Why:
If the reg mmMP1_SMN_C2PMSG_90 is being written to during amdgpu driver
load or driver unload, subsequent amdgpu driver load will fail at
smu_hw_init. The default of mmMP1_SMN_C2PMSG_90 register at a clean
environment is 0x1 and if value differs from expected, amdgpu driver
load will fail.
How to fix:
Ignore the initial value in smu response register before the first smu
message is sent, proceed further to send the message. If register holds
0x0 or an unexpected value after smu message was sent set fw_state_hang
flag and no further smu messages will be sent.
Signed-off-by: Danijel Slivka <danijel.sli...@amd.com>
---
drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h | 1 +
drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c | 7 +++++--
2 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index a34c802f52be..bfe08fa0db6d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -562,6 +562,7 @@ struct smu_context {
uint32_t smc_fw_if_version;
uint32_t smc_fw_version;
uint32_t smc_fw_caps;
+ bool smc_fw_state_hang;
bool uploading_custom_pp_table;
bool dc_controlled_by_gpio;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index 5592fd825aa3..9e4e62dcbee7 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -421,7 +421,7 @@ int smu_cmn_send_smc_msg_with_param(struct smu_context *smu,
if (poll) {
reg = __smu_cmn_poll_stat(smu);
res = __smu_cmn_reg2errno(smu, reg);
- if (reg == SMU_RESP_NONE || res == -EREMOTEIO) {
+ if ((reg == SMU_RESP_NONE || res == -EREMOTEIO) &&
smu->smc_fw_state_hang) {
__smu_cmn_reg_print_error(smu, reg, index, param, msg);
goto Out;
}
@@ -429,8 +429,11 @@ int smu_cmn_send_smc_msg_with_param(struct smu_context
*smu,
__smu_cmn_send_msg(smu, (uint16_t) index, param);
reg = __smu_cmn_poll_stat(smu);
res = __smu_cmn_reg2errno(smu, reg);
- if (res != 0)
+ if (res != 0) {
+ if (reg == SMU_RESP_NONE || res == -EREMOTEIO)
+ smu->smc_fw_state_hang = true;
__smu_cmn_reg_print_error(smu, reg, index, param, msg);
+ }
if (read_arg) {
smu_cmn_read_arg(smu, read_arg);
dev_dbg(adev->dev, "smu send message: %s(%d) param: 0x%08x,
resp: 0x%08x,\
--
2.34.1
