On 1/14/25 3:25 PM, Shuah Khan wrote:
>
> Thank you for bumping it up to top of my Inbox.
> I will apply these for 6.14-rc1 now.
>
Thank you very much Shuah.
Reinette
Hi Shuah,
On 12/19/24 10:35 AM, Reinette Chatre wrote:
> Hi Shuah,
>
> On 12/16/24 7:18 AM, Maciej Wieczor-Retman wrote:
>>
>> Sub-Numa Clustering (SNC) allows splitting CPU cores, caches and memory
>> into multiple NUMA nodes. When enabled, NUMA-aware applica
Hi Shuah,
On 12/16/24 7:18 AM, Maciej Wieczor-Retman wrote:
>
> Sub-Numa Clustering (SNC) allows splitting CPU cores, caches and memory
> into multiple NUMA nodes. When enabled, NUMA-aware applications can
> achieve better performance on bigger server platforms.
>
> SNC support was merged into t
veloped-by: Tony Luck
> Signed-off-by: Tony Luck
> Signed-off-by: Maciej Wieczor-Retman
> ---
Thank you very much.
Reviewed-by: Reinette Chatre
Reinette
gelog]
Signed-off-by: Isaku Yamahata
Signed-off-by: Reinette Chatre
---
tools/testing/selftests/kvm/include/test_util.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/testing/selftests/kvm/include/test_util.h
b/tools/testing/selftests/kvm/include/test_util.h
liable path to check for existence of sub node files is
> /sys/fs/resctrl/mon_data/mon_L3_00/mon_sub_L3_00.
>
> Add helper that checks for mon_sub_L3_00 existence.
>
> Correct old messages to account for kernel support of SNC in
> resctrl.
>
> Signed-off-by: Maciej Wi
Hi Maciej,
On 12/9/24 3:09 AM, Maciej Wieczor-Retman wrote:
>
> Sub-Numa Clustering (SNC) allows splitting CPU cores, caches and memory
> into multiple NUMA nodes. When enabled, NUMA-aware applications can
> achieve better performance on bigger server platforms.
>
> SNC support in the kernel was
Hi Maciej,
On 12/9/24 3:09 AM, Maciej Wieczor-Retman wrote:
> Sub-NUMA Cluster divides CPUs sharing an L3 cache into separate NUMA
> nodes. Systems may support splitting into either two, three, four or six
> nodes. When SNC mode is enabled the effective amount of L3 cache
> available for allocatio
Hi Maciej,
On 12/2/24 3:08 AM, Maciej Wieczor-Retman wrote:
> diff --git a/tools/testing/selftests/resctrl/resctrlfs.c
> b/tools/testing/selftests/resctrl/resctrlfs.c
> index 50561993d37c..d0a5c0f78397 100644
> --- a/tools/testing/selftests/resctrl/resctrlfs.c
> +++ b/tools/testing/selftests/res
Hi Maciej,
On 12/2/24 3:08 AM, Maciej Wieczor-Retman wrote:
> diff --git a/tools/testing/selftests/resctrl/resctrlfs.c
> b/tools/testing/selftests/resctrl/resctrlfs.c
> index d38d6dd90be4..50561993d37c 100644
> --- a/tools/testing/selftests/resctrl/resctrlfs.c
> +++ b/tools/testing/selftests/res
Hi Maciej,
On 10/29/24 6:00 AM, Maciej Wieczor-Retman wrote:
> diff --git a/tools/testing/selftests/resctrl/resctrl.h
> b/tools/testing/selftests/resctrl/resctrl.h
> index 2dda56084588..851b37c9c38a 100644
> --- a/tools/testing/selftests/resctrl/resctrl.h
> +++ b/tools/testing/selftests/resctrl/r
Hi Maciej,
On 10/29/24 6:00 AM, Maciej Wieczor-Retman wrote:
> Resctrl selftest prints a message on test failure that Sub-Numa
> Clustering (SNC) could be enabled and points the user to check their BIOS
> settings. No actual check is performed before printing that message so
> it is not very accur
Hi Maciej,
On 10/29/24 6:00 AM, Maciej Wieczor-Retman wrote:
> Sub-NUMA Cluster divides CPUs sharing an L3 cache into separate NUMA
> nodes. Systems may support splitting into either two, three or four
> nodes.
