summaryrefslogtreecommitdiff
path: root/drivers/gpu
AgeCommit message (Collapse)Author
2018-11-21qxl: Make sure qxl_cursor memory is pinnedChristophe Fergeau
QEMU keeps a vram reference to the last QXLCursorCmd it received. This QXLCursorCmd command points to a QXLCursor instance (stored in vram too). However, while the QXLCursorCmd memory is pinned, the QXLCursor memory is not. When booting a recent Fedora to its login screen while monitoring the QXLCursorCmd QEMU holds, it's possible to see the QXLCursor memory becoming invalid shortly after boot. Pinning that memory ensures that that QXLCursor memory is not going to be moved by the guest kernel. Moving the pin/unpin to qxl_release_list_add()/qxl_release_free_list() would be a more generic fix. However, doing this quickly exhausts QXL video memory, so more fixing would be needed before this is workable. Signed-off-by: Christophe Fergeau <cfergeau@redhat.com> Link: http://patchwork.freedesktop.org/patch/msgid/20181120162004.22807-3-cfergeau@redhat.com Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
2018-11-21qxl: Remove unused qxl_bo_pin argumentsChristophe Fergeau
The 'domain' argument to qxl_bo_pin is redundant with 'bo', and 'gpu_addr' is unused, so we can remove both. Signed-off-by: Christophe Fergeau <cfergeau@redhat.com> Link: http://patchwork.freedesktop.org/patch/msgid/20181120162004.22807-2-cfergeau@redhat.com Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
2018-11-21qxl: No need for NULL check before calling qxl_bo_unref()Christophe Fergeau
qxl_bo_unref() is already performing a NULL check. Signed-off-by: Christophe Fergeau <cfergeau@redhat.com> Link: http://patchwork.freedesktop.org/patch/msgid/20181120162004.22807-1-cfergeau@redhat.com Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
2018-11-21drm/cirrus: Remove set but not used variable 'bo'YueHaibing
Fixes gcc '-Wunused-but-set-variable' warning: drivers/gpu/drm/cirrus/cirrus_fbdev.c: In function 'cirrusfb_create': drivers/gpu/drm/cirrus/cirrus_fbdev.c:172:20: warning: variable 'bo' set but not used [-Wunused-but-set-variable] It never used since introduction in commit f9aa76a85248 ("drm/kms: driver for virtual cirrus under qemu") Signed-off-by: YueHaibing <yuehaibing@huawei.com> Link: http://patchwork.freedesktop.org/patch/msgid/1542283836-152176-1-git-send-email-yuehaibing@huawei.com Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
2018-11-21drm/i915: Write GPU relocs harder with gen3Chris Wilson
Under moderate amounts of GPU stress, we can observe on Bearlake and Pineview (later gen3 models) that we execute the following batch buffer before the write into the batch is coherent. Adding extra (tested with upto 32x) MI_FLUSH to either the invalidation, flush or both phases does not solve the incoherency issue with the relocations, but emitting the MI_STORE_DWORD_IMM twice does. So be it. Fixes: 7dd4f6729f92 ("drm/i915: Async GPU relocation processing") Testcase: igt/gem_tiled_fence_blits # blb/pnv 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> Link: https://patchwork.freedesktop.org/patch/msgid/20181119154153.15327-1-chris@chris-wilson.co.uk (cherry picked from commit 7fa28e146994da1e8a4124623d7da97b798ea520) Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
2018-11-20drm/i915: Downgrade unknown CSR firmware warningsLucas De Marchi
Like it was done in commit 9e180d9991dc ("drm/i915: Downgrade unknown firmware warnings") for huc and guc: downgrade CSR firmware warnings. If we have released no firmware yet for a platform, stop scaring the consumer and merely note its expected absence. By simply removing the warning and early return we hit the condition with the appropriate message. Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20181117004234.23437-2-lucas.demarchi@intel.com
2018-11-20drm/i915: allow to load DMC firmware on next genLucas De Marchi
Before commit d8a5b7d79fb7 ("drm/i915/csr: keep max firmware size together with firmare name and version") it was possible to load the firmware for testing purposes via parameter. Let's use the size of the last known platform to recover that behavior. Cc: Jani Nikula <jani.nikula@intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com> Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20181117004234.23437-1-lucas.demarchi@intel.com
