Roger He [Tue, 15 Aug 2017 08:05:59 +0000 (16:05 +0800)]
drm/amd/amdgpu: expose fragment size as module parameter (v2)
Allow overrides on the command line.
v2: agd: sqaush in spelling fix and bogus default value warning
Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Roger He <Hongbo.He@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Roger He [Fri, 11 Aug 2017 12:00:41 +0000 (20:00 +0800)]
drm/amd/amdgpu: store fragment_size in vm_manager
adds fragment_size in the vm_manager structure and
implements hardware setup for it.
Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Roger He <Hongbo.He@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Tue, 1 Aug 2017 09:27:36 +0000 (11:27 +0200)]
drm/amdgpu: rename VM invalidated to moved
That better describes what happens here with the BO.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Tue, 1 Aug 2017 08:51:43 +0000 (10:51 +0200)]
drm/amdgpu: separate bo_va structure
Split that into vm_bo_base and bo_va to allow other uses as well.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 3 Aug 2017 18:30:50 +0000 (20:30 +0200)]
drm/amdgpu: drop the extra VM huge page flag v2
Just add the flags to the addr field as well.
v2: add some more comments that the flag is for huge pages.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 3 Aug 2017 17:24:06 +0000 (19:24 +0200)]
drm/amdgpu: remove superflous amdgpu_bo_kmap in the VM
We now properly kmap all BOs after validation.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 31 Jul 2017 13:32:40 +0000 (15:32 +0200)]
drm/amdgpu: cleanup static CSA handling
Move the CSA bo_va from the VM to the fpriv structure.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Wed, 9 Aug 2017 13:33:49 +0000 (15:33 +0200)]
drm/amdgpu: SHADOW and VRAM_CONTIGUOUS flags shouldn't be used by userspace
The shadow handling isn't implemented completely for userspace BOs and
the kernel sets the VRAM_CONTIGUOUS as necessary.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Chunming Zhou [Fri, 11 Aug 2017 01:34:33 +0000 (09:34 +0800)]
drm/amdgpu: save list length when fence is signaled
update the list first to avoid redundant checks.
Signed-off-by: Chunming Zhou <David1.Zhou@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> Cc: stable@vger.kernel.org
Christian König [Mon, 7 Aug 2017 15:46:49 +0000 (17:46 +0200)]
drm/amdgpu: move vram usage tracking into the vram manager v2
Looks like a better place for this.
v2: use atomic64_t members instead
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 7 Aug 2017 15:11:33 +0000 (17:11 +0200)]
drm/amdgpu: move gtt usage tracking into the gtt manager v2
It doesn't make much sense to count those numbers twice.
v2: use and atomic64_t instead
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 7 Aug 2017 13:47:51 +0000 (15:47 +0200)]
drm/amdgpu: move debug print into the MM managers
Instead of the separate switch/case in the calling function.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 7 Aug 2017 12:07:43 +0000 (14:07 +0200)]
drm/amdgpu: fix incorrect use of the lru_lock
The BO manager has its own lock and doesn't use the lru_lock.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 7 Aug 2017 12:03:54 +0000 (14:03 +0200)]
drm/radeon: fix incorrect use of the lru_lock
The BO manager has its own lock and doesn't use the lru_lock.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 7 Aug 2017 09:13:41 +0000 (11:13 +0200)]
drm/ttm: make ttm_mem_type_manager_func debug more useful
Provide the drm printer directly instead of just the callback.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Mon, 31 Jul 2017 13:35:24 +0000 (09:35 -0400)]
drm/amd/amdgpu: Add tracepoint for DMA page mapping (v4)
This helps map DMA addresses back to physical addresses.
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(v2): Added tracepoints for USERPTR, SG mappings, and
SWIOTBL mappings. Reformatted trace call perform
PCI decoding internal to the trace.
