summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd
AgeCommit message (Collapse)AuthorFilesLines
2016-07-27drm/amdkfd: destroy dbgmgr in notifier releaseOded Gabbay1-2/+8
commit bc4755a4bd1845ef6e88ac8c62f12e05bb530256 upstream. amdkfd need to destroy the debug manager in case amdkfd's notifier function is called before the unbind function, because in that case, the unbind function will exit without destroying debug manager. Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-07-27drm/amdkfd: unbind only existing processesOded Gabbay1-25/+35
commit 121b78e679ee3ffab780115e260b2775d0cc1f73 upstream. When unbinding a process from a device (initiated by amd_iommu_v2), the driver needs to make sure that process still exists in the process table. There is a possibility that amdkfd's own notifier handler - kfd_process_notifier_release() - was called before the unbind function and it already removed the process from the process table. v2: Because there can be only one process with the specified pasid, and because *p can't be NULL inside the hash_for_each_rcu macro, it is more reasonable to just put the whole code inside the if statement that compares the pasid value. That way, when we exit hash_for_each_rcu, we simply exit the function as well. Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-07-27drm/amdgpu/gfx7: fix broken condition checkAlex Deucher1-1/+1
commit 8b18300c13a1e08e152f6b6a430faac84f986231 upstream. Wrong operator. Reported-by: David Binderman <linuxdev.baldrick@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-06-08drm/amdgpu: Fix hdmi deep color support.Mario Kleiner1-5/+5
commit 9d746ab68163d642dae13756b2b3145b2e38cb65 upstream. When porting the hdmi deep color detection code from radeon-kms to amdgpu-kms apparently some kind of copy and paste error happened, attaching an else branch to the wrong if statement. The result is that hdmi deep color mode is always disabled, regardless of gpu and display capabilities and user wishes, as the code mistakenly thinks that the display doesn't provide the required max_tmds_clock limit and falls back to 8 bpc. This patch fixes deep color support, as tested on a R9 380 Tonga Pro + suitable display, and should be backported to all kernels with amdgpu-kms support. Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-06-08drm/amdgpu: use drm_mode_vrefresh() rather than mode->vrefreshAlex Deucher1-1/+1
commit 6b8812eb004ee2b24aac8b1a711a0e8e797df3ce upstream. This is a port of radeon commit: 3d2d98ee1af0cf6eebfbd6bff4c17d3601ac1284 drm/radeon: use drm_mode_vrefresh() rather than mode->vrefresh to amdgpu. Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-05-11drm/amdgpu: set metadata pointer to NULL after freeing.Dave Airlie1-0/+1
commit 0092d3edcb23fcdb8cbe4159ba94a534290ff982 upstream. Without this there was a double free of the metadata, which ended up freeing the fd table for me here, and taking out the machine more often than not. I reproduced with X.org + modesetting DDX + latest llvm/mesa, also required using dri3. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Dave Airlie <airlied@redhat.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-05-11drm/amdgpu: make sure vertical front porch is at least 1Alex Deucher1-0/+4
commit 0126d4b9a516256f2432ca0dc78ab293a8255378 upstream. hw doesn't like a 0 value. Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-05-05drm/amdkfd: uninitialized variable in dbgdev_wave_control_set_registers()Dan Carpenter1-1/+1
commit 93fce954427effee89e44a976299b15dd75b4bbc upstream. At the end of the function we expect "status" to be zero, but it's either -EINVAL or uninitialized. Fixes: 788bf83db301 ('drm/amdkfd: Add wave control operation to debugger') Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-05-05drm/amdgpu: fix regression on CIK (v2)Grigori Goronzy1-1/+1
This fix was written against drm-next, but when it was backported to 4.5 as a stable fix, the driver internal structure change was missed. Fix that up here to avoid a hang due to waiting for the wrong sequence number. v2: agd: fix up commit message Signed-off-by: Grigori Goronzy <greg@chown.ath.cx> Cc: stable@vger.kernel.org Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-05-05amdgpu/uvd: add uvd fw version for amdgpuSonny Jiang3-1/+5
commit 562e2689baebaa2ac25b7ec934385480ed1cb7d6 upstream. Was previously always hardcoded to 0. Signed-off-by: Sonny Jiang <sonny.jiang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-05-05drm/amdgpu: bump the afmt limit for CZ, ST, PolarisAlex Deucher1-1/+1
commit 83c5cda2ccf40a7a7e4bb674321509b346e23d5a upstream. Fixes array overflow on these chips. Reviewed-by: Harry Wentland <harry.wentland@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-05-05drm/amdgpu: use defines for CRTCs and AMFT blocksAlex Deucher1-2/+2
