linux-kernel - Re: [PATCH 2/2] PCI: designware: use iATU0 for cfg and IO, iATU1 for MEM

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <20150423154700.2f2043c3@xhacker>
Date:	Thu, 23 Apr 2015 15:47:00 +0800
From:	Jisheng Zhang <jszhang@...vell.com>
To:	Fabrice Gasnier <fabrice.gasnier@...com>
CC:	"jg1.han@...sung.com" <jg1.han@...sung.com>,
	"bhelgaas@...gle.com" <bhelgaas@...gle.com>,
	"Minghuan.Lian@...escale.com" <Minghuan.Lian@...escale.com>,
	"linux-pci@...r.kernel.org" <linux-pci@...r.kernel.org>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	"linux-arm-kernel@...ts.infradead.org" 
	<linux-arm-kernel@...ts.infradead.org>
Subject: Re: [PATCH 2/2] PCI: designware: use iATU0 for cfg and IO, iATU1
 for MEM

Hi Fabrice,

On Thu, 23 Apr 2015 00:35:10 -0700
Fabrice Gasnier <fabrice.gasnier@...com> wrote:

> Hi Jisheng,
> 
> On 04/22/2015 02:58 PM, Jisheng Zhang wrote:
> > Most transactions' type are cfg0 and MEM, so the Current iATU usage is not
> > balanced, iATU0 is hot while iATU1 is rarely used. This patch refactors
> > the iATU usage: iATU0 for cfg and IO, iATU1 for MEM. This allocation
> > ideas comes from Minghuan Lian<Minghuan.Lian@...escale.com>:
> >
> >   http://www.spinics.net/lists/linux-pci/msg40440.html
> >
> > Signed-off-by: Jisheng Zhang<jszhang@...vell.com>
> > ---
> >   drivers/pci/host/pcie-designware.c | 83 +++++++++++++++++++++-----------------
> >   1 file changed, 47 insertions(+), 36 deletions(-)
> >
> > diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
> > index 1da1446..bb81c8ad 100644
> > --- a/drivers/pci/host/pcie-designware.c
> > +++ b/drivers/pci/host/pcie-designware.c
> > @@ -508,6 +508,13 @@ int dw_pcie_host_init(struct pcie_port *pp)
> >   	if (pp->ops->host_init)
> >   		pp->ops->host_init(pp);
> >   
> > +	dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX0,
> > +				  PCIE_ATU_TYPE_IO, pp->io_mod_base,
> > +				  pp->io_bus_addr, pp->io_size);
> > +	dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX1,
> > +				  PCIE_ATU_TYPE_MEM, pp->mem_mod_base,
> > +				  pp->mem_bus_addr, pp->mem_size);
> > +
> Some platforms doesn't have support for ATU. I think this is the reason 
> to have
> rd_other_conf / wr_other_conf ops in the driver.

oops. Thanks for the information. So what about something like:

if (!pp->ops->rd_other_conf) {
	dw_pcie_prog_outbound_atu(...);
	dw_pcie_prog_outbound_atu(...);
}

Thanks,
Jisheng

> IMO, this is not suitable to have this in the initialization routine for 
> all platforms.
> 
> Regards,
> Fabrice

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/