- 25 Aug, 2022 19 commits
-
-
Felix Kuehling authored
Only allocate doorbells when the first queue is created on a GPU or the doorbells need to be mapped into CPU or GPU virtual address space. This avoids allocating doorbells unnecessarily and can allow more processes to use KFD on multi-GPU systems. Signed-off-by:
Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by:
Kent Russell <kent.Russell@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Evan Quan authored
To fit the latest 78.53 PMFW. Signed-off-by:
Evan Quan <evan.quan@amd.com> Reviewed-by:
Feifei Xu <Feifei.Xu@amd.com> Signed-off-by:
-
Roman Li authored
[Why] We have 2 back-to-back checks for skipping connectors. Logically one of them will do the job. [How] Remove redundant check. Reviewed-by:
Hersen Wu <hersenxs.wu@amd.com>> Acked-by:
Brian Chang <Brian.Chang@amd.com> Signed-off-by:
Roman Li <roman.li@amd.com> Tested-by:
Daniel Wheeler <daniel.wheeler@amd.com> Signed-off-by:
-
Leo Chen authored
[Why & How] Adding log for clock table from SMU helps with the debugging process. Implemented using DC_LOG_SMU to output log. Reviewed-by:
Charlene Liu <Charlene.Liu@amd.com> Acked-by:
Leo Chen <sancchen@amd.com> Tested-by:
-
Alvin Lee authored
[Description] Uncomment scaling cmd assignment since FW headers are now promoted. Reviewed-by:
Martin Leung <Martin.Leung@amd.com> Acked-by:
Alvin Lee <Alvin.Lee2@amd.com> Tested-by:
-
Alvin Lee authored
[Why] Sometimes pixel clock needs to remain active after transmitter disable. [How] Use update_phy_state to track PHY state after stream enable/disable and program pixel clock as needed. Reviewed-by:
Taimur Hassan <Syed.Hassan@amd.com> Signed-off-by:
-
Alvin Lee authored
[Description] Refcount is incremented on allocation and when adding to the context. Therefore we must release the phantom plane and stream after removing from the context. Reviewed-by:
Aric Cyr <Aric.Cyr@amd.com> Acked-by:
-
Aurabindo Pillai authored
[Why&How] When using IGT, kms_bw multi display tests trigger an assert since we ignore virtual signal type. k1/k2 dividers should be correctly programmed if VSYNC needs to be correct. Add the appropriate condition to the if arm to fix this. Reviewed-by:
Rodrigo Siqueira <Rodrigo.Siqueira@amd.com> Acked-by:
Aurabindo Pillai <aurabindo.pillai@amd.com> Tested-by:
-
Robin Chen authored
[Why] The DAL driver may transmit the wrong cursor position to PSRSU DMUB driver when there are multiple planes. [How] Currently the driver apply the HW cursor on the top plane. So we should only transmit the cursor position on the top plane to PSRSU DMUB driver. Reviewed-by:
Anthony Koo <Anthony.Koo@amd.com> Acked-by:
Robin Chen <po-tchen@amd.com> Tested-by:
-
Aurabindo Pillai authored
DC was using compile time initialization of register addresses using SR_* macros and their variants. These have been converted to use runtime initialization. The REG_STRUCT macro is a definition that is added to SR_* macros. During initialization, this must be defined before SR_* macros are invoked, which are in turn invoked through various IP initialization macros. Reviewed-by:
Harry Wentland <Harry.Wentland@amd.com> Acked-by:
-
Aurabindo Pillai authored
DC was using compile time initialization of register addresses using SR_* macros and their variants. These have been converted to use runtime initialization. The REG_STRUCT macro is a definition that is added to SR_* macros. During initialization, this must be defined before SR_* macros are invoked, which are in turn invoked through various IP initialization macros. Reviewed-by:
-
Ilya Bakoulin authored
[Why] Retrying on receiving a NACK can result in long overall EDID read times in some cases. [How] Retry only on DEFER and return immediately on NACK. Reviewed-by:
Ilya Bakoulin <Ilya.Bakoulin@amd.com> Tested-by:
-
Saaem Rizvi authored
[WHY] Reprogramming the stream despite no changes in ODM combine mode. Reprogramming the stream would cause intermittent black screen on display which could only be recovered through enable/disable sequence. [HOW] Fixed bug where we detected a change in ODM combine mode despite ODM combine mode being disabled. Also removed code which required stream to be reprogrammed once a change in ODM combine mode was noticed. Lastly we do not support dynamic ODM switching for HDMI TMDS and FRL on DCN32, therefore we never want to change its ODM policy. Reviewed-by:
Samson Tam <Samson.Tam@amd.com> Acked-by:
Saaem Rizvi <SyedSaaem.Rizvi@amd.com> Tested-by:
-
Samson Tam authored
[Why] odm 2:1 policy is splitting the pipes in 4k144. then in subvp code, we merge the pipes. but since the configuration is unsupported, we keep the pipes split [How] for unsupported subvp configuration, redo the dml and pipe split calls Reviewed-by:
Jun Lei <Jun.Lei@amd.com> Acked-by:
-
Derek Lai authored
[Why] RV2 do not change pipe split policy in the minimal pipe split transition state. This will unblock mode support on some parts that limit to DPM0 for power reason. [How] Do not change pipe split policy in the minimal pipe split transition state to allow 4k multi display configs to be supported at DPM0. Reviewed-by:
Derek Lai <Derek.Lai@amd.com> Tested-by:
-
Aric Cyr authored
This verion brings along following fixes: -Add scaling factor for SubVP -Modify stop_dbg_mode return value -Add gfx_off members and document -Add GFXOFF function for vangogh -Add GFXOFF stats to debug -Fix codestyle problems -Fix overflow on MIN_I64 -Fix Unneeded semicolon -Fix comment typo -Remove useless condition in amdgpu_job_stop_all_jobs_on_sched() -Add decoder_iv_ts helper for ih_v6 -Add chip version to DCN32 -Avoid doing vm_init multiple time -Modify size calculation in MALL -Fix DSC for phantom pipes -Update clock table policy for DCN314 -Modify header inclusion pattern -Fix plug/unplug external monitor will playback MPO video -Add debug parameter to retain default clock table -Increase tlb flush timeout for sriov -Fix compare intergers of different widths -Add reserved dc_log_type -Fix pixel clock programming Acked-by:
-
Anthony Koo authored
- For SubVP add scaling factor to allow firmware to calculate accurate line to start programming Reviewed-by:
-
Vignesh Chander authored
Skip set_topology_info as xgmi TA will now block it and host needs to program it. Signed-off-by:
Vignesh Chander <Vignesh.Chander@amd.com> Reviewed-By : Shaoyun Liu <Shaoyun.Liu@amd.com> Signed-off-by:
-
Tim Huang authored
For some ASICs, like GFX IP v11.0.1, only have one SDMA instance, so not need to configure SDMA1_RLC_CGCG_CTRL for this case. Signed-off-by:
Tim Huang <tim.huang@amd.com> Reviewed-by:
Yifan Zhang <yifan1.zhang@amd.com> Signed-off-by:
-
- 22 Aug, 2022 15 commits
-
-
Tales Aparecida authored
Removes DEFINEs that should have been removed after they were introduced to ObjectID.h by the commit abea57d7 ("drm/amdgpu: Add BRACKET_LAYOUT_ENUMs to ObjectID.h") Signed-off-by:
Tales Aparecida <tales.aparecida@gmail.com> Signed-off-by:
-
Roman Li authored
[Why] DCN314 supports PCON. [How] Explicitly enable it in dcn314 resources. Signed-off-by:
Hamza Mahfooz <hamza.mahfooz@amd.com> Signed-off-by:
-
Tim Huang authored
Enable AMD_CG_SUPPORT_BIF_MGCG and AMD_CG_SUPPORT_BIF_LS support. Signed-off-by:
-
Tim Huang authored
Add BIF Clock Gating MGCG and LS support for NBIO IP v7.7.0. Signed-off-by:
-
Tim Huang authored
Add the BIF0_PCIE_TX_POWER_CTRL_1 register offset and mask macro definitions for AMD_CG_SUPPORT_BIF_LS. Signed-off-by:
-
Zhenneng Li authored
