Re: [PATCH] drm/amd/display: Fix mutex lock in dcn10
Applied. Thanks! On 2022-09-25 17:53, Daniel Gomez wrote: Removal of DC_FP_* wrappers from dml (9696679bf7ac) provokes a mutex lock [2] on the amdgpu driver. Re-arrange the dcn10 code to avoid locking the mutex by placing the DC_FP_* wrappers around the proper functions. This fixes the following WARN/stacktrace: BUG: sleeping function called from invalid context at kernel/locking/mutex.c:283 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 227, name: systemd-udevd preempt_count: 1, expected: 0 CPU: 4 PID: 227 Comm: systemd-udevd Not tainted 6.0.0-rc6-qtec-standard #2 Hardware name: Qtechnology A/S QT5222/QT5221, BIOS v1.0.1 06/07/2021 Call Trace: dump_stack_lvl+0x33/0x42 __might_resched.cold.172+0xa5/0xb3 mutex_lock+0x1a/0x40 amdgpu_dpm_get_clock_by_type_with_voltage+0x38/0x70 [amdgpu] dm_pp_get_clock_levels_by_type_with_voltage+0x64/0xa0 [amdgpu] dcn_bw_update_from_pplib+0x70/0x340 [amdgpu] dcn10_create_resource_pool+0x8c8/0xd20 [amdgpu] ? __kmalloc+0x1c7/0x4a0 dc_create_resource_pool+0xe7/0x190 [amdgpu] dc_create+0x212/0x5d0 [amdgpu] amdgpu_dm_init+0x246/0x370 [amdgpu] ? schedule_hrtimeout_range_clock+0x93/0x120 ? phm_wait_for_register_unequal.part.1+0x4a/0x80 [amdgpu] dm_hw_init+0xe/0x20 [amdgpu] amdgpu_device_init.cold.56+0x1324/0x1653 [amdgpu] ? pci_bus_read_config_word+0x43/0x80 amdgpu_driver_load_kms+0x15/0x120 [amdgpu] amdgpu_pci_probe+0x116/0x320 [amdgpu] pci_device_probe+0x97/0x110 really_probe+0xdd/0x340 __driver_probe_device+0x80/0x170 driver_probe_device+0x1f/0x90 __driver_attach+0xdc/0x180 ? __device_attach_driver+0x100/0x100 ? __device_attach_driver+0x100/0x100 bus_for_each_dev+0x74/0xc0 bus_add_driver+0x19e/0x210 ? kset_find_obj+0x30/0xa0 ? 0xa0a5b000 driver_register+0x6b/0xc0 ? 0xa0a5b000 do_one_initcall+0x4a/0x1f0 ? __vunmap+0x28e/0x2f0 ? __cond_resched+0x15/0x30 ? kmem_cache_alloc_trace+0x3d/0x440 do_init_module+0x4a/0x1e0 load_module+0x1cba/0x1e10 ? __do_sys_finit_module+0xb7/0x120 __do_sys_finit_module+0xb7/0x120 do_syscall_64+0x3c/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7ff2b5f5422d Code: 5d c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d c3 ab 0e 00 f7 d8 64 89 01 48 RSP: 002b:7ffc44ab28e8 EFLAGS: 0246 ORIG_RAX: 0139 RAX: ffda RBX: 555c566a9240 RCX: 7ff2b5f5422d RDX: RSI: 7ff2b60bb353 RDI: 0019 RBP: 7ff2b60bb353 R08: R09: 555c566a9240 R10: 0019 R11: 0246 R12: R13: 0002 R14: R15: Fixes: 9696679bf7ac ("drm/amd/display: remove DC_FP_* wrapper from dml folder") Signed-off-by: Daniel Gomez --- .../amd/display/dc/dcn10/dcn10_hw_sequencer.c | 12 +- .../drm/amd/display/dc/dcn10/dcn10_resource.c | 66 +- .../drm/amd/display/dc/dml/calcs/dcn_calcs.c | 118 -- .../gpu/drm/amd/display/dc/inc/dcn_calcs.h| 19 ++- 4 files changed, 138 insertions(+), 77 deletions(-) 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 5b5d952b2b8c..cb1e06d62841 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 @@ -2994,6 +2994,7 @@ void dcn10_prepare_bandwidth( { struct dce_hwseq *hws = dc->hwseq; struct hubbub *hubbub = dc->res_pool->hubbub; + int