From 877f26bf3ca65447e923e86305a7f2a20d059e21 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 26 Jan 2023 10:15:37 -0500 Subject: [PATCH 01/14] drm/amd/display: disable S/G display on DCN 2.1.0 Causes flickering or white screens in some configurations. Disable it for now until we can fix the issue. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2352 Cc: roman.li@amd.com Cc: yifan1.zhang@amd.com Reviewed-by: Yifan Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 31bce529f685..da2ec41a0477 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1499,7 +1499,6 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) (adev->apu_flags & AMD_APU_IS_PICASSO)) init_data.flags.gpu_vm_support = true; break; - case IP_VERSION(2, 1, 0): case IP_VERSION(3, 0, 1): case IP_VERSION(3, 1, 2): case IP_VERSION(3, 1, 3): From 077e9659581acab70f2dcc04b5bc799aca3a056b Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 25 Jan 2023 09:57:27 -0500 Subject: [PATCH 02/14] drm/amd/display: disable S/G display on DCN 3.1.2/3 Causes flickering or white screens in some configurations. Disable it for now until we can fix the issue. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2352 Cc: roman.li@amd.com Cc: yifan1.zhang@amd.com Reviewed-by: Yifan Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index da2ec41a0477..78e047e1429c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1500,8 +1500,6 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) init_data.flags.gpu_vm_support = true; break; case IP_VERSION(3, 0, 1): - case IP_VERSION(3, 1, 2): - case IP_VERSION(3, 1, 3): case IP_VERSION(3, 1, 6): init_data.flags.gpu_vm_support = true; break; From 5c4e8c71d1202cd84d870e7e5cb8d6b52f9c3507 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 31 Jan 2023 09:56:46 -0500 Subject: [PATCH 03/14] drm/amd/display: properly handling AGP aperture in vm setup Take into account whether or not the AGP aperture is enabled or not when calculating the system aperture. Fixes white screens with DCN 3.1.4. Based on a patch from Yifan Zhang Cc: Yifan Zhang Acked-by: Harry Wentland Reviewed-by: Yifan Zhang Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.1.x --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 42 ++++++++++++------- 1 file changed, 28 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 78e047e1429c..7f6e27561899 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1184,24 +1184,38 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_ memset(pa_config, 0, sizeof(*pa_config)); - logical_addr_low = min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18; - pt_base = amdgpu_gmc_pd_addr(adev->gart.bo); - - if (adev->apu_flags & AMD_APU_IS_RAVEN2) - /* - * Raven2 has a HW issue that it is unable to use the vram which - * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the - * workaround that increase system aperture high address (add 1) - * to get rid of the VM fault and hardware hang. - */ - logical_addr_high = max((adev->gmc.fb_end >> 18) + 0x1, adev->gmc.agp_end >> 18); - else - logical_addr_high = max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18; - agp_base = 0; agp_bot = adev->gmc.agp_start >> 24; agp_top = adev->gmc.agp_end >> 24; + /* AGP aperture is disabled */ + if (agp_bot == agp_top) { + logical_addr_low = adev->gmc.vram_start >> 18; + if (adev->apu_flags & AMD_APU_IS_RAVEN2) + /* + * Raven2 has a HW issue that it is unable to use the vram which + * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the + * workaround that increase system aperture high address (add 1) + * to get rid of the VM fault and hardware hang. + */ + logical_addr_high = (adev->gmc.fb_end >> 18) + 0x1; + else + logical_addr_high = adev->gmc.vram_end >> 18; + } else { + logical_addr_low = min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18; + if (adev->apu_flags & AMD_APU_IS_RAVEN2) + /* + * Raven2 has a HW issue that it is unable to use the vram which + * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the + * workaround that increase system aperture high address (add 1) + * to get rid of the VM fault and hardware hang. + */ + logical_addr_high = max((adev->gmc.fb_end >> 18) + 0x1, adev->gmc.agp_end >> 18); + else + logical_addr_high = max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18; + } + + pt_base = amdgpu_gmc_pd_addr(adev->gart.bo); page_table_start.high_part = (u32)(adev->gmc.gart_start >> 44) & 0xF; page_table_start.low_part = (u32)(adev->gmc.gart_start >> 12); From 7ece674cd9468ce740494f6108c39831cfc7eb4e Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 31 Jan 2023 13:10:55 -0500 Subject: [PATCH 04/14] Revert "drm/amd/display: disable S/G display on DCN 3.1.4" This reverts commit 9aa15370819294beb7eb67c9dcbf654d79ff8790. This is fixed now so we can re-enable S/G display on DCN 3.1.4. Reviewed-by: Yifan Zhang Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.1.x --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 7f6e27561899..78452856b2a3 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1514,6 +1514,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) init_data.flags.gpu_vm_support = true; break; case IP_VERSION(3, 0, 1): + case IP_VERSION(3, 1, 4): case IP_VERSION(3, 1, 6): init_data.flags.gpu_vm_support = true; break; From 5630a35024d12432827bd7e7986dd60cfe2f983b Mon Sep 17 00:00:00 2001 From: Kenneth Feng Date: Fri, 3 Feb 2023 14:19:37 +0800 Subject: [PATCH 05/14] drm/amd/amdgpu: enable athub cg 11.0.3 enable athub cg on gc 11.0.3 Signed-off-by: Kenneth Feng Reviewed-by: Likun Gao Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/soc21.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 9eff5f41df9d..7050238c4c48 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -641,7 +641,9 @@ static int soc21_common_early_init(void *handle) AMD_CG_SUPPORT_GFX_CGLS | AMD_CG_SUPPORT_REPEATER_FGCG | AMD_CG_SUPPORT_GFX_MGCG | - AMD_CG_SUPPORT_HDP_SD; + AMD_CG_SUPPORT_HDP_SD | + AMD_CG_SUPPORT_ATHUB_MGCG | + AMD_CG_SUPPORT_ATHUB_LS; adev->pg_flags = AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_JPEG; From 49d0555976f0972af68397ed996375c135b38ba7 Mon Sep 17 00:00:00 2001 From: Melissa Wen Date: Tue, 31 Jan 2023 15:05:46 -0100 Subject: [PATCH 06/14] drm/amd/display: fix cursor offset on rotation 180 Cursor gets clipped off in the middle of the screen with hw rotation 180. Fix a miscalculation of cursor offset when it's placed near the edges in the pipe split case. Cursor bugs with hw rotation were reported on AMD issue tracker: https://gitlab.freedesktop.org/drm/amd/-/issues/2247 The issues on rotation 270 was fixed by: https://lore.kernel.org/amd-gfx/20221118125935.4013669-22-Brian.Chang@amd.com/ that partially addressed the rotation 180 too. So, this patch is the final bits for rotation 180. Reported-by: Xaver Hugl Reviewed-by: Harry Wentland Fixes: 9d84c7ef8a87 ("drm/amd/display: Correct cursor position on horizontal mirror") Signed-off-by: Melissa Wen Signed-off-by: Hamza Mahfooz Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index fe2023f18b7d..8f894c1d1d1e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -3626,7 +3626,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) (int)hubp->curs_attr.width || pos_cpy.x <= (int)hubp->curs_attr.width + pipe_ctx->plane_state->src_rect.x) { - pos_cpy.x = temp_x + viewport_width; + pos_cpy.x = 2 * viewport_width - temp_x; } } } else { From 0e763afcb50814e256ecb780fcc0f3bade2e1a0c Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Fri, 3 Feb 2023 15:33:59 +0800 Subject: [PATCH 07/14] drm/amd/pm: add SMU 13.0.7 missing GetPptLimit message mapping Add missing GetPptLimit message mapping. Signed-off-by: Evan Quan Reviewed-by: Feifei Xu Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.1.x --- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index e87db7e02e8a..9e1967d8049e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -124,6 +124,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_7_message_map[SMU_MSG_MAX_COUNT] = MSG_MAP(DFCstateControl, PPSMC_MSG_SetExternalClientDfCstateAllow, 