Christian König [Sat, 29 Jul 2017 11:28:55 +0000 (13:28 +0200)]
drm/amdgpu: fix Vega10 HW config for 2MB pages
Those values weren't correct. This should result in quite some speedup.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 13 Jul 2017 10:51:31 +0000 (12:51 +0200)]
drm/amdgpu: only bind VM shadows after validation v2
No need to do this on every CS.
v2: remove all other bind, reorder code
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 3 Aug 2017 15:44:01 +0000 (11:44 -0400)]
drm/amdgpu: only move VM BOs in the LRU during validation v2
This should save us a bunch of command submission overhead.
v2: move the LRU move to the right place to avoid the move for the root BO
and handle the shadow BOs as well. This turned out to be a bug fix because
the move needs to happen before the kmap.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 20 Jul 2017 18:55:06 +0000 (20:55 +0200)]
drm/ttm: individualize BO reservation obj when they are freed
Use the BOs reservation object when it is put on the ddelete list. This way we
avoid delaying freeing up the BO because of new fences on the reservation object.
This is used by dma-buf and amdgpu's VM page tables.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Wed, 26 Jul 2017 12:59:10 +0000 (14:59 +0200)]
drm/ttm: remove nonsense wait in ttm_bo_cleanup_refs_and_unlock
With shared reservation objects the assumption that no fence
could have been added isn't true any more.
Additional to that the BO is about to be destroyed, so removing the
fences now has no advantage whatsoever.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Dave Airlie [Thu, 17 Aug 2017 19:41:32 +0000 (05:41 +1000)]
Merge tag 'omapdrm-4.14' of git://git.kernel.org/pub/scm/linux/kernel/git/tomba/linux into drm-next
omapdrm changes for v4.14
* HDMI hot plug IRQ support (instead of polling)
* Big driver cleanup from Laurent (no functional changes)
* OMAP5 DSI support (only the pinmuxing was missing)
* tag 'omapdrm-4.14' of git://git.kernel.org/pub/scm/linux/kernel/git/tomba/linux: (60 commits)
drm/omap: Potential NULL deref in omap_crtc_duplicate_state()
drm/omap: remove no-op cleanup code
drm/omap: rename omapdrm device back
drm: omapdrm: Remove omapdrm platform data
ARM: OMAP2+: Don't register omapdss device for omapdrm
ARM: OMAP2+: Remove unused omapdrm platform device
drm: omapdrm: Remove the omapdss driver
drm: omapdrm: Register omapdrm platform device in omapdss driver
drm: omapdrm: hdmi: Don't allocate PHY features dynamically
drm: omapdrm: hdmi: Configure the PHY from the HDMI core version
drm: omapdrm: hdmi: Configure the PLL from the HDMI core version
drm: omapdrm: hdmi: Pass HDMI core version as integer to HDMI audio
drm: omapdrm: hdmi: Replace OMAP SoC model check with HDMI xmit version
drm: omapdrm: hdmi: Rename functions and structures to use hdmi_ prefix
drm/omap: add OMAP5 DSIPHY lane-enable support
drm/omap: use regmap_update_bit() when muxing DSI pads
drm: omapdrm: Remove dss_features.h
drm: omapdrm: Move supported outputs feature to dss driver
drm: omapdrm: Move DSS_FCK feature to dss driver
drm: omapdrm: Move PCD, LINEWIDTH and DOWNSCALE features to dispc driver
...
Dave Airlie [Thu, 17 Aug 2017 19:30:53 +0000 (05:30 +1000)]
Merge branch 'drm-next-4.14' of git://people.freedesktop.org/~agd5f/linux into drm-next
More features for 4.14. Nothing too major here. I have a few more additional
patches for large page support in vega10 among other things, but they require
some resevation object patches from drm-misc-next, so I'll send that request
once you've pulled the latest drm-misc-next. Highlights:
- Fixes for ACP audio on stoney
- SR-IOV fixes for vega10
- various powerplay fixes
- lots of code clean up
* 'drm-next-4.14' of git://people.freedesktop.org/~agd5f/linux: (62 commits)
drm/amdgpu/gfx7: fix function name
drm/amd/amdgpu: Disabling Power Gating for Stoney platform
drm/amd/amdgpu: Added a quirk for Stoney platform
drm/amdgpu: jt_size was wrongly counted twice
drm/amdgpu: fix missing endian-safe guard
drm/amdgpu: ignore digest_size when loading sdma fw for raven
drm/amdgpu: Uninitialized variable in amdgpu_ttm_backend_bind()
drm/amd/powerplay: fix coding style in hwmgr.c
drm/amd/powerplay: refine dmesg info under powerplay.