>
> When SNC mode is enabled the effective amount of L3 cache available
> for allocati
On 11/4/24 4:07 PM, Shuah Khan wrote:
> On 11/4/24 16:14, Reinette Chatre wrote:
>>
>>
>> On 11/4/24 2:28 PM, Shuah Khan wrote:
>>> On 11/4/24 15:16, Reinette Chatre wrote:
>>>> Hi Shuah,
>>>>
>>>> On 10/24/24 3:36 PM
On 11/4/24 2:28 PM, Shuah Khan wrote:
> On 11/4/24 15:16, Reinette Chatre wrote:
>> Hi Shuah,
>>
>> On 10/24/24 3:36 PM, Shuah Khan wrote:
>>> On 10/24/24 15:18, Reinette Chatre wrote:
>>>
>>> Is this patch series ready to be applied?
>>&g
Hi Shuah,
On 10/24/24 3:36 PM, Shuah Khan wrote:
> On 10/24/24 15:18, Reinette Chatre wrote:
>
> Is this patch series ready to be applied?
>
It is now ready after receiving anticipated tags. Could you please consider it
for inclusion?
Thank you very much.
Reinette
On 10/25/24 6:54 AM, Ilpo Järvinen wrote:
> On Thu, 24 Oct 2024, Reinette Chatre wrote:
>
>> Hi Shuah,
>>
>> On 10/24/24 3:36 PM, Shuah Khan wrote:
>>>
>>> Is this patch series ready to be applied?
>>>
>>
>> I believe it is close
nt "mem_bw".
Signed-off-by: Reinette Chatre
Reviewed-by: Ilpo Järvinen
---
Changes since V2:
- Add Ilpo's Reviewed-by tag.
Changes since V1:
- New patch.
---
tools/testing/selftests/resctrl/mba_test.c| 4 +-
tools/testing/selftests/resctrl/mbm_test.c| 4 +-
tools/
e to AMD systems since it
only applies to the MBA and MBM tests that are isolated to Intel.
[1]
https://ark.intel.com/content/www/us/en/ark/products/237261/intel-xeon-platinum-8592-processor-320m-cache-1-9-ghz.html
Reinette Chatre (15):
selftests/resctrl: Make functions only used in same fi
existing behavior of CMT test is to use test defined value for the
buffer size even if the user provides another value via command line.
This behavior is maintained since the test requires that the buffer size
matches the size of the cache allocated, and the amount of cache
allocated can instead
ory bandwidth from perf IMC
counter and from resctrl file system")
Signed-off-by: Reinette Chatre
Reviewed-by: Ilpo Järvinen
---
Changes since V2:
- Rephrase changelog. (Ilpo)
- Add Ilpo's Reviewed-by tag.
Changes since V1:
- New patch.
---
tools/testing/selftests/resctrl/resctrl_v
ask' was not declared. Should it be static?
Signed-off-by: Reinette Chatre
Reviewed-by: Ilpo Järvinen
---
Changes since v1:
- Add Ilpo's Reviewed-by tag.
- Let subject describe the change, not the tool that found it. (checkpatch.pl)
---
tools/testing/selftests/resctrl/resctrl_val.c | 8
ther benchmark
(that may or may not use a buffer) or if user space amended the buffer
size.
Ensure that accurate buffer size is printed when using "fill_buf"
benchmark and omit the buffer size information if another benchmark
is used.
Fixes: ecdbb911f22d ("selftests/resctrl: Add
the test parameters the
array size depends on.
Reported-by: Ilpo Järvinen
Closes:
https://lore.kernel.org/all/45af2a8c-517d-8f0d-137d-ad0f3f6a3...@linux.intel.com/
Signed-off-by: Reinette Chatre
Reviewed-by: Ilpo Järvinen
---
Changes since V3:
- Add Ilpo's Reviewed-by tag.
Changes sin
te" operations to the buffer.
Ignore any attempt from user space to enable this unsupported test
configuration, instead always use read operations.
Keep the initialization of the, now unused, "fill_buf" parameters
to reserve these parameter positions since it has been exposed as an A
Hi Shuah,
On 10/24/24 3:36 PM, Shuah Khan wrote:
>
> Is this patch series ready to be applied?
