[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20170317003321.GB28800@wotan.suse.de>
Date: Fri, 17 Mar 2017 01:33:21 +0100
From: "Luis R. Rodriguez" <mcgrof@...nel.org>
To: Bjorn Helgaas <helgaas@...nel.org>,
Liviu Dudau <Liviu.Dudau@....com>
Cc: Lorenzo Pieralisi <lorenzo.pieralisi@....com>,
"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
Andy Lutomirski <luto@...capital.net>,
linux-pci@...r.kernel.org, linux-arm-kernel@...ts.infradead.org,
Wenrui Li <wenrui.li@...k-chips.com>,
Gabriele Paoloni <gabriele.paoloni@...wei.com>,
Catalin Marinas <catalin.marinas@....com>,
Shawn Lin <shawn.lin@...k-chips.com>,
Will Deacon <will.deacon@....com>,
Michal Simek <michal.simek@...inx.com>,
Thierry Reding <thierry.reding@...il.com>,
Tanmay Inamdar <tinamdar@....com>, linux-arch@...r.kernel.org,
Pratyush Anand <pratyush.anand@...il.com>,
Russell King <linux@...linux.org.uk>,
Jon Mason <jonmason@...adcom.com>,
Murali Karicheri <m-karicheri2@...com>,
Arnd Bergmann <arnd@...db.de>,
Bharat Kumar Gogada <bharat.kumar.gogada@...inx.com>,
Ray Jui <rjui@...adcom.com>,
John Garry <john.garry@...wei.com>,
Joao Pinto <Joao.Pinto@...opsys.com>,
Bjorn Helgaas <bhelgaas@...gle.com>,
Mingkai Hu <mingkai.hu@...escale.com>,
Thomas Petazzoni <thomas.petazzoni@...e-electrons.com>,
Jingoo Han <jingoohan1@...il.com>,
linux-kernel@...r.kernel.org,
Stanimir Varbanov <svarbanov@...sol.com>,
Minghuan Lian <minghuan.Lian@...escale.com>,
Zhou Wang <wangzhou1@...ilicon.com>,
Roy Zang <tie-fei.zang@...escale.com>,
"Luis R. Rodriguez" <mcgrof@...nel.org>
Subject: Re: [PATCH 02/20] PCI: fix pci_remap_iospace() remap attribute
On Thu, Mar 16, 2017 at 04:48:44PM -0500, Bjorn Helgaas wrote:
> [+cc Luis]
>
> On Mon, Feb 27, 2017 at 03:14:13PM +0000, Lorenzo Pieralisi wrote:
> > According to the PCI local bus specifications (Revision 3.0, 3.2.5),
> > I/O Address space transactions are non-posted. On architectures where
> > I/O space is implemented through a chunk of memory mapped space mapped
> > to PCI address space (ie IA64/ARM/ARM64) the memory mapping for the
> > region backing I/O Address Space transactions determines the I/O
> > transactions attributes (before the transactions actually reaches the
> > PCI bus where it is handled according to the PCI specifications).
> >
> > Current pci_remap_iospace() interface, that is used to map the PCI I/O
> > Address Space into virtual address space, use pgprot_device() as memory
> > attribute for the virtual address mapping, that in some architectures
> > (ie ARM64) provides non-cacheable but write bufferable mappings (ie
> > posted writes),
<sarcasm>
Gee wiz, I am glad this is so well documented.
</sarcasm>
> > which clash with the non-posted write behaviour for I/O
> > Address Space mandated by the PCI specifications.
> >
> > Update the prot ioremap_page_range() parameter in pci_remap_iospace()
> > to pgprot_noncached to ensure that the virtual mapping backing
> > I/O Address Space guarantee non-posted write transactions issued
> > when addressing I/O Address Space through the MMIO mapping.
How did we end up with pgprot_device() then in the first place Liviu Dudau [0] ?
I ask for two reasons:
a) should we then use a Fixes tag for this patch ?
b) it does not seem clear what the semantics for pgprot_device() or even
pgprot_noncached(). Can you add some ?
8b921acfeffdb ("PCI: Add pci_remap_iospace() to map bus I/O resources")
Also this patch claims archs can override this call alone, as its __weak.
So is the right thing to do to change pci_remap_iospace() to pgprot_noncached()
or is it for archs to add their own pci_remap_iospace()? If so why ? Without
proper semantics defined for these helpers this is all fuzzy.
> > Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@....com>
> > Cc: Arnd Bergmann <arnd@...db.de>
> > Cc: Will Deacon <will.deacon@....com>
> > Cc: Bjorn Helgaas <bhelgaas@...gle.com>
> > Cc: Russell King <linux@...linux.org.uk>
> > Cc: Catalin Marinas <catalin.marinas@....com>
> > ---
> > drivers/pci/pci.c | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
> > index bd98674..bfb3c6e 100644
> > --- a/drivers/pci/pci.c
> > +++ b/drivers/pci/pci.c
> > @@ -3375,7 +3375,7 @@ int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr)
> > return -EINVAL;
> >
> > return ioremap_page_range(vaddr, vaddr + resource_size(res), phys_addr,
> > - pgprot_device(PAGE_KERNEL));
> > + pgprot_noncached(PAGE_KERNEL));
>
> pgprot_device() is equivalent to pgprot_noncached() on all arches
> except ARM64, and I trust you're doing the right thing on ARM64, so
> I'm fine with this from a PCI perspective.
>
> I do find this puzzling because I naively expected pgprot_noncached()
> to match up with ioremap_nocache(), and apparently it doesn't.
>
> For example, ARM64 ioremap_nocache() uses PROT_DEVICE_nGnRE, which
> doesn't match the MT_DEVICE_nGnRnE in pgprot_noncached().
>
> The point of these patches is to use non-posted mappings. Apparently
> you can do that with pgprot_noncached() here, but ioremap_nocache()
> isn't enough for the config space mappings?
This is for iospace it seems, so the other patch I think was for
config space.
Luis
> I suppose that's a consequence of the pgprot_noncached() vs
> ioremap_nocache() mismatch, but this is all extremely confusing.
>
> > #else
> > /* this architecture does not have memory mapped I/O space,
> > so this function should never be called */
> > --
> > 2.10.0
> >
> >
> > _______________________________________________
> > linux-arm-kernel mailing list
> > linux-arm-kernel@...ts.infradead.org
> > http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
>
--
Luis Rodriguez, SUSE LINUX GmbH
Maxfeldstrasse 5; D-90409 Nuernberg
Powered by blists - more mailing lists