commit 3ea25f858fd5aeee888059952bbb8e910541eebb upstream. Prerequiste for the next patch which ups the limits. Reviewed-by: Harry Wentland <harry.wentland@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-05-05drm/amdgpu: when suspending, if uvd/vce was running. need to cancel delay work.Rex Zhu2-0/+3
commit 85cc88f02eb0ecf44493c1b2ebb6f206cd5fc321 upstream. fix the issue that when resume back, uvd/vce dpm was disabled and uvd/vce's performace dropped. Signed-off-by: Rex Zhu <Rex.Zhu@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> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-05-05Revert "drm/amdgpu: disable runtime pm on PX laptops without dGPU power control"Alex Deucher2-11/+5
commit e9bef455af8eb0e837e179aab8988ae2649fd8d3 upstream. This reverts commit bedf2a65c1aa8fb29ba8527fd00c0f68ec1f55f1. See the radeon revert for an extended description. Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-20drm/amdgpu/gmc: use proper register for vram type on FijiAlex Deucher1-1/+8
commit b634de4f446c062a0c95ec4d150b4cf7c85e3526 upstream. The offset changed on Fiji. Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-20drm/amdgpu/gmc: move vram type fetching into sw_initAlex Deucher2-16/+16
commit d1518a1db31a25682ea09c4b135fa72d9883be42 upstream. early_init gets called before atom asic init so on non-posted cards, the vram type is not initialized. Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-12drm/amdgpu: include the right version of gmc header files for icelandKen Wang1-2/+2
commit 16a8a49be1b878ef6dd5d1663d456e254e54ae3d upstream. Signed-off-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-12drm/amdgpu: disable runtime pm on PX laptops without dGPU power controlAlex Deucher2-5/+11
commit bedf2a65c1aa8fb29ba8527fd00c0f68ec1f55f1 upstream. Some PX laptops don't provide an ACPI method to control dGPU power. On those systems, the driver is responsible for handling the dGPU power state. Disable runtime PM on them until support for this is implemented. Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-16drm/amdgpu: Fix error handling in amdgpu_flip_work_func.Mario Kleiner1-2/+2
commit 90e94b160c7f647ddffda707f5e3c0c66c170df8 upstream. The patch e1d09dc0ccc6: "drm/amdgpu: Don't hang in amdgpu_flip_work_func on disabled crtc." from Feb 19, 2016, leads to the following static checker warning, as reported by Dan Carpenter in https://lists.freedesktop.org/archives/dri-devel/2016-February/101987.html drivers/gpu/drm/amd/amdgpu/amdgpu_display.c:127 amdgpu_flip_work_func() warn: should this be 'repcnt == -1' drivers/gpu/drm/amd/amdgpu/amdgpu_display.c:136 amdgpu_flip_work_func() error: double unlock 'spin_lock:&crtc->dev->event_lock' drivers/gpu/drm/amd/amdgpu/amdgpu_display.c:136 amdgpu_flip_work_func() error: double unlock 'irqsave:flags' This patch fixes both reported problems: Change post-decrement of repcnt to pre-decrement, so it can't underflow anymore, but still performs up to three repetitions - three is the maximum one could expect in practice. Move the spin_unlock_irqrestore to where it actually belongs. Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com> Cc: Michel Dänzer <michel.daenzer@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-10drm/amdgpu: fix topaz/tonga gmc assignment in 4.4 stableAlex Deucher1-6/+6
When upstream commit 429c45deae6e57f1bb91bfb05b671063fb0cef60 was applied to 4.4 as d60703ca942e8d044d61360bc9792fcab54b95d0 it applied incorrectly to the tonga_ip_blocks array rather than the topaz_ip_blocks array. Fix that up here. Bug: https://bugzilla.kernel.org/show_bug.cgi?id=113951 Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-10drm/amdgpu: Use drm_calloc_large for VM page_tables arrayMichel Dänzer1-4/+3
commit 9571e1d84042f5670df9fabdcbe7dd5da3abe43e upstream. It can be big, depending on the VM address space size, which is tunable via the vm_size module parameter. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93721 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> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-10drm/amdgpu: return from atombios_dp_get_dpcd only when errorArindam Nath1-1/+1
commit 0b39c531cfa12dad54eac238c2e303b994df1ef7 upstream. In amdgpu_connector_hotplug(), we need to start DP link training only after we have received DPCD. The function amdgpu_atombios_dp_get_dpcd() returns non-zero value only when an error condition is met, otherwise returns zero. So in case the function encounters an error, we need to skip rest of the code and return from amdgpu_connector_hotplug() immediately. Only when we are successfull in reading DPCD pin, we should carry on with turning-on the monitor. Signed-off-by: Arindam Nath <arindam.nath@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-10drm/amdgpu/gfx8: specify which engine to wait before vm flushChunming Zhou1-1/+2
