Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
---
arch/x86/kernel/apic_64.c |2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index d8d03e0..2a9f4bc 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/
On 05.12.07 08:51:02, Arjan van de Ven wrote:
> which kernel code is using or going to use these export?
For IBS it is Perfmon. See here:
http://git.kernel.org/?p=linux/kernel/git/eranian/linux-2.6.git;a=commit;h=7caef3e19d17349f869884f5adf7c9823e32ade7
MCE export has been added for consistency r
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
---
arch/x86/kernel/apic_64.c |2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 5a31a8c..a678e8f 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
---
arch/x86/kernel/apic_32.c | 31 +++
1 files changed, 31 insertions(+), 0 deletions(-)
diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index 1872f88..ce6e341 100644
--- a/arch/x86/kernel/a
. The vector mapping is hardcoded for
now.
Also macro definitions in apicdef.h has been updated.
The patch is relative to x86/cleanup tree.
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
---
arch/x86/kernel/apic_64.c | 26 ++
arch/x86/kernel/cpu/
This patch adds extended interrupt support for AMD Barcelona CPUs. The
patch provides functions to setup MCE and IBS interrupt
vectors. Compared to the previous K8 implementation the vector offsets
are centrally handled now in apic_64.c. Thus, the APIC setup code is
responsible for vector mappings.
On 10.11.07 21:32:39, Andi Kleen wrote:
> It would be really good to extract a core perfmon and start with
> that and then add stuff as it makes sense.
>
> e.g. core perfmon could be something simple like just support
> to context switch state and initialize counters in a basic way
> and perhaps
On 13.11.07 13:02:08, Adrian Bunk wrote:
> On Tue, Nov 13, 2007 at 12:44:43PM +0100, Robert Richter wrote:
> > x86 CPU specific code is currently implemented in different ways for
> > 64 and 32 bit. While there are almost no CPU specific files for 64
> > bit, there is th
x86 CPU specific code is currently implemented in different ways for
64 and 32 bit. While there are almost no CPU specific files for 64
bit, there is the arch/x86/kernel/cpu/ directory for 32 bit. Is there
already an idea about whether to use kernel/cpu also for 64 bit?
Thanks,
-Robert
--
Advan
On 12.11.07 12:31:44, Maciej W. Rozycki wrote:
> > -#defineGET_APIC_VERSION(x) ((x)&0xFF)
> > -#defineGET_APIC_MAXLVT(x) (((x)>>16)&0xFF)
> > -#defineAPIC_INTEGRATED(x) ((x)&0xF0)
> > +#defineGET_APIC_VERS
Thomas,
On 06.11.07 21:32:12, Thomas Gleixner wrote:
> Thanks for doing this, but please check the x86 git repository
> (cleanup / mm branch) for stuff which has been worked on already.
>
> Maybe we need some coordination for this.
Is it for sure that the x86/cleanup tree will go upstream soon a
On 07.11.07 12:41:09, Jeremy Fitzhardinge wrote:
> > -#defineGET_APIC_VERSION(x) ((x)&0xFF)
> > -#defineGET_APIC_MAXLVT(x) (((x)>>16)&0xFF)
> > -#defineAPIC_INTEGRATED(x) ((x)&0xF0)
> > +#defineGET_APIC_VE
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
---
include/asm-x86/apicdef_32.h |3 +--
1 files changed, 1 insertions(+), 2 deletions(-)
Index: linux-perfmon/include/asm-x86/apicdef_32.h
===
--- linux-perfmon.orig/i
The following patch series unifies apicdef*h header files for the x86
architure. For a better review there are many small patches.
--
Advanced Micro Devices, Inc.
Operating System Research Center
email: [EMAIL PROTECTED]
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
---
include/asm-x86/apicdef_64.h |3 +--
1 files changed, 1 insertions(+), 2 deletions(-)
Index: linux-perfmon/include/asm-x86/apicdef_64.h
===
--- linux-perfmon.orig/i
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
---
include/asm-x86/apicdef.h | 10 +-
1 files changed, 5 insertions(+), 5 deletions(-)
Index: linux-perfmon/include/asm-x86/apicdef.h
===
--- linux-perfmon.orig/i
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
---
include/asm-x86/apicdef.h| 401 +-
include/asm-x86/apicdef_32.h | 402 --
include/asm-x86/apicdef_64.h | 402 ---
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
---
include/asm-x86/apicdef_32.h | 28
include/asm-x86/apicdef_64.h | 11 +++
2 files changed, 39 insertions(+), 0 deletions(-)
Index: linux-perfmon/include/asm-x86/apicde
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
---
include/asm-x86/apicdef_32.h | 16
1 files changed, 8 insertions(+), 8 deletions(-)
Index: linux-perfmon/include/asm-x86/apicdef_32.h
===
---
> This patch is necessary to make Event Based Profiling work reliably on a
> Family10h processor
>
> ---
> op_model_athlon.c | 22 --
> 1 file changed, 16 insertions(+), 6 deletions(-)
> ---
>
> Signed-off-by: Barry Kasindorf <[EMAIL PROTEC
On 05.09.07 11:12:00, H. Peter Anvin wrote:
> >PCI Devices will not be the same on the bus since PCI read/write
> >functions will have different behavior. Without the patches you will
> >get an error when accessing ECS with CF8. We need ECS access for
> >patches that setups local interrupt vectors.
