100 Коммитов
Автор SHA1 Сообщение Дата
Amber Lin 31d51acb26 kfdtest: blacklist KFDSVMEvictTest.QueueTest
Temporarily blacklist KFDSVMEvictTest.QueueTest on gfx950

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2025-05-23 01:22:11 -04:00
Amber Lin 9c6828647b kfdtest: blacklist KFDSVMEvictTest.QueueTest
Temporarily blacklist KFDSVMEvictTest.QueueTest on gfx950

Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 31d51acb26]
2025-05-23 01:22:11 -04:00
Amber Lin 5e28208cec kfdtest: Skip SVMEvict with xnack=0
Random driver deadlock on svm_range_evict_svm_bo_worker() is obeserved on
NPS2/DPX mode. It's seen with xnack off and happens more often on the
partition with less VRAM because of TMR.

Temporarily skip SVM Evict tests on Family AV when xnack is disabled.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2025-04-25 12:45:36 -04:00
Amber Lin 9d98d7479d kfdtest: Skip SVMEvict with xnack=0
Random driver deadlock on svm_range_evict_svm_bo_worker() is obeserved on
NPS2/DPX mode. It's seen with xnack off and happens more often on the
partition with less VRAM because of TMR.

Temporarily skip SVM Evict tests on Family AV when xnack is disabled.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 5e28208cec]
2025-04-25 12:45:36 -04:00
Amber Lin bdb6e43b54 Revert "kfdtest: Temporarily blacklist KFDNegativeTest"
This reverts commit fcf3f91379.

MEC v18 starts to support pipe reset
2025-04-21 14:14:10 -04:00
Amber Lin bf3bb1f1a1 Revert "kfdtest: Temporarily blacklist KFDNegativeTest"
This reverts commit fffdffc3ce.

MEC v18 starts to support pipe reset


[ROCm/ROCR-Runtime commit: bdb6e43b54]
2025-04-21 14:14:10 -04:00
Amber Lin fcf3f91379 kfdtest: Temporarily blacklist KFDNegativeTest
Blacklist KFDNegativeTest.BasicPipeReset from gfx950 until MEC can
support pipe reset on GC 9.5.0.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2025-03-10 10:37:19 -07:00
Amber Lin fffdffc3ce kfdtest: Temporarily blacklist KFDNegativeTest
Blacklist KFDNegativeTest.BasicPipeReset from gfx950 until MEC can
support pipe reset on GC 9.5.0.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: fcf3f91379]
2025-03-10 10:37:19 -07:00
Amber Lin 0b6e457201 kfdtest: Create gfx950 blacklist
This patch creates the blacklist for gfx950 by copying gfx942 but adding
KFDGWSTest.Semaphore as GWS support is completely removed from gfx950.

Change-Id: I5d7c17e57b8cfd9fae63780ecc9dd55662cfdade
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2025-01-28 08:26:44 -05:00
Amber Lin e262729f6f kfdtest: Create gfx950 blacklist
This patch creates the blacklist for gfx950 by copying gfx942 but adding
KFDGWSTest.Semaphore as GWS support is completely removed from gfx950.

Change-Id: I5d7c17e57b8cfd9fae63780ecc9dd55662cfdade
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 0b6e457201]
2025-01-28 08:26:44 -05:00
Amber Lin e342c9c890 kfdtest: Temporarily blacklist some tests
Temporarily blacklist some tests on gfx90a until they are solved.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Change-Id: I87cc3a996ea7d55ed8f20f5b4eecfd8bb691effd
2021-02-23 12:20:29 -05:00
Amber Lin ccc62ccf8b kfdtest: Temporarily blacklist some tests
Temporarily blacklist some tests on gfx90a until they are solved.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Change-Id: I87cc3a996ea7d55ed8f20f5b4eecfd8bb691effd


[ROCm/ROCR-Runtime commit: e342c9c890]
2021-02-23 12:20:29 -05:00
Amber Lin 8c6dd3cbae libhsakmt: Add device ID used in Simnow
Simnow simulator uses 0x7400 as gfx90a's device ID

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Change-Id: I0022509ef643760bc906e537b4fc64f1523fd8bf
2021-02-23 12:20:29 -05:00
Amber Lin 8d96c2c71f libhsakmt: Add device ID used in Simnow
Simnow simulator uses 0x7400 as gfx90a's device ID

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Change-Id: I0022509ef643760bc906e537b4fc64f1523fd8bf


[ROCm/ROCR-Runtime commit: 8c6dd3cbae]
2021-02-23 12:20:29 -05:00
Amber Lin 9f72c8c08f OAM: Add get dev and pci properties and sensor count
Also, add amdoam_get_error_description.