commit 9cac537332f5502c103415b25609548c276a09f8 upstream. Select between me and pfp properly. Signed-off-by: Chunming Zhou <David1.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-10drm/amdgpu: apply gfx_v8 fixes to gfx_v7 as wellChristian König1-0/+13
commit feebe91aa9a9d99d9ec157612a614fadb79beb99 upstream. We never ported that back to CIK, so we could run into VM faults here. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-10drm/amdgpu/pm: update current crtc info after setting the powerstateAlex Deucher1-3/+3
commit eda1d1cf8d18383f19cd2b752f786120efa4768f upstream. On CI, we need to see if the number of crtcs changes to determine whether or not we need to upload the mclk table again. In practice we don't currently upload the mclk table again after the initial load. The only reason you would would be to add new states, e.g., for arbitrary mclk setting which is not currently supported. Acked-by: Jordan Lazare <Jordan.Lazare@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-10drm/amdgpu: mask out WC from BO on unsupported archesOded Gabbay1-0/+8
commit a187f17f0e15a046aa5d7263b35df55230d92779 upstream. Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu/pm: adjust display configuration after powerstateAlex Deucher1-2/+3
commit 8e7cedc6f7fe762ffe6e348502be34b11fa79298 upstream. set_power_state defaults to no displays, so we need to update the display configuration after setting up the powerstate on the first call. In most cases this is not an issue since ends up getting called multiple times at any given modeset and the proper order is achieved in the display changed handling at the top of the function. Reviewed-by: Christian König <christian.koenig@amd.com> Acked-by: Jordan Lazare <Jordan.Lazare@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: Don't hang in amdgpu_flip_work_func on disabled crtc.Mario Kleiner1-3/+15
commit e1d09dc0ccc6c91e3916476f636edb76da1f65bb upstream. This fixes a regression introduced in Linux 4.4. This is a port of the same fix for radeon-kms in the patch "drm/radeon: Don't hang in radeon_flip_work_func on disabled crtc. (v2)" Limit the amount of time amdgpu_flip_work_func can delay programming a page flip, by both limiting the maximum amount of time per wait cycle and the maximum number of wait cycles. Continue the flip if the limit is exceeded, even if that may result in a visual or timing glitch. This is to prevent a hang of page flips, as reported in fdo bug #93746: Disconnecting a DisplayPort display in parallel to a kms pageflip getting queued can cause the following hang of page flips and thereby an unusable desktop: 1. kms pageflip ioctl() queues pageflip -> queues execution of amdgpu_flip_work_func. 2. Hotunplug of display causes the driver to DPMS OFF the unplugged display. Display engine shuts down, scanout no longer moves, but stays at its resting position at start line of vblank. 3. amdgpu_flip_work_func executes while crtc is off, and due to the non-moving scanout position, the new flip delay code introduced into Linux 4.4 by commit 8e36f9d33c13 ("drm/amdgpu: Fixup hw vblank counter/ts..") enters an infinite wait loop. 4. After reconnecting the display, the pageflip continues to hang in 3. and the display doesn't update its view of the desktop. This patch fixes the Linux 4.4 regression from fdo bug #93746 <https://bugs.freedesktop.org/show_bug.cgi?id=93746> Reported-by: Bernd Steinhauser <linux@bernd-steinhauser.de> Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Michel Dänzer <michel.daenzer@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-03-04drm/amdgpu: use post-decrement in error handlingRasmus Villemoes1-1/+1
commit 09ccbb74b6718ad4d1290de3f5669212c0ac7d4b upstream. We need to use post-decrement to get the pci_map_page undone also for i==0, and to avoid some very unpleasant behaviour if pci_map_page failed already at i==0. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: fix issue with overlapping userptrsChristian König3-1/+23
commit cc1de6e800c253172334f8774c419dc64401cd2e upstream. Otherwise we could try to evict overlapping userptr BOs in get_user_pages(), leading to a possible circular locking dependency. Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: hold reference to fences in amdgpu_sa_bo_new (v2)Nicolai Hähnle1-1/+4
commit a8d81b36267366603771431747438d18f32ae2d5 upstream. An arbitrary amount of time can pass between spin_unlock and fence_wait_any_timeout, so we need to ensure that nobody frees the fences from under us. A stress test (rapidly starting and killing hundreds of glxgears instances) ran into a deadlock in fence_wait_any_timeout after about an hour, and this race condition appears to be a plausible cause. v2: agd: rebase on upstream Signed-off-by: Nicolai Hähnle <nicolai.haehnle@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: remove unnecessary forward declarationNicolai Hähnle1-2/+0
commit b19763d0d867eb863953500a5c87f2fd663863b8 upstream. Signed-off-by: Nicolai Hähnle <nicolai.haehnle@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: fix s4 resumeFlora Cui1-4/+9
commit ca19852884c8937eed89560f924f5a34cfcc22af upstream. No need to re-init asic if it's already been initialized. Skip IB tests since kernel processes are frozen in thaw. Signed-off-by: Flora Cui <Flora.Cui@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: remove exp hardware support from icelandAlex Deucher1-5/+5
commit dba280b20bfd1c2bed8a07ce3f75a6da8ba7d247 upstream. It's working now. bug: https://bugs.freedesktop.org/show_bug.cgi?id=92270 Reviewed-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: don't load MEC2 on topazAlex Deucher2-11/+5
commit 97dde76a30c2e67fa5fb9cb6a4072c0178c9df26 upstream. Not validated. Reviewed-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: drop topaz support from gmc8 moduleAlex Deucher1-27/+1
commit 8878d8548ac7fae43cd6d82579f966eb8825e282 upstream. topaz is actually gmc7. Reviewed-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: pull topaz gmc bits into gmc_v7Alex Deucher1-2/+33
commit 72b459c8f716ef03a8a0c78078547ce64d8d29a2 upstream. Add the topaz golden settings into the gmc7 module. Reviewed-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: The VI specific EXE bit should only apply to GMC v8.0 aboveKen Wang1-1/+1
commit 8f3c162961fc2d92ec73a66496aab69eb2e19c36 upstream. Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Ken Wang <Qingqing.Wang@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: iceland use CI based MC IPKen Wang2-4/+13
commit 429c45deae6e57f1bb91bfb05b671063fb0cef60 upstream. Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Ken Wang <Qingqing.Wang@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: move gmc7 support out of CIK dependencyAlex Deucher1-1/+2
commit e42d85261680edfc350a6c2a86b7fbb44a85014b upstream. It's used by iceland which is VI. Reviewed-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: no need to load MC firmware on fijiAlex Deucher1-4/+2
commit ad32152eb26043d165eed9406cb9e2f7011f6b10 upstream. Vbios does this for us on asic_init. Reviewed-by: Ken Wang >Qingqing.Wang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: fix amdgpu_bo_pin_restricted VRAM placing v2Christian König1-1/+2
commit 78d0e182b6c1f5336f6e8cbb197f403276dabc7f upstream. We could pin BOs into invisible VRAM otherwise. v2: make logic more readable as suggested by Michel Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> (v1) Reviewed-by: Rex Zhu <Rex.Zhu@amd.com> (v1) Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: fix tonga smu resumeAlex Deucher1-15/+2
commit e160e4db833c7e8587ec3c88efaed0d84f1bcf42 upstream. Need to make sure smu buffers are pinned on resume. This matches what Fiji does. Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Ken Wang <Qingqing.Wang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: fix lost sync_to if scheduler is enabled.Chunming Zhou1-2/+3
commit 888c9e33e4c5a503285921046c621f7c73199d2f upstream. when scheduler is enabled, the semaphore isn't used at all. Signed-off-by: Chunming Zhou <David1.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: call hpd_irq_event on resumeAlex Deucher1-0/+1
commit 54fb2a5cd0baf8e97d743de411e2f832d1afa68d upstream. Need to call this on resume if displays changes during suspend in order to properly be notified of changes. Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-04drm/amdgpu: Fix off-by-one errors in amdgpu_vm_bo_mapFelix Kuehling1-5/+5
commit 005ae95e6ec119c64e2d16eb65a94c49e1dcf9f0 upstream. eaddr is sometimes treated as the last address inside the address range, and sometimes as the first address outside the range. This was resulting in errors when a test filled up the entire address space. Make it consistent to always be the last address within the range. Signed-off-by: Felix.Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-12-17drm/amdgpu: fix user fence handlingChristian König2-22/+44
This fixes a random corruption under memory pressure. We need to fence the BO for the user fence as well, otherwise it might be swapped out and the GPU could write the fence value to an undesired location. 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> Cc: stable@vger.kernel.org
2015-12-09drm/amdgpu: fix the lost duplicates checkingChunming Zhou1-0/+8
Signed-off-by: Chunming Zhou <David1.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> Cc: stable@vger.kernel.org
2015-12-04drm/amdgpu: Fixup hw vblank counter/ts for new drm_update_vblank_count() (v3)Alex Deucher6-30/+140