Although radeon card fence and wait for gpu to finish processing current batch rings, there is still a corner case that radeon lockup work queue may not be fully flushed, and meanwhile the radeon_suspend_kms() function has called pci_set_power_state() to put device in D3hot state. Per PCI spec rev 4.0 on 5.3.1.4.1 D3hot State. > Configuration and Message requests are the only TLPs accepted by a Function in > the D3hot state. All other received Requests must be handled as Unsupported Requests, > and all received Completions may optionally be handled as Unexpected Completions. This issue will happen in following logs: Unable to handle kernel paging request at virtual address 00008800e0008010 CPU 0 kworker/0:3(131): Oops 0 pc = [<ffffffff811bea5c>] ra = [<ffffffff81240844>] ps = 0000 Tainted: G W pc is at si_gpu_check_soft_reset+0x3c/0x240 ra is at si_dma_is_lockup+0x34/0xd0 v0 = 0000000000000000 t0 = fff08800e0008010 t1 = 0000000000010000 t2 = 0000000000008010 t3 = fff00007e3c00000 t4 = fff00007e3c00258 t5 = 000000000000ffff t6 = 0000000000000001 t7 = fff00007ef078000 s0 = fff00007e3c016e8 s1 = fff00007e3c00000 s2 = fff00007e3c00018 s3 = fff00007e3c00000 s4 = fff00007fff59d80 s5 = 0000000000000000 s6 = fff00007ef07bd98 a0 = fff00007e3c00000 a1 = fff00007e3c016e8 a2 = 0000000000000008 a3 = 0000000000000001 a4 = 8f5c28f5c28f5c29 a5 = ffffffff810f4338 t8 = 0000000000000275 t9 = ffffffff809b66f8 t10 = ff6769c5d964b800 t11= 000000000000b886 pv = ffffffff811bea20 at = 0000000000000000 gp = ffffffff81d89690 sp = 00000000aa814126 Disabling lock debugging due to kernel taint Trace: [<ffffffff81240844>] si_dma_is_lockup+0x34/0xd0 [<ffffffff81119610>] radeon_fence_check_lockup+0xd0/0x290 [<ffffffff80977010>] process_one_work+0x280/0x550 [<ffffffff80977350>] worker_thread+0x70/0x7c0 [<ffffffff80977410>] worker_thread+0x130/0x7c0 [<ffffffff80982040>] kthread+0x200/0x210 [<ffffffff809772e0>] worker_thread+0x0/0x7c0 [<ffffffff80981f8c>] kthread+0x14c/0x210 [<ffffffff80911658>] ret_from_kernel_thread+0x18/0x20 [<ffffffff80981e40>] kthread+0x0/0x210 Code: ad3e0008 43f0074a ad7e0018 ad9e0020 8c3001e8 40230101 <88210000> 4821ed21 So force lockup work queue flush to fix this problem. Acked-by:
Christian König <christian.koenig@amd.com> Signed-off-by:
Zhenneng Li <lizhenneng@kylinos.cn> Signed-off-by:
-
Magali Lemes authored
dml_wrapper* files were removed in commit 01b537ee ("drm/amd/display: Remove unused code"), as they are not used anywhere. However, the header file wasn't removed, so remove the header as well. Signed-off-by:
Magali Lemes <magalilemes00@gmail.com> Signed-off-by:
-
Maíra Canal authored
The file amdgpu_dm_plane.c missed the header amdgpu_dm_plane.h, which resulted on the following warning: drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_plane.c:1046:5: warning: no previous prototype for 'fill_dc_scaling_info' [-Wmissing-prototypes] drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_plane.c:1222:6: warning: no previous prototype for 'handle_cursor_update' [-Wmissing-prototypes] drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_plane.c:152:6: warning: no previous prototype for 'modifier_has_dcc' [-Wmissing-prototypes] drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_plane.c:1576:5: warning: no previous prototype for 'amdgpu_dm_plane_init' [-Wmissing-prototypes] drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_plane.c:157:10: warning: no previous prototype for 'modifier_gfx9_swizzle_mode' [-Wmissing-prototypes] drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_plane.c:752:5: warning: no previous prototype for 'fill_plane_buffer_attributes' [-Wmissing-prototypes] drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_plane.c:83:31: warning: no previous prototype for 'amd_get_format_info' [-Wmissing-prototypes] drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_plane.c:88:6: warning: no previous prototype for 'fill_blending_from_plane_state' [-Wmissing-prototypes] drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_plane.c:992:5: warning: no previous prototype for 'dm_plane_helper_check_state' [-Wmissing-prototypes] Therefore, include the missing header on the file and turn global functions that are not used outside of the file into static functions. Fixes: 5d945cbc ("drm/amd/display: Create a file dedicated to planes") Reported-by:
