This product fixes an issue where configuring the Maximum Transmission Unit (MTU) for a Virtual Function fails on a guest OS.

This product addresses an issue where a link is lost on a Virtual Machine when hypervisor is restored from low-power state, such as freeze or suspend.

This product fixes an issue where configuring the Maximum Transmission Unit (MTU) for a Virtual Function fails on a guest OS.

This product addresses an issue where a link is lost on a Virtual Machine when hypervisor is restored from low-power state, such as freeze or suspend.

• An issue that prevented the firmware from detecting a link_down event thus preventing the IB bond interface from going to a failover mode.

Fixes submitted in version 14.26.1040:

• A function was misbehaving when a PCIe TLP was set with a poisoned indication.
• The “destroy mkey “ command was getting stuck when rebooting the hypervisor.
• The total firmware reset time is increased by 1 second.

Fixes submitted in version 16.26.1040:

• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Unexpected queue pairs transitioned to error in lossy tests.
• Limited the maximum amount of dumps created on a PF.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Stability issues with RDMA over Converged Ethernet (RoCE) retransmissions under stress were affecting Zero-Touch-RoCE.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.
• Large number of packets dropped when running Jumbo frames with TTL rewrite.
• Limited the number of the elements in the Quality of Service (QoS) tree 2K.
  Note: Creating more than 250 Vport_tc for every TC is not allowed.
• Queue Pair (QP) flow query was always taking port 1, Firmware will now reply the proper port, 1 or 2, for the dual port RoCE net device.
• The nack counters constantly reported as “0”.
• In a rare scenario when the driver is executing the "2err" command and the QP is in Send Queue (SQ) drain state, the firmware might post event of broken Work Queue (WQ) instead of sending error Completion Queue Element (CQEs) on all the Work Queue Entry (WQEs).

• An issue that prevented the firmware from detecting a link_down event thus preventing the IB bond interface from going to a failover mode.

Fixes submitted in version 14.26.1040:

• A function was misbehaving when a PCIe TLP was set with a poisoned indication.
• The “destroy mkey “ command was getting stuck when rebooting the hypervisor.
• The total firmware reset time is increased by 1 second.

Fixes submitted in version 16.26.1040:

• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Unexpected queue pairs transitioned to error in lossy tests.
• Limited the maximum amount of dumps created on a PF.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Stability issues with RDMA over Converged Ethernet (RoCE) retransmissions under stress were affecting Zero-Touch-RoCE.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.
• Large number of packets dropped when running Jumbo frames with TTL rewrite.
• Limited the number of the elements in the Quality of Service (QoS) tree 2K.
  Note: Creating more than 250 Vport_tc for every TC is not allowed.
• Queue Pair (QP) flow query was always taking port 1, Firmware will now reply the proper port, 1 or 2, for the dual port RoCE net device.
• The nack counters constantly reported as “0”.
• In a rare scenario when the driver is executing the "2err" command and the QP is in Send Queue (SQ) drain state, the firmware might post event of broken Work Queue (WQ) instead of sending error Completion Queue Element (CQEs) on all the Work Queue Entry (WQEs).

• An issue that prevented the firmware from detecting a link_down event thus preventing the IB bond interface from going to a failover mode.

Fixes submitted in version 14.26.1040:

• A function was misbehaving when a PCIe TLP was set with a poisoned indication.
• The “destroy mkey “ command was getting stuck when rebooting the hypervisor.
• The total firmware reset time is increased by 1 second.

Fixes submitted in version 16.26.1040:

• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Unexpected queue pairs transitioned to error in lossy tests.
• Limited the maximum amount of dumps created on a PF.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Stability issues with RDMA over Converged Ethernet (RoCE) retransmissions under stress were affecting Zero-Touch-RoCE.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.
• Large number of packets dropped when running Jumbo frames with TTL rewrite.
• Limited the number of the elements in the Quality of Service (QoS) tree 2K.
  Note: Creating more than 250 Vport_tc for every TC is not allowed.
• Queue Pair (QP) flow query was always taking port 1, Firmware will now reply the proper port, 1 or 2, for the dual port RoCE net device.
• The nack counters constantly reported as “0”.
• In a rare scenario when the driver is executing the "2err" command and the QP is in Send Queue (SQ) drain state, the firmware might post event of broken Work Queue (WQ) instead of sending error Completion Queue Element (CQEs) on all the Work Queue Entry (WQEs).

• An issue that prevented the firmware from detecting a link_down event thus preventing the IB bond interface from going to a failover mode.

Fixes submitted in version 14.26.1040:

• A function was misbehaving when a PCIe TLP was set with a poisoned indication.
• The “destroy mkey “ command was getting stuck when rebooting the hypervisor.
• The total firmware reset time is increased by 1 second.

Fixes submitted in version 16.26.1040:

• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Unexpected queue pairs transitioned to error in lossy tests.
• Limited the maximum amount of dumps created on a PF.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Stability issues with RDMA over Converged Ethernet (RoCE) retransmissions under stress were affecting Zero-Touch-RoCE.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.
• Large number of packets dropped when running Jumbo frames with TTL rewrite.
• Limited the number of the elements in the Quality of Service (QoS) tree 2K.
  Note: Creating more than 250 Vport_tc for every TC is not allowed.
• Queue Pair (QP) flow query was always taking port 1, Firmware will now reply the proper port, 1 or 2, for the dual port RoCE net device.
• The nack counters constantly reported as “0”.
• In a rare scenario when the driver is executing the "2err" command and the QP is in Send Queue (SQ) drain state, the firmware might post event of broken Work Queue (WQ) instead of sending error Completion Queue Element (CQEs) on all the Work Queue Entry (WQEs).

• Build environment using QSpectre compiler switch
• Request FDMI Data Change from drivers
• fcinfo /diag, and continual busy status failures.

• Build environment using QSpectre compiler switch
• Request FDMI Data Change from drivers
• fcinfo /diag, and continual busy status failures.

Ver. 1.60(B) contains updates to the component packaging and is functionally equivalent to ver. 1.60. It is not necessary to upgrade with Revision B if a previous component Revision was used to upgrade the firmware to version 1.60.

