From: Bjorn Helgaas <bhelgaas@google.com>
To: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: "linux-pci@vger.kernel.org" <linux-pci@vger.kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
linux-arm <linux-arm-kernel@lists.infradead.org>,
Arnd Bergmann <arnd@arndb.de>, Will Deacon <will.deacon@arm.com>,
Russell King <linux@armlinux.org.uk>,
Catalin Marinas <catalin.marinas@arm.com>,
Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Pratyush Anand <pratyush.anand@gmail.com>,
Jingoo Han <jingoohan1@gmail.com>,
Mingkai Hu <mingkai.hu@freescale.com>,
John Garry <john.garry@huawei.com>,
Tanmay Inamdar <tinamdar@apm.com>,
Murali Karicheri <m-karicheri2@ti.com>,
Bharat Kumar Gogada <bharat.kumar.gogada@xilinx.com>,
Ray Jui <rjui@broadcom.com>, Wenrui Li <wenrui.li@rock-chips.com>,
Shawn Lin <shawn.lin@rock-chips.com>,
Minghuan Lian <minghuan.Lian@freescale.com>,
Jon Mason <jonmason@broadcom.com>,
Gabriele Paoloni <gabriele.paoloni@huawei.com>,
Thomas Petazzoni <thomas.petazzoni@free-electrons.com>,
Joao Pinto <Joao.Pinto@synopsys.com>,
Thierry Reding <thierry.reding@gmail.com>,
Michal Simek <michal.simek@xilinx.com>,
Stanimir Varbanov <svarbanov@mm-sol.com>,
Zhou Wang <wangzhou1@hisilicon.com>,
Roy Zang <tie-fei.zang@freescale.com>,
"Luis R. Rodriguez" <mcgrof@kernel.org>,
Michael Ellerman <mpe@ellerman.id.au>
Subject: Re: [PATCH v4 02/21] linux/io.h: add PCI config space remap interface
Date: Thu, 20 Apr 2017 08:12:37 -0500 [thread overview]
Message-ID: <CAErSpo4wEACDex+9LC_gmdNWO+HAi7mJM7d-3s_GjRgEhezKQw@mail.gmail.com> (raw)
In-Reply-To: <20170420105153.GA9741@red-moon>
On Thu, Apr 20, 2017 at 5:51 AM, Lorenzo Pieralisi
<lorenzo.pieralisi@arm.com> wrote:
> [+ Michael]
>
> On Wed, Apr 19, 2017 at 05:48:51PM +0100, Lorenzo Pieralisi wrote:
>> The PCI specifications (Rev 3.0, 3.2.5 "Transaction Ordering and
>> Posting") mandate non-posted configuration transactions. As further
>> highlighted in the PCIe specifications (4.0 - Rev0.3, "Ordering
>> Considerations for the Enhanced Configuration Access Mechanism"),
>> through ECAM and ECAM-derivative configuration mechanism, the memory
>> mapped transactions from the host CPU into Configuration Requests on the
>> PCI express fabric may create ordering problems for software because
>> writes to memory address are typically posted transactions (unless the
>> architecture can enforce through virtual address mapping non-posted
>> write transactions behaviour) but writes to Configuration Space are not
>> posted on the PCI express fabric.
>>
>> Current DT and ACPI host bridge controllers map PCI configuration space
>> (ECAM and ECAM-derivative) into the virtual address space through
>> ioremap() calls, that are non-cacheable device accesses on most
>> architectures, but may provide "bufferable" or "posted" write semantics
>> in architecture like eg ARM/ARM64 that allow ioremap'ed regions writes
>> to be buffered in the bus connecting the host CPU to the PCI fabric;
>> this behaviour, as underlined in the PCIe specifications, may trigger
>> transactions ordering rules and must be prevented.
>>
>> Introduce a new generic and explicit API to create a memory
>> mapping for ECAM and ECAM-derivative config space area that
>> defaults to ioremap_nocache() (which should provide a sane default
>> behaviour) but still allowing architectures on which ioremap_nocache()
>> results in posted write transactions to override the function
>> call with an arch specific implementation that complies with
>> the PCI specifications for configuration transactions.
