From 84c63d040938f64a7dc195696301166e75231bf5 Mon Sep 17 00:00:00 2001 From: Nikola Cornij Date: Thu, 6 May 2021 22:46:52 -0400 Subject: drm/amd/display: Use the correct max downscaling value for DCN3.x family [why] As per spec, DCN3.x can do 6:1 downscaling and DCN2.x can do 4:1. The max downscaling limit value for DCN2.x is 250, which means it's calculated as 1000 / 4 = 250. For DCN3.x this then gives 1000 / 6 = 167. [how] Set maximum downscaling limit to 167 for DCN3.x Signed-off-by: Nikola Cornij Reviewed-by: Charlene Liu Reviewed-by: Harry Wentland Acked-by: Stylon Wang Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c | 7 ++++--- drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c | 7 ++++--- drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c | 7 ++++--- 3 files changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 4a5fa23d8e7b..5fcc2e64305d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -826,10 +826,11 @@ static const struct dc_plane_cap plane_cap = { .fp16 = 16000 }, + /* 6:1 downscaling ratio: 1000/6 = 166.666 */ .max_downscale_factor = { - .argb8888 = 600, - .nv12 = 600, - .fp16 = 600 + .argb8888 = 167, + .nv12 = 167, + .fp16 = 167 } }; diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c index 5b54b7fc5105..472696f949ac 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c @@ -843,10 +843,11 @@ static const struct dc_plane_cap plane_cap = { .fp16 = 16000 }, + /* 6:1 downscaling ratio: 1000/6 = 166.666 */ .max_downscale_factor = { - .argb8888 = 600, - .nv12 = 600, - .fp16 = 600 + .argb8888 = 167, + .nv12 = 167, + .fp16 = 167 }, 64, 64 diff --git a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c index fc2dea243d1b..a33f0365329b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c @@ -284,10 +284,11 @@ static const struct dc_plane_cap plane_cap = { .nv12 = 16000, .fp16 = 16000 }, + /* 6:1 downscaling ratio: 1000/6 = 166.666 */ .max_downscale_factor = { - .argb8888 = 600, - .nv12 = 600, - .fp16 = 600 + .argb8888 = 167, + .nv12 = 167, + .fp16 = 167 }, 16, 16 -- cgit v1.2.3 From 0c8df343c200529e6b9820bdfed01814140f75e4 Mon Sep 17 00:00:00 2001 From: Christian König Date: Wed, 12 May 2021 10:36:43 +0200 Subject: drm/radeon: use the dummy page for GART if needed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Imported BOs don't have a pagelist any more. Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Fixes: 0575ff3d33cd ("drm/radeon: stop using pages with drm_prime_sg_to_page_addr_arrays v2") CC: stable@vger.kernel.org # 5.12 --- drivers/gpu/drm/radeon/radeon_gart.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c index 3808a753127b..04109a2a6fd7 100644 --- a/drivers/gpu/drm/radeon/radeon_gart.c +++ b/drivers/gpu/drm/radeon/radeon_gart.c @@ -301,7 +301,8 @@ int radeon_gart_bind(struct radeon_device *rdev, unsigned offset, p = t / (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); for (i = 0; i < pages; i++, p++) { - rdev->gart.pages[p] = pagelist[i]; + rdev->gart.pages[p] = pagelist ? pagelist[i] : + rdev->dummy_page.page; page_base = dma_addr[i]; for (j = 0; j < (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); j++, t++) { page_entry = radeon_gart_get_page_entry(page_base, flags); -- cgit v1.2.3 From d53751568359e5b3ffb859b13cbd79dc77a571f1 Mon Sep 17 00:00:00 2001 From: Yi Li Date: Fri, 14 May 2021 14:40:39 +0800 Subject: drm/amdgpu: Fix GPU TLB update error when PAGE_SIZE > AMDGPU_PAGE_SIZE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When PAGE_SIZE is larger than AMDGPU_PAGE_SIZE, the number of GPU TLB entries which need to update in amdgpu_map_buffer() should be multiplied by AMDGPU_GPU_PAGES_IN_CPU_PAGE (PAGE_SIZE / AMDGPU_PAGE_SIZE). Reviewed-by: Christian König Signed-off-by: Yi Li Signed-off-by: Huacai Chen Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 3bef0432cac2..a376a993e474 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -225,7 +225,7 @@ static int amdgpu_ttm_map_buffer(struct ttm_buffer_object *bo, *addr += mm_cur->start & ~PAGE_MASK; num_dw = ALIGN(adev->mman.buffer_funcs->copy_num_dw, 8); - num_bytes = num_pages * 8; + num_bytes = num_pages * 8 * AMDGPU_GPU_PAGES_IN_CPU_PAGE; r = amdgpu_job_alloc_with_ib(adev, num_dw * 4 + num_bytes, AMDGPU_IB_POOL_DELAYED, &job); -- cgit v1.2.3 From dbd1003d1252db5973dddf20b24bb0106ac52aa2 Mon Sep 17 00:00:00 2001 From: Changfeng Date: Fri, 14 May 2021 15:28:25 +0800 Subject: drm/amdgpu: disable 3DCGCG on picasso/raven1 to avoid compute hang There is problem with 3DCGCG firmware and it will cause compute test hang on picasso/raven1. It needs to disable 3DCGCG in driver to avoid compute hang. Signed-off-by: Changfeng Reviewed-by: Alex Deucher Reviewed-by: Huang Rui Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 10 +++++++--- drivers/gpu/drm/amd/amdgpu/soc15.c | 2 -- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index a078a38c2cee..516467e962b7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -4943,7 +4943,7 @@ static void gfx_v9_0_update_3d_clock_gating(struct amdgpu_device *adev, amdgpu_gfx_rlc_enter_safe_mode(adev); /* Enable 3D CGCG/CGLS */ - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG)) { + if (enable) { /* write cmd to clear cgcg/cgls ov */ def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE); /* unset CGCG override */ @@ -4955,8 +4955,12 @@ static void gfx_v9_0_update_3d_clock_gating(struct amdgpu_device *adev, /* enable 3Dcgcg FSM(0x0000363f) */ def = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D); - data = (0x36 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) | - RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK; + if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG) + data = (0x36 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) | + RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK; + else + data = 0x0 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT; + if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGLS) data |= (0x000F << RLC_CGCG_CGLS_CTRL_3D__CGLS_REP_COMPANSAT_DELAY__SHIFT) | RLC_CGCG_CGLS_CTRL_3D__CGLS_EN_MASK; diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 8e1b9a40839f..980675052b53 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1392,7 +1392,6 @@ static int soc15_common_early_init(void *handle) adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS | AMD_CG_SUPPORT_GFX_CP_LS | - AMD_CG_SUPPORT_GFX_3D_CGCG | AMD_CG_SUPPORT_GFX_3D_CGLS | AMD_CG_SUPPORT_GFX_CGCG | AMD_CG_SUPPORT_GFX_CGLS | @@ -1412,7 +1411,6 @@ static int soc15_common_early_init(void *handle) AMD_CG_SUPPORT_GFX_MGLS | AMD_CG_SUPPORT_GFX_RLC_LS | AMD_CG_SUPPORT_GFX_CP_LS | - AMD_CG_SUPPORT_GFX_3D_CGCG | AMD_CG_SUPPORT_GFX_3D_CGLS | AMD_CG_SUPPORT_GFX_CGCG | AMD_CG_SUPPORT_GFX_CGLS | -- cgit v1.2.3 From 080039273b126eeb0185a61c045893a25dbc046e Mon Sep 17 00:00:00 2001 From: Chris Park Date: Tue, 4 May 2021 16:20:55 -0400 Subject: drm/amd/display: Disconnect non-DP with no EDID [Why] Active DP dongles return no EDID when dongle is connected, but VGA display is taken out. Current driver behavior does not remove the active display when this happens, and this is a gap between dongle DTP and dongle behavior. [How] For active DP dongles and non-DP scenario, disconnect sink on detection when no EDID is read due to timeout. Signed-off-by: Chris Park Reviewed-by: Nicholas Kazlauskas Acked-by: Stylon Wang Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index f4374d83662a..c1f5474c205a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -1076,6 +1076,24 @@ static bool dc_link_detect_helper(struct dc_link *link, dc_is_dvi_signal(link->connector_signal)) { if (prev_sink) dc_sink_release(prev_sink); + link_disconnect_sink(link); + + return false; + } + /* + * Abort detection for DP connectors if we have + * no EDID and connector is active converter + * as there are no display downstream + * + */ + if (dc_is_dp_sst_signal(link->connector_signal) && + (link->dpcd_caps.dongle_type == + DISPLAY_DONGLE_DP_VGA_CONVERTER || + link->dpcd_caps.dongle_type == + DISPLAY_DONGLE_DP_DVI_CONVERTER)) { + if (prev_sink) + dc_sink_release(prev_sink); + link_disconnect_sink(link); return false; } -- cgit v1.2.3 From fa7e6abc75f3d491bc561734312d065dc9dc2a77 Mon Sep 17 00:00:00 2001 From: Jingwen Chen Date: Mon, 17 May 2021 16:16:10 +0800 