[SWDEV-488276/SWDEV-497613] Update memory partition set functionality

Changes:
  - [CLI] Added warning screen to AMD SMI users
    setting memory partition
  - [CLI] Added a progress bar time-bar for CLI sets display to 40 seconds
  - [API] Updated to wait until the driver reloads with SYSFS files active
  - [CLI] Now users can set or reset without providing:
    amd-smi set -g all <set arguments>
    or amd-smi reset -g all <set arguments>
    now can directly call -> sudo amd-smi set <set arguments>
    or sudo amd-smi reset <set arguments>
  - [SWDEV-475712][CLI/API] Fixed target_graphics_version field
    not properly displaying for older MI or Navi ASICs.
  - [All APIs] Added a catch for the driver to report invalid arguments
    now these APIs will show AMDSMI_STATUS_INVAL
    (ex. changing to NPS8 if the device does not support it)
  - [Install] Modified paths for Python install commands to support
    multi-ROCm installs

Change-Id: Id11f25d68a82d23c6b2d77ccb30b51e860dd0ca7
Signed-off-by: Charis Poag <Charis.Poag@amd.com>

rocm_smi/include/rocm_smi/rocm_smi.h

@@ -4596,25 +4596,6 @@ 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
- *  @retval ::RSMI_STATUS_BUSY A resource or mutex could not be acquired
- *  because it is already being used - device is busy
- *
- */
-rsmi_status_t rsmi_dev_compute_partition_reset(uint32_t dv_ind);
-
 /**
  *  @brief Retrieves the partition_id for a desired device
  *
@@ -4680,6 +4661,39 @@ rsmi_status_t
 rsmi_dev_memory_partition_get(uint32_t dv_ind, char *memory_partition,
                               uint32_t len);
 
+/**
+ *  @brief Retrieves the available memory partition capabilities
+ *  for a desired device
+ *
+ *  @details
+ *  Given a device index @p dv_ind and a string @p memory_partition_caps ,
+ *  and uint32 @p len , this function will attempt to obtain the device's
+ *  available memory partition capabilities string. Upon successful
+ *  retreival, the obtained device's available memory partition capablilities
+ *  string shall be stored in the passed @p memory_partition_caps
+ *  char string variable.
+ *
+ *  @param[in] dv_ind a device index
+ *
+ *  @param[inout] memory_partition_caps a pointer to a char string variable,
+ *  which the device's available memory partition capabilities will be written to.
+ *
+ *  @param[in] len the length of the caller provided buffer @p len ,
+ *  suggested length is 30 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
+ *  @retval ::RSMI_STATUS_INSUFFICIENT_SIZE is returned if @p len bytes is not
+ *  large enough to hold the entire memory partition value. In this case,
+ *  only @p len bytes will be written.
+ *
+ */
+rsmi_status_t rsmi_dev_memory_partition_capabilities_get(
+                uint32_t dv_ind, char *memory_partition_caps, uint32_t len);
+
 /**
  *  @brief Modifies a selected device's current memory partition setting.
  *
@@ -4707,27 +4721,6 @@ rsmi_status_t
 rsmi_dev_memory_partition_set(uint32_t dv_ind,
                               rsmi_memory_partition_type_t memory_partition);
 
-/**
- *  @brief Reverts a selected device's memory partition setting back to its
- *  boot state.
- *
- *  @details Given a device index @p dv_ind , this function will attempt to
- *  revert its current memory 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
- *  @retval ::RSMI_STATUS_AMDGPU_RESTART_ERR could not successfully restart
- *  the amdgpu driver
- *  @retval ::RSMI_STATUS_BUSY A resource or mutex could not be acquired
- *  because it is already being used - device is busy
- *
- */
-rsmi_status_t rsmi_dev_memory_partition_reset(uint32_t dv_ind);
-
 /** @} */  // end of memory_partition
 
 /*****************************************************************************/

rocm_smi/include/rocm_smi/rocm_smi_device.h

@@ -182,6 +182,7 @@ enum DevInfoTypes {
   kDevAvailableComputePartition,
   kDevComputePartition,
   kDevMemoryPartition,
+  kDevAvailableMemoryPartition,
 
   // The information read from pci core sysfs
   kDevPCieTypeStart = 1000,
@@ -245,6 +246,8 @@ class Device {
     bool DeviceAPISupported(std::string name, uint64_t variant,
                                                         uint64_t sub_variant);
     rsmi_status_t restartAMDGpuDriver(void);
+    rsmi_status_t isRestartInProgress(bool *isRestartInProgress,
+                                      bool *isAMDGPUModuleLive);
     rsmi_status_t storeDevicePartitions(uint32_t dv_ind);
     template <typename T> std::string readBootPartitionState(uint32_t dv_ind);
     rsmi_status_t check_amdgpu_property_reinforcement_query(uint32_t dev_idx, AMDGpuVerbTypes_t verb_type);

rocm_smi/include/rocm_smi/rocm_smi_utils.h

@@ -92,7 +92,8 @@ std::pair<bool, std::string> executeCommand(std::string command,
 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);
+bool containsString(std::string originalString, std::string substring,
+                    bool displayComparisons = false);
 std::tuple<bool, std::string> readTmpFile(
                                           uint32_t dv_ind,
                                           std::string stateName,
@@ -141,6 +142,8 @@ std::string removeNewLines(const std::string &s);
 
 std::string removeString(const std::string origStr,
                         const std::string &removeMe);
+void system_wait(int milli_seconds);
+int countDigit(uint64_t n);
 template <typename T>
   std::string print_int_as_hex(T i, bool showHexNotation = true,
   int overloadBitSize = 0) {