Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

ファームウェアの依存関係：

機能強化/新しい機能：

このバージョンは、Intel uPLR1ガイダンスに準拠しています。

既知の問題点：

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR1 guidance.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

ファームウェアの依存関係：

機能強化/新しい機能：

このバージョンは、Intel uPLR1ガイダンスに準拠しています。

既知の問題点：

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR1 guidance.

Known Issues:

Red Hat Enterprise Linux 9.5

14.4.329.9にアップデートされたバージョン

Red Hat Enterprise Linux 9.5

Version updated to 14.4.329.9

Red Hat Enterprise Linux 9.5

ドライバーをバージョン10.02.13.00-k1にアップデートしました 

Red Hat Enterprise Linux 9.5

Updated Driver version 10.02.13.00-k1 

• RESTおよびHPE iLO UIの背面のOCPAおよびOCPBラベルの名前をOCPスロットA およびOCPスロット Bに変更しました。

• HPE iLO Redfishがエアフィルターの交換に関する明確なイベント通知を発行する機能。

• Azure Stack HCI 23H2 OSのサポート。

• HPE ブランドガイドラインに準拠しました。

• HPE iLOにHPE Compute Ops Managementを含むHPE ProLiant Advancedライセンスの追加。

• 仮想メディアマウントのURLの長さのサポートが1023文字に増加しました。

• Renamed the rear OCPA and OCPB labeling in REST and HPE iLO UI to OCP Slot A and OCP Slot B.

• Ability of HPE iLO Redfish to raise a clear event notification for an air filter replacement.

• Support for Azure Stack HCI 23H2 OS.

• Adhered to HPE branding guidelines.

• Addition of HPE ProLiant Advanced License to HPE iLO with HPE Compute Ops Management.

• Support for the Virtual Media Mount URL length increased to 1023 characters.

• RESTおよびHPE iLO UIの背面のOCPAおよびOCPBラベルの名前をOCPスロットA およびOCPスロット Bに変更しました。

• HPE iLO Redfishがエアフィルターの交換に関する明確なイベント通知を発行する機能。

• Azure Stack HCI 23H2 OSのサポート。

• HPE ブランドガイドラインに準拠しました。

• HPE iLOにHPE Compute Ops Managementを含むHPE ProLiant Advancedライセンスの追加。

• 仮想メディアマウントのURLの長さのサポートが1023文字に増加しました。

• Renamed the rear OCPA and OCPB labeling in REST and HPE iLO UI to OCP Slot A and OCP Slot B.

• Ability of HPE iLO Redfish to raise a clear event notification for an air filter replacement.

• Support for Azure Stack HCI 23H2 OS.

• Adhered to HPE branding guidelines.

• Addition of HPE ProLiant Advanced License to HPE iLO with HPE Compute Ops Management.

• Support for the Virtual Media Mount URL length increased to 1023 characters.

Red Hat Enterprise Linux 9.5

ドライバーをバージョン10.02.12.01-k1にアップデートしました

Red Hat Enterprise Linux 9.5

Updated Driver version 10.02.12.01-k1

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

ファームウェアの依存関係：

機能強化/新しい機能：

このバージョンは、Intel uPLR1ガイダンスに準拠しています。

既知の問題点：

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR1 guidance.

Known Issues:

Red Hat Enterprise Linux 9.5

ドライバーをバージョン10.02.12.01-k1にアップデートしました

Red Hat Enterprise Linux 9.5

Updated Driver version 10.02.12.01-k1

This product enhanced the compatibility with the latest drivers.

This product enhanced the compatibility with the latest drivers.

This product enhanced the compatibility with the latest drivers.

This product enhanced the compatibility with the latest drivers.

Red Hat Enterprise Linux 9.5

ドライバーをバージョン10.02.12.01-k1にアップデートしました

Red Hat Enterprise Linux 9.5

Updated Driver version 10.02.12.01-k1

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

ファームウェアの依存関係：

機能強化/新しい機能：

このバージョンは、Intel uPLR1ガイダンスに準拠しています。

既知の問題点：

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR1 guidance.

Known Issues:

• Increased the RX lossless buffer size to delay the transmission of Pause/PFC frames during NIC congestion.
• Added support for SyncE at 1G link speed.
• Added a new mechanism for allocations and deallocations flows to enhance parallelism.
• When using a multi-host deployment, each host is assigned unique ports and PFs and manages its own LAG.
• Added support for a new synchronized flow, including a tool and driver, to perform a fwreset on setups with a PCIe switch configuration.
• Unified PTP is now supported across different VFs on the same PF.
• Added support for new MADs: PortRecoveryPolicyConfig and PortRecoveryPolicyCounters . During the PHY recovery process, the firmware core will indicate the  port_logical_state as Active.
• Added a new NV config (SM_DISABLE, default 0) which, when enabled, blocks SMP traffic that does not originate from the SM.
• Added the ability to set cable length as a parameter in the PFCC access register. The cable length is used in the calculation of RX lossless buffer parameters, including size, Xoff, and Xon thresholds.

