Linux-kselftest-mirror

linux-kselftest-mirror@lists.linaro.org

125 participants
14267 discussions

[PATCH v3 02/12] rust: macros: use `quote!` from vendored crate

by Gary Guo

From: Gary Guo <gary(a)garyguo.net> With `quote` crate now vendored in the kernel, we can remove our custom `quote!` macro implementation and just rely on that crate instead. The `quote` crate uses types from the `proc-macro2` library so we also update to use that, and perform conversion in the top-level lib.rs. Clippy complains about unnecessary `.to_string()` as `proc-macro2` provides additional `PartialEq` impl, so they are removed. Reviewed-by: Tamir Duberstein <tamird(a)gmail.com> Reviewed-by: Benno Lossin <lossin(a)kernel.org> Signed-off-by: Gary Guo <gary(a)garyguo.net> --- rust/macros/concat_idents.rs | 2 +- rust/macros/export.rs | 4 +- rust/macros/fmt.rs | 4 +- rust/macros/helpers.rs | 4 +- rust/macros/kunit.rs | 5 +- rust/macros/lib.rs | 21 ++-- rust/macros/module.rs | 6 +- rust/macros/paste.rs | 2 +- rust/macros/quote.rs | 182 ----------------------------------- rust/macros/vtable.rs | 7 +- 10 files changed, 32 insertions(+), 205 deletions(-) delete mode 100644 rust/macros/quote.rs diff --git a/rust/macros/concat_idents.rs b/rust/macros/concat_idents.rs index 7e4b450f3a507..12cb231c3d715 100644 --- a/rust/macros/concat_idents.rs +++ b/rust/macros/concat_idents.rs @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 -use proc_macro::{token_stream, Ident, TokenStream, TokenTree}; +use proc_macro2::{token_stream, Ident, TokenStream, TokenTree}; use crate::helpers::expect_punct; diff --git a/rust/macros/export.rs b/rust/macros/export.rs index a08f6337d5c8d..92d9b30971929 100644 --- a/rust/macros/export.rs +++ b/rust/macros/export.rs @@ -1,7 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 +use proc_macro2::TokenStream; +use quote::quote; + use crate::helpers::function_name; -use proc_macro::TokenStream; /// Please see [`crate::export`] for documentation. pub(crate) fn export(_attr: TokenStream, ts: TokenStream) -> TokenStream { diff --git a/rust/macros/fmt.rs b/rust/macros/fmt.rs index 2f4b9f6e22110..19f709262552b 100644 --- a/rust/macros/fmt.rs +++ b/rust/macros/fmt.rs @@ -1,8 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 -use proc_macro::{Ident, TokenStream, TokenTree}; use std::collections::BTreeSet; +use proc_macro2::{Ident, TokenStream, TokenTree}; +use quote::quote_spanned; + /// Please see [`crate::fmt`] for documentation. pub(crate) fn fmt(input: TokenStream) -> TokenStream { let mut input = input.into_iter(); diff --git a/rust/macros/helpers.rs b/rust/macros/helpers.rs index 365d7eb499c08..13fafaba12261 100644 --- a/rust/macros/helpers.rs +++ b/rust/macros/helpers.rs @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 -use proc_macro::{token_stream, Group, Ident, TokenStream, TokenTree}; +use proc_macro2::{token_stream, Group, Ident, TokenStream, TokenTree}; pub(crate) fn try_ident(it: &mut token_stream::IntoIter) -> Option<String> { if let Some(TokenTree::Ident(ident)) = it.next() { @@ -86,7 +86,7 @@ pub(crate) fn function_name(input: TokenStream) -> Option<Ident> { let mut input = input.into_iter(); while let Some(token) = input.next() { match token { - TokenTree::Ident(i) if i.to_string() == "fn" => { + TokenTree::Ident(i) if i == "fn" => { if let Some(TokenTree::Ident(i)) = input.next() { return Some(i); } diff --git a/rust/macros/kunit.rs b/rust/macros/kunit.rs index b395bb0536959..5cd6aa5eef07d 100644 --- a/rust/macros/kunit.rs +++ b/rust/macros/kunit.rs @@ -4,10 +4,11 @@ //! //! Copyright (c) 2023 José Expósito <jose.exposito89(a)gmail.com> -use proc_macro::{Delimiter, Group, TokenStream, TokenTree}; use std::collections::HashMap; use std::fmt::Write; +use proc_macro2::{Delimiter, Group, TokenStream, TokenTree}; + pub(crate) fn kunit_tests(attr: TokenStream, ts: TokenStream) -> TokenStream { let attr = attr.to_string(); @@ -59,7 +60,7 @@ pub(crate) fn kunit_tests(attr: TokenStream, ts: TokenStream) -> TokenStream { } _ => (), }, - TokenTree::Ident(i) if i.to_string() == "fn" && attributes.contains_key("test") => { + TokenTree::Ident(i) if i == "fn" && attributes.contains_key("test") => { if let Some(TokenTree::Ident(test_name)) = body_it.next() { tests.push((test_name, attributes.remove("cfg").unwrap_or_default())) } diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs index b38002151871a..945982c21f703 100644 --- a/rust/macros/lib.rs +++ b/rust/macros/lib.rs @@ -11,8 +11,6 @@ // to avoid depending on the full `proc_macro_span` on Rust >= 1.88.0. #![cfg_attr(not(CONFIG_RUSTC_HAS_SPAN_FILE), feature(proc_macro_span))] -#[macro_use] -mod quote; mod concat_idents; mod export; mod fmt; @@ -132,7 +130,7 @@ /// the kernel module. #[proc_macro] pub fn module(ts: TokenStream) -> TokenStream { - module::module(ts) + module::module(ts.into()).into() } /// Declares or implements a vtable trait. @@ -207,7 +205,7 @@ pub fn module(ts: TokenStream) -> TokenStream { /// [`kernel::error::VTABLE_DEFAULT_ERROR`]: ../kernel/error/constant.VTABLE_DEFAULT_ERROR.html #[proc_macro_attribute] pub fn vtable(attr: TokenStream, ts: TokenStream) -> TokenStream { - vtable::vtable(attr, ts) + vtable::vtable(attr.into(), ts.into()).into() } /// Export a function so that C code can call it via a header file. @@ -230,7 +228,7 @@ pub fn vtable(attr: TokenStream, ts: TokenStream) -> TokenStream { /// automatically exported with `EXPORT_SYMBOL_GPL`. #[proc_macro_attribute] pub fn export(attr: TokenStream, ts: TokenStream) -> TokenStream { - export::export(attr, ts) + export::export(attr.into(), ts.into()).into() } /// Like [`core::format_args!`], but automatically wraps arguments in [`kernel::fmt::Adapter`]. @@ -248,7 +246,7 @@ pub fn export(attr: TokenStream, ts: TokenStream) -> TokenStream { /// [`pr_info!`]: ../kernel/macro.pr_info.html #[proc_macro] pub fn fmt(input: TokenStream) -> TokenStream { - fmt::fmt(input) + fmt::fmt(input.into()).into() } /// Concatenate two identifiers. @@ -306,7 +304,7 @@ pub fn fmt(input: TokenStream) -> TokenStream { /// ``` #[proc_macro] pub fn concat_idents(ts: TokenStream) -> TokenStream { - concat_idents::concat_idents(ts) + concat_idents::concat_idents(ts.into()).into() } /// Paste identifiers together. @@ -444,9 +442,12 @@ pub fn concat_idents(ts: TokenStream) -> TokenStream { /// [`paste`]: https://docs.rs/paste/ #[proc_macro] pub fn paste(input: TokenStream) -> TokenStream { - let mut tokens = input.into_iter().collect(); + let mut tokens = proc_macro2::TokenStream::from(input).into_iter().collect(); paste::expand(&mut tokens); - tokens.into_iter().collect() + tokens + .into_iter() + .collect::<proc_macro2::TokenStream>() + .into() } /// Registers a KUnit test suite and its test cases using a user-space like syntax. @@ -473,5 +474,5 @@ pub fn paste(input: TokenStream) -> TokenStream { /// ``` #[proc_macro_attribute] pub fn kunit_tests(attr: TokenStream, ts: TokenStream) -> TokenStream { - kunit::kunit_tests(attr, ts) + kunit::kunit_tests(attr.into(), ts.into()).into() } diff --git a/rust/macros/module.rs b/rust/macros/module.rs index 80cb9b16f5aaf..b855a2b586e18 100644 --- a/rust/macros/module.rs +++ b/rust/macros/module.rs @@ -1,9 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 -use crate::helpers::*; -use proc_macro::{token_stream, Delimiter, Literal, TokenStream, TokenTree}; use std::fmt::Write; +use proc_macro2::{token_stream, Delimiter, Literal, TokenStream, TokenTree}; + +use crate::helpers::*; + fn expect_string_array(it: &mut token_stream::IntoIter) -> Vec<String> { let group = expect_group(it); assert_eq!(group.delimiter(), Delimiter::Bracket); diff --git a/rust/macros/paste.rs b/rust/macros/paste.rs index cce712d19855b..2181e312a7d32 100644 --- a/rust/macros/paste.rs +++ b/rust/macros/paste.rs @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 -use proc_macro::{Delimiter, Group, Ident, Spacing, Span, TokenTree}; +use proc_macro2::{Delimiter, Group, Ident, Spacing, Span, TokenTree}; fn concat_helper(tokens: &[TokenTree]) -> Vec<(String, Span)> { let mut tokens = tokens.iter(); diff --git a/rust/macros/quote.rs b/rust/macros/quote.rs deleted file mode 100644 index ddfc21577539c..0000000000000 --- a/rust/macros/quote.rs +++ /dev/null @@ -1,182 +0,0 @@ -// SPDX-License-Identifier: Apache-2.0 OR MIT - -use proc_macro::{TokenStream, TokenTree}; - -pub(crate) trait ToTokens { - fn to_tokens(&self, tokens: &mut TokenStream); -} - -impl<T: ToTokens> ToTokens for Option<T> { - fn to_tokens(&self, tokens: &mut TokenStream) { - if let Some(v) = self { - v.to_tokens(tokens); - } - } -} - -impl ToTokens for proc_macro::Group { - fn to_tokens(&self, tokens: &mut TokenStream) { - tokens.extend([TokenTree::from(self.clone())]); - } -} - -impl ToTokens for proc_macro::Ident { - fn to_tokens(&self, tokens: &mut TokenStream) { - tokens.extend([TokenTree::from(self.clone())]); - } -} - -impl ToTokens for TokenTree { - fn to_tokens(&self, tokens: &mut TokenStream) { - tokens.extend([self.clone()]); - } -} - -impl ToTokens for TokenStream { - fn to_tokens(&self, tokens: &mut TokenStream) { - tokens.extend(self.clone()); - } -} - -/// Converts tokens into [`proc_macro::TokenStream`] and performs variable interpolations with -/// the given span. -/// -/// This is a similar to the -/// [`quote_spanned!`](https://docs.rs/quote/latest/quote/macro.quote_spanned.html) macro from the -/// `quote` crate but provides only just enough functionality needed by the current `macros` crate. -macro_rules! quote_spanned { - ($span:expr => $($tt:tt)*) => {{ - let mut tokens = ::proc_macro::TokenStream::new(); - { - #[allow(unused_variables)] - let span = $span; - quote_spanned!(@proc tokens span $($tt)*); - } - tokens - }}; - (@proc $v:ident $span:ident) => {}; - (@proc $v:ident $span:ident #$id:ident $($tt:tt)*) => { - $crate::quote::ToTokens::to_tokens(&$id, &mut $v); - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident #(#$id:ident)* $($tt:tt)*) => { - for token in $id { - $crate::quote::ToTokens::to_tokens(&token, &mut $v); - } - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident ( $($inner:tt)* ) $($tt:tt)*) => { - #[allow(unused_mut)] - let mut tokens = ::proc_macro::TokenStream::new(); - quote_spanned!(@proc tokens $span $($inner)*); - $v.extend([::proc_macro::TokenTree::Group(::proc_macro::Group::new( - ::proc_macro::Delimiter::Parenthesis, - tokens, - ))]); - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident [ $($inner:tt)* ] $($tt:tt)*) => { - let mut tokens = ::proc_macro::TokenStream::new(); - quote_spanned!(@proc tokens $span $($inner)*); - $v.extend([::proc_macro::TokenTree::Group(::proc_macro::Group::new( - ::proc_macro::Delimiter::Bracket, - tokens, - ))]); - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident { $($inner:tt)* } $($tt:tt)*) => { - let mut tokens = ::proc_macro::TokenStream::new(); - quote_spanned!(@proc tokens $span $($inner)*); - $v.extend([::proc_macro::TokenTree::Group(::proc_macro::Group::new( - ::proc_macro::Delimiter::Brace, - tokens, - ))]); - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident :: $($tt:tt)*) => { - $v.extend([::proc_macro::Spacing::Joint, ::proc_macro::Spacing::Alone].map(|spacing| { - ::proc_macro::TokenTree::Punct(::proc_macro::Punct::new(':', spacing)) - })); - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident : $($tt:tt)*) => { - $v.extend([::proc_macro::TokenTree::Punct( - ::proc_macro::Punct::new(':', ::proc_macro::Spacing::Alone), - )]); - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident , $($tt:tt)*) => { - $v.extend([::proc_macro::TokenTree::Punct( - ::proc_macro::Punct::new(',', ::proc_macro::Spacing::Alone), - )]); - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident @ $($tt:tt)*) => { - $v.extend([::proc_macro::TokenTree::Punct( - ::proc_macro::Punct::new('@', ::proc_macro::Spacing::Alone), - )]); - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident ! $($tt:tt)*) => { - $v.extend([::proc_macro::TokenTree::Punct( - ::proc_macro::Punct::new('!', ::proc_macro::Spacing::Alone), - )]); - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident ; $($tt:tt)*) => { - $v.extend([::proc_macro::TokenTree::Punct( - ::proc_macro::Punct::new(';', ::proc_macro::Spacing::Alone), - )]); - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident + $($tt:tt)*) => { - $v.extend([::proc_macro::TokenTree::Punct( - ::proc_macro::Punct::new('+', ::proc_macro::Spacing::Alone), - )]); - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident = $($tt:tt)*) => { - $v.extend([::proc_macro::TokenTree::Punct( - ::proc_macro::Punct::new('=', ::proc_macro::Spacing::Alone), - )]); - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident # $($tt:tt)*) => { - $v.extend([::proc_macro::TokenTree::Punct( - ::proc_macro::Punct::new('#', ::proc_macro::Spacing::Alone), - )]); - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident & $($tt:tt)*) => { - $v.extend([::proc_macro::TokenTree::Punct( - ::proc_macro::Punct::new('&', ::proc_macro::Spacing::Alone), - )]); - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident _ $($tt:tt)*) => { - $v.extend([::proc_macro::TokenTree::Ident( - ::proc_macro::Ident::new("_", $span), - )]); - quote_spanned!(@proc $v $span $($tt)*); - }; - (@proc $v:ident $span:ident $id:ident $($tt:tt)*) => { - $v.extend([::proc_macro::TokenTree::Ident( - ::proc_macro::Ident::new(stringify!($id), $span), - )]); - quote_spanned!(@proc $v $span $($tt)*); - }; -} - -/// Converts tokens into [`proc_macro::TokenStream`] and performs variable interpolations with -/// mixed site span ([`Span::mixed_site()`]). -/// -/// This is a similar to the [`quote!`](https://docs.rs/quote/latest/quote/macro.quote.html) macro -/// from the `quote` crate but provides only just enough functionality needed by the current -/// `macros` crate. -/// -/// [`Span::mixed_site()`]: https://doc.rust-lang.org/proc_macro/struct.Span.html#method.mixed_site -macro_rules! quote { - ($($tt:tt)*) => { - quote_spanned!(::proc_macro::Span::mixed_site() => $($tt)*) - } -} diff --git a/rust/macros/vtable.rs b/rust/macros/vtable.rs index ee06044fcd4f3..a67d1cc81a2d3 100644 --- a/rust/macros/vtable.rs +++ b/rust/macros/vtable.rs @@ -1,9 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 -use proc_macro::{Delimiter, Group, TokenStream, TokenTree}; use std::collections::HashSet; use std::fmt::Write; +use proc_macro2::{Delimiter, Group, TokenStream, TokenTree}; + pub(crate) fn vtable(_attr: TokenStream, ts: TokenStream) -> TokenStream { let mut tokens: Vec<_> = ts.into_iter().collect(); @@ -31,7 +32,7 @@ pub(crate) fn vtable(_attr: TokenStream, ts: TokenStream) -> TokenStream { let mut consts = HashSet::new(); while let Some(token) = body_it.next() { match token { - TokenTree::Ident(ident) if ident.to_string() == "fn" => { + TokenTree::Ident(ident) if ident == "fn" => { let fn_name = match body_it.next() { Some(TokenTree::Ident(ident)) => ident.to_string(), // Possibly we've encountered a fn pointer type instead. @@ -39,7 +40,7 @@ pub(crate) fn vtable(_attr: TokenStream, ts: TokenStream) -> TokenStream { }; functions.push(fn_name); } - TokenTree::Ident(ident) if ident.to_string() == "const" => { + TokenTree::Ident(ident) if ident == "const" => { let const_name = match body_it.next() { Some(TokenTree::Ident(ident)) => ident.to_string(), // Possibly we've encountered an inline const block instead. -- 2.51.2

