Updated Driver version 10.02.15.00-k1

]]> Added support for:

SuSE Linux Enterprise Server 15.7

Updated Driver version 10.02.14.00-k1

]]> Initial version.

]]> TBD

]]>
  • This product now supports Red Hat Enterprise Linux 9.6.
  • This product now supports Software Cross Timestamping feature for E810.
    • ]]>         This product fixed an issue where the 'ethtool ethx' displayed 'AUI' with AOC cable, should display 'Fibre'.

    ]]>         To eliminate the risk of gen drop issue.

    ]]>
  • FW update to eliminate the risk of Drive missing issue.
  • Fixed low sequential write performance in Windows 2022
    • ]]>         See the iSUT Release Notes for information about the issues resolved in this release

    ]]>         See the iSUT Release Notes for information about the issues resolved in this release

    ]]>         See the iSUT Release Notes for information about the issues resolved in this release

    ]]>         See the iSUT Release Notes for information about the issues resolved in this release

    ]]>         SR 2.10.0/SR 3.5.0 RC

    ]]>
  • Fixed an issue that drives are still listed at the OS level when the controller is offline.
    • ]]>         Added SLES16 support

    ]]>
  • Add support for users to clear NVRAM using Factory Repurpose operation
    • Command: storcli /cx set factory repurpose
    • ]]>         See the AMS Release Notes for information about the enhancements in this release.

    ]]>         See the AMS Release Notes for information about the issues resolved in this release

    ]]>         See the AMS Release Notes for information about the enhancements in this release.

    ]]>         See the AMS Release Notes for information about the issues resolved in this release

    ]]>         To Do

    ]]>         To Do

    ]]>         Support new Gen12 servers.

    ]]>         Support new ML110 and DL560 Gen11 servers

    ]]>         Driver version 5.4.85.0
    This driver is only supported on VMware ESXi 8.0u3

    ]]>         Driver version 5.4.83.1
    This driver is only supported on VMware ESXi 8.0u3

    ]]>         This Firmware package contains following firmware versions:

    Adapter

    Speed

    MBI

    Firmware

    UEFI

    Boot Bios
    HPE SN1610Q 32Gb Dual Port Fibre Channel Host Bus Adapter 32Gb 02.11.06 09.15.11 7.39 0.0
    HPE SN1610Q 32Gb Single Port Fibre Channel Host Bus Adapter 32Gb 02.11.06 09.15.11 7.39 0.0
    HPE SN1700Q 64Gb Dual Port Fibre Channel Host Bus Adapter 64Gb 02.11.06 09.15.11 7.39 0.0
    HPE SN1700Q 64Gb Single Port Fibre Channel Host Bus Adapter 64Gb 02.11.06 09.15.11 7.39 0.0
    ]]>         This Firmware package contains following firmware versions:

    Adapter

    Speed

    MBI

    Firmware

    UEFI

    Boot Bios
    HPE SN1610Q 32Gb Dual Port Fibre Channel Host Bus Adapter 32Gb 02.11.01 09.15.05 7.39 0.0
    HPE SN1610Q 32Gb Single Port Fibre Channel Host Bus Adapter 32Gb 02.11.01 09.15.05 7.39 0.0
    HPE SN1700Q 64Gb Dual Port Fibre Channel Host Bus Adapter 64Gb 02.11.01 09.15.05 7.39 0.0
    HPE SN1700Q 64Gb Single Port Fibre Channel Host Bus Adapter 64Gb 02.11.01 09.15.05 7.39 0.0
    ]]>         Fixed the following:

    1. Windows BitLocker causes the system boot due to ROM signature failure during POST.
    2. Increase an internal timeout value for SPI/Flash read.
    ]]>         Updated Driver version 10.02.15.00-k1

    ]]>         Added Support For:

    Red Hat Enterprise Linux 10

    Updated Driver version 10.02.14.00-k1

    ]]>
  • Improvements to our out-of-band message handling to ensure robust device management capabilities
  • Changes to improve our PCIe link compatibility as well as device reliability
  • This firmware update is recommended as it improves our system interoperability and prevents specific scenarios that could cause the drive to become unresponsive.
    • ]]>
  • Improvements to our out-of-band message handling to ensure robust device management capabilities
  • Changes to improve our PCIe link compatibility as well as device reliability
  • This firmware update is recommended as it improves our system interoperability and prevents specific scenarios that could cause the drive to become unresponsive.
    • ]]>
  • DMTF PLDM Redfish Device Enablement enhancements
    • Redfish Volume Transformation Support
      • POST #Volume.ChangeRAIDLayout: RAID Layout Change. Change in the RAID Layout is achieved by providing the target RAIDType and the list of the drives in the input JSON body.
      • POST #Volume.ChangeRAIDLayout: Resize. ChangeRAIDLayout can be used to resize the volume by adding new Unconfigured Good drives without changing the RAIDType. In such cases RAIDType must not be provided in the input JSON body but the full drive list must be provided accordingly.
      • PATCH Volume[CapacityBytes]: This operation is used for resizing the volume when there is unused size available in the volume. There is no scope for adding any new drives here
      • POST #Volume.CheckConsistency: This operation starts Consistency Check operation on the volume. No input is expected for this operation.
    • Redfish Metrics GET Support
      • StorageControllerMetrics: UncorrectableECCErrorCount, CorrectableECCErrorCount, CorrectableParityErrorCount, StateChangeCount
      • PortMetrics: SAS.InvalidDwordCount, SAS.LossOfDwordSynchronizationCount, SAS.RunningDisparityErrorCount, PCIeErrors.CorrectableErrorCount, PCIeErrors.FatalErrorCount, PCIeErrors.NonFatalErrorCount
      • Each counter can hold a value up to 65535. Once the counter reaches the maximum value the value is not reset.
      • Metrics are cleared when user performs Controller NVRAM clear or Redfish ResetToDefaults.ResetAll.
  • Add support for users to clear NVRAM using MRSA and storcli Factory Repurpose operation.
    • Clear NVRAM operation is not allowed if there is any configuration present on the controller or if there is any pinned cache.
    • After clearing NVRAM, controller FW performs Online Controller Reset (OCR). If for some reason OCR cannot be performed, then the user will be notified to perform a system reboot.
    • The Clear NVRAM operation is equivalent to Redfish ResetToDefaults.ResetAll operation functionally.
  • Change the backplane bay count information to the actual bay that is connected to controller. For non-hotplug configuration, controller always shows 16 bays.
    • ]]>
  • Fix a00143124en_us Advisory: HPE MR Gen11 Controller - MR Gen11 Controllers on HPE Gen11 Servers May Fail to Generate "WriteCacheDataLoss" in the IML
  • Fix a00148035en_us Advisory: HPE MR Gen11 Controllers - The Bay And Box NVMe Drive Location Is Not Displayed in the One-Time Boot Menu
  • Fix an issue that Read/Write transfers over 128KB on LTO fail in Linux OS
  • Fix an issue that Backup Exec doesn’t work with LTO
  • Fix an issue that controller might be dropped by the iLO in server boot up when there are 240 Logical Drives are configured
  • Fix a rare issue that server health shows critical temporally when remove drive continuously.
  • Fix an issue that unexpected PCIConfiglink page events, Task management to the virtual SES device time out messages are logged in snapdump
  • Fix an issue that Slot capable protocol is missing for empty bay
  • Fix an issue that Link Speed for LTO connected to controller shows Unknown
  • Fix an issue that Request Sense command causes task management on the drive where sanitization is in progress.
  • Fix an issue that Redfish PATCH StorageController[ControllerRates] silently sets random values when the value beyond 255 is used.
  • Fix an issue that incorrect controller error event may be logged when controller is configured as passthrough and do vm reboot
  • Fix an issue that active width, current speed are wrong in Redfish Fabric port when two backplanes connected to same storage port.
  • Fix a rare issue that NVMe drive link status may fail after reboot 
  • Fix a rare issue that controller may assert when there are multiple drives removed and inserted in a short time
  • Fix an issue that sanitize percentage does not progress on SATA drives if there is SATA passthrough command running
  • Fix an issue that sanitize percentage does not progress on NVMe drives
  • Fix a rare issue that IO timeout and device reset may occur with stress test of Read/Write and Non-Read/Write commands
    • ]]>
  • DMTF PLDM Redfish Device Enablement enhancements
    • Redfish Volume Transformation Support
      • POST #Volume.ChangeRAIDLayout: RAID Layout Change. Change in the RAID Layout is achieved by providing the target RAIDType and the list of the drives in the input JSON body.
      • POST #Volume.ChangeRAIDLayout: Resize. ChangeRAIDLayout can be used to resize the volume by adding new Unconfigured Good drives without changing the RAIDType. In such cases RAIDType must not be provided in the input JSON body but the full drive list must be provided accordingly.
      • PATCH Volume[CapacityBytes]: This operation is used for resizing the volume when there is unused size available in the volume. There is no scope for adding any new drives here
      • POST #Volume.CheckConsistency: This operation starts Consistency Check operation on the volume. No input is expected for this operation.
    • Redfish Metrics GET Support
      • StorageControllerMetrics: UncorrectableECCErrorCount, CorrectableECCErrorCount, CorrectableParityErrorCount, StateChangeCount
      • PortMetrics: SAS.InvalidDwordCount, SAS.LossOfDwordSynchronizationCount, SAS.RunningDisparityErrorCount, PCIeErrors.CorrectableErrorCount, PCIeErrors.FatalErrorCount, PCIeErrors.NonFatalErrorCount
      • Each counter can hold a value up to 65535. Once the counter reaches the maximum value the value is not reset.
      • Metrics are cleared when user performs Controller NVRAM clear or Redfish ResetToDefaults.ResetAll.
  • Add support for users to clear NVRAM using MRSA and storcli Factory Repurpose operation.
    • Clear NVRAM operation is not allowed if there is any configuration present on the controller or if there is any pinned cache.
    • After clearing NVRAM, controller FW performs Online Controller Reset (OCR). If for some reason OCR cannot be performed, then the user will be notified to perform a system reboot.
    • The Clear NVRAM operation is equivalent to Redfish ResetToDefaults.ResetAll operation functionally.
  • Change the backplane bay count information to the actual bay that is connected to controller. For non-hotplug configuration, controller always shows 16 bays.
    • ]]>
  • Fix a00143124en_us Advisory: HPE MR Gen11 Controller - MR Gen11 Controllers on HPE Gen11 Servers May Fail to Generate "WriteCacheDataLoss" in the IML
  • Fix a00148035en_us Advisory: HPE MR Gen11 Controllers - The Bay And Box NVMe Drive Location Is Not Displayed in the One-Time Boot Menu
  • Fix an issue that Read/Write transfers over 128KB on LTO fail in Linux OS
  • Fix an issue that Backup Exec doesn’t work with LTO
  • Fix an issue that controller might be dropped by the iLO in server boot up when there are 240 Logical Drives are configured
  • Fix a rare issue that server health shows critical temporally when remove drive continuously.
  • Fix an issue that unexpected PCIConfiglink page events, Task management to the virtual SES device time out messages are logged in snapdump
  • Fix an issue that Slot capable protocol is missing for empty bay
  • Fix an issue that Link Speed for LTO connected to controller shows Unknown
  • Fix an issue that Request Sense command causes task management on the drive where sanitization is in progress.
  • Fix an issue that Redfish PATCH StorageController[ControllerRates] silently sets random values when the value beyond 255 is used.
  • Fix an issue that incorrect controller error event may be logged when controller is configured as passthrough and do vm reboot
  • Fix an issue that active width, current speed are wrong in Redfish Fabric port when two backplanes connected to same storage port.
  • Fix a rare issue that NVMe drive link status may fail after reboot 
  • Fix a rare issue that controller may assert when there are multiple drives removed and inserted in a short time
  • Fix an issue that sanitize percentage does not progress on SATA drives if there is SATA passthrough command running
  • Fix an issue that sanitize percentage does not progress on NVMe drives
  • Fix a rare issue that IO timeout and device reset may occur with stress test of Read/Write and Non-Read/Write commands
    • ]]>
  • This version of FW now supports the 15.36TB model and FW fixes of drive time-out/failures.
    • ]]>
  • Updated Support Platform
    • ]]>
  • Updated Component Data
    • ]]>
  • Updated Supported Environments
    • ]]>
  • Updated Supported Environments
  • Updated Supported Products
    • ]]>         Important Notes:

    This revision of the System ROM includes AMD reference code TurinPI 1.0.0.6 for AMD 5th Generation EPYC processors.

    Details about reported security vulnerabilities and their mitigation can be found at the following link Security Bulletin Library | HPE Support.

    Firmware Dependencies:

    None

    Problems Fixed:

    Addressed an issue where the attribute names in the BIOS Attribute Registry were not aligned with the BIOS Settings URI.

    Addressed an issue where the DisplayName of the AllowLoginWithIlo attribute in the BIOS registry was displayed incorrectly.

    Addressed an issue where the second firmware information in RBSU could show as "Unknown" for Intel E610/E810 NIC cards.

    Corrected the USB numbering in the media bay.

    Addressed an issue where sending a GET request to /redfish/v1/ComponentIntegrity/HardwareDataBlob resulted in an error with the messageId SystemResetRequired.

    Addressed an issue where Redfish BIOS settings might not be applied when upgrading the BIOS and changing BIOS settings simultaneously.

    Addressed an issue where the SMBIOS Type9 information was incorrect for empty OCP slots.

    Addressed an issue where the IML entry for a mapped-out DIMM might not be logged.

    Addressed an issue where SaveUserDefaults in Redfish base configurations still showed "Yes" after saving settings and rebooting.

    Addressed an issue where the PCIe Riser MCU firmware information might not display correctly.

    Addressed an issue where an incorrect Structured Boot Name might appear in the OS boot options.

    Addressed an issue where the information for PCIe Slot3 and Slot4 was swapped.

    Addressed an issue where the server name might be displayed incorrectly in the iLO web interface.

    Known Issues:

    None]]>
  • Improve the FW about data mismatch after SPL
    • ]]>         TBD

    ]]>
  • This product fixes issue where In HW LAG mode 1 with Port1 link down, RX packet and byte counters in the VM do not increment during VF-to-VF RoCE traffic.
  • This product fixes issue where Active CQ value differs between debugfs and rdma resource show.
  • This product fixes issue where in existing sysfs counters.
  • This product fixes issue where header file inclusion.
    • ]]>         TBD

    ]]>
  • This product fixes an issue where the Port Reset attributes are missing under RDE port Schema.
  • This product fixes an issue where the link failed with the LCP-1250RJ3SR-KH transceiver.
  • This product fixes an issue where the FW PLDM upgrade may failed with CVL4.71 when MCTP traffic loading is heavy.
  • This product fixes an issue where the BSOD observed in Windows OS with OOB driver when transmit balancing is enabled in NIC HII menu.
    • ]]>         This product VMware ESXi 9 supported.

    ]]>         This product fixes to align DDP with the new FW version and NVM 4.7.

    ]]>         This product fixes an issue where the VM traffic may not working when VF driver disabled or not installed.

    ]]>         This product fixes an issue where the VM traffic may not working when VF driver disabled or not installed.

    ]]>         TBD

    ]]>
  • This product fixes an issue where the Port Reset attributes are missing under RDE port Schema.
  • This product fixes an issue where the link failed with the LCP-1250RJ3SR-KH transceiver.
  • This product fixes an issue where the FW PLDM upgrade may failed with CVL4.71 when MCTP traffic loading is heavy.
  • This product fixes an issue where the BSOD observed in Windows OS with OOB driver when transmit balancing is enabled in NIC HII menu.
    • ]]>         Important Notes:

    None

    Firmware Dependencies:

    None

    Enhancements/New Features:

    This is the initial verison of the firmware.

    Known Issues:

    None

    ]]>         TBD

    ]]>
  • This product now adds support for E610 device.
  • This product now supports Red Hat Enterprise Linux 9.6.
  • This product adds support for NVM update during FW recovery.
    • ]]>
  • This product fixes remove 128 CPUs limit for XDP.
  • This product fixes stop setting carrier on while the adapter is down.
  • This product fixes use netdev->fcoe_mtu when required.
  • Known issue: Firmware OROM version displays as "0.0.0" via "ethtool -i".
    • ]]>
  • This FW update contains the fix for false ILO message of temporary drive "degraded" status.
  • After the FW update, if the latest drive FW version is not correctly reflected in iLO under the scenarios outlined below, a system reboot or iLO reset may be required.
    • HPK3 -> HPK5 (or later version)
    • HPK4 -> HPK5 (or later version)
    • ]]>
  • This FW update contains the fix for false ILO message of temporary drive "degraded" status.
    • ]]>         TBD

    ]]>         This product fixes to align DDP with the new FW version and NVM 4.7.

    ]]>         See the AMS Release Notes for information about the enhancements in this release.

    ]]>         See the AMS Release Notes for information about the issues resolved in this release.

    ]]>         See the AMS Release Notes for information about the enhancements in this release.

    ]]>         See the AMS Release Notes for information about the issues resolved in this release.

    ]]>         This product added WoL support for Intel E610 OCP.

    ]]>
  • This product fixed system freeze during the E610 adapter disablement when maximum number of VFs is allocated.
  • This product fixed driver failed after booting installation media with updated driver via UEFI & Legacy.
    • ]]>         This product added WoL support for Intel E610 OCP.

    ]]>
  • This product fixed system freeze during the E610 adapter disablement when maximum number of VFs is allocated.
  • This product fixed driver failed after booting installation media with updated driver via UEFI & Legacy.
    • ]]>
  • This firmware fixes an issue where the drive can become inaccessible after an emergency power off, and corrects a potential verification issue during read recovery.
    • ]]>         TBD

    ]]>         This product now adds support for E610 device.

    ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>
  • Improve random read/write perfomance.
    • ]]>         New features and changes included in version 28.46.3048:

    • This release contains important reliability improvements and security hardening enhancements. HPE recommends upgrading your devices firmware to this release to improve the devices’ firmware security and reliability.
    ]]>         The following fixes have been included in version 28.46.3048:

    • The adapter card would drop NC-SI over MCTP commands when padding bytes were present after the NC-SI checksum.
    ]]>         New features and changes included in version 28.45.1200:

    • Introduced a 1ms delay for SPDM responses.
    ]]>         The following fixes have been included in version 28.45.1200:

    • Fixed DC InfiniBand functionality.
    ]]>

  • Fix windows tool cert expire issue.