2018-11-20drm/i915/ilk: Fix warning when reading emon_status with no outputJosé Roberto de Souza
When there is no output no one will hold a runtime_pm reference causing a warning when trying to read emom_status in debugfs. [22.756480] ------------[ cut here ]------------ [22.756489] RPM wakelock ref not held during HW access [22.756578] WARNING: CPU: 0 PID: 1058 at drivers/gpu/drm/i915/intel_drv.h:2104 gen5_read32+0x16b/0x1a0 [i915] [22.756580] Modules linked in: snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic i915 coretemp crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core e1000e snd_pcm mei_me prime_numbers mei lpc_ich [22.756595] CPU: 0 PID: 1058 Comm: debugfs_test Not tainted 4.20.0-rc1-CI-Trybot_3219+ #1 [22.756597] Hardware name: Hewlett-Packard HP Compaq 8100 Elite SFF PC/304Ah, BIOS 786H1 v01.13 07/14/2011 [22.756634] RIP: 0010:gen5_read32+0x16b/0x1a0 [i915] [22.756637] Code: a4 ea e0 0f 0b e9 d2 fe ff ff 80 3d a5 71 19 00 00 0f 85 d3 fe ff ff 48 c7 c7 48 d0 2d a0 c6 05 91 71 19 00 01 e8 35 a4 ea e0 <0f> 0b e9 b9 fe ff ff e8 69 c6 f2 e0 85 c0 75 92 48 c7 c2 78 d0 2d [22.756639] RSP: 0018:ffffc90000f1fd38 EFLAGS: 00010282 [22.756642] RAX: 0000000000000000 RBX: ffff8801f7ab0000 RCX: 0000000000000006 [22.756643] RDX: 0000000000000006 RSI: ffffffff8212886a RDI: ffffffff820d6d57 [22.756645] RBP: 0000000000011020 R08: 0000000043e3d1a8 R09: 0000000000000000 [22.756647] R10: ffffc90000f1fd80 R11: 0000000000000000 R12: 0000000000000001 [22.756649] R13: ffff8801f7ab0068 R14: 0000000000000001 R15: ffff88020d53d188 [22.756651] FS: 00007f2878849980(0000) GS:ffff880213a00000(0000) knlGS:0000000000000000 [22.756653] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [22.756655] CR2: 00005638deedf028 CR3: 0000000203292001 CR4: 00000000000206f0 [22.756657] Call Trace: [22.756689] i915_mch_val+0x1b/0x60 [i915] [22.756721] i915_emon_status+0x45/0xd0 [i915] [22.756730] seq_read+0xdb/0x3c0 [22.756736] ? lockdep_hardirqs_off+0x94/0xd0 [22.756740] ? __slab_free+0x24e/0x510 [22.756746] full_proxy_read+0x52/0x90 [22.756752] __vfs_read+0x31/0x170 [22.756759] ? do_sys_open+0x13b/0x240 [22.756763] ? rcu_read_lock_sched_held+0x6f/0x80 [22.756766] vfs_read+0x9e/0x140 [22.756770] ksys_read+0x50/0xc0 [22.756775] do_syscall_64+0x55/0x190 [22.756781] entry_SYSCALL_64_after_hwframe+0x49/0xbe [22.756783] RIP: 0033:0x7f28781dc34e [22.756786] Code: 00 00 00 00 48 8b 15 71 8c 20 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff c3 0f 1f 40 00 8b 05 ba d0 20 00 85 c0 75 16 31 c0 0f 05 <48> 3d 00 f0 ff ff 77 5a f3 c3 0f 1f 84 00 00 00 00 00 41 54 55 49 [22.756787] RSP: 002b:00007ffd33fa0d08 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [22.756790] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f28781dc34e [22.756792] RDX: 0000000000000200 RSI: 00007ffd33fa0d50 RDI: 0000000000000008 [22.756794] RBP: 00007ffd33fa0f60 R08: 0000000000000000 R09: 0000000000000020 [22.756796] R10: 0000000000000000 R11: 0000000000000246 R12: 00005638de45c2c0 [22.756797] R13: 00007ffd33fa14b0 R14: 0000000000000000 R15: 0000000000000000 [22.756806] irq event stamp: 47950 [22.756811] hardirqs last enabled at (47949): [<ffffffff810fba74>] vprintk_emit+0x124/0x320 [22.756813] hardirqs last disabled at (47950): [<ffffffff810019b0>] trace_hardirqs_off_thunk+0x1a/0x1c [22.756816] softirqs last enabled at (47518): [<ffffffff81c0033a>] __do_softirq+0x33a/0x4b9 [22.756820] softirqs last disabled at (47479): [<ffffffff8108df29>] irq_exit+0xa9/0xc0 [22.756858] WARNING: CPU: 0 PID: 1058 at drivers/gpu/drm/i915/intel_drv.h:2104 gen5_read32+0x16b/0x1a0 [i915] [22.756860] ---[ end trace bf56fa7d6a3cbf7a ] Signed-off-by: José Roberto de Souza <jose.souza@intel.com> Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20181119230101.32460-1-jose.souza@intel.com
2018-11-20drm/amdgpu: Enable HDP memory light sleepKenneth Feng
Due to the register name and setting change of HDP memory light sleep on Vega20,change accordingly in the driver. Signed-off-by: Kenneth Feng <kenneth.feng@amd.com> Reviewed-by: Evan Quan <evan.quan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-20drm/amdgpu: enable paging queue doorbell support v4Philip Yang
