... s information: Right now we disable MMCONFIG on machines where the ... graphics card. pci-disable-decode-of-io-memory-during-bar-sizing ... RAM access when you turn decode off, stupidly. I've yet ... avoid using MMCONFIG until the BAR sizing is done. However, this ...

linux-kernel - Robert Hancock - Oct 29 2007 - 19:52

... it to firmware people" > thing, of course. Dammit, Intel *could* have ... . What's broken is our PCI probing with certain address space ... and don't disable decode while sizing BARs (probably a latent ... linux-kernel" in the body of a message to majordomo@vger ...

linux-kernel - Jesse Barnes - Oct 30 2007 - 18:04

... devices have their > > IO regions registered on top of it, because ... probably the only reason the PCI layer doesn't > overwrite it ... Robert's patch and the disable decode stuff applied. Jesse - To ... linux-kernel" in the body of a message to majordomo@vger ...

linux-kernel - Jesse Barnes - Oct 30 2007 - 18:39

... Right now MMCONFIG > is effectively disabled very aggressively because it's ... quite a few of them. > > and what "you're supposed to ... just made it a real PCI BAR in the > Northbridge, and ... what they want on the subject.. but that doesn't necessarily ...

linux-kernel - Robert Hancock - Oct 30 2007 - 19:41

... other possible workaround would be to avoid using MMCONFIG until the BAR > sizing is done. The only sane solution is the one that ... : send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at ...

linux-kernel - Linus Torvalds - Oct 30 2007 - 11:15

... is... you're not supposed to mix both types of accesses ... Right now MMCONFIG is effectively disabled very aggressively because it's ... it to firmware people" thing, of course. Dammit, Intel *could* have ... just made it a real PCI BAR in the Northbridge, and ...

linux-kernel - Linus Torvalds - Oct 30 2007 - 13:07

... to avoid using MMCONFIG > > until the BAR sizing is done. > > The only sane ... problem is... you're not supposed to mix both types of accesses. > At that point, almost all ... twist then: use CONF1 *until* you're using something above 256, and then ...

linux-kernel - Arjan van de Ven - Oct 30 2007 - 12:47

... What's broken is our PCI probing with certain address space ... picture. There's been tons of problems with MMCONFIG. Like the ... devices have their IO regions registered on top of it, because ... not do that idiotic "hidden IO resources that are described by ...

linux-kernel - Linus Torvalds - Oct 30 2007 - 18:22

... What's broken is our PCI probing with certain address space ... picture. There's been tons of > problems with MMCONFIG. Like the ... devices have their > IO regions registered on top of it, because ... the numerous non-PC ports of Linux), and this particular problem ...

linux-kernel - Jesse Barnes - Oct 30 2007 - 18:31

... the numerous non-PC ports of Linux), and this > particular problem, ... config space MMIO area of the PCI controller does not overlap ... in an area overlapping with PCI MMIO space, which breaks both ... linux-kernel" in the body of a message to majordomo@vger ...

linux-kernel - David Miller - Oct 30 2007 - 18:44

... broken? We seem to slowly grow more uses of registers > 256, but yes it's still mostly ... if that was not done. It has a pci config space access in a time critical path ... line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org ...

linux-kernel - Andi Kleen - Oct 30 2007 - 14:50

... EFI people who were just confused. There's no way to disable conf1 accesses on any known chipset, afaik. Linus - To ... list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at ...

linux-kernel - Linus Torvalds - Oct 30 2007 - 15:06

... > people who were just confused. > There's no way to disable conf1 accesses on any known chipset, afaik. There was a tester ... list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at ...

linux-kernel - Andi Kleen - Oct 30 2007 - 15:37

... you read the table location out > of the ACPI tables you can start ... take a look at arch/x86/pci/mmconfig-shared.c and look for ... you aren't even aware of these kinds of fundamnetal issues. You ... linux-kernel" in the body of a message to majordomo@vger.kernel ...

linux-kernel - Linus Torvalds - Oct 30 2007 - 19:59

... take a look at arch/x86/pci/mmconfig-shared.c and look for ... you aren't even aware of these kinds of fundamnetal > issues. You probably ... them? We have a few bits of code in there to look at ... linux-kernel" in the body of a message to majordomo@vger.kernel ...

linux-kernel - Jesse Barnes - Oct 30 2007 - 21:30

... like this is still necessary. Jesse - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the ...

linux-kernel - Jesse Barnes - Oct 26 2007 - 12:59

... it? :) thanks, greg k-h - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at ...

linux-kernel - Greg KH - Oct 26 2007 - 22:41

... twist then: use CONF1 *until* you're using > > something above 256, and then ... area have > been exactly the kinds of things like "we don't ... , and > change it from "you're not supposed to mix" to " ... linux-kernel" in the body of a message to majordomo@vger. ...

linux-kernel - Arjan van de Ven - Oct 30 2007 - 13:28

... is not worth optimizing for at all. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ ...

linux-kernel - David Miller - Oct 30 2007 - 17:41