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 --- drivers/xen/time.c | 175 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 175 insertions(+) create mode 100644 drivers/xen/time.c (limited to 'drivers/xen/time.c') diff --git a/drivers/xen/time.c b/drivers/xen/time.c new file mode 100644 index 000000000..a2be0a4d4 --- /dev/null +++ b/drivers/xen/time.c @@ -0,0 +1,175 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Xen stolen ticks accounting. + */ +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include +#include +#include +#include +#include + +/* runstate info updated by Xen */ +static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate); + +static DEFINE_PER_CPU(u64[4], old_runstate_time); + +/* return an consistent snapshot of 64-bit time/counter value */ +static u64 get64(const u64 *p) +{ + u64 ret; + + if (BITS_PER_LONG < 64) { + u32 *p32 = (u32 *)p; + u32 h, l, h2; + + /* + * Read high then low, and then make sure high is + * still the same; this will only loop if low wraps + * and carries into high. + * XXX some clean way to make this endian-proof? + */ + do { + h = READ_ONCE(p32[1]); + l = READ_ONCE(p32[0]); + h2 = READ_ONCE(p32[1]); + } while(h2 != h); + + ret = (((u64)h) << 32) | l; + } else + ret = READ_ONCE(*p); + + return ret; +} + +static void xen_get_runstate_snapshot_cpu_delta( + struct vcpu_runstate_info *res, unsigned int cpu) +{ + u64 state_time; + struct vcpu_runstate_info *state; + + BUG_ON(preemptible()); + + state = per_cpu_ptr(&xen_runstate, cpu); + + do { + state_time = get64(&state->state_entry_time); + rmb(); /* Hypervisor might update data. */ + *res = __READ_ONCE(*state); + rmb(); /* Hypervisor might update data. */ + } while (get64(&state->state_entry_time) != state_time || + (state_time & XEN_RUNSTATE_UPDATE)); +} + +static void xen_get_runstate_snapshot_cpu(struct vcpu_runstate_info *res, + unsigned int cpu) +{ + int i; + + xen_get_runstate_snapshot_cpu_delta(res, cpu); + + for (i = 0; i < 4; i++) + res->time[i] += per_cpu(old_runstate_time, cpu)[i]; +} + +void xen_manage_runstate_time(int action) +{ + static struct vcpu_runstate_info *runstate_delta; + struct vcpu_runstate_info state; + int cpu, i; + + switch (action) { + case -1: /* backup runstate time before suspend */ + if (unlikely(runstate_delta)) + pr_warn_once("%s: memory leak as runstate_delta is not NULL\n", + __func__); + + runstate_delta = kmalloc_objs(*runstate_delta, + num_possible_cpus(), GFP_ATOMIC); + if (unlikely(!runstate_delta)) { + pr_warn("%s: failed to allocate runstate_delta\n", + __func__); + return; + } + + for_each_possible_cpu(cpu) { + xen_get_runstate_snapshot_cpu_delta(&state, cpu); + memcpy(runstate_delta[cpu].time, state.time, + sizeof(runstate_delta[cpu].time)); + } + + break; + + case 0: /* backup runstate time after resume */ + if (unlikely(!runstate_delta)) { + pr_warn("%s: cannot accumulate runstate time as runstate_delta is NULL\n", + __func__); + return; + } + + for_each_possible_cpu(cpu) { + for (i = 0; i < 4; i++) + per_cpu(old_runstate_time, cpu)[i] += + runstate_delta[cpu].time[i]; + } + + break; + + default: /* do not accumulate runstate time for checkpointing */ + break; + } + + if (action != -1 && runstate_delta) { + kfree(runstate_delta); + runstate_delta = NULL; + } +} + +/* return true when a vcpu could run but has no real cpu to run on */ +bool xen_vcpu_stolen(int vcpu) +{ + return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable; +} + +u64 xen_steal_clock(int cpu) +{ + struct vcpu_runstate_info state; + + xen_get_runstate_snapshot_cpu(&state, cpu); + return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline]; +} + +void xen_setup_runstate_info(int cpu) +{ + struct vcpu_register_runstate_memory_area area; + + area.addr.v = &per_cpu(xen_runstate, cpu); + + if (HYPERVISOR_vcpu_op(VCPUOP_register_runstate_memory_area, + xen_vcpu_nr(cpu), &area)) + BUG(); +} + +void __init xen_time_setup_guest(void) +{ + bool xen_runstate_remote; + + xen_runstate_remote = !HYPERVISOR_vm_assist(VMASST_CMD_enable, + VMASST_TYPE_runstate_update_flag); + + static_call_update(pv_steal_clock, xen_steal_clock); + + static_key_slow_inc(¶virt_steal_enabled); + if (xen_runstate_remote) + static_key_slow_inc(¶virt_steal_rq_enabled); +} -- cgit v1.3.1