>
I believe it is close ... I would like to give Ilpo some time to peek
at patches 2 and 10 to confirm if I got their fixes right this time. The
rest of the series is ready.
Thank you
Reinette
. This avoids wraparound while making the purpose
of "allocation > ALLOCATION_MAX" clear and eliminates the
need for the "allocation < ALLOCATION_MIN" check.
Reported-by: Ilpo Järvinen
Closes:
https://lore.kernel.org/lkml/1903ac13-5c9c-ef8d-78e0-417ac34a9...@linux.intel.com/
S
arated the buffer
prepare phase from the benchmark run phase reducing the need for the
tests themselves to accommodate the benchmark's "settle" time.
With these enhancements there are no remaining portions needing
to "settle" and the first test run can contribute to
ntime" part
of the benchmark (or entire user provided benchmark).
Keep the "wait one second" delay before measurements start. For the
default "fill_buf" benchmark this time now covers only the "runtime"
portion that needs to be measured. For the user provided b
t adequate comparison between
performance counters and resctrl.
Signed-off-by: Reinette Chatre
Reviewed-by: Ilpo Järvinen
---
Changes since V2:
- Add Ilpo's Reviewed-by tag.
Changes since V1:
- Fix code alignment and spacing.
- Modify flow to use "continue" instead of "break" n
ss while keeping the existing default
as minimum, now renamed to MINIMUM_SPAN, that has been appropriate for
testing so far.
Signed-off-by: Reinette Chatre
Reviewed-by: Ilpo Järvinen
---
Changes since V3:
- Add Ilpo's Reviewed-by tag.
Changes since V2:
- Move duplicate code into helper. (Il
ly cycle through the buffer once (by setting "once = true")
and thus breaking the CMT, MBA, and MBM tests that expect
workload/interference to be reflected by their measurements.
Prevent user space from changing the "once" parameter and ensure
that it is always false for the CMT, MBA
the
maximum field width.
Signed-off-by: Reinette Chatre
Reviewed-by: Ilpo Järvinen
---
This makes the code robust against any changes in information read
from sysfs. The existing sysfs content fit well into the arrays, thus
this is not considered a bugfix.
Changes since V3:
- Add Ilpo's Rev
39 ("selftests/resctrl: Add built in benchmark")
Signed-off-by: Reinette Chatre
Reviewed-by: Ilpo Järvinen
---
Changes since V2:
- Add Ilpo's Reviewed-by tag.
Changes since V1:
- New patch.
---
tools/testing/selftests/resctrl/fill_buf.c | 2 +-
1 file changed, 1 insertion(+), 1 deletio
Hi Ilpo,
On 10/18/24 2:03 AM, Ilpo Järvinen wrote:
> On Thu, 17 Oct 2024, Reinette Chatre wrote:
>> +/*
>> + * Allocate and initialize a struct fill_buf_param with user provided
>> + * (via "-b fill_buf ") parameters.
>> + *
>> + * Use defaults (that ma
Hi Ilpo,
On 10/18/24 1:46 AM, Ilpo Järvinen wrote:
> On Thu, 17 Oct 2024, Reinette Chatre wrote:
>> @@ -138,15 +139,26 @@ static int mbm_run_test(const struct resctrl_test
>> *test, const struct user_param
>> .setup = mbm_setup,
>
arated the buffer
prepare phase from the benchmark run phase reducing the need for the
tests themselves to accommodate the benchmark's "settle" time.
With these enhancements there are no remaining portions needing
to "settle" and the first test run can contribute to
the test parameters the
array size depends on.
Reported-by: Ilpo Järvinen
Closes:
https://lore.kernel.org/all/45af2a8c-517d-8f0d-137d-ad0f3f6a3...@linux.intel.com/
Signed-off-by: Reinette Chatre
---
Changes since V2:
- New patch.
---
tools/testing/selftests/resctrl/mba_test.c | 3 ++-
1 file
t adequate comparison between
performance counters and resctrl.
Signed-off-by: Reinette Chatre
Reviewed-by: Ilpo Järvinen
---
Changes since V2:
- Add Ilpo's Reviewed-by tag.