9 minutes

[PATCH net-next v9 0/5] net: devmem: improve cpu cost of RX token management

by Bobby Eshleman

This series improves the CPU cost of RX token management by adding an attribute to NETDEV_CMD_BIND_RX that configures sockets using the binding to avoid the xarray allocator and instead use a per-binding niov array and a uref field in niov. Improvement is ~13% cpu util per RX user thread. Using kperf, the following results were observed: Before: Average RX worker idle %: 13.13, flows 4, test runs 11 After: Average RX worker idle %: 26.32, flows 4, test runs 11 Two other approaches were tested, but with no improvement. Namely, 1) using a hashmap for tokens and 2) keeping an xarray of atomic counters but using RCU so that the hotpath could be mostly lockless. Neither of these approaches proved better than the simple array in terms of CPU. The attribute NETDEV_A_DMABUF_AUTORELEASE is added to toggle the optimization. It is an optional attribute and defaults to 0 (i.e., optimization on). Signed-off-by: Bobby Eshleman <bobbyeshleman(a)meta.com> Changes in v9: - fixed build with NET_DEVMEM=n - fixed bug in rx bindings count logic - Link to v8: https://lore.kernel.org/r/20260107-scratch-bobbyeshleman-devmem-tcp-token-u… Changes in v8: - change static branch logic (only set when enabled, otherwise just always revert back to disabled) - fix missing tests - Link to v7: https://lore.kernel.org/r/20251119-scratch-bobbyeshleman-devmem-tcp-token-u… Changes in v7: - use netlink instead of sockopt (Stan) - restrict system to only one mode, dmabuf bindings can not co-exist with different modes (Stan) - use static branching to enforce single system-wide mode (Stan) - Link to v6: https://lore.kernel.org/r/20251104-scratch-bobbyeshleman-devmem-tcp-token-u… Changes in v6: - renamed 'net: devmem: use niov array for token management' to refer to optionality of new config - added documentation and tests - make autorelease flag per-socket sockopt instead of binding field / sysctl - many per-patch changes (see Changes sections per-patch) - Link to v5: https://lore.kernel.org/r/20251023-scratch-bobbyeshleman-devmem-tcp-token-u… Changes in v5: - add sysctl to opt-out of performance benefit, back to old token release - Link to v4: https://lore.kernel.org/all/20250926-scratch-bobbyeshleman-devmem-tcp-token… Changes in v4: - rebase to net-next - Link to v3: https://lore.kernel.org/r/20250926-scratch-bobbyeshleman-devmem-tcp-token-u… Changes in v3: - make urefs per-binding instead of per-socket, reducing memory footprint - fallback to cleaning up references in dmabuf unbind if socket leaked tokens - drop ethtool patch - Link to v2: https://lore.kernel.org/r/20250911-scratch-bobbyeshleman-devmem-tcp-token-u… Changes in v2: - net: ethtool: prevent user from breaking devmem single-binding rule (Mina) - pre-assign niovs in binding->vec for RX case (Mina) - remove WARNs on invalid user input (Mina) - remove extraneous binding ref get (Mina) - remove WARN for changed binding (Mina) - always use GFP_ZERO for binding->vec (Mina) - fix length of alloc for urefs - use atomic_set(, 0) to initialize sk_user_frags.urefs - Link to v1: https://lore.kernel.org/r/20250902-scratch-bobbyeshleman-devmem-tcp-token-u… --- Bobby Eshleman (5): net: devmem: rename tx_vec to vec in dmabuf binding net: devmem: refactor sock_devmem_dontneed for autorelease split net: devmem: implement autorelease token management net: devmem: document NETDEV_A_DMABUF_AUTORELEASE netlink attribute selftests: drv-net: devmem: add autorelease test Documentation/netlink/specs/netdev.yaml | 12 +++ Documentation/networking/devmem.rst | 70 +++++++++++++ include/net/netmem.h | 1 + include/net/sock.h | 7 +- include/uapi/linux/netdev.h | 1 + net/core/devmem.c | 116 ++++++++++++++++++---- net/core/devmem.h | 29 +++++- net/core/netdev-genl-gen.c | 5 +- net/core/netdev-genl.c | 10 +- net/core/sock.c | 103 ++++++++++++++----- net/ipv4/tcp.c | 76 +++++++++++--- net/ipv4/tcp_ipv4.c | 11 +- net/ipv4/tcp_minisocks.c | 3 +- tools/include/uapi/linux/netdev.h | 1 + tools/testing/selftests/drivers/net/hw/devmem.py | 21 +++- tools/testing/selftests/drivers/net/hw/ncdevmem.c | 19 ++-- 16 files changed, 407 insertions(+), 78 deletions(-) --- base-commit: 6ad078fa0ababa8de2a2b39f476d2abd179a3cf6 change-id: 20250829-scratch-bobbyeshleman-devmem-tcp-token-upstream-292be174d503 Best regards, -- Bobby Eshleman <bobbyeshleman(a)meta.com>