Subject: drm/amd/amdgpu: fix refcount leak MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [Why] the gem object rfb->base.obj[0] is get according to num_planes in amdgpufb_create, but is not put according to num_planes [How] put rfb->base.obj[0] in amdgpu_fbdev_destroy according to num_planes Signed-off-by: Jingwen Chen Acked-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c index 4f10c4529840..09b048647523 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c @@ -288,10 +288,13 @@ out: static int amdgpu_fbdev_destroy(struct drm_device *dev, struct amdgpu_fbdev *rfbdev) { struct amdgpu_framebuffer *rfb = &rfbdev->rfb; + int i; drm_fb_helper_unregister_fbi(&rfbdev->helper); if (rfb->base.obj[0]) { + for (i = 0; i < rfb->base.format->num_planes; i++) + drm_gem_object_put(rfb->base.obj[0]); amdgpufb_destroy_pinned_object(rfb->base.obj[0]); rfb->base.obj[0] = NULL; drm_framebuffer_unregister_private(&rfb->base); -- cgit v1.2.3 From ab95cb3e1bc44d4376bd8d331b1cff82b99020e3 Mon Sep 17 00:00:00 2001 From: James Zhu Date: Tue, 18 May 2021 08:44:23 -0400 Subject: drm/amdgpu: add video_codecs query support for aldebaran Add video_codecs query support for aldebaran. Signed-off-by: James Zhu Reviewed-by: Leo Liu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/soc15.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 980675052b53..e65c286f93a6 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -302,6 +302,7 @@ static int soc15_query_video_codecs(struct amdgpu_device *adev, bool encode, *codecs = &rv_video_codecs_decode; return 0; case CHIP_ARCTURUS: + case CHIP_ALDEBARAN: case CHIP_RENOIR: if (encode) *codecs = &vega_video_codecs_encode; -- cgit v1.2.3 From 1e5c37385097c35911b0f8a0c67ffd10ee1af9a2 Mon Sep 17 00:00:00 2001 From: xinhui pan Date: Tue, 18 May 2021 10:56:07 +0800 Subject: drm/amdgpu: Fix a use-after-free MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit looks like we forget to set ttm->sg to NULL. Hit panic below [ 1235.844104] general protection fault, probably for non-canonical address 0x6b6b6b6b6b6b7b4b: 0000 [#1] SMP DEBUG_PAGEALLOC NOPTI [ 1235.989074] Call Trace: [ 1235.991751] sg_free_table+0x17/0x20 [ 1235.995667] amdgpu_ttm_backend_unbind.cold+0x4d/0xf7 [amdgpu] [ 1236.002288] amdgpu_ttm_backend_destroy+0x29/0x130 [amdgpu] [ 1236.008464] ttm_tt_destroy+0x1e/0x30 [ttm] [ 1236.013066] ttm_bo_cleanup_memtype_use+0x51/0xa0 [ttm] [ 1236.018783] ttm_bo_release+0x262/0xa50 [ttm] [ 1236.023547] ttm_bo_put+0x82/0xd0 [ttm] [ 1236.027766] amdgpu_bo_unref+0x26/0x50 [amdgpu] [ 1236.032809] amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x7aa/0xd90 [amdgpu] [ 1236.040400] kfd_ioctl_alloc_memory_of_gpu+0xe2/0x330 [amdgpu] [ 1236.046912] kfd_ioctl+0x463/0x690 [amdgpu] Signed-off-by: xinhui pan Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index a376a993e474..d5cbc51c5eaa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1210,6 +1210,7 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_device *bdev, if (gtt && gtt->userptr) { amdgpu_ttm_tt_set_user_pages(ttm, NULL); kfree(ttm->sg); + ttm->sg = NULL; ttm->page_flags &= ~TTM_PAGE_FLAG_SG; return; } -- cgit v1.2.3 From 99c45ba5799d6b938bd9bd20edfeb6f3e3e039b9 Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Mon, 17 May 2021 16:35:40 +0800 Subject: drm/amdgpu: update gc golden setting for Navi12 Current golden setting is out of date. Signed-off-by: Guchun Chen Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 2408ed4c7d84..7ce76a6b3a35 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -1395,9 +1395,10 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG, 0xffffffff, 0x20000000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG2, 0xffffffff, 0x00000420), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000200), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x04800000), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x04900000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DFSM_TILES_IN_FLIGHT, 0x0000ffff, 0x0000003f), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_LAST_OF_BURST_CONFIG, 0xffffffff, 0x03860204), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1800ff, 