drm/amdgpu: don't finish the ring if not initialized
drm/radeon: Fix preferred typo
drm/amdgpu: Fix preferred typo
drm/radeon: Fix stolen typo
drm/amdgpu: Fix stolen typo
drm/amd/powerplay: fix coccinelle warnings in vega10_hwmgr.c
drm/amdgpu: set gfx_v9_0_ip_funcs as static
drm/radeon: switch to drm_*{get,put} helpers
drm/amdgpu: switch to drm_*{get,put} helpers
drm/amd/powerplay: add CZ profile support
drm/amd/powerplay: fix PSI not enabled by kmd
...
Dave Airlie [Wed, 16 Aug 2017 21:33:41 +0000 (07:33 +1000)]
Merge tag 'drm-misc-next-2017-08-16' of git://anongit.freedesktop.org/git/drm-misc into drm-next
UAPI Changes:
- vc4: Allow userspace to dictate rendering order in submit_cl ioctl (Eric)
Cross-subsystem Changes:
- vboxvideo: One of Cihangir's patches applies to vboxvideo which is maintained
in staging
Core Changes:
- atomic_legacy_backoff is officially killed (Daniel)
- Extract drm_device.h (Daniel)
- Unregister drm device on unplug (Daniel)
- Rename deprecated drm_*_(un)?reference functions to drm_*_{get|put} (Cihangir)
Driver Changes:
- vc4: Error/destroy path cleanups, log level demotion, edid leak (Eric)
- various: Make various drm_*_funcs structs const (Bhumika)
- tinydrm: add support for LEGO MINDSTORMS EV3 LCD (David)
- various: Second half of .dumb_{map_offset|destroy} defaults set (Noralf)
Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Eric Anholt <eric@anholt.net> Cc: Bhumika Goyal <bhumirks@gmail.com> Cc: Cihangir Akturk <cakturk@gmail.com> Cc: David Lechner <david@lechnology.com> Cc: Noralf Trønnes <noralf@tronnes.org>
* tag 'drm-misc-next-2017-08-16' of git://anongit.freedesktop.org/git/drm-misc: (50 commits)
drm/gem-cma-helper: Remove drm_gem_cma_dumb_map_offset()
drm/virtio: Use the drm_driver.dumb_destroy default
drm/bochs: Use the drm_driver.dumb_destroy default
drm/mgag200: Use the drm_driver.dumb_destroy default
drm/exynos: Use .dumb_map_offset and .dumb_destroy defaults
drm/msm: Use the drm_driver.dumb_destroy default
drm/ast: Use the drm_driver.dumb_destroy default
drm/qxl: Use the drm_driver.dumb_destroy default
drm/udl: Use the drm_driver.dumb_destroy default
drm/cirrus: Use the drm_driver.dumb_destroy default
drm/tegra: Use .dumb_map_offset and .dumb_destroy defaults
drm/gma500: Use .dumb_map_offset and .dumb_destroy defaults
drm/mxsfb: Use .dumb_map_offset and .dumb_destroy defaults
drm/meson: Use .dumb_map_offset and .dumb_destroy defaults
drm/kirin: Use .dumb_map_offset and .dumb_destroy defaults
drm/vc4: Continue the switch to drm_*_put() helpers
drm/vc4: Fix leak of HDMI EDID
dma-buf: fix reservation_object_wait_timeout_rcu to wait correctly v2
dma-buf: add reservation_object_copy_fences (v2)
drm/tinydrm: add support for LEGO MINDSTORMS EV3 LCD
...
