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] [day] [month] [year] [list]
Message-ID: <45cac39e-3b9e-f5f6-a534-421574953856@quicinc.com>
Date:   Mon, 6 Mar 2023 17:58:31 +0530
From:   Mukesh Ojha <quic_mojha@...cinc.com>
To:     Uros Bizjak <ubizjak@...il.com>,
        <linux-trace-kernel@...r.kernel.org>,
        <linux-kernel@...r.kernel.org>
CC:     Steven Rostedt <rostedt@...dmis.org>,
        Masami Hiramatsu <mhiramat@...nel.org>
Subject: Re: [PATCH v4 3/3] ring_buffer: Use try_cmpxchg instead of cmpxchg



On 3/5/2023 9:25 PM, Uros Bizjak wrote:
> Use try_cmpxchg instead of cmpxchg (*ptr, old, new) == old.
> x86 CMPXCHG instruction returns success in ZF flag, so this change
> saves a compare after cmpxchg (and related move instruction in
> front of cmpxchg).
> 
> Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg
> fails. There is no need to re-read the value in the loop.
> 
> No functional change intended.
> 
> Cc: Steven Rostedt <rostedt@...dmis.org>
> Cc: Masami Hiramatsu <mhiramat@...nel.org>
> Signed-off-by: Uros Bizjak <ubizjak@...il.com>
> ---
> v2: Convert only loops with cmpxchg.
> ---
>   kernel/trace/ring_buffer.c | 8 ++++----
>   1 file changed, 4 insertions(+), 4 deletions(-)
> 
> diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
> index 5235037f83d3..d17345b522f4 100644
> --- a/kernel/trace/ring_buffer.c
> +++ b/kernel/trace/ring_buffer.c
> @@ -4061,10 +4061,10 @@ void ring_buffer_record_off(struct trace_buffer *buffer)
>   	unsigned int rd;
>   	unsigned int new_rd;
>   
> +	rd = atomic_read(&buffer->record_disabled);
>   	do {
> -		rd = atomic_read(&buffer->record_disabled);
>   		new_rd = rd | RB_BUFFER_OFF;
> -	} while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd);
> +	} while (!atomic_try_cmpxchg(&buffer->record_disabled, &rd, new_rd));
>   }
>   EXPORT_SYMBOL_GPL(ring_buffer_record_off);
>   
> @@ -4084,10 +4084,10 @@ void ring_buffer_record_on(struct trace_buffer *buffer)
>   	unsigned int rd;
>   	unsigned int new_rd;
>   
> +	rd = atomic_read(&buffer->record_disabled);
>   	do {
> -		rd = atomic_read(&buffer->record_disabled);
>   		new_rd = rd & ~RB_BUFFER_OFF;
> -	} while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd);
> +	} while (!atomic_try_cmpxchg(&buffer->record_disabled, &rd, new_rd));
>   }

Acked-by: Mukesh Ojha <quic_mojha@...cinc.com>

-Mukesh
>   EXPORT_SYMBOL_GPL(ring_buffer_record_on);
>   

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