The majority of runtime-pm operations are bounded and scoped within a
function; these are easy to verify that the wakeref are handled
correctly. We can employ the compiler to help us, and reduce the number
of wakerefs tracked when debugging, by passing around cookies provided
by the various rpm_get functions to their rpm_put counterpart. This
makes the pairing explicit, and given the required wakeref cookie the
compiler can verify that we pass an initialised value to the rpm_put
(quite handy for double checking error paths).
For regular builds, the compiler should be able to eliminate the unused
local variables and the program growth should be minimal. Fwiw, it came
out as a net improvement as gcc was able to refactor rpm_get and
rpm_get_if_in_use together,
v2: Just s/rpm_put/rpm_put_unchecked/ everywhere, leaving the manual
mark up for smaller more targeted patches.
v3: Mention the cookie in Returns
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190114142129.24398-2-chris@chris-wilson.co.uk
Everytime we take a wakeref, record the stack trace of where it was
taken; clearing the set if we ever drop back to no owners. For debugging
a rpm leak, we can look at all the current wakerefs and check if they
have a matching rpm_put.
v2: Use skip=0 for unwinding the stack as it appears our noinline
function doesn't appear on the stack (nor does save_stack_trace itself!)
v3: Allow rpm->debug_count to disappear between inspections and so
avoid calling krealloc(0) as that may return a ZERO_PTR not NULL! (Mika)
v4: Show who last acquire/released the runtime pm
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Tested-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190114142129.24398-1-chris@chris-wilson.co.uk
The wait-for-idle used from within the shrinker_lock_uninterruptible
depends on the struct_mutex locking state being known and declared to
i915_request_wait(). As it is conceivable that we reach the vmap
notifier from underneath struct_mutex (and so keep on relying on the
mutex_trylock_recursive), we should not blindly call i915_request_wait.
In the process we can remove the dubious polling to acquire
struct_mutex, and simply act, or not, on a successful trylock.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190109164204.23935-2-chris@chris-wilson.co.uk
If the current process is being killed (it was interrupted with SIGKILL
or equivalent), it will not make any progress in page allocation and we
can abort performing the shrinking on its behalf. So we can use
mutex_lock_killable() instead (although this path should only be
reachable from kswapd currently).
Tvrtko pointed out that it should also be reachable from debugfs, which
he would prefer retain its interruptiblity. As a compromise, killable is a
step in the right direction!
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190109164204.23935-1-chris@chris-wilson.co.uk
If we find an incompletely setup vma inside the request/engine at the
time of a hang, it may not have vma->pages initialised, so skip
capturing the object before we iterate over NULL.
Spotted by Matthew in preparation for using unpinned vma to track engine
state.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190110111522.11023-1-chris@chris-wilson.co.uk
The only gen8+ platform that has the feature is BDW, but we don't define
the feature flag on any BDW platform and we only have partial support in
the gen8 path (irq enabling code, but no handler).
The only thing we could do in the irq handler is report the error
to userspace, but no one asked/cared about that since BDW was
released so it is relatively safe to assume that even if we added the
message no one would look at it. Just drop the dead code from the
driver instead.
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190109213147.16851-1-daniele.ceraolospurio@intel.com
commit 4a15c75c42 ("drm/i915: Introduce per-engine workarounds")
refactored the workaround code to have functions per-engine, but didn't
call any of them from logical_xcs_ring_init. Since we do have a non-RCS
workaround for KBL (WaKBLVECSSemaphoreWaitPoll) we do need to call
intel_engine_init_workarounds for non-RCS engines.
Note that whitelist is still RCS-only.
v2: move the call to logical_ring_init (Chris)
Fixes: 4a15c75c42 ("drm/i915: Introduce per-engine workarounds")
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190110013232.8972-2-daniele.ceraolospurio@intel.com
By using the wa lists inside the live driver structures, we won't
catch issues where those are incorrectly setup or corrupted.
To cover this gap, update the workaround framework to allow saving the
wa lists to independent structures and use them in the selftests.
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190110013232.8972-1-daniele.ceraolospurio@intel.com
[tursulin: Fixup checkpatch whitespace complaint in memset.]
In the continual quest to reduce the amount of global work required when
submitting requests, replace i915_retire_requests() after allocation
failure to retiring just our ring.
v2: Don't forget the list iteration included an early break, so we would
never throttle on the last request in the ring/timeline.
v3: Use the common ring_retire_requests()
References: 11abf0c5a0 ("drm/i915: Limit the backpressure for i915_request allocation")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190109215932.26454-1-chris@chris-wilson.co.uk
Add support for PMIC MIPI sequences using the new
intel_soc_pmic_exec_mipi_pmic_seq_element function.
This fixes the DSI LCD panel not lighting up when not initialized by the
GOP (because an external monitor was connected) on GPD win and GPD pocket
devices.
Specifically the LCD panel seems to need GPIO pin 9 on the PMIC to be
driven high, which is done through a PMIC MIPI sequence. Before this commit
if the sequence was not executed by the GOP the pin would stay low causing
the LCD panel to not work. Having the MIPI sequences properly control this
GPIO should also help save some power when the panel is off.
Changes in v2, v3:
-Only changes to other patches in this patch-set
Changes in v4:
-Move decoding of the raw 15 bytes PMIC MIPI sequence element into
i2c-address, register-address, value and mask into the mipi_exec_pmic()
function instead of passing the raw data to
intel_soc_pmic_exec_mipi_pmic_seq_element()
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190107111556.4510-5-hdegoede@redhat.com
Needs just a few additional includes here and there.
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190108082709.3748-1-jani.nikula@intel.com
If we haven't shipped and enabled firmware for a particular platform,
there is nothing the user can do about it. Don't scare the user with an
unactionable, unidentifiable warning!
<6> [310.769452] i915 0000:00:02.0: GuC: No firmware known for this platform!
<4> [310.769458] [drm] HuC: No firmware known for this platform!
Unify both GuC/HuC messages to include the device for which we lack the
firmware, and provide the platform name as an aide-memoire.
v2: Move and refine the message to common site of intel_uc_fw_fetch.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190108150246.1471-1-chris@chris-wilson.co.uk
Ignore trying to shrink from i915 if we fail to acquire the struct_mutex
in the shrinker while performing direct-reclaim. The trade-off being
(much) lower latency for non-i915 clients at an increased risk of being
unable to obtain a page from direct-reclaim without hitting the
oom-notifier. The proviso being that we still keep trying to hard
obtain the lock for kswapd so that we can reap under heavy memory
pressure.
v2: Taint all mutexes taken within the shrinker with the struct_mutex
subclass as an early warning system, and drop I915_SHRINK_ACTIVE from
vmap to reduce the number of dangerous paths. We also have to drop
I915_SHRINK_ACTIVE from oom-notifier to be able to make the same claim
that ACTIVE is only used from outside context, which fits in with a
longer strategy of avoiding stalls due to scanning active during
shrinking.
The danger in using the subclass struct_mutex is that we declare
ourselves more knowledgable than lockdep and deprive ourselves of
automatic coverage. Instead, we require ourselves to mark up any mutex
taken inside the shrinker in order to detect lock-inversion, and if we
miss any we are doomed to a deadlock at the worst possible moment.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190107115509.12523-1-chris@chris-wilson.co.uk
Generally catch up with 5.0-rc1, and specifically get the changes:
96d4f267e4 ("Remove 'type' argument from access_ok() function")
0b2c8f8b6b ("i915: fix missing user_access_end() in page fault exception case")
594cc251fd ("make 'user_access_begin()' do 'access_ok()'")
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Include the total size of closed vma when reporting the per_ctx_stats of
debugfs/i915_gem_objects.
Whilst adjusting the context tracking, note that we can simply use our
list of contexts in i915->contexts rather than circumlocute via
dev->filelist and the per-file context idr, with the result that we can
show objects allocated to different vm (i.e. contexts within a file).
We change the output to show every context of each client, with its own
unique set of objects (for full-ppgtt machines, i.e. gen7+, for older
hardware all objects are in the global gtt and so can not be associated
with a single context). That should result in no loss of information,
and for gen7+, no duplication of active objects.