commit 4dfd6486 "drm: Use vblank timestamps to guesstimate how many vblanks were missed" introduced in Linux 4.4-rc1 makes the drm core more fragile to drivers which don't update hw vblank counters and vblank timestamps in sync with firing of the vblank irq and essentially at leading edge of vblank. This exposed a problem with radeon-kms/amdgpu-kms which do not satisfy above requirements: The vblank irq fires a few scanlines before start of vblank, but programmed pageflips complete at start of vblank and vblank timestamps update at start of vblank, whereas the hw vblank counter increments only later, at start of vsync. This leads to problems like off by one errors for vblank counter updates, vblank counters apparently going backwards or vblank timestamps apparently having time going backwards. The net result is stuttering of graphics in games, or little hangs, as well as total failure of timing sensitive applications. See bug #93147 for an example of the regression on Linux 4.4-rc: https://bugs.freedesktop.org/show_bug.cgi?id=93147 This patch tries to align all above events better from the viewpoint of the drm core / of external callers to fix the problem: 1. The apparent start of vblank is shifted a few scanlines earlier, so the vblank irq now always happens after start of this extended vblank interval and thereby drm_update_vblank_count() always samples the updated vblank count and timestamp of the new vblank interval. To achieve this, the reporting of scanout positions by radeon_get_crtc_scanoutpos() now operates as if the vblank starts radeon_crtc->lb_vblank_lead_lines before the real start of the hw vblank interval. This means that the vblank timestamps which are based on these scanout positions will now update at this earlier start of vblank. 2. The driver->get_vblank_counter() function will bump the returned vblank count as read from the hw by +1 if the query happens after the shifted earlier start of the vblank, but before the real hw increment at start of vsync, so the counter appears to increment at start of vblank in sync with the timestamp update. 3. Calls from vblank irq-context and regular non-irq calls are now treated identical, always simulating the shifted vblank start, to avoid inconsistent results for queries happening from vblank irq vs. happening from drm_vblank_enable() or vblank_disable_fn(). 4. The radeon_flip_work_func will delay mmio programming a pageflip until the start of the real vblank iff it happens to execute inside the shifted earlier start of the vblank, so pageflips now also appear to execute at start of the shifted vblank, in sync with vblank counter and timestamp updates. This to avoid some races between updates of vblank count and timestamps that are used for swap scheduling and pageflip execution which could cause pageflips to execute before the scheduled target vblank. The lb_vblank_lead_lines "fudge" value is calculated as the size of the display controllers line buffer in scanlines for the given video mode: Vblank irq's are triggered by the line buffer logic when the line buffer refill for a video frame ends, ie. when the line buffer source read position enters the hw vblank. This means that a vblank irq could fire at most as many scanlines before the current reported scanout position of the crtc timing generator as the number of scanlines the line buffer can maximally hold for a given video mode. This patch has been successfully tested on a RV730 card with DCE-3 display engine and on a evergreen card with DCE-4 display engine, in single-display and dual-display configuration, with different video modes. A similar patch is needed for amdgpu-kms to fix the same problem. Limitations: - Maybe replace the udelay() in the flip_work_func() by a suitable usleep_range() for a bit better efficiency? Will try that. - Line buffer sizes in pixels are hard-coded on < DCE-4 to a value i just guessed to be high enough to work ok, lacking info on the true sizes atm. Probably fixes: fdo#93147 Port of Mario's radeon fix to amdgpu. Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (v1) Reviewed-by: Mario Kleiner <mario.kleiner.de@gmail.com> (v2) Refine amdgpu_flip_work_func() for better efficiency. In amdgpu_flip_work_func, replace the busy waiting udelay(5) with event lock held by a more performance and energy efficient usleep_range() until at least predicted true start of hw vblank, with some slack for scheduler happiness. Release the event lock during waits to not delay other outputs in doing their stuff, as the waiting can last up to 200 usecs in some cases. Also small fix to code comment and formatting in that function. (v2) Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com> (v3) Fix crash in crtc disabled case
2015-12-04drm/amdgpu: add spin lock to protect freed list in vm (v2)jimqu2-3/+15
there is a protection fault about freed list when OCL test. add a spin lock to protect it. v2: drop changes in vm_fini Signed-off-by: JimQu <jim.qu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
generated by cgit v1.2.3 (git 2.39.0) at 2025-09-16 16:54:43 +0300