On behalf of
Amber Lin <Amber.Lin@amd.com> and
Divya Shikre <DivyaUday.Shikre@amd.com>

Change-Id: I1f5ac0c5948adb2c30008e95c501e8b69b8183b6


[ROCm/rocm_smi_lib commit: 27deaea6e8]
2020-06-23 17:21:07 -05:00
Amber Lin 27deaea6e8 OAM: Add get dev and pci properties and sensor count
Also, add amdoam_get_error_description.

On behalf of
Amber Lin <Amber.Lin@amd.com> and
Divya Shikre <DivyaUday.Shikre@amd.com>

Change-Id: I1f5ac0c5948adb2c30008e95c501e8b69b8183b6
2020-06-23 17:21:07 -05:00
Amber Lin 328aa330b2 OAM: Add get dev and pci properties and sensor count
Also, add amdoam_get_error_description.

On behalf of
Amber Lin <Amber.Lin@amd.com> and
Divya Shikre <DivyaUday.Shikre@amd.com>

Change-Id: I1f5ac0c5948adb2c30008e95c501e8b69b8183b6


[ROCm/amdsmi commit: 27deaea6e8]
2020-06-23 17:21:07 -05:00
Amber Lin a37a88ddcb libhsakmt: Sync up the ioctl number
Update the non-upstream ioctl numbers to align with the change in the
kernel.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Change-Id: Ie0ddccb343a023b55eb18477c59341acaa666e99
2020-05-12 15:06:07 -04:00
Amber Lin 2aa89d8bf4 libhsakmt: Sync up the ioctl number
Update the non-upstream ioctl numbers to align with the change in the
kernel.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Change-Id: Ie0ddccb343a023b55eb18477c59341acaa666e99


[ROCm/ROCR-Runtime commit: a37a88ddcb]
2020-05-12 15:06:07 -04:00
Amber Lin 894ca737bc Allow specifying rsmi-lib install path
Instead of hard-coding install path to /opt/rocm, allow users to specify
where "make install" goes to so users can install lib to their local build
path for testing purpose without touching global /opt/rocm files.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Change-Id: I4144988e325edae4d1d1a2824e031996091036d3


[ROCm/rocm_smi_lib commit: 741f9c31ff]
2020-05-06 18:08:22 -04:00
Amber Lin 741f9c31ff Allow specifying rsmi-lib install path
Instead of hard-coding install path to /opt/rocm, allow users to specify
where "make install" goes to so users can install lib to their local build
path for testing purpose without touching global /opt/rocm files.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Change-Id: I4144988e325edae4d1d1a2824e031996091036d3
2020-05-06 18:08:22 -04:00
Amber Lin 264b0ea526 Allow specifying rsmi-lib install path
Instead of hard-coding install path to /opt/rocm, allow users to specify
where "make install" goes to so users can install lib to their local build
path for testing purpose without touching global /opt/rocm files.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Change-Id: I4144988e325edae4d1d1a2824e031996091036d3


[ROCm/amdsmi commit: 741f9c31ff]
2020-05-06 18:08:22 -04:00
Amber Lin 23541e0289 libhsakmt: handle CPU cache info on non-NUMA sys
When CONFIG_NUMA is not enabled in the kernel config, only one CPU node
presents on the system and /sys/devices/system/node/nodeX directories
don't exist. Read CPU cache information from /sys/devices/system/cpu in
this situation.

Change-Id: I017ff17dd72678a0551edcc77446664501aa42ca
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2019-10-17 11:53:19 -04:00
Amber Lin 211742a1f7 libhsakmt: handle CPU cache info on non-NUMA sys
When CONFIG_NUMA is not enabled in the kernel config, only one CPU node
presents on the system and /sys/devices/system/node/nodeX directories
don't exist. Read CPU cache information from /sys/devices/system/cpu in
this situation.

Change-Id: I017ff17dd72678a0551edcc77446664501aa42ca
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 23541e0289]
2019-10-17 11:53:19 -04:00
Amber Lin 5a09880620 libhsakmt: fix typo in error message
When fail to get CPU dirs from //sys/devices/system/node/nodeX directory,
the error message should print node_dir, not path.

Change-Id: If76a51918c8dd55fa6605a62f3d29f9efc6fadb3
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2019-09-30 14:29:39 -04:00
Amber Lin 637bbb5c9c libhsakmt: fix typo in error message
When fail to get CPU dirs from //sys/devices/system/node/nodeX directory,
the error message should print node_dir, not path.

Change-Id: If76a51918c8dd55fa6605a62f3d29f9efc6fadb3
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 5a09880620]
2019-09-30 14:29:39 -04:00
Amber Lin 4fa930af5a libhsakmt: get cpu cache info from sysfs
Replace cpuid call with sysfs data to get CPU cache information. With this
change, x86 check is also removed since sysfs applies to other platforms.
CPU cache information can be retrieved from
/sys/devices/system/node/nodeX/cpuY/cache where Y is processor number
represented in /proc/cpuinfo at "processor" entry.

Change-Id: Ic47df6d5dafaf1aae5b46b1fdee42691c697e49e
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2019-08-26 14:52:01 -04:00
Amber Lin 98604d9885 libhsakmt: get cpu cache info from sysfs
Replace cpuid call with sysfs data to get CPU cache information. With this
change, x86 check is also removed since sysfs applies to other platforms.
CPU cache information can be retrieved from
/sys/devices/system/node/nodeX/cpuY/cache where Y is processor number
represented in /proc/cpuinfo at "processor" entry.

Change-Id: Ic47df6d5dafaf1aae5b46b1fdee42691c697e49e
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 4fa930af5a]
2019-08-26 14:52:01 -04:00
Amber Lin 1fddfd316a libhsakmt: reduce /proc/cpuinfo opens
/proc/cpuinfo are opened, read, and closed multiple times. Once for vendor
name and multiple times for model name -- each node opens once. For example
in a 2 CPUs + 4 GPUs system, it'll be opened 7 times. This patch reads it
one time and stores it in a cpuinfo buffer. This cpuinfo buffer is freed
when the snapshot is done.

Also replace returns with gotos inside the snapshot to avoid possible
memory leak.

Change-Id: Iaf26a6c7e7323a8651d137c3706179449b9e3c80
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2019-08-15 12:37:26 -04:00
Amber Lin e34fe6caaf libhsakmt: reduce /proc/cpuinfo opens
/proc/cpuinfo are opened, read, and closed multiple times. Once for vendor
name and multiple times for model name -- each node opens once. For example
in a 2 CPUs + 4 GPUs system, it'll be opened 7 times. This patch reads it
one time and stores it in a cpuinfo buffer. This cpuinfo buffer is freed
when the snapshot is done.

Also replace returns with gotos inside the snapshot to avoid possible
memory leak.

Change-Id: Iaf26a6c7e7323a8651d137c3706179449b9e3c80
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 1fddfd316a]
2019-08-15 12:37:26 -04:00
Amber Lin cfa47ac1f9 libhsakmt: Fix missing apicid in topology
While adding x2APIC support, apicid for non-x2apic was missing out by
mistake.



Change-Id: I25eed362c035c0e9fb9ea948899c49f70311f269
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2019-03-11 13:05:37 -04:00
Amber Lin f8028a40fd libhsakmt: Support x2APIC in topology
Current processor/cache topology code implements xAPIC architecture, which
is 8 bits addressability. This is not enough for a system having more than
255 processors. x2APIC is the extension of xAPIC architecture to support
32 bit addressability of processors. This patch detects the x2APIC
enablement and uses the extension leaf to get apicid when detected.

Change-Id: I0826585d02f696a46cd5efb9a6630c60af01e2d8
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2019-03-01 16:42:30 -05:00
Amber Lin bc0bc878f4 libhsakmt: Fix missing apicid in topology
While adding x2APIC support, apicid for non-x2apic was missing out by
mistake.



Change-Id: I25eed362c035c0e9fb9ea948899c49f70311f269
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: cfa47ac1f9]
2019-03-11 13:05:37 -04:00
Amber Lin ee54c2ec5a libhsakmt: Support x2APIC in topology
Current processor/cache topology code implements xAPIC architecture, which
is 8 bits addressability. This is not enough for a system having more than
255 processors. x2APIC is the extension of xAPIC architecture to support
32 bit addressability of processors. This patch detects the x2APIC
enablement and uses the extension leaf to get apicid when detected.

Change-Id: I0826585d02f696a46cd5efb9a6630c60af01e2d8
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: f8028a40fd]
2019-03-01 16:42:30 -05:00
Amber Lin 7031a77428 Update README to reflect cmake change
New CMakeLists.txt sets a default module search so -DCMAKE_MODULE_PATH is
no longer required in the command.

Change-Id: I95189ce2f36016b7c4929239d0e512851bec5ef6
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2018-01-04 15:55:20 -05:00
Amber Lin 83bbc28ad9 Update README to reflect cmake change
New CMakeLists.txt sets a default module search so -DCMAKE_MODULE_PATH is
no longer required in the command.

Change-Id: I95189ce2f36016b7c4929239d0e512851bec5ef6
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 7031a77428]
2018-01-04 15:55:20 -05:00
Amber Lin 8bc83e1e9b Update README to include new requirement
Latest Thunk requires the user to belong to video group. Add this
statement to README.md to notify external users on Github.

Change-Id: Id9843abf09de5b63a3b7c3f7b322bc9099c6ff1a
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-12-18 12:10:24 -05:00
Amber Lin 91ee9033f1 Update README to include new requirement
Latest Thunk requires the user to belong to video group. Add this
statement to README.md to notify external users on Github.

