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

[PATCH v2 0/2] KVM: selftests: access_tracking_perf_test: skip the test when NUMA balancing is active

by Maxim Levitsky

Due to several issues which are unlikely to be fixed in the near future, the access_tracking_perf_test sanity check for how many pages are still clean after an iteration is not reliable when NUMA balancing is active. This patch series refactors this test to skip this check by default automatically. V2: adopted Sean's suggestions. Best regards, Maxim Levitsky Maxim Levitsky (1): KVM: selftests: access_tracking_perf_test: add option to skip the sanity check Sean Christopherson (1): KVM: selftests: Extract guts of THP accessor to standalone sysfs helpers .../selftests/kvm/access_tracking_perf_test.c | 33 +++++++++++++-- .../testing/selftests/kvm/include/test_util.h | 1 + tools/testing/selftests/kvm/lib/test_util.c | 42 ++++++++++++++----- 3 files changed, 61 insertions(+), 15 deletions(-) -- 2.26.3

6 months, 3 weeks

3
7
0 0

[PATCH v1] selftests/mm/cow: fix minor memory leak in child_vmsplice_memcmp_fn()

by Malaya Kumar Rout

Static Analyis for cow.c: error Exception branch exits without releasing memory 'old' and 'new' fix the issue by releasing the allocated memory. Signed-off-by: Malaya Kumar Rout <malayarout91(a)gmail.com> --- tools/testing/selftests/mm/cow.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 9446673645eb..fdee42850548 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -168,18 +168,18 @@ static int child_vmsplice_memcmp_fn(char *mem, size_t size, memcpy(old, mem, size); if (pipe(fds) < 0) - return -errno; + goto out; /* Trigger a read-only pin. */ transferred = vmsplice(fds[1], &iov, 1, 0); if (transferred < 0) - return -errno; + goto out; if (transferred == 0) return -EINVAL; /* Unmap it from our page tables. */ if (munmap(mem, size) < 0) - return -errno; + goto out; /* Wait until the parent modified it. */ write(comm_pipes->child_ready[1], "0", 1); @@ -190,10 +190,15 @@ static int child_vmsplice_memcmp_fn(char *mem, size_t size, for (total = 0; total < transferred; total += cur) { cur = read(fds[0], new + total, transferred - total); if (cur < 0) - return -errno; + goto out; } return memcmp(old, new, transferred); + +out: + free(old); + free(new); + return -errno; } typedef int (*child_fn)(char *mem, size_t size, struct comm_pipes *comm_pipes); -- 2.43.0

6 months, 3 weeks

2
1
0 0

[PATCH] selftests: vDSO: vdso_standalone_test_x86: Replace source file with symlink

by Thomas Weißschuh

With the switch over to nolibc the source file vdso_standalone_test_x86.c was intended to be replaced with a symlink to vdso_test_gettimeofday.c. This was the patch that was submitted to LKML, but during application the symlink was replaced by a textual copy of the linked-to file. Having two copies introduces the possibility of divergence and increases maintenance burden, switch back to a symlink. Link: https://lore.kernel.org/lkml/20250226-parse_vdso-nolibc-v2-16-28e14e031ed8@… Fixes: 8770a9183fe1 ("selftests: vDSO: vdso_standalone_test_x86: Switch to nolibc") Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- If symlinks are problematic an #include shim would also work. These are not handled really well by the kselftests build system though, as #include dependencies are not tracked by it. --- .../selftests/vDSO/vdso_standalone_test_x86.c | 59 +--------------------- 1 file changed, 1 insertion(+), 58 deletions(-) diff --git a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c deleted file mode 100644 index 9ce795b806f0992b83cef78c7e16fac0e54750da..0000000000000000000000000000000000000000 --- a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c +++ /dev/null @@ -1,58 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * vdso_test_gettimeofday.c: Sample code to test parse_vdso.c and - * vDSO gettimeofday() - * Copyright (c) 2014 Andy Lutomirski - * - * Compile with: - * gcc -std=gnu99 vdso_test_gettimeofday.c parse_vdso_gettimeofday.c - * - * Tested on x86, 32-bit and 64-bit. It may work on other architectures, too. - */ - -#include <stdio.h> -#ifndef NOLIBC -#include <sys/auxv.h> -#include <sys/time.h> -#endif - -#include "../kselftest.h" -#include "parse_vdso.h" -#include "vdso_config.h" -#include "vdso_call.h" - -int main(int argc, char **argv) -{ - const char *version = versions[VDSO_VERSION]; - const char **name = (const char **)&names[VDSO_NAMES]; - - unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR); - if (!sysinfo_ehdr) { - printf("AT_SYSINFO_EHDR is not present!\n"); - return KSFT_SKIP; - } - - vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR)); - - /* Find gettimeofday. */ - typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz); - gtod_t gtod = (gtod_t)vdso_sym(version, name[0]); - - if (!gtod) { - printf("Could not find %s\n", name[0]); - return KSFT_SKIP; - } - - struct timeval tv; - long ret = VDSO_CALL(gtod, 2, &tv, 0); - - if (ret == 0) { - printf("The time is %lld.%06lld\n", - (long long)tv.tv_sec, (long long)tv.tv_usec); - } else { - printf("%s failed\n", name[0]); - return KSFT_FAIL; - } - - return 0; -} diff --git a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c new file mode 120000 index 0000000000000000000000000000000000000000..4d3d96f1e440c965474681a6f35375a60b3921be --- /dev/null +++ b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c @@ -0,0 +1 @@ +vdso_test_gettimeofday.c \ No newline at end of file --- base-commit: 1e26c5e28ca5821a824e90dd359556f5e9e7b89f change-id: 20250326-vdso-selftests-fix-vdso_standalone_test_x86-c3a77b57ccbd Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

6 months, 3 weeks

1
0
0 0

[PATCH v4 00/30] context_tracking,x86: Defer some IPIs until a user->kernel transition

by Valentin Schneider

Context ======= We've observed within Red Hat that isolated, NOHZ_FULL CPUs running a pure-userspace application get regularly interrupted by IPIs sent from housekeeping CPUs. Those IPIs are caused by activity on the housekeeping CPUs leading to various on_each_cpu() calls, e.g.: 64359.052209596 NetworkManager 0 1405 smp_call_function_many_cond (cpu=0, func=do_kernel_range_flush) smp_call_function_many_cond+0x1 smp_call_function+0x39 on_each_cpu+0x2a flush_tlb_kernel_range+0x7b __purge_vmap_area_lazy+0x70 _vm_unmap_aliases.part.42+0xdf change_page_attr_set_clr+0x16a set_memory_ro+0x26 bpf_int_jit_compile+0x2f9 bpf_prog_select_runtime+0xc6 bpf_prepare_filter+0x523 sk_attach_filter+0x13 sock_setsockopt+0x92c __sys_setsockopt+0x16a __x64_sys_setsockopt+0x20 do_syscall_64+0x87 entry_SYSCALL_64_after_hwframe+0x65 The heart of this series is the thought that while we cannot remove NOHZ_FULL CPUs from the list of CPUs targeted by these IPIs, they may not have to execute the callbacks immediately. Anything that only affects kernelspace can wait until the next user->kernel transition, providing it can be executed "early enough" in the entry code. The original implementation is from Peter [1]. Nicolas then added kernel TLB invalidation deferral to that [2], and I picked it up from there. Deferral approach ================= Storing each and every callback, like a secondary call_single_queue turned out to be a no-go: the whole point of deferral is to keep NOHZ_FULL CPUs in userspace for as long as possible - no signal of any form would be sent when deferring an IPI. This means that any form of queuing for deferred callbacks would end up as a convoluted memory leak. Deferred IPIs must thus be coalesced, which this series achieves by assigning IPIs a "type" and having a mapping of IPI type to callback, leveraged upon kernel entry. What about IPIs whose callback take a parameter, you may ask? Peter suggested during OSPM23 [3] that since on_each_cpu() targets housekeeping CPUs *and* isolated CPUs, isolated CPUs can access either global or housekeeping-CPU-local state to "reconstruct" the data that would have been sent via the IPI. This series does not affect any IPI callback that requires an argument, but the approach would remain the same (one coalescable callback executed on kernel entry). Kernel entry vs execution of the deferred operation =================================================== This is what I've referred to as the "Danger Zone" during my LPC24 talk [4]. There is a non-zero length of code that is executed upon kernel entry before the deferred operation can be itself executed (i.e. before we start getting into context_tracking.c proper), i.e.: idtentry_func_foo() <--- we're in the kernel irqentry_enter() enter_from_user_mode() __ct_user_exit() ct_kernel_enter_state() ct_work_flush() <--- deferred operation is executed here This means one must take extra care to what can happen in the early entry code, and that <bad things> cannot happen. For instance, we really don't want to hit instructions that have been modified by a remote text_poke() while we're on our way to execute a deferred sync_core(). Patches doing the actual deferral have more detail on this. Patches ======= o Patches 1-2 are standalone objtool cleanups. o Patches 3-4 add an RCU testing feature. o Patches 5-6 add infrastructure for annotating static keys and static calls that may be used in noinstr code (courtesy of Josh). o Patches 7-19 use said annotations on relevant keys / calls. o Patch 20 enforces proper usage of said annotations (courtesy of Josh). o Patches 21-23 fiddle with CT_STATE* within context tracking o Patches 24-29 add the actual IPI deferral faff o Patch 30 adds a freebie: deferring IPIs for NOHZ_IDLE. Not tested that much! if you care about battery-powered devices and energy consumption, go give it a try! Patches are also available at: https://gitlab.com/vschneid/linux.git -b redhat/isolirq/defer/v4 Stuff I'd like eyes and neurons on ================================== Context-tracking vs idle. Patch 22 "improves" the situation by adding an IDLE->KERNEL transition when getting an IRQ while idle, but it leaves the following window: ~> IRQ ct_nmi_enter() state = state + CT_STATE_KERNEL - CT_STATE_IDLE [...] ct_nmi_exit() state = state - CT_STATE_KERNEL + CT_STATE_IDLE [...] /!\ CT_STATE_IDLE here while we're really in kernelspace! /!\ ct_cpuidle_exit() state = state + CT_STATE_KERNEL - CT_STATE_IDLE Said window is contained within cpu_idle_poll() and the cpuidle call within cpuidle_enter_state(), both being noinstr (the former is __cpuidle which is noinstr itself). Thus objtool will consider it as early entry and will warn accordingly of any static key / call misuse, so the damage is somewhat contained, but it's not ideal. I tried fiddling with this but idle polling likes being annoying, as it is shaped like so: ct_cpuidle_enter(); raw_local_irq_enable(); while (!tif_need_resched() && (cpu_idle_force_poll || tick_check_broadcast_expired())) cpu_relax(); raw_local_irq_disable(); ct_cpuidle_exit(); IOW, getting an IRQ that doesn't end up setting NEED_RESCHED while idle-polling doesn't come near ct_cpuidle_exit(), which prevents me from having the outermost ct_nmi_exit() leave the state as CT_STATE_KERNEL (rather than CT_STATE_IDLE). Testing ======= Xeon E5-2699 system with SMToff, NOHZ_FULL, isolated CPUs. RHEL9 userspace. Workload is using rteval (kernel compilation + hackbench) on housekeeping CPUs and a dummy stay-in-userspace loop on the isolated CPUs. The main invocation is: $ trace-cmd record -e "csd_queue_cpu" -f "cpu & CPUS{$ISOL_CPUS}" \ -e "ipi_send_cpumask" -f "cpumask & CPUS{$ISOL_CPUS}" \ -e "ipi_send_cpu" -f "cpu & CPUS{$ISOL_CPUS}" \ rteval --onlyload --loads-cpulist=$HK_CPUS \ --hackbench-runlowmem=True --duration=$DURATION This only records IPIs sent to isolated CPUs, so any event there is interference (with a bit of fuzz at the start/end of the workload when spawning the processes). All tests were done with a duration of 6 hours. v6.13-rc6 # This is the actual IPI count $ trace-cmd report | grep callback | awk '{ print $(NF) }' | sort | uniq -c | sort -nr 531 callback=generic_smp_call_function_single_interrupt+0x0 # These are the different CSD's that caused IPIs $ trace-cmd report | grep csd_queue | awk '{ print $(NF-1) }' | sort | uniq -c | sort -nr 12818 func=do_flush_tlb_all 910 func=do_kernel_range_flush 78 func=do_sync_core v6.13-rc6 + patches: # This is the actual IPI count $ trace-cmd report | grep callback | awk '{ print $(NF) }' | sort | uniq -c | sort -nr # Zilch! # These are the different CSD's that caused IPIs $ trace-cmd report | grep csd_queue | awk '{ print $(NF-1) }' | sort | uniq -c | sort -nr # Nada! Note that tlb_remove_table_smp_sync() showed up during testing of v3, and has gone as mysteriously as it showed up. Yair had a series adressing this [5] which would be worth revisiting. Acknowledgements ================ Special thanks to: o Clark Williams for listening to my ramblings about this and throwing ideas my way o Josh Poimboeuf for all his help with everything objtool-related o All of the folks who attended various (too many?) talks about this and provided precious feedback. Links ===== [1]: https://lore.kernel.org/all/20210929151723.162004989@infradead.org/ [2]: https://github.com/vianpl/linux.git -b ct-work-defer-wip [3]: https://youtu.be/0vjE6fjoVVE [4]: https://lpc.events/event/18/contributions/1889/ [5]: https://lore.kernel.org/lkml/20230620144618.125703-1-ypodemsk@redhat.com/ Revisions ========= RFCv3 -> v4 ++++++++++++++ o Rebased onto v6.13-rc6 o New objtool patches from Josh o More .noinstr static key/call patches o Static calls now handled as well (again thanks to Josh) o Fixed clearing the work bits on kernel exit o Messed with IRQ hitting an idle CPU vs context tracking o Various comment and naming cleanups o Made RCU_DYNTICKS_TORTURE depend on !COMPILE_TEST (PeterZ) o Fixed the CT_STATE_KERNEL check when setting a deferred work (Frederic) o Cleaned up the __flush_tlb_all() mess thanks to PeterZ RFCv2 -> RFCv3 ++++++++++++++ o Rebased onto v6.12-rc6 o Added objtool documentation for the new warning (Josh) o Added low-size RCU watching counter to TREE04 torture scenario (Paul) o Added FORCEFUL jump label and static key types o Added noinstr-compliant helpers for tlb flush deferral RFCv1 -> RFCv2 ++++++++++++++ o Rebased onto v6.5-rc1 o Updated the trace filter patches (Steven) o Fixed __ro_after_init keys used in modules (Peter) o Dropped the extra context_tracking atomic, squashed the new bits in the existing .state field (Peter, Frederic) o Added an RCU_EXPERT config for the RCU dynticks counter size, and added an rcutorture case for a low-size counter (Paul) o Fixed flush_tlb_kernel_range_deferrable() definition Josh Poimboeuf (3): jump_label: Add annotations for validating noinstr usage static_call: Add read-only-after-init static calls objtool: Add noinstr validation for static branches/calls Peter Zijlstra (1): x86,tlb: Make __flush_tlb_global() noinstr-compliant Valentin Schneider (26): objtool: Make validate_call() recognize indirect calls to pv_ops[] objtool: Flesh out warning related to pv_ops[] calls rcu: Add a small-width RCU watching counter debug option rcutorture: Make TREE04 use CONFIG_RCU_DYNTICKS_TORTURE x86/paravirt: Mark pv_sched_clock static call as __ro_after_init x86/idle: Mark x86_idle static call as __ro_after_init x86/paravirt: Mark pv_steal_clock static call as __ro_after_init riscv/paravirt: Mark pv_steal_clock static call as __ro_after_init loongarch/paravirt: Mark pv_steal_clock static call as __ro_after_init arm64/paravirt: Mark pv_steal_clock static call as __ro_after_init arm/paravirt: Mark pv_steal_clock static call as __ro_after_init perf/x86/amd: Mark perf_lopwr_cb static call as __ro_after_init sched/clock: Mark sched_clock_running key as __ro_after_init x86/speculation/mds: Mark mds_idle_clear key as allowed in .noinstr sched/clock, x86: Mark __sched_clock_stable key as allowed in .noinstr x86/kvm/vmx: Mark vmx_l1d_should flush and vmx_l1d_flush_cond keys as allowed in .noinstr stackleack: Mark stack_erasing_bypass key as allowed in .noinstr context_tracking: Explicitely use CT_STATE_KERNEL where it is missing context_tracking: Exit CT_STATE_IDLE upon irq/nmi entry context_tracking: Turn CT_STATE_* into bits context-tracking: Introduce work deferral infrastructure context_tracking,x86: Defer kernel text patching IPIs x86/tlb: Make __flush_tlb_local() noinstr-compliant x86/tlb: Make __flush_tlb_all() noinstr x86/mm, mm/vmalloc: Defer flush_tlb_kernel_range() targeting NOHZ_FULL CPUs context-tracking: Add a Kconfig to enable IPI deferral for NO_HZ_IDLE arch/Kconfig | 9 ++ arch/arm/kernel/paravirt.c | 2 +- arch/arm64/kernel/paravirt.c | 2 +- arch/loongarch/kernel/paravirt.c | 2 +- arch/riscv/kernel/paravirt.c | 2 +- arch/x86/Kconfig | 1 + arch/x86/events/amd/brs.c | 2 +- arch/x86/include/asm/context_tracking_work.h | 22 ++++ arch/x86/include/asm/invpcid.h | 13 +-- arch/x86/include/asm/paravirt.h | 4 +- arch/x86/include/asm/text-patching.h | 1 + arch/x86/include/asm/tlbflush.h | 3 +- arch/x86/include/asm/xen/hypercall.h | 11 +- arch/x86/kernel/alternative.c | 38 ++++++- arch/x86/kernel/cpu/bugs.c | 9 +- arch/x86/kernel/kprobes/core.c | 4 +- arch/x86/kernel/kprobes/opt.c | 4 +- arch/x86/kernel/module.c | 2 +- arch/x86/kernel/paravirt.c | 4 +- arch/x86/kernel/process.c | 2 +- arch/x86/kvm/vmx/vmx.c | 11 +- arch/x86/mm/tlb.c | 46 ++++++-- arch/x86/xen/mmu_pv.c | 10 +- arch/x86/xen/xen-ops.h | 12 +- include/asm-generic/sections.h | 15 +++ include/linux/context_tracking.h | 21 ++++ include/linux/context_tracking_state.h | 64 +++++++++-- include/linux/context_tracking_work.h | 28 +++++ include/linux/jump_label.h | 30 ++++- include/linux/objtool.h | 7 ++ include/linux/static_call.h | 19 ++++ kernel/context_tracking.c | 98 ++++++++++++++-- kernel/rcu/Kconfig.debug | 15 +++ kernel/sched/clock.c | 7 +- kernel/stackleak.c | 6 +- kernel/time/Kconfig | 19 ++++ mm/vmalloc.c | 35 +++++- tools/objtool/Documentation/objtool.txt | 34 ++++++ tools/objtool/check.c | 106 +++++++++++++++--- tools/objtool/include/objtool/check.h | 1 + tools/objtool/include/objtool/elf.h | 1 + tools/objtool/include/objtool/special.h | 1 + tools/objtool/special.c | 18 ++- .../selftests/rcutorture/configs/rcu/TREE04 | 1 + 44 files changed, 635 insertions(+), 107 deletions(-) create mode 100644 arch/x86/include/asm/context_tracking_work.h create mode 100644 include/linux/context_tracking_work.h -- 2.43.0

