linux-kernel - Re: [PATCH v3 09/16] perf/core: Use static_call to optimize perf_guest_info

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <5ad3e3f9-260b-52b2-e0c8-9ab824e08fb4@redhat.com>
Date:   Wed, 22 Sep 2021 08:33:14 +0200
From:   Paolo Bonzini <pbonzini@...hat.com>
To:     Sean Christopherson <seanjc@...gle.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        Will Deacon <will@...nel.org>,
        Mark Rutland <mark.rutland@....com>,
        Marc Zyngier <maz@...nel.org>, Guo Ren <guoren@...nel.org>,
        Nick Hu <nickhu@...estech.com>,
        Greentime Hu <green.hu@...il.com>,
        Vincent Chen <deanbo422@...il.com>,
        Paul Walmsley <paul.walmsley@...ive.com>,
        Palmer Dabbelt <palmer@...belt.com>,
        Albert Ou <aou@...s.berkeley.edu>,
        Boris Ostrovsky <boris.ostrovsky@...cle.com>,
        Juergen Gross <jgross@...e.com>
Cc:     Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Jiri Olsa <jolsa@...hat.com>,
        Namhyung Kim <namhyung@...nel.org>,
        James Morse <james.morse@....com>,
        Alexandru Elisei <alexandru.elisei@....com>,
        Suzuki K Poulose <suzuki.poulose@....com>,
        Vitaly Kuznetsov <vkuznets@...hat.com>,
        Wanpeng Li <wanpengli@...cent.com>,
        Jim Mattson <jmattson@...gle.com>,
        Joerg Roedel <joro@...tes.org>,
        Stefano Stabellini <sstabellini@...nel.org>,
        linux-arm-kernel@...ts.infradead.org,
        linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org,
        kvmarm@...ts.cs.columbia.edu, linux-csky@...r.kernel.org,
        linux-riscv@...ts.infradead.org, kvm@...r.kernel.org,
        xen-devel@...ts.xenproject.org,
        Artem Kashkanov <artem.kashkanov@...el.com>,
        Like Xu <like.xu.linux@...il.com>,
        Zhu Lingshan <lingshan.zhu@...el.com>
Subject: Re: [PATCH v3 09/16] perf/core: Use static_call to optimize
 perf_guest_info_callbacks

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@...radead.org>
> Cc: Like Xu <like.xu.linux@...il.com>
> Signed-off-by: Sean Christopherson <seanjc@...gle.com>
> ---
>   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@...hat.com>