On 05.09.07 06:58:58, H. Peter Anvin wrote:
> >But at the moment there is no need for further discussion on this subject
> >because Andi refuses to add support for Barcelona CF8/CFC ECS access.
> >
>
> Well, they don't add any functionality, do they? As such, I would agree
> with Andi -- we onl
On 03.09.07 09:48:15, dean gaudet wrote:
> it's so very unfortunate the PCI standard has no feature bit to indicate
> the presence of ECS.
Right. Not nice.
> FWIW in my testing on a range of machines spanning 7 or 8 years i could
> read config space reg 256... and get 0x when the device
Andi,
On 03.09.07 14:48:41, Andi Kleen wrote:
> > As said above, I do not see CF8 access as a workaround. I expect my
> > system to work in the same way also if MMCONFIG is not available.
>
> It should boot sure, but exotic stuff not working is not a major issue
It is not only about booting the
Andi,
On 03.09.07 12:15:03, Andi Kleen wrote:
> > But it is needed for some devices for full functionality.
>
> Examples? I can only think of PCI express error reporting, which
> few drivers implement anyways and isn't really a show stopper
> if it doesn't work. Besides I would be surprised if i
This patch sets the config space size for AMD Barcelona PCI devices to
4096.
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
---
arch/i386/pci/fixup.c | 14 ++
1 file changed, 14 insertions(+)
Index: linux-2.6/arch/i386/pci/f
This patch adds MSR definitions for the northbridge configuration
register for AMD's Barcelona CPUs.
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
---
include/asm-i386/msr-index.h |1 +
1 file changed, 1 insertion(+)
Index: linux-2.6/include/asm-i386/
(resent due to mail server issues)
Hello,
the following series of patches adds support for PCI extended
configuration space access of AMD's Barcelona CPUs (family 10h). It
modifies the CF8/CFC IO register access method and sets the size of
the CPU's PCI devices to 4096 bytes.
Regards,
Robert
-
This patch implements PCI extended configuration space access for
AMD's Barcelona CPUs. It extends the method using CF8/CFC IO
addresses. An x86 capability bit has been introduced that is set for
CPUs supporting PCI extended config space accesses.
Signed-off-by: Robert Richter <[EMAIL P
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
---
include/linux/pci_ids.h |5 +
1 file changed, 5 insertions(+)
Index: linux-2.6/include/linux/pci_ids.h
===
--- linux-2.6.orig/include/linux/pci_ids.h
+++ lin
Already added to the -mm tree. Its filename is
i386-add-amd64-barcelona-pmu-msr-definitions.patch
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
---
include/asm-i386/msr-index.h | 36 +---
1 file changed, 25 insertions(+), 11 deletions(-)
Index:
On 20.06.07 12:43:59, David Rientjes wrote:
> On Wed, 20 Jun 2007, Robert Richter wrote:
>
> > This patch renames *_k8_* symbols to *_amd64_*.
> >
> > Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
> >
> > Index: linux-2
On 20.06.07 12:49:05, David Rientjes wrote:
> On Wed, 20 Jun 2007, Robert Richter wrote:
>
> > Debug messages added for better debugging.
> >
>
> And you added BUG_ON()'s.
>
> > Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
> >
On 20.06.07 13:22:16, Stephane Eranian wrote:
> David,
>
> On Wed, Jun 20, 2007 at 12:49:05PM -0700, David Rientjes wrote:
> > On Wed, 20 Jun 2007, Robert Richter wrote:
> >
> > > Debug messages added for better debugging.
> > >
> >
> >
On 20.06.07 12:45:35, David Rientjes wrote:
> On Wed, 20 Jun 2007, Robert Richter wrote:
>
> > Index: linux-2.6.22-rc3/arch/x86_64/perfmon/perfmon_k8.c
> > ===
> > --- linux-2.6.22-rc3.orig/arch/x86
Hello,
this is version 2 of the patch series. Thanks to David and James for
reviewing this. Below you can find a diff that shows changes to the
previous version. The patches are relative to Stephane's 2.6.22-rc3
Perfmon2 release.
Regards,
Robert
Index: linux-2.6.22-rc3/arch/i386/perfmon/perfmon.
This patch renames module perfmon_k8 to perfmon_amd64.
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
Index: linux-2.6.22-rc3/arch/i386/perfmon/Kconfig
===
--- linux-2.6.22-rc3.orig/arch/i386/perfmon/Kconfig
+++ linux-2.6.
This patch implements an initial AMD64 PMU configuration.
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
Index: linux-2.6.22-rc3/arch/i386/perfmon/perfmon.c
===
--- linux-2.6.22-rc3.orig/arch/i386/perfmon/perfmon.c
+++
This patch renames *_k8_* symbols to *_amd64_*.
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
Index: linux-2.6.22-rc3/arch/x86_64/perfmon/perfmon_k8.c
===
--- linux-2.6.22-rc3.orig/arch/x86_64/perfmon/perfmon_k8.c
+++
only occur if the PMU
description has been configured incorrectly. Also the function
interface does not allow the return of error codes. So this can be
handled using BUG_ON().
