From 5febf432df1cfa5b25d99b54c32103fafbdd0eb9 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Sun, 16 Aug 2026 15:32:33 +0200 Subject: kbuild: rust: keep Rust objects out of Clang LTO with inline helpers Under `CONFIG_LTO_CLANG` + `CONFIG_RUST_INLINE_HELPERS`, one may hit `objtool` errors such as: vmlinux.o: error: objtool: _R..._3Gsp4boot+0xd6a: can't find jump dest instruction at .text._R..._3Gsp4boot+0x1dfd The reason is that in such builds, the Clang invocation that compiles the combined Rust plus helpers bitcode emits LLVM bitcode (again) -- the final code generation happens in the linker's LTO step, which the `-mllvm` trap options passed to Clang do not reach. This, in turn, means that unreachable traps are missing, and the impossible paths do not merely fallthrough to the next symbol, but past the end of their own section, since LTO builds place each function in its own section. Thus filter `CC_FLAGS_LTO` out of the Clang invocation, so that it always emits machine code directly, with the traps in place. Assisted-by: LLM Cc: Gary Guo Cc: Boqun Feng Cc: Alice Ryhl Cc: Matthew Maurer Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: stable@vger.kernel.org Fixes: 3a2486cc1da5 ("kbuild: rust: provide an option to inline C helpers into Rust") Acked-by: Gary Guo Link: https://patch.msgid.link/20260816133233.197500-2-ojeda@kernel.org Signed-off-by: Miguel Ojeda --- samples/bpf/offwaketime.bpf.c | 141 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 141 insertions(+) create mode 100644 samples/bpf/offwaketime.bpf.c (limited to 'samples/bpf/offwaketime.bpf.c') diff --git a/samples/bpf/offwaketime.bpf.c b/samples/bpf/offwaketime.bpf.c new file mode 100644 index 000000000..4a65ba76c --- /dev/null +++ b/samples/bpf/offwaketime.bpf.c @@ -0,0 +1,141 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include "vmlinux.h" +#include +#include +#include +#include + +#ifndef PERF_MAX_STACK_DEPTH +#define PERF_MAX_STACK_DEPTH 127 +#endif + +#define MINBLOCK_US 1 +#define MAX_ENTRIES 10000 + +struct key_t { + char waker[TASK_COMM_LEN]; + char target[TASK_COMM_LEN]; + u32 wret; + u32 tret; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, struct key_t); + __type(value, u64); + __uint(max_entries, MAX_ENTRIES); +} counts SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, u64); + __uint(max_entries, MAX_ENTRIES); +} start SEC(".maps"); + +struct wokeby_t { + char name[TASK_COMM_LEN]; + u32 ret; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, struct wokeby_t); + __uint(max_entries, MAX_ENTRIES); +} wokeby SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(key_size, sizeof(u32)); + __uint(value_size, PERF_MAX_STACK_DEPTH * sizeof(u64)); + __uint(max_entries, MAX_ENTRIES); +} stackmap SEC(".maps"); + +#define STACKID_FLAGS (0 | BPF_F_FAST_STACK_CMP) + +SEC("kprobe/try_to_wake_up") +int waker(struct pt_regs *ctx) +{ + struct task_struct *p = (void *)PT_REGS_PARM1_CORE(ctx); + u32 pid = BPF_CORE_READ(p, pid); + struct wokeby_t woke; + + bpf_get_current_comm(&woke.name, sizeof(woke.name)); + woke.ret = bpf_get_stackid(ctx, &stackmap, STACKID_FLAGS); + + bpf_map_update_elem(&wokeby, &pid, &woke, BPF_ANY); + return 0; +} + +static inline int update_counts(void *ctx, u32 pid, u64 delta) +{ + struct wokeby_t *woke; + u64 zero = 0, *val; + struct key_t key; + + __builtin_memset(&key.waker, 0, sizeof(key.waker)); + bpf_get_current_comm(&key.target, sizeof(key.target)); + key.tret = bpf_get_stackid(ctx, &stackmap, STACKID_FLAGS); + key.wret = 0; + + woke = bpf_map_lookup_elem(&wokeby, &pid); + if (woke) { + key.wret = woke->ret; + __builtin_memcpy(&key.waker, woke->name, sizeof(key.waker)); + bpf_map_delete_elem(&wokeby, &pid); + } + + val = bpf_map_lookup_elem(&counts, &key); + if (!val) { + bpf_map_update_elem(&counts, &key, &zero, BPF_NOEXIST); + val = bpf_map_lookup_elem(&counts, &key); + if (!val) + return 0; + } + (*val) += delta; + return 0; +} + +#if 1 +/* taken from /sys/kernel/tracing/events/sched/sched_switch/format */ +SEC("tracepoint/sched/sched_switch") +int oncpu(struct trace_event_raw_sched_switch *ctx) +{ + /* record previous thread sleep time */ + u32 pid = ctx->prev_pid; +#else +SEC("kprobe.multi/finish_task_switch*") +int oncpu(struct pt_regs *ctx) +{ + struct task_struct *p = (void *)PT_REGS_PARM1_CORE(ctx); + /* record previous thread sleep time */ + u32 pid = BPF_CORE_READ(p, pid); +#endif + u64 delta, ts, *tsp; + + ts = bpf_ktime_get_ns(); + bpf_map_update_elem(&start, &pid, &ts, BPF_ANY); + + /* calculate current thread's delta time */ + pid = bpf_get_current_pid_tgid(); + tsp = bpf_map_lookup_elem(&start, &pid); + if (!tsp) + /* missed start or filtered */ + return 0; + + delta = bpf_ktime_get_ns() - *tsp; + bpf_map_delete_elem(&start, &pid); + delta = delta / 1000; + if (delta < MINBLOCK_US) + return 0; + + return update_counts(ctx, pid, delta); +} +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; -- cgit v1.3.1