kernel test robot <lkp@intel.com> Signed-off-by:
Maíra Canal <mairacanal@riseup.net> Signed-off-by:
-
Yang Li authored
Semicolon is not required after curly braces. Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=1918Reported-by:
Abaci Robot <abaci@linux.alibaba.com> Signed-off-by:
Yang Li <yang.lee@linux.alibaba.com> Signed-off-by:
-
Hamza Mahfooz authored
Addresses the following warning: drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn30/display_mode_vba_30.c:3596:6: error: stack frame size (2092) exceeds limit (2048) in 'dml30_ModeSupportAndSystemConfigurationFull' [-Werror,-Wframe-larger-than] void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib) ^ UseMinimumDCFCLK() is eating away at dml30_ModeSupportAndSystemConfigurationFull()'s stack space, so use a pointer to struct vba_vars_st instead of passing lots of large arrays as parameters by value. Signed-off-by: -
shaoyunl authored
The additional call is caused by merge conflict Reviewed-by:
shaoyunl <shaoyun.liu@amd.com> Signed-off-by:
-
Candice Li authored
No need to set up rb when no gfx rings. Signed-off-by:
Candice Li <candice.li@amd.com> Reviewed-by:
Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by:
-
YiPeng Chai authored
Only amdgpu_get_xgmi_hive but no amdgpu_put_xgmi_hive which will leak the hive reference. Signed-off-by:
YiPeng Chai <YiPeng.Chai@amd.com> Reviewed-by:
-
YiPeng Chai authored
V1: The amdgpu_xgmi_remove_device function will send unload command to psp through psp ring to terminate xgmi, but psp ring has been destroyed in psp_hw_fini. V2: 1. Change the commit title. 2. Restore amdgpu_xgmi_remove_device to its original calling location. Move psp_xgmi_terminate call from amdgpu_xgmi_remove_device to psp_hw_fini. Signed-off-by:
-
Tim Huang authored
Enable GFXOFF allow control when set the GFX power gating. Signed-off-by:
-
- 16 Aug, 2022 6 commits
-
-
André Almeida authored
Add comments to document gfx_off related members of struct amdgpu_gfx. Signed-off-by:
André Almeida <andrealmeid@igalia.com> Signed-off-by:
-
André Almeida authored
Add documentation explaining those two new files. While here, add a note about the value type. Signed-off-by:
-
André Almeida authored
Implement functions to get and set GFXOFF's entry count and residency for vangogh. Signed-off-by:
-
André Almeida authored
Add debugfs interface to log GFXOFF statistics: - Read amdgpu_gfxoff_count to get the total GFXOFF entry count at the time of query since system power-up - Write 1 to amdgpu_gfxoff_residency to start logging, and 0 to stop. Read it to get average GFXOFF residency % multiplied by 100 during the last logging interval. Both features are designed to be keep the values persistent between suspends. Signed-off-by:
-
Tales Aparecida authored
Fixes five checkpatch warnings: CHECK: Please don't use multiple blank lines + + ERROR: Macros with complex values should be enclosed in parentheses +#define MAX_I64 \ + (int64_t)((1ULL << 63) - 1) WARNING: Missing a blank line after declarations + struct bw_fixed res; + ASSERT(value < BW_FIXED_MAX_I32 && value > BW_FIXED_MIN_I32); ERROR: that open brace { should be on the previous line + do + { ERROR: that open brace { should be on the previous line + if (remainder >= arg2_value) + { Signed-off-by: -
David Gow authored
The definition of MIN_I64 in bw_fixed.c can cause gcc to whinge about integer overflow, because it is treated as a positive value, which is then negated. The temporary positive value is not necessarily representable. This causes the following warning: ../drivers/gpu/drm/amd/amdgpu/../display/dc/dml/calcs/bw_fixed.c:30:19: warning: integer overflow in expression ‘-9223372036854775808’ of type ‘long long int’ results in ‘-9223372036854775808’ [-Woverflow] 30 | (int64_t)(-(1LL << 63)) | ^ Writing out (-MAX_I64 - 1) works instead. Signed-off-by:David Gow <davidgow@google.com> Signed-off-by:
-