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/20190107115509.12523-2-chris@chris-wilson.co.uk
Haswell also requires the RING_IMR flush for its unique vebox setup to
avoid losing interrupts, as per 476af9c260 ("drm/i915/gen6: Flush
RING_IMR changes before changing the global GT IMR"):
On Baytail, notably, we can still detect missed interrupt syndrome
(where we never spot a completed request). In this case, it can be
alleviated by always keeping the interrupt unmasked, implying that the
interrupt is being lost in the window after modifying the IMR. (This is
the reason we still have the posting reads on enable_irq, if we remove
them we miss interrupts!) Having narrowed the issue down to the IMR,
rather than keeping it always enabled, applying the usual posting
read/flush of the RING_IMR before unmasking the GT IMR also seems to
prevent the missed interrupt. So be it.
References: 476af9c260 ("drm/i915/gen6: Flush RING_IMR changes before changing the global GT IMR")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190105115647.4970-1-chris@chris-wilson.co.uk
CC [M] drivers/gpu/drm/i915/intel_device_info.o
drivers/gpu/drm/i915/intel_device_info.c:727: warning: Function parameter or member 'dev_priv' not described in 'intel_device_info_runtime_init'
drivers/gpu/drm/i915/intel_device_info.c:727: warning: Excess function parameter 'info' description in 'intel_device_info_runtime_init'
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190105014652.3472-1-chris@chris-wilson.co.uk
-----BEGIN PGP SIGNATURE-----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=hFld
-----END PGP SIGNATURE-----
Merge tag 'drm-next-2019-01-05' of git://anongit.freedesktop.org/drm/drm
Pull drm fixes from Dave Airlie:
"Happy New Year, just decloaking from leave to get some stuff from the
last week in before rc1:
core:
- two regression fixes for damage blob and atomic
i915 gvt:
- Some missed GVT fixes from the original pull
amdgpu:
- new PCI IDs
- SR-IOV fixes
- DC fixes
- Vega20 fixes"
* tag 'drm-next-2019-01-05' of git://anongit.freedesktop.org/drm/drm: (53 commits)
drm: Put damage blob when destroy plane state
drm: fix null pointer dereference on null state pointer
drm/amdgpu: Add new VegaM pci id
drm/ttm: Use drm_debug_printer for all ttm_bo_mem_space_debug output
drm/amdgpu: add Vega20 PSP ASD firmware loading
drm/amd/display: Fix MST dp_blank REG_WAIT timeout
drm/amd/display: validate extended dongle caps
drm/amd/display: Use div_u64 for flip timestamp ns to ms
drm/amdgpu/uvd:Change uvd ring name convention
drm/amd/powerplay: add Vega20 LCLK DPM level setting support
drm/amdgpu: print process info when job timeout
drm/amdgpu/nbio7.4: add hw bug workaround for vega20
drm/amdgpu/nbio6.1: add hw bug workaround for vega10/12
drm/amd/display: Optimize passive update planes.
drm/amd/display: verify lane status before exiting verify link cap
drm/amd/display: Fix bug with not updating VSP infoframe
drm/amd/display: Add retry to read ddc_clock pin
drm/amd/display: Don't skip link training for empty dongle
drm/amd/display: Wait edp HPD to high in detect_sink
drm/amd/display: fix surface update sequence
...
Our attempt to account for bit17 swizzling of pread/pwrite onto tiled
objects was flawed due to the simple fact that we do not always know the
swizzling for a particular page (due to the swizzling varying based on
location in certain unbalanced configurations). Furthermore, the
pread/pwrite paths are now unbalanced in that we are required to use the
GTT as in some cases we do not have direct CPU access to the backing
physical pages (thus some paths trying to account for the swizzle, but
others neglecting, chaos ensues).
