drm/amd/powerplay: add sensor lock support for smu

when multithreading access sysfs of amdgpu_pm_info at the sametime.
the swsmu driver cause smu firmware hang.

eg:
single thread access:
Message A + Param A ==> right
Message B + Param B ==> right
Message C + Param C ==> right
multithreading access:
Message A + Param B ==> error
Message B + Param A ==> error
Message C + Param C ==> right

the patch will add sensor lock(mutex) to avoid this error.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 5.3.x

diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 33960fb38a5d7324f2637ff435adfa37d48c2bc0..4acf139ea014099beb2616344a462e119203eedb 100644 (file)
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -843,6 +843,8 @@ static int smu_sw_init(void *handle)
        smu->smu_baco.state = SMU_BACO_STATE_EXIT;
        smu->smu_baco.platform_support = false;
 
+       mutex_init(&smu->sensor_lock);
+
        smu->watermarks_bitmap = 0;
        smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
        smu->default_power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;

diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index f1f072012facb18dd156ef964fbe4455c0176de2..d493a3f8c07a63bd570b25905e965f854bf74e90 100644 (file)
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -1018,6 +1018,7 @@ static int arcturus_read_sensor(struct smu_context *smu,
        if (!data || !size)
                return -EINVAL;
 
+       mutex_lock(&smu->sensor_lock);
        switch (sensor) {
        case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
                *(uint32_t *)data = pptable->FanMaximumRpm;
@@ -1044,6 +1045,7 @@ static int arcturus_read_sensor(struct smu_context *smu,
        default:
                ret = smu_smc_read_sensor(smu, sensor, data, size);
        }
+       mutex_unlock(&smu->sensor_lock);
 
        return ret;
 }

diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
index 6109815a0401a7c8835e961a0e43f7335d1d490c..23171a4d9a31cfed921873f504f629580bb3ac38 100644 (file)
--- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
@@ -344,6 +344,7 @@ struct smu_context
        const struct smu_funcs          *funcs;
        const struct pptable_funcs      *ppt_funcs;
        struct mutex                    mutex;
+       struct mutex                    sensor_lock;
        uint64_t pool_size;
 
        struct smu_table_context        smu_table;

diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index 2574f7186e169a71cfebdf79b636f9807630ebab..0b461404af6b489972fd62dca5217c8bc32191cc 100644 (file)
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -1386,6 +1386,7 @@ static int navi10_read_sensor(struct smu_context *smu,
        if(!data || !size)
                return -EINVAL;
 
+       mutex_lock(&smu->sensor_lock);
        switch (sensor) {
        case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
                *(uint32_t *)data = pptable->FanMaximumRpm;
@@ -1409,6 +1410,7 @@ static int navi10_read_sensor(struct smu_context *smu,
        default:
                ret = smu_smc_read_sensor(smu, sensor, data, size);
        }
+       mutex_unlock(&smu->sensor_lock);
 
        return ret;
 }

diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index 64386ee3f878105286077773bcb14def63e4119c..bbd8ebd58434bd2b00316a5d71bbbfd05d456fce 100644 (file)
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3023,6 +3023,7 @@ static int vega20_read_sensor(struct smu_context *smu,
        if(!data || !size)
                return -EINVAL;
 
+       mutex_lock(&smu->sensor_lock);
        switch (sensor) {
        case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
                *(uint32_t *)data = pptable->FanMaximumRpm;
@@ -3048,6 +3049,7 @@ static int vega20_read_sensor(struct smu_context *smu,
        default:
                ret = smu_smc_read_sensor(smu, sensor, data, size);
        }
+       mutex_unlock(&smu->sensor_lock);
 
        return ret;
 }