    • ]]>
  • Add support for users to clear NVRAM using Factory Repurpose operation
    • Command: storcli /cx set factory repurpose
    • ]]>
  • Enabled HPE COM for XD230 platform on HPE iLO7.
  • Enabled HPE OneView for XD230 platform on HPE iLO7.
  • Enabled Virtual Serial Port (VSP) by default.
  • Enabled monitoring of Direct Attached NVMe drives through HPE iLO SNMP when AMS is not installed on the host operating system.
  • Modified SNMP storage controller properties to match the attribute values from the Redfish interface.
  • Added Domain Name Support for Thales Cipher Trust Manager.
  • Support for Automatic Management of TLS certificates using the ACME (Automatic Certificate Management Environment) protocol, which eliminates the need for manual certificate enrollment and renewal, ensures HPE always has a valid, trusted TLS certificate, and works with any RFC 8555 ACMEv2 compliant server such as STEP-CA.
  • Enhanced the HPE iLO password length to 8 from 0.
  • Added support for NVIDIA RTX6000D GPU.
  • MTU Size is now configurable for iLO Dedicated Network port
    • ]]>
  • None
    • ]]>
  • None
    • ]]>
  • Fixed an issue with the logic to load the Gateway Certificate to the correct SSL context after an HPE iLO reset.
  • Fixed an issue where after an upgrade to HPE iLO v1.18.00, HPE iLO may incorrectly report server POST status and the device discovery may not complete.
    • ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>
  • This firmware version fixes a bug with the unmap command that may cause a drive hang
    • ]]>
  • Updated Supported Environments
    • ]]>
  • Updated Supported Environments
    • ]]>
  • To fix 1) chip kill -The host IO CMD may get timed out and shows SNS=04/40/C2 and 2) garbage collection checking for performance recovery.
    • ]]>
  • Added fix to address a rare case where drive health queries can trigger false drive predictive failure.
  • For more information, refer to HPE Customer Advisory at the following URL: https://support.hpe.com/hpesc/public/docDisplay?docId=emr_na-a00146367en_us which will be active on 20-Mar-2025.
    • ]]>         SR 2.10.0/SR 3.5.0 RC

    ]]>
  • Fixed an issue that drives are still listed at the OS level when the controller is offline.
    • ]]>         Updated the kit to version 6.0.0.1-4

    ]]>         Updated the kit to version 6.0.0.1-4

    ]]>
  • DMTF PLDM Redfish Device Enablement enhancements
    • Redfish Volume Transformation Support
      • POST #Volume.ChangeRAIDLayout: RAID Layout Change. Change in the RAID Layout is achieved by providing the target RAIDType and the list of the drives in the input JSON body.
      • POST #Volume.ChangeRAIDLayout: Resize. ChangeRAIDLayout can be used to resize the volume by adding new Unconfigured Good drives without changing the RAIDType. In such cases RAIDType must not be provided in the input JSON body but the full drive list must be provided accordingly.
      • PATCH Volume[CapacityBytes]: This operation is used for resizing the volume when there is unused size available in the volume. There is no scope for adding any new drives here
      • POST #Volume.CheckConsistency: This operation starts Consistency Check operation on the volume. No input is expected for this operation.
    • Redfish Metrics GET Support
      • StorageControllerMetrics: UncorrectableECCErrorCount, CorrectableECCErrorCount, CorrectableParityErrorCount, StateChangeCount
      • PortMetrics: SAS.InvalidDwordCount, SAS.LossOfDwordSynchronizationCount, SAS.RunningDisparityErrorCount, PCIeErrors.CorrectableErrorCount, PCIeErrors.FatalErrorCount, PCIeErrors.NonFatalErrorCount
      • Each counter can hold a value up to 65535. Once the counter reaches the maximum value the value is not reset.
      • Metrics are cleared when user performs Controller NVRAM clear or Redfish ResetToDefaults.ResetAll.
  • Add support for users to clear NVRAM using MRSA and storcli Factory Repurpose operation.
    • Clear NVRAM operation is not allowed if there is any configuration present on the controller or if there is any pinned cache.
    • After clearing NVRAM, controller FW performs Online Controller Reset (OCR). If for some reason OCR cannot be performed, then the user will be notified to perform a system reboot.
    • The Clear NVRAM operation is equivalent to Redfish ResetToDefaults.ResetAll operation functionally.
  • Change the backplane bay count information to the actual bay that is connected to controller. For non-hotplug configuration, controller always shows 16 bays.
    • ]]>
  • Fix a00143124en_us Advisory: HPE MR Gen11 Controller - MR Gen11 Controllers on HPE Gen11 Servers May Fail to Generate "WriteCacheDataLoss" in the IML
  • Fix a00148035en_us Advisory: HPE MR Gen11 Controllers - The Bay And Box NVMe Drive Location Is Not Displayed in the One-Time Boot Menu
  • Fix an issue that Read/Write transfers over 128KB on LTO fail in Linux OS
  • Fix an issue that Backup Exec doesn’t work with LTO
  • Fix an issue that controller might be dropped by the iLO in server boot up when there are 240 Logical Drives are configured
  • Fix a rare issue that server health shows critical temporally when remove drive continuously.
  • Fix an issue that unexpected PCIConfiglink page events, Task management to the virtual SES device time out messages are logged in snapdump
  • Fix an issue that Slot capable protocol is missing for empty bay
  • Fix an issue that Link Speed for LTO connected to controller shows Unknown
  • Fix an issue that Request Sense command causes task management on the drive where sanitization is in progress.
  • Fix an issue that Redfish PATCH StorageController[ControllerRates] silently sets random values when the value beyond 255 is used.
  • Fix an issue that incorrect controller error event may be logged when controller is configured as passthrough and do vm reboot
  • Fix an issue that active width, current speed are wrong in Redfish Fabric port when two backplanes connected to same storage port.
  • Fix a rare issue that NVMe drive link status may fail after reboot 
  • Fix a rare issue that controller may assert when there are multiple drives removed and inserted in a short time
  • Fix an issue that sanitize percentage does not progress on SATA drives if there is SATA passthrough command running
  • Fix an issue that sanitize percentage does not progress on NVMe drives
  • Fix a rare issue that IO timeout and device reset may occur with stress test of Read/Write and Non-Read/Write commands
    • ]]>
  • DMTF PLDM Redfish Device Enablement enhancements
    • Redfish Volume Transformation Support
      • POST #Volume.ChangeRAIDLayout: RAID Layout Change. Change in the RAID Layout is achieved by providing the target RAIDType and the list of the drives in the input JSON body.
      • POST #Volume.ChangeRAIDLayout: Resize. ChangeRAIDLayout can be used to resize the volume by adding new Unconfigured Good drives without changing the RAIDType. In such cases RAIDType must not be provided in the input JSON body but the full drive list must be provided accordingly.
      • PATCH Volume[CapacityBytes]: This operation is used for resizing the volume when there is unused size available in the volume. There is no scope for adding any new drives here
      • POST #Volume.CheckConsistency: This operation starts Consistency Check operation on the volume. No input is expected for this operation.
    • Redfish Metrics GET Support
      • StorageControllerMetrics: UncorrectableECCErrorCount, CorrectableECCErrorCount, CorrectableParityErrorCount, StateChangeCount
      • PortMetrics: SAS.InvalidDwordCount, SAS.LossOfDwordSynchronizationCount, SAS.RunningDisparityErrorCount, PCIeErrors.CorrectableErrorCount, PCIeErrors.FatalErrorCount, PCIeErrors.NonFatalErrorCount
      • Each counter can hold a value up to 65535. Once the counter reaches the maximum value the value is not reset.
      • Metrics are cleared when user performs Controller NVRAM clear or Redfish ResetToDefaults.ResetAll.
  • Add support for users to clear NVRAM using MRSA and storcli Factory Repurpose operation.
    • Clear NVRAM operation is not allowed if there is any configuration present on the controller or if there is any pinned cache.
    • After clearing NVRAM, controller FW performs Online Controller Reset (OCR). If for some reason OCR cannot be performed, then the user will be notified to perform a system reboot.
    • The Clear NVRAM operation is equivalent to Redfish ResetToDefaults.ResetAll operation functionally.
  • Change the backplane bay count information to the actual bay that is connected to controller. For non-hotplug configuration, controller always shows 16 bays.
    • ]]>
  • Fix a00143124en_us Advisory: HPE MR Gen11 Controller - MR Gen11 Controllers on HPE Gen11 Servers May Fail to Generate "WriteCacheDataLoss" in the IML
  • Fix a00148035en_us Advisory: HPE MR Gen11 Controllers - The Bay And Box NVMe Drive Location Is Not Displayed in the One-Time Boot Menu
  • Fix an issue that Read/Write transfers over 128KB on LTO fail in Linux OS
  • Fix an issue that Backup Exec doesn’t work with LTO
  • Fix an issue that controller might be dropped by the iLO in server boot up when there are 240 Logical Drives are configured
  • Fix a rare issue that server health shows critical temporally when remove drive continuously.
  • Fix an issue that unexpected PCIConfiglink page events, Task management to the virtual SES device time out messages are logged in snapdump
  • Fix an issue that Slot capable protocol is missing for empty bay
  • Fix an issue that Link Speed for LTO connected to controller shows Unknown
  • Fix an issue that Request Sense command causes task management on the drive where sanitization is in progress.
  • Fix an issue that Redfish PATCH StorageController[ControllerRates] silently sets random values when the value beyond 255 is used.
  • Fix an issue that incorrect controller error event may be logged when controller is configured as passthrough and do vm reboot
  • Fix an issue that active width, current speed are wrong in Redfish Fabric port when two backplanes connected to same storage port.
  • Fix a rare issue that NVMe drive link status may fail after reboot 
  • Fix a rare issue that controller may assert when there are multiple drives removed and inserted in a short time
  • Fix an issue that sanitize percentage does not progress on SATA drives if there is SATA passthrough command running
  • Fix an issue that sanitize percentage does not progress on NVMe drives
  • Fix a rare issue that IO timeout and device reset may occur with stress test of Read/Write and Non-Read/Write commands
    • ]]>         TBD

    ]]>
  • Regular FW maintenance for fixing MCU,sanitize, DRAM and log page..etc.
    • ]]>
  • Fixes PCIe link drop, Drive detection after hot re-insert on Windows and includes other regular FW patch releases.
    • ]]>
  • Add support for users to clear NVRAM using Factory Repurpose operation
    • Command: storcli /cx set factory repurpose
    • ]]>
  • Add support for users to clear NVRAM using Factory Repurpose operation
    • Command: storcli /cx set factory repurpose
    • ]]>         TBD

    ]]>         This product now adds support for E610 device.

    ]]>
  • Known issue: Firmware OROM version displays as "0.0.0" via "ethtool -i".
  • Known issue: Firmware OROM version displays incorrectly via "esxcli network nic get -n interface".
    • ]]>
  • Updated Supported Environments
    • ]]>
  • Updated Supported Environments
    • ]]>
  • DMTF PLDM Redfish Device Enablement enhancements
    • Redfish Volume Transformation Support
      • POST #Volume.ChangeRAIDLayout: RAID Layout Change. Change in the RAID Layout is achieved by providing the target RAIDType and the list of the drives in the input JSON body.
      • POST #Volume.ChangeRAIDLayout: Resize. ChangeRAIDLayout can be used to resize the volume by adding new Unconfigured Good drives without changing the RAIDType. In such cases RAIDType must not be provided in the input JSON body but the full drive list must be provided accordingly.
      • PATCH Volume[CapacityBytes]: This operation is used for resizing the volume when there is unused size available in the volume. There is no scope for adding any new drives here
      • POST #Volume.CheckConsistency: This operation starts Consistency Check operation on the volume. No input is expected for this operation.
    • Redfish Metrics GET Support
      • StorageControllerMetrics: UncorrectableECCErrorCount, CorrectableECCErrorCount, CorrectableParityErrorCount, StateChangeCount
      • PortMetrics: SAS.InvalidDwordCount, SAS.LossOfDwordSynchronizationCount, SAS.RunningDisparityErrorCount, PCIeErrors.CorrectableErrorCount, PCIeErrors.FatalErrorCount, PCIeErrors.NonFatalErrorCount
      • Each counter can hold a value up to 65535. Once the counter reaches the maximum value the value is not reset.
      • Metrics are cleared when user performs Controller NVRAM clear or Redfish ResetToDefaults.ResetAll.
  • Add support for users to clear NVRAM using MRSA and storcli Factory Repurpose operation.
    • Clear NVRAM operation is not allowed if there is any configuration present on the controller or if there is any pinned cache.
    • After clearing NVRAM, controller FW performs Online Controller Reset (OCR). If for some reason OCR cannot be performed, then the user will be notified to perform a system reboot.
    • The Clear NVRAM operation is equivalent to Redfish ResetToDefaults.ResetAll operation functionally.
  • Change the backplane bay count information to the actual bay that is connected to controller. For non-hotplug configuration, controller always shows 16 bays.
    • ]]>
  • Fix a00143124en_us Advisory: HPE MR Gen11 Controller - MR Gen11 Controllers on HPE Gen11 Servers May Fail to Generate "WriteCacheDataLoss" in the IML
  • Fix a00148035en_us Advisory: HPE MR Gen11 Controllers - The Bay And Box NVMe Drive Location Is Not Displayed in the One-Time Boot Menu
  • Fix an issue that Read/Write transfers over 128KB on LTO fail in Linux OS
  • Fix an issue that Backup Exec doesn’t work with LTO
  • Fix an issue that controller might be dropped by the iLO in server boot up when there are 240 Logical Drives are configured
  • Fix a rare issue that server health shows critical temporally when remove drive continuously.
  • Fix an issue that unexpected PCIConfiglink page events, Task management to the virtual SES device time out messages are logged in snapdump
  • Fix an issue that Slot capable protocol is missing for empty bay
  • Fix an issue that Link Speed for LTO connected to controller shows Unknown
  • Fix an issue that Request Sense command causes task management on the drive where sanitization is in progress.
  • Fix an issue that Redfish PATCH StorageController[ControllerRates] silently sets random values when the value beyond 255 is used.
  • Fix an issue that incorrect controller error event may be logged when controller is configured as passthrough and do vm reboot
  • Fix an issue that active width, current speed are wrong in Redfish Fabric port when two backplanes connected to same storage port.
  • Fix a rare issue that NVMe drive link status may fail after reboot 
  • Fix a rare issue that controller may assert when there are multiple drives removed and inserted in a short time
  • Fix an issue that sanitize percentage does not progress on SATA drives if there is SATA passthrough command running
  • Fix an issue that sanitize percentage does not progress on NVMe drives
  • Fix a rare issue that IO timeout and device reset may occur with stress test of Read/Write and Non-Read/Write commands
    • ]]>
  • DMTF PLDM Redfish Device Enablement enhancements
    • Redfish Volume Transformation Support
      • POST #Volume.ChangeRAIDLayout: RAID Layout Change. Change in the RAID Layout is achieved by providing the target RAIDType and the list of the drives in the input JSON body.
      • POST #Volume.ChangeRAIDLayout: Resize. ChangeRAIDLayout can be used to resize the volume by adding new Unconfigured Good drives without changing the RAIDType. In such cases RAIDType must not be provided in the input JSON body but the full drive list must be provided accordingly.
      • PATCH Volume[CapacityBytes]: This operation is used for resizing the volume when there is unused size available in the volume. There is no scope for adding any new drives here
      • POST #Volume.CheckConsistency: This operation starts Consistency Check operation on the volume. No input is expected for this operation.
    • Redfish Metrics GET Support
      • StorageControllerMetrics: UncorrectableECCErrorCount, CorrectableECCErrorCount, CorrectableParityErrorCount, StateChangeCount
      • PortMetrics: SAS.InvalidDwordCount, SAS.LossOfDwordSynchronizationCount, SAS.RunningDisparityErrorCount, PCIeErrors.CorrectableErrorCount, PCIeErrors.FatalErrorCount, PCIeErrors.NonFatalErrorCount
      • Each counter can hold a value up to 65535. Once the counter reaches the maximum value the value is not reset.
      • Metrics are cleared when user performs Controller NVRAM clear or Redfish ResetToDefaults.ResetAll.
  • Add support for users to clear NVRAM using MRSA and storcli Factory Repurpose operation.
    • Clear NVRAM operation is not allowed if there is any configuration present on the controller or if there is any pinned cache.
    • After clearing NVRAM, controller FW performs Online Controller Reset (OCR). If for some reason OCR cannot be performed, then the user will be notified to perform a system reboot.
    • The Clear NVRAM operation is equivalent to Redfish ResetToDefaults.ResetAll operation functionally.
  • Change the backplane bay count information to the actual bay that is connected to controller. For non-hotplug configuration, controller always shows 16 bays.
    • ]]>
  • Fix a00143124en_us Advisory: HPE MR Gen11 Controller - MR Gen11 Controllers on HPE Gen11 Servers May Fail to Generate "WriteCacheDataLoss" in the IML
  • Fix a00148035en_us Advisory: HPE MR Gen11 Controllers - The Bay And Box NVMe Drive Location Is Not Displayed in the One-Time Boot Menu
  • Fix an issue that Read/Write transfers over 128KB on LTO fail in Linux OS
  • Fix an issue that Backup Exec doesn’t work with LTO
  • Fix an issue that controller might be dropped by the iLO in server boot up when there are 240 Logical Drives are configured
  • Fix a rare issue that server health shows critical temporally when remove drive continuously.
  • Fix an issue that unexpected PCIConfiglink page events, Task management to the virtual SES device time out messages are logged in snapdump
  • Fix an issue that Slot capable protocol is missing for empty bay
  • Fix an issue that Link Speed for LTO connected to controller shows Unknown
  • Fix an issue that Request Sense command causes task management on the drive where sanitization is in progress.
  • Fix an issue that Redfish PATCH StorageController[ControllerRates] silently sets random values when the value beyond 255 is used.
  • Fix an issue that incorrect controller error event may be logged when controller is configured as passthrough and do vm reboot
  • Fix an issue that active width, current speed are wrong in Redfish Fabric port when two backplanes connected to same storage port.
  • Fix a rare issue that NVMe drive link status may fail after reboot 
  • Fix a rare issue that controller may assert when there are multiple drives removed and inserted in a short time
  • Fix an issue that sanitize percentage does not progress on SATA drives if there is SATA passthrough command running
  • Fix an issue that sanitize percentage does not progress on NVMe drives
  • Fix a rare issue that IO timeout and device reset may occur with stress test of Read/Write and Non-Read/Write commands
    • ]]>
  • This is a firmware maintenance release. It addresses a potential data loss issue, along with other bug fixes and improvements.
  • For more information, refer to HPE Customer Bulletin at the following URL: https://support.hpe.com/hpsc/doc/public/display?docId=a00150711en_us.
    • ]]>
  • This is a firmware maintenance release. It addresses a potential data loss issue, along with other bug fixes and improvements.
  • For more information, refer to HPE Customer Bulletin at the following URL: https://support.hpe.com/hpsc/doc/public/display?docId=a00150711en_us which will be active on 18-Aug-2025.
    • ]]>
  • Fix FW assert and other regular fixes
    • ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>
  • Improve random read/write perfomance.
    • ]]>         Regular Firmware changes included:

    •     corner case performance enhance.
    •     Servo change that resolves issue with early heat application from Idle sweep seek terminated that may cause read errors
    ]]>
  • Update maximum continuous operation temperature values for host thermal management and reporting.
  • Assert fixes, logging enhancements and all current firmware improvements.
    • ]]>         TBD