There are no known users who do use pread/pwrite into a tiled object
(you need to manually detile anyway, so why now just use mmap and avoid
the copy?) and no user bug reports to indicate that it is being used in
the wild. As no one is hitting the buggy path, we can just remove the
buggy code.
v2: Just use the fault allowing kmap() + normal copy_(to|from)_user
v3: Avoid int overflow in computing 'length' from 'remain' (Tvrtko)
References: fe115628d5 ("drm/i915: Implement pwrite without struct-mutex")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Acked-by: Kenneth Graunke <kenneth@whitecape.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20190105120758.9237-1-chris@chris-wilson.co.uk
Originally, the rule used to be that you'd have to do access_ok()
separately, and then user_access_begin() before actually doing the
direct (optimized) user access.
But experience has shown that people then decide not to do access_ok()
at all, and instead rely on it being implied by other operations or
similar. Which makes it very hard to verify that the access has
actually been range-checked.
If you use the unsafe direct user accesses, hardware features (either
SMAP - Supervisor Mode Access Protection - on x86, or PAN - Privileged
Access Never - on ARM) do force you to use user_access_begin(). But
nothing really forces the range check.
By putting the range check into user_access_begin(), we actually force
people to do the right thing (tm), and the range check vill be visible
near the actual accesses. We have way too long a history of people
trying to avoid them.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When commit fddcd00a49 ("drm/i915: Force the slow path after a
user-write error") unified the error handling for various user access
problems, it didn't do the user_access_end() that is needed for the
unsafe_put_user() case.
It's not a huge deal: a missed user_access_end() will only mean that
SMAP protection isn't active afterwards, and for the error case we'll be
returning to user mode soon enough anyway. But it's wrong, and adding
the proper user_access_end() is trivial enough (and doing it for the
other error cases where it isn't needed doesn't hurt).
I noticed it while doing the same prep-work for changing
user_access_begin() that precipitated the access_ok() changes in commit
96d4f267e4 ("Remove 'type' argument from access_ok() function").
Fixes: fddcd00a49 ("drm/i915: Force the slow path after a user-write error")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: stable@kernel.org # v4.20
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
If we declare the driver wedged during early initialisation, we leave
the driver in an undefined state (with respect to GEM execution). As
this leads to unexpected behaviour if we allow the user to unwedge the
device (through debugfs, and performed by igt at test start), do not.
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/20190103213340.1669-1-chris@chris-wilson.co.uk
Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument
of the user address range verification function since we got rid of the
old racy i386-only code to walk page tables by hand.
It existed because the original 80386 would not honor the write protect
bit when in kernel mode, so you had to do COW by hand before doing any
user access. But we haven't supported that in a long time, and these
days the 'type' argument is a purely historical artifact.
A discussion about extending 'user_access_begin()' to do the range
checking resulted this patch, because there is no way we're going to
move the old VERIFY_xyz interface to that model. And it's best done at
the end of the merge window when I've done most of my merges, so let's
just get this done once and for all.
This patch was mostly done with a sed-script, with manual fix-ups for
the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form.
There were a couple of notable cases:
- csky still had the old "verify_area()" name as an alias.
- the iter_iov code had magical hardcoded knowledge of the actual
values of VERIFY_{READ,WRITE} (not that they mattered, since nothing
really used it)
- microblaze used the type argument for a debug printout
but other than those oddities this should be a total no-op patch.
I tried to fix up all architectures, did fairly extensive grepping for
access_ok() uses, and the changes are trivial, but I may have missed
something. Any missed conversion should be trivially fixable, though.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When we first introduced the reset to sanitize the GPU on taking over
from the BIOS and before returning control to third parties (the BIOS!),
we restricted it to only systems utilizing HW contexts as we were
uncertain of how stable our reset mechanism truly was. We now have
reasonable coverage across all machines that expose a GPU reset method,
and so we should be safe to sanitize the GPU state everywhere.
v2: We _have_ to skip the reset if it would clobber the display.
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/20190103112104.19561-1-chris@chris-wilson.co.uk
As the question of 32b/64b kernels became relevant in the light of
certain bugs, include that information in the error state.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Acked-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190103101245.15100-1-chris@chris-wilson.co.uk
On Baytail, notably, we can still detect missed interrupt syndrome
(where we never spot a completed request). In this case, it can be
alleviated by always keeping the interrupt unmasked, implying that the
interrupt is being lost in the window after modifying the IMR. (This is
the reason we still have the posting reads on enable_irq, if we remove
them we miss interrupts!) Having narrowed the issue down to the IMR,
rather than keeping it always enabled, applying the usual posting
read/flush of the RING_IMR before unmasking the GT IMR also seems to
prevent the missed interrupt. So be it.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190102163524.19353-1-chris@chris-wilson.co.uk
With kasan on a slow machine, it can take an age to check all the
partial mappings in a single iteration, so break it up with a
cond_resched) to avoid RCU stall reports.
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/20190102114431.23022-1-chris@chris-wilson.co.uk
The debugfs, error state and regular dmesg logging dump needs seem to be
different. Remove the generic dump function only used for the welcome
message. This may be added back later when better abstractions are
identified, but at the moment this seems to be the simplest considering
the device info rework in progress. No longer rely on device info being
a substruct of dev_priv.
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/70ff0c7c0ec3ef8747af3c78e272b5a82be3d55b.1546267488.git.jani.nikula@intel.com
Including (in no particular order):
- Page table code for AMD IOMMU now supports large pages where
smaller page-sizes were mapped before. VFIO had to work around
that in the past and I included a patch to remove it (acked by
Alex Williamson)
- Patches to unmodularize a couple of IOMMU drivers that would
never work as modules anyway.
- Work to unify the the iommu-related pointers in
'struct device' into one pointer. This work is not finished
yet, but will probably be in the next cycle.
- NUMA aware allocation in iommu-dma code
- Support for r8a774a1 and r8a774c0 in the Renesas IOMMU driver
- Scalable mode support for the Intel VT-d driver
- PM runtime improvements for the ARM-SMMU driver
- Support for the QCOM-SMMUv2 IOMMU hardware from Qualcom
- Various smaller fixes and improvements
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2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=DT9A
-----END PGP SIGNATURE-----
Merge tag 'iommu-updates-v4.21' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull IOMMU updates from Joerg Roedel:
- Page table code for AMD IOMMU now supports large pages where smaller
page-sizes were mapped before. VFIO had to work around that in the
past and I included a patch to remove it (acked by Alex Williamson)
- Patches to unmodularize a couple of IOMMU drivers that would never
work as modules anyway.
- Work to unify the the iommu-related pointers in 'struct device' into
one pointer. This work is not finished yet, but will probably be in
the next cycle.
- NUMA aware allocation in iommu-dma code
- Support for r8a774a1 and r8a774c0 in the Renesas IOMMU driver
- Scalable mode support for the Intel VT-d driver
- PM runtime improvements for the ARM-SMMU driver
- Support for the QCOM-SMMUv2 IOMMU hardware from Qualcom
- Various smaller fixes and improvements
* tag 'iommu-updates-v4.21' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (78 commits)
iommu: Check for iommu_ops == NULL in iommu_probe_device()
ACPI/IORT: Don't call iommu_ops->add_device directly
iommu/of: Don't call iommu_ops->add_device directly
iommu: Consolitate ->add/remove_device() calls
iommu/sysfs: Rename iommu_release_device()
dmaengine: sh: rcar-dmac: Use device_iommu_mapped()
xhci: Use device_iommu_mapped()
powerpc/iommu: Use device_iommu_mapped()
ACPI/IORT: Use device_iommu_mapped()
iommu/of: Use device_iommu_mapped()
driver core: Introduce device_iommu_mapped() function
iommu/tegra: Use helper functions to access dev->iommu_fwspec
iommu/qcom: Use helper functions to access dev->iommu_fwspec
iommu/of: Use helper functions to access dev->iommu_fwspec
iommu/mediatek: Use helper functions to access dev->iommu_fwspec
iommu/ipmmu-vmsa: Use helper functions to access dev->iommu_fwspec
iommu/dma: Use helper functions to access dev->iommu_fwspec
iommu/arm-smmu: Use helper functions to access dev->iommu_fwspec
ACPI/IORT: Use helper functions to access dev->iommu_fwspec
iommu: Introduce wrappers around dev->iommu_fwspec
...
