On 28 April 2016 at 23:26, Andrew Morton wrote:
> On Thu, 28 Apr 2016 21:04:18 +0200 Mathias Krause
> wrote:
>
>> If /proc//environ gets read before the envp[] array is fully set
>> up in create_{aout,elf,elf_fdpic,flat}_tables(), we might end
On 28 April 2016 at 23:26, Andrew Morton wrote:
> On Thu, 28 Apr 2016 21:04:18 +0200 Mathias Krause
> wrote:
>
>> If /proc//environ gets read before the envp[] array is fully set
>> up in create_{aout,elf,elf_fdpic,flat}_tables(), we might end up trying
>> to read more bytes than are actually
> The new cgroup namespace currently only allows for superficial
> interaction with the user namespace (it checks against the namespace
> it was created in whether or not a user has the right capabilities
> before allowing mounting, and things like that). However, there is one
> glaring feature
> The new cgroup namespace currently only allows for superficial
> interaction with the user namespace (it checks against the namespace
> it was created in whether or not a user has the right capabilities
> before allowing mounting, and things like that). However, there is one
> glaring feature
On 2016年04月28日 22:48, Eduardo Valentin wrote:
> On Thu, Apr 28, 2016 at 02:48:41PM +0800, Wei Ni wrote:
>>
>>
>> On 2016年04月28日 07:30, Eduardo Valentin wrote:
>>> From: Eduardo Valentin
>>> To: Wei Ni
>>> Cc: thierry.red...@gmail.com, robh...@kernel.org,
On 2016年04月28日 22:48, Eduardo Valentin wrote:
> On Thu, Apr 28, 2016 at 02:48:41PM +0800, Wei Ni wrote:
>>
>>
>> On 2016年04月28日 07:30, Eduardo Valentin wrote:
>>> From: Eduardo Valentin
>>> To: Wei Ni
>>> Cc: thierry.red...@gmail.com, robh...@kernel.org, rui.zh...@intel.com,
>>>
On Fri, Apr 29, 2016 at 12:59 AM, Mikulas Patocka wrote:
>
>
> On Fri, 29 Apr 2016, Ming Lei wrote:
>
>> On Thu, Apr 28, 2016 at 11:58 PM, Mikulas Patocka
>> wrote:
>> >
>> >
>> > On Thu, 28 Apr 2016, Ming Lei wrote:
>> >
>> >> Hi Mikulas,
>> >>
>> >>
On Fri, Apr 29, 2016 at 12:59 AM, Mikulas Patocka wrote:
>
>
> On Fri, 29 Apr 2016, Ming Lei wrote:
>
>> On Thu, Apr 28, 2016 at 11:58 PM, Mikulas Patocka
>> wrote:
>> >
>> >
>> > On Thu, 28 Apr 2016, Ming Lei wrote:
>> >
>> >> Hi Mikulas,
>> >>
>> >> On Thu, Apr 28, 2016 at 11:29 PM, Mikulas
Hi Linus,
A few fixes all over the place:
radeon is probably the biggest standout, it's a fix for screen
corruption or hung black outputs so I thought it was worth pulling in.
Otherwise some amdgpu power control fixes, some misc vmwgfx fixes,
one etnaviv fix, one virtio-gpu fix, two DP MST
Hi Linus,
A few fixes all over the place:
radeon is probably the biggest standout, it's a fix for screen
corruption or hung black outputs so I thought it was worth pulling in.
Otherwise some amdgpu power control fixes, some misc vmwgfx fixes,
one etnaviv fix, one virtio-gpu fix, two DP MST
It's more convenient to use existing function helper to convert string
"on/off" to boolean.
Signed-off-by: Minfei Huang
---
lib/kstrtox.c| 2 +-
mm/page_alloc.c | 9 +
mm/page_poison.c | 8 +---
3 files changed, 3 insertions(+), 16 deletions(-)
diff --git
It's more convenient to use existing function helper to convert string
"on/off" to boolean.
Signed-off-by: Minfei Huang
---
lib/kstrtox.c| 2 +-
mm/page_alloc.c | 9 +
mm/page_poison.c | 8 +---
3 files changed, 3 insertions(+), 16 deletions(-)
diff --git a/lib/kstrtox.c
On Fri, Apr 29, 2016 at 01:17:09AM +0900, Sergey Senozhatsky wrote:
> Pass GFP flags to zs_malloc() instead of using a fixed set
> (supplied during pool creation), so we can be more flexible,
> but, more importantly, this will be need to switch zram to
> per-cpu compression streams.
>
> Apart
On Fri, Apr 29, 2016 at 01:17:09AM +0900, Sergey Senozhatsky wrote:
> Pass GFP flags to zs_malloc() instead of using a fixed set
> (supplied during pool creation), so we can be more flexible,
> but, more importantly, this will be need to switch zram to
> per-cpu compression streams.
>
> Apart
Signed-off-by: Manav Batra
Separates out assignment in one line to two lines.
---
drivers/staging/rts5208/rtsx.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/staging/rts5208/rtsx.c b/drivers/staging/rts5208/rtsx.c
index
Signed-off-by: Manav Batra
Separates out assignment in one line to two lines.
---
drivers/staging/rts5208/rtsx.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/staging/rts5208/rtsx.c b/drivers/staging/rts5208/rtsx.c
index 25d095a..77c2580 100644
---
On Thu, Apr 28, 2016 at 10:30:49PM -0700, Manav Batra wrote:
> Signed-off-by: Manav Batra
I can't take patches without any changelog text :(
On Thu, Apr 28, 2016 at 10:30:49PM -0700, Manav Batra wrote:
> Signed-off-by: Manav Batra
I can't take patches without any changelog text :(
On Fri, Apr 29, 2016 at 09:38:24AM +0900, Sergey Senozhatsky wrote:
> On (04/28/16 15:07), Andrew Morton wrote:
> > Needed a bit of tweaking due to
> > http://ozlabs.org/~akpm/mmotm/broken-out/zsmalloc-reordering-function-parameter.patch
>
> Thanks.
>
> > From: Dan Streetman
On Fri, Apr 29, 2016 at 09:38:24AM +0900, Sergey Senozhatsky wrote:
> On (04/28/16 15:07), Andrew Morton wrote:
> > Needed a bit of tweaking due to
> > http://ozlabs.org/~akpm/mmotm/broken-out/zsmalloc-reordering-function-parameter.patch
>
> Thanks.
>
> > From: Dan Streetman
> > Subject:
Signed-off-by: Manav Batra
---
drivers/staging/rts5208/rtsx.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/staging/rts5208/rtsx.c b/drivers/staging/rts5208/rtsx.c
index 25d095a..77c2580 100644
--- a/drivers/staging/rts5208/rtsx.c
+++
Signed-off-by: Manav Batra
---
drivers/staging/rts5208/rtsx.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/staging/rts5208/rtsx.c b/drivers/staging/rts5208/rtsx.c
index 25d095a..77c2580 100644
--- a/drivers/staging/rts5208/rtsx.c
+++
Signed-off-by: Manav Batra
---
drivers/staging/rts5208/sd.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/staging/rts5208/sd.c b/drivers/staging/rts5208/sd.c
index 87d6976..fbd2f90 100644
--- a/drivers/staging/rts5208/sd.c
+++
Signed-off-by: Manav Batra
---
drivers/staging/rts5208/sd.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/staging/rts5208/sd.c b/drivers/staging/rts5208/sd.c
index 87d6976..fbd2f90 100644
--- a/drivers/staging/rts5208/sd.c
+++ b/drivers/staging/rts5208/sd.c
@@
On Thu, Apr 14, 2016 at 08:48:48PM +0530, Sudip Mukherjee wrote:
> The semaphore was being released twice, once at the beginning of the
> thread and then again when the thread is about to close.