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
Index: linux-2.6.22-rc3/arch/i386/perfmon/per
d;
> > u64 *mask;
> > unsigned int i, num, ena;
> > + unsigned int ibs_check = 0;
> > +#define IBS_CHECK_FETCHCTL 0x01
> > +#define IBS_CHECK_FETCHCTR 0x02
> > +#define IBS_CHECK_OPCTL0x04
> > +#define IBS_CHECK_OPCTR0x08
> > +#define
This patch implements Barcelona CPU detection.
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
Index: linux-2.6.22-rc3/arch/i386/perfmon/perfmon.c
===
--- linux-2.6.22-rc3.orig/arch/i386/perfmon/perfmon.c
+++ linux-2.6.22-rc
David,
hex values are now lowercase, thanks. This also affects patch #6.
Andi,
since this is not a Perfmon specific patch, could you apply it?
Thanks,
-Robert
---
This patch rearranges AMD64 MSR definitions.
2nd try:
- hex values made lowercase
Signed-off-by: Robert Richter
Debug messages added for better debugging.
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
Index: linux-2.6.22-rc3/perfmon/perfmon_file.c
===
--- linux-2.6.22-rc3.orig/perfmon/perfmon_file.c
+++ linux-2.6.22-rc3/p
David,
> Please don't include mixed cases of hex digits. This entire file has all
> hex digits in lowercase type, so please conform to that.
I fixed this in the 2nd version of the patch.
> > +#define K8_MTRRFIXRANGE_DRAM_ENABLE0x0004 /* MtrrFixDramEn bit
> >*/
> > +#define K8_
Minor changes (whitespace, comments, ...)
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
Index: linux-2.6.22-rc3/arch/x86_64/perfmon/perfmon_k8.c
===
--- linux-2.6.22-rc3.orig/arch/x86_64/perfmon/perfmon_k8.c
+++ linux-2.6.
David,
thanks for your comments.
On 15.06.07 11:54:24, David Rientjes wrote:
> On Fri, 15 Jun 2007, Robert Richter wrote:
>
> > Index: linux-2.6.22-rc3/arch/i386/perfmon/perfmon.c
> > ===
> > --- linux-2
This patch renames *_k8_* symbols to *_amd64_*.
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
Index: linux-2.6.22-rc3/arch/x86_64/perfmon/perfmon_k8.c
===
--- linux-2.6.22-rc3.orig/arch/x86_64/perfmon/perfmon_k8.c
+++
This patch renames module perfmon_k8 to perfmon_amd64.
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
Index: linux-2.6.22-rc3/arch/i386/perfmon/Kconfig
===
--- linux-2.6.22-rc3.orig/arch/i386/perfmon/Kconfig
+++ linux-2.6.
This patch implements an initial AMD64 PMU configuration.
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
Index: linux-2.6.22-rc3/arch/i386/perfmon/perfmon.c
===
--- linux-2.6.22-rc3.orig/arch/i386/perfmon/perfmon.c
+++
This patch implements Instruction Based Sampling (IBS).
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
Index: linux-2.6.22-rc3/arch/i386/perfmon/perfmon.c
===
--- linux-2.6.22-rc3.orig/arch/i386/perfmon/perfmon.c
+++ linux-
This patch rearranges AMD64 MSR definitions.
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
Index: linux-2.6.22-rc3/include/asm-i386/msr-index.h
===
--- linux-2.6.22-rc3.orig/include/asm-i386/msr-index.h
+++ linux-2.6.
Debug messages added for better debugging.
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
Index: linux-2.6.22-rc3/perfmon/perfmon_file.c
===
--- linux-2.6.22-rc3.orig/perfmon/perfmon_file.c
+++ linux-2.6.22-rc3/p
Minor changes (whitespace, comments, ...)
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
Index: linux-2.6.22-rc3/arch/x86_64/perfmon/perfmon_k8.c
===
--- linux-2.6.22-rc3.orig/arch/x86_64/perfmon/perfmon_k8.c
+++ linux-2.6.
This patch implements Barcelona CPU detection.
Signed-off-by: Robert Richter <[EMAIL PROTECTED]>
Index: linux-2.6.22-rc3/arch/i386/perfmon/perfmon.c
===
--- linux-2.6.22-rc3.orig/arch/i386/perfmon/perfmon.c
+++ linux-2.6.22-rc
Hello,
the following series of patches adds support for Instruction Based
Sampling (IBS) of Barcelona CPUs. IBS is a code profiling mechanism
that enables the processor to select a random instruction fetch or
micro-op after a programmed time interval has expired and record
specific performance inf
Stephane,
> > > +
> > > + if (current_cpu_data.x86 != 15) {
> > > + PFM_INFO("unsupported family=%d", current_cpu_data.x86);
> > > + return -1;
> > > + }
> >
> > Already obsolete with Barcelona and Griffin (16 and 17) but very similar
> > counters.
> >
> Yes, but those will get
901 - 957 of 957 matches
Mail list logo