0), MSG_MAP(ArmD3, PPSMC_MSG_ArmD3, 0), MSG_MAP(AllowGpo, PPSMC_MSG_SetGpoAllow, 0), + MSG_MAP(GetPptLimit, PPSMC_MSG_GetPptLimit, 0), }; static struct cmn2asic_mapping smu_v13_0_7_clk_map[SMU_CLK_COUNT] = { From 9874cc2df4e892c8744aa0472866cbf7c3cf1862 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Tue, 31 Jan 2023 10:40:09 +0800 Subject: [PATCH 08/14] drm/amd/pm: bump SMU 13.0.0 driver_if header version This can suppress the warning caused by version mismatch. Signed-off-by: Evan Quan Acked-by: Alex Deucher Acked-by: Guchun Chen Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.1.x --- .../drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h | 5 +++-- drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h index d6b964cf73bd..4bc7aee4d44f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h @@ -123,7 +123,8 @@ (1 << FEATURE_DS_FCLK_BIT) | \ (1 << FEATURE_DS_LCLK_BIT) | \ (1 << FEATURE_DS_DCFCLK_BIT) | \ - (1 << FEATURE_DS_UCLK_BIT)) + (1 << FEATURE_DS_UCLK_BIT) | \ + (1ULL << FEATURE_DS_VCN_BIT)) //For use with feature control messages typedef enum { @@ -522,9 +523,9 @@ typedef enum { TEMP_HOTSPOT_M, TEMP_MEM, TEMP_VR_GFX, - TEMP_VR_SOC, TEMP_VR_MEM0, TEMP_VR_MEM1, + TEMP_VR_SOC, TEMP_VR_U, TEMP_LIQUID0, TEMP_LIQUID1, diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index e8c6febb8b64..d9c4821bcfc8 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -28,7 +28,7 @@ #define SMU13_DRIVER_IF_VERSION_INV 0xFFFFFFFF #define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x04 #define SMU13_DRIVER_IF_VERSION_ALDE 0x08 -#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_0 0x34 +#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_0 0x37 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x07 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_10 0x32 From dc38b996db968f51f0fe45845a519c5cd7f6bd04 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Tue, 7 Feb 2023 10:42:31 +0800 Subject: [PATCH 09/14] drm/amd/pm: bump SMU 13.0.7 driver_if header version This can suppress the warning caused by version mismatch. Signed-off-by: Evan Quan Acked-by: Alex Deucher Acked-by: Guchun Chen Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.1.x --- .../inc/pmfw_if/smu13_driver_if_v13_0_7.h | 29 ++++++++++--------- drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h | 2 +- 2 files changed, 16 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h index d6b13933a98f..48a3a3952ceb 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h @@ -113,20 +113,21 @@ #define NUM_FEATURES 64 #define ALLOWED_FEATURE_CTRL_DEFAULT 0xFFFFFFFFFFFFFFFFULL -#define ALLOWED_FEATURE_CTRL_SCPM (1 << FEATURE_DPM_GFXCLK_BIT) | \ - (1 << FEATURE_DPM_GFX_POWER_OPTIMIZER_BIT) | \ - (1 << FEATURE_DPM_UCLK_BIT) | \ - (1 << FEATURE_DPM_FCLK_BIT) | \ - (1 << FEATURE_DPM_SOCCLK_BIT) | \ - (1 << FEATURE_DPM_MP0CLK_BIT) | \ - (1 << FEATURE_DPM_LINK_BIT) | \ - (1 << FEATURE_DPM_DCN_BIT) | \ - (1 << FEATURE_DS_GFXCLK_BIT) | \ - (1 << FEATURE_DS_SOCCLK_BIT) | \ - (1 << FEATURE_DS_FCLK_BIT) | \ - (1 << FEATURE_DS_LCLK_BIT) | \ - (1 << FEATURE_DS_DCFCLK_BIT) | \ - (1 << FEATURE_DS_UCLK_BIT) +#define ALLOWED_FEATURE_CTRL_SCPM ((1 << FEATURE_DPM_GFXCLK_BIT) | \ + (1 << FEATURE_DPM_GFX_POWER_OPTIMIZER_BIT) | \ + (1 << FEATURE_DPM_UCLK_BIT) | \ + (1 << FEATURE_DPM_FCLK_BIT) | \ + (1 << FEATURE_DPM_SOCCLK_BIT) | \ + (1 << FEATURE_DPM_MP0CLK_BIT) | \ + (1 << FEATURE_DPM_LINK_BIT) | \ + (1 << FEATURE_DPM_DCN_BIT) | \ + (1 << FEATURE_DS_GFXCLK_BIT) | \ + (1 << FEATURE_DS_SOCCLK_BIT) | \ + (1 << FEATURE_DS_FCLK_BIT) | \ + (1 << FEATURE_DS_LCLK_BIT) | \ + (1 << FEATURE_DS_DCFCLK_BIT) | \ + (1 << FEATURE_DS_UCLK_BIT) | \ + (1ULL << FEATURE_DS_VCN_BIT)) //For use with feature control messages typedef enum { diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index d9c4821bcfc8..992163e66f7b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -32,7 +32,7 @@ #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x07 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_10 0x32 -#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x35 +#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x37 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_10 0x1D #define SMU13_MODE1_RESET_WAIT_TIME_IN_MS 500 //500ms From c108a18462949fe709ebd6b0be68398d643bc285 Mon Sep 17 00:00:00 2001 From: Kent Russell Date: Mon, 6 Feb 2023 12:21:42 -0500 Subject: [PATCH 10/14] drm/amdgpu: Add unique_id support for GC 11.0.1/2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These can support unique_id, so create the sysfs file for them Signed-off-by: Kent Russell Reviewed-by: Harish Kasiviswanathan Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.1.x --- drivers/gpu/drm/amd/pm/amdgpu_pm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index a9170360d7e8..2f3e239e623d 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -1991,6 +1991,8 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ case IP_VERSION(9, 4, 2): case IP_VERSION(10, 3, 0): case IP_VERSION(11, 0, 0): + case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 2): *states = ATTR_STATE_SUPPORTED; break; default: From e53448e0a1efa5133c7db78f1df1f4caf177676b Mon Sep 17 00:00:00 2001 From: Friedrich Vock Date: Thu, 2 Feb 2023 17:21:03 +0100 Subject: [PATCH 11/14] drm/amdgpu: Use the TGID for trace_amdgpu_vm_update_ptes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The pid field corresponds to the result of gettid() in userspace. However, userspace cannot reliably attribute PTE events to processes with just the thread id. This patch allows userspace to easily attribute PTE update events to specific processes by comparing this field with the result of getpid(). For attributing events to specific threads, the thread id is also contained in the common fields of each trace event. Reviewed-by: Christian König Signed-off-by: Friedrich Vock Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index b5f3bba851db..01e42bdd8e4e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -974,7 +974,7 @@ int amdgpu_vm_ptes_update(struct amdgpu_vm_update_params *params, trace_amdgpu_vm_update_ptes(params, frag_start, upd_end, min(nptes, 32u), dst, incr, upd_flags, - vm->task_info.pid, + vm->task_info.tgid, vm->immediate.fence_context); amdgpu_vm_pte_update_flags(params, to_amdgpu_bo_vm(pt), cursor.level, pe_start, dst, From 5ad7bbf3dba5c4a684338df1f285080f2588b535 Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Thu, 2 Feb 2023 10:48:56 -0300 Subject: [PATCH 12/14] drm/amdgpu/fence: Fix oops due to non-matching drm_sched init/fini MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently amdgpu calls drm_sched_fini() from the fence driver sw fini routine - such function is expected to be called only after the respective init function - drm_sched_init() - was executed successfully. Happens that we faced a driver probe failure in the Steam Deck recently, and the function drm_sched_fini() was called even without its counter-part had been previously called, causing the following oops: amdgpu: probe of 0000:04:00.0 failed with error -110 BUG: kernel NULL pointer dereference, address: 0000000000000090 PGD 0 P4D 0 Oops: 0002 [#1] PREEMPT SMP NOPTI CPU: 0 PID: 609 Comm: systemd-udevd Not tainted 6.2.0-rc3-gpiccoli #338 Hardware name: Valve Jupiter/Jupiter, BIOS F7A0113 11/04/2022 RIP: 0010:drm_sched_fini+0x84/0xa0 [gpu_sched] [...] Call Trace: amdgpu_fence_driver_sw_fini+0xc8/0xd0 [amdgpu] amdgpu_device_fini_sw+0x2b/0x3b0 [amdgpu] amdgpu_driver_release_kms+0x16/0x30 [amdgpu] devm_drm_dev_init_release+0x49/0x70 [...] To prevent that, check if the drm_sched was properly initialized for a given ring before calling its fini counter-part. Notice ideally we'd use sched.ready for that; such field is set as the latest thing on drm_sched_init(). But amdgpu seems to "override" the meaning of such field - in the above oops for example, it was a GFX ring causing the crash, and the sched.ready field was set to true in the ring init routine, regardless of the state of the DRM scheduler. Hence, we ended-up using sched.ops as per Christian's suggestion [0], and also removed the no_scheduler check [1]. [0] https://lore.kernel.org/amd-gfx/984ee981-2906-0eaf-ccec-9f80975cb136@amd.com/ [1] https://lore.kernel.org/amd-gfx/cd0e2994-f85f-d837-609f-7056d5fb7231@amd.com/ Fixes: 067f44c8b459 ("drm/amdgpu: avoid over-handle of fence driver fini in s3 test (v2)") Suggested-by: Christian König Cc: Guchun Chen Cc: Luben Tuikov Cc: Mario Limonciello Reviewed-by: Luben Tuikov Signed-off-by: Guilherme G. Piccoli Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 00444203220d..faff4a3f96e6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -618,7 +618,13 @@ void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev) if (!ring || !ring->fence_drv.initialized) continue; - if (!ring->no_scheduler) + /* + * Notice we check for sched.ops since there's some + * override on the meaning of sched.ready by amdgpu. + * The natural check would be sched.ready, which is + * set as drm_sched_init() finishes... + */ + if (ring->sched.ops) drm_sched_fini(&ring->sched); for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j) From 6c1a6d0b64e1a15016ba7450cce8629f94de56c7 Mon Sep 17 00:00:00 2001 From: JesseZhang Date: Wed, 8 Feb 2023 10:07:18 +0800 Subject: [PATCH 13/14] amd/amdgpu: remove test ib on hw ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit test ib function is not necessary on hw ring, so remove it. v2: squash in NULL check fix Signed-off-by: JesseZhang Acked-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 2 +- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index f752c7ae7f60..3989e755a5b4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -295,7 +295,7 @@ struct amdgpu_ring { #define amdgpu_ring_parse_cs(r, p, job, ib) ((r)->funcs->parse_cs((p), (job), (ib))) #define amdgpu_ring_patch_cs_in_place(r, p, job, ib) ((r)->funcs->patch_cs_in_place((p), (job), (ib))) #define amdgpu_ring_test_ring(r) (r)->funcs->test_ring((r)) -#define amdgpu_ring_test_ib(r, t) (r)->funcs->test_ib((r), (t)) +#define amdgpu_ring_test_ib(r, t) ((r)->funcs->test_ib ? (r)->funcs->test_ib((r), (t)) : 0) #define amdgpu_ring_get_rptr(r) (r)->funcs->get_rptr((r)) #define amdgpu_ring_get_wptr(r) (r)->funcs->get_wptr((r)) #define amdgpu_ring_set_wptr(r) (r)->funcs->set_wptr((r)) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index f202b45c413c..5dde6f82a1ca 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -6877,7 +6877,6 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_gfx = { .emit_gds_switch = gfx_v9_0_ring_emit_gds_switch, .emit_hdp_flush = gfx_v9_0_ring_emit_hdp_flush, .test_ring = gfx_v9_0_ring_test_ring, - .test_ib = gfx_v9_0_ring_test_ib, .insert_nop = amdgpu_ring_insert_nop, .pad_ib = amdgpu_ring_generic_pad_ib, .emit_switch_buffer = gfx_v9_ring_emit_sb, From c6ac406cd8ff610a2d5da298b1d3071acfcde7f0 Mon Sep 17 00:00:00 2001 From: Jane Jian Date: Fri, 13 Jan 2023 18:53:45 +0800 Subject: [PATCH 14/14] drm/amdgpu/smu: skip pptable init under sriov sriov does not need to init pptable from amdgpu driver we finish it from PF Signed-off-by: Jane Jian Acked-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.1.x --- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index cf96c3f2affe..508e392547d7 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -407,6 +407,9 @@ static int smu_v13_0_0_setup_pptable(struct smu_context *smu) struct amdgpu_device *adev = smu->adev; int ret = 0; + if (amdgpu_sriov_vf(smu->adev)) + return 0; + ret = smu_v13_0_0_get_pptable_from_pmfw(smu, &smu_table->power_play_table, &smu_table->power_play_table_size); @@ -1257,6 +1260,9 @@ static int smu_v13_0_0_get_thermal_temperature_range(struct smu_context *smu, table_context->power_play_table; PPTable_t *pptable = smu->smu_table.driver_pptable; + if (amdgpu_sriov_vf(smu->adev)) + return 0; + if (!range) return -EINVAL;