From 4617721c502b2ddaa4e324e86da4997edf738fa5 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 2 Sep 2026 09:55:01 -0400 Subject: ftrace: Synchronize the initialization of ftrace_ops There's some internal state that ftrace_ops needs to have set, but since it can be declared outside of the ftrace.c code, it calls ftrace_ops_init() on the ops in every global function. The issue is that if two tasks call it on the same ops at the same time it is possible to have the initialization of one corrupt the initialization of the other call. Create a ops_mutex to use to synchronize every initialization of the ftrace_ops. The mutex is taken within checking the ftrace_ops flag that states it was initializied but the flag is checked again after the mutex has been taken. Checking first outside the mutex allows it to shortcut having to take the mutex. But then the check needs to be done again after the mute is taken in case of races. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260902095501.6b59af20@gandalf.local.home Fixes: f04f24fb7e48d ("ftrace, kprobes: Fix a deadlock on ftrace_regex_lock") Reported-by: sashiko-bot@kernel.org Close: https://lore.kernel.org/all/20260829025528.49A831F000E9@smtp.kernel.org/ Signed-off-by: Steven Rostedt --- 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