Commit-Graf
57 Incheckningar
Upphovsman SHA1 Meddelande Datum
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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 b3b6367cb8 Add gfx803 DID
Add 0x67D0 to gfx803 support list.

Change-Id: Ifdb1fad4a3c42bea54856f6d5248c00ed546ad85
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 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 e17c67f049 Implement Start/Stop/Query Trace
StartTrace and StopTrace send ioctl requests to enable/disable performance
counters. QueryTrace reads the counter from the perf_event fd.

Change-Id: Ibf79675bc23fcf129371bfd100f8e262121bc684
2017-03-02 14:00:25 -05:00
Amber Lin 9ba2b68fdb Add gfx900 support
Add gfx900 device to the support

Change-Id: I71f30ef43e5e0ef0e7b5f18205b6cc4767d9d861
2017-02-27 10:39:05 -05:00
Amber Lin 1025579c0b Implement PMC AcquireTrace
Existing code uses lockf to ensure exclusive PMC access of one process and
one TraceId. However Thunk spec allows hsaKmtPmcAcquireTraceAccess to get
exclusive access to the defined set of counters, not exclusive to one
process or one TraceId. Multiple counter sets of multiple TraceIds is
allowed if they meet the concurrent access limit evaluated by the hardware
/driver.

Change-Id: I59cacb855a707fe326a4070452fcbbd3c95ac223
2017-02-27 09:33:58 -05:00
Amber Lin cb60c5f18a Support multiple blocks in RegisterTrace
Existing code assumes all counters sent to hsaKmtPmcRegisterTrace belong
to one PMC block and this block is SQ. This patch considers cases when
counters are in different blocks, and removes the hard-coded SQ. As a
matter of fact, SQ is non-privileged so the user even shouldn't use SQ
counters to register/release trace. This patch also ignores
non-privileged blocks as what HSA Thunk spec describes.

This patch also records counters information in trace structure so
AcquireTrace can get counters information using that TraceId.

Change-Id: Ifa5741050553d4615baab01f7485a9e09435b019
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-02-21 15:32:18 -05:00
Amber Lin 9dadac6dc9 Add IOMMU to performance counter table
Add IOMMUv2 to blocks returned by hsaKmtPmcGetCounterProperties(). IOMMU
information is read from sysfs.

Change-Id: I3a1c6f902f947913570a78700fc0ffc444e1dd72
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-02-03 14:35:27 -05:00
Amber Lin d4dbf562a9 Replace spaces with tabs
Thunk follows Linux kernel coding convention to use tabs instead of
spaces.

Change-Id: I4eddcfa9a0513f16c869d9cc63f9f1dae0c39f83
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-02-03 10:13:24 -05:00
Amber Lin 72b842a6dc Sync up gfx803 DIDs with KFD
Add gfx803 10/11 device IDs that were recently added to KFD.

Change-Id: Id40b117ae47bacedefa6e333fdfdf58dea92cd2d
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
2017-02-01 12:05:24 -05:00
Amber Lin 2a50ebba98 Allow a memory to be registered multiple times
A memory region is allowed to be registered multiple times when the memory
is specified by a user pointer. If it's registered with the same user
pointer but with different sizes, it's treated as different instances and
multiple VM objects are created with different GPU address.


Change-Id: I49627111bb5db36d18f1133b252fb62a611f06a4
2016-11-18 17:46:12 -05:00
Amber Lin 660a6ebbd4 Disable CPU cache info in non-x86
CPU cache information reported by Thunk topology is obtained from cpuid
instruction. This instruction only applies to X86 systems. It can cause
compile errors on non-X86 platforms. This patch temporarily disables CPU
cache functions in topology for non-X86 platforms in order to compile.

Change-Id: If86671817b0d036cb324eebf3f354682bfb75856
2016-09-14 17:30:50 -04:00
Amber Lin 4911c91389 Search VM object by range
Add vm_find_object_by_userptr_range so QueryPointerInfo can find the
object as well when the pointer is not the starting address but it's
inside the memory range. Also rename vm_find_object_xxx functions to
_by_address and _by_address_range to be consistent.

Change-Id: I5c2b3a05b41493e32b7fd9154665bf078b043606
2016-09-13 12:44:29 -04:00
Amber Lin 19f2676ea7 Pointer attributes on APU
Add CPUVM aperture to keep track of memory allocation that is not known
to GPU driver. Together with GPUVM, this patch adds the pointer attributes
support to APU.

Change-Id: If13f9cf01ff8b9f709b99b66661e7505246adf4c
2016-09-12 11:32:26 -04:00
Amber Lin 51e4d27c37 Add pointer attributes API
Add two pointer attributes APIs:
hsaKmtQueryPointerInfo - allow the user to query the memory information
    using a pointer. This pointer can point to any address inside the
    range known to HSA.
hsaKmtSetMemoryUserData - allow the user to attach data to a pointer to
    add memory tracking information. This pointer must match the start
    address of a memory allocation or registration.
TODO: This patch implements support on dGPU. Needs to add APU.

Change-Id: I4711809274248434901f0794f50ebfa13a7371a8
2016-09-07 17:24:46 -04:00
Amber Lin 0b5c65a903 Add performance counters for gfx803
Counter IDs in SQ_PERFCOUNTER0_SELECT are identical on gfx803 10 and
gfx803 11.

Change-Id: I5cfefd44b52989efd1d89311cf8c70c84ea2b230
2016-08-08 18:10:51 -04:00
Amber Lin 876384305b Add gfx803 support
Add gfx803 and gfx80311 device IDs to the support

Change-Id: I16220fd811db102c02e5e0c5b82e40ec299877af
2016-08-08 11:30:57 -04:00
Amber Lin 6c4d19a9d2 Shorten the device list in PerfCounter
get_block_properties uses the complete DID to identify the GPU. This list
is getting too long when more devices are added. Reading the 12 most
significant digits is good enough to identify the GPU.


Change-Id: Ieebb05402bbe08af12eb7289dfeb5bbf1f515b0f
2016-07-27 17:21:31 -04:00
Amber Lin 6d21c4e753 Add performance counters for gfx70x
Add performance counters for gfx70x. The reference is the gfx7 register spec.
The register being looked at is SQ_PERFCOUNTER0_SELECT.

Change-Id: I344bfb7452f6148f4dc268163d12c553c6be8424
2016-05-20 16:24:36 -04:00
Amber Lin 73ad0a1942 Correct NumCaches against the CPU node
In a NUMA system, topology should report NumCaches as the number of caches
within the node but current code reports the total caches in the system. This
patch fixes the error. This patch also uses cpuid to get cache information
instead of reading from sysfs files. See "Intel Corporation, Intel 64 and IA-32
 Architectures Software Developer's  Manual Volume 2(2A, 2B & 2C) Instruction
Set Reference" 3-179 for cpuid instruction features used in this patch.


Change-Id: I8ecece6c2b230741822620b44e66ddc201ff5112
2016-05-03 11:39:33 -04:00
Amber Lin 7416805a44 Revert "Free resources when dlclose is called"
This reverts commit 582b70f9c3.

Conflicts:
	src/fmm.c
	src/perfctr.c

Change-Id: Ib6113c2dd3962c72100c7f74cdef6897e1df40b3
2016-01-22 17:58:33 -05:00
Amber Lin 582b70f9c3 Free resources when dlclose is called
When the Thunk is initialized multiple times in the lifetime of a single process
, some global resources are leaked. This can happen when dlopen and dlclose are
 used to load the library at runtime, rather than linking the runtime against
the Thunk. This patch adds the destructor to release global resources when
dlclose is called.


Change-Id: Ia00da0d41f095d0b2706f98c0e75effedd596f49
2015-12-11 16:32:41 -05:00
Amber Lin a5bc8360e8 Fix sibling map in CPU cache properties
Previous code only works for systems where shared_cpu_map lists 32 or less
bits. Some systems list more than 32 bits and express them as
XXXXXXXX,XXXXXXXX,.... This patch adds that calculation. Also increase
MAX_CPU_CORES and MAX_CACHES to accommodate more advanced systems.

Change-Id: Ia5c7041866456a6aa3b66f8f0f951022d7c51028
2015-11-12 08:31:51 -05:00
Amber Lin b6f65f9849 Add CPU cache information
Fill up cache properties of CPU node by reading data from /proc/cpuinfo
and /sys/devices/system/cpu/cpuX/cache/indexY



Change-Id: I0a96760575e504e38962554f192c3fe66bea3c15
2015-11-09 07:16:24 -05:00
Amber Lin 082f8314c4 Sync up HSA_ENGINE_ID type with Windows/Perforce
HSA_ENGINE_ID in Perforce added ui32 to the typedef while in Git it doesn't.
This causes conflicts to RT applications. Decision being made is to change Git
to match Perforce.

Change-Id: I7e9c6437b023bb23ec9578737f8534e9453589b9
2015-09-24 00:10:52 -04:00
Amber Lin f7fffdc2be Enable GFXIP version info for dGPU
Add GFXIP version 8.0.2(major.minor.stepping) for gfx802 and 8.0.3 for gfx803.


Change-Id: Icc7cac6b2e8a78d9cff4105aeb2bfcd2c7759027
2015-09-22 15:04:43 -04:00
Amber Lin a3925a3a19 Enable version info via thunk interface
- Replace HSAuint32 with HSA_ENGINE_ID for EngineId type so it explicitely
  presents version information for ucode and GfxIP
- Created a GfxIP lookup table to pass the version information. This lookup
  searches for matching device ID.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Acked-by: John Bridgman <John.Bridgman@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
2015-07-31 14:56:33 -04:00