Because increase SDMA_DOORBELL_RANGE to add new SDMA doorbell for paging queue will break SRIOV, instead we can reserve and map two doorbell pages for amdgpu, paging queues doorbell index use same index as SDMA gfx queues index but on second page. For Vega20, after we change doorbell layout to increase SDMA doorbell for 8 SDMA RLC queues later, we could use new doorbell index for paging queue. Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-20drm/amdgpu: fix typo in function sdma_v4_0_page_resumePhilip Yang
This looks like copy paste typo Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-20drm/amdgpu: Remove dead static variableRex Zhu
The static struct drm_driver *driver was not used because drm_pci_init was deprecated v2: Remove static pointer pdriver(Christian) Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-20drm/amdkfd: change system memory overcommit limitEric Huang
It is to improve system limit by: 1. replacing userptrlimit with a total memory limit that conunts TTM memory usage and userptr usage. 2. counting acc size for all BOs. Signed-off-by: Eric Huang <JinHuiEric.Huang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-20drm/amdgpu: Fix KFD doorbell SG BO mappingFelix Kuehling
This change prepares for adding SG BOs that will be used for mapping doorbells into GPUVM address space. This type of BO would be mistaken for an invalid userptr BO. Improve that check to test that it's actually a userptr BO so that SG BOs that are still in the CPU domain can be validated and mapped correctly. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-20drm/amdkfd: Fix and simplify sync object handling for KFDFelix Kuehling
The adev parameter in amdgpu_sync_fence and amdgpu_sync_resv is only needed for updating sync->last_vm_update. This breaks if different adevs are passed to calls for the same sync object. Always pass NULL for calls from KFD because sync objects used for KFD don't belong to any particular device, and KFD doesn't need the sync->last_vm_update fence. This fixes kernel log warnings on multi-GPU systems after recent changes in amdgpu_amdkfd_gpuvm_restore_process_bos. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-20drm/amdgpu: KFD Restore process: Optimize waitingHarish Kasiviswanathan
Instead of waiting for each KFD BO after validation just wait for the last BO moving fence. Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-20drm/amdgpu: Remove explicit wait after VM validateHarish Kasiviswanathan
PD or PT might have to be moved during validation and this move has to be completed before updating it. If page table updates are done using SDMA then this serializing is done by SDMA command submission. And if PD/PT updates are done by CPU, then explicit waiting for PD/PT updates are done in amdgpu VM amdgpu_vm_wait_pd function. Sync to PD BO moving fence to handle corner case where none of the PTs are updated but PD is evicted. Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-20drm/i915/selftests: Hold task reference to reset workerChris Wilson
As the worker may exit by itself, we need to hold a task reference to it in the parent. References: https://bugs.freedesktop.org/show_bug.cgi?id=108735 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20181120120601.24083-1-chris@chris-wilson.co.uk
2018-11-20drm: Introduce new DRM_FORMAT_XYUVStanislav Lisovskiy
v5: This is YUV444 packed format same as AYUV, but without alpha, as supported by i915. v6: Removed unneeded initializer for new XYUV format. v7: Added is_yuv field initialization according to latest drm_fourcc format structure initialization changes. v8: Edited commit message to be more clear about skl+, renamed PLANE_CTL_FORMAT_AYUV to PLANE_CTL_FORMAT_XYUV as this format doesn't support per-pixel alpha. Fixed minor code issues. v9: Moved DRM format check to proper place in intel_framebuffer_init. v10: Changed DRM_FORMAT_XYUV to be DRM_FORMAT_XYUV8888 v11: Fixed rebase conflict, caused by added new formats to drm-tip meanwhile. Reviewed-by: Alexandru Gheorghe <alexandru-cosmin.gheorghe@arm.com> Signed-off-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com> [vsyrjala: Removed stray tab and sorted the formats differently] Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20181109093916.25858-2-stanislav.lisovskiy@intel.com
2018-11-20drm/tinydrm: Use DRM_GEM_CMA_VMAP_DRIVER_OPSNoralf Trønnes
