MIME-Version: 1.0
References: <CABdmKX3HFuaE0qwcADk-KLtVUdao-uhH-1zn4gv7ezq+bZE94w@mail.gmail.com>
 <20230117082508.8953-1-jaewon31.kim@samsung.com> <20230117083103epcms1p63382eee1cce1077248a4b634681b0aca@epcms1p6>
 <CANDhNCpKY5Af059ok8ZcgJ=wt7NaorZxqQXaTS848CwY0LNFiw@mail.gmail.com>
 <20230125095646epcms1p2a97e403a9589ee1b74a3e7ac7d573f9b@epcms1p2>
 <20230125101957epcms1p2d06d65a9147e16f3281b13c085e5a74c@epcms1p2>
 <CANDhNCoAKtHmxFomdGfTfXy8ZvFMfMRj4jZ+b8wMMD+5AmAB0g@mail.gmail.com>
 <20230126044218epcms1p35474178c2f2b18524f35c7d9799e3aed@epcms1p3>
 <CANDhNCo1JRmfouBn985GZLmPY-xLn9JKNJfubY0PAUrCpY8K4g@mail.gmail.com>
 <20230204150215epcms1p8d466d002c1e4dc2005d38f847adea6fa@epcms1p8>
 <CGME20230117082521epcas1p22a709521a9e6d2346d06ac220786560d@epcms1p1>
 <CANDhNCrAMVT3rg0GPJhYKD75EAUn8bsivrp3yMJcsd6bouj1rQ@mail.gmail.com> <20230207073335epcms1p15df191db83bec0cb791e6f79dcecb31f@epcms1p1>
In-Reply-To: <20230207073335epcms1p15df191db83bec0cb791e6f79dcecb31f@epcms1p1>
From:   John Stultz <jstultz@google.com>
Date:   Tue, 7 Feb 2023 08:56:07 -0800
Message-ID: <CANDhNCpM+R0sPuGoeBW0=he+6YMKTn2YLm4AZZ2+C=5YRLZBLg@mail.gmail.com>
Subject: Re: (2) [PATCH] dma-buf: system_heap: avoid reclaim for order 4
To:     jaewon31.kim@samsung.com
Cc:     "T.J. Mercier" <tjmercier@google.com>,
        "sumit.semwal@linaro.org" <sumit.semwal@linaro.org>,
        "daniel.vetter@ffwll.ch" <daniel.vetter@ffwll.ch>,
        "akpm@linux-foundation.org" <akpm@linux-foundation.org>,
        "hannes@cmpxchg.org" <hannes@cmpxchg.org>,
        "mhocko@kernel.org" <mhocko@kernel.org>,
        "linux-mm@kvack.org" <linux-mm@kvack.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "jaewon31.kim@gmail.com" <jaewon31.kim@gmail.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Mon, Feb 6, 2023 at 11:33 PM Jaewon Kim <jaewon31.kim@samsung.com> wrote:
> >I don't mean to discourage you, especially after all the effort here.
> >
> >Do you think evaluating the before and after impact to buffer usage
> >
> >(not just allocation) would be doable in the near term?
> >
>
> Hello sorry but I don't have expertise on iommu. Actually I'm also wondering
> all IOMMU can use order 4 free pages, if they are allocated. I am not sure
> but I remember I heard order 9 (2MB) could be used, but I don't know about order 8 4.
>
> I guess IOMMU mmap also be same patern like we expect. I mean if order 4 is
> prepared it could be faster like 1 to 4 times. But it, I think, should NOT be
> that much slow even though the entire free memory is prepared as order 0 pages.
>
> >
> >
> >If you don't think so, given the benefit to allocation under pressure
> >
> >is large (and I don't mean to give you hurdles to jump), I'm willing
> >
> >to ack your change to get it merged, but if we later see performance
> >
> >trouble, I'll be quick to advocate for reverting it.  Is that ok?
> >
>
> Yes sure. I also want to know if it is.

Ok. Please resend your latest patch and I'll go ahead and ack it and
we'll watch.

Thanks again for your efforts here!
-john