Age | Commit message (Collapse) | Author |
|
Bug: 313458962
Test: gfxbench
Signed-off-by: Jack Diver <diverj@google.com>
(cherry picked from https://partner-android-review.googlesource.com/q/commit:3d3cde1cabde47ebb37db73b5e99a238e29b6762)
Merged-In: Ifd1f9946b2a3c78c412986c57e499b9bd2ef4b3c
Change-Id: Ifd1f9946b2a3c78c412986c57e499b9bd2ef4b3c
|
|
Bug: 321199350
Test: gfxbench
Signed-off-by: Jack Diver <diverj@google.com>
(cherry picked from https://partner-android-review.googlesource.com/q/commit:57ef78bad803aab9d83325f80349f33727af9af8)
Merged-In: I94ff92333cae9b9c54f27af550777fc21da06cb7
Change-Id: I94ff92333cae9b9c54f27af550777fc21da06cb7
|
|
Use ACPM GPU signal to make enable/disable decisions for the SLC
partition.
Currently, the signal is sampled during scheduling tick.
Bug: 313458962
Test: gfxbench
Signed-off-by: Jack Diver <diverj@google.com>
(cherry picked from https://partner-android-review.googlesource.com/q/commit:dec457352147d282921e0ae81ce3a7154e80c64e)
Merged-In: Ife0adedf6006daaf17062a0f555d126c1fd45465
Change-Id: Ife0adedf6006daaf17062a0f555d126c1fd45465
|
|
Bug: 313458962
Test: gfxbench
Signed-off-by: Jack Diver <diverj@google.com>
(cherry picked from https://partner-android-review.googlesource.com/q/commit:ef62a44e1e80286433fae8918996eb57647ba84c)
Merged-In: Id2ab03db4b8b3122bc1f87ecb97715fa3a5d80e4
Change-Id: Id2ab03db4b8b3122bc1f87ecb97715fa3a5d80e4
|
|
Bug: 313458962
Test: gfxbench
Signed-off-by: Jack Diver <diverj@google.com>
(cherry picked from https://partner-android-review.googlesource.com/q/commit:89419b7e89dcd2bb9f5c0259e8b5c5a875610131)
Merged-In: I74a81b54764da315510ce988d0aa450b2761725f
Change-Id: I74a81b54764da315510ce988d0aa450b2761725f
|
|
Drop demand to 0 on context idle
Bug: 296485687
Test: gfxbench background task
Signed-off-by: Jack Diver <diverj@google.com>
(cherry picked from https://partner-android-review.googlesource.com/q/commit:b9d48114d56973c60294ec4b94d06d63b845f1ea)
Merged-In: I7ca904323c365c6e5e3ab57e23457fca397cf7ae
Change-Id: I7ca904323c365c6e5e3ab57e23457fca397cf7ae
|
|
IFPO feature has been unusued and only creates overhead for smooth
driver updates.
Bug: 324019470
Change-Id: Iab65e95b9ba21d74cc158557e3fa78d4478c9a71
Signed-off-by: Vamsidhar reddy Gaddam <gvamsi@google.com>
|
|
Bug: 301208289
Test: gfxbench
Change-Id: I799115a5c3a6221c074c20b037d51e7a93d96845
Signed-off-by: Mattias Simonsson <mattiass@google.com>
|
|
Bug: 312206733
Change-Id: I154b927152d768944e02fe6083e66bdbb0f47e3a
Signed-off-by: Varad Gautam <varadgautam@google.com>
|
|
and use it throughout kbase.
Bug: 312206733
Change-Id: Iba908d1dff259aef4bfc35d0ca9df8682e759a9c
Signed-off-by: Varad Gautam <varadgautam@google.com>
|
|
kobject_uevent_env() shouldn't be called from an interrutpt ctx. Log a
warning and return early if pixel_gpu_uevent_send() is accidentally
called from an interrupt.
Bug: 312206733
Change-Id: I66dc5f14c4bf736ffa423aed701906d9da5e00ec
Signed-off-by: Varad Gautam <varadgautam@google.com>
|
|
Update KMD to R47P0
Bug: 315267052
Test: Outlined in go/pixel-gpu-kmd-r47p0
Change-Id: I89454c4c862033fe330b260a9bc6cc777a3ca231
Signed-off-by: Vamsidhar reddy Gaddam <gvamsi@google.com>
|
|
Provenance: ipdelivery@ad01e50d640910a99224382bb227e6d4de627657
Change-Id: I19ac9bce34a5c5a319c1b4a388e8b037b3dfe6e7
|
|
Bug: 277090000
Test: Trigger sscd
Change-Id: I6ca23cc74806efc364b10ee17e654f4252d3ec1f
Signed-off-by: Yunju Lee <yunjulee@google.com>
|
|
Bug: 300854197
SBMerger: 571992243
Change-Id: Ie9096d3afd31c2e5959618fb2f1354bca8be3cfd
Signed-off-by: SecurityBot <android-nexus-securitybot@system.gserviceaccount.com>
|
|
Fix potential out-of-bounds read due to missing bounds check.
Bug: 298264460
Signed-off-by: Guus Sliepen <gsliepen@google.com>
Change-Id: I57b67a4177e4fe6d84a261eeb00b6b833da5486b
Merged-In: I57b67a4177e4fe6d84a261eeb00b6b833da5486b
|
|
Move macros, struct, and functions required by sscd from source file to
header file. Add firmware core dump segment to sscd. Implement firmware
core dump in sscd.
Bug: 277090000
Test: Trigger sscd manually
Change-Id: I3546e74e647e60f13f18c5e9ef6a4a24413f02fb
|
|
android13-gs-pixel-5.10-24Q1" into android13-gs-pixel-5.10-24Q1
|
|
Fix potential integer overflow within buffer liveness ioctl.
Bug: 296984851
Test: N/A
Change-Id: Ib1c9ee25a89b0a39ec905f109ee2c57c502428db
(cherry picked from https://partner-android-review.googlesource.com/q/commit:02e5329e2e3f4af00f51560895b5bbe87fe824ef)
Signed-off-by: Jack Diver <diverj@google.com>
|
|
Record the freq recommended by the governor before it's clamped
via a new `gpu_gov_rec` clock tracepoint.
Also record a new tracepoint `gpu_gov_rec_violate` if this freq
is outside of the level lock window.
Bug: 291855615
Test: Manual trace
Signed-off-by: Varad Gautam <varadgautam@google.com>
Change-Id: I45d0ffbebb6fa83d1a47b9d2afc8d96ce420afce
|
|
Bug: 291855615
Test: Record manual trace.
Signed-off-by: Varad Gautam <varadgautam@google.com>
Change-Id: Id4341c3809b2e3b147122adaabaa01ac7b265dfc
|
|
Bug: 290882327
Change-Id: I90723cbaa3f294431087587fd8025f0688e51bf2
|
|
We use pm_runtime for handling suspends, which means that an
internal linux power workqueue will take and hold the CSF
scheduler lock while performing suspend operations.
This workqueue runs at default priority and so might not be
scheduled fast enough if there is high CPU load, which results
in missed frames.
By promoting the CSF scheduler lock to an rt_mutex we ensure
that the GPU wakes up faster when there is work that needs to
be done, since our other internal realtime threads will be
waiting on the scheduler lock in these cases.
Bug: 296862283
Test: CUJ close camera
Change-Id: Ibe81ad7e26a75acb1640b2820902eb8144a48fdd
Merged-In: I0e81a45e3d65f60337250d35c53ef6447c876051
|
|
Test: Boot to home, gfx-bench sweep
Bug: 294167925
(cherry picked from https://partner-android-review.googlesource.com/q/commit:3143995156d9372ca6af0be57aa29dd0ec14cce1)
Merged-In: I4a122fe023b43c3763884fda99cfed17048a3eb0
Change-Id: I4a122fe023b43c3763884fda99cfed17048a3eb0
Signed-off-by: Jack Diver <diverj@google.com>
|
|
Provenance: ipdelivery@d10c137c7691a470b8b33786aec4965315db4561
Change-Id: I4fbcc669d3b8e36c8288c91fdddd8b79258b6635
|
|
We have accumulated various logging that is no longer required, and
some messages that sound more scary than they need to.
Bug: 291710900
Test: boot to home
Change-Id: I870a4136e1de423281b14a2e3ba8f643e9243d81
|
|
When an ITMON fault report identifies a transaction originated by the
GPU, search for the faulting address in all GPU page tables and log
whether it was found or not.
Bug: 288088318
Test: boot to home
Change-Id: Ic774d4d84af625a33b94b79069f62c8a71adaad7
|
|
Merge DDK version R43P0 from upstream branch
Provenance: 48a9c7e25986318c8475bc245de51e7bec2606e8 (ipdelivery/EAC/v_r43p0)
VX504X08X-BU-00000-r43p0-01eac0 - Valhall Android DDK
VX504X08X-BU-60000-r43p0-01eac0 - Valhall Android Document Bundle
VX504X08X-DC-11001-r43p0-01eac0 - Valhall Android DDK Software Errata
VX504X08X-SW-99006-r43p0-01eac0 - Valhall Android Renderscript AOSP parts
Bug 278174418
Commit-Topic: R43P0_KMD
Signed-off-by: Debarshi Dutta <debarshid@google.com>
Change-Id: I84fb19e7ce5f28e735d44a4993d51bd985aac80b
|
|
Bug: 276704984
Change-Id: Id86861197e8f0929b3594fa28d21b8e3b6bee0f9
Signed-off-by: Varad Gautam <varadgautam@google.com>
|
|
Add the following types of GPU uevents:
1. KMD_ERROR: Reports incidents where kbase runs into an error
(includes FW errors).
2. GPU_RESET: Reports failed or successful GPU reset incidents.
Bug: 275367216
Bug: 275367223
Test: Combined with userspace patches: b/276704984#comment2
Change-Id: Ie0d18f96c590cba561e8425eba210136bfef039d
Signed-off-by: Varad Gautam <varadgautam@google.com>
|
|
Add an interface to emit uevents with env GPU_UEVENT_TYPE and
GPU_UEVENT_INFO from kbase. This will be used to report common
GPU failure conditions.
To avoid flooding the userspace with uevents, these are ratelimited
to one uevent per GPU_UEVENT_TYPE per GPU_UEVENT_TIMEOUT_MS.
Bug: 275367216
Bug: 275367223
Test: Combined with userspace patches: b/276704984#comment2
Change-Id: I557df22c87f435aca4d05e0038609e1c9f82de54
Doc: go/pixel-gpu-instability-monitoring
Signed-off-by: Varad Gautam <varadgautam@google.com>
|
|
Init call for SLC portion of the GPU context was missing.
Bug: 276392249
Change-Id: I7f9b8a89a463f66845f5da91adca63d30f138c83
Signed-off-by: Jack Diver <diverj@google.com>
|
|
Bug: 254279889
Test: Boots to home
Signed-off-by: Jack Diver <diverj@google.com>
(cherry picked from https://partner-android-review.googlesource.com/q/commit:08be62386b8b087e1979c0396a23847246ca36bb)
Change-Id: I1427019107b67139381390a5a73bf518b99927c8
|
|
Use mgm_resize_callback to update memory group size.
Add entry point allowing memory group size to be queried.
Bug: 264990406
Test: Boot to home
Test: gfx-bench mh3.1
Change-Id: I80f595724c7418b97e07679719d2b76e4ee7b96f
Signed-off-by: Jack Diver <diverj@google.com>
|
|
Add a heuristic to ratelimit SSCD generation for "GPU hang"-type
coredumps. Typically when the GPU hangs, this codepath is hit multiple
times leading to unnecessary SSCD generation per hang (sometimes > 200
coredumps for a single incident).
The heuristic skips SSCD generation depending on:
1. whether there was a "GPU hang" coredump recently within the
GPU_HANG_SSCD_TIMEOUT_MS time window.
2. whether there was an unsuccesful GPU reset, which implies the
system will end up rebooting soon.
Change-Id: I761057aee9c4ff9f32d658c49b99eb162486033b
Bug: 264595878
Signed-off-by: Varad Gautam <varadgautam@google.com>
Test: b/264595878#comment7
|
|
A malicious app could cause kernel log storm by intentionally supplying
invalid virtual addresses.
The message is primarily intended for debugging cache performance, and is
not needed in bug reports.
Bug: 264990406
Test: Boot to home
Test: Malicious test app
Change-Id: If9292038f286456dc593ad0dcbc6e0a74e063e5c
Signed-off-by: Jack Diver <diverj@google.com>
|
|
Implement demand based SLC partition resizing.
Implement region migration into the SLC memory group.
Bug: 264990406
Test: Boot to home
Test: gfx-bench mh3.1
Change-Id: Ibf763652f3db133066c254b66b1316a49803e54f
Signed-off-by: Jack Diver <diverj@google.com>
|
|
Track the per kctx usage and demand of SLC, updating in response to the
buffer_liveness_ioctl.