The CMA helper now has the functionality to ensure a virtual address on imported buffer so use that. While touching all tinydrm drivers, remove the unnecessary inclusion of drm_fb_helper.h in some drivers. Cc: David Lechner <david@lechnology.com> Cc: Eric Anholt <eric@anholt.net> Signed-off-by: Noralf Trønnes <noralf@tronnes.org> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Eric Anholt <eric@anholt.net> Link: https://patchwork.freedesktop.org/patch/msgid/20181110145647.17580-6-noralf@tronnes.org
2018-11-20drm/cma-helper: Add DRM_GEM_CMA_VMAP_DRIVER_OPSNoralf Trønnes
This adds functionality to the CMA helper which ensures that the kernel virtual address is set on the CMA GEM object also for imported buffers. The drivers have been audited to ensure that none set ->vaddr on imported buffers, making the conditional dma_buf_vunmap() call in drm_gem_cma_free_object() safe. Signed-off-by: Noralf Trønnes <noralf@tronnes.org> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Eric Anholt <eric@anholt.net> Link: https://patchwork.freedesktop.org/patch/msgid/20181110145647.17580-5-noralf@tronnes.org
2018-11-20drm/gem: Add drm_gem_object_funcsNoralf Trønnes
This adds an optional function table on GEM objects. The main benefit is for drivers that support more than one type of memory (shmem,vram,cma) for their buffers depending on the hardware it runs on. With the callbacks attached to the GEM object itself, it is easier to have core helpers for the the various buffer types. The driver only has to make the decision about buffer type on GEM object creation and all other callbacks can be handled by the chosen helper. drm_driver->gem_prime_res_obj has not been added since there's a todo to put a reservation_object into drm_gem_object. v3: Add todo entry v2: Drop drm_gem_object_funcs->prime_mmap in favour of drm_gem_prime_mmap() (Daniel Vetter) v1: - drm_gem_object_funcs.map -> .prime_map let it only do PRIME mmap like the function it superseeds (Daniel Vetter) - Flip around the if ladders and make obj->funcs the first choice highlighting the fact that this the new default way of doing it (Daniel Vetter) Signed-off-by: Noralf Trønnes <noralf@tronnes.org> Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch> Acked-by: Christian König <christian.koenig@amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/20181110145647.17580-4-noralf@tronnes.org
2018-11-20drm/prime: Add drm_gem_prime_mmap()Noralf Trønnes
Add a generic PRIME GEM mmap function. v2: Fix link in docs (Daniel Vetter) Suggested-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Noralf Trønnes <noralf@tronnes.org> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Acked-by: Christian König <christian.koenig@amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/20181110145647.17580-3-noralf@tronnes.org
2018-11-20drm/driver: Add defaults for .gem_prime_export/import callbacksNoralf Trønnes
The majority of drivers use drm_gem_prime_export() and drm_gem_prime_import() for these callbacks so let's make them the default. Signed-off-by: Noralf Trønnes <noralf@tronnes.org> Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch> Acked-by: Christian König <christian.koenig@amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/20181110145647.17580-2-noralf@tronnes.org
2018-11-20drm/panel: s6d16d0: fix spelling mistake "enble" -> "enable"Colin Ian King
Trivial fix to spelling mistake in DRM_DEV_ERROR error message Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Linus Walleij <linus.walleij@linaro.org> Link: https://patchwork.freedesktop.org/patch/msgid/20181106154022.9209-1-colin.king@canonical.com
2018-11-20Merge drm/drm-next into drm-intel-next-queuedJani Nikula
Pull in v4.20-rc3 via drm-next. Signed-off-by: Jani Nikula <jani.nikula@intel.com>
2018-11-20drm/i915/fixed: cosmetic cleanupJani Nikula
Clean up fixed point temp variable initialization, use the more conventional tmp name for temp variables, add empty lines before return. No functional changes. Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20181116120729.7580-5-jani.nikula@intel.com
2018-11-20drm/i915/fixed: simplify is_fixed16_zero()Jani Nikula
Simply return the condition. No functional changes. Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20181116120729.7580-4-jani.nikula@intel.com
2018-11-20drm/i915/fixed: simplify FP_16_16_MAX definitionJani Nikula
No need to use a compound statement enclosed in parenthesis where a C99 compound literal will do. No functional changes. Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20181116120729.7580-3-jani.nikula@intel.com