> The semaphore is acquired immediately after creating the thread so we
> should be releasing it when
On Thu, Apr 14, 2016 at 08:48:48PM +0530, Sudip Mukherjee wrote:
> The semaphore was being released twice, once at the beginning of the
> thread and then again when the thread is about to close.
> The semaphore is acquired immediately after creating the thread so we
> should be releasing it when
On 2016/4/28 5:32, Arnaldo Carvalho de Melo wrote:
Em Wed, Apr 20, 2016 at 06:59:50PM +, Wang Nan escreveu:
Allow 'perf record' to split its output into multiple files.
For example:
I squashed:
-> 360 T 04/20 Wang Nan(1.7K) ├─>[PATCH v6 6/7]
perf record: Re-synthesize
Am Dienstag, 26. April 2016, 20:23:46 schrieb George Spelvin:
Hi George,
> > And considering that I only want to have 0.9 bits of entropy, why
> > should I not collapse it? The XOR operation does not destroy the existing
> > entropy, it only caps it to at most one bit of information theoretical
On 2016/4/28 5:32, Arnaldo Carvalho de Melo wrote:
Em Wed, Apr 20, 2016 at 06:59:50PM +, Wang Nan escreveu:
Allow 'perf record' to split its output into multiple files.
For example:
I squashed:
-> 360 T 04/20 Wang Nan(1.7K) ├─>[PATCH v6 6/7]
perf record: Re-synthesize
Am Dienstag, 26. April 2016, 20:23:46 schrieb George Spelvin:
Hi George,
> > And considering that I only want to have 0.9 bits of entropy, why
> > should I not collapse it? The XOR operation does not destroy the existing
> > entropy, it only caps it to at most one bit of information theoretical
The previous version of Intel's CQM introduced pmu::count as a replacement
for reading CQM events. This was done to avoid using an IPI to read the
CQM occupancy event when reading events attached to a thread.
Using pmu->count in place of pmu->read is inconsistent with the usage by
other PMUs and
CQM was the only user of pmu->count, no need to have it anymore.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
include/linux/perf_event.h | 6 --
kernel/events/core.c | 10 --
kernel/trace/bpf_trace.c | 5
Create a CQM_EVENT_ATTR_STR to use in CQM to remove dependency
on the unrelated x86's PMU EVENT_ATTR_STR.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
arch/x86/events/intel/cqm.c | 17 -
1 file changed, 12
The previous version of Intel's CQM introduced pmu::count as a replacement
for reading CQM events. This was done to avoid using an IPI to read the
CQM occupancy event when reading events attached to a thread.
Using pmu->count in place of pmu->read is inconsistent with the usage by
other PMUs and
CQM was the only user of pmu->count, no need to have it anymore.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
include/linux/perf_event.h | 6 --
kernel/events/core.c | 10 --
kernel/trace/bpf_trace.c | 5 ++---
3 files changed, 2 insertions(+),
Create a CQM_EVENT_ATTR_STR to use in CQM to remove dependency
on the unrelated x86's PMU EVENT_ATTR_STR.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
arch/x86/events/intel/cqm.c | 17 -
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git
Move code around, delete unnecesary code and do some renaming in
in order to increase readibility of next patches. Create cqm.h file.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
arch/x86/events/intel/cqm.c | 170
Move code around, delete unnecesary code and do some renaming in
in order to increase readibility of next patches. Create cqm.h file.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
arch/x86/events/intel/cqm.c | 170 +++-
CQM defines a dirty threshold that is the minimum number of dirty
cache lines that a prmid can hold before being eligible to be reused.
This threshold is zero unless there exist significant contention of prmids
(more on this on the patch that introduces rotation of RMIDs).
A limbo prmid is a
Cgroups and/or tasks that require to be monitored using a RMID
are abstracted as a MOnitored Resources (monr's). A CQM event points
to a monr to read occupancy (and in the future other attributes) of the
RMIDs associated to the monr.