6 months, 3 weeks

11
85
0 0

[PATCHv5 net-next 0/2] wireguard: selftests: use nftables for testing

by Hangbin Liu

This patch set convert iptables to nftables for wireguard testing, as iptables is deparated and nftables is the default framework of most releases. v5: remove the counter in nft rules and link nft statically (Jason A. Donenfeld) v4: no update, just re-send v3: drop iptables directly (Jason A. Donenfeld) Also convert to using nft for qemu testing (Jason A. Donenfeld) v2: use one nft table for testing (Phil Sutter) Hangbin Liu (2): wireguard: selftests: convert iptables to nft wireguard: selftests: update to using nft for qemu test tools/testing/selftests/wireguard/netns.sh | 29 +++++++++------ .../testing/selftests/wireguard/qemu/Makefile | 36 ++++++++++++++----- .../selftests/wireguard/qemu/kernel.config | 7 ++-- 3 files changed, 49 insertions(+), 23 deletions(-) -- 2.46.0

6 months, 3 weeks

2
5
0 0

[PATCH rcu 00/11] RCU torture changes for v6.15

by Boqun Feng

Hi, Please find the upcoming changes in rcutorture for v6.15. The changes can also be found at: git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux.git torture.2025.02.05a Regards, Boqun Paul E. McKenney (11): torture: Add get_torture_init_jiffies() for test-start time rcutorture: Add a test_boost_holdoff module parameter rcutorture: Include grace-period sequence numbers in failure/close-call rcutorture: Expand failure/close-call grace-period output rcu: Trace expedited grace-period numbers in hexadecimal rcutorture: Add ftrace-compatible timestamp to GP# failure/close-call output rcutorture: Make cur_ops->format_gp_seqs take buffer length rcutorture: Move RCU_TORTURE_TEST_{CHK_RDR_STATE,LOG_CPU} to bool rcutorture: Complain when invalid SRCU reader_flavor is specified srcu: Add FORCE_NEED_SRCU_NMI_SAFE Kconfig for testing torture: Make SRCU lockdep testing use srcu_read_lock_nmisafe() .../admin-guide/kernel-parameters.txt | 5 ++ include/linux/torture.h | 1 + include/trace/events/rcu.h | 2 +- kernel/rcu/Kconfig | 11 ++++ kernel/rcu/Kconfig.debug | 18 ++++- kernel/rcu/rcu.h | 2 + kernel/rcu/rcutorture.c | 65 +++++++++++++++++-- kernel/rcu/tiny.c | 14 ++++ kernel/rcu/tree.c | 20 ++++++ kernel/torture.c | 12 ++++ .../selftests/rcutorture/bin/srcu_lockdep.sh | 2 +- 11 files changed, 144 insertions(+), 8 deletions(-) -- 2.39.5 (Apple Git-154)

6 months, 3 weeks

3
18
0 0

Exclusive Proposal

by Gen Johan Bruntink

Hello I am keen to exchange thoughts on financial opportunities with you. If it aligns with your preferences, I would appreciate your WhatsApp contact details for a more fluid dialogue. Should that not suit, please let me know a convenient time for us to correspond directly. Thank you for your kind consideration. I eagerly anticipate your reply. Warm regards, General Johanne

6 months, 3 weeks

1
0
0 0

[PATCH v10 net-next 0/5] 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 v10. v10 - Remove leftover include in include/linux/netdevice.h and anonimous struct in sch_dualpi2.c (Paolo Abeni <pabeni(a)redhat.com>) - Use kfree_skb_reason() and add SKB_DROP_REASON_DUALPI2_STEP_DROP drop reason (Paolo Abeni <pabeni(a)redhat.com>) - Split DualPI2 patch into 3 patches: Struct definition & parsing, Dump statstics & configuration, Enqueue/Dequeue (Paolo Abeni <pabeni(a)redhat.com>) v9 - Fix mem_usage error in previous version - Add min_qlen_step to dualpi2 attribute as the minimum queue length in number of packets in the L-queue to start step threshold marking. In previous versions, this value was fixed to 2, so only when the queue length of the L queue was greater or equal to 2 packets step threshold was applied to mark packets in the L-queue. This will cause larger queuing delays for L4S traffic at low rates (<20Mbps). So we parameterize it and change the default value to 0. Comparsion of tcp_1down run 'HTB 20Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 11.55 11.70 ms 350 TCP upload avg : 18.96 N/A Mbits/s 350 TCP upload sum : 18.96 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 10.81 10.70 ms 350 TCP upload avg : 18.91 N/A Mbits/s 350 TCP upload sum : 18.91 N/A Mbits/s 350 Comparsion of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 12.61 12.80 ms 350 TCP upload avg : 9.48 N/A Mbits/s 350 TCP upload sum : 9.48 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.06 10.80 ms 350 TCP upload avg : 9.43 N/A Mbits/s 350 TCP upload sum : 9.43 N/A Mbits/s 350 Comparsion of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 40.86 37.45 ms 350 TCP upload avg : 0.88 N/A Mbits/s 350 TCP upload sum : 0.88 N/A Mbits/s 350 TCP upload::1 : 0.88 0.97 Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.07 10.40 ms 350 TCP upload avg : 0.55 N/A Mbits/s 350 TCP upload sum : 0.55 N/A Mbits/s 350 TCP upload::1 : 0.55 0.59 Mbits/s 350 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 (4): Documentation: netlink: specs: tc: Add DualPI2 specification selftests/tc-testing: Add selftests for qdisc DualPI2 sched: Struct definition and parsing of dualpi2 qdisc sched: Dump configuration and statistics of dualpi2 qdisc Koen De Schepper (1): sched: Add enqueue/dequeue of dualpi2 qdisc Documentation/netlink/specs/tc.yaml | 144 +++ include/net/dropreason-core.h | 6 + include/uapi/linux/pkt_sched.h | 39 + net/sched/Kconfig | 12 + net/sched/Makefile | 1 + net/sched/sch_dualpi2.c | 1092 +++++++++++++++++ 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, 1445 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

6 months, 3 weeks

2
6
0 0

[PATCH v5 0/6] rust: reduce pointer casts, enable related lints

by Tamir Duberstein

This started with a patch that enabled `clippy::ptr_as_ptr`. Benno Lossin suggested I also look into `clippy::ptr_cast_constness` and I discovered `clippy::as_ptr_cast_mut`. This series now enables all 3 lints. It also enables `clippy::as_underscore` which ensures other pointer casts weren't missed. The first commit reduces the need for pointer casts and is shared with another series[1]. The final patch also enables pointer provenance lints and fixes violations. See that commit message for details. The build system portion of that commit is pretty messy but I couldn't find a better way to convincingly ensure that these lints were applied globally. Suggestions would be very welcome. Link: https://lore.kernel.org/all/20250307-no-offset-v1-0-0c728f63b69c@gmail.com/ [1] Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- Changes in v5: - Use `pointer::addr` in OF. (Boqun Feng) - Add documentation on stubs. (Benno Lossin) - Mark stubs `#[inline]`. - Pick up Alice's RB on a shared commit from https://lore.kernel.org/all/Z9f-3Aj3_FWBZRrm@google.com/. - Link to v4: https://lore.kernel.org/r/20250315-ptr-as-ptr-v4-0-b2d72c14dc26@gmail.com Changes in v4: - Add missing SoB. (Benno Lossin) - Use `without_provenance_mut` in alloc. (Boqun Feng) - Limit strict provenance lints to the `kernel` crate to avoid complex logic in the build system. This can be revisited on MSRV >= 1.84.0. - Rebase on rust-next. - Link to v3: https://lore.kernel.org/r/20250314-ptr-as-ptr-v3-0-e7ba61048f4a@gmail.com Changes in v3: - Fixed clippy warning in rust/kernel/firmware.rs. (kernel test robot) Link: https://lore.kernel.org/all/202503120332.YTCpFEvv-lkp@intel.com/ - s/as u64/as bindings::phys_addr_t/g. (Benno Lossin) - Use strict provenance APIs and enable lints. (Benno Lossin) - Link to v2: https://lore.kernel.org/r/20250309-ptr-as-ptr-v2-0-25d60ad922b7@gmail.com Changes in v2: - Fixed typo in first commit message. - Added additional patches, converted to series. - Link to v1: https://lore.kernel.org/r/20250307-ptr-as-ptr-v1-1-582d06514c98@gmail.com --- Tamir Duberstein (6): rust: retain pointer mut-ness in `container_of!` rust: enable `clippy::ptr_as_ptr` lint rust: enable `clippy::ptr_cast_constness` lint rust: enable `clippy::as_ptr_cast_mut` lint rust: enable `clippy::as_underscore` lint rust: use strict provenance APIs Makefile | 4 ++ init/Kconfig | 3 + rust/bindings/lib.rs | 1 + rust/kernel/alloc.rs | 2 +- rust/kernel/alloc/allocator_test.rs | 2 +- rust/kernel/alloc/kvec.rs | 4 +- rust/kernel/block/mq/operations.rs | 2 +- rust/kernel/block/mq/request.rs | 7 +- rust/kernel/device.rs | 5 +- rust/kernel/device_id.rs | 2 +- rust/kernel/devres.rs | 19 +++--- rust/kernel/error.rs | 2 +- rust/kernel/firmware.rs | 3 +- rust/kernel/fs/file.rs | 2 +- rust/kernel/io.rs | 16 ++--- rust/kernel/kunit.rs | 15 ++--- rust/kernel/lib.rs | 113 ++++++++++++++++++++++++++++++++- rust/kernel/list/impl_list_item_mod.rs | 2 +- rust/kernel/miscdevice.rs | 2 +- rust/kernel/of.rs | 6 +- rust/kernel/pci.rs | 15 +++-- rust/kernel/platform.rs | 6 +- rust/kernel/print.rs | 11 ++-- rust/kernel/rbtree.rs | 23 +++---- rust/kernel/seq_file.rs | 3 +- rust/kernel/str.rs | 18 ++---- rust/kernel/sync/poll.rs | 2 +- rust/kernel/uaccess.rs | 12 ++-- rust/kernel/workqueue.rs | 12 ++-- rust/uapi/lib.rs | 1 + 30 files changed, 218 insertions(+), 97 deletions(-) --- base-commit: 498f7ee4773f22924f00630136da8575f38954e8 change-id: 20250307-ptr-as-ptr-21b1867fc4d4 Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

6 months, 3 weeks

5
54
0 0

kself test fail for "kci_test_bridge_parent_id"

by ALOK TIWARI

Hi, "kci_test_bridge_parent_id" test failed with error "as device can not be enslaved while up". Here is Error log. ------------------- > ./rtnetlink.sh -t kci_test_bridge_parent_id -v COMMAND: ip link add name test-dummy0 type dummy COMMAND: ip link set test-dummy0 up COMMAND: modprobe -q netdevsim COMMAND: ip link add name test-bond0 type bond mode 802.3ad COMMAND: ip link set dev eni10np1 master test-bond0 Error: Device can not be enslaved while up. COMMAND: ip link set dev eni20np1 master test-bond0 Error: Device can not be enslaved while up. COMMAND: ip link add name test-br0 type bridge COMMAND: ip link set dev test-bond0 master test-br0 FAIL: bridge_parent_id ------------------- upstream commit ec4ffd100ffb ("Revert "net: rtnetlink: Enslave device before bringing it up""), suggest the following scenario! $ ip link set dummy0 up $ ip link set dummy0 master bond0 down According to last commit, do we need to modify "kci_test_bridge_parent_id" test set to down. --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -1129,8 +1129,8 @@ kci_test_bridge_parent_id() dev10=`ls ${sysfsnet}10/net/` dev20=`ls ${sysfsnet}20/net/` run_cmd ip link add name test-bond0 type bond mode 802.3ad - run_cmd ip link set dev $dev10 master test-bond0 - run_cmd ip link set dev $dev20 master test-bond0 + run_cmd ip link set dev $dev10 master test-bond0 down + run_cmd ip link set dev $dev20 master test-bond0 down run_cmd ip link add name test-br0 type bridge Success log with modified test case > ./rtnetlink.sh -t kci_test_bridge_parent_id -v COMMAND: ip link add name test-dummy0 type dummy COMMAND: ip link set test-dummy0 up COMMAND: modprobe -q netdevsim COMMAND: ip link add name test-bond0 type bond mode 802.3ad COMMAND: ip link set dev eni10np1 master test-bond0 down COMMAND: ip link set dev eni20np1 master test-bond0 down COMMAND: ip link add name test-br0 type bridge COMMAND: ip link set dev test-bond0 master test-br0 PASS: bridge_parent_id Thanks, Alok