52 minutes

[PATCH v4 00/19] ublk: add support for integrity data

by Caleb Sander Mateos

Much work has recently gone into supporting block device integrity data (sometimes called "metadata") in Linux. Many NVMe devices these days support metadata transfers and/or automatic protection information generation and verification. However, ublk devices can't yet advertise integrity data capabilities. This patch series wires up support for integrity data in ublk. The ublk feature is referred to as "integrity" rather than "metadata" to match the block layer's name for it and to avoid confusion with the existing and unrelated UBLK_IO_F_META. To advertise support for integrity data, a ublk server fills out the struct ublk_params's integrity field and sets UBLK_PARAM_TYPE_INTEGRITY. The struct ublk_param_integrity flags and csum_type fields use the existing LBMD_PI_* constants from the linux/fs.h UAPI header. The ublk driver fills out a corresponding struct blk_integrity. When a request with integrity data is issued to the ublk device, the ublk driver sets UBLK_IO_F_INTEGRITY in struct ublksrv_io_desc's op_flags field. This is necessary for a ublk server for which bi_offload_capable() returns true to distinguish requests with integrity data from those without. Integrity data transfers can currently only be performed via the ublk user copy mechanism. The overhead of zero-copy buffer registration makes it less appealing for the small transfers typical of integrity data. Additionally, neither io_uring NVMe passthru nor IORING_RW_ATTR_FLAG_PI currently allow an io_uring registered buffer for the integrity data. The ki_pos field of the struct kiocb passed to the user copy ->{read,write}_iter() callback gains a bit UBLKSRV_IO_INTEGRITY_FLAG for a ublk server to indicate whether to access the request's data or integrity data. Not yet supported is an analogue for the IO_INTEGRITY_CHK_*/BIP_CHECK_* flags to ask the ublk server to verify the guard, reftag, and/or apptag of a request's protection information. The user copy mechanism currently forbids a ublk server from reading the data/integrity buffer of a read-direction request. We could potentially relax this restriction for integrity data on reads. Alternatively, the ublk driver could verify the requested fields as part of the user copy operation. v4: - Add max_integrity_segments to struct ublk_param_integrity (Ming) - Move UBLKSRV_IO_INTEGRITY_FLAG to avoid overflow from QID + UBLKSRV_IO_BUF_OFFSET (Ming) - Check UBLK_F_INTEGRITY when UBLKSRV_IO_INTEGRITY_FLAG is used (Ming) - Initialize integrity backing file to disable integrity checks (Ming) v3: - Drop support for communicating BIP_CHECK_* for now until the interface is decided - Add Reviewed-by tags v2: - Communicate BIP_CHECK_* flags and expected reftag seed and app tag to ublk server - Add UBLK_F_INTEGRITY feature flag (Ming) - Don't change the definition of UBLKSRV_IO_BUF_TOTAL_BITS (Ming) - Drop patches already applied - Add Reviewed-by tags Caleb Sander Mateos (16): blk-integrity: take const pointer in blk_integrity_rq() ublk: move ublk flag check functions earlier ublk: set UBLK_IO_F_INTEGRITY in ublksrv_io_desc ublk: split out ublk_copy_user_bvec() helper ublk: split out ublk_user_copy() helper ublk: inline ublk_check_and_get_req() into ublk_user_copy() ublk: move offset check out of __ublk_check_and_get_req() ublk: optimize ublk_user_copy() on daemon task selftests: ublk: display UBLK_F_INTEGRITY support selftests: ublk: add utility to get block device metadata size selftests: ublk: add kublk support for integrity params selftests: ublk: implement integrity user copy in kublk selftests: ublk: support non-O_DIRECT backing files selftests: ublk: add integrity data support to loop target selftests: ublk: add integrity params test selftests: ublk: add end-to-end integrity test Stanley Zhang (3): ublk: support UBLK_PARAM_TYPE_INTEGRITY in device creation ublk: implement integrity user copy ublk: support UBLK_F_INTEGRITY drivers/block/ublk_drv.c | 358 +++++++++++++------ include/linux/blk-integrity.h | 6 +- include/uapi/linux/ublk_cmd.h | 25 ++ tools/testing/selftests/ublk/Makefile | 7 +- tools/testing/selftests/ublk/common.c | 4 +- tools/testing/selftests/ublk/fault_inject.c | 1 + tools/testing/selftests/ublk/file_backed.c | 90 ++++- tools/testing/selftests/ublk/kublk.c | 90 ++++- tools/testing/selftests/ublk/kublk.h | 37 +- tools/testing/selftests/ublk/metadata_size.c | 36 ++ tools/testing/selftests/ublk/null.c | 1 + tools/testing/selftests/ublk/stripe.c | 6 +- tools/testing/selftests/ublk/test_common.sh | 10 + tools/testing/selftests/ublk/test_loop_08.sh | 111 ++++++ tools/testing/selftests/ublk/test_null_04.sh | 166 +++++++++ 15 files changed, 817 insertions(+), 131 deletions(-) create mode 100644 tools/testing/selftests/ublk/metadata_size.c create mode 100755 tools/testing/selftests/ublk/test_loop_08.sh create mode 100755 tools/testing/selftests/ublk/test_null_04.sh -- 2.45.2

54 minutes

[PATCH net-next 0/2] selftests: Couple of fixes in Toeplitz RPS cases

by Gal Pressman

Fix a couple of bugs in the RPS cases of the Toeplitz selftest. Gal Pressman (2): selftests: drv-net: fix RPS mask handling in toeplitz test selftests: drv-net: fix RPS mask handling for high CPU numbers tools/testing/selftests/drivers/net/hw/toeplitz.c | 4 ++-- tools/testing/selftests/drivers/net/hw/toeplitz.py | 9 ++++++--- 2 files changed, 8 insertions(+), 5 deletions(-) -- 2.40.1

1 hour, 10 minutes

[PATCH cgroup/for-6.20 v4 0/5] cgroup/cpuset: Don't invalidate sibling partitions on cpuset.cpus conflict

by Waiman Long

v4: - Add tags and fix patch 4 commit log v3: - Patch 2: Change the condition for calling reset_partition_data() to (new_prs <= 0). - Patch 4: Update commit log and code comment to clarify the change. - Add a new patch 5 to move the empty cpus/mems check to cpuset1_validate_change(). v2: - Patch 1: additional comment - Patch 2: simplify the conditions for triggering call to compute_excpus(). - Patch 3: update description of cpuset.cpus.exclusive in cgroup-v2.rst to reflect the new behavior and change the name of the new cpus_excl_conflict() parameter to xcpus_changed. - Patch 4: update description of cpuset.cpus.partition in cgroup-v2.rst to clarify what exclusive CPUs will be used when a partition is created. This patch series is inspired by the cpuset patch sent by Sun Shaojie [1]. The idea is to avoid invalidating sibling partitions when there is a cpuset.cpus conflict. However this patch series does it in a slightly different way to make its behavior more consistent with other cpuset properties. The first 3 patches are just some cleanup and minor bug fixes on issues found during the investigation process. The last one is the major patch that changes the way cpuset.cpus is being handled during the partition creation process. Instead of invalidating sibling partitions when there is a conflict, it will strip out the conflicting exclusive CPUs and assign the remaining non-conflicting exclusive CPUs to the new partition unless there is no more CPU left which will fail the partition creation process. It is similar to the idea that cpuset.cpus.effective may only contain a subset of CPUs specified in cpuset.cpus. So cpuset.cpus.exclusive.effective may contain only a subset of cpuset.cpus when a partition is created without setting cpuset.cpus.exclusive. Even setting cpuset.cpus.exclusive instead of cpuset.cpus may not guarantee all the requested CPUs can be granted if parent doesn't have access to some of those exclusive CPUs. The difference is that conflicts from siblings is not possible with cpuset.cpus.exclusive as long as it can be set successfully without failure. [1] https://lore.kernel.org/lkml/20251117015708.977585-1-sunshaojie@kylinos.cn/ Waiman Long (5): cgroup/cpuset: Streamline rm_siblings_excl_cpus() cgroup/cpuset: Consistently compute effective_xcpus in update_cpumasks_hier() cgroup/cpuset: Don't fail cpuset.cpus change in v2 cgroup/cpuset: Don't invalidate sibling partitions on cpuset.cpus conflict cgroup/cpuset: Move the v1 empty cpus/mems check to cpuset1_validate_change() Documentation/admin-guide/cgroup-v2.rst | 40 +++-- kernel/cgroup/cpuset-internal.h | 12 ++ kernel/cgroup/cpuset-v1.c | 33 ++++ kernel/cgroup/cpuset.c | 163 ++++++------------ .../selftests/cgroup/test_cpuset_prs.sh | 29 +++- 5 files changed, 150 insertions(+), 127 deletions(-) -- 2.52.0