    ]]>
  • This product now adds support for E610 device.
  • This product adds support for NVM update during FW recovery.
    • ]]>
  • This product fixes remove 128 CPUs limit for XDP.
  • This product fixes stop setting carrier on while the adapter is down.
  • This product fixes use netdev->fcoe_mtu when required.
  • Known issue: Firmware OROM version displays as "0.0.0" via "ethtool -i".
    • ]]>
  • Rebuilt using latest certificates for Windows installers
    • ]]>
  • Fixed the “Parity Initialization Method” information displayed for non-parity RAID levels. 
  • Fixed an issue where users were unable to clear the controller’s configuration when a foreign volume was present. 
  • Fixed an issue where a foreign-owned SED drive was being listed for array creation. 
  • Fixed an issue where the last failure reason was not listing on physical drives. 
  • Fixed an issue where SSAScripting failed to create an encrypted volume while in express local mode. 
  • Fixed an issue where an error/warning message was not being generated correctly while expanding a RAID 1+0 volume. 
  • Fixed an issue where a duplicate entry for the physical drive was displayed. 
    • ]]>
  • This FW update contains the fix for false ILO message of temporary drive "degraded" status.
  • After the FW update, if the latest drive FW version is not correctly reflected in iLO under the scenarios outlined below, a system reboot or iLO reset may be required.
    • HPK2 -> HPK4 (or later version)
    • HPK3 -> HPK4 (or later version)
    • ]]>
  • This FW update contains the fix for false ILO message of temporary drive "degraded" status.
    • ]]>
  • DMTF PLDM Redfish Device Enablement enhancements
    • Redfish Volume Transformation Support
      • POST #Volume.ChangeRAIDLayout: RAID Layout Change. Change in the RAID Layout is achieved by providing the target RAIDType and the list of the drives in the input JSON body.
      • POST #Volume.ChangeRAIDLayout: Resize. ChangeRAIDLayout can be used to resize the volume by adding new Unconfigured Good drives without changing the RAIDType. In such cases RAIDType must not be provided in the input JSON body but the full drive list must be provided accordingly.
      • PATCH Volume[CapacityBytes]: This operation is used for resizing the volume when there is unused size available in the volume. There is no scope for adding any new drives here
      • POST #Volume.CheckConsistency: This operation starts Consistency Check operation on the volume. No input is expected for this operation.
    • Redfish Metrics GET Support
      • StorageControllerMetrics: UncorrectableECCErrorCount, CorrectableECCErrorCount, CorrectableParityErrorCount, StateChangeCount
      • PortMetrics: SAS.InvalidDwordCount, SAS.LossOfDwordSynchronizationCount, SAS.RunningDisparityErrorCount, PCIeErrors.CorrectableErrorCount, PCIeErrors.FatalErrorCount, PCIeErrors.NonFatalErrorCount
      • Each counter can hold a value up to 65535. Once the counter reaches the maximum value the value is not reset.
      • Metrics are cleared when user performs Controller NVRAM clear or Redfish ResetToDefaults.ResetAll.
  • Add support for users to clear NVRAM using MRSA and storcli Factory Repurpose operation.
    • Clear NVRAM operation is not allowed if there is any configuration present on the controller or if there is any pinned cache.
    • After clearing NVRAM, controller FW performs Online Controller Reset (OCR). If for some reason OCR cannot be performed, then the user will be notified to perform a system reboot.
    • The Clear NVRAM operation is equivalent to Redfish ResetToDefaults.ResetAll operation functionally.
  • Change the backplane bay count information to the actual bay that is connected to controller. For non-hotplug configuration, controller always shows 16 bays.
    • ]]>
  • Fix a00143124en_us Advisory: HPE MR Gen11 Controller - MR Gen11 Controllers on HPE Gen11 Servers May Fail to Generate "WriteCacheDataLoss" in the IML
  • Fix a00148035en_us Advisory: HPE MR Gen11 Controllers - The Bay And Box NVMe Drive Location Is Not Displayed in the One-Time Boot Menu
  • Fix an issue that Read/Write transfers over 128KB on LTO fail in Linux OS
  • Fix an issue that Backup Exec doesn’t work with LTO
  • Fix an issue that controller might be dropped by the iLO in server boot up when there are 240 Logical Drives are configured
  • Fix a rare issue that server health shows critical temporally when remove drive continuously.
  • Fix an issue that unexpected PCIConfiglink page events, Task management to the virtual SES device time out messages are logged in snapdump
  • Fix an issue that Slot capable protocol is missing for empty bay
  • Fix an issue that Link Speed for LTO connected to controller shows Unknown
  • Fix an issue that Request Sense command causes task management on the drive where sanitization is in progress.
  • Fix an issue that Redfish PATCH StorageController[ControllerRates] silently sets random values when the value beyond 255 is used.
  • Fix an issue that incorrect controller error event may be logged when controller is configured as passthrough and do vm reboot
  • Fix an issue that active width, current speed are wrong in Redfish Fabric port when two backplanes connected to same storage port.
  • Fix a rare issue that NVMe drive link status may fail after reboot 
  • Fix a rare issue that controller may assert when there are multiple drives removed and inserted in a short time
  • Fix an issue that sanitize percentage does not progress on SATA drives if there is SATA passthrough command running
  • Fix an issue that sanitize percentage does not progress on NVMe drives
  • Fix a rare issue that IO timeout and device reset may occur with stress test of Read/Write and Non-Read/Write commands
    • ]]>
  • DMTF PLDM Redfish Device Enablement enhancements
    • Redfish Volume Transformation Support
      • POST #Volume.ChangeRAIDLayout: RAID Layout Change. Change in the RAID Layout is achieved by providing the target RAIDType and the list of the drives in the input JSON body.
      • POST #Volume.ChangeRAIDLayout: Resize. ChangeRAIDLayout can be used to resize the volume by adding new Unconfigured Good drives without changing the RAIDType. In such cases RAIDType must not be provided in the input JSON body but the full drive list must be provided accordingly.
      • PATCH Volume[CapacityBytes]: This operation is used for resizing the volume when there is unused size available in the volume. There is no scope for adding any new drives here
      • POST #Volume.CheckConsistency: This operation starts Consistency Check operation on the volume. No input is expected for this operation.
    • Redfish Metrics GET Support
      • StorageControllerMetrics: UncorrectableECCErrorCount, CorrectableECCErrorCount, CorrectableParityErrorCount, StateChangeCount
      • PortMetrics: SAS.InvalidDwordCount, SAS.LossOfDwordSynchronizationCount, SAS.RunningDisparityErrorCount, PCIeErrors.CorrectableErrorCount, PCIeErrors.FatalErrorCount, PCIeErrors.NonFatalErrorCount
      • Each counter can hold a value up to 65535. Once the counter reaches the maximum value the value is not reset.
      • Metrics are cleared when user performs Controller NVRAM clear or Redfish ResetToDefaults.ResetAll.
  • Add support for users to clear NVRAM using MRSA and storcli Factory Repurpose operation.
    • Clear NVRAM operation is not allowed if there is any configuration present on the controller or if there is any pinned cache.
    • After clearing NVRAM, controller FW performs Online Controller Reset (OCR). If for some reason OCR cannot be performed, then the user will be notified to perform a system reboot.
    • The Clear NVRAM operation is equivalent to Redfish ResetToDefaults.ResetAll operation functionally.
  • Change the backplane bay count information to the actual bay that is connected to controller. For non-hotplug configuration, controller always shows 16 bays.
    • ]]>
  • Fix a00143124en_us Advisory: HPE MR Gen11 Controller - MR Gen11 Controllers on HPE Gen11 Servers May Fail to Generate "WriteCacheDataLoss" in the IML
  • Fix a00148035en_us Advisory: HPE MR Gen11 Controllers - The Bay And Box NVMe Drive Location Is Not Displayed in the One-Time Boot Menu
  • Fix an issue that Read/Write transfers over 128KB on LTO fail in Linux OS
  • Fix an issue that Backup Exec doesn’t work with LTO
  • Fix an issue that controller might be dropped by the iLO in server boot up when there are 240 Logical Drives are configured
  • Fix a rare issue that server health shows critical temporally when remove drive continuously.
  • Fix an issue that unexpected PCIConfiglink page events, Task management to the virtual SES device time out messages are logged in snapdump
  • Fix an issue that Slot capable protocol is missing for empty bay
  • Fix an issue that Link Speed for LTO connected to controller shows Unknown
  • Fix an issue that Request Sense command causes task management on the drive where sanitization is in progress.
  • Fix an issue that Redfish PATCH StorageController[ControllerRates] silently sets random values when the value beyond 255 is used.
  • Fix an issue that incorrect controller error event may be logged when controller is configured as passthrough and do vm reboot
  • Fix an issue that active width, current speed are wrong in Redfish Fabric port when two backplanes connected to same storage port.
  • Fix a rare issue that NVMe drive link status may fail after reboot 
  • Fix a rare issue that controller may assert when there are multiple drives removed and inserted in a short time
  • Fix an issue that sanitize percentage does not progress on SATA drives if there is SATA passthrough command running
  • Fix an issue that sanitize percentage does not progress on NVMe drives
  • Fix a rare issue that IO timeout and device reset may occur with stress test of Read/Write and Non-Read/Write commands
    • ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>
  • To fix - Frequent insertion of low priority commands during IO execution may lead to drive offline randomly.

    • For more information, refer to HPE Customer Advisory at the following URL: https://support.hpe.com/hpesc/public/docDisplay?docId=a00141941en_us 

    ]]>         New features and changes included in version 26.46.3048:

    • Added support for RSS with crypto offload enabling the NIC to parallelize packet processing across CPU cores while performing encryption/decryption in hardware. Additionally, introduced a new l4_type_ext parameter with values: 0 (None), 1 (TCP), 2 (UDP), 3 (ICMP).
    • Added an extra validation for the payload_len field in incoming NC-SI messages. Previously, invalid packets might have been accepted; now, such packets are silently dropped.
    • This release contains important reliability improvements and security hardening enhancements. HPE recommends upgrading your devices firmware to this release to improve the devices’ firmware security and reliability.
    ]]>         The following issues have been fixed in version 26.46.3048:

    • Configuring a small MTU led to fragmentation of packets critical for the PXE boot process. As a result, the PXE boot filters mistakenly discarded these packets, causing the PXE boot to fail.
    ]]>         Security Hardening Enhancements: This release contains important reliability improvements and security hardening enhancements. HPE recommends upgrading your device's firmware to this release to improve the firmware security and reliability of your device.
     

    No new features and changes have been included in version 26.45.1020.

    ]]>         The following issues have been fixed in version 26.45.1020:

    • Configuring PHY_RATE_MASK for 10G in NV settings incorrectly disabled 10G capabilities.
    • RTT packets with any destination MAC address were incorrectly treated as having a valid destination MAC. The new firmware now discards RTT packets if their destination MAC does not match the port's MAC.
    ]]>         This product enhances to update PNP ID table（Plug and Play Identifier）

    ]]>         This product enhances to update PNP ID table. (Plug and Play Identifier)

    ]]>
  • Regular FW maintenance release for sanitize, DRAM,DMA transfer and log page fix.
    • ]]>
  • Adding 15T model number support and MCU code fix in FW release.
    • ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>
  • An error was found in the queue fullhandling process that results in the FUA bit not getting properly set, which could lead to the drive self-initiated reset
  • The FW fix is to resolve the handling of FUA bit during the queue full handling process has been implemented
  • The FW was confirmed to resolve the issue of drives resetting under queue full handling situations.
    • ]]>         Initial version.

    ]]>         TBD

    ]]>         Initial release to support Red Hat Enterprise Linux 10.

    ]]>         This product added WoL support for Intel E610 OCP.

    ]]>
  • This product fixed system freeze during the E610 adapter disablement when maximum number of VFs is allocated.
  • This product fixed driver failed after booting installation media with updated driver via UEFI & Legacy.
    • ]]>         This product added WoL support for Intel E610 OCP.

    ]]>
  • This product fixed system freeze during the E610 adapter disablement when maximum number of VFs is allocated.
  • This product fixed driver failed after booting installation media with updated driver via UEFI & Legacy.
    • ]]>         Updated Driver version 10.02.15.00-k1

    ]]>
  • Firmware changes aligned for future FIPS code release and one assert fix.
    • ]]>
  • Fixes the logic bug in the media cache cleaning abort handling that caused the drive to choose and execute the R/W command before the Request Sense to prevent assert.
  • Adding other logging and FW enhancements.
    • ]]>         Fix build tool certification issue.

    ]]>
  • Fix an issue that system may crash when importing Logical Drive.
    • ]]>         TBD

    ]]>
  • This product fixes an issue where the Port Reset attributes are missing under RDE port Schema.
  • This product fixes an issue where the link failed with the LCP-1250RJ3SR-KH transceiver.
  • This product fixes an issue where the FW PLDM upgrade may failed with CVL4.71 when MCTP traffic loading is heavy.
  • This product fixes an issue where the BSOD observed in Windows OS with OOB driver when transmit balancing is enabled in NIC HII menu.
    • ]]>
  • Support Gen12 servers.
    • ]]>         For Gen11 PR3 & 2023 March MSB

    ]]>
  • Add support for users to clear NVRAM using Factory Repurpose operation
    • Command: storcli /cx set factory repurpose
    • ]]>
  • Add support for users to clear NVRAM using Factory Repurpose operation
    • Command: storcli /cx set factory repurpose
    • ]]>         TBD

    ]]>         The following new features and changes have been included in version 25.07-0.9.7.1:
     

    • Hardware Steering (HWS): Enabled HWS as a secondary option for the device steering mode. If Software Steering (SWS) is not supported, HWS will be used by default, assuming it is available. Firmware Steering (FW) will now serve as the default only when both SWS and HWS are unsupported.

    • Hardware-Managed Flow Steering (HMFS): HMFS is a new approach to managing steering rules, where STEs are written to the ICM by hardware instead of software (as in software-managed steering). This enables a higher rate of rule insertion.

    • Queue Affinity Bonding: Added support for 4-port bonding to allow users to add both p0 and p1 to a bond without requiring SSH access to the host or bringing down the driver beforehand.

    • Multiple Doorbells per PF: Increased the number of doorbells from 1 to 8, distributing them in a round-robin manner across channel send and receive queues. This enhancement improves scalability on multi-core systems with high packet rates by reducing MMIO contention on doorbell addresses. In high packet-rate scenarios, Sub-NUMA Clustering is also required to maintain consistent channel packet rates.

    • HQoS for Virtualization Solution: Added support for hierarchical group structures to enable multi-tier resource control, where parent groups enforce overall limits and child groups dynamically share available bandwidth. This design is essential for effective QoS enforcement, burst handling, and fair bandwidth allocation, ensuring workloads receive appropriate resources.

    • Number of lanes Configuration when Auto-Negotiation is Disabled: Added support for specifying the number of lanes (protocol width) when auto-negotiation is disabled. Since each combination of speed and lane count corresponds to a unique link mode, this allows the user to select a specific link mode when auto-negotiation is off. This change aligns with a recent firmware update that requires the driver to provide a single link mode, rather than a bitmap based on the user-defined speed.

    • Extend ODP Statistics with Operation Count: Added the following new page-granularity counters:
      • num_page_faults: counts the number of page fault events handled
      • num_invalidations: counts the number of page invalidation events handled
    ]]>         The following issues have been fixed in version  25.07-0.9.7.1:

    • OFED installation caused CIFS to break in RHEL 8.4 and above. A dummy module was added so that CIFS will be disabled after OFED installation in RHEL 8.4 and above.
    • Performance degradation on older kernel versions using RX cache, particularly on slower ARM CPUs with larger RX buffers. The issue was caused by the driver attempting to allocate new RX pages too quickly, leading to head-of-line blocking in the RX cache. The fix improves RX cache usage by triggering page allocation for a bulk of at least 2 WQEs, allowing the application more time to process packets and return buffers to the RX cache, thereby reducing blocking and enhancing performance.
    • VF behavior was not aligned with /sys/class/net/<interface-name>/device/sriov_numvfs (silently ignore attempts to set the same number of VFs, and prevent changing the number of VFs until existing VFs are removed).
    • On BlueField-3 devices running linux-bluefield kernel versions 5.15.0-1050 or 5.15.0-1060, a kernel crash occurred due to a NULL pointer dereference in the cls_api network scheduler.
    ]]>         The following new features and changes have been included in version 25.04-0.6.1.1:

    • Trust Lockdown Health Syndrome: Added a new health syndrome for trust lockdown and expose the CRR bit in the health buffer. When the CRR bit is set, it indicates that the syndrome requires a cold reset for recovery.
    • A Single PTP Device per Hardware Clock: PHC is typically shared across multiple functions. Currently, the driver creates a separate PTP device for each network interface sharing the same PHC, resulting in redundancy and added complexity. To address this, a single PTP device is now created to represent the shared PHC when operating in real-time mode.
    • Log IB State Transitions: Enhanced visibility into IB device state transitions by adding log messages to the kernel log (dmesg). Each time an IB device changes state, a corresponding message will be logged. For example: "mlx5_0: Port: 1 Link DOWN".
    • Optional-counters Binding Support and New Packets/bytes Counters: Previously, optional counters were available only on a per-link basis. This release introduces the ability to bind optional counters to a specific counter object, enabling users to track optional counters across a specific QP group. Support is provided for both automatic and manual binding modes. In both cases, the optional counters that are bound to the QP are those currently configured on the link at the time of binding. Additionally, four new optional counters that track RDMA ingress and egress traffic are introduced: rdma_tx_bytes; rdma_tx_packets; rdma_rx_bytes; rdma_rx_packets. This functionality is exposed to users via the iproute2 package, which must be updated to support this feature.
    • User CAPability (UCAP) API: The User CAPability (UCAP) API introduces a mechanism for creating user contexts with specific firmware privileges. It offers fine-grained control over firmware features by exposing each capability as a character device with root-level read-write access. Root processes can grant users these privileges by allowing access to the corresponding character devices. When a user context is created using a UCAP file descriptor, it inherits the associated privileges. For mlx5, two UCAP character devices are provided, and any user context opened with at least one of them is treated as privileged. To guarantee the execution of privileged commands, non-privileged commands are restricted when a privileged user is active on the device.
    ]]>         The following issues have been fixed in version  25.04-0.6.1.1:

    • Buffer initialization became a performance bottleneck during the allocation of large buffers, typically when using a high number of QPs with large message sizes. The root cause was the inefficient use of rand(). This has been resolved by replacing it with a faster pseudo-random algorithm.
    • A potential deadlock that could occur during the handling of peer memory registration failures.
    • The following error occurred when switching to SwitchDev mode: "mlx5_core 0000:03:00.0: mlx5_cmd_out_err:835:(pid 24362): CREATE_FLOW_GROUP(0x933) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x4065f0), err(-22); mlx5_core 0000:03:00.0: E-Switch: Failed to create peer miss flow group err(-22)"
    • A sysfs issue that occurred when accessing hardware counters from within a namespace.
    • "ibstat" would fail and crash when encountering a non-RoCE/IB device, preventing it from displaying information for the remaining valid RoCE/IB devices.
    • Bandwidth degradation in cases of high number of QPs, where polling only 16 CQEs per iteration may not be sufficient to process all completions in time.
    • A race condition between firmware syndrome report and driver initialization during boot.
    • The driver failed to load when a firmware syndrome was detected during boot.
    • The mlnx_tune -l command did not list several operating systems that were in fact supported.
    • The kernel did not define TCA_TUNNEL_KEY_ENC_SRC_PORT. To align offload behavior with non-offload, the OVS community introduced a commit ( netdev-offload-tc: Fix offload of tunnel key tp_src) that causes offload to fail if this tunnel attribute is used. Now, any rule with a tunnel set action that includes a tunnel source port can no longer be offloaded.
    • LLDP traffic from VFs or BF host PFs was not reaching the representor kernel interfaces.
    • Flows where both the inner and outer destination (dst) and/or source (src) MAC addresses were rewritten to the same value, the outer MAC address rewrite was ignored, leading to an outer MAC address of 00:00:00:00:00:00.
    • Enabling sFlow with OVN caused OVS to crash.
    • OVS crashed unexpectedly after DPUs repeatedly broadcast the error message “packet with own source address.”
    • Changing the hw-offload setting from true to false while ports were configured led to errors reported in the OVS log.
    ]]>         Instead of using sed command, using awk command to fetch the right column name

    ]]>         Instead of using sed command, using awk command to fetch the right column name

    ]]>         Updated the PCIe DeEmphasis setting for specific front OCP cases on the DL380 Gen12.

    ]]>         Important Notes:

    This version of the System ROM contains updates aligned with GNR/SRF UPLR1.5 updates.

    Details about reported security vulnerabilities and their mitigation can be found at the following link Security Bulletin Library | HPE Support.

    Firmware Dependencies:

    None

    Problems Fixed:

    Addressed an issue where system might not be able to perform PXE boot when 400G NICs are installed.

    Addressed an issue where the setting change of "UPI Link Enablement" under "System Utilities > System Configuration > RBSU > Power and Performance Options > Intel UPI Options" might not take effect.

    Addressed an issue where the setting change of "UPI Link Power Management" under "System Utilities > System Configuration > RBSU > Power and Performance Options > Intel UPI Options" might not take effect.

    Addressed an issue where the system might not boot up when 10x RTX6000 Pro GPU cards are installed (DL380a).

