Re: [RFC 3/5] dma-mapping: Enable global non-coherent pool support for RISC-V

From: Christoph Hellwig <hch@lst.de>
To: Atish Patra <atishp@atishpatra.org>
Cc: devicetree <devicetree@vger.kernel.org>,
	Albert Ou <aou@eecs.berkeley.edu>,
	Guo Ren <guoren@linux.alibaba.com>,
	Frank Rowand <frowand.list@gmail.com>,
	"linux-kernel@vger.kernel.org List"
	<linux-kernel@vger.kernel.org>,
	linux-riscv <linux-riscv@lists.infradead.org>,
	Atish Patra <atish.patra@wdc.com>,
	iommu@lists.linux-foundation.org,
	Rob Herring <robh+dt@kernel.org>,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	Tobias Klauser <tklauser@distanz.ch>,
	Robin Murphy <robin.murphy@arm.com>,
	Christoph Hellwig <hch@lst.de>,
	Dmitry Vyukov <dvyukov@google.com>
Subject: Re: [RFC 3/5] dma-mapping: Enable global non-coherent pool support for RISC-V
Date: Tue, 27 Jul 2021 10:52:44 +0200	[thread overview]
Message-ID: <20210727085244.GA20609@lst.de> (raw)
In-Reply-To: <CAOnJCU+qRznBTn9Mt6t_DE6UUz6_LuaBBuOmnURS2Yh3pmpjvg@mail.gmail.com>

On Mon, Jul 26, 2021 at 03:47:54PM -0700, Atish Patra wrote:
> arch_dma_set_uncached works as well in this case. However, mips,
> niops2 & xtensa uses a
> fixed (via config) value for the offset. Similar approach can't be
> used here because the platform specific
> offset value has to be determined at runtime so that a single kernel
> image can boot on all platforms.

Nothing in the interface requires a fixed offset.  And using the offset
has one enormous advantage in that there is no need to declare a
statically sized pool - allocations are fully dynamic.  And any kind of
fixed pool tends to cause huge problems.

> 1. a new DT property so that arch specific code is aware of the
> non-cacheable window offset.

Yes.

> individual device if a per-device non-cacheable
>    window support is required in future. As of now, the beagleV memory

If you require a per-device noncachable area you can use the per-device
coherent pools.  But why would you want that?

> region lies in 0x10_0000_00000 - x17_FFFF_FFFF
>    which is mapped to start of DRAM 0x80000000. All of the
> non-coherent devices can do 32bit DMA only.

Adjust ZONE_DMA32 so that it takes the uncached offset into account.

> > > -     mem = dma_init_coherent_memory(phys_addr, phys_addr, size, true);
> > > +     if (phys_addr == device_addr)
> > > +             mem = dma_init_coherent_memory(phys_addr, device_addr, size, true);
> > > +     else
> > > +             mem = dma_init_coherent_memory(phys_addr, device_addr, size, false);
> >
> > Nak.  The phys_addr != device_addr support is goign away.  This needs
> 
> ok.
> 
> > to be filled in using dma-ranges property hanging of the struct device.
> 
> struct device is only accessible in rmem_dma_device_init. I couldn't
> find a proper way to access it during
> dma_reserved_default_memory setup under global pool.
> 
> Does that mean we should use a per-device memory pool instead of a
> global non-coherent pool ?

Indeed, that would be a problem in this case.  But if we can just
use the uncached offset directly I think everything will be much
simpler.
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu