linux-kernel - Re: [PATCH] powerpc/qspinlock: Add spinlock contention tracepoint

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: <7bba99d8-b171-4ac1-a33c-4c086f3684fd@csgroup.eu>
Date: Wed, 30 Jul 2025 08:46:28 +0200
From: Christophe Leroy <christophe.leroy@...roup.eu>
To: "Nysal Jan K.A." <nysal@...ux.ibm.com>,
 Madhavan Srinivasan <maddy@...ux.ibm.com>
Cc: Michael Ellerman <mpe@...erman.id.au>, Nicholas Piggin
 <npiggin@...il.com>, linuxppc-dev@...ts.ozlabs.org,
 linux-kernel@...r.kernel.org
Subject: Re: [PATCH] powerpc/qspinlock: Add spinlock contention tracepoint



Le 25/07/2025 à 10:14, Nysal Jan K.A. a écrit :
> Add a lock contention tracepoint in the queued spinlock slowpath.
> Also add the __lockfunc annotation so that in_lock_functions()
> works as expected.
> 
> Signed-off-by: Nysal Jan K.A. <nysal@...ux.ibm.com>
> ---
>   arch/powerpc/lib/qspinlock.c | 13 ++++++++-----
>   1 file changed, 8 insertions(+), 5 deletions(-)
> 
> diff --git a/arch/powerpc/lib/qspinlock.c b/arch/powerpc/lib/qspinlock.c
> index bcc7e4dff8c3..622e7f45c2ce 100644
> --- a/arch/powerpc/lib/qspinlock.c
> +++ b/arch/powerpc/lib/qspinlock.c
> @@ -9,6 +9,7 @@
>   #include <linux/sched/clock.h>
>   #include <asm/qspinlock.h>
>   #include <asm/paravirt.h>
> +#include <trace/events/lock.h>
>   
>   #define MAX_NODES	4
>   
> @@ -708,8 +709,9 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
>   	qnodesp->count--;
>   }
>   
> -void queued_spin_lock_slowpath(struct qspinlock *lock)
> +void __lockfunc queued_spin_lock_slowpath(struct qspinlock *lock)
>   {
> +	trace_contention_begin(lock, LCB_F_SPIN);
>   	/*
>   	 * This looks funny, but it induces the compiler to inline both
>   	 * sides of the branch rather than share code as when the condition
> @@ -718,16 +720,17 @@ void queued_spin_lock_slowpath(struct qspinlock *lock)
>   	if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) && is_shared_processor()) {
>   		if (try_to_steal_lock(lock, true)) {
>   			spec_barrier();
> -			return;
> +		} else {
> +			queued_spin_lock_mcs_queue(lock, true);

If I read correctly, now all this is single line so you have to drop the 
braces , see 
https://docs.kernel.org/process/coding-style.html#placing-braces-and-spaces

>   		}
> -		queued_spin_lock_mcs_queue(lock, true);
>   	} else {
>   		if (try_to_steal_lock(lock, false)) {
>   			spec_barrier();
> -			return;
> +		} else {
> +			queued_spin_lock_mcs_queue(lock, false);
>   		}

Same here.

> -		queued_spin_lock_mcs_queue(lock, false);
>   	}
> +	trace_contention_end(lock, 0);
>   }
>   EXPORT_SYMBOL(queued_spin_lock_slowpath);
>