    Addressed an issue where the ACPI BERT table could not be exported by UEFI/ROM.

    Addressed an issue where the setting change of "PCIe ASPM Support" under "System Utilities > System Configuration > RBSU > PCIe Device Configuration > Advanced PCIe Configuration > PCIe ASPM Support (Global)" might not take effect.

    Addressed an issue where the system might have PCR value change be reported after system reboot.

    Addressed an issue where the system TPM-0 measurements might change after system reboot.

    Addressed an issue where the system Redfish URI might be removed after performing delete action through redfish API but failed.

    Addressed an issue where the system with 2x6980P processors might encounter processor cores missing from RBSU and OS. (U66)

    Addressed an issue where the system might list some null string under "Utilities> System Information> PCIe Device Information" when MR932i-p is installed.

    Addressed an issue where the system with VROC enabled might get reboot when drives were Hot-Added.

    Known Issues:

    None]]>         Updated the default Secure Boot DBX.

    Optimized the UEFI Memory Map to reduce memory fragmentation distribution.

    Greyed out the Page Table Entry Speculative Lock Scheduling knob under RBSU->System Options->Processor Options->Page Table Entry Speculative Lock Scheduling since it can only be enabled.

    ]]>         Important Notes:

    This version of the System ROM contains updates aligned with Intel GNR/SRF UPLR1 BKC update.

    Details about reported security vulnerabilities and their mitigation can be found at the following link Security Bulletin Library | HPE Support.

    Firmware Dependencies:

    None

    Problems Fixed:

    Addressed an issue where unsupported property (IntelProcVtd) might be listed under (/redfish/v1/systems/1/bios/) accidentally.

    Addressed an issue where system might spend a long time in the "Early Processor Initialization" step after power-on.

    Known Issues:

    None]]>         Updated the PCIe DeEmphasis setting for specific front OCP cases on the DL380 Gen12.

    ]]>         Important Notes:

    This version of the System ROM contains updates aligned with GNR/SRF UPLR1.5 updates.

    Details about reported security vulnerabilities and their mitigation can be found at the following link Security Bulletin Library | HPE Support.

    Firmware Dependencies:

    None

    Problems Fixed:

    Addressed an issue where system might not be able to perform PXE boot when 400G NICs are installed.

    Addressed an issue where the setting change of "UPI Link Enablement" under "System Utilities > System Configuration > RBSU > Power and Performance Options > Intel UPI Options" might not take effect.

    Addressed an issue where the setting change of "UPI Link Power Management" under "System Utilities > System Configuration > RBSU > Power and Performance Options > Intel UPI Options" might not take effect.

    Addressed an issue where the system might not boot up when 10x RTX6000 Pro GPU cards are installed (DL380a).

    Addressed an issue where the ACPI BERT table could not be exported by UEFI/ROM.

    Addressed an issue where the setting change of "PCIe ASPM Support" under "System Utilities > System Configuration > RBSU > PCIe Device Configuration > Advanced PCIe Configuration > PCIe ASPM Support (Global)" might not take effect.

    Addressed an issue where the system might have PCR value change be reported after system reboot.

    Addressed an issue where the system TPM-0 measurements might change after system reboot.

    Addressed an issue where the system Redfish URI might be removed after performing delete action through redfish API but failed.

    Addressed an issue where the system with 2x6980P processors might encounter processor cores missing from RBSU and OS. (U66)

    Addressed an issue where the system might list some null string under "Utilities> System Information> PCIe Device Information" when MR932i-p is installed.

    Addressed an issue where the system with VROC enabled might get reboot when drives were Hot-Added.

    Known Issues:

    None]]>         Updated the default Secure Boot DBX.

    Optimized the UEFI Memory Map to reduce memory fragmentation distribution.

    Greyed out the Page Table Entry Speculative Lock Scheduling knob under RBSU->System Options->Processor Options->Page Table Entry Speculative Lock Scheduling since it can only be enabled.

    ]]>         Important Notes:

    This version of the System ROM contains updates aligned with Intel GNR/SRF UPLR1 BKC update.

    Details about reported security vulnerabilities and their mitigation can be found at the following link Security Bulletin Library | HPE Support.

    Firmware Dependencies:

    None

    Problems Fixed:

    Addressed an issue where unsupported property (IntelProcVtd) might be listed under (/redfish/v1/systems/1/bios/) accidentally.

    Addressed an issue where system might spend a long time in the "Early Processor Initialization" step after power-on.

    Known Issues:

    None]]>         Updated to driver version 14.4.624.0

    The raw driver files can be obtained by extracting the Smart Component and then extracting the Emulex installer.  Use this command:

        elxdrvr-fc-version.exe /q2 extract=2

    The extracted files are located:

        C:\Users\Administrator\Documents\Emulex\Drivers\FC-version

    Each kit folder has subsequent architecture folders with subsequent OS folders.  For example,

        C:\Users\Administrator\Documents\Emulex\Drivers\FC-version\x64\win2022

    ]]>         Updated to driver version 14.4.393.20

    The raw driver files can be obtained by extracting the Smart Component and then extracting the Emulex installer.  Use this command:

        elxdrvr-fc-version.exe /q2 extract=2

    The extracted files are located:

        C:\Users\Administrator\Documents\Emulex\Drivers\FC-version

    Each kit folder has subsequent architecture folders with subsequent OS folders.  For example,

        C:\Users\Administrator\Documents\Emulex\Drivers\FC-version\x64\win2022

    ]]>         Updated to version 9.4.11.20

    ]]>         TBD

    ]]>
  • Regular FW maintenance release for sanitize, DRAM and log page fix.
    • ]]>
  • Fix for PCIe link length drop in AMD x2 system configuration
  • Fix for drive detection after hot re-insert on Windows
  • Fix for other regular FW patch release
    • ]]>
  • This maintenance revision improves data integrity.  The risk of not upgrading to this firmware is the increased possibility of data corruption in certain error and timing conditions.
    • ]]>
  • This product enhanced traffic flow in queue map rebalance.
  • This product enhanced  media type detection over PHY logic.
    • ]]>         This product fixed the system event logging.

    ]]>
  • This product enhanced traffic flow in queue map rebalance.
  • This product enhanced  media type detection over PHY logic.
    • ]]>         This product fixed the system event logging.

    ]]>         Initial version

    ]]>         Added SLES16 support

    ]]>
  • Added RHEL10 support
    • ]]>
  • Fix a00145710en_us: HPE MR Gen11 and Gen10 Plus Storage Controllers - Purple Screen of Death (PSOD) May Be Observed When Updating Controller Firmware Via Service Pack for ProLiant (SPP) in Remote Deployment Mode With a VMware ESXi OS
    • ]]>
  • Fix a00145710en_us: HPE MR Gen11 and Gen10 Plus Storage Controllers - Purple Screen of Death (PSOD) May Be Observed When Updating Controller Firmware Via Service Pack for ProLiant (SPP) in Remote Deployment Mode With a VMware ESXi OS
    • ]]>         SR 2.10.0/SR 3.5.0 RC

    ]]>         SR 2.9.2 patch 1

    ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>
  • This maintenance revision improves data integrity.  The risk of not upgrading to this firmware is the increased possibility of data corruption in certain error and timing conditions..
    • ]]>         TBD

    ]]>
  • This product fixes the issue where ESXi Datastore not seen when NPAR is enabled.
  • This product fixes the issue where PSOD is seen when enable NPAR using 2 NICs.
    • ]]>
  • DMTF PLDM Redfish Device Enablement enhancements
    • Redfish Volume Transformation Support
      • POST #Volume.ChangeRAIDLayout: RAID Layout Change. Change in the RAID Layout is achieved by providing the target RAIDType and the list of the drives in the input JSON body.
      • POST #Volume.ChangeRAIDLayout: Resize. ChangeRAIDLayout can be used to resize the volume by adding new Unconfigured Good drives without changing the RAIDType. In such cases RAIDType must not be provided in the input JSON body but the full drive list must be provided accordingly.
      • PATCH Volume[CapacityBytes]: This operation is used for resizing the volume when there is unused size available in the volume. There is no scope for adding any new drives here
      • POST #Volume.CheckConsistency: This operation starts Consistency Check operation on the volume. No input is expected for this operation.
    • Redfish Metrics GET Support
      • StorageControllerMetrics: UncorrectableECCErrorCount, CorrectableECCErrorCount, CorrectableParityErrorCount, StateChangeCount
      • PortMetrics: SAS.InvalidDwordCount, SAS.LossOfDwordSynchronizationCount, SAS.RunningDisparityErrorCount, PCIeErrors.CorrectableErrorCount, PCIeErrors.FatalErrorCount, PCIeErrors.NonFatalErrorCount
      • Each counter can hold a value up to 65535. Once the counter reaches the maximum value the value is not reset.
      • Metrics are cleared when user performs Controller NVRAM clear or Redfish ResetToDefaults.ResetAll.
  • Add support for users to clear NVRAM using MRSA and storcli Factory Repurpose operation.
    • Clear NVRAM operation is not allowed if there is any configuration present on the controller or if there is any pinned cache.
    • After clearing NVRAM, controller FW performs Online Controller Reset (OCR). If for some reason OCR cannot be performed, then the user will be notified to perform a system reboot.
    • The Clear NVRAM operation is equivalent to Redfish ResetToDefaults.ResetAll operation functionally.
  • Change the backplane bay count information to the actual bay that is connected to controller. For non-hotplug configuration, controller always shows 16 bays.
    • ]]>
  • Fix a00143124en_us Advisory: HPE MR Gen11 Controller - MR Gen11 Controllers on HPE Gen11 Servers May Fail to Generate "WriteCacheDataLoss" in the IML
  • Fix a00148035en_us Advisory: HPE MR Gen11 Controllers - The Bay And Box NVMe Drive Location Is Not Displayed in the One-Time Boot Menu
  • Fix an issue that Read/Write transfers over 128KB on LTO fail in Linux OS
  • Fix an issue that Backup Exec doesn’t work with LTO
  • Fix an issue that controller might be dropped by the iLO in server boot up when there are 240 Logical Drives are configured
  • Fix a rare issue that server health shows critical temporally when remove drive continuously.
  • Fix an issue that unexpected PCIConfiglink page events, Task management to the virtual SES device time out messages are logged in snapdump
  • Fix an issue that Slot capable protocol is missing for empty bay
  • Fix an issue that Link Speed for LTO connected to controller shows Unknown
  • Fix an issue that Request Sense command causes task management on the drive where sanitization is in progress.
  • Fix an issue that Redfish PATCH StorageController[ControllerRates] silently sets random values when the value beyond 255 is used.
  • Fix an issue that incorrect controller error event may be logged when controller is configured as passthrough and do vm reboot
  • Fix an issue that active width, current speed are wrong in Redfish Fabric port when two backplanes connected to same storage port.
  • Fix a rare issue that NVMe drive link status may fail after reboot 
  • Fix a rare issue that controller may assert when there are multiple drives removed and inserted in a short time
  • Fix an issue that sanitize percentage does not progress on SATA drives if there is SATA passthrough command running
  • Fix an issue that sanitize percentage does not progress on NVMe drives
  • Fix a rare issue that IO timeout and device reset may occur with stress test of Read/Write and Non-Read/Write commands
    • ]]>
  • DMTF PLDM Redfish Device Enablement enhancements
    • Redfish Volume Transformation Support
      • POST #Volume.ChangeRAIDLayout: RAID Layout Change. Change in the RAID Layout is achieved by providing the target RAIDType and the list of the drives in the input JSON body.
      • POST #Volume.ChangeRAIDLayout: Resize. ChangeRAIDLayout can be used to resize the volume by adding new Unconfigured Good drives without changing the RAIDType. In such cases RAIDType must not be provided in the input JSON body but the full drive list must be provided accordingly.
      • PATCH Volume[CapacityBytes]: This operation is used for resizing the volume when there is unused size available in the volume. There is no scope for adding any new drives here
      • POST #Volume.CheckConsistency: This operation starts Consistency Check operation on the volume. No input is expected for this operation.
    • Redfish Metrics GET Support
      • StorageControllerMetrics: UncorrectableECCErrorCount, CorrectableECCErrorCount, CorrectableParityErrorCount, StateChangeCount
      • PortMetrics: SAS.InvalidDwordCount, SAS.LossOfDwordSynchronizationCount, SAS.RunningDisparityErrorCount, PCIeErrors.CorrectableErrorCount, PCIeErrors.FatalErrorCount, PCIeErrors.NonFatalErrorCount
      • Each counter can hold a value up to 65535. Once the counter reaches the maximum value the value is not reset.
      • Metrics are cleared when user performs Controller NVRAM clear or Redfish ResetToDefaults.ResetAll.
  • Add support for users to clear NVRAM using MRSA and storcli Factory Repurpose operation.
    • Clear NVRAM operation is not allowed if there is any configuration present on the controller or if there is any pinned cache.
    • After clearing NVRAM, controller FW performs Online Controller Reset (OCR). If for some reason OCR cannot be performed, then the user will be notified to perform a system reboot.
    • The Clear NVRAM operation is equivalent to Redfish ResetToDefaults.ResetAll operation functionally.
  • Change the backplane bay count information to the actual bay that is connected to controller. For non-hotplug configuration, controller always shows 16 bays.
    • ]]>
  • Fix a00143124en_us Advisory: HPE MR Gen11 Controller - MR Gen11 Controllers on HPE Gen11 Servers May Fail to Generate "WriteCacheDataLoss" in the IML
  • Fix a00148035en_us Advisory: HPE MR Gen11 Controllers - The Bay And Box NVMe Drive Location Is Not Displayed in the One-Time Boot Menu
  • Fix an issue that Read/Write transfers over 128KB on LTO fail in Linux OS
  • Fix an issue that Backup Exec doesn’t work with LTO
  • Fix an issue that controller might be dropped by the iLO in server boot up when there are 240 Logical Drives are configured
  • Fix a rare issue that server health shows critical temporally when remove drive continuously.
  • Fix an issue that unexpected PCIConfiglink page events, Task management to the virtual SES device time out messages are logged in snapdump
  • Fix an issue that Slot capable protocol is missing for empty bay
  • Fix an issue that Link Speed for LTO connected to controller shows Unknown
  • Fix an issue that Request Sense command causes task management on the drive where sanitization is in progress.
  • Fix an issue that Redfish PATCH StorageController[ControllerRates] silently sets random values when the value beyond 255 is used.
  • Fix an issue that incorrect controller error event may be logged when controller is configured as passthrough and do vm reboot
  • Fix an issue that active width, current speed are wrong in Redfish Fabric port when two backplanes connected to same storage port.
  • Fix a rare issue that NVMe drive link status may fail after reboot 
  • Fix a rare issue that controller may assert when there are multiple drives removed and inserted in a short time
  • Fix an issue that sanitize percentage does not progress on SATA drives if there is SATA passthrough command running
  • Fix an issue that sanitize percentage does not progress on NVMe drives
  • Fix a rare issue that IO timeout and device reset may occur with stress test of Read/Write and Non-Read/Write commands
    • ]]>         New features and changes included in version 28.46.3048:

    • This release contains important reliability improvements and security hardening enhancements. HPE recommends upgrading your devices firmware to this release to improve the devices’ firmware security and reliability.
    ]]>         The following fixes have been included in version 28.46.3048:

    • The adapter card would drop NC-SI over MCTP commands when padding bytes were present after the NC-SI checksum.
    ]]>         New features and changes included in version 28.45.1200:

    • Introduced a 1ms delay for SPDM responses.
    ]]>         The following fixes have been included in version 28.45.1200:

    • Fixed DC InfiniBand functionality.
    ]]>         Added support for:

    Red Hat Enterprise Linux 9.7

    Updated to version 14.4.731.6

    ]]>         Added support for:

    Red Hat Enterprise Linux 10.0

    Updated to version 14.4.473.24

    ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>
  • This fix is for unrecovered errors may occur on the targeted Blocks of Wear-leveling process when host issues Read command.
    • ]]>         TBD

    ]]>         This product fixes where MBA configuration reset to defaults after updating firmware.

    ]]>         See the iSUT Release Notes for information about the issues resolved in this release

    ]]>         See the iSUT Release Notes for information about the issues resolved in this release

    ]]>
  • This is a maintenance release that contains code fix improvements and drive function enhancements. Upgrading from HPK1 to HPK2 requires power cycle.
    • ]]>         TBD

    ]]>
  • This product fixes an issue where the Port Reset attributes are missing under RDE port Schema.
  • This product fixes an issue where the link failed with the LCP-1250RJ3SR-KH transceiver.
  • This product fixes an issue where the FW PLDM upgrade may failed with CVL4.71 when MCTP traffic loading is heavy.
  • This product fixes an issue where the BSOD observed in Windows OS with OOB driver when transmit balancing is enabled in NIC HII menu.
    • ]]>         TBD

    ]]>         This product fixes where MBA configuration reset to defaults after updating firmware.

    ]]>         Initial version.

    ]]>         TBD

    ]]>         Initial release to support Red Hat Enterprise Linux 10.

    ]]>         Updated the PCIe DeEmphasis setting for specific front OCP cases on the DL380 Gen12.

    ]]>         Important Notes:

    This version of the System ROM contains updates aligned with GNR/SRF UPLR1.5 updates.

    Details about reported security vulnerabilities and their mitigation can be found at the following link Security Bulletin Library | HPE Support.

    Firmware Dependencies:

    None

    Problems Fixed:

    Addressed an issue preventing PXE boot functionality when 400G NIC cards are present in the system

    Addressed an issue where the setting change of "UPI Link Enablement" under "System Utilities > System Configuration > RBSU > Power and Performance Options > Intel UPI Options" may not have been applied successfully.

    Addressed an issue where the setting change of "UPI Link Power Management" under "System Utilities > System Configuration > RBSU > Power and Performance Options > Intel UPI Options" may not have been properly applied.

    Addressed an issue that could prevent system boot when 10x RTX6000 Pro GPU cards are installed (DL380a).

    Addressed an issue where the ACPI BERT table was not exportable via UEFI/ROM.

    Addressed an issue where the setting change of "PCIe ASPM Support" under "System Utilities > System Configuration > RBSU > PCIe Device Configuration > Advanced PCIe Configuration > PCIe ASPM Support (Global)" may not have been properly applied.

    Addressed an issue where PCR values could be reported as changed following a system reboot.

    Addressed an issue where the system TPM-0 measurements might change after a system reboot.

    Addressed an issue where a failed delete operation via the Redfish API could inadvertently remove the system Redfish URI.

    Addressed an issue where systems configured with dual 6980P processors might not display all processor cores in RBSU or the OS. (U66)

    Addressed an issue where the system might list some null string under "Utilities> System Information> PCIe Device Information" when a MR932i-p is installed.

    Addressed an issue where the system with VROC enabled might reboot when drives were Hot-Added.

    Known Issues:

    None]]>         Updated the default Secure Boot DBX.

    Optimized the UEFI Memory Map to reduce memory fragmentation distribution.

    Greyed out the Page Table Entry Speculative Lock Scheduling knob under RBSU->System Options->Processor Options->Page Table Entry Speculative Lock Scheduling since it can only be enabled.

    ]]>         Important Notes:

    This version of the System ROM contains updates aligned with Intel GNR/SRF UPLR1 BKC update.

    Details about reported security vulnerabilities and their mitigation can be found at the following link Security Bulletin Library | HPE Support.

    Firmware Dependencies:

    None

    Problems Fixed:

    Addressed an issue where unsupported property (IntelProcVtd) might be listed under (/redfish/v1/systems/1/bios/) accidentally.

    Addressed an issue where system might spend a long time in the "Early Processor Initialization" step after power-on.