This revision of the System ROM includes the latest revision of the Intel microcode which, in combination with operating system updates, provides mitigation for Variant 2 of the Side Channel Analysis vulnerability, also known as Spectre. The revision of the microcode included in this System ROM does NOT have issues with more frequent reboots and unpredictable system behavior which impacted the previous Intel microcode which was part of the Spectre Variant 2 mitigation. Additional information is available from Intel’s Security Exploit Newsroom, https://newsroom.intel.com/press-kits/security-exploits-intel-products/.

Firmware Dependencies:

None

Problems Fixed:

Updated the Intel processor microcode to the latest version.

Known Issues:

None

Ver. 1.60(B) contains updates to the component packaging and is functionally equivalent to ver. 1.60. It is not necessary to upgrade with Revision B if a previous component Revision was used to upgrade the firmware to version 1.60.

This revision of the System ROM includes the latest revision of the Intel microcode which, in combination with operating system updates, provides mitigation for Variant 2 of the Side Channel Analysis vulnerability, also known as Spectre. The revision of the microcode included in this System ROM does NOT have issues with more frequent reboots and unpredictable system behavior which impacted the previous Intel microcode which was part of the Spectre Variant 2 mitigation. Additional information is available from Intel’s Security Exploit Newsroom, https://newsroom.intel.com/press-kits/security-exploits-intel-products/.

Firmware Dependencies:

None

Problems Fixed:

Updated the Intel processor microcode to the latest version.

Known Issues:

None

This revision of the System ROM includes the latest revision of the Intel microcode which, in combination with operating system updates, provides mitigation for Variant 2 of the Side Channel Analysis vulnerability, also known as Spectre. The revision of the microcode included in this System ROM does NOT have issues with more frequent reboots and unpredictable system behavior which impacted the previous Intel microcode which was part of the Spectre Variant 2 mitigation. Additional information is available from Intel’s Security Exploit Newsroom, https://newsroom.intel.com/press-kits/security-exploits-intel-products/.

Firmware Dependencies:

None

Problems Fixed:

Updated the Intel processor microcode to the latest version.

Known Issues:

None

This revision of the System ROM includes the latest revision of the Intel microcode which, in combination with operating system updates, provides mitigation for Variant 2 of the Side Channel Analysis vulnerability, also known as Spectre. The revision of the microcode included in this System ROM does NOT have issues with more frequent reboots and unpredictable system behavior which impacted the previous Intel microcode which was part of the Spectre Variant 2 mitigation. Additional information is available from Intel’s Security Exploit Newsroom, https://newsroom.intel.com/press-kits/security-exploits-intel-products/.

Firmware Dependencies:

None

Problems Fixed:

Updated the Intel processor microcode to the latest version.

Known Issues:

None

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

Driver run into a Purple Screen of Death (PSOD) after Invalid entry, prints in the vmkernel log;

"WARNING: qlnativefc: vmhba2(12:0.0): Invalid ISP SCSI completion handle(281) req=1

WARNING: qlnativefc: vmhba2(12:0.0): Invalid ISP SCSI completion handle(282) req=1"

Driver run into a Purple Screen of Death (PSOD) after Invalid entry, prints in the vmkernel log;

"WARNING: qlnativefc: vmhba2(12:0.0): Invalid ISP SCSI completion handle(281) req=1

WARNING: qlnativefc: vmhba2(12:0.0): Invalid ISP SCSI completion handle(282) req=1"

• Incorrect supported speed values were being reported in management app
• Purple Screen of Death (PSOD) observed during N_Port ID Virtualization (NPIV) failover
• Sending Small Computer System Interface (SCSI) pass thru commands to an N_Port ID Virtualization (NPIV) port was incomplete
• Driver vmkmgmt shows the VM Identifier (VMID) info under the N_Port ID Virtualization (NPIV) section, when N_Port ID Virtualization (NPIV) is not enabled
• Various unexpected behaviors with introduced Simplified Fabric Discovery support.
• ql2xt10difvendor was disabled and associated with ql2xenablesmartsan
• zdump does not  get saved off on Boot From SAN (BFS) configuration
• FDMI 2 RHBA command was getting rejected by the switch

• Incorrect supported speed values were being reported in management app
• Purple Screen of Death (PSOD) observed during N_Port ID Virtualization (NPIV) failover
• Sending Small Computer System Interface (SCSI) pass thru commands to an N_Port ID Virtualization (NPIV) port was incomplete
• Driver vmkmgmt shows the VM Identifier (VMID) info under the N_Port ID Virtualization (NPIV) section, when N_Port ID Virtualization (NPIV) is not enabled
• Various unexpected behaviors with introduced Simplified Fabric Discovery support.
• ql2xt10difvendor was disabled and associated with ql2xenablesmartsan
• zdump does not  get saved off on Boot From SAN (BFS) configuration
• FDMI 2 RHBA command was getting rejected by the switch

• SATA drive could stop responding  while on HBA mode when non-NCQ commands are executed
• Controller could stop responding when upgrading due to the DDR Cache Module exceeding its limitations
• SSD Cache module could become disable while upgrading FW
• Data from the HPE Smart Drive Backplane could potentially become corrupted if a non-HPE carrier is present

• SATA drive could stop responding  while on HBA mode when non-NCQ commands are executed
• Controller could stop responding when upgrading due to the DDR Cache Module exceeding its limitations
• SSD Cache module could become disable while upgrading FW
• Data from the HPE Smart Drive Backplane could potentially become corrupted if a non-HPE carrier is present

  - iLO gets stalled when IPv4 static address is not assigned in an IPv6 only environment using Embedded Remote Support.
  - Embedded Remote Support crashes if more than 17 IP addresses are assigned to host network interface.
  - Embedded Remote Support is not reporting all host IP addresses in Service Events.

  - iLO gets stalled when IPv4 static address is not assigned in an IPv6 only environment using Embedded Remote Support.
  - Embedded Remote Support crashes if more than 17 IP addresses are assigned to host network interface.
  - Embedded Remote Support is not reporting all host IP addresses in Service Events.