The monrs form a hierarchy that captures the dependency within
CQM defines a dirty threshold that is the minimum number of dirty
cache lines that a prmid can hold before being eligible to be reused.
This threshold is zero unless there exist significant contention of prmids
(more on this on the patch that introduces rotation of RMIDs).
A limbo prmid is a
Cgroups and/or tasks that require to be monitored using a RMID
are abstracted as a MOnitored Resources (monr's). A CQM event points
to a monr to read occupancy (and in the future other attributes) of the
RMIDs associated to the monr.
The monrs form a hierarchy that captures the dependency within
Allow a PMU to clean an event before the event's torn down in
perf_events begins.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
include/linux/perf_event.h | 6 ++
kernel/events/core.c | 4
2 files changed, 10
Allow a PMU to clean an event before the event's torn down in
perf_events begins.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
include/linux/perf_event.h | 6 ++
kernel/events/core.c | 4
2 files changed, 10 insertions(+)
diff --git
The hooks allows architectures to extend the behavior of the
perf subsystem.
In this patch series, the hooks will be used by Intel's CQM PMU to
provide support for the llc_occupancy event.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
Create a monr per monitored cgroup. Inserts monrs in the monr hierarchy.
Task events are leaves of the lowest monitored ancestor cgroup (the lowest
cgroup ancestor with a monr).
CQM starts after the cgroup subsystem, and uses the cqm_initialized_key
static key to avoid interfering with the perf
The hooks allows architectures to extend the behavior of the
perf subsystem.
In this patch series, the hooks will be used by Intel's CQM PMU to
provide support for the llc_occupancy event.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
include/linux/perf_event.h | 28
Create a monr per monitored cgroup. Inserts monrs in the monr hierarchy.
Task events are leaves of the lowest monitored ancestor cgroup (the lowest
cgroup ancestor with a monr).
CQM starts after the cgroup subsystem, and uses the cqm_initialized_key
static key to avoid interfering with the perf
Some events, such as Intel's CQM llc_occupancy, need small deviations
from the traditional behavior in the generic code in a way that depends
on the event itself (and known by the PMU) and not in a field of
perf_event_attrs.
An example is the recursive scope for cgroups: The generic code handles
This version of RMID rotation improves over original one by:
1. Being per-package. No need for IPIs to test for occupancy.
2. Since the monr hierarchy removed the potential conflicts between
events, the new RMID rotation logic does not need to check and
resolve conflicts.
3. No
Some events, such as Intel's CQM llc_occupancy, need small deviations
from the traditional behavior in the generic code in a way that depends
on the event itself (and known by the PMU) and not in a field of
perf_event_attrs.
An example is the recursive scope for cgroups: The generic code handles
This version of RMID rotation improves over original one by:
1. Being per-package. No need for IPIs to test for occupancy.
2. Since the monr hierarchy removed the potential conflicts between
events, the new RMID rotation logic does not need to check and
resolve conflicts.
3. No
Utilized to detach a monr from a cgroup before the event's reference
to the cgroup is removed.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
arch/x86/events/intel/cqm.c | 16 +---
1 file changed, 13 insertions(+), 3
Utilized to detach a monr from a cgroup before the event's reference
to the cgroup is removed.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
arch/x86/events/intel/cqm.c | 16 +---
1 file changed, 13 insertions(+), 3 deletions(-)
diff --git
Use newly added pmu_event flags to:
- Allow thread events to be read from any CPU even if not in
ACTIVE state. Since inter-package values are polled, a thread's
occupancy is always:
local occupancy (read from hw) + remote occupancy (polled values)
- Allow cpu/cgroup events to be read
To avoid IPIs from IRQ disabled contexts, the occupancy for a RMID in a
remote package (a package other than the one the current cpu belongs) is
obtained from a cache that is periodically updated.
This removes the need for an IPI when reading occupancy for a task event,
that was the reason to add
Some offcore and uncore events, such as the new intel_cqm/llc_occupancy,
can be read even if the event is not active in its CPU (or in any CPU).
In those cases, a freshly read value is more recent, (and therefore
preferable) than the last value stored at event sched out.
There are two cases
Some offcore and uncore events, such as the new intel_cqm/llc_occupancy,
can be read even if the event is not active in its CPU (or in any CPU).
In those cases, a freshly read value is more recent, (and therefore
preferable) than the last value stored at event sched out.
There are two cases
Use newly added pmu_event flags to:
- Allow thread events to be read from any CPU even if not in
ACTIVE state. Since inter-package values are polled, a thread's
occupancy is always:
local occupancy (read from hw) + remote occupancy (polled values)
- Allow cpu/cgroup events to be read
To avoid IPIs from IRQ disabled contexts, the occupancy for a RMID in a
remote package (a package other than the one the current cpu belongs) is
obtained from a cache that is periodically updated.
This removes the need for an IPI when reading occupancy for a task event,
that was the reason to add
The CQM hardware is not compatible with the way generic code handles
cgroup hierarchies (simultaneously adding the events of for all ancestors
of the current cgroup). This version of Intel's CQM driver handles
cgroup hierarchy internally.
Set PERF_CGROUP_NO_RECURSION for llc_occupancy events to
Since inherited events are part of the same cqm cache group, they share the
RMID and therefore they cannot provide the granularity required by
inherit_stats. Changing this would require to create a subtree of monrs for
each parent event and its inherited events, a potential improvement for
future
The CQM hardware is not compatible with the way generic code handles
cgroup hierarchies (simultaneously adding the events of for all ancestors
of the current cgroup). This version of Intel's CQM driver handles
cgroup hierarchy internally.
Set PERF_CGROUP_NO_RECURSION for llc_occupancy events to
Since inherited events are part of the same cqm cache group, they share the
RMID and therefore they cannot provide the granularity required by
inherit_stats. Changing this would require to create a subtree of monrs for
each parent event and its inherited events, a potential improvement for
future
A package wide event can return a valid read even if it has not run in a
specific cpu, this does not fit well with the assumption that run == 0
is equivalent to a .
To fix the problem, this patch defines special error values for val,
run and ena (~0ULL), and use them to signal read errors,
New PMUs, such as CQM's, do not guarantee that a read will succeed even
if pmu::add was successful.
In the generic code, this patch adds an int error return and completes the
error checking path up to perf_read().
In CQM's PMU, it adds proper error handling of hw read failure errors.
In other
Expose the boolean attribute intel_cqm.cont_monitoring . When set, the
associated group will be monitored even if no perf cgroup event is
attached to it.
The occupancy of a cgroup must be read using a perf_event, regardless of
the value of intel_cqm.cont_monitoring .
Reviewed-by: Stephane
Allow architectures to define additional attributes for the perf cgroup.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
include/linux/perf_event.h | 4
kernel/events/core.c | 2 ++
2 files changed, 6 insertions(+)
Expose the boolean attribute intel_cqm.cont_monitoring . When set, the
associated group will be monitored even if no perf cgroup event is
attached to it.
The occupancy of a cgroup must be read using a perf_event, regardless of
the value of intel_cqm.cont_monitoring .
Reviewed-by: Stephane
Allow architectures to define additional attributes for the perf cgroup.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
include/linux/perf_event.h | 4
kernel/events/core.c | 2 ++
2 files changed, 6 insertions(+)
diff --git a/include/linux/perf_event.h
A package wide event can return a valid read even if it has not run in a
specific cpu, this does not fit well with the assumption that run == 0
is equivalent to a .
To fix the problem, this patch defines special error values for val,
run and ena (~0ULL), and use them to signal read errors,
New PMUs, such as CQM's, do not guarantee that a read will succeed even
if pmu::add was successful.
In the generic code, this patch adds an int error return and completes the
error checking path up to perf_read().
In CQM's PMU, it adds proper error handling of hw read failure errors.
In other
perf_event context switches events to newly exec'ed tasks using
perf_event_exec. Add a hook for such path.
In x86, perf_event_arch_exec is used to synchronize the software
cache of the PQR_ASSOC msr, setting the right RMID for the new task.
Reviewed-by: Stephane Eranian
From: Stephane Eranian
When an event is in error state, read() returns 0
instead of sizeof() buffer. In certain modes, such
as interval printing, ignoring the 0 return value
may cause bogus count deltas to be computed and
thus invalid results printed.
this patch fixes this
Allow monitored cgroups to update the PQR MSR during task switch even
without an associated perf_event.
The package RMID for the current monr associated with a monitored
cgroup is written to hw during task switch (after perf_events is run)
if perf_event did not write a RMID for an event.
This hook allows architecture specific code to be called at the end of
the task switch and after perf_events' context switch but before the
scheduler lock is released.
The specific use case in this series is to avoid multiple writes to a slow
MSR until all functions which modify such register in
perf_event context switches events to newly exec'ed tasks using
perf_event_exec. Add a hook for such path.
In x86, perf_event_arch_exec is used to synchronize the software
cache of the PQR_ASSOC msr, setting the right RMID for the new task.
Reviewed-by: Stephane Eranian
Signed-off-by: David
From: Stephane Eranian
When an event is in error state, read() returns 0
instead of sizeof() buffer. In certain modes, such
as interval printing, ignoring the 0 return value
may cause bogus count deltas to be computed and
thus invalid results printed.
this patch fixes this problem by modifying
Allow monitored cgroups to update the PQR MSR during task switch even
without an associated perf_event.
The package RMID for the current monr associated with a monitored
cgroup is written to hw during task switch (after perf_events is run)
if perf_event did not write a RMID for an event.
This hook allows architecture specific code to be called at the end of
the task switch and after perf_events' context switch but before the
scheduler lock is released.
The specific use case in this series is to avoid multiple writes to a slow
MSR until all functions which modify such register in
First part of new CQM logic. This patch introduces the struct pkg_data
that contains all per-package CQM data required by the new RMID hierarchy.
The raw RMID value is encapsulated in a Package RMID (prmid) structure
that provides atomic updates and caches recent reads. This caching
throttles the
In preparation for future patches that will introduce a per-package
rotation of RMIDs.
The new rotation logic follows the same ideas as the present rotation
logic being removed but takes advantage of the per-package RMID design
and a more detailed bookkeeping to guarantee to meet user SLOs.
It
First part of new CQM logic. This patch introduces the struct pkg_data
that contains all per-package CQM data required by the new RMID hierarchy.
The raw RMID value is encapsulated in a Package RMID (prmid) structure
that provides atomic updates and caches recent reads. This caching
throttles the
In preparation for future patches that will introduce a per-package
rotation of RMIDs.
The new rotation logic follows the same ideas as the present rotation
logic being removed but takes advantage of the per-package RMID design
and a more detailed bookkeeping to guarantee to meet user SLOs.
It
Read RMIDs llc_occupancy for cgroups by adding the occupancy of all
pmonrs with a read_rmid along its subtree in the pmonr hierarchy for
the event's package.
The RMID to read for a monr is the same as its RMID to schedule in hw if
the monr is in (A)state. If in (IL)state, the RMID to read is that
The new version of Intel's CQM uses a RMID hierarchy to avoid conflicts
between cpu, cgroup and task events, making unnecessary to check and
resolve conflicts between events of different types (ie. cgroup vs task).
Reviewed-by: Stephane Eranian
Signed-off-by: David
Add Intel's PQR as its own build target, remove its build dependency
on CQM, and add CONFIG_INTEL_RDT as a configuration flag to build PQR
and all of its related drivers (currently CQM, future: MBM, CAT, CDP).
