AI/rocm-systems
2
0
Forc 0
Cód Saincheisteanna Iarratais Tarraingthe Gníomhartha Pacáistí Tionscadail Scaoileann Vicí Gníomhaíocht

[SWDEV-381630] Add reset partition functionality

Brabhsáil Foinse 
Updates:
    * Added rsmi_dev_compute_partition_reset & rsmi_dev_nps_mode_reset
    * Added --resetcomputepartition and --resetnpsmode python smi calls
    * Added temp data files rocmsmi_boot_compute_partition_<device num>
      & rocmsmi_boot_nps_mode_partition_<device num>, writes UNKNOWN
      if data cannot be read or device does not support
    * Cleaned up NPS & compute API documentation
    * Added creation and reading of API temp files (used in reset
      functionality)
    * Cleaned up output of rocm_smi_example
    * Updated rocm_smi_example to check if running with sudo permission
      before executing write API calls (cleans up erroneous output)
    * Added template specialization for storing temp data, requires
      specific rsmi_type_t enums (restrics what data can be stored)
    * Added storage of temp data, if temp files do not exist
    * Updated google tests for NPS & compute to include reset API calls

Change-Id: I69895a466b97107617e6dbb355737b84499a76c9
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Tá an tiomantas seo le fáil i:
Charis Poag
2023-02-14 17:06:03 -06:00
tuismitheoir 9ef376cd61
tiomantas 77c950a4bf
D'athraigh 12 comhad le 577 breiseanna agus 46 scriosta
Íoslódáil an comhad paiste Íoslódáil Comhad Diff Leathnaigh gach comhaid Laghdaigh gach comhaid
include/rocm_smi/rocm_smi.h
+41 -4
Féach ar an gComhad
@@ -3540,12 +3540,13 @@ rsmi_is_P2P_accessible(uint32_t dv_ind_src, uint32_t dv_ind_dst,
* which the device's current compute partition will be written to.
*
* @param[in] len the length of the caller provided buffer @p compute_partition
* , suggested length is 4 or greater.
*
* @retval ::RSMI_STATUS_SUCCESS call was successful
* @retval ::RSMI_STATUS_INVALID_ARGS the provided arguments are not valid
* @retval ::RSMI_STATUS_UNEXPECTED_DATA data provided to function is not valid
* @retval ::RSMI_STATUS_NOT_SUPPORTED installed software or hardware does not
* support this function with the given arguments
* support this function
* @retval ::RSMI_STATUS_INSUFFICIENT_SIZE is returned if @p len bytes is not
* large enough to hold the entire compute partition value. In this case,
* only @p len bytes will be written.
@@ -3572,13 +3573,30 @@ rsmi_dev_compute_partition_get(uint32_t dv_ind, char *compute_partition,
* @retval ::RSMI_STATUS_PERMISSION function requires root access
* @retval ::RSMI_STATUS_INVALID_ARGS the provided arguments are not valid
* @retval ::RSMI_STATUS_NOT_SUPPORTED installed software or hardware does not
* support this function with the given arguments
* support this function
*
*/
rsmi_status_t
rsmi_dev_compute_partition_set(uint32_t dv_ind,
rsmi_compute_partition_type_t compute_partition);
/**
* @brief Reverts a selected device's compute partition setting back to its
* boot state.
*
* @details Given a device index @p dv_ind , this function will attempt to
* revert its compute partition setting back to its boot state.
*
* @param[in] dv_ind a device index
*
* @retval ::RSMI_STATUS_SUCCESS call was successful
* @retval ::RSMI_STATUS_PERMISSION function requires root access
* @retval ::RSMI_STATUS_NOT_SUPPORTED installed software or hardware does not
* support this function
*
*/
rsmi_status_t rsmi_dev_compute_partition_reset(uint32_t dv_ind);
/** @} */ // end of ComputePartition
