[PATCH] [Intrepid SRU, Jaunty] x86: only scan the root bus in early PCI quirks

[Tim Gardner]

Stefan Bader wrote:
> Tim Gardner wrote:
>> Yingying Zhao wrote:
>>> SRU Justification:
>>> We found a problem that on Tylersburg-HEDT with Nvidia Graphics card, system may result in kernel panic. Andi Kleen provided the patch to fix this problem. Please consider to include this patch in Jaunty and Intrepid.
>>>
>>> Patch (also attached):
>>> --
>>> commit 8659c406ade32f47da2c95889094801921d6330a
>>> Author: Andi Kleen <andi at firstfloor.org>
>>> Date:   Fri Jan 9 12:17:39 2009 -0800
>>>
>>>     x86: only scan the root bus in early PCI quirks
>>>     
>>>     We found a situation on Linus' machine that the Nvidia timer quirk hit on
>>>     a Intel chipset system.  The problem is that the system has a fancy Nvidia
>>>     card with an own PCI bridge, and the early-quirks code looking for any
>>>     NVidia bridge triggered on it incorrectly.  This didn't lead a boot
>>>     failure by luck, but the timer routing code selecting the wrong timer
>>>     first and some ugly messages.  It might lead to real problems on other
>>>     systems.
>>>     
>>>     I checked all the devices which are currently checked for by early_quirks
>>>     and it turns out they are all located in the root bus zero.
>>>     
>>>     So change the early-quirks loop to only scan bus 0.  This incidently also
>>>     saves quite some unnecessary scanning work, because early_quirks doesn't
>>>     go through all the non root busses.
>>>     
>>>     The graphics card is not on bus 0, so it is not matched anymore.
>>>     
>>>     Signed-off-by: Andi Kleen <ak at linux.intel.com>
>>>     Cc: Ingo Molnar <mingo at elte.hu>
>>>     Cc: Thomas Gleixner <tglx at linutronix.de>
>>>     Cc: "H. Peter Anvin" <hpa at zytor.com>
>>>     Cc: Jesse Barnes <jbarnes at virtuousgeek.org>
>>>     Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
>>>     Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
>>>
>>> diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
>>> index 744aa7f..76b8cd9 100644
>>> --- a/arch/x86/kernel/early-quirks.c
>>> +++ b/arch/x86/kernel/early-quirks.c
>>> @@ -201,6 +201,12 @@ struct chipset {
>>>  	void (*f)(int num, int slot, int func);
>>>  };
>>>  
>>> +/*
>>> + * Only works for devices on the root bus. If you add any devices
>>> + * not on bus 0 readd another loop level in early_quirks(). But
>>> + * be careful because at least the Nvidia quirk here relies on
>>> + * only matching on bus 0.
>>> + */
>>>  static struct chipset early_qrk[] __initdata = {
>>>  	{ PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
>>>  	  PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs },
>>> @@ -267,17 +273,17 @@ static int __init check_dev_quirk(int num, int slot, int func)
>>>  
>>>  void __init early_quirks(void)
>>>  {
>>> -	int num, slot, func;
>>> +	int slot, func;
>>>  
>>>  	if (!early_pci_allowed())
>>>  		return;
>>>  
>>>  	/* Poor man's PCI discovery */
>>> -	for (num = 0; num < 32; num++)
>>> -		for (slot = 0; slot < 32; slot++)
>>> -			for (func = 0; func < 8; func++) {
>>> -				/* Only probe function 0 on single fn devices */
>>> -				if (check_dev_quirk(num, slot, func))
>>> -					break;
>>> -			}
>>> +	/* Only scan the root bus */
>>> +	for (slot = 0; slot < 32; slot++)
>>> +		for (func = 0; func < 8; func++) {
>>> +			/* Only probe function 0 on single fn devices */
>>> +			if (check_dev_quirk(0, slot, func))
>>> +				break;
>>> +		}
>>>  }
>>>
>>>
>>>
>> applied to Jaunty
>>
> 
> This is sort of nitpick, but I think formally I'd need at least one ack for 
> Intrepid...
> 

Unless someone has this specific problem (which would satisfy SRU
requirements), then I'd say apply it to the stable branch only.

-- 
Tim Gardner tim.gardner at canonical.com