summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm
Commit message (Collapse)AuthorAgeFilesLines
* Merge tag 'drm-intel-fixes-2015-01-29' of ↵Dave Airlie2015-01-304-26/+19
|\ | | | | | | | | | | | | | | | | | | | | | | | | git://anongit.freedesktop.org/drm-intel into drm-fixes misc i915 fixes, mostly all stable material as well. * tag 'drm-intel-fixes-2015-01-29' of git://anongit.freedesktop.org/drm-intel: drm/i915: BDW Fix Halo PCI IDs marked as ULT. drm/i915: Fix and clean BDW PCH identification drm/i915: Only fence tiled region of object. drm/i915: fix inconsistent brightness after resume drm/i915: Init PPGTT before context enable
| * drm/i915: BDW Fix Halo PCI IDs marked as ULT.Rodrigo Vivi2015-01-261-2/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | BDW with PCI-IDs ended in "2" aren't ULT, but HALO. Let's fix it and at least allow VGA to work on this units. v2: forgot ammend and v1 doesn't compile Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=87220 Cc: Xion Zhang <xiong.y.zhang@intel.com> Cc: Guo Jinxian <jinxianx.guo@intel.com> Cc: Jani Nikula <jani.nikula@intel.com> Cc: Stable <stable@vger.kernel.org> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com>
| * drm/i915: Fix and clean BDW PCH identificationRodrigo Vivi2015-01-261-10/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | It seems in the past we have BDW with PCH not been propperly identified and we force it to be LPT and we were warning !IS_HASWELL on propper identification. Now that products are out there we are receiveing logs with this incorrect WARN. And also according to local tests on all production BDW here ULT or HALO we don't need this force anymore. So let's clean this block for real. v2: Fix LPT_LP WARNs to avoid wrong warns on BDW_ULT (By Jani). Reference: https://bugs.freedesktop.org/attachment.cgi?id=110972 Cc: Jani Nikula <jani.nikula@intel.com> Cc: Paulo Zanoni <paulo.r.zanoni@intel.com> Cc: Xion Zhang <xiong.y.zhang@intel.com> Cc: stable@vger.kernel.org Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com>
| * drm/i915: Only fence tiled region of object.Bob Paauwe2015-01-261-0/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When creating a fence for a tiled object, only fence the area that makes up the actual tiles. The object may be larger than the tiled area and if we allow those extra addresses to be fenced, they'll get converted to addresses beyond where the object is mapped. This opens up the possiblity of writes beyond the end of object. To prevent this, we adjust the size of the fence to only encompass the area that makes up the actual tiles. The extra space is considered un-tiled and now behaves as if it was a linear object. Testcase: igt/gem_tiled_fence_overflow Reported-by: Dan Hettena <danh@ghs.com> Signed-off-by: Bob Paauwe <bob.j.paauwe@intel.com> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: stable@vger.kernel.org Signed-off-by: Jani Nikula <jani.nikula@intel.com>
| * drm/i915: fix inconsistent brightness after resumeJeremiah Mahler2015-01-261-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | commit 6dda730e55f412a6dfb181cae6784822ba463847 Author: Jani Nikula <jani.nikula@intel.com> Date: Tue Jun 24 18:27:40 2014 +0300 drm/i915: respect the VBT minimum backlight brightness introduced a bug which resulted in inconsistent brightness levels on different machines. If a suspended was entered with the screen off some machines would resume with the screen at minimum brightness and others at maximum brightness. The following commands can be used to produce this behavior. xset dpms force off sleep 1 sudo systemctl suspend (resume ...) The root cause of this problem is a comparison which checks to see if the backlight level is zero when the panel is enabled. If it is zero, it is set to the maximum level. Unfortunately, not all machines have a minimum level of zero. On those machines the level is left at the minimum instead of begin set to the maximum. Fix the bug by updating the comparison to check for the minimum backlight level instead of zero. Also, expand the comparison for the possible case when the level is less than the minimum. Fixes: 6dda730e55f4 ("respect the VBT minimum backlight brightness") Signed-off-by: Jeremiah Mahler <jmmahler@gmail.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com>
| * drm/i915: Init PPGTT before context enableDavid Woodhouse2015-01-261-13/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit 82460d972 ("drm/i915: Rework ppgtt init to no require an aliasing ppgtt") introduced a regression on Broadwell, triggering the following IOMMU fault at startup: vgaarb: device changed decodes: PCI:0000:00:02.0,olddecodes=io+mem,decodes=io+mem:owns=io+mem dmar: DRHD: handling fault status reg 2 dmar: DMAR:[DMA Write] Request device [00:02.0] fault addr 880000 DMAR:[fault reason 23] Unknown fbcon: inteldrmfb (fb0) is primary device Further commentary from Daniel: I sugggested this change to David after staring at the offending patch for a while. I have no idea and theory whatsoever why this would upset the gpu less than the other way round. But it seems to work. David promised to chase hw people a bit more to get a more meaningful answer. Wrt the comment that this deletes: I've done some digging and afaict loading context before ppgtt enable was once required before our recent restructuring of the context/ppgtt init code: Before that context sw setup (i.e. allocating the default context) and hw setup was smashed together. Also the setup of the default context was the bit that actually allocated the aliasing ppgtt structures. Which is the reason for the context before ppgtt depency. Or was, since with all the untangling there's no no real depency any more (functional, who knows what the hw is doing), so the comment is just stale. Signed-off-by: David Woodhouse <David.Woodhouse@intel.com> Cc: stable@vger.kernel.org Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Jani Nikula <jani.nikula@intel.com>
* | drm: fix fb-helper vs MST dangling connector ptrs (v2)Rob Clark2015-01-301-0/+30
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | VT switch back/forth from console to xserver (for example) has potential to go horribly wrong if a dynamic DP MST connector ends up in the saved modeset that is restored when switching back to fbcon. When removing a dynamic connector, don't forget to clean up the saved state. v1: original v2: null out set->fb if no more connectors to avoid making i915 cranky Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1184968 Cc: stable@vger.kernel.org #v3.17+ Signed-off-by: Rob Clark <robdclark@gmail.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
* | Merge branch 'drm-fixes-3.19' of git://people.freedesktop.org/~agd5f/linux ↵Dave Airlie2015-01-2713-53/+111
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | into drm-fixes Suspend/resume regression fix for 3.19. * 'drm-fixes-3.19' of git://people.freedesktop.org/~agd5f/linux: drm/radeon: Remove rdev->gart.pages_addr array drm/radeon: Restore GART table contents after pinning it in VRAM v3 drm/radeon: Split off gart_get_page_entry ASIC hook from set_page_entry
| * | drm/radeon: Remove rdev->gart.pages_addr arrayMichel Dänzer2015-01-226-20/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | radeon_vm_map_gart can use rdev->gart.pages_entry instead. Also move the masking of the page address to radeon_vm_map_gart from its callers. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | drm/radeon: Restore GART table contents after pinning it in VRAM v3Michel Dänzer2015-01-221-0/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The GART table BO has to be moved out of VRAM for suspend/resume. Any updates to the GART table during that time were silently dropped without this change. This caused GPU lockups on resume in some cases, see the bug reports referenced below. This might also make GPU reset more robust in some cases, as we no longer rely on the GART table in VRAM being preserved across the GPU lockup/reset. v2: Add logic to radeon_gart_table_vram_pin directly instead of reinstating radeon_gart_restore v3: Move code after assignment of rdev->gart.table_addr so that the GART TLB flush can work as intended, add code comment explaining why we're doing this Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=85204 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=86267 Reviewed-by: Christian König <christian.koenig@amd.com> Cc: stable@vger.kernel.org Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * | drm/radeon: Split off gart_get_page_entry ASIC hook from set_page_entryMichel Dänzer2015-01-229-37/+100
| |/ | | | | | | | | | | | | | | | | | | | | | | get_page_entry calculates the GART page table entry, which is just written to the GART page table by set_page_entry. This is a prerequisite for the following fix. Reviewed-by: Christian König <christian.koenig@amd.com> Cc: stable@vger.kernel.org Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* | Merge tag 'drm-amdkfd-fixes-2015-01-26' of ↵Dave Airlie2015-01-278-39/+106
