Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20230403122738.6006-1-zhangpeng.00@bytedance.com> <CAG_fn=UEah3DLYm2yKxBKg=L=Qc_PSnrKhZ2==snbw05XAtVZQ@mail.gmail.com>
In-Reply-To: <CAG_fn=UEah3DLYm2yKxBKg=L=Qc_PSnrKhZ2==snbw05XAtVZQ@mail.gmail.com>
From:   Alexander Potapenko <glider@google.com>
Date:   Tue, 4 Apr 2023 12:40:23 +0200
Message-ID: <CAG_fn=VJwtnn8zu8oOZuG2rNUM46Rvz-36oEfVJiCsyeee8unA@mail.gmail.com>
Subject: Re: [PATCH v2] mm: kfence: Improve the performance of
 __kfence_alloc() and __kfence_free()
To:     Peng Zhang <zhangpeng.00@bytedance.com>
Cc:     elver@google.com, dvyukov@google.com, akpm@linux-foundation.org,
        kasan-dev@googlegroups.com, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

> >
> >         /* Apply to left of object. */
> > -       for (addr = pageaddr; addr < meta->addr; addr++) {
> > -               if (!fn((u8 *)addr))
> > +       for (; meta->addr - addr >= sizeof(u64); addr += sizeof(u64)) {
> > +               if (unlikely(*((u64 *)addr) != KFENCE_CANARY_PATTERN_U64))
> >                         break;
> >         }
> I am confused. Right now this loop either runs from pageaddr to
> meta_addr if there's no corruption, or breaks at the first corrupted
> byte.
> Regardless of that, we are applying check_canary_byte() to every byte
> of that range in the following loop.
> Shouldn't the two be nested, like in the case of the canary bytes to
> the right of the object?
>
Please disregard my comment. This loop is fine, it just speeds up
finding the first corrupted byte.