Reviewed-by: Stephane Eranian
Signed-off-by: David
Pre-allocate enough anodes to be able to at least hold one set of RMIDs
per package before running out of anodes.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
arch/x86/events/intel/cqm.c | 10 ++
1 file changed, 10
Read RMIDs llc_occupancy for cgroups by adding the occupancy of all
pmonrs with a read_rmid along its subtree in the pmonr hierarchy for
the event's package.
The RMID to read for a monr is the same as its RMID to schedule in hw if
the monr is in (A)state. If in (IL)state, the RMID to read is that
The new version of Intel's CQM uses a RMID hierarchy to avoid conflicts
between cpu, cgroup and task events, making unnecessary to check and
resolve conflicts between events of different types (ie. cgroup vs task).
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
Add Intel's PQR as its own build target, remove its build dependency
on CQM, and add CONFIG_INTEL_RDT as a configuration flag to build PQR
and all of its related drivers (currently CQM, future: MBM, CAT, CDP).
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
Pre-allocate enough anodes to be able to at least hold one set of RMIDs
per package before running out of anodes.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
arch/x86/events/intel/cqm.c | 10 ++
1 file changed, 10 insertions(+)
diff --git
Removing MBM code from arch/x86/events/intel/cqm.c. MBM will be added
using the new RMID infrastucture introduced in this patch series.
Also, remove updates to CQM that are superseded by this series.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
Removing MBM code from arch/x86/events/intel/cqm.c. MBM will be added
using the new RMID infrastucture introduced in this patch series.
Also, remove updates to CQM that are superseded by this series.
Reviewed-by: Stephane Eranian
Signed-off-by: David Carrillo-Cisneros
---
This series introduces the next iteration of kernel support for the
Cache QoS Monitoring (CQM) technology available in Intel Xeon processors.
One of the main limitations of the previous version is the inability
to simultaneously monitor:
1) cpu event and any other event in that cpu.
2) cgroup
On 04/29/2016 09:12 AM, Jason Wang wrote:
> On 04/28/2016 10:43 PM, Michael S. Tsirkin wrote:
>> > On Thu, Apr 28, 2016 at 02:37:16PM +0800, Jason Wang wrote:
>>> >>
>>> >> On 04/27/2016 07:45 PM, Michael S. Tsirkin wrote:
>>> On Fri, Mar 25, 2016 at 10:34:34AM +0800, Jason Wang wrote:
On 04/29/2016 09:12 AM, Jason Wang wrote:
> On 04/28/2016 10:43 PM, Michael S. Tsirkin wrote:
>> > On Thu, Apr 28, 2016 at 02:37:16PM +0800, Jason Wang wrote:
>>> >>
>>> >> On 04/27/2016 07:45 PM, Michael S. Tsirkin wrote:
>>> On Fri, Mar 25, 2016 at 10:34:34AM +0800, Jason Wang wrote:
This series introduces the next iteration of kernel support for the
Cache QoS Monitoring (CQM) technology available in Intel Xeon processors.
One of the main limitations of the previous version is the inability
to simultaneously monitor:
1) cpu event and any other event in that cpu.
2) cgroup
On 2016-04-28 23:47, Wolfram Sang wrote:
> On Wed, Apr 20, 2016 at 05:18:02PM +0200, Peter Rosin wrote:
>> The root i2c adapter lock is then no longer held by the i2c mux during
>> accesses behind the i2c gate, and such accesses need to take that lock
>> just like any other ordinary i2c accesses
On 2016-04-28 23:47, Wolfram Sang wrote:
> On Wed, Apr 20, 2016 at 05:18:02PM +0200, Peter Rosin wrote:
>> The root i2c adapter lock is then no longer held by the i2c mux during
>> accesses behind the i2c gate, and such accesses need to take that lock
>> just like any other ordinary i2c accesses
1 - 100 of 2004 matches
Mail list logo