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://people.freedesktop.org/~gabbayo/linux into drm-fixes A couple of fixes for -rc7 in amdkfd: - Forgot to free resources when creation of queue has failed - Initialization of pipelines was incorrect (3 patches) In addition, The patch "drm/amdkfd: Allow user to limit only queues per device" is not a fix, but I would like to push it for 3.19 as it changes the ABI between amdkfd and userspace (by changing the module parameters). I would prefer *not* to support the two deprecated module parameters if I don't have too, as amdkfd hasn't been released yet. * tag 'drm-amdkfd-fixes-2015-01-26' of git://people.freedesktop.org/~gabbayo/linux: drm/amdkfd: Fix bug in call to init_pipelines() drm/amdkfd: Fix bug in pipelines initialization drm/radeon: Don't increment pipe_id in kgd_init_pipeline drm/amdkfd: Allow user to limit only queues per device drm/amdkfd: PQM handle queue creation fault
| * | drm/amdkfd: Fix bug in call to init_pipelines()Oded Gabbay2015-01-221-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes a bug where the first_pipe index passed into init_pipelines() was a #define instead of the value that is passed into amdkfd by radeon Signed-off-by: Oded Gabbay <oded.gabbay@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
| * | drm/amdkfd: Fix bug in pipelines initializationOded Gabbay2015-01-221-1/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes a bug when calling to init_pipeline() interface. The index that was passed to that function didn't take into account the first_pipe value, which represents the first pipe index that is under amdkfd's responsibility. Signed-off-by: Oded Gabbay <oded.gabbay@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
| * | drm/radeon: Don't increment pipe_id in kgd_init_pipelineOded Gabbay2015-01-221-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes the behavior of kgd_init_pipeline in that this function shouldn't automatically increase the pipe_id argument by 1 right at the start of the function. This is because the first_pipe value might not be always 1, and because a proper interface function should not hide this info inside its implementation. In other words, the calling function should provide the real pipe_id and not count on kgd_init_pipeline to "fix" it. Signed-off-by: Oded Gabbay <oded.gabbay@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
| * | drm/amdkfd: Allow user to limit only queues per deviceOded Gabbay2015-01-187-36/+96
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch replaces the two current amdkfd module parameters with a new one. The current parameters that are being replaced are: - Maximum number of HSA processes - Maximum number of queues per process The new parameter that replaces them is called "Maximum queues per device" This replacement achieves two goals: - Allows the user to have as many HSA processes as it wants (until a maximum of 512 HSA processes in Kaveri). - Removes the limitation the user had on maximum number of queues per HSA process. E.g. the user can now have processes which only have one queue and other processes which have hundreds of queues, while before the user couldn't have more than 128 queues per process (as default). The default value of the new parameter is 4096 (32 * 128, which were the defaults of the old parameters). There is almost no additional GART memory required for the default case. As a reminder, this amount of queues requires a little bit below 4MB of GART memory. v2: In addition, This patch defines a new counter for queues accounting in the DQM structure. This is done because the current counter only counts active queues which allows the user to create more queues than the max_num_of_queues_per_device module parameter allows. However, we need the current counter for the runlist packet build process, so the solution is to have a dedicated counter for this accounting. Signed-off-by: Oded Gabbay <oded.gabbay@amd.com> Reviewed-by: Ben Goz <ben.goz@amd.com>
| * | drm/amdkfd: PQM handle queue creation faultBen Goz2015-01-151-0/+3
| |/ | | | | | | | | | | | | | | If the first queue created was failed on DQM then PQM should unregister the process from DQM. Signed-off-by: Ben Goz <ben.goz@amd.com> Signed-off-by: Oded Gabbay <oded.gabbay@amd.com>
* | Merge branch 'drm-tda998x-fixes' of ↵Dave Airlie2015-01-271-10/+42
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://ftp.arm.linux.org.uk/~rmk/linux-arm into drm-fixes 3 fixes for the tda998x. * 'drm-tda998x-fixes' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: drm/i2c: tda998x: set the CEC I2C address based on the slave I2C address drm: tda998x: Fix EDID read timeout on HDMI connect drm: tda998x: Protect the page register
