From: Yu Zhao <yu.zhao@uniscape.net>
To: Greg KH <greg@kroah.com>
Cc: "Zhao, Yu" <yu.zhao@intel.com>,
"linux-pci@vger.kernel.org" <linux-pci@vger.kernel.org>,
"achiang@hp.com" <achiang@hp.com>,
"grundler@parisc-linux.org" <grundler@parisc-linux.org>,
"mingo@elte.hu" <mingo@elte.hu>,
"jbarnes@virtuousgeek.org" <jbarnes@virtuousgeek.org>,
"matthew@wil.cx" <matthew@wil.cx>,
"randy.dunlap@oracle.com" <randy.dunlap@oracle.com>,
"rdreier@cisco.com" <rdreier@cisco.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
"virtualization@lists.linux-foundation.org"
<virtualization@lists.linux-foundation.org>
Subject: Re: [PATCH 16/16 v6] PCI: document the new PCI boot parameters
Date: Sat, 08 Nov 2008 13:00:29 +0800 [thread overview]
Message-ID: <49151CED.8060507@uniscape.net> (raw)
In-Reply-To: <20081107185325.GE2320@kroah.com>
Greg KH wrote:
> On Fri, Nov 07, 2008 at 04:35:47PM +0800, Zhao, Yu wrote:
>> Greg KH wrote:
>>> On Fri, Nov 07, 2008 at 04:17:02PM +0800, Zhao, Yu wrote:
>>>>> Well, to do it "correctly" you are going to have to tell the driver to
>>>>> shut itself down, and reinitialize itself.
>>>>> Turns out, that doesn't really work for disk and network devices without
>>>>> dropping the connection (well, network devices should be fine probably).
>>>>> So you just can't do this, sorry. That's why the BIOS handles all of
>>>>> these issues in a PCI hotplug system.
>>>>> How does the hardware people think we are going to handle this in the
>>>>> OS? It's not something that any operating system can do, is it part of
>>>>> the IOV PCI spec somewhere?
>>>> No, it's not part of the PCI IOV spec.
>>>>
>>>> I just want the IOV (and whole PCI subsystem) have more flexibility on
>>>> various BIOSes. So can we reconsider about resource rebalance as boot
>>>> option, or should we forget about this idea?
>>> As you have proposed it, the boot option will not work at all, so I
>>> think we need to forget about it. Especially if it is not really
>>> needed.
>> I guess at least one thing would work if people don't want to boot twice:
>> give the bus number 0 as rebalance starting point, then all system
>> resources would be reshuffled :-)
>
> Hm, but don't we do that today with our basic resource reservation logic
> at boot time? What would be different about this kind of proposal?
The generic PCI core can do this but this feature is kind of disabled by
low level PCI code in x86. The low level code tries to reserve resource
according to configuration from BIOS. If the BIOS is wrong, the
allocation would fail and the generic PCI core couldn't repair it
because the bridge resources may have been allocated by the PCI low
level and the PCI core can't expand them to find enough resource for the
subordinates.
The proposal is to disable x86 PCI low level to allocation resources
according to BIOS so PCI core can fully control the resource allocation.
The PCI core takes all resources from BARs it knows into account and
configure the resource windows on the bridges according to its own
calculation.