1 hour, 14 minutes

[PATCH cgroup/for-6.20 v5 0/5] cgroup/cpuset: Don't invalidate sibling partitions on cpuset.cpus conflict

by Waiman Long

v5: - Fix patch 4 doc change as reported by Michael. v4: - Add tags and fix patch 4 commit log v3: - Patch 2: Change the condition for calling reset_partition_data() to (new_prs <= 0). - Patch 4: Update commit log and code comment to clarify the change. - Add a new patch 5 to move the empty cpus/mems check to cpuset1_validate_change(). v2: - Patch 1: additional comment - Patch 2: simplify the conditions for triggering call to compute_excpus(). - Patch 3: update description of cpuset.cpus.exclusive in cgroup-v2.rst to reflect the new behavior and change the name of the new cpus_excl_conflict() parameter to xcpus_changed. - Patch 4: update description of cpuset.cpus.partition in cgroup-v2.rst to clarify what exclusive CPUs will be used when a partition is created. This patch series is inspired by the cpuset patch sent by Sun Shaojie [1]. The idea is to avoid invalidating sibling partitions when there is a cpuset.cpus conflict. However this patch series does it in a slightly different way to make its behavior more consistent with other cpuset properties. The first 3 patches are just some cleanup and minor bug fixes on issues found during the investigation process. The last one is the major patch that changes the way cpuset.cpus is being handled during the partition creation process. Instead of invalidating sibling partitions when there is a conflict, it will strip out the conflicting exclusive CPUs and assign the remaining non-conflicting exclusive CPUs to the new partition unless there is no more CPU left which will fail the partition creation process. It is similar to the idea that cpuset.cpus.effective may only contain a subset of CPUs specified in cpuset.cpus. So cpuset.cpus.exclusive.effective may contain only a subset of cpuset.cpus when a partition is created without setting cpuset.cpus.exclusive. Even setting cpuset.cpus.exclusive instead of cpuset.cpus may not guarantee all the requested CPUs can be granted if parent doesn't have access to some of those exclusive CPUs. The difference is that conflicts from siblings is not possible with cpuset.cpus.exclusive as long as it can be set successfully without failure. [1] https://lore.kernel.org/lkml/20251117015708.977585-1-sunshaojie@kylinos.cn/ Waiman Long (5): cgroup/cpuset: Streamline rm_siblings_excl_cpus() cgroup/cpuset: Consistently compute effective_xcpus in update_cpumasks_hier() cgroup/cpuset: Don't fail cpuset.cpus change in v2 cgroup/cpuset: Don't invalidate sibling partitions on cpuset.cpus conflict cgroup/cpuset: Move the v1 empty cpus/mems check to cpuset1_validate_change() Documentation/admin-guide/cgroup-v2.rst | 41 +++-- kernel/cgroup/cpuset-internal.h | 12 ++ kernel/cgroup/cpuset-v1.c | 33 ++++ kernel/cgroup/cpuset.c | 163 ++++++------------ .../selftests/cgroup/test_cpuset_prs.sh | 29 +++- 5 files changed, 151 insertions(+), 127 deletions(-) -- 2.52.0

1 hour, 16 minutes

[PATCH net-next v10 0/7] netconsole: support automatic target recovery

by Andre Carvalho

This patchset introduces target resume capability to netconsole allowing it to recover targets when underlying low-level interface comes back online. The patchset starts by refactoring netconsole state representation in order to allow representing deactivated targets (targets that are disabled due to interfaces unregister). It then modifies netconsole to handle NETDEV_REGISTER events for such targets, setups netpoll and forces the device UP. Targets are matched with incoming interfaces depending on how they were bound in netconsole (by mac or interface name). For these reasons, we also attempt resuming on NETDEV_CHANGENAME. The patchset includes a selftest that validates netconsole target state transitions and that target is functional after resumed. Signed-off-by: Andre Carvalho <asantostc(a)gmail.com> --- Changes in v10: - Define wrappers around dynamic_netconsole_mutex lock/unlock and use them on process_resume_target to avoid build failures and #ifdefs inside callsite (suggested by Breno). - Refactored other dynamic_netconsole_mutex to use the wrappers for consistency. - Ensure we cancel pending working during removal of dynamic targets, which requires also holding dynamic_netconsole_mutex. - Introduce standalone workqueue to avoid potential leaks during module cleanup, flushing all pending resume events before removing all targets. - Link to v9: https://lore.kernel.org/r/20260104-netcons-retrigger-v9-0-38aa643d2283@gmai… Changes in v9: - Hold dynamic_netconsole_mutex on process_resume_target. - Cleanup dev_name as part of netconsole_process_cleanups_core to ensure we correctly resume by mac (for targets bound by mac) - Link to v8: https://lore.kernel.org/r/20251128-netcons-retrigger-v8-0-0bccbf4c6385@gmai… Changes in v8: - Handle NETDEV_REGISTER/CHANGENAME instead of NETDEV_UP (and force the device UP), to increase the chances of succesfully resuming a target. This requires using a workqueue instead of inline in the event notifier as we can't UP the device otherwise. - Link to v7: https://lore.kernel.org/r/20251126-netcons-retrigger-v7-0-1d86dba83b1c@gmai… Changes in v7: - selftest: use ${EXIT_STATUS} instead of ${ksft_pass} to avoid shellcheck warning - Link to v6: https://lore.kernel.org/r/20251121-netcons-retrigger-v6-0-9c03f5a2bd6f@gmai… Changes in v6: - Rebase on top of net-next to resolve conflicts, no functional changes. - Link to v5: https://lore.kernel.org/r/20251119-netcons-retrigger-v5-0-2c7dda6055d6@gmai… Changes in v5: - patch 3: Set (de)enslaved target as DISABLED instead of DEACTIVATED to prevent resuming it. - selftest: Fix test cleanup by moving trap line to outside of loop and remove unneeded 'local' keyword - Rename maybe_resume_target to resume_target, add netconsole_ prefix to process_resumable_targets. - Hold device reference before calling __netpoll_setup. - Link to v4: https://lore.kernel.org/r/20251116-netcons-retrigger-v4-0-5290b5f140c2@gmai… Changes in v4: - Simplify selftest cleanup, removing trap setup in loop. - Drop netpoll helper (__setup_netpoll_hold) and manage reference inside netconsole. - Move resume_list processing logic to separate function. - Link to v3: https://lore.kernel.org/r/20251109-netcons-retrigger-v3-0-1654c280bbe6@gmai… Changes in v3: - Resume by mac or interface name depending on how target was created. - Attempt to resume target without holding target list lock, by moving the target to a temporary list. This is required as netpoll may attempt to allocate memory. - Link to v2: https://lore.kernel.org/r/20250921-netcons-retrigger-v2-0-a0e84006237f@gmai… Changes in v2: - Attempt to resume target in the same thread, instead of using workqueue . - Add wrapper around __netpoll_setup (patch 4). - Renamed resume_target to maybe_resume_target and moved conditionals to inside its implementation, keeping code more clear. - Verify that device addr matches target mac address when target was setup using mac. - Update selftest to cover targets bound by mac and interface name. - Fix typo in selftest comment and sort tests alphabetically in Makefile. - Link to v1: https://lore.kernel.org/r/20250909-netcons-retrigger-v1-0-3aea904926cf@gmai… --- Andre Carvalho (5): netconsole: convert 'enabled' flag to enum for clearer state management netconsole: clear dev_name for devices bound by mac netconsole: introduce helpers for dynamic_netconsole_mutex lock/unlock netconsole: resume previously deactivated target selftests: netconsole: validate target resume Breno Leitao (2): netconsole: add target_state enum netconsole: add STATE_DEACTIVATED to track targets disabled by low level drivers/net/netconsole.c | 305 ++++++++++++++++----- tools/testing/selftests/drivers/net/Makefile | 1 + .../selftests/drivers/net/lib/sh/lib_netcons.sh | 35 ++- .../selftests/drivers/net/netcons_resume.sh | 97 +++++++ 4 files changed, 364 insertions(+), 74 deletions(-) --- base-commit: 60d8484c4cec811f5ceb6550655df74490d1a165 change-id: 20250816-netcons-retrigger-a4f547bfc867 Best regards, -- Andre Carvalho <asantostc(a)gmail.com>