Change-Id: Id9843abf09de5b63a3b7c3f7b322bc9099c6ff1a
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 8bc83e1e9b]
2017-12-18 12:10:24 -05:00
Amber Lin 6f7b55f2d8 Add debug message in PMC trace
Print data in PMC trace when the debug level is set to 7(pr_debug).

Change-Id: I9abbb8f6c3f7962fb637528578c1a58b7784042d
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-11-22 10:09:49 -05:00
Amber Lin b3439f48c2 Add debug message in PMC trace
Print data in PMC trace when the debug level is set to 7(pr_debug).

Change-Id: I9abbb8f6c3f7962fb637528578c1a58b7784042d
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 6f7b55f2d8]
2017-11-22 10:09:49 -05:00
Amber Lin 61d1c6ffac Correct command in make package
cmake command in making packages was not updated.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>

Change-Id: Iafd3d9f4941d782bd77cfd0efafe48a02221b002
2017-11-20 10:28:25 -05:00
Amber Lin d2467747f1 Correct command in make package
cmake command in making packages was not updated.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>

Change-Id: Iafd3d9f4941d782bd77cfd0efafe48a02221b002


[ROCm/ROCR-Runtime commit: 61d1c6ffac]
2017-11-20 10:28:25 -05:00
Amber Lin 310e3d7b8b Use absolute path on cmake parameter
Update build instructions in README.md to use absolute path on cmake
parameter, CMAKE_MODULE_PATH. Relative path causes build error. Tested
on cmake 3.5.1 ans cmake 3.5.2.

Change-Id: I1b8e8deb9f4941580580be8087a94655ae155d02
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-11-02 17:34:46 -04:00
Amber Lin 6ba2a9b764 Use absolute path on cmake parameter
Update build instructions in README.md to use absolute path on cmake
parameter, CMAKE_MODULE_PATH. Relative path causes build error. Tested
on cmake 3.5.1 ans cmake 3.5.2.

Change-Id: I1b8e8deb9f4941580580be8087a94655ae155d02
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 310e3d7b8b]
2017-11-02 17:34:46 -04:00
Amber Lin 5815d9de9b Fix endless loop
Fix a while loop that can cause forever loop when cpuid instruction
doesn't work properly.

Change-Id: Iefa49d23b40c994eb4369621974a7d3c4067e47a
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-10-12 14:22:42 -04:00
Amber Lin a6fc0a8be1 Fix endless loop
Fix a while loop that can cause forever loop when cpuid instruction
doesn't work properly.

Change-Id: Iefa49d23b40c994eb4369621974a7d3c4067e47a
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 5815d9de9b]
2017-10-12 14:22:42 -04:00
Amber Lin 117fa5034b Fix PmcGetCounterProperties
Blocks inside of HsaCounterProperties structure is not a fixed size. It
varies with number of counters in the block -- size of Counters in
HsaCounterBlockProperties is different in every block. Current
implementation assumes fixed size and the next block will overwrite the
previous block's Counters. This patch change the array implementation to
using a pointer so it'll move the next block to the correction position.

Change-Id: I72800f4db5f2a68215fba477a61ca07ec99054bf
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-09-01 17:58:15 -04:00
Amber Lin 784e3dc3c6 Fix PmcGetCounterProperties
Blocks inside of HsaCounterProperties structure is not a fixed size. It
varies with number of counters in the block -- size of Counters in
HsaCounterBlockProperties is different in every block. Current
implementation assumes fixed size and the next block will overwrite the
previous block's Counters. This patch change the array implementation to
using a pointer so it'll move the next block to the correction position.

Change-Id: I72800f4db5f2a68215fba477a61ca07ec99054bf
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 117fa5034b]
2017-09-01 17:58:15 -04:00
Amber Lin a74f6896ea Revert "Set guard page as disabled as default"
This reverts commit 65d680c035.

Change-Id: I09b7e7915ec4759cab57d5863089a2c4a44dfacd
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-08-30 10:48:23 -04:00
Amber Lin 2506a31248 Revert "Set guard page as disabled as default"
This reverts commit 4d839c4dc6.

Change-Id: I09b7e7915ec4759cab57d5863089a2c4a44dfacd
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: a74f6896ea]
2017-08-30 10:48:23 -04:00
Amber Lin a81b29890c Fix mmap when the count reaches the max
Applications may try to allocate lots host memory and reaches the mmap
limit (/proc/sys/vm/max_map_count). When Applications fails to allocate
memory and calls hsaKmtFreeMemory to release the memory, Thunk fails to
reduce the maps count so the following hsaKmtAllocMemory calls continue
to fail, which doesn't make sense to the application. This patch checks
the mmap to NORESERVE return value. If it fails and the error number is
ENOMEM, reduce the map count by munmap and map it again immediately.