• Increased the RX lossless buffer size to delay the transmission of Pause/PFC frames during NIC congestion.
• Added support for SyncE at 1G link speed.
• Added a new mechanism for allocations and deallocations flows to enhance parallelism.
• When using a multi-host deployment, each host is assigned unique ports and PFs and manages its own LAG.
• Added support for a new synchronized flow, including a tool and driver, to perform a fwreset on setups with a PCIe switch configuration.
• Unified PTP is now supported across different VFs on the same PF.
• Added support for new MADs: PortRecoveryPolicyConfig and PortRecoveryPolicyCounters . During the PHY recovery process, the firmware core will indicate the  port_logical_state as Active.
• Added a new NV config (SM_DISABLE, default 0) which, when enabled, blocks SMP traffic that does not originate from the SM.
• Added the ability to set cable length as a parameter in the PFCC access register. The cable length is used in the calculation of RX lossless buffer parameters, including size, Xoff, and Xon thresholds.

• PCIeテレメトリ (NSMタイプ2) のサポートが追加されました。
• PCC NPソリューションをACEハードウェアプラットフォームからDPAハードウェアプラットフォームに移行しました。新しい機能は、次のモードに適用できます: 1) PCC_INT_EN=TrueかつPCC_INT_NP_RTT_DATA_MODE=INGRESS_BYTE 2) PCC_INT_EN=TrueかつPCC_INT_NP_RTT_DATA_MODE=NO_DATA。最初のモードは、RTT応答でZTRCC RXバイトをサポートするために使用されます。
• eSwitchマネージャーごとに選択されたすべての機能でエラーCQEイベントを示すオプションが追加されました。この表示は、エラーに関する関連情報 (シンドローム、function_id、タイムスタンプ、QP番号など) を含む新しいWQEとして定義されます。
• 拡張カーネルロックダウン権限セット。新しいHCA機能ビットマスクフィールドtool_partial_capを使用して、ツール (権限TOOLS_RESORCES) によって次のサブ操作を呼び出すことができるようになりました。

5つのサブ操作は次のとおりです。

• QUERY_HCA_CAPと他の機能
• QUERY_VUIDと直接データ
• QUERY_ROCE_ADDRESSと他のvport
• SET_HCA_CAPと他の機能
• POSTPONE_CONNECTED_QP_TIMEOUTと他のvport

新しく追加された機能は次のとおりです。

• tool_partial_cap.postpone_conn_qp_timeout_other_vport,
• tool_partial_cap.set_hca_cap_other_func
• tool_partial_cap.query_roce_addr_other_vport
• tool_partial_cap.query_vuid_direct_data
• tool_partial_cap.query_hca_cap_other_func

• LAGにグループ化された複数のE-SwitchにわたるQoSスケジューリングのサポートが追加されました。ある物理機能のVPortメンバーを、別の物理機能からのレートグループに追加することができ、グループのレート制限はそれらのVPortメンバーにも適用されます。
• ステアリングアクション (STC) の"Jump To Flow"テーブルパラメーターに'table_type_valid'および'table_type'フィールドが追加され、ユーザーがNIC_TXからFDB_TXにジャンプしてACLテーブルをバイパスできるようになりました。
• さまざまなユースケースでNICドメインをバイパスすることでホップ削減を可能にしました。このようなアクションにより、大量のフローとデバイスを処理するためのホップ数が削減されます (PPSが向上します)。この新しい機能を有効にするために、テーブルのRX側にジャンプできるようにする新しいSTCアクションタイプ"JUMP_TO_FDB_RX"が追加されました。
• 動的フレックスパーサーでサポートされる"ARC-IN"の最大数を1から8に、"ARC-OUT"の最大数を3から8に増やしました。
• PCC ZTR_RTTCにレートとラウンドトリップ時間 (RTT) のヒストグラムサポートが追加されました。
• VF移行中にCQドアベルが失われた場合に備えて回復手順を追加しました。
• VGAゲインとCTLEのためのPCIe Gen4/5の新しい静的構成を変更しました。
• Gen4/5開始点のCTLEおよびVGAゲインを変更しました。
• SPDMのRDT値を増加しました。

• Added support for PCIe Telemetry (NSM Type 2).
• Migrated PCC NP solution from ACE hardware platform to DPA hardware platform. The new capability is applicable to the following modes: 1) PCC_INT_EN=True and PCC_INT_NP_RTT_DATA_MODE=INGRESS_BYTE 2) PCC_INT_EN=True and PCC_INT_NP_RTT_DATA_MODE=NO_DATA. The first mode is used to support ZTRCC RX bytes in RTT response.
• Added the option to indicate an error CQE event on every selected function per eSwitch manager. This indication is defined as a new WQE including the relevant information about the error (such as: syndrome, function_id, timestamp, QPs num etc.).
• Extended kernel lockdown permission set. The following sub-operations can now be called by tools (permission TOOLS_RESORCES) using new HCA capability bitmask field: tool_partial_cap.