| * | drm/i2c: tda998x: set the CEC I2C address based on the slave I2C addressAndrew Jackson2015-01-211-1/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The I2C address for the TDA9989 and TDA19989 is fixed at 0x34 but the two LSBs of the TDA19988's address are set by two configuration pins on the chip. Irrespective of the chip, the associated CEC peripheral's I2C address is based upon the main I2C address. This patch avoids any special handling required to support systems that contain multiple TDA19988 devices on the same I2C bus. Signed-off-by: Andrew Jackson <Andrew.Jackson@arm.com> Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * | drm: tda998x: Fix EDID read timeout on HDMI connectJean-Francois Moine2014-12-011-4/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When the HDMI cable is disconnected and reconnected, EDID reading is called too early raising a EDID read timeout. This patch uses the system work queue to delay the notification of the HDMI connect/disconnect event. Signed-off-by: Jean-Francois Moine <moinejf@free.fr> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * | drm: tda998x: Protect the page registerJean-Francois Moine2014-12-011-5/+20
| | | | | | | | | | | | | | | | | | | | | | | | As the HDMI registers of the TDA998x chips are accessed by pages, the page register must be protected. Signed-off-by: Jean-Francois Moine <moinejf@free.fr> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* | | Merge branch 'vmwgfx-fixes-3.19' of ↵Dave Airlie2015-01-227-86/+56
|\ \ \ | |_|/ |/| | | | | | | | | | | | | | | | | | | | git://people.freedesktop.org/~thomash/linux into drm-fixes fix a vmwgfx regression sleeping wrong task state. * 'vmwgfx-fixes-3.19' of git://people.freedesktop.org/~thomash/linux: drm/vmwgfx: Replace the hw mutex with a hw spinlock
| * | drm/vmwgfx: Replace the hw mutex with a hw spinlockThomas Hellstrom2015-01-197-86/+56
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fixes a case where we call vmw_fifo_idle() from within a wait function with task state !TASK_RUNNING, which is illegal. In addition, make the locking fine-grained, so that it is performed once for every read- and write operation. This is of course more costly, but we don't perform much register access in the timing critical paths anyway. Instead we have the extra benefit of being sure that we don't forget the hw lock around register accesses. I think currently the kms code was quite buggy w r t this. This fixes Red Hat Bugzilla Bug 1180796 Cc: stable@vger.kernel.org Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
* | | Merge tag 'drm-amdkfd-fixes-2015-01-13' of ↵Dave Airlie2015-01-215-213/+3
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://people.freedesktop.org/~gabbayo/linux into drm-fixes - Remove the interrupt SW ring buffer impl. as it is not used by any module in amdkfd. - Fix a sparse warning * tag 'drm-amdkfd-fixes-2015-01-13' of git://people.freedesktop.org/~gabbayo/linux: drm/amdkfd: Fix sparse warning (different address space) drm/amdkfd: Drop interrupt SW ring buffer
| * | | drm/amdkfd: Fix sparse warning (different address space)Oded Gabbay2015-01-081-1/+1
| | | | | | | | | | | | | | | | Signed-off-by: Oded Gabbay <oded.gabbay@amd.com>
| * | | drm/amdkfd: Drop interrupt SW ring bufferMichel Dänzer2015-01-084-212/+2
| |/ / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The work queue couldn't reliably prevent the SW ring buffer from overflowing, so dmesg was spammed by kfd kfd: Interrupt ring overflow, dropping interrupt. messages when running e.g. the Atlantis Substance demo from https://wiki.unrealengine.com/Linux_Demos on Kaveri. Since the SW ring buffer doesn't actually do anything at this point, just remove it for now. When actual interrupt processing code is added to amdkfd, it should try to do things immediately and only defer to work queues when necessary. Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Oded Gabbay <oded.gabbay@amd.com>
* | | Merge tag 'drm-intel-fixes-2015-01-15' of ↵Dave Airlie2015-01-215-15/+24
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://anongit.freedesktop.org/drm-intel into drm-fixes misc i915 fixes * tag 'drm-intel-fixes-2015-01-15' of git://anongit.freedesktop.org/drm-intel: drm/i915: Fix mutex->owner inspection race under DEBUG_MUTEXES drm/i915: Ban Haswell from using RCS flips drm/i915: vlv: sanitize RPS interrupt mask during GPU idling drm/i915: fix HW lockup due to missing RPS IRQ workaround on GEN6 drm/i915: gen9: fix RPS interrupt routing to CPU vs. GT
| * | | drm/i915: Fix mutex->owner inspection race under DEBUG_MUTEXESChris Wilson2015-01-121-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If CONFIG_DEBUG_MUTEXES is set, the mutex->owner field is only cleared if the mutex debugging is enabled which introduces a race in our mutex_is_locked_by() - i.e. we may inspect the old owner value before it is acquired by the new task. This is the root cause of this error: diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c index 5cf6731..3ef3736 100644 --- a/kernel/locking/mutex-debug.c +++ b/kernel/locking/mutex-debug.c @@ -80,13 +80,13 @@ void debug_mutex_unlock(struct mutex *lock) DEBUG_LOCKS_WARN_ON(lock->owner != current); DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); - mutex_clear_owner(lock); } /* * __mutex_slowpath_needs_to_unlock() is explicitly 0 for debug * mutexes so that we can do it here after we've verified state. */ + mutex_clear_owner(lock); atomic_set(&lock->count, 1); } Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=87955 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: stable@vger.kernel.org Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Jani Nikula <jani.nikula@intel.com>
| * | | drm/i915: Ban Haswell from using RCS flipsChris Wilson2015-01-121-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Like Ivybridge, we have reports that we get random hangs when flipping with multiple pipes. Extend commit 2a92d5bca1999b69c78f3c3e97b5484985b094b9 Author: Chris Wilson <chris@chris-wilson.co.uk> Date: Tue Jul 8 10:40:29 2014 +0100 drm/i915: Disable RCS flips on Ivybridge to also apply to Haswell. Reported-and-tested-by: Scott Tsai <scottt.tw@gmail.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=87759 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: stable@vger.kernel.org # 2a92d5bca199 drm/i915: Disable RCS flips on Ivybridge Cc: stable@vger.kernel.org Signed-off-by: Jani Nikula <jani.nikula@intel.com>
| * | | drm/i915: vlv: sanitize RPS interrupt mask during GPU idlingImre Deak2015-01-122-2/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We apply the RPS interrupt workaround on VLV everywhere except when writing the mask directly during idling the GPU. For consistency do this also there. While at it also extend the code comment about affected platforms. I couldn't reproduce the issue on VLV fixed by this workaround, by removing the workaround from everywhere, while it's 100% reproducible on SNB using igt/gem_reset_stats/ban-ctx-render. So also add a note that it hasn't been verified if the workaround really applies to VLV/CHV. Suggested-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Jani Nikula <jani.nikula@intel.com>
| * | | drm/i915: fix HW lockup due to missing RPS IRQ workaround on GEN6Imre Deak2015-01-123-12/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In commit dbea3cea69508e9d548ed4a6be13de35492e5d15 Author: Imre Deak <imre.deak@intel.com> Date: Mon Dec 15 18:59:28 2014 +0200 drm/i915: sanitize RPS resetting during GPU reset we disable RPS interrupts during GPU resetting, but don't apply the necessary GEN6 HW workaround. This leads to a HW lockup during a subsequent "looping batchbuffer" workload. This is triggered by the testcase that submits exactly this kind of workload after a simulated GPU reset. I'm not sure how likely the bug would have triggered otherwise, since we would have applied the workaround anyway shortly after the GPU reset, when enabling GT powersaving from the deferred work. This may also fix unrelated issues, since during driver loading / suspending we also disable RPS interrupts and so we also had a short window during the rest of the loading / resuming where a similar workload could run without the workaround applied. v2: - separate the fix to route RPS interrupts to the CPU on GEN9 too to a separate patch (Daniel) Bisected-by: Ander Conselvan de Oliveira <ander.conselvan.de.oliveira@intel.com> Testcase: igt/gem_reset_stats/ban-ctx-render Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=87429 Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Jani Nikula <jani.nikula@intel.com>
| * | | drm/i915: gen9: fix RPS interrupt routing to CPU vs. GTImre Deak2015-01-121-1/+1
| |/ / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | GEN8+ HW has the option to route PM interrupts to either the CPU or to GT. For GEN8 this was already set correctly to routing to CPU, but not for GEN9, so fix this. Note that when disabling RPS interrupts this was set already correctly, though in that case it didn't matter much except for the possibility of spurious interrupts. Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Jani Nikula <jani.nikula@intel.com>