2 hours

[PATCH bpf-next v5 0/9] bpf: Extend BPF syscall with common attributes support

by Leon Hwang

This patch series builds upon the discussion in "[PATCH bpf-next v4 0/4] bpf: Improve error reporting for freplace attachment failure" [1]. This patch series introduces support for *common attributes* in the BPF syscall, providing a unified mechanism for passing shared metadata across all BPF commands. The initial set of common attributes includes: 1. 'log_buf': User-provided buffer for storing log output. 2. 'log_size': Size of the provided log buffer. 3. 'log_level': Verbosity level for logging. 4. 'log_true_size': The size of log reported by kernel. With this extension, the BPF syscall will be able to return meaningful error messages (e.g., failures of creating map), improving debuggability and user experience. Links: [1] https://lore.kernel.org/bpf/20250224153352.64689-1-leon.hwang@linux.dev/ Changes: v4 -> v5: * Rework reporting 'log_true_size' for prog_load, btf_load, and map_create (per Alexei). RFC v3 -> v4: * Drop RFC. * Address comments from Andrii: * Add parentheses in 'sys_bpf_ext()'. * Avoid creating new fd in 'probe_sys_bpf_ext()'. * Add a new struct to wrap log fields in libbpf. * Address comments from Alexei: * Do not skip writing to user space when log_true_size is zero. * Do not use 'bool' arguments. * Drop the adding WARN_ON_ONCE()'s. RFC v2 -> RFC v3: * Rename probe_sys_bpf_extended to probe_sys_bpf_ext. * Refactor reporting 'log_true_size' for prog_load. * Refactor reporting 'btf_log_true_size' for btf_load. * Add warnings for internal bugs in map_create. * Check log_true_size in test cases. * Address comment from Alexei: * Change kvzalloc/kvfree to kzalloc/kfree. * Address comments from Andrii: * Move BPF_COMMON_ATTRS to 'enum bpf_cmd' alongside brief comment. * Add bpf_check_uarg_tail_zero() for extra checks. * Rename sys_bpf_extended to sys_bpf_ext. * Rename sys_bpf_fd_extended to sys_bpf_ext_fd. * Probe the new feature using NULL and -EFAULT. * Move probe_sys_bpf_ext to libbpf_internal.h and drop LIBBPF_API. * Return -EUSERS when log attrs are conflict between bpf_attr and bpf_common_attr. * Avoid touching bpf_vlog_init(). * Update the reason messages in map_create. * Finalize the log using __cleanup(). * Report log size to users. * Change type of log_buf from '__u64' to 'const char *' and cast type using ptr_to_u64() in bpf_map_create(). * Do not return -EOPNOTSUPP when kernel doesn't support this feature in bpf_map_create(). * Add log_level support for map creation for consistency. * Address comment from Eduard: * Use common_attrs->log_level instead of BPF_LOG_FIXED. RFC v1 -> RFC v2: * Fix build error reported by test bot. * Address comments from Alexei: * Drop new uapi for freplace. * Add common attributes support for prog_load and btf_load. * Add common attributes support for map_create. Leon Hwang (9): bpf: Extend BPF syscall with common attributes support libbpf: Add support for extended bpf syscall bpf: Refactor reporting log_true_size for prog_load bpf: Add syscall common attributes support for prog_load bpf: Refactor reporting btf_log_true_size for btf_load bpf: Add syscall common attributes support for btf_load bpf: Add syscall common attributes support for map_create libbpf: Add common attr support for map_create selftests/bpf: Add tests to verify map create failure log include/linux/bpf.h | 19 +- include/linux/bpf_verifier.h | 17 ++ include/linux/btf.h | 3 +- include/linux/syscalls.h | 3 +- include/uapi/linux/bpf.h | 8 + kernel/bpf/btf.c | 32 +--- kernel/bpf/log.c | 103 +++++++++++ kernel/bpf/syscall.c | 122 ++++++++++--- kernel/bpf/verifier.c | 19 +- tools/include/uapi/linux/bpf.h | 8 + tools/lib/bpf/bpf.c | 49 ++++- tools/lib/bpf/bpf.h | 17 +- tools/lib/bpf/features.c | 8 + tools/lib/bpf/libbpf_internal.h | 3 + .../selftests/bpf/prog_tests/map_init.c | 168 ++++++++++++++++++ 15 files changed, 518 insertions(+), 61 deletions(-) -- 2.52.0