>>
>> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
>> Cc: Arnd Bergmann <arnd@arndb.de>
>> Cc: Will Deacon <will.deacon@arm.com>
>> Cc: Bjorn Helgaas <bhelgaas@google.com>
>> Cc: Russell King <linux@armlinux.org.uk>
>> Cc: Catalin Marinas <catalin.marinas@arm.com>
>> ---
>> include/linux/io.h | 19 +++++++++++++++++++
>> 1 file changed, 19 insertions(+)
>>
>> diff --git a/include/linux/io.h b/include/linux/io.h
>> index 82ef36e..3934aba 100644
>> --- a/include/linux/io.h
>> +++ b/include/linux/io.h
>> @@ -91,6 +91,25 @@ void devm_memunmap(struct device *dev, void *addr);
>> void *__devm_memremap_pages(struct device *dev, struct resource *res);
>>
>> /*
>> + * The PCI specifications (Rev 3.0, 3.2.5 "Transaction Ordering and
>> + * Posting") mandate non-posted configuration transactions. There is
>> + * no ioremap API in the kernel that can guarantee non-posted write
>> + * semantics across arches so provide a default implementation for
>> + * mapping PCI config space that defaults to ioremap_nocache(); arches
>> + * should override it if they have memory mapping implementations that
>> + * guarantee non-posted writes semantics to make the memory mapping
>> + * compliant with the PCI specification.
>> + */
>> +#ifndef pci_remap_cfgspace
>> +#define pci_remap_cfgspace pci_remap_cfgspace
>> +static inline void __iomem *pci_remap_cfgspace(phys_addr_t offset,
>> + size_t size)
>> +{
>> + return ioremap_nocache(offset, size);
>> +}
>> +#endif
>> +
>> +/*
>
> As an heads-up, this patch strictly depends on:
>
> https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/arch/powerpc/include/asm/io.h?id=590c369e7ecc00be736be39ae0c62d1b5d563a51
>
> to go upstream first, otherwise we would break powerpc compilation
> (owing to powerpc including linux/io.h before ioremap_nocache() is
> defined in arch/powerpc/include/asm/io.h).
>
> If we want to decouple them I must drop the static inline and make
> it a #define, it is not ideal but we must be aware of this, I really
> want to prevent breakage if we go ahead with this set (and -next can
> hide the issue).
It looks like Stephen merges powerpc/next into linux-next before
pci/next, so this will probably be OK there. I'll try to remember to
wait for the powerpc stuff to make it to Linus' tree during the merge
window before I send my pull request.
Bjorn
next prev parent reply other threads:[~2017-04-20 13:13 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-19 16:48 [PATCH v4 00/21] PCI: fix config space memory mappings Lorenzo Pieralisi
2017-04-19 16:48 ` [PATCH v4 01/21] PCI: remove __weak tag from pci_remap_iospace() Lorenzo Pieralisi
2017-04-19 16:48 ` [PATCH v4 02/21] linux/io.h: add PCI config space remap interface Lorenzo Pieralisi
2017-04-20 10:51 ` Lorenzo Pieralisi
2017-04-20 13:12 ` Bjorn Helgaas [this message]
2017-04-19 16:48 ` [PATCH v4 03/21] ARM64: implement pci_remap_cfgspace() interface Lorenzo Pieralisi
