summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/pm/swsmu
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/pm/swsmu')
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c34
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h2
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c10
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c9
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c9
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c1
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c4
7 files changed, 48 insertions, 21 deletions
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 4dea79a0c5b5..ce41a8309582 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -24,6 +24,7 @@
#include <linux/firmware.h>
#include <linux/pci.h>
+#include <linux/reboot.h>
#include "amdgpu.h"
#include "amdgpu_smu.h"
@@ -1078,6 +1079,34 @@ static void smu_interrupt_work_fn(struct work_struct *work)
smu->ppt_funcs->interrupt_work(smu);
}
+static void smu_swctf_delayed_work_handler(struct work_struct *work)
+{
+ struct smu_context *smu =
+ container_of(work, struct smu_context, swctf_delayed_work.work);
+ struct smu_temperature_range *range =
+ &smu->thermal_range;
+ struct amdgpu_device *adev = smu->adev;
+ uint32_t hotspot_tmp, size;
+
+ /*
+ * If the hotspot temperature is confirmed as below SW CTF setting point
+ * after the delay enforced, nothing will be done.
+ * Otherwise, a graceful shutdown will be performed to prevent further damage.
+ */
+ if (range->software_shutdown_temp &&
+ smu->ppt_funcs->read_sensor &&
+ !smu->ppt_funcs->read_sensor(smu,
+ AMDGPU_PP_SENSOR_HOTSPOT_TEMP,
+ &hotspot_tmp,
+ &size) &&
+ hotspot_tmp / 1000 < range->software_shutdown_temp)
+ return;
+
+ dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
+ dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
+ orderly_poweroff(true);
+}
+
static int smu_sw_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1120,6 +1149,9 @@ static int smu_sw_init(void *handle)
smu->smu_dpm.dpm_level = AMD_DPM_FORCED_LEVEL_AUTO;
smu->smu_dpm.requested_dpm_level = AMD_DPM_FORCED_LEVEL_AUTO;
+ INIT_DELAYED_WORK(&smu->swctf_delayed_work,
+ smu_swctf_delayed_work_handler);
+
ret = smu_smc_table_sw_init(smu);
if (ret) {
dev_err(adev->dev, "Failed to sw init smc table!\n");
@@ -1600,6 +1632,8 @@ static int smu_smc_hw_cleanup(struct smu_context *smu)
return ret;
}
+ cancel_delayed_work_sync(&smu->swctf_delayed_work);
+
ret = smu_disable_dpms(smu);
if (ret) {
dev_err(adev->dev, "Fail to disable dpm features!\n");
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 09469c750a96..6e2069dcb6b9 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -573,6 +573,8 @@ struct smu_context
u32 debug_param_reg;
u32 debug_msg_reg;
u32 debug_resp_reg;
+
+ struct delayed_work swctf_delayed_work;
};
struct i2c_adapter;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 275f708db636..c94d825a871b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -1654,7 +1654,7 @@ static int navi10_force_clk_levels(struct smu_context *smu,
enum smu_clk_type clk_type, uint32_t mask)
{
- int ret = 0, size = 0;
+ int ret = 0;
uint32_t soft_min_level = 0, soft_max_level = 0, min_freq = 0, max_freq = 0;
soft_min_level = mask ? (ffs(mask) - 1) : 0;
@@ -1675,15 +1675,15 @@ static int navi10_force_clk_levels(struct smu_context *smu,
ret = smu_v11_0_get_dpm_freq_by_index(smu, clk_type, soft_min_level, &min_freq);
if (ret)
- return size;
+ return 0;
ret = smu_v11_0_get_dpm_freq_by_index(smu, clk_type, soft_max_level, &max_freq);
if (ret)
- return size;
+ return 0;
ret = smu_v11_0_set_soft_freq_limited_range(smu, clk_type, min_freq, max_freq);
if (ret)
- return size;
+ return 0;
break;
case SMU_DCEFCLK:
dev_info(smu->adev->dev,"Setting DCEFCLK min/max dpm level is not supported!\n");
@@ -1693,7 +1693,7 @@ static int navi10_force_clk_levels(struct smu_context *smu,
break;
}
- return size;
+ return 0;
}
static int navi10_populate_umd_state_clk(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index e1ef88ee1ed3..aa4a5498a12f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1412,13 +1412,8 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev,
if (client_id == SOC15_IH_CLIENTID_THM) {
switch (src_id) {
case THM_11_0__SRCID__THM_DIG_THERM_L2H:
- dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
- /*
- * SW CTF just occurred.
- * Try to do a graceful shutdown to prevent further damage.
- */
- dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
- orderly_poweroff(true);
+ schedule_delayed_work(&smu->swctf_delayed_work,
+ msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY));
break;
case THM_11_0__SRCID__THM_DIG_THERM_H2L:
dev_emerg(adev->dev, "ERROR: GPU under temperature range detected\n");
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index e52c563f0dac..3856da6c3f3d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -1353,13 +1353,8 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev,
if (client_id == SOC15_IH_CLIENTID_THM) {
switch (src_id) {
case THM_11_0__SRCID__THM_DIG_THERM_L2H:
- dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
- /*
- * SW CTF just occurred.
- * Try to do a graceful shutdown to prevent further damage.
- */
- dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
- orderly_poweroff(true);
+ schedule_delayed_work(&smu->swctf_delayed_work,
+ msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY));
break;
case THM_11_0__SRCID__THM_DIG_THERM_H2L:
dev_emerg(adev->dev, "ERROR: GPU under temperature range detected\n");
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index a6083957ae51..124287cbbff8 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -1710,6 +1710,7 @@ static int smu_v13_0_0_get_thermal_temperature_range(struct smu_context *smu,
range->mem_emergency_max = (pptable->SkuTable.TemperatureLimit[TEMP_MEM] + CTF_OFFSET_MEM)*
SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
range->software_shutdown_temp = powerplay_table->software_shutdown_temp;
+ range->software_shutdown_temp_offset = pptable->SkuTable.FanAbnormalTempLimitOffset;
return 0;
}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index a92ea4601ea4..6ef12252beb5 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -200,7 +200,6 @@ struct PPTable_t {
};
#define SMUQ10_TO_UINT(x) ((x) >> 10)
-#define SMUQ16_TO_UINT(x) ((x) >> 16)
struct smu_v13_0_6_dpm_map {
enum smu_clk_type clk_type;
@@ -1994,8 +1993,9 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
gpu_metrics->average_socket_power =
SMUQ10_TO_UINT(metrics->SocketPower);
+ /* Energy is reported in 15.625mJ units */
gpu_metrics->energy_accumulator =
- SMUQ16_TO_UINT(metrics->SocketEnergyAcc);
+ SMUQ10_TO_UINT(metrics->SocketEnergyAcc);
gpu_metrics->current_gfxclk =
SMUQ10_TO_UINT(metrics->GfxclkFrequency[xcc0]);
generated by cgit v1.2.3-70-g09d2 (git 2.51.1) at 2025-11-01 18:16:16 +0000