The 5 sub-operations are:

• QUERY_HCA_CAP with other function
• QUERY_VUID with direct data
• QUERY_ROCE_ADDRESS with other vport
• SET_HCA_CAP with other function
• POSTPONE_CONNECTED_QP_TIMEOUT with other vport

The new added caps are:

• tool_partial_cap.postpone_conn_qp_timeout_other_vport,
• tool_partial_cap.set_hca_cap_other_func
• tool_partial_cap.query_roce_addr_other_vport
• tool_partial_cap.query_vuid_direct_data
• tool_partial_cap.query_hca_cap_other_func

• Added support for QoS scheduling across multiple E-Switches grouped in a LAG. VPort members of a Physical Function can be added to a rate group from another Physical Function and rate limits of the group will apply to those VPort members as well.
• Added 'table_type_valid' and 'table_type' fields to the steering action (STC) "Jump To Flow" table parameters to enable the user to jump from NIC_TX to FDB_TX and bypass the ACL table.
• Enabled hop reduction by bypassing NIC domain in various use cases. Such action reduces the number of hops (improves PPS) to deal with mass number of flows and devices. To enable this new capability, a new STC action type "JUMP_TO_FDB_RX" was added to allow jumping into the RX side of a table.
• Increased the maximum number of supported "ARC-IN" from 1 to 8 and "ARC-OUT" from 3 to 8 for the dynamic flex parser.
• Added histogram support for rate and Round-Trip Time (RTT) in PCC ZTR_RTTC.
• Added a recovery step in case of CQ doorbell getting lost during VF migration.
• Changed PCIe Gen4/5 new static configuration for VGA gain and CTLE.
• Changed the CTLE and VGA gain for Gen4/5 starting point.
• Increased SPDM's RDT value.

o POST Storage.SetEncryptionKey

o PATCH Storage[EncryptionMode]

o PATCH/POST Volume[Encrypted]

• Note: MR controller support SED only. Therefore, Volume[EncryptionTypes] is not writeable during POST (Create) or PATCH (Update). Correspondingly the following Annotations are not populated:

a. EncryptionTypes@Redfish.AllowableValues (Volume Schema)

b. @Redfish.WriteableProperties[EncryptionTypes] (Volume Schema)

c. EncryptionTypes@Redfish.OptionalOnCreate (Volume Capabilities)

d. EncryptionTypes@Redfish.AllowableValues (Volume Capabilities)

e. EncryptionTypes@Redfish.UpdatableAfterCreate (Volume Capabilities)

o POST Volume.ForceEnable

o POST Drive.RevertToOriginalFactoryState

o Note:

• PATCH Volume[Encrypted] can be issued only with option ‘true’ on eligible volumes. PATCH Volume[Encrypted] with option ‘false’ will be failed because a secure volume cannot be changed to an unsecure volume in MR firmware.
• During POST (Create) ‘Encrypted’ option is not allowed for creating a volume with RAIDType=None. This is because MR does not support creating a secure JBOD in one step. After creating the JBOD, PATCH Volume[Encrypted = true] can be issued to create a secure JBOD.
• Whenever user requests to change to EKM, a reboot is a must to obtain the key via UEFI driver.
• Add MR408i-p support
• Added support for UBM10 backplanes
• Support UBM backplane FW version display and FW update when UBM controller is in bootloader state if there is an interruption during FW update
• Support NVMe SSD for Unmap capable Logical Drive. Please note that SATA SSD is not supported for Unmap capable Logical Drive.
• NAND flash refresh improvements

o The algorithm that posts the event "System reset required" after a specified number of days has been removed. The refresh happens after the same specified time and the new events are populated as below:

• Before starting the Nand flash refresh: “NAND refresh in progress: changing WB Logical Drives to WT”
• After the completion of Nand flash refresh: “NAND refresh complete: changing WT virtual disks to WB”
• The above behaviors are applicable only to MR400 controllers and are not applicable to MR200 controllers
• RAID1 Consistency Check Event String Change

o The Event String has been changed from "Consistency Check found inconsistent parity on LD <Ld Id> at strip <Strip Number>" to "Consistency Check found inconsistency on LD <Ld Id> at strip <Strip Number>".

• Support a new controller property, "Spin Down Drives At Shutdown", to control spindown of configured drives during shutdown
• Support for SCSI NVMe Translation Layer Specification version 1.14
• Added HPE ProLiant Compute DL380a