• Servers do not complete the process to connect to OneConnectManager Management Host On Windows 2008/ 2012 and 2016

• Servers do not complete the process to connect to OneConnectManager Management Host On Windows 2008/ 2012 and 2016

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

• Temperature sensors logic inside gSEP model and SES database
• When an IOM is pulled the surviving IOM reports false critical temperatures

Please refer to the Release Notes for the complete listing of fixes, enhancements, known issues and work-arounds corresponding to this firmware.

• Temperature sensors logic inside gSEP model and SES database
• When an IOM is pulled the surviving IOM reports false critical temperatures

Please refer to the Release Notes for the complete listing of fixes, enhancements, known issues and work-arounds corresponding to this firmware.

• Temperature sensors logic inside gSEP model and SES database
• When an IOM is pulled the surviving IOM reports false critical temperatures

Please refer to the Release Notes for the complete listing of fixes, enhancements, known issues and work-arounds corresponding to this firmware.

• Temperature sensors logic inside gSEP model and SES database
• When an IOM is pulled the surviving IOM reports false critical temperatures

Please refer to the Release Notes for the complete listing of fixes, enhancements, known issues and work-arounds corresponding to this firmware.

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

This product fixes a issue where configuring the Maximum Transmission Unit (MTU) on a Virtual Function fails on a guest OS.

This product fixes a issue where configuring the Maximum Transmission Unit (MTU) on a Virtual Function fails on a guest OS.

Ver. 1.0.9(J) contains updates to the component packaging and is functionally equivalent to ver. 1.0.9. It is not necessary to upgrade with Revision J if a previous component Revision was used to upgrade the firmware to version 1.0.9.

Firmware Dependencies:

None

Problems Fixed:

Addresses an issue in which the minimum power capping value was incorrectly being calculated on certain systems. This fix increases the accuracy of the minimum capping value set during POST.

Known Issues:

None

Ver. 1.0.9(J) contains updates to the component packaging and is functionally equivalent to ver. 1.0.9. It is not necessary to upgrade with Revision J if a previous component Revision was used to upgrade the firmware to version 1.0.9.

Firmware Dependencies:

None

Problems Fixed:

Addresses an issue in which the minimum power capping value was incorrectly being calculated on certain systems. This fix increases the accuracy of the minimum capping value set during POST.

Known Issues:

None

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

• IPoIB could not to function when there were Dynamically Connected Transport (DC) CNAK Queue Pairs (QPs) active.
• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.

Fixes submitted in version 16.26.1040:

• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Unexpected queue pairs transitioned to error in lossy tests.
• Limited the maximum amount of dumps created on a PF.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Stability issues with RDMA over Converged Ethernet (RoCE) retransmissions under stress were affecting Zero-Touch-RoCE.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.
• Large number of packets dropped when running Jumbo frames with TTL rewrite.
• Limited the number of the elements in the Quality of Service (QoS) tree 2K.
  Note: Creating more than 250 Vport_tc for every TC is not allowed.
• Queue Pair (QP) flow query was always taking port 1, Firmware will now reply the proper port, 1 or 2, for the dual port RoCE net device.
• The nack counters constantly reported as “0”.
• In a rare scenario when the driver is executing the "2err" command and the QP is in Send Queue (SQ) drain state, the firmware might post event of broken Work Queue (WQ) instead of sending error Completion Queue Element (CQEs) on all the Work Queue Entry (WQEs).

• IPoIB could not to function when there were Dynamically Connected Transport (DC) CNAK Queue Pairs (QPs) active.
• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.

Fixes submitted in version 16.26.1040:

• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Unexpected queue pairs transitioned to error in lossy tests.
• Limited the maximum amount of dumps created on a PF.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Stability issues with RDMA over Converged Ethernet (RoCE) retransmissions under stress were affecting Zero-Touch-RoCE.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.
• Large number of packets dropped when running Jumbo frames with TTL rewrite.
• Limited the number of the elements in the Quality of Service (QoS) tree 2K.
  Note: Creating more than 250 Vport_tc for every TC is not allowed.
• Queue Pair (QP) flow query was always taking port 1, Firmware will now reply the proper port, 1 or 2, for the dual port RoCE net device.
• The nack counters constantly reported as “0”.
• In a rare scenario when the driver is executing the "2err" command and the QP is in Send Queue (SQ) drain state, the firmware might post event of broken Work Queue (WQ) instead of sending error Completion Queue Element (CQEs) on all the Work Queue Entry (WQEs).

• IPoIB could not to function when there were Dynamically Connected Transport (DC) CNAK Queue Pairs (QPs) active.
• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.

Fixes submitted in version 16.26.1040:

• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Unexpected queue pairs transitioned to error in lossy tests.
• Limited the maximum amount of dumps created on a PF.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Stability issues with RDMA over Converged Ethernet (RoCE) retransmissions under stress were affecting Zero-Touch-RoCE.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.
• Large number of packets dropped when running Jumbo frames with TTL rewrite.
• Limited the number of the elements in the Quality of Service (QoS) tree 2K.
  Note: Creating more than 250 Vport_tc for every TC is not allowed.
• Queue Pair (QP) flow query was always taking port 1, Firmware will now reply the proper port, 1 or 2, for the dual port RoCE net device.
• The nack counters constantly reported as “0”.
• In a rare scenario when the driver is executing the "2err" command and the QP is in Send Queue (SQ) drain state, the firmware might post event of broken Work Queue (WQ) instead of sending error Completion Queue Element (CQEs) on all the Work Queue Entry (WQEs).

• IPoIB could not to function when there were Dynamically Connected Transport (DC) CNAK Queue Pairs (QPs) active.
• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.

Fixes submitted in version 16.26.1040:

• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Unexpected queue pairs transitioned to error in lossy tests.
• Limited the maximum amount of dumps created on a PF.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Stability issues with RDMA over Converged Ethernet (RoCE) retransmissions under stress were affecting Zero-Touch-RoCE.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.
• Large number of packets dropped when running Jumbo frames with TTL rewrite.
• Limited the number of the elements in the Quality of Service (QoS) tree 2K.
  Note: Creating more than 250 Vport_tc for every TC is not allowed.
• Queue Pair (QP) flow query was always taking port 1, Firmware will now reply the proper port, 1 or 2, for the dual port RoCE net device.
• The nack counters constantly reported as “0”.
• In a rare scenario when the driver is executing the "2err" command and the QP is in Send Queue (SQ) drain state, the firmware might post event of broken Work Queue (WQ) instead of sending error Completion Queue Element (CQEs) on all the Work Queue Entry (WQEs).

