The following commit has been merged into the irq/urgent branch of tip:

Commit-ID:     1dd1eff161bd55968d3d46bc36def62d71fb4785
Gitweb:        https://git.kernel.org/tip/1dd1eff161bd55968d3d46bc36def62d71fb4785
Author:        Zqiang <qiang.zhang1211@gmail.com>
AuthorDate:    Sat, 27 Apr 2024 18:28:08 +08:00
Committer:     Thomas Gleixner <tglx@linutronix.de>
CommitterDate: Mon, 29 Apr 2024 05:03:51 +02:00

softirq: Fix suspicious RCU usage in __do_softirq()

Currently, the condition "__this_cpu_read(ksoftirqd) == current" is used to
invoke rcu_softirq_qs() in ksoftirqd tasks context for non-RT kernels.

This works correctly as long as the context is actually task context but
this condition is wrong when:

     - the current task is ksoftirqd
     - the task is interrupted in a RCU read side critical section
     - __do_softirq() is invoked on return from interrupt

Syzkaller triggered the following scenario:

  -> finish_task_switch()
    -> put_task_struct_rcu_user()
      -> call_rcu(&task->rcu, delayed_put_task_struct)
        -> __kasan_record_aux_stack()
          -> pfn_valid()
            -> rcu_read_lock_sched()
              <interrupt>
                __irq_exit_rcu()
                -> __do_softirq)()
                   -> if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
                     __this_cpu_read(ksoftirqd) == current)
                     -> rcu_softirq_qs()
                       -> RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map))

The rcu quiescent state is reported in the rcu-read critical section, so
the lockdep warning is triggered.

Fix this by splitting out the inner working of __do_softirq() into a helper
function which takes an argument to distinguish between ksoftirqd task
context and interrupted context and invoke it from the relevant call sites
with the proper context information and use that for the conditional
invocation of rcu_softirq_qs().

Reported-by: syzbot+dce04ed6d1438ad69656@syzkaller.appspotmail.com
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Zqiang <qiang.zhang1211@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20240427102808.29356-1-qiang.zhang1211@gmail.com
Link: https://lore.kernel.org/lkml/8f281a10-b85a-4586-9586-5bbc12dc784f@paulmck-laptop/T/#mea8aba4abfcb97bbf499d169ce7f30c4cff1b0e3
---
 kernel/softirq.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/kernel/softirq.c b/kernel/softirq.c
index b315b21..0258201 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -508,7 +508,7 @@ static inline bool lockdep_softirq_start(void) { return false; }
 static inline void lockdep_softirq_end(bool in_hardirq) { }
 #endif
 
-asmlinkage __visible void __softirq_entry __do_softirq(void)
+static void handle_softirqs(bool ksirqd)
 {
 	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
 	unsigned long old_flags = current->flags;
@@ -563,8 +563,7 @@ restart:
 		pending >>= softirq_bit;
 	}
 
-	if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
-	    __this_cpu_read(ksoftirqd) == current)
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) && ksirqd)
 		rcu_softirq_qs();
 
 	local_irq_disable();
@@ -584,6 +583,11 @@ restart:
 	current_restore_flags(old_flags, PF_MEMALLOC);
 }
 
+asmlinkage __visible void __softirq_entry __do_softirq(void)
+{
+	handle_softirqs(false);
+}
+
 /**
  * irq_enter_rcu - Enter an interrupt context with RCU watching
  */
@@ -921,7 +925,7 @@ static void run_ksoftirqd(unsigned int cpu)
 		 * We can safely run softirq on inline stack, as we are not deep
 		 * in the task stack here.
 		 */
-		__do_softirq();
+		handle_softirqs(true);
 		ksoftirqd_run_end();
 		cond_resched();
 		return;