Change-Id: I127cb479dfd86b199172eef269d59426f23859ea
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-08-29 11:47:29 -04:00
Amber Lin 13282b9115 Fix mmap when the count reaches the max
Applications may try to allocate lots host memory and reaches the mmap
limit (/proc/sys/vm/max_map_count). When Applications fails to allocate
memory and calls hsaKmtFreeMemory to release the memory, Thunk fails to
reduce the maps count so the following hsaKmtAllocMemory calls continue
to fail, which doesn't make sense to the application. This patch checks
the mmap to NORESERVE return value. If it fails and the error number is
ENOMEM, reduce the map count by munmap and map it again immediately.



Change-Id: I127cb479dfd86b199172eef269d59426f23859ea
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: a81b29890c]
2017-08-29 11:47:29 -04:00
Amber Lin 65d680c035 Set guard page as disabled as default
Due to max_mmap_count issue, set default of guard page as disabled.


Change-Id: Ic9dfe69b621733e9fac86831b008a122994a67e7
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-08-24 16:27:52 -04:00
Amber Lin 4d839c4dc6 Set guard page as disabled as default
Due to max_mmap_count issue, set default of guard page as disabled.


Change-Id: Ic9dfe69b621733e9fac86831b008a122994a67e7
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 65d680c035]
2017-08-24 16:27:52 -04:00
Amber Lin 369902bf5b IOMMU path in sysfs is renamed
IOMMU path in sysfs was amd_iommu. After implementing multiple devices
support, the path is replaced with amd_iommu_<index>. Current Thunk spec
is not clear about how to support multiple instances in one block. There
is no products having multiple IOMMUs yet at this point. This patch
changes the path to support both amd_iommu and amd_iommu_0 for Carizo.

Change-Id: I3beea2fc78d96296232226191501a02ccf20d6b1
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-08-23 14:00:49 -04:00
Amber Lin 9ab8250fbc IOMMU path in sysfs is renamed
IOMMU path in sysfs was amd_iommu. After implementing multiple devices
support, the path is replaced with amd_iommu_<index>. Current Thunk spec
is not clear about how to support multiple instances in one block. There
is no products having multiple IOMMUs yet at this point. This patch
changes the path to support both amd_iommu and amd_iommu_0 for Carizo.

Change-Id: I3beea2fc78d96296232226191501a02ccf20d6b1
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 369902bf5b]
2017-08-23 14:00:49 -04:00
Amber Lin 73707766ef Add debugging message on memory
Add pr_debug to all memory APIs and pr_err to some failure cases.

Change-Id: I8b519a1228cc19e6c04118fd87432e7f48f3cbf9
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-08-22 09:55:20 -04:00
Amber Lin a885ad3724 Add debugging message on memory
Add pr_debug to all memory APIs and pr_err to some failure cases.

Change-Id: I8b519a1228cc19e6c04118fd87432e7f48f3cbf9
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 73707766ef]
2017-08-22 09:55:20 -04:00
Amber Lin f1a5248cf2 Simplify memory maps
Simplify fmm_map_to_gpu_nodes code. Also fix a memory leak in this change.

Change-Id: I3487338b78c915de44588d0206bac4c53e728c60
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-08-15 17:34:30 -04:00
Amber Lin 951796c73d Simplify memory maps
Simplify fmm_map_to_gpu_nodes code. Also fix a memory leak in this change.

Change-Id: I3487338b78c915de44588d0206bac4c53e728c60
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: f1a5248cf2]
2017-08-15 17:34:30 -04:00
Amber Lin e46743b1dd Workaround cpuid issue under Valgrind
Topology uses cpuid to get CPU cache information. However when running
under Valgrind, data returned from cpuid are not from the processor we set
affinity to. Instead they are all from one specific processor. For a quick
workaround so other teams can continue their work, this patch will report
CPU cache from that specific processor and ignore others.

Change-Id: I5cfac2329dac277f3dbde1be92fa26e085465401
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-07-24 12:04:17 -04:00
Amber Lin 391d9ee403 Workaround cpuid issue under Valgrind
Topology uses cpuid to get CPU cache information. However when running
under Valgrind, data returned from cpuid are not from the processor we set
affinity to. Instead they are all from one specific processor. For a quick
workaround so other teams can continue their work, this patch will report
CPU cache from that specific processor and ignore others.

Change-Id: I5cfac2329dac277f3dbde1be92fa26e085465401
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: e46743b1dd]
2017-07-24 12:04:17 -04:00
Amber Lin ac468f676c Replace lock file with shared memory
Performance counters have limited slots for concurrent profiling. We
need a mechanism to synchronize the slots access across different
processes. Lock file file was first used for this access control. It
reveals a RedHat bug that /var/lock, symbolic linked to /run/lock, is
not writable by others. To avoid this bug and to simplify the code,
POSIX shared memory is created to replace the lock file usage. Access
of the shared memory is controlled by semaphores.