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

Firmware Dependencies:

Problems Fixed:

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

Firmware Dependencies:

Problems Fixed:

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

• New servo which disables a feature that could cause unrecoverable data errors. 
• A fix for an issue where the drive could become unresponsive after a hard reset.

• New servo which disables a feature that could cause unrecoverable data errors. 
• A fix for an issue where the drive could become unresponsive after a hard reset.

These drivers have been recompiled with a build setting that allows SUM to identify them correctly for installation on systems they support.

These drivers have been recompiled with a build setting that allows SUM to identify them correctly for installation on systems they support.

• Fix incorrect CacheOperationalStatus data for Smart Array B140i Controller
• Fix memory leak issues causing ESXi host to become unresponsive or crash
   

Agentless Management Service

• Fix buffer overrun when acquiring vib summary from ESXi host database
• Fix cpqSePciSlotBoardName for empty slots with no CPU
• Fix cpqSePciSlotBoardName for FC Adapters with specific Device IDs
• Disable multiple IPv6 support in Gen9 to fix Host discovery issues due to missing support in iLO
• Fix AMS hang when total IPv6 address string sizes exceed 256 bytes

• Fix incorrect CacheOperationalStatus data for Smart Array B140i Controller
• Fix memory leak issues causing ESXi host to become unresponsive or crash
   

Agentless Management Service

• Fix buffer overrun when acquiring vib summary from ESXi host database
• Fix cpqSePciSlotBoardName for empty slots with no CPU
• Fix cpqSePciSlotBoardName for FC Adapters with specific Device IDs
• Disable multiple IPv6 support in Gen9 to fix Host discovery issues due to missing support in iLO
• Fix AMS hang when total IPv6 address string sizes exceed 256 bytes

• Fixed false Solid State Disk Wear alert reported by the SmartArray WBEM provider

Agentless Management Service

• Fixed reporting of HPE QLogic NX2 driver components in the cpqHoSwVer MIB to resolve blank Installed driver versions displayed in SUM

• Fixed false Solid State Disk Wear alert reported by the SmartArray WBEM provider

Agentless Management Service

• Fixed reporting of HPE QLogic NX2 driver components in the cpqHoSwVer MIB to resolve blank Installed driver versions displayed in SUM

• Addressed memory leaks
• Corrected segfaults reported in ahslog
• Improved synchronization between iLO and amsd

• Addressed memory leaks
• Corrected segfaults reported in ahslog
• Improved synchronization between iLO and amsd

• addressed segfaults seen in the ahslog

• addressed segfaults seen in the ahslog

• Flash read
• Read Diagnostic Parameters (RDP) respond data format
• Cleanup trace buffer initialization
• Unintended wait
• Incomplete login in point-to-point mode
• Restore World Wide Port Name (WWPN) of Physical Port for fabric configuration only for loop down

• Flash read
• Read Diagnostic Parameters (RDP) respond data format
• Cleanup trace buffer initialization
• Unintended wait
• Incomplete login in point-to-point mode
• Restore World Wide Port Name (WWPN) of Physical Port for fabric configuration only for loop down

• Servers do not complete the process to connect to OneConnectManager Management Host On Windows 2008/ 2012 and 2016

• Servers do not complete the process to connect to OneConnectManager Management Host On Windows 2008/ 2012 and 2016

This issue is only encounter when upgrading to version 2018.10.18 (5.5.0.66-1). All other versions are not affected.

This issue is only encounter when upgrading to version 2018.10.18 (5.5.0.66-1). All other versions are not affected.

• The Enabled-ClusterS2D command now completes successfully when executed on a SATA drive within a D3610 disk enclosure.

Please refer to the Release Notes for the complete listing of fixes, enhancements, known issues and work-arounds corresponding to this firmware.

• The Enabled-ClusterS2D command now completes successfully when executed on a SATA drive within a D3610 disk enclosure.

Please refer to the Release Notes for the complete listing of fixes, enhancements, known issues and work-arounds corresponding to this firmware.

• Fixed TLB exception during upgrade from Rev build 1.11.000 to 0412.000

• Fixed expander bootstrap task which failed with 0xB1 error code appearing in the console due to missing NVRAM tag - Product Name

• Enabled-ClusterS2D command that does not complete with SATA drive in D3610

Please refer to the Release Notes for the complete listing of fixes, enhancements, known issues and work-arounds corresponding to this firmware.

• Fixed TLB exception during upgrade from Rev build 1.11.000 to 0412.000

• Fixed expander bootstrap task which failed with 0xB1 error code appearing in the console due to missing NVRAM tag - Product Name

• Enabled-ClusterS2D command that does not complete with SATA drive in D3610

Please refer to the Release Notes for the complete listing of fixes, enhancements, known issues and work-arounds corresponding to this firmware.

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

None

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

None

• Flash read
• Read Diagnostic Parameters (RDP) respond data format
• Cleanup trace buffer initialization
• Unintended wait
• Incomplete login in point-to-point mode
• Restore World Wide Port Name (WWPN) of Physical Port for fabric configuration only for loop down

• Flash read
• Read Diagnostic Parameters (RDP) respond data format
• Cleanup trace buffer initialization
• Unintended wait
• Incomplete login in point-to-point mode
• Restore World Wide Port Name (WWPN) of Physical Port for fabric configuration only for loop down

• New servo which disables a feature that could cause unrecoverable data errors. 
• A fix for an issue where the drive could become unresponsive after a hard reset.

• New servo which disables a feature that could cause unrecoverable data errors. 
• A fix for an issue where the drive could become unresponsive after a hard reset.

This product addresses an iSCSI discovery failure with VLAN.

This product addresses an issue where an iSCSI portal is discovered with invalid an VLAN ID.

This product addresses an iSCSI discovery failure with VLAN.

This product addresses an issue where an iSCSI portal is discovered with invalid an VLAN ID.