6 months, 3 weeks

1
0
0 0

[PATCH] firmware: cs_dsp: Ensure cs_dsp_load[_coeff]() returns 0 on success

by Richard Fitzgerald

Set ret = 0 on successful completion of the processing loop in cs_dsp_load() and cs_dsp_load_coeff() to ensure that the function returns 0 on success. All normal firmware files will have at least one data block, and processing this block will set ret == 0, from the result of either regmap_raw_write() or cs_dsp_parse_coeff(). The kunit tests create a dummy firmware file that contains only the header, without any data blocks. This gives cs_dsp a file to "load" that will not cause any side-effects. As there aren't any data blocks, the processing loop will not set ret == 0. Originally there was a line after the processing loop: ret = regmap_async_complete(regmap); which would set ret == 0 before the function returned. Commit fe08b7d5085a ("firmware: cs_dsp: Remove async regmap writes") changed the regmap write to a normal sync write, so the call to regmap_async_complete() wasn't necessary and was removed. It was overlooked that the ret here wasn't only to check the result of regmap_async_complete(), it also set the final return value of the function. Fixes: fe08b7d5085a ("firmware: cs_dsp: Remove async regmap writes") Signed-off-by: Richard Fitzgerald <rf(a)opensource.cirrus.com> --- drivers/firmware/cirrus/cs_dsp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index 42433c19eb30..560724ce21aa 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -1631,6 +1631,7 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, cs_dsp_debugfs_save_wmfwname(dsp, file); + ret = 0; out_fw: cs_dsp_buf_free(&buf_list); @@ -2338,6 +2339,7 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware cs_dsp_debugfs_save_binname(dsp, file); + ret = 0; out_fw: cs_dsp_buf_free(&buf_list); -- 2.43.0

6 months, 3 weeks

2
1
0 0

[PATCH v5 iproute2-next 0/1] DualPI2 iproute2 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 iproute2 patch v4. v5 (25-Mar-25) - Use matches() to replace current strcmp() (Stephen Hemminger <stephen(a)networkplumber.org>) - Use general parse_percent() for handling scaled percentage values (Stephen Hemminger <stephen(a)networkplumber.org>) - Add print function for JSON of dualpi2 stats (Stephen Hemminger <stephen(a)networkplumber.org>) v4 (16-Mar-25) - Add min_qlen_step to dualpi2 attribute as the minimum queue length in number of packets in the L-queue to start step amrking. v3 (21-Feb-25) - Add memlimit to dualpi2 attribute, and add memory_used, max_memory_used, memory_limit in dualpi2 stats (Dave Taht <dave.taht(a)gmail.com>) - Update manual to align latest implementation and clarify the queue naming and default unit - Use common "get_scaled_alpha_beta" and clean print_opt for Dualpi2 v2 (23-Oct-24) - Rename get_float in dualpi2 to get_float_min_max in utils.c - Move get_float from iplink_can.c in utils.c (Stephen Hemminger <stephen(a)networkplumber.org>) - Add print function for JSON of dualpi2 (Stephen Hemminger <stephen(a)networkplumber.org>) For more details of DualPI2, plesae refer IETF RFC9332 (https://datatracker.ietf.org/doc/html/rfc9332). Best Regards, Chia-Yu Chia-Yu Chang (1): tc: add dualpi2 scheduler module bash-completion/tc | 11 +- include/uapi/linux/pkt_sched.h | 39 +++ include/utils.h | 2 + ip/iplink_can.c | 14 - lib/utils.c | 30 ++ man/man8/tc-dualpi2.8 | 249 ++++++++++++++++ tc/Makefile | 1 + tc/q_dualpi2.c | 519 +++++++++++++++++++++++++++++++++ 8 files changed, 850 insertions(+), 15 deletions(-) create mode 100644 man/man8/tc-dualpi2.8 create mode 100644 tc/q_dualpi2.c -- 2.34.1

6 months, 3 weeks

1
1
0 0

[PATCH v3 0/2] selftests: livepatch: test if ftrace can trace a livepatched function

by Filipe Xavier

This patchset add ftrace helpers functions and add a 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> Suggested-by: Marcos Paulo de Souza <mpdesouza(a)suse.com> Reviewed-by: Marcos Paulo de Souza <mpdesouza(a)suse.com> Acked-by: Miroslav Benes <mbenes(a)suse.cz> --- Changes in v3: - functions.sh: fixed sed to remove warning from shellcheck and add grep -Fw params. - test-ftrace.sh: change constant to use common SYSFS_KLP_DIR. - Link to v2: https://lore.kernel.org/r/20250318-ftrace-sftest-livepatch-v2-0-60cb0aa95cc… Changes in v2: - functions.sh: change check traced function to accept a list of functions. - Link to v1: https://lore.kernel.org/r/20250306-ftrace-sftest-livepatch-v1-0-a6f1dfc30e1… --- Filipe Xavier (2): selftests: livepatch: add new ftrace helpers functions selftests: livepatch: test if ftrace can trace a livepatched function tools/testing/selftests/livepatch/functions.sh | 49 ++++++++++++++++++++++++ tools/testing/selftests/livepatch/test-ftrace.sh | 34 ++++++++++++++++ 2 files changed, 83 insertions(+) --- base-commit: 848e076317446f9c663771ddec142d7c2eb4cb43 change-id: 20250306-ftrace-sftest-livepatch-60d9dc472235 Best regards, -- Filipe Xavier <felipeaggger(a)gmail.com>

6 months, 3 weeks

3
6
0 0

[PATCH] selftests/x86/lam: fix resource leak in do_uring() and allocate_dsa_pasid()

by Malaya Kumar Rout

Exception branch returns without closing the file descriptors 'file_fd' and 'fd' Signed-off-by: Malaya Kumar Rout <malayarout91(a)gmail.com> --- tools/testing/selftests/x86/lam.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c index 18d736640ece..eaba0a921322 100644 --- a/tools/testing/selftests/x86/lam.c +++ b/tools/testing/selftests/x86/lam.c @@ -682,7 +682,7 @@ int do_uring(unsigned long lam) return 1; if (fstat(file_fd, &st) < 0) - return 1; + goto cleanup; off_t file_sz = st.st_size; @@ -690,7 +690,7 @@ int do_uring(unsigned long lam) fi = malloc(sizeof(*fi) + sizeof(struct iovec) * blocks); if (!fi) - return 1; + goto cleanup; fi->file_sz = file_sz; fi->file_fd = file_fd; @@ -698,7 +698,7 @@ int do_uring(unsigned long lam) ring = malloc(sizeof(*ring)); if (!ring) { free(fi); - return 1; + goto cleanup; } memset(ring, 0, sizeof(struct io_ring)); @@ -730,6 +730,9 @@ int do_uring(unsigned long lam) free(fi); +cleanup: + close(file_fd); + return ret; } @@ -1189,8 +1192,10 @@ void *allocate_dsa_pasid(void) wq = mmap(NULL, 0x1000, PROT_WRITE, MAP_SHARED | MAP_POPULATE, fd, 0); - if (wq == MAP_FAILED) + if (wq == MAP_FAILED) { + close(fd); perror("mmap"); + } return wq; } -- 2.43.0

6 months, 3 weeks

1
0
0 0

[PATCH 0/3] selftests: vDSO: chacha: Bugfixes

by Thomas Weißschuh

Bugfixes for a few issues I ran into. Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- Thomas Weißschuh (3): selftests: vDSO: chacha: Correctly skip test if necessary selftests: vDSO: chacha: Include asm/hwcap.h for arm64 selftests: vDSO: chacha: Provide default definition of HWCAP_S390_VXRS tools/testing/selftests/vDSO/vdso_test_chacha.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) --- base-commit: 586de92313fcab8ed84ac5f78f4d2aae2db92c59 change-id: 20250324-s390-vdso-hwcap-0914c0f7c7f1 Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

6 months, 3 weeks

2
7
0 0

[PATCH v6 0/6] rust: reduce `as` casts, enable related lints

by Tamir Duberstein

This started with a patch that enabled `clippy::ptr_as_ptr`. Benno Lossin suggested I also look into `clippy::ptr_cast_constness` and I discovered `clippy::as_ptr_cast_mut`. This series now enables all 3 lints. It also enables `clippy::as_underscore` which ensures other pointer casts weren't missed. The first commit reduces the need for pointer casts and is shared with another series[1]. As a late addition, `clippy::cast_lossless` is also enabled. Link: https://lore.kernel.org/all/20250307-no-offset-v1-0-0c728f63b69c@gmail.com/ [1] Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- Changes in v6: - Drop strict provenance patch. - Fix URLs in doc comments. - Add patch to enable `clippy::cast_lossless`. - Rebase on rust-next. - Link to v5: https://lore.kernel.org/r/20250317-ptr-as-ptr-v5-0-5b5f21fa230a@gmail.com Changes in v5: - Use `pointer::addr` in OF. (Boqun Feng) - Add documentation on stubs. (Benno Lossin) - Mark stubs `#[inline]`. - Pick up Alice's RB on a shared commit from https://lore.kernel.org/all/Z9f-3Aj3_FWBZRrm@google.com/. - Link to v4: https://lore.kernel.org/r/20250315-ptr-as-ptr-v4-0-b2d72c14dc26@gmail.com Changes in v4: - Add missing SoB. (Benno Lossin) - Use `without_provenance_mut` in alloc. (Boqun Feng) - Limit strict provenance lints to the `kernel` crate to avoid complex logic in the build system. This can be revisited on MSRV >= 1.84.0. - Rebase on rust-next. - Link to v3: https://lore.kernel.org/r/20250314-ptr-as-ptr-v3-0-e7ba61048f4a@gmail.com Changes in v3: - Fixed clippy warning in rust/kernel/firmware.rs. (kernel test robot) Link: https://lore.kernel.org/all/202503120332.YTCpFEvv-lkp@intel.com/ - s/as u64/as bindings::phys_addr_t/g. (Benno Lossin) - Use strict provenance APIs and enable lints. (Benno Lossin) - Link to v2: https://lore.kernel.org/r/20250309-ptr-as-ptr-v2-0-25d60ad922b7@gmail.com Changes in v2: - Fixed typo in first commit message. - Added additional patches, converted to series. - Link to v1: https://lore.kernel.org/r/20250307-ptr-as-ptr-v1-1-582d06514c98@gmail.com --- Tamir Duberstein (6): rust: retain pointer mut-ness in `container_of!` rust: enable `clippy::ptr_as_ptr` lint rust: enable `clippy::ptr_cast_constness` lint rust: enable `clippy::as_ptr_cast_mut` lint rust: enable `clippy::as_underscore` lint rust: enable `clippy::cast_lossless` lint Makefile | 5 +++++ drivers/gpu/drm/drm_panic_qr.rs | 10 +++++----- rust/bindings/lib.rs | 1 + rust/kernel/alloc/allocator_test.rs | 2 +- rust/kernel/alloc/kvec.rs | 4 ++-- rust/kernel/block/mq/operations.rs | 2 +- rust/kernel/block/mq/request.rs | 7 ++++--- rust/kernel/device.rs | 5 +++-- rust/kernel/device_id.rs | 2 +- rust/kernel/devres.rs | 19 ++++++++++--------- rust/kernel/dma.rs | 6 +++--- rust/kernel/error.rs | 2 +- rust/kernel/firmware.rs | 3 ++- rust/kernel/fs/file.rs | 2 +- rust/kernel/io.rs | 18 +++++++++--------- rust/kernel/kunit.rs | 15 +++++++-------- rust/kernel/lib.rs | 5 ++--- rust/kernel/list/impl_list_item_mod.rs | 2 +- rust/kernel/miscdevice.rs | 2 +- rust/kernel/net/phy.rs | 4 ++-- rust/kernel/of.rs | 6 +++--- rust/kernel/pci.rs | 13 ++++++++----- rust/kernel/platform.rs | 6 ++++-- rust/kernel/print.rs | 11 +++++------ rust/kernel/rbtree.rs | 23 ++++++++++------------- rust/kernel/seq_file.rs | 3 ++- rust/kernel/str.rs | 10 +++++----- rust/kernel/sync/poll.rs | 2 +- rust/kernel/workqueue.rs | 12 ++++++------ rust/uapi/lib.rs | 1 + 30 files changed, 107 insertions(+), 96 deletions(-) --- base-commit: 28bb48c4cb34f65a9aa602142e76e1426da31293 change-id: 20250307-ptr-as-ptr-21b1867fc4d4 Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

6 months, 3 weeks

2
8
0 0

[PATCH v2 0/2] selftests: livepatch: test if ftrace can trace a livepatched function

by Filipe Xavier

This patchset add ftrace helpers functions and add a 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> Suggested-by: Marcos Paulo de Souza <mpdesouza(a)suse.com> Reviewed-by: Marcos Paulo de Souza <mpdesouza(a)suse.com> --- Changes in v2: - functions.sh: change check traced function to accept a list of functions. - Link to v1: https://lore.kernel.org/r/20250306-ftrace-sftest-livepatch-v1-0-a6f1dfc30e1… --- Filipe Xavier (2): selftests: livepatch: add new ftrace helpers functions selftests: livepatch: test if ftrace can trace a livepatched function tools/testing/selftests/livepatch/functions.sh | 49 ++++++++++++++++++++++++ tools/testing/selftests/livepatch/test-ftrace.sh | 34 ++++++++++++++++ 2 files changed, 83 insertions(+) --- base-commit: 848e076317446f9c663771ddec142d7c2eb4cb43 change-id: 20250306-ftrace-sftest-livepatch-60d9dc472235 Best regards, -- Filipe Xavier <felipeaggger(a)gmail.com>

6 months, 3 weeks

3
7
0 0

[PATCH net-next v7 0/9] Device memory TCP TX

by Mina Almasry

v7: https://lore.kernel.org/netdev/20250227041209.2031104-1-almasrymina@google.… === Changelog: - Check the dmabuf net_iov binding belongs to the device the TX is going out on. (Jakub) - Provide detailed inspection of callsites of __skb_frag_ref/skb_page_unref in patch 2's changelog (Jakub) 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 (8): netmem: add niov->type attribute to distinguish different net_iov types 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 | 38 ++- include/net/sock.h | 1 + include/uapi/linux/netdev.h | 1 + net/core/datagram.c | 48 ++- net/core/dev.c | 33 ++ net/core/devmem.c | 118 ++++++- net/core/devmem.h | 83 ++++- 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, 1002 insertions(+), 75 deletions(-) base-commit: 8ef890df4031121a94407c84659125cbccd3fdbe -- 2.49.0.rc0.332.g42c0ae87b1-goog

6 months, 3 weeks

5
21
0 0

[PATCH net-next] selftests: drv-net: rss_ctx: Don't assume indirection table is present

by Gal Pressman

The test_rss_context_dump() test assumes the indirection table is always supported, which is not true for all drivers, e.g., virtio_net when VIRTIO_NET_F_RSS is disabled. Skip the check if 'indir' is not present. Reviewed-by: Nimrod Oren <noren(a)nvidia.com> Signed-off-by: Gal Pressman <gal(a)nvidia.com> --- tools/testing/selftests/drivers/net/hw/rss_ctx.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index d6e69d7d5e43..ca60ae325c22 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -392,7 +392,7 @@ def test_rss_context_dump(cfg): # Sanity-check the results for data in ctxs: - ksft_ne(set(data['indir']), {0}, "indir table is all zero") + ksft_ne(set(data.get('indir', [1])), {0}, "indir table is all zero") ksft_ne(set(data.get('hkey', [1])), {0}, "key is all zero") # More specific checks -- 2.40.1

6 months, 3 weeks

3
2
0 0

[PATCH net-next v1 1/2] net: pktgen: add strict buffer parsing index check

by Peter Seiderer

Add strict buffer parsing index check to avoid the following Smatch warning: net/core/pktgen.c:877 get_imix_entries() warn: check that incremented offset 'i' is capped Checking the buffer index i after every get_user/i++ step and returning with error code immediately avoids the current indirect (but correct) error handling. Reported-by: Dan Carpenter <dan.carpenter(a)linaro.org> Closes: https://lore.kernel.org/netdev/36cf3ee2-38b1-47e5-a42a-363efeb0ace3@stanley… Signed-off-by: Peter Seiderer <ps.report(a)gmx.net> --- net/core/pktgen.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/core/pktgen.c b/net/core/pktgen.c index e850598db3e7..fe7fdefab994 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -856,6 +856,9 @@ static ssize_t get_imix_entries(const char __user *buffer, if (pkt_dev->n_imix_entries >= MAX_IMIX_ENTRIES) return -E2BIG; + if (i >= maxlen) + return -EINVAL; + max = min(10, maxlen - i); len = num_arg(&buffer[i], max, &size); if (len < 0) @@ -869,6 +872,8 @@ static ssize_t get_imix_entries(const char __user *buffer, if (c != ',') return -EINVAL; i++; + if (i >= maxlen) + return -EINVAL; if (size < 14 + 20 + 8) size = 14 + 20 + 8; @@ -911,6 +916,9 @@ static ssize_t get_labels(const char __user *buffer, if (n >= MAX_MPLS_LABELS) return -E2BIG; + if (i >= maxlen) + return -EINVAL; + max = min(8, maxlen - i); len = hex32_arg(&buffer[i], max, &tmp); if (len < 0) -- 2.48.1