Changes since V1:
- Fix code alignment and spacing.
- Modify flow to use "continue" instead of "break" n
ntime" part
of the benchmark (or entire user provided benchmark).
Keep the "wait one second" delay before measurements start. For the
default "fill_buf" benchmark this time now covers only the "runtime"
portion that needs to be measured. For the user provided b
ss while keeping the existing default
as minimum, now renamed to MINIMUM_SPAN, that has been appropriate for
testing so far.
Signed-off-by: Reinette Chatre
---
Changes since V2:
- Move duplicate code into helper. (Ilpo)
- Rename DEFAULT_SPAN to MINIMUM_SPAN to reflect its new purpose. (Ilpo)
-
existing behavior of CMT test is to use test defined value for the
buffer size even if the user provides another value via command line.
This behavior is maintained since the test requires that the buffer size
matches the size of the cache allocated, and the amount of cache
allocated can inste
te" operations to the buffer.
Ignore any attempt from user space to enable this unsupported test
configuration, instead always use read operations.
Keep the initialization of the, now unused, "fill_buf" parameters
to reserve these parameter positions since it has been exposed as an API.
nt "mem_bw".
Signed-off-by: Reinette Chatre
Reviewed-by: Ilpo Järvinen
---
Changes since V2:
- Add Ilpo's Reviewed-by tag.
Changes since V1:
- New patch.
---
tools/testing/selftests/resctrl/mba_test.c| 4 +-
tools/testing/selftests/resctrl/mbm_test.c| 4 +-
tools/
ly cycle through the buffer once (by setting "once = true")
and thus breaking the CMT, MBA, and MBM tests that expect
workload/interference to be reflected by their measurements.
Prevent user space from changing the "once" parameter and ensure
that it is always false for the CMT, MBA
. This avoids wraparound while making the purpose
of "allocation > ALLOCATION_MAX" clear and eliminates the
need for the "allocation < ALLOCATION_MIN" check.
Reported-by: Ilpo Järvinen
Closes:
https://lore.kernel.org/lkml/1903ac13-5c9c-ef8d-78e0-417ac34a9...@linux.intel.com/
S
the
maximum field width.
Signed-off-by: Reinette Chatre
---
This makes the code robust against any changes in information read
from sysfs. The existing sysfs content fit well into the arrays, thus
this is not considered a bugfix.
Changes since V2:
- New patch
---
tools/testing/selftests/resctrl
39 ("selftests/resctrl: Add built in benchmark")
Signed-off-by: Reinette Chatre
Reviewed-by: Ilpo Järvinen
---
Changes since V2:
- Add Ilpo's Reviewed-by tag.
Changes since V1:
- New patch.
---
tools/testing/selftests/resctrl/fill_buf.c | 2 +-
1 file changed, 1 insertion(+), 1 deletio
ory bandwidth from perf IMC
counter and from resctrl file system")
Signed-off-by: Reinette Chatre
Reviewed-by: Ilpo Järvinen
---
Changes since V2:
- Rephrase changelog. (Ilpo)
- Add Ilpo's Reviewed-by tag.
Changes since V1:
- New patch.
---
tools/testing/selftests/resctrl/resctrl_v
ther benchmark
(that may or may not use a buffer) or if user space amended the buffer
size.
Ensure that accurate buffer size is printed when using "fill_buf"
benchmark and omit the buffer size information if another benchmark
is used.
Fixes: ecdbb911f22d ("selftests/resctrl: Add
ask' was not declared. Should it be static?
Signed-off-by: Reinette Chatre
Reviewed-by: Ilpo Järvinen
---
Changes since v1:
- Add Ilpo's Reviewed-by tag.
- Let subject describe the change, not the tool that found it. (checkpatch.pl)
---
tools/testing/selftests/resctrl/resctrl_val.c | 8
t is not applicable to AMD systems since it
only applies to the MBA and MBM tests that are isolated to Intel.
[1]
https://ark.intel.com/content/www/us/en/ark/products/237261/intel-xeon-platinum-8592-processor-320m-cache-1-9-ghz.html
Reinette Chatre (15):
selftests/resctrl: Make functions only us
Hi Ilpo,
On 10/4/24 7:29 AM, Ilpo Järvinen wrote:
> On Thu, 12 Sep 2024, Reinette Chatre wrote:
...