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

Firmware Dependencies:

Problems Fixed:

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

Firmware Dependencies:

Problems Fixed:

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

This issue is only encounter when upgrading to version 2018.10.18 (5.5.0.66-1). All other versions are not affected

This issue is only encounter when upgrading to version 2018.10.18 (5.5.0.66-1). All other versions are not affected

• Fixed an issue that cause the firmware to hang when an FLR occurred at the same time as the teardown. As a result, the teardown flow took a lock, and never  released it because it was being aborted by an FLR.

Fixes in version 14.26.4012 :

• Updated the firmware behavior to report PLDM version 1.1.0 regardless of whether Redfish was enabled or not.
• Enabled the option to prevent clock and capture CPLD GPIOs glitch upon firmware reset.
• Fixed an issue that caused a function to misbehave when a PCIe Traffic Light Protocol(TLP) was set with a poisoned indication.
• Fixed a rare issue that resulted in “destroy mkey “ command getting stuck when rebooting the hypervisor.

Fixes in version 16.26.6000 :

• Fixed an issue that prevented PCI link from being established when the firmware was corrupted.
• Fixed an issue that triggered a firmware assert and resulted in a wrong deallocation of a resource when Packet Pacing was enabled, and a QP was being destroyed.
• Fixed an issue that cause the firmware to hang when an FLR occurred at the same time as the teardown. As a result, the teardown flow took a lock, and never  released it because it was being aborted by an FLR.

Fixes in version 16.26.4012:

• Updated the firmware behavior to report PLDM version 1.1.0 regardless of whether Redfish was enabled or not.
• Enabled the option to prevent clock and capture CPLD GPIOs glitch upon firmware reset.
• Fixed an issue that slowed the firmware flows when executing many destroy XRQ commands on an XRQ that supported DC transport service.
• Fixed an issue that caused performance degradation when working in dual-port devices under bidirectional traffic stress.
• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Fixed an issue that resulted in unexpected queue pairs transitioned to error in lossy tests.
• Limited the maximum amount of dumps created on a Physical Function(PF).
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Fixed a stability issue in RoCE retransmissions under stress affecting Zero-Touch-RoCE.
• Fixed an issue that caused a function to misbehave when a PCIe TLP was set with a poisoned indication.
• Fixed an issue that caused large number of packet to drop when running Jumbo frames with Time to live (TTL) rewrite
• Limited the number of the elements in the QoS tree 2K. Creating more than 250 Vport_tc for every TC was not allowed
• Fixed the query QP flow. Instead of always taking port 1, FW will now reply the proper port, 1 or 2, for the dual port RDMA over Converged Ethernet(RoCE) net device.
• Fixed an issue that caused the nack counters to constantly be reported as “0”. 
• In a rare scenario when the driver was executing the "2err" command and th Queue pair(QP) was in SQ drain state, the firmware might post event of broken Work Queue (WQ) instead of sending error CQEs on all the WQEs.

• Fixed an issue that cause the firmware to hang when an FLR occurred at the same time as the teardown. As a result, the teardown flow took a lock, and never  released it because it was being aborted by an FLR.

Fixes in version 14.26.4012 :

• Updated the firmware behavior to report PLDM version 1.1.0 regardless of whether Redfish was enabled or not.
• Enabled the option to prevent clock and capture CPLD GPIOs glitch upon firmware reset.
• Fixed an issue that caused a function to misbehave when a PCIe Traffic Light Protocol(TLP) was set with a poisoned indication.
• Fixed a rare issue that resulted in “destroy mkey “ command getting stuck when rebooting the hypervisor.

Fixes in version 16.26.6000 :

• Fixed an issue that prevented PCI link from being established when the firmware was corrupted.
• Fixed an issue that triggered a firmware assert and resulted in a wrong deallocation of a resource when Packet Pacing was enabled, and a QP was being destroyed.
• Fixed an issue that cause the firmware to hang when an FLR occurred at the same time as the teardown. As a result, the teardown flow took a lock, and never  released it because it was being aborted by an FLR.

Fixes in version 16.26.4012:

• Updated the firmware behavior to report PLDM version 1.1.0 regardless of whether Redfish was enabled or not.
• Enabled the option to prevent clock and capture CPLD GPIOs glitch upon firmware reset.
• Fixed an issue that slowed the firmware flows when executing many destroy XRQ commands on an XRQ that supported DC transport service.
• Fixed an issue that caused performance degradation when working in dual-port devices under bidirectional traffic stress.
• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Fixed an issue that resulted in unexpected queue pairs transitioned to error in lossy tests.
• Limited the maximum amount of dumps created on a Physical Function(PF).
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Fixed a stability issue in RoCE retransmissions under stress affecting Zero-Touch-RoCE.
• Fixed an issue that caused a function to misbehave when a PCIe TLP was set with a poisoned indication.
• Fixed an issue that caused large number of packet to drop when running Jumbo frames with Time to live (TTL) rewrite
• Limited the number of the elements in the QoS tree 2K. Creating more than 250 Vport_tc for every TC was not allowed
• Fixed the query QP flow. Instead of always taking port 1, FW will now reply the proper port, 1 or 2, for the dual port RDMA over Converged Ethernet(RoCE) net device.
• Fixed an issue that caused the nack counters to constantly be reported as “0”. 
• In a rare scenario when the driver was executing the "2err" command and th Queue pair(QP) was in SQ drain state, the firmware might post event of broken Work Queue (WQ) instead of sending error CQEs on all the WQEs.

• Updated the firmware behavior to report PLDM version 1.1.0 regardless of whether Redfish was enabled or not.
• Enabled the option to prevent clock and capture CPLD GPIOs glitch upon firmware reset.

Fixes in version 14.26.1040 :

• Fixed an issue that caused a function to misbehave when a PCIe Traffic Light Protocol(TLP) was set with a poisoned indication.
• Fixed a rare issue that resulted in “destroy mkey “ command getting stuck when rebooting the hypervisor.

Fixes in version 16.26.2002 :

• Updated the firmware behavior to report PLDM version 1.1.0 regardless of whether Redfish was enabled or not.
• Enabled the option to prevent clock and capture CPLD GPIOs glitch upon firmware reset.
• Fixed an issue that slowed the firmware flows when executing many destroy XRQ commands on an XRQ that supported DC transport service.
• Fixed an issue that caused performance degradation when working in dual-port devices under bidirectional traffic stress.

Fixes in version 16.26.1040 :

• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Fixed an issue that resulted in unexpected queue pairs transitioned to error in lossy tests.
• Limited the maximum amount of dumps created on a Physical Function(PF).
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Fixed a stability issue in RoCE retransmissions under stress affecting Zero-Touch-RoCE.
• Fixed an issue that caused a function to misbehave when a PCIe TLP was set with a poisoned indication.
• Fixed an issue that caused large number of packet to drop when running Jumbo frames with Time to live (TTL) rewrite
• Limited the number of the elements in the QoS tree 2K. Creating more than 250 Vport_tc for every TC was not allowed
• Fixed the query QP flow. Instead of always taking port 1, FW will now reply the proper port, 1 or 2, for the dual port RDMA over Converged Ethernet(RoCE) net device.
• Fixed an issue that caused the nack counters to constantly be reported as “0”. 
• In a rare scenario when the driver was executing the "2err" command and th Queue pair(QP) was in SQ drain state, the firmware might post event of broken Work Queue (WQ) instead of sending error CQEs on all the WQEs.

• Updated the firmware behavior to report PLDM version 1.1.0 regardless of whether Redfish was enabled or not.
• Enabled the option to prevent clock and capture CPLD GPIOs glitch upon firmware reset.

Fixes in version 14.26.1040 :

• Fixed an issue that caused a function to misbehave when a PCIe Traffic Light Protocol(TLP) was set with a poisoned indication.
• Fixed a rare issue that resulted in “destroy mkey “ command getting stuck when rebooting the hypervisor.

Fixes in version 16.26.2002 :

• Updated the firmware behavior to report PLDM version 1.1.0 regardless of whether Redfish was enabled or not.
• Enabled the option to prevent clock and capture CPLD GPIOs glitch upon firmware reset.
• Fixed an issue that slowed the firmware flows when executing many destroy XRQ commands on an XRQ that supported DC transport service.
• Fixed an issue that caused performance degradation when working in dual-port devices under bidirectional traffic stress.

Fixes in version 16.26.1040 :

• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Fixed an issue that resulted in unexpected queue pairs transitioned to error in lossy tests.
• Limited the maximum amount of dumps created on a Physical Function(PF).
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Fixed a stability issue in RoCE retransmissions under stress affecting Zero-Touch-RoCE.
• Fixed an issue that caused a function to misbehave when a PCIe TLP was set with a poisoned indication.
• Fixed an issue that caused large number of packet to drop when running Jumbo frames with Time to live (TTL) rewrite
• Limited the number of the elements in the QoS tree 2K. Creating more than 250 Vport_tc for every TC was not allowed
• Fixed the query QP flow. Instead of always taking port 1, FW will now reply the proper port, 1 or 2, for the dual port RDMA over Converged Ethernet(RoCE) net device.
• Fixed an issue that caused the nack counters to constantly be reported as “0”. 
• In a rare scenario when the driver was executing the "2err" command and th Queue pair(QP) was in SQ drain state, the firmware might post event of broken Work Queue (WQ) instead of sending error CQEs on all the WQEs.

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

Firmware Dependencies:

Problems Fixed:

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

Firmware Dependencies:

Problems Fixed:

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

Firmware Dependencies:

Problems Fixed:

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

Firmware Dependencies:

Problems Fixed:

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

• IPoIB could not to function when there were Dynamically Connected Transport (DC) CNAK Queue Pairs (QPs) active.
• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.

Fixes submitted in version 16.26.1040:

• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Unexpected queue pairs transitioned to error in lossy tests.
• Limited the maximum amount of dumps created on a PF.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Stability issues with RDMA over Converged Ethernet (RoCE) retransmissions under stress were affecting Zero-Touch-RoCE.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.
• Large number of packets dropped when running Jumbo frames with TTL rewrite.
• Limited the number of the elements in the Quality of Service (QoS) tree 2K.
  Note: Creating more than 250 Vport_tc for every TC is not allowed.
• Queue Pair (QP) flow query was always taking port 1, Firmware will now reply the proper port, 1 or 2, for the dual port RoCE net device.
• The nack counters constantly reported as “0”.
• In a rare scenario when the driver is executing the "2err" command and the QP is in Send Queue (SQ) drain state, the firmware might post event of broken Work Queue (WQ) instead of sending error Completion Queue Element (CQEs) on all the Work Queue Entry (WQEs).

• IPoIB could not to function when there were Dynamically Connected Transport (DC) CNAK Queue Pairs (QPs) active.
• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.

Fixes submitted in version 16.26.1040:

• On rare occasions, when firmware coalesce Host stuck events occur, a async event might be delayed to be reported, and not be triggered until the next time the PCIe hangs on one of the hosts.
• Unexpected queue pairs transitioned to error in lossy tests.
• Limited the maximum amount of dumps created on a PF.
• Renamed the GMP Mellanox Vendor Specific External Capability mask enum from IsDiagnosticCountersSupported to IsDiagnosticDataSupported.
• Stability issues with RDMA over Converged Ethernet (RoCE) retransmissions under stress were affecting Zero-Touch-RoCE.
• Fixed an issue that caused a function to misbehave when a PCIe Transaction Layer Packet (TLP) was set with a poisoned indication.
• Large number of packets dropped when running Jumbo frames with TTL rewrite.
• Limited the number of the elements in the Quality of Service (QoS) tree 2K.
  Note: Creating more than 250 Vport_tc for every TC is not allowed.
• Queue Pair (QP) flow query was always taking port 1, Firmware will now reply the proper port, 1 or 2, for the dual port RoCE net device.
• The nack counters constantly reported as “0”.
• In a rare scenario when the driver is executing the "2err" command and the QP is in Send Queue (SQ) drain state, the firmware might post event of broken Work Queue (WQ) instead of sending error Completion Queue Element (CQEs) on all the Work Queue Entry (WQEs).

• mlxconfig tool reported all possible expansion ROM images, instead of presenting only the existing images.
• Modifying VMQoS rate limiter parameters during traffic caused transmission failure.
• Aligned the default tuning type in PHY TEST MODE to the device protocol.
• When a device is operating in Safe Mode state, and the user issues the mlxfwreset command, the device might fail to come-up correctly after the reset.
  Note: Do not run mlxfwreset when operating in a Safe Mode state.
• Fixed an issue related to PCIe "Surprise link down" event reporting capability.
• Fixed an issue that resulted in the link partner experiencing false active linkup when plugging in a base-T cable to a closed port.