Regards,
Yu
next prev parent reply other threads:[~2008-11-08 5:01 UTC|newest]
Thread overview: 118+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-10-22 8:38 [PATCH 0/16 v6] PCI: Linux kernel SR-IOV support Yu Zhao
2008-10-22 8:40 ` [PATCH 1/16 v6] PCI: remove unnecessary arg of pci_update_resource() Yu Zhao
2008-10-22 8:40 ` [PATCH 2/16 v6] PCI: define PCI resource names in an 'enum' Yu Zhao
2008-10-22 14:24 ` Bjorn Helgaas
2008-10-22 14:44 ` Yu Zhao
2008-10-22 14:51 ` Bjorn Helgaas
2008-10-22 14:53 ` Yu Zhao
2008-11-14 0:43 ` Simon Horman
2008-10-22 8:41 ` [PATCH 3/16 v6] PCI: export __pci_read_base Yu Zhao
2008-10-22 8:41 ` [PATCH 4/16 v6] PCI: make pci_alloc_child_bus() be able to handle NULL bridge Yu Zhao
2008-10-22 8:41 ` [PATCH 5/16 v6] PCI: add a wrapper for resource_alignment() Yu Zhao
2008-10-22 8:42 ` [PATCH 6/16 v6] PCI: add a new function to map BAR offset Yu Zhao
2008-10-22 8:42 ` [PATCH 7/16 v6] PCI: cleanup pcibios_allocate_resources() Yu Zhao
2008-10-23 7:10 ` Yinghai Lu
2008-10-23 6:50 ` Yu Zhao
2008-10-22 8:43 ` [PATCH 8/16 v6] PCI: add boot options to reassign resources Yu Zhao
2008-10-22 14:35 ` Bjorn Helgaas
2008-10-22 14:49 ` Yu Zhao
2008-10-22 8:43 ` [PATCH 9/16 v6] PCI: add boot option to align MMIO resources Yu Zhao
2008-10-22 14:34 ` Bjorn Helgaas
2008-10-22 14:52 ` Yu Zhao
2008-10-22 8:43 ` [PATCH 10/16 v6] PCI: cleanup pci_bus_add_devices() Yu Zhao
2008-10-22 8:44 ` [PATCH 11/16 v6] PCI: split a new function from pci_bus_add_devices() Yu Zhao
2008-10-22 8:44 ` [PATCH 12/16 v6] PCI: support the SR-IOV capability Yu Zhao
2008-10-22 8:44 ` [PATCH 13/16 v6] PCI: reserve bus range for SR-IOV device Yu Zhao
2008-10-22 8:45 ` [PATCH 14/16 v6] PCI: document for SR-IOV user and developer Yu Zhao
2008-10-22 8:45 ` [PATCH 15/16 v6] PCI: document the SR-IOV sysfs entries Yu Zhao
2008-11-06 4:33 ` Greg KH
2008-11-06 4:46 ` Greg KH
2008-11-07 3:01 ` Zhao, Yu
2008-11-07 3:18 ` Greg KH
2008-11-13 6:50 ` Yu Zhao
2008-11-14 0:55 ` Greg KH
2008-11-17 8:09 ` Yu Zhao
2008-11-18 15:05 ` Greg KH
2008-11-18 16:49 ` Kay Sievers
2008-10-22 8:45 ` [PATCH 16/16 v6] PCI: document the new PCI boot parameters Yu Zhao
2008-10-22 14:27 ` Bjorn Helgaas
2008-10-22 17:01 ` Randy Dunlap
2008-11-06 4:32 ` Greg KH
2008-11-07 2:37 ` Zhao, Yu
2008-11-07 2:50 ` Greg KH
2008-11-07 3:40 ` Zhao, Yu
2008-11-07 4:17 ` Matthew Wilcox
2008-12-11 1:43 ` Yu Zhao
2008-12-11 4:33 ` Grant Grundler
2008-12-11 15:39 ` H L
2008-11-07 6:16 ` Greg KH
2008-11-07 7:50 ` Zhao, Yu
2008-11-07 8:02 ` Greg KH
2008-11-07 8:17 ` Zhao, Yu
2008-11-07 8:24 ` Greg KH
2008-11-07 8:35 ` Zhao, Yu