6 months, 3 weeks

3
4
0 0

[PATCH v2 net-next 00/15] AccECN protocol patch series

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Plese find v2: v2 (18-03-2025) - Add one missing patch from previous AccECN protocol preparation patch series to this patch series The full patch series can be found in https://github.com/L4STeam/linux-net-next/commits/upstream_l4steam/ The Accurate ECN draft can be found in https://datatracker.ietf.org/doc/html/draft-ietf-tcpm-accurate-ecn-28 Best regards, Chia-Yu Chia-Yu Chang (1): tcp: accecn: AccECN option failure handling Ilpo Järvinen (14): tcp: fast path functions later tcp: AccECN core tcp: accecn: AccECN negotiation tcp: accecn: add AccECN rx byte counters tcp: accecn: AccECN needs to know delivered bytes tcp: allow embedding leftover into option padding tcp: sack option handling improvements tcp: accecn: AccECN option tcp: accecn: AccECN option send control tcp: accecn: AccECN option ceb/cep heuristic tcp: accecn: AccECN ACE field multi-wrap heuristic tcp: accecn: try to fit AccECN option with SACK tcp: try to avoid safer when ACKs are thinned gro: flushing when CWR is set negatively affects AccECN include/linux/tcp.h | 27 +- include/net/netns/ipv4.h | 2 + include/net/tcp.h | 198 +++++++++++-- include/uapi/linux/tcp.h | 7 + net/ipv4/syncookies.c | 3 + net/ipv4/sysctl_net_ipv4.c | 19 ++ net/ipv4/tcp.c | 26 +- net/ipv4/tcp_input.c | 591 +++++++++++++++++++++++++++++++++++-- net/ipv4/tcp_ipv4.c | 5 +- net/ipv4/tcp_minisocks.c | 92 +++++- net/ipv4/tcp_offload.c | 3 +- net/ipv4/tcp_output.c | 299 +++++++++++++++++-- net/ipv6/syncookies.c | 1 + net/ipv6/tcp_ipv6.c | 1 + 14 files changed, 1177 insertions(+), 97 deletions(-) -- 2.34.1

6 months, 3 weeks

4
18
0 0

[PATCH net-next] selftests: drv-net: rss_input_xfrm: Check test prerequisites before running

by Gal Pressman

Ensure the following prerequisites before executing the test: 1. 'socat' is installed on the remote host. 2. Python version supports socket.SO_INCOMING_CPU (available since v3.11). Skip the test if either prerequisite is not met. Reviewed-by: Nimrod Oren <noren(a)nvidia.com> Signed-off-by: Gal Pressman <gal(a)nvidia.com> --- .../testing/selftests/drivers/net/hw/rss_input_xfrm.py | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py index 53bb08cc29ec..58d74ba6c343 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py +++ b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py @@ -7,7 +7,7 @@ from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge, cmd, fd_read_timeout from lib.py import NetDrvEpEnv from lib.py import EthtoolFamily, NetdevFamily from lib.py import KsftSkipEx, KsftFailEx -from lib.py import rand_port +from lib.py import rand_port, CmdExitFailure def traffic(cfg, local_port, remote_port, ipver): @@ -32,6 +32,14 @@ def test_rss_input_xfrm(cfg, ipver): if multiprocessing.cpu_count() < 2: raise KsftSkipEx("Need at least two CPUs to test symmetric RSS hash") + try: + cmd("hash socat", host=cfg.remote) + except CmdExitFailure: + raise KsftSkipEx("socat not installed on remote") + + if not hasattr(socket, "SO_INCOMING_CPU"): + raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11") + input_xfrm = cfg.ethnl.rss_get( {'header': {'dev-name': cfg.ifname}}).get('input_xfrm') -- 2.40.1

6 months, 3 weeks

3
3
0 0

[PATCH 08/10] kunit: add module description for backtrace suppression test

by Arnd Bergmann

From: Arnd Bergmann <arnd(a)arndb.de> The module was added but has no description: WARNING: modpost: missing MODULE_DESCRIPTION() in lib/kunit/backtrace-suppression-test.o Fixes: ebf1c420422a ("kunit: add test cases for backtrace warning suppression") Signed-off-by: Arnd Bergmann <arnd(a)arndb.de> --- lib/kunit/backtrace-suppression-test.c | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/kunit/backtrace-suppression-test.c b/lib/kunit/backtrace-suppression-test.c index 8b4125af2481..1ceb30c736d7 100644 --- a/lib/kunit/backtrace-suppression-test.c +++ b/lib/kunit/backtrace-suppression-test.c @@ -102,3 +102,4 @@ static struct kunit_suite backtrace_suppression_test_suite = { kunit_test_suites(&backtrace_suppression_test_suite); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit test for suppressing warning tracebacks"); -- 2.39.5

6 months, 3 weeks

1
0
0 0

[PATCH net-next v11 00/10] 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/20250313-hash-v4-0-c75c494b495e@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 v11: - Added the missing code to free vnet_hash in patch "tap: Introduce virtio-net hash feature". - Link to v10: https://lore.kernel.org/r/20250313-rss-v10-0-3185d73a9af0@daynix.com Changes in v10: - Split common code and TUN/TAP-specific code into separate patches. - Reverted a spurious style change in patch "tun: Introduce virtio-net hash feature". - Added a comment explaining disable_ipv6 in tests. - Used AF_PACKET for patch "selftest: tun: Add tests for virtio-net hashing". I also added the usage of FIXTURE_VARIANT() as the testing function now needs access to more variant-specific variables. - Corrected the message of patch "selftest: tun: Add tests for virtio-net hashing"; it mentioned validation of configuration but it is not scope of this patch. - Expanded the description of patch "selftest: tun: Add tests for virtio-net hashing". - Added patch "tun: Allow steering eBPF program to fall back". - Changed to handle TUNGETVNETHASHCAP before taking the rtnl lock. - Removed redundant tests for tun_vnet_ioctl(). - Added patch "selftest: tap: Add tests for virtio-net ioctls". - Added a design explanation of ioctls for extensibility and migration. - Removed a few branches in patch "vhost/net: Support VIRTIO_NET_F_HASH_REPORT". - Link to v9: https://lore.kernel.org/r/20250307-rss-v9-0-df76624025eb@daynix.com Changes in v9: - Added a missing return statement in patch "tun: Introduce virtio-net hash feature". - Link to v8: https://lore.kernel.org/r/20250306-rss-v8-0-7ab4f56ff423@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 (10): virtio_net: Add functions for hashing net: flow_dissector: Export flow_keys_dissector_symmetric tun: Allow steering eBPF program to fall back tun: Add common virtio-net hash feature code tun: Introduce virtio-net hash feature tap: Introduce virtio-net hash feature selftest: tun: Test vnet ioctls without device selftest: tun: Add tests for virtio-net hashing selftest: tap: Add tests for virtio-net ioctls vhost/net: Support VIRTIO_NET_F_HASH_REPORT Documentation/networking/tuntap.rst | 7 + drivers/net/Kconfig | 1 + drivers/net/ipvlan/ipvtap.c | 2 +- drivers/net/macvtap.c | 2 +- drivers/net/tap.c | 78 +++++- drivers/net/tun.c | 90 +++++-- drivers/net/tun_vnet.h | 155 ++++++++++- drivers/vhost/net.c | 68 ++--- include/linux/if_tap.h | 4 +- include/linux/skbuff.h | 3 + include/linux/virtio_net.h | 188 ++++++++++++++ include/net/flow_dissector.h | 1 + include/uapi/linux/if_tun.h | 82 ++++++ net/core/flow_dissector.c | 3 +- net/core/skbuff.c | 4 + tools/testing/selftests/net/Makefile | 2 +- tools/testing/selftests/net/tap.c | 97 ++++++- tools/testing/selftests/net/tun.c | 491 ++++++++++++++++++++++++++++++++++- 18 files changed, 1194 insertions(+), 84 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>

6 months, 3 weeks

4
13
0 0

[PATCH v4 00/18] riscv: add SBI FWFT misaligned exception delegation support

by Clément Léger

The SBI Firmware Feature extension allows the S-mode to request some specific features (either hardware or software) to be enabled. This series uses this extension to request misaligned access exception delegation to S-mode in order to let the kernel handle it. It also adds support for the KVM FWFT SBI extension based on the misaligned access handling infrastructure. FWFT SBI extension is part of the SBI V3.0 specifications [1]. It can be tested using the qemu provided at [2] which contains the series from [3]. kvm-unit-tests [4] can be used inside kvm to tests the correct delegation of misaligned exceptions. Upstream OpenSBI can be used. Note: Since SBI V3.0 is not yet ratified, FWFT extension API is split between interface only and implementation, allowing to pick only the interface which do not have hard dependencies on SBI. The tests can be run using the included kselftest: $ qemu-system-riscv64 \ -cpu rv64,trap-misaligned-access=true,v=true \ -M virt \ -m 1024M \ -bios fw_dynamic.bin \ -kernel Image ... # ./misaligned TAP version 13 1..23 # Starting 23 tests from 1 test cases. # RUN global.gp_load_lh ... # OK global.gp_load_lh ok 1 global.gp_load_lh # RUN global.gp_load_lhu ... # OK global.gp_load_lhu ok 2 global.gp_load_lhu # RUN global.gp_load_lw ... # OK global.gp_load_lw ok 3 global.gp_load_lw # RUN global.gp_load_lwu ... # OK global.gp_load_lwu ok 4 global.gp_load_lwu # RUN global.gp_load_ld ... # OK global.gp_load_ld ok 5 global.gp_load_ld # RUN global.gp_load_c_lw ... # OK global.gp_load_c_lw ok 6 global.gp_load_c_lw # RUN global.gp_load_c_ld ... # OK global.gp_load_c_ld ok 7 global.gp_load_c_ld # RUN global.gp_load_c_ldsp ... # OK global.gp_load_c_ldsp ok 8 global.gp_load_c_ldsp # RUN global.gp_load_sh ... # OK global.gp_load_sh ok 9 global.gp_load_sh # RUN global.gp_load_sw ... # OK global.gp_load_sw ok 10 global.gp_load_sw # RUN global.gp_load_sd ... # OK global.gp_load_sd ok 11 global.gp_load_sd # RUN global.gp_load_c_sw ... # OK global.gp_load_c_sw ok 12 global.gp_load_c_sw # RUN global.gp_load_c_sd ... # OK global.gp_load_c_sd ok 13 global.gp_load_c_sd # RUN global.gp_load_c_sdsp ... # OK global.gp_load_c_sdsp ok 14 global.gp_load_c_sdsp # RUN global.fpu_load_flw ... # OK global.fpu_load_flw ok 15 global.fpu_load_flw # RUN global.fpu_load_fld ... # OK global.fpu_load_fld ok 16 global.fpu_load_fld # RUN global.fpu_load_c_fld ... # OK global.fpu_load_c_fld ok 17 global.fpu_load_c_fld # RUN global.fpu_load_c_fldsp ... # OK global.fpu_load_c_fldsp ok 18 global.fpu_load_c_fldsp # RUN global.fpu_store_fsw ... # OK global.fpu_store_fsw ok 19 global.fpu_store_fsw # RUN global.fpu_store_fsd ... # OK global.fpu_store_fsd ok 20 global.fpu_store_fsd # RUN global.fpu_store_c_fsd ... # OK global.fpu_store_c_fsd ok 21 global.fpu_store_c_fsd # RUN global.fpu_store_c_fsdsp ... # OK global.fpu_store_c_fsdsp ok 22 global.fpu_store_c_fsdsp # RUN global.gen_sigbus ... [12797.988647] misaligned[618]: unhandled signal 7 code 0x1 at 0x0000000000014dc0 in misaligned[4dc0,10000+76000] [12797.988990] CPU: 0 UID: 0 PID: 618 Comm: misaligned Not tainted 6.13.0-rc6-00008-g4ec4468967c9-dirty #51 [12797.989169] Hardware name: riscv-virtio,qemu (DT) [12797.989264] epc : 0000000000014dc0 ra : 0000000000014d00 sp : 00007fffe165d100 [12797.989407] gp : 000000000008f6e8 tp : 0000000000095760 t0 : 0000000000000008 [12797.989544] t1 : 00000000000965d8 t2 : 000000000008e830 s0 : 00007fffe165d160 [12797.989692] s1 : 000000000000001a a0 : 0000000000000000 a1 : 0000000000000002 [12797.989831] a2 : 0000000000000000 a3 : 0000000000000000 a4 : ffffffffdeadbeef [12797.989964] a5 : 000000000008ef61 a6 : 626769735f6e0000 a7 : fffffffffffff000 [12797.990094] s2 : 0000000000000001 s3 : 00007fffe165d838 s4 : 00007fffe165d848 [12797.990238] s5 : 000000000000001a s6 : 0000000000010442 s7 : 0000000000010200 [12797.990391] s8 : 000000000000003a s9 : 0000000000094508 s10: 0000000000000000 [12797.990526] s11: 0000555567460668 t3 : 00007fffe165d070 t4 : 00000000000965d0 [12797.990656] t5 : fefefefefefefeff t6 : 0000000000000073 [12797.990756] status: 0000000200004020 badaddr: 000000000008ef61 cause: 0000000000000006 [12797.990911] Code: 8793 8791 3423 fcf4 3783 fc84 c737 dead 0713 eef7 (c398) 0001 # OK global.gen_sigbus ok 23 global.gen_sigbus # PASSED: 23 / 23 tests passed. # Totals: pass:23 fail:0 xfail:0 xpass:0 skip:0 error:0 With kvm-tools: # lkvm run -k sbi.flat -m 128 Info: # lkvm run -k sbi.flat -m 128 -c 1 --name guest-97 Info: Removed ghost socket file "/root/.lkvm//guest-97.sock". ########################################################################## # kvm-unit-tests ########################################################################## ... [test messages elided] PASS: sbi: fwft: FWFT extension probing no error PASS: sbi: fwft: get/set reserved feature 0x6 error == SBI_ERR_DENIED PASS: sbi: fwft: get/set reserved feature 0x3fffffff error == SBI_ERR_DENIED PASS: sbi: fwft: get/set reserved feature 0x80000000 error == SBI_ERR_DENIED PASS: sbi: fwft: get/set reserved feature 0xbfffffff error == SBI_ERR_DENIED PASS: sbi: fwft: misaligned_deleg: Get misaligned deleg feature no error PASS: sbi: fwft: misaligned_deleg: Set misaligned deleg feature invalid value error PASS: sbi: fwft: misaligned_deleg: Set misaligned deleg feature invalid value error PASS: sbi: fwft: misaligned_deleg: Set misaligned deleg feature value no error PASS: sbi: fwft: misaligned_deleg: Set misaligned deleg feature value 0 PASS: sbi: fwft: misaligned_deleg: Set misaligned deleg feature value no error PASS: sbi: fwft: misaligned_deleg: Set misaligned deleg feature value 1 PASS: sbi: fwft: misaligned_deleg: Verify misaligned load exception trap in supervisor SUMMARY: 50 tests, 2 unexpected failures, 12 skipped This series is available at [6]. Link: https://github.com/riscv-non-isa/riscv-sbi-doc/releases/download/vv3.0-rc2/… [1] Link: https://github.com/rivosinc/qemu/tree/dev/cleger/misaligned [2] Link: https://lore.kernel.org/all/20241211211933.198792-3-fkonrad@amd.com/T/ [3] Link: https://github.com/clementleger/kvm-unit-tests/tree/dev/cleger/fwft_v1 [4] Link: https://github.com/clementleger/unaligned_test [5] Link: https://github.com/rivosinc/linux/tree/dev/cleger/fwft_v1 [6] --- V4: - Check SBI version 3.0 instead of 2.0 for FWFT presence - Use long for kvm_sbi_fwft operation return value - Init KVM sbi extension even if default_disabled - Remove revert_on_fail parameter for sbi_fwft_feature_set(). - Fix comments for sbi_fwft_set/get() - Only handle local features (there are no globals yet in the spec) - Add new SBI errors to sbi_err_map_linux_errno() V3: - Added comment about kvm sbi fwft supported/set/get callback requirements - Move struct kvm_sbi_fwft_feature in kvm_sbi_fwft.c - Add a FWFT interface V2: - Added Kselftest for misaligned testing - Added get_user() usage instead of __get_user() - Reenable interrupt when possible in misaligned access handling - Document that riscv supports unaligned-traps - Fix KVM extension state when an init function is present - Rework SBI misaligned accesses trap delegation code - Added support for CPU hotplugging - Added KVM SBI reset callback - Added reset for KVM SBI FWFT lock - Return SBI_ERR_DENIED_LOCKED when LOCK flag is set Clément Léger (18): riscv: add Firmware Feature (FWFT) SBI extensions definitions riscv: sbi: add new SBI error mappings riscv: sbi: add FWFT extension interface riscv: sbi: add SBI FWFT extension calls riscv: misaligned: request misaligned exception from SBI riscv: misaligned: use on_each_cpu() for scalar misaligned access probing riscv: misaligned: use correct CONFIG_ ifdef for misaligned_access_speed riscv: misaligned: move emulated access uniformity check in a function riscv: misaligned: add a function to check misalign trap delegability riscv: misaligned: factorize trap handling riscv: misaligned: enable IRQs while handling misaligned accesses riscv: misaligned: use get_user() instead of __get_user() Documentation/sysctl: add riscv to unaligned-trap supported archs selftests: riscv: add misaligned access testing RISC-V: KVM: add SBI extension init()/deinit() functions RISC-V: KVM: add SBI extension reset callback RISC-V: KVM: add support for FWFT SBI extension RISC-V: KVM: add support for SBI_FWFT_MISALIGNED_DELEG Documentation/admin-guide/sysctl/kernel.rst | 4 +- arch/riscv/include/asm/cpufeature.h | 8 +- arch/riscv/include/asm/kvm_host.h | 5 +- arch/riscv/include/asm/kvm_vcpu_sbi.h | 12 + arch/riscv/include/asm/kvm_vcpu_sbi_fwft.h | 29 ++ arch/riscv/include/asm/sbi.h | 62 +++++ arch/riscv/include/uapi/asm/kvm.h | 1 + arch/riscv/kernel/sbi.c | 95 +++++++ arch/riscv/kernel/traps.c | 57 ++-- arch/riscv/kernel/traps_misaligned.c | 118 +++++++- arch/riscv/kernel/unaligned_access_speed.c | 11 +- arch/riscv/kvm/Makefile | 1 + arch/riscv/kvm/vcpu.c | 7 +- arch/riscv/kvm/vcpu_sbi.c | 54 ++++ arch/riscv/kvm/vcpu_sbi_fwft.c | 252 +++++++++++++++++ arch/riscv/kvm/vcpu_sbi_sta.c | 3 +- .../selftests/riscv/misaligned/.gitignore | 1 + .../selftests/riscv/misaligned/Makefile | 12 + .../selftests/riscv/misaligned/common.S | 33 +++ .../testing/selftests/riscv/misaligned/fpu.S | 180 +++++++++++++ tools/testing/selftests/riscv/misaligned/gp.S | 103 +++++++ .../selftests/riscv/misaligned/misaligned.c | 254 ++++++++++++++++++ 22 files changed, 1255 insertions(+), 47 deletions(-) create mode 100644 arch/riscv/include/asm/kvm_vcpu_sbi_fwft.h create mode 100644 arch/riscv/kvm/vcpu_sbi_fwft.c create mode 100644 tools/testing/selftests/riscv/misaligned/.gitignore create mode 100644 tools/testing/selftests/riscv/misaligned/Makefile create mode 100644 tools/testing/selftests/riscv/misaligned/common.S create mode 100644 tools/testing/selftests/riscv/misaligned/fpu.S create mode 100644 tools/testing/selftests/riscv/misaligned/gp.S create mode 100644 tools/testing/selftests/riscv/misaligned/misaligned.c -- 2.47.2