Change-Id: I1e13c17f0e042fdfe6657afe8b3c88db7e84d292
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-07-06 13:48:34 -04:00
Amber Lin 5cb0798d6a Replace lock file with shared memory
Performance counters have limited slots for concurrent profiling. We
need a mechanism to synchronize the slots access across different
processes. Lock file file was first used for this access control. It
reveals a RedHat bug that /var/lock, symbolic linked to /run/lock, is
not writable by others. To avoid this bug and to simplify the code,
POSIX shared memory is created to replace the lock file usage. Access
of the shared memory is controlled by semaphores.

Change-Id: I1e13c17f0e042fdfe6657afe8b3c88db7e84d292
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: ac468f676c]
2017-07-06 13:48:34 -04:00
Amber Lin 897c4e2fff Replace printf/fprintf with pr_xxx
Libraries normally don't print messages. We use pr_err, pr_warn,
pr_info, and pr_debug to print messages to stderr when prints are
enabled for debugging.

Change-Id: I9caf719343aa618c88e7b500f9737a46702e424a
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-06-28 10:47:35 -04:00
Amber Lin 75c3086af9 Replace printf/fprintf with pr_xxx
Libraries normally don't print messages. We use pr_err, pr_warn,
pr_info, and pr_debug to print messages to stderr when prints are
enabled for debugging.

Change-Id: I9caf719343aa618c88e7b500f9737a46702e424a
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 897c4e2fff]
2017-06-28 10:47:35 -04:00
Amber Lin ccfe739929 Introduce debug level to Thunk
Existing Thunk has printf/fprintf in the code while normally libraries
don't print any message. This patch introduces a print machenism similar to
how the Linux kernel prints to console based on the log level. The default
is not to print any message, but setting HSAKMT_DEBUG_LEVEL will enable the
prints.

Change-Id: Ic071e122d35a82260218e9914cde4815e69df742
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-06-26 16:33:17 -04:00
Amber Lin 29124d3af3 Introduce debug level to Thunk
Existing Thunk has printf/fprintf in the code while normally libraries
don't print any message. This patch introduces a print machenism similar to
how the Linux kernel prints to console based on the log level. The default
is not to print any message, but setting HSAKMT_DEBUG_LEVEL will enable the
prints.

Change-Id: Ic071e122d35a82260218e9914cde4815e69df742
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: ccfe739929]
2017-06-26 16:33:17 -04:00
Amber Lin 13aadde56e Use environment variable to force gfx version
For experimental purpose, we need an option to change compute capability
by forcing the GfxIp version. This patch allows to use environment
variable HSA_OVERRIDE_GFX_VERSION=major.minor.stepping to replace the
default version. For example:
export HSA_OVERRIDE_GFX_VERSION=9.0.1

Change-Id: I90cfbd43619d9d3aebf53321d4e058f01bcd7088
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-06-22 18:15:17 -04:00
Amber Lin 29f0578061 Use environment variable to force gfx version
For experimental purpose, we need an option to change compute capability
by forcing the GfxIp version. This patch allows to use environment
variable HSA_OVERRIDE_GFX_VERSION=major.minor.stepping to replace the
default version. For example:
export HSA_OVERRIDE_GFX_VERSION=9.0.1

Change-Id: I90cfbd43619d9d3aebf53321d4e058f01bcd7088
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 13aadde56e]
2017-06-22 18:15:17 -04:00
Amber Lin 6e113e2634 Free control stack correctly
ctl_stack_copy is allocated from malloc. It should be freed by free.

Change-Id: Ib924da20200d91f52f106fe173464d47862759a8
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-06-19 09:01:35 -04:00
Amber Lin 79eaea7358 Free control stack correctly
ctl_stack_copy is allocated from malloc. It should be freed by free.

Change-Id: Ib924da20200d91f52f106fe173464d47862759a8
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 6e113e2634]
2017-06-19 09:01:35 -04:00
Amber Lin 5114a9368b Change gfx900 compute capability to 9.0.1
9.0.1 is XNACK enabled gfx900 compile target. Compiler must generate ISA
that's XNACK enabled.



Change-Id: Ic4987132ef9f8d06d9e2bcdb8f7eeb875cdd2b44
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-06-13 17:04:42 -04:00
Amber Lin 35dcb1c392 Change gfx900 compute capability to 9.0.1
9.0.1 is XNACK enabled gfx900 compile target. Compiler must generate ISA
that's XNACK enabled.



Change-Id: Ic4987132ef9f8d06d9e2bcdb8f7eeb875cdd2b44
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 5114a9368b]
2017-06-13 17:04:42 -04:00
Amber Lin ceaaa1a57c A missing block in PMC
DB block was missing in the UUID look-up.