0x00000044), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff0ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGE_PRIV_CONTROL, 0x00007fff, 0x000001fe), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0xffffffff, 0xe4e4e4e4), @@ -1415,12 +1416,13 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0x00000820, 0x00000820), SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_SPARE, 0xffffffff, 0xffff3101), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1, 0x001f0000, 0x00070104), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ALU_CLK_CTRL, 0xffffffff, 0xffffffff), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ARB_CONFIG, 0x00000133, 0x00000130), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_LDS_CLK_CTRL, 0xffffffff, 0xffffffff), SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CNTL, 0xffdf80ff, 0x479c0010), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffffffff, 0x00800000) + SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffffffff, 0x00c00000) }; static bool gfx_v10_is_rlcg_rw(struct amdgpu_device *adev, u32 offset, uint32_t *flag, bool write) -- cgit v1.2.3 From 77194d8642dd4cb7ea8ced77bfaea55610574c38 Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Mon, 17 May 2021 16:38:00 +0800 Subject: drm/amdgpu: update sdma golden setting for Navi12 Current golden setting is out of date. Signed-off-by: Guchun Chen Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index 920fc6d4a127..8859133ce37e 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -123,6 +123,10 @@ static const struct soc15_reg_golden golden_settings_sdma_nv14[] = { static const struct soc15_reg_golden golden_settings_sdma_nv12[] = { SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_RLC3_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_GB_ADDR_CONFIG, 0x001877ff, 0x00000044), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_GB_ADDR_CONFIG_READ, 0x001877ff, 0x00000044), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_GB_ADDR_CONFIG, 0x001877ff, 0x00000044), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_GB_ADDR_CONFIG_READ, 0x001877ff, 0x00000044), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_RLC3_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000), }; -- cgit v1.2.3 From 9c2876d56f1ce9b6b2072f1446fb1e8d1532cb3d Mon Sep 17 00:00:00 2001 From: Lang Yu Date: Mon, 17 May 2021 12:47:20 +0800 Subject: drm/amd/amdgpu: fix a potential deadlock in gpu reset MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When amdgpu_ib_ring_tests failed, the reset logic called amdgpu_device_ip_suspend twice, then deadlock occurred. Deadlock log: [ 805.655192] amdgpu 0000:04:00.0: amdgpu: ib ring test failed (-110). [ 806.290952] [drm] free PSP TMR buffer [ 806.319406] ============================================ [ 806.320315] WARNING: possible recursive locking detected [ 806.321225] 5.11.0-custom #1 Tainted: G W OEL [ 806.322135] -------------------------------------------- [ 806.323043] cat/2593 is trying to acquire lock: [ 806.323825] ffff888136b1cdc8 (&adev->dm.dc_lock){+.+.}-{3:3}, at: dm_suspend+0xb8/0x1d0 [amdgpu] [ 806.325668] but task is already holding lock: [ 806.326664] ffff888136b1cdc8 (&adev->dm.dc_lock){+.+.}-{3:3}, at: dm_suspend+0xb8/0x1d0 [amdgpu] [ 806.328430] other info that might help us debug this: [ 806.329539] Possible unsafe locking scenario: [ 806.330549] CPU0 [ 806.330983] ---- [ 806.331416] lock(&adev->dm.dc_lock); [ 806.332086] lock(&adev->dm.dc_lock); [ 806.332738] *** DEADLOCK *** [ 806.333747] May be due to missing lock nesting notation [ 806.334899] 3 locks held by cat/2593: [ 806.335537] #0: ffff888100d3f1b8 (&attr->mutex){+.+.}-{3:3}, at: simple_attr_read+0x4e/0x110 [ 806.337009] #1: ffff888136b1fd78 (&adev->reset_sem){++++}-{3:3}, at: amdgpu_device_lock_adev+0x42/0x94 [amdgpu] [ 806.339018] #2: ffff888136b1cdc8 (&adev->dm.dc_lock){+.+.}-{3:3}, at: dm_suspend+0xb8/0x1d0 [amdgpu] [ 806.340869] stack backtrace: [ 806.341621] CPU: 6 PID: 2593 Comm: cat Tainted: G W OEL 5.11.0-custom #1 [ 806.342921] Hardware name: AMD Celadon-CZN/Celadon-CZN, BIOS WLD0C23N_Weekly_20_12_2 12/23/2020 [ 806.344413] Call Trace: [ 806.344849] dump_stack+0x93/0xbd [ 806.345435] __lock_acquire.cold+0x18a/0x2cf [ 806.346179] lock_acquire+0xca/0x390 [ 806.346807] ? dm_suspend+0xb8/0x1d0 [amdgpu] [ 806.347813] __mutex_lock+0x9b/0x930 [ 806.348454] ? dm_suspend+0xb8/0x1d0 [amdgpu] [ 806.349434] ? amdgpu_device_indirect_rreg+0x58/0x70 [amdgpu] [ 806.350581] ? _raw_spin_unlock_irqrestore+0x47/0x50 [ 806.351437] ? dm_suspend+0xb8/0x1d0 [amdgpu] [ 806.352437] ? rcu_read_lock_sched_held+0x4f/0x80 [ 806.353252] ? rcu_read_lock_sched_held+0x4f/0x80 [ 806.354064] mutex_lock_nested+0x1b/0x20 [ 806.354747] ? mutex_lock_nested+0x1b/0x20 [ 806.355457] dm_suspend+0xb8/0x1d0 [amdgpu] [ 806.356427] ? soc15_common_set_clockgating_state+0x17d/0x19 [amdgpu] [ 806.357736] amdgpu_device_ip_suspend_phase1+0x78/0xd0 [amdgpu] [ 806.360394] amdgpu_device_ip_suspend+0x21/0x70 [amdgpu] [ 806.362926] amdgpu_device_pre_asic_reset+0xb3/0x270 [amdgpu] [ 806.365560] amdgpu_device_gpu_recover.cold+0x679/0x8eb [amdgpu] Signed-off-by: Lang Yu Acked-by: Christian KÃnig Reviewed-by: Andrey Grodzovsky Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 8b2a37bf2adf..66ddfe4f58c2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4479,7 +4479,6 @@ out: r = amdgpu_ib_ring_tests(tmp_adev); if (r) { dev_err(tmp_adev->dev, "ib ring test failed (%d).\n", r); - r = amdgpu_device_ip_suspend(tmp_adev); need_full_reset = true; r = -EAGAIN; goto end; -- cgit v1.2.3 From a2b4785f01280a4291edb9fda69032fc2e4bfd3f Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 18 May 2021 17:48:02 +0200 Subject: drm/amdgpu: stop touching sched.ready in the backend MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This unfortunately comes up in regular intervals and breaks GPU reset for the engine in question. The sched.ready flag controls if an engine can't get working during hw_init, but should never be set to false during hw_fini. v2: squash in unused variable fix (Alex) Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c | 2 -- drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c | 2 -- drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 5 ----- drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 8 +------- 4 files changed, 1 insertion(+), 16 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c index 83531997aeba..938ef4ce5b76 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c @@ -198,8 +198,6 @@ static int jpeg_v2_5_hw_fini(void *handle) if (adev->jpeg.cur_state != AMD_PG_STATE_GATE && RREG32_SOC15(JPEG, i, mmUVD_JRBC_STATUS)) jpeg_v2_5_set_powergating_state(adev, AMD_PG_STATE_GATE); - - ring->sched.ready = false; } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c index de5dfcfb3859..94be35357f7d 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c @@ -166,8 +166,6 @@ static int jpeg_v3_0_hw_fini(void *handle) RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS)) jpeg_v3_0_set_powergating_state(adev, AMD_PG_STATE_GATE); - ring->sched.ready = false; - return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index b1ad9e52b234..240596b25fe4 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -497,11 +497,6 @@ static void sdma_v5_2_gfx_stop(struct amdgpu_device *adev) ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, 0); WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL), ib_cntl); } - - sdma0->sched.ready = false; - sdma1->sched.ready = false; - sdma2->sched.ready = false; - sdma3->sched.ready = false; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index cf165ab5dd26..14470da52113 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -373,7 +373,7 @@ static int vcn_v3_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; struct amdgpu_ring *ring; - int i, j; + int i; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { if (adev->vcn.harvest_config & (1 << i)) @@ -388,12 +388,6 @@ static int vcn_v3_0_hw_fini(void *handle) vcn_v3_0_set_powergating_state(adev, AMD_PG_STATE_GATE); } } - ring->sched.ready = false; - - for (j = 0; j < adev->vcn.num_enc_rings; ++j) { - ring = &adev->vcn.inst[i].ring_enc[j]; - ring->sched.ready = false; - } } return 0; -- cgit v1.2.3