2018-11-20drm/i915/fixed: prefer kernel types over stdint typesJani Nikula
While at it, conform to kernel spacing (i.e. no space) after cast. No functional changes. Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20181116120729.7580-2-jani.nikula@intel.com
2018-11-20drm/i915: extract fixed point math to i915_fixed.hJani Nikula
Reduce bloat in one of the bigger header files. Fix some indentation while at it. No functional changes. v2: Add include guards (Joonas) Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20181116120729.7580-1-jani.nikula@intel.com
2018-11-20drm/i915: Write GPU relocs harder with gen3Chris Wilson
Under moderate amounts of GPU stress, we can observe on Bearlake and Pineview (later gen3 models) that we execute the following batch buffer before the write into the batch is coherent. Adding extra (tested with upto 32x) MI_FLUSH to either the invalidation, flush or both phases does not solve the incoherency issue with the relocations, but emitting the MI_STORE_DWORD_IMM twice does. So be it. Fixes: 7dd4f6729f92 ("drm/i915: Async GPU relocation processing") Testcase: igt/gem_tiled_fence_blits # blb/pnv 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> Link: https://patchwork.freedesktop.org/patch/msgid/20181119154153.15327-1-chris@chris-wilson.co.uk
2018-11-20drm/bridge/sii902x: Add missing dependency on I2C_MUXFabrizio Castro
kbuild test robot reports: >> ERROR: "i2c_mux_add_adapter" [drivers/gpu/drm/bridge/sii902x.ko] undefined! >> ERROR: "i2c_mux_alloc" [drivers/gpu/drm/bridge/sii902x.ko] undefined! >> ERROR: "i2c_mux_del_adapters" [drivers/gpu/drm/bridge/sii902x.ko] undefined! Quite obviously the driver depends on I2C_MUX, but adding a "depends on" introduces a recursive dependency, therefore this patch selects I2C_MUX instead. Fixes: 21d808405fe4 ("drm/bridge/sii902x: Fix EDID readback") Signed-off-by: Fabrizio Castro <fabrizio.castro@bp.renesas.com> Link: https://lists.01.org/pipermail/kbuild-all/2018-November/054924.html Acked-by: Peter Rosin <peda@axentia.se> Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com> Link: https://patchwork.freedesktop.org/patch/msgid/1542633978-22064-1-git-send-email-fabrizio.castro@bp.renesas.com
2018-11-20drm/i915: Prevent machine hang from Broxton's vtd w/a and error captureChris Wilson
Since capturing the error state requires fiddling around with the GGTT to read arbitrary buffers and is itself run under stop_machine(), it deadlocks the machine (effectively a hard hang) when run in conjunction with Broxton's VTd workaround to serialize GGTT access. v2: Store the ERR_PTR in first_error so that the error can be reported to the user via sysfs. v3: Mention the quirk in dmesg (using info as per usual) Fixes: 0ef34ad6222a ("drm/i915: Serialize GTT/Aperture accesses on BXT") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Cc: John Harrison <john.C.Harrison@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20181102161232.17742-5-chris@chris-wilson.co.uk (cherry picked from commit fb6f0b64e455b207a636346588e65bf9598d30eb) Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
2018-11-19drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c: Remove duplicate headerBrajeswar Ghosh
Remove gca/gfx_8_0_enum.h which is included more than once Signed-off-by: Brajeswar Ghosh <brajeswar.linux@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-19drm/amdgpu/psp: use define rather than magic number for mode1 resetAlex Deucher
Use the define rather than hardcoded value. Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-19drm/scheduler: Fix bad job be re-processed in TDRTrigger Huang
A bad job is the one triggered TDR(In the current amdgpu's implementation, actually all the jobs in the current joq-queue will be treated as bad jobs). In the recovery process, its fence will be fake signaled and as a result, the work behind will be scheduled to delete it from the mirror list, but if the TDR process is invoked before the work's execution, then this bad job might be processed again and the call dma_fence_set_error to its fence in TDR process will lead to kernel warning trace: [ 143.033605] WARNING: CPU: 2 PID: 53 at ./include/linux/dma-fence.h:437 amddrm_sched_job_recovery+0x1af/0x1c0 [amd_sched] kernel: [ 143.033606] Modules linked in: amdgpu(OE) amdchash(OE) amdttm(OE) amd_sched(OE) amdkcl(OE) amd_iommu_v2 