Take back patch:drop unnecessary message support check
Because the gpu reset fail problem on renoir can be fixed by:
drm/amd/powerplay: skip invalid msg when smu set mp1 state
It needs to remove SWSMU_CODE_LAYER_L1 in smu_cmn.h to guard a clear
code layer.
Signed-off-by: changfeng <Changfeng.Zhu@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add support for reporting thermal throttling events through SMI.
Also, add a counter to count the number of throttling interrupts
observed and report the count in the SMI event message.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
when GPU hang, driver has multi-paths to enter amdgpu_device_gpu_recover,
the atomic adev->in_gpu_reset and hive->in_reset are used to avoid
re-entering GPU recovery.
During GPU reset and resume, it is unsafe that other threads access GPU,
which maybe cause GPU reset failed. Therefore the new rw_semaphore
adev->reset_sem is introduced, which protect GPU from being accessed by
external threads during recovery.
v2:
1. add rwlock for some ioctls, debugfs and file-close function.
2. change to use dqm->is_resetting and dqm_lock for protection in kfd
driver.
3. remove try_lock and change adev->in_gpu_reset as atomic, to avoid
re-enter GPU recovery for the same GPU hang.
v3:
1. change back to use adev->reset_sem to protect kfd callback
functions, because dqm_lock couldn't protect all codes, for example:
free_mqd must be called outside of dqm_lock;
[ 1230.176199] Hardware name: Supermicro SYS-7049GP-TRT/X11DPG-QT, BIOS 3.1 05/23/2019
[ 1230.177221] Call Trace:
[ 1230.178249] dump_stack+0x98/0xd5
[ 1230.179443] amdgpu_virt_kiq_reg_write_reg_wait+0x181/0x190 [amdgpu]
[ 1230.180673] gmc_v9_0_flush_gpu_tlb+0xcc/0x310 [amdgpu]
[ 1230.181882] amdgpu_gart_unbind+0xa9/0xe0 [amdgpu]
[ 1230.183098] amdgpu_ttm_backend_unbind+0x46/0x180 [amdgpu]
[ 1230.184239] ? ttm_bo_put+0x171/0x5f0 [ttm]
[ 1230.185394] ttm_tt_unbind+0x21/0x40 [ttm]
[ 1230.186558] ttm_tt_destroy.part.12+0x12/0x60 [ttm]
[ 1230.187707] ttm_tt_destroy+0x13/0x20 [ttm]
[ 1230.188832] ttm_bo_cleanup_memtype_use+0x36/0x80 [ttm]
[ 1230.189979] ttm_bo_put+0x1be/0x5f0 [ttm]
[ 1230.191230] amdgpu_bo_unref+0x1e/0x30 [amdgpu]
[ 1230.192522] amdgpu_amdkfd_free_gtt_mem+0xaf/0x140 [amdgpu]
[ 1230.193833] free_mqd+0x25/0x40 [amdgpu]
[ 1230.195143] destroy_queue_cpsch+0x1a7/0x270 [amdgpu]
[ 1230.196475] pqm_destroy_queue+0x105/0x260 [amdgpu]
[ 1230.197819] kfd_ioctl_destroy_queue+0x37/0x70 [amdgpu]
[ 1230.199154] kfd_ioctl+0x277/0x500 [amdgpu]
[ 1230.200458] ? kfd_ioctl_get_clock_counters+0x60/0x60 [amdgpu]
[ 1230.201656] ? tomoyo_file_ioctl+0x19/0x20
[ 1230.202831] ksys_ioctl+0x98/0xb0
[ 1230.204004] __x64_sys_ioctl+0x1a/0x20
[ 1230.205174] do_syscall_64+0x5f/0x250
[ 1230.206339] entry_SYSCALL_64_after_hwframe+0x49/0xbe
2. remove try_lock and introduce atomic hive->in_reset, to avoid
re-enter GPU recovery.
v4:
1. remove an unnecessary whitespace change in kfd_chardev.c
2. remove comment codes in amdgpu_device.c
3. add more detailed comment in commit message
4. define a wrap function amdgpu_in_reset
v5:
1. Fix some style issues.
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Suggested-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com>
Suggested-by: Lijo Lazar <Lijo.Lazar@amd.com>
Suggested-by: Luben Tukov <luben.tuikov@amd.com>
Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The variable result is being initialized with a value that is never read
and it is being updated later with a new value. The initialization is
redundant and can be removed.
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Fix below warnings reported by coccicheck:
./drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c:557:2-7: WARNING: NULL check before some freeing functions is not needed.
Fixes: 4d55b0dd1c ("drm/amd/display: Add DCN3 CLK_MGR")
Signed-off-by: Li Heng <liheng40@huawei.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Some asic may not support for some message of set mp1 state.
If the return value of smu_send_smc_msg is -EINVAL, that means it failed
to send msg to smc as it can not map an valid message for the ASIC. And
with that case, smu_set_mp1_state should be skipped as those ASIC was in
fact do not support for that.
Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
It's not necessary to retrieve the power features status when the
asic is booted up the first time. This patch can have the features
enablement status still checked in suspend/resume case and removed
from the first boot up sequence.
Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Fix this warning:
CC [M] drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.o
In file included from drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h:29,
from drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h:26,
from drivers/gpu/drm/amd/amdgpu/amdgpu.h:43,
from drivers/gpu/drm/amd/amdgpu/df_v3_6.c:23:
drivers/gpu/drm/amd/amdgpu/df_v3_6.c: In function ‘df_v3_6_pmc_get_count’:
./include/drm/drm_print.h:487:2: warning: ‘hi_base_addr’ may be used uninitialized in this function [-Wmaybe-uninitialized]
487 | __drm_dbg(DRM_UT_DRIVER, fmt, ##__VA_ARGS__)
| ^~~~~~~~~
drivers/gpu/drm/amd/amdgpu/df_v3_6.c:649:25: note: ‘hi_base_addr’ was declared here
649 | uint32_t lo_base_addr, hi_base_addr, lo_val = 0, hi_val = 0;
| ^~~~~~~~~~~~
In file included from drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h:29,
from drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h:26,
from drivers/gpu/drm/amd/amdgpu/amdgpu.h:43,
from drivers/gpu/drm/amd/amdgpu/df_v3_6.c:23:
./include/drm/drm_print.h:487:2: warning: ‘lo_base_addr’ may be used uninitialized in this function [-Wmaybe-uninitialized]
487 | __drm_dbg(DRM_UT_DRIVER, fmt, ##__VA_ARGS__)
| ^~~~~~~~~
drivers/gpu/drm/amd/amdgpu/df_v3_6.c:649:11: note: ‘lo_base_addr’ was declared here
649 | uint32_t lo_base_addr, hi_base_addr, lo_val = 0, hi_val = 0;
Signed-off-by: Tom St Denis <tom.stdenis@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This patch is to move get_invalidate_req into gfxhub/mmhub level. It will avoid
mismatch of the different gfxhub/mmhub register offsets and fields in the same
gmc block.
Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This patch is to introduce vmhub funcs helper to add following callback
(print_l2_protection_fault_status). Each GC/MMHUB register specific programming
should be in gfxhub/mmhub level.
v2: remove the condition of funcs assignment.
Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This patch adds a member in vmhub structure to store the vm fault interrupt
masks for different version gfxhubs/mmhubs.
Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The below 3 messages are not supported on Renoir
SMU_MSG_PrepareMp1ForShutdown
SMU_MSG_PrepareMp1ForUnload
SMU_MSG_PrepareMp1ForReset
It needs to revert patch:
drm/amd/powerplay: drop unnecessary message support check
to avoid set mp1 state fail during gpu reset on renoir.
Signed-off-by: changfeng <Changfeng.Zhu@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The driver uses it for EEPROM access, but it's just an i2c bus.
v2: change the callback name as well.
Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
It's not really ras related. It's just a lock for the
bus in general. This removes the ras dependency from
the smu i2c bus.
Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
NULL dereference occurs when string that is not ended with space or
newline is written to some dpm sysfs interface (for example pp_dpm_sclk).
This happens because strsep replaces the tmp with NULL if the delimiter
is not present in string, which is then dereferenced by tmp[0].
Reproduction example:
sudo sh -c 'echo -n 1 > /sys/class/drm/card0/device/pp_dpm_sclk'
Signed-off-by: Paweł Gronowski <me@woland.xyz>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
Implement an interface to obtain plane size caps
[How]
Add min_width, min_height fields to dc_plane_cap structure.
Set values to 16x16 for discrete ASICs, and 64x64 for others.
Signed-off-by: Igor Kravchenko <Igor.Kravchenko@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Qingqing Zhuo <qingqing.zhuo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why&How]
Fix build error by protecting code with config guard
to enable building amdgpu without CONFIG_DRM_AMD_DC_DCN
enabled. This option is disabled by default for allmodconfig.
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Qingqing Zhuo <qingqing.zhuo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why&How]
Accessing dcn20_add_dsc_to_stream_resource directly
causes build failure for configuration which has
CONFIG_DRM_AMD_DC_DCN disabled. Fix this by
calling the corresponding function exposed via dc
resource functions.
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Qingqing Zhuo <qingqing.zhuo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[why]
On DCN20, Some features would not be activated when ALLM was turned on.
TV seemed to activate only the latest info packet sent, and the ALLM
info packet was sent after the VSIF info packet.
The packet indices was also inconsistent between DCN10 and DCN20.
[how]
Change the packet indices of DCN20 to match those of DCN10.
This makes them consistent and also makes the vendor info packet
be sent after the hfvsif info packet.
Signed-off-by: Naveed Ashfaq <Naveed.Ashfaq@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Qingqing Zhuo <qingqing.zhuo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
dcn20_add_dsc_to_stream_resource is accessed in amdgpu_dm directly.
This creates build error for configuration with DCN disabled.
[How]
Make the function available through a resource pool function so
that dcn20 function need not be called directly.
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Qingqing Zhuo <qingqing.zhuo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
