Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-15 Thread Andi Kleen
On Thu, Sep 13, 2007 at 10:20:56AM -0700, H. Peter Anvin wrote: > Yinghai Lu wrote: > > > > BIOS guys also said that fam 10h need mmconfig via eax accessing, may > > need OS do sth, so it is safe to stay with MCFG entry for SB like > > mcp55... > > > > but latest kernel already have that

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-15 Thread Andi Kleen
On Thu, Sep 13, 2007 at 10:20:56AM -0700, H. Peter Anvin wrote: Yinghai Lu wrote: BIOS guys also said that fam 10h need mmconfig via eax accessing, may need OS do sth, so it is safe to stay with MCFG entry for SB like mcp55... but latest kernel already have that workaround to make

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread H. Peter Anvin
Andreas Herrmann wrote: > On Thu, Sep 13, 2007 at 10:20:56AM -0700, H. Peter Anvin wrote: >> Yinghai Lu wrote: >>> BIOS guys also said that fam 10h need mmconfig via eax accessing, may >>> need OS do sth, so it is safe to stay with MCFG entry for SB like >>> mcp55... >>> >>> but latest kernel

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Andreas Herrmann
On Thu, Sep 13, 2007 at 10:20:56AM -0700, H. Peter Anvin wrote: > Yinghai Lu wrote: > > > > BIOS guys also said that fam 10h need mmconfig via eax accessing, may > > need OS do sth, so it is safe to stay with MCFG entry for SB like > > mcp55... > > > > but latest kernel already have that

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Yinghai Lu
Andreas Herrmann wrote: On Thu, Sep 13, 2007 at 01:53:15PM +0200, Andi Kleen wrote: On Thursday 13 September 2007 12:47, Greg KH wrote: On Thu, Sep 13, 2007 at 11:47:42AM +0200, Andi Kleen wrote: On Thursday 13 September 2007 04:21, Yinghai Lu wrote: [PATCH] x86_64: set cfg_size for AMD

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Andreas Herrmann
On Thu, Sep 13, 2007 at 01:53:15PM +0200, Andi Kleen wrote: > On Thursday 13 September 2007 12:47, Greg KH wrote: > > On Thu, Sep 13, 2007 at 11:47:42AM +0200, Andi Kleen wrote: > > > On Thursday 13 September 2007 04:21, Yinghai Lu wrote: > > > > [PATCH] x86_64: set cfg_size for AMD Family 10h in

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread H. Peter Anvin
Yinghai Lu wrote: > On 9/13/07, H. Peter Anvin <[EMAIL PROTECTED]> wrote: >> Yinghai Lu wrote: >>> BIOS guys also said that fam 10h need mmconfig via eax accessing, may >>> need OS do sth, so it is safe to stay with MCFG entry for SB like >>> mcp55... >>> >>> but latest kernel already have that

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Yinghai Lu
On 9/13/07, H. Peter Anvin <[EMAIL PROTECTED]> wrote: > Yinghai Lu wrote: > > > > BIOS guys also said that fam 10h need mmconfig via eax accessing, may > > need OS do sth, so it is safe to stay with MCFG entry for SB like > > mcp55... > > > > but latest kernel already have that workaround to make

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread H. Peter Anvin
Yinghai Lu wrote: > > BIOS guys also said that fam 10h need mmconfig via eax accessing, may > need OS do sth, so it is safe to stay with MCFG entry for SB like > mcp55... > > but latest kernel already have that workaround to make mmconfig via eax... > This is actually a good point. Since the

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Yinghai Lu
On 9/13/07, Andi Kleen <[EMAIL PROTECTED]> wrote: > On Thursday 13 September 2007 12:47, Greg KH wrote: > > On Thu, Sep 13, 2007 at 11:47:42AM +0200, Andi Kleen wrote: > > > On Thursday 13 September 2007 04:21, Yinghai Lu wrote: > > > > [PATCH] x86_64: set cfg_size for AMD Family 10h in case

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Andi Kleen
On Thursday 13 September 2007 12:47, Greg KH wrote: > On Thu, Sep 13, 2007 at 11:47:42AM +0200, Andi Kleen wrote: > > On Thursday 13 September 2007 04:21, Yinghai Lu wrote: > > > [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is > > > used. > > > > > > reuse pci_cfg_space_size

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Greg KH
On Thu, Sep 13, 2007 at 11:47:42AM +0200, Andi Kleen wrote: > On Thursday 13 September 2007 04:21, Yinghai Lu wrote: > > [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used. > > > > reuse pci_cfg_space_size but skip check pci express and pci-x CAP ID. > > I just rejected a

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Andi Kleen
On Thursday 13 September 2007 04:21, Yinghai Lu wrote: > [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used. > > reuse pci_cfg_space_size but skip check pci express and pci-x CAP ID. I just rejected a similar patch -- this should be done using MMCONFIG -Andi - To

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Andi Kleen
On Thursday 13 September 2007 04:21, Yinghai Lu wrote: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used. reuse pci_cfg_space_size but skip check pci express and pci-x CAP ID. I just rejected a similar patch -- this should be done using MMCONFIG -Andi - To unsubscribe

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Greg KH
On Thu, Sep 13, 2007 at 11:47:42AM +0200, Andi Kleen wrote: On Thursday 13 September 2007 04:21, Yinghai Lu wrote: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used. reuse pci_cfg_space_size but skip check pci express and pci-x CAP ID. I just rejected a similar

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Andi Kleen
On Thursday 13 September 2007 12:47, Greg KH wrote: On Thu, Sep 13, 2007 at 11:47:42AM +0200, Andi Kleen wrote: On Thursday 13 September 2007 04:21, Yinghai Lu wrote: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used. reuse pci_cfg_space_size but skip check

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Yinghai Lu
On 9/13/07, Andi Kleen [EMAIL PROTECTED] wrote: On Thursday 13 September 2007 12:47, Greg KH wrote: On Thu, Sep 13, 2007 at 11:47:42AM +0200, Andi Kleen wrote: On Thursday 13 September 2007 04:21, Yinghai Lu wrote: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread H. Peter Anvin
Yinghai Lu wrote: BIOS guys also said that fam 10h need mmconfig via eax accessing, may need OS do sth, so it is safe to stay with MCFG entry for SB like mcp55... but latest kernel already have that workaround to make mmconfig via eax... This is actually a good point. Since the CPU

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Yinghai Lu
On 9/13/07, H. Peter Anvin [EMAIL PROTECTED] wrote: Yinghai Lu wrote: BIOS guys also said that fam 10h need mmconfig via eax accessing, may need OS do sth, so it is safe to stay with MCFG entry for SB like mcp55... but latest kernel already have that workaround to make mmconfig via

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread H. Peter Anvin
Yinghai Lu wrote: On 9/13/07, H. Peter Anvin [EMAIL PROTECTED] wrote: Yinghai Lu wrote: BIOS guys also said that fam 10h need mmconfig via eax accessing, may need OS do sth, so it is safe to stay with MCFG entry for SB like mcp55... but latest kernel already have that workaround to make

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Andreas Herrmann
On Thu, Sep 13, 2007 at 01:53:15PM +0200, Andi Kleen wrote: On Thursday 13 September 2007 12:47, Greg KH wrote: On Thu, Sep 13, 2007 at 11:47:42AM +0200, Andi Kleen wrote: On Thursday 13 September 2007 04:21, Yinghai Lu wrote: [PATCH] x86_64: set cfg_size for AMD Family 10h in case

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Yinghai Lu
Andreas Herrmann wrote: On Thu, Sep 13, 2007 at 01:53:15PM +0200, Andi Kleen wrote: On Thursday 13 September 2007 12:47, Greg KH wrote: On Thu, Sep 13, 2007 at 11:47:42AM +0200, Andi Kleen wrote: On Thursday 13 September 2007 04:21, Yinghai Lu wrote: [PATCH] x86_64: set cfg_size for AMD

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread Andreas Herrmann
On Thu, Sep 13, 2007 at 10:20:56AM -0700, H. Peter Anvin wrote: Yinghai Lu wrote: BIOS guys also said that fam 10h need mmconfig via eax accessing, may need OS do sth, so it is safe to stay with MCFG entry for SB like mcp55... but latest kernel already have that workaround to make

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-13 Thread H. Peter Anvin
Andreas Herrmann wrote: On Thu, Sep 13, 2007 at 10:20:56AM -0700, H. Peter Anvin wrote: Yinghai Lu wrote: BIOS guys also said that fam 10h need mmconfig via eax accessing, may need OS do sth, so it is safe to stay with MCFG entry for SB like mcp55... but latest kernel already have that

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-12 Thread Andrew Morton
On Wed, 12 Sep 2007 19:21:43 -0700 Yinghai Lu <[EMAIL PROTECTED]> wrote: > +/** > + * Regular PCI devices have 256 bytes, but AMD Family 10h Opteron ext config > + * have 4096 bytes. Even if the device is capable, that doesn't mean we can > + * access it. Maybe we don't have a way to generate

[PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-12 Thread Yinghai Lu
[PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used. reuse pci_cfg_space_size but skip check pci express and pci-x CAP ID. Signed-off-by: Yinghai Lu <[EMAIL PROTECTED]> arch/i386/pci/fixup.c | 13 + drivers/pci/probe.c | 11 ++-

[PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-12 Thread Yinghai Lu
[PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used. reuse pci_cfg_space_size but skip check pci express and pci-x CAP ID. Signed-off-by: Yinghai Lu [EMAIL PROTECTED] arch/i386/pci/fixup.c | 13 + drivers/pci/probe.c | 11 ++- include/linux/pci.h

Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

2007-09-12 Thread Andrew Morton
On Wed, 12 Sep 2007 19:21:43 -0700 Yinghai Lu [EMAIL PROTECTED] wrote: +/** + * Regular PCI devices have 256 bytes, but AMD Family 10h Opteron ext config + * have 4096 bytes. Even if the device is capable, that doesn't mean we can + * access it. Maybe we don't have a way to generate