drm_kms_helper drm i2c_algo_bit fb_sys_fops syscopyarea sysfillrect sysimgblt kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64 snd_hda_codec_generic crypto_simd glue_helper cryptd snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq joydev snd_seq_device snd_timer snd soundcore binfmt_misc input_leds mac_hid serio_raw nfsd auth_rpcgss nfs_acl lockd grace sunrpc sch_fq_codel parport_pc ppdev lp parport ip_tables x_tables autofs4 8139too floppy psmouse 8139cp mii i2c_piix4 pata_acpi [ 143.033649] CPU: 2 PID: 53 Comm: kworker/2:1 Tainted: G OE 4.15.0-20-generic #21-Ubuntu [ 143.033650] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 143.033653] Workqueue: events drm_sched_job_timedout [amd_sched] [ 143.033656] RIP: 0010:amddrm_sched_job_recovery+0x1af/0x1c0 [amd_sched] [ 143.033657] RSP: 0018:ffffa9f880fe7d48 EFLAGS: 00010202 [ 143.033659] RAX: 0000000000000007 RBX: ffff9b98f2b24c00 RCX: ffff9b98efef4f08 [ 143.033660] RDX: ffff9b98f2b27400 RSI: ffff9b98f2b24c50 RDI: ffff9b98efef4f18 [ 143.033660] RBP: ffffa9f880fe7d98 R08: 0000000000000001 R09: 00000000000002b6 [ 143.033661] R10: 0000000000000000 R11: 0000000000000000 R12: ffff9b98efef3430 [ 143.033662] R13: ffff9b98efef4d80 R14: ffff9b98efef4e98 R15: ffff9b98eaf91c00 [ 143.033663] FS: 0000000000000000(0000) GS:ffff9b98ffd00000(0000) knlGS:0000000000000000 [ 143.033664] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 143.033665] CR2: 00007fc49c96d470 CR3: 000000001400a005 CR4: 00000000003606e0 [ 143.033669] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 143.033669] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 143.033670] Call Trace: [ 143.033744] amdgpu_device_gpu_recover+0x144/0x820 [amdgpu] [ 143.033788] amdgpu_job_timedout+0x9b/0xa0 [amdgpu] [ 143.033791] drm_sched_job_timedout+0xcc/0x150 [amd_sched] [ 143.033795] process_one_work+0x1de/0x410 [ 143.033797] worker_thread+0x32/0x410 [ 143.033799] kthread+0x121/0x140 [ 143.033801] ? process_one_work+0x410/0x410 [ 143.033803] ? kthread_create_worker_on_cpu+0x70/0x70 [ 143.033806] ret_from_fork+0x35/0x40 So just delete the bad job from mirror list directly Changes in v3: - Add a helper function to delete the bad jobs from mirror list and call it directly *before* the job's fence is signaled Changes in v2: - delete the useless list node check - also delete bad jobs in drm_sched_main because: kthread_unpark(ring->sched.thread) will be invoked very early before amdgpu_device_gpu_recover's return, then drm_sched_main will have chance to pick up a new job from the job queue. This new job will be added into the mirror list and processed by amdgpu_job_run, but may not be deleted from the mirror list on time due to the same reason. And finally re-processed by drm_sched_job_recovery Signed-off-by: Trigger Huang <Trigger.Huang@amd.com> Reviewed-by: Christian König <chrstian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-19drm/amdgpu/gfx: use proper offset define for MEC doorbellsAlex Deucher
Looks like a copy paste typo. Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-19drm/amdkfd: Workaround PASID missing in gfx9 interrupt payload under non HWSYong Zhao
This is a known gfx9 HW issue, and this change can perfectly workaround the issue. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-19drm/amdkfd: Adjust the debug message in KFD ISRYong Zhao
This makes debug message get printed even when there is early return. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-19drm/amdkfd: Added Vega12 and Polaris12 for KFD.Gang Ba
Add Vega12 and Polaris12 device info and device IDs to KFD. Signed-off-by: Gang Ba <gaba@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-19drm/amdkfd: Replace mqd with mqd_mgr as the variable name for mqd_managerYong Zhao
This will make reading code much easier. This fixes a few spots missed in a previous commit with the same title. Signed-off-by: Yong Zhao <yong.zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-19drm/amd/pp: handle negative values when reading ODGreathouse, Joseph