Noralf Trønnes [Sun, 6 Aug 2017 15:41:02 +0000 (17:41 +0200)]
drm/exynos: Use .dumb_map_offset and .dumb_destroy defaults
This driver can use the drm_driver.dumb_destroy and
drm_driver.dumb_map_offset defaults, so no need to set them.
Use drm_gem_dumb_map_offset() in exynos_drm_gem_map_ioctl() and
remove exynos_drm_gem_dumb_map_offset().
Dan Carpenter [Fri, 11 Aug 2017 20:16:06 +0000 (23:16 +0300)]
drm/omap: Potential NULL deref in omap_crtc_duplicate_state()
If the kmalloc() fails then we dereference "state" when we set
"state->zpos".
Fixes: 3dfeb631a15d ("drm/omap: Rework the rotation-on-crtc hack") Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Tomi Valkeinen [Tue, 15 Aug 2017 13:04:20 +0000 (16:04 +0300)]
drm/omap: remove no-op cleanup code
The driver sets crtc and plane rotation properties back to 0 degrees in
dev_lastclose() using drm_object_property_set_value().
drm_object_property_set_value() doesn't do anything with atomic drivers,
and a recent change added WARN_ON() when atomic driver calls the
function.
So remove the code.
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Laurent Pinchart [Fri, 11 Aug 2017 13:49:11 +0000 (16:49 +0300)]
ARM: OMAP2+: Don't register omapdss device for omapdrm
The omapdrm driver doesn't need the omapdss device anymore. Although it
can't be removed completely as the fbdev driver still requires it, we
can condition its registration to the usage of the omapfb driver.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com> Acked-by: Tony Lindgren <tony@atomide.com> Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ti.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Laurent Pinchart [Fri, 11 Aug 2017 13:49:08 +0000 (16:49 +0300)]
drm: omapdrm: Register omapdrm platform device in omapdss driver
The omapdrm platform device is a virtual device created for the sole
purpose of handling the omapdss/omapdrm driver split. It should
eventually be removed. As a first step to ease refactoring move its
registration from platform code to driver code.
The omapdrm driver name must be changed internally to avoid probing both
the device registered in platform code and the device registered in the
omapdss driver, as that would otherwise break bisection.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com> Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ti.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Laurent Pinchart [Fri, 11 Aug 2017 13:49:07 +0000 (16:49 +0300)]
drm: omapdrm: hdmi: Don't allocate PHY features dynamically
There's no need to allocate memory dynamically to duplicate the contents
of a const structure, only to store the memory pointer in a const
pointer field. Just use the original structures directly.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Laurent Pinchart [Fri, 11 Aug 2017 13:49:06 +0000 (16:49 +0300)]
drm: omapdrm: hdmi: Configure the PHY from the HDMI core version
The OMAP4 and OMAP5 HDMI PHYs have different properties that require
specific handling in the HDMI PHY driver. This needs knowledge of the
PHY version, which is currently inferred from the DSS version. As part
of the effort to remove usage of the DSS version, use the HDMI
controller version instead.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Laurent Pinchart [Fri, 11 Aug 2017 13:49:05 +0000 (16:49 +0300)]
drm: omapdrm: hdmi: Configure the PLL from the HDMI core version
The OMAP4 and OMAP5 PLLs have different properties that require specific
handling in the HDMI PLL driver. This needs knowledge of the PLL
version, which is currently inferred from the DSS version. AS part of
the effort to remove usage of the DSS version, use the HDMI controller
version instead.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Laurent Pinchart [Fri, 11 Aug 2017 13:49:04 +0000 (16:49 +0300)]
drm: omapdrm: hdmi: Pass HDMI core version as integer to HDMI audio
The HDMI audio driver only needs to know which generation of HDMI
transmitter it deals with, not the detailed SoC model. Pass the version
number as an integer to prepare for removal of the OMAP SoC version from
the omapdrm driver.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com> Acked-by: Mark Brown <broonie@kernel.org> Acked-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Laurent Pinchart [Fri, 11 Aug 2017 13:49:03 +0000 (16:49 +0300)]
drm: omapdrm: hdmi: Replace OMAP SoC model check with HDMI xmit version
The HDMI wrapper code only needs to differentiate between major OMAP
revisions, which can be obtained from the HDMI transmitter compatible
string. Replace the OMAP SoC model checks to prepare for removal of the
OMAP SoC version platform data.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Laurent Pinchart [Fri, 11 Aug 2017 13:49:02 +0000 (16:49 +0300)]
drm: omapdrm: hdmi: Rename functions and structures to use hdmi_ prefix
The dsi_pll_ops structure and dsi_init_pll_data() function incorrectly
use a dsi_ prefix, likely due to copy & paste. Fix it by using the
correct hdmi_ prefix.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Tomi Valkeinen [Thu, 10 Aug 2017 06:33:07 +0000 (09:33 +0300)]
drm/omap: add OMAP5 DSIPHY lane-enable support
We are missing OMAP5 DSIPHY lane-enable support, which has prevented
OMAP5 DSI working in mainline. This patch adds the lane-enable similarly
to the recently added OMAP4 version.
