kernel/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c, branch v6.6.40

drm/amdgpu: Fix pci state save during mode-1 reset

2024-07-05T07:33:53+00:00

[ Upstream commit 74fa02c4a5ea1ade5156a6ce494d3ea83881c2d8 ] Cache the PCI state before bus master is disabled. The saved state is later used for other cases like restoring config space after mode-2 reset. Fixes: 5c03e5843e6b ("drm/amdgpu:add smu mode1/2 support for aldebaran") Signed-off-by: Lijo Lazar Reviewed-by: Feifei Xu Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

Revert "drm/amd/amdgpu: Fix potential ioremap() memory leaks in amdgpu_device_init()"

2024-04-13T11:07:41+00:00

commit 03c6284df179de3a4a6e0684764b1c71d2a405e2 upstream. This patch causes the following iounmap erorr and calltrace iounmap: bad address 00000000d0b3631f The original patch was unjustified because amdgpu_device_fini_sw() will always cleanup the rmmio mapping. This reverts commit eb4f139888f636614dab3bcce97ff61cefc4b3a7. Signed-off-by: Ma Jun Suggested-by: Christian König Reviewed-by: Christian König Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman

drm/amd/amdgpu: Fix potential ioremap() memory leaks in amdgpu_device_init()

2024-04-13T11:07:36+00:00

[ Upstream commit eb4f139888f636614dab3bcce97ff61cefc4b3a7 ] This ensures that the memory mapped by ioremap for adev->rmmio, is properly handled in amdgpu_device_init(). If the function exits early due to an error, the memory is unmapped. If the function completes successfully, the memory remains mapped. Reported by smatch: drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:4337 amdgpu_device_init() warn: 'adev->rmmio' from ioremap() not released on lines: 4035,4045,4051,4058,4068,4337 Cc: Christian König Cc: Alex Deucher Signed-off-by: Srinivasan Shanmugam Reviewed-by: Christian König Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amd: Flush GFXOFF requests in prepare stage

2024-04-10T14:35:55+00:00

[ Upstream commit ca299b4512d4b4f516732a48ce9aa19d91f4473e ] If the system hasn't entered GFXOFF when suspend starts it can cause hangs accessing GC and RLC during the suspend stage. Cc: # 6.1.y: 5095d5418193 ("drm/amd: Evict resources during PM ops prepare() callback") Cc: # 6.1.y: cb11ca3233aa ("drm/amd: Add concept of running prepare_suspend() sequence for IP blocks") Cc: # 6.1.y: 2ceec37b0e3d ("drm/amd: Add missing kernel doc for prepare_suspend()") Cc: # 6.1.y: 3a9626c816db ("drm/amd: Stop evicting resources on APUs in suspend") Cc: # 6.6.y: 5095d5418193 ("drm/amd: Evict resources during PM ops prepare() callback") Cc: # 6.6.y: cb11ca3233aa ("drm/amd: Add concept of running prepare_suspend() sequence for IP blocks") Cc: # 6.6.y: 2ceec37b0e3d ("drm/amd: Add missing kernel doc for prepare_suspend()") Cc: # 6.6.y: 3a9626c816db ("drm/amd: Stop evicting resources on APUs in suspend") Cc: # 6.1+ Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3132 Fixes: ab4750332dbe ("drm/amdgpu/sdma5.2: add begin/end_use ring callbacks") Reviewed-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amd: Add concept of running prepare_suspend() sequence for IP blocks

2024-04-10T14:35:55+00:00

[ Upstream commit cb11ca3233aa3303dc11dca25977d2e7f24be00f ] If any IP blocks allocate memory during their hw_fini() sequence this can cause the suspend to fail under memory pressure. Introduce a new phase that IP blocks can use to allocate memory before suspend starts so that it can potentially be evicted into swap instead. Reviewed-by: Christian König Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher Stable-dep-of: ca299b4512d4 ("drm/amd: Flush GFXOFF requests in prepare stage") Signed-off-by: Sasha Levin

drm/amd: Evict resources during PM ops prepare() callback

2024-04-10T14:35:55+00:00

[ Upstream commit 5095d5418193eb2748c7d8553c7150b8f1c44696 ] Linux PM core has a prepare() callback run before suspend. If the system is under high memory pressure, the resources may need to be evicted into swap instead. If the storage backing for swap is offlined during the suspend() step then such a call may fail. So move this step into prepare() to move evict majority of resources and update all non-pmops callers to call the same callback. Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2362 Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher Stable-dep-of: ca299b4512d4 ("drm/amd: Flush GFXOFF requests in prepare stage") Signed-off-by: Sasha Levin

Revert "drm/amd: flush any delayed gfxoff on suspend entry"

2024-02-23T08:25:01+00:00

commit 916361685319098f696b798ef1560f69ed96e934 upstream. commit ab4750332dbe ("drm/amdgpu/sdma5.2: add begin/end_use ring callbacks") caused GFXOFF control to be used more heavily and the codepath that was removed from commit 0dee72639533 ("drm/amd: flush any delayed gfxoff on suspend entry") now can be exercised at suspend again. Users report that by using GNOME to suspend the lockscreen trigger will cause SDMA traffic and the system can deadlock. This reverts commit 0dee726395333fea833eaaf838bc80962df886c8. Acked-by: Alex Deucher Fixes: ab4750332dbe ("drm/amdgpu/sdma5.2: add begin/end_use ring callbacks") Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman

drm/amdgpu: Release 'adev->pm.fw' before return in 'amdgpu_device_need_post()'

2024-02-05T20:14:33+00:00

[ Upstream commit 8a44fdd3cf91debbd09b43bd2519ad2b2486ccf4 ] In function 'amdgpu_device_need_post(struct amdgpu_device *adev)' - 'adev->pm.fw' may not be released before return. Using the function release_firmware() to release adev->pm.fw. Thus fixing the below: drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:1571 amdgpu_device_need_post() warn: 'adev->pm.fw' from request_firmware() not released on lines: 1554. Cc: Monk Liu Cc: Christian König Cc: Alex Deucher Signed-off-by: Srinivasan Shanmugam Suggested-by: Lijo Lazar Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdgpu: skip gpu_info fw loading on navi12

2024-01-10T16:17:01+00:00

commit 21f6137c64c65d6808c4a81006956197ca203383 upstream. It's no longer required. Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2318 Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdgpu: disable MCBP by default

2023-12-13T17:45:30+00:00

[ Upstream commit d6a57588666301acd9d42d3b00d74240964f07f6 ] Disable MCBP(mid command buffer preemption) by default as old Mesa hangs with it. We shall not enable the feature that breaks old usermode driver. Fixes: 50a7c8765ca6 ("drm/amdgpu: enable mcbp by default on gfx9") Signed-off-by: Jiadong Zhu Acked-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin