From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mx0b-0016f401.pphosted.com ([67.231.156.173]:28890 "EHLO mx0b-0016f401.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752597AbbDWHvS (ORCPT ); Thu, 23 Apr 2015 03:51:18 -0400 Date: Thu, 23 Apr 2015 15:47:00 +0800 From: Jisheng Zhang To: Fabrice Gasnier CC: "jg1.han@samsung.com" , "bhelgaas@google.com" , "Minghuan.Lian@freescale.com" , "linux-pci@vger.kernel.org" , "linux-kernel@vger.kernel.org" , "linux-arm-kernel@lists.infradead.org" Subject: Re: [PATCH 2/2] PCI: designware: use iATU0 for cfg and IO, iATU1 for MEM Message-ID: <20150423154700.2f2043c3@xhacker> In-Reply-To: <5538A0AE.6050005@st.com> References: <1429707494-2732-1-git-send-email-jszhang@marvell.com> <1429707494-2732-3-git-send-email-jszhang@marvell.com> <5538A0AE.6050005@st.com> MIME-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Sender: linux-pci-owner@vger.kernel.org List-ID: Hi Fabrice, On Thu, 23 Apr 2015 00:35:10 -0700 Fabrice Gasnier 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: > > > > http://www.spinics.net/lists/linux-pci/msg40440.html > > > > Signed-off-by: Jisheng Zhang > > --- > > 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