    Known Issues:

    None]]>         This product enhancement enables a self-shutdown feature to prevent overheating when certain monitoring features are disabled. 
    It applies only to newer hardware that originally shipped with firmware version 223.1.135.7 or higher and is not enabled on earlier revisions.

    ]]>
  • This product fixes the issue where the firmware version details failed to update and the card showed as not operational after upgrading BCM5741x adapters 
  • This product fixes the issue where failed to detect a 10GBASE-LR SFP+ causing incorrect defaults and a link failure.
  • This product fixes the issue where iLO BMC shared  IP on OCP NIC, link flap occurred during OS reboot.
  • This product fixes the issue where the adapter is unable to establish link after rebooting when using the “HPE 10GBASE-T SFP+ 30m RJ45 Transceiver” HPE PN 813874-B21 with vendor PN SP7053-HPE.
    • ]]>         This product enhancement enables a self-shutdown feature to prevent overheating when certain monitoring features are disabled. 
    It applies only to newer hardware that originally shipped with firmware version 223.1.135.7 or higher and is not enabled on earlier revisions.

    ]]>
  • This product fixes the issue where the firmware version details failed to update and the card showed as not operational after upgrading BCM5741x adapters 
  • This product fixes the issue where failed to detect a 10GBASE-LR SFP+ causing incorrect defaults and a link failure.
  • This product fixes the issue where iLO BMC shared  IP on OCP NIC, link flap occurred during OS reboot.
    • ]]>
  • Changes and improvements made in HPK1 are to enhance receiver signals by changing the drive’s internal PHY register values on Gen11 x2 direct attached system.
    • ]]>
  • Changes and improvements made in HPK1 are to enhance receiver signals by changing the drive’s internal PHY register values on Gen11 x2 direct attached system.
    • ]]>
  • This firmware provides bug fixes for the P5620/P5520.
    • ]]>         SR 2.10.0/SR 3.5.0 RC

    ]]>
  • Improve the tolerance of error handling.
  • Enhancement of DMA engine attributes to prevent PSOD.
    • ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>         This product fixes an issue where the VM traffic may not working when VF driver disabled or not installed.

    ]]>         This product fixes an issue where the VM traffic may not working when VF driver disabled or not installed.

    ]]>
  • Change the backplane bay count information to the actual bay that is connected to controller.
  • Add support for users to clear NVRAM using Factory Repurpose operation
  • Re-order MRSA GUI buttons
    • Move the Rebuild button to the top before Make Online button
    • Add the Rebuild button in the Offline Drive warning session
  • Change the recommended action for Degarded Volume to “Make sure all the participating drives are connected and rebuild is complete”.
    • ]]>
  • Fix MRSA issue in a00150411en_us Advisory: HPE Compute MR Controllers - HPE MR Storage Administrator (MRSA) Launch Issue and Storage Command Line Interface (StorCLI) Installation Warning Message Observed With Red Hat Enterprise Linux Server 10
    • ]]>
  • Change the backplane bay count information to the actual bay that is connected to controller.
  • Add support for users to clear NVRAM using Factory Repurpose operation
  • Re-order LSA GUI buttons
    • Move the Rebuild button to the top before Make Online button
    • Add the Rebuild button in the Offline Drive warning session
  • Change the recommended action for Degarded Volume to “Make sure all the participating drives are connected and rebuild is complete”.
    • ]]>
  • Fix MRSA issue in a00150411en_us Advisory: HPE Compute MR Controllers - HPE MR Storage Administrator (MRSA) Launch Issue and Storage Command Line Interface (StorCLI) Installation Warning Message Observed With Red Hat Enterprise Linux Server 10
    • ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>         Added SLES16 support

    ]]>
  • Added RHEL10 support
    • ]]>         TBD

    ]]>         Initial version.

    ]]>         The following new features and changes have been included in version 25.07-0.9.7.1:
     

    • Hardware Steering (HWS): Enabled HWS as a secondary option for the device steering mode. If Software Steering (SWS) is not supported, HWS will be used by default, assuming it is available. Firmware Steering (FW) will now serve as the default only when both SWS and HWS are unsupported.

    • Hardware-Managed Flow Steering (HMFS): HMFS is a new approach to managing steering rules, where STEs are written to the ICM by hardware instead of software (as in software-managed steering). This enables a higher rate of rule insertion.

    • Queue Affinity Bonding: Added support for 4-port bonding to allow users to add both p0 and p1 to a bond without requiring SSH access to the host or bringing down the driver beforehand.

    • Multiple Doorbells per PF: Increased the number of doorbells from 1 to 8, distributing them in a round-robin manner across channel send and receive queues. This enhancement improves scalability on multi-core systems with high packet rates by reducing MMIO contention on doorbell addresses. In high packet-rate scenarios, Sub-NUMA Clustering is also required to maintain consistent channel packet rates.

    • HQoS for Virtualization Solution: Added support for hierarchical group structures to enable multi-tier resource control, where parent groups enforce overall limits and child groups dynamically share available bandwidth. This design is essential for effective QoS enforcement, burst handling, and fair bandwidth allocation, ensuring workloads receive appropriate resources.

    • Number of lanes Configuration when Auto-Negotiation is Disabled: Added support for specifying the number of lanes (protocol width) when auto-negotiation is disabled. Since each combination of speed and lane count corresponds to a unique link mode, this allows the user to select a specific link mode when auto-negotiation is off. This change aligns with a recent firmware update that requires the driver to provide a single link mode, rather than a bitmap based on the user-defined speed.

    • Extend ODP Statistics with Operation Count: Added the following new page-granularity counters:
      • num_page_faults: counts the number of page fault events handled
      • num_invalidations: counts the number of page invalidation events handled
    ]]>         The following issues have been fixed in version  25.07-0.9.7.1:

    • OFED installation caused CIFS to break in RHEL 8.4 and above. A dummy module was added so that CIFS will be disabled after OFED installation in RHEL 8.4 and above.
    • Performance degradation on older kernel versions using RX cache, particularly on slower ARM CPUs with larger RX buffers. The issue was caused by the driver attempting to allocate new RX pages too quickly, leading to head-of-line blocking in the RX cache. The fix improves RX cache usage by triggering page allocation for a bulk of at least 2 WQEs, allowing the application more time to process packets and return buffers to the RX cache, thereby reducing blocking and enhancing performance.
    • VF behavior was not aligned with /sys/class/net/<interface-name>/device/sriov_numvfs (silently ignore attempts to set the same number of VFs, and prevent changing the number of VFs until existing VFs are removed).
    • On BlueField-3 devices running linux-bluefield kernel versions 5.15.0-1050 or 5.15.0-1060, a kernel crash occurred due to a NULL pointer dereference in the cls_api network scheduler.
    ]]>         The following new features and changes have been included in version 25.04-0.6.1.1:

    • Trust Lockdown Health Syndrome: Added a new health syndrome for trust lockdown and expose the CRR bit in the health buffer. When the CRR bit is set, it indicates that the syndrome requires a cold reset for recovery.
    • A Single PTP Device per Hardware Clock: PHC is typically shared across multiple functions. Currently, the driver creates a separate PTP device for each network interface sharing the same PHC, resulting in redundancy and added complexity. To address this, a single PTP device is now created to represent the shared PHC when operating in real-time mode.
    • Log IB State Transitions: Enhanced visibility into IB device state transitions by adding log messages to the kernel log (dmesg). Each time an IB device changes state, a corresponding message will be logged. For example: "mlx5_0: Port: 1 Link DOWN".
    • Optional-counters Binding Support and New Packets/bytes Counters: Previously, optional counters were available only on a per-link basis. This release introduces the ability to bind optional counters to a specific counter object, enabling users to track optional counters across a specific QP group. Support is provided for both automatic and manual binding modes. In both cases, the optional counters that are bound to the QP are those currently configured on the link at the time of binding. Additionally, four new optional counters that track RDMA ingress and egress traffic are introduced: rdma_tx_bytes; rdma_tx_packets; rdma_rx_bytes; rdma_rx_packets. This functionality is exposed to users via the iproute2 package, which must be updated to support this feature.
    • User CAPability (UCAP) API: The User CAPability (UCAP) API introduces a mechanism for creating user contexts with specific firmware privileges. It offers fine-grained control over firmware features by exposing each capability as a character device with root-level read-write access. Root processes can grant users these privileges by allowing access to the corresponding character devices. When a user context is created using a UCAP file descriptor, it inherits the associated privileges. For mlx5, two UCAP character devices are provided, and any user context opened with at least one of them is treated as privileged. To guarantee the execution of privileged commands, non-privileged commands are restricted when a privileged user is active on the device.
    ]]>         The following issues have been fixed in version  25.04-0.6.1.1:

    • Buffer initialization became a performance bottleneck during the allocation of large buffers, typically when using a high number of QPs with large message sizes. The root cause was the inefficient use of rand(). This has been resolved by replacing it with a faster pseudo-random algorithm.
    • A potential deadlock that could occur during the handling of peer memory registration failures.
    • The following error occurred when switching to SwitchDev mode: "mlx5_core 0000:03:00.0: mlx5_cmd_out_err:835:(pid 24362): CREATE_FLOW_GROUP(0x933) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x4065f0), err(-22); mlx5_core 0000:03:00.0: E-Switch: Failed to create peer miss flow group err(-22)"
    • A sysfs issue that occurred when accessing hardware counters from within a namespace.
    • "ibstat" would fail and crash when encountering a non-RoCE/IB device, preventing it from displaying information for the remaining valid RoCE/IB devices.
    • Bandwidth degradation in cases of high number of QPs, where polling only 16 CQEs per iteration may not be sufficient to process all completions in time.
    • A race condition between firmware syndrome report and driver initialization during boot.
    • The driver failed to load when a firmware syndrome was detected during boot.
    • The mlnx_tune -l command did not list several operating systems that were in fact supported.
    • The kernel did not define TCA_TUNNEL_KEY_ENC_SRC_PORT. To align offload behavior with non-offload, the OVS community introduced a commit ( netdev-offload-tc: Fix offload of tunnel key tp_src) that causes offload to fail if this tunnel attribute is used. Now, any rule with a tunnel set action that includes a tunnel source port can no longer be offloaded.
    • LLDP traffic from VFs or BF host PFs was not reaching the representor kernel interfaces.
    • Flows where both the inner and outer destination (dst) and/or source (src) MAC addresses were rewritten to the same value, the outer MAC address rewrite was ignored, leading to an outer MAC address of 00:00:00:00:00:00.
    • Enabling sFlow with OVN caused OVS to crash.
    • OVS crashed unexpectedly after DPUs repeatedly broadcast the error message “packet with own source address.”
    • Changing the hw-offload setting from true to false while ports were configured led to errors reported in the OVS log.
    ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>         TBD

    ]]>
  • This product now adds support for E610 device.
  • This product now supports Red Hat Enterprise Linux 9.6.
    • ]]>         Known issue: Firmware OROM version displays incorrectly via "esxcli network nic get -n interface".

    ]]>
  • Firmware changes aligned for future FIPS code release and one assert fix.
    • ]]>
  • Fixes the logic bug in the media cache cleaning abort handling that caused the drive to choose and execute the R/W command before the Request Sense to prevent assert.
  • Adding other logging and FW enhancements.
    • ]]>         New features and changes included in version 28.46.3048:

    • This release contains important reliability improvements and security hardening enhancements. HPE recommends upgrading your devices firmware to this release to improve the devices’ firmware security and reliability.
    ]]>         The following fixes have been included in version 28.46.3048:

    • The adapter card would drop NC-SI over MCTP commands when padding bytes were present after the NC-SI checksum.
    ]]>         New features and changes included in version 28.45.1200:

    • Introduced a 1ms delay for SPDM responses.
    ]]>         The following fixes have been included in version 28.45.1200:

    • Fixed DC InfiniBand functionality.
    ]]>
  • Assert fixes, current firmware improvements and bug fixes.
    • ]]>
  • This product enhanced traffic flow in queue map rebalance.
  • This product enhanced  media type detection over PHY logic.
    • ]]>         This product fixed the system event logging.

    ]]>
  • This product enhanced traffic flow in queue map rebalance.
  • This product enhanced  media type detection over PHY logic.
    • ]]>         This product fixed the system event logging.

    ]]>
  • New release 6.50.13.0
    • ]]>
  • Added support for VMware ESXi 9.0 
    • ]]>
  • Fixed the “Parity Initialization Method” information displayed for non-parity RAID levels. 
  • Fixed an issue where users were unable to clear the controller’s configuration when a foreign volume was present. 
  • Fixed an issue where a foreign-owned SED drive was being listed for array creation. 
  • Fixed an issue where the last failure reason was not listing on physical drives. 
  • Fixed an issue where SSAScripting failed to create an encrypted volume while in express local mode. 
  • Fixed an issue where an error/warning message was not being generated correctly while expanding a RAID 1+0 volume. 
  • Fixed an issue where a duplicate entry for the physical drive was displayed. 
    • ]]>         Changes and improvements that have been made in the firmware HPK4 which disable MCTP over PCIe VDM over the previous firmware.

    ]]>         Changes and improvements that have been made in the firmware HPK4 which disable MCTP over PCIe VDM over the previous firmware.

    ]]>         TBD

    ]]>
  • This product fixes the issue where ESXi Datastore not seen when NPAR is enabled.
  • This product fixes the issue where PSOD is seen when enable NPAR using 2 NICs.

    •  

    ]]>         See the AMS Release Notes for information about the enhancements in this release.

    ]]>         See the AMS Release Notes for information about the issues resolved in this release

    ]]>         See the AMS Release Notes for information about the enhancements in this release.

    ]]>         See the AMS Release Notes for information about the issues resolved in this release

    ]]>         Updated Driver version 10.02.15.00-k1

    ]]>         Added Support For:

    Red Hat Enterprise Linux 10

    Updated Driver version 10.02.14.00-k1

    ]]>
  • Updated Supported Products
    • ]]>
  • Updated Supported Products
    • ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>         For SEP2025 SPP

    ]]>         This product added WoL support for Intel E610 OCP.

    ]]>
  • This product fixed system freeze during the E610 adapter disablement when maximum number of VFs is allocated.
  • This product fixed driver failed after booting installation media with updated driver via UEFI & Legacy.
    • ]]>         This product added WoL support for Intel E610 OCP.

    ]]>
  • This product fixed system freeze during the E610 adapter disablement when maximum number of VFs is allocated.
  • This product fixed driver failed after booting installation media with updated driver via UEFI & Legacy.
    • ]]>
  • Fix a00145710en_us: HPE MR Gen11 and Gen10 Plus Storage Controllers - Purple Screen of Death (PSOD) May Be Observed When Updating Controller Firmware Via Service Pack for ProLiant (SPP) in Remote Deployment Mode With a VMware ESXi OS
    • ]]>
  • Fix a00145710en_us: HPE MR Gen11 and Gen10 Plus Storage Controllers - Purple Screen of Death (PSOD) May Be Observed When Updating Controller Firmware Via Service Pack for ProLiant (SPP) in Remote Deployment Mode With a VMware ESXi OS
    • ]]>         Initial Build

    ]]>         Initial Build

    ]]>         • Corrected the NVMe SMART Data (Data Units Read and Unsafe Shutdowns) in AHS.
    • Ability to update H200 NVL PCIe Accelerator GPU and CEC firmware using HPE iLO.
    • Support of certificate management and enhanced measurements for SPDM devices on HPE ProLiant Gen 11 servers.
    • Ability to enable or disable fallback sensor using the HPE iLO interface.
    • Support for periodic and manually triggered sensor-based bezel air filter health monitoring in HPE ProLiant DL145 Gen11 Servers.
    • Ability of the HPE iLO GUI to list the link status info for RDE enabled NICs independent of OS and AMS.
    • Ability of HPE iLO encryption to support domain-based users and certificates.
    • Ability to update VRD firmware using HPE iLO.

    ]]>
  • Fixed an issue where trying to connect to COM, HPE iLO logged some unclear or encrypted endpoints in AHS for connection failures or success.
  • Fixed an issue where on issuing virtual media-related commands in an SSH session to retrieve the current status, the command failed and subsequently caused the SMASH CLP session to hang.
  • Fixed an issue with the backup_start event to protect the back up process from auxiliary power cycle interruptions. This fix includes the implementation of IML logging.
  • Fixed an issue with HPE iLO to display power supplies as per power supply type AC or DC.
  • Fixed an issue with timeout duration for CHIF/libhpsrv transfer cases.
  • Fixed an issue with COM firmware update.
    • ]]>         Important Notes:

    None

    Firmware Dependencies:

    None

    Enhancements/New Features:

    This is the initial version of the firmware.

    Known Issues:

    None]]>
  • HPK8 is a planned maintenance release that follows HPK5. This is a recommended FW release that provides bug fixes for the P5430 15.36T, 7.68T, 3.84T (4K IU) Solid State Drives.
    • ]]>
  • HPK5 is a planned maintenance release that follows HPK2. This is a recommended FW release that provides bug fixes for the  4K IU Solid State Drives.
  • Noted this FW change require a system power cycle after installation for it to take effect.
    • ]]>         Updated Driver version 10.02.15.00-k1

    ]]>         Added Support For:

    Red Hat Enterprise Linux 10

    Updated Driver version 10.02.14.00-k1

    ]]>
  • This maintenance revision improves data integrity.  The risk of not upgrading to this firmware is the increased possibility of data corruption in certain error and timing conditions.
    • ]]>
  • This maintenance revision improves data integrity.  The risk of not upgrading to this firmware is the increased possibility of data corruption in certain error and timing conditions.
  • For more information, refer to HPE Customer Advisory at the following URL: https://support.hpe.com/hpesc/public/docDisplay?docId=emr_na-a00138902en_us which will be active on 24-April-2024.
    • ]]>         TBD

    ]]>         This product fixes issue where link disconnected with the latest Out-of-Box (OOB) Driver.

    ]]>         SR 2.10.0/SR 3.5.0 RC

    ]]>
  • This Firmware version adds compatibility with the latest NAND generation for continuity of supply.
    • ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>
  • Updated Supported Environments
    • ]]>
  • Updated Supported Environments
    • ]]>
  • Improves data integrity. 
  • The risk of not upgrading to this firmware is the increased possibility of data corruption in certain error and timing conditions. 
  • Several maintenance items are included in this firmware revision that reduce the probability of hangs and provide a minor performance improvement.
    • ]]>
  • Firmware maintenance release of Samsung PM1743 NVMe SSD with HPK6
    • ]]>
  • Modify Power State modes (25/18/16/14W) which can be enabled as an option.
  • Improved on TTR requirement to fix device temporarily not found issue after hot-plug.
    • ]]>         New version.

    ]]>         Fixed Secure boot not enable.

    ]]>
  • Updated Supported Products
    • ]]>
  • Updated Supported Products
    • ]]>
  • This is a maintenance release that contains code improvements for CAP.TO and LED behavior.
    • ]]>          This is an initial FW.

    ]]>         TBD

    ]]>
  • This product fixes an issue where the Port Reset attributes are missing under RDE port Schema.
  • This product fixes an issue where the link failed with the LCP-1250RJ3SR-KH transceiver.
  • This product fixes an issue where the FW PLDM upgrade may failed with CVL4.71 when MCTP traffic loading is heavy.
  • This product fixes an issue where the BSOD observed in Windows OS with OOB driver when transmit balancing is enabled in NIC HII menu.
    • ]]>         For Sep SPP 2025

    ]]>
  • Added Write Cache Status field to the info page for physical drives when "pd all show detail" is used.
    • ]]>
  • Corrected wrong wording of Parity Initialization messages.
  • Fixed vulnerability CVE-2023-45853.
    • ]]>         Initial version.

    ]]>         Initial version from HPE.

     

    The following fixes have been included in version 40.46.3048:

    • Fix for the adapter card dropping NC-SI over MCTP commands when padding bytes were present after the NC-SI checksum. 
    ]]>         Initial version.