2 hours, 20 minutes

[PATCH v5 net 2/2] selftests: net: simple selftest for ipvtap

by Dmitry Skorodumov

This is a simple ipvtap test to test handling IP-address add/remove on ipvlan interface. It creates a veth-interface and then creates several network-namespace with ipvlan0 interface in it linked to veth. Then it starts to add/remove addresses on ipvlan0 interfaces in several threads. At finish, it checks that there is no duplicated addresses. Signed-off-by: Dmitry Skorodumov <skorodumov.dmitry(a)huawei.com> --- v5: - Execution time of ip-set thread is limited with 1 minute. - Don't use KSFT_MACHINE_SLOW. - Fixed position of "CONFIG_TAP=m" in config v4: - Removed unneeded modprobe - Number of threads is 8, if KSFT_MACHINE_SLOW==yes. It is needed, since on debug-build test may take more than 15 minutes. - Now veth is created in own namespace - Added comment about why test adds/removes random ip tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/config | 2 + tools/testing/selftests/net/ipvtap_test.sh | 168 +++++++++++++++++++++ 3 files changed, 171 insertions(+) create mode 100755 tools/testing/selftests/net/ipvtap_test.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index b66ba04f19d9..45c4ea381bc3 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -48,6 +48,7 @@ TEST_PROGS := \ ipv6_flowlabel.sh \ ipv6_force_forwarding.sh \ ipv6_route_update_soft_lockup.sh \ + ipvtap_test.sh \ l2_tos_ttl_inherit.sh \ l2tp.sh \ link_netns.py \ diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 1e1f253118f5..b84362b9b508 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -48,6 +48,7 @@ CONFIG_IPV6_SEG6_LWTUNNEL=y CONFIG_IPV6_SIT=y CONFIG_IPV6_VTI=y CONFIG_IPVLAN=m +CONFIG_IPVTAP=m CONFIG_KALLSYMS=y CONFIG_L2TP=m CONFIG_L2TP_ETH=m @@ -116,6 +117,7 @@ CONFIG_PROC_SYSCTL=y CONFIG_PSAMPLE=m CONFIG_RPS=y CONFIG_SYSFS=y +CONFIG_TAP=m CONFIG_TCP_MD5SIG=y CONFIG_TEST_BLACKHOLE_DEV=m CONFIG_TEST_BPF=m diff --git a/tools/testing/selftests/net/ipvtap_test.sh b/tools/testing/selftests/net/ipvtap_test.sh new file mode 100755 index 000000000000..354ca7ce8584 --- /dev/null +++ b/tools/testing/selftests/net/ipvtap_test.sh @@ -0,0 +1,168 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Simple tests for ipvtap + + +# +# The testing environment looks this way: +# +# |------HNS-------| |------PHY-------| +# | veth<----------------->veth | +# |------|--|------| |----------------| +# | | +# | | |-----TST0-------| +# | |------------|----ipvlan | +# | |----------------| +# | +# | |-----TST1-------| +# |---------------|----ipvlan | +# |----------------| +# + +ALL_TESTS=" + test_ip_set +" + +source lib.sh + +DEBUG=0 + +VETH_HOST=vethtst.h +VETH_PHY=vethtst.p + +NS_COUNT=32 +IP_ITERATIONS=1024 +IPSET_TIMEOUT="60s" + +ns_run() { + ns=$1 + shift + if [[ "$ns" == "global" ]]; then + "$@" >/dev/null + else + ip netns exec "$ns" "$@" >/dev/null + fi +} + +test_ip_setup_env() { + setup_ns NS_PHY + setup_ns HST_NS + + # setup simulated other-host (phy) and host itself + ns_run "$HST_NS" ip link add $VETH_HOST type veth peer name $VETH_PHY \ + netns "$NS_PHY" >/dev/null + ns_run "$HST_NS" ip link set $VETH_HOST up + ns_run "$NS_PHY" ip link set $VETH_PHY up + + for ((i=0; i<NS_COUNT; i++)); do + setup_ns ipvlan_ns_$i + ns="ipvlan_ns_$i" + if [ "$DEBUG" = "1" ]; then + echo "created NS ${!ns}" + fi + if ! ns_run "$HST_NS" ip link add netns ${!ns} ipvlan0 \ + link $VETH_HOST \ + type ipvtap mode l2 bridge; then + exit_error "FAIL: Failed to configure ipvlan link." + fi + done +} + +test_ip_cleanup_env() { + ns_run "$HST_NS" ip link del $VETH_HOST + cleanup_all_ns +} + +exit_error() { + echo "$1" + exit $ksft_fail +} + +rnd() { + echo $(( RANDOM % 32 + 16 )) +} + +test_ip_set_thread() { + # Here we are trying to create some IP conflicts between namespaces. + # If just add/remove IP, nothing interesting will happen. + # But if add random IP and then remove random IP, + # eventually conflicts start to apear. + ip link set ipvlan0 up + for ((i=0; i<IP_ITERATIONS; i++)); do + v=$(rnd) + ip a a "172.25.0.$v/24" dev ipvlan0 2>/dev/null + ip a a "fc00::$v/64" dev ipvlan0 2>/dev/null + v=$(rnd) + ip a d "172.25.0.$v/24" dev ipvlan0 2>/dev/null + ip a d "fc00::$v/64" dev ipvlan0 2>/dev/null + done +} + +test_ip_set() { + RET=0 + + trap test_ip_cleanup_env EXIT + + test_ip_setup_env + + declare -A ns_pids + for ((i=0; i<NS_COUNT; i++)); do + ns="ipvlan_ns_$i" + ns_run ${!ns} timeout "$IPSET_TIMEOUT" \ + bash -c "$0 test_ip_set_thread"& + ns_pids[$i]=$! + done + + for ((i=0; i<NS_COUNT; i++)); do + wait "${ns_pids[$i]}" + done + + declare -A all_ips + for ((i=0; i<NS_COUNT; i++)); do + ns="ipvlan_ns_$i" + ip_output=$(ip netns exec ${!ns} ip a l dev ipvlan0 | grep inet) + while IFS= read -r nsip_out; do + if [[ -z $nsip_out ]]; then + continue; + fi + nsip=$(awk '{print $2}' <<< "$nsip_out") + if [[ -v all_ips[$nsip] ]]; then + RET=$ksft_fail + log_test "conflict for $nsip" + return "$RET" + else + all_ips[$nsip]=$i + fi + done <<< "$ip_output" + done + + if [ "$DEBUG" = "1" ]; then + for key in "${!all_ips[@]}"; do + echo "$key: ${all_ips[$key]}" + done + fi + + trap - EXIT + test_ip_cleanup_env + + log_test "test multithreaded ip set" +} + +if [[ "$1" == "-d" ]]; then + DEBUG=1 + shift +fi + +if [[ "$1" == "-t" ]]; then + shift + TESTS="$*" +fi + +if [[ "$1" == "test_ip_set_thread" ]]; then + test_ip_set_thread +else + require_command ip + + tests_run +fi -- 2.43.0

