[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <C45A2710-BAC4-42FF-93A6-C0165A3EC446@linux.alibaba.com>
Date: Tue, 15 Oct 2024 11:40:34 +0800
From: maqiao.mq <mqaio@...ux.alibaba.com>
To: Oleg Nesterov <oleg@...hat.com>
Cc: linux-trace-kernel@...r.kernel.org,
rostedt@...dmis.org,
"Masami Hiramatsu (Google)" <mhiramat@...nel.org>,
mathieu.desnoyers@...icios.com,
namhyung.kim@....com,
linux-kernel@...r.kernel.org,
bpf@...r.kernel.org
Subject: Re: [PATCH] uprobe: avoid out-of-bounds memory access of fetching
args
> 2024年10月14日 下午10:58,Oleg Nesterov <oleg@...hat.com> 写道:
>
> Sorry, currently I don't have time to even try to read this patch, just
> one note below...
>
> On 10/14, Ma Qiao wrote:
>>
>> @@ -979,6 +980,11 @@ static struct uprobe_cpu_buffer *prepare_uprobe_buffer(struct trace_uprobe *tu,
>> ucb = uprobe_buffer_get();
>> ucb->dsize = tu->tp.size + dsize;
>>
>> + if (WARN_ON_ONCE(ucb->dsize > MAX_UCB_BUFFER_SIZE)) {
>> + ucb->dsize = MAX_UCB_BUFFER_SIZE;
>> + dsize = MAX_UCB_BUFFER_SIZE - tu->tp.size;
>> + }
>> +
>
> Then you can probably kill the
>
> if (WARN_ON_ONCE(ucb->dsize > PAGE_SIZE))
>
> check in __uprobe_trace_func(), no?
>
> Oleg.
Thanks for reminder, I will remove it in v2
Powered by blists - more mailing lists