Am 23.09.22 um 16:17 schrieb Daniel Gomez:
Commit [1] removes DC_FP_* wrappers from dml. However, this generates
the BUG [2] on the amdgpu driver. Restore DC_FP_* wrappers in dml/calcs
but only for the functions dcn_bw_update_from_pplib and
dcn_bw_notify_pplib_of_wm_ranges.
That's a really bad idea. The wrappers must be *outside* of the code
file which uses floating point code.
The code should probably just be re-aranged to not try to lock the mutex
inside the critical section.
Regards,
Christian.
[1] 9696679bf7ac40a8fb6a488a75bd66d4414cd3c3 drm/amd/display: remove
DC_FP_* wrapper from dml folder
[2] BUG: sleeping function called from invalid context at
kernel/locking/mutex.c:283
Signed-off-by: Daniel Gomez <daniel@xxxxxxxx>
---
Hi,
The patch [1] introduces BUG [2] since linux 5.18. The reason seems to be
wrapping entirely the functions dcn_bw_update_from_pplib and
dcn_bw_notify_pplib_of_wm_ranges in the dcn10.
On dcn_bw_update_from_pplib function the problem seems to be the
dm_pp_get_clock_levels_by_type_with_voltage call.
Any suggestions on what should we do here?
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:
<TASK>
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
? 0xffffffffa0a5b000
driver_register+0x6b/0xc0
? 0xffffffffa0a5b000
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:00007ffc44ab28e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
RAX: ffffffffffffffda RBX: 0000555c566a9240 RCX: 00007ff2b5f5422d
RDX: 0000000000000000 RSI: 00007ff2b60bb353 RDI: 0000000000000019
RBP: 00007ff2b60bb353 R08: 0000000000000000 R09: 0000555c566a9240
R10: 0000000000000019 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000020000 R14: 0000000000000000 R15: 0000000000000000
</TASK>
drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c | 2 --
drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c | 10 ++++++++++
2 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 174eebbe8b4f..a6ef20b43f3a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -1505,7 +1505,6 @@ static bool dcn10_resource_construct(
&& pool->base.pp_smu->rv_funcs.set_pme_wa_enable != NULL)
dc->debug.az_endpoint_mute_only = false;
- DC_FP_START();
if (!dc->debug.disable_pplib_clock_request)
dcn_bw_update_from_pplib(dc);
dcn_bw_sync_calcs_and_dml(dc);
@@ -1513,7 +1512,6 @@ static bool dcn10_resource_construct(
dc->res_pool = &pool->base;
dcn_bw_notify_pplib_of_wm_ranges(dc);
}
- DC_FP_END();
{
struct irq_service_init_data init_data;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c
index db3b16b77034..a3c71d875adb 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c
@@ -1490,6 +1490,8 @@ void dcn_bw_update_from_pplib(struct dc *dc)
res = dm_pp_get_clock_levels_by_type_with_voltage(
ctx, DM_PP_CLOCK_TYPE_FCLK, &fclks);
+ DC_FP_START();
+
if (res)
res = verify_clock_values(&fclks);
@@ -1519,9 +1521,13 @@ void dcn_bw_update_from_pplib(struct dc *dc)
} else
BREAK_TO_DEBUGGER();
+ DC_FP_END();
+
res = dm_pp_get_clock_levels_by_type_with_voltage(
ctx, DM_PP_CLOCK_TYPE_DCFCLK, &dcfclks);
+ DC_FP_START();
+
if (res)
res = verify_clock_values(&dcfclks);
@@ -1532,6 +1538,8 @@ void dcn_bw_update_from_pplib(struct dc *dc)
dc->dcn_soc->dcfclkv_max0p9 = dcfclks.data[dcfclks.num_levels - 1].clocks_in_khz / 1000.0;
} else
BREAK_TO_DEBUGGER();
+
+ DC_FP_END();
}
void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
@@ -1546,9 +1554,11 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
if (!pp || !pp->set_wm_ranges)
return;
+ DC_FP_START();
min_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 * 1000000 / 32;
min_dcfclk_khz = dc->dcn_soc->dcfclkv_min0p65 * 1000;
socclk_khz = dc->dcn_soc->socclk * 1000;
+ DC_FP_END();
/* Now notify PPLib/SMU about which Watermarks sets they should select
* depending on DPM state they are in. And update BW MGR GFX Engine and
--
2.35.1