Fixes in version 12.24.1000:

• Fixed an issue that caused the max_qp_retry_freq_exceeded counter (including a CQE with error syndrome 0x97, and the QP moving to error state) to be activated only after exceeding the NIC Vport context max_qp_retry_limit, and not when reaching it.

Fixes in version 16.24.1000:

• PCIe bifurcation issue.
• Deadlock in RX related to the “send-invalidate” flow, resulted in RX getting stuck.
• Rare errors in RX that resulted in double completion.

• mlxconfig tool reported all possible expansion ROM images, instead of presenting only the existing images.
• Modifying VMQoS rate limiter parameters during traffic caused transmission failure.
• Aligned the default tuning type in PHY TEST MODE to the device protocol.
• When a device is operating in Safe Mode state, and the user issues the mlxfwreset command, the device might fail to come-up correctly after the reset.
  Note: Do not run mlxfwreset when operating in a Safe Mode state.
• Fixed an issue related to PCIe "Surprise link down" event reporting capability.
• Fixed an issue that resulted in the link partner experiencing false active linkup when plugging in a base-T cable to a closed port.

Fixes in version 12.24.1000:

• Fixed an issue that caused the max_qp_retry_freq_exceeded counter (including a CQE with error syndrome 0x97, and the QP moving to error state) to be activated only after exceeding the NIC Vport context max_qp_retry_limit, and not when reaching it.

Fixes in version 16.24.1000:

• PCIe bifurcation issue.
• Deadlock in RX related to the “send-invalidate” flow, resulted in RX getting stuck.
• Rare errors in RX that resulted in double completion.

o   For additional information, reference Customer Bulletin a00097210en_us.

IMPORTANT: RAID 0 and Unassigned drives are not affected.

o   For additional information, reference Customer Bulletin a00097210en_us.

IMPORTANT: RAID 0 and Unassigned drives are not affected.

Please reference Customer Advisory a00095304en_us.

Please reference Customer Advisory a00095304en_us.

Please reference Customer Advisory SIK5264.

Please reference Customer Advisory SIK5264.

• HPG6 firmware improves drive reliability where disk drives are exposed to long periods of host inactivity which exceed 1 second.
• Online firmware update fails when drives are connected behind AHCI controller.

• HPG6 firmware improves drive reliability where disk drives are exposed to long periods of host inactivity which exceed 1 second.
• Online firmware update fails when drives are connected behind AHCI controller.

• TBD
• TBD

• TBD
• TBD

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

Firmware Dependencies:

Problems Fixed:

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

Firmware Dependencies:

Problems Fixed:

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

This product addresses an iSCSI discovery failure with VLAN.

This product addresses an issue where an iSCSI portal is discovered with invalid an VLAN ID.

This product addresses an iSCSI discovery failure with VLAN.

This product addresses an issue where an iSCSI portal is discovered with invalid an VLAN ID.

• Modified the loop initial values in hpasmcli from 2 to 0.
• Modifications to check the read and write variables to match RBSU in Legacy and UEFI mode
• Updated the hpasmcli check string to correctly report the impitool information

• Modified the loop initial values in hpasmcli from 2 to 0.
• Modifications to check the read and write variables to match RBSU in Legacy and UEFI mode
• Updated the hpasmcli check string to correctly report the impitool information

In extremely rare cases, the following QLogic Fibre Channel (FC) Host Bus Adapters (HBAs), SN1100Q, SN1600Q and SN1610Q may cause the host Operating System (OS) to stop. Subsequent OS reboot may reveal some filesystem data is unavailable or inconsistent. Out of an abundance of caution, HPE updated the Firmware/BIOS/UEFI (Boot Image) packages for these adapters to eliminate possible exposure to this extremely rare but critical issue.

Additional issue details will be published when they become available.

In extremely rare cases, the following QLogic Fibre Channel (FC) Host Bus Adapters (HBAs), SN1100Q, SN1600Q and SN1610Q may cause the host Operating System (OS) to stop. Subsequent OS reboot may reveal some filesystem data is unavailable or inconsistent. Out of an abundance of caution, HPE updated the Firmware/BIOS/UEFI (Boot Image) packages for these adapters to eliminate possible exposure to this extremely rare but critical issue.

Additional issue details will be published when they become available.

In extremely rare cases, the following QLogic Fibre Channel (FC) Host Bus Adapters (HBAs), SN1100Q, SN1600Q and SN1610Q may cause the host Operating System (OS) to stop. Subsequent OS reboot may reveal some filesystem data is unavailable or inconsistent. Out of an abundance of caution, HPE updated the Firmware/BIOS/UEFI (Boot Image) packages for these adapters to eliminate possible exposure to this extremely rare but critical issue.

Additional issue details will be published when they become available.

In extremely rare cases, the following QLogic Fibre Channel (FC) Host Bus Adapters (HBAs), SN1100Q, SN1600Q and SN1610Q may cause the host Operating System (OS) to stop. Subsequent OS reboot may reveal some filesystem data is unavailable or inconsistent. Out of an abundance of caution, HPE updated the Firmware/BIOS/UEFI (Boot Image) packages for these adapters to eliminate possible exposure to this extremely rare but critical issue.

Additional issue details will be published when they become available.

This product addresses an issue where boot mode is not restored to the default value after a factory reset.

This product addresses an issue where the F1 help messages "Number of VFs per PF" and "Legacy Boot Protocol" option display incorrectly in Japanese and Simplified Chinese languages.

This product addresses an issue where boot mode is not restored to the default value after a factory reset.

This product addresses an issue where the F1 help messages "Number of VFs per PF" and "Legacy Boot Protocol" option display incorrectly in Japanese and Simplified Chinese languages.

Please reference Customer Advisory a00095304en_us.

Please reference Customer Advisory a00095304en_us.

Please reference Customer Advisory SIK5264.

Please reference Customer Advisory SIK5264.

This product now correctly loads on the 16th port of a 16-port device.