    ]]>         Initial version from HPE.

     

    The following fixes have been included in version 40.46.3048:

    • Fix for the adapter card dropping NC-SI over MCTP commands when padding bytes were present after the NC-SI checksum. 
    ]]>         Fix windows build tool expire issue
     

    ]]>
  • Change the backplane bay count information to the actual bay that is connected to controller.
  • Add support for users to clear NVRAM using Factory Repurpose operation
  • Re-order LSA GUI buttons
    • Move the Rebuild button to the top before Make Online button
    • Add the Rebuild button in the Offline Drive warning session
  • Change the recommended action for Degarded Volume to “Make sure all the participating drives are connected and rebuild is complete”.
    • ]]>         Added SLES16 support

    ]]>
  • Added RHEL10 support
    • ]]>
  • Updated Software Category
    • ]]>
  • Updated installer.dll
    • ]]>
  • Added Supported Platforms
    • ]]>         The following new features and changes have been included in version 25.07-0.9.7.1:
     

    • Hardware Steering (HWS): Enabled HWS as a secondary option for the device steering mode. If Software Steering (SWS) is not supported, HWS will be used by default, assuming it is available. Firmware Steering (FW) will now serve as the default only when both SWS and HWS are unsupported.

    • Hardware-Managed Flow Steering (HMFS): HMFS is a new approach to managing steering rules, where STEs are written to the ICM by hardware instead of software (as in software-managed steering). This enables a higher rate of rule insertion.

    • Queue Affinity Bonding: Added support for 4-port bonding to allow users to add both p0 and p1 to a bond without requiring SSH access to the host or bringing down the driver beforehand.

    • Multiple Doorbells per PF: Increased the number of doorbells from 1 to 8, distributing them in a round-robin manner across channel send and receive queues. This enhancement improves scalability on multi-core systems with high packet rates by reducing MMIO contention on doorbell addresses. In high packet-rate scenarios, Sub-NUMA Clustering is also required to maintain consistent channel packet rates.

    • HQoS for Virtualization Solution: Added support for hierarchical group structures to enable multi-tier resource control, where parent groups enforce overall limits and child groups dynamically share available bandwidth. This design is essential for effective QoS enforcement, burst handling, and fair bandwidth allocation, ensuring workloads receive appropriate resources.

    • Number of lanes Configuration when Auto-Negotiation is Disabled: Added support for specifying the number of lanes (protocol width) when auto-negotiation is disabled. Since each combination of speed and lane count corresponds to a unique link mode, this allows the user to select a specific link mode when auto-negotiation is off. This change aligns with a recent firmware update that requires the driver to provide a single link mode, rather than a bitmap based on the user-defined speed.

    • Extend ODP Statistics with Operation Count: Added the following new page-granularity counters:
      • num_page_faults: counts the number of page fault events handled
      • num_invalidations: counts the number of page invalidation events handled
    ]]>         The following issues have been fixed in version  25.07-0.9.7.1:

    • OFED installation caused CIFS to break in RHEL 8.4 and above. A dummy module was added so that CIFS will be disabled after OFED installation in RHEL 8.4 and above.
    • Performance degradation on older kernel versions using RX cache, particularly on slower ARM CPUs with larger RX buffers. The issue was caused by the driver attempting to allocate new RX pages too quickly, leading to head-of-line blocking in the RX cache. The fix improves RX cache usage by triggering page allocation for a bulk of at least 2 WQEs, allowing the application more time to process packets and return buffers to the RX cache, thereby reducing blocking and enhancing performance.
    • VF behavior was not aligned with /sys/class/net/<interface-name>/device/sriov_numvfs (silently ignore attempts to set the same number of VFs, and prevent changing the number of VFs until existing VFs are removed).
    • On BlueField-3 devices running linux-bluefield kernel versions 5.15.0-1050 or 5.15.0-1060, a kernel crash occurred due to a NULL pointer dereference in the cls_api network scheduler.
    ]]>         The following new features and changes have been included in version 25.04-0.6.1.1:

    • Trust Lockdown Health Syndrome: Added a new health syndrome for trust lockdown and expose the CRR bit in the health buffer. When the CRR bit is set, it indicates that the syndrome requires a cold reset for recovery.
    • A Single PTP Device per Hardware Clock: PHC is typically shared across multiple functions. Currently, the driver creates a separate PTP device for each network interface sharing the same PHC, resulting in redundancy and added complexity. To address this, a single PTP device is now created to represent the shared PHC when operating in real-time mode.
    • Log IB State Transitions: Enhanced visibility into IB device state transitions by adding log messages to the kernel log (dmesg). Each time an IB device changes state, a corresponding message will be logged. For example: "mlx5_0: Port: 1 Link DOWN".
    • Optional-counters Binding Support and New Packets/bytes Counters: Previously, optional counters were available only on a per-link basis. This release introduces the ability to bind optional counters to a specific counter object, enabling users to track optional counters across a specific QP group. Support is provided for both automatic and manual binding modes. In both cases, the optional counters that are bound to the QP are those currently configured on the link at the time of binding. Additionally, four new optional counters that track RDMA ingress and egress traffic are introduced: rdma_tx_bytes; rdma_tx_packets; rdma_rx_bytes; rdma_rx_packets. This functionality is exposed to users via the iproute2 package, which must be updated to support this feature.
    • User CAPability (UCAP) API: The User CAPability (UCAP) API introduces a mechanism for creating user contexts with specific firmware privileges. It offers fine-grained control over firmware features by exposing each capability as a character device with root-level read-write access. Root processes can grant users these privileges by allowing access to the corresponding character devices. When a user context is created using a UCAP file descriptor, it inherits the associated privileges. For mlx5, two UCAP character devices are provided, and any user context opened with at least one of them is treated as privileged. To guarantee the execution of privileged commands, non-privileged commands are restricted when a privileged user is active on the device.
    ]]>         The following issues have been fixed in version  25.04-0.6.1.1:

    • Buffer initialization became a performance bottleneck during the allocation of large buffers, typically when using a high number of QPs with large message sizes. The root cause was the inefficient use of rand(). This has been resolved by replacing it with a faster pseudo-random algorithm.
    • A potential deadlock that could occur during the handling of peer memory registration failures.
    • The following error occurred when switching to SwitchDev mode: "mlx5_core 0000:03:00.0: mlx5_cmd_out_err:835:(pid 24362): CREATE_FLOW_GROUP(0x933) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x4065f0), err(-22); mlx5_core 0000:03:00.0: E-Switch: Failed to create peer miss flow group err(-22)"
    • A sysfs issue that occurred when accessing hardware counters from within a namespace.
    • "ibstat" would fail and crash when encountering a non-RoCE/IB device, preventing it from displaying information for the remaining valid RoCE/IB devices.
    • Bandwidth degradation in cases of high number of QPs, where polling only 16 CQEs per iteration may not be sufficient to process all completions in time.
    • A race condition between firmware syndrome report and driver initialization during boot.
    • The driver failed to load when a firmware syndrome was detected during boot.
    • The mlnx_tune -l command did not list several operating systems that were in fact supported.
    • The kernel did not define TCA_TUNNEL_KEY_ENC_SRC_PORT. To align offload behavior with non-offload, the OVS community introduced a commit ( netdev-offload-tc: Fix offload of tunnel key tp_src) that causes offload to fail if this tunnel attribute is used. Now, any rule with a tunnel set action that includes a tunnel source port can no longer be offloaded.
    • LLDP traffic from VFs or BF host PFs was not reaching the representor kernel interfaces.
    • Flows where both the inner and outer destination (dst) and/or source (src) MAC addresses were rewritten to the same value, the outer MAC address rewrite was ignored, leading to an outer MAC address of 00:00:00:00:00:00.
    • Enabling sFlow with OVN caused OVS to crash.
    • OVS crashed unexpectedly after DPUs repeatedly broadcast the error message “packet with own source address.”
    • Changing the hw-offload setting from true to false while ports were configured led to errors reported in the OVS log.
    ]]>         This product fixed an issue where the Relaxed Ordering feature was incorrectly disabled when using firmware versions newer than XX.36.2024.

    ]]>         Added support for the DOCA Telemetry Library on Windows.

    ]]>
  • This product fixed an issue that could cause a BSOD during the suspend/resume process when the firmware is not functional.
  • This product fixed an issue where "Mlx5Cmd -Stat" displayed incorrect physical location information on multi-segment PCI machines when the adapter was disabled.
  • This product fixed an issue where Event 399 displayed incorrect information.
  • This product fixed an issue that triggered Error events 410 and 304 when enabling or disabling pktmon on an adapter operating in VMQ/SR-IOV mode.
    • ]]>
  • This is a planned maintenance release covering bug fixes. This firmware includes updates to improve PLI circuit reliability.
    • ]]>
  • HPG3 is a planned maintenance release covering bug fixes for 2.5” and M.2. There are no critical functional updates, and risk is low for customers who do not upgrade, especially if drives are not stored without power for a long period of time (~2 years).
    • ]]>         Initial version.

    ]]>         TBD

    ]]>         This product now supports Software Cross Timestamping feature for E810.

    ]]>         This product fixed an issue where the 'ethtool ethx' displayed 'AUI' with AOC cable, should display 'Fibre'.

    ]]>
  • Support windows 2022 and 2025 OS only.
    • ]]>
  • Fix windows tool cert expire issue.
     
    • ]]>
  • Fix windows tool cert expire issue.
     
    • ]]>         This product adds Automatic Link on Startup option under the NIC Configuration in HPE RBSU menu.

    ]]>
  • This product fixed PXE Boot does not work when MS secured-core enabled with HPE ProLiant Gen11 AMD platform server.
  • This product fixed Link Speed selection under NIC Configuration in HPE RBSU menu.
     
    • ]]>         This product adds Automatic Link on Startup option under the NIC Configuration in HPE RBSU menu.

    ]]>
  • This product fixed PXE Boot does not work when MS secured-core enabled with HPE ProLiant Gen11 AMD platform server.
  • This product fixed Link Speed selection under NIC Configuration in HPE RBSU menu.
     
    • ]]>         Updated to version 14.4.731.6

    ]]>         Added support for:

    Red Hat Enterprise Linux 10.0

    Updated to version 14.4.473.24

    ]]>
  • FW assert fix and other regular maintenance release.
    • ]]>         The following new features and changes have been included in version 25.07-0.9.7.1:
     

    • Hardware Steering (HWS): Enabled HWS as a secondary option for the device steering mode. If Software Steering (SWS) is not supported, HWS will be used by default, assuming it is available. Firmware Steering (FW) will now serve as the default only when both SWS and HWS are unsupported.

    • Hardware-Managed Flow Steering (HMFS): HMFS is a new approach to managing steering rules, where STEs are written to the ICM by hardware instead of software (as in software-managed steering). This enables a higher rate of rule insertion.

    • Queue Affinity Bonding: Added support for 4-port bonding to allow users to add both p0 and p1 to a bond without requiring SSH access to the host or bringing down the driver beforehand.

    • Multiple Doorbells per PF: Increased the number of doorbells from 1 to 8, distributing them in a round-robin manner across channel send and receive queues. This enhancement improves scalability on multi-core systems with high packet rates by reducing MMIO contention on doorbell addresses. In high packet-rate scenarios, Sub-NUMA Clustering is also required to maintain consistent channel packet rates.

    • HQoS for Virtualization Solution: Added support for hierarchical group structures to enable multi-tier resource control, where parent groups enforce overall limits and child groups dynamically share available bandwidth. This design is essential for effective QoS enforcement, burst handling, and fair bandwidth allocation, ensuring workloads receive appropriate resources.

    • Number of lanes Configuration when Auto-Negotiation is Disabled: Added support for specifying the number of lanes (protocol width) when auto-negotiation is disabled. Since each combination of speed and lane count corresponds to a unique link mode, this allows the user to select a specific link mode when auto-negotiation is off. This change aligns with a recent firmware update that requires the driver to provide a single link mode, rather than a bitmap based on the user-defined speed.

    • Extend ODP Statistics with Operation Count: Added the following new page-granularity counters:
      • num_page_faults: counts the number of page fault events handled
      • num_invalidations: counts the number of page invalidation events handled
    ]]>         The following issues have been fixed in version  25.07-0.9.7.1:

    • OFED installation caused CIFS to break in RHEL 8.4 and above. A dummy module was added so that CIFS will be disabled after OFED installation in RHEL 8.4 and above.
    • Performance degradation on older kernel versions using RX cache, particularly on slower ARM CPUs with larger RX buffers. The issue was caused by the driver attempting to allocate new RX pages too quickly, leading to head-of-line blocking in the RX cache. The fix improves RX cache usage by triggering page allocation for a bulk of at least 2 WQEs, allowing the application more time to process packets and return buffers to the RX cache, thereby reducing blocking and enhancing performance.
    • VF behavior was not aligned with /sys/class/net/<interface-name>/device/sriov_numvfs (silently ignore attempts to set the same number of VFs, and prevent changing the number of VFs until existing VFs are removed).
    • On BlueField-3 devices running linux-bluefield kernel versions 5.15.0-1050 or 5.15.0-1060, a kernel crash occurred due to a NULL pointer dereference in the cls_api network scheduler.
    ]]>         The following new features and changes have been included in version 25.04-0.6.1.1:

    • Trust Lockdown Health Syndrome: Added a new health syndrome for trust lockdown and expose the CRR bit in the health buffer. When the CRR bit is set, it indicates that the syndrome requires a cold reset for recovery.
    • A Single PTP Device per Hardware Clock: PHC is typically shared across multiple functions. Currently, the driver creates a separate PTP device for each network interface sharing the same PHC, resulting in redundancy and added complexity. To address this, a single PTP device is now created to represent the shared PHC when operating in real-time mode.
    • Log IB State Transitions: Enhanced visibility into IB device state transitions by adding log messages to the kernel log (dmesg). Each time an IB device changes state, a corresponding message will be logged. For example: "mlx5_0: Port: 1 Link DOWN".
    • Optional-counters Binding Support and New Packets/bytes Counters: Previously, optional counters were available only on a per-link basis. This release introduces the ability to bind optional counters to a specific counter object, enabling users to track optional counters across a specific QP group. Support is provided for both automatic and manual binding modes. In both cases, the optional counters that are bound to the QP are those currently configured on the link at the time of binding. Additionally, four new optional counters that track RDMA ingress and egress traffic are introduced: rdma_tx_bytes; rdma_tx_packets; rdma_rx_bytes; rdma_rx_packets. This functionality is exposed to users via the iproute2 package, which must be updated to support this feature.
    • User CAPability (UCAP) API: The User CAPability (UCAP) API introduces a mechanism for creating user contexts with specific firmware privileges. It offers fine-grained control over firmware features by exposing each capability as a character device with root-level read-write access. Root processes can grant users these privileges by allowing access to the corresponding character devices. When a user context is created using a UCAP file descriptor, it inherits the associated privileges. For mlx5, two UCAP character devices are provided, and any user context opened with at least one of them is treated as privileged. To guarantee the execution of privileged commands, non-privileged commands are restricted when a privileged user is active on the device.
    ]]>         The following issues have been fixed in version  25.04-0.6.1.1:

    • Buffer initialization became a performance bottleneck during the allocation of large buffers, typically when using a high number of QPs with large message sizes. The root cause was the inefficient use of rand(). This has been resolved by replacing it with a faster pseudo-random algorithm.
    • A potential deadlock that could occur during the handling of peer memory registration failures.
    • The following error occurred when switching to SwitchDev mode: "mlx5_core 0000:03:00.0: mlx5_cmd_out_err:835:(pid 24362): CREATE_FLOW_GROUP(0x933) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x4065f0), err(-22); mlx5_core 0000:03:00.0: E-Switch: Failed to create peer miss flow group err(-22)"
    • A sysfs issue that occurred when accessing hardware counters from within a namespace.
    • "ibstat" would fail and crash when encountering a non-RoCE/IB device, preventing it from displaying information for the remaining valid RoCE/IB devices.
    • Bandwidth degradation in cases of high number of QPs, where polling only 16 CQEs per iteration may not be sufficient to process all completions in time.
    • A race condition between firmware syndrome report and driver initialization during boot.
    • The driver failed to load when a firmware syndrome was detected during boot.
    • The mlnx_tune -l command did not list several operating systems that were in fact supported.
    • The kernel did not define TCA_TUNNEL_KEY_ENC_SRC_PORT. To align offload behavior with non-offload, the OVS community introduced a commit ( netdev-offload-tc: Fix offload of tunnel key tp_src) that causes offload to fail if this tunnel attribute is used. Now, any rule with a tunnel set action that includes a tunnel source port can no longer be offloaded.
    • LLDP traffic from VFs or BF host PFs was not reaching the representor kernel interfaces.
    • Flows where both the inner and outer destination (dst) and/or source (src) MAC addresses were rewritten to the same value, the outer MAC address rewrite was ignored, leading to an outer MAC address of 00:00:00:00:00:00.
    • Enabling sFlow with OVN caused OVS to crash.
    • OVS crashed unexpectedly after DPUs repeatedly broadcast the error message “packet with own source address.”
    • Changing the hw-offload setting from true to false while ports were configured led to errors reported in the OVS log.
    ]]>         TBD

    ]]>
  • This product fixes an issue where firmware updates failed when using the UEFI-FMP update method.
  • This product fixes an issue where the AssignablePhysicalNetworkPorts hyperlink under NetworkDeviceFunctions was not expanded correctly with Redfish expand queries.
  • This product fixes an issue where VLAN-tagged packets were looped back or misrouted due to VEB behavior, causing TCP retransmissions and link instability in LACP configurations.
  • This product fixes an issue where the adapter did not correctly report all supported link speeds (1G/10G/25G) via ethtool.
    • ]]>         Initial version

    ]]>         Important Notes:

    None

    Firmware Dependencies:

    None

    Enhancements/New Features:

    Enhanced the accuracy of power value displayed in iLO Web where the average power value should be equal to or below the power cap value.

    Known Issues:

    None

    ]]>
  • A Drive Firmware enhancement has been made for  Primera 600 products to reduce the probability of infrequent, unexpected power loss on some backed drives.
    • ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>
  • This maintenance revision improves data integrity.  The risk of not upgrading to this firmware is the increased possibility of data corruption in certain error and timing conditions.
    • ]]>         Updated to driver version 25.4.50020.0

    ]]>         Updated to driver version 24.10.26603.0

    ]]>         This product added WoL support for Intel E610 OCP.

    ]]>
  • This product fixed system freeze during the E610 adapter disablement when maximum number of VFs is allocated.
  • This product fixed driver failed after booting installation media with updated driver via UEFI & Legacy.
    • ]]>         This product added WoL support for Intel E610 OCP.

    ]]>
  • This product fixed system freeze during the E610 adapter disablement when maximum number of VFs is allocated.
  • This product fixed driver failed after booting installation media with updated driver via UEFI & Legacy.
    • ]]>         Added support for:

    SUSE Linux Enterprise Server 16

    Updated to version 14.4.731.6

    ]]>
  • Regular FW maintenance release.
    • ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>
  • Add support for users to clear NVRAM using Factory Repurpose operation
    • Command: storcli /cx set factory repurpose
    • ]]>
  • Add support for users to clear NVRAM using Factory Repurpose operation
    • Command: storcli /cx set factory repurpose
    • ]]>         TBD

    ]]>
  • This product enhances to create per PF worker thread to process Async events.
  • This product enhances to Improve driver init in kdump kernel.
  • This product enhances to handle FW recovery when bond mode is present.
    • ]]>
  • This product fixes issue where hwrm failure while running ethtool reset.
  • This product fixes issue where incorrect GSO type reporting in HW-GRO. (Generic Receive Offload)
    • ]]>         Updated the PCIe DeEmphasis setting for specific front OCP cases on the DL380 Gen12.