* | | drm: fb helper should avoid sleeping in panic contextRui Wang2015-01-211-2/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There are still some places in the fb helper that need to avoid sleeping in panic context. Here's an example: [ 65.615496] bad: scheduling from the idle thread! [ 65.620747] CPU: 92 PID: 0 Comm: swapper/92 Tainted: G M E 3.18.0-rc4-7-default+ #20 [ 65.630364] Hardware name: Intel Corporation BRICKLAND/BRICKLAND, BIOS BRHSXSD1.86B.0056.R01.1409242327 09/24/2014 [ 65.641923] ffff88087f693d80 ffff88087f689878 ffffffff81566db9 0000000000000000 [ 65.650226] ffff88087f693d80 ffff88087f689898 ffffffff810871ff ffff88046eb3e0d0 [ 65.658527] ffff88087f693d80 ffff88087f6898c8 ffffffff8107c1fa 000000017f6898b8 [ 65.666830] Call Trace: [ 65.669557] <#MC> [<ffffffff81566db9>] dump_stack+0x46/0x58 [ 65.675994] [<ffffffff810871ff>] dequeue_task_idle+0x2f/0x40 [ 65.682412] [<ffffffff8107c1fa>] dequeue_task+0x5a/0x80 [ 65.688345] [<ffffffff810804f3>] deactivate_task+0x23/0x30 [ 65.694569] [<ffffffff81569050>] __schedule+0x580/0x7f0 [ 65.700502] [<ffffffff81569739>] schedule_preempt_disabled+0x29/0x70 [ 65.707696] [<ffffffff8156abb6>] __ww_mutex_lock_slowpath+0xb8/0x162 [ 65.714891] [<ffffffff8156acb3>] __ww_mutex_lock+0x53/0x85 [ 65.721125] [<ffffffffa00b3a5d>] drm_modeset_lock+0x3d/0x110 [drm] [ 65.728132] [<ffffffffa00b3c2a>] __drm_modeset_lock_all+0x8a/0x120 [drm] [ 65.735721] [<ffffffffa00b3cd0>] drm_modeset_lock_all+0x10/0x30 [drm] [ 65.743015] [<ffffffffa01af8bf>] drm_fb_helper_pan_display+0x2f/0xf0 [drm_kms_helper] [ 65.751857] [<ffffffff8132bd21>] fb_pan_display+0xd1/0x1a0 [ 65.758081] [<ffffffff81326010>] bit_update_start+0x20/0x50 [ 65.764400] [<ffffffff813259f2>] fbcon_switch+0x3a2/0x550 [ 65.770528] [<ffffffff813a01c9>] redraw_screen+0x189/0x240 [ 65.776750] [<ffffffff81322f8a>] fbcon_blank+0x20a/0x2d0 [ 65.782778] [<ffffffff8137d359>] ? erst_writer+0x209/0x330 [ 65.789002] [<ffffffff810ba2f3>] ? internal_add_timer+0x63/0x80 [ 65.795710] [<ffffffff810bc137>] ? mod_timer+0x127/0x1e0 [ 65.801740] [<ffffffff813a0cd8>] do_unblank_screen+0xa8/0x1d0 [ 65.808255] [<ffffffff813a0e10>] unblank_screen+0x10/0x20 [ 65.814381] [<ffffffff812ca0d9>] bust_spinlocks+0x19/0x40 [ 65.820508] [<ffffffff81561ca7>] panic+0x106/0x1f5 [ 65.825955] [<ffffffff8102336c>] mce_panic+0x2ac/0x2e0 [ 65.831789] [<ffffffff812c796a>] ? delay_tsc+0x4a/0x80 [ 65.837625] [<ffffffff81024e1f>] do_machine_check+0xbaf/0xbf0 [ 65.844138] [<ffffffff813365d7>] ? intel_idle+0xc7/0x150 [ 65.850166] [<ffffffff8156f03f>] machine_check+0x1f/0x30 [ 65.856195] [<ffffffff813365d7>] ? intel_idle+0xc7/0x150 [ 65.862222] <<EOE>> [<ffffffff814283d5>] cpuidle_enter_state+0x55/0x170 [ 65.869823] [<ffffffff814285a7>] cpuidle_enter+0x17/0x20 [ 65.875852] [<ffffffff81097b08>] cpu_startup_entry+0x2d8/0x370 [ 65.882467] [<ffffffff8102fe29>] start_secondary+0x159/0x180 There's __drm_modeset_lock_all() which Daniel Vetter introduced for this purpose. We can leverage that without reinventing anything. This patch works with the latest kernel. Reviewed-by: Rob Clark <robdclark@gmail.com> Tested-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Rui Wang <rui.y.wang@intel.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
* | | Merge branch 'exynos-drm-fixes' of ↵Dave Airlie2015-01-213-23/+8
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/daeinki/drm-exynos into drm-fixes This pull request includes below fixups, - Remove duplicated machine checking. . It seems that this code was added when you merged 'v3.18-rc7' into drm-next. commit id : e8115e79aa62b6ebdb3e8e61ca4092cc32938afc - Fix hdmiphy reset. . Exynos hdmi has two interfaces to control hdmyphy, one is I2C, other is APB bus - memory mapped I/O. So this patch makes hdmiphy reset to be done according to interfaces, I2C or APB bus. - And add some exception codes. * 'exynos-drm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/daeinki/drm-exynos: drm/exynos: fix warning of vblank reference count drm/exynos: remove unnecessary runtime pm operations drm/exynos: fix reset codes for memory mapped hdmi phy drm/exynos: remove the redundant machine checking code