6 months, 3 weeks

2
27
0 0

[PATCH v5 08/17] rust: kunit: refactor to use `&raw [const|mut]`

by Antonio Hickey

Replacing all occurrences of `addr_of!(place)` with `&raw const place`. This will allow us to reduce macro complexity, and improve consistency with existing reference syntax as `&raw const` is similar to `&` making it fit more naturally with other existing code. 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/kunit.rs | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) 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(), );

6 months, 3 weeks

3
2
0 0

[PATCHv4 RESEND net-next 0/2] selftests: wireguards: use nftables for testing

by Hangbin Liu

This patch set convert iptables to nftables for wireguard testing, as iptables is deparated and nftables is the default framework of most releases. v3: drop iptables directly (Jason A. Donenfeld) Also convert to using nft for qemu testing (Jason A. Donenfeld) v2: use one nft table for testing (Phil Sutter) Hangbin Liu (2): selftests: wireguards: convert iptables to nft selftests: wireguard: update to using nft for qemu test tools/testing/selftests/wireguard/netns.sh | 29 +++++++++----- .../testing/selftests/wireguard/qemu/Makefile | 40 ++++++++++++++----- .../selftests/wireguard/qemu/kernel.config | 7 ++-- 3 files changed, 53 insertions(+), 23 deletions(-) -- 2.46.0

6 months, 3 weeks

3
13
0 0

[PATCH v2] tools/nolibc: Add support for SPARC

by Thomas Weißschuh

Add support for 32bit and 64bit SPARC to nolibc. Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> Acked-by: Willy Tarreau <w(a)1wt.eu> Tested-by: Sebastian Andrzej Siewior <sebastian(a)breakpoint.cc> # UltraSparc T4 (Niagara4) --- This is only tested on QEMU. Any tests on real hardware would be very welcome. --- Changes in v2: - Pick up tags - Fix comment about syscall return register - Reword comment about stackpointer offsets - Link to v1: https://lore.kernel.org/r/20250316-nolibc-sparc-v1-1-2e97022d5e2c@weissschu… --- tools/include/nolibc/arch-sparc.h | 191 ++++++++++++++++++++++++++++ tools/include/nolibc/arch.h | 2 + tools/testing/selftests/nolibc/Makefile | 11 ++ tools/testing/selftests/nolibc/run-tests.sh | 2 + 4 files changed, 206 insertions(+) diff --git a/tools/include/nolibc/arch-sparc.h b/tools/include/nolibc/arch-sparc.h new file mode 100644 index 0000000000000000000000000000000000000000..1435172f3dfe33566cd8c61d726455702c804f6a --- /dev/null +++ b/tools/include/nolibc/arch-sparc.h @@ -0,0 +1,191 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * SPARC (32bit and 64bit) specific definitions for NOLIBC + * Copyright (C) 2025 Thomas Weißschuh <linux(a)weissschuh.net> + */ + +#ifndef _NOLIBC_ARCH_SPARC_H +#define _NOLIBC_ARCH_SPARC_H + +#include <linux/unistd.h> + +#include "compiler.h" +#include "crt.h" + +/* + * Syscalls for SPARC: + * - registers are native word size + * - syscall number is passed in g1 + * - arguments are in o0-o5 + * - the system call is performed by calling a trap instruction + * - syscall return value is in o0 + * - syscall error flag is in the carry bit of the processor status register + */ + +#ifdef __arch64__ + +#define _NOLIBC_SYSCALL "t 0x6d\n" \ + "bcs,a %%xcc, 1f\n" \ + "sub %%g0, %%o0, %%o0\n" \ + "1:\n" + +#else + +#define _NOLIBC_SYSCALL "t 0x10\n" \ + "bcs,a 1f\n" \ + "sub %%g0, %%o0, %%o0\n" \ + "1:\n" + +#endif /* __arch64__ */ + +#define my_syscall0(num) \ +({ \ + register long _num __asm__ ("g1") = (num); \ + register long _arg1 __asm__ ("o0"); \ + \ + __asm__ volatile ( \ + _NOLIBC_SYSCALL \ + : "+r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num __asm__ ("g1") = (num); \ + register long _arg1 __asm__ ("o0") = (long)(arg1); \ + \ + __asm__ volatile ( \ + _NOLIBC_SYSCALL \ + : "+r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("g1") = (num); \ + register long _arg1 __asm__ ("o0") = (long)(arg1); \ + register long _arg2 __asm__ ("o1") = (long)(arg2); \ + \ + __asm__ volatile ( \ + _NOLIBC_SYSCALL \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("g1") = (num); \ + register long _arg1 __asm__ ("o0") = (long)(arg1); \ + register long _arg2 __asm__ ("o1") = (long)(arg2); \ + register long _arg3 __asm__ ("o2") = (long)(arg3); \ + \ + __asm__ volatile ( \ + _NOLIBC_SYSCALL \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num __asm__ ("g1") = (num); \ + register long _arg1 __asm__ ("o0") = (long)(arg1); \ + register long _arg2 __asm__ ("o1") = (long)(arg2); \ + register long _arg3 __asm__ ("o2") = (long)(arg3); \ + register long _arg4 __asm__ ("o3") = (long)(arg4); \ + \ + __asm__ volatile ( \ + _NOLIBC_SYSCALL \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("g1") = (num); \ + register long _arg1 __asm__ ("o0") = (long)(arg1); \ + register long _arg2 __asm__ ("o1") = (long)(arg2); \ + register long _arg3 __asm__ ("o2") = (long)(arg3); \ + register long _arg4 __asm__ ("o3") = (long)(arg4); \ + register long _arg5 __asm__ ("o4") = (long)(arg5); \ + \ + __asm__ volatile ( \ + _NOLIBC_SYSCALL \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num __asm__ ("g1") = (num); \ + register long _arg1 __asm__ ("o0") = (long)(arg1); \ + register long _arg2 __asm__ ("o1") = (long)(arg2); \ + register long _arg3 __asm__ ("o2") = (long)(arg3); \ + register long _arg4 __asm__ ("o3") = (long)(arg4); \ + register long _arg5 __asm__ ("o4") = (long)(arg5); \ + register long _arg6 __asm__ ("o5") = (long)(arg6); \ + \ + __asm__ volatile ( \ + _NOLIBC_SYSCALL \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +/* startup code */ +void __attribute__((weak, noreturn)) __nolibc_entrypoint __no_stack_protector _start(void) +{ + __asm__ volatile ( + /* + * Save argc pointer to o0, as arg1 of _start_c. + * Account for the window save area, which is 16 registers wide. + */ +#ifdef __arch64__ + "add %sp, 128 + 2047, %o0\n" /* on sparc64 / v9 the stack is offset by 2047 */ +#else + "add %sp, 64, %o0\n" +#endif + "b,a _start_c\n" /* transfer to c runtime */ + ); + __nolibc_entrypoint_epilogue(); +} + +static pid_t getpid(void); + +static __attribute__((unused)) +pid_t sys_fork(void) +{ + pid_t parent, ret; + + parent = getpid(); + ret = my_syscall0(__NR_fork); + + /* The syscall returns the parent pid in the child instead of 0 */ + if (ret == parent) + return 0; + else + return ret; +} +#define sys_fork sys_fork + +#endif /* _NOLIBC_ARCH_SPARC_H */ diff --git a/tools/include/nolibc/arch.h b/tools/include/nolibc/arch.h index 8a2c143c0fba288147e5a7bf9db38ffb08367616..b8c1da9a88d1593d5a97f60909ede5d0c17699eb 100644 --- a/tools/include/nolibc/arch.h +++ b/tools/include/nolibc/arch.h @@ -33,6 +33,8 @@ #include "arch-s390.h" #elif defined(__loongarch__) #include "arch-loongarch.h" +#elif defined(__sparc__) +#include "arch-sparc.h" #else #error Unsupported Architecture #endif diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index 58bcbbd029bc3ad9ccac968191b703ccf5df0717..5060e189dc842d761dd13d70b8afdb2ff3390bc5 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -56,6 +56,8 @@ ARCH_mips32be = mips ARCH_riscv32 = riscv ARCH_riscv64 = riscv ARCH_s390x = s390 +ARCH_sparc32 = sparc +ARCH_sparc64 = sparc ARCH := $(or $(ARCH_$(XARCH)),$(XARCH)) # kernel image names by architecture @@ -76,6 +78,8 @@ IMAGE_riscv64 = arch/riscv/boot/Image IMAGE_s390x = arch/s390/boot/bzImage IMAGE_s390 = arch/s390/boot/bzImage IMAGE_loongarch = arch/loongarch/boot/vmlinuz.efi +IMAGE_sparc32 = arch/sparc/boot/image +IMAGE_sparc64 = arch/sparc/boot/image IMAGE = $(objtree)/$(IMAGE_$(XARCH)) IMAGE_NAME = $(notdir $(IMAGE)) @@ -97,6 +101,8 @@ DEFCONFIG_riscv64 = defconfig DEFCONFIG_s390x = defconfig DEFCONFIG_s390 = defconfig compat.config DEFCONFIG_loongarch = defconfig +DEFCONFIG_sparc32 = sparc32_defconfig +DEFCONFIG_sparc64 = sparc64_defconfig DEFCONFIG = $(DEFCONFIG_$(XARCH)) EXTRACONFIG = $(EXTRACONFIG_$(XARCH)) @@ -122,6 +128,8 @@ QEMU_ARCH_riscv64 = riscv64 QEMU_ARCH_s390x = s390x QEMU_ARCH_s390 = s390x QEMU_ARCH_loongarch = loongarch64 +QEMU_ARCH_sparc32 = sparc +QEMU_ARCH_sparc64 = sparc64 QEMU_ARCH = $(QEMU_ARCH_$(XARCH)) QEMU_ARCH_USER_ppc64le = ppc64le @@ -152,6 +160,8 @@ QEMU_ARGS_riscv64 = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_T QEMU_ARGS_s390x = -M s390-ccw-virtio -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_s390 = -M s390-ccw-virtio -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_loongarch = -M virt -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_sparc32 = -M SS-5 -m 256M -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_sparc64 = -M sun4u -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS = -m 1G $(QEMU_ARGS_$(XARCH)) $(QEMU_ARGS_BIOS) $(QEMU_ARGS_EXTRA) # OUTPUT is only set when run from the main makefile, otherwise @@ -174,6 +184,7 @@ CFLAGS_s390x = -m64 CFLAGS_s390 = -m31 CFLAGS_mips32le = -EL -mabi=32 -fPIC CFLAGS_mips32be = -EB -mabi=32 +CFLAGS_sparc32 = $(call cc-option,-m32) CFLAGS_STACKPROTECTOR ?= $(call cc-option,-mstack-protector-guard=global $(call cc-option,-fstack-protector-all)) CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables -std=c89 -W -Wall -Wextra \ $(call cc-option,-fno-stack-protector) $(call cc-option,-Wmissing-prototypes) \ diff --git a/tools/testing/selftests/nolibc/run-tests.sh b/tools/testing/selftests/nolibc/run-tests.sh index 0299a0912d4049dd12217f9835b81d231e1d2bfd..040956a9f5b8dda3e78abc0d4b6073f4fcd9e3ee 100755 --- a/tools/testing/selftests/nolibc/run-tests.sh +++ b/tools/testing/selftests/nolibc/run-tests.sh @@ -25,6 +25,7 @@ all_archs=( riscv32 riscv64 s390x s390 loongarch + sparc32 sparc64 ) archs="${all_archs[@]}" @@ -111,6 +112,7 @@ crosstool_arch() { loongarch) echo loongarch64;; mips*) echo mips;; s390*) echo s390;; + sparc*) echo sparc64;; *) echo "$1";; esac } --- base-commit: bceb73904c855c78402dca94c82915f078f259dd change-id: 20250226-nolibc-sparc-abf4775dc813 Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