>> diff --git a/tools/testing/selftests/resctrl/mbm_test.c
>> b/tools/testing/selftests/resctrl/mbm_test.c
>> index 7635ee6b9339..8c818e292dce 100644
>> --- a/tool
Hi Ilpo,
On 10/4/24 7:20 AM, Ilpo Järvinen wrote:
> On Thu, 12 Sep 2024, Reinette Chatre wrote:
>
>> By default the MBM and MBA tests use the "fill_buf" benchmark to
>> read from a buffer with the goal to measure the memory bandwidth
>> generated by this buffer
Hi Ilpo,
On 10/4/24 7:05 AM, Ilpo Järvinen wrote:
> On Thu, 12 Sep 2024, Reinette Chatre wrote:
>> tools/testing/selftests/resctrl/cmt_test.c| 32 ++
>> tools/testing/selftests/resctrl/mba_test.c| 13 ++-
>> tools/testing/selftests/resctrl/mbm_test.c
Hi Ilpo,
On 9/30/24 6:49 AM, Ilpo Järvinen wrote:
> On Thu, 12 Sep 2024, Reinette Chatre wrote:
>
>> The CMT, MBM, and MBA tests rely on a benchmark that runs while
>> the test makes changes to needed configuration (for example memory
>> bandwidth allocation) and takes
Hi Ilpo,
On 9/30/24 6:52 AM, Ilpo Järvinen wrote:
> On Thu, 12 Sep 2024, Reinette Chatre wrote:
>> diff --git a/tools/testing/selftests/resctrl/resctrl.h
>> b/tools/testing/selftests/resctrl/resctrl.h
>> index 51f5f4b25e06..ba1ce1b35699 100644
>> --- a/tools/testing/
Hi Ilpo,
On 9/30/24 6:35 AM, Ilpo Järvinen wrote:
> On Thu, 12 Sep 2024, Reinette Chatre wrote:
>
>> The MBM and MBA tests need to discover the event and umask with which to
>> configure the performance event used to measure read memory bandwidth.
>> This is done by
Hi Maciej,
On 8/27/24 1:15 AM, Maciej Wieczor-Retman wrote:
On 2024-08-12 at 16:40:10 -0700, Reinette Chatre wrote:
On 7/12/24 2:04 AM, Maciej Wieczor-Retman wrote:
+
+ if ((get_vendor() == ARCH_INTEL) && snc_unreliable) {
+ ksft_print_msg("Sub-NUMA Cluster
arated the buffer
prepare phase from the benchmark run phase reducing the need for the
tests themselves to accommodate the benchmark's "settle" time.
With these enhancements there are no remaining portions needing
to "settle" and the first test run can contribute to me
t adequate comparison between
performance counters and resctrl.
Signed-off-by: Reinette Chatre
---
Changes since V1:
- Fix code alignment and spacing.
- Modify flow to use "continue" instead of "break" now that
earlier changes decreases throttling.
- Expand comment of define to e
ntime" part
of the benchmark (or entire user provided benchmark).
Keep the "wait one second" delay before measurements start. For the
default "fill_buf" benchmark this time now covers only the "runtime"
portion that needs to be measured. For the user provided b
ss while keeping the existing default
as minimum that has been appropriate for testing so far.
Signed-off-by: Reinette Chatre
---
Changes since V1:
- Ensure buffer is at least double L3 cache size. (Ilpo)
- Support user override of default buffer size. (Ilpo)
---
tools/testing/selftests/re
existing behavior of CMT test is to use test defined value for the
buffer size even if the user provides another value via command line.
This behavior is maintained since the test requires that the buffer size
matches the size of the cache allocated, and the amount of cache
allocated can instead be ch
nt "mem_bw".
Signed-off-by: Reinette Chatre
---
Changes since V1:
- New patch.
---
tools/testing/selftests/resctrl/mba_test.c| 4 +-
tools/testing/selftests/resctrl/mbm_test.c| 4 +-
tools/testing/selftests/resctrl/resctrl.h | 8 +-
tools/testing/selftes
the MBA and MBM tests only measure "read" operations. The
"read" operation is also most appropriate for the CMT test that aims
to use the benchmark to allocate into the cache.