| * | | drm/exynos: fix warning of vblank reference countJoonyoung Shim2015-01-181-1/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Prevented re-enabling the vblank interrupt by drm_vblank_off and drm_vblank_get from mixer_wait_for_vblank returns error after drm_vblank_off. We get below warnings without this error handling because vblank reference count is mismatched by above sequence. setting mode 1920x1080-60Hz@XR24 on connectors 16, crtc 13 [ 19.900793] ------------[ cut here ]------------ [ 19.903959] WARNING: CPU: 0 PID: 0 at drivers/gpu/drm/drm_irq.c:1072 exynos_drm_crtc_finish_pageflip+0xac/0xdc() [ 19.914076] Modules linked in: [ 19.917116] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.19.0-rc4-00040-g3d729789-dirty #46 [ 19.925342] Hardware name: SAMSUNG EXYNOS (Flattened Device Tree) [ 19.931437] [<c0014430>] (unwind_backtrace) from [<c001158c>] (show_stack+0x10/0x14) [ 19.939131] [<c001158c>] (show_stack) from [<c04cdd50>] (dump_stack+0x84/0xc4) [ 19.946329] [<c04cdd50>] (dump_stack) from [<c00226f4>] (warn_slowpath_common+0x80/0xb0) [ 19.954382] [<c00226f4>] (warn_slowpath_common) from [<c00227c0>] (warn_slowpath_null+0x1c/0x24) [ 19.963132] [<c00227c0>] (warn_slowpath_null) from [<c02c20cc>] (exynos_drm_crtc_finish_pageflip+0xac/0xdc) [ 19.972841] [<c02c20cc>] (exynos_drm_crtc_finish_pageflip) from [<c02cb7ec>] (mixer_irq_handler+0xdc/0x104) [ 19.982546] [<c02cb7ec>] (mixer_irq_handler) from [<c005c904>] (handle_irq_event_percpu+0x78/0x134) [ 19.991555] [<c005c904>] (handle_irq_event_percpu) from [<c005c9fc>] (handle_irq_event+0x3c/0x5c) [ 20.000395] [<c005c9fc>] (handle_irq_event) from [<c005f384>] (handle_fasteoi_irq+0xe0/0x1ac) [ 20.008885] [<c005f384>] (handle_fasteoi_irq) from [<c005bf88>] (generic_handle_irq+0x2c/0x3c) [ 20.017463] [<c005bf88>] (generic_handle_irq) from [<c005c254>] (__handle_domain_irq+0x7c/0xec) [ 20.026128] [<c005c254>] (__handle_domain_irq) from [<c0008698>] (gic_handle_irq+0x30/0x68) [ 20.034449] [<c0008698>] (gic_handle_irq) from [<c00120c0>] (__irq_svc+0x40/0x74) [ 20.041893] Exception stack(0xc06fff68 to 0xc06fffb0) [ 20.046923] ff60: 00000000 00000000 000052f6 c001b460 c06fe000 c07064e8 [ 20.055070] ff80: c04d743c c07392a2 c0739440 c06da340 ef7fca80 00000000 01000000 c06fffb0 [ 20.063212] ffa0: c000f24c c000f250 60000013 ffffffff [ 20.068245] [<c00120c0>] (__irq_svc) from [<c000f250>] (arch_cpu_idle+0x38/0x3c) [ 20.075611] [<c000f250>] (arch_cpu_idle) from [<c0050948>] (cpu_startup_entry+0x108/0x16c) [ 20.083846] [<c0050948>] (cpu_startup_entry) from [<c06aec5c>] (start_kernel+0x3a0/0x3ac) [ 20.091980] ---[ end trace 2c76ee0500489d1b ]--- Signed-off-by: Joonyoung Shim <jy0922.shim@samsung.com> Signed-off-by: Inki Dae <inki.dae@samsung.com>
| * | | drm/exynos: remove unnecessary runtime pm operationsJoonyoung Shim2015-01-181-4/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In booting, we can see a below message. [ 3.241728] exynos-mixer 14450000.mixer: Unbalanced pm_runtime_enable! Already pm_runtime_enable is called by probe function. Remove pm_runtime_enable/disable from mixer_bind and mixer_unbind. Signed-off-by: Joonyoung Shim <jy0922.shim@samsung.com> Signed-off-by: Inki Dae <inki.dae@samsung.com>
| * | | drm/exynos: fix reset codes for memory mapped hdmi phyJoonyoung Shim2015-01-181-6/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This fixes reset codes to support memory mapped hdmi phy as well as hdmi phy dedicated i2c lines. Signed-off-by: Joonyoung Shim <jy0922.shim@samsung.com> Signed-off-by: Inki Dae <inki.dae@samsung.com>
| * | | drm/exynos: remove the redundant machine checking codeHyungwon Hwang2015-01-121-12/+0
| |/ / | | | | | | | | | | | | | | | | | | | | | | | | | | | This code is unnecessary, because same logic is already included. Refer this mail thread[1] for detail. [1] http://lists.freedesktop.org/archives/dri-devel/2015-January/075132.html Signed-off-by: Hyungwon Hwang <human.hwang@samsung.com> Signed-off-by: Inki Dae <inki.dae@samsung.com>
* | | drm/radeon: use rv515_ring_start on r5xxAlex Deucher2015-01-151-2/+16
| | | | | | | | | | | | | | | | | | | | | This was accidently lost in 76a0df859def. Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
* | | drm/radeon: add si dpm quirk listAlex Deucher2015-01-121-0/+39
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This adds a quirks list to fix stability problems with certain SI boards. bug: https://bugs.freedesktop.org/show_bug.cgi?id=76490 Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
* | | drm/radeon: don't print error on -ERESTARTSYSChristian König2015-01-121-1/+1
| | | | | | | | | | | | | | | Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* | | drm/radeon: add a dpm quirk listAlex Deucher2015-01-081-0/+33
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Disable dpm on certain problematic boards rather than disabling dpm for the entire chip family since most boards work fine. https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1386534 https://bugzilla.kernel.org/show_bug.cgi?id=83731 Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