6 months, 3 weeks

2
1
0 0

[RFC -next 00/10] Add ZC notifications to splice and sendfile

by Joe Damato

Greetings: Welcome to the RFC. Currently, when a user app uses sendfile the user app has no way to know if the bytes were transmit; sendfile simply returns, but it is possible that a slow client on the other side may take time to receive and ACK the bytes. In the meantime, the user app which called sendfile has no way to know whether it can overwrite the data on disk that it just sendfile'd. One way to fix this is to add zerocopy notifications to sendfile similar to how MSG_ZEROCOPY works with sendmsg. This is possible thanks to the extensive work done by Pavel [1]. To support this, two important user ABI changes are proposed: - A new splice flag, SPLICE_F_ZC, which allows users to signal that splice should generate zerocopy notifications if possible. - A new system call, sendfile2, which is similar to sendfile64 except that it takes an additional argument, flags, which allows the user to specify either a "regular" sendfile or a sendfile with zerocopy notifications enabled. In either case, user apps can read notifications from the error queue (like they would with MSG_ZEROCOPY) to determine when their call to sendfile has completed. I tested this RFC using the selftest modified in the last patch and also by using the selftest between two different physical hosts: # server ./msg_zerocopy -4 -i eth0 -t 2 -v -r tcp # client (does the sendfiling) dd if=/dev/zero of=sendfile_data bs=1M count=8 ./msg_zerocopy -4 -i eth0 -D $SERVER_IP -v -l 1 -t 2 -z -f sendfile_data tcp I would love to get high level feedback from folks on a few things: - Is this functionality, at a high level, something that would be desirable / useful? I think so, but I'm of course I am biased ;) - Is this approach generally headed in the right direction? Are the proposed user ABI changes reasonable? If the above two points are generally agreed upon then I'd welcome feedback on the patches themselves :) This is kind of a net thing, but also kind of a splice thing so hope I am sending this to right places to get appropriate feedback. I based my code on the vfs/for-next tree, but am happy to rebase on another tree if desired. The cc-list got a little out of control, so I manually trimmed it down quite a bit; sorry if I missed anyone I should have CC'd in the process. Thanks, Joe [1]: https://lore.kernel.org/netdev/cover.1657643355.git.asml.silence@gmail.com/ Joe Damato (10): splice: Add ubuf_info to prepare for ZC splice: Add helper that passes through splice_desc splice: Factor splice_socket into a helper splice: Add SPLICE_F_ZC and attach ubuf fs: Add splice_write_sd to file operations fs: Extend do_sendfile to take a flags argument fs: Add sendfile2 which accepts a flags argument fs: Add sendfile flags for sendfile2 fs: Add sendfile2 syscall selftests: Add sendfile zerocopy notification test arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/arm/tools/syscall.tbl | 1 + arch/arm64/tools/syscall_32.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/mips/kernel/syscalls/syscall_n32.tbl | 1 + arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 1 + arch/parisc/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/s390/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + fs/read_write.c | 40 +++++++--- fs/splice.c | 87 +++++++++++++++++---- include/linux/fs.h | 2 + include/linux/sendfile.h | 10 +++ include/linux/splice.h | 7 +- include/linux/syscalls.h | 2 + include/uapi/asm-generic/unistd.h | 4 +- net/socket.c | 1 + scripts/syscall.tbl | 1 + tools/testing/selftests/net/msg_zerocopy.c | 54 ++++++++++++- tools/testing/selftests/net/msg_zerocopy.sh | 5 ++ 27 files changed, 200 insertions(+), 29 deletions(-) create mode 100644 include/linux/sendfile.h base-commit: 2e72b1e0aac24a12f3bf3eec620efaca7ab7d4de -- 2.43.0

6 months, 3 weeks

5
37
0 0

[PATCH v9 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 v9. v9 - Fix mem_usage error in previous version - Add min_qlen_step to dualpi2 attribute as the minimum queue length in number of packets in the L-queue to start step threshold marking. In previous versions, this value was fixed to 2, so only when the queue length of the L queue was greater or equal to 2 packets step threshold was applied to mark packets in the L-queue. This will cause larger queuing delays for L4S traffic at low rates (<20Mbps). So we parameterize it and change the default value to 0. Comparsion of tcp_1down run 'HTB 20Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 11.55 11.70 ms 350 TCP upload avg : 18.96 N/A Mbits/s 350 TCP upload sum : 18.96 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 10.81 10.70 ms 350 TCP upload avg : 18.91 N/A Mbits/s 350 TCP upload sum : 18.91 N/A Mbits/s 350 Comparsion of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 12.61 12.80 ms 350 TCP upload avg : 9.48 N/A Mbits/s 350 TCP upload sum : 9.48 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.06 10.80 ms 350 TCP upload avg : 9.43 N/A Mbits/s 350 TCP upload sum : 9.43 N/A Mbits/s 350 Comparsion of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 40.86 37.45 ms 350 TCP upload avg : 0.88 N/A Mbits/s 350 TCP upload sum : 0.88 N/A Mbits/s 350 TCP upload::1 : 0.88 0.97 Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.07 10.40 ms 350 TCP upload avg : 0.55 N/A Mbits/s 350 TCP upload sum : 0.55 N/A Mbits/s 350 TCP upload::1 : 0.55 0.59 Mbits/s 350 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 | 144 +++ include/linux/netdevice.h | 1 + include/uapi/linux/pkt_sched.h | 39 + net/sched/Kconfig | 12 + net/sched/Makefile | 1 + net/sched/sch_dualpi2.c | 1090 +++++++++++++++++ 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, 1438 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

6 months, 3 weeks

2
4
0 0

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

by Tamir Duberstein

This is one of just 3 remaining "Test Module" kselftests (the others being printf 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 bitmap. I've already sent out a conversion series for each of printf[0] and scanf[1]. There was a previous attempt[2] to do this in July 2024. Please bear with me as I try to understand and address the objections from that time. I've spoken with Muhammad Usama Anjum, the author of that series, and received their approval to "take over" this work. Here we go... On 7/26/24 11:45 PM, John Hubbard wrote: > > This changes the situation from "works for Linus' tab completion > case", to "causes a tab completion problem"! :) > > I think a tests/ subdir is how we eventually decided to do this [1], > right? > > So: > > lib/tests/bitmap_kunit.c > > [1] https://lore.kernel.org/20240724201354.make.730-kees@kernel.org This is true and unfortunate, but not trivial to fix because new kallsyms tests were placed in lib/tests in commit 84b4a51fce4c ("selftests: add new kallsyms selftests") *after* the KUnit filename best practices were adopted. I propose that the KUnit maintainers blaze this trail using `string_kunit.c` which currently still lives in lib/ despite the KUnit docs giving it as an example at lib/tests/. On 7/27/24 12:24 AM, Shuah Khan wrote: > > This change will take away the ability to run bitmap tests during > boot on a non-kunit kernel. > > Nack on this change. I wan to see all tests that are being removed > from lib because they have been converted - also it doesn't make > sense to convert some tests like this one that add the ability test > during boot. This point was also discussed in another thread[3] in which: On 7/27/24 12:35 AM, Shuah Khan wrote: > > Please make sure you aren't taking away the ability to run these tests during > boot. > > It doesn't make sense to convert every single test especially when it > is intended to be run during boot without dependencies - not as a kunit test > but a regression test during boot. > > bitmap is one example - pay attention to the config help test - bitmap > one clearly states it runs regression testing during boot. Any test that > says that isn't a candidate for conversion. > > I am going to nack any such conversions. The crux of the argument seems to be that the config help text is taken to describe the author's intent with the fragment "at boot". I think this may be a case of confirmation bias: I see at least the following KUnit tests with "at boot" in their help text: - CPUMASK_KUNIT_TEST - BITFIELD_KUNIT - CHECKSUM_KUNIT - UTIL_MACROS_KUNIT It seems to me that the inference being made is that any test that runs "at boot" is intended to be run by both developers and users, but I find no evidence that bitmap in particular would ever provide additional value when run by users. There's further discussion about KUnit not being "ideal for cases where people would want to check a subsystem on a running kernel", but I find no evidence that bitmap in particular is actually testing the running kernel; it is a unit test of the bitmap functions, which is also stated in the config help text. David Gow made many of the same points in his final reply[4], which was never replied to. Link: https://lore.kernel.org/all/20250207-printf-kunit-convert-v2-0-057b23860823… [0] Link: https://lore.kernel.org/all/20250207-scanf-kunit-convert-v4-0-a23e2afaede8@… [1] Link: https://lore.kernel.org/all/20240726110658.2281070-1-usama.anjum@collabora.… [2] Link: https://lore.kernel.org/all/327831fb-47ab-4555-8f0b-19a8dbcaacd7@collabora.… [3] Link: https://lore.kernel.org/all/CABVgOSmMoPD3JfzVd4VTkzGL2fZCo8LfwzaVSzeFimPrhg… [4] Thanks for your attention. Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- Tamir Duberstein (3): bitmap: remove _check_eq_u32_array bitmap: convert self-test to KUnit bitmap: 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 | 24 +- lib/Makefile | 2 +- lib/{test_bitmap.c => bitmap_kunit.c} | 454 +++++++++++++--------------------- tools/testing/selftests/lib/bitmap.sh | 3 - tools/testing/selftests/lib/config | 1 - 19 files changed, 195 insertions(+), 304 deletions(-) --- base-commit: 2014c95afecee3e76ca4a56956a936e23283f05b change-id: 20250207-bitmap-kunit-convert-92d3147b2eee Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

6 months, 3 weeks

8
26
0 0

[PATCH v4 08/16] rust: kunit: refactor to use `&raw [const|mut]`

by Antonio Hickey

Replacing all occurrences of `addr_of!(place)` and `addr_of_mut!(place)` with `&raw const place` and `&raw mut place` respectively. This will allow us to reduce macro complexity, and improve consistency with existing reference syntax as `&raw const`, `&raw mut` are similar to `&`, `&mut` making it fit more naturally with other existing code. 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/kunit.rs | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) 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(), ); -- 2.48.1

6 months, 3 weeks

5
7
0 0

[PATCH net-next 0/6] netconsole: Add support for userdata release

by Breno Leitao

I am submitting a series of patches that introduce a new feature for the netconsole subsystem, specifically the addition of the 'release' field to the sysdata structure. This feature allows the kernel release/version to be appended to the userdata dictionary in every message sent, enhancing the information available for debugging and monitoring purposes. This complements the already supported release prepend feature, which was added some time ago. The release prepend appends the release information at the message header, which is not ideal for two reasons: 1) It is difficult to determine if a message includes this information, making it hard and resource-intensive to parse. 2) When a message is fragmented, the release information is appended to every message fragment, consuming valuable space in the packet. The "release prepend" feature was created before the concept of userdata and sysdata. Now that this format has proven successful, we are implementing the release feature as part of this enhanced structure. This patch series aims to improve the netconsole subsystem by providing a more efficient and user-friendly way to include kernel release information in messages. I believe these changes will significantly aid in system analysis and troubleshooting. Suggested-by: Manu Bretelle <chantr4(a)gmail.com> Signed-off-by: Breno Leitao <leitao(a)debian.org> --- Breno Leitao (6): netconsole: introduce 'release' as a new sysdata field netconsole: implement configfs for release_enabled netconsole: add 'sysdata' suffix to related functions netconsole: append release to sysdata selftests: netconsole: Add tests for 'release' feature in sysdata docs: netconsole: document release feature Documentation/networking/netconsole.rst | 25 ++++++++ drivers/net/netconsole.c | 71 ++++++++++++++++++++-- .../selftests/drivers/net/netcons_sysdata.sh | 44 +++++++++++++- 3 files changed, 133 insertions(+), 7 deletions(-) --- base-commit: 941defcea7e11ad7ff8f0d4856716dd637d757dd change-id: 20250314-netcons_release-dc1f1f5ca0f7 Best regards, -- Breno Leitao <leitao(a)debian.org>

6 months, 3 weeks

3
13
0 0

[PATCH] KVM: selftests: Fix a couple "prio" signedness bugs

by Dan Carpenter

There is an assert which relies on "prio" to be signed. GUEST_ASSERT(prio >= 0); Change the type from uint32_t to int. Fixes: 728fcc46d2c2 ("KVM: selftests: aarch64: Add test for restoring active IRQs") Fixes: 0ad3ff4a6adc ("KVM: selftests: aarch64: Add preemption tests in vgic_irq") Signed-off-by: Dan Carpenter <dan.carpenter(a)linaro.org> --- --- tools/testing/selftests/kvm/arm64/vgic_irq.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c index f4ac28d53747..e89c0fc5eef3 100644 --- a/tools/testing/selftests/kvm/arm64/vgic_irq.c +++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c @@ -294,7 +294,8 @@ static void guest_restore_active(struct test_args *args, uint32_t first_intid, uint32_t num, kvm_inject_cmd cmd) { - uint32_t prio, intid, ap1r; + uint32_t intid, ap1r; + int prio; int i; /* @@ -362,7 +363,8 @@ static void test_inject_preemption(struct test_args *args, uint32_t first_intid, int num, kvm_inject_cmd cmd) { - uint32_t intid, prio, step = KVM_PRIO_STEPS; + uint32_t intid, step = KVM_PRIO_STEPS; + int prio; int i; /* Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs -- 2.47.2

6 months, 3 weeks

2
1
0 0

[RFC PATCH 1/2] time/timekeeping: Fix possible inconsistencies in _COARSE clockids

by John Stultz

Lei Chen raised an issue with CLOCK_MONOTONIC_COARSE seeing time inconsistencies. Lei tracked down that this was being caused by the adjustment tk->tkr_mono.xtime_nsec -= offset; which is made to compensate for the unaccumulated cycles in offset when the mult value is adjusted forward, so that the non-_COARSE clockids don't see inconsistencies. However, the _COARSE clockids don't use the mult*offset value in their calculations, so this subtraction can cause the _COARSE clock ids to jump back a bit. Now, by design, this negative adjustment should be fine, because the logic run from timekeeping_adjust() is done after we accumulate approx mult*interval_cycles into xtime_nsec. The accumulated (mult*interval_cycles) will be larger then the (mult_adj*offset) value subtracted from xtime_nsec, and both operations are done together under the tk_core.lock, so the net change to xtime_nsec should always be positive. However, do_adjtimex() calls into timekeeping_advance() as well, since we want to apply the ntp freq adjustment immediately. In this case, we don't return early when the offset is smaller then interval_cycles, so we don't end up accumulating any time into xtime_nsec. But we do go on to call timekeeping_adjust(), which modifies the mult value, and subtracts from xtime_nsec to correct for the new mult value. Here because we did not accumulate anything, we have a window where the _COARSE clockids that don't utilize the mult*offset value, can see an inconsistency. So to fix this, rework the timekeeping_advance() logic a bit so that when we are called from do_adjtimex() and the offset is smaller then cycle_interval, that we call timekeeping_forward(), to first accumulate the sub-interval time into xtime_nsec. Then with no unaccumulated cycles in offset, we can do the mult adjustment without worry of the subtraction having an impact. NOTE: This was implemented as a potential alternative to Thomas' approach here: https://lore.kernel.org/lkml/87cyej5rid.ffs@tglx/ And similarly, it needs some additional review and testing, as it was developed while packing for conference travel. Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Stephen Boyd <sboyd(a)kernel.org> Cc: Anna-Maria Behnsen <anna-maria(a)linutronix.de> Cc: Frederic Weisbecker <frederic(a)kernel.org> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Miroslav Lichvar <mlichvar(a)redhat.com> Cc: linux-kselftest(a)vger.kernel.org Cc: kernel-team(a)android.com Cc: Lei Chen <lei.chen(a)smartx.com> Fixes: da15cfdae033 ("time: Introduce CLOCK_REALTIME_COARSE") Reported-by: Lei Chen <lei.chen(a)smartx.com> Closes: https://lore.kernel.org/lkml/20250310030004.3705801-1-lei.chen@smartx.com/ Diagnosed-by: Thomas Gleixner <tglx(a)linutronix.de> Signed-off-by: John Stultz <jstultz(a)google.com> --- kernel/time/timekeeping.c | 87 ++++++++++++++++++++++++++++----------- 1 file changed, 62 insertions(+), 25 deletions(-) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 1e67d076f1955..6f3a145e7b113 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -682,18 +682,18 @@ static void timekeeping_update_from_shadow(struct tk_data *tkd, unsigned int act } /** - * timekeeping_forward_now - update clock to the current time + * timekeeping_forward - update clock to given cycle now value * @tk: Pointer to the timekeeper to update + * @cycle_now: Current clocksource read value * * Forward the current clock to update its state since the last call to * update_wall_time(). This is useful before significant clock changes, * as it avoids having to deal with this time offset explicitly. */ -static void timekeeping_forward_now(struct timekeeper *tk) +static void timekeeping_forward(struct timekeeper *tk, u64 cycle_now) { - u64 cycle_now, delta; + u64 delta; - cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask, tk->tkr_mono.clock->max_raw_delta); tk->tkr_mono.cycle_last = cycle_now; @@ -710,6 +710,21 @@ static void timekeeping_forward_now(struct timekeeper *tk) } } +/** + * timekeeping_forward_now - update clock to the current time + * @tk: Pointer to the timekeeper to update + * + * Forward the current clock to update its state since the last call to + * update_wall_time(). This is useful before significant clock changes, + * as it avoids having to deal with this time offset explicitly. + */ +static void timekeeping_forward_now(struct timekeeper *tk) +{ + u64 cycle_now = tk_clock_read(&tk->tkr_mono); + + timekeeping_forward(tk, cycle_now); +} + /** * ktime_get_real_ts64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set @@ -2151,6 +2166,45 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, return offset; } +static u64 timekeeping_accumulate(struct timekeeper *tk, u64 now, u64 offset, + unsigned int *clock_set) +{ + struct timekeeper *real_tk = &tk_core.timekeeper; + int shift = 0, maxshift; + + /* + * If we have a sub-cycle_interval offset, we + * are likely doing a TK_FREQ_ADJ, so accumulate + * everything so we don't have a remainder offset + * when later adjusting the multiplier + */ + if (offset < real_tk->cycle_interval) { + timekeeping_forward(tk, now); + *clock_set = 1; + return 0; + } + + /* + * With NO_HZ we may have to accumulate many cycle_intervals + * (think "ticks") worth of time at once. To do this efficiently, + * we calculate the largest doubling multiple of cycle_intervals + * that is smaller than the offset. We then accumulate that + * chunk in one go, and then try to consume the next smaller + * doubled multiple. + */ + shift = ilog2(offset) - ilog2(tk->cycle_interval); + shift = max(0, shift); + /* Bound shift to one less than what overflows tick_length */ + maxshift = (64 - (ilog2(ntp_tick_length()) + 1)) - 1; + shift = min(shift, maxshift); + while (offset >= tk->cycle_interval) { + offset = logarithmic_accumulation(tk, offset, shift, clock_set); + if (offset < tk->cycle_interval << shift) + shift--; + } + return offset; +} + /* * timekeeping_advance - Updates the timekeeper to the current time and * current NTP tick length @@ -2160,8 +2214,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) struct timekeeper *tk = &tk_core.shadow_timekeeper; struct timekeeper *real_tk = &tk_core.timekeeper; unsigned int clock_set = 0; - int shift = 0, maxshift; - u64 offset; + u64 cycle_now, offset; guard(raw_spinlock_irqsave)(&tk_core.lock); @@ -2169,7 +2222,8 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) if (unlikely(timekeeping_suspended)) return false; - offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), + cycle_now = tk_clock_read(&tk->tkr_mono); + offset = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask, tk->tkr_mono.clock->max_raw_delta); @@ -2177,24 +2231,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) return false; - /* - * With NO_HZ we may have to accumulate many cycle_intervals - * (think "ticks") worth of time at once. To do this efficiently, - * we calculate the largest doubling multiple of cycle_intervals - * that is smaller than the offset. We then accumulate that - * chunk in one go, and then try to consume the next smaller - * doubled multiple. - */ - shift = ilog2(offset) - ilog2(tk->cycle_interval); - shift = max(0, shift); - /* Bound shift to one less than what overflows tick_length */ - maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; - shift = min(shift, maxshift); - while (offset >= tk->cycle_interval) { - offset = logarithmic_accumulation(tk, offset, shift, &clock_set); - if (offset < tk->cycle_interval<<shift) - shift--; - } + offset = timekeeping_accumulate(tk, cycle_now, offset, &clock_set); /* Adjust the multiplier to correct NTP error */ timekeeping_adjust(tk, offset); -- 2.49.0.rc1.451.g8f38331e32-goog

6 months, 3 weeks

2
6
0 0

[PATCH net 0/7] selftests/net: Mixed select()+polling mode for TCP-AO tests

by Dmitry Safonov via B4 Relay

Should fix flaky tcp-ao/connect-deny-ipv6 test. Begging pardon for the delay since the report and for sending it this late in the release cycle. Signed-off-by: Dmitry Safonov <0x7f454c46(a)gmail.com> --- Dmitry Safonov (7): selftests/net: Print TCP flags in more common format selftests/net: Provide tcp-ao counters comparison helper selftests/net: Fetch and check TCP-MD5 counters selftests/net: Add mixed select()+polling mode to TCP-AO tests selftests/net: Print the testing side in unsigned-md5 selftests/net: Delete timeout from test_connect_socket() selftests/net: Drop timeout argument from test_client_verify() tools/testing/selftests/net/tcp_ao/connect-deny.c | 58 ++-- tools/testing/selftests/net/tcp_ao/connect.c | 22 +- tools/testing/selftests/net/tcp_ao/icmps-discard.c | 17 +- .../testing/selftests/net/tcp_ao/key-management.c | 76 ++--- tools/testing/selftests/net/tcp_ao/lib/aolib.h | 114 ++++++-- .../testing/selftests/net/tcp_ao/lib/ftrace-tcp.c | 7 +- tools/testing/selftests/net/tcp_ao/lib/sock.c | 315 +++++++++++++++------ tools/testing/selftests/net/tcp_ao/restore.c | 75 +++-- tools/testing/selftests/net/tcp_ao/rst.c | 47 ++- tools/testing/selftests/net/tcp_ao/self-connect.c | 18 +- tools/testing/selftests/net/tcp_ao/seq-ext.c | 30 +- tools/testing/selftests/net/tcp_ao/unsigned-md5.c | 118 ++++---- 12 files changed, 552 insertions(+), 345 deletions(-) --- base-commit: 0fed89a961ea851945d23cc35beb59d6e56c0964 change-id: 20250312-tcp-ao-selftests-polling-21b6bbdf77b6 Best regards, -- Dmitry Safonov <0x7f454c46(a)gmail.com>

6 months, 3 weeks

4
14
0 0

[PATCH v8 0/3] rust: kunit: Support KUnit tests with a user-space like syntax

by David Gow

Hi all, This is v8 of the Rust/KUnit integration patch. I think all of the suggestions have at least been responded to (even if there are a few I'm leaving as either future projects or matters of taste). Hopefully this is good-to-go for 6.15, so we can start using it concurrently with making any additional improvements we may wish. This series was originally written by José Expósito, and has been modified and updated by Matt Gilbride, Miguel Ojeda, and myself. The original version can be found here: https://github.com/Rust-for-Linux/linux/pull/950 Add support for writing KUnit tests in Rust. While Rust doctests are already converted to KUnit tests and run, they're really better suited for examples, rather than as first-class unit tests. This series implements a series of direct Rust bindings for KUnit tests, as well as a new macro which allows KUnit tests to be written using a close variant of normal Rust unit test syntax. The only change required is replacing '#[cfg(test)]' with '#[kunit_tests(kunit_test_suite_name)]' An example test would look like: #[kunit_tests(rust_kernel_hid_driver)] mod tests { use super::*; use crate::{c_str, driver, hid, prelude::*}; use core::ptr; struct SimpleTestDriver; impl Driver for SimpleTestDriver { type Data = (); } #[test] fn rust_test_hid_driver_adapter() { let mut hid = bindings::hid_driver::default(); let name = c_str!("SimpleTestDriver"); static MODULE: ThisModule = unsafe { ThisModule::from_ptr(ptr::null_mut()) }; let res = unsafe { <hid::Adapter<SimpleTestDriver> as driver::DriverOps>::register(&mut hid, name, &MODULE) }; assert_eq!(res, Err(ENODEV)); // The mock returns -19 } } Please give this a go, and make sure I haven't broken it! There's almost certainly a lot of improvements which can be made -- and there's a fair case to be made for replacing some of this with generated C code which can use the C macros -- but this is hopefully an adequate implementation for now, and the interface can (with luck) remain the same even if the implementation changes. A few small notable missing features: - Attributes (like the speed of a test) are hardcoded to the default value. - Similarly, the module name attribute is hardcoded to NULL. In C, we use the KBUILD_MODNAME macro, but I couldn't find a way to use this from Rust which wasn't more ugly than just disabling it. - Assertions are not automatically rewritten to use KUnit assertions. --- Changes since v7: https://lore.kernel.org/rust-for-linux/20250214074051.1619256-1-davidgow@go… - Reworked the SAFETY comment for addr_of_mut! use with statics in kunit_unsafe_test_suite!() (again) - Removed the second mocking example, which was causing confusion. The first example of in_kunit_test() should be clear enough. Changes since v6: https://lore.kernel.org/rust-for-linux/20250214074051.1619256-1-davidgow@go… - Fixed an [allow(unused_unsafe)] which ended up in patch 2 instead of patch 1. (Thanks, Tamir!) - Doc comments now have several useful links. (Thanks, Tamir!) - Fix a potential compile error under macos. (Thanks, Tamir!) - Several small tidy-ups to limit unsafe usage. (Thanks, Tamir!) Changes since v5: https://lore.kernel.org/all/20241213081035.2069066-1-davidgow@google.com/ - Rebased against 6.14-rc1 - Fixed a bunch of warnings / clippy lints introduced in Rust 1.83 and 1.84. - No longer needs static_mut_refs / const_mut_refs, and is much cleaned up as a result. (Thanks, Miguel) - Major documentation and example fixes. (Thanks, Miguel) Changes since v4: https://lore.kernel.org/linux-kselftest/20241101064505.3820737-1-davidgow@g… - Rebased against 6.13-rc1 - Allowed an unused_unsafe warning after the behaviour of addr_of_mut!() changed in Rust 1.82. (Thanks Boqun, Miguel) - "Expect" that the sample assert_eq!(1+1, 2) produces a clippy warning due to a redundant assertion. (Thanks Boqun, Miguel) - Fix some missing safety comments, and remove some unneeded 'unsafe' blocks. (Thanks Boqun) - Fix a couple of minor rustfmt issues which were triggering checkpatch warnings. Changes since v3: https://lore.kernel.org/linux-kselftest/20241030045719.3085147-2-davidgow@g… - The kunit_unsafe_test_suite!() macro now panic!s if the suite name is too long, triggering a compile error. (Thanks, Alice!) - The #[kunit_tests()] macro now preserves span information, so errors can be better reported. (Thanks, Boqun!) - The example tests have been updated to no longer use assert_eq!() with a constant bool argument (which triggered a clippy warning now we have the span info). Changes since v2: https://lore.kernel.org/linux-kselftest/20241029092422.2884505-1-davidgow@g… - Include missing rust/macros/kunit.rs file from v2. (Thanks Boqun!) - The kunit_unsafe_test_suite!() macro will truncate the name of the suite if it is too long. (Thanks Alice!) - The proc macro now emits an error if the suite name is too long. - We no longer needlessly use UnsafeCell<> in kunit_unsafe_test_suite!(). (Thanks Alice!) Changes since v1: https://lore.kernel.org/lkml/20230720-rustbind-v1-0-c80db349e3b5@google.com… - Rebase on top of the latest rust-next (commit 718c4069896c) - Make kunit_case a const fn, rather than a macro (Thanks Boqun) - As a result, the null terminator is now created with kernel::kunit::kunit_case_null() - Use the C kunit_get_current_test() function to implement in_kunit_test(), rather than re-implementing it (less efficiently) ourselves. Changes since the GitHub PR: - Rebased on top of kselftest/kunit - Add const_mut_refs feature This may conflict with https://lore.kernel.org/lkml/20230503090708.2524310-6-nmi@metaspace.dk/ - Add rust/macros/kunit.rs to the KUnit MAINTAINERS entry --- José Expósito (3): rust: kunit: add KUnit case and suite macros rust: macros: add macro to easily run KUnit tests rust: kunit: allow to know if we are in a test MAINTAINERS | 1 + rust/kernel/kunit.rs | 171 +++++++++++++++++++++++++++++++++++++++++++ rust/macros/kunit.rs | 161 ++++++++++++++++++++++++++++++++++++++++ rust/macros/lib.rs | 29 ++++++++ 4 files changed, 362 insertions(+) create mode 100644 rust/macros/kunit.rs -- 2.49.0.rc0.332.g42c0ae87b1-goog

6 months, 3 weeks

2
7
0 0

[PATCH net v4 0/3] vsock/bpf: Handle races between sockmap update and connect() disconnecting

by Michal Luczaj

Signal delivery during connect() may disconnect an already established socket. Problem is that such socket might have been placed in a sockmap before the connection was closed. PATCH 1 ensures this race won't lead to an unconnected vsock staying in the sockmap. PATCH 2 selftests it. PATCH 3 fixes a related race. Note that selftest in PATCH 2 does test this code as well, but winning this race variant may take more than 2 seconds, so I'm not advertising it. Signed-off-by: Michal Luczaj <mhal(a)rbox.co> --- Changes in v4: - Selftest: send signal to only our own process - Link to v3: https://lore.kernel.org/r/20250316-vsock-trans-signal-race-v3-0-17a6862277c… Changes in v3: - Selftest: drop unnecessary variable initialization and reorder the calls - Link to v2: https://lore.kernel.org/r/20250314-vsock-trans-signal-race-v2-0-421a41f60f4… Changes in v2: - Handle one more path of tripping the warning - Add a selftest - Collect R-b [Stefano] - Link to v1: https://lore.kernel.org/r/20250307-vsock-trans-signal-race-v1-1-3aca3f771fb… --- Michal Luczaj (3): vsock/bpf: Fix EINTR connect() racing sockmap update selftest/bpf: Add test for AF_VSOCK connect() racing sockmap update vsock/bpf: Fix bpf recvmsg() racing transport reassignment net/vmw_vsock/af_vsock.c | 10 ++- net/vmw_vsock/vsock_bpf.c | 24 ++++-- .../selftests/bpf/prog_tests/sockmap_basic.c | 99 ++++++++++++++++++++++ 3 files changed, 124 insertions(+), 9 deletions(-) --- base-commit: da9e8efe7ee10e8425dc356a9fc593502c8e3933 change-id: 20250305-vsock-trans-signal-race-d62f7718d099 Best regards, -- Michal Luczaj <mhal(a)rbox.co>

6 months, 3 weeks

4
11
0 0

[PATCH bpf-next] selftests/bpf: Sanitize pointer prior fclose()

by Björn Töpel

From: Björn Töpel <bjorn(a)rivosinc.com> There are scenarios where env.{sub,}test_state->stdout_saved, can be NULL, e.g. sometimes when the watchdog timeout kicks in, or if the open_memstream syscall is not available. Avoid crashing test_progs by adding an explicit NULL check prior the fclose() call. Signed-off-by: Björn Töpel <bjorn(a)rivosinc.com> --- tools/testing/selftests/bpf/test_progs.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index d4ec9586b98c..309d9d4a8ace 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -103,12 +103,14 @@ static void stdio_restore(void) pthread_mutex_lock(&stdout_lock); if (env.subtest_state) { - fclose(env.subtest_state->stdout_saved); + if (env.subtest_state->stdout_saved) + fclose(env.subtest_state->stdout_saved); env.subtest_state->stdout_saved = NULL; stdout = env.test_state->stdout_saved; stderr = env.test_state->stdout_saved; } else { - fclose(env.test_state->stdout_saved); + if (env.test_state->stdout_saved) + fclose(env.test_state->stdout_saved); env.test_state->stdout_saved = NULL; stdout = env.stdout_saved; stderr = env.stderr_saved; base-commit: f3f8649585a445414521a6d5b76f41b51205086d -- 2.45.2

6 months, 3 weeks

3
2
0 0

[PATCH net v2 3/3] 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") Signed-off-by: Justin Iurman <justin.iurman(a)uliege.be> --- Cc: Shuah Khan <shuah(a)kernel.org> Cc: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/config | 2 + .../selftests/net/lwt_dst_cache_ref_loop.sh | 246 ++++++++++++++++++ 3 files changed, 249 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 5916f3b81c39..843ab747645d 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -101,6 +101,7 @@ 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..881eb399798f --- /dev/null +++ b/tools/testing/selftests/net/lwt_dst_cache_ref_loop.sh @@ -0,0 +1,246 @@ +#!/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." + 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 + +trap cleanup EXIT + +setup +run + +exit $ksft_pass -- 2.34.1

6 months, 3 weeks

3
3
0 0

[PATCH bpf-next v3 0/3] bpf: Fix use-after-free of sockmap

by Jiayuan Chen

Hi all, this is the v3 version. === Syzkaller reported this issue [1]. The current sockmap has a dependency on sk_socket in both read and write stages, but there is a possibility that sk->sk_socket is released during the process, leading to panic situations. For a detailed reproduction, please refer to the description in the v2: https://lore.kernel.org/bpf/20250228055106.58071-1-jiayuan.chen@linux.dev/ The corresponding fix approaches are described in the commit messages of each patch. By the way, the current sockmap lacks statistical information, especially global statistics, such as the number of successful or failed rx and tx operations. These statistics cannot be obtained from the socket interface itself. These data will be of great help in troubleshooting issues and observing sockmap behavior. If the maintainer/reviewer does not object, I think we can provide these statistical information in the future, either through proc/trace/bpftool. [1] https://syzkaller.appspot.com/bug?extid=dd90a702f518e0eac072 --- v2 -> v3: 1. Michal Luczaj reported similar race issue under sockmap sending path. 2. Rcu lock is conflict with mutex_lock in unix socket read implementation. https://lore.kernel.org/bpf/20250228055106.58071-1-jiayuan.chen@linux.dev/ 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 when sending bpf, sockmap: avoid using sk_socket after free when reading selftests/bpf: Add edge case tests for sockmap net/core/skmsg.c | 22 ++++++- .../selftests/bpf/prog_tests/socket_helpers.h | 13 +++- .../selftests/bpf/prog_tests/sockmap_basic.c | 60 +++++++++++++++++++ 3 files changed, 91 insertions(+), 4 deletions(-) -- 2.47.1