    ]]>         Important Notes:

    This version of the System ROM contains updates aligned with GNR/SRF UPLR1.5 updates.

    Details about reported security vulnerabilities and their mitigation can be found at the following link Security Bulletin Library | HPE Support.

    Firmware Dependencies:

    None

    Problems Fixed:

    Addressed an issue where system might not be able to perform PXE boot when 400G NICs are installed.

    Addressed an issue where the setting change of "UPI Link Enablement" under "System Utilities > System Configuration > RBSU > Power and Performance Options > Intel UPI Options" might not take effect.

    Addressed an issue where the setting change of "UPI Link Power Management" under "System Utilities > System Configuration > RBSU > Power and Performance Options > Intel UPI Options" might not take effect.

    Addressed an issue where the system might not boot up when 10x RTX6000 Pro GPU cards are installed (DL380a).

    Addressed an issue where the ACPI BERT table could not be exported by UEFI/ROM.

    Addressed an issue where the setting change of "PCIe ASPM Support" under "System Utilities > System Configuration > RBSU > PCIe Device Configuration > Advanced PCIe Configuration > PCIe ASPM Support (Global)" might not take effect.

    Addressed an issue where the system might have PCR value change be reported after system reboot.

    Addressed an issue where the system TPM-0 measurements might change after system reboot.

    Addressed an issue where the system Redfish URI might be removed after performing delete action through redfish API but failed.

    Addressed an issue where the system with 2x6980P processors might encounter processor cores missing from RBSU and OS. (U66)

    Addressed an issue where the system might list some null string under "Utilities> System Information> PCIe Device Information" when MR932i-p is installed.

    Addressed an issue where the system with VROC enabled might get reboot when drives were Hot-Added.

    Known Issues:

    None]]>         Updated the default Secure Boot DBX.

    Optimized the UEFI Memory Map to reduce memory fragmentation distribution.

    Greyed out the Page Table Entry Speculative Lock Scheduling knob under RBSU->System Options->Processor Options->Page Table Entry Speculative Lock Scheduling since it can only be enabled.

    ]]>         Important Notes:

    This version of the System ROM contains updates aligned with Intel GNR/SRF UPLR1 BKC update.

    Details about reported security vulnerabilities and their mitigation can be found at the following link Security Bulletin Library | HPE Support.

    Firmware Dependencies:

    None

    Problems Fixed:

    Addressed an issue where unsupported property (IntelProcVtd) might be listed under (/redfish/v1/systems/1/bios/) accidentally.

    Addressed an issue where system might spend a long time in the "Early Processor Initialization" step after power-on.

    Known Issues:

    None]]>         TBD

    ]]>
  • This product fixes an issue where firmware updates failed when using the UEFI-FMP update method.
  • This product fixes an issue where the AssignablePhysicalNetworkPorts hyperlink under NetworkDeviceFunctions was not expanded correctly with Redfish expand queries.
  • This product fixes an issue where VLAN-tagged packets were looped back or misrouted due to VEB behavior, causing TCP retransmissions and link instability in LACP configurations.
  • This product fixes an issue where the adapter did not correctly report all supported link speeds (1G/10G/25G) via ethtool.
    • ]]>
  • Updated Supported Environments
    • ]]>
  • Updated Supported Environments
    • ]]>
  • Regular FW maintenance release for sanitize, DRAM and log page fix.
    • ]]>
  • Fix for PCIe link length drop in AMD x2 system configuration
  • Fix for drive detection after hot re-insert on Windows
  • Fix for other regular FW patch release
    • ]]>         See the iSUT Release Notes for information about the issues resolved in this release

    ]]>         See the iSUT Release Notes for information about the issues resolved in this release

    ]]>         See the iSUT Release Notes for information about the issues resolved in this release

    ]]>         See the iSUT Release Notes for information about the issues resolved in this release

    ]]>
  • RSOD issue fixed. RSOD was occurred during server power-on if enable the VROC.
    • ]]>         TBD

    ]]>
  • This product enhances to create per PF worker thread to process Async events.
  • This product enhances to Improve driver init in kdump kernel.
  • This product enhances to handle FW recovery when bond mode is present.
    • ]]>
  • This product fixes issue where hwrm failure while running ethtool reset.
  • This product fixes issue where incorrect GSO type reporting in HW-GRO. (Generic Receive Offload)
    • ]]>         See the AMS Release Notes for information about the enhancements in this release.

    ]]>         See the AMS Release Notes for information about the issues resolved in this release.

    ]]>         See the AMS Release Notes for information about the enhancements in this release.

    ]]>         See the AMS Release Notes for information about the issues resolved in this release.

    ]]>         For SEP2025 SPP

    ]]>
  • This product enhances the Windows driver to support PCIe compliance configuration by enabling pass-through firmware commands with long input message sizes.
  • This product enhances adding new event log warning message.
    • ]]>
  • This product enhances to improve user mode RDMA abortive cleanup.
  • This product enhances FW logging to host to work across device reset.
    • ]]>
  • This product fixes issue where BSOD (Blue Screen of Death) occurs when install Windows Server 2025 OS on ISCSI LUN.
  • This product fixes issue where packet drops is seen when jumbo frame is enabled.
    • ]]>
  • Introduced Self-Encrypting Drive on P81162-B21 NS204i-u 960GB NVMe SED Boot Device
  • Support new Gen 12 servers.
    • ]]>
  • Fixed an issue that NS204i-u firmware information is not visible in UEFI when DMA remapping is enabled
  • Fixed an issue that NS204i-r is intermittently undetected on DX360 Gen10 Plus after continuous reboots
    • ]]>
  • Introduced Self-Encrypting Drive on P81162-B21 NS204i-u 960GB NVMe SED Boot Device
  • Support new Gen 12 servers.
    • ]]>
  • Fixed an issue that NS204i-u firmware information is not visible in UEFI when DMA remapping is enabled
  • Fixed an issue that NS204i-r is intermittently undetected on DX360 Gen10 Plus after continuous reboots
    • ]]>         New features and changes included in version 22.46.3048:

    • Added support for RSS with crypto offload enabling the NIC to parallelize packet processing across CPU cores while performing encryption/decryption in hardware. Additionally, introduced a new l4_type_ext parameter with values: 0 (None), 1 (TCP), 2 (UDP), 3 (ICMP).
    • Added an extra validation for the payload_len field in incoming NC-SI messages. Previously, invalid packets might have been accepted; now, such packets are silently dropped.
    • This release contains important reliability improvements and security hardening enhancements. HPE recommends upgrading your devices firmware to this release to improve the devices’ firmware security and reliability.
    ]]>         The following issues have been fixed in version 22.46.3048:

    • Configuring a small MTU led to fragmentation of packets critical for the PXE boot process. As a result, the PXE boot filters mistakenly discarded these packets, causing the PXE boot to fail.
    ]]>         Security Hardening Enhancements: This release contains important reliability improvements and security hardening enhancements. HPE recommends upgrading your device's firmware to this release to improve the firmware security and reliability of your device.

     

    No new features and changes have been included in version 22.45.1020.

    ]]>         The following issues have been fixed in version 22.45.1020:

    • PCC_CNP_COUNT could not be reset using the pcc_counter.sh script in the DOCA tools.
    • VQoS algorithm issue related to learning when an element is active and when it begins sending traffic.
    • A race condition that would prevent the application from transmitting when VQoS was enabled.
    • Bandwidth would drop when unbinding multiple VFs with VQoS enabled.
    • RTT packets with any destination MAC address were incorrectly treated as having a valid destination MAC. The new firmware now discards RTT packets if their destination MAC does not match the port's MAC.
    ]]>
  • Updated Supported Platform
    • ]]>
  • Updated Component Data
    • ]]>         TBD

    ]]>         This product fixes issue where link disconnected with the latest Out-of-Box (OOB) Driver.

    ]]>         Updated the PCIe DeEmphasis setting for specific front OCP cases on the DL380 Gen12.

    ]]>         Important Notes:

    This version of the System ROM contains updates aligned with GNR/SRF UPLR1.5 updates.

    Details about reported security vulnerabilities and their mitigation can be found at the following link Security Bulletin Library | HPE Support.

    Firmware Dependencies:

    None

    Problems Fixed:

    Addressed an issue where system might not be able to perform PXE boot when 400G NICs are installed.

    Addressed an issue where the setting change of "UPI Link Enablement" under "System Utilities > System Configuration > RBSU > Power and Performance Options > Intel UPI Options" might not take effect.

    Addressed an issue where the setting change of "UPI Link Power Management" under "System Utilities > System Configuration > RBSU > Power and Performance Options > Intel UPI Options" might not take effect.

    Addressed an issue where the system might not boot up when 10x RTX6000 Pro GPU cards are installed (DL380a).

    Addressed an issue where the ACPI BERT table could not be exported by UEFI/ROM.

    Addressed an issue where the setting change of "PCIe ASPM Support" under "System Utilities > System Configuration > RBSU > PCIe Device Configuration > Advanced PCIe Configuration > PCIe ASPM Support (Global)" might not take effect.

    Addressed an issue where the system might have PCR value change be reported after system reboot.

    Addressed an issue where the system TPM-0 measurements might change after system reboot.

    Addressed an issue where the system Redfish URI might be removed after performing delete action through redfish API but failed.

    Addressed an issue where the system with 2x6980P processors might encounter processor cores missing from RBSU and OS. (U66)

    Addressed an issue where the system might list some null string under "Utilities> System Information> PCIe Device Information" when MR932i-p is installed.

    Addressed an issue where the system with VROC enabled might get reboot when drives were Hot-Added.

    Known Issues:

    None]]>         Updated the default Secure Boot DBX.

    Optimized the UEFI Memory Map to reduce memory fragmentation distribution.

    Greyed out the Page Table Entry Speculative Lock Scheduling knob under RBSU->System Options->Processor Options->Page Table Entry Speculative Lock Scheduling since it can only be enabled.

    ]]>         Important Notes:

    This version of the System ROM contains updates aligned with Intel GNR/SRF UPLR1 BKC update.

    Details about reported security vulnerabilities and their mitigation can be found at the following link Security Bulletin Library | HPE Support.

    Firmware Dependencies:

    None

    Problems Fixed:

    Addressed an issue where unsupported property (IntelProcVtd) might be listed under (/redfish/v1/systems/1/bios/) accidentally.

    Addressed an issue where system might spend a long time in the "Early Processor Initialization" step after power-on.

    Known Issues:

    None]]>         This product enhances the handling of link status during D0  to D3 power domain transition.
     

    ]]>
  • This product fixes the issue where, in breakout mode, a cable remove or insert failed to bring the link up because the module did not exit the DPDeactivated (Data Path Deactivated) state in time.
  • This product fixes the issue where the adapter is unable to establish link after rebooting when using the “HPE 10GBASE-T SFP+ 30m RJ45 Transceiver” HPE PN 813874-B21 with vendor PN SP7053-HPE.
    • ]]>         This product enhances the handling of link status during D0  to D3 power domain transition.
     

    ]]>         This product fixes the issue where, in breakout mode, a cable remove or insert failed to bring the link up because the module did not exit the DPDeactivated (Data Path Deactivated) state in time.

    ]]>
  • This is a firmware maintenance release. It addresses a potential data loss issue, along with other bug fixes and improvements.
  • For more information, refer to HPE Customer Bulletin at the following URL: https://support.hpe.com/hpsc/doc/public/display?docId=a00150711en_us.
    • ]]>
  • This is a firmware maintenance release. It addresses a potential data loss issue, along with other bug fixes and improvements.
  • For more information, refer to HPE Customer Bulletin at the following URL: https://support.hpe.com/hpsc/doc/public/display?docId=a00150711en_us which will be active on 18-Aug-2025.
    • ]]>
  • FW HPK5 may cause Uncorrectable Machine Check Exception (UMCE) to occur. It is recommended to update FW to HPK6.
    • ]]>
  • Prioritize disabling Non-Fatal Error reporting at the beginning of FLR processing
  • Fix known FW bug PI/CI indexing issue
    • ]]>         See the AMS Release Notes for information about the enhancements in this release.

    ]]>         See the AMS Release Notes for information about the issues resolved in this release.

    ]]>         See the AMS Release Notes for information about the enhancements in this release.

    ]]>         See the AMS Release Notes for information about the issues resolved in this release.

    ]]>
  • Rebuilt using latest certificates for Windows installers
    • ]]>
  • Fixed the “Parity Initialization Method” information displayed for non-parity RAID levels. 
  • Fixed an issue where users were unable to clear the controller’s configuration when a foreign volume was present. 
  • Fixed an issue where a foreign-owned SED drive was being listed for array creation. 
    • ]]>         TBD

    ]]>         Initial release to support Red Hat Enterprise Linux 10.

    ]]>
  • Assert fixes, current firmware improvements and bug fixes
    • ]]>         Updated to version 14.4.731.6

    ]]>         Added support for:

    SuSE Linux Enterprise 15 SP 7

    Updated to version 14.4.473.26

    ]]>         TBD

    ]]>         TBD

    ]]>         Updated the PCIe DeEmphasis setting for specific front OCP cases on the DL380 Gen12.

    ]]>         Important Notes:

    This version of the System ROM contains updates aligned with GNR/SRF UPLR1.5 updates.

    Details about reported security vulnerabilities and their mitigation can be found at the following link Security Bulletin Library | HPE Support.

    Firmware Dependencies:

    None

    Problems Fixed:

    Addressed an issue where system might not be able to perform PXE boot when 400G NICs are installed.

    Addressed an issue where the setting change of "UPI Link Enablement" under "System Utilities > System Configuration > RBSU > Power and Performance Options > Intel UPI Options" might not take effect.

    Addressed an issue where the setting change of "UPI Link Power Management" under "System Utilities > System Configuration > RBSU > Power and Performance Options > Intel UPI Options" might not take effect.

    Addressed an issue where the system might not boot up when 10x RTX6000 Pro GPU cards are installed (DL380a).

    Addressed an issue where the ACPI BERT table could not be exported by UEFI/ROM.

    Addressed an issue where the setting change of "PCIe ASPM Support" under "System Utilities > System Configuration > RBSU > PCIe Device Configuration > Advanced PCIe Configuration > PCIe ASPM Support (Global)" might not take effect.

    Addressed an issue where the system might have PCR value change be reported after system reboot.

    Addressed an issue where the system TPM-0 measurements might change after system reboot.

    Addressed an issue where the system Redfish URI might be removed after performing delete action through redfish API but failed.

    Addressed an issue where the system with 2x6980P processors might encounter processor cores missing from RBSU and OS. (U66)

    Addressed an issue where the system might list some null string under "Utilities> System Information> PCIe Device Information" when MR932i-p is installed.

    Addressed an issue where the system with VROC enabled might get reboot when drives were Hot-Added.

    Known Issues:

    None]]>         Updated the default Secure Boot DBX.

    Optimized the UEFI Memory Map to reduce memory fragmentation distribution.

    Greyed out the Page Table Entry Speculative Lock Scheduling knob under RBSU->System Options->Processor Options->Page Table Entry Speculative Lock Scheduling since it can only be enabled.

    ]]>         Important Notes:

    This version of the System ROM contains updates aligned with Intel GNR/SRF UPLR1 BKC update.

    Details about reported security vulnerabilities and their mitigation can be found at the following link Security Bulletin Library | HPE Support.

    Firmware Dependencies:

    None

    Problems Fixed:

    Addressed an issue where unsupported property (IntelProcVtd) might be listed under (/redfish/v1/systems/1/bios/) accidentally.

    Addressed an issue where system might spend a long time in the "Early Processor Initialization" step after power-on.

    Known Issues:

    None]]>         TBD

    ]]>
  • This product fixes an issue where the Port Reset attributes are missing under RDE port Schema.
  • This product fixes an issue where the link failed with the LCP-1250RJ3SR-KH transceiver.
  • This product fixes an issue where the FW PLDM upgrade may failed with CVL4.71 when MCTP traffic loading is heavy.
  • This product fixes an issue where the BSOD observed in Windows OS with OOB driver when transmit balancing is enabled in NIC HII menu.
    • ]]>         Upgraded to version 22.45.1020

    ]]>         Upgraded to version 26.43.1014

    ]]>         Support new Gen12 servers.

    ]]>         Support both Gen10P and Gen11 servers

    ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>
  • This maintenance revision improves data integrity.  The risk of not upgrading to this firmware is the increased possibility of data corruption in certain error and timing conditions.

    •  

    ]]>
  • Updated Supported Environments
    • ]]>
  • Updated Supported Environments
    • ]]>
  • Firmware changes aligned for FIPS code release and one assert fix
    • ]]>         1.Fixes the logic bug in the media cache cleaning abort handling that caused the drive to choose and execute the R/W command before the Request Sense to prevent assert.
    2. Adding other logging and FW enhancements.

    ]]>         Initial version.

    ]]>         TBD

    ]]>         This product fixes default number of queues to resolve RSS issues.

    ]]>
  • Updated setup utility dependencies
    • ]]>
  • Updated Supported Environments
    • ]]>         For NovSPP2025

    ]]>
  • Change the backplane bay count information to the actual bay that is connected to controller.
  • Add support for users to clear NVRAM using Factory Repurpose operation
  • Re-order LSA GUI buttons
    • Move the Rebuild button to the top before Make Online button
    • Add the Rebuild button in the Offline Drive warning session
  • Change the recommended action for Degarded Volume to “Make sure all the participating drives are connected and rebuild is complete”.
    • ]]>
  • Fix MRSA issue in a00150411en_us Advisory: HPE Compute MR Controllers - HPE MR Storage Administrator (MRSA) Launch Issue and Storage Command Line Interface (StorCLI) Installation Warning Message Observed With Red Hat Enterprise Linux Server 10
    • ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>         TBD

    ]]>         This Firmware package contains following firmware versions:

    Adapter

    Speed

    Universal Boot Image

    Firmware

    UEFI

    Boot Bios

    HPE SN1620E 32Gb Dual Port Fibre Channel Host Bus Adapter

    32Gb

    14.4.731.5

    14.4.731.5

    14.4.716.0

    14.4.718.0
    HPE SN1720E 64Gb Dual Port Fibre Channel Host Bus Adapter 64Gb 14.4.731.5 14.4.731.5 14.4.716.0 14.4.718.0
    ]]>         This Firmware package contains following firmware versions:

    Adapter

    Speed

    Universal Boot Image

    Firmware

    UEFI

    Boot Bios

    HPE SN1620E 32Gb Dual Port Fibre Channel Host Bus Adapter

    32Gb

    14.4.473.30

    14.4.473.30

    14.4.473.29

    14.4.469.0
    HPE SN1720E 64Gb Dual Port Fibre Channel Host Bus Adapter 64Gb 14.4.473.30 14.4.473.30 14.4.473.29 14.4.469.0
    ]]>         Fixed the Following:

    1. Switch Login Incomplete After Firmware Upgrade
    2. Boot Incomplete on RHEL 10
    ]]>         See the AMS Release Notes for information about the issues resolved in this release.

    ]]>         See the AMS Release Notes for information about the issues resolved in this release.

    ]]>         See the AMS Release Notes for information about the enhancements in this release.

    ]]>         See the AMS Release Notes for information about the issues resolved in this release.

