There was a size check to warn if the GuC error state capture buffer
allocation would be too small to fit a reasonable amount of capture
data for the current platform. Unfortunately, the test was done too
early in the boot sequence and was actually testing 'if(-ENODEV >
size)'.
Move the check to be later. The check is only used to print a warning
message, so it doesn't really matter how early or late it is done.
Note that it is not possible to dynamically size the buffer because
the allocation needs to be done before the engine information is
available (at least, it would be in the intended two-phase GuC init
process).
Now that the check works, it is reporting size too small for newer
platforms. The check includes a 3x oversample multiplier to allow for
multiple error captures to be bufferd by GuC before i915 has a chance
to read them out. This is less important than simply being big enough
to fit the first capture.
So a) bump the default size to be large enough for one capture minimum
and b) make the warning only if one capture won't fit, instead use a
notice for the 3x size.
Note that the size estimate is a worst case scenario. Actual captures
will likely be smaller.
Lastly, use drm_warn istead of DRM_WARN as the former provides more
infmration and the latter is deprecated.
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220728022028.2190627-3-John.C.Harrison@Intel.com
Although all DSS belong to a single pool on Xe_HP platforms (i.e.,
they're not organized into slices from a topology point of view), we do
still need to pass 'group' and 'instance' targets when steering register
accesses to a specific instance of a per-DSS multicast register. The
rules for how to determine group and instance IDs (which previously used
legacy terms "slice" and "subslice") varies by platform. Some platforms
determine steering by gslice membership, some platforms by cslice
membership, and future platforms may have other rules.
Since looping over each DSS and performing steered unicast register
accesses is a relatively common pattern, let's add a dedicated iteration
macro to handle this (and replace the platform-specific "instdone" loop
we were using previously. This will avoid the calling code needing to
figure out the details about how to obtain steering IDs for a specific
DSS.
Most of the places where we use this new loop are in the GPU errorstate
code at the moment, but we do have some additional features coming in
the future that will also need to loop over each DSS and steer some
register accesses accordingly.
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Matt Atwood <matthew.s.atwood@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220701232006.1016135-1-matthew.d.roper@intel.com
Both error-capture and relay-logging mechanism use the GuC
log infrastructure. That means the KMD must send a log flush
complete notification back to GuC after reading the data out.
This call is currently being sent synchronously.
However, synchronous H2Gs cause problems when the system is
backed up. There is no need for this to be synchronous. The
KMD wasn't even looking at the return status from it. So make
it asynchronous and then there is no issue about time outs.
Signed-off-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220607002314.1451656-2-alan.previn.teres.alexis@intel.com
Print the GuC captured error state register list (string names
and values) when gpu_coredump_state printout is invoked via
the i915 debugfs for flushing the gpu error-state that was
captured prior.
Since GuC could have reported multiple engine register dumps
in a single notification event, parse the captured data
(appearing as a stream of structures) to identify each dump as
a different 'engine-capture-group-output'.
Finally, for each 'engine-capture-group-output' that is found,
verify if the engine register dump corresponds to the
engine_coredump content that was previously populated by the
i915_gpu_coredump function. That function would have copied
the context's vma's including the bacth buffer during the
G2H-context-reset notification that occurred earlier. Perform
this verification check by comparing guc_id, lrca and engine-
instance obtained from the 'engine-capture-group-output' vs a
copy of that same info taken during i915_gpu_coredump. If
they match, then print those vma's as well (such as the batch
buffers).
NOTE: the output format was verified using the gem_exec_capture
IGT test.
Signed-off-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220321164527.2500062-14-alan.previn.teres.alexis@intel.com
Add a flags parameter through all of the coredump creation
functions. Add a bitmask flag to indicate if the top
level gpu_coredump event is triggered in response to
a GuC context reset notification.
Using that flag, ensure all coredump functions that
read or print mmio-register values related to work submission
or command-streamer engines are skipped and replaced with
a calls guc-capture module equivalent functions to retrieve
or print the register dump.
While here, split out display related register reading
and printing into its own function that is called agnostic
to whether GuC had triggered the reset.
For now, introduce an empty printing function that can
filled in on a subsequent patch just to handle formatting.
Signed-off-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220321164527.2500062-13-alan.previn.teres.alexis@intel.com
In the rare but possible scenario where we are in the midst of
multiple GuC error-capture (and engine reset) events and the
user also triggers a forced full GT reset or the internal watchdog
triggers the same, intel_guc_submission_reset_prepare's call
to flush_work(&guc->ct.requests.worker) can cause the G2H message
handler to trigger intel_guc_capture_store_snapshot upon
receiving new G2H error-capture notifications. This can happen
despite the prior call to disable_submission(guc);. However,
there's no race-free way for intel_guc_capture_store_snapshot to
know that we are in the midst of a reset. That said, we can never
dynamically allocate the output nodes in this handler. Thus, we
shall pre-allocate a fixed number of empty nodes up front (at the
time of ADS registration) that we can consume from or return to
an internal cached list of nodes.
Signed-off-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220321164527.2500062-12-alan.previn.teres.alexis@intel.com
- Upon the G2H Notify-Err-Capture event, parse through the
GuC Log Buffer (error-capture-subregion) and generate one or
more capture-nodes. A single node represents a single "engine-
instance-capture-dump" and contains at least 3 register lists:
global, engine-class and engine-instance. An internal link
list is maintained to store one or more nodes.
- Because the link-list node generation happen before the call
to i915_gpu_codedump, duplicate global and engine-class register
lists for each engine-instance register dump if we find
dependent-engine resets in a engine-capture-group.
- When i915_gpu_coredump calls into capture_engine, (in a
subsequent patch) we detach the matching node (guc-id,
LRCA, etc) from the link list above and attach it to
i915_gpu_coredump's intel_engine_coredump structure when have
matching LRCA/guc-id/engine-instance.
Additional notes to be aware of:
- GuC generates the error capture dump into the GuC log buffer but
this buffer is one big log buffer with 3 independent subregions
within it. Each subregion is populated with different content
and used in different ways and timings but all regions operate
behave as independent ring buffers. Each guc-log subregion
(general-logs, crash-dump and error- capture) has it's own
guc_log_buffer_state that contain independent read and write
pointers.
Signed-off-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220321164527.2500062-11-alan.previn.teres.alexis@intel.com
Update GuC ADS size allocation to include space for
the lists of error state capture register descriptors.
Then, populate GuC ADS with the lists of registers we want
GuC to report back to host on engine reset events. This list
should include global, engine-class and engine-instance
registers for every engine-class type on the current hardware.
Ensure we allocate a persistent store for the register lists
that are populated into ADS so that we don't need to allocate
memory during GT resets when GuC is reloaded and ADS population
happens again.
NOTE: Start with a sample static table of register lists to
layout the framework before adding real registers in subsequent
patch. This static register tables are a different format from
the ADS populated list.
Signed-off-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220321164527.2500062-2-alan.previn.teres.alexis@intel.com