6 months, 3 weeks

3
11
0 0

[PATCH] kunit: tool: fix count of tests if late test plan

by Rae Moar

Fix test count with late test plan. For example, TAP version 13 ok 1 test1 1..4 Returns a count of 1 passed, 1 crashed (because it expects tests after the test plan): returning the total count of 2 tests Change this to be 1 passed, 1 error: total count of 1 test Signed-off-by: Rae Moar <rmoar(a)google.com> --- tools/testing/kunit/kunit_parser.py | 4 ++++ tools/testing/kunit/kunit_tool_test.py | 4 ++-- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index da53a709773a..c176487356e6 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -809,6 +809,10 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: test.log.extend(parse_diagnostic(lines)) if test.name != "" and not peek_test_name_match(lines, test): test.add_error(printer, 'missing subtest result line!') + elif not lines: + print_log(test.log, printer) + test.status = TestStatus.NO_TESTS + test.add_error(printer, 'No more test results!') else: parse_test_result(lines, test, expected_num, printer) diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 5ff4f6ffd873..bbba921e0eac 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -371,8 +371,8 @@ class KUnitParserTest(unittest.TestCase): """ result = kunit_parser.parse_run_tests(output.splitlines(), stdout) # Missing test results after test plan should alert a suspected test crash. - self.assertEqual(kunit_parser.TestStatus.TEST_CRASHED, result.status) - self.assertEqual(result.counts, kunit_parser.TestCounts(passed=1, crashed=1, errors=1)) + self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) + self.assertEqual(result.counts, kunit_parser.TestCounts(passed=1, errors=2)) def line_stream_from_strs(strs: Iterable[str]) -> kunit_parser.LineStream: return kunit_parser.LineStream(enumerate(strs, start=1)) base-commit: 2e0cf2b32f72b20b0db5cc665cd8465d0f257278 -- 2.49.0.395.g12beb8f557-goog

6 months, 3 weeks

2
1
0 0

[PATCH v3 1/2] 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 by parsing test plan line to avoid the infinite loop. Signed-off-by: Rae Moar <rmoar(a)google.com> --- Changes since v2: - None, adds test in second patch 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.rc1.451.g8f38331e32-goog

6 months, 3 weeks

3
6
0 0

[PATCH net-next 00/12] mptcp: pm: prep work for new ops and sysctl knobs

by Matthieu Baerts (NGI0)

Here are a few cleanups, preparation work for the new PM ops, and sysctl knobs. - Patch 1: reorg: move generic NL code used by all PMs to pm_netlink.c. - Patch 2: use kmemdup() instead of kmalloc + copy. - Patch 3: small cleanup to use pm var instead of msk->pm. - Patch 4: reorg: id_avail_bitmap is only used by the in-kernel PM. - Patch 5: use struct_group to easily reset a subset of PM data vars. - Patch 6: introduce the minimal skeleton for the new PM ops. - Patch 7: register in-kernel and userspace PM ops. - Patch 8: new net.mptcp.path_manager sysctl knob, deprecating pm_type. - Patch 9: map the new path_manager sysctl knob with pm_type. - Patch 10: map the old pm_type sysctl knob with path_manager. - Patch 11: new net.mptcp.available_path_managers sysctl knob. - Patch 12: new test to validate path_manager and pm_type mapping. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Geliang Tang (11): mptcp: pm: in-kernel: use kmemdup helper mptcp: pm: use pm variable instead of msk->pm mptcp: pm: only fill id_avail_bitmap for in-kernel pm mptcp: pm: add struct_group in mptcp_pm_data mptcp: pm: define struct mptcp_pm_ops mptcp: pm: register in-kernel and userspace PM mptcp: sysctl: set path manager by name mptcp: sysctl: map path_manager to pm_type mptcp: sysctl: map pm_type to path_manager mptcp: sysctl: add available_path_managers selftests: mptcp: add pm sysctl mapping tests Matthieu Baerts (NGI0) (1): mptcp: pm: split netlink and in-kernel init Documentation/networking/mptcp-sysctl.rst | 23 +++++ include/net/mptcp.h | 14 +++ net/mptcp/ctrl.c | 113 +++++++++++++++++++++- net/mptcp/pm.c | 97 ++++++++++++++++--- net/mptcp/pm_kernel.c | 16 +-- net/mptcp/pm_netlink.c | 6 ++ net/mptcp/pm_userspace.c | 10 ++ net/mptcp/protocol.h | 17 ++++ tools/testing/selftests/net/mptcp/userspace_pm.sh | 30 +++++- 9 files changed, 301 insertions(+), 25 deletions(-) --- base-commit: e016cf5f39e9c53e274a7b7122a949d8839b8782 change-id: 20250312-net-next-mptcp-pm-ops-intro-01510135cd5e Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

6 months, 3 weeks

3
25
0 0

[PATCH v2 0/2] Fix xdp_adjust_frags_tail_grow selftest on powerpc

by Saket Kumar Bhaskar

For platforms on powerpc architecture with a default page size greater than 4096, there was an inconsistency in fragment size calculation. This caused the BPF selftest xdp_adjust_tail/xdp_adjust_frags_tail_grow to fail on powerpc. The issue occurred because the fragment buffer size in bpf_prog_test_run_xdp() was set to 4096, while the actual data size in the fragment within the shared skb was checked against PAGE_SIZE (65536 on powerpc) in min_t, causing it to exceed 4096 and be set accordingly. This discrepancy led to an overflow when bpf_xdp_frags_increase_tail() checked for tailroom, as skb_frag_size(frag) could be greater than rxq->frag_size (when PAGE_SIZE > 4096). This change fixes: 1. test_run by getting the correct arch dependent PAGE_SIZE. 2. selftest by caculating tailroom and getting correct PAGE_SIZE. Changes: v1 -> v2: * Address comments from Alexander * Use dynamic page size, cacheline size and size of struct skb_shared_info to calculate parameters. * Fixed both test_run and selftest. v1: https://lore.kernel.org/all/20250122183720.1411176-1-skb99@linux.ibm.com/ Saket Kumar Bhaskar (2): bpf, test_run: Replace hardcoded page size with dynamic PAGE_SIZE in test_run selftests/bpf: Refactor xdp_adjust_tail selftest with dynamic sizing .../bpf/prog_tests/xdp_adjust_tail.c | 160 +++++++++++++----- .../bpf/progs/test_xdp_adjust_tail_grow.c | 41 +++-- 2 files changed, 149 insertions(+), 52 deletions(-) -- 2.43.5

6 months, 3 weeks

2
5
0 0

[PATCH 0/2] fs/proc/task_mmu: add guard region bit to pagemap

by Lorenzo Stoakes

Currently there is no means of determining whether a give page in a mapping range is designated a guard region (as installed via madvise() using the MADV_GUARD_INSTALL flag). This is generally not an issue, but in some instances users may wish to determine whether this is the case. This series adds this ability via /proc/$pid/pagemap, updates the documentation and adds a self test to assert that this functions correctly. Lorenzo Stoakes (2): fs/proc/task_mmu: add guard region bit to pagemap tools/selftests: add guard region test for /proc/$pid/pagemap Documentation/admin-guide/mm/pagemap.rst | 3 +- fs/proc/task_mmu.c | 6 ++- tools/testing/selftests/mm/guard-regions.c | 47 ++++++++++++++++++++++ tools/testing/selftests/mm/vm_util.h | 1 + 4 files changed, 55 insertions(+), 2 deletions(-) -- 2.48.1

6 months, 3 weeks

5
14
0 0

[PATCH bpf-next 0/2] selftests/bpf: Migrate test_xdp_vlan.sh into test_progs

by Bastien Curutchet (eBPF Foundation)

Hi all, This patch series continues the work to migrate the script tests into prog_tests. test_xdp_vlan.sh tests the ability of an XDP program to modify the VLAN ids on the fly. This isn't currently covered by an other test in the test_progs framework so I add a new file prog_tests/xdp_vlan.c that does the exact same tests (same network topology, same BPF programs) and remove the script. Signed-off-by: Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com> --- Bastien Curutchet (eBPF Foundation) (2): selftests/bpf: test_xdp_vlan: Rename BPF sections selftests/bpf: Migrate test_xdp_vlan.sh into test_progs tools/testing/selftests/bpf/Makefile | 4 +- tools/testing/selftests/bpf/prog_tests/xdp_vlan.c | 175 ++++++++++++++++ tools/testing/selftests/bpf/progs/test_xdp_vlan.c | 20 +- tools/testing/selftests/bpf/test_xdp_vlan.sh | 233 --------------------- .../selftests/bpf/test_xdp_vlan_mode_generic.sh | 9 - .../selftests/bpf/test_xdp_vlan_mode_native.sh | 9 - 6 files changed, 186 insertions(+), 264 deletions(-) --- base-commit: a814b9be27fb3c3f49343aee4b015b76f5875558 change-id: 20250130-xdp_vlan-e825cc4df14a Best regards, -- Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com>

6 months, 4 weeks

4
8
0 0

[PATCH] rseq/selftests: fix name clash with rseq UAPI header

by Michael Jeanson

When the rseq UAPI header is included 'union rseq' clashes with 'struct rseq', it's not the case in the rseq selftests but it does break the KVM selftests that also include this file. Rename 'union rseq' to 'union rseq_tls' to fix this. Fixes: e6644c967d3c ("rseq/selftests: Ensure the rseq ABI TLS is actually 1024 bytes") Reported-by: Mark Brown <broonie(a)kernel.org> Signed-off-by: Michael Jeanson <mjeanson(a)efficios.com> Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> --- tools/testing/selftests/rseq/rseq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index 6d8997d815ef..663a9cef1952 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -75,13 +75,13 @@ static int rseq_ownership; * Use a union to ensure we allocate a TLS area of 1024 bytes to accomodate an * rseq registration that is larger than the current rseq ABI. */ -union rseq { +union rseq_tls { struct rseq_abi abi; char dummy[RSEQ_THREAD_AREA_ALLOC_SIZE]; }; static -__thread union rseq __rseq __attribute__((tls_model("initial-exec"))) = { +__thread union rseq_tls __rseq __attribute__((tls_model("initial-exec"))) = { .abi = { .cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED, }, -- 2.43.0

6 months, 4 weeks

1
0
0 0

[PATCH v10 nf-next 0/3] conntrack: bridge: add double vlan, pppoe and pppoe-in-q

by Eric Woudstra

Conntrack bridge only tracks untagged and 802.1q. To make the bridge-fastpath experience more similar to the forward-fastpath experience, add double vlan, pppoe and pppoe-in-q tagged packets to bridge conntrack and to bridge filter chain. Split from patch-set: bridge-fastpath and related improvements v9 Eric Woudstra (3): netfilter: bridge: Add conntrack double vlan and pppoe netfilter: nft_chain_filter: Add bridge double vlan and pppoe selftests: netfilter: Add conntrack_bridge.sh net/bridge/netfilter/nf_conntrack_bridge.c | 83 +++++++-- net/netfilter/nft_chain_filter.c | 20 +- .../testing/selftests/net/netfilter/Makefile | 1 + .../net/netfilter/conntrack_bridge.sh | 176 ++++++++++++++++++ 4 files changed, 267 insertions(+), 13 deletions(-) create mode 100755 tools/testing/selftests/net/netfilter/conntrack_bridge.sh -- 2.47.1

6 months, 4 weeks

2
7
0 0

[PATCH net] selftests: drv-net: use defer in the ping test

by Jakub Kicinski

Make sure the test cleans up after itself. The XDP off statements at the end of the test may not be reached. Fixes: 75cc19c8ff89 ("selftests: drv-net: add xdp cases for ping.py") Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: ap420073(a)gmail.com CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/drivers/net/ping.py | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py index 93f4b411b378..fc69bfcc37c4 100755 --- a/tools/testing/selftests/drivers/net/ping.py +++ b/tools/testing/selftests/drivers/net/ping.py @@ -7,7 +7,7 @@ from lib.py import ksft_run, ksft_exit from lib.py import ksft_eq, KsftSkipEx, KsftFailEx from lib.py import EthtoolFamily, NetDrvEpEnv from lib.py import bkg, cmd, wait_port_listen, rand_port -from lib.py import ethtool, ip +from lib.py import defer, ethtool, ip remote_ifname="" no_sleep=False @@ -60,6 +60,7 @@ no_sleep=False prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o" cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote) cmd(f"ip link set dev {cfg.ifname} mtu 1500 xdpgeneric obj {prog} sec xdp", shell=True) + defer(cmd, f"ip link set dev {cfg.ifname} xdpgeneric off") if no_sleep != True: time.sleep(10) @@ -68,7 +69,9 @@ no_sleep=False test_dir = os.path.dirname(os.path.realpath(__file__)) prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o" cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote) + defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote) ip("link set dev %s mtu 9000 xdpgeneric obj %s sec xdp.frags" % (cfg.ifname, prog)) + defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdpgeneric off") if no_sleep != True: time.sleep(10) @@ -78,6 +81,7 @@ no_sleep=False prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o" cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote) cmd(f"ip -j link set dev {cfg.ifname} mtu 1500 xdp obj {prog} sec xdp", shell=True) + defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off") xdp_info = ip("-d link show %s" % (cfg.ifname), json=True)[0] if xdp_info['xdp']['mode'] != 1: """ @@ -94,10 +98,11 @@ no_sleep=False test_dir = os.path.dirname(os.path.realpath(__file__)) prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o" cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote) + defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote) try: cmd(f"ip link set dev {cfg.ifname} mtu 9000 xdp obj {prog} sec xdp.frags", shell=True) + defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off") except Exception as e: - cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote) raise KsftSkipEx('device does not support native-multi-buffer XDP') if no_sleep != True: @@ -111,6 +116,7 @@ no_sleep=False cmd(f"ip link set dev {cfg.ifname} xdpoffload obj {prog} sec xdp", shell=True) except Exception as e: raise KsftSkipEx('device does not support offloaded XDP') + defer(ip, f"link set dev {cfg.ifname} xdpoffload off") cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote) if no_sleep != True: @@ -157,7 +163,6 @@ no_sleep=False _test_v4(cfg) _test_v6(cfg) _test_tcp(cfg) - ip("link set dev %s xdpgeneric off" % cfg.ifname) def test_xdp_generic_mb(cfg, netnl) -> None: _set_xdp_generic_mb_on(cfg) @@ -169,7 +174,6 @@ no_sleep=False _test_v4(cfg) _test_v6(cfg) _test_tcp(cfg) - ip("link set dev %s xdpgeneric off" % cfg.ifname) def test_xdp_native_sb(cfg, netnl) -> None: _set_xdp_native_sb_on(cfg) @@ -181,7 +185,6 @@ no_sleep=False _test_v4(cfg) _test_v6(cfg) _test_tcp(cfg) - ip("link set dev %s xdp off" % cfg.ifname) def test_xdp_native_mb(cfg, netnl) -> None: _set_xdp_native_mb_on(cfg) @@ -193,14 +196,12 @@ no_sleep=False _test_v4(cfg) _test_v6(cfg) _test_tcp(cfg) - ip("link set dev %s xdp off" % cfg.ifname) def test_xdp_offload(cfg, netnl) -> None: _set_xdp_offload_on(cfg) _test_v4(cfg) _test_v6(cfg) _test_tcp(cfg) - ip("link set dev %s xdpoffload off" % cfg.ifname) def main() -> None: with NetDrvEpEnv(__file__) as cfg: @@ -213,7 +214,6 @@ no_sleep=False test_xdp_native_mb, test_xdp_offload], args=(cfg, EthtoolFamily())) - set_interface_init(cfg) ksft_exit() -- 2.48.1

6 months, 4 weeks

3
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror