On Thu, 2015-09-10 at 14:58 +0100, Matt Fleming wrote:
> On Tue, 2015-09-08 at 18:06 +0100, Juvva, Kanaka D wrote:
> >
> > There are two aspects:
> >
> > 1) Programming MSRs
> > 2) EVENT_ATTR_STR(llc_local_bw, intel_cqm_llc_local_bw, "event=0x04");
> >
> > 1 is used for programming MSRs
> >
On Thu, 2015-09-10 at 14:58 +0100, Matt Fleming wrote:
> On Tue, 2015-09-08 at 18:06 +0100, Juvva, Kanaka D wrote:
> >
> > There are two aspects:
> >
> > 1) Programming MSRs
> > 2) EVENT_ATTR_STR(llc_local_bw, intel_cqm_llc_local_bw, "event=0x04");
> >
> > 1 is used for programming MSRs
> >
for freeing or picking an RMID.
Signed-off-by: Kanaka Juvva
---
arch/x86/kernel/cpu/perf_event_intel_cqm.c | 11 ++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 63eb68b..7aa3bc0
y perf,
perf event codes are in powers of 2
version3: Improved readbility of code
Incorporated upstream comments for Patch v2
Signed-off-by: Kanaka Juvva
---
arch/x86/include/asm/cpufeature.h | 2 +
arch/x86/kernel/cpu/common.c | 4 +-
arch/x86/kern
,
perf event codes are in powers of 2
version3: Improved readbility of code
Incorporated upstream comments for Patch v2
Signed-off-by: Kanaka Juvva kanaka.d.ju...@linux.intel.com
---
arch/x86/include/asm/cpufeature.h | 2 +
arch/x86/kernel/cpu/common.c
for freeing or picking an RMID.
Signed-off-by: Kanaka Juvva kanaka.d.ju...@linux.intel.com
---
arch/x86/kernel/cpu/perf_event_intel_cqm.c | 11 ++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
b/arch/x86/kernel/cpu
once in a second. Overflow is
detected and handled. Running average value is calculated for each
bandwidth type upon reading a new value from the MSR. Sliding window
stores the values read from MSR. Sliding window size is configurable.
Signed-off-by: Kanaka Juvva
---
arch/x86/include/asm
once in a second. Overflow is
detected and handled. Running average value is calculated for each
bandwidth type upon reading a new value from the MSR. Sliding window
stores the values read from MSR. Sliding window size is configurable.
Signed-off-by: Kanaka Juvva kanaka.d.ju...@linux.intel.com
Added lock in event reader function. The cqm_pick_event_reader() function
accesses cqm_cpumask and it is critical section between this and
cqm_stable().
This situation is true when a CPU is hotplugged. Mutex is used to protect
the critical section.
Signed-off-by: Kanaka Juvva
---
arch/x86
Added lock in event reader function. The cqm_pick_event_reader() function
accesses cqm_cpumask and it is critical section between this and
cqm_stable().
This situation is true when a CPU is hotplugged. Mutex is used to protect
the critical section.
Signed-off-by: Kanaka Juvva kanaka.d.ju
be read atleast once in a second. Overflow is
detected and handled. Cumulative average value is calculated for each
bandwidth type upon reading a new value from the MSR.
Signed-off-by: Kanaka Juvva
---
arch/x86/include/asm/cpufeature.h | 2 +
arch/x86/kernel/cpu/common.c
be read atleast once in a second. Overflow is
detected and handled. Cumulative average value is calculated for each
bandwidth type upon reading a new value from the MSR.
Signed-off-by: Kanaka Juvva kanaka.d.ju...@linux.intel.com
---
arch/x86/include/asm/cpufeature.h | 2 +
arch/x86
be read atleast once in a second. Overflow is
detected and handled. Cumulative average value is calculated for each
bandwidth type upon reading a new value from the MSR.
Signed-off-by: Kanaka Juvva
---
arch/x86/include/asm/cpufeature.h | 2 +
arch/x86/kernel/cpu/common.c
be read atleast once in a second. Overflow is
detected and handled. Cumulative average value is calculated for each
bandwidth type upon reading a new value from the MSR.
Signed-off-by: Kanaka Juvva kanaka.d.ju...@linux.intel.com
---
arch/x86/include/asm/cpufeature.h | 2 +
arch/x86
14 matches
Mail list logo