min_fclk_khz, min_dcfclk_khz, socclk_khz; if (dc->debug.sanity_checks) hws->funcs.verify_allow_pstate_change_high(dc); @@ -3016,8 +3017,11 @@ void dcn10_prepare_bandwidth( if (dc->debug.pplib_wm_report_mode == WM_REPORT_OVERRIDE) { DC_FP_START(); - dcn_bw_notify_pplib_of_wm_ranges(dc); + dcn_get_soc_clks( + dc, &min_fclk_khz, &min_dcfclk_khz, &socclk_khz); DC_FP_END(); + dcn_bw_notify_pplib_of_wm_ranges( + dc, min_fclk_khz, min_dcfclk_khz, socclk_khz); } if (dc->debug.sanity_checks) @@ -3030,6 +3034,7 @@ void dcn10_optimize_bandwidth( { struct dce_hwseq *hws = dc->hwseq; struct hubbub *hubbub = dc->res_pool->hubbub; + int min_fclk_khz, min_dcfclk_khz, socclk_khz; if (dc->debug.sanity_checks) hws->funcs.verify_allow_pstate_change_high(dc); @@ -3053,8 +3058,11 @@ void dcn10_optimize_bandwidth( if (dc->debug.pplib_wm_report_mode == WM_REPORT_OVERRIDE) { DC_FP_START(); - dcn_bw_notify_pplib_of_wm_ranges(dc); + dcn_get_soc_clks( + dc, &min_fclk_khz, &min_dcfclk_khz, &socclk_khz); DC_FP_END(); + dcn_bw_notify_pplib_of
Re: [PATCH] drm/amd/display: Fix mutex lock in dcn10
Am 25.09.22 um 23:53 schrieb Daniel Gomez: Removal of DC_FP_* wrappers from dml (9696679bf7ac) provokes a mutex lock [2] on the amdgpu driver. Re-arrange the dcn10 code to avoid locking the mutex by placing the DC_FP_* wrappers around the proper functions. Of hand that looks correct to me now, but our DC team needs to take a closer look. Regards, Christian. This fixes the following WARN/stacktrace: BUG: sleeping function called from invalid context at kernel/locking/mutex.c:283 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 227, name: systemd-udevd preempt_count: 1, expected: 0 CPU: 4 PID: 227 Comm: systemd-udevd Not tainted 6.0.0-rc6-qtec-standard #2 Hardware name: Qtechnology A/S QT5222/QT5221, BIOS v1.0.1 06/07/2021 Call Trace: dump_stack_lvl+0x33/0x42 __might_resched.cold.172+0xa5/0xb3 mutex_lock+0x1a/0x40 amdgpu_dpm_get_clock_by_type_with_voltage+0x38/0x70 [amdgpu] dm_pp_get_clock_levels_by_type_with_voltage+0x64/0xa0 [amdgpu] dcn_bw_update_from_pplib+0x70/0x340 [amdgpu] dcn10_create_resource_pool+0x8c8/0xd20 [amdgpu] ? __kmalloc+0x1c7/0x4a0 dc_create_resource_pool+0xe7/0x190 [amdgpu] dc_create+0x212/0x5d0 [amdgpu] amdgpu_dm_init+0x246/0x370 [amdgpu] ? schedule_hrtimeout_range_clock+0x93/0x120 ? phm_wait_for_register_unequal.part.1+0x4a/0x80 [amdgpu] dm_hw_init+0xe/0x20 [amdgpu] amdgpu_device_init.cold.56+0x1324/0x1653 [amdgpu] ? pci_bus_read_config_word+0x43/0x80 amdgpu_driver_load_kms+0x15/0x120 [amdgpu] amdgpu_pci_probe+0x116/0x320 [amdgpu] pci_device_probe+0x97/0x110 really_probe+0xdd/0x340 __driver_probe_device+0x80/0x170 driver_probe_device+0x1f/0x90 __driver_attach+0xdc/0x180 ? __device_attach_driver+0x100/0x100 ? __device_attach_driver+0x100/0x100 bus_for_each_dev+0x74/0xc0 bus_add_driver+0x19e/0x210 ? kset_find_obj+0x30/0xa0 ? 0xa0a5b000 driver_register+0x6b/0xc0 ? 