2017-04-20 10:33 ` Catalin Marinas
2017-04-19 16:48 ` [PATCH v4 04/21] ARM: " Lorenzo Pieralisi
2017-04-19 16:48 ` [PATCH v4 05/21] lib: fix Devres devm_ioremap_* offset parameter kerneldoc description Lorenzo Pieralisi
2017-04-28 21:20 ` Tejun Heo
2017-04-19 16:48 ` [PATCH v4 06/21] PCI: implement Devres interface to map PCI config space Lorenzo Pieralisi
2017-04-19 16:48 ` [PATCH v4 07/21] PCI: ECAM: use pci_remap_cfgspace() to map config region Lorenzo Pieralisi
2017-04-19 16:48 ` [PATCH v4 08/21] PCI: xilinx: update PCI config space remap function Lorenzo Pieralisi
2017-04-19 16:48 ` [PATCH v4 09/21] PCI: xilinx-nwl: " Lorenzo Pieralisi
2017-04-19 16:48 ` [PATCH v4 10/21] PCI: spear13xx: " Lorenzo Pieralisi
2017-04-19 16:49 ` [PATCH v4 11/21] PCI: rockchip: " Lorenzo Pieralisi
2017-04-19 16:49 ` [PATCH v4 12/21] PCI: qcom: " Lorenzo Pieralisi
2017-04-19 16:49 ` [PATCH v4 13/21] PCI: iproc-platform: " Lorenzo Pieralisi
2017-04-19 16:49 ` [PATCH v4 14/21] PCI: designware: " Lorenzo Pieralisi
2017-04-21 22:02 ` Jingoo Han
2017-04-19 16:49 ` [PATCH v4 15/21] PCI: armada8k: " Lorenzo Pieralisi
2017-04-19 16:49 ` [PATCH v4 16/21] PCI: xgene: " Lorenzo Pieralisi
2017-04-19 16:49 ` [PATCH v4 17/21] PCI: tegra: " Lorenzo Pieralisi
2017-04-19 16:49 ` [PATCH v4 18/21] PCI: hisi: " Lorenzo Pieralisi
2017-04-19 16:49 ` [PATCH v4 19/21] PCI: layerscape: " Lorenzo Pieralisi
2017-04-19 16:49 ` [PATCH v4 20/21] PCI: keystone-dw: " Lorenzo Pieralisi
2017-04-19 16:49 ` [PATCH v4 21/21] PCI: versatile: " Lorenzo Pieralisi
2017-04-20 13:25 ` [PATCH v4 00/21] PCI: fix config space memory mappings Bjorn Helgaas
2017-04-25 6:40 ` Jon Masters
2017-04-25 16:20 ` Jingoo Han
2017-04-25 18:31 ` Khuong Dinh
2017-04-26 10:53 ` Dongdong Liu
2017-04-26 17:24 ` Jingoo Han
2017-04-27 1:46 ` Dongdong Liu
2017-04-27 16:42 ` Khuong Dinh
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAErSpo4wEACDex+9LC_gmdNWO+HAi7mJM7d-3s_GjRgEhezKQw@mail.gmail.com \
--to=bhelgaas@google.com \
--cc=Joao.Pinto@synopsys.com \
--cc=arnd@arndb.de \
--cc=benh@kernel.crashing.org \
--cc=bharat.kumar.gogada@xilinx.com \
--cc=catalin.marinas@arm.com \
--cc=gabriele.paoloni@huawei.com \
--cc=jingoohan1@gmail.com \
--cc=john.garry@huawei.com \
--cc=jonmason@broadcom.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=linux@armlinux.org.uk \
--cc=lorenzo.pieralisi@arm.com \
--cc=m-karicheri2@ti.com \
--cc=mcgrof@kernel.org \
--cc=michal.simek@xilinx.com \
--cc=minghuan.Lian@freescale.com \
--cc=mingkai.hu@freescale.com \
--cc=mpe@ellerman.id.au \
--cc=pratyush.anand@gmail.com \
--cc=rjui@broadcom.com \
--cc=shawn.lin@rock-chips.com \
--cc=svarbanov@mm-sol.com \
--cc=thierry.reding@gmail.com \
--cc=thomas.petazzoni@free-electrons.com \
--cc=tie-fei.zang@freescale.com \
--cc=tinamdar@apm.com \
--cc=wangzhou1@hisilicon.com \
--cc=wenrui.li@rock-chips.com \
--cc=will.deacon@arm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).