/*****************************************************************************/
@@ -3609,7 +3627,7 @@ rsmi_dev_compute_partition_set(uint32_t dv_ind,
* @retval ::RSMI_STATUS_INVALID_ARGS the provided arguments are not valid
* @retval ::RSMI_STATUS_UNEXPECTED_DATA data provided to function is not valid
* @retval ::RSMI_STATUS_NOT_SUPPORTED installed software or hardware does not
* support this function with the given arguments
* support this function
* @retval ::RSMI_STATUS_INSUFFICIENT_SIZE is returned if @p len bytes is not
* large enough to hold the entire nps mode value. In this case,
* only @p len bytes will be written.
@@ -3634,7 +3652,7 @@ rsmi_dev_nps_mode_get(uint32_t dv_ind, char *nps_mode, uint32_t len);
* @retval ::RSMI_STATUS_PERMISSION function requires root access
* @retval ::RSMI_STATUS_INVALID_ARGS the provided arguments are not valid
* @retval ::RSMI_STATUS_NOT_SUPPORTED installed software or hardware does not
* support this function with the given arguments
* support this function
* @retval ::RSMI_STATUS_AMDGPU_RESTART_ERR could not successfully restart
* the amdgpu driver
*
@@ -3642,6 +3660,25 @@ rsmi_dev_nps_mode_get(uint32_t dv_ind, char *nps_mode, uint32_t len);
rsmi_status_t
rsmi_dev_nps_mode_set(uint32_t dv_ind, rsmi_nps_mode_type_t nps_mode);
/**
* @brief Reverts a selected device's NPS mode setting back to its
* boot state.
*
* @details Given a device index @p dv_ind , this function will attempt to
* revert its NPS mode setting back to its boot state.
*
* @param[in] dv_ind a device index
*
* @retval ::RSMI_STATUS_SUCCESS call was successful
* @retval ::RSMI_STATUS_PERMISSION function requires root access
* @retval ::RSMI_STATUS_NOT_SUPPORTED installed software or hardware does not
* support this function
* @retval ::RSMI_STATUS_AMDGPU_RESTART_ERR could not successfully restart
* the amdgpu driver
*
*/
rsmi_status_t rsmi_dev_nps_mode_reset(uint32_t dv_ind);
/** @} */ // end of NPSMode
/*****************************************************************************/
include/rocm_smi/rocm_smi_device.h
+2
Féach ar an gComhad
@@ -217,6 +217,8 @@ class Device {
bool DeviceAPISupported(std::string name, uint64_t variant,
uint64_t sub_variant);
rsmi_status_t restartAMDGpuDriver(void);
rsmi_status_t storeDevicePartitions(uint32_t dv_ind);
template <typename T> std::string readBootPartitionState(uint32_t dv_ind);
private:
std::shared_ptr<Monitor> monitor_;
include/rocm_smi/rocm_smi_utils.h
+11 -6
Féach ar an gComhad
@@ -66,18 +66,23 @@ namespace amd {
namespace smi {
pthread_mutex_t *GetMutex(uint32_t dv_ind);
int SameFile(const std::string fileA, const std::string fileB);
bool FileExists(char const *filename);
int isRegularFile(std::string fname, bool *is_reg);
int ReadSysfsStr(std::string path, std::string *retStr);
int WriteSysfsStr(std::string path, std::string val);
bool IsInteger(const std::string & n_str);
std::pair<bool, std::string> executeCommand(std::string command, bool stdOut = true);
std::pair<bool, std::string> executeCommand(std::string command,
bool stdOut = true);
rsmi_status_t storeTmpFile(uint32_t dv_ind, std::string parameterName,
std::string stateName, std::string storageData);
std::vector<std::string> getListOfAppTmpFiles();
bool containsString(std::string originalString, std::string substring);
std::tuple<bool, std::string> readTmpFile(
uint32_t dv_ind,
std::string stateName,
std::string parameterName);
void displayAppTmpFilesContent(void);
rsmi_status_t handleException();
rsmi_status_t
GetDevValueVec(amd::smi::DevInfoTypes type,