We're seeing on CI that some contexts don't have the programmed OA
period timer that directs the OA unit on how often to write reports.
The issue is that we're not holding the drm lock from when we edit the
context images down to when we set the exclusive_stream variable. This
leaves a window for the deferred context allocation to call
i915_oa_init_reg_state() that will not program the expected OA timer
value, because we haven't set the exclusive_stream yet.
v2: Drop need_lock from gen8_configure_all_contexts() (Matt)
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Fixes: 701f8231a2 ("drm/i915/perf: prune OA configs")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102254
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103715
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103755
Link: https://patchwork.freedesktop.org/patch/msgid/20180301110613.1737-1-lionel.g.landwerlin@intel.com
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: intel-gfx@lists.freedesktop.org
Cc: <stable@vger.kernel.org> # v4.14+
To pull in the HDCP changes, especially wait_for changes to drm/i915
that Chris wants to build on top of.
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
We want to de-emphasize the link between the request (dependency,
execution and fence tracking) from GEM and so rename the struct from
drm_i915_gem_request to i915_request. That is we may implement the GEM
user interface on top of requests, but they are an abstraction for
tracking execution rather than an implementation detail of GEM. (Since
they are not tied to HW, we keep the i915 prefix as opposed to intel.)
In short, the spatch:
@@
@@
- struct drm_i915_gem_request
+ struct i915_request
A corollary to contracting the type name, we also harmonise on using
'rq' shorthand for local variables where space if of the essence and
repetition makes 'request' unwieldy. For globals and struct members,
'request' is still much preferred for its clarity.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180221095636.6649-1-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
This is the mindless scripted replacement of kernel use of POLL*
variables as described by Al, done by this script:
for V in IN OUT PRI ERR RDNORM RDBAND WRNORM WRBAND HUP RDHUP NVAL MSG; do
L=`git grep -l -w POLL$V | grep -v '^t' | grep -v /um/ | grep -v '^sa' | grep -v '/poll.h$'|grep -v '^D'`
for f in $L; do sed -i "-es/^\([^\"]*\)\(\<POLL$V\>\)/\\1E\\2/" $f; done
done
with de-mangling cleanups yet to come.
NOTE! On almost all architectures, the EPOLL* constants have the same
values as the POLL* constants do. But they keyword here is "almost".
For various bad reasons they aren't the same, and epoll() doesn't
actually work quite correctly in some cases due to this on Sparc et al.
The next patch from Al will sort out the final differences, and we
should be all done.
Scripted-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-----BEGIN PGP SIGNATURE-----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=pLN1
-----END PGP SIGNATURE-----
Merge tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux
Pull drm updates from Dave Airlie:
"This seems to have been a comparatively quieter merge window, I assume
due to holidays etc. The "biggest" change is AMD header cleanups, which
merge/remove a bunch of them. The AMD gpu scheduler is now being made generic
with the etnaviv driver wanting to reuse the code, hopefully other drivers
can go in the same direction.
Otherwise it's the usual lots of stuff in i915/amdgpu, not so much stuff
elsewhere.
Core:
- Add .last_close and .output_poll_changed helpers to reduce driver footprints
- Fix plane clipping
- Improved debug printing support
- Add panel orientation property
- Update edid derived properties at edid setting
- Reduction in fbdev driver footprint
- Move amdgpu scheduler into core for other drivers to use.
i915:
- Selftest and IGT improvements
- Fast boot prep work on IPS, pipe config
- HW workarounds for Cannonlake, Geminilake
- Cannonlake clock and HDMI2.0 fixes
- GPU cache invalidation and context switch improvements
- Display planes cleanup
- New PMU interface for perf queries
- New firmware support for KBL/SKL
- Geminilake HW workaround for perforamce
- Coffeelake stolen memory improvements
- GPU reset robustness work
- Cannonlake horizontal plane flipping
- GVT work
amdgpu/radeon:
- RV and Vega header file cleanups (lots of lines gone!)
- TTM operation context support
- 48-bit GPUVM support for Vega/RV
- ECC support for Vega
- Resizeable BAR support
- Multi-display sync support
- Enable swapout for reserved BOs during allocation
- S3 fixes on Raven
- GPU reset cleanup and fixes
- 2+1 level GPU page table
amdkfd:
- GFX7/8 SDMA user queues support
- Hardware scheduling for multiple processes
- dGPU prep work
rcar:
- Added R8A7743/5 support
- System suspend/resume support
sun4i:
- Multi-plane support for YUV formats
- A83T and LVDS support
msm:
- Devfreq support for GPU
tegra:
- Prep work for adding Tegra186 support
- Tegra186 HDMI support
- HDMI2.0 and zpos support by using generic helpers
tilcdc:
- Misc fixes
omapdrm:
- Support memory bandwidth limits
- DSI command mode panel cleanups
- DMM error handling
exynos:
- drop the old IPP subdriver.
etnaviv:
- Occlusion query fixes
- Job handling fixes
- Prep work for hooking in gpu scheduler
armada:
- Move closer to atomic modesetting
- Allow disabling primary plane if overlay is full screen
imx:
- Format modifier support
- Add tile prefetch to PRE
- Runtime PM support for PRG
ast:
- fix LUT loading"
* tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux: (1471 commits)
drm/ast: Load lut in crtc_commit
drm: Check for lessee in DROP_MASTER ioctl
drm: fix gpu scheduler link order
drm/amd/display: Demote error print to debug print when ATOM impl missing
dma-buf: fix reservation_object_wait_timeout_rcu once more v2
drm/amdgpu: Avoid leaking PM domain on driver unbind (v2)
drm/amd/amdgpu: Add Polaris version check
drm/amdgpu: Reenable manual GPU reset from sysfs
drm/amdgpu: disable MMHUB power gating on raven
drm/ttm: Don't unreserve swapped BOs that were previously reserved
drm/ttm: Don't add swapped BOs to swap-LRU list
drm/amdgpu: only check for ECC on Vega10
drm/amd/powerplay: Fix smu_table_entry.handle type
drm/ttm: add VADDR_FLAG_UPDATED_COUNT to correctly update dma_page global count
drm: Fix PANEL_ORIENTATION_QUIRKS breaking the Kconfig DRM menuconfig
drm/radeon: fill in rb backend map on evergreen/ni.
drm/amdgpu/gfx9: fix ngg enablement to clear gds reserved memory (v2)
drm/ttm: only free pages rather than update global memory count together
drm/amdgpu: fix CPU based VM updates
drm/amdgpu: fix typo in amdgpu_vce_validate_bo
...
Execlists and legacy ringbuffer submission are no longer feature
comparable (execlists now offer greater functionality that should
overcome their performance hit) and obsoletes the unsafe module
parameter, i.e. comparing the two modes of execution is no longer
useful, so remove the debug tool.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> #i915_perf.c
Link: https://patchwork.freedesktop.org/patch/msgid/20171120205504.21892-1-chris@chris-wilson.co.uk
Now that we have this stored in the device info, we can drop it from perf
part of the driver.
Note that this requires to init perf after we've computed the frequency,
hence why we move i915_perf_init() from i915_driver_init_early() to after
intel_device_info_runtime_init().
v2: Use div_u64 (Chris)
v3: Drop u64 divs by switching to kHz (Chris/Ville)
Move i915_perf_fini to i915_driver_cleanup_hw (Matthew)
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171113181902.12411-2-lionel.g.landwerlin@intel.com
During request construction, after pinning the context we know whether
or not we have to emit a context switch. So move this common operation
from every caller into i915_gem_request_alloc() itself.
v2: Always submit the request if we emitted some commands during request
construction, as typically it also involves changes in global state.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171120102002.22254-2-chris@chris-wilson.co.uk
This replaces accesses to the reg field of the i915_reg_t structure
with the i915_mmio_reg_offset() inline function.
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Ewelina Musial <ewelina.musial@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171113233455.12085-2-lionel.g.landwerlin@intel.com
-----BEGIN PGP SIGNATURE-----
iQEcBAABAgAGBQJZ9kEFAAoJEHm+PkMAQRiGw6wH/0j197qyGd0hkVFMJO6LAgN3
KQWS4nZ5BkVDocwv0RVnUJTtXqU1eozFgdVEtSoaFXpzlHGuptR2Tau9efDCJ7w3
/utZxqvhGebZd2T+j+/o/LE8BRQxhADBNJq2D/o0WNt8ecxuG0GIkhkEYt/o3z1v
/sxlwVwzXB7Dc/h1WcgGJG7cS6L9KzzAzGAS/iNvdFrPOygHBv8c0MxVZIiBIeeK
1nZdyvbyM8uenSyG+prGt9ENrqXZxxfwUxIchi2V7A9m1WmD5zijNkf1JCWji/O+
UsA1auxna7MwoxjxqZuGm4MlKOwZ+8xutk4JGgc+aP/ulndJbJYu+4op/3vaFBM=
=Mhx+
-----END PGP SIGNATURE-----
Backmerge tag 'v4.14-rc7' into drm-next
Linux 4.14-rc7
Requested by Ben Skeggs for nouveau to avoid major conflicts,
and things were getting a bit conflicty already, esp around amdgpu
reverts.
The compat callback was missing and triggered failures in 32bits
userspace when enabling/disable the perf stream. We don't require any
particular processing here as these ioctls don't take any argument.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: eec688e142 ("drm/i915: Add i915 perf infrastructure")
Cc: linux-stable <stable@vger.kernel.org>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024152728.4873-1-lionel.g.landwerlin@intel.com
(cherry picked from commit 191f896085)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
The compat callback was missing and triggered failures in 32bits
userspace when enabling/disable the perf stream. We don't require any
particular processing here as these ioctls don't take any argument.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: eec688e142 ("drm/i915: Add i915 perf infrastructure")
Cc: linux-stable <stable@vger.kernel.org>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024152728.4873-1-lionel.g.landwerlin@intel.com
Our global struct with params is named exactly the same way
as new preferred name for the drm_i915_private function parameter.
To avoid such name reuse lets use different name for the global.
v5: pure rename
v6: fix
Credits-to: Coccinelle
@@
identifier n;
@@
(
- i915.n
+ i915_modparams.n
)
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Ville Syrjala <ville.syrjala@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170919193846.38060-1-michal.wajdeczko@intel.com
As we cannot have an exclusive stream set if the perf has not been
initialized, we only need to check for that exclusive stream.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170810175743.25401-3-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
This is called from execlist context init which we need to be unlocked.
Commit f89823c212 ("drm/i915/perf: Implement
I915_PERF_ADD/REMOVE_CONFIG interface") added a lockdep assert to this
path for unclear reasons, remove it again!
Fixes: f89823c212 ("drm/i915/perf: Implement I915_PERF_ADD/REMOVE_CONFIG interface")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170810175743.25401-2-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
The motivation behind this new interface is expose at runtime the
creation of new OA configs which can be used as part of the i915 perf
open interface. This will enable the kernel to learn new configs which
may be experimental, or otherwise not part of the core set currently
available through the i915 perf interface.
v2: Drop DRM_ERROR for userspace errors (Matthew)
Add padding to userspace structure (Matthew)
s/guid/uuid/ (Matthew)
v3: Use u32 instead of int to iterate through registers (Matthew)
v4: Lock access to dynamic config list (Lionel)
v5: by Matthew:
Fix uninitialized error values
Fix incorrect unwiding when opening perf stream
Use kmalloc_array() to store register
Use uuid_is_valid() to valid config uuids
Declare ioctls as write only
Check padding members are set to 0
by Lionel:
Return ENOENT rather than EINVAL when trying to remove non
existing config
v6: by Chris:
Use ref counts for OA configs
Store UUID in drm_i915_perf_oa_config rather then using pointer
Shuffle fields of drm_i915_perf_oa_config to avoid padding
v7: by Chris
Rename uapi pointers fields to end with '_ptr'
v8: by Andrzej, Marek, Sebastian
Update register whitelisting
by Lionel
Add more register names for documentation
Allow configuration programming in non-paranoid mode
Add support for value filter for a couple of registers already
programmed in other part of the kernel
v9: Documentation fix (Lionel)
Allow writing WAIT_FOR_RC6_EXIT only on Gen8+ (Andrzej)
v10: Perform read access_ok() on register pointers (Lionel)
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Andrzej Datczuk <andrzej.datczuk@intel.com>
Reviewed-by: Andrzej Datczuk <andrzej.datczuk@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170803165812.2373-2-lionel.g.landwerlin@intel.com
In the following commit we'll introduce loadable userspace
configs. This change reworks how configurations are handled in the
perf driver and retains only the test configurations in kernel space.
We now store the test config in dev_priv and resolve the id only once
when opening the perf stream. The OA config is then handled through a
pointer to the structure holding the configuration details.
v2: Rework how test configs are handled (Lionel)
v3: Use u32 to hold number of register (Matthew)
v4: Removed unused dev_priv->perf.oa.current_config variable (Matthew)
v5: Lock device when accessing exclusive_stream (Lionel)
v6: Ensure OACTXCONTROL is always reprogrammed (Lionel)
v7: Switch a couple of index variable from int to u32 (Matthew)
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170803165812.2373-3-lionel.g.landwerlin@intel.com
We were reserving fewer dwords in the ring than necessary. Indeed
we're always writing all registers once, so discard the actual number
of registers given by the user and just program the whitelisted ones
once.
Fixes: 19f81df285 ("drm/i915/perf: Add OA unit support for Gen 8+")
Reported-by: Matthew Auld <matthew.william.auld@gmail.com>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Cc: <stable@vger.kernel.org> # v4.12+
Link: https://patchwork.freedesktop.org/patch/msgid/20170803165812.2373-6-lionel.g.landwerlin@intel.com
1acfc104cd missed to convert this one caller to be lockless. The side
effect of that was that the error check in lookup_context() became
incorrect. Convert now this caller too.
Fixes: 1acfc104cd ("drm/i915: Enable rcu-only context lookups")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170714151242.517-1-imre.deak@intel.com
OA buffer initialization involves access to HW registers to set
the OA base, head and tail. Ensure device is awake while setting
these. With this, all oa.ops are covered under RPM and forcewake
wakelock.
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1498585181-23048-1-git-send-email-sagar.a.kamble@intel.com
Fixes: d79651522e ("drm/i915: Enable i915 perf stream for Haswell OA unit")
Cc: <stable@vger.kernel.org> # v4.11+
If we move the actual cleanup of the context to a worker, we can allow
the final free to be called from any context and avoid undue latency in
the caller.
v2: Negotiate handling the delayed contexts free by flushing the
workqueue before calling i915_gem_context_fini() and performing the final
free of the kernel context directly
v3: Flush deferred frees before new context allocations
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170620110547.15947-2-chris@chris-wilson.co.uk
Add OA support for Kabylake (pretty much identical to Skylake), and
also add the associated OA configurations.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
In earlier iterations of the i915-perf driver we had a number of
callbacks/hooks from other parts of the i915 driver to e.g. notify us
when a legacy context was pinned and these could run asynchronously with
respect to the stream file operations and might also run in atomic
context.
dev_priv->perf.hook_lock had been for serialising access to state needed
within these callbacks, but as the code has evolved some of the hooks
have gone away or are implemented to avoid needing to lock any state.
The remaining use of this lock was actually redundant considering how
the gen7 oacontrol state used to be updated as part of a context pin
hook.
Signed-off-by: Robert Bragg <robert@sixbynine.org>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
An oa_exponent_to_ns() utility and per-gen timebase constants where
recently removed when updating the tail pointer race condition WA, and
this restores those so we can update the _PROP_OA_EXPONENT validation
done in read_properties_unlocked() to not assume we have a 12.5MHz
timebase as we did for Haswell.
Accordingly the oa_sample_rate_hard_limit value that's referenced by
proc_dointvec_minmax defining the absolute limit for the OA sampling
frequency is now initialized to (timestamp_frequency / 2) instead of the
6.25MHz constant for Haswell.
v2:
Specify frequency of 19.2MHz for BXT (Ville)
Initialize oa_sample_rate_hard_limit per-gen too (Lionel)
Signed-off-by: Robert Bragg <robert@sixbynine.org>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Enables access to OA unit metrics for BDW, CHV, SKL and BXT which all
share (more-or-less) the same OA unit design.
Of particular note in comparison to Haswell: some OA unit HW config
state has become per-context state and as a consequence it is somewhat
more complicated to manage synchronous state changes from the cpu while
there's no guarantee of what context (if any) is currently actively
running on the gpu.
The periodic sampling frequency which can be particularly useful for
system-wide analysis (as opposed to command stream synchronised
MI_REPORT_PERF_COUNT commands) is perhaps the most surprising state to
have become per-context save and restored (while the OABUFFER
destination is still a shared, system-wide resource).
This support for gen8+ takes care to consider a number of timing
challenges involved in synchronously updating per-context state
primarily by programming all config state from the cpu and updating all
current and saved contexts synchronously while the OA unit is still
disabled.
The driver intentionally avoids depending on command streamer
programming to update OA state considering the lack of synchronization
between the automatic loading of OACTXCONTROL state (that includes the
periodic sampling state and enable state) on context restore and the
parsing of any general purpose BB the driver can control. I.e. this
implementation is careful to avoid the possibility of a context restore
temporarily enabling any out-of-date periodic sampling state. In
addition to the risk of transiently-out-of-date state being loaded
automatically; there are also internal HW latencies involved in the
loading of MUX configurations which would be difficult to account for
from the command streamer (and we only want to enable the unit when once
the MUX configuration is complete).
Since the Gen8+ OA unit design no longer supports clock gating the unit
off for a single given context (which effectively stopped any progress
of counters while any other context was running) and instead supports
tagging OA reports with a context ID for filtering on the CPU, it means
we can no longer hide the system-wide progress of counters from a
non-privileged application only interested in metrics for its own
context. Although we could theoretically try and subtract the progress
of other contexts before forwarding reports via read() we aren't in a
position to filter reports captured via MI_REPORT_PERF_COUNT commands.
As a result, for Gen8+, we always require the
dev.i915.perf_stream_paranoid to be unset for any access to OA metrics
if not root.
v5: Drain submitted requests when enabling metric set to ensure no
lite-restore erases the context image we just updated (Lionel)
v6: In addition to drain, switch to kernel context & update all
context in place (Chris)
v7: Add missing mutex_unlock() if switching to kernel context fails
(Matthew)
v8: Simplify OA period/flex-eu-counters programming by using the
batchbuffer instead of modifying ctx-image (Lionel)
v9: Back to updating the context image (due to erroneous testing,
batchbuffer programming the OA unit doesn't actually work)
(Lionel)
Pin context before updating context image (Chris)
Drop MMIO programming now that we switch to a kernel context with
right values in initial context image (Chris)
v10: Just pin_map the contexts we want to modify or let the
configuration happen on first use (Chris)
v11: Update kernel context OA config through the batchbuffer rather
than on the fly ctx-image update (Lionel)
v12: Rework OA context registers update again by swithing away from
user contexts and reconfiguring the kernel context through the
batchbuffer and updating all the other contexts' context image.
Also take care to lock slice/subslice configuration when OA is
on. (Lionel)
v13: Request rpcs updates on all engine when updating the OA config
(Lionel)
v14: Drop any kind of rpcs management now that we monitor sseu
configuration changes in a later patch (Lionel)
Remove usleep after programming the NOA configs on Gen8+, this
doesn't seem to be needed (Lionel)
v15: Respect coding style for block comments (Chris)
v16: Add missing i915_add_request() in case we fail to emit OA
configuration (Matthew)
Signed-off-by: Robert Bragg <robert@sixbynine.org>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com> \o/
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Gen8+ might have mux configurations per slices/subslices. Depending on
whether slices/subslices have been fused off, only part of the
configuration needs to be applied. This change reworks the mux
configurations query mechanism to allow more than one set of registers
to be programmed.
v2: s/n_mux_regs/n_mux_configs/ (Matthew)
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
This change is pre-emptively aiming to avoid a potential cause of kernel
logging noise in case some condition were to result in us seeing invalid
OA reports.
The workaround for the OA unit's tail pointer race condition is what
avoids the primary known cause of invalid reports being seen and with
that in place we aren't expecting to see this notice but it can't be
entirely ruled out.
Just in case some condition does lead to the notice then it's likely
that it will be triggered repeatedly while attempting to append a
sequence of reports and depending on the configured OA sampling
frequency that might be a large number of repeat notices.
v2: (Chris) avoid inconsistent warning on throttle with
printk_ratelimit()
v3: (Matt) init and summarise with stream init/close not driver init/fini
Signed-off-by: Robert Bragg <robert@sixbynine.org>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170511154345.962-9-lionel.g.landwerlin@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
This updates the tail pointer race workaround handling to updating the
'aged' pointer before looking to start aging a new one. There's the
possibility that there is already new data available and so we can
immediately start aging a new pointer without having to first wait for a
later hrtimer callback (and then another to age).
Signed-off-by: Robert Bragg <robert@sixbynine.org>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170511154345.962-8-lionel.g.landwerlin@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
There's a HW race condition between OA unit tail pointer register
updates and writes to memory whereby the tail pointer can sometimes get
ahead of what's been written out to the OA buffer so far (in terms of
what's visible to the CPU).
Although this can be observed explicitly while copying reports to
userspace by checking for a zeroed report-id field in tail reports, we
want to account for this earlier, as part of the _oa_buffer_check to
avoid lots of redundant read() attempts.
Previously the driver used to define an effective tail pointer that
lagged the real pointer by a 'tail margin' measured in bytes derived
from OA_TAIL_MARGIN_NSEC and the configured sampling frequency.
Unfortunately this was flawed considering that the OA unit may also
automatically generate non-periodic reports (such as on context switch)
or the OA unit may be enabled without any periodic sampling.
This improves how we define a tail pointer for reading that lags the
real tail pointer by at least %OA_TAIL_MARGIN_NSEC nanoseconds, which
gives enough time for the corresponding reports to become visible to the
CPU.
The driver now maintains two tail pointers:
1) An 'aging' tail with an associated timestamp that is tracked until we
can trust the corresponding data is visible to the CPU; at which point
it is considered 'aged'.
2) An 'aged' tail that can be used for read()ing.
The two separate pointers let us decouple read()s from tail pointer aging.
The tail pointers are checked and updated at a limited rate within a
hrtimer callback (the same callback that is used for delivering POLLIN
events) and since we're now measuring the wall clock time elapsed since
a given tail pointer was read the mechanism no longer cares about
the OA unit's periodic sampling frequency.
The natural place to handle the tail pointer updates was in
gen7_oa_buffer_is_empty() which is called as part of blocking reads and
the hrtimer callback used for polling, and so this was renamed to
oa_buffer_check() considering the added side effect while checking
whether the buffer contains data.
Signed-off-by: Robert Bragg <robert@sixbynine.org>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170511154345.962-6-lionel.g.landwerlin@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
This avoids redundantly passing an (inout) head and tail pointer to
gen7_append_oa_reports() from gen7_oa_read which doesn't need to
reference either itself.
Moving the head/tail reads and writes into gen7_append_oa_reports should
have no functional effect except to avoid some redundant head pointer
writes in cases where nothing was copied to userspace.
This is a stepping stone towards updating how the head and tail pointer
state is managed to improve the workaround for the OA unit's tail
pointer race. It reduces the number of places we need to read/write the
head and tail pointers.
Signed-off-by: Robert Bragg <robert@sixbynine.org>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170511154345.962-5-lionel.g.landwerlin@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
There's no need for the driver to keep reading back the head pointer
from hardware since the hardware doesn't update it automatically. This
way we can treat any invalid head pointer value as a software/driver
bug instead of spurious hardware behaviour.
This change is also a small stepping stone towards re-working how
the head and tail state is managed as part of an improved workaround
for the tail register race condition.
Signed-off-by: Robert Bragg <robert@sixbynine.org>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20170511154345.962-4-lionel.g.landwerlin@intel.com
If the function for checking whether there is OA buffer data available
(during a poll or blocking read) has false positives then we want to
avoid a situation where the subsequent read() returns EAGAIN (after
a more accurate check) followed by a poll() immediately reporting
the same false positive POLLIN event and effectively maintaining a
busy loop until there really is data.
This makes sure that we clear the .pollin event status whenever we
return EAGAIN to userspace which will throttle subsequent POLLIN events
and repeated attempts to read to the 5ms intervals of the hrtimer
callback we have.
Signed-off-by: Robert Bragg <robert@sixbynine.org>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170511154345.962-3-lionel.g.landwerlin@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Since unifying ringbuffer/execlist submission to use
engine->pin_context, we ensure that the intel_ring is available before
we start constructing the request. We can therefore move the assignment
of the request->ring to the central i915_gem_request_alloc() and not
require it in every engine->request_alloc() callback. Another small step
towards simplification (of the core, but at a cost of handling error
pointers in less important callers of engine->pin_context).
v2: Rearrange a few branches to reduce impact of PTR_ERR() on gcc's code
generation.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Oscar Mateo <oscar.mateo@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170504093308.4137-1-chris@chris-wilson.co.uk
Don't throw a warning if we are given an invalid property id. While
here let's also bring back Robert' original idea of catching unhandled
enumeration values at compile time.
Fixes: eec688e142 ("drm/i915: Add i915 perf infrastructure")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Robert Bragg <robert@sixbynine.org>
Reviewed-by: Robert Bragg <robert@sixbynine.org>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170327203236.18276-1-matthew.auld@intel.com
Lionel Landwerlin