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 --- arch/arm64/lib/delay.c | 84 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) create mode 100644 arch/arm64/lib/delay.c (limited to 'arch/arm64/lib/delay.c') diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c new file mode 100644 index 000000000..e278e060e --- /dev/null +++ b/arch/arm64/lib/delay.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Delay loops based on the OpenRISC implementation. + * + * Copyright (C) 2012 ARM Limited + * + * Author: Will Deacon + */ + +#include +#include +#include +#include +#include + +#include + +#define USECS_TO_CYCLES(time_usecs) \ + xloops_to_cycles((time_usecs) * 0x10C7UL) + +static inline unsigned long xloops_to_cycles(unsigned long xloops) +{ + return (xloops * loops_per_jiffy * HZ) >> 32; +} + +/* + * Force the use of CNTVCT_EL0 in order to have the same base as WFxT. + * This avoids some annoying issues when CNTVOFF_EL2 is not reset 0 on a + * KVM host running at EL1 until we do a vcpu_put() on the vcpu. When + * running at EL2, the effective offset is always 0. + * + * Note that userspace cannot change the offset behind our back either, + * as the vcpu mutex is held as long as KVM_RUN is in progress. + */ +static cycles_t notrace __delay_cycles(void) +{ + guard(preempt_notrace)(); + return __arch_counter_get_cntvct_stable(); +} + +void __delay(unsigned long cycles) +{ + cycles_t start = __delay_cycles(); + + if (alternative_has_cap_unlikely(ARM64_HAS_WFXT)) { + u64 end = start + cycles; + + /* + * Start with WFIT. If an interrupt makes us resume + * early, use a WFET loop to complete the delay. + */ + wfit(end); + while ((__delay_cycles() - start) < cycles) + wfet(end); + } else if (arch_timer_evtstrm_available()) { + const cycles_t timer_evt_period = + USECS_TO_CYCLES(ARCH_TIMER_EVT_STREAM_PERIOD_US); + + while ((__delay_cycles() - start + timer_evt_period) < cycles) + wfe(); + } + + while ((__delay_cycles() - start) < cycles) + cpu_relax(); +} +EXPORT_SYMBOL(__delay); + +inline void __const_udelay(unsigned long xloops) +{ + __delay(xloops_to_cycles(xloops)); +} +EXPORT_SYMBOL(__const_udelay); + +void __udelay(unsigned long usecs) +{ + __const_udelay(usecs * 0x10C7UL); /* 2**32 / 1000000 (rounded up) */ +} +EXPORT_SYMBOL(__udelay); + +void __ndelay(unsigned long nsecs) +{ + __const_udelay(nsecs * 0x5UL); /* 2**32 / 1000000000 (rounded up) */ +} +EXPORT_SYMBOL(__ndelay); -- cgit v1.3.1