On Mon, Feb 02, 2026 at 05:13:34PM +0800, Li Zhe wrote:
> In the current KLP transition implementation, the strategy for running
> tasks relies on waiting for a context switch to attempt to clear the
> TIF_PATCH_PENDING flag. Alternatively, determine whether the
> TIF_PATCH_PENDING flag can be cleared by inspecting the stack once the
> process has yielded the CPU. However, this approach proves problematic
> in certain environments.
> 
> Consider a scenario where the majority of system CPUs are configured
> with nohzfull and isolcpus, each dedicated to a VM with a vCPU pinned
> to that physical core and configured with idle=poll within the guest.
> Under such conditions, these vCPUs rarely leave the CPU. Combined with
> the high core counts typical of modern server platforms, this results
> in transition completion times that are not only excessively prolonged
> but also highly unpredictable.
> 
> This patch resolves this issue by registering a callback with
> stop_machine. The callback attempts to transition the associated running
> task. In a VM environment configured with 32 CPUs, the live patching
> operation completes promptly after the SIGNALS_TIMEOUT period with this
> patch applied; without it, the process nearly fails to complete under
> the same scenario.
> 
> Co-developed-by: Rui Qi <[email protected]>
> Signed-off-by: Rui Qi <[email protected]>
> Signed-off-by: Li Zhe <[email protected]>

PeterZ, what's your take on this?

I wonder if we could instead do resched_cpu() or something similar to
trigger the call to klp_sched_try_switch() in __schedule()?

> ---
>  kernel/livepatch/transition.c | 62 ++++++++++++++++++++++++++++++++---
>  1 file changed, 58 insertions(+), 4 deletions(-)
> 
> diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
> index 2351a19ac2a9..9c078b9bd755 100644
> --- a/kernel/livepatch/transition.c
> +++ b/kernel/livepatch/transition.c
> @@ -10,6 +10,7 @@
>  #include <linux/cpu.h>
>  #include <linux/stacktrace.h>
>  #include <linux/static_call.h>
> +#include <linux/stop_machine.h>
>  #include "core.h"
>  #include "patch.h"
>  #include "transition.h"
> @@ -297,6 +298,61 @@ static int klp_check_and_switch_task(struct task_struct 
> *task, void *arg)
>       return 0;
>  }
>  
> +enum klp_stop_work_bit {
> +     KLP_STOP_WORK_PENDING_BIT,
> +};
> +
> +struct klp_stop_work_info {
> +     struct task_struct *task;
> +     unsigned long flag;
> +};
> +
> +static DEFINE_PER_CPU(struct cpu_stop_work, klp_transition_stop_work);
> +static DEFINE_PER_CPU(struct klp_stop_work_info, klp_stop_work_info);
> +
> +static int klp_check_task(struct task_struct *task, void *old_name)
> +{
> +     if (task == current)
> +             return klp_check_and_switch_task(current, old_name);
> +     else
> +             return task_call_func(task, klp_check_and_switch_task, 
> old_name);
> +}
> +
> +static int klp_transition_stop_work_fn(void *arg)
> +{
> +     struct klp_stop_work_info *info = (struct klp_stop_work_info *)arg;
> +     struct task_struct *task = info->task;
> +     const char *old_name;
> +
> +     clear_bit(KLP_STOP_WORK_PENDING_BIT, &info->flag);
> +
> +     if (likely(klp_patch_pending(task)))
> +             klp_check_task(task, &old_name);
> +
> +     put_task_struct(task);
> +
> +     return 0;
> +}
> +
> +static void klp_try_transition_running_task(struct task_struct *task)
> +{
> +     int cpu = task_cpu(task);
> +
> +     if (klp_signals_cnt && !(klp_signals_cnt % SIGNALS_TIMEOUT)) {
> +             struct klp_stop_work_info *info =
> +                     per_cpu_ptr(&klp_stop_work_info, cpu);
> +
> +             if (test_and_set_bit(KLP_STOP_WORK_PENDING_BIT, &info->flag))
> +                     return;
> +
> +             info->task = get_task_struct(task);
> +             if (!stop_one_cpu_nowait(cpu, klp_transition_stop_work_fn, info,
> +                                      per_cpu_ptr(&klp_transition_stop_work,
> +                                      cpu)))
> +                     put_task_struct(task);
> +     }
> +}
> +
>  /*
>   * Try to safely switch a task to the target patch state.  If it's currently
>   * running, or it's sleeping on a to-be-patched or to-be-unpatched function, 
> or
> @@ -323,10 +379,7 @@ static bool klp_try_switch_task(struct task_struct *task)
>        * functions.  If all goes well, switch the task to the target patch
>        * state.
>        */
> -     if (task == current)
> -             ret = klp_check_and_switch_task(current, &old_name);
> -     else
> -             ret = task_call_func(task, klp_check_and_switch_task, 
> &old_name);
> +     ret = klp_check_task(task, &old_name);
>  
>       switch (ret) {
>       case 0:         /* success */
> @@ -335,6 +388,7 @@ static bool klp_try_switch_task(struct task_struct *task)
>       case -EBUSY:    /* klp_check_and_switch_task() */
>               pr_debug("%s: %s:%d is running\n",
>                        __func__, task->comm, task->pid);
> +             klp_try_transition_running_task(task);
>               break;
>       case -EINVAL:   /* klp_check_and_switch_task() */
>               pr_debug("%s: %s:%d has an unreliable stack\n",
> -- 
> 2.20.1

-- 
Josh

Reply via email to