On Mon, Apr 29, 2024 at 03:08:02AM -0000, tip-bot2 for Zqiang wrote:
> The following commit has been merged into the irq/urgent branch of tip:
> 
> Commit-ID:     1dd1eff161bd55968d3d46bc36def62d71fb4785
> Gitweb:        https://git.kernel.org/tip/1dd1eff161bd55968d3d46bc36def62d71fb4785
> Author:        Zqiang <qiang.zhang1211@gmail.com>
> AuthorDate:    Sat, 27 Apr 2024 18:28:08 +08:00
> Committer:     Thomas Gleixner <tglx@linutronix.de>
> CommitterDate: Mon, 29 Apr 2024 05:03:51 +02:00
> 
> softirq: Fix suspicious RCU usage in __do_softirq()
> 
> Currently, the condition "__this_cpu_read(ksoftirqd) == current" is used to
> invoke rcu_softirq_qs() in ksoftirqd tasks context for non-RT kernels.
> 
> This works correctly as long as the context is actually task context but
> this condition is wrong when:
> 
>      - the current task is ksoftirqd
>      - the task is interrupted in a RCU read side critical section
>      - __do_softirq() is invoked on return from interrupt
> 
> Syzkaller triggered the following scenario:
> 
>   -> finish_task_switch()
>     -> put_task_struct_rcu_user()
>       -> call_rcu(&task->rcu, delayed_put_task_struct)
>         -> __kasan_record_aux_stack()
>           -> pfn_valid()
>             -> rcu_read_lock_sched()
>               <interrupt>
>                 __irq_exit_rcu()
>                 -> __do_softirq)()
>                    -> if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
>                      __this_cpu_read(ksoftirqd) == current)
>                      -> rcu_softirq_qs()
>                        -> RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map))
> 
> The rcu quiescent state is reported in the rcu-read critical section, so
> the lockdep warning is triggered.
> 
> Fix this by splitting out the inner working of __do_softirq() into a helper
> function which takes an argument to distinguish between ksoftirqd task
> context and interrupted context and invoke it from the relevant call sites
> with the proper context information and use that for the conditional
> invocation of rcu_softirq_qs().
> 
> Reported-by: syzbot+dce04ed6d1438ad69656@syzkaller.appspotmail.com
> Suggested-by: Thomas Gleixner <tglx@linutronix.de>
> Signed-off-by: Zqiang <qiang.zhang1211@gmail.com>
> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
> Link: https://lore.kernel.org/r/20240427102808.29356-1-qiang.zhang1211@gmail.com
> Link: https://lore.kernel.org/lkml/8f281a10-b85a-4586-9586-5bbc12dc784f@paulmck-laptop/T/#mea8aba4abfcb97bbf499d169ce7f30c4cff1b0e3

I can add that this also fixes a UAF reported by syzbot
(partially, another part of UAF is an unrelated bug):

Reported-by: syzbot+98edc2df894917b3431f@syzkaller.appspotmail.com



> ---
>  kernel/softirq.c | 12 ++++++++----
>  1 file changed, 8 insertions(+), 4 deletions(-)
> 
> diff --git a/kernel/softirq.c b/kernel/softirq.c
> index b315b21..0258201 100644
> --- a/kernel/softirq.c
> +++ b/kernel/softirq.c
> @@ -508,7 +508,7 @@ static inline bool lockdep_softirq_start(void) { return false; }
>  static inline void lockdep_softirq_end(bool in_hardirq) { }
>  #endif
>  
> -asmlinkage __visible void __softirq_entry __do_softirq(void)
> +static void handle_softirqs(bool ksirqd)
>  {
>  	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
>  	unsigned long old_flags = current->flags;
> @@ -563,8 +563,7 @@ restart:
>  		pending >>= softirq_bit;
>  	}
>  
> -	if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
> -	    __this_cpu_read(ksoftirqd) == current)
> +	if (!IS_ENABLED(CONFIG_PREEMPT_RT) && ksirqd)
>  		rcu_softirq_qs();
>  
>  	local_irq_disable();
> @@ -584,6 +583,11 @@ restart:
>  	current_restore_flags(old_flags, PF_MEMALLOC);
>  }
>  
> +asmlinkage __visible void __softirq_entry __do_softirq(void)
> +{
> +	handle_softirqs(false);
> +}
> +
>  /**
>   * irq_enter_rcu - Enter an interrupt context with RCU watching
>   */
> @@ -921,7 +925,7 @@ static void run_ksoftirqd(unsigned int cpu)
>  		 * We can safely run softirq on inline stack, as we are not deep
>  		 * in the task stack here.
>  		 */
> -		__do_softirq();
> +		handle_softirqs(true);
>  		ksoftirqd_run_end();
>  		cond_resched();
>  		return;