This product now correctly loads on the 16th port of a 16-port device.

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

This product addresses an issue where the ixgben driver has high CPU overhead when an SFP+ module is absent.

This product addresses an issue where the ixgben driver has high CPU overhead when an SFP+ module is absent.

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

None

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

None

• ​Drive models XP0032GEFEN, XP0032GDZME, XP0064GDZMF, and XP0064GEFEP must have firmware version HPS6 installed prior to updating to firmware version HPS8.

Problems Fixed:

• HPS8 firmware release resolved a firmware timing issue which occurred during drive long self-test and resulted in a timeout condition that caused the drive to become unrecognized by the system.
• Online firmware update fails when drives are connected behind AHCI controller.

Problems Fixed for HPS8 (B):

• When attempting to update drive firmware in a VMware vSphere 6.5 environment, the update would fail and the event was logged as a segmentation fault error.

• ​Drive models XP0032GEFEN, XP0032GDZME, XP0064GDZMF, and XP0064GEFEP must have firmware version HPS6 installed prior to updating to firmware version HPS8.

Problems Fixed:

• HPS8 firmware release resolved a firmware timing issue which occurred during drive long self-test and resulted in a timeout condition that caused the drive to become unrecognized by the system.
• Online firmware update fails when drives are connected behind AHCI controller.

Problems Fixed for HPS8 (B):

• When attempting to update drive firmware in a VMware vSphere 6.5 environment, the update would fail and the event was logged as a segmentation fault error.

Firmware Dependencies:

Problems Fixed:

This revision of the System ROM includes the latest revision of the Intel microcode which provides mitigation for an Intel sighting where under complex micro-architectural conditions, executing X87 or AVX or integer divide instructions may results in unpredictable system behavior. This issue is not unique to HPE servers.

Known Issues:

Firmware Dependencies:

Problems Fixed:

This revision of the System ROM includes the latest revision of the Intel microcode which provides mitigation for an Intel sighting where under complex micro-architectural conditions, executing X87 or AVX or integer divide instructions may results in unpredictable system behavior. This issue is not unique to HPE servers.

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-0151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

Known Issues:

None

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

None

None

Firmware Dependencies:

None

Problems Fixed:

This revision of the System ROM includes the latest support for Intel Trusted eXecution Technology (TXT) which provides mitigation for CVE-2019-151. This mitigation is only needed for systems that have TXT enabled (TXT is disabled by default). This issue is not unique to HPE servers.

This revision of the System ROM includes the latest revision of the Intel Reference Code support that provides mitigation for CVE-2019-11137. This issue is not unique to HPE servers.

Known Issues:

None

Firmware Dependencies:

Problems Fixed:

This revision of the System ROM includes the latest revision of the Intel microcode which provides mitigation for an Intel sighting where under complex micro-architectural conditions, executing X87 or AVX or integer divide instructions may results in unpredictable system behavior. This issue is not unique to HPE servers.

Known Issues:

Firmware Dependencies:

Problems Fixed:

This revision of the System ROM includes the latest revision of the Intel microcode which provides mitigation for an Intel sighting where under complex micro-architectural conditions, executing X87 or AVX or integer divide instructions may results in unpredictable system behavior. This issue is not unique to HPE servers.

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

Firmware Dependencies:

Problems Fixed:

Known Issues:

These drivers have been recompiled with a build setting that allows SUM to identify them correctly for installation on systems they support.

These drivers have been recompiled with a build setting that allows SUM to identify them correctly for installation on systems they support.

• When using OneView, attempts to upgrade firmware from version 1.18 to 1.20 failed.

Note: If the target device was previously updated to firmware version 1.20, it is not necessary to apply firmware update 1.20(C).

• When using OneView, attempts to upgrade firmware from version 1.18 to 1.20 failed.

Note: If the target device was previously updated to firmware version 1.20, it is not necessary to apply firmware update 1.20(C).

• Modified the loop initial values in hpasmcli from 2 to 0.
• Modifications to check the read and write variables to match RBSU in Legacy and UEFI mode
• Updated the hpasmcli check string to correctly report the impitool information

• Modified the loop initial values in hpasmcli from 2 to 0.
• Modifications to check the read and write variables to match RBSU in Legacy and UEFI mode
• Updated the hpasmcli check string to correctly report the impitool information

o   For additional information, reference Customer Bulletin a00097210en_us.

IMPORTANT: RAID 0 and Unassigned drives are not affected.

o   For additional information, reference Customer Bulletin a00097210en_us.

IMPORTANT: RAID 0 and Unassigned drives are not affected.

This product addresses an issue where the ixgben driver has high CPU overhead when an SFP+ module is absent.

This product addresses an issue where the ixgben driver has high CPU overhead when an SFP+ module is absent.

None

Firmware Dependencies:

None

Problems Fixed:

Addressed an issue where the system would never enter Data Fabric C-States.  Data Fabric C-States can help reduce overall power consumption of a system that is running an idle or low stress workload.

Addressed an issue where the system would report the HPE Memory Type as Unknown.  This was only an issue with reporting and did not affect system behavior.

Addressed an issue where RestCli or a Redfish "Get" command could return some invalid configuration settings.

Addressed an issue where systems configured with an UBM backplane may very rarely become unresponsive during post with a red error screen (RSOD) indicating a general protection fault in the PlatformStorageSupportDxe Image.

Addressed an issue where systems configured with an UBM backplane will not honor a customer configured One-Time boot setting.

Known Issues:

None

None

Firmware Dependencies:

None

Problems Fixed:

Addressed an issue where the system would never enter Data Fabric C-States.  Data Fabric C-States can help reduce overall power consumption of a system that is running an idle or low stress workload.

Addressed an issue where the system would report the HPE Memory Type as Unknown.  This was only an issue with reporting and did not affect system behavior.

Addressed an issue where RestCli or a Redfish "Get" command could return some invalid configuration settings.

Addressed an issue where systems configured with an UBM backplane may very rarely become unresponsive during post with a red error screen (RSOD) indicating a general protection fault in the PlatformStorageSupportDxe Image.

Addressed an issue where systems configured with an UBM backplane will not honor a customer configured One-Time boot setting.

Known Issues:

None