2 hours, 53 minutes

[PATCH v9 00/30] KVM: arm64: Implement support for SME

by Mark Brown

I've removed the RFC tag from this version of the series, but the items that I'm looking for feedback on remains the same: - The userspace ABI, in particular: - The vector length used for the SVE registers, access to the SVE registers and access to ZA and (if available) ZT0 depending on the current state of PSTATE.{SM,ZA}. - The use of a single finalisation for both SVE and SME. - The addition of control for enabling fine grained traps in a similar manner to FGU but without the UNDEF, I'm not clear if this is desired at all and at present this requires symmetric read and write traps like FGU. That seemed like it might be desired from an implementation point of view but we already have one case where we enable an asymmetric trap (for ARM64_WORKAROUND_AMPERE_AC03_CPU_38) and it seems generally useful to enable asymmetrically. This series implements support for SME use in non-protected KVM guests. Much of this is very similar to SVE, the main additional challenge that SME presents is that it introduces a new vector length similar to the SVE vector length and two new controls which change the registers seen by guests: - PSTATE.ZA enables the ZA matrix register and, if SME2 is supported, the ZT0 LUT register. - PSTATE.SM enables streaming mode, a new floating point mode which uses the SVE register set with the separately configured SME vector length. In streaming mode implementation of the FFR register is optional. It is also permitted to build systems which support SME without SVE, in this case when not in streaming mode no SVE registers or instructions are available. Further, there is no requirement that there be any overlap in the set of vector lengths supported by SVE and SME in a system, this is expected to be a common situation in practical systems. Since there is a new vector length to configure we introduce a new feature parallel to the existing SVE one with a new pseudo register for the streaming mode vector length. Due to the overlap with SVE caused by streaming mode rather than finalising SME as a separate feature we use the existing SVE finalisation to also finalise SME, a new define KVM_ARM_VCPU_VEC is provided to help make user code clearer. Finalising SVE and SME separately would introduce complication with register access since finalising SVE makes the SVE registers writeable by userspace and doing multiple finalisations results in an error being reported. Dealing with a state where the SVE registers are writeable due to one of SVE or SME being finalised but may have their VL changed by the other being finalised seems like needless complexity with minimal practical utility, it seems clearer to just express directly that only one finalisation can be done in the ABI. Access to the floating point registers follows the architecture: - When both SVE and SME are present: - If PSTATE.SM == 0 the vector length used for the Z and P registers is the SVE vector length. - If PSTATE.SM == 1 the vector length used for the Z and P registers is the SME vector length. - If only SME is present: - If PSTATE.SM == 0 the Z and P registers are inaccessible and the floating point state accessed via the encodings for the V registers. - If PSTATE.SM == 1 the vector length used for the Z and P registers - The SME specific ZA and ZT0 registers are only accessible if SVCR.ZA is 1. The VMM must understand this, in particular when loading state SVCR should be configured before other state. It should be noted that while the architecture refers to PSTATE.SM and PSTATE.ZA these PSTATE bits are not preserved in SPSR_ELx, they are only accessible via SVCR. There are a large number of subfeatures for SME, most of which only offer additional instructions but some of which (SME2 and FA64) add architectural state. These are configured via the ID registers as per usual. Protected KVM supported, with the implementation maintaining the existing restriction that the hypervisor will refuse to run if streaming mode or ZA is enabled. This both simplfies the code and avoids the need to allocate storage for host ZA and ZT0 state, there seems to be little practical use case for supporting this and the memory usage would be non-trivial. The new KVM_ARM_VCPU_VEC feature and ZA and ZT0 registers have not been added to the get-reg-list selftest, the idea of supporting additional features there without restructuring the program to generate all possible feature combinations has been rejected. I will post a separate series which does that restructuring. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v9: - Rebase onto v6.19-rc1. - ABI document clarifications. - Add changes dropping asserts on single bit wide bitfields in set_id_regs. - Link to v8: https://lore.kernel.org/r/20250902-kvm-arm64-sme-v8-0-2cb2199c656c@kernel.o… Changes in v8: - Small fixes in ABI documentation. - Link to v7: https://lore.kernel.org/r/20250822-kvm-arm64-sme-v7-0-7a65d82b8b10@kernel.o… Changes in v7: - Rebase onto v6.17-rc1. - Handle SMIDR_EL1 as a VM wide ID register and use this in feat_sme_smps(). - Expose affinity fields in SMIDR_EL1. - Remove SMPRI_EL1 from vcpu_sysreg, the value is always 0 currently. - Prevent userspace writes to SMPRIMAP_EL2. - Link to v6: https://lore.kernel.org/r/20250625-kvm-arm64-sme-v6-0-114cff4ffe04@kernel.o… Changes in v6: - Rebase onto v6.16-rc3. - Link to v5: https://lore.kernel.org/r/20250417-kvm-arm64-sme-v5-0-f469a2d5f574@kernel.o… Changes in v5: - Rebase onto v6.15-rc2. - Add pKVM guest support. - Always restore SVCR. - Link to v4: https://lore.kernel.org/r/20250214-kvm-arm64-sme-v4-0-d64a681adcc2@kernel.o… Changes in v4: - Rebase onto v6.14-rc2 and Mark Rutland's fixes. - Expose SME to nested guests. - Additional cleanups and test fixes following on from the rebase. - Flush register state on VMM PSTATE.{SM,ZA}. - Link to v3: https://lore.kernel.org/r/20241220-kvm-arm64-sme-v3-0-05b018c1ffeb@kernel.o… Changes in v3: - Rebase onto v6.12-rc2. - Link to v2: https://lore.kernel.org/r/20231222-kvm-arm64-sme-v2-0-da226cb180bb@kernel.o… Changes in v2: - Rebase onto v6.7-rc3. - Configure subfeatures based on host system only. - Complete nVHE support. - There was some snafu with sending v1 out, it didn't make it to the lists but in case it hit people's inboxes I'm sending as v2. --- Mark Brown (30): arm64/sysreg: Update SMIDR_EL1 to DDI0601 2025-06 arm64/fpsimd: Update FA64 and ZT0 enables when loading SME state arm64/fpsimd: Decide to save ZT0 and streaming mode FFR at bind time arm64/fpsimd: Check enable bit for FA64 when saving EFI state arm64/fpsimd: Determine maximum virtualisable SME vector length KVM: arm64: Pay attention to FFR parameter in SVE save and load KVM: arm64: Pull ctxt_has_ helpers to start of sysreg-sr.h KVM: arm64: Move SVE state access macros after feature test macros KVM: arm64: Rename SVE finalization constants to be more general KVM: arm64: Document the KVM ABI for SME KVM: arm64: Define internal features for SME KVM: arm64: Rename sve_state_reg_region KVM: arm64: Store vector lengths in an array KVM: arm64: Implement SME vector length configuration KVM: arm64: Support SME control registers KVM: arm64: Support TPIDR2_EL0 KVM: arm64: Support SME identification registers for guests KVM: arm64: Support SME priority registers KVM: arm64: Provide assembly for SME register access KVM: arm64: Support userspace access to streaming mode Z and P registers KVM: arm64: Flush register state on writes to SVCR.SM and SVCR.ZA KVM: arm64: Expose SME specific state to userspace KVM: arm64: Context switch SME state for guests KVM: arm64: Handle SME exceptions KVM: arm64: Expose SME to nested guests KVM: arm64: Provide interface for configuring and enabling SME for guests KVM: arm64: selftests: Remove spurious check for single bit safe values KVM: arm64: selftests: Skip impossible invalid value tests KVM: arm64: selftests: Add SME system registers to get-reg-list KVM: arm64: selftests: Add SME to set_id_regs test Documentation/virt/kvm/api.rst | 120 ++++++++--- arch/arm64/include/asm/fpsimd.h | 26 +++ arch/arm64/include/asm/kvm_emulate.h | 6 + arch/arm64/include/asm/kvm_host.h | 163 ++++++++++++--- arch/arm64/include/asm/kvm_hyp.h | 5 +- arch/arm64/include/asm/kvm_pkvm.h | 2 +- arch/arm64/include/asm/vncr_mapping.h | 2 + arch/arm64/include/uapi/asm/kvm.h | 33 +++ arch/arm64/kernel/cpufeature.c | 2 - arch/arm64/kernel/fpsimd.c | 89 ++++---- arch/arm64/kvm/arm.c | 10 + arch/arm64/kvm/config.c | 11 +- arch/arm64/kvm/fpsimd.c | 28 ++- arch/arm64/kvm/guest.c | 252 ++++++++++++++++++++--- arch/arm64/kvm/handle_exit.c | 14 ++ arch/arm64/kvm/hyp/fpsimd.S | 28 ++- arch/arm64/kvm/hyp/include/hyp/switch.h | 168 +++++++++++++-- arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 110 ++++++---- arch/arm64/kvm/hyp/nvhe/hyp-main.c | 86 ++++++-- arch/arm64/kvm/hyp/nvhe/pkvm.c | 85 ++++++-- arch/arm64/kvm/hyp/nvhe/switch.c | 4 +- arch/arm64/kvm/hyp/nvhe/sys_regs.c | 6 + arch/arm64/kvm/hyp/vhe/switch.c | 17 +- arch/arm64/kvm/hyp/vhe/sysreg-sr.c | 7 + arch/arm64/kvm/nested.c | 3 +- arch/arm64/kvm/reset.c | 156 ++++++++++---- arch/arm64/kvm/sys_regs.c | 140 ++++++++++++- arch/arm64/tools/sysreg | 8 +- include/uapi/linux/kvm.h | 1 + tools/testing/selftests/kvm/arm64/get-reg-list.c | 15 +- tools/testing/selftests/kvm/arm64/set_id_regs.c | 84 ++++++-- 31 files changed, 1367 insertions(+), 314 deletions(-) --- base-commit: 3e7f562e20ee87a25e104ef4fce557d39d62fa85 change-id: 20230301-kvm-arm64-sme-06a1246d3636 Best regards, -- Mark Brown <broonie(a)kernel.org>

3 hours, 48 minutes

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror