen: remove extra tmp variable (re-use len instead) net: pktgen: remove some superfluous variable initializing net: pktgen: fix mpls maximum labels list parsing net: pktgen: fix access outside of user given buffer in pktgen_if_write() net: pktgen: fix mpls reset parsing net: pktgen: remove all superfluous index assignements selftest: net: add proc_net_pktgen net/core/pktgen.c | 288 ++++---- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/config | 1 + tools/testing/selftests/net/proc_net_pktgen.c | 646 ++++++++++++++++++ 4 files changed, 805 insertions(+), 131 deletions(-) create mode 100644 tools/testing/selftests/net/proc_net_pktgen.c -- 2.48.1

4 months, 2 weeks

3
15
0 0

[PATCH][next] selftests/x86/xstate: Fix spelling mistake "hader" -> "header"

by Colin Ian King

There is a spelling mistake in a sig_print message. Fix it. Signed-off-by: Colin Ian King <colin.i.king(a)gmail.com> --- tools/testing/selftests/x86/xstate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/x86/xstate.c b/tools/testing/selftests/x86/xstate.c index 875777911d82..23c1d6c964ea 100644 --- a/tools/testing/selftests/x86/xstate.c +++ b/tools/testing/selftests/x86/xstate.c @@ -391,7 +391,7 @@ static void validate_sigfpstate(int sig, siginfo_t *si, void *ctx_void) if (get_xstatebv(xbuf) & xstate.mask) sig_print("[OK]\t'xfeatures' in XSAVE header is valid\n"); else - sig_print("[FAIL]\t'xfeatures' in XSAVE hader is not valid\n"); + sig_print("[FAIL]\t'xfeatures' in XSAVE header is not valid\n"); if (validate_xstate_same(stashed_xbuf, xbuf)) sig_print("[OK]\txstate delivery was successful\n"); -- 2.47.2

4 months, 2 weeks

1
0
0 0

[PATCH sysctl-next v2] selftests/sysctl: fix wording of help messages

by Bharadwaj Raju

Fix grammar such as "number amount of times is recommended" etc -> "the recommended number of times". Signed-off-by: Bharadwaj Raju <bharadwaj.raju777(a)gmail.com> --- tools/testing/selftests/sysctl/sysctl.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh index f6e129a82ffd..db1616857d89 100755 --- a/tools/testing/selftests/sysctl/sysctl.sh +++ b/tools/testing/selftests/sysctl/sysctl.sh @@ -857,7 +857,7 @@ list_tests() echo echo "TEST_ID x NUM_TEST" echo "TEST_ID: Test ID" - echo "NUM_TESTS: Number of recommended times to run the test" + echo "NUM_TESTS: Recommended number of times to run the test" echo echo "0001 x $(get_test_count 0001) - tests proc_dointvec_minmax()" echo "0002 x $(get_test_count 0002) - tests proc_dostring()" @@ -884,7 +884,7 @@ usage() echo "Valid tests: 0001-$MAX_TEST" echo "" echo " all Runs all tests (default)" - echo " -t Run test ID the number amount of times is recommended" + echo " -t Run test ID the recommended number of times" echo " -w Watch test ID run until it runs into an error" echo " -c Run test ID once" echo " -s Run test ID x test-count number of times" @@ -898,7 +898,7 @@ usage() echo Example uses: echo echo "$TEST_NAME.sh -- executes all tests" - echo "$TEST_NAME.sh -t 0002 -- Executes test ID 0002 number of times is recommended" + echo "$TEST_NAME.sh -t 0002 -- Executes test ID 0002 the recommended number of times" echo "$TEST_NAME.sh -w 0002 -- Watch test ID 0002 run until an error occurs" echo "$TEST_NAME.sh -s 0002 -- Run test ID 0002 once" echo "$TEST_NAME.sh -c 0002 3 -- Run test ID 0002 three times" -- 2.48.1

4 months, 2 weeks

2
1
0 0

[PATCH net-next 0/2] expand cmsg_ipv6.sh with ipv4 support

by Willem de Bruijn

From: Willem de Bruijn <willemb(a)google.com> Expand IPV6_TCLASS to also cover IP_TOS. Expand IPV6_HOPLIMIT to also cover IP_TTL. A series of two patches for basic readability (patch 1 is a noop), and so that git does not interpret code changes + file rename as a whole file del + add. Willem de Bruijn (2): selftests/net: prepare cmsg_ipv6.sh for ipv4 selftests/net: expand cmsg_ipv6.sh with ipv4 tools/testing/selftests/net/Makefile | 2 +- tools/testing/selftests/net/cmsg_ip.sh | 184 ++++++++++++++++++++++ tools/testing/selftests/net/cmsg_ipv6.sh | 154 ------------------ tools/testing/selftests/net/cmsg_sender.c | 90 +++++++---- 4 files changed, 240 insertions(+), 190 deletions(-) create mode 100755 tools/testing/selftests/net/cmsg_ip.sh delete mode 100755 tools/testing/selftests/net/cmsg_ipv6.sh -- 2.48.1.658.g4767266eb4-goog

4 months, 2 weeks

2
3
0 0

[PATCH V2 0/3] selftests: add ublk selftests

by Ming Lei

Hello Guys, The 1st patch adds one ublk utility and one entry test. The 2nd patch adds test over file backed ublk. The 3rd patch adds test for ublk zero copy. How to run: - make install - make headers_install INSTALL_HDR_PATH=/usr # in case UAPI is changed - reboot - make -C tools/testing/selftests TARGETS=ublk run_test Thanks, V2: - fix one sqe allocation bug, so ublk zero copy with io_link can pass - dump log in case of error - add one more test for mkfs/mount on zero copy Ming Lei (3): selftests: ublk: add kernel selftests for ublk selftests: ublk: add file backed ublk selftests: ublk: add ublk zero copy test MAINTAINERS | 1 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/ublk/.gitignore | 3 + tools/testing/selftests/ublk/Makefile | 15 + tools/testing/selftests/ublk/config | 1 + tools/testing/selftests/ublk/kublk.c | 1679 ++++++++++++++++++ tools/testing/selftests/ublk/test_common.sh | 112 ++ tools/testing/selftests/ublk/test_loop_01.sh | 30 + tools/testing/selftests/ublk/test_loop_02.sh | 21 + tools/testing/selftests/ublk/test_loop_03.sh | 32 + tools/testing/selftests/ublk/test_loop_04.sh | 21 + tools/testing/selftests/ublk/test_null_01.sh | 18 + 12 files changed, 1934 insertions(+) create mode 100644 tools/testing/selftests/ublk/.gitignore create mode 100644 tools/testing/selftests/ublk/Makefile create mode 100644 tools/testing/selftests/ublk/config create mode 100644 tools/testing/selftests/ublk/kublk.c create mode 100755 tools/testing/selftests/ublk/test_common.sh create mode 100755 tools/testing/selftests/ublk/test_loop_01.sh create mode 100755 tools/testing/selftests/ublk/test_loop_02.sh create mode 100755 tools/testing/selftests/ublk/test_loop_03.sh create mode 100755 tools/testing/selftests/ublk/test_loop_04.sh create mode 100755 tools/testing/selftests/ublk/test_null_01.sh -- 2.47.0

4 months, 2 weeks

2
5
0 0

[PATCH v2] selftests/vDSO: fix GNU hash table entry size for s390x

by Thomas Weißschuh

Commit 14be4e6f3522 ("selftests: vDSO: fix ELF hash table entry size for s390x") changed the type of the ELF hash table entries to 64bit on s390x. However the *GNU* hash tables entries are always 32bit. The "bucket" pointer is shared between both hash algorithms. On s390x the GNU algorithm assigns and dereferences this pointer to a 64bit value as a pointer to a 32bit value, leading to compiler warnings and runtime crashes. Introduce a new dedicated "gnu_bucket" pointer which is used by the GNU hash. Fixes: e0746bde6f82 ("selftests/vDSO: support DT_GNU_HASH") Reviewed-by: Jens Remus <jremus(a)linux.ibm.com> Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- Changes in v2: - Fix wording around the width of pointers vs the pointed-to values - Link to v1: https://lore.kernel.org/r/20250213-selftests-vdso-s390-gnu-hash-v1-1-ace3bc… --- tools/testing/selftests/vDSO/parse_vdso.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c index 2fe5e983cb22f1ed066d0310a54f6aef2ed77ed8..f89d052c730eb43eea28d69ca27b56e897503e16 100644 --- a/tools/testing/selftests/vDSO/parse_vdso.c +++ b/tools/testing/selftests/vDSO/parse_vdso.c @@ -53,7 +53,7 @@ static struct vdso_info /* Symbol table */ ELF(Sym) *symtab; const char *symstrings; - ELF(Word) *gnu_hash; + ELF(Word) *gnu_hash, *gnu_bucket; ELF_HASH_ENTRY *bucket, *chain; ELF_HASH_ENTRY nbucket, nchain; @@ -185,8 +185,8 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) /* The bucket array is located after the header (4 uint32) and the bloom * filter (size_t array of gnu_hash[2] elements). */ - vdso_info.bucket = vdso_info.gnu_hash + 4 + - sizeof(size_t) / 4 * vdso_info.gnu_hash[2]; + vdso_info.gnu_bucket = vdso_info.gnu_hash + 4 + + sizeof(size_t) / 4 * vdso_info.gnu_hash[2]; } else { vdso_info.nbucket = hash[0]; vdso_info.nchain = hash[1]; @@ -268,11 +268,11 @@ void *vdso_sym(const char *version, const char *name) if (vdso_info.gnu_hash) { uint32_t h1 = gnu_hash(name), h2, *hashval; - i = vdso_info.bucket[h1 % vdso_info.nbucket]; + i = vdso_info.gnu_bucket[h1 % vdso_info.nbucket]; if (i == 0) return 0; h1 |= 1; - hashval = vdso_info.bucket + vdso_info.nbucket + + hashval = vdso_info.gnu_bucket + vdso_info.nbucket + (i - vdso_info.gnu_hash[1]); for (;; i++) { ELF(Sym) *sym = &vdso_info.symtab[i]; --- base-commit: 2014c95afecee3e76ca4a56956a936e23283f05b change-id: 20250213-selftests-vdso-s390-gnu-hash-7206671abc85 Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

4 months, 2 weeks

3
3
0 0

[PATCH v2 0/2] tools/nolibc: add support for [v]sscanf()

by Thomas Weißschuh

The implementation is limited and only supports numeric arguments. Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- Changes in v2: - Return __LINE__ from different testcases to directly point to the failed testcase - Add some comments - Expand commit message - Link to v1: https://lore.kernel.org/r/20240731-nolibc-scanf-v1-0-f71bcc4abb9e@weissschu… --- Thomas Weißschuh (2): tools/nolibc: add support for [v]sscanf() Revert "selftests: kselftest: Fix build failure with NOLIBC" tools/include/nolibc/stdio.h | 98 ++++++++++++++++++++++++++++ tools/testing/selftests/kselftest.h | 5 -- tools/testing/selftests/nolibc/nolibc-test.c | 68 +++++++++++++++++++ 3 files changed, 166 insertions(+), 5 deletions(-) --- base-commit: 665fa8dea90d9fbc0e7137c7e1315d6f7e15757e change-id: 20240414-nolibc-scanf-f1db6930d0c6 Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

4 months, 2 weeks

3
4
0 0

[PATCH v8 0/8] Buddy allocator like (or non-uniform) folio split

by Zi Yan

Hi all, This patchset adds a new buddy allocator like (or non-uniform) large folio split from a order-n folio to order-m with m < n. It reduces 1. the total number of after-split folios from 2^(n-m) to n-m+1; 2. the amount of memory needed for multi-index xarray split from 2^(n/6-m/6) to n/6-m/6, assuming XA_CHUNK_SHIFT=6; 3. keep more large folios after a split from all order-m folios to order-(n-1) to order-m folios. For example, to split an order-9 to order-0, folio split generates 10 (or 11 for anonymous memory) folios instead of 512, allocates 1 xa_node instead of 8, and leaves 1 order-8, 1 order-7, ..., 1 order-1 and 2 order-0 folios (or 4 order-0 for anonymous memory) instead of 512 order-0 folios. It is on top of mm-everything-2025-02-15-05-49 with V7 reverted. It is ready to be merged. Instead of duplicating existing split_huge_page*() code, __folio_split() is introduced as the shared backend code for both split_huge_page_to_list_to_order() and folio_split(). __folio_split() can support both uniform split and buddy allocator like (or non-uniform) split. All existing split_huge_page*() users can be gradually converted to use folio_split() if possible. In this patchset, I converted truncate_inode_partial_folio() to use folio_split(). xfstests quick group passed for both tmpfs and xfs. Changelog === From V7[9]: 1. Fixed a wrong function name in lib/test_xarray.c. 2. Made __split_folio_to_order() never fail, since the old order check is already done in __folio_split(). (per David Hildenbrand) 3. Fixed an issue reported by syzbot[10] by not dropping the original folio during truncate. 4. Fixed a WARNING when READ_ONLY_THP_FOR_FS is enabled. (Thank David Hildenbrand for reporting the issue) 5. Used two separate struct page* parameters, split_at and lock_at, to specify at which subpage the non-uniform split happens and which subpage to keep locked after the split, respectively. It improves code readability. From V6[8]: 1. Added an xarray function xas_try_split() to support iterative folio split, removing the need of using xas_split_alloc() and xas_split(). The function guarantees that at most one xa_node is allocated for each call. 2. Added concrete numbers of after-split folios and xa_node savings to cover letter, commit log. (per Andrew) From V5[7]: 1. Split shmem to any lower order patches are in mm tree, so dropped from this series. 2. Rename split_folio_at() to try_folio_split() to clarify that non-uniform split will not be used if it is not supported. From V4[6]: 1. Enabled shmem support in both uniform and buddy allocator like split and added selftests for it. 2. Added functions to check if uniform split and buddy allocator like split are supported for the given folio and order. 3. Made truncate fall back to uniform split if buddy allocator split is not supported (CONFIG_READ_ONLY_THP_FOR_FS and FS without large folio). 4. Added the missing folio_clear_has_hwpoisoned() to __split_unmapped_folio(). From V3[5]: 1. Used xas_split_alloc(GFP_NOWAIT) instead of xas_nomem(), since extra operations inside xas_split_alloc() are needed for correctness. 2. Enabled folio_split() for shmem and no issue was found with xfstests quick test group. 3. Split both ends of a truncate range in truncate_inode_partial_folio() to avoid wasting memory in shmem truncate (per David Hildenbrand). 4. Removed page_in_folio_offset() since page_folio() does the same thing. 5. Finished truncate related tests from xfstests quick test group on XFS and tmpfs without issues. 6. Disabled buddy allocator like split on CONFIG_READ_ONLY_THP_FOR_FS and FS without large folio. This check was missed in the prior versions. From V2[3]: 1. Incorporated all the feedback from Kirill[4]. 2. Used GFP_NOWAIT for xas_nomem(). 3. Tested the code path when xas_nomem() fails. 4. Added selftests for folio_split(). 5. Fixed no THP config build error. From V1[2]: 1. Split the original patch 1 into multiple ones for easy review (per Kirill). 2. Added xas_destroy() to avoid memory leak. 3. Fixed nr_dropped not used error (per kernel test robot). 4. Added proper error handling when xas_nomem() fails to allocate memory for xas_split() during buddy allocator like split. From RFC[1]: 1. Merged backend code of split_huge_page_to_list_to_order() and folio_split(). The same code is used for both uniform split and buddy allocator like split. 2. Use xas_nomem() instead of xas_split_alloc() for folio_split(). 3. folio_split() now leaves the first after-split folio unlocked, instead of the one containing the given page, since the caller of truncate_inode_partial_folio() locks and unlocks the first folio. 4. Extended split_huge_page debugfs to use folio_split(). 5. Added truncate_inode_partial_folio() as first user of folio_split(). Design === folio_split() splits a large folio in the same way as buddy allocator splits a large free page for allocation. The purpose is to minimize the number of folios after the split. For example, if user wants to free the 3rd subpage in a order-9 folio, folio_split() will split the order-9 folio as: O-0, O-0, O-0, O-0, O-2, O-3, O-4, O-5, O-6, O-7, O-8 if it is anon O-1, O-0, O-0, O-2, O-3, O-4, O-5, O-6, O-7, O-9 if it is pagecache Since anon folio does not support order-1 yet. The split process is similar to existing approach: 1. Unmap all page mappings (split PMD mappings if exist); 2. Split meta data like memcg, page owner, page alloc tag; 3. Copy meta data in struct folio to sub pages, but instead of spliting the whole folio into multiple smaller ones with the same order in a shot, this approach splits the folio iteratively. Taking the example above, this approach first splits the original order-9 into two order-8, then splits left part of order-8 to two order-7 and so on; 4. Post-process split folios, like write mapping->i_pages for pagecache, adjust folio refcounts, add split folios to corresponding list; 5. Remap split folios 6. Unlock split folios. __split_unmapped_folio() and __split_folio_to_order() replace __split_huge_page() and __split_huge_page_tail() respectively. __split_unmapped_folio() uses different approaches to perform uniform split and buddy allocator like split: 1. uniform split: one single call to __split_folio_to_order() is used to uniformly split the given folio. All resulting folios are put back to the list after split. The folio containing the given page is left to caller to unlock and others are unlocked. 2. buddy allocator like (or non-uniform) split: (old_order - new_order) calls to __split_folio_to_order() are used to split the given folio at order N to order N-1. After each call, the target folio is changed to the one containing the page, which is given as a folio_split() parameter. After each call, folios not containing the page are put back to the list. The folio containing the page is put back to the list when its order is new_order. All folios are unlocked except the first folio, which is left to caller to unlock. Patch Overview === 1. Patch 1 added a new xarray function xas_try_split() to perform iterative xarray split. 2. Patch 2 added __split_unmapped_folio() and __split_folio_to_order() to prepare for moving to new backend split code. 3. Patch 3 moved common code in split_huge_page_to_list_to_order() to __folio_split(). 4. Patch 4 added new folio_split() and made split_huge_page_to_list_to_order() share the new __split_unmapped_folio() with folio_split(). 5. Patch 5 removed no longer used __split_huge_page() and __split_huge_page_tail(). 6. Patch 6 added a new in_folio_offset to split_huge_page debugfs for folio_split() test. 7. Patch 7 used try_folio_split() for truncate operation. 8. Patch 8 added folio_split() tests. Any comments and/or suggestions are welcome. Thanks. [1] https://lore.kernel.org/linux-mm/20241008223748.555845-1-ziy@nvidia.com/ [2] https://lore.kernel.org/linux-mm/20241028180932.1319265-1-ziy@nvidia.com/ [3] https://lore.kernel.org/linux-mm/20241101150357.1752726-1-ziy@nvidia.com/ [4] https://lore.kernel.org/linux-mm/e6ppwz5t4p4kvir6eqzoto4y5fmdjdxdyvxvtw43nc… [5] https://lore.kernel.org/linux-mm/20241205001839.2582020-1-ziy@nvidia.com/ [6] https://lore.kernel.org/linux-mm/20250106165513.104899-1-ziy@nvidia.com/ [7] https://lore.kernel.org/linux-mm/20250116211042.741543-1-ziy@nvidia.com/ [8] https://lore.kernel.org/linux-mm/20250205031417.1771278-1-ziy@nvidia.com/ [9] https://lore.kernel.org/linux-mm/20250211155034.268962-1-ziy@nvidia.com/ [10] https://lore.kernel.org/all/67af65cb.050a0220.21dd3.004a.GAE@google.com/ Zi Yan (8): xarray: add xas_try_split() to split a multi-index entry mm/huge_memory: add two new (not yet used) functions for folio_split() mm/huge_memory: move folio split common code to __folio_split() mm/huge_memory: add buddy allocator like (non-uniform) folio_split() mm/huge_memory: remove the old, unused __split_huge_page() mm/huge_memory: add folio_split() to debugfs testing interface mm/truncate: use buddy allocator like folio split for truncate operation selftests/mm: add tests for folio_split(), buddy allocator like split Documentation/core-api/xarray.rst | 14 +- include/linux/huge_mm.h | 36 + include/linux/xarray.h | 7 + lib/test_xarray.c | 47 ++ lib/xarray.c | 138 +++- mm/huge_memory.c | 756 ++++++++++++------ mm/truncate.c | 31 +- tools/testing/radix-tree/Makefile | 1 + .../selftests/mm/split_huge_page_test.c | 34 +- 9 files changed, 783 insertions(+), 281 deletions(-) -- 2.47.2

4 months, 2 weeks

2
12
0 0

[PATCH] selftests/ftrace: Use readelf to find entry point in uprobe test

by Heiko Carstens

The uprobe events test fails on s390, but also on x86 (Fedora 41). The problem appears to be that there is an assumption that adding a uprobe to the beginning of the executable mapping of /bin/sh is sufficient to trigger a uprobe event when /bin/sh is executed. This assumption is not necessarily true. Therefore use "readelf -h" to find the entry point address of /bin/sh and use this address when adding the uprobe event. This adds a dependency to readelf which is not always installed. Therefore add a check and exit with exit_unresolved if it is not installed. Signed-off-by: Heiko Carstens <hca(a)linux.ibm.com> --- .../ftrace/test.d/dynevent/add_remove_uprobe.tc | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc index 86c76679c56e..f2048c244526 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc @@ -3,14 +3,18 @@ # description: Generic dynamic event - add/remove/test uprobe events # requires: uprobe_events +if ! which readelf > /dev/null 2>&1 ; then + echo "No readelf found. skipped." + exit_unresolved +fi + echo 0 > events/enable echo > dynamic_events REALBIN=`readlink -f /bin/sh` +ENTRYPOINT=`readelf -h ${REALBIN} | grep Entry | sed -e 's/[^0]*//'` -echo 'cat /proc/$$/maps' | /bin/sh | \ - grep "r-xp .*${REALBIN}$" | \ - awk '{printf "p:myevent %s:0x%s\n", $6,$3 }' >> uprobe_events +echo "p:myevent ${REALBIN}:${ENTRYPOINT}" >> uprobe_events grep -q myevent uprobe_events test -d events/uprobes/myevent -- 2.45.2

4 months, 2 weeks

3
2
0 0

[PATCH bpf-next v3 0/6] XDP metadata support for tun driver

by Marcus Wichelmann

Hi, thank you for your reviw. As promised, here is V3 of this patch series. I noticed that the updated selftests were flaky sometimes due to the kernel networking stack sending IPv6 multicast listener reports on the created test interfaces. This can be seen here: https://github.com/kernel-patches/bpf/actions/runs/13449071153/job/37580497… Setting the NOARP flag on the interfaces should fix this race condition. Successful pipeline: https://github.com/kernel-patches/bpf/actions/runs/13500667544 Signed-off-by: Marcus Wichelmann <marcus.wichelmann(a)hetzner-cloud.de> Acked-by: Jason Wang <jasowang(a)redhat.com> Reviewed-by: Willem de Bruijn <willemb(a)google.com> --- v3: - change the condition to handle xdp_buffs without metadata support, as suggested by Willem de Bruijn <willemb(a)google.com> - add clarifying comment why that condition is needed - set NOARP flag in selftests to ensure that the kernel does not send packets on the test interfaces that may interfere with the tests v2: https://lore.kernel.org/bpf/20250217172308.3291739-1-marcus.wichelmann@hetz… - submit against bpf-next subtree - split commits and improved commit messages - remove redundant metasize check and add clarifying comment instead - use max() instead of ternary operator - add selftest for metadata support in the tun driver v1: https://lore.kernel.org/all/20250130171614.1657224-1-marcus.wichelmann@hetz… Marcus Wichelmann (6): net: tun: enable XDP metadata support net: tun: enable transfer of XDP metadata to skb selftests/bpf: move open_tuntap to network helpers selftests/bpf: refactor xdp_context_functional test and bpf program selftests/bpf: add test for XDP metadata support in tun driver selftests/bpf: fix file descriptor assertion in open_tuntap helper drivers/net/tun.c | 28 ++- tools/testing/selftests/bpf/network_helpers.c | 28 +++ tools/testing/selftests/bpf/network_helpers.h | 3 + .../selftests/bpf/prog_tests/lwt_helpers.h | 29 ---- .../bpf/prog_tests/xdp_context_test_run.c | 163 ++++++++++++++++-- .../selftests/bpf/progs/test_xdp_meta.c | 56 +++--- 6 files changed, 230 insertions(+), 77 deletions(-) -- 2.43.0

4 months, 2 weeks

4
26
0 0

[PATCH sched_ext/for-6.15] selftests/sched_ext: Add NUMA-aware scheduler test

by Andrea Righi

Add a selftest to validate the behavior of the NUMA-aware scheduler functionalities, including idle CPU selection within nodes, per-node DSQs and CPU to node mapping. Signed-off-by: Andrea Righi <arighi(a)nvidia.com> --- tools/testing/selftests/sched_ext/Makefile | 1 + tools/testing/selftests/sched_ext/numa.bpf.c | 100 +++++++++++++++++++ tools/testing/selftests/sched_ext/numa.c | 59 +++++++++++ 3 files changed, 160 insertions(+) create mode 100644 tools/testing/selftests/sched_ext/numa.bpf.c create mode 100644 tools/testing/selftests/sched_ext/numa.c diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 0117622246007..f4531327b8e76 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -172,6 +172,7 @@ auto-test-targets := \ maximal \ maybe_null \ minimal \ + numa \ prog_run \ reload_loop \ select_cpu_dfl \ diff --git a/tools/testing/selftests/sched_ext/numa.bpf.c b/tools/testing/selftests/sched_ext/numa.bpf.c new file mode 100644 index 0000000000000..a79d86ed54a1b --- /dev/null +++ b/tools/testing/selftests/sched_ext/numa.bpf.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A scheduler that validates the behavior of the NUMA-aware + * functionalities. + * + * The scheduler creates a separate DSQ for each NUMA node, ensuring tasks + * are exclusively processed by CPUs within their respective nodes. Idle + * CPUs are selected only within the same node, so task migration can only + * occurs between CPUs belonging to the same node. + * + * Copyright (c) 2025 Andrea Righi <arighi(a)nvidia.com> + */ + +#include <scx/common.bpf.h> + +char _license[] SEC("license") = "GPL"; + +UEI_DEFINE(uei); + +const volatile unsigned int __COMPAT_SCX_PICK_IDLE_IN_NODE; + +static bool is_cpu_idle(s32 cpu, int node) +{ + const struct cpumask *idle_cpumask; + bool idle; + + idle_cpumask = __COMPAT_scx_bpf_get_idle_cpumask_node(node); + idle = bpf_cpumask_test_cpu(cpu, idle_cpumask); + scx_bpf_put_cpumask(idle_cpumask); + + return idle; +} + +s32 BPF_STRUCT_OPS(numa_select_cpu, + struct task_struct *p, s32 prev_cpu, u64 wake_flags) +{ + int node = __COMPAT_scx_bpf_cpu_node(scx_bpf_task_cpu(p)); + s32 cpu; + + /* + * We could just use __COMPAT_scx_bpf_pick_any_cpu_node() here, + * since it already tries to pick an idle CPU within the node + * first, but let's use both functions for better testing coverage. + */ + cpu = __COMPAT_scx_bpf_pick_idle_cpu_node(p->cpus_ptr, node, + __COMPAT_SCX_PICK_IDLE_IN_NODE); + if (cpu < 0) + cpu = __COMPAT_scx_bpf_pick_any_cpu_node(p->cpus_ptr, node, + __COMPAT_SCX_PICK_IDLE_IN_NODE); + + if (is_cpu_idle(cpu, node)) + scx_bpf_error("CPU %d should be marked as busy", cpu); + + if (__COMPAT_scx_bpf_cpu_node(cpu) != node) + scx_bpf_error("CPU %d should be in node %d", cpu, node); + + return cpu; +} + +void BPF_STRUCT_OPS(numa_enqueue, struct task_struct *p, u64 enq_flags) +{ + int node = __COMPAT_scx_bpf_cpu_node(scx_bpf_task_cpu(p)); + + scx_bpf_dsq_insert(p, node, SCX_SLICE_DFL, enq_flags); +} + +void BPF_STRUCT_OPS(numa_dispatch, s32 cpu, struct task_struct *prev) +{ + int node = __COMPAT_scx_bpf_cpu_node(cpu); + + scx_bpf_dsq_move_to_local(node); +} + +s32 BPF_STRUCT_OPS_SLEEPABLE(numa_init) +{ + int node, err; + + bpf_for(node, 0, __COMPAT_scx_bpf_nr_node_ids()) { + err = scx_bpf_create_dsq(node, node); + if (err) + return err; + } + + return 0; +} + +void BPF_STRUCT_OPS(numa_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops numa_ops = { + .select_cpu = (void *)numa_select_cpu, + .enqueue = (void *)numa_enqueue, + .dispatch = (void *)numa_dispatch, + .init = (void *)numa_init, + .exit = (void *)numa_exit, + .name = "numa", +}; diff --git a/tools/testing/selftests/sched_ext/numa.c b/tools/testing/selftests/sched_ext/numa.c new file mode 100644 index 0000000000000..b060c3b65c82b --- /dev/null +++ b/tools/testing/selftests/sched_ext/numa.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2025 Andrea Righi <arighi(a)nvidia.com> + */ +#include <bpf/bpf.h> +#include <scx/common.h> +#include <sys/wait.h> +#include <unistd.h> +#include "numa.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status setup(void **ctx) +{ + struct numa *skel; + + skel = numa__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + skel->rodata->__COMPAT_SCX_PICK_IDLE_IN_NODE = SCX_PICK_IDLE_IN_NODE; + skel->struct_ops.numa_ops->flags = SCX_OPS_BUILTIN_IDLE_PER_NODE; + SCX_FAIL_IF(numa__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct numa *skel = ctx; + struct bpf_link *link; + + link = bpf_map__attach_struct_ops(skel->maps.numa_ops); + SCX_FAIL_IF(!link, "Failed to attach scheduler"); + + /* Just sleeping is fine, plenty of scheduling events happening */ + sleep(1); + + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE)); + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct numa *skel = ctx; + + numa__destroy(skel); +} + +struct scx_test numa = { + .name = "numa", + .description = "Verify NUMA-aware functionalities", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&numa) -- 2.48.1

4 months, 2 weeks

2
1
0 0

[PATCH v3 0/2] selftests: sched: Add default target support for sched

by Sinadin Shan

This patch series introduces changes to add default build support for the sched tests in selftests. The only test under sched is cs_prctl_test which validates cookies when core scheduling is in effect. This test fails on systems where core scheduling is disabled. The patch series also modifies this behaviour to gracefully skip the test on such systems. A system with core scheduling disabled would skip the test like: ~# ./run_kselftest.sh TAP version 13 1..1 timeout set to 45 selftests: sched: cs_prctl_test prctl failed: Invalid argument Core sched not supported, hence skipping tests ok 1 selftests: sched: cs_prctl_test # SKIP Signed-off-by: Sinadin Shan <sinadin.shan(a)oracle.com> --- v3: * Use prctl to check core sched support instead of config * v2 link: https://lore.kernel.org/all/20250221115750.631990-1-sinadin.shan@oracle.com/ v2: * Add patch to skip cs_prctl_test on core scheduling disabled systems * v1 link: https://lore.kernel.org/all/20250219064658.449069-1-sinadin.shan@oracle.com --- Sinadin Shan (2): selftests: sched: add sched as a default selftest target selftests: sched: skip cs_prctl_test for systems with core scheduling disabled tools/testing/selftests/Makefile | 1 + tools/testing/selftests/sched/cs_prctl_test.c | 34 ++++++++++++++++++- 2 files changed, 34 insertions(+), 1 deletion(-) -- 2.43.5

4 months, 2 weeks

3
4
0 0

[PATCH net-next v5 0/9] Device memory TCP TX

by Mina Almasry

v5: https://lore.kernel.org/netdev/20250220020914.895431-1-almasrymina@google.c… === v5 has no major changes; it clears up the relatively minor issues pointed out to in v4, and rebases the series on top of net-next to resolve the conflict with a patch that raced to the tree. It also collects the review tags from v4. Changes: - Rebase to net-next - Fix issues in selftest (Stan). - Address comments in the devmem and netmem driver docs (Stan and Bagas) - Fix zerocopy_fill_skb_from_devmem return error code (Stan). v4: https://lore.kernel.org/netdev/20250203223916.1064540-1-almasrymina@google.… === v4 mainly addresses the critical driver support issue surfaced in v3 by Paolo and Stan. Drivers aiming to support netmem_tx should make sure not to pass the netmem dma-addrs to the dma-mapping APIs, as these dma-addrs may come from dma-bufs. Additionally other feedback from v3 is addressed. Major changes: - Add helpers to handle netmem dma-addrs. Add GVE support for netmem_tx. - Fix binding->tx_vec not being freed on error paths during the tx binding. - Add a minimal devmem_tx test to devmem.py. - Clean up everything obsolete from the cover letter (Paolo). v3: https://patchwork.kernel.org/project/netdevbpf/list/?series=929401&state=* === Address minor comments from RFCv2 and fix a few build warnings and ynl-regen issues. No major changes. RFC v2: https://patchwork.kernel.org/project/netdevbpf/list/?series=920056&state=* ======= RFC v2 addresses much of the feedback from RFC v1. I plan on sending something close to this as net-next reopens, sending it slightly early to get feedback if any. Major changes: -------------- - much improved UAPI as suggested by Stan. We now interpret the iov_base of the passed in iov from userspace as the offset into the dmabuf to send from. This removes the need to set iov.iov_base = NULL which may be confusing to users, and enables us to send multiple iovs in the same sendmsg() call. ncdevmem and the docs show a sample use of that. - Removed the duplicate dmabuf iov_iter in binding->iov_iter. I think this is good improvment as it was confusing to keep track of 2 iterators for the same sendmsg, and mistracking both iterators caused a couple of bugs reported in the last iteration that are now resolved with this streamlining. - Improved test coverage in ncdevmem. Now multiple sendmsg() are tested, and sending multiple iovs in the same sendmsg() is tested. - Fixed issue where dmabuf unmapping was happening in invalid context (Stan). ==================================================================== The TX path had been dropped from the Device Memory TCP patch series post RFCv1 [1], to make that series slightly easier to review. This series rebases the implementation of the TX path on top of the net_iov/netmem framework agreed upon and merged. The motivation for the feature is thoroughly described in the docs & cover letter of the original proposal, so I don't repeat the lengthy descriptions here, but they are available in [1]. Full outline on usage of the TX path is detailed in the documentation included with this series. Test example is available via the kselftest included in the series as well. The series is relatively small, as the TX path for this feature largely piggybacks on the existing MSG_ZEROCOPY implementation. Patch Overview: --------------- 1. Documentation & tests to give high level overview of the feature being added. 1. Add netmem refcounting needed for the TX path. 2. Devmem TX netlink API. 3. Devmem TX net stack implementation. 4. Make dma-buf unbinding scheduled work to handle TX cases where it gets freed from contexts where we can't sleep. 5. Add devmem TX documentation. 6. Add scaffolding enabling driver support for netmem_tx. Add helpers, driver feature flag, and docs to enable drivers to declare netmem_tx support. 7. Guard netmem_tx against being enabled against drivers that don't support it. 8. Add devmem_tx selftests. Add TX path to ncdevmem and add a test to devmem.py. Testing: -------- Testing is very similar to devmem TCP RX path. The ncdevmem test used for the RX path is now augemented with client functionality to test TX path. * Test Setup: Kernel: net-next with this RFC and memory provider API cherry-picked locally. Hardware: Google Cloud A3 VMs. NIC: GVE with header split & RSS & flow steering support. Performance results are not included with this version, unfortunately. I'm having issues running the dma-buf exporter driver against the upstream kernel on my test setup. The issues are specific to that dma-buf exporter and do not affect this patch series. I plan to follow up this series with perf fixes if the tests point to issues once they're up and running. Special thanks to Stan who took a stab at rebasing the TX implementation on top of the netmem/net_iov framework merged. Parts of his proposal [2] that are reused as-is are forked off into their own patches to give full credit. [1] https://lore.kernel.org/netdev/20240909054318.1809580-1-almasrymina@google.… [2] https://lore.kernel.org/netdev/20240913150913.1280238-2-sdf@fomichev.me/T/#… Cc: sdf(a)fomichev.me Cc: asml.silence(a)gmail.com Cc: dw(a)davidwei.uk Cc: Jamal Hadi Salim <jhs(a)mojatatu.com> Cc: Victor Nogueira <victor(a)mojatatu.com> Cc: Pedro Tammela <pctammela(a)mojatatu.com> Cc: Samiullah Khawaja <skhawaja(a)google.com> Mina Almasry (8): net: add get_netmem/put_netmem support net: devmem: Implement TX path net: devmem: make dmabuf unbinding scheduled work net: add devmem TCP TX documentation net: enable driver support for netmem TX gve: add netmem TX support to GVE DQO-RDA mode net: check for driver support in netmem TX selftests: ncdevmem: Implement devmem TCP TX Stanislav Fomichev (1): net: devmem: TCP tx netlink api Documentation/netlink/specs/netdev.yaml | 12 + Documentation/networking/devmem.rst | 150 ++++++++- .../networking/net_cachelines/net_device.rst | 1 + Documentation/networking/netdev-features.rst | 5 + Documentation/networking/netmem.rst | 23 +- drivers/net/ethernet/google/gve/gve_main.c | 4 + drivers/net/ethernet/google/gve/gve_tx_dqo.c | 8 +- include/linux/netdevice.h | 2 + include/linux/skbuff.h | 17 +- include/linux/skbuff_ref.h | 4 +- include/net/netmem.h | 23 ++ include/net/sock.h | 1 + include/uapi/linux/netdev.h | 1 + net/core/datagram.c | 48 ++- net/core/dev.c | 3 + net/core/devmem.c | 113 ++++++- net/core/devmem.h | 69 +++- net/core/netdev-genl-gen.c | 13 + net/core/netdev-genl-gen.h | 1 + net/core/netdev-genl.c | 73 ++++- net/core/skbuff.c | 48 ++- net/core/sock.c | 6 + net/ipv4/ip_output.c | 3 +- net/ipv4/tcp.c | 46 ++- net/ipv6/ip6_output.c | 3 +- net/vmw_vsock/virtio_transport_common.c | 5 +- tools/include/uapi/linux/netdev.h | 1 + .../selftests/drivers/net/hw/devmem.py | 26 +- .../selftests/drivers/net/hw/ncdevmem.c | 300 +++++++++++++++++- 29 files changed, 938 insertions(+), 71 deletions(-) base-commit: b66e19dcf684b21b6d3a1844807bd1df97ad197a -- 2.48.1.601.g30ceb7b040-goog

4 months, 2 weeks

5
22
0 0

[PATCHv2 net 0/3] bond: fix xfrm offload issues

by Hangbin Liu

The first patch fixes the incorrect locks using in bond driver. The second patch fixes the xfrm offload feature during setup active-backup mode. The third patch add a ipsec offload testing. v2: move the mutex lock to a work queue (Cosmin Ratiu) Hangbin Liu (3): bonding: move mutex lock to a work queue for XFRM GC tasks bonding: fix xfrm offload feature setup on active-backup mode selftests: bonding: add ipsec offload test drivers/net/bonding/bond_main.c | 43 +++-- drivers/net/bonding/bond_netlink.c | 16 +- include/net/bonding.h | 7 + .../selftests/drivers/net/bonding/Makefile | 3 +- .../drivers/net/bonding/bond_ipsec_offload.sh | 155 ++++++++++++++++++ .../selftests/drivers/net/bonding/config | 4 + 6 files changed, 209 insertions(+), 19 deletions(-) create mode 100755 tools/testing/selftests/drivers/net/bonding/bond_ipsec_offload.sh -- 2.46.0

4 months, 2 weeks

3
12
0 0

[PATCH RFC 0/4] mm: KUnit tests for the page allocator

by Brendan Jackman

The page allocator does a lot of stuff that is not visible to the user in any deterministic way. But this stuff is still important and it would be nice to test that behaviour. KUnit is a tool for unit-testing kernel-internal APIs. This is an attempt to adopt it the page allocator. I have been hacking on this as a way to try and test the code I'm writing for my ASI page_alloc integration proposal [0]. It's been extremely useful to be able to "just call it and see what it does". So I wanna gather some feedback on whether this basic idea is of interest before I invest too much more time in it. You can run these tests like this: tools/testing/kunit/kunit.py run \ --arch=x86_64 --kernel_args="movablecore=2G" \ --qemu_args="-m 4G" --kunitconfig mm/.kunitconfig Unit-testing code that has mutable global variables can be a pain. Unit-testing code with mutable global variables _that can change concurrently with the tests_ is basically impossible. So, we need some way to isolate an "instance" of the allocator that doesn't refer to any such concurrently-mutated state. Luckily, the allocator only has one really important global variable: node_data. So, the approach here is to carve out a subset of that variable which is as isolated as possible from the rest of rthe system, which can be used for deterministic testing. This is achieved by crating a fake "isolated" node at boot, and plugging in memory at test init time. This is an RFC and not a PATCH because: 1. I have not taken much care to ensure the isolation is complete. There are probably sources of flakiness and nondeterminism in here. 2. I suspect the the basic idea might be over-complicated: do we really need memory hotplug here? Do we even need the instance of the allocator we're testing to actual memory behind the pages it's allocating, or could we just hallucinate a new region of vmemmap without any of that awkwardness? One significant downside of relying on memory hotplug is that the test won't run if we can't hotplug anything out. That means you have to fiddle with the platform to even run the tests - see the --kernel_args and --qemu_args I had to add to my kunit.py command above. So yeah, other suggestions welcome. 2b. I'm not very confident I'm using the hotplug API properly. 3. There's no point in merging this without actually having at least a few tests that are actually interesting! Maybe a "build it and they will come" approach can be justified to some extent, but there's a nonzero cost to the infrastructure so we should probably have some confidence that they will indeed come. [0] https://lore.kernel.org/linux-mm/20250129144320.2675822-1-jackmanb@google.c… Signed-off-by: Brendan Jackman <jackmanb(a)google.com> --- Brendan Jackman (4): kunit: Allocate assertion data with GFP_ATOMIC mm/page_alloc_test: Add empty KUnit boilerplate mm/page_alloc_test: Add logic to isolate a node for testing mm/page_alloc_test: Add smoke-test for page allocation drivers/base/memory.c | 5 +- include/linux/memory.h | 4 + include/linux/nodemask.h | 13 +++ kernel/kthread.c | 3 + lib/kunit/assert.c | 2 +- lib/kunit/resource.c | 2 +- lib/kunit/test.c | 2 +- mm/.kunitconfig | 10 ++ mm/Kconfig | 8 ++ mm/Makefile | 2 + mm/internal.h | 11 ++ mm/memory_hotplug.c | 26 +++-- mm/numa_memblks.c | 22 ++++ mm/page_alloc.c | 37 +++++- mm/page_alloc_test.c | 296 +++++++++++++++++++++++++++++++++++++++++++++++ 15 files changed, 429 insertions(+), 14 deletions(-) --- base-commit: d082ecbc71e9e0bf49883ee4afd435a77a5101b6 change-id: 20250219-page-alloc-kunit-df76ef8d8eb9 Best regards, -- Brendan Jackman <jackmanb(a)google.com>

4 months, 2 weeks

3
14
0 0

[PATCH 0/9] selftests/x86/xstate: Introduce common code for testing extended states

by Chang S. Bae

Hi all, This series proposes a rework of xstate-related tests to improve maintainability and expand test coverage. == Motivation: Addressing Missing and New XSTATE Tests == With the introduction of AMX, a new test suite [1] was created to verify dynamic state handling by the kernel as observed from userspace. However, previous tests for non-dynamic states like AVX lacked ABI validation, leaving gaps in coverage. While these states currently function without major issues (following the alternate sigstack fix [2]), xstate testing in the x86 selftest suite has been largely overlooked. Now, with Intel introducing another extended state, Advanced Performance Extensions (APX) [3], a correspondent test case is need. The APX enabling series will follow shortly and will leverage this refactored selftest framework. == Selftest Code Rework == To ensure ABI validation and core functionality across various xstates, refactoring the test code is necessary. Without this, existing code from amx.c would need to be duplicated, compromising the structural quality of xstate tests. This series introduces a shared test framework for extended state validation, applicable to both existing and new xstates. The test cases cover: * Context switching * ABI compatibility for signal handling * ABI compatibility for ptrace interactions == Patch Organization == The patchset is structured as follows: * PATCH1: Preparatory cleanup — removing redundant signal handler registration code. * PATCH2/3: Introduce low-level XSAVE helpers and xstate component enumeration. * PATCH4/5: Refactor existing test code. * PATCH6: Introduce a new signal test case. * PATCH7/8: Consolidate test invocations and clarify the list of supported features. * PATCH9: Add test coverage for AVX. == Coverage and Future Work Considerations == Currently, these tests are aligned with 64-bit mode only. Support for 32-bit cases will be considered when necessary, but only after this phase of rework is finalized. FWIW, the AMX TILECFG state is trivial, requiring almost constant values. Additionally, various PKRU tests are already established in tools/selftests/mm. This series is based on the tip/master branch. You can also find it in the following repository: git://github.com/intel/apx.git selftest-xstate_v1 Thanks, Chang [1] https://lore.kernel.org/all/20211026122523.AFB99C1F@davehans-spike.ostc.int… [2] https://lore.kernel.org/lkml/20210518200320.17239-1-chang.seok.bae@intel.co… [3] https://www.intel.com/content/www/us/en/developer/articles/technical/advanc… Chang S. Bae (9): selftests/x86: Consolidate redundant signal helper functions selftests/x86/xstate: Refactor XSAVE helpers for general use selftests/x86/xstate: Enumerate and name xstate components selftests/x86/xstate: Refactor context switching test selftests/x86/xstate: Refactor ptrace ABI test selftests/x86/xstate: Introduce signal ABI test selftests/x86/xstate: Consolidate test invocations into a single entry selftests/x86/xstate: Clarify supported xstates selftests/x86/avx: Add AVX test tools/testing/selftests/x86/Makefile | 6 +- tools/testing/selftests/x86/amx.c | 442 +--------------- tools/testing/selftests/x86/avx.c | 12 + .../selftests/x86/corrupt_xstate_header.c | 14 +- tools/testing/selftests/x86/entry_from_vm86.c | 24 +- tools/testing/selftests/x86/fsgsbase.c | 24 +- tools/testing/selftests/x86/helpers.h | 28 + tools/testing/selftests/x86/ioperm.c | 25 +- tools/testing/selftests/x86/iopl.c | 25 +- tools/testing/selftests/x86/ldt_gdt.c | 18 +- tools/testing/selftests/x86/mov_ss_trap.c | 14 +- tools/testing/selftests/x86/ptrace_syscall.c | 24 +- tools/testing/selftests/x86/sigaltstack.c | 26 +- tools/testing/selftests/x86/sigreturn.c | 24 +- .../selftests/x86/single_step_syscall.c | 22 - .../testing/selftests/x86/syscall_arg_fault.c | 12 - tools/testing/selftests/x86/syscall_nt.c | 12 - tools/testing/selftests/x86/sysret_rip.c | 24 +- tools/testing/selftests/x86/test_vsyscall.c | 13 - tools/testing/selftests/x86/unwind_vdso.c | 12 - tools/testing/selftests/x86/xstate.c | 477 ++++++++++++++++++ tools/testing/selftests/x86/xstate.h | 195 +++++++ 22 files changed, 753 insertions(+), 720 deletions(-) create mode 100644 tools/testing/selftests/x86/avx.c create mode 100644 tools/testing/selftests/x86/xstate.c create mode 100644 tools/testing/selftests/x86/xstate.h base-commit: 5bff053d066ba892464995ae4a7246f7a78fce2d -- 2.45.2

4 months, 2 weeks

2
10
0 0

[PATCH v5 0/3] Enable Zicbom in usermode

by Yunhui Cui

v1/v2: There is only the first patch: RISC-V: Enable cbo.clean/flush in usermode, which mainly removes the enabling of cbo.inval in user mode. v3: Add the functionality of Expose Zicbom and selftests for Zicbom. v4: Modify the order of macros, The test_no_cbo_inval function is added separately. v5: 1. Modify the order of RISCV_HWPROBE_KEY_ZICBOM_BLOCK_SIZE in hwprobe.rst 2. "TEST_NO_ZICBOINVAL" -> "TEST_NO_CBO_INVAL" Yunhui Cui (3): RISC-V: Enable cbo.clean/flush in usermode RISC-V: hwprobe: Expose Zicbom extension and its block size RISC-V: selftests: Add TEST_ZICBOM into CBO tests Documentation/arch/riscv/hwprobe.rst | 6 ++ arch/riscv/include/asm/hwprobe.h | 2 +- arch/riscv/include/uapi/asm/hwprobe.h | 2 + arch/riscv/kernel/cpufeature.c | 8 +++ arch/riscv/kernel/sys_hwprobe.c | 6 ++ tools/testing/selftests/riscv/hwprobe/cbo.c | 66 +++++++++++++++++---- 6 files changed, 78 insertions(+), 12 deletions(-) -- 2.39.2

4 months, 2 weeks

6
12
0 0

[PATCH 0/3] selftests: add ublk selftests

by Ming Lei

Hello Guys, The 1st patch adds one ublk utility and one entry test. The 2nd patch adds test over file backed ublk. The 3rd patch adds test for ublk zero copy. How to run: - make install - make headers_install INSTALL_HDR_PATH=/usr - reboot - make -C tools/testing/selftests TARGETS=ublk run_test Thanks, Ming Lei (3): selftests: ublk: add kernel selftests for ublk selftests: ublk: add file backed ublk selftests: ublk: add ublk zero copy test MAINTAINERS | 1 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/ublk/.gitignore | 3 + tools/testing/selftests/ublk/Makefile | 14 + tools/testing/selftests/ublk/config | 1 + tools/testing/selftests/ublk/kublk.c | 1671 ++++++++++++++++++ tools/testing/selftests/ublk/test_common.sh | 112 ++ tools/testing/selftests/ublk/test_loop_01.sh | 30 + tools/testing/selftests/ublk/test_loop_02.sh | 21 + tools/testing/selftests/ublk/test_loop_03.sh | 32 + tools/testing/selftests/ublk/test_null_01.sh | 18 + 11 files changed, 1904 insertions(+) create mode 100644 tools/testing/selftests/ublk/.gitignore create mode 100644 tools/testing/selftests/ublk/Makefile create mode 100644 tools/testing/selftests/ublk/config create mode 100644 tools/testing/selftests/ublk/kublk.c create mode 100755 tools/testing/selftests/ublk/test_common.sh create mode 100755 tools/testing/selftests/ublk/test_loop_01.sh create mode 100755 tools/testing/selftests/ublk/test_loop_02.sh create mode 100755 tools/testing/selftests/ublk/test_loop_03.sh create mode 100755 tools/testing/selftests/ublk/test_null_01.sh -- 2.47.0

4 months, 2 weeks

1
3
0 0

[PATCH v10 3/3] selftests/rseq: Add test for mm_cid compaction

by Gabriele Monaco

A task in the kernel (task_mm_cid_work) runs somewhat periodically to compact the mm_cid for each process. Add a test to validate that it runs correctly and timely. The test spawns 1 thread pinned to each CPU, then each thread, including the main one, runs in short bursts for some time. During this period, the mm_cids should be spanning all numbers between 0 and nproc. At the end of this phase, a thread with high enough mm_cid (>= nproc/2) is selected to be the new leader, all other threads terminate. After some time, the only running thread should see 0 as mm_cid, if that doesn't happen, the compaction mechanism didn't work and the test fails. The test never fails if only 1 core is available, in which case, we cannot test anything as the only available mm_cid is 0. Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Signed-off-by: Gabriele Monaco <gmonaco(a)redhat.com> --- tools/testing/selftests/rseq/.gitignore | 1 + tools/testing/selftests/rseq/Makefile | 2 +- .../selftests/rseq/mm_cid_compaction_test.c | 200 ++++++++++++++++++ 3 files changed, 202 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/rseq/mm_cid_compaction_test.c diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore index 16496de5f6ce4..2c89f97e4f737 100644 --- a/tools/testing/selftests/rseq/.gitignore +++ b/tools/testing/selftests/rseq/.gitignore @@ -3,6 +3,7 @@ basic_percpu_ops_test basic_percpu_ops_mm_cid_test basic_test basic_rseq_op_test +mm_cid_compaction_test param_test param_test_benchmark param_test_compare_twice diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 5a3432fceb586..ce1b38f46a355 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -16,7 +16,7 @@ OVERRIDE_TARGETS = 1 TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ param_test_benchmark param_test_compare_twice param_test_mm_cid \ - param_test_mm_cid_benchmark param_test_mm_cid_compare_twice + param_test_mm_cid_benchmark param_test_mm_cid_compare_twice mm_cid_compaction_test TEST_GEN_PROGS_EXTENDED = librseq.so diff --git a/tools/testing/selftests/rseq/mm_cid_compaction_test.c b/tools/testing/selftests/rseq/mm_cid_compaction_test.c new file mode 100644 index 0000000000000..7ddde3b657dd6 --- /dev/null +++ b/tools/testing/selftests/rseq/mm_cid_compaction_test.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include <assert.h> +#include <pthread.h> +#include <sched.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stddef.h> + +#include "../kselftest.h" +#include "rseq.h" + +#define VERBOSE 0 +#define printf_verbose(fmt, ...) \ + do { \ + if (VERBOSE) \ + printf(fmt, ##__VA_ARGS__); \ + } while (0) + +/* 0.5 s */ +#define RUNNER_PERIOD 500000 +/* Number of runs before we terminate or get the token */ +#define THREAD_RUNS 5 + +/* + * Number of times we check that the mm_cid were compacted. + * Checks are repeated every RUNNER_PERIOD. + */ +#define MM_CID_COMPACT_TIMEOUT 10 + +struct thread_args { + int cpu; + int num_cpus; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + pthread_t *tinfo; + struct thread_args *args_head; +}; + +static void __noreturn *thread_runner(void *arg) +{ + struct thread_args *args = arg; + int i, ret, curr_mm_cid; + cpu_set_t cpumask; + + CPU_ZERO(&cpumask); + CPU_SET(args->cpu, &cpumask); + ret = pthread_setaffinity_np(pthread_self(), sizeof(cpumask), &cpumask); + if (ret) { + errno = ret; + perror("Error: failed to set affinity"); + abort(); + } + pthread_barrier_wait(args->barrier); + + for (i = 0; i < THREAD_RUNS; i++) + usleep(RUNNER_PERIOD); + curr_mm_cid = rseq_current_mm_cid(); + /* + * We select one thread with high enough mm_cid to be the new leader. + * All other threads (including the main thread) will terminate. + * After some time, the mm_cid of the only remaining thread should + * converge to 0, if not, the test fails. + */ + if (curr_mm_cid >= args->num_cpus / 2 && + !pthread_mutex_trylock(args->token)) { + printf_verbose( + "cpu%d has mm_cid=%d and will be the new leader.\n", + sched_getcpu(), curr_mm_cid); + for (i = 0; i < args->num_cpus; i++) { + if (args->tinfo[i] == pthread_self()) + continue; + ret = pthread_join(args->tinfo[i], NULL); + if (ret) { + errno = ret; + perror("Error: failed to join thread"); + abort(); + } + } + pthread_barrier_destroy(args->barrier); + free(args->tinfo); + free(args->token); + free(args->barrier); + free(args->args_head); + + for (i = 0; i < MM_CID_COMPACT_TIMEOUT; i++) { + curr_mm_cid = rseq_current_mm_cid(); + printf_verbose("run %d: mm_cid=%d on cpu%d.\n", i, + curr_mm_cid, sched_getcpu()); + if (curr_mm_cid == 0) + exit(EXIT_SUCCESS); + usleep(RUNNER_PERIOD); + } + exit(EXIT_FAILURE); + } + printf_verbose("cpu%d has mm_cid=%d and is going to terminate.\n", + sched_getcpu(), curr_mm_cid); + pthread_exit(NULL); +} + +int test_mm_cid_compaction(void) +{ + cpu_set_t affinity; + int i, j, ret = 0, num_threads; + pthread_t *tinfo; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + struct thread_args *args; + + sched_getaffinity(0, sizeof(affinity), &affinity); + num_threads = CPU_COUNT(&affinity); + tinfo = calloc(num_threads, sizeof(*tinfo)); + if (!tinfo) { + perror("Error: failed to allocate tinfo"); + return -1; + } + args = calloc(num_threads, sizeof(*args)); + if (!args) { + perror("Error: failed to allocate args"); + ret = -1; + goto out_free_tinfo; + } + token = malloc(sizeof(*token)); + if (!token) { + perror("Error: failed to allocate token"); + ret = -1; + goto out_free_args; + } + barrier = malloc(sizeof(*barrier)); + if (!barrier) { + perror("Error: failed to allocate barrier"); + ret = -1; + goto out_free_token; + } + if (num_threads == 1) { + fprintf(stderr, "Cannot test on a single cpu. " + "Skipping mm_cid_compaction test.\n"); + /* only skipping the test, this is not a failure */ + goto out_free_barrier; + } + pthread_mutex_init(token, NULL); + ret = pthread_barrier_init(barrier, NULL, num_threads); + if (ret) { + errno = ret; + perror("Error: failed to initialise barrier"); + goto out_free_barrier; + } + for (i = 0, j = 0; i < CPU_SETSIZE && j < num_threads; i++) { + if (!CPU_ISSET(i, &affinity)) + continue; + args[j].num_cpus = num_threads; + args[j].tinfo = tinfo; + args[j].token = token; + args[j].barrier = barrier; + args[j].cpu = i; + args[j].args_head = args; + if (!j) { + /* The first thread is the main one */ + tinfo[0] = pthread_self(); + ++j; + continue; + } + ret = pthread_create(&tinfo[j], NULL, thread_runner, &args[j]); + if (ret) { + errno = ret; + perror("Error: failed to create thread"); + abort(); + } + ++j; + } + printf_verbose("Started %d threads.\n", num_threads); + + /* Also main thread will terminate if it is not selected as leader */ + thread_runner(&args[0]); + + /* only reached in case of errors */ +out_free_barrier: + free(barrier); +out_free_token: + free(token); +out_free_args: + free(args); +out_free_tinfo: + free(tinfo); + + return ret; +} + +int main(int argc, char **argv) +{ + if (!rseq_mm_cid_available()) { + fprintf(stderr, "Error: rseq_mm_cid unavailable\n"); + return -1; + } + if (test_mm_cid_compaction()) + return -1; + return 0; +} -- 2.48.1

4 months, 2 weeks

1
0
0 0

[PATCH net-next] selftests/net: ensure mptcp is enabled in netns

by Hangbin Liu

Some distributions may not enable MPTCP by default. All other MPTCP tests source mptcp_lib.sh to ensure MPTCP is enabled before testing. However, the ip_local_port_range test is the only one that does not include this step. Let's also ensure MPTCP is enabled in netns for ip_local_port_range so that it passes on all distributions. Suggested-by: Davide Caratti <dcaratti(a)redhat.com> Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> --- tools/testing/selftests/net/ip_local_port_range.sh | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/ip_local_port_range.sh b/tools/testing/selftests/net/ip_local_port_range.sh index 6c6ad346eaa0..4ff746db1256 100755 --- a/tools/testing/selftests/net/ip_local_port_range.sh +++ b/tools/testing/selftests/net/ip_local_port_range.sh @@ -2,4 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 ./in_netns.sh \ - sh -c 'sysctl -q -w net.ipv4.ip_local_port_range="40000 49999" && ./ip_local_port_range' + sh -c 'sysctl -q -w net.mptcp.enabled=1 && \ + sysctl -q -w net.ipv4.ip_local_port_range="40000 49999" && \ + ./ip_local_port_range' -- 2.46.0

4 months, 2 weeks

3
3
0 0

[PATCH net] selftests: drv-net: Check if combined-count exists

by Joe Damato

Some drivers, like tg3, do not set combined-count: $ ethtool -l enp4s0f1 Channel parameters for enp4s0f1: Pre-set maximums: RX: 4 TX: 4 Other: n/a Combined: n/a Current hardware settings: RX: 4 TX: 1 Other: n/a Combined: n/a In the case where combined-count is not set, the ethtool netlink code in the kernel elides the value and the code in the test: netnl.channels_get(...) With a tg3 device, the returned dictionary looks like: {'header': {'dev-index': 3, 'dev-name': 'enp4s0f1'}, 'rx-max': 4, 'rx-count': 4, 'tx-max': 4, 'tx-count': 1} Note that the key 'combined-count' is missing. As a result of this missing key the test raises an exception: # Exception| if channels['combined-count'] == 0: # Exception| ~~~~~~~~^^^^^^^^^^^^^^^^^^ # Exception| KeyError: 'combined-count' Change the test to check if 'combined-count' is a key in the dictionary first and if not assume that this means the driver has separate RX and TX queues. With this change, the test now passes successfully on tg3 and mlx5 (which does have a 'combined-count'). Fixes: 1cf270424218 ("net: selftest: add test for netdev netlink queue-get API") Signed-off-by: Joe Damato <jdamato(a)fastly.com> --- tools/testing/selftests/drivers/net/queues.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py index 38303da957ee..baa8845d9f64 100755 --- a/tools/testing/selftests/drivers/net/queues.py +++ b/tools/testing/selftests/drivers/net/queues.py @@ -45,10 +45,13 @@ def addremove_queues(cfg, nl) -> None: netnl = EthtoolFamily() channels = netnl.channels_get({'header': {'dev-index': cfg.ifindex}}) - if channels['combined-count'] == 0: - rx_type = 'rx' + if 'combined-count' in channels: + if channels['combined-count'] == 0: + rx_type = 'rx' + else: + rx_type = 'combined' else: - rx_type = 'combined' + rx_type = 'rx' expected = curr_queues - 1 cmd(f"ethtool -L {cfg.dev['ifname']} {rx_type} {expected}", timeout=10) base-commit: bc50682128bde778a1ddc457a02d92a637c20c6f -- 2.43.0

4 months, 2 weeks

3
3
0 0

[PATCH 0/3] selftests/damon: three fixes for false results

by SeongJae Park

Fix three DAMON selftest bugs that causes two and one false positive failures and success. SeongJae Park (3): selftests/damon/damos_quota: make real expectation of quota exceeds selftests/damon/damon_nr_regions: set ops update for merge results check to 100ms selftests/damon/damon_nr_regions: sort collected regiosn before checking with min/max boundaries tools/testing/selftests/damon/damon_nr_regions.py | 2 ++ tools/testing/selftests/damon/damos_quota.py | 9 ++++++--- 2 files changed, 8 insertions(+), 3 deletions(-) base-commit: 0ab548cd0961a01f9ef65aa999ca84febcdb04ab -- 2.39.5

4 months, 2 weeks

1
3
0 0

[PATCH] selftests/net: deflake GRO tests and fix return value and output

by Kevin Krakauer

GRO tests are timing dependent and can easily flake. This is partially mitigated in gro.sh by giving each subtest 3 chances to pass. However, this still flakes on some machines. Set the device's napi_defer_hard_irqs to 50 so that GRO is less likely to immediately flush. This already happened in setup_loopback.sh, but wasn't added to setup_veth.sh. This accounts for most of the reduction in flakiness. We also increase the number of chances for success from 3 to 6. `gro.sh -t <test>` now returns a passing/failing exit code as expected. gro.c:main no longer erroneously claims a test passes when running as a server. Tested: Ran `gro.sh -t large` 100 times with and without this change. Passed 100/100 with and 64/100 without. Ran inside strace to increase flakiness. Signed-off-by: Kevin Krakauer <krakauer(a)google.com> --- tools/testing/selftests/net/gro.c | 8 +++++--- tools/testing/selftests/net/gro.sh | 5 +++-- tools/testing/selftests/net/setup_veth.sh | 1 + 3 files changed, 9 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c index b2184847e388..d5824eadea10 100644 --- a/tools/testing/selftests/net/gro.c +++ b/tools/testing/selftests/net/gro.c @@ -1318,11 +1318,13 @@ int main(int argc, char **argv) read_MAC(src_mac, smac); read_MAC(dst_mac, dmac); - if (tx_socket) + if (tx_socket) { gro_sender(); - else + } else { + /* Only the receiver exit status determines test success. */ gro_receiver(); + fprintf(stderr, "Gro::%s test passed.\n", testname); + } - fprintf(stderr, "Gro::%s test passed.\n", testname); return 0; } diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh index 02c21ff4ca81..703173f8c8a9 100755 --- a/tools/testing/selftests/net/gro.sh +++ b/tools/testing/selftests/net/gro.sh @@ -21,7 +21,7 @@ run_test() { # Each test is run 3 times to deflake, because given the receive timing, # not all packets that should coalesce will be considered in the same flow # on every try. - for tries in {1..3}; do + for tries in {1..6}; do # Actual test starts here ip netns exec $server_ns ./gro "${ARGS[@]}" "--rx" "--iface" "server" \ 1>>log.txt & @@ -100,5 +100,6 @@ trap cleanup EXIT if [[ "${test}" == "all" ]]; then run_all_tests else - run_test "${proto}" "${test}" + exit_code=$(run_test "${proto}" "${test}") + exit $exit_code fi; diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh index 1f78a87f6f37..9882ad730c24 100644 --- a/tools/testing/selftests/net/setup_veth.sh +++ b/tools/testing/selftests/net/setup_veth.sh @@ -12,6 +12,7 @@ setup_veth_ns() { [[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}" echo 1000000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" + echo 50 > "/sys/class/net/${ns_dev}/napi_defer_hard_irqs" ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535 ip -netns "${ns_name}" link set dev "${ns_dev}" up -- 2.48.1

4 months, 2 weeks

3
5
0 0

[PATCH v7 00/10] Basic SEV-SNP Selftests

by Pratik R. Sampat

This patch series extends the sev_init2 and the sev_smoke test to exercise the SEV-SNP VM launch workflow. Primarily, it introduces the architectural defines, its support in the SEV library and extends the tests to interact with the SEV-SNP ioctl() wrappers. Patch 1 - Do not advertize SNP on initialization failure Patch 2 - SNP test for KVM_SEV_INIT2 Patch 3 - Add vmgexit helper Patch 4 - Add SMT control interface helper Patch 5 - Replace assert() with TEST_ASSERT_EQ() Patch 6 - Introduce SEV+ VM type check Patch 7 - SNP iotcl() plumbing for the SEV library Patch 8 - Force set GUEST_MEMFD for SNP Patch 9 - Cleanups of smoke test - Decouple policy from type Patch 10 - SNP smoke test The series is based on git.kernel.org/pub/scm/virt/kvm/kvm.git next v6..v7: Based on comments from Sean - * Replaced FW check with sev->snp_initialized * Dropped the patch which removes SEV+ KVM advertizement if INIT fails. This should be now be resolved by the combination of the patches [1,2] from Ashish. * Change vmgexit to an inline function * Export SMT control parsing interface to kvm_util Note: hyperv_cpuid KST only compile testeworkbench.editor.empty.hintd * Replace assert() with TEST_ASSERT_EQ() within SEV library * Define KVM_SEV_PAGE_TYPE_INVALID for SEV call of encrypt_region() * Parameterize encrypt_region() to include privatize_region() * Deduplication of sev test calls between SEV,SEV-ES and SNP * Removed FW version tests for SNP * Included testing of SNP_POLICY_DBG * Dropped most tags from patches that have been changed or indirectly affected [1] https://lore.kernel.org/all/d6d08c6b-9602-4f3d-92c2-8db6d50a1b92@amd.com [2] https://lore.kernel.org/all/f78ddb64087df27e7bcb1ae0ab53f55aa0804fab.173922… v5..v6: https://lore.kernel.org/kvm/ab433246-e97c-495b-ab67-b0cb1721fb99@amd.com/ * Rename is_sev_platform_init to sev_fw_initialized (Nikunj) * Rename KVM CPU feature X86_FEATURE_SNP to X86_FEATURE_SEV_SNP (Nikunj) * Collected Tags from Nikunj, Pankaj, Srikanth. v4..v5: https://lore.kernel.org/kvm/8e7d8172-879e-4a28-8438-343b1c386ec9@amd.com/ * Introduced a check to disable advertising support for SEV, SEV-ES and SNP when platform initialization fails (Nikunj) * Remove the redundant SNP check within is_sev_vm() (Nikunj) * Cleanup of the encrypt_region flow for better readability (Nikunj) * Refactor paths to use the canonical $(ARCH) to rebase for kvm/next v3..v4: https://lore.kernel.org/kvm/20241114234104.128532-1-pratikrajesh.sampat@amd… * Remove SNP FW API version check in the test and ensure the KVM capability advertizes the presence of the feature. Retain the minimum version definitions to exercise these API versions in the smoke test * Retained only the SNP smoke test and SNP_INIT2 test * The SNP architectural defined merged with SNP_INIT2 test patch * SNP shutdown merged with SNP smoke test patch * Add SEV VM type check to abstract comparisons and reduce clutter * Define a SNP default policy which sets bits based on the presence of SMT * Decouple privatization and encryption for it to be SNP agnostic * Assert for only positive tests using vm_ioctl() * Dropped tested-by tags In summary - based on comments from Sean, I have primarily reduced the scope of this patch series to focus on breaking down the SNP smoke test patch (v3 - patch2) to first introduce SEV-SNP support and use this interface to extend the sev_init2 and the sev_smoke test. The rest of the v3 patchset that introduces ioctl, pre fault, fallocate and negative tests, will be re-worked and re-introduced subsequently in future patch series post addressing the issues discussed. v2..v3: https://lore.kernel.org/kvm/20240905124107.6954-1-pratikrajesh.sampat@amd.c… * Remove the assignments for the prefault and fallocate test type enums. * Fix error message for sev launch measure and finish. * Collect tested-by tags [Peter, Srikanth]](<This patch series extends the sev_init2 and the sev_smoke test to exercise the SEV-SNP VM launch workflow. Primarily, it introduces the architectural defines, its support in the SEV library and extends the tests to interact with the SEV-SNP ioctl() wrappers. Patch 1 - Do not advertize SNP on initialization failure Patch 2 - SNP test for KVM_SEV_INIT2 Patch 3 - Add vmgexit helper Patch 4 - Helper for SMT control interface Patch 5 - Replace assert() with TEST_ASSERT_EQ() Patch 6 - Introduce SEV+ VM type check Patch 7 - SNP iotcl() plumbing for the SEV library Patch 8 - Force set GUEST_MEMFD for SNP Patch 9 - Cleanups of smoke test - Decouple policy from type Patch 10 - SNP smoke test The series is based on git.kernel.org/pub/scm/virt/kvm/kvm.git next v6..v7 Based on comments from Sean - * Replaced FW check with sev-%3Esnp_initialized * Dropped the patch which removes SEV+ KVM advertizement if INIT fails This should be resolved by the combination of [1][2] from Ashish: * Change vmgexit to an inline function * Export SMT control parsing interface to kvm_util * Replace assert() with TEST_ASSERT_EQ() within SEV library * Define KVM_SEV_PAGE_TYPE_INVALID for SEV to use it with encrypt_region() * Parameterize encrypt_region() to include privatize_region() functionality * Deduplication of sev test calls between SEV,SEV-ES and SNP * Removed FW version tests for SNP * Included testing of SNP_POLICY_DBG * Dropped most tags from patches that have directly / indirectly changed. [1] https://lore.kernel.org/all/d6d08c6b-9602-4f3d-92c2-8db6d50a1b92@amd.com [2] https://lore.kernel.org/all/f78ddb64087df27e7bcb1ae0ab53f55aa0804fab.173922… v5..v6 https://lore.kernel.org/kvm/ab433246-e97c-495b-ab67-b0cb1721fb99@amd.com/ * Rename is_sev_platform_init to sev_fw_initialized (Nikunj) * Rename KVM CPU feature X86_FEATURE_SNP to X86_FEATURE_SEV_SNP (Nikunj) * Collected Tags from Nikunj, Pankaj, Srikanth. v4..v5: https://lore.kernel.org/kvm/8e7d8172-879e-4a28-8438-343b1c386ec9@amd.com/ * Introduced a check to disable advertising support for SEV, SEV-ES and SNP when platform initialization fails (Nikunj) * Remove the redundant SNP check within is_sev_vm() (Nikunj) * Cleanup of the encrypt_region flow for better readability (Nikunj) * Refactor paths to use the canonical $(ARCH) to rebase for kvm/next v3..v4: https://lore.kernel.org/kvm/20241114234104.128532-1-pratikrajesh.sampat@amd… * Remove SNP FW API version check in the test and ensure the KVM capability advertizes the presence of the feature. Retain the minimum version definitions to exercise these API versions in the smoke test * Retained only the SNP smoke test and SNP_INIT2 test * The SNP architectural defined merged with SNP_INIT2 test patch * SNP shutdown merged with SNP smoke test patch * Add SEV VM type check to abstract comparisons and reduce clutter * Define a SNP default policy which sets bits based on the presence of SMT * Decouple privatization and encryption for it to be SNP agnostic * Assert for only positive tests using vm_ioctl() * Dropped tested-by tags In summary - based on comments from Sean, I have primarily reduced the scope of this patch series to focus on breaking down the SNP smoke test patch (v3 - patch2) to first introduce SEV-SNP support and use this interface to extend the sev_init2 and the sev_smoke test. The rest of the v3 patchset that introduces ioctl, pre fault, fallocate and negative tests, will be re-worked and re-introduced subsequently in future patch series post addressing the issues discussed. v2..v3: https://lore.kernel.org/kvm/20240905124107.6954-1-pratikrajesh.sampat@amd.c… * Remove the assignments for the prefault and fallocate test type enums. * Fix error message for sev launch measure and finish. * Collect tested-by tags [Peter, Srikanth] Pratik R. Sampat (10): KVM: SEV: Disable SEV-SNP support on initialization failure KVM: selftests: SEV-SNP test for KVM_SEV_INIT2 KVM: selftests: Add vmgexit helper KVM: selftests: Add SMT control state helper KVM: selftests: Replace assert() with TEST_ASSERT_EQ() KVM: selftests: Introduce SEV VM type check KVM: selftests: Add library support for interacting with SNP KVM: selftests: Force GUEST_MEMFD flag for SNP VM type KVM: selftests: Abstractions for SEV to decouple policy from type KVM: selftests: Add a basic SEV-SNP smoke test arch/x86/include/uapi/asm/kvm.h | 1 + arch/x86/kvm/svm/sev.c | 4 +- drivers/crypto/ccp/sev-dev.c | 8 ++ include/linux/psp-sev.h | 3 + tools/arch/x86/include/uapi/asm/kvm.h | 1 + .../testing/selftests/kvm/include/kvm_util.h | 35 +++++++ .../selftests/kvm/include/x86/processor.h | 1 + tools/testing/selftests/kvm/include/x86/sev.h | 42 ++++++++- tools/testing/selftests/kvm/lib/kvm_util.c | 7 +- .../testing/selftests/kvm/lib/x86/processor.c | 4 +- tools/testing/selftests/kvm/lib/x86/sev.c | 93 +++++++++++++++++-- .../testing/selftests/kvm/x86/hyperv_cpuid.c | 19 ---- .../selftests/kvm/x86/sev_init2_tests.c | 13 +++ .../selftests/kvm/x86/sev_smoke_test.c | 75 +++++++++------ 14 files changed, 246 insertions(+), 60 deletions(-) -- 2.43.0

4 months, 2 weeks

3
17
0 0

[PATCH v7 00/14] iommufd: Add vIOMMU infrastructure (Part-3: vEVENTQ)

by Nicolin Chen

As the vIOMMU infrastructure series part-3, this introduces a new vEVENTQ object. The existing FAULT object provides a nice notification pathway to the user space with a queue already, so let vEVENTQ reuse that. Mimicing the HWPT structure, add a common EVENTQ structure to support its derivatives: IOMMUFD_OBJ_FAULT (existing) and IOMMUFD_OBJ_VEVENTQ (new). An IOMMUFD_CMD_VEVENTQ_ALLOC is introduced to allocate vEVENTQ object for vIOMMUs. One vIOMMU can have multiple vEVENTQs in different types but can not support multiple vEVENTQs in the same type. The forwarding part is fairly simple but might need to replace a physical device ID with a virtual device ID in a driver-level event data structure. So, this also adds some helpers for drivers to use. As usual, this series comes with the selftest coverage for this new ioctl and with a real world use case in the ARM SMMUv3 driver. This is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_veventq-v7 Paring QEMU branch for testing: https://github.com/nicolinc/qemu/commits/wip/for_iommufd_veventq-v7 Changelog v7 * Rebase on Jason's for-next tree for latest fault.c * Add Reviewed-by * Update commit logs * Add __reserved field sanity * Skip kfree() on the static header * Replace "bool on_list" with list_is_last() * Use u32 for flags in iommufd_vevent_header * Drop casting in iommufd_viommu_get_vdev_id() * Update the bounding logic to veventq->sequence * Add missing cpu_to_le64() around STRTAB_STE_1_MEV * Reuse veventq->common.lock to fence sequence and num_events * Rename overflow to lost_events and log it in upon kmalloc failure * Correct the error handling part in iommufd_veventq_deliver_fetch() * Add an arm_smmu_clear_vmaster() to simplify identity/blocked domain attach ops * Add additional four event records to forward to user space VM, and update the uAPI doc * Reuse the existing smmu->streams_mutex lock to fence master->vmaster pointer, instead of adding a new rwsem v6 https://lore.kernel.org/all/cover.1737754129.git.nicolinc@nvidia.com/ * Drop supports_veventq viommu op * Split bug/cosmetics fixes out of the series * Drop the blocking mutex around copy_to_user() * Add veventq_depth in uAPI to limit vEVENTQ size * Revise the documentation for a clear description * Fix sparse warnings in arm_vmaster_report_event() * Rework iommufd_viommu_get_vdev_id() to return -ENOENT v.s. 0 * Allow Abort/Bypass STEs to allocate vEVENTQ and set STE.MEV for DoS mitigations v5 https://lore.kernel.org/all/cover.1736237481.git.nicolinc@nvidia.com/ * Add Reviewed-by from Baolu * Reorder the OBJ list as well * Fix alphabetical order after renaming in v4 * Add supports_veventq viommu op for vEVENTQ type validation v4 https://lore.kernel.org/all/cover.1735933254.git.nicolinc@nvidia.com/ * Rename "vIRQ" to "vEVENTQ" * Use flexible array in struct iommufd_vevent * Add the new ioctl command to union ucmd_buffer * Fix the alphabetical order in union ucmd_buffer too * Rename _TYPE_NONE to _TYPE_DEFAULT aligning with vIOMMU naming v3 https://lore.kernel.org/all/cover.1734477608.git.nicolinc@nvidia.com/ * Rebase on Will's for-joerg/arm-smmu/updates for arm_smmu_event series * Add "Reviewed-by" lines from Kevin * Fix typos in comments, kdocs, and jump tags * Add a patch to sort struct iommufd_ioctl_op * Update iommufd's userpsace-api documentation * Update uAPI kdoc to quote SMMUv3 offical spec * Drop the unused workqueue in struct iommufd_virq * Drop might_sleep() in iommufd_viommu_report_irq() helper * Add missing "break" in iommufd_viommu_get_vdev_id() helper * Shrink the scope of the vmaster's read lock in SMMUv3 driver * Pass in two arguments to iommufd_eventq_virq_handler() helper * Move "!ops || !ops->read" validation into iommufd_eventq_init() * Move "fault->ictx = ictx" closer to iommufd_ctx_get(fault->ictx) * Update commit message for arm_smmu_attach_prepare/commit_vmaster() * Keep "iommufd_fault" as-is and rename "iommufd_eventq_virq" to just "iommufd_virq" v2 https://lore.kernel.org/all/cover.1733263737.git.nicolinc@nvidia.com/ * Rebase on v6.13-rc1 * Add IOPF and vIRQ in iommufd.rst (userspace-api) * Add a proper locking in iommufd_event_virq_destroy * Add iommufd_event_virq_abort with a lockdep_assert_held * Rename "EVENT_*" to "EVENTQ_*" to describe the objects better * Reorganize flows in iommufd_eventq_virq_alloc for abort() to work * Adde struct arm_smmu_vmaster to store vSID upon attaching to a nested domain, calling a newly added iommufd_viommu_get_vdev_id helper * Adde an arm_vmaster_report_event helper in arm-smmu-v3-iommufd file to simplify the routine in arm_smmu_handle_evt() of the main driver v1 https://lore.kernel.org/all/cover.1724777091.git.nicolinc@nvidia.com/ Thanks! Nicolin Nicolin Chen (14): iommufd/fault: Move two fault functions out of the header iommufd/fault: Add an iommufd_fault_init() helper iommufd: Abstract an iommufd_eventq from iommufd_fault iommufd: Rename fault.c to eventq.c iommufd: Add IOMMUFD_OBJ_VEVENTQ and IOMMUFD_CMD_VEVENTQ_ALLOC iommufd/viommu: Add iommufd_viommu_get_vdev_id helper iommufd/viommu: Add iommufd_viommu_report_event helper iommufd/selftest: Require vdev_id when attaching to a nested domain iommufd/selftest: Add IOMMU_TEST_OP_TRIGGER_VEVENT for vEVENTQ coverage iommufd/selftest: Add IOMMU_VEVENTQ_ALLOC test coverage Documentation: userspace-api: iommufd: Update FAULT and VEVENTQ iommu/arm-smmu-v3: Introduce struct arm_smmu_vmaster iommu/arm-smmu-v3: Report events that belong to devices attached to vIOMMU iommu/arm-smmu-v3: Set MEV bit in nested STE for DoS mitigations drivers/iommu/iommufd/Makefile | 2 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 35 + drivers/iommu/iommufd/iommufd_private.h | 135 +++- drivers/iommu/iommufd/iommufd_test.h | 10 + include/linux/iommufd.h | 23 + include/uapi/linux/iommufd.h | 105 +++ tools/testing/selftests/iommu/iommufd_utils.h | 115 ++++ .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 72 +++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 79 ++- drivers/iommu/iommufd/driver.c | 72 +++ drivers/iommu/iommufd/eventq.c | 597 ++++++++++++++++++ drivers/iommu/iommufd/fault.c | 342 ---------- drivers/iommu/iommufd/hw_pagetable.c | 6 +- drivers/iommu/iommufd/main.c | 7 + drivers/iommu/iommufd/selftest.c | 54 ++ drivers/iommu/iommufd/viommu.c | 2 + tools/testing/selftests/iommu/iommufd.c | 36 ++ .../selftests/iommu/iommufd_fail_nth.c | 7 + Documentation/userspace-api/iommufd.rst | 17 + 19 files changed, 1308 insertions(+), 408 deletions(-) create mode 100644 drivers/iommu/iommufd/eventq.c delete mode 100644 drivers/iommu/iommufd/fault.c base-commit: 598749522d4254afb33b8a6c1bea614a95896868 -- 2.43.0

4 months, 2 weeks

3
33
0 0

[PATCH net-next v6 0/8] Some pktgen fixes/improvments (part II)

by Peter Seiderer

While taking a look at '[PATCH net] pktgen: Avoid out-of-range in get_imix_entries' ([1]) and '[PATCH net v2] pktgen: Avoid out-of-bounds access in get_imix_entries' ([2], [3]) and doing some tests and code review I detected that the /proc/net/pktgen/... parsing logic does not honour the user given buffer bounds (resulting in out-of-bounds access). This can be observed e.g. by the following simple test (sometimes the old/'longer' previous value is re-read from the buffer): $ echo add_device lo@0 > /proc/net/pktgen/kpktgend_0 $ echo "min_pkt_size 12345" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 12345 max_pkt_size: 0 Result: OK: min_pkt_size=12345 $ echo -n "min_pkt_size 123" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 12345 max_pkt_size: 0 Result: OK: min_pkt_size=12345 $ echo "min_pkt_size 123" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 123 max_pkt_size: 0 Result: OK: min_pkt_size=123 So fix the out-of-bounds access (and some minor findings) and add a simple proc_net_pktgen selftest... Patch set splited into part I (now already applied to net-next) - net: pktgen: replace ENOTSUPP with EOPNOTSUPP - net: pktgen: enable 'param=value' parsing - net: pktgen: fix hex32_arg parsing for short reads - net: pktgen: fix 'rate 0' error handling (return -EINVAL) - net: pktgen: fix 'ratep 0' error handling (return -EINVAL) - net: pktgen: fix ctrl interface command parsing - net: pktgen: fix access outside of user given buffer in pktgen_thread_write() And part II (this one): - net: pktgen: use defines for the various dec/hex number parsing digits lengths - net: pktgen: fix mix of int/long - net: pktgen: remove extra tmp variable (re-use len instead) - net: pktgen: remove some superfluous variable initializing - net: pktgen: fix mpls maximum labels list parsing - net: pktgen: fix access outside of user given buffer in pktgen_if_write() - net: pktgen: fix mpls reset parsing - net: pktgen: remove all superfluous index assignements - selftest: net: add proc_net_pktgen Regards, Peter Changes v5 -> v6: - add rev-by Simon Horman - drop patch 'net: pktgen: use defines for the various dec/hex number parsing digits lengths' - adjust to dropped patch ''net: pktgen: use defines for the various dec/hex number parsing digits lengths' - net: pktgen: fix mix of int/long - fix line break (suggested by Simon Horman) Changes v4 -> v5: - split up patchset into part i/ii (suggested by Simon Horman) - add rev-by Simon Horman - net: pktgen: align some variable declarations to the most common pattern -> net: pktgen: fix mix of int/long - instead of align to most common pattern (int) adjust all usages to size_t for i and max and ssize_t for len and adjust function signatures of hex32_arg(), count_trail_chars(), num_arg() and strn_len() accordingly - respect reverse xmas tree order for local variable declarations (where possible without too much code churn) - update subject line and patch description - dropped net: pktgen: hex32_arg/num_arg error out in case no characters are available - keep empty hex/num arg is implicit assumed as zero value - dropped net: pktgen: num_arg error out in case no valid character is parsed - keep empty hex/num arg is implicit assumed as zero value - Change patch description ('Fixes:' -> 'Addresses the following:', suggested by Simon Horman) - net: pktgen: remove all superfluous index assignements - new patch (suggested by Simon Horman) - selftest: net: add proc_net_pktgen - addapt to dropped patch 'net: pktgen: hex32_arg/num_arg error out in case no characters are available', empty hex/num arg is now implicit assumed as zero value (instead of failure) Changes v3 -> v4: - add rev-by Simon Horman - new patch 'net: pktgen: use defines for the various dec/hex number parsing digits lengths' (suggested by Simon Horman) - replace C99 comment (suggested by Paolo Abeni) - drop available characters check in strn_len() (suggested by Paolo Abeni) - factored out patch 'net: pktgen: align some variable declarations to the most common pattern' (suggested by Paolo Abeni) - factored out patch 'net: pktgen: remove extra tmp variable (re-use len instead)' (suggested by Paolo Abeni) - factored out patch 'net: pktgen: remove some superfluous variable initializing' (suggested by Paolo Abeni) - factored out patch 'net: pktgen: fix mpls maximum labels list parsing' (suggested by Paolo Abeni) - factored out 'net: pktgen: hex32_arg/num_arg error out in case no characters are available' (suggested by Paolo Abeni) - factored out 'net: pktgen: num_arg error out in case no valid character is parsed' (suggested by Paolo Abeni) Changes v2 -> v3: - new patch: 'net: pktgen: fix ctrl interface command parsing' - new patch: 'net: pktgen: fix mpls reset parsing' - tools/testing/selftests/net/proc_net_pktgen.c: - fix typo in change description ('v1 -> v1' and tyop) - rename some vars to better match usage add_loopback_0 -> thr_cmd_add_loopback_0 rm_loopback_0 -> thr_cmd_rm_loopback_0 wrong_ctrl_cmd -> wrong_thr_cmd legacy_ctrl_cmd -> legacy_thr_cmd ctrl_fd -> thr_fd - add ctrl interface tests Changes v1 -> v2: - new patch: 'net: pktgen: fix hex32_arg parsing for short reads' - new patch: 'net: pktgen: fix 'rate 0' error handling (return -EINVAL)' - new patch: 'net: pktgen: fix 'ratep 0' error handling (return -EINVAL)' - net/core/pktgen.c: additional fix get_imix_entries() and get_labels() - tools/testing/selftests/net/proc_net_pktgen.c: - fix tyop not vs. nod (suggested by Jakub Kicinski) - fix misaligned line (suggested by Jakub Kicinski) - enable fomerly commented out CONFIG_XFRM dependent test (command spi), as CONFIG_XFRM is enabled via tools/testing/selftests/net/config CONFIG_XFRM_INTERFACE/CONFIG_XFRM_USER (suggestex by Jakub Kicinski) - add CONFIG_NET_PKTGEN=m to tools/testing/selftests/net/config (suggested by Jakub Kicinski) - add modprobe pktgen to FIXTURE_SETUP() (suggested by Jakub Kicinski) - fix some checkpatch warnings (Missing a blank line after declarations) - shrink line length by re-naming some variables (command -> cmd, device -> dev) - add 'rate 0' testcase - add 'ratep 0' testcase [1] https://lore.kernel.org/netdev/20241006221221.3744995-1-artem.chernyshev@re… [2] https://lore.kernel.org/netdev/20250109083039.14004-1-pchelkin@ispras.ru/ [3] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… Peter Seiderer (8): net: pktgen: fix mix of int/long net: pktgen: remove extra tmp variable (re-use len instead) net: pktgen: remove some superfluous variable initializing net: pktgen: fix mpls maximum labels list parsing net: pktgen: fix access outside of user given buffer in pktgen_if_write() net: pktgen: fix mpls reset parsing net: pktgen: remove all superfluous index assignements selftest: net: add proc_net_pktgen net/core/pktgen.c | 288 ++++---- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/config | 1 + tools/testing/selftests/net/proc_net_pktgen.c | 646 ++++++++++++++++++ 4 files changed, 805 insertions(+), 131 deletions(-) create mode 100644 tools/testing/selftests/net/proc_net_pktgen.c -- 2.48.1

4 months, 2 weeks

2
10
0 0

[PATCH net] xfrm_output: Force software GSO only in tunnel mode

by Cosmin Ratiu

The cited commit fixed a software GSO bug with VXLAN + IPSec in tunnel mode. Unfortunately, it is slightly broader than necessary, as it also severely affects performance for Geneve + IPSec transport mode over a device capable of both HW GSO and IPSec crypto offload. In this case, xfrm_output unnecessarily triggers software GSO instead of letting the HW do it. In simple iperf3 tests over Geneve + IPSec transport mode over a back-2-back pair of NICs with MTU 1500, the performance was observed to be up to 6x worse when doing software GSO compared to leaving it to the hardware. This commit makes xfrm_output only trigger software GSO in crypto offload cases for already encapsulated packets in tunnel mode, as not doing so would then cause the inner tunnel skb->inner_networking_header to be overwritten and break software GSO for that packet later if the device turns out to not be capable of HW GSO. Taking a closer look at the conditions for the original bug, to better understand the reasons for this change: - vxlan_build_skb -> iptunnel_handle_offloads sets inner_protocol and inner network header. - then, udp_tunnel_xmit_skb -> ip_tunnel_xmit adds outer transport and network headers. - later in the xmit path, xfrm_output -> xfrm_outer_mode_output -> xfrm4_prepare_output -> xfrm4_tunnel_encap_add overwrites the inner network header with the one set in ip_tunnel_xmit before adding the second outer header. - __dev_queue_xmit -> validate_xmit_skb checks whether GSO segmentation needs to happen based on dev features. In the original bug, the hw couldn't segment the packets, so skb_gso_segment was invoked. - deep in the .gso_segment callback machinery, __skb_udp_tunnel_segment tries to use the wrong inner network header, expecting the one set in iptunnel_handle_offloads but getting the one set by xfrm instead. - a bit later, ipv6_gso_segment accesses the wrong memory based on that wrong inner network header. With the new change, the original bug (or similar ones) cannot happen again, as xfrm will now trigger software GSO before applying a tunnel. This concern doesn't exist in packet offload mode, when the HW adds encapsulation headers. For the non-offloaded packets (crypto in SW), software GSO is still done unconditionally in the else branch. Reviewed-by: Dragos Tatulea <dtatulea(a)nvidia.com> Reviewed-by: Yael Chemla <ychemla(a)nvidia.com> Fixes: a204aef9fd77 ("xfrm: call xfrm_output_gso when inner_protocol is set in xfrm_output") Signed-off-by: Cosmin Ratiu <cratiu(a)nvidia.com> --- net/xfrm/xfrm_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index f7abd42c077d..42f1ca513879 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -758,7 +758,7 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) skb->encapsulation = 1; if (skb_is_gso(skb)) { - if (skb->inner_protocol) + if (skb->inner_protocol && x->props.mode == XFRM_MODE_TUNNEL) return xfrm_output_gso(net, sk, skb); skb_shinfo(skb)->gso_type |= SKB_GSO_ESP; -- 2.45.0

4 months, 2 weeks

3
2
0 0

[PATCH v2 0/2] selftests: sched: Add default target support for sched

by Sinadin Shan

This patch series introduces changes to add default build support for the sched tests in selftests. The only test under sched is cs_prctl_test which validates cookies when core scheduling is in effect. This test fails on systems where core scheduling is disabled. The patch series also modifies this behaviour to gracefully skip the test on such systems. For example, such a test skip would look like: TAP version 13 1..1 timeout set to 45 selftests: sched: cs_prctl_test Checking for CONFIG_SCHED_CORE support Core scheduling not enabled in kernel, hence skipping tests ok 1 selftests: sched: cs_prctl_test # SKIP and a successful run: TAP version 13 1..1 timeout set to 45 selftests: sched: cs_prctl_test Checking for CONFIG_SCHED_CORE support CONFIG_SCHED_CORE=y . . . SUCCESS !!! ok 1 selftests: sched: cs_prctl_test Signed-off-by: Sinadin Shan <sinadin.shan(a)oracle.com> --- v2: * Add patch to skip cs_prctl_test on core scheduling disabled systems * v1 link: https://lore.kernel.org/all/20250219064658.449069-1-sinadin.shan@oracle.com --- Sinadin Shan (2): selftests: sched: add sched as a default selftest target selftests: sched: skip cs_prctl_test for systems with core scheduling disabled tools/testing/selftests/Makefile | 1 + tools/testing/selftests/sched/cs_prctl_test.c | 29 ++++++++++++++++++- 2 files changed, 29 insertions(+), 1 deletion(-) -- 2.43.5

4 months, 2 weeks

3
6
0 0

[PATCH 1/2] libbpf: BPF program load type enum

by Slava Imameev

Replacing the boolean field with an enum simplifies the addition of new load types. Currently, the bpf_program structure defines the autoload type using a boolean field. This field is now replaced with an enum, allowing new BPF program loading types to be introduced by extending the enum value range. This patch is the first in a series of two. Signed-off-by: Slava Imameev <slava.imameev(a)crowdstrike.com> --- tools/lib/bpf/libbpf.c | 50 ++++++++++++------- tools/lib/bpf/libbpf.h | 16 ++++++ tools/lib/bpf/libbpf.map | 2 + .../selftests/bpf/prog_tests/load_type.c | 40 +++++++++++++++ .../selftests/bpf/progs/test_load_type.c | 23 +++++++++ 5 files changed, 112 insertions(+), 19 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/load_type.c create mode 100644 tools/testing/selftests/bpf/progs/test_load_type.c diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 194809da5172..9af5c0b08b8b 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -473,7 +473,7 @@ struct bpf_program { struct bpf_object *obj; int fd; - bool autoload; + enum bpf_prog_load_type load_type; bool autoattach; bool sym_global; bool mark_btf_static; @@ -824,11 +824,11 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, * autoload set to false. */ if (sec_name[0] == '?') { - prog->autoload = false; + prog->load_type = BPF_PROG_LOAD_TYPE_DISABLED; /* from now on forget there was ? in section name */ sec_name++; } else { - prog->autoload = true; + prog->load_type = BPF_PROG_LOAD_TYPE_AUTO; } prog->autoattach = true; @@ -1117,7 +1117,8 @@ static int bpf_object_adjust_struct_ops_autoload(struct bpf_object *obj) } } if (use_cnt) - prog->autoload = should_load; + prog->load_type = should_load ? BPF_PROG_LOAD_TYPE_AUTO + : BPF_PROG_LOAD_TYPE_DISABLED; } return 0; @@ -1202,7 +1203,7 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map) * then bpf_object_adjust_struct_ops_autoload() will update its * autoload accordingly. */ - st_ops->progs[i]->autoload = false; + st_ops->progs[i]->load_type = BPF_PROG_LOAD_TYPE_DISABLED; st_ops->progs[i] = NULL; } @@ -1241,7 +1242,7 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map) * if user replaced it with another program or NULL */ if (st_ops->progs[i] && st_ops->progs[i] != prog) - st_ops->progs[i]->autoload = false; + st_ops->progs[i]->load_type = BPF_PROG_LOAD_TYPE_DISABLED; /* Update the value from the shadow type */ st_ops->progs[i] = prog; @@ -3482,7 +3483,7 @@ static bool obj_needs_vmlinux_btf(const struct bpf_object *obj) } bpf_object__for_each_program(prog, obj) { - if (!prog->autoload) + if (prog->load_type == BPF_PROG_LOAD_TYPE_DISABLED) continue; if (prog_needs_vmlinux_btf(prog)) return true; @@ -5973,7 +5974,7 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) /* no need to apply CO-RE relocation if the program is * not going to be loaded */ - if (!prog->autoload) + if (prog->load_type == BPF_PROG_LOAD_TYPE_DISABLED) continue; /* adjust insn_idx from section frame of reference to the local @@ -7106,7 +7107,7 @@ static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_pat */ if (prog_is_subprog(obj, prog)) continue; - if (!prog->autoload) + if (prog->load_type == BPF_PROG_LOAD_TYPE_DISABLED) continue; err = bpf_object__relocate_calls(obj, prog); @@ -7142,7 +7143,7 @@ static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_pat prog = &obj->programs[i]; if (prog_is_subprog(obj, prog)) continue; - if (!prog->autoload) + if (prog->load_type == BPF_PROG_LOAD_TYPE_DISABLED) continue; /* Process data relos for main programs */ @@ -7906,8 +7907,8 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) prog = &obj->programs[i]; if (prog_is_subprog(obj, prog)) continue; - if (!prog->autoload) { - pr_debug("prog '%s': skipped loading\n", prog->name); + if (prog->load_type != BPF_PROG_LOAD_TYPE_AUTO) { + pr_debug("prog '%s': skipped auto-loading\n", prog->name); continue; } prog->log_level |= log_level; @@ -9224,16 +9225,13 @@ const char *bpf_program__section_name(const struct bpf_program *prog) bool bpf_program__autoload(const struct bpf_program *prog) { - return prog->autoload; + return prog->load_type == BPF_PROG_LOAD_TYPE_AUTO; } int bpf_program__set_autoload(struct bpf_program *prog, bool autoload) { - if (prog->obj->loaded) - return libbpf_err(-EINVAL); - - prog->autoload = autoload; - return 0; + return bpf_program__set_load_type(prog, + autoload ? BPF_PROG_LOAD_TYPE_AUTO : BPF_PROG_LOAD_TYPE_DISABLED); } bool bpf_program__autoattach(const struct bpf_program *prog) @@ -13983,7 +13981,7 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) struct bpf_program *prog = *prog_skel->prog; struct bpf_link **link = prog_skel->link; - if (!prog->autoload || !prog->autoattach) + if (prog->load_type != BPF_PROG_LOAD_TYPE_AUTO || !prog->autoattach) continue; /* auto-attaching not supported for this program */ @@ -14087,3 +14085,17 @@ void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s) free(s->progs); free(s); } + +int bpf_program__set_load_type(struct bpf_program *prog, enum bpf_prog_load_type type) +{ + if (prog->obj->loaded) + return libbpf_err(-EINVAL); + + prog->load_type = type; + return 0; +} + +enum bpf_prog_load_type bpf_program__load_type(const struct bpf_program *prog) +{ + return prog->load_type; +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 3020ee45303a..21e3d1f51cb3 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -1918,6 +1918,22 @@ LIBBPF_API int libbpf_register_prog_handler(const char *sec, */ LIBBPF_API int libbpf_unregister_prog_handler(int handler_id); +/** + * The program load type: + * + * - BPF_PROG_LOAD_TYPE_DISABLED: the program is not loaded. + * - BPF_PROG_LOAD_TYPE_AUTO: the program is autoloaded when the bpf_object is loaded. + */ +enum bpf_prog_load_type { + BPF_PROG_LOAD_TYPE_DISABLED = 0, + BPF_PROG_LOAD_TYPE_AUTO, +}; + +LIBBPF_API int bpf_program__set_load_type(struct bpf_program *prog, + enum bpf_prog_load_type loadtype); +LIBBPF_API enum bpf_prog_load_type bpf_program__load_type(const struct bpf_program *prog); + + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index a8b2936a1646..08323e7930fd 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -436,4 +436,6 @@ LIBBPF_1.6.0 { bpf_linker__add_buf; bpf_linker__add_fd; bpf_linker__new_fd; + bpf_program__load_type; + bpf_program__set_load_type; } LIBBPF_1.5.0; diff --git a/tools/testing/selftests/bpf/prog_tests/load_type.c b/tools/testing/selftests/bpf/prog_tests/load_type.c new file mode 100644 index 000000000000..7c8d55173b2b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/load_type.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include <time.h> +#include "test_load_type.skel.h" + +void test_load_type(void) +{ + int duration = 0, err; + struct test_load_type *skel; + + skel = test_load_type__open(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + goto cleanup; + + /* don't load prog1 */ + bpf_program__set_load_type(skel->progs.prog1, BPF_PROG_LOAD_TYPE_DISABLED); + + /* load and attach prog2 */ + bpf_program__set_load_type(skel->progs.prog2, BPF_PROG_LOAD_TYPE_AUTO); + CHECK(!bpf_program__autoload(skel->progs.prog2), "prog2", "not autoload?!\n"); + + err = test_load_type__load(skel); + if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) + goto cleanup; + + CHECK(!bpf_program__autoattach(skel->progs.prog2), "prog2", "not autoattach?!\n"); + + err = test_load_type__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + usleep(1); + + CHECK(skel->bss->prog1_called, "prog1", "called?!\n"); + CHECK(!skel->bss->prog2_called, "prog2", "not called\n"); + +cleanup: + test_load_type__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_load_type.c b/tools/testing/selftests/bpf/progs/test_load_type.c new file mode 100644 index 000000000000..a0d39757c5b9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_load_type.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +bool prog1_called = false; +bool prog2_called = false; + +SEC("raw_tp/sys_enter") +int prog1(const void *ctx) +{ + prog1_called = true; + return 0; +} + +SEC("raw_tp/sys_enter") +int prog2(const void *ctx) +{ + prog2_called = true; + return 0; +} + +char _license[] SEC("license") = "GPL"; -- 2.39.5 (Apple Git-154)

4 months, 2 weeks

3
9
0 0

[PATCH v1] selftests/user_events: Fix failures caused by test code

by realxxyq＠163.com

From: Yiqian Xun <xunyiqian(a)kylinos.cn> In parse_abi function,the dyn_test fails because the enable_file isn’t closed after successfully registering an event. By adding wait_for_delete(), the dyn_test now passes as expected. Signed-off-by: Yiqian Xun <xunyiqian(a)kylinos.cn> --- tools/testing/selftests/user_events/dyn_test.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c index bdf9ab127488..54c9412f8dee 100644 --- a/tools/testing/selftests/user_events/dyn_test.c +++ b/tools/testing/selftests/user_events/dyn_test.c @@ -127,6 +127,8 @@ static int parse_abi(int *check, const char *value) close(fd); + wait_for_delete(); + return ret; } -- 2.25.1

4 months, 2 weeks

4
5
0 0

Re: Re: Re: Re: Re: [PATCH 2/2] libbpf: BPF programs dynamic loading and attaching

by Slava Imameev

> > > On Mon, 2025-02-10 at 16:06 -0800, Andrii Nakryiko wrote: > > > > Tracking associated maps for a program is not necessary. As long as > > > > the last BPF program using the BPF map is unloaded, the kernel will > > > > automatically free not-anymore-referenced BPF map. Note that > > > > bpf_object itself will keep FDs for BPF maps, so you'd need to make > > > > sure to do bpf_object__close() to release those references. > > > > > > > > But if you are going to ask to re-create BPF maps next time BPF > > > > program is loaded... Well, I'll say you are asking for a bit too > > > > > much, > > > > tbh. If you want to be *that* sophisticated, it shouldn't be too > > > > hard > > > > for you to get all this information from BPF program's > > > > instructions. > > > > > > > > We really are that sophisticated (see below for more details). We could > > scan program instructions, but we'd then tie our logic to BPF > > implementation details and duplicate logic already present in libbpf > > (https://urldefense.com/v3/__https://elixir.bootlin.com/linux/v6.13.2/source… <https://urldefense.com/v3/__https://elixir.bootlin.com/linux/v6.13.2/source…>*L6087__;Iw!!BmdzS3_lV9HdKG8!384hiRcpmYOjMU3kT-1m4GxWp5XxwHj9ICrDtIUKCmCbxLVAxemc6UN64cE3Mktu_z4f2JheoKm6RBYQdc-MiPbyexk6-Rn48A$ > > ). Obviously this *can* be done but it's not at all ideal from an > > application perspective. > > > > > I agree it's not ideal, but it's also not some complicated and > bound-to-be-changed logic. What you point out in libbpf source code is > a bit different thing, reality is much simpler. Only so-called ldimm64 > instruction (BPF_LD | BPF_IMM | BPF_DW opcode) can be referencing map > FD, so analysing this is borderline trivial. And this is part of BPF > ISA, so not going to change. Our approach is to associate an array of maps as a property with each BPF program, this property is initialised at the relocation stage. So, we do not need to parse BPF program instructions. Instead, we rely on recorded relocations. I think this is a more robust and clean solution with advantage of all code in the same place and being at the higher level of abstraction with a relocation table. The mainline libbpf keeps array of maps for a bpf_object, we extended this by adding an array of maps associated with each bpf_program. For example, a code excerpt, from our development branch, which associates a map with bpf_program at relocation phase: insn[0].src_reg = BPF_PSEUDO_MAP_FD; insn[0].imm = map->fd; err = bpf_program__add_map(prog, map); > > > > > > > > > > bpf_object is the unit of coherence in libbpf, so I don't see us > > > > refcounting maps between bpf_objects. Kernel is doing refcounting > > > > based on FDs, so see if you can use that. > > > > > > > > I can understand that. That said, I think if there's no logic across > > objects, and bpf_object access is not thread-safe, it puts us into a > > tough situation: > > - Complex refcounting, code scanning, etc to keep consistency when > > manipulating maps used by multiple programs. > > - Parallel loading not being well-balanced, if we split programs across > > objects. > > > > We could alternatively write our own custom loader, but then we’d have > > to duplicate much of the useful logic that libbpf already implements: > > skeleton generation, map/program association, embedding programs into > > ELFs, loading logic and kernel probing, etc. We’d like some way to > > handle dynamic/parallel loading without having to replicate all the > > advantages libbpf grants us. > > > > > Yeah, I can understand that as well, but bpf_object's single-threaded > design and the fact that bpf_object__load is kind of the final step > where programs are loaded (or not) is pretty backed in. I don't see > bpf_object becoming multi-threaded. We understood this, but the current bpf_object design allowed us to use it in a multithreaded environment with minor modification for bpf_program load. We understand that the design choice of libbpf being single threaded is unlikely to be reconsidered. > > > > > > > > > > bpf_object is the unit of coherence in libbpf, so I don't see us > > > > refcounting maps between bpf_objects. Kernel is doing refcounting > > > > based on FDs, so see if you can use that. > > > > > > > > I can understand that. That said, I think if there's no logic across > > objects, and bpf_object access is not thread-safe, it puts us into a > > tough situation: > > - Complex refcounting, code scanning, etc to keep consistency when > > manipulating maps used by multiple programs. > > - Parallel loading not being well-balanced, if we split programs across > > objects. > > > > We could alternatively write our own custom loader, but then we’d have > > to duplicate much of the useful logic that libbpf already implements: > > skeleton generation, map/program association, embedding programs into > > ELFs, loading logic and kernel probing, etc. We’d like some way to > > handle dynamic/parallel loading without having to replicate all the > > advantages libbpf grants us. > > > > > Yeah, I can understand that as well, but bpf_object's single-threaded > design and the fact that bpf_object__load is kind of the final step > where programs are loaded (or not) is pretty backed in. I don't see > bpf_object becoming multi-threaded. The dynamic program > loading/unloading/loading again is something that I can't yet justify, > tbh. > > > So the best I can propose you is to use libbpf's skeleton and > bpf_object concept for, effectively, ELF handling, relocations, all > the preparations up to loading BPF programs. And after that you can > take over loading and handling program lifetime outside of bpf_object. > > > Dynamic map creation after bpf_object__load() I think is completely > outside of the scope and you'll have to solve this problem for > yourself. I would point out, though, that internally libbpf already > switched to sort-of pre-creating stable FDs for maps before they are > actually created in the kernel. So it's conceivable that we can have > more granularity in bpf_object preparation. I.e., first step would be > to parse ELF and handle relocations, prepare everything. After that we > can have a step to create maps, and then another one to create > programs. Usually people would do all that, but you can stop right > before maps creation or before program creation, whatever fits your > use case better. > > > The key is that program instructions will be final and won't need > adjustments regardless of maps actually being created or not. FDs, as > I mentioned, are stable regardless. We used this in our design, so we did not need to scan BPF program instructions to fix map's fds referenced by instructions from a dynamically loaded bpf_program with dynamically created maps. > > > > The use case here is that our security monitoring agent leverages eBPF > > as its foundational technology to gather telemetry from the kernel. As > > part of that, we hook many different kernel subsystems (process, > > memory, filesystem, network, etc), tying them together and tracking > > with maps. So we legitimately have a very large number of programs all > > doing different work. For products of this scale, it increases security > > and performance to load this set of programs and their maps in an > > optimized, parallel fashion and subsequently change the loaded set of > > programs and maps dynamically without disturbing the rest of the > > application. > > > Yes, makes sense. You'll need to decide for yourself if it's actually > more meaningful to split those 200 programs into independent > bpf_objects by features, and be rigorous about sharing state (maps) > through bpf_map__reuse_fd(), which would allow to parallelize loading > within confines of existing libbpf APIs. Or you can be a bit more > low-level with program loading outside of bpf_object API, as I > described above. Yes, this can be one of the ways to share bpf maps across multiple bpf_objects and use existing libbpf for parallel bps programs loading, if we want to keep a full libbpf compatibility, but at a cost of complicating design, as we need to convert a single bpf_object model to multiple bpf_objects with a new layer that manages these bpf_objects. In our case, as a bpf_program can map to multiple features, which can be modified independently, and to achieve an even load balancing across multiple threads, it would be probably one bpf_program for a bpf_object.

4 months, 2 weeks

1
0
0 0

[RESEND PATCH v2] wireguard: selftests: Cleanup CONFIG_UBSAN_SANITIZE_ALL

by WangYuli

Commit 918327e9b7ff ("ubsan: Remove CONFIG_UBSAN_SANITIZE_ALL") removed the CONFIG_UBSAN_SANITIZE_ALL configuration option. Eliminate invalid configurations to improve code readability. Link: https://lore.kernel.org/all/20250123105743.GO395043@kernel.org/ Reviewed-by: Simon Horman <horms(a)kernel.org> Signed-off-by: WangYuli <wangyuli(a)uniontech.com> --- Changelog: *v1->v2: Add Simon Horman's "Reviewed-by" tag. Signed-off-by: WangYuli <wangyuli(a)uniontech.com> --- tools/testing/selftests/wireguard/qemu/debug.config | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config index 139fd9aa8b12..828f14300d0a 100644 --- a/tools/testing/selftests/wireguard/qemu/debug.config +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -22,7 +22,6 @@ CONFIG_HAVE_ARCH_KASAN=y CONFIG_KASAN=y CONFIG_KASAN_INLINE=y CONFIG_UBSAN=y -CONFIG_UBSAN_SANITIZE_ALL=y CONFIG_DEBUG_KMEMLEAK=y CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_SHIRQ=y -- 2.47.2

4 months, 2 weeks

2
1
0 0

[PATCH 00/16] selftests: vDSO: parse_vdso: Make compatible with nolibc

by Thomas Weißschuh

For testing the functionality of the vDSO, it is necessary to build userspace programs for multiple different architectures. It is additional work to acquire matching userspace cross-compilers with full C libraries and then building root images out of those. The kernel tree already contains nolibc, a small, header-only C library. By using it, it is possible to build userspace programs without any additional dependencies. For example the kernel.org crosstools or multi-target clang can be used to build test programs for a multitude of architectures. While nolibc is very limited, it is enough for many selftests. With some minor adjustments it is possible to make parse_vdso.c compatible with nolibc. As an example, vdso_standalone_test_x86 is now built from the same C code as the regular vdso_test_gettimeofday, while still being completely standalone. This should probably go through the kselftest tree. Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- Thomas Weißschuh (16): MAINTAINERS: Add vDSO selftests elf, uapi: Add definition for STN_UNDEF elf, uapi: Add definition for DT_GNU_HASH elf, uapi: Add definitions for VER_FLG_BASE and VER_FLG_WEAK elf, uapi: Add type ElfXX_Versym elf, uapi: Add types ElfXX_Verdef and ElfXX_Veraux tools/include: Add uapi/linux/elf.h selftests: Add headers target selftests: vDSO: vdso_standalone_test_x86: Use vdso_init_form_sysinfo_ehdr selftests: vDSO: parse_vdso: Drop vdso_init_from_auxv() selftests: vDSO: parse_vdso: Use UAPI headers instead of libc headers selftests: vDSO: parse_vdso: Test __SIZEOF_LONG__ instead of ULONG_MAX selftests: vDSO: parse_vdso: Make compatible with nolibc selftests: vDSO: vdso_test_gettimeofday: Clean up includes selftests: vDSO: vdso_test_gettimeofday: Make compatible with nolibc selftests: vDSO: vdso_standalone_test_x86: Switch to nolibc MAINTAINERS | 1 + include/uapi/linux/elf.h | 38 ++ tools/include/uapi/linux/elf.h | 524 +++++++++++++++++++++ tools/testing/selftests/lib.mk | 5 +- tools/testing/selftests/vDSO/Makefile | 11 +- tools/testing/selftests/vDSO/parse_vdso.c | 21 +- tools/testing/selftests/vDSO/parse_vdso.h | 1 - .../selftests/vDSO/vdso_standalone_test_x86.c | 143 +----- .../selftests/vDSO/vdso_test_gettimeofday.c | 4 +- 9 files changed, 584 insertions(+), 164 deletions(-) --- base-commit: 2014c95afecee3e76ca4a56956a936e23283f05b change-id: 20241017-parse_vdso-nolibc-e069baa7ff48 Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

4 months, 2 weeks

4
31
0 0

[PATCH v9 3/3] selftests/rseq: Add test for mm_cid compaction

by Gabriele Monaco

A task in the kernel (task_mm_cid_work) runs somewhat periodically to compact the mm_cid for each process. Add a test to validate that it runs correctly and timely. The test spawns 1 thread pinned to each CPU, then each thread, including the main one, runs in short bursts for some time. During this period, the mm_cids should be spanning all numbers between 0 and nproc. At the end of this phase, a thread with high enough mm_cid (>= nproc/2) is selected to be the new leader, all other threads terminate. After some time, the only running thread should see 0 as mm_cid, if that doesn't happen, the compaction mechanism didn't work and the test fails. The test never fails if only 1 core is available, in which case, we cannot test anything as the only available mm_cid is 0. Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Signed-off-by: Gabriele Monaco <gmonaco(a)redhat.com> --- tools/testing/selftests/rseq/.gitignore | 1 + tools/testing/selftests/rseq/Makefile | 2 +- .../selftests/rseq/mm_cid_compaction_test.c | 200 ++++++++++++++++++ 3 files changed, 202 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/rseq/mm_cid_compaction_test.c diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore index 16496de5f6ce4..2c89f97e4f737 100644 --- a/tools/testing/selftests/rseq/.gitignore +++ b/tools/testing/selftests/rseq/.gitignore @@ -3,6 +3,7 @@ basic_percpu_ops_test basic_percpu_ops_mm_cid_test basic_test basic_rseq_op_test +mm_cid_compaction_test param_test param_test_benchmark param_test_compare_twice diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 5a3432fceb586..ce1b38f46a355 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -16,7 +16,7 @@ OVERRIDE_TARGETS = 1 TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ param_test_benchmark param_test_compare_twice param_test_mm_cid \ - param_test_mm_cid_benchmark param_test_mm_cid_compare_twice + param_test_mm_cid_benchmark param_test_mm_cid_compare_twice mm_cid_compaction_test TEST_GEN_PROGS_EXTENDED = librseq.so diff --git a/tools/testing/selftests/rseq/mm_cid_compaction_test.c b/tools/testing/selftests/rseq/mm_cid_compaction_test.c new file mode 100644 index 0000000000000..7ddde3b657dd6 --- /dev/null +++ b/tools/testing/selftests/rseq/mm_cid_compaction_test.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include <assert.h> +#include <pthread.h> +#include <sched.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stddef.h> + +#include "../kselftest.h" +#include "rseq.h" + +#define VERBOSE 0 +#define printf_verbose(fmt, ...) \ + do { \ + if (VERBOSE) \ + printf(fmt, ##__VA_ARGS__); \ + } while (0) + +/* 0.5 s */ +#define RUNNER_PERIOD 500000 +/* Number of runs before we terminate or get the token */ +#define THREAD_RUNS 5 + +/* + * Number of times we check that the mm_cid were compacted. + * Checks are repeated every RUNNER_PERIOD. + */ +#define MM_CID_COMPACT_TIMEOUT 10 + +struct thread_args { + int cpu; + int num_cpus; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + pthread_t *tinfo; + struct thread_args *args_head; +}; + +static void __noreturn *thread_runner(void *arg) +{ + struct thread_args *args = arg; + int i, ret, curr_mm_cid; + cpu_set_t cpumask; + + CPU_ZERO(&cpumask); + CPU_SET(args->cpu, &cpumask); + ret = pthread_setaffinity_np(pthread_self(), sizeof(cpumask), &cpumask); + if (ret) { + errno = ret; + perror("Error: failed to set affinity"); + abort(); + } + pthread_barrier_wait(args->barrier); + + for (i = 0; i < THREAD_RUNS; i++) + usleep(RUNNER_PERIOD); + curr_mm_cid = rseq_current_mm_cid(); + /* + * We select one thread with high enough mm_cid to be the new leader. + * All other threads (including the main thread) will terminate. + * After some time, the mm_cid of the only remaining thread should + * converge to 0, if not, the test fails. + */ + if (curr_mm_cid >= args->num_cpus / 2 && + !pthread_mutex_trylock(args->token)) { + printf_verbose( + "cpu%d has mm_cid=%d and will be the new leader.\n", + sched_getcpu(), curr_mm_cid); + for (i = 0; i < args->num_cpus; i++) { + if (args->tinfo[i] == pthread_self()) + continue; + ret = pthread_join(args->tinfo[i], NULL); + if (ret) { + errno = ret; + perror("Error: failed to join thread"); + abort(); + } + } + pthread_barrier_destroy(args->barrier); + free(args->tinfo); + free(args->token); + free(args->barrier); + free(args->args_head); + + for (i = 0; i < MM_CID_COMPACT_TIMEOUT; i++) { + curr_mm_cid = rseq_current_mm_cid(); + printf_verbose("run %d: mm_cid=%d on cpu%d.\n", i, + curr_mm_cid, sched_getcpu()); + if (curr_mm_cid == 0) + exit(EXIT_SUCCESS); + usleep(RUNNER_PERIOD); + } + exit(EXIT_FAILURE); + } + printf_verbose("cpu%d has mm_cid=%d and is going to terminate.\n", + sched_getcpu(), curr_mm_cid); + pthread_exit(NULL); +} + +int test_mm_cid_compaction(void) +{ + cpu_set_t affinity; + int i, j, ret = 0, num_threads; + pthread_t *tinfo; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + struct thread_args *args; + + sched_getaffinity(0, sizeof(affinity), &affinity); + num_threads = CPU_COUNT(&affinity); + tinfo = calloc(num_threads, sizeof(*tinfo)); + if (!tinfo) { + perror("Error: failed to allocate tinfo"); + return -1; + } + args = calloc(num_threads, sizeof(*args)); + if (!args) { + perror("Error: failed to allocate args"); + ret = -1; + goto out_free_tinfo; + } + token = malloc(sizeof(*token)); + if (!token) { + perror("Error: failed to allocate token"); + ret = -1; + goto out_free_args; + } + barrier = malloc(sizeof(*barrier)); + if (!barrier) { + perror("Error: failed to allocate barrier"); + ret = -1; + goto out_free_token; + } + if (num_threads == 1) { + fprintf(stderr, "Cannot test on a single cpu. " + "Skipping mm_cid_compaction test.\n"); + /* only skipping the test, this is not a failure */ + goto out_free_barrier; + } + pthread_mutex_init(token, NULL); + ret = pthread_barrier_init(barrier, NULL, num_threads); + if (ret) { + errno = ret; + perror("Error: failed to initialise barrier"); + goto out_free_barrier; + } + for (i = 0, j = 0; i < CPU_SETSIZE && j < num_threads; i++) { + if (!CPU_ISSET(i, &affinity)) + continue; + args[j].num_cpus = num_threads; + args[j].tinfo = tinfo; + args[j].token = token; + args[j].barrier = barrier; + args[j].cpu = i; + args[j].args_head = args; + if (!j) { + /* The first thread is the main one */ + tinfo[0] = pthread_self(); + ++j; + continue; + } + ret = pthread_create(&tinfo[j], NULL, thread_runner, &args[j]); + if (ret) { + errno = ret; + perror("Error: failed to create thread"); + abort(); + } + ++j; + } + printf_verbose("Started %d threads.\n", num_threads); + + /* Also main thread will terminate if it is not selected as leader */ + thread_runner(&args[0]); + + /* only reached in case of errors */ +out_free_barrier: + free(barrier); +out_free_token: + free(token); +out_free_args: + free(args); +out_free_tinfo: + free(tinfo); + + return ret; +} + +int main(int argc, char **argv) +{ + if (!rseq_mm_cid_available()) { + fprintf(stderr, "Error: rseq_mm_cid unavailable\n"); + return -1; + } + if (test_mm_cid_compaction()) + return -1; + return 0; +} -- 2.48.1

4 months, 2 weeks

1
0
0 0

[PATCH] selftests/memory-hotplug: debugging improvement

by Leonardo Felipe Takao Hirata

Formats testing messages to improve debugging: - Inserts alignment tabs with printf for testing results - Changes messages to improve readability and understanding Signed-off-by: Leonardo Felipe Takao Hirata <leofthirata(a)gmail.com> --- .../memory-hotplug/mem-on-off-test.sh | 21 ++++++++++++------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh index 611be86eaf3d..7a2eea366c1b 100755 --- a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh +++ b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh @@ -143,6 +143,11 @@ online_all_offline_memory() done } +print_status() +{ + printf '\t\t%-37s %12s\n' "$1" "$2" +} + error=-12 priority=0 # Run with default of ratio=2 for Kselftest run @@ -184,16 +189,16 @@ echo "Test scope: $ratio% hotplug memory" # Online all hot-pluggable memory # hotpluggable_num=`hotpluggable_offline_memory | wc -l` -echo -e "\t online all hot-pluggable memory in offline state:" +echo -e "Changing all OFFLINE hot-pluggable memory blocks to ONLINE:\n" if [ "$hotpluggable_num" -gt 0 ]; then for memory in `hotpluggable_offline_memory`; do - echo "offline->online memory$memory" + echo -e "\t\tOFFLINE -> ONLINE memory block ($memory)" if ! online_memory_expect_success $memory; then retval=1 fi done else - echo -e "\t\t SKIPPED - no hot-pluggable memory in offline state" + echo -e "\t\t SKIPPED - no hot-pluggable memory in OFFLINE state" fi # @@ -201,16 +206,16 @@ fi # hotpluggable_num=`hotpluggable_online_memory | wc -l` target=`echo "a=$hotpluggable_num*$ratio; if ( a%100 ) a/100+1 else a/100" | bc` -echo -e "\t offline $ratio% hot-pluggable memory in online state" -echo -e "\t trying to offline $target out of $hotpluggable_num memory block(s):" +echo -e "\nOFFLINE $ratio% hot-pluggable memory in ONLINE state ($target memory block(s))" +echo -e "Changing $target out of $hotpluggable_num OFFLINE memory block(s) to ONLINE:\n" for memory in `hotpluggable_online_memory`; do if [ "$target" -gt 0 ]; then - echo "online->offline memory$memory" + tmp="ONLINE -> OFFLINE memory block (${memory})" if offline_memory_expect_success $memory &>/dev/null; then target=$(($target - 1)) - echo "-> Success" + print_status "$tmp" "[SUCCESS]" else - echo "-> Failure" + print_status "$tmp" "[FAILURE]" fi fi done -- 2.43.0

4 months, 2 weeks

1
0
0 0

[PATCH AUTOSEL 6.6 02/20] selftests/bpf: Fix invalid flag of recv()

by Sasha Levin

From: Jiayuan Chen <mrpre(a)163.com> [ Upstream commit a0c11149509aa905aeec10cf9998091443472b0b ] SOCK_NONBLOCK flag is only effective during socket creation, not during recv. Use MSG_DONTWAIT instead. Signed-off-by: Jiayuan Chen <mrpre(a)163.com> Signed-off-by: Martin KaFai Lau <martin.lau(a)kernel.org> Acked-by: Jakub Sitnicki <jakub(a)cloudflare.com> Acked-by: John Fastabend <john.fastabend(a)gmail.com> Link: https://patch.msgid.link/20250122100917.49845-5-mrpre@163.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/bpf/prog_tests/sockmap_basic.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index dda7060e86a09..b16d765a153a9 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -402,8 +402,8 @@ static void test_sockmap_skb_verdict_shutdown(void) if (!ASSERT_EQ(err, 1, "epoll_wait(fd)")) goto out_close; - n = recv(c1, &b, 1, SOCK_NONBLOCK); - ASSERT_EQ(n, 0, "recv_timeout(fin)"); + n = recv(c1, &b, 1, MSG_DONTWAIT); + ASSERT_EQ(n, 0, "recv(fin)"); out_close: close(c1); close(p1); @@ -459,7 +459,7 @@ static void test_sockmap_skb_verdict_fionread(bool pass_prog) ASSERT_EQ(avail, expected, "ioctl(FIONREAD)"); /* On DROP test there will be no data to read */ if (pass_prog) { - recvd = recv_timeout(c1, &buf, sizeof(buf), SOCK_NONBLOCK, IO_TIMEOUT_SEC); + recvd = recv_timeout(c1, &buf, sizeof(buf), MSG_DONTWAIT, IO_TIMEOUT_SEC); ASSERT_EQ(recvd, sizeof(buf), "recv_timeout(c0)"); } -- 2.39.5

4 months, 2 weeks

1
0
0 0

[PATCH AUTOSEL 6.12 02/28] selftests/bpf: Fix invalid flag of recv()

by Sasha Levin

From: Jiayuan Chen <mrpre(a)163.com> [ Upstream commit a0c11149509aa905aeec10cf9998091443472b0b ] SOCK_NONBLOCK flag is only effective during socket creation, not during recv. Use MSG_DONTWAIT instead. Signed-off-by: Jiayuan Chen <mrpre(a)163.com> Signed-off-by: Martin KaFai Lau <martin.lau(a)kernel.org> Acked-by: Jakub Sitnicki <jakub(a)cloudflare.com> Acked-by: John Fastabend <john.fastabend(a)gmail.com> Link: https://patch.msgid.link/20250122100917.49845-5-mrpre@163.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/bpf/prog_tests/sockmap_basic.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 82bfb266741cf..fb08c565d6aad 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -492,8 +492,8 @@ static void test_sockmap_skb_verdict_shutdown(void) if (!ASSERT_EQ(err, 1, "epoll_wait(fd)")) goto out_close; - n = recv(c1, &b, 1, SOCK_NONBLOCK); - ASSERT_EQ(n, 0, "recv_timeout(fin)"); + n = recv(c1, &b, 1, MSG_DONTWAIT); + ASSERT_EQ(n, 0, "recv(fin)"); out_close: close(c1); close(p1); @@ -546,7 +546,7 @@ static void test_sockmap_skb_verdict_fionread(bool pass_prog) ASSERT_EQ(avail, expected, "ioctl(FIONREAD)"); /* On DROP test there will be no data to read */ if (pass_prog) { - recvd = recv_timeout(c1, &buf, sizeof(buf), SOCK_NONBLOCK, IO_TIMEOUT_SEC); + recvd = recv_timeout(c1, &buf, sizeof(buf), MSG_DONTWAIT, IO_TIMEOUT_SEC); ASSERT_EQ(recvd, sizeof(buf), "recv_timeout(c0)"); } -- 2.39.5

4 months, 2 weeks

1
0
0 0

[PATCH AUTOSEL 6.13 01/32] selftests/bpf: Adjust data size to have ETH_HLEN

by Sasha Levin

From: Shigeru Yoshida <syoshida(a)redhat.com> [ Upstream commit c7f2188d68c114095660a950b7e880a1e5a71c8f ] The function bpf_test_init() now returns an error if user_size (.data_size_in) is less than ETH_HLEN, causing the tests to fail. Adjust the data size to ensure it meets the requirement of ETH_HLEN. Signed-off-by: Shigeru Yoshida <syoshida(a)redhat.com> Signed-off-by: Martin KaFai Lau <martin.lau(a)kernel.org> Link: https://patch.msgid.link/20250121150643.671650-2-syoshida@redhat.com Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- .../testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c | 4 ++-- .../testing/selftests/bpf/prog_tests/xdp_devmap_attach.c | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c index c7f74f068e788..df27535995af8 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c @@ -52,10 +52,10 @@ static void test_xdp_with_cpumap_helpers(void) ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to cpumap entry prog_id"); /* send a packet to trigger any potential bugs in there */ - char data[10] = {}; + char data[ETH_HLEN] = {}; DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = &data, - .data_size_in = 10, + .data_size_in = sizeof(data), .flags = BPF_F_TEST_XDP_LIVE_FRAMES, .repeat = 1, ); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c index 27ffed17d4be3..461ab18705d5c 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c @@ -23,7 +23,7 @@ static void test_xdp_with_devmap_helpers(void) __u32 len = sizeof(info); int err, dm_fd, dm_fd_redir, map_fd; struct nstoken *nstoken = NULL; - char data[10] = {}; + char data[ETH_HLEN] = {}; __u32 idx = 0; SYS(out_close, "ip netns add %s", TEST_NS); @@ -58,7 +58,7 @@ static void test_xdp_with_devmap_helpers(void) /* send a packet to trigger any potential bugs in there */ DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = &data, - .data_size_in = 10, + .data_size_in = sizeof(data), .flags = BPF_F_TEST_XDP_LIVE_FRAMES, .repeat = 1, ); @@ -158,7 +158,7 @@ static void test_xdp_with_devmap_helpers_veth(void) struct nstoken *nstoken = NULL; __u32 len = sizeof(info); int err, dm_fd, dm_fd_redir, map_fd, ifindex_dst; - char data[10] = {}; + char data[ETH_HLEN] = {}; __u32 idx = 0; SYS(out_close, "ip netns add %s", TEST_NS); @@ -208,7 +208,7 @@ static void test_xdp_with_devmap_helpers_veth(void) /* send a packet to trigger any potential bugs in there */ DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = &data, - .data_size_in = 10, + .data_size_in = sizeof(data), .flags = BPF_F_TEST_XDP_LIVE_FRAMES, .repeat = 1, ); -- 2.39.5

4 months, 2 weeks

1
1
0 0

[PATCH -next] selftests/filesystems: Remove duplicate sys/types.h header

by Jiapeng Chong

./tools/testing/selftests/filesystems/utils.c: sys/types.h is included more than once. Reported-by: Abaci Robot <abaci(a)linux.alibaba.com> Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=19042 Signed-off-by: Jiapeng Chong <jiapeng.chong(a)linux.alibaba.com> --- tools/testing/selftests/filesystems/utils.c | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/testing/selftests/filesystems/utils.c b/tools/testing/selftests/filesystems/utils.c index e553c89c5b19..06419bf4ba19 100644 --- a/tools/testing/selftests/filesystems/utils.c +++ b/tools/testing/selftests/filesystems/utils.c @@ -3,7 +3,6 @@ #define _GNU_SOURCE #endif #include <fcntl.h> -#include <sys/types.h> #include <dirent.h> #include <grp.h> #include <linux/limits.h> -- 2.32.0.3.g01195cf9f

4 months, 2 weeks

1
0
0 0

[PATCH] selftests/mount: Use 'const' for filename parameters

by Ritvik Gupta

The filename parameter in write_file(), maybe_write_file(), and vmaybe_write_file() is unmodified / read-only. So, used 'const' to improve type safety. Signed-off-by: Ritvik Gupta <ritvikfoss(a)gmail.com> --- tools/testing/selftests/mount/unprivileged-remount-test.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c index d2917054fe3a..e80ac76261e7 100644 --- a/tools/testing/selftests/mount/unprivileged-remount-test.c +++ b/tools/testing/selftests/mount/unprivileged-remount-test.c @@ -54,7 +54,7 @@ static void die(char *fmt, ...) exit(EXIT_FAILURE); } -static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap) +static void vmaybe_write_file(bool enoent_ok, const char *filename, char *fmt, va_list ap) { char buf[4096]; int fd; @@ -92,7 +92,7 @@ static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list } } -static void maybe_write_file(char *filename, char *fmt, ...) +static void maybe_write_file(const char *filename, char *fmt, ...) { va_list ap; @@ -102,7 +102,7 @@ static void maybe_write_file(char *filename, char *fmt, ...) } -static void write_file(char *filename, char *fmt, ...) +static void write_file(const char *filename, char *fmt, ...) { va_list ap; -- 2.48.1

4 months, 2 weeks

1
0
0 0

[PATCH rcu 00/20] SRCU changes for v6.15

by Boqun Feng

Hi, Please find the upcoming changes in SRCU for v6.15. The changes can also be found at: git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux.git srcu.2025.02.05a Regards, Boqun Paul E. McKenney (20): srcu: Make Tiny SRCU able to operate in preemptible kernels srcu: Define SRCU_READ_FLAVOR_ALL in terms of symbols srcu: Use ->srcu_gp_seq for rcutorture reader batch srcu: Pull ->srcu_{un,}lock_count into a new srcu_ctr structure srcu: Make SRCU readers use ->srcu_ctrs for counter selection srcu: Make Tree SRCU updates independent of ->srcu_idx srcu: Force synchronization for srcu_get_delay() srcu: Rename srcu_check_read_flavor_lite() to srcu_check_read_flavor_force() srcu: Add SRCU_READ_FLAVOR_SLOWGP to flag need for synchronize_rcu() srcu: Pull pointer-to-integer conversion into __srcu_ptr_to_ctr() srcu: Pull integer-to-pointer conversion into __srcu_ctr_to_ptr() srcu: Move SRCU Tree/Tiny definitions from srcu.h srcu: Add SRCU-fast readers rcutorture: Add ability to test srcu_read_{,un}lock_fast() refscale: Add srcu_read_lock_fast() support using "srcu-fast" rcutorture: Make scenario SRCU-P use srcu_read_lock_fast() srcu: Fix srcu_read_unlock_{lite,nmisafe}() kernel-doc srcu: Document that srcu_{read_lock,down_read}() can share srcu_struct srcu: Add srcu_down_read_fast() and srcu_up_read_fast() srcu: Make SRCU-fast also be NMI-safe include/linux/srcu.h | 102 +++++++-- include/linux/srcutiny.h | 27 ++- include/linux/srcutree.h | 98 +++++++-- kernel/rcu/rcu.h | 9 +- kernel/rcu/rcutorture.c | 11 + kernel/rcu/refscale.c | 32 ++- kernel/rcu/srcutiny.c | 6 + kernel/rcu/srcutree.c | 199 +++++++++--------- .../rcutorture/configs/rcu/SRCU-P.boot | 1 + 9 files changed, 359 insertions(+), 126 deletions(-) -- 2.39.5 (Apple Git-154)

4 months, 2 weeks

1
20
0 0

[PATCH net v2 2/2] selftests: drv-net: test XDP, HDS auto and the ioctl path

by Jakub Kicinski

Test XDP and HDS interaction. While at it add a test for using the IOCTL, as that turned out to be the real culprit. Testing bnxt: # NETIF=eth0 ./ksft-net-drv/drivers/net/hds.py KTAP version 1 1..12 ok 1 hds.get_hds ok 2 hds.get_hds_thresh ok 3 hds.set_hds_disable # SKIP disabling of HDS not supported by the device ok 4 hds.set_hds_enable ok 5 hds.set_hds_thresh_zero ok 6 hds.set_hds_thresh_max ok 7 hds.set_hds_thresh_gt ok 8 hds.set_xdp ok 9 hds.enabled_set_xdp ok 10 hds.ioctl ok 11 hds.ioctl_set_xdp ok 12 hds.ioctl_enabled_set_xdp # Totals: pass:11 fail:0 xfail:0 xpass:0 skip:1 error:0 and netdevsim: # ./ksft-net-drv/drivers/net/hds.py KTAP version 1 1..12 ok 1 hds.get_hds ok 2 hds.get_hds_thresh ok 3 hds.set_hds_disable ok 4 hds.set_hds_enable ok 5 hds.set_hds_thresh_zero ok 6 hds.set_hds_thresh_max ok 7 hds.set_hds_thresh_gt ok 8 hds.set_xdp ok 9 hds.enabled_set_xdp ok 10 hds.ioctl ok 11 hds.ioctl_set_xdp ok 12 hds.ioctl_enabled_set_xdp # Totals: pass:12 fail:0 xfail:0 xpass:0 skip:0 error:0 Netdevsim needs a sane default for tx/rx ring size. ethtool 6.11 is needed for the --disable-netlink option. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- Since this is targeting net there is no cfg.rpath(), I'll follow up once in net-next. v2: - add the ioctl tests - factor out some common logic CC: shuah(a)kernel.org CC: hawk(a)kernel.org CC: petrm(a)nvidia.com CC: willemb(a)google.com CC: jstancek(a)redhat.com CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/net/lib/Makefile | 3 + drivers/net/netdevsim/ethtool.c | 2 + .../testing/selftests/net/lib/xdp_dummy.bpf.c | 13 ++ tools/testing/selftests/drivers/net/hds.py | 145 +++++++++++++++++- 4 files changed, 160 insertions(+), 3 deletions(-) create mode 100644 tools/testing/selftests/net/lib/xdp_dummy.bpf.c diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile index bc6b6762baf3..c22623b9a2a5 100644 --- a/tools/testing/selftests/net/lib/Makefile +++ b/tools/testing/selftests/net/lib/Makefile @@ -9,7 +9,10 @@ TEST_FILES := ../../../../../Documentation/netlink/specs TEST_FILES += ../../../../net/ynl TEST_GEN_FILES += csum +TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c)) TEST_INCLUDES := $(wildcard py/*.py sh/*.sh) include ../../lib.mk + +include ../bpf.mk diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c index 5c80fbee7913..7ab358616e03 100644 --- a/drivers/net/netdevsim/ethtool.c +++ b/drivers/net/netdevsim/ethtool.c @@ -184,9 +184,11 @@ static const struct ethtool_ops nsim_ethtool_ops = { static void nsim_ethtool_ring_init(struct netdevsim *ns) { + ns->ethtool.ring.rx_pending = 512; ns->ethtool.ring.rx_max_pending = 4096; ns->ethtool.ring.rx_jumbo_max_pending = 4096; ns->ethtool.ring.rx_mini_max_pending = 4096; + ns->ethtool.ring.tx_pending = 512; ns->ethtool.ring.tx_max_pending = 4096; } diff --git a/tools/testing/selftests/net/lib/xdp_dummy.bpf.c b/tools/testing/selftests/net/lib/xdp_dummy.bpf.c new file mode 100644 index 000000000000..d988b2e0cee8 --- /dev/null +++ b/tools/testing/selftests/net/lib/xdp_dummy.bpf.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define KBUILD_MODNAME "xdp_dummy" +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("xdp") +int xdp_dummy_prog(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py index 394971b25c0b..90807b21a6eb 100755 --- a/tools/testing/selftests/drivers/net/hds.py +++ b/tools/testing/selftests/drivers/net/hds.py @@ -2,17 +2,54 @@ # SPDX-License-Identifier: GPL-2.0 import errno +import os from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_raises, KsftSkipEx -from lib.py import EthtoolFamily, NlError +from lib.py import CmdExitFailure, EthtoolFamily, NlError from lib.py import NetDrvEnv +from lib.py import defer, ethtool, ip -def get_hds(cfg, netnl) -> None: + +def _get_hds_mode(cfg, netnl) -> str: try: rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) except NlError as e: raise KsftSkipEx('ring-get not supported by device') if 'tcp-data-split' not in rings: raise KsftSkipEx('tcp-data-split not supported by device') + return rings['tcp-data-split'] + + +def _xdp_onoff(cfg): + test_dir = os.path.dirname(os.path.realpath(__file__)) + prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o" + ip(f"link set dev %s xdp obj %s sec xdp" % + (cfg.ifname, prog)) + ip(f"link set dev %s xdp off" % cfg.ifname) + + +def _ioctl_ringparam_modify(cfg, netnl) -> None: + """ + Helper for performing a hopefully unimportant IOCTL SET. + IOCTL does not support HDS, so it should not affect the HDS config. + """ + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + + if 'tx' not in rings: + raise KsftSkipEx('setting Tx ring size not supported') + + try: + ethtool(f"--disable-netlink -G {cfg.ifname} tx {rings['tx'] // 2}") + except CmdExitFailure as e: + ethtool(f"--disable-netlink -G {cfg.ifname} tx {rings['tx'] * 2}") + defer(ethtool, f"-G {cfg.ifname} tx {rings['tx']}") + + +def get_hds(cfg, netnl) -> None: + _get_hds_mode(cfg, netnl) + def get_hds_thresh(cfg, netnl) -> None: try: @@ -104,6 +141,103 @@ from lib.py import NetDrvEnv netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': hds_gt}) ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + +def set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "auto" / UNKNOWN mode, XDP installation should work. + """ + mode = _get_hds_mode(cfg, netnl) + if mode == 'enabled': + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + _xdp_onoff(cfg) + + +def enabled_set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "enabled" mode, XDP installation should not work. + """ + _get_hds_mode(cfg, netnl) + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'enabled'}) + + defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + with ksft_raises(CmdExitFailure) as e: + _xdp_onoff(cfg) + + +def set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "auto" / UNKNOWN mode, XDP installation should work. + """ + mode = _get_hds_mode(cfg, netnl) + if mode == 'enabled': + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + _xdp_onoff(cfg) + + +def enabled_set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "enabled" mode, XDP installation should not work. + """ + _get_hds_mode(cfg, netnl) # Trigger skip if not supported + + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'enabled'}) + defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + with ksft_raises(CmdExitFailure) as e: + _xdp_onoff(cfg) + + +def ioctl(cfg, netnl) -> None: + mode1 = _get_hds_mode(cfg, netnl) + _ioctl_ringparam_modify(cfg, netnl) + mode2 = _get_hds_mode(cfg, netnl) + + ksft_eq(mode1, mode2) + + +def ioctl_set_xdp(cfg, netnl) -> None: + """ + Like set_xdp(), but we perturb the settings via the legacy ioctl. + """ + mode = _get_hds_mode(cfg, netnl) + if mode == 'enabled': + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + _ioctl_ringparam_modify(cfg, netnl) + + _xdp_onoff(cfg) + + +def ioctl_enabled_set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "enabled" mode, XDP installation should not work. + """ + _get_hds_mode(cfg, netnl) # Trigger skip if not supported + + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'enabled'}) + defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + with ksft_raises(CmdExitFailure) as e: + _xdp_onoff(cfg) + + def main() -> None: with NetDrvEnv(__file__, queue_count=3) as cfg: ksft_run([get_hds, @@ -112,7 +246,12 @@ from lib.py import NetDrvEnv set_hds_enable, set_hds_thresh_zero, set_hds_thresh_max, - set_hds_thresh_gt], + set_hds_thresh_gt, + set_xdp, + enabled_set_xdp, + ioctl, + ioctl_set_xdp, + ioctl_enabled_set_xdp], args=(cfg, EthtoolFamily())) ksft_exit() -- 2.48.1

4 months, 2 weeks

3
2
0 0

[PATCH] selftests/mount: Close 'fd' when write fails

by ritvikfoss＠gmail.com

From: Ritvik Gupta <ritvikfoss(a)gmail.com> 1. Close the file descriptor when write fails. 2. Introduce 'close_or_die' helper function to reduce repetition. Signed-off-by: Ritvik Gupta <ritvikfoss(a)gmail.com> --- .../selftests/mount/unprivileged-remount-test.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c index d2917054fe3a..3dd9df58725b 100644 --- a/tools/testing/selftests/mount/unprivileged-remount-test.c +++ b/tools/testing/selftests/mount/unprivileged-remount-test.c @@ -54,6 +54,13 @@ static void die(char *fmt, ...) exit(EXIT_FAILURE); } +static void close_or_die(char *filename, int fd) { + if (close(fd) != 0) { + die("close of %s failed: %s\n", + filename, strerror(errno)); + } +} + static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap) { char buf[4096]; @@ -79,6 +86,7 @@ static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list } written = write(fd, buf, buf_len); if (written != buf_len) { + close_or_die(filename, fd); if (written >= 0) { die("short write to %s\n", filename); } else { @@ -86,10 +94,7 @@ static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list filename, strerror(errno)); } } - if (close(fd) != 0) { - die("close of %s failed: %s\n", - filename, strerror(errno)); - } + close_or_die(filename, fd); } static void maybe_write_file(char *filename, char *fmt, ...) -- 2.48.1

4 months, 2 weeks

3
5
0 0

[PATCH] selftets: lib: remove reference to prime_numbers

by Tamir Duberstein

Remove a leftover shell script reference from commit 313b38a6ecb4 ("lib/prime_numbers: convert self-test to KUnit"). Reported-by: kernel test robot <oliver.sang(a)intel.com> Closes: https://lore.kernel.org/oe-lkp/202502171110.708d965a-lkp@intel.com Fixes: 313b38a6ecb4 ("lib/prime_numbers: convert self-test to KUnit") Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- tools/testing/selftests/lib/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/lib/Makefile b/tools/testing/selftests/lib/Makefile index c52fe3ad8e98..66dcbe2e39fa 100644 --- a/tools/testing/selftests/lib/Makefile +++ b/tools/testing/selftests/lib/Makefile @@ -4,5 +4,5 @@ # No binaries, but make sure arg-less "make" doesn't trigger "run_tests" all: -TEST_PROGS := printf.sh bitmap.sh prime_numbers.sh scanf.sh +TEST_PROGS := printf.sh bitmap.sh scanf.sh include ../lib.mk --- base-commit: 0ae0fa3bf0b44c8611d114a9f69985bf451010c3 change-id: 20250217-fix-prime-numbers-f5202155b226 Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

4 months, 2 weeks

2
3
0 0

[PATCH] selftests/mount: Explicitly define buffer size

by ritvikfoss＠gmail.com

From: Ritvik Gupta <ritvikfoss(a)gmail.com> Define macro ('MAX_BUF_SIZE') for buffer size instead of hardcoded value '4096', to improve readability. Signed-off-by: Ritvik Gupta <ritvikfoss(a)gmail.com> --- tools/testing/selftests/mount/unprivileged-remount-test.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c index d2917054fe3a..67a550b7c69b 100644 --- a/tools/testing/selftests/mount/unprivileged-remount-test.c +++ b/tools/testing/selftests/mount/unprivileged-remount-test.c @@ -45,6 +45,8 @@ # define MS_STRICTATIME (1 << 24) #endif +#define MAX_BUF_SIZE 4096 + static void die(char *fmt, ...) { va_list ap; @@ -56,7 +58,7 @@ static void die(char *fmt, ...) static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap) { - char buf[4096]; + char buf[MAX_BUF_SIZE]; int fd; ssize_t written; int buf_len; -- 2.48.1

4 months, 2 weeks

3
2
0 0

[PATCH net-next v4 0/9] Device memory TCP TX

by Mina Almasry

v4: https://lore.kernel.org/netdev/20250203223916.1064540-1-almasrymina@google.… === v4 mainly addresses the critical driver support issue surfaced in v3 by Paolo and Stan. Drivers aiming to support netmem_tx should make sure not to pass the netmem dma-addrs to the dma-mapping APIs, as these dma-addrs may come from dma-bufs. Additionally other feedback from v3 is addressed. Major changes: - Add helpers to handle netmem dma-addrs. Add GVE support for netmem_tx. - Fix binding->tx_vec not being freed on error paths during the tx binding. - Add a minimal devmem_tx test to devmem.py. - Clean up everything obsolete from the cover letter (Paolo). v3: https://patchwork.kernel.org/project/netdevbpf/list/?series=929401&state=* === Address minor comments from RFCv2 and fix a few build warnings and ynl-regen issues. No major changes. RFC v2: https://patchwork.kernel.org/project/netdevbpf/list/?series=920056&state=* ======= RFC v2 addresses much of the feedback from RFC v1. I plan on sending something close to this as net-next reopens, sending it slightly early to get feedback if any. Major changes: -------------- - much improved UAPI as suggested by Stan. We now interpret the iov_base of the passed in iov from userspace as the offset into the dmabuf to send from. This removes the need to set iov.iov_base = NULL which may be confusing to users, and enables us to send multiple iovs in the same sendmsg() call. ncdevmem and the docs show a sample use of that. - Removed the duplicate dmabuf iov_iter in binding->iov_iter. I think this is good improvment as it was confusing to keep track of 2 iterators for the same sendmsg, and mistracking both iterators caused a couple of bugs reported in the last iteration that are now resolved with this streamlining. - Improved test coverage in ncdevmem. Now multiple sendmsg() are tested, and sending multiple iovs in the same sendmsg() is tested. - Fixed issue where dmabuf unmapping was happening in invalid context (Stan). ==================================================================== The TX path had been dropped from the Device Memory TCP patch series post RFCv1 [1], to make that series slightly easier to review. This series rebases the implementation of the TX path on top of the net_iov/netmem framework agreed upon and merged. The motivation for the feature is thoroughly described in the docs & cover letter of the original proposal, so I don't repeat the lengthy descriptions here, but they are available in [1]. Full outline on usage of the TX path is detailed in the documentation included with this series. Test example is available via the kselftest included in the series as well. The series is relatively small, as the TX path for this feature largely piggybacks on the existing MSG_ZEROCOPY implementation. Patch Overview: --------------- 1. Documentation & tests to give high level overview of the feature being added. 1. Add netmem refcounting needed for the TX path. 2. Devmem TX netlink API. 3. Devmem TX net stack implementation. 4. Make dma-buf unbinding scheduled work to handle TX cases where it gets freed from contexts where we can't sleep. 5. Add devmem TX documentation. 6. Add scaffolding enabling driver support for netmem_tx. Add helpers, driver feature flag, and docs to enable drivers to declare netmem_tx support. 7. Guard netmem_tx against being enabled against drivers that don't support it. 8. Add devmem_tx selftests. Add TX path to ncdevmem and add a test to devmem.py. Testing: -------- Testing is very similar to devmem TCP RX path. The ncdevmem test used for the RX path is now augemented with client functionality to test TX path. * Test Setup: Kernel: net-next with this RFC and memory provider API cherry-picked locally. Hardware: Google Cloud A3 VMs. NIC: GVE with header split & RSS & flow steering support. Performance results are not included with this version, unfortunately. I'm having issues running the dma-buf exporter driver against the upstream kernel on my test setup. The issues are specific to that dma-buf exporter and do not affect this patch series. I plan to follow up this series with perf fixes if the tests point to issues once they're up and running. Special thanks to Stan who took a stab at rebasing the TX implementation on top of the netmem/net_iov framework merged. Parts of his proposal [2] that are reused as-is are forked off into their own patches to give full credit. [1] https://lore.kernel.org/netdev/20240909054318.1809580-1-almasrymina@google.… [2] https://lore.kernel.org/netdev/20240913150913.1280238-2-sdf@fomichev.me/T/#… Cc: sdf(a)fomichev.me Cc: asml.silence(a)gmail.com Cc: dw(a)davidwei.uk Cc: Jamal Hadi Salim <jhs(a)mojatatu.com> Cc: Victor Nogueira <victor(a)mojatatu.com> Cc: Pedro Tammela <pctammela(a)mojatatu.com> Cc: Samiullah Khawaja <skhawaja(a)google.com> Mina Almasry (8): net: add get_netmem/put_netmem support net: devmem: Implement TX path net: devmem: make dmabuf unbinding scheduled work net: add devmem TCP TX documentation net: enable driver support for netmem TX gve: add netmem TX support to GVE DQO-RDA mode net: check for driver support in netmem TX selftests: ncdevmem: Implement devmem TCP TX Stanislav Fomichev (1): net: devmem: TCP tx netlink api Documentation/netlink/specs/netdev.yaml | 12 + Documentation/networking/devmem.rst | 150 ++++++++- .../networking/net_cachelines/net_device.rst | 1 + Documentation/networking/netdev-features.rst | 5 + Documentation/networking/netmem.rst | 14 +- drivers/net/ethernet/google/gve/gve_main.c | 4 + drivers/net/ethernet/google/gve/gve_tx_dqo.c | 8 +- include/linux/netdevice.h | 2 + include/linux/skbuff.h | 17 +- include/linux/skbuff_ref.h | 4 +- include/net/netmem.h | 23 ++ include/net/sock.h | 1 + include/uapi/linux/netdev.h | 1 + net/core/datagram.c | 48 ++- net/core/dev.c | 3 + net/core/devmem.c | 114 ++++++- net/core/devmem.h | 69 +++- net/core/netdev-genl-gen.c | 13 + net/core/netdev-genl-gen.h | 1 + net/core/netdev-genl.c | 73 ++++- net/core/skbuff.c | 48 ++- net/core/sock.c | 6 + net/ipv4/ip_output.c | 3 +- net/ipv4/tcp.c | 46 ++- net/ipv6/ip6_output.c | 3 +- net/vmw_vsock/virtio_transport_common.c | 5 +- tools/include/uapi/linux/netdev.h | 1 + .../selftests/drivers/net/hw/devmem.py | 28 +- .../selftests/drivers/net/hw/ncdevmem.c | 300 +++++++++++++++++- 29 files changed, 931 insertions(+), 72 deletions(-) -- 2.48.1.601.g30ceb7b040-goog

4 months, 2 weeks

3
23
0 0

[PATCH net-next] selftests: fib_nexthops: do not mark skipped tests as failed

by Hangbin Liu

The current test marks all unexpected return values as failed and sets ret to 1. If a test is skipped, the entire test also returns 1, incorrectly indicating failure. To fix this, add a skipped variable and set ret to 4 if it was previously 0. Otherwise, keep ret set to 1. Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> --- tools/testing/selftests/net/fib_nexthops.sh | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 77c83d9508d3..6a58e23e1588 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -76,11 +76,13 @@ log_test() printf "TEST: %-60s [ OK ]\n" "${msg}" nsuccess=$((nsuccess+1)) else - ret=1 - nfail=$((nfail+1)) if [[ $rc -eq $ksft_skip ]]; then + [[ $ret -eq 0 ]] && ret=$ksft_skip + nskip=$((nskip+1)) printf "TEST: %-60s [SKIP]\n" "${msg}" else + ret=1 + nfail=$((nfail+1)) printf "TEST: %-60s [FAIL]\n" "${msg}" fi @@ -2528,6 +2530,7 @@ done if [ "$TESTS" != "none" ]; then printf "\nTests passed: %3d\n" ${nsuccess} printf "Tests failed: %3d\n" ${nfail} + printf "Tests skipped: %2d\n" ${nskip} fi exit $ret -- 2.46.0

4 months, 2 weeks

2
1
0 0

[PATCH] kunit: tool: Implement listing of available architectures

by Thomas Weißschuh

To implement custom scripting around kunit.py it is useful to get a list of available architectures. While it is possible to manually inspect tools/testing/kunit/qemu_configs/, this is annoying to implement and introduces a dependency on a kunit.py implementation detail. Introduce 'kunit.py run --arch help' which lists all known architectures in an easy to parse list. This is equivalent on how QEMU implements listing of possible argument values. Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- Documentation/dev-tools/kunit/run_wrapper.rst | 2 ++ tools/testing/kunit/kunit_kernel.py | 8 ++++++++ 2 files changed, 10 insertions(+) diff --git a/Documentation/dev-tools/kunit/run_wrapper.rst b/Documentation/dev-tools/kunit/run_wrapper.rst index 19ddf5e07013314c608b570e297a8ff79a8efe7f..6697c71ee8ca020b8ac7e91b46e29ab082d9dea0 100644 --- a/Documentation/dev-tools/kunit/run_wrapper.rst +++ b/Documentation/dev-tools/kunit/run_wrapper.rst @@ -182,6 +182,8 @@ via UML. To run tests on qemu, by default it requires two flags: is ignored), the tests will run via UML. Non-UML architectures, for example: i386, x86_64, arm and so on; run on qemu. + ``--arch help`` lists all valid ``--arch`` values. + - ``--cross_compile``: Specifies the Kbuild toolchain. It passes the same argument as passed to the ``CROSS_COMPILE`` variable used by Kbuild. As a reminder, this will be the prefix for the toolchain diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index d30f90eae9a4237e85910fd36f7f1c731d952319..e04195b135edc8f1aabe21d094b276e47c4f6848 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -14,6 +14,7 @@ import os import shlex import shutil import signal +import sys import threading from typing import Iterator, List, Optional, Tuple from types import FrameType @@ -201,6 +202,13 @@ def _default_qemu_config_path(arch: str) -> str: return config_path options = [f[:-3] for f in os.listdir(QEMU_CONFIGS_DIR) if f.endswith('.py')] + + if arch == 'help': + print('um') + for option in options: + print(option) + sys.exit() + raise ConfigError(arch + ' is not a valid arch, options are ' + str(sorted(options))) def _get_qemu_ops(config_path: str, --- base-commit: 2014c95afecee3e76ca4a56956a936e23283f05b change-id: 20250220-kunit-list-552a8cdc011e Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

4 months, 2 weeks

2
1
0 0

[PATCH net-next v10 00/13] net: Improve netns handling in rtnetlink

by Xiao Liang

This patch series includes some netns-related improvements and fixes for rtnetlink, to make link creation more intuitive: 1) Creating link in another net namespace doesn't conflict with link names in current one. 2) Refector rtnetlink link creation. Create link in target namespace directly. So that # ip link add netns ns1 link-netns ns2 tun0 type gre ... will create tun0 in ns1, rather than create it in ns2 and move to ns1. And don't conflict with another interface named "tun0" in current netns. Patch 01 avoids link name conflict in different netns. To achieve 2), there're mainly 3 steps: - Patch 02 packs newlink() parameters into a struct, including the original "src_net" along with more netns context. No semantic changes are introduced. - Patch 03 ~ 09 converts device drivers to use the explicit netns extracted from params. - Patch 10 ~ 11 removes the old netns parameter, and converts rtnetlink to create device in target netns directly. Patch 12 ~ 13 adds some tests for link name and link netns. --- BTW please note there're some issues found in current code: - In amt_newlink() drivers/net/amt.c: amt->net = net; ... amt->stream_dev = dev_get_by_index(net, ... Uses net, but amt_lookup_upper_dev() only searches in dev_net. So the AMT device may not be properly deleted if it's in a different netns from lower dev. - In lowpan_newlink() in net/ieee802154/6lowpan/core.c: wdev = dev_get_by_index(dev_net(ldev), nla_get_u32(tb[IFLA_LINK])); Looks for IFLA_LINK in dev_net, but in theory the ifindex is defined in link netns. And thanks to Kuniyuki for fixing related issues in gtp and pfcp: https://lore.kernel.org/netdev/20250110014754.33847-1-kuniyu@amazon.com/ --- v10: - Move link/peer net helper functions to from patch 02 to 03. - Remove redundant tunnel->net assignment for IPv4 tunnels (patch 05). - Initialize tunnel->net before calling register_netdevice() for IPv6 tunnels (patch 07). - Coding style fixes. v9: link: https://lore.kernel.org/all/20250210133002.883422-1-shaw.leon@gmail.com/ - Change the prototype of macvlan_common_newlink(). - Minor fixes of coding style and local variables. v8: link: https://lore.kernel.org/all/20250113143719.7948-1-shaw.leon@gmail.com/ - Move dev and ext_ack out from param struct. - Validate link_net and dev_net are identical for 6lowpan. v7: link: https://lore.kernel.org/all/20250104125732.17335-1-shaw.leon@gmail.com/ - Add selftest kconfig. - Remove a duplicated test of ip6gre. v6: link: https://lore.kernel.org/all/20241218130909.2173-1-shaw.leon@gmail.com/ - Split prototype, driver and rtnetlink changes. - Add more tests for link netns. - Fix IPv6 tunnel net overwriten in ndo_init(). - Reorder variable declarations. - Exclude a ip_tunnel-specific patch. v5: link: https://lore.kernel.org/all/20241209140151.231257-1-shaw.leon@gmail.com/ - Fix function doc in batman-adv. - Include peer_net in rtnl newlink parameters. v4: link: https://lore.kernel.org/all/20241118143244.1773-1-shaw.leon@gmail.com/ - Pack newlink() parameters to a single struct. - Use ynl async_msg_queue.empty() in selftest. v3: link: https://lore.kernel.org/all/20241113125715.150201-1-shaw.leon@gmail.com/ - Drop "netns_atomic" flag and module parameter. Add netns parameter to newlink() instead, and convert drivers accordingly. - Move python NetNSEnter helper to net selftest lib. v2: link: https://lore.kernel.org/all/20241107133004.7469-1-shaw.leon@gmail.com/ - Check NLM_F_EXCL to ensure only link creation is affected. - Add self tests for link name/ifindex conflict and notifications in different netns. - Changes in dummy driver and ynl in order to add the test case. v1: link: https://lore.kernel.org/all/20241023023146.372653-1-shaw.leon@gmail.com/ Xiao Liang (13): rtnetlink: Lookup device in target netns when creating link rtnetlink: Pack newlink() params into struct net: Use link/peer netns in newlink() of rtnl_link_ops ieee802154: 6lowpan: Validate link netns in newlink() of rtnl_link_ops net: ip_tunnel: Don't set tunnel->net in ip_tunnel_init() net: ip_tunnel: Use link netns in newlink() of rtnl_link_ops net: ipv6: Init tunnel link-netns before registering dev net: ipv6: Use link netns in newlink() of rtnl_link_ops net: xfrm: Use link netns in newlink() of rtnl_link_ops rtnetlink: Remove "net" from newlink params rtnetlink: Create link directly in target net namespace selftests: net: Add python context manager for netns entering selftests: net: Add test cases for link and peer netns drivers/infiniband/ulp/ipoib/ipoib_netlink.c | 9 +- drivers/net/amt.c | 11 +- drivers/net/bareudp.c | 9 +- drivers/net/bonding/bond_netlink.c | 6 +- drivers/net/can/dev/netlink.c | 4 +- drivers/net/can/vxcan.c | 7 +- .../ethernet/qualcomm/rmnet/rmnet_config.c | 9 +- drivers/net/geneve.c | 9 +- drivers/net/gtp.c | 10 +- drivers/net/ipvlan/ipvlan.h | 3 +- drivers/net/ipvlan/ipvlan_main.c | 8 +- drivers/net/ipvlan/ipvtap.c | 6 +- drivers/net/macsec.c | 9 +- drivers/net/macvlan.c | 21 +-- drivers/net/macvtap.c | 6 +- drivers/net/netkit.c | 14 +- drivers/net/pfcp.c | 9 +- drivers/net/ppp/ppp_generic.c | 9 +- drivers/net/team/team_core.c | 6 +- drivers/net/veth.c | 7 +- drivers/net/vrf.c | 5 +- drivers/net/vxlan/vxlan_core.c | 9 +- drivers/net/wireguard/device.c | 7 +- drivers/net/wireless/virtual/virt_wifi.c | 8 +- drivers/net/wwan/wwan_core.c | 16 +- include/linux/if_macvlan.h | 6 +- include/net/ip_tunnels.h | 5 +- include/net/rtnetlink.h | 40 ++++- net/8021q/vlan_netlink.c | 9 +- net/batman-adv/soft-interface.c | 9 +- net/bridge/br_netlink.c | 6 +- net/caif/chnl_net.c | 5 +- net/core/rtnetlink.c | 34 +++-- net/hsr/hsr_netlink.c | 12 +- net/ieee802154/6lowpan/core.c | 7 +- net/ipv4/ip_gre.c | 22 ++- net/ipv4/ip_tunnel.c | 7 +- net/ipv4/ip_vti.c | 9 +- net/ipv4/ipip.c | 9 +- net/ipv6/ip6_gre.c | 26 ++-- net/ipv6/ip6_tunnel.c | 18 ++- net/ipv6/ip6_vti.c | 14 +- net/ipv6/sit.c | 20 ++- net/xfrm/xfrm_interface_core.c | 15 +- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/config | 5 + .../testing/selftests/net/lib/py/__init__.py | 2 +- tools/testing/selftests/net/lib/py/netns.py | 18 +++ tools/testing/selftests/net/link_netns.py | 141 ++++++++++++++++++ tools/testing/selftests/net/netns-name.sh | 10 ++ 50 files changed, 486 insertions(+), 181 deletions(-) create mode 100755 tools/testing/selftests/net/link_netns.py -- 2.48.1

4 months, 2 weeks

4
24
0 0

[PATCH v2] ww_mutex: convert self-test to KUnit

by Tamir Duberstein

Convert this unit test to a KUnit test. This allows the test to benefit from the KUnit tooling. Note that care is taken to avoid test-ending assertions in worker threads, which is unsafe in KUnit (and wasn't done before this change either). Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- I tested this using: $ tools/testing/kunit/kunit.py run --arch arm64 --make_options LLVM=1 ww_mutex ; [12:48:16] ================== ww_mutex (5 subtests) =================== ; [12:48:16] ======================= test_mutex ======================== ; [12:48:16] [PASSED] flags=0 ; [12:48:16] [PASSED] flags=1 ; [12:48:16] [PASSED] flags=2 ; [12:48:16] [PASSED] flags=3 ; [12:48:16] [PASSED] flags=4 ; [12:48:17] [PASSED] flags=5 ; [12:48:17] [PASSED] flags=6 ; [12:48:17] [PASSED] flags=7 ; [12:48:17] =================== [PASSED] test_mutex ==================== ; [12:48:17] ========================= test_aa ========================= ; [12:48:17] [PASSED] lock ; [12:48:17] [PASSED] trylock ; [12:48:17] ===================== [PASSED] test_aa ===================== ; [12:48:17] ======================== test_abba ======================== ; [12:48:17] [PASSED] trylock=0,resolve=0 ; [12:48:17] [PASSED] trylock=1,resolve=1 ; [12:48:17] [PASSED] trylock=0,resolve=0 ; [12:48:17] [PASSED] trylock=1,resolve=1 ; [12:48:17] ==================== [PASSED] test_abba ==================== ; [12:48:17] ======================= test_cycle ======================== ; [12:48:17] [PASSED] nthreads=2 ; [12:48:17] =================== [PASSED] test_cycle ==================== ; [12:48:21] ========================= stress ========================== ; [12:48:21] [PASSED] nlocks=16,nthreads_per_cpu=2,flags=1 ; [12:48:23] [PASSED] nlocks=16,nthreads_per_cpu=2,flags=2 ; [12:48:23] [PASSED] nlocks=2046,nthreads_per_cpu=3,flags=7 ; [12:48:23] ===================== [PASSED] stress ====================== ; [12:48:23] ==================== [PASSED] ww_mutex ===================== ; [12:48:23] ============================================================ ; [12:48:23] Testing complete. Ran 18 tests: passed: 18 --- Changes in v2: - Avoid KUNIT_ASSERT_* in non-main thread. (David Gow) - Include rationale and details in the commit message. (Boqun Feng) - Introduce test_abba_param to avoid odd-looking bit shifting. (Dan Carpenter) - Rebase on linux-next. - Move the test to tests/ per KUnit style guide. - Link to v1: https://lore.kernel.org/r/20250210-ww_mutex-kunit-convert-v1-1-972f0201f71e… --- kernel/locking/Makefile | 3 +- kernel/locking/tests/Makefile | 3 + .../{test-ww_mutex.c => tests/ww_mutex_kunit.c} | 319 +++++++++++---------- lib/Kconfig.debug | 12 +- tools/testing/selftests/locking/ww_mutex.sh | 19 -- 5 files changed, 176 insertions(+), 180 deletions(-) diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 0db4093d17b8..b5fa68d18823 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -30,5 +30,6 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o -obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o obj-$(CONFIG_LOCK_EVENT_COUNTS) += lock_events.o + +obj-y += tests/ diff --git a/kernel/locking/tests/Makefile b/kernel/locking/tests/Makefile new file mode 100644 index 000000000000..8ddde822c793 --- /dev/null +++ b/kernel/locking/tests/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-$(CONFIG_WW_MUTEX_KUNIT_TEST) += ww_mutex_kunit.o diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/tests/ww_mutex_kunit.c similarity index 66% rename from kernel/locking/test-ww_mutex.c rename to kernel/locking/tests/ww_mutex_kunit.c index bcb1b9fea588..a8d412231735 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/tests/ww_mutex_kunit.c @@ -3,10 +3,10 @@ * Module-based API test facility for ww_mutexes */ -#include <linux/kernel.h> - +#include <kunit/test.h> #include <linux/completion.h> #include <linux/delay.h> +#include <linux/kernel.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/prandom.h> @@ -54,12 +54,39 @@ static void test_mutex_work(struct work_struct *work) ww_mutex_unlock(&mtx->mutex); } -static int __test_mutex(unsigned int flags) +static const unsigned int *gen_range( + unsigned int *storage, + const unsigned int min, + const unsigned int max, + const int *prev) +{ + if (prev != NULL) { + if (*prev >= max) + return NULL; + *storage = *prev + 1; + } else { + *storage = min; + } + return storage; +} + +static const void *test_mutex_gen_params(const void *prev, char *desc) +{ + static unsigned int storage; + const unsigned int *next = gen_range(&storage, 0, __TEST_MTX_LAST - 1, prev); + + if (next != NULL) + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "flags=%x", *next); + return next; +} + +static void test_mutex(struct kunit *test) { #define TIMEOUT (HZ / 16) + const unsigned int *param = test->param_value; + const unsigned int flags = *param; struct test_mutex mtx; struct ww_acquire_ctx ctx; - int ret; ww_mutex_init(&mtx.mutex, &ww_class); if (flags & TEST_MTX_CTX) @@ -79,53 +106,42 @@ static int __test_mutex(unsigned int flags) if (flags & TEST_MTX_SPIN) { unsigned long timeout = jiffies + TIMEOUT; - ret = 0; do { if (completion_done(&mtx.done)) { - ret = -EINVAL; + KUNIT_FAIL(test, "mutual exclusion failure"); break; } cond_resched(); } while (time_before(jiffies, timeout)); } else { - ret = wait_for_completion_timeout(&mtx.done, TIMEOUT); + KUNIT_EXPECT_EQ(test, wait_for_completion_timeout(&mtx.done, TIMEOUT), 0); } ww_mutex_unlock(&mtx.mutex); if (flags & TEST_MTX_CTX) ww_acquire_fini(&ctx); - if (ret) { - pr_err("%s(flags=%x): mutual exclusion failure\n", - __func__, flags); - ret = -EINVAL; - } - flush_work(&mtx.work); destroy_work_on_stack(&mtx.work); - return ret; #undef TIMEOUT } -static int test_mutex(void) +static const void *test_aa_gen_params(const void *prev, char *desc) { - int ret; - int i; - - for (i = 0; i < __TEST_MTX_LAST; i++) { - ret = __test_mutex(i); - if (ret) - return ret; - } + static unsigned int storage; + const unsigned int *next = gen_range(&storage, 0, 1, prev); - return 0; + if (next != NULL) + snprintf(desc, KUNIT_PARAM_DESC_SIZE, *next ? "trylock" : "lock"); + return next; } -static int test_aa(bool trylock) +static void test_aa(struct kunit *test) { + const unsigned int *param = test->param_value; + const bool trylock = *param; struct ww_mutex mutex; struct ww_acquire_ctx ctx; int ret; - const char *from = trylock ? "trylock" : "lock"; ww_mutex_init(&mutex, &ww_class); ww_acquire_init(&ctx, &ww_class); @@ -133,46 +149,42 @@ static int test_aa(bool trylock) if (!trylock) { ret = ww_mutex_lock(&mutex, &ctx); if (ret) { - pr_err("%s: initial lock failed!\n", __func__); + KUNIT_FAIL(test, "initial lock failed, ret=%d", ret); goto out; } } else { ret = !ww_mutex_trylock(&mutex, &ctx); if (ret) { - pr_err("%s: initial trylock failed!\n", __func__); + KUNIT_FAIL(test, "initial trylock failed, ret=%d", ret); goto out; } } - if (ww_mutex_trylock(&mutex, NULL)) { - pr_err("%s: trylocked itself without context from %s!\n", __func__, from); + ret = ww_mutex_trylock(&mutex, NULL); + if (ret) { + KUNIT_FAIL(test, "trylocked itself without context, ret=%d", ret); ww_mutex_unlock(&mutex); - ret = -EINVAL; goto out; } - if (ww_mutex_trylock(&mutex, &ctx)) { - pr_err("%s: trylocked itself with context from %s!\n", __func__, from); + ret = ww_mutex_trylock(&mutex, &ctx); + if (ret) { + KUNIT_FAIL(test, "trylocked itself with context, ret=%d", ret); ww_mutex_unlock(&mutex); - ret = -EINVAL; goto out; } ret = ww_mutex_lock(&mutex, &ctx); if (ret != -EALREADY) { - pr_err("%s: missed deadlock for recursing, ret=%d from %s\n", - __func__, ret, from); + KUNIT_FAIL(test, "missed deadlock for recursing, ret=%d", ret); if (!ret) ww_mutex_unlock(&mutex); - ret = -EINVAL; goto out; } ww_mutex_unlock(&mutex); - ret = 0; out: ww_acquire_fini(&ctx); - return ret; } struct test_abba { @@ -217,11 +229,36 @@ static void test_abba_work(struct work_struct *work) abba->result = err; } -static int test_abba(bool trylock, bool resolve) +union test_abba_param { + unsigned int value; + struct { + unsigned int trylock : 1; + unsigned int resolve : 1; + }; +}; + +static const void *test_abba_gen_params(const void *prev, char *desc) { + static unsigned int storage; + const unsigned int *next = gen_range(&storage, 0b00, 0b11, prev); + + if (next != NULL) { + const union test_abba_param param = { .value = *next }; + + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "trylock=%d,resolve=%d", + param.trylock, param.resolve); + } + return next; +} + +static void test_abba(struct kunit *test) +{ + const union test_abba_param *param = test->param_value; + const bool trylock = param->trylock; + const bool resolve = param->resolve; struct test_abba abba; struct ww_acquire_ctx ctx; - int err, ret; + int err; ww_mutex_init(&abba.a_mutex, &ww_class); ww_mutex_init(&abba.b_mutex, &ww_class); @@ -259,21 +296,17 @@ static int test_abba(bool trylock, bool resolve) flush_work(&abba.work); destroy_work_on_stack(&abba.work); - ret = 0; if (resolve) { if (err || abba.result) { - pr_err("%s: failed to resolve ABBA deadlock, A err=%d, B err=%d\n", - __func__, err, abba.result); - ret = -EINVAL; + KUNIT_FAIL(test, "failed to resolve ABBA deadlock, A err=%d, B err=%d", + err, abba.result); } } else { if (err != -EDEADLK && abba.result != -EDEADLK) { - pr_err("%s: missed ABBA deadlock, A err=%d, B err=%d\n", - __func__, err, abba.result); - ret = -EINVAL; + KUNIT_FAIL(test, "missed ABBA deadlock, A err=%d, B err=%d", + err, abba.result); } } - return ret; } struct test_cycle { @@ -314,15 +347,25 @@ static void test_cycle_work(struct work_struct *work) cycle->result = err ?: erra; } -static int __test_cycle(unsigned int nthreads) +static const void *test_cycle_gen_params(const void *prev, char *desc) { + static unsigned int storage; + const unsigned int *next = gen_range(&storage, 2, num_online_cpus(), prev); + + if (next != NULL) + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "nthreads=%d", *next); + return next; +} + +static void test_cycle(struct kunit *test) +{ + const unsigned int *param = test->param_value; + const unsigned int nthreads = *param; struct test_cycle *cycles; unsigned int n, last = nthreads - 1; - int ret; - cycles = kmalloc_array(nthreads, sizeof(*cycles), GFP_KERNEL); - if (!cycles) - return -ENOMEM; + cycles = kunit_kmalloc_array(test, nthreads, sizeof(*cycles), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, cycles); for (n = 0; n < nthreads; n++) { struct test_cycle *cycle = &cycles[n]; @@ -348,41 +391,24 @@ static int __test_cycle(unsigned int nthreads) flush_workqueue(wq); - ret = 0; for (n = 0; n < nthreads; n++) { struct test_cycle *cycle = &cycles[n]; if (!cycle->result) continue; - pr_err("cyclic deadlock not resolved, ret[%d/%d] = %d\n", - n, nthreads, cycle->result); - ret = -EINVAL; + KUNIT_FAIL(test, "cyclic deadlock not resolved, ret[%d/%d] = %d", + n, nthreads, cycle->result); break; } for (n = 0; n < nthreads; n++) ww_mutex_destroy(&cycles[n].a_mutex); - kfree(cycles); - return ret; -} - -static int test_cycle(unsigned int ncpus) -{ - unsigned int n; - int ret; - - for (n = 2; n <= ncpus + 1; n++) { - ret = __test_cycle(n); - if (ret) - return ret; - } - - return 0; } struct stress { struct work_struct work; + struct kunit *test; struct ww_mutex *locks; unsigned long timeout; int nlocks; @@ -401,12 +427,12 @@ static inline u32 prandom_u32_below(u32 ceil) return ret; } -static int *get_random_order(int count) +static int *get_random_order(struct kunit *test, int count) { int *order; int n, r; - order = kmalloc_array(count, sizeof(*order), GFP_KERNEL); + order = kunit_kmalloc_array(test, count, sizeof(*order), GFP_KERNEL); if (!order) return order; @@ -435,7 +461,8 @@ static void stress_inorder_work(struct work_struct *work) struct ww_acquire_ctx ctx; int *order; - order = get_random_order(nlocks); + order = get_random_order(stress->test, nlocks); + KUNIT_EXPECT_NOT_NULL(stress->test, order); if (!order) return; @@ -472,13 +499,10 @@ static void stress_inorder_work(struct work_struct *work) ww_acquire_fini(&ctx); if (err) { - pr_err_once("stress (%s) failed with %d\n", - __func__, err); + KUNIT_FAIL(stress->test, "lock[%d] failed, err=%d", n, err); break; } } while (!time_after(jiffies, stress->timeout)); - - kfree(order); } struct reorder_lock { @@ -495,19 +519,19 @@ static void stress_reorder_work(struct work_struct *work) int *order; int n, err; - order = get_random_order(stress->nlocks); + order = get_random_order(stress->test, stress->nlocks); + KUNIT_EXPECT_NOT_NULL(stress->test, order); if (!order) return; for (n = 0; n < stress->nlocks; n++) { - ll = kmalloc(sizeof(*ll), GFP_KERNEL); + ll = kunit_kmalloc(stress->test, sizeof(*ll), GFP_KERNEL); + KUNIT_EXPECT_NOT_NULL(stress->test, ll); if (!ll) - goto out; - + return; ll->lock = &stress->locks[order[n]]; list_add(&ll->link, &locks); } - kfree(order); order = NULL; do { @@ -523,8 +547,7 @@ static void stress_reorder_work(struct work_struct *work) ww_mutex_unlock(ln->lock); if (err != -EDEADLK) { - pr_err_once("stress (%s) failed with %d\n", - __func__, err); + KUNIT_FAIL(stress->test, "lock failed, err=%d", err); break; } @@ -538,11 +561,6 @@ static void stress_reorder_work(struct work_struct *work) ww_acquire_fini(&ctx); } while (!time_after(jiffies, stress->timeout)); - -out: - list_for_each_entry_safe(ll, ln, &locks, link) - kfree(ll); - kfree(order); } static void stress_one_work(struct work_struct *work) @@ -558,8 +576,7 @@ static void stress_one_work(struct work_struct *work) dummy_load(stress); ww_mutex_unlock(lock); } else { - pr_err_once("stress (%s) failed with %d\n", - __func__, err); + KUNIT_FAIL(stress->test, "lock failed, err=%d", err); break; } } while (!time_after(jiffies, stress->timeout)); @@ -570,22 +587,41 @@ static void stress_one_work(struct work_struct *work) #define STRESS_ONE BIT(2) #define STRESS_ALL (STRESS_INORDER | STRESS_REORDER | STRESS_ONE) -static int stress(int nlocks, int nthreads, unsigned int flags) +struct stress_case { + int nlocks; + int nthreads_per_cpu; + unsigned int flags; +}; + +static const struct stress_case stress_cases[] = { + { 16, 2, STRESS_INORDER }, + { 16, 2, STRESS_REORDER }, + { 2046, hweight32(STRESS_ALL), STRESS_ALL }, +}; + +static void stress_case_to_desc(const struct stress_case *param, char *desc) { + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "nlocks=%d,nthreads_per_cpu=%d,flags=%x", + param->nlocks, param->nthreads_per_cpu, param->flags); +} + +KUNIT_ARRAY_PARAM(stress_cases, stress_cases, stress_case_to_desc); + +static void stress(struct kunit *test) +{ + const struct stress_case *param = test->param_value; + const int nlocks = param->nlocks; + int nthreads = param->nthreads_per_cpu * num_online_cpus(); + const unsigned int flags = param->flags; struct ww_mutex *locks; struct stress *stress_array; int n, count; - locks = kmalloc_array(nlocks, sizeof(*locks), GFP_KERNEL); - if (!locks) - return -ENOMEM; + locks = kunit_kmalloc_array(test, nlocks, sizeof(*locks), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, locks); - stress_array = kmalloc_array(nthreads, sizeof(*stress_array), - GFP_KERNEL); - if (!stress_array) { - kfree(locks); - return -ENOMEM; - } + stress_array = kunit_kmalloc_array(test, nthreads, sizeof(*stress_array), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, stress_array); for (n = 0; n < nlocks; n++) ww_mutex_init(&locks[n], &ww_class); @@ -617,6 +653,7 @@ static int stress(int nlocks, int nthreads, unsigned int flags) stress = &stress_array[count++]; INIT_WORK(&stress->work, fn); + stress->test = test; stress->locks = locks; stress->nlocks = nlocks; stress->timeout = jiffies + 2*HZ; @@ -629,70 +666,42 @@ static int stress(int nlocks, int nthreads, unsigned int flags) for (n = 0; n < nlocks; n++) ww_mutex_destroy(&locks[n]); - kfree(stress_array); - kfree(locks); - - return 0; } -static int __init test_ww_mutex_init(void) +static int ww_mutex_suite_init(struct kunit_suite *suite) { - int ncpus = num_online_cpus(); - int ret, i; - - printk(KERN_INFO "Beginning ww mutex selftests\n"); - - prandom_seed_state(&rng, get_random_u64()); - wq = alloc_workqueue("test-ww_mutex", WQ_UNBOUND, 0); if (!wq) return -ENOMEM; - ret = test_mutex(); - if (ret) - return ret; - - ret = test_aa(false); - if (ret) - return ret; - - ret = test_aa(true); - if (ret) - return ret; - - for (i = 0; i < 4; i++) { - ret = test_abba(i & 1, i & 2); - if (ret) - return ret; - } - - ret = test_cycle(ncpus); - if (ret) - return ret; - - ret = stress(16, 2*ncpus, STRESS_INORDER); - if (ret) - return ret; - - ret = stress(16, 2*ncpus, STRESS_REORDER); - if (ret) - return ret; - - ret = stress(2046, hweight32(STRESS_ALL)*ncpus, STRESS_ALL); - if (ret) - return ret; + prandom_seed_state(&rng, get_random_u64()); - printk(KERN_INFO "All ww mutex selftests passed\n"); return 0; } -static void __exit test_ww_mutex_exit(void) +static void ww_mutex_suite_exit(struct kunit_suite *suite) { - destroy_workqueue(wq); + if (wq) + destroy_workqueue(wq); } -module_init(test_ww_mutex_init); -module_exit(test_ww_mutex_exit); +static struct kunit_case ww_mutex_cases[] = { + KUNIT_CASE_PARAM(test_mutex, test_mutex_gen_params), + KUNIT_CASE_PARAM(test_aa, test_aa_gen_params), + KUNIT_CASE_PARAM(test_abba, test_abba_gen_params), + KUNIT_CASE_PARAM(test_cycle, test_cycle_gen_params), + KUNIT_CASE_PARAM_ATTR(stress, stress_cases_gen_params, {.speed = KUNIT_SPEED_SLOW}), + {}, +}; + +static struct kunit_suite ww_mutex_suite = { + .name = "ww_mutex", + .suite_init = ww_mutex_suite_init, + .suite_exit = ww_mutex_suite_exit, + .test_cases = ww_mutex_cases, +}; + +kunit_test_suite(ww_mutex_suite); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Intel Corporation"); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 85b95d645b10..2c9da8647eaf 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1595,16 +1595,18 @@ config LOCK_TORTURE_TEST Say M if you want these torture tests to build as a module. Say N if you are unsure. -config WW_MUTEX_SELFTEST - tristate "Wait/wound mutex selftests" +config WW_MUTEX_KUNIT_TEST + tristate "KUnit test for wait/wound mutex" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS help - This option provides a kernel module that runs tests on the - on the struct ww_mutex locking API. + This option provides a KUnit test that exercises the struct + ww_mutex locking API. It is recommended to enable DEBUG_WW_MUTEX_SLOWPATH in conjunction with this test harness. - Say M if you want these self tests to build as a module. + Say M if you want these tests to build as a module. Say N if you are unsure. config SCF_TORTURE_TEST diff --git a/tools/testing/selftests/locking/ww_mutex.sh b/tools/testing/selftests/locking/ww_mutex.sh deleted file mode 100755 index 91e4ac7566af..000000000000 --- a/tools/testing/selftests/locking/ww_mutex.sh +++ /dev/null @@ -1,19 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 - -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 - -# Runs API tests for struct ww_mutex (Wait/Wound mutexes) -if ! /sbin/modprobe -q -n test-ww_mutex; then - echo "ww_mutex: module test-ww_mutex is not found [SKIP]" - exit $ksft_skip -fi - -if /sbin/modprobe -q test-ww_mutex; then - /sbin/modprobe -q -r test-ww_mutex - echo "locking/ww_mutex: ok" -else - echo "locking/ww_mutex: [FAIL]" - exit 1 -fi --- base-commit: 7b7a883c7f4de1ee5040bd1c32aabaafde54d209 change-id: 20250208-ww_mutex-kunit-convert-71842a7a6be2 Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

4 months, 2 weeks

2
5
0 0

[PATCH bpf-next v2] arm64, bpf: Add 12-argument support for bpf trampoline

by Puranjay Mohan

The arm64 bpf JIT currently supports attaching the trampoline to functions with <= 8 arguments. This is because up to 8 arguments can be passed in registers r0-r7. If there are more than 8 arguments then the 9th and later arguments are passed on the stack, with SP pointing to the first stacked argument. See aapcs64[1] for more details. If the 8th argument is a structure of size > 8B, then it is passed fully on stack and r7 is not used for passing any argument. If there is a 9th argument, it will be passed on the stack, even though r7 is available. Add the support of storing and restoring arguments passed on the stack to the arm64 bpf trampoline. This will allow attaching the trampoline to functions that take up to 12 arguments. [1] https://github.com/ARM-software/abi-aa/blob/main/aapcs64/aapcs64.rst#parame… Signed-off-by: Puranjay Mohan <puranjay(a)kernel.org> --- Changes in V1 -> V2: V1: https://lore.kernel.org/all/20240704173227.130491-1-puranjay@kernel.org/ - Fixed the argument handling for composite types (structs) --- arch/arm64/net/bpf_jit_comp.c | 139 ++++++++++++++----- tools/testing/selftests/bpf/DENYLIST.aarch64 | 3 - 2 files changed, 107 insertions(+), 35 deletions(-) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 751331f5ba90..063bf5e11fc6 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -30,6 +30,8 @@ #define TMP_REG_3 (MAX_BPF_JIT_REG + 3) #define FP_BOTTOM (MAX_BPF_JIT_REG + 4) #define ARENA_VM_START (MAX_BPF_JIT_REG + 5) +/* Up to eight function arguments are passed in registers r0-r7 */ +#define ARM64_MAX_REG_ARGS 8 #define check_imm(bits, imm) do { \ if ((((imm) > 0) && ((imm) >> (bits))) || \ @@ -2001,26 +2003,51 @@ static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_links *tl, } } -static void save_args(struct jit_ctx *ctx, int args_off, int nregs) +static void save_args(struct jit_ctx *ctx, int args_off, int orig_sp_off, + int nargs, int nreg_args) { + const u8 tmp = bpf2a64[TMP_REG_1]; + int arg_pos; int i; - for (i = 0; i < nregs; i++) { - emit(A64_STR64I(i, A64_SP, args_off), ctx); + for (i = 0; i < nargs; i++) { + if (i < nreg_args) { + emit(A64_STR64I(i, A64_SP, args_off), ctx); + } else { + arg_pos = orig_sp_off + (i - nreg_args) * 8; + emit(A64_LDR64I(tmp, A64_SP, arg_pos), ctx); + emit(A64_STR64I(tmp, A64_SP, args_off), ctx); + } args_off += 8; } } -static void restore_args(struct jit_ctx *ctx, int args_off, int nregs) +static void restore_args(struct jit_ctx *ctx, int args_off, int nreg_args) { int i; - for (i = 0; i < nregs; i++) { + for (i = 0; i < nreg_args; i++) { emit(A64_LDR64I(i, A64_SP, args_off), ctx); args_off += 8; } } +static void restore_stack_args(struct jit_ctx *ctx, int args_off, int stk_arg_off, + int nargs, int nreg_args) +{ + const u8 tmp = bpf2a64[TMP_REG_1]; + int arg_pos; + int i; + + for (i = nreg_args; i < nargs; i++) { + arg_pos = args_off + i * 8; + emit(A64_LDR64I(tmp, A64_SP, arg_pos), ctx); + emit(A64_STR64I(tmp, A64_SP, stk_arg_off), ctx); + + stk_arg_off += 8; + } +} + /* Based on the x86's implementation of arch_prepare_bpf_trampoline(). * * bpf prog and function entry before bpf trampoline hooked: @@ -2034,15 +2061,17 @@ static void restore_args(struct jit_ctx *ctx, int args_off, int nregs) */ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, struct bpf_tramp_links *tlinks, void *func_addr, - int nregs, u32 flags) + int nargs, int nreg_args, u32 flags) { int i; int stack_size; + int stk_arg_off; + int orig_sp_off; int retaddr_off; int regs_off; int retval_off; int args_off; - int nregs_off; + int nargs_off; int ip_off; int run_ctx_off; struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY]; @@ -2052,6 +2081,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, __le32 **branches = NULL; /* trampoline stack layout: + * SP + orig_sp_off [ first stack arg ] if nargs > 8 * [ parent ip ] * [ FP ] * SP + retaddr_off [ self ip ] @@ -2069,14 +2099,24 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, * [ ... ] * SP + args_off [ arg reg 1 ] * - * SP + nregs_off [ arg regs count ] + * SP + nargs_off [ arg count ] * * SP + ip_off [ traced function ] BPF_TRAMP_F_IP_ARG flag * * SP + run_ctx_off [ bpf_tramp_run_ctx ] + * + * [ stack_argN ] + * [ ... ] + * SP + stk_arg_off [ stack_arg1 ] BPF_TRAMP_F_CALL_ORIG */ stack_size = 0; + stk_arg_off = stack_size; + if ((flags & BPF_TRAMP_F_CALL_ORIG) && (nargs - nreg_args > 0)) { + /* room for saving arguments passed on stack */ + stack_size += (nargs - nreg_args) * 8; + } + run_ctx_off = stack_size; /* room for bpf_tramp_run_ctx */ stack_size += round_up(sizeof(struct bpf_tramp_run_ctx), 8); @@ -2086,13 +2126,13 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, if (flags & BPF_TRAMP_F_IP_ARG) stack_size += 8; - nregs_off = stack_size; + nargs_off = stack_size; /* room for args count */ stack_size += 8; args_off = stack_size; /* room for args */ - stack_size += nregs * 8; + stack_size += nargs * 8; /* room for return value */ retval_off = stack_size; @@ -2110,6 +2150,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, /* return address locates above FP */ retaddr_off = stack_size + 8; + /* original SP position + * stack_size + parent function frame + patched function frame + */ + orig_sp_off = stack_size + 32; + /* bpf trampoline may be invoked by 3 instruction types: * 1. bl, attached to bpf prog or kernel function via short jump * 2. br, attached to bpf prog or kernel function via long jump @@ -2135,12 +2180,12 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, emit(A64_STR64I(A64_R(10), A64_SP, ip_off), ctx); } - /* save arg regs count*/ - emit(A64_MOVZ(1, A64_R(10), nregs, 0), ctx); - emit(A64_STR64I(A64_R(10), A64_SP, nregs_off), ctx); + /* save argument count */ + emit(A64_MOVZ(1, A64_R(10), nargs, 0), ctx); + emit(A64_STR64I(A64_R(10), A64_SP, nargs_off), ctx); - /* save arg regs */ - save_args(ctx, args_off, nregs); + /* save arguments passed in regs and on the stack */ + save_args(ctx, args_off, orig_sp_off, nargs, nreg_args); /* save callee saved registers */ emit(A64_STR64I(A64_R(19), A64_SP, regs_off), ctx); @@ -2167,7 +2212,10 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, } if (flags & BPF_TRAMP_F_CALL_ORIG) { - restore_args(ctx, args_off, nregs); + /* restore arguments that were passed in registers */ + restore_args(ctx, args_off, nreg_args); + /* restore arguments that were passed on the stack */ + restore_stack_args(ctx, args_off, stk_arg_off, nargs, nreg_args); /* call original func */ emit(A64_LDR64I(A64_R(10), A64_SP, retaddr_off), ctx); emit(A64_ADR(A64_LR, AARCH64_INSN_SIZE * 2), ctx); @@ -2196,7 +2244,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, } if (flags & BPF_TRAMP_F_RESTORE_REGS) - restore_args(ctx, args_off, nregs); + restore_args(ctx, args_off, nreg_args); /* restore callee saved register x19 and x20 */ emit(A64_LDR64I(A64_R(19), A64_SP, regs_off), ctx); @@ -2228,19 +2276,42 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, return ctx->idx; } -static int btf_func_model_nregs(const struct btf_func_model *m) +static int btf_func_model_nargs(const struct btf_func_model *m) { - int nregs = m->nr_args; + int nargs = m->nr_args; int i; - /* extra registers needed for struct argument */ + /* extra registers or stack slots needed for struct argument */ for (i = 0; i < MAX_BPF_FUNC_ARGS; i++) { /* The arg_size is at most 16 bytes, enforced by the verifier. */ if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) - nregs += (m->arg_size[i] + 7) / 8 - 1; + nargs += (m->arg_size[i] + 7) / 8 - 1; } - return nregs; + return nargs; +} + +/* get the count of the regs that are used to pass arguments */ +static int btf_func_model_nreg_args(const struct btf_func_model *m) +{ + int nargs = m->nr_args; + int nreg_args = 0; + int i; + + for (i = 0; i < nargs; i++) { + /* The arg_size is at most 16 bytes, enforced by the verifier. */ + if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) { + /* struct members are all in the registers or all + * on the stack. + */ + if (nreg_args + ((m->arg_size[i] + 7) / 8 - 1) > 7) + break; + nreg_args += (m->arg_size[i] + 7) / 8 - 1; + } + nreg_args++; + } + + return (nreg_args > ARM64_MAX_REG_ARGS ? ARM64_MAX_REG_ARGS : nreg_args); } int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, @@ -2251,14 +2322,16 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, .idx = 0, }; struct bpf_tramp_image im; - int nregs, ret; + int nargs, nreg_args, ret; - nregs = btf_func_model_nregs(m); - /* the first 8 registers are used for arguments */ - if (nregs > 8) + nargs = btf_func_model_nargs(m); + if (nargs > MAX_BPF_FUNC_ARGS) return -ENOTSUPP; - ret = prepare_trampoline(&ctx, &im, tlinks, func_addr, nregs, flags); + nreg_args = btf_func_model_nreg_args(m); + + ret = prepare_trampoline(&ctx, &im, tlinks, func_addr, nargs, nreg_args, + flags); if (ret < 0) return ret; @@ -2285,7 +2358,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr) { - int ret, nregs; + int ret, nargs, nreg_args; void *image, *tmp; u32 size = ro_image_end - ro_image; @@ -2302,13 +2375,15 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image, .idx = 0, }; - nregs = btf_func_model_nregs(m); - /* the first 8 registers are used for arguments */ - if (nregs > 8) + nargs = btf_func_model_nargs(m); + if (nargs > MAX_BPF_FUNC_ARGS) return -ENOTSUPP; + nreg_args = btf_func_model_nreg_args(m); + jit_fill_hole(image, (unsigned int)(ro_image_end - ro_image)); - ret = prepare_trampoline(&ctx, im, tlinks, func_addr, nregs, flags); + ret = prepare_trampoline(&ctx, im, tlinks, func_addr, nargs, nreg_args, + flags); if (ret > 0 && validate_code(&ctx) < 0) { ret = -EINVAL; diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 index 3c7c3e79aa93..e865451e90d2 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -4,9 +4,6 @@ fexit_sleep # The test never returns. The r kprobe_multi_bench_attach # needs CONFIG_FPROBE kprobe_multi_test # needs CONFIG_FPROBE module_attach # prog 'kprobe_multi': failed to auto-attach: -95 -fentry_test/fentry_many_args # fentry_many_args:FAIL:fentry_many_args_attach unexpected error: -524 -fexit_test/fexit_many_args # fexit_many_args:FAIL:fexit_many_args_attach unexpected error: -524 -tracing_struct/struct_many_args # struct_many_args:FAIL:tracing_struct_many_args__attach unexpected error: -524 fill_link_info/kprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95 fill_link_info/kretprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95 fill_link_info/kprobe_multi_invalid_ubuff # bpf_program__attach_kprobe_multi_opts unexpected error: -95 -- 2.40.1

4 months, 2 weeks

3
4
0 0

[PATCH] selftests/landlock: add binaries to gitignore

by Bharadwaj Raju

Building the test creates binaries 'wait-pipe' and 'sandbox-and-launch' which need to be gitignore'd. Signed-off-by: Bharadwaj Raju <bharadwaj.raju777(a)gmail.com> --- tools/testing/selftests/landlock/.gitignore | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/landlock/.gitignore b/tools/testing/selftests/landlock/.gitignore index 470203a7cd73..0566c50dfcad 100644 --- a/tools/testing/selftests/landlock/.gitignore +++ b/tools/testing/selftests/landlock/.gitignore @@ -1,2 +1,4 @@ /*_test /true +/wait-pipe +/sandbox-and-launch -- 2.43.0

4 months, 2 weeks

2
1
0 0

[PATCH v6 00/14] iommufd: Add vIOMMU infrastructure (Part-3: vEVENTQ)

by Nicolin Chen

As the vIOMMU infrastructure series part-3, this introduces a new vEVENTQ object. The existing FAULT object provides a nice notification pathway to the user space with a queue already, so let vEVENTQ reuse that. Mimicing the HWPT structure, add a common EVENTQ structure to support its derivatives: IOMMUFD_OBJ_FAULT (existing) and IOMMUFD_OBJ_VEVENTQ (new). An IOMMUFD_CMD_VEVENTQ_ALLOC is introduced to allocate vEVENTQ object for vIOMMUs. One vIOMMU can have multiple vEVENTQs in different types but can not support multiple vEVENTQs in the same type. The forwarding part is fairly simple but might need to replace a physical device ID with a virtual device ID in a driver-level event data structure. So, this also adds some helpers for drivers to use. As usual, this series comes with the selftest coverage for this new ioctl and with a real world use case in the ARM SMMUv3 driver. This is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_veventq-v6 Testing with RMR patches for MSI: https://github.com/nicolinc/iommufd/commits/iommufd_veventq-v6-with-rmr Paring QEMU branch for testing: https://github.com/nicolinc/qemu/commits/wip/for_iommufd_veventq-v6 Changelog v6 * Drop supports_veventq viommu op * Split bug/cosmetics fixes out of the series * Drop the blocking mutex around copy_to_user() * Add veventq_depth in uAPI to limit vEVENTQ size * Revise the documentation for a clear description * Fix sparse warnings in arm_vmaster_report_event() * Rework iommufd_viommu_get_vdev_id() to return -ENOENT v.s. 0 * Allow Abort/Bypass STEs to allocate vEVENTQ and set STE.MEV for DoS mitigations v5 https://lore.kernel.org/all/cover.1736237481.git.nicolinc@nvidia.com/ * Add Reviewed-by from Baolu * Reorder the OBJ list as well * Fix alphabetical order after renaming in v4 * Add supports_veventq viommu op for vEVENTQ type validation v4 https://lore.kernel.org/all/cover.1735933254.git.nicolinc@nvidia.com/ * Rename "vIRQ" to "vEVENTQ" * Use flexible array in struct iommufd_vevent * Add the new ioctl command to union ucmd_buffer * Fix the alphabetical order in union ucmd_buffer too * Rename _TYPE_NONE to _TYPE_DEFAULT aligning with vIOMMU naming v3 https://lore.kernel.org/all/cover.1734477608.git.nicolinc@nvidia.com/ * Rebase on Will's for-joerg/arm-smmu/updates for arm_smmu_event series * Add "Reviewed-by" lines from Kevin * Fix typos in comments, kdocs, and jump tags * Add a patch to sort struct iommufd_ioctl_op * Update iommufd's userpsace-api documentation * Update uAPI kdoc to quote SMMUv3 offical spec * Drop the unused workqueue in struct iommufd_virq * Drop might_sleep() in iommufd_viommu_report_irq() helper * Add missing "break" in iommufd_viommu_get_vdev_id() helper * Shrink the scope of the vmaster's read lock in SMMUv3 driver * Pass in two arguments to iommufd_eventq_virq_handler() helper * Move "!ops || !ops->read" validation into iommufd_eventq_init() * Move "fault->ictx = ictx" closer to iommufd_ctx_get(fault->ictx) * Update commit message for arm_smmu_attach_prepare/commit_vmaster() * Keep "iommufd_fault" as-is and rename "iommufd_eventq_virq" to just "iommufd_virq" v2 https://lore.kernel.org/all/cover.1733263737.git.nicolinc@nvidia.com/ * Rebase on v6.13-rc1 * Add IOPF and vIRQ in iommufd.rst (userspace-api) * Add a proper locking in iommufd_event_virq_destroy * Add iommufd_event_virq_abort with a lockdep_assert_held * Rename "EVENT_*" to "EVENTQ_*" to describe the objects better * Reorganize flows in iommufd_eventq_virq_alloc for abort() to work * Adde struct arm_smmu_vmaster to store vSID upon attaching to a nested domain, calling a newly added iommufd_viommu_get_vdev_id helper * Adde an arm_vmaster_report_event helper in arm-smmu-v3-iommufd file to simplify the routine in arm_smmu_handle_evt() of the main driver v1 https://lore.kernel.org/all/cover.1724777091.git.nicolinc@nvidia.com/ Thanks! Nicolin Nicolin Chen (14): iommufd/fault: Move two fault functions out of the header iommufd/fault: Add an iommufd_fault_init() helper iommufd: Abstract an iommufd_eventq from iommufd_fault iommufd: Rename fault.c to eventq.c iommufd: Add IOMMUFD_OBJ_VEVENTQ and IOMMUFD_CMD_VEVENTQ_ALLOC iommufd/viommu: Add iommufd_viommu_get_vdev_id helper iommufd/viommu: Add iommufd_viommu_report_event helper iommufd/selftest: Require vdev_id when attaching to a nested domain iommufd/selftest: Add IOMMU_TEST_OP_TRIGGER_VEVENT for vEVENTQ coverage iommufd/selftest: Add IOMMU_VEVENTQ_ALLOC test coverage Documentation: userspace-api: iommufd: Update FAULT and VEVENTQ iommu/arm-smmu-v3: Introduce struct arm_smmu_vmaster iommu/arm-smmu-v3: Report events that belong to devices attached to vIOMMU iommu/arm-smmu-v3: Set MEV bit in nested STE for DoS mitigations drivers/iommu/iommufd/Makefile | 2 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 31 ++ drivers/iommu/iommufd/iommufd_private.h | 141 +++++-- drivers/iommu/iommufd/iommufd_test.h | 10 + include/linux/iommufd.h | 23 ++ include/uapi/linux/iommufd.h | 100 +++++ tools/testing/selftests/iommu/iommufd_utils.h | 115 ++++++ .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 62 +++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 94 +++-- drivers/iommu/iommufd/driver.c | 69 ++++ drivers/iommu/iommufd/{fault.c => eventq.c} | 364 +++++++++++++++--- drivers/iommu/iommufd/hw_pagetable.c | 6 +- drivers/iommu/iommufd/main.c | 7 + drivers/iommu/iommufd/selftest.c | 54 +++ drivers/iommu/iommufd/viommu.c | 2 + tools/testing/selftests/iommu/iommufd.c | 36 ++ .../selftests/iommu/iommufd_fail_nth.c | 7 + Documentation/userspace-api/iommufd.rst | 17 + 18 files changed, 1018 insertions(+), 122 deletions(-) rename drivers/iommu/iommufd/{fault.c => eventq.c} (50%) base-commit: e94dc6ddda8dd3770879a132d577accd2cce25f9 prerequisite-patch-id: bc39b89c8e2b8298a337943610e1cfd84d9b7d7d prerequisite-patch-id: 5cd371c3fddec696510e3e9c4f449dc60bd7c2ae prerequisite-patch-id: adbc6b7916b03f56eff01a9f1b33a7832fe0884e prerequisite-patch-id: c62d01dcfe8faeb928847fb4e51f82eebafe6ae3 prerequisite-patch-id: 0000000000000000000000000000000000000000 -- 2.43.0

4 months, 2 weeks

5
59
0 0

[PATCH] selftests: sched: add sched as a default selftest target

by Sinadin Shan

The sched tests are missing a target entry and hence out-of-tree build support. For instance: make -C tools/testing/selftests install INSTALL_LOCATION=/foo/bar is expected to build the sched tests and place them at /foo/bar. But this is not observed since a TARGET entry is not present for sched. This was suggested by Shuah in this conversation Link: https://lore.kernel.org/linux-kselftest/60dd0240-8e45-4958-acf2-7eeee917785… Add support for sched selftests by adding sched as a default TARGET Signed-off-by: Sinadin Shan <sinadin.shan(a)oracle.com> --- tools/testing/selftests/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 8daac70c2f9d2..e2d0d389ad912 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -91,6 +91,7 @@ TARGETS += rlimits TARGETS += rseq TARGETS += rtc TARGETS += rust +TARGETS += sched TARGETS += sched_ext TARGETS += seccomp TARGETS += sgx -- 2.43.5

4 months, 3 weeks

4
8
0 0

[PATCH] selftests/sysctl: fix wording of help messages

by Bharadwaj Raju

Fix paramter -> parameter, and recomended -> recommended in sysctl.sh's help messages. Also correct grammar: "number amount of times is recommended" etc -> "the recommended number of times". Signed-off-by: Bharadwaj Raju <bharadwaj.raju777(a)gmail.com> --- tools/testing/selftests/sysctl/sysctl.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh index 84472b436c07..a8e5736e89a8 100755 --- a/tools/testing/selftests/sysctl/sysctl.sh +++ b/tools/testing/selftests/sysctl/sysctl.sh @@ -764,7 +764,7 @@ sysctl_test_0007() fi if [ ! -f /proc/cmdline ]; then - echo -e "SKIPPING\nThere is no /proc/cmdline to check for paramter" + echo -e "SKIPPING\nThere is no /proc/cmdline to check for parameter" return $ksft_skip fi @@ -884,7 +884,7 @@ usage() echo "Valid tests: 0001-$MAX_TEST" echo "" echo " all Runs all tests (default)" - echo " -t Run test ID the number amount of times is recommended" + echo " -t Run test ID the recommended number of times" echo " -w Watch test ID run until it runs into an error" echo " -c Run test ID once" echo " -s Run test ID x test-count number of times" @@ -898,7 +898,7 @@ usage() echo Example uses: echo echo "$TEST_NAME.sh -- executes all tests" - echo "$TEST_NAME.sh -t 0002 -- Executes test ID 0002 number of times is recomended" + echo "$TEST_NAME.sh -t 0002 -- Executes test ID 0002 the recommended number of times" echo "$TEST_NAME.sh -w 0002 -- Watch test ID 0002 run until an error occurs" echo "$TEST_NAME.sh -s 0002 -- Run test ID 0002 once" echo "$TEST_NAME.sh -c 0002 3 -- Run test ID 0002 three times" -- 2.48.1

4 months, 3 weeks

2
1
0 0

[PATCH] selftests: fix spelling/grammar errors in sysctl/sysctl.sh

by Chandra Pratap

Fix the grammatical/spelling errors in sysctl/sysctl.sh. This fixes all errors pointed out by codespell in the file. Signed-off-by: Chandra Pratap <chandrapratap3519(a)gmail.com> --- tools/testing/selftests/sysctl/sysctl.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh index 84472b436c07..f6e129a82ffd 100755 --- a/tools/testing/selftests/sysctl/sysctl.sh +++ b/tools/testing/selftests/sysctl/sysctl.sh @@ -21,7 +21,7 @@ TEST_FILE=$(mktemp) # ENABLED: 1 if enabled, 0 otherwise # TARGET: test target file required on the test_sysctl module # SKIP_NO_TARGET: 1 skip if TARGET not there -# 0 run eventhough TARGET not there +# 0 run even though TARGET not there # # Once these are enabled please leave them as-is. Write your own test, # we have tons of space. @@ -764,7 +764,7 @@ sysctl_test_0007() fi if [ ! -f /proc/cmdline ]; then - echo -e "SKIPPING\nThere is no /proc/cmdline to check for paramter" + echo -e "SKIPPING\nThere is no /proc/cmdline to check for parameter" return $ksft_skip fi @@ -898,7 +898,7 @@ usage() echo Example uses: echo echo "$TEST_NAME.sh -- executes all tests" - echo "$TEST_NAME.sh -t 0002 -- Executes test ID 0002 number of times is recomended" + echo "$TEST_NAME.sh -t 0002 -- Executes test ID 0002 number of times is recommended" echo "$TEST_NAME.sh -w 0002 -- Watch test ID 0002 run until an error occurs" echo "$TEST_NAME.sh -s 0002 -- Run test ID 0002 once" echo "$TEST_NAME.sh -c 0002 3 -- Run test ID 0002 three times" -- 2.48.0-rc1

4 months, 3 weeks

2
1
0 0

[PATCH net-next v6 0/7] Some pktgen fixes/improvments (part I)

by Peter Seiderer

While taking a look at '[PATCH net] pktgen: Avoid out-of-range in get_imix_entries' ([1]) and '[PATCH net v2] pktgen: Avoid out-of-bounds access in get_imix_entries' ([2], [3]) and doing some tests and code review I detected that the /proc/net/pktgen/... parsing logic does not honour the user given buffer bounds (resulting in out-of-bounds access). This can be observed e.g. by the following simple test (sometimes the old/'longer' previous value is re-read from the buffer): $ echo add_device lo@0 > /proc/net/pktgen/kpktgend_0 $ echo "min_pkt_size 12345" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 12345 max_pkt_size: 0 Result: OK: min_pkt_size=12345 $ echo -n "min_pkt_size 123" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 12345 max_pkt_size: 0 Result: OK: min_pkt_size=12345 $ echo "min_pkt_size 123" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 123 max_pkt_size: 0 Result: OK: min_pkt_size=123 So fix the out-of-bounds access (and some minor findings) and add a simple proc_net_pktgen selftest... Patch set splited into part I (this one) - net: pktgen: replace ENOTSUPP with EOPNOTSUPP - net: pktgen: enable 'param=value' parsing - net: pktgen: fix hex32_arg parsing for short reads - net: pktgen: fix 'rate 0' error handling (return -EINVAL) - net: pktgen: fix 'ratep 0' error handling (return -EINVAL) - net: pktgen: fix ctrl interface command parsing - net: pktgen: fix access outside of user given buffer in pktgen_thread_write() And part II (will follow): - net: pktgen: fix mix of int/long - net: pktgen: remove extra tmp variable (re-use len instead) - net: pktgen: remove some superfluous variable initializing - net: pktgen: fix mpls maximum labels list parsing - net: pktgen: fix access outside of user given buffer in pktgen_if_write() - net: pktgen: fix mpls reset parsing - net: pktgen: remove all superfluous index assignements - selftest: net: add proc_net_pktgen Regards, Peter Changes v5 -> v6: - add rev-by Simon Horman - drop patch 'net: pktgen: use defines for the various dec/hex number parsing digits lengths' Changes v4 -> v5: - split up patchset into part i/ii (suggested by Simon Horman) Changes v3 -> v4: - add rev-by Simon Horman - new patch 'net: pktgen: use defines for the various dec/hex number parsing digits lengths' (suggested by Simon Horman) - replace C99 comment (suggested by Paolo Abeni) - drop available characters check in strn_len() (suggested by Paolo Abeni) - factored out patch 'net: pktgen: align some variable declarations to the most common pattern' (suggested by Paolo Abeni) - factored out patch 'net: pktgen: remove extra tmp variable (re-use len instead)' (suggested by Paolo Abeni) - factored out patch 'net: pktgen: remove some superfluous variable initializing' (suggested by Paolo Abeni) - factored out patch 'net: pktgen: fix mpls maximum labels list parsing' (suggested by Paolo Abeni) - factored out 'net: pktgen: hex32_arg/num_arg error out in case no characters are available' (suggested by Paolo Abeni) - factored out 'net: pktgen: num_arg error out in case no valid character is parsed' (suggested by Paolo Abeni) Changes v2 -> v3: - new patch: 'net: pktgen: fix ctrl interface command parsing' - new patch: 'net: pktgen: fix mpls reset parsing' - tools/testing/selftests/net/proc_net_pktgen.c: - fix typo in change description ('v1 -> v1' and tyop) - rename some vars to better match usage add_loopback_0 -> thr_cmd_add_loopback_0 rm_loopback_0 -> thr_cmd_rm_loopback_0 wrong_ctrl_cmd -> wrong_thr_cmd legacy_ctrl_cmd -> legacy_thr_cmd ctrl_fd -> thr_fd - add ctrl interface tests Changes v1 -> v2: - new patch: 'net: pktgen: fix hex32_arg parsing for short reads' - new patch: 'net: pktgen: fix 'rate 0' error handling (return -EINVAL)' - new patch: 'net: pktgen: fix 'ratep 0' error handling (return -EINVAL)' - net/core/pktgen.c: additional fix get_imix_entries() and get_labels() - tools/testing/selftests/net/proc_net_pktgen.c: - fix tyop not vs. nod (suggested by Jakub Kicinski) - fix misaligned line (suggested by Jakub Kicinski) - enable fomerly commented out CONFIG_XFRM dependent test (command spi), as CONFIG_XFRM is enabled via tools/testing/selftests/net/config CONFIG_XFRM_INTERFACE/CONFIG_XFRM_USER (suggestex by Jakub Kicinski) - add CONFIG_NET_PKTGEN=m to tools/testing/selftests/net/config (suggested by Jakub Kicinski) - add modprobe pktgen to FIXTURE_SETUP() (suggested by Jakub Kicinski) - fix some checkpatch warnings (Missing a blank line after declarations) - shrink line length by re-naming some variables (command -> cmd, device -> dev) - add 'rate 0' testcase - add 'ratep 0' testcase [1] https://lore.kernel.org/netdev/20241006221221.3744995-1-artem.chernyshev@re… [2] https://lore.kernel.org/netdev/20250109083039.14004-1-pchelkin@ispras.ru/ [3] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… Peter Seiderer (7): net: pktgen: replace ENOTSUPP with EOPNOTSUPP net: pktgen: enable 'param=value' parsing net: pktgen: fix hex32_arg parsing for short reads net: pktgen: fix 'rate 0' error handling (return -EINVAL) net: pktgen: fix 'ratep 0' error handling (return -EINVAL) net: pktgen: fix ctrl interface command parsing net: pktgen: fix access outside of user given buffer in pktgen_thread_write() net/core/pktgen.c | 39 ++++++++++++++++++++++----------------- 1 file changed, 22 insertions(+), 17 deletions(-) -- 2.48.1

4 months, 3 weeks

2
8
0 0

[PATCH net-next v2] tun: Pad virtio headers

by Akihiko Odaki

tun simply advances iov_iter when it needs to pad virtio header, which leaves the garbage in the buffer as is. This will become especially problematic when tun starts to allow enabling the hash reporting feature; even if the feature is enabled, the packet may lack a hash value and may contain a hole in the virtio header because the packet arrived before the feature gets enabled or does not contain the header fields to be hashed. If the hole is not filled with zero, it is impossible to tell if the packet lacks a hash value. In theory, a user of tun can fill the buffer with zero before calling read() to avoid such a problem, but leaving the garbage in the buffer is awkward anyway so replace advancing the iterator with writing zeros. A user might have initialized the buffer to some non-zero value, expecting tun to skip writing it. As this was never a documented feature, this seems unlikely. The overhead of filling the hole in the header is negligible when the header size is specified according to the specification as doing so will not make another cache line dirty under a reasonable assumption. Below is a proof of this statement: The first 10 bytes of the header is always written and tun also writes the packet itself immediately after the packet unless the packet is empty. This makes a hole between these writes whose size is: sz - 10 where sz is the specified header size. Therefore, we will never make another cache line dirty when: sz < L1_CACHE_BYTES + 10 where L1_CACHE_BYTES is the cache line size. Assuming L1_CACHE_BYTES >= 16, this inequation holds when: sz < 26. sz <= 20 according to the current specification so we even have a margin of 5 bytes in case that the header size grows in a future version of the specification. Signed-off-by: Akihiko Odaki <akihiko.odaki(a)daynix.com> --- Changes in v2: - Dropped the code to set num_buffers to 1. - Incorporated a grammatical improvement suggested by Michael S. Tsirkin. - Added an explanation of this patch's risk suggested by Michael S. Tsirkin. - Noted that it will not make another cache line dirty. - Added an error check. - Link to v1: https://lore.kernel.org/r/20250213-buffers-v1-1-ec4a0821957a@daynix.com --- drivers/net/tun_vnet.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/tun_vnet.h b/drivers/net/tun_vnet.h index fd7411c4447ffb180e032fe3e22f6709c30da8e9..58b9ac7a5fc4084c789fe94fe36b5f8631bf1fa4 100644 --- a/drivers/net/tun_vnet.h +++ b/drivers/net/tun_vnet.h @@ -143,7 +143,8 @@ static inline int tun_vnet_hdr_put(int sz, struct iov_iter *iter, if (unlikely(copy_to_iter(hdr, sizeof(*hdr), iter) != sizeof(*hdr))) return -EFAULT; - iov_iter_advance(iter, sz - sizeof(*hdr)); + if (iov_iter_zero(sz - sizeof(*hdr), iter) != sz - sizeof(*hdr)) + return -EFAULT; return 0; } --- base-commit: f54eab84fc17ef79b701e29364b7d08ca3a1d2f6 change-id: 20250116-buffers-96e14bf023fc prerequisite-change-id: 20241230-tun-66e10a49b0c7:v6 prerequisite-patch-id: 871dc5f146fb6b0e3ec8612971a8e8190472c0fb prerequisite-patch-id: 2797ed249d32590321f088373d4055ff3f430a0e prerequisite-patch-id: ea3370c72d4904e2f0536ec76ba5d26784c0cede prerequisite-patch-id: 837e4cf5d6b451424f9b1639455e83a260c4440d prerequisite-patch-id: ea701076f57819e844f5a35efe5cbc5712d3080d prerequisite-patch-id: 701646fb43ad04cc64dd2bf13c150ccbe6f828ce prerequisite-patch-id: 53176dae0c003f5b6c114d43f936cf7140d31bb5 Best regards, -- Akihiko Odaki <akihiko.odaki(a)daynix.com>

4 months, 3 weeks

5
4
0 0

[RESEND][PATCH 0/3] selftests/tracing: Test only toplevel README file not the instances

by Steven Rostedt

Allow some more tests to run in instances. There's a few tests that require something in README to be present to run. But currently README can't be used for instance tests. Fix that and then allow 4 more tests to run in instances. [ RESEND to include selftest maintainers and lists: original: https://lore.kernel.org/linux-trace-kernel/20250116012009.840870709@goodmis… ] Steven Rostedt (3): selftests/tracing: Test only toplevel README file not the instances selftests/ftrace: Clean up triggers after setting them selftests/tracing: Allow some more tests to run in instances ---- tools/testing/selftests/ftrace/test.d/functions | 8 +++++++- .../test.d/trigger/inter-event/trigger-action-hist-xfail.tc | 1 + .../test.d/trigger/inter-event/trigger-onchange-action-hist.tc | 3 +++ .../test.d/trigger/inter-event/trigger-snapshot-action-hist.tc | 3 +++ .../selftests/ftrace/test.d/trigger/trigger-hist-expressions.tc | 1 + 5 files changed, 15 insertions(+), 1 deletion(-)

4 months, 3 weeks

2
4
0 0

[PATCH 0/6] selftests/mm: Some cleanups from trying to run them

by Brendan Jackman

I never had much luck running mm selftests so I spent a couple of hours digging into why. Looks like most of the reason is missing SKIP checks, so this series is just adding a bunch of those that I found. I did not do anything like all of them, just the ones I spotted in gup_test, mmap, userfaultfd and memfd_secret. Signed-off-by: Brendan Jackman <jackmanb(a)google.com> --- Brendan Jackman (6): selftests/mm: Report errno when things fail selftests/mm: Fix assumption that sudo is present selftests/mm: Skip uffd-stress if userfaultfd not available selftests/mm: Skip uffd-wp-mremap if userfaultfd not available selftests/mm: Print some details when uffd-stress gets bad params selftests/mm: Don't fail uffd-stress if too many CPUs tools/testing/selftests/mm/gup_longterm.c | 32 ++++++++++++++--------------- tools/testing/selftests/mm/run_vmtests.sh | 22 ++++++++++++++++---- tools/testing/selftests/mm/uffd-stress.c | 11 +++++++--- tools/testing/selftests/mm/uffd-wp-mremap.c | 5 ++++- 4 files changed, 46 insertions(+), 24 deletions(-) --- base-commit: 87a132e73910e8689902aed7f2fc229d6908383b change-id: 20250220-mm-selftests-2d7d0542face Best regards, -- Brendan Jackman <jackmanb(a)google.com>

4 months, 3 weeks

2
13
0 0

[PATCH] selftests/tracing: Test only toplevel README file not the instances

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> For the tests that have both a README attribute as well as the instance flag to run the tests as an instance, the instance version will always exit with UNSUPPORTED. That's because the instance directory does not contain a README file. Currently, the tests check for a README file in the directory that the test runs in and if there's a requirement for something to be present in the README file, it will not find it, as the instance directory doesn't have it. Have the tests check if the current directory is an instance directory, and if it is, check two directories above the current directory for the README file: /sys/kernel/tracing/README /sys/kernel/tracing/instances/foo/../../README Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- tools/testing/selftests/ftrace/test.d/functions | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index 779f3e62ec90..9f2a67fbaf4d 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -156,7 +156,13 @@ check_requires() { # Check required files and tracers exit_unsupported fi elif [ "$r" != "$i" ]; then - if ! grep -Fq "$r" README ; then + # If this is an instance, check the top directory + if echo $TRACING_DIR | grep -q "/instances/"; then + test="$TRACING_DIR/../.." + else + test=$TRACING_DIR + fi + if ! grep -Fq "$r" $test/README ; then echo "Required feature pattern \"$r\" is not in README." exit_unsupported fi -- 2.45.2

4 months, 3 weeks

2
6
0 0

[PATCH v6 0/9] Basic SEV-SNP Selftests

by Pratik R. Sampat

This patch series extends the sev_init2 and the sev_smoke test to exercise the SEV-SNP VM launch workflow. Primarily, it introduces the architectural defines, its support in the SEV library and extends the tests to interact with the SEV-SNP ioctl() wrappers. Patch 1 - Do not advertize SNP on incompatible firmware Patch 2 - Remove SEV support on platform init failure Patch 3 - SNP test for KVM_SEV_INIT2 Patch 4 - Add VMGEXIT helper Patch 5 - Introduce SEV+ VM type check Patch 6 - SNP iotcl() plumbing for the SEV library Patch 7 - Force set GUEST_MEMFD for SNP Patch 8 - Cleanups of smoke test - Decouple policy from type Patch 9 - SNP smoke test The series is based on git.kernel.org/pub/scm/virt/kvm/kvm.git next v5..v6 * Rename is_sev_platform_init to sev_fw_initialized (Nikunj) * Rename KVM CPU feature X86_FEATURE_SNP to X86_FEATURE_SEV_SNP (Nikunj) * Collected Tags from Nikunj, Pankaj, Srikanth. v4..v5: https://lore.kernel.org/kvm/8e7d8172-879e-4a28-8438-343b1c386ec9@amd.com/ * Introduced a check to disable advertising support for SEV, SEV-ES and SNP when platform initialization fails (Nikunj) * Remove the redundant SNP check within is_sev_vm() (Nikunj) * Cleanup of the encrypt_region flow for better readability (Nikunj) * Refactor paths to use the canonical $(ARCH) to rebase for kvm/next v3..v4: https://lore.kernel.org/kvm/20241114234104.128532-1-pratikrajesh.sampat@amd… * Remove SNP FW API version check in the test and ensure the KVM capability advertizes the presence of the feature. Retain the minimum version definitions to exercise these API versions in the smoke test * Retained only the SNP smoke test and SNP_INIT2 test * The SNP architectural defined merged with SNP_INIT2 test patch * SNP shutdown merged with SNP smoke test patch * Add SEV VM type check to abstract comparisons and reduce clutter * Define a SNP default policy which sets bits based on the presence of SMT * Decouple privatization and encryption for it to be SNP agnostic * Assert for only positive tests using vm_ioctl() * Dropped tested-by tags In summary - based on comments from Sean, I have primarily reduced the scope of this patch series to focus on breaking down the SNP smoke test patch (v3 - patch2) to first introduce SEV-SNP support and use this interface to extend the sev_init2 and the sev_smoke test. The rest of the v3 patchset that introduces ioctl, pre fault, fallocate and negative tests, will be re-worked and re-introduced subsequently in future patch series post addressing the issues discussed. v2..v3: https://lore.kernel.org/kvm/20240905124107.6954-1-pratikrajesh.sampat@amd.c… * Remove the assignments for the prefault and fallocate test type enums. * Fix error message for sev launch measure and finish. * Collect tested-by tags [Peter, Srikanth] Pratik R. Sampat (9): KVM: SEV: Disable SEV-SNP on FW validation failure KVM: SEV: Disable SEV on platform init failure KVM: selftests: SEV-SNP test for KVM_SEV_INIT2 KVM: selftests: Add VMGEXIT helper KVM: selftests: Introduce SEV VM type check KVM: selftests: Add library support for interacting with SNP KVM: selftests: Force GUEST_MEMFD flag for SNP VM type KVM: selftests: Abstractions for SEV to decouple policy from type KVM: selftests: Add a basic SEV-SNP smoke test arch/x86/kvm/svm/sev.c | 6 +- drivers/crypto/ccp/sev-dev.c | 16 +++ include/linux/psp-sev.h | 6 ++ .../selftests/kvm/include/x86/processor.h | 1 + tools/testing/selftests/kvm/include/x86/sev.h | 55 ++++++++++- tools/testing/selftests/kvm/lib/kvm_util.c | 7 +- .../testing/selftests/kvm/lib/x86/processor.c | 4 +- tools/testing/selftests/kvm/lib/x86/sev.c | 99 ++++++++++++++++++- .../selftests/kvm/x86/sev_init2_tests.c | 13 +++ .../selftests/kvm/x86/sev_smoke_test.c | 96 ++++++++++++++---- 10 files changed, 272 insertions(+), 31 deletions(-) -- 2.43.0

4 months, 3 weeks

3
23
0 0

[PATCH] selftests: pid_namespace and pidfd missing include

by Alessandro Zanni

Running "make kselftest" results in several errors like these: pidfd_fdinfo_test.c:231:36: error: ‘MS_REC’ undeclared (first use in this function) 231 | r = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); pidfd_fdinfo_test.c:231:45: error: ‘MS_PRIVATE’ undeclared (first use in this function); did you mean ‘MAP_PRIVATE’? 231 | r = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); pid_max.c:48:9: warning: implicit declaration of function ‘umount2’; did you mean ‘SYS_umount2’? [-Wimplicit-function-declaration] 48 | umount2("/proc", MNT_DETACH); This patch adds the <sys/mount.h> include in pidfd_fdinfo_test.c and pid_max.c files to find the variables MS_REC, MS_PRIVATE, MNT_DETACH. Signed-off-by: Alessandro Zanni <alessandro.zanni87(a)gmail.com> --- tools/testing/selftests/pid_namespace/pid_max.c | 1 + tools/testing/selftests/pidfd/pidfd_fdinfo_test.c | 1 + 2 files changed, 2 insertions(+) diff --git a/tools/testing/selftests/pid_namespace/pid_max.c b/tools/testing/selftests/pid_namespace/pid_max.c index 51c414faabb0..972bedc475f1 100644 --- a/tools/testing/selftests/pid_namespace/pid_max.c +++ b/tools/testing/selftests/pid_namespace/pid_max.c @@ -11,6 +11,7 @@ #include <string.h> #include <syscall.h> #include <sys/wait.h> +#include <sys/mount.h> #include "../kselftest_harness.h" #include "../pidfd/pidfd.h" diff --git a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c index f062a986e382..f718aac75068 100644 --- a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c +++ b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c @@ -13,6 +13,7 @@ #include <syscall.h> #include <sys/wait.h> #include <sys/mman.h> +#include <sys/mount.h> #include "pidfd.h" #include "../kselftest.h" -- 2.43.0

4 months, 3 weeks

3
3
0 0

[PATCH] kunit: qemu_configs: SH: Respect kunit cmdline

by Thomas Weißschuh

The default SH kunit configuration sets CONFIG_CMDLINE_OVERWRITE which completely disregards the cmdline passed from the bootloader/QEMU in favor of the builtin CONFIG_CMDLINE. However the kunit tool needs to pass arguments to the in-kernel kunit core, for filters and other runtime parameters. Enable CONFIG_CMDLINE_EXTEND instead, so kunit arguments are respected. Fixes: 8110a3cab05e ("kunit: tool: Add support for SH under QEMU") Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- tools/testing/kunit/qemu_configs/sh.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/kunit/qemu_configs/sh.py b/tools/testing/kunit/qemu_configs/sh.py index 78a474a5b95f3a7d6064a2d3b728810ced095606..f00cb89fdef6aa1c0abd83ca18e7004a4fdd96e1 100644 --- a/tools/testing/kunit/qemu_configs/sh.py +++ b/tools/testing/kunit/qemu_configs/sh.py @@ -7,7 +7,9 @@ CONFIG_CPU_SUBTYPE_SH7751R=y CONFIG_MEMORY_START=0x0c000000 CONFIG_SH_RTS7751R2D=y CONFIG_RTS7751R2D_PLUS=y -CONFIG_SERIAL_SH_SCI=y''', +CONFIG_SERIAL_SH_SCI=y +CONFIG_CMDLINE_EXTEND=y +''', qemu_arch='sh4', kernel_path='arch/sh/boot/zImage', kernel_command_line='console=ttySC1', --- base-commit: 2014c95afecee3e76ca4a56956a936e23283f05b change-id: 20250220-kunit-sh-f42a3a8cce35 Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

4 months, 3 weeks

1
0
0 0

[PATCH net-next v3 0/6] Device memory TCP TX

by Mina Almasry

v3: https://patchwork.kernel.org/project/netdevbpf/list/?series=929401&state=* === Address minor comments from RFCv2 and fix a few build warnings and ynl-regen issues. No major changes. RFC v2: https://patchwork.kernel.org/project/netdevbpf/list/?series=920056&state=* ======= RFC v2 addresses much of the feedback from RFC v1. I plan on sending something close to this as net-next reopens, sending it slightly early to get feedback if any. Major changes: -------------- - much improved UAPI as suggested by Stan. We now interpret the iov_base of the passed in iov from userspace as the offset into the dmabuf to send from. This removes the need to set iov.iov_base = NULL which may be confusing to users, and enables us to send multiple iovs in the same sendmsg() call. ncdevmem and the docs show a sample use of that. - Removed the duplicate dmabuf iov_iter in binding->iov_iter. I think this is good improvment as it was confusing to keep track of 2 iterators for the same sendmsg, and mistracking both iterators caused a couple of bugs reported in the last iteration that are now resolved with this streamlining. - Improved test coverage in ncdevmem. Now muliple sendmsg() are tested, and sending multiple iovs in the same sendmsg() is tested. - Fixed issue where dmabuf unmapping was happening in invalid context (Stan). ==================================================================== The TX path had been dropped from the Device Memory TCP patch series post RFCv1 [1], to make that series slightly easier to review. This series rebases the implementation of the TX path on top of the net_iov/netmem framework agreed upon and merged. The motivation for the feature is thoroughly described in the docs & cover letter of the original proposal, so I don't repeat the lengthy descriptions here, but they are available in [1]. Sending this series as RFC as the winder closure is immenient. I plan on reposting as non-RFC once the tree re-opens, addressing any feedback I receive in the meantime. Full outline on usage of the TX path is detailed in the documentation added in the first patch. Test example is available via the kselftest included in the series as well. The series is relatively small, as the TX path for this feature largely piggybacks on the existing MSG_ZEROCOPY implementation. Patch Overview: --------------- 1. Documentation & tests to give high level overview of the feature being added. 2. Add netmem refcounting needed for the TX path. 3. Devmem TX netlink API. 4. Devmem TX net stack implementation. Testing: -------- Testing is very similar to devmem TCP RX path. The ncdevmem test used for the RX path is now augemented with client functionality to test TX path. * Test Setup: Kernel: net-next with this RFC and memory provider API cherry-picked locally. Hardware: Google Cloud A3 VMs. NIC: GVE with header split & RSS & flow steering support. Performance results are not included with this version, unfortunately. I'm having issues running the dma-buf exporter driver against the upstream kernel on my test setup. The issues are specific to that dma-buf exporter and do not affect this patch series. I plan to follow up this series with perf fixes if the tests point to issues once they're up and running. Special thanks to Stan who took a stab at rebasing the TX implementation on top of the netmem/net_iov framework merged. Parts of his proposal [2] that are reused as-is are forked off into their own patches to give full credit. [1] https://lore.kernel.org/netdev/20240909054318.1809580-1-almasrymina@google.… [2] https://lore.kernel.org/netdev/20240913150913.1280238-2-sdf@fomichev.me/T/#… Cc: sdf(a)fomichev.me Cc: asml.silence(a)gmail.com Cc: dw(a)davidwei.uk Cc: Jamal Hadi Salim <jhs(a)mojatatu.com> Cc: Victor Nogueira <victor(a)mojatatu.com> Cc: Pedro Tammela <pctammela(a)mojatatu.com> Cc: Samiullah Khawaja <skhawaja(a)google.com> Mina Almasry (5): net: add devmem TCP TX documentation selftests: ncdevmem: Implement devmem TCP TX net: add get_netmem/put_netmem support net: devmem: Implement TX path net: devmem: make dmabuf unbinding scheduled work Stanislav Fomichev (1): net: devmem: TCP tx netlink api Documentation/netlink/specs/netdev.yaml | 12 + Documentation/networking/devmem.rst | 144 ++++++++- include/linux/skbuff.h | 15 +- include/linux/skbuff_ref.h | 4 +- include/net/netmem.h | 3 + include/net/sock.h | 1 + include/uapi/linux/netdev.h | 1 + include/uapi/linux/uio.h | 6 +- net/core/datagram.c | 41 ++- net/core/devmem.c | 111 ++++++- net/core/devmem.h | 70 +++- net/core/netdev-genl-gen.c | 13 + net/core/netdev-genl-gen.h | 1 + net/core/netdev-genl.c | 66 +++- net/core/skbuff.c | 36 ++- net/core/sock.c | 8 + net/ipv4/tcp.c | 36 ++- net/vmw_vsock/virtio_transport_common.c | 3 +- tools/include/uapi/linux/netdev.h | 1 + .../selftests/drivers/net/hw/ncdevmem.c | 300 +++++++++++++++++- 20 files changed, 819 insertions(+), 53 deletions(-) -- 2.48.1.362.g079036d154-goog

4 months, 3 weeks

7
38
0 0

[PATCH net 0/2] bond: fix xfrm offload feature during init

by Hangbin Liu

The first patch fixes the xfrm offload feature during setup active-backup mode. The second patch add a ipsec offload testing. Hangbin Liu (2): bonding: fix xfrm offload feature setup on active-backup mode selftests: bonding: add ipsec offload test drivers/net/bonding/bond_main.c | 2 +- drivers/net/bonding/bond_netlink.c | 17 +- include/net/bonding.h | 1 + .../selftests/drivers/net/bonding/Makefile | 3 +- .../drivers/net/bonding/bond_ipsec_offload.sh | 155 ++++++++++++++++++ .../selftests/drivers/net/bonding/config | 4 + 6 files changed, 173 insertions(+), 9 deletions(-) create mode 100755 tools/testing/selftests/drivers/net/bonding/bond_ipsec_offload.sh -- 2.39.5 (Apple Git-154)

4 months, 3 weeks

6
28
0 0

[PATCH v8 2/2] selftests/rseq: Add test for mm_cid compaction

by Gabriele Monaco

A task in the kernel (task_mm_cid_work) runs somewhat periodically to compact the mm_cid for each process. Add a test to validate that it runs correctly and timely. The test spawns 1 thread pinned to each CPU, then each thread, including the main one, runs in short bursts for some time. During this period, the mm_cids should be spanning all numbers between 0 and nproc. At the end of this phase, a thread with high enough mm_cid (>= nproc/2) is selected to be the new leader, all other threads terminate. After some time, the only running thread should see 0 as mm_cid, if that doesn't happen, the compaction mechanism didn't work and the test fails. The test never fails if only 1 core is available, in which case, we cannot test anything as the only available mm_cid is 0. Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Signed-off-by: Gabriele Monaco <gmonaco(a)redhat.com> --- tools/testing/selftests/rseq/.gitignore | 1 + tools/testing/selftests/rseq/Makefile | 2 +- .../selftests/rseq/mm_cid_compaction_test.c | 200 ++++++++++++++++++ 3 files changed, 202 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/rseq/mm_cid_compaction_test.c diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore index 16496de5f6ce4..2c89f97e4f737 100644 --- a/tools/testing/selftests/rseq/.gitignore +++ b/tools/testing/selftests/rseq/.gitignore @@ -3,6 +3,7 @@ basic_percpu_ops_test basic_percpu_ops_mm_cid_test basic_test basic_rseq_op_test +mm_cid_compaction_test param_test param_test_benchmark param_test_compare_twice diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 5a3432fceb586..ce1b38f46a355 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -16,7 +16,7 @@ OVERRIDE_TARGETS = 1 TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ param_test_benchmark param_test_compare_twice param_test_mm_cid \ - param_test_mm_cid_benchmark param_test_mm_cid_compare_twice + param_test_mm_cid_benchmark param_test_mm_cid_compare_twice mm_cid_compaction_test TEST_GEN_PROGS_EXTENDED = librseq.so diff --git a/tools/testing/selftests/rseq/mm_cid_compaction_test.c b/tools/testing/selftests/rseq/mm_cid_compaction_test.c new file mode 100644 index 0000000000000..7ddde3b657dd6 --- /dev/null +++ b/tools/testing/selftests/rseq/mm_cid_compaction_test.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include <assert.h> +#include <pthread.h> +#include <sched.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stddef.h> + +#include "../kselftest.h" +#include "rseq.h" + +#define VERBOSE 0 +#define printf_verbose(fmt, ...) \ + do { \ + if (VERBOSE) \ + printf(fmt, ##__VA_ARGS__); \ + } while (0) + +/* 0.5 s */ +#define RUNNER_PERIOD 500000 +/* Number of runs before we terminate or get the token */ +#define THREAD_RUNS 5 + +/* + * Number of times we check that the mm_cid were compacted. + * Checks are repeated every RUNNER_PERIOD. + */ +#define MM_CID_COMPACT_TIMEOUT 10 + +struct thread_args { + int cpu; + int num_cpus; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + pthread_t *tinfo; + struct thread_args *args_head; +}; + +static void __noreturn *thread_runner(void *arg) +{ + struct thread_args *args = arg; + int i, ret, curr_mm_cid; + cpu_set_t cpumask; + + CPU_ZERO(&cpumask); + CPU_SET(args->cpu, &cpumask); + ret = pthread_setaffinity_np(pthread_self(), sizeof(cpumask), &cpumask); + if (ret) { + errno = ret; + perror("Error: failed to set affinity"); + abort(); + } + pthread_barrier_wait(args->barrier); + + for (i = 0; i < THREAD_RUNS; i++) + usleep(RUNNER_PERIOD); + curr_mm_cid = rseq_current_mm_cid(); + /* + * We select one thread with high enough mm_cid to be the new leader. + * All other threads (including the main thread) will terminate. + * After some time, the mm_cid of the only remaining thread should + * converge to 0, if not, the test fails. + */ + if (curr_mm_cid >= args->num_cpus / 2 && + !pthread_mutex_trylock(args->token)) { + printf_verbose( + "cpu%d has mm_cid=%d and will be the new leader.\n", + sched_getcpu(), curr_mm_cid); + for (i = 0; i < args->num_cpus; i++) { + if (args->tinfo[i] == pthread_self()) + continue; + ret = pthread_join(args->tinfo[i], NULL); + if (ret) { + errno = ret; + perror("Error: failed to join thread"); + abort(); + } + } + pthread_barrier_destroy(args->barrier); + free(args->tinfo); + free(args->token); + free(args->barrier); + free(args->args_head); + + for (i = 0; i < MM_CID_COMPACT_TIMEOUT; i++) { + curr_mm_cid = rseq_current_mm_cid(); + printf_verbose("run %d: mm_cid=%d on cpu%d.\n", i, + curr_mm_cid, sched_getcpu()); + if (curr_mm_cid == 0) + exit(EXIT_SUCCESS); + usleep(RUNNER_PERIOD); + } + exit(EXIT_FAILURE); + } + printf_verbose("cpu%d has mm_cid=%d and is going to terminate.\n", + sched_getcpu(), curr_mm_cid); + pthread_exit(NULL); +} + +int test_mm_cid_compaction(void) +{ + cpu_set_t affinity; + int i, j, ret = 0, num_threads; + pthread_t *tinfo; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + struct thread_args *args; + + sched_getaffinity(0, sizeof(affinity), &affinity); + num_threads = CPU_COUNT(&affinity); + tinfo = calloc(num_threads, sizeof(*tinfo)); + if (!tinfo) { + perror("Error: failed to allocate tinfo"); + return -1; + } + args = calloc(num_threads, sizeof(*args)); + if (!args) { + perror("Error: failed to allocate args"); + ret = -1; + goto out_free_tinfo; + } + token = malloc(sizeof(*token)); + if (!token) { + perror("Error: failed to allocate token"); + ret = -1; + goto out_free_args; + } + barrier = malloc(sizeof(*barrier)); + if (!barrier) { + perror("Error: failed to allocate barrier"); + ret = -1; + goto out_free_token; + } + if (num_threads == 1) { + fprintf(stderr, "Cannot test on a single cpu. " + "Skipping mm_cid_compaction test.\n"); + /* only skipping the test, this is not a failure */ + goto out_free_barrier; + } + pthread_mutex_init(token, NULL); + ret = pthread_barrier_init(barrier, NULL, num_threads); + if (ret) { + errno = ret; + perror("Error: failed to initialise barrier"); + goto out_free_barrier; + } + for (i = 0, j = 0; i < CPU_SETSIZE && j < num_threads; i++) { + if (!CPU_ISSET(i, &affinity)) + continue; + args[j].num_cpus = num_threads; + args[j].tinfo = tinfo; + args[j].token = token; + args[j].barrier = barrier; + args[j].cpu = i; + args[j].args_head = args; + if (!j) { + /* The first thread is the main one */ + tinfo[0] = pthread_self(); + ++j; + continue; + } + ret = pthread_create(&tinfo[j], NULL, thread_runner, &args[j]); + if (ret) { + errno = ret; + perror("Error: failed to create thread"); + abort(); + } + ++j; + } + printf_verbose("Started %d threads.\n", num_threads); + + /* Also main thread will terminate if it is not selected as leader */ + thread_runner(&args[0]); + + /* only reached in case of errors */ +out_free_barrier: + free(barrier); +out_free_token: + free(token); +out_free_args: + free(args); +out_free_tinfo: + free(tinfo); + + return ret; +} + +int main(int argc, char **argv) +{ + if (!rseq_mm_cid_available()) { + fprintf(stderr, "Error: rseq_mm_cid unavailable\n"); + return -1; + } + if (test_mm_cid_compaction()) + return -1; + return 0; +} -- 2.48.1

4 months, 3 weeks

1
0
0 0

[PATCH] selftests:sysctl:Fix minor grammers in sysctl test

by Sumya Hoque

Hello everyone, Some minor grammer issues that I have fixed: 1. echo "If an error every occurs --> echo "If an error occurs, every execution 2. Example uses --> Example Usage Signed-off-by: Sumya Hoque <sumyahoque2012(a)gmail.com> --- tools/testing/selftests/sysctl/sysctl.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh index 84472b436c07..a4d76147ed8a 100755 --- a/tools/testing/selftests/sysctl/sysctl.sh +++ b/tools/testing/selftests/sysctl/sysctl.sh @@ -891,11 +891,11 @@ usage() echo " -l List all test ID list" echo " -h|--help Help" echo - echo "If an error every occurs execution will immediately terminate." + echo "If an error occurs, every execution will immediately terminate." echo "If you are adding a new test try using -w <test-ID> first to" echo "make sure the test passes a series of tests." echo - echo Example uses: + echo Example usage: echo echo "$TEST_NAME.sh -- executes all tests" echo "$TEST_NAME.sh -t 0002 -- Executes test ID 0002 number of times is recomended" -- 2.34.1

4 months, 3 weeks

3
3
0 0

[PATCH v3 Linux-6.12.y 1/1] selftests/mm: build with -O2

by Yifei Liu

From: Kevin Brodsky <kevin.brodsky(a)arm.com> [ Upstream commit 46036188ea1f5266df23a6149dea0df1c77cd1c7 ] The mm kselftests are currently built with no optimisation (-O0). It's unclear why, and besides being obviously suboptimal, this also prevents the pkeys tests from working as intended. Let's build all the tests with -O2. [kevin.brodsky(a)arm.com: silence unused-result warnings] Link: https://lkml.kernel.org/r/20250107170110.2819685-1-kevin.brodsky@arm.com Link: https://lkml.kernel.org/r/20241209095019.1732120-6-kevin.brodsky@arm.com Signed-off-by: Kevin Brodsky <kevin.brodsky(a)arm.com> Cc: Aruna Ramakrishna <aruna.ramakrishna(a)oracle.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: Joey Gouly <joey.gouly(a)arm.com> Cc: Keith Lucas <keith.lucas(a)oracle.com> Cc: Ryan Roberts <ryan.roberts(a)arm.com> Cc: Shuah Khan <shuah(a)kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> (cherry picked from commit 46036188ea1f5266df23a6149dea0df1c77cd1c7) [Yifei: This commit also fix the failure of pkey_sighandler_tests_64, which is also in linux-6.12.y, thus backport this commit. It is already backported to linux-6.13.y by commit d9eb5a1e76f56] Signed-off-by: Yifei Liu <yifei.l.liu(a)oracle.com> --- tools/testing/selftests/mm/Makefile | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 02e1204971b0..c0138cb19705 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -33,9 +33,16 @@ endif # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) +CFLAGS = -Wall -O2 -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm +# Some distributions (such as Ubuntu) configure GCC so that _FORTIFY_SOURCE is +# automatically enabled at -O1 or above. This triggers various unused-result +# warnings where functions such as read() or write() are called and their +# return value is not checked. Disable _FORTIFY_SOURCE to silence those +# warnings. +CFLAGS += -U_FORTIFY_SOURCE + TEST_GEN_FILES = cow TEST_GEN_FILES += compaction_test TEST_GEN_FILES += gup_longterm -- 2.46.0

4 months, 3 weeks

1
0
0 0

[PATCH net 2/2] selftests: drv-net: test installing XDP with HDS set to auto

by Jakub Kicinski

Testing bnxt: # NETIF=eth0 ./ksft-net-drv/drivers/net/hds.py KTAP version 1 1..9 ok 1 hds.get_hds ok 2 hds.get_hds_thresh ok 3 hds.set_hds_disable # SKIP disabling of HDS not supported by the device ok 4 hds.set_hds_enable ok 5 hds.set_hds_thresh_zero ok 6 hds.set_hds_thresh_max ok 7 hds.set_hds_thresh_gt ok 8 hds.set_xdp ok 9 hds.set_xdp_enabled # Totals: pass:8 fail:0 xfail:0 xpass:0 skip:1 error:0 Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: hawk(a)kernel.org CC: petrm(a)nvidia.com CC: willemb(a)google.com CC: jstancek(a)redhat.com CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/net/lib/Makefile | 3 + .../testing/selftests/net/lib/xdp_dummy.bpf.c | 13 +++++ tools/testing/selftests/drivers/net/hds.py | 55 ++++++++++++++++++- 3 files changed, 68 insertions(+), 3 deletions(-) create mode 100644 tools/testing/selftests/net/lib/xdp_dummy.bpf.c diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile index bc6b6762baf3..c22623b9a2a5 100644 --- a/tools/testing/selftests/net/lib/Makefile +++ b/tools/testing/selftests/net/lib/Makefile @@ -9,7 +9,10 @@ TEST_FILES := ../../../../../Documentation/netlink/specs TEST_FILES += ../../../../net/ynl TEST_GEN_FILES += csum +TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c)) TEST_INCLUDES := $(wildcard py/*.py sh/*.sh) include ../../lib.mk + +include ../bpf.mk diff --git a/tools/testing/selftests/net/lib/xdp_dummy.bpf.c b/tools/testing/selftests/net/lib/xdp_dummy.bpf.c new file mode 100644 index 000000000000..d988b2e0cee8 --- /dev/null +++ b/tools/testing/selftests/net/lib/xdp_dummy.bpf.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define KBUILD_MODNAME "xdp_dummy" +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("xdp") +int xdp_dummy_prog(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py index 394971b25c0b..cd1a0eea39a8 100755 --- a/tools/testing/selftests/drivers/net/hds.py +++ b/tools/testing/selftests/drivers/net/hds.py @@ -2,17 +2,26 @@ # SPDX-License-Identifier: GPL-2.0 import errno +import os from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_raises, KsftSkipEx -from lib.py import EthtoolFamily, NlError +from lib.py import CmdExitFailure, EthtoolFamily, NlError from lib.py import NetDrvEnv +from lib.py import defer, ip -def get_hds(cfg, netnl) -> None: + +def _get_hds_mode(cfg, netnl) -> str: try: rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) except NlError as e: raise KsftSkipEx('ring-get not supported by device') if 'tcp-data-split' not in rings: raise KsftSkipEx('tcp-data-split not supported by device') + return rings['tcp-data-split'] + + +def get_hds(cfg, netnl) -> None: + _get_hds_mode(cfg, netnl) + def get_hds_thresh(cfg, netnl) -> None: try: @@ -104,6 +113,44 @@ from lib.py import NetDrvEnv netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': hds_gt}) ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + +def set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "auto" / UNKNOWN mode, XDP installation should work. + """ + mode = _get_hds_mode(cfg, netnl) + if mode == 'enabled': + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + test_dir = os.path.dirname(os.path.realpath(__file__)) + prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o" + ip(f"link set dev %s xdp obj %s sec xdp" % + (cfg.ifname, prog)) + ip(f"link set dev %s xdp off" % cfg.ifname) + + +def set_xdp_enabled(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "enabled" mode, XDP installation should not work. + """ + _get_hds_mode(cfg, netnl) + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'enabled'}) + + defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + test_dir = os.path.dirname(os.path.realpath(__file__)) + prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o" + with ksft_raises(CmdExitFailure) as e: + ip(f"link set dev %s xdp obj %s sec xdp" % + (cfg.ifname, prog)) + ip(f"link set dev %s xdp off" % cfg.ifname) + + def main() -> None: with NetDrvEnv(__file__, queue_count=3) as cfg: ksft_run([get_hds, @@ -112,7 +159,9 @@ from lib.py import NetDrvEnv set_hds_enable, set_hds_thresh_zero, set_hds_thresh_max, - set_hds_thresh_gt], + set_hds_thresh_gt, + set_xdp, + set_xdp_enabled], args=(cfg, EthtoolFamily())) ksft_exit() -- 2.48.1

4 months, 3 weeks

1
0
0 0

[PATCH] selftests/bpf: DENYLIST.aarch64: enable kprobe_multi tests for ARM64

by Alexis Lothoré (eBPF Foundation)

The kprobe_multi feature was disabled on ARM64 due to the lack of fprobe support. The fprobe rewrite on function_graph has been recently merged and thus brought support for fprobes on arm64. This then enables kprobe_multi support on arm64, and so the corresponding tests can now be run on this architecture. Remove the tests depending on kprobe_multi from DENYLIST.aarch64 to allow those to run in CI. CONFIG_FPROBE is already correctly set in tools/testing/selftests/bpf/config Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore(a)bootlin.com> --- The tests being enabled with this series have been run locally in an ARM64 qemu environment, and in Github CI. I only did some testing to ensure that the tests depending on kprobe_multi now run correctly on arm64, it is fair to stress that all the hard work has actually been done by M. Hiramatsu ([0]) [0] https://lore.kernel.org/bpf/173518987627.391279.3307342580035322889.stgit@d… --- tools/testing/selftests/bpf/DENYLIST.aarch64 | 9 --------- 1 file changed, 9 deletions(-) diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 index 901349da680fa67896d279d184db78e964d9ae27..6d8feda27ce9de07d77d6e384666082923e3dc76 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -1,12 +1,3 @@ -bpf_cookie/multi_kprobe_attach_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 -bpf_cookie/multi_kprobe_link_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 -kprobe_multi_bench_attach # needs CONFIG_FPROBE -kprobe_multi_test # needs CONFIG_FPROBE -module_attach # prog 'kprobe_multi': failed to auto-attach: -95 fentry_test/fentry_many_args # fentry_many_args:FAIL:fentry_many_args_attach unexpected error: -524 fexit_test/fexit_many_args # fexit_many_args:FAIL:fexit_many_args_attach unexpected error: -524 tracing_struct/struct_many_args # struct_many_args:FAIL:tracing_struct_many_args__attach unexpected error: -524 -fill_link_info/kprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95 -fill_link_info/kretprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95 -fill_link_info/kprobe_multi_invalid_ubuff # bpf_program__attach_kprobe_multi_opts unexpected error: -95 -missed/kprobe_recursion # missed_kprobe_recursion__attach unexpected error: -95 (errno 95) --- base-commit: d3417ac824b98e8773bc04b93e09c4b93c2c6cad change-id: 20250219-enable_kprobe_multi_tests-c8d53336e5cd Best regards, -- Alexis Lothoré, Bootlin Embedded Linux and Kernel engineering https://bootlin.com

4 months, 3 weeks

2
1
0 0

[PATCH v8] Kunit to check the longest symbol length

by Sergio González Collado

The longest length of a symbol (KSYM_NAME_LEN) was increased to 512 in the reference [1]. This patch adds kunit test suite to check the longest symbol length. These tests verify that the longest symbol length defined is supported. This test can also help other efforts for longer symbol length, like [2]. The test suite defines one symbol with the longest possible length. The first test verify that functions with names of the created symbol, can be called or not. The second test, verify that the symbols are created (or not) in the kernel symbol table. [1] https://lore.kernel.org/lkml/20220802015052.10452-6-ojeda@kernel.org/ [2] https://lore.kernel.org/lkml/20240605032120.3179157-1-song@kernel.org/ Tested-by: Martin Rodriguez Reboredo <yakoyoku(a)gmail.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Reviewed-by: Rae Moar <rmoar(a)google.com> Signed-off-by: Sergio González Collado <sergio.collado(a)gmail.com> Link: https://github.com/Rust-for-Linux/linux/issues/504 --- V7 -> V8: typo fixed & rebased --- V6 -> V7: rebased --- V5 -> V6: remove tests with symbols of length KSYM_NAME_LEN+1 --- V4 -> V5: fixed typo, added improved description --- V3 -> V4: add x86 mantainers, add new reference. --- V2 -> V3: updated base and added MODULE_DESCRIPTION() and MODULE_AUTHOR() --- V1 -> V2: corrected CI tests. Added fix proposed at [3] [3] https://lore.kernel.org/lkml/Y9ES4UKl%2F+DtvAVS@gmail.com/T/#m3ef0e12bb834d… The test execution should result in something like: ``` [20:04:35] =============== longest-symbol (4 subtests) ================ [20:04:35] [PASSED] test_longest_symbol [20:04:35] [PASSED] test_longest_symbol_kallsyms [20:04:35] ================= [PASSED] longest-symbol ================== [20:04:35] ============================================================ [20:04:35] Testing complete. Ran 4 tests: passed: 4 ``` --- arch/x86/tools/insn_decoder_test.c | 3 +- lib/Kconfig.debug | 9 ++++ lib/Makefile | 2 + lib/longest_symbol_kunit.c | 84 ++++++++++++++++++++++++++++++ 4 files changed, 97 insertions(+), 1 deletion(-) create mode 100644 lib/longest_symbol_kunit.c diff --git a/arch/x86/tools/insn_decoder_test.c b/arch/x86/tools/insn_decoder_test.c index 472540aeabc2..6c2986d2ad11 100644 --- a/arch/x86/tools/insn_decoder_test.c +++ b/arch/x86/tools/insn_decoder_test.c @@ -10,6 +10,7 @@ #include <assert.h> #include <unistd.h> #include <stdarg.h> +#include <linux/kallsyms.h> #define unlikely(cond) (cond) @@ -106,7 +107,7 @@ static void parse_args(int argc, char **argv) } } -#define BUFSIZE 256 +#define BUFSIZE (256 + KSYM_NAME_LEN) int main(int argc, char **argv) { diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 1af972a92d06..62d43aa9e8f0 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2838,6 +2838,15 @@ config FORTIFY_KUNIT_TEST by the str*() and mem*() family of functions. For testing runtime traps of FORTIFY_SOURCE, see LKDTM's "FORTIFY_*" tests. +config LONGEST_SYM_KUNIT_TEST + tristate "Test the longest symbol possible" if !KUNIT_ALL_TESTS + depends on KUNIT && KPROBES + default KUNIT_ALL_TESTS + help + Tests the longest symbol possible + + If unsure, say N. + config HW_BREAKPOINT_KUNIT_TEST bool "Test hw_breakpoint constraints accounting" if !KUNIT_ALL_TESTS depends on HAVE_HW_BREAKPOINT diff --git a/lib/Makefile b/lib/Makefile index d5cfc7afbbb8..e8fec9defec2 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -393,6 +393,8 @@ obj-$(CONFIG_FORTIFY_KUNIT_TEST) += fortify_kunit.o obj-$(CONFIG_CRC_KUNIT_TEST) += crc_kunit.o obj-$(CONFIG_SIPHASH_KUNIT_TEST) += siphash_kunit.o obj-$(CONFIG_USERCOPY_KUNIT_TEST) += usercopy_kunit.o +obj-$(CONFIG_LONGEST_SYM_KUNIT_TEST) += longest_symbol_kunit.o +CFLAGS_longest_symbol_kunit.o += $(call cc-disable-warning, missing-prototypes) obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o diff --git a/lib/longest_symbol_kunit.c b/lib/longest_symbol_kunit.c new file mode 100644 index 000000000000..2a2dd1151097 --- /dev/null +++ b/lib/longest_symbol_kunit.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test the longest symbol length. Execute with: + * ./tools/testing/kunit/kunit.py run longest-symbol + * --arch=x86_64 --kconfig_add CONFIG_KPROBES=y --kconfig_add CONFIG_MODULES=y + * --kconfig_add CONFIG_RETPOLINE=n --kconfig_add CONFIG_CFI_CLANG=n + * --kconfig_add CONFIG_MITIGATION_RETPOLINE=n + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <kunit/test.h> +#include <linux/stringify.h> +#include <linux/kprobes.h> +#include <linux/kallsyms.h> + +#define DI(name) s##name##name +#define DDI(name) DI(n##name##name) +#define DDDI(name) DDI(n##name##name) +#define DDDDI(name) DDDI(n##name##name) +#define DDDDDI(name) DDDDI(n##name##name) + +#define PLUS1(name) __PASTE(name, e) + +/*Generate a symbol whose name length is 511 */ +#define LONGEST_SYM_NAME DDDDDI(g1h2i3j4k5l6m7n) + +#define RETURN_LONGEST_SYM 0xAAAAA + +noinline int LONGEST_SYM_NAME(void); +noinline int LONGEST_SYM_NAME(void) +{ + return RETURN_LONGEST_SYM; +} + +_Static_assert(sizeof(__stringify(LONGEST_SYM_NAME)) == KSYM_NAME_LEN, +"Incorrect symbol length found. Expected KSYM_NAME_LEN: " +__stringify(KSYM_NAME) ", but found: " +__stringify(sizeof(LONGEST_SYM_NAME))); + +static void test_longest_symbol(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, RETURN_LONGEST_SYM, LONGEST_SYM_NAME()); +}; + +static void test_longest_symbol_kallsyms(struct kunit *test) +{ + unsigned long (*kallsyms_lookup_name)(const char *name); + static int (*longest_sym)(void); + + struct kprobe kp = { + .symbol_name = "kallsyms_lookup_name", + }; + + if (register_kprobe(&kp) < 0) { + pr_info("%s: kprobe not registered\n", __func__); + KUNIT_FAIL(test, "test_longest_symbol kallsyms: kprobe not registered\n"); + return; + } + + kunit_warn(test, "test_longest_symbol kallsyms: kprobe registered\n"); + kallsyms_lookup_name = (unsigned long (*)(const char *name))kp.addr; + unregister_kprobe(&kp); + + longest_sym = + (void *) kallsyms_lookup_name(__stringify(LONGEST_SYM_NAME)); + KUNIT_EXPECT_EQ(test, RETURN_LONGEST_SYM, longest_sym()); +}; + +static struct kunit_case longest_symbol_test_cases[] = { + KUNIT_CASE(test_longest_symbol), + KUNIT_CASE(test_longest_symbol_kallsyms), + {} +}; + +static struct kunit_suite longest_symbol_test_suite = { + .name = "longest-symbol", + .test_cases = longest_symbol_test_cases, +}; +kunit_test_suite(longest_symbol_test_suite); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Test the longest symbol length"); +MODULE_AUTHOR("Sergio González Collado"); base-commit: a86bf2283d2c9769205407e2b54777c03d012939 -- 2.39.2

4 months, 3 weeks

2
3
0 0

[PATCH v4 0/3] printf: convert self-test to KUnit

by Tamir Duberstein

This is one of just 3 remaining "Test Module" kselftests (the others being bitmap and scanf), the rest having been converted to KUnit. I tested this using: $ tools/testing/kunit/kunit.py run --arch arm64 --make_options LLVM=1 printf I have also sent out a series converting scanf[0]. Link: https://lore.kernel.org/all/20250204-scanf-kunit-convert-v3-0-386d7c3ee714@… [0] Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- Changes in v4: - Add patch "implicate test line in failure messages". - Rebase on linux-next, move scanf_kunit.c into lib/tests/. - Link to v3: https://lore.kernel.org/r/20250210-printf-kunit-convert-v3-0-ee6ac5500f5e@g… Changes in v3: - Remove extraneous trailing newlines from failure messages. - Replace `pr_warn` with `kunit_warn`. - Drop arch changes. - Remove KUnit boilerplate from CONFIG_PRINTF_KUNIT_TEST help text. - Restore `total_tests` counting. - Remove tc_fail macro in last patch. - Link to v2: https://lore.kernel.org/r/20250207-printf-kunit-convert-v2-0-057b23860823@g… Changes in v2: - Incorporate code review from prior work[0] by Arpitha Raghunandan. - Link to v1: https://lore.kernel.org/r/20250204-printf-kunit-convert-v1-0-ecf1b846a4de@g… Link: https://lore.kernel.org/lkml/20200817043028.76502-1-98.arpi@gmail.com/t/#u [0] --- Tamir Duberstein (3): printf: convert self-test to KUnit printf: break kunit into test cases printf: implicate test line in failure messages Documentation/core-api/printk-formats.rst | 4 +- MAINTAINERS | 2 +- lib/Kconfig.debug | 12 +- lib/Makefile | 1 - lib/tests/Makefile | 1 + lib/{test_printf.c => tests/printf_kunit.c} | 437 ++++++++++++---------------- tools/testing/selftests/lib/config | 1 - tools/testing/selftests/lib/printf.sh | 4 - 8 files changed, 200 insertions(+), 262 deletions(-) --- base-commit: 7b7a883c7f4de1ee5040bd1c32aabaafde54d209 change-id: 20250131-printf-kunit-convert-fd4012aa2ec6 Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

4 months, 3 weeks

2
5
0 0

[PATCH] spelling mistake

by goralbaris

Signed-off-by: goralbaris <goralbaris(a)gmail.com> --- tools/testing/selftests/kvm/x86_64/hyperv_features.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 068e9c69710d..db442bf3b8d3 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -457,7 +457,7 @@ static void guest_test_msrs_access(void) msr->fault_expected = true; break; case 45: - /* MSR is vailable when CPUID feature bit is set */ + /* MSR is available when CPUID feature bit is set */ if (!has_invtsc) goto next_stage; vcpu_set_cpuid_feature(vcpu, HV_ACCESS_TSC_INVARIANT); -- 2.34.1

4 months, 3 weeks

1
0
0 0

[PATCH bpf-next v2 0/4] selftests/bpf: tc_links/tc_opts: Unserialize tests

by Bastien Curutchet (eBPF Foundation)

Hi all, Both tc_links.c and tc_opts.c do their tests on the loopback interface. It prevents from parallelizing their executions. Add a new behaviour to the test_progs framework that creates and opens a new network namespace to run a test in it. This is done automatically on tests whose names start with 'ns_'. One test already has a name starting with 'ns_', so PATCH 1 renames it to avoid conflicts. PATCH 2 introduces the test_progs 'feature'. PATCH 3 & 4 convert some tests to use these dedicated namespaces. Signed-off-by: Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com> --- Changes in v2: - Handle the netns creation / opening directly in test_progs - Link to v1: https://lore.kernel.org/bpf/e3838d93-04e3-4e96-af53-e9e63550d7ba@bootlin.com --- Bastien Curutchet (eBPF Foundation) (4): selftests/bpf: ns_current_pid_tgid: Rename the test function selftests/bpf: Optionally open a dedicated namespace to run test in it selftests/bpf: tc_links/tc_opts: Unserialize tests selftests/bpf: ns_current_pid_tgid: Use test_progs's ns_ feature .../selftests/bpf/prog_tests/ns_current_pid_tgid.c | 47 ++++++++-------------- tools/testing/selftests/bpf/prog_tests/tc_links.c | 28 ++++++------- tools/testing/selftests/bpf/prog_tests/tc_opts.c | 40 +++++++++--------- tools/testing/selftests/bpf/test_progs.c | 12 ++++++ 4 files changed, 63 insertions(+), 64 deletions(-) --- base-commit: a814b9be27fb3c3f49343aee4b015b76f5875558 change-id: 20250219-b4-tc_links-b6d5bf709e1f Best regards, -- Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com>

4 months, 3 weeks

3
6
0 0

[PATCH v1 00/13] iommu: Add MSI mapping support with nested SMMU

by Nicolin Chen

[ Background ] On ARM GIC systems and others, the target address of the MSI is translated by the IOMMU. For GIC, the MSI address page is called "ITS" page. When the IOMMU is disabled, the MSI address is programmed to the physical location of the GIC ITS page (e.g. 0x20200000). When the IOMMU is enabled, the ITS page is behind the IOMMU, so the MSI address is programmed to an allocated IO virtual address (a.k.a IOVA), e.g. 0xFFFF0000, which must be mapped to the physical ITS page: IOVA (0xFFFF0000) ===> PA (0x20200000). When a 2-stage translation is enabled, IOVA will be still used to program the MSI address, though the mappings will be in two stages: IOVA (0xFFFF0000) ===> IPA (e.g. 0x80900000) ===> PA (0x20200000) (IPA stands for Intermediate Physical Address). If the device that generates MSI is attached to an IOMMU_DOMAIN_DMA, the IOVA is dynamically allocated from the top of the IOVA space. If attached to an IOMMU_DOMAIN_UNMANAGED (e.g. a VFIO passthrough device), the IOVA is fixed to an MSI window reported by the IOMMU driver via IOMMU_RESV_SW_MSI, which is hardwired to MSI_IOVA_BASE (IOVA==0x8000000) for ARM IOMMUs. So far, this IOMMU_RESV_SW_MSI works well as kernel is entirely in charge of the IOMMU translation (1-stage translation), since the IOVA for the ITS page is fixed and known by kernel. However, with virtual machine enabling a nested IOMMU translation (2-stage), a guest kernel directly controls the stage-1 translation with an IOMMU_DOMAIN_DMA, mapping a vITS page (at an IPA 0x80900000) onto its own IOVA space (e.g. 0xEEEE0000). Then, the host kernel can't know that guest-level IOVA to program the MSI address. There have been two approaches to solve this problem: 1. Create an identity mapping in the stage-1. VMM could insert a few RMRs (Reserved Memory Regions) in guest's IORT. Then the guest kernel would fetch these RMR entries from the IORT and create an IOMMU_RESV_DIRECT region per iommu group for a direct mapping. Eventually, the mappings would look like: IOVA (0x8000000) === IPA (0x8000000) ===> 0x20200000 This requires an IOMMUFD ioctl for kernel and VMM to agree on the IPA. 2. Forward the guest-level MSI IOVA captured by VMM to the host-level GIC driver, to program the correct MSI IOVA. Forward the VMM-defined vITS page location (IPA) to the kernel for the stage-2 mapping. Eventually: IOVA (0xFFFF0000) ===> IPA (0x80900000) ===> PA (0x20200000) This requires a VFIO ioctl (for IOVA) and an IOMMUFD ioctl (for IPA). Worth mentioning that when Eric Auger was working on the same topic with the VFIO iommu uAPI, he had the approach (2) first, and then switched to the approach (1), suggested by Jean-Philippe for reduction of complexity. The approach (1) basically feels like the existing VFIO passthrough that has a 1-stage mapping for the unmanaged domain, yet only by shifting the MSI mapping from stage 1 (guest-has-no-iommu case) to stage 2 (guest-has- iommu case). So, it could reuse the existing IOMMU_RESV_SW_MSI piece, by sharing the same idea of "VMM leaving everything to the kernel". The approach (2) is an ideal solution, yet it requires additional effort for kernel to be aware of the 1-stage gIOVA(s) and 2-stage IPAs for vITS page(s), which demands VMM to closely cooperate. * It also brings some complicated use cases to the table where the host or/and guest system(s) has/have multiple ITS pages. [ Execution ] Though these two approaches feel very different on the surface, they can share some underlying common infrastructure. Currently, only one pair of sw_msi functions (prepare/compose) are provided by dma-iommu for irqchip drivers to directly use. There could be different versions of functions from different domain owners: for existing VFIO passthrough cases and in- kernel DMA domain cases, reuse the existing dma-iommu's version of sw_msi functions; for nested translation use cases, there can be another version of sw_msi functions to handle mapping and msi_msg(s) differently. As a part-1 supporting the approach (1), i.e. the RMR solution: - Get rid of the duplication in the "compose" function - Introduce a function pointer for the previously "prepare" function - Allow different domain owners to set their own "sw_msi" implementations - Implement an iommufd_sw_msi function to additionally support a nested translation use case using the approach (1) - Add a pair of IOMMUFD options for a SW_MSI window for kernel and VMM to agree on (for approach 1) [ Future Plan ] Part-2 and beyond will continue the effort of supporting the approach (2) for a complete vITS-to-pITS mapping: 1) Map the phsical ITS page (potentially via IOMMUFD_CMD_IOAS_MAP_MSI) 2) Convey the IOVAs per-irq (potentially via VFIO_IRQ_SET_ACTION_PREPARE) Note that the set_option uAPI in this series might not fit since this requires it is an array of MSI IOVAs.) --- This is a joint effort that includes Jason's rework in irq/iommu/iommufd base level and my additional patches on top of that for new uAPIs. This series is on github: https://github.com/nicolinc/iommufd/commits/iommufd_msi_p1-v1 Pairing QEMU branch for testing (approach 1): https://github.com/nicolinc/qemu/commits/wip/for_iommufd_msi_p1-v1-rmr (Note: QEMU virt command no longer requires iommmufd object v.s. RFCv2) Changelog v1 * Rebase on v6.14-rc1 and iommufd_attach_handle-v1 series https://lore.kernel.org/all/cover.1738645017.git.nicolinc@nvidia.com/ * Correct typos * Replace set_bit with __set_bit * Use a common helper to get iommufd_handle * Add kdoc for iommu_msi_iova/iommu_msi_page_shift * Rename msi_msg_set_msi_addr() to msi_msg_set_addr() * Update selftest for a better coverage for the new options * Change IOMMU_OPTION_SW_MSI_START/SIZE to be per-idev and properly check against device's reserved region list RFCv2 https://lore.kernel.org/kvm/cover.1736550979.git.nicolinc@nvidia.com/ * Rebase on v6.13-rc6 * Drop all the irq/pci patches and rework the compose function instead * Add a new sw_msi op to iommu_domain for a per type implementation and let iommufd core has its own implementation to support both approaches * Add RMR-solution (approach 1) support since it is straightforward and have been used in some out-of-tree projects widely RFCv1 https://lore.kernel.org/kvm/cover.1731130093.git.nicolinc@nvidia.com/ Thanks! Nicolin Jason Gunthorpe (5): genirq/msi: Store the IOMMU IOVA directly in msi_desc instead of iommu_cookie genirq/msi: Rename iommu_dma_compose_msi_msg() to msi_msg_set_addr() iommu: Make iommu_dma_prepare_msi() into a generic operation irqchip: Have CONFIG_IRQ_MSI_IOMMU be selected by the irqchips that need it iommufd: Implement sw_msi support natively Nicolin Chen (8): iommu: Turn fault_data to iommufd private pointer iommu: Turn iova_cookie to dma-iommu private pointer iommufd/device: Move sw_msi_start from igroup to idev iommufd: Pass in idev to iopt_table_enforce_dev_resv_regions iommufd: Add IOMMU_OPTION_SW_MSI_START/SIZE ioctls iommufd/selftest: Add MOCK_FLAGS_DEVICE_NO_ATTACH iommufd/selftest: Add a testing reserved region iommufd/selftest: Add coverage for IOMMU_OPTION_SW_MSI_START/SIZE drivers/iommu/Kconfig | 1 - drivers/irqchip/Kconfig | 4 + kernel/irq/Kconfig | 1 + drivers/iommu/iommufd/iommufd_private.h | 29 ++- drivers/iommu/iommufd/iommufd_test.h | 4 + include/linux/iommu.h | 58 ++++-- include/linux/msi.h | 47 +++-- include/uapi/linux/iommufd.h | 20 +- drivers/iommu/dma-iommu.c | 63 ++---- drivers/iommu/iommu.c | 29 +++ drivers/iommu/iommufd/device.c | 196 ++++++++++++++---- drivers/iommu/iommufd/fault.c | 2 +- drivers/iommu/iommufd/hw_pagetable.c | 5 +- drivers/iommu/iommufd/io_pagetable.c | 18 +- drivers/iommu/iommufd/ioas.c | 97 +++++++++ drivers/iommu/iommufd/main.c | 13 ++ drivers/iommu/iommufd/selftest.c | 41 +++- drivers/irqchip/irq-gic-v2m.c | 5 +- drivers/irqchip/irq-gic-v3-its.c | 13 +- drivers/irqchip/irq-gic-v3-mbi.c | 12 +- drivers/irqchip/irq-ls-scfg-msi.c | 5 +- tools/testing/selftests/iommu/iommufd.c | 97 +++++++++ .../selftests/iommu/iommufd_fail_nth.c | 21 ++ 23 files changed, 608 insertions(+), 173 deletions(-) base-commit: 2b5bc8c9425fd87e094a08f72498536133da80e1 -- 2.43.0

4 months, 3 weeks

4
27
0 0

[PATCH bpf-next v2 0/6] XDP metadata support for tun driver

by Marcus Wichelmann

Hi all, Thank you for your review comments. Here is an updated patch series with the requested changes. To add a selftest for the metadata support of the tun driver, I refactored an existing "xdp_context_functional" test which already tested something similar but for the veth driver. I made the testing logic behind it more reusable so that it also works for the tun driver and possibly other drivers in the future. The last patch ("fix file descriptor assertion in open_tuntap helper") fixes an assertion in an existing helper function that I just moved and reused. Somehow the file descriptor for /dev/net/tun turned out to be 0 when running in the BPF kernel-patches GitHub CI, so the assert condition needed adjustment: https://github.com/kernel-patches/bpf/actions/runs/13339140896 Successful pipeline: https://github.com/kernel-patches/bpf/actions/runs/13372306548 --- v2: - submit against bpf-next subtree - split commits and improved commit messages - remove redundant metasize check and add clarifying comment instead - use max() instead of ternary operator - add selftest for metadata support in the tun driver v1: https://lore.kernel.org/all/20250130171614.1657224-1-marcus.wichelmann@hetz… Marcus Wichelmann (6): net: tun: enable XDP metadata support net: tun: enable transfer of XDP metadata to skb selftests/bpf: move open_tuntap to network helpers selftests/bpf: refactor xdp_context_functional test and bpf program selftests/bpf: add test for XDP metadata support in tun driver selftests/bpf: fix file descriptor assertion in open_tuntap helper drivers/net/tun.c | 24 ++- tools/testing/selftests/bpf/network_helpers.c | 28 ++++ tools/testing/selftests/bpf/network_helpers.h | 3 + .../selftests/bpf/prog_tests/lwt_helpers.h | 29 ---- .../bpf/prog_tests/xdp_context_test_run.c | 152 +++++++++++++++--- .../selftests/bpf/progs/test_xdp_meta.c | 56 ++++--- 6 files changed, 215 insertions(+), 77 deletions(-) -- 2.43.0

4 months, 3 weeks

3
15
0 0

[PATCH] selftests/mm: run_vmtests.sh: fix half_ufd_size_MB calculation

by Rafael Aquini

From: Rafael Aquini <raquini(a)redhat.com> We noticed that uffd-stress test was always failing to run when invoked for the hugetlb profiles on x86_64 systems with a processor count of 64 or bigger: ... # ------------------------------------ # running ./uffd-stress hugetlb 128 32 # ------------------------------------ # ERROR: invalid MiB (errno=9, @uffd-stress.c:459) ... # [FAIL] not ok 3 uffd-stress hugetlb 128 32 # exit=1 ... The problem boils down to how run_vmtests.sh (mis)calculates the size of the region it feeds to uffd-stress. The latter expects to see an amount of MiB while the former is just giving out the number of free hugepages halved down. This measurement discrepancy ends up violating uffd-stress' assertion on number of hugetlb pages allocated per CPU, causing it to bail out with the error above. This commit fixes that issue by adjusting run_vmtests.sh's half_ufd_size_MB calculation so it properly renders the region size in MiB, as expected, while maintaining all of its original constraints in place. Fixes: 2e47a445d7b3 ("selftests/mm: run_vmtests.sh: fix hugetlb mem size calculation") Signed-off-by: Rafael Aquini <raquini(a)redhat.com> --- tools/testing/selftests/mm/run_vmtests.sh | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 333c468c2699..157d07e5aaa3 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -304,7 +304,9 @@ uffd_stress_bin=./uffd-stress CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon 20 16 # Hugetlb tests require source and destination huge pages. Pass in half # the size of the free pages we have, which is used for *each*. -half_ufd_size_MB=$((freepgs / 2)) +# uffd-stress expects a region expressed in MiB, so we adjust +# half_ufd_size_MB accordingly. +half_ufd_size_MB=$(((freepgs * hpgsize_KB) / 1024 / 2)) CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 32 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb-private "$half_ufd_size_MB" 32 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem 20 16 -- 2.47.0

4 months, 3 weeks

3
2
0 0

[RFC PATCH 0/2] Add NV Selftest cases

by Ganapatrao Kulkarni

In this patch seried, modified kvm selftests code to enable guest code to run in vEL2(As guest Hypervisor). Also added test cases to test guest code booting in vEL2 and register access of VNCR mapped registers. This patchset is created as per discussions over ml[1]. Posting RFC patch for the early feedback and to further explore requirements and test cases. Ganapatrao Kulkarni (2): KVM: arm64: nv: selftests: Add guest hypervisor test KVM: arm64: nv: selftests: Access VNCR mapped registers tools/testing/selftests/kvm/Makefile.kvm | 2 + .../selftests/kvm/arm64/nv_guest_hypervisor.c | 83 ++++++ .../selftests/kvm/arm64/nv_vncr_regs_test.c | 255 ++++++++++++++++++ .../kvm/include/arm64/kvm_util_arch.h | 3 + .../selftests/kvm/include/arm64/nv_util.h | 28 ++ .../testing/selftests/kvm/include/kvm_util.h | 1 + .../selftests/kvm/lib/arm64/processor.c | 59 +++- 7 files changed, 417 insertions(+), 14 deletions(-) create mode 100644 tools/testing/selftests/kvm/arm64/nv_guest_hypervisor.c create mode 100644 tools/testing/selftests/kvm/arm64/nv_vncr_regs_test.c create mode 100644 tools/testing/selftests/kvm/include/arm64/nv_util.h -- 2.48.1

4 months, 3 weeks

2
9
0 0

[PATCH v7 2/2] selftests/rseq: Add test for mm_cid compaction

by Gabriele Monaco

A task in the kernel (task_mm_cid_work) runs somewhat periodically to compact the mm_cid for each process. Add a test to validate that it runs correctly and timely. The test spawns 1 thread pinned to each CPU, then each thread, including the main one, runs in short bursts for some time. During this period, the mm_cids should be spanning all numbers between 0 and nproc. At the end of this phase, a thread with high enough mm_cid (>= nproc/2) is selected to be the new leader, all other threads terminate. After some time, the only running thread should see 0 as mm_cid, if that doesn't happen, the compaction mechanism didn't work and the test fails. The test never fails if only 1 core is available, in which case, we cannot test anything as the only available mm_cid is 0. Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Signed-off-by: Gabriele Monaco <gmonaco(a)redhat.com> --- tools/testing/selftests/rseq/.gitignore | 1 + tools/testing/selftests/rseq/Makefile | 2 +- .../selftests/rseq/mm_cid_compaction_test.c | 200 ++++++++++++++++++ 3 files changed, 202 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/rseq/mm_cid_compaction_test.c diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore index 16496de5f6ce4..2c89f97e4f737 100644 --- a/tools/testing/selftests/rseq/.gitignore +++ b/tools/testing/selftests/rseq/.gitignore @@ -3,6 +3,7 @@ basic_percpu_ops_test basic_percpu_ops_mm_cid_test basic_test basic_rseq_op_test +mm_cid_compaction_test param_test param_test_benchmark param_test_compare_twice diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 5a3432fceb586..ce1b38f46a355 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -16,7 +16,7 @@ OVERRIDE_TARGETS = 1 TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ param_test_benchmark param_test_compare_twice param_test_mm_cid \ - param_test_mm_cid_benchmark param_test_mm_cid_compare_twice + param_test_mm_cid_benchmark param_test_mm_cid_compare_twice mm_cid_compaction_test TEST_GEN_PROGS_EXTENDED = librseq.so diff --git a/tools/testing/selftests/rseq/mm_cid_compaction_test.c b/tools/testing/selftests/rseq/mm_cid_compaction_test.c new file mode 100644 index 0000000000000..7ddde3b657dd6 --- /dev/null +++ b/tools/testing/selftests/rseq/mm_cid_compaction_test.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include <assert.h> +#include <pthread.h> +#include <sched.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stddef.h> + +#include "../kselftest.h" +#include "rseq.h" + +#define VERBOSE 0 +#define printf_verbose(fmt, ...) \ + do { \ + if (VERBOSE) \ + printf(fmt, ##__VA_ARGS__); \ + } while (0) + +/* 0.5 s */ +#define RUNNER_PERIOD 500000 +/* Number of runs before we terminate or get the token */ +#define THREAD_RUNS 5 + +/* + * Number of times we check that the mm_cid were compacted. + * Checks are repeated every RUNNER_PERIOD. + */ +#define MM_CID_COMPACT_TIMEOUT 10 + +struct thread_args { + int cpu; + int num_cpus; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + pthread_t *tinfo; + struct thread_args *args_head; +}; + +static void __noreturn *thread_runner(void *arg) +{ + struct thread_args *args = arg; + int i, ret, curr_mm_cid; + cpu_set_t cpumask; + + CPU_ZERO(&cpumask); + CPU_SET(args->cpu, &cpumask); + ret = pthread_setaffinity_np(pthread_self(), sizeof(cpumask), &cpumask); + if (ret) { + errno = ret; + perror("Error: failed to set affinity"); + abort(); + } + pthread_barrier_wait(args->barrier); + + for (i = 0; i < THREAD_RUNS; i++) + usleep(RUNNER_PERIOD); + curr_mm_cid = rseq_current_mm_cid(); + /* + * We select one thread with high enough mm_cid to be the new leader. + * All other threads (including the main thread) will terminate. + * After some time, the mm_cid of the only remaining thread should + * converge to 0, if not, the test fails. + */ + if (curr_mm_cid >= args->num_cpus / 2 && + !pthread_mutex_trylock(args->token)) { + printf_verbose( + "cpu%d has mm_cid=%d and will be the new leader.\n", + sched_getcpu(), curr_mm_cid); + for (i = 0; i < args->num_cpus; i++) { + if (args->tinfo[i] == pthread_self()) + continue; + ret = pthread_join(args->tinfo[i], NULL); + if (ret) { + errno = ret; + perror("Error: failed to join thread"); + abort(); + } + } + pthread_barrier_destroy(args->barrier); + free(args->tinfo); + free(args->token); + free(args->barrier); + free(args->args_head); + + for (i = 0; i < MM_CID_COMPACT_TIMEOUT; i++) { + curr_mm_cid = rseq_current_mm_cid(); + printf_verbose("run %d: mm_cid=%d on cpu%d.\n", i, + curr_mm_cid, sched_getcpu()); + if (curr_mm_cid == 0) + exit(EXIT_SUCCESS); + usleep(RUNNER_PERIOD); + } + exit(EXIT_FAILURE); + } + printf_verbose("cpu%d has mm_cid=%d and is going to terminate.\n", + sched_getcpu(), curr_mm_cid); + pthread_exit(NULL); +} + +int test_mm_cid_compaction(void) +{ + cpu_set_t affinity; + int i, j, ret = 0, num_threads; + pthread_t *tinfo; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + struct thread_args *args; + + sched_getaffinity(0, sizeof(affinity), &affinity); + num_threads = CPU_COUNT(&affinity); + tinfo = calloc(num_threads, sizeof(*tinfo)); + if (!tinfo) { + perror("Error: failed to allocate tinfo"); + return -1; + } + args = calloc(num_threads, sizeof(*args)); + if (!args) { + perror("Error: failed to allocate args"); + ret = -1; + goto out_free_tinfo; + } + token = malloc(sizeof(*token)); + if (!token) { + perror("Error: failed to allocate token"); + ret = -1; + goto out_free_args; + } + barrier = malloc(sizeof(*barrier)); + if (!barrier) { + perror("Error: failed to allocate barrier"); + ret = -1; + goto out_free_token; + } + if (num_threads == 1) { + fprintf(stderr, "Cannot test on a single cpu. " + "Skipping mm_cid_compaction test.\n"); + /* only skipping the test, this is not a failure */ + goto out_free_barrier; + } + pthread_mutex_init(token, NULL); + ret = pthread_barrier_init(barrier, NULL, num_threads); + if (ret) { + errno = ret; + perror("Error: failed to initialise barrier"); + goto out_free_barrier; + } + for (i = 0, j = 0; i < CPU_SETSIZE && j < num_threads; i++) { + if (!CPU_ISSET(i, &affinity)) + continue; + args[j].num_cpus = num_threads; + args[j].tinfo = tinfo; + args[j].token = token; + args[j].barrier = barrier; + args[j].cpu = i; + args[j].args_head = args; + if (!j) { + /* The first thread is the main one */ + tinfo[0] = pthread_self(); + ++j; + continue; + } + ret = pthread_create(&tinfo[j], NULL, thread_runner, &args[j]); + if (ret) { + errno = ret; + perror("Error: failed to create thread"); + abort(); + } + ++j; + } + printf_verbose("Started %d threads.\n", num_threads); + + /* Also main thread will terminate if it is not selected as leader */ + thread_runner(&args[0]); + + /* only reached in case of errors */ +out_free_barrier: + free(barrier); +out_free_token: + free(token); +out_free_args: + free(args); +out_free_tinfo: + free(tinfo); + + return ret; +} + +int main(int argc, char **argv) +{ + if (!rseq_mm_cid_available()) { + fprintf(stderr, "Error: rseq_mm_cid unavailable\n"); + return -1; + } + if (test_mm_cid_compaction()) + return -1; + return 0; +} -- 2.48.1

4 months, 3 weeks

1
0
0 0

[PATCH v5 3/3] rseq/selftests: Add test for mm_cid compaction

by Gabriele Monaco

A task in the kernel (task_mm_cid_work) runs somewhat periodically to compact the mm_cid for each process. Add a test to validate that it runs correctly and timely. The test spawns 1 thread pinned to each CPU, then each thread, including the main one, runs in short bursts for some time. During this period, the mm_cids should be spanning all numbers between 0 and nproc. At the end of this phase, a thread with high enough mm_cid (>= nproc/2) is selected to be the new leader, all other threads terminate. After some time, the only running thread should see 0 as mm_cid, if that doesn't happen, the compaction mechanism didn't work and the test fails. The test never fails if only 1 core is available, in which case, we cannot test anything as the only available mm_cid is 0. To: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Signed-off-by: Gabriele Monaco <gmonaco(a)redhat.com> --- tools/testing/selftests/rseq/.gitignore | 1 + tools/testing/selftests/rseq/Makefile | 2 +- .../selftests/rseq/mm_cid_compaction_test.c | 200 ++++++++++++++++++ 3 files changed, 202 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/rseq/mm_cid_compaction_test.c diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore index 16496de5f6ce4..2c89f97e4f737 100644 --- a/tools/testing/selftests/rseq/.gitignore +++ b/tools/testing/selftests/rseq/.gitignore @@ -3,6 +3,7 @@ basic_percpu_ops_test basic_percpu_ops_mm_cid_test basic_test basic_rseq_op_test +mm_cid_compaction_test param_test param_test_benchmark param_test_compare_twice diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 5a3432fceb586..ce1b38f46a355 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -16,7 +16,7 @@ OVERRIDE_TARGETS = 1 TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ param_test_benchmark param_test_compare_twice param_test_mm_cid \ - param_test_mm_cid_benchmark param_test_mm_cid_compare_twice + param_test_mm_cid_benchmark param_test_mm_cid_compare_twice mm_cid_compaction_test TEST_GEN_PROGS_EXTENDED = librseq.so diff --git a/tools/testing/selftests/rseq/mm_cid_compaction_test.c b/tools/testing/selftests/rseq/mm_cid_compaction_test.c new file mode 100644 index 0000000000000..701719b320049 --- /dev/null +++ b/tools/testing/selftests/rseq/mm_cid_compaction_test.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include <assert.h> +#include <pthread.h> +#include <sched.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stddef.h> + +#include "../kselftest.h" +#include "rseq.h" + +#define VERBOSE 0 +#define printf_verbose(fmt, ...) \ + do { \ + if (VERBOSE) \ + printf(fmt, ##__VA_ARGS__); \ + } while (0) + +/* 0.5 s */ +#define RUNNER_PERIOD 500000 +/* Number of runs before we terminate or get the token */ +#define THREAD_RUNS 5 + +/* + * Number of times we check that the mm_cid were compacted. + * Checks are repeated every RUNNER_PERIOD. + */ +#define MM_CID_COMPACT_TIMEOUT 10 + +struct thread_args { + int cpu; + int num_cpus; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + pthread_t *tinfo; + struct thread_args *args_head; +}; + +static void __noreturn *thread_runner(void *arg) +{ + struct thread_args *args = arg; + int i, ret, curr_mm_cid; + cpu_set_t cpumask; + + CPU_ZERO(&cpumask); + CPU_SET(args->cpu, &cpumask); + ret = pthread_setaffinity_np(pthread_self(), sizeof(cpumask), &cpumask); + if (ret) { + errno = ret; + perror("Error: failed to set affinity"); + abort(); + } + pthread_barrier_wait(args->barrier); + + for (i = 0; i < THREAD_RUNS; i++) + usleep(RUNNER_PERIOD); + curr_mm_cid = rseq_current_mm_cid(); + /* + * We select one thread with high enough mm_cid to be the new leader + * all other threads (including the main thread) will terminate. + * After some time, the mm_cid of the only remaining thread should + * converge to 0, if not, the test fails. + */ + if (curr_mm_cid >= args->num_cpus / 2 && + !pthread_mutex_trylock(args->token)) { + printf_verbose( + "cpu%d has mm_cid=%d and will be the new leader.\n", + sched_getcpu(), curr_mm_cid); + for (i = 0; i < args->num_cpus; i++) { + if (args->tinfo[i] == pthread_self()) + continue; + ret = pthread_join(args->tinfo[i], NULL); + if (ret) { + errno = ret; + perror("Error: failed to join thread"); + abort(); + } + } + pthread_barrier_destroy(args->barrier); + free(args->tinfo); + free(args->token); + free(args->barrier); + free(args->args_head); + + for (i = 0; i < MM_CID_COMPACT_TIMEOUT; i++) { + curr_mm_cid = rseq_current_mm_cid(); + printf_verbose("run %d: mm_cid=%d on cpu%d.\n", i, + curr_mm_cid, sched_getcpu()); + if (curr_mm_cid == 0) + exit(EXIT_SUCCESS); + usleep(RUNNER_PERIOD); + } + exit(EXIT_FAILURE); + } + printf_verbose("cpu%d has mm_cid=%d and is going to terminate.\n", + sched_getcpu(), curr_mm_cid); + pthread_exit(NULL); +} + +int test_mm_cid_compaction(void) +{ + cpu_set_t affinity; + int i, j, ret = 0, num_threads; + pthread_t *tinfo; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + struct thread_args *args; + + sched_getaffinity(0, sizeof(affinity), &affinity); + num_threads = CPU_COUNT(&affinity); + tinfo = calloc(num_threads, sizeof(*tinfo)); + if (!tinfo) { + perror("Error: failed to allocate tinfo"); + return -1; + } + args = calloc(num_threads, sizeof(*args)); + if (!args) { + perror("Error: failed to allocate args"); + ret = -1; + goto out_free_tinfo; + } + token = malloc(sizeof(*token)); + if (!token) { + perror("Error: failed to allocate token"); + ret = -1; + goto out_free_args; + } + barrier = malloc(sizeof(*barrier)); + if (!barrier) { + perror("Error: failed to allocate barrier"); + ret = -1; + goto out_free_token; + } + if (num_threads == 1) { + fprintf(stderr, "Cannot test on a single cpu. " + "Skipping mm_cid_compaction test.\n"); + /* only skipping the test, this is not a failure */ + goto out_free_barrier; + } + pthread_mutex_init(token, NULL); + ret = pthread_barrier_init(barrier, NULL, num_threads); + if (ret) { + errno = ret; + perror("Error: failed to initialise barrier"); + goto out_free_barrier; + } + for (i = 0, j = 0; i < CPU_SETSIZE && j < num_threads; i++) { + if (!CPU_ISSET(i, &affinity)) + continue; + args[j].num_cpus = num_threads; + args[j].tinfo = tinfo; + args[j].token = token; + args[j].barrier = barrier; + args[j].cpu = i; + args[j].args_head = args; + if (!j) { + /* The first thread is the main one */ + tinfo[0] = pthread_self(); + ++j; + continue; + } + ret = pthread_create(&tinfo[j], NULL, thread_runner, &args[j]); + if (ret) { + errno = ret; + perror("Error: failed to create thread"); + abort(); + } + ++j; + } + printf_verbose("Started %d threads.\n", num_threads); + + /* Also main thread will terminate if it is not selected as leader */ + thread_runner(&args[0]); + + /* only reached in case of errors */ +out_free_barrier: + free(barrier); +out_free_token: + free(token); +out_free_args: + free(args); +out_free_tinfo: + free(tinfo); + + return ret; +} + +int main(int argc, char **argv) +{ + if (!rseq_mm_cid_available()) { + fprintf(stderr, "Error: rseq_mm_cid unavailable\n"); + return -1; + } + if (test_mm_cid_compaction()) + return -1; + return 0; +} -- 2.48.1

4 months, 3 weeks

3
4
0 0

[PATCH net-next v5 0/8] Some pktgen fixes/improvments (part I)

by Peter Seiderer

While taking a look at '[PATCH net] pktgen: Avoid out-of-range in get_imix_entries' ([1]) and '[PATCH net v2] pktgen: Avoid out-of-bounds access in get_imix_entries' ([2], [3]) and doing some tests and code review I detected that the /proc/net/pktgen/... parsing logic does not honour the user given buffer bounds (resulting in out-of-bounds access). This can be observed e.g. by the following simple test (sometimes the old/'longer' previous value is re-read from the buffer): $ echo add_device lo@0 > /proc/net/pktgen/kpktgend_0 $ echo "min_pkt_size 12345" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 12345 max_pkt_size: 0 Result: OK: min_pkt_size=12345 $ echo -n "min_pkt_size 123" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 12345 max_pkt_size: 0 Result: OK: min_pkt_size=12345 $ echo "min_pkt_size 123" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 123 max_pkt_size: 0 Result: OK: min_pkt_size=123 So fix the out-of-bounds access (and some minor findings) and add a simple proc_net_pktgen selftest... Patch set splited into part I (this one) - net: pktgen: replace ENOTSUPP with EOPNOTSUPP - net: pktgen: enable 'param=value' parsing - net: pktgen: fix hex32_arg parsing for short reads - net: pktgen: fix 'rate 0' error handling (return -EINVAL) - net: pktgen: fix 'ratep 0' error handling (return -EINVAL) - net: pktgen: fix ctrl interface command parsing - net: pktgen: fix access outside of user given buffer in pktgen_thread_write() And part II (will follow): - net: pktgen: use defines for the various dec/hex number parsing digits lengths - net: pktgen: fix mix of int/long - net: pktgen: remove extra tmp variable (re-use len instead) - net: pktgen: remove some superfluous variable initializing - net: pktgen: fix mpls maximum labels list parsing - net: pktgen: fix access outside of user given buffer in pktgen_if_write() - net: pktgen: fix mpls reset parsing - net: pktgen: remove all superfluous index assignements - selftest: net: add proc_net_pktgen Regards, Peter Changes v4 -> v5: - split up patchset into part i/ii (suggested by Simon Horman) Changes v3 -> v4: - add rev-by Simon Horman - new patch 'net: pktgen: use defines for the various dec/hex number parsing digits lengths' (suggested by Simon Horman) - replace C99 comment (suggested by Paolo Abeni) - drop available characters check in strn_len() (suggested by Paolo Abeni) - factored out patch 'net: pktgen: align some variable declarations to the most common pattern' (suggested by Paolo Abeni) - factored out patch 'net: pktgen: remove extra tmp variable (re-use len instead)' (suggested by Paolo Abeni) - factored out patch 'net: pktgen: remove some superfluous variable initializing' (suggested by Paolo Abeni) - factored out patch 'net: pktgen: fix mpls maximum labels list parsing' (suggested by Paolo Abeni) - factored out 'net: pktgen: hex32_arg/num_arg error out in case no characters are available' (suggested by Paolo Abeni) - factored out 'net: pktgen: num_arg error out in case no valid character is parsed' (suggested by Paolo Abeni) Changes v2 -> v3: - new patch: 'net: pktgen: fix ctrl interface command parsing' - new patch: 'net: pktgen: fix mpls reset parsing' - tools/testing/selftests/net/proc_net_pktgen.c: - fix typo in change description ('v1 -> v1' and tyop) - rename some vars to better match usage add_loopback_0 -> thr_cmd_add_loopback_0 rm_loopback_0 -> thr_cmd_rm_loopback_0 wrong_ctrl_cmd -> wrong_thr_cmd legacy_ctrl_cmd -> legacy_thr_cmd ctrl_fd -> thr_fd - add ctrl interface tests Changes v1 -> v2: - new patch: 'net: pktgen: fix hex32_arg parsing for short reads' - new patch: 'net: pktgen: fix 'rate 0' error handling (return -EINVAL)' - new patch: 'net: pktgen: fix 'ratep 0' error handling (return -EINVAL)' - net/core/pktgen.c: additional fix get_imix_entries() and get_labels() - tools/testing/selftests/net/proc_net_pktgen.c: - fix tyop not vs. nod (suggested by Jakub Kicinski) - fix misaligned line (suggested by Jakub Kicinski) - enable fomerly commented out CONFIG_XFRM dependent test (command spi), as CONFIG_XFRM is enabled via tools/testing/selftests/net/config CONFIG_XFRM_INTERFACE/CONFIG_XFRM_USER (suggestex by Jakub Kicinski) - add CONFIG_NET_PKTGEN=m to tools/testing/selftests/net/config (suggested by Jakub Kicinski) - add modprobe pktgen to FIXTURE_SETUP() (suggested by Jakub Kicinski) - fix some checkpatch warnings (Missing a blank line after declarations) - shrink line length by re-naming some variables (command -> cmd, device -> dev) - add 'rate 0' testcase - add 'ratep 0' testcase [1] https://lore.kernel.org/netdev/20241006221221.3744995-1-artem.chernyshev@re… [2] https://lore.kernel.org/netdev/20250109083039.14004-1-pchelkin@ispras.ru/ [3] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… Peter Seiderer (8): net: pktgen: replace ENOTSUPP with EOPNOTSUPP net: pktgen: enable 'param=value' parsing net: pktgen: fix hex32_arg parsing for short reads net: pktgen: fix 'rate 0' error handling (return -EINVAL) net: pktgen: fix 'ratep 0' error handling (return -EINVAL) net: pktgen: fix ctrl interface command parsing net: pktgen: fix access outside of user given buffer in pktgen_thread_write() net: pktgen: use defines for the various dec/hex number parsing digits lengths net/core/pktgen.c | 119 +++++++++++++++++++++++++--------------------- 1 file changed, 66 insertions(+), 53 deletions(-) -- 2.48.1

4 months, 3 weeks

4
15
0 0

[PATCH bpf-next 0/3] selftests/bpf: tc_links/tc_opts: Unserialize tests

by Bastien Curutchet (eBPF Foundation)

Hi all, Both tc_links.c and tc_opts.c do their tests on the loopback interface. It prevents from parallelizing their executions. Use namespaces and the new append_tid() helper to allow this parallelization. Signed-off-by: Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com> --- Bastien Curutchet (eBPF Foundation) (3): selftests/bpf: tc_helpers: Add create_and_open_tid_ns() selftests/bpf: tc_link/tc_opts: Use unique namespace selftests/bpf: tc_links/tc_opts: Serialize tests .../testing/selftests/bpf/prog_tests/tc_helpers.h | 12 ++ tools/testing/selftests/bpf/prog_tests/tc_links.c | 164 +++++++++++++-- tools/testing/selftests/bpf/prog_tests/tc_opts.c | 230 ++++++++++++++++++--- 3 files changed, 361 insertions(+), 45 deletions(-) --- base-commit: cfed0f474a4bb2f12b54de5d6a7301cfb7dc0dbd change-id: 20250128-tc_links-d894a23b7063 Best regards, -- Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com>

4 months, 3 weeks

4
6
0 0

[PATCH v2 Linux-6.12.y Linux-6.13.y 1/1] selftests/mm: build with -O2

by Yifei Liu

From: Kevin Brodsky <kevin.brodsky(a)arm.com> [ Upstream commit 46036188ea1f5266df23a6149dea0df1c77cd1c7 ] The mm kselftests are currently built with no optimisation (-O0). It's unclear why, and besides being obviously suboptimal, this also prevents the pkeys tests from working as intended. Let's build all the tests with -O2. [kevin.brodsky(a)arm.com: silence unused-result warnings] Link: https://lkml.kernel.org/r/20250107170110.2819685-1-kevin.brodsky@arm.com Link: https://lkml.kernel.org/r/20241209095019.1732120-6-kevin.brodsky@arm.com Signed-off-by: Kevin Brodsky <kevin.brodsky(a)arm.com> Cc: Aruna Ramakrishna <aruna.ramakrishna(a)oracle.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: Joey Gouly <joey.gouly(a)arm.com> Cc: Keith Lucas <keith.lucas(a)oracle.com> Cc: Ryan Roberts <ryan.roberts(a)arm.com> Cc: Shuah Khan <shuah(a)kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> (cherry picked from commit 46036188ea1f5266df23a6149dea0df1c77cd1c7) [Yifei: This commit also fix the failure of pkey_sighandler_tests_64, which is also in linux-6.12.y and linux-6.13.y, thus backport this commit] Signed-off-by: Yifei Liu <yifei.l.liu(a)oracle.com> --- tools/testing/selftests/mm/Makefile | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 02e1204971b0..c0138cb19705 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -33,9 +33,16 @@ endif # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) +CFLAGS = -Wall -O2 -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm +# Some distributions (such as Ubuntu) configure GCC so that _FORTIFY_SOURCE is +# automatically enabled at -O1 or above. This triggers various unused-result +# warnings where functions such as read() or write() are called and their +# return value is not checked. Disable _FORTIFY_SOURCE to silence those +# warnings. +CFLAGS += -U_FORTIFY_SOURCE + TEST_GEN_FILES = cow TEST_GEN_FILES += compaction_test TEST_GEN_FILES += gup_longterm -- 2.46.0

4 months, 3 weeks

3
6
0 0