Avoid any potential inconsistencies between test and measurement by
removing code for unsupported "
ly cycle through the buffer once (by setting "once = true")
and thus breaking the CMT, MBA, and MBM tests that expect
workload/interference to be reflected by their measurements.
Prevent user space from changing the "once" parameter and ensure
that it is always false for the CMT, MBA
trl: Read memory bandwidth from perf IMC
counter and from resctrl file system")
Signed-off-by: Reinette Chatre
---
Changes since V1:
- New patch.
---
tools/testing/selftests/resctrl/resctrl_val.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/tools/testing/sel
. This avoids wraparound while making the purpose
of "allocation > ALLOCATION_MAX" clear and eliminates the
need for the "allocation < ALLOCATION_MIN" check.
Reported-by: Ilpo Järvinen
Closes:
https://lore.kernel.org/lkml/1903ac13-5c9c-ef8d-78e0-417ac34a9...@linux.intel.com/
S
39 ("selftests/resctrl: Add built in benchmark")
Signed-off-by: Reinette Chatre
---
Changes since V1:
- New patch.
---
tools/testing/selftests/resctrl/fill_buf.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/testing/selftests/resctrl/fill_buf.c
b/tools
ther benchmark
(that may or may not use a buffer) or if user space amended the buffer
size.
Ensure that accurate buffer size is printed when using "fill_buf"
benchmark and omit the buffer size information if another benchmark
is used.
Fixes: ecdbb911f22d ("selftests/resctrl: Add
ask' was not declared. Should it be static?
Signed-off-by: Reinette Chatre
Reviewed-by: Ilpo Järvinen
---
Changes since v1:
- Add Ilpo's Reviewed-by tag.
- Let subject describe the change, not the tool that found it. (checkpatch.pl)
---
tools/testing/selftests/resctrl/resctrl_val.c | 8
ements on Emerald Rapids, Sapphire Rapids, and Ice Lake
systems. This limit is not applicable to AMD systems since it
only applies to the MBA and MBM tests that are isolated to Intel.
[1]
https://ark.intel.com/content/www/us/en/ark/products/237261/intel-xeon-platinum-8592-processor-320m-cache
Hi Ilpo,
On 9/6/24 1:44 AM, Ilpo Järvinen wrote:
On Thu, 5 Sep 2024, Reinette Chatre wrote:
On 9/5/24 4:45 AM, Ilpo Järvinen wrote:
On Wed, 4 Sep 2024, Reinette Chatre wrote:
On 9/4/24 4:43 AM, Ilpo Järvinen wrote:
On Fri, 30 Aug 2024, Reinette Chatre wrote:
On 8/30/24 4:42 AM, Ilpo
Hi Ilpo,
On 9/6/24 3:00 AM, Ilpo Järvinen wrote:
On Thu, 5 Sep 2024, Reinette Chatre wrote:
On 9/5/24 5:10 AM, Ilpo Järvinen wrote:
On Wed, 4 Sep 2024, Reinette Chatre wrote:
On 9/4/24 4:57 AM, Ilpo Järvinen wrote:
On Fri, 30 Aug 2024, Reinette Chatre wrote:
On 8/30/24 3:56 AM, Ilpo
nst struct
resctrl_test *test)
return false;
return ((ecx >> 3) & 1);
+#endif /* end arch */
+ return false;
}
static int noncont_cat_run_test(const struct resctrl_test *test,
Thank you very much.
