Re: [PATCH 7/9] srcu: Detect duplicate callback enqueue at registration

[Paul E. McKenney]

On Fri, Oct 23, 2026 at 06:18:39PM +0800, Kunwu Chan wrote:
> Move the duplicate-callback check from srcu_do_enqueue() to
> __call_srcu() entry so that detected duplicate registrations
> are rejected before they reach the deferred-list enqueue path.
> Report the callback address, function symbol, and object
> information, rate-limited to the first three occurrences.
> 
> Signed-off-by: Kunwu Chan <chentao@xxxxxxxxxx>

Getting the stackof the call_srcu() once double-enqueue is detected
would be a very good thing!

One question below.

> ---
>  kernel/rcu/srcutree.c | 20 ++++++++++++++------
>  1 file changed, 14 insertions(+), 6 deletions(-)
> 
> diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
> index 1993ddbdb828..3838d9fdf532 100644
> --- a/kernel/rcu/srcutree.c
> +++ b/kernel/rcu/srcutree.c
> @@ -27,6 +27,7 @@
>  #include <linux/smp.h>
>  #include <linux/delay.h>
>  #include <linux/module.h>
> +#include <linux/mm.h>
>  #include <linux/slab.h>
>  #include <linux/srcu.h>
>  
> @@ -1511,12 +1512,6 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
>  static void srcu_do_enqueue(struct srcu_struct *ssp, struct rcu_head *rhp,
>  			    rcu_callback_t func, bool do_norm)
>  {
> -	if (debug_rcu_head_queue(rhp)) {
> -		/* Probable double call_srcu(), so leak the callback. */
> -		WRITE_ONCE(rhp->func, srcu_leak_callback);
> -		WARN_ONCE(1, "call_srcu(): Leaked duplicate callback\n");
> -		return;
> -	}
>  	rhp->func = func;
>  	(void)srcu_gp_start_if_needed(ssp, rhp, do_norm);
>  }
> @@ -1529,6 +1524,8 @@ static void srcu_do_enqueue(struct srcu_struct *ssp, struct rcu_head *rhp,
>  static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
>  			rcu_callback_t func, bool do_norm)
>  {
> +	static atomic_t doublefrees;
> +
>  	/* Misaligned rcu_head! */
>  	WARN_ON_ONCE((unsigned long)rhp & (sizeof(void *) - 1));
>  
> @@ -1539,6 +1536,16 @@ static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
>  	if (WARN_ON_ONCE(ssp->srcu_reader_flavor == SRCU_READ_FLAVOR_ATOMIC))
>  		return; // Leak the callback rather than corrupt SRCU state.
>  
> +	if (debug_rcu_head_queue(rhp)) {
> +		if (atomic_inc_return(&doublefrees) < 4) {

Why this hard-coded 4?  Why not 3 or 5?  Should this be adjustable via
Kconfig or kernel boot parameter?  Or, alternatively, should the below
pr_err() instead be pr_err_ratelimited()?

> +			pr_err("%s(): Duplicate call_srcu() CB %p->%pS()\n",
> +			       __func__, rhp, rhp->func);
> +			mem_dump_obj(rhp);

Does any of this automatically dump out the stack that was recorded
in earlier patches in this series?

> +		}
> +		WRITE_ONCE(rhp->func, srcu_leak_callback);
> +		return;
> +	}
> +
>  	/* Record the caller: the irq_work's stack says nothing about it. */
>  	kasan_record_aux_stack(rhp);
>  
> @@ -1554,6 +1561,7 @@ static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
>  		if (READ_ONCE(sndp->draining) && !in_nmi()) {
>  			WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU),
>  				  "call_srcu() re-entered during callback drain; leaking callback\n");
> +			debug_rcu_head_unqueue(rhp);
>  			return;
>  		}
>  		sdp = this_cpu_ptr(ssp->sda);
> -- 
> 2.43.0
>