a. LAUNCH_ERR
- Userspace error.
- Triggered due to faulty launch.
- Handle using recovery to reset CE engine and teardown the
faulty channel.
b. An INVALID_CONFIG -
- Triggered when LCE is mapped to floorswept PCE.
- On iGPU, we use the default PCE 2 LCE HW mapping.
The default mapping can be read from NV_CE_PCE2LCE_CONFIG
INIT value in CE refmanual.
- NvGPU driver configures the mapping on dGPUs (currently only on
Turing).
- So, this interrupt can only be triggered if there is
kernel or HW error
- Recovery ( which is killing the context + engine reset) will
not help resolve this error.
- Trigger Quiesce as part of handling.
c. A MTHD_BUFFER_FAULT -
- NvGPU driver allocates fault buffers for all TSGs or contexts,
maps them in BAR2 VA space and writes the VA into channel
instance block.
- Can be triggered only due to kernel bug
- Recovery will not help, need quiesce
d. FBUF_CRC_FAIL
- Triggered when the CRC entry read from the method fault buffer
does not match the computed CRC from the methods contained in
the buffer.
- This indicates memory corruption and is a fatal interrupt which
at least requires the LCE to be reset before operations can
start again, if not the entire GPU.
- Better to quiesce on memory corruption
CE Engine reset (via recovery) will not help.
e. FBUF_MAGIC_CHK_FAIL
- Triggered when the MAGIC_NUM entry read from the method fault
buf does not match NV_CE_MTHD_BUFFER_GLOBAL_HDR_MAGIC_NUM_VAL
- This indicates memory corruption and is a fatal interrupt
- Better to quiesce on memory corruption
f. STALLING_DEBUG
- Only triggered with SW write for debug purposes
- Debug interrupt, currently ignored
Move launch error handling from GP10b to GV11b HAL as -
1. LAUNCHERR_REPORT errcode METHOD_BUFFER_ACCESS_FAULT is not
defined on Pascal
2. We do not support GP10b on dev-main ToT
JIRA NVGPU-8102
Change-Id: Idc84119bc23b5e85f3479fe62cc8720e98b627a5
Signed-off-by: Tejal Kudav <tkudav@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2678893
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Below CE interrupts do not have any users(usecases) on safety build;
disable them only on safety build.
1. BLOCKPIPE stall intr: Not used by GFX(VKSC) and CUDA on safety.
2. NONBLOCK_PIPE nonstall intr: Non-stall intrs are not supported
on safety build. Also, this one is not used by GFX(VKSC)
and CUDA.
3. STALLING_DEBUG intr: Added in Orin tree. It is only needed for
debugging. Disable on safety build as there is no current
usage in driver.
4. POISON_ERROR intr: Poison is a fault containment and not
supported on GA10b.
5. INVALID_CONFIG intr: Floor sweeping not supported on functional
safety SKU.
Bug 3548082
Change-Id: I8d97ccb38f138b2c04a780e1c255a64d28723405
Signed-off-by: Tejal Kudav <tkudav@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2671927
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Move interrupt specific data-members from common.mc to common.cic
Some of these data members like sw_irq_stall_last_handled_cond need
To be initialized much earlier during the OS specific init/probe stage.
Also, some more members from struct nvgpu_interrupts(like stall_size,
stall_lines[]), which will soon be moved to CIC will also need to be
initialized early during the OS specific probe stage.
However, the chip specific LUT can only be initialized after the
hal_init stage where the HALs are all initialized.
Split the CIC init to accommodate the above initialization requirements.
JIRA NVGPU-6899
Change-Id: I9333db4cde59bb0aa8f6eb9f8472f00369817a5d
Signed-off-by: Tejal Kudav <tkudav@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2552535
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
common.cic unit is divided into common.cic.mon and common.cic.rm
based on rm and mon process split.
CIC-mon subunit includes the code which is utilized in critical
interrupt handling path like initialization, error detection and
error reporting path. CIC-rm subunit includes the code corresponding
to rest of interrupt handling(like collecting error debug data from
registers) and ISR status management (status of deferred interrupts).
Split the CIC APIs and data-members into above two subunits.
JIRA NVGPU-6899
Change-Id: I151b59105ff570607c4a62e974785e9c1323ef69
Signed-off-by: Tejal Kudav <tkudav@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2551897
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
CIC (Central Interrupt controller) will be responsible for the
interrupt handling. common.cic unit is the placeholder for all
interrupt related code. Move interrupt related defines and
Public APIs present in common.mc to common.cic.
Note: The common.mc interrupts related struct definitions are
not moved as part of this patch.
Adapt the code to use interrupt handling related defines and public
APIs migrated from common.mc to common.cic
JIRA NVGPU-6899
Change-Id: I747e2b556c0dd66d58d74ee5bb36768b9370d276
Signed-off-by: Tejal Kudav <tkudav@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2535618
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-cert <svc-mobile-cert@nvidia.com>
Reviewed-by: svc_kernel_abi <svc_kernel_abi@nvidia.com>
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Remove current mc hals
- mc.reset()
- mc.enable()
- mc.disable()
- mc.reset_mask()
- mc.reset_engine()
- mc.reset_engine_enable()
Add new mc hals
- mc.enable_units(g, units, enable)
> enable/disable given unit(s)
- mc.enable_dev(g, dev, enable)
> enable/disable engine represented by given device pointer
- mc.enable_devtype(g, devtype)
> enable/disable all engines of given devtype
Move common mc intr functions to common/mc/mc_intr.c.
Add below common mc functions
- nvgpu_mc_reset_units(g, units)
> reset given logical OR of nvgpu unit bitmap
- nvgpu_mc_reset_dev(g, dev)
> reset given single engine via dev
> if engine is graphics, reset gpcs for nvgpu_next
- nvgpu_mc_reset_devtype(g, devtype)
> reset all engines of given devtype
> if devtype is graphics, reset gpcs for nvgpu_next
Bug 200648985
Bug 3109773
Change-Id: Idc67a14a0a7cde83de44fbfbec13007fead3ed5c
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2408523
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
The FIFO pbdma map is an array of bit maps that link PBDMAs to runlists.
This array allows other software to query what PBDMA(s) serves a given
runlist. The PBDMA map is read verbatim from an array of host registers.
These registers are stored in a kmalloc()'ed array.
This causes a problem for the device management code. The device
management initialization executes well before the rest of the FIFO
PBDMA initialization occurs. Thus, if the device management code
queries the PBDMA mapping for a given device/runlist, the mapping has
yet to be populated.
In the next patches in this series the engine management code is subsumed
into the device management code. In other words the device struct is
reused by the engine management and all host SW does is pull pointers to
the host managed devices from the device manager. This means that all
engine initialization that used to be done on top of the device
management needs to move to the device code.
So, long story short, the PBDMA map needs to be read from the registers
directly, instead of an array that gets allocated long after the device
code has run.
This patch removes the pbdma map array, deletes two HALs that managed
that, and instead provides a new HAL to query this map directly from
the registers so that the device code can use it.
JIRA NVGPU-5421
Change-Id: I5966d440903faee640e3b41494d2caf4cd177b6d
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2361134
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-cert <svc-mobile-cert@nvidia.com>
Reviewed-by: svc-mobile-misra <svc-mobile-misra@nvidia.com>
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Nvgpu does not support nested interrupts and as a result priv/pbus
interrupt do not reach cpu while other interrupts on intr_0 (stall)
tree are being processed. This issue is not specific to priv/pbus
but since pbus errors are critical, it is important to detect it
early on.
Below is the snippet from one of the failing logs where nvgpu
is doing recovery to process gr interrupt.
Right after GR engine is reset (PGRAPH of PMC_ENABLE), failing priv
accesses should have triggered pbus interrupt but it does not reach cpu
until gr interrupt is handled. Any interrupt that requires recovery will
take longer to finish isr as recovery is done as part of isr.
Also intr_0 (stall) interrupts are paused while stall interrupt is being
processed.
gm20b_gr_falcon_bind_instblk:147 [ERR] arbiter idle timeout, status: badf1020
gm20b_gr_falcon_wait_for_fecs_arb_idle:125 [ERR] arbiter idle timeout, fecs ctxsw status: 0xbadf1020
Fix to detect pbus intr while other stall interrupts are being processed
is to move pbus intr enable/disable/clear/handle to nonstall (intr_1)
tree. Configure pbus_intr_en_1 to route pbus to nostall tree.
Priv interrupts cannot be moved to nonstall (intr_1) tree due
to h/w not supporting this.
In Turing, moving pbus intr to nonstall is not feasible as mc_intr(1)
tree is deprecated. Add Turing specific stall intr handler hals with
original logic to route pbus intr to mc_intr(0).
JIRA NVGPU-25
Bug 200603566
Change-Id: I36fc376800802f20a0ea581b4f787bcc6c73ec7e
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2354192
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-misra <svc-mobile-misra@nvidia.com>
Reviewed-by: svc-mobile-cert <svc-mobile-cert@nvidia.com>
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Fix what unit tests can be easily fixed, but disable some others. It's
not clear why the MM related tests started failing - there's really zero
reason for this. The list of disable tests are primarily engine related
but there are some others that get inflenced by the device and engine
structure.
test_poweroff.init_poweroff=2
test_is_stall_and_eng_intr_pending.intr_is_stall_and_eng_intr_pending=2
test_isr_nonstall.isr_nonstall=2
test_isr_stall.isr_stall=2
test_engine_enum_from_type.enum_from_type=2
test_engine_find_busy_doing_ctxsw.find_busy_doing_ctxsw=2
test_engine_get_active_eng_info.get_active_eng_info=2
test_engine_get_fast_ce_runlist_id.get_fast_ce_runlist_id=2
test_engine_get_gr_runlist_id.get_gr_runlist_id=2
test_engine_get_mask_on_id.get_mask_on_id=2
test_engine_get_runlist_busy_engines.get_runlist_busy_engines=2
test_engine_ids.ids=2
test_engine_init_info.init_info=2
test_engine_interrupt_mask.interrupt_mask=2
test_engine_is_valid_runlist_id.is_valid_runlist_id=2
test_engine_mmu_fault_id.mmu_fault_id=2
test_engine_mmu_fault_id_veid.mmu_fault_id_veid=2
test_engine_setup_sw.setup_sw=2
test_engine_status.status=2
test_fifo_init_support.init_support=2
test_fifo_remove_support.remove_support=2
test_gp10b_engine_init_ce_info.engine_init_ce_info=2
test_nvgpu_mem_iommu_translate.mem_iommu_translate=2
test_nvgpu_mem_phys_ops.nvgpu_mem_phys_ops=2
And delete unit tests for functions that no longer exist:
test_device_info_parse_enum.top_device_info_parse_enum
test_get_device_info.top_get_device_info
test_get_num_engine_type_entries.top_get_num_engine_type_entries
test_is_engine_ce.top_is_engine_ce
test_is_engine_gr.top_is_engine_gr
JIRA NVGPU-5421
Change-Id: I343c0b1ea44c472b22356c896672153fc889ffc0
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2355300
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This adds a new device management unit in the common code responsible
for facilitating the parsing of the GPU top device list and providing
that info to other units in nvgpu.
The basic idea is to read this list once from HW and store it in a
set of lists corresponding to each device type (graphics, LCE, etc).
Many of the HALs in top can be deleted and instead implemented using
common code parsing the SW representation.
Every time the driver queries the device list it does so using a
device type and instance ID. This is common code. The HAL is responsible
for populating the device list in such a way that the driver can
query it in a chip agnostic manner.
Also delete some of the unit tests for functions that no longer
exist. This code will require new unit tests in time; those should be
quite simple to write once unit testing is needed.
JIRA NVGPU-5421
Change-Id: Ie41cd255404b90ae0376098a2d6e9f9abdd3f5ea
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2319649
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Many tests used various incarnations of the mock register framework.
This was based on a dump of gv11b registers. Tests that greatly
benefitted from having generally sane register values all rely
heavily on this framework.
However, every test essentially did their own thing. This was not
efficient and has caused a some issues in cleaning up the device and
host code.
Therefore introduce a much leaner and simplified register framework.
All unit tests now automatically get a good subset of the gv11b
registers auto-populated. As part of this also populate the HAL with
a nvgpu_detect_chip() call. Many tests can now _probably_ have all
their HAL init (except dummy HAL stuff) deleted. But this does
require a few fixups here and there to set HALs to NULL where tests
expect HALs to be NULL by default.
Where necessary HALs are cleared with a memset to prevent unwanted
code from executing.
Overall, this imposes a far smaller burden on tests to initialize
their environments.
Something to consider for the future, though, is how to handle
supporting multiple chips in the unit test world.
JIRA NVGPU-5422
Change-Id: Icf1a63f728e9c5671ee0fdb726c235ffbd2843e2
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2335334
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Address following issues uncovered during inspection:
1. Remove the doxygen comment from nvgpu_wait_for_deferred_interrupts
definition.
2. Use NVGPU_MC_INTR_STALLING instead of hardcoding the index.
3. Define doxygen groups NVGPU_MC_UNIT_ENUMS,
NVGPU_MC_INTR_TYPE_DEFINES, NVGPU_MC_INTR_UNIT_DEFINES and
NVGPU_MC_INTR_ENABLE_DEFINES.
4. Update the doxygen comments.
5. Fix the cleanup, typo in the description of the test
test_wait_for_deferred_interrupts.
JIRA NVGPU-4795
Change-Id: Ifc6756832aabf9dd42ee174eb1373495e6d38c86
Signed-off-by: Sagar Kamble <skamble@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2287627
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
The atomic counter in interrupt handler can overflow and result in
calling of BUG() which will crash the process. The equivalent
functionality can be implemented with just setting an atomic variable at
start of handler and resetting at end of handler. The wait can be longer
in case there is constant interrupts coming but ultimately it will end.
Generally the wait path is not time critical so it should not be an
issue. Also, fix the unit tests for mc.
Change-Id: I9b8a236f72e057e89a969d2e98d4d3f9be81b379
Signed-off-by: shashank singh <shashsingh@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2247819
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-misra <svc-mobile-misra@nvidia.com>
Reviewed-by: svc-mobile-cert <svc-mobile-cert@nvidia.com>
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
PMU IRQs were not enabled assuming entire functionality for LS PMU.
Debugging early init issues of PMU falcon ECC errors triggered
during nvgpu power-on will be cumbersome if interrupts are not
enabled early. FMEA analysis of the nvgpu init path also
requires this interrupt be enabled earlier.
Hence, Enable the PMU ECC IRQ early during nvgpu_finalize_poweron.
pmu_enable_irq is updated to enable interrupts differently for
safety and non-safety. PMU interrupts disabling is moved out
of nvgpu_pmu_destroy to nvgpu_prepare_poweroff. Prepared new
wrapper API nvgpu_pmu_enable_irq.
PMU ECC init and isr mutex init is moved to the beginning of
nvgpu_pmu_early_init as for safety, ls pmu code path is
disabled. Fixed the pmu_early_init dependent and mc
interrupt related unit tests.
Update the doxygen for changed functions.
JIRA NVGPU-4439
Change-Id: I1a1e792d2ad2cc7a926c8c1456d4d0d6d1f14d1a
Signed-off-by: Sagar Kamble <skamble@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2251732
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