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
The most recent merge commit in airlied/drm-next has problems with
confusing old_crtc_state and new_crtc_state. Use the
for_each_oldnew_crtc_in_state macros to clean up the confusion,
and explicitly look at the correct state instead of looking at
asyh->state.
With these fixes it becomes more obvious what the code is trying to do,
which will hopefully prevent future confusion.
Cc: Dave Airlie <airlied@redhat.com> Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
Alex Deucher [Tue, 15 Aug 2017 14:34:55 +0000 (10:34 -0400)]
drm/amdgpu/gfx7: fix function name
Was using the wrong prefix (gmc rather than gfx). The function
is related to the gfx hw, not gmc. This also makes it consistent
with the naming in gfx8.
Reviewed-by: Harry Wentland <harry.wentland@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Evan Quan [Thu, 10 Aug 2017 07:17:56 +0000 (15:17 +0800)]
drm/amdgpu: fix missing endian-safe guard
Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Dan Carpenter [Wed, 9 Aug 2017 10:30:46 +0000 (13:30 +0300)]
drm/amdgpu: Uninitialized variable in amdgpu_ttm_backend_bind()
My static checker complains that it's possible for "r" to be
uninitialized. It used to be set to zero so this returns it to the old
behavior.
Fixes: 98a7f88ce9a9 ("drm/amdgpu: bind BOs with GTT space allocated directly v2") Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Trigger Huang [Tue, 8 Aug 2017 10:42:51 +0000 (06:42 -0400)]
drm/amdgpu: don't finish the ring if not initialized
If a ring is not initialized, it also should not be finished.
For example, in Vega10's SR-IOV environment, UVD's decode ring is not
initialized, but will be finnished in amdgpu_uvd_sw_fini, because UVD
driver put all the uvd decode ring's finish operation into
amdgpu_uvd_sw_fini function, while not uvd_vXXX_0_sw_fini. This will
lead to amdgpu module unloading failure.
Signed-off-by: Trigger Huang <trigger.huang@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Kent Russell [Tue, 8 Aug 2017 11:50:46 +0000 (07:50 -0400)]
drm/radeon: Fix preferred typo
Change "prefered" to "preferred"
Signed-off-by: Kent Russell <kent.russell@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Kent Russell [Tue, 8 Aug 2017 11:58:01 +0000 (07:58 -0400)]
drm/amdgpu: Fix preferred typo
Change "prefered" to "preferred"
Signed-off-by: Kent Russell <kent.russell@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Kent Russell [Tue, 8 Aug 2017 11:48:52 +0000 (07:48 -0400)]
drm/radeon: Fix stolen typo
Change "stollen" to "stolen"
Signed-off-by: Kent Russell <kent.russell@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Kent Russell [Tue, 8 Aug 2017 11:48:01 +0000 (07:48 -0400)]
drm/amdgpu: Fix stolen typo
Change "stollen" to "stolen"
Signed-off-by: Kent Russell <kent.russell@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Huang Rui [Fri, 4 Aug 2017 08:56:38 +0000 (16:56 +0800)]
drm/amdgpu: set gfx_v9_0_ip_funcs as static
We won't use this member in other files, so set it static.
Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cihangir Akturk [Thu, 3 Aug 2017 11:58:35 +0000 (14:58 +0300)]
drm/radeon: switch to drm_*{get,put} helpers
drm_*_reference() and drm_*_unreference() functions are just
compatibility alias for drm_*_get() and drm_*_put() adn should not be
used by new code. So convert all users of compatibility functions to use
the new APIs.
Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Cihangir Akturk <cakturk@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cihangir Akturk [Thu, 3 Aug 2017 11:58:16 +0000 (14:58 +0300)]
drm/amdgpu: switch to drm_*{get,put} helpers
drm_*_reference() and drm_*_unreference() functions are just
compatibility alias for drm_*_get() and drm_*_put() and should not be
used by new code. So convert all users of compatibility functions to use
the new APIs.
Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Cihangir Akturk <cakturk@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Wed, 14 Jun 2017 22:46:14 +0000 (18:46 -0400)]
drm/amd/powerplay: add CZ profile support
Support the profiling modes for sclk.
v2: delete profileing mode for mclk.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Tested-and-Reviewed-by Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Jean Delvare [Sun, 30 Jul 2017 08:18:25 +0000 (10:18 +0200)]
drm/amdgpu: Fix undue fallthroughs in golden registers initialization
As I was staring at the si_init_golden_registers code, I noticed that
the Pitcairn initialization silently falls through the Cape Verde
initialization, and the Oland initialization falls through the Hainan
initialization. However there is no comment stating that this is
intentional, and the radeon driver doesn't have any such fallthrough,
so I suspect this is not supposed to happen.
Signed-off-by: Jean Delvare <jdelvare@suse.de> Fixes: 62a37553414a ("drm/amdgpu: add si implementation v10") Cc: Ken Wang <Qingqing.Wang@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: "Marek Olšák" <maraeo@gmail.com> Cc: "Christian König" <christian.koenig@amd.com> Cc: Flora Cui <Flora.Cui@amd.com> Reviewed-by: Marek Olšák <marek.olsak@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
Felix Kuehling [Fri, 28 Jul 2017 20:54:54 +0000 (16:54 -0400)]
drm/amdgpu: Fix KFD initialization for multi-GPU systems
kfd2kgd is device-specific, so it should not be a global variable.
Merge amdgpu_amdkfd_load_interface and amdgpu_amdkfd_device_probe
so that it's only needed as a local variable in one function.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Fri, 28 Jul 2017 03:37:35 +0000 (23:37 -0400)]
drm/amdgpu: drop old ip definitions for gfxhub and mmhub
The gfxhub and mmhub code are now helpers for gmc rather
than standalone IPs. When that changes these were left
over. Remove them.
Acked-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
We achieved that by setting S(SYSTEM) and P(PDE as PTE) bit to 1 for
PDEs and setting S bit to 1 for PTEs when the corresponding addresses
are not occupied by gpu driver allocated buffers.
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The parameter init_value contains the value to which we initialized
VRAM bo when AMDGPU_GEM_CREATE_VRAM_CLEARED flag is set.
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 27 Jul 2017 15:43:00 +0000 (17:43 +0200)]
drm/amdgpu: use amdgpu_bo_free_kernel more often
Saves us even more loc.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 27 Jul 2017 15:24:36 +0000 (17:24 +0200)]
drm/amdgpu: use amdgpu_bo_create_kernel more often
Saves us quite a bunch of loc.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 27 Jul 2017 15:08:54 +0000 (17:08 +0200)]
drm/amdgpu: add amdgpu_bo_create_reserved
Same as amdgpu_bo_create_kernel, but keeps the BO reserved.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 27 Jul 2017 12:52:53 +0000 (14:52 +0200)]
drm/amdgpu: improve amdgpu_bo_create_kernel
Make allocating the new BO optional.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 20 Jul 2017 21:58:19 +0000 (23:58 +0200)]
drm/amdgpu: shadow and mn list are mutually exclusive
Save some memory because only one of those is used at all times.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>