Re: [PATCH v3 09/16] perf/core: Use static_call to optimize perf_guest_info_callbacks

[Paolo Bonzini]

On 22/09/21 02:05, Sean Christopherson wrote:
> Use static_call to optimize perf's guest callbacks on arm64 and x86,
> which are now the only architectures that define the callbacks.  Use
> DEFINE_STATIC_CALL_RET0 as the default/NULL for all guest callbacks, as
> the callback semantics are that a return value '0' means "not in guest".
>
> static_call obviously avoids the overhead of CONFIG_RETPOLINE=y, but is
> also advantageous versus other solutions, e.g. per-cpu callbacks, in that
> a per-cpu memory load is not needed to detect the !guest case.
>
> Based on code from Peter and Like.
>
> Suggested-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
> Cc: Like Xu <like.xu.linux@xxxxxxxxx>
> Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
> ---
>   include/linux/perf_event.h | 28 ++++++----------------------
>   kernel/events/core.c       | 15 +++++++++++++++
>   2 files changed, 21 insertions(+), 22 deletions(-)
>
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index eefa197d5354..d582dfeb4e20 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -1240,37 +1240,21 @@ extern void perf_event_bpf_event(struct bpf_prog *prog,
>   
>   #ifdef CONFIG_GUEST_PERF_EVENTS
>   extern struct perf_guest_info_callbacks *perf_guest_cbs;
> -static inline struct perf_guest_info_callbacks *perf_get_guest_cbs(void)
> -{
> -	/* Reg/unreg perf_guest_cbs waits for readers via synchronize_rcu(). */
> -	lockdep_assert_preemption_disabled();
> +DECLARE_STATIC_CALL(__perf_guest_state, *perf_guest_cbs->state);
> +DECLARE_STATIC_CALL(__perf_guest_get_ip, *perf_guest_cbs->get_ip);
> +DECLARE_STATIC_CALL(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr);
>   
> -	/* Prevent reloading between a !NULL check and dereferences. */
> -	return READ_ONCE(perf_guest_cbs);
> -}
>   static inline unsigned int perf_guest_state(void)
>   {
> -	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
> -
> -	return guest_cbs ? guest_cbs->state() : 0;
> +	return static_call(__perf_guest_state)();
>   }
>   static inline unsigned long perf_guest_get_ip(void)
>   {
> -	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
> -
> -	/*
> -	 * Arbitrarily return '0' in the unlikely scenario that the callbacks
> -	 * are unregistered between checking guest state and getting the IP.
> -	 */
> -	return guest_cbs ? guest_cbs->get_ip() : 0;
> +	return static_call(__perf_guest_get_ip)();
>   }
>   static inline unsigned int perf_guest_handle_intel_pt_intr(void)
>   {
> -	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
> -
> -	if (guest_cbs && guest_cbs->handle_intel_pt_intr)
> -		return guest_cbs->handle_intel_pt_intr();
> -	return 0;
> +	return static_call(__perf_guest_handle_intel_pt_intr)();
>   }
>   extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs);
>   extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs);
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index c6ec05809f54..79c8ee1778a4 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -6485,12 +6485,23 @@ static void perf_pending_event(struct irq_work *entry)
>   #ifdef CONFIG_GUEST_PERF_EVENTS
>   struct perf_guest_info_callbacks *perf_guest_cbs;
>   
> +DEFINE_STATIC_CALL_RET0(__perf_guest_state, *perf_guest_cbs->state);
> +DEFINE_STATIC_CALL_RET0(__perf_guest_get_ip, *perf_guest_cbs->get_ip);
> +DEFINE_STATIC_CALL_RET0(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr);
> +
>   void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
>   {
>   	if (WARN_ON_ONCE(perf_guest_cbs))
>   		return;
>   
>   	WRITE_ONCE(perf_guest_cbs, cbs);
> +	static_call_update(__perf_guest_state, cbs->state);
> +	static_call_update(__perf_guest_get_ip, cbs->get_ip);
> +
> +	/* Implementing ->handle_intel_pt_intr is optional. */
> +	if (cbs->handle_intel_pt_intr)
> +		static_call_update(__perf_guest_handle_intel_pt_intr,
> +				   cbs->handle_intel_pt_intr);
>   }
>   EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks);
>   
> @@ -6500,6 +6511,10 @@ void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
>   		return;
>   
>   	WRITE_ONCE(perf_guest_cbs, NULL);
> +	static_call_update(__perf_guest_state, (void *)&__static_call_return0);
> +	static_call_update(__perf_guest_get_ip, (void *)&__static_call_return0);
> +	static_call_update(__perf_guest_handle_intel_pt_intr,
> +			   (void *)&__static_call_return0);
>   	synchronize_rcu();
>   }
>   EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);

Reviewed-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>