Reading the sysfs files pp_sclk_od and pp_mclk_od return the percentage difference between the VBIOS-provided default frequency and the current (possibly user-set) frequency in the highest SCLK and MCLK DPM states, respectively. Writing to these files provides an easy mechanism for setting a higher-than-default maximum frequency. We normally only allow values >= 0 to be written here. However, with the addition of pp_od_clk_voltage, we now allow users to set custom DPM tables. If they then set the maximum DPM state to something less than the default, later reads of pp_*_od should return a negative value. The highest DPM state is now less than the VBIOS-provided default, so the percentage is negative. The math to calculate this was originally performed with unsigned values, meaning reads that should return negative values returned meaningless data. This patch corrects that issue and normalizes how all of the calculations are done across the various hwmgr types. Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-19drm/amdgpu: Add missing firmware entry for HAINANTakashi Iwai
Due to lack of MODULE_FIRMWARE() with hainan_mc.bin, the driver doesn't work properly in initrd. Let's add it. Bugzilla: https://bugzilla.suse.com/show_bug.cgi?id=1116239 Fixes: 8eaf2b1faaf4 ("drm/amdgpu: switch firmware path for SI parts") Cc: <stable@vger.kernel.org> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Takashi Iwai <tiwai@suse.de> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-19drm/amd/powerplay: disable Vega20 DS related featuresEvan Quan
Disable these features on Vega20 for now. Signed-off-by: Evan Quan <evan.quan@amd.com> Acked-by: Feifei Xu<Feifei.Xu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-19drm/amdgpu: Fix oops when pp_funcs->switch_power_profile is unsetFelix Kuehling
On Vega20 and other pre-production GPUs, powerplay is not enabled yet. Check for NULL pointers before calling pp_funcs function pointers. Also affects Kaveri. CC: Joerg Roedel <jroedel@suse.de> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Tested-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
2018-11-19Revert "drm/amdgpu: use GMC v9 KIQ workaround only for the GFXHUB" (v2)Chengming Gui
With GFXOFF enabled, this patch will cause PCO amdgpu_test failed, but GFXOFF is necessary for PCO, so revert the patch. This reverts commit b83761bb0b09ec11c924afe9d88e458cb16a0372. v2: add a comment for future reference (Alex) Reviewed-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Jack Gui <Jack.Gui@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-19drm/amd/powerplay: Ratelimit all "was not implemented" messagesJoerg Roedel
Running kfdtest on an AMD Carizzo flooded the kernel log with thousands of these "was not implemented" messages, making it impossible to see other messages there. Ratelimit the messages to prevent user-space from flooding the kernel log. Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-19drm/amd/display: Clean up DCN1 clock requestsDavid Francis
[Why] There was a full clock request struct of which only one value was being used. [How] Replace the struct with a uint32_t Signed-off-by: David Francis <David.Francis@amd.com> Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com> Reviewed-by: Sun peng Li <Sunpeng.Li@amd.com> Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2018-11-19drm/amd/display: Support amdgpu "max bpc" connector property (v2)Nicholas Kazlauskas
[Why] Many panels support more than 8bpc but some modes are unavailable while running at greater than 8bpc due to DP/HDMI bandwidth constraints. Support for more than 8bpc was added recently in the driver but it defaults to the maximum supported bpc - locking out these modes. This should be a user configurable option such that the user can select what bpc configuration they would like. [How] This patch adds support for getting and setting the amdgpu driver specific "max bpc" property on the connector. It also adds support for limiting the output bpc based on the property value. The default limitation is the lowest value in the range, 8bpc. This was the old value before the range was uncapped. This patch should be updated/replaced later once common drm support for max bpc lands. Bugzilla: https://bugs.freedesktop.org/108542 Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=201585 Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=200645 Fixes: e03fd3f300f6 ("drm/amd/display: Do not limit color depth to 8bpc") v2: rebase on upstream (Alex) Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Harry Wentland <harry.wentland@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
generated by cgit (git 2.34.1) at 2025-09-16 17:55:21 +0000