Setting SLC PBHA bits and resizing the partition are stubbed for now.
Bug: 264990406
Test: Boot to home
Test: Manual ioctl call
Change-Id: Idfe54f7baad25b9403a69f7269b7c8fc53dedaaa
Signed-off-by: Jack Diver <diverj@google.com>
|
|
Add SLC platform integration, and plumb custom ioctl through.
Bug: 264990406
Test: Boot to home
Test: Manual ioctl call
Change-Id: I0009cec83f54cfed8e12477c5ebd7aa01cf50cc8
Signed-off-by: Jack Diver <diverj@google.com>
|
|
Allocate a platform_data struct, which can be extended for more uses
than per-UID DVFS metrics.
Bug: 264990406
Test: Boot
Test: Check DVFS time_in_state reporting
Change-Id: Iae17f85e6ece87e5bd8aa6f13c75c6f5504e8436
Signed-off-by: Jack Diver <diverj@google.com>
|
|
Bug: 255246572
Change-Id: I4154a51b5f02391cda656a64dc03db3df7671ed9
Signed-off-by: Robin Peng <robinpeng@google.com>
|
|
Takes a snapshot of the contexts that are scheduled on the GPU during a
crash.
Test: collect a few reports, and check that these are intelligible.
Bug: 269802054
Change-Id: I1b2955307c9b6eac5f5d7c6c32ef719dc4bfe47f
Signed-off-by: Kevin DuBois <kevindubois@google.com>
|
|
Bug: 268756179
Change-Id: I0f5476fdfa32aa600cc029284c86862231275797
Signed-off-by: Siddharth Kapoor <ksiddharth@google.com>
|
|
IFPO was in neutral by default, it would do the idleness signalling, but
not actually turn off the rails. This flag setting made sense at one point, but having the rails connected by default is a less convoluted configuration.
Test: build, see rails going off
Bug: 265314487
Change-Id: I9c96f0d29c6787f60cb2a47754b204bde1b9fc29
|
|
Fixes off-by one error in awaiting debug command.
Bug: 260770411
Test: IFPO debug runs
Change-Id: I939dc38b0293b221668c47eb420878b9fd125a95
Signed-off-by: Jeremy Kemp <jeremykemp@google.com>
|
|
Provenance: 056ded72d351d1bf6319f7b2b925496dd6ad304f (ipdelivery/EAC/v_r40p0)
VX504X08X-BU-00000-r40p0-01eac0 - Valhall Android DDK
VX504X08X-BU-60000-r40p0-01eac0 - Valhall Android Document Bundle
VX504X08X-DC-11001-r40p0-01eac0 - Valhall Android DDK Software Errata
VX504X08X-SW-99006-r40p0-01eac0 - Valhall Android Renderscript AOSP parts
Change-Id: I6db6b45c73c5447dd246533246e65b5ef2c8872f
|
|
Gather the KTRACE buffer into the SSCD report to give us some
information about the CPU side activity before ramdump.
Should only be enabled on debug builds.
Test: trigger ramdump, see usable data in dmesg
Bug: 249325561
Change-Id: I151644e425d8c3d235c2c540819f9c50c01f2bf8
|
|
Disable GPU FW log, as it incurs performance penalty when left on
Bug: 228779790
Test: benchmark before and after setting this switch
Change-Id: If3b824eb3a7cbde502b3eef38befb9e9856eee50
Signed-off-by: Jack Diver <diverj@google.com>
(cherry picked from commit d4578bc2eb297fdb4c15bb54cd48d45c38ff1885)
|
|
partner/android13-gs-pixel-5.10-tm-qpr2""
This reverts commit 34e635317dc2a91076ac341df3867ac3bdb31ef1.
Bug: 228779790
Change-Id: Ic9d131af5568d7f55f610f255fa1c02925b18482
(cherry picked from commit 1c916e3f7c4d999f68e40c60fee6fe39418fcecd)
|
|
Disable GPU FW log, as it incurs performance penalty when left on
Bug: 228779790
Bug: 256851310
Test: benchmark before and after setting this switch
Change-Id: If3b824eb3a7cbde502b3eef38befb9e9856eee50
Signed-off-by: Jack Diver <diverj@google.com>
|