0xa0a5b000 do_one_initcall+0x4a/0x1f0 ? __vunmap+0x28e/0x2f0 ? __cond_resched+0x15/0x30 ? kmem_cache_alloc_trace+0x3d/0x440 do_init_module+0x4a/0x1e0 load_module+0x1cba/0x1e10 ? __do_sys_finit_module+0xb7/0x120 __do_sys_finit_module+0xb7/0x120 do_syscall_64+0x3c/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7ff2b5f5422d Code: 5d c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d c3 ab 0e 00 f7 d8 64 89 01 48 RSP: 002b:7ffc44ab28e8 EFLAGS: 0246 ORIG_RAX: 0139 RAX: ffda RBX: 555c566a9240 RCX: 7ff2b5f5422d RDX: RSI: 7ff2b60bb353 RDI: 0019 RBP: 7ff2b60bb353 R08: R09: 555c566a9240 R10: 0019 R11: 0246 R12: R13: 0002 R14: R15: Fixes: 9696679bf7ac ("drm/amd/display: remove DC_FP_* wrapper from dml folder") Signed-off-by: Daniel Gomez --- .../amd/display/dc/dcn10/dcn10_hw_sequencer.c | 12 +- .../drm/amd/display/dc/dcn10/dcn10_resource.c | 66 +- .../drm/amd/display/dc/dml/calcs/dcn_calcs.c | 118 -- .../gpu/drm/amd/display/dc/inc/dcn_calcs.h| 19 ++- 4 files changed, 138 insertions(+), 77 deletions(-) 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 5b5d952b2b8c..cb1e06d62841 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 @@ -2994,6 +2994,7 @@ void dcn10_prepare_bandwidth( { struct dce_hwseq *hws = dc->hwseq; struct hubbub *hubbub = dc->res_pool->hubbub; + int min_fclk_khz, min_dcfclk_khz, socclk_khz; if (dc->debug.sanity_checks) hws->funcs.verify_allow_pstate_change_high(dc); @@ -3016,8 +3017,11 @@ void dcn10_prepare_bandwidth( if (dc->debug.pplib_wm_report_mode == WM_REPORT_OVERRIDE) { DC_FP_START(); - dcn_bw_notify_pplib_of_wm_ranges(dc); + dcn_get_soc_clks( + dc, &min_fclk_khz, &min_dcfclk_khz, &socclk_khz); DC_FP_END(); + dcn_bw_notify_pplib_of_wm_ranges( + dc, min_fclk_khz, min_dcfclk_khz, socclk_khz); } if (dc->debug.sanity_checks) @@ -3030,6 +3034,7 @@ void dcn10_optimize_bandwidth( { struct dce_hwseq *hws = dc->hwseq; struct hubbub *hubbub = dc->res_pool->hubbub; + int min_fclk_khz, min_dcfclk_khz, socclk_khz; if (dc->debug.sanity_checks) hws->funcs.verify_allow_pstate_change_high(dc); @@ -3053,8 +3058,11 @@ void dcn10_optimize_bandwidth( if (dc->debug.pplib_wm_report_mode == WM_REPORT_OVERRIDE) { DC_FP_START(); - dcn_bw_notify_pplib_of_wm_ranges(dc); + dcn_get_soc_clks( + dc, &min_fclk_khz, &min
[PATCH] drm/amd/display: Fix mutex lock in dcn10
Removal of DC_FP_* wrappers from dml (9696679bf7ac) provokes a mutex lock [2] on the amdgpu driver. Re-arrange the dcn10 code to avoid locking the mutex by placing the DC_FP_* wrappers around the proper functions. This fixes the following WARN/stacktrace: BUG: sleeping function called from invalid context at kernel/locking/mutex.c:283 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 227, name: systemd-udevd preempt_count: 1, expected: 0 CPU: 4 PID: 227 Comm: systemd-udevd Not tainted 6.0.0-rc6-qtec-standard #2 Hardware name: Qtechnology A/S QT5222/QT5221, BIOS v1.0.1 06/07/2021 Call Trace: dump_stack_lvl+0x33/0x42 __might_resched.cold.172+0xa5/0xb3 mutex_lock+0x1a/0x40 amdgpu_dpm_get_clock_by_type_with_voltage+0x38/0x70 [amdgpu] dm_pp_get_clock_levels_by_type_with_voltage+0x64/0xa0 [amdgpu] dcn_bw_update_from_pplib+0x70/0x340 [amdgpu] dcn10_create_resource_pool+0x8c8/0xd20 [amdgpu] ? __kmalloc+0x1c7/0x4a0 dc_create_resource_pool+0xe7/0x190 [amdgpu] dc_create+0x212/0x5d0 [amdgpu] amdgpu_dm_init+0x246/0x370 [amdgpu] ? schedule_hrtimeout_range_clock+0x93/0x120 ? phm_wait_for_register_unequal.part.1+0x4a/0x80 [amdgpu] dm_hw_init+0xe/0x20 [amdgpu] amdgpu_device_init.cold.56+0x1324/0x1653 [amdgpu] ? pci_bus_read_config_word+0x43/0x80 amdgpu_driver_load_kms+0x15/0x120 [amdgpu] amdgpu_pci_probe+0x116/0x320 [amdgpu] pci_device_probe+0x97/0x110 really_probe+0xdd/0x340 __driver_probe_device+0x80/0x170 driver_probe_device+0x1f/0x90 __driver_attach+0xdc/0x180 ? __device_attach_driver+0x100/0x100 ? __device_attach_driver+0x100/0x100 bus_for_each_dev+0x74/0xc0 bus_add_driver+0x19e/0x210 ? kset_find_obj+0x30/0xa0 ? 0xa0a5b000 driver_register+0x6b/0xc0 ? 0xa0a5b000 do_one_initcall+0x4a/0x1f0 ? __vunmap+0x28e/0x2f0 ? __cond_resched+0x15/0x30 ? kmem_cache_alloc_trace+0x3d/0x440 do_init_module+0x4a/0x1e0 load_module+0x1cba/0x1e10 ? __do_sys_finit_module+0xb7/0x120 __do_sys_finit_module+0xb7/0x120 do_syscall_64+0x3c/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7ff2b5f5422d Code: 5d c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d c3 ab 0e 00 f7 d8 64 89 01 48 RSP: 002b:7ffc44ab28e8 EFLAGS: 0246 ORIG_RAX: 0139 RAX: ffda RBX: 555c566a9240 RCX: 7ff2b5f5422d RDX: RSI: 7ff2b60bb353 RDI: 0019 RBP: 7ff2b60bb353 R08: R09: 555c566a9240 R10: 0019 R11: 0246 R12: R13: 0002 R14: R15: Fixes: 9696679bf7ac ("drm/amd/display: remove DC_FP_* wrapper from dml folder") Signed-off-by: Daniel Gomez --- .../amd/display/dc/dcn10/dcn10_hw_sequencer.c | 12 +- .../drm/amd/display/dc/dcn10/dcn10_resource.c | 66 +- .../drm/amd/display/dc/dml/calcs/dcn_calcs.c | 118 -- .../gpu/drm/amd/display/dc/inc/dcn_calcs.h| 19 ++- 4 files changed, 138 insertions(+), 77 deletions(-) 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 5b5d952b2b8c..cb1e06d62841 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 @@ -2994,6 +2994,7 @@ void dcn10_prepare_bandwidth( { struct dce_hwseq *hws = dc->hwseq; struct hubbub *hubbub = dc->res_pool->hubbub; + int min_fclk_khz, min_dcfclk_khz, socclk_khz; if (dc->debug.sanity_checks) hws->funcs.verify_allow_pstate_change_high(dc); @@ -3016,8 +3017,11 @@ void dcn10_prepare_bandwidth( if (dc->debug.pplib_wm_report_mode == WM_REPORT_OVERRIDE) { DC_FP_START(); - dcn_bw_notify_pplib_of_wm_ranges(dc); + dcn_get_soc_clks( + dc, &min_fclk_khz, &min_dcfclk_khz, &socclk_khz); DC_FP_END(); + dcn_bw_notify_pplib_of_wm_ranges( + dc, min_fclk_khz, min_dcfclk_khz, socclk_khz); } if (dc->debug.sanity_checks) @@ -3030,6 +3034,7 @@ void dcn10_optimize_bandwidth( { struct dce_hwseq *hws = dc->hwseq; struct hubbub *hubbub = dc->res_pool->hubbub; + int min_fclk_khz, min_dcfclk_khz, socclk_khz; if (dc->debug.sanity_checks) hws->funcs.verify_allow_pstate_change_high(dc); @@ -3053,8 +3058,11 @@ void dcn10_optimize_bandwidth( if (dc->debug.pplib_wm_report_mode == WM_REPORT_OVERRIDE) { DC_FP_START(); - dcn_bw_notify_pplib_of_wm_ranges(dc); + dcn_get_soc_clks( + dc, &min_fclk_khz, &min_dcfclk_khz, &socclk_khz); DC_FP_END(); + dcn_bw_notify_pplib_of_wm_ranges( + dc, min_fclk_khz, min_dcfclk_khz, socclk_khz); }