Change-Id: Ife5c25859bab6ec7fd99d0cd4d098ab044a08142
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-06-05 12:21:56 -04:00
Amber Lin b354927222 A missing block in PMC
DB block was missing in the UUID look-up.

Change-Id: Ife5c25859bab6ec7fd99d0cd4d098ab044a08142
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: ceaaa1a57c]
2017-06-05 12:21:56 -04:00
Amber Lin 683fc96325 Implement hsaKmtGetQueueInfo interface
For items in HsaQueueInfo, control stack information comes from KFD, CU
mask information is maintained in Thunk, and others (queue detail error
and queue type extended) are ignored (value = 0) at this point.

Change-Id: Ib21370b0f52b2bb4ebe6a9b4b6ec6139cccb25ca
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-06-01 14:15:54 -04:00
Amber Lin dd782c86c0 Implement hsaKmtGetQueueInfo interface
For items in HsaQueueInfo, control stack information comes from KFD, CU
mask information is maintained in Thunk, and others (queue detail error
and queue type extended) are ignored (value = 0) at this point.

Change-Id: Ib21370b0f52b2bb4ebe6a9b4b6ec6139cccb25ca
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 683fc96325]
2017-06-01 14:15:54 -04:00
Amber Lin ca06b0966b Add more non-priv PMC blocks to GFX9
This patch adds more non-privileged PMC blocks to GFX9/gfx900 to cover
blocks added in HSA Thunk Spec.

Change-Id: Ia3d953213a32536b2275231149f11ba060791442
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-05-01 09:14:03 -04:00
Amber Lin 0d55f4a1f7 Add more non-priv PMC blocks to GFX9
This patch adds more non-privileged PMC blocks to GFX9/gfx900 to cover
blocks added in HSA Thunk Spec.

Change-Id: Ia3d953213a32536b2275231149f11ba060791442
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: ca06b0966b]
2017-05-01 09:14:03 -04:00
Amber Lin ed4a22e0d3 Add more non-priv PMC blocks to GFX8
This patch adds more non-privileged PMC blocks to GFX8 products: gfx801,
gfx803, and gfx803. Most of them have the same counter IDs on the same
block. For certain blocks when the product doesn't have the same counter
IDs, gfx8_xx_ is used to represent the product.

Change-Id: I059913c974bf2eb875fd1cf6f8b0d8c9c9bd7c14
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-04-27 11:22:12 -04:00
Amber Lin d4a47bae3e Add more non-priv PMC blocks to GFX8
This patch adds more non-privileged PMC blocks to GFX8 products: gfx801,
gfx803, and gfx803. Most of them have the same counter IDs on the same
block. For certain blocks when the product doesn't have the same counter
IDs, gfx8_xx_ is used to represent the product.

Change-Id: I059913c974bf2eb875fd1cf6f8b0d8c9c9bd7c14
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: ed4a22e0d3]
2017-04-27 11:22:12 -04:00
Amber Lin 9f19acbdb7 Add more non-priv PMC blocks to gfx70x/GFX7
HSA Thunk Spec was updated to include more non-privileged blocks for
profiling. This patch adds those newly added non-privileged blocks for
gfx70x.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>

Change-Id: Id745ac236c871e8e61a128a2460784f9c9c354b6
2017-04-25 13:08:10 -04:00
Amber Lin edd6771ef1 Add more non-priv PMC blocks to gfx70x/GFX7
HSA Thunk Spec was updated to include more non-privileged blocks for
profiling. This patch adds those newly added non-privileged blocks for
gfx70x.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>

Change-Id: Id745ac236c871e8e61a128a2460784f9c9c354b6


[ROCm/ROCR-Runtime commit: 9f19acbdb7]
2017-04-25 13:08:10 -04:00
Amber Lin c119653add Create indirect IO links
KFD added all direct IO links to sysfs, so this patch removes all direct
links related code and modify the indirect links function to reflect the
change.

Change-Id: Iaec7b5f6c59f9034f8f960ca1fe1145d51dab367
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-04-07 07:18:13 -04:00
Amber Lin 426aad482c Create indirect IO links
KFD added all direct IO links to sysfs, so this patch removes all direct
links related code and modify the indirect links function to reflect the
change.

Change-Id: Iaec7b5f6c59f9034f8f960ca1fe1145d51dab367
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: c119653add]
2017-04-07 07:18:13 -04:00
Amber Lin 73eff30d7d Add TCA block to PMC support
Add TCA to PMC tables.

Change-Id: Ia4164ab4581ea3f539706f534f672e5c24f5362f
2017-03-20 10:22:21 -04:00
Amber Lin 65f40a36cf Add TCA block to PMC support
Add TCA to PMC tables.

Change-Id: Ia4164ab4581ea3f539706f534f672e5c24f5362f


[ROCm/ROCR-Runtime commit: 73eff30d7d]
2017-03-20 10:22:21 -04:00
Amber Lin 3738a1b5f2 Re-formatting IO link code
- Typo fix: *_link_tye to *_link_type and a missing word in comments
- Replace printf with fprintf(stderr
- Shorten lines to fit in 80 characters

Change-Id: Ibeb0b98d5c59d617ae06d9854a9dde16251ded52
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-03-09 11:08:22 -05:00
Amber Lin cddc3c032f Re-formatting IO link code
- Typo fix: *_link_tye to *_link_type and a missing word in comments
- Replace printf with fprintf(stderr
- Shorten lines to fit in 80 characters

Change-Id: Ibeb0b98d5c59d617ae06d9854a9dde16251ded52
Signed-off-by: Amber Lin <Amber.Lin@amd.com>


[ROCm/ROCR-Runtime commit: 3738a1b5f2]
2017-03-09 11:08:22 -05:00
Amber Lin 2c2b1e0db2 Support profiling on gfx900
Add gfx900 to PMC support. This patch lists SQ counters.

Change-Id: Ia1e60e76ff71ab2e38d9d5de12ac9d527b3e8c6a
2017-03-07 14:30:40 -05:00
Amber Lin 68315e3157 Support profiling on gfx900
Add gfx900 to PMC support. This patch lists SQ counters.

Change-Id: Ia1e60e76ff71ab2e38d9d5de12ac9d527b3e8c6a


[ROCm/ROCR-Runtime commit: 2c2b1e0db2]
2017-03-07 14:30:40 -05:00
Amber Lin 9e32cdb113 Don't duplicate PMC tables
Many devices have the same counter IDs for the hardware block. Devices
in the same GFX generation usually have the same block counters. No need
to list each device individually. Instead, have a table to share with all
devices that have the same counter IDs, and have separated tables for
devices that don't have the same counter IDs.

Change-Id: I857056edc6f491f61af6e9598580e5dc7d372f94
2017-03-07 11:31:23 -05:00
Amber Lin ad5c8c4844 Don't duplicate PMC tables
Many devices have the same counter IDs for the hardware block. Devices
in the same GFX generation usually have the same block counters. No need
to list each device individually. Instead, have a table to share with all
devices that have the same counter IDs, and have separated tables for
devices that don't have the same counter IDs.

Change-Id: I857056edc6f491f61af6e9598580e5dc7d372f94


[ROCm/ROCR-Runtime commit: 9e32cdb113]
2017-03-07 11:31:23 -05:00
Amber Lin b3b6367cb8 Add gfx803 DID
Add 0x67D0 to gfx803 support list.

Change-Id: Ifdb1fad4a3c42bea54856f6d5248c00ed546ad85
2017-03-07 07:25:49 -05:00
Amber Lin 0b074112f2 Add gfx803 DID
Add 0x67D0 to gfx803 support list.

Change-Id: Ifdb1fad4a3c42bea54856f6d5248c00ed546ad85


[ROCm/ROCR-Runtime commit: b3b6367cb8]
2017-03-07 07:25:49 -05:00
Amber Lin 4827b09119 Unify the device ID list
Integrate the supported device ID list distributed in topology, queue, and
pmc into one place: topology.

Change-Id: If035cf8e4a6fc6caff6c94ec627647cfb11c3d79
2017-03-06 16:26:51 -05:00
Amber Lin 4ddf99f4a9 Unify the device ID list
Integrate the supported device ID list distributed in topology, queue, and
pmc into one place: topology.

Change-Id: If035cf8e4a6fc6caff6c94ec627647cfb11c3d79


[ROCm/ROCR-Runtime commit: 4827b09119]
2017-03-06 16:26:51 -05:00
Amber Lin 1a8a9cb57b Make the lock file writable by others
Though S_IWOTH flag is set in the open() call, the lock file is not
created as accessable by others if others try to open the file with O_RDWR
permission. It's because the default umask masks off S_IWOTH. This patch
changes the umask to S_IXOTH since others don't need that permission but
it'll open up S_IWOTH. Restore the umask to original after the file is
opened.

Change-Id: I8a239e1566ce0b0b18821913385f239db7c3588e
2017-03-03 11:05:13 -05:00
Amber Lin 9b6439a5bb Make the lock file writable by others
Though S_IWOTH flag is set in the open() call, the lock file is not
created as accessable by others if others try to open the file with O_RDWR
permission. It's because the default umask masks off S_IWOTH. This patch
changes the umask to S_IXOTH since others don't need that permission but
it'll open up S_IWOTH. Restore the umask to original after the file is
opened.

Change-Id: I8a239e1566ce0b0b18821913385f239db7c3588e


[ROCm/ROCR-Runtime commit: 1a8a9cb57b]
2017-03-03 11:05:13 -05:00