    ]]>
  • Remove ROM flash way from this FWPKG.
    • ]]>         Updated to driver version 14.4.624.0

    The raw driver files can be obtained by extracting the Smart Component and then extracting the Emulex installer.  Use this command:

        elxdrvr-fc-version.exe /q2 extract=2

    The extracted files are located:

        C:\Users\Administrator\Documents\Emulex\Drivers\FC-version

    Each kit folder has subsequent architecture folders with subsequent OS folders.  For example,

        C:\Users\Administrator\Documents\Emulex\Drivers\FC-version\x64\win2022

    ]]>         Updated to driver version 14.4.393.20

    The raw driver files can be obtained by extracting the Smart Component and then extracting the Emulex installer.  Use this command:

        elxdrvr-fc-version.exe /q2 extract=2

    The extracted files are located:

        C:\Users\Administrator\Documents\Emulex\Drivers\FC-version

    Each kit folder has subsequent architecture folders with subsequent OS folders.  For example,

        C:\Users\Administrator\Documents\Emulex\Drivers\FC-version\x64\win2022

    ]]>
  • Firmware changes aligned for FIPS code release and one assert fix
    • ]]>         1) Fixes the logic bug in the media cache cleaning abort handling that caused the drive to choose and execute the R/W command before the Request Sense to prevent assert.
    2) Adding other logging and FW enhancements.

    ]]>
  • This firmware fixes an issue where the drive can become inaccessible after an emergency power off, and corrects a potential verification issue during read recovery.
    • ]]>
  • Fixes potential data integrity risk found during supplier ongoing testing.
  • Corrects conditions which could cause the drive to become inaccessible.
  • Includes improvements to enhance drive reliability.
    • ]]>
  • DMTF PLDM Redfish Device Enablement enhancements
    • Redfish Volume Transformation Support
      • POST #Volume.ChangeRAIDLayout: RAID Layout Change. Change in the RAID Layout is achieved by providing the target RAIDType and the list of the drives in the input JSON body.
      • POST #Volume.ChangeRAIDLayout: Resize. ChangeRAIDLayout can be used to resize the volume by adding new Unconfigured Good drives without changing the RAIDType. In such cases RAIDType must not be provided in the input JSON body but the full drive list must be provided accordingly.
      • PATCH Volume[CapacityBytes]: This operation is used for resizing the volume when there is unused size available in the volume. There is no scope for adding any new drives here
      • POST #Volume.CheckConsistency: This operation starts Consistency Check operation on the volume. No input is expected for this operation.
    • Redfish Metrics GET Support
      • StorageControllerMetrics: UncorrectableECCErrorCount, CorrectableECCErrorCount, CorrectableParityErrorCount, StateChangeCount
      • PortMetrics: SAS.InvalidDwordCount, SAS.LossOfDwordSynchronizationCount, SAS.RunningDisparityErrorCount, PCIeErrors.CorrectableErrorCount, PCIeErrors.FatalErrorCount, PCIeErrors.NonFatalErrorCount
      • Each counter can hold a value up to 65535. Once the counter reaches the maximum value the value is not reset.
      • Metrics are cleared when user performs Controller NVRAM clear or Redfish ResetToDefaults.ResetAll.
  • Add support for users to clear NVRAM using MRSA and storcli Factory Repurpose operation.
    • Clear NVRAM operation is not allowed if there is any configuration present on the controller or if there is any pinned cache.
    • After clearing NVRAM, controller FW performs Online Controller Reset (OCR). If for some reason OCR cannot be performed, then the user will be notified to perform a system reboot.
    • The Clear NVRAM operation is equivalent to Redfish ResetToDefaults.ResetAll operation functionally.
  • Change the backplane bay count information to the actual bay that is connected to controller. For non-hotplug configuration, controller always shows 16 bays.
    • ]]>
  • Fix a00143124en_us Advisory: HPE MR Gen11 Controller - MR Gen11 Controllers on HPE Gen11 Servers May Fail to Generate "WriteCacheDataLoss" in the IML
  • Fix a00148035en_us Advisory: HPE MR Gen11 Controllers - The Bay And Box NVMe Drive Location Is Not Displayed in the One-Time Boot Menu
  • Fix an issue that Read/Write transfers over 128KB on LTO fail in Linux OS
  • Fix an issue that Backup Exec doesn’t work with LTO
  • Fix an issue that controller might be dropped by the iLO in server boot up when there are 240 Logical Drives are configured
  • Fix a rare issue that server health shows critical temporally when remove drive continuously.
  • Fix an issue that unexpected PCIConfiglink page events, Task management to the virtual SES device time out messages are logged in snapdump
  • Fix an issue that Slot capable protocol is missing for empty bay
  • Fix an issue that Link Speed for LTO connected to controller shows Unknown
  • Fix an issue that Request Sense command causes task management on the drive where sanitization is in progress.
  • Fix an issue that Redfish PATCH StorageController[ControllerRates] silently sets random values when the value beyond 255 is used.
  • Fix an issue that incorrect controller error event may be logged when controller is configured as passthrough and do vm reboot
  • Fix an issue that active width, current speed are wrong in Redfish Fabric port when two backplanes connected to same storage port.
  • Fix a rare issue that NVMe drive link status may fail after reboot 
  • Fix a rare issue that controller may assert when there are multiple drives removed and inserted in a short time
  • Fix an issue that sanitize percentage does not progress on SATA drives if there is SATA passthrough command running
  • Fix an issue that sanitize percentage does not progress on NVMe drives
  • Fix a rare issue that IO timeout and device reset may occur with stress test of Read/Write and Non-Read/Write commands
    • ]]>
  • DMTF PLDM Redfish Device Enablement enhancements
    • Redfish Volume Transformation Support
      • POST #Volume.ChangeRAIDLayout: RAID Layout Change. Change in the RAID Layout is achieved by providing the target RAIDType and the list of the drives in the input JSON body.
      • POST #Volume.ChangeRAIDLayout: Resize. ChangeRAIDLayout can be used to resize the volume by adding new Unconfigured Good drives without changing the RAIDType. In such cases RAIDType must not be provided in the input JSON body but the full drive list must be provided accordingly.
      • PATCH Volume[CapacityBytes]: This operation is used for resizing the volume when there is unused size available in the volume. There is no scope for adding any new drives here
      • POST #Volume.CheckConsistency: This operation starts Consistency Check operation on the volume. No input is expected for this operation.
    • Redfish Metrics GET Support
      • StorageControllerMetrics: UncorrectableECCErrorCount, CorrectableECCErrorCount, CorrectableParityErrorCount, StateChangeCount
      • PortMetrics: SAS.InvalidDwordCount, SAS.LossOfDwordSynchronizationCount, SAS.RunningDisparityErrorCount, PCIeErrors.CorrectableErrorCount, PCIeErrors.FatalErrorCount, PCIeErrors.NonFatalErrorCount
      • Each counter can hold a value up to 65535. Once the counter reaches the maximum value the value is not reset.
      • Metrics are cleared when user performs Controller NVRAM clear or Redfish ResetToDefaults.ResetAll.
  • Add support for users to clear NVRAM using MRSA and storcli Factory Repurpose operation.
    • Clear NVRAM operation is not allowed if there is any configuration present on the controller or if there is any pinned cache.
    • After clearing NVRAM, controller FW performs Online Controller Reset (OCR). If for some reason OCR cannot be performed, then the user will be notified to perform a system reboot.
    • The Clear NVRAM operation is equivalent to Redfish ResetToDefaults.ResetAll operation functionally.
  • Change the backplane bay count information to the actual bay that is connected to controller. For non-hotplug configuration, controller always shows 16 bays.
    • ]]>
  • Fix a00143124en_us Advisory: HPE MR Gen11 Controller - MR Gen11 Controllers on HPE Gen11 Servers May Fail to Generate "WriteCacheDataLoss" in the IML
  • Fix a00148035en_us Advisory: HPE MR Gen11 Controllers - The Bay And Box NVMe Drive Location Is Not Displayed in the One-Time Boot Menu
  • Fix an issue that Read/Write transfers over 128KB on LTO fail in Linux OS
  • Fix an issue that Backup Exec doesn’t work with LTO
  • Fix an issue that controller might be dropped by the iLO in server boot up when there are 240 Logical Drives are configured
  • Fix a rare issue that server health shows critical temporally when remove drive continuously.
  • Fix an issue that unexpected PCIConfiglink page events, Task management to the virtual SES device time out messages are logged in snapdump
  • Fix an issue that Slot capable protocol is missing for empty bay
  • Fix an issue that Link Speed for LTO connected to controller shows Unknown
  • Fix an issue that Request Sense command causes task management on the drive where sanitization is in progress.
  • Fix an issue that Redfish PATCH StorageController[ControllerRates] silently sets random values when the value beyond 255 is used.
  • Fix an issue that incorrect controller error event may be logged when controller is configured as passthrough and do vm reboot
  • Fix an issue that active width, current speed are wrong in Redfish Fabric port when two backplanes connected to same storage port.
  • Fix a rare issue that NVMe drive link status may fail after reboot 
  • Fix a rare issue that controller may assert when there are multiple drives removed and inserted in a short time
  • Fix an issue that sanitize percentage does not progress on SATA drives if there is SATA passthrough command running
  • Fix an issue that sanitize percentage does not progress on NVMe drives
  • Fix a rare issue that IO timeout and device reset may occur with stress test of Read/Write and Non-Read/Write commands
    • ]]>         Added support for:

    Red Hat Enterprise Linux 10.1

    Updated to version 14.4.731.6

    ]]>         Added support for:

    Red Hat Enterprise Linux 10.0

    Updated to version 14.4.473.24

    ]]>         For SEP2025 SPP

    ]]>
  • HPK6 is a planned maintenance release that follows the HPK3 FW release for the P5430, 30.72TB (8K IU) Solid State Drive. This is a recommended FW release
    • ]]>         See the AMS Release Notes for information about the enhancements in this release.

    ]]>         See the AMS Release Notes for information about the issues resolved in this release.

    ]]>         TBD

    ]]>
  • This product fixes an issue where the Port Reset attributes are missing under RDE port Schema.
  • This product fixes an issue where the link failed with the LCP-1250RJ3SR-KH transceiver.
  • This product fixes an issue where the FW PLDM upgrade may failed with CVL4.71 when MCTP traffic loading is heavy.
  • This product fixes an issue where the BSOD observed in Windows OS with OOB driver when transmit balancing is enabled in NIC HII menu.
    • ]]>         This product fixed an issue where the Relaxed Ordering feature was incorrectly disabled when using firmware versions newer than XX.36.2024.

    ]]>         Added support for the DOCA Telemetry Library on Windows.

    ]]>
  • This product fixed an issue that could cause a BSOD during the suspend/resume process when the firmware is not functional.
  • This product fixed an issue where "Mlx5Cmd -Stat" displayed incorrect physical location information on multi-segment PCI machines when the adapter was disabled.
  • This product fixed an issue where Event 399 displayed incorrect information.
  • This product fixed an issue that triggered Error events 410 and 304 when enabling or disabling pktmon on an adapter operating in VMQ/SR-IOV mode.
    • ]]>         Initial version.

    ]]>         TBD

    ]]>         This product fixes default number of queues to resolve RSS issues.

    ]]>          

    •     This firmware revision improves data integrity and reliability by optimizing adjacent track refresh parameters and management of emergency power loss table structure
    •     The risk of not upgrading to this firmware is the increased possibility of data corruption in emergency power loss events
    •     Several maintenance items are included in this firmware revision that reduce the probability of hangs and provide some minor performance improvements
    ]]>         Initial version

    ]]>         Updated to version 14.4.731.6

    ]]>
  • Improve FW handling on capacitor charge timeout mechanism
  • Change the sense code during download microcode (0E)
    • ]]>         This is initial release

    ]]>         Updated to version 14.4.731.6

    ]]>         Added support for:

    Red Hat Enterprise Linux 10.0

    Updated to version 14.4.473.24

    ]]>         Initial version.

    ]]>         Initial version from HPE.

     

    The following fixes have been included in version 40.46.3048:

    • Fix for the adapter card dropping NC-SI over MCTP commands when padding bytes were present after the NC-SI checksum. 
    ]]>
  • Rebuilt using latest certificates for Windows installers
    • ]]>
  • Fixed the “Parity Initialization Method” information displayed for non-parity RAID levels. 
  • Fixed an issue where users were unable to clear the controller’s configuration when a foreign volume was present. 
  • Fixed an issue where a foreign-owned SED drive was being listed for array creation. 
  • Fixed an issue where the last failure reason was not listing on physical drives. 
  • Fixed an issue where SSAScripting failed to create an encrypted volume while in express local mode. 
  • Fixed an issue where an error/warning message was not being generated correctly while expanding a RAID 1+0 volume. 
  • Fixed an issue where a duplicate entry for the physical drive was displayed. 
    • ]]>
  • Updated Supported Environments
    • ]]>
  • Updated Supported Environments
    • ]]>
  • Fix contains optimization to increase the time for Recovery operation and few checks for maintenance
    • ]]>
  • Fix FW force update from iLO GUI or SPP (HPK3 --> HPK3)
  • The FW address: PCIe link drop and 0ther regular FW patches release.
    • ]]>
  • The FW address: PCIe link drop and 0ther regular FW patches release.
    • ]]>         New features and changes included in version 26.46.3048:

    • Added support for RSS with crypto offload enabling the NIC to parallelize packet processing across CPU cores while performing encryption/decryption in hardware. Additionally, introduced a new l4_type_ext parameter with values: 0 (None), 1 (TCP), 2 (UDP), 3 (ICMP).
    • Added an extra validation for the payload_len field in incoming NC-SI messages. Previously, invalid packets might have been accepted; now, such packets are silently dropped.
    • This release contains important reliability improvements and security hardening enhancements. HPE recommends upgrading your devices firmware to this release to improve the devices’ firmware security and reliability.
    ]]>         The following issues have been fixed in version 26.46.3048:

    • Configuring a small MTU led to fragmentation of packets critical for the PXE boot process. As a result, the PXE boot filters mistakenly discarded these packets, causing the PXE boot to fail.
    ]]>         Security Hardening Enhancements: This release contains important reliability improvements and security hardening enhancements. HPE recommends upgrading your device's firmware to this release to improve the firmware security and reliability of your device.
     

    No new features and changes have been included in version 26.45.1020.

    ]]>         The following issues have been fixed in version 26.45.1020:

    • Configuring PHY_RATE_MASK for 10G in NV settings incorrectly disabled 10G capabilities.
    • RTT packets with any destination MAC address were incorrectly treated as having a valid destination MAC. The new firmware now discards RTT packets if their destination MAC does not match the port's MAC.
    ]]>         Driver version 5.5.85.0
    This driver is only supported on VMware ESXi 9.0

    ]]>         Driver version 5.4.83.1
    This driver is only supported on VMware ESXi 9.0

    ]]>         Support SY480 Gen12 server.

    ]]>         Support RL300 Gen11 server and Gen12 servers.

    ]]>         Updated Driver version 10.02.15.00-k1

    ]]>         Added Support For:

    Red Hat Enterprise Linux 10

    Updated Driver version 10.02.14.00-k1

    ]]>         SR 2.10.0/SR 3.5.0 RC

    ]]>         TBD

    ]]>         This product now adds support for E610 device.

    ]]>
  • Known issue: Firmware OROM version displays as "0.0.0" via "ethtool -i".
  • Known issue: Firmware OROM version displays incorrectly via "esxcli network nic get -n interface".
    • ]]>         Updated to version 9.4.11.20

    ]]>         Updated to version 9.4.11.20

    ]]>
  • Added Azure Local 24H2 OS support
    • ]]>
  • Fix an issue that system may crash when importing Logical Drive.
    • ]]>
  • Fix contains optimization to increase the time for Recovery operation and few checks for maintenance
    • ]]>
  • To fix chip kill -The host IO CMD may get timed out and shows SNS=04/40/C2.
    • ]]>
  • Added fix to address a rare case where drive health queries can trigger false drive predictive failure.
  • For more information, refer to HPE Customer Advisory at the following URL: https://support.hpe.com/hpesc/public/docDisplay?docId=emr_na-a00146367en_us which will be active on 20-Mar-2025.
    • ]]>         TBD

    ]]>         Initial release to support Red Hat Enterprise Linux 10.

    ]]>
  • RSOD issue fixed. RSOD was occurred during server power-on if enable the VROC.
    • ]]>
  • Improve the FW about data mismatch after SPL issued.
    • ]]>
  • This is a maintenance release that contains code fix improvements and drive function enhancements.
    • ]]>         Updated Driver version 10.02.15.00-k1

    ]]>         Updated the PCIe DeEmphasis setting for specific front OCP cases on the DL380 Gen12.

    ]]>         Important Notes:

    This version of the System ROM contains updates aligned with GNR/SRF UPLR1.5 updates.

    Details about reported security vulnerabilities and their mitigation can be found at the following link Security Bulletin Library | HPE Support.

    Firmware Dependencies:

    None

    Problems Fixed:

    Addressed an issue where system might not be able to perform PXE boot when 400G NICs are installed.

    Addressed an issue where the setting change of "UPI Link Enablement" under "System Utilities > System Configuration > RBSU > Power and Performance Options > Intel UPI Options" might not take effect.

    Addressed an issue where the setting change of "UPI Link Power Management" under "System Utilities > System Configuration > RBSU > Power and Performance Options > Intel UPI Options" might not take effect.

    Addressed an issue where the system might not boot up when 10x RTX6000 Pro GPU cards are installed (DL380a).

    Addressed an issue where the ACPI BERT table could not be exported by UEFI/ROM.

    Addressed an issue where the setting change of "PCIe ASPM Support" under "System Utilities > System Configuration > RBSU > PCIe Device Configuration > Advanced PCIe Configuration > PCIe ASPM Support (Global)" might not take effect.

    Addressed an issue where the system might have PCR value change be reported after system reboot.

    Addressed an issue where the system TPM-0 measurements might change after system reboot.

    Addressed an issue where the system Redfish URI might be removed after performing delete action through redfish API but failed.

    Addressed an issue where the system with 2x6980P processors might encounter processor cores missing from RBSU and OS. (U66)

    Addressed an issue where the system might list some null string under "Utilities> System Information> PCIe Device Information" when MR932i-p is installed.

    Addressed an issue where the system with VROC enabled might get reboot when drives were Hot-Added.

    Known Issues:

    None]]>         Updated the default Secure Boot DBX.

    Optimized the UEFI Memory Map to reduce memory fragmentation distribution.

    Greyed out the Page Table Entry Speculative Lock Scheduling knob under RBSU->System Options->Processor Options->Page Table Entry Speculative Lock Scheduling since it can only be enabled.

    ]]>         Important Notes:

    This version of the System ROM contains updates aligned with Intel GNR/SRF UPLR1 BKC update.

    Details about reported security vulnerabilities and their mitigation can be found at the following link Security Bulletin Library | HPE Support.

    Firmware Dependencies:

    None

    Problems Fixed:

    Addressed an issue where unsupported property (IntelProcVtd) might be listed under (/redfish/v1/systems/1/bios/) accidentally.

    Addressed an issue where system might spend a long time in the "Early Processor Initialization" step after power-on.

    Known Issues:

    None]]>
  • Verified the UNMAP command and confirmed that the Block Limits VPD page data is correct with the latest firmware.
    • ]]>
  • Fix a potential mutex deadlock between reset and event handling thread. The issue may happen when there is heavy IO, device add/delete and SCSI rescan running in the same time.
    • ]]>
  • Verified the UNMAP command and confirmed that the Block Limits VPD page data is correct with the latest firmware.
    • ]]>
  • Fix a potential mutex deadlock between reset and event handling thread. The issue may happen when there is heavy IO, device add/delete and SCSI rescan running in the same time.
    • ]]>         Upgraded to version 26.45.1020

    ]]>         Upgraded to version 26.43.1014

    ]]>
  • This product enhances the Windows driver to support PCIe compliance configuration by enabling pass-through firmware commands with long input message sizes.
  • This product enhances adding new event log warning message.
    • ]]>
  • This product enhances to improve user mode RDMA abortive cleanup.
  • This product enhances FW logging to host to work across device reset.
    • ]]>         This product fixes issue where packet drops is seen when jumbo frame is enabled.

    ]]>