Now that we have eliminated the CPU-side irq_seqno_barrier by moving the
delays on the GPU before emitting the MI_USER_INTERRUPT, we can remove
the engine->irq_seqno_barrier infrastructure. Though intentionally
slowing down the GPU is nasty, so is the code we can now remove!
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181228171641.16531-6-chris@chris-wilson.co.uk
The irq_seqno_barrier is a tradeoff between doing work on every request
(on the GPU) and doing work after every interrupt (on the CPU). We
presume we have many more requests than interrupts! However, for
Ironlake, the workaround is a pretty hideous usleep() and so even though
it was found we need to repeat the MI_STORE_DWORD_IMM 8 times, or about
1us of GPU time, doing so is preferrable than requiring a sleep of
125-250us on the CPU where we desire to respond immediately (ideally from
within the interrupt handler)!
The additional MI_STORE_DWORD_IMM also have the side-effect of flushing
MI operations from userspace which are not caught by MI_FLUSH!
Testcase: igt/gem_sync
Testcase: igt/gem_exec_whisper
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181228171641.16531-5-chris@chris-wilson.co.uk
The irq_seqno_barrier is a tradeoff between doing work on every request
(on the GPU) and doing work after every interrupt (on the CPU). We
presume we have many more requests than interrupts! However, the current
w/a for Ivybridge is an implicit delay that currently fails sporadically
and consistently if we move the w/a into the irq handler itself. This
makes the CPU barrier untenable for upcoming interrupt handler changes
and so we need to replace it with a delay on the GPU before we send the
MI_USER_INTERRUPT. As it turns out that delay is 32x MI_STORE_DWORD_IMM,
or about 0.6us per request! Quite nasty, but the lesser of two evils
looking to the future.
Testcase: igt/gem_sync
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181228171641.16531-4-chris@chris-wilson.co.uk
The MI_FLUSH_DW does appear coherent with the following
MI_USER_INTERRUPT, but only on Sandybridge. Ivybridge requires a heavier
hammer, but on Sandybridge we can stop requiring the irq_seqno barrier.
Testcase: igt/gem_sync
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181228171641.16531-3-chris@chris-wilson.co.uk
Having transitioned to using PIPECONTROL to combine the flush with the
breadcrumb write using their post-sync functions, assume that this will
resolve the serialisation with the subsequent MI_USER_INTERRUPT. That is
when inspecting the breadcrumb after an interrupt we can rely on the write
being posted (i.e. the HWSP will be coherent).
Testing using gem_sync shows that the PIPECONTROL + CS stall does
serialise the command streamer sufficient that the breadcrumb lands
before the MI_USER_INTERRUPT. The same is not true for MI_FLUSH_DW.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181228171641.16531-2-chris@chris-wilson.co.uk
Now that we perform the request flushing inline with emitting the
breadcrumb, we can remove the now redundant manual flush. And we can
also remove the infrastructure that remained only for its purpose.
v2: emit_breadcrumb_sz is in dwords, but rq->reserved_space is in bytes
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181228171641.16531-1-chris@chris-wilson.co.uk
drivers/gpu/drm/i915/intel_display.c:10708: warning: Function parameter or member 'cur' not described in 'intel_wm_need_update'
drivers/gpu/drm/i915/intel_display.c:10708: warning: Function parameter or member 'new' not described in 'intel_wm_need_update'
drivers/gpu/drm/i915/intel_display.c:10708: warning: Excess function parameter 'plane' description in 'intel_wm_need_update'
drivers/gpu/drm/i915/intel_display.c:10708: warning: Excess function parameter 'state' description in 'intel_wm_need_update'
References: cd1d3ee90e ("drm/i915: Use intel_ types more consistently for watermark code (v2)")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181231143505.2523-1-chris@chris-wilson.co.uk
It is only initialized to zero once so does not need an explicit
initializer.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181231122212.1667-1-jani.nikula@intel.com
