[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <C82FEB90-B8F3-4869-B905-8940DEBD6889@fb.com>
Date: Thu, 16 Dec 2021 19:40:40 +0000
From: Song Liu <songliubraving@...com>
To: Peter Zijlstra <peterz@...radead.org>
CC: Song Liu <song@...nel.org>, bpf <bpf@...r.kernel.org>,
Networking <netdev@...r.kernel.org>,
LKML <linux-kernel@...r.kernel.org>,
"Alexei Starovoitov" <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
"Andrii Nakryiko" <andrii@...nel.org>,
Kernel Team <Kernel-team@...com>,
"x86@...nel.org" <x86@...nel.org>
Subject: Re: [PATCH v2 bpf-next 5/7] x86/alternative: introduce text_poke_jit
> On Dec 15, 2021, at 1:17 AM, Peter Zijlstra <peterz@...radead.org> wrote:
>
> On Tue, Dec 14, 2021 at 10:01:00PM -0800, Song Liu wrote:
>> This will be used by BPF jit compiler to dump JITed binary to a RWX huge
>
> OK, I read the actually allocator you use and the relevant code for this
> patch and the above is a typo, you meant: RX. Those pages are most
> definitely not writable.
Yeah, it was a typo. I meant to say ROX.
Thanks,
Song
>
>
>> +void *text_poke_jit(void *addr, const void *opcode, size_t len)
>> +{
>> + unsigned long start = (unsigned long)addr;
>> + size_t patched = 0;
>> +
>> + if (WARN_ON_ONCE(core_kernel_text(start)))
>> + return NULL;
>> +
>> + while (patched < len) {
>> + unsigned long ptr = start + patched;
>> + size_t s;
>> +
>> + s = min_t(size_t, PAGE_SIZE * 2 - offset_in_page(ptr), len - patched);
>
> Cute, should work.
>
>> +
>> + __text_poke((void *)ptr, opcode + patched, s);
>> + patched += s;
>> + }
>> + return addr;
>> +}
Powered by blists - more mailing lists