2008-11-07 18:53 ` Greg KH
2008-11-08 5:00 ` Yu Zhao [this message]
2008-11-08 5:25 ` Greg KH
2008-11-08 6:05 ` Yu Zhao
2008-11-08 5:50 ` freevanx
2008-11-08 5:54 ` Greg KH
2008-11-09 14:19 ` Pavel Machek
2008-11-09 14:34 ` Alexander Graf
2008-11-06 4:48 ` [PATCH 0/16 v6] PCI: Linux kernel SR-IOV support Greg KH
2008-11-06 15:40 ` H L
2008-11-06 15:43 ` Greg KH
2008-11-06 16:41 ` H L
2008-11-06 16:49 ` Greg KH
2008-11-06 17:38 ` Fischer, Anna
2008-11-06 18:03 ` Greg KH
2008-11-06 20:04 ` Fischer, Anna
2008-11-09 12:44 ` Avi Kivity
2008-11-09 19:25 ` Greg KH
2008-11-09 19:37 ` Avi Kivity
2008-11-11 6:08 ` Greg KH
2008-11-11 9:00 ` Avi Kivity
2008-11-06 18:36 ` Matthew Wilcox
2008-11-06 22:38 ` Anthony Liguori
2008-11-06 22:58 ` Matthew Wilcox
2008-11-07 6:19 ` Greg KH
2008-11-07 15:17 ` Yu Zhao
2008-11-07 18:48 ` Greg KH
2008-11-08 11:09 ` Fischer, Anna
2008-11-08 15:37 ` Leonid Grossman
2008-11-13 7:49 ` Yu Zhao
2008-11-09 12:47 ` Avi Kivity
2008-11-07 1:52 ` Dong, Eddie
2008-11-07 2:08 ` Nakajima, Jun
2008-11-07 15:21 ` Andi Kleen
2008-11-09 12:53 ` Avi Kivity
2008-11-07 16:01 ` Yu Zhao
[not found] ` <87d4h7pnnm.fsf__4937.77150190926$1226071173$gmane$org@basil.nowhere.org>
2008-11-12 22:41 ` Anthony Liguori
2008-11-16 16:04 ` Avi Kivity
2008-11-17 1:46 ` Zhao, Yu
2008-11-06 17:47 ` Matthew Wilcox
2008-11-06 17:53 ` Greg KH
2008-11-06 22:24 ` Simon Horman
2008-11-06 22:40 ` Anthony Liguori
2008-11-07 6:17 ` Greg KH
2008-11-07 7:47 ` Zhao, Yu
2008-11-11 0:18 ` Rusty Russell
2008-11-17 12:01 ` Yu Zhao
2008-11-09 12:58 ` Avi Kivity
2008-11-09 6:41 ` Muli Ben-Yehuda
2008-11-09 13:03 ` Avi Kivity
2008-11-06 23:54 ` Chris Wright
2008-11-07 6:10 ` Greg KH
2008-11-07 7:06 ` Zhao, Yu
2008-11-07 7:29 ` Leonid Grossman
2008-11-06 18:05 ` H L
2008-11-06 18:24 ` Greg KH
2008-11-07 6:03 ` Zhao, Yu
2008-11-06 16:51 ` git repository for SR-IOV development? H L
2008-11-06 16:59 ` Greg KH
2008-11-06 19:58 ` H L
2008-11-06 22:56 ` Simon Horman
2008-11-07 1:58 ` Greg KH
2008-11-07 13:09 ` Yu Zhao
2008-11-07 5:18 ` [PATCH 0/16 v6] PCI: Linux kernel SR-IOV support Zhao, Yu
2008-11-07 6:07 ` Greg KH
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=49151CED.8060507@uniscape.net \
--to=yu.zhao@uniscape.net \
--cc=achiang@hp.com \
--cc=greg@kroah.com \
--cc=grundler@parisc-linux.org \
--cc=jbarnes@virtuousgeek.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=matthew@wil.cx \
--cc=mingo@elte.hu \
--cc=randy.dunlap@oracle.com \
--cc=rdreier@cisco.com \
--cc=virtualization@lists.linux-foundation.org \
--cc=yu.zhao@intel.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).