* | | drm/radeon: fix VM flush on CIK (v3)Alex Deucher2015-01-082-0/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We need to wait for the GPUVM flush to complete. There was some confusion as to how this mechanism was supposed to work. The operation is not atomic. For GPU initiated invalidations you need to read back a VM register to introduce enough latency for the update to complete. v2: drop gart changes v3: just read back rather than polling Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
* | | drm/radeon: fix VM flush on SI (v3)Alex Deucher2015-01-083-0/+36
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We need to wait for the GPUVM flush to complete. There was some confusion as to how this mechanism was supposed to work. The operation is not atomic. For GPU initiated invalidations you need to read back a VM register to introduce enough latency for the update to complete. v2: drop gart changes v3: just read back rather than polling Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
* | | drm/radeon: fix VM flush on cayman/aruba (v3)Alex Deucher2015-01-083-0/+40
|/ / | | | | | | | | | | | | | | | | | | | | | | | | | | | | We need to wait for the GPUVM flush to complete. There was some confusion as to how this mechanism was supposed to work. The operation is not atomic. For GPU initiated invalidations you need to read back a VM register to introduce enough latency for the update to complete. v2: drop gart changes v3: just read back rather than polling Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
* | Merge tag 'amdkfd-fixes-2015-01-06' of ↵Dave Airlie2015-01-087-152/+213
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://people.freedesktop.org/~gabbayo/linux into drm-fixes - Complete overhaul to the main IOCTL function, kfd_ioctl(), according to drm_ioctl() example. This includes changing the IOCTL definitions, so it breaks compatibility with previous versions of the userspace. However, because the kernel was not officialy released yet, and this the first kernel that includes amdkfd, I assume I can still do that at this stage. - A couple of bug fixes for the non-HWS path (used for bring-ups and debugging purposes only). * tag 'amdkfd-fixes-2015-01-06' of git://people.freedesktop.org/~gabbayo/linux: drm/amdkfd: rewrite kfd_ioctl() according to drm_ioctl() drm/amdkfd: reformat IOCTL definitions to drm-style drm/amdkfd: Do copy_to/from_user in general kfd_ioctl() drm/amdkfd: unmap VMID<-->PASID when relesing VMID (non-HWS) drm/radeon: Assign VMID to PASID for IH in non-HWS mode drm/radeon: do not leave queue acquired if timeout happens in kgd_hqd_destroy() drm/amdkfd: Load mqd to hqd in non-HWS mode drm/amd: Fixing typos in kfd<->kgd interface
| * | drm/amdkfd: rewrite kfd_ioctl() according to drm_ioctl()Oded Gabbay2015-01-062-48/+86
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch changes kfd_ioctl() to be very similar to drm_ioctl(). The patch defines an array of amdkfd_ioctls, which maps IOCTL definition to the ioctl function. The kfd_ioctl() uses that mapping to call the appropriate ioctl function, through a function pointer. This patch also declares a new typedef for the ioctl function pointer. v2: Renamed KFD_COMMAND_(START|END) to AMDKFD_... Signed-off-by: Oded Gabbay <oded.gabbay@amd.com> Acked-by: Christian König <christian.koenig@amd.com>
| * | drm/amdkfd: reformat IOCTL definitions to drm-styleOded Gabbay2015-01-061-7/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch reformats the ioctl definitions in kfd_ioctl.h to be similar to the drm ioctls definition style. v2: Renamed KFD_COMMAND_(START|END) to AMDKFD_... Signed-off-by: Oded Gabbay <oded.gabbay@amd.com> Acked-by: Christian König <christian.koenig@amd.com>
| * | drm/amdkfd: Do copy_to/from_user in general kfd_ioctl()Oded Gabbay2015-01-061-117/+117
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch moves the copy_to_user() and copy_from_user() calls from the different ioctl functions in amdkfd to the general kfd_ioctl() function, as this is a common code for all ioctls. This was done according to example taken from drm_ioctl.c Signed-off-by: Oded Gabbay <oded.gabbay@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
| * | drm/amdkfd: unmap VMID<-->PASID when relesing VMID (non-HWS)Ben Goz2015-01-051-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes a bug where deallocate_vmid() didn't actually unmap the VMID<-->PASID mapping (in the registers). That can cause undefined behavior. This bug only occurs in non-HWS mode. Signed-off-by: Ben Goz <ben.goz@amd.com> Signed-off-by: Oded Gabbay <oded.gabbay@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com>
OpenPOWER on IntegriCloud