Acked-by: Reinette Chatre
Reinette
Hi Shuah,
On 9/5/24 11:06 AM, Shuah Khan wrote:
On 9/4/24 06:54, Ilpo Järvinen wrote:
On Wed, 4 Sep 2024, Shuah Khan wrote:
On 9/4/24 06:18, Ilpo Järvinen wrote:
On Tue, 3 Sep 2024, Shuah Khan wrote:
On 9/3/24 08:45, Ilpo Järvinen wrote:
This series first generalizes resctrl selftest non-
Hi Ilpo,
On 9/5/24 4:45 AM, Ilpo Järvinen wrote:
On Wed, 4 Sep 2024, Reinette Chatre wrote:
On 9/4/24 4:43 AM, Ilpo Järvinen wrote:
On Fri, 30 Aug 2024, Reinette Chatre wrote:
On 8/30/24 4:42 AM, Ilpo Järvinen wrote:
On Thu, 29 Aug 2024, Reinette Chatre wrote:
The MBA test incrementally
Hi Ilpo,
On 9/5/24 5:10 AM, Ilpo Järvinen wrote:
On Wed, 4 Sep 2024, Reinette Chatre wrote:
On 9/4/24 4:57 AM, Ilpo Järvinen wrote:
On Fri, 30 Aug 2024, Reinette Chatre wrote:
On 8/30/24 3:56 AM, Ilpo Järvinen wrote:
On Thu, 29 Aug 2024, Reinette Chatre wrote:
@@ -699,111 +639,80 @@ int
Hi Ilpo,
On 9/4/24 4:43 AM, Ilpo Järvinen wrote:
On Fri, 30 Aug 2024, Reinette Chatre wrote:
On 8/30/24 4:42 AM, Ilpo Järvinen wrote:
On Thu, 29 Aug 2024, Reinette Chatre wrote:
The MBA test incrementally throttles memory bandwidth, each time
followed by a comparison between the memory
Hi Ilpo,
On 9/4/24 4:57 AM, Ilpo Järvinen wrote:
On Fri, 30 Aug 2024, Reinette Chatre wrote:
Thank you for taking a look.
On 8/30/24 3:56 AM, Ilpo Järvinen wrote:
On Thu, 29 Aug 2024, Reinette Chatre wrote:
...
@@ -684,11 +622,13 @@ int resctrl_val(const struct resctrl_test *test
Hi Ilpo,
On 9/3/24 7:45 AM, Ilpo Järvinen wrote:
The x86 selftests makefile clobbers CFLAGS preventing lib.mk from
making the necessary adjustments into CFLAGS. This would lead to a
build failure after upcoming change which wants to add -DHAVE_CPUID=
into CFLAGS.
Reorder CFLAGS initialization i
flags in all error handling
> paths. In other words, the page is marked as reclaimable only in the
> happy path of sgx_encl_eaug_page(). Therefore, in the particular code
> path affected in this commit, the "page reclaimer tracked" condition is
> always false and the warning
x86/kernel/cpu/sgx/ioctl.c
> index b65ab214bdf5..c542d4dd3e64 100644
> --- a/arch/x86/kernel/cpu/sgx/ioctl.c
> +++ b/arch/x86/kernel/cpu/sgx/ioctl.c
> @@ -1142,6 +1142,7 @@ static long sgx_encl_remove_pages(struct sgx_encl *encl,
>* Do not keep encl->lock because of dependency on
>* mmap_lock acquired in sgx_zap_enclave_ptes().
>*/
> + entry->desc |= SGX_ENCL_PAGE_BEING_REMOVED;
> mutex_unlock(&encl->lock);
>
> sgx_zap_enclave_ptes(encl, addr);
Thank you very much for tracking down and fixing this issue.
Acked-by: Reinette Chatre
Reinette
Hi Dmitrii,
Thank you very much for uncovering and fixing this issue.
On 4/30/2024 7:38 AM, Dmitrii Kuvaiskii wrote:
> On Mon, Apr 29, 2024 at 04:11:03PM +0300, Jarkko Sakkinen wrote:
>> On Mon Apr 29, 2024 at 1:43 PM EEST, Dmitrii Kuvaiskii wrote:
>>> Two enclave threads may try to add and remov
ce, and (2) by
>>> replacing sgx_encl_free_epc_page() with sgx_free_epc_page() so that no
>>> EREMOVE is performed.
>>
>> What is the collateral damage caused by ENCLS[EREMOVE]?
>
> As explained above, the damage is that the SGX driver leaves the enclave
Hi Kai,
On 4/23/2024 4:50 AM, Huang, Kai wrote:
>> diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c
>> b/arch/x86/kernel/cpu/sgx/ioctl.c
>> index b65ab214bdf5..2340a82fa796 100644
>> --- a/arch/x86/kernel/cpu/sgx/ioctl.c
>> +++ b/arch/x86/kernel/cpu/sgx/ioctl.c
>> @@ -806,6 +806,9 @@ sgx_enclave_rest
Hi Dave,
On 9/28/2023 5:11 PM, Dave Hansen wrote:
> On 9/28/23 16:08, Reinette Chatre wrote:
>> I'd like to check in on the status of this patch. This two month old
>> patch looks to be a needed fix and has Jarkko and Kai's review tags,
>> but I am not able to fin
86/sgx: Support adding of pages to an initialized
> enclave")
> Cc: sta...@vger.kernel.org # v6.0+
> Signed-off-by: Haitao Huang
> Reviewed-by: Jarkko Sakkinen
> Reviewed-by: Kai Huang
> Acked-by: Reinette Chatre
> ---
> v6:
> - Removed 'Under heavy load&#x
Hi Maciej,
On 9/1/2023 6:42 AM, Wieczor-Retman Maciej wrote:
> Writing bitmasks to the schemata can fail when the bitmask doesn't
> adhere to constraints defined by what a particular CPU supports.
> Some example of constraints are max length or having contiguous bits.
> The driver should properly
Hi James,
On 4/8/2021 10:20 AM, James Morse wrote:
On 31/03/2021 22:36, Reinette Chatre wrote:
On 3/12/2021 9:58 AM, James Morse wrote:
resctrl is the defacto Linux ABI for SoC resource partitioning features.
To support it on another architecture, it needs to be abstracted from
the features
Hi James,
On 4/8/2021 10:20 AM, James Morse wrote:
On 07/04/2021 00:42, Reinette Chatre wrote:
On 4/6/2021 10:13 AM, James Morse wrote:
On 31/03/2021 22:35, Reinette Chatre wrote:
On 3/12/2021 9:58 AM, James Morse wrote:
resctrl is the defacto Linux ABI for SoC resource partitioning
Hi James,
On 4/6/2021 10:13 AM, James Morse wrote:
On 31/03/2021 22:35, Reinette Chatre wrote:
On 3/12/2021 9:58 AM, James Morse wrote:
resctrl is the defacto Linux ABI for SoC resource partitioning features.
To support it on another architecture, it needs to be abstracted from
the features
Hi James,
On 3/12/2021 9:58 AM, James Morse wrote:
struct pseudo_lock_region points to the rdt_resource. Once the
resources are merged, this won't be unique. The resource name
is moving into the scheam, so that eventually resctrl can generate
s/scheam/schema/?
Reinette
Hi James,
On 3/12/2021 9:58 AM, James Morse wrote:
The resctrl_schema struct holds properties that vary with the style of
configuration that resctrl applies to a resource.
There are already two values for the hardware's num_closid, depending on
whether the architecture presents the L3 or L3CODE
Hi James,
On 3/12/2021 9:58 AM, James Morse wrote:
Once the arch code is abstracted from the resctrl filesystem code
the separate schema for CDP are created by the filesystem code. This
means the same resource is used for different schema, or types of
configuration.
Helpers like rdtgroup_cbm_ov
Hi James,
On 3/12/2021 9:58 AM, James Morse wrote:
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h
b/arch/x86/kernel/cpu/resctrl/internal.h
index 8a9da490134b..57484d2f6214 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -361,12 +361,14 @
Hi James,
On 3/12/2021 9:58 AM, James Morse wrote:
To support multiple architectures, the resctrl code needs to be split
into a 'fs' specific part in core code, and an arch-specific backend.
It should be difficult for the arch-specific backends to diverge,
supporting slightly different ABIs for
Hi James,
On 3/12/2021 9:58 AM, James Morse wrote:
resctrl is the defacto Linux ABI for SoC resource partitioning features.
To support it on another architecture, it needs to be abstracted from
the features provided by Intel RDT and AMD PQoS, and moved to /fs/.
Split struct rdt_domain up too. M
Hi James,
A significant time has passed since the first version and with that a
lot of my context lost.
On 3/12/2021 9:58 AM, James Morse wrote:
resctrl is the defacto Linux ABI for SoC resource partitioning features.
To support it on another architecture, it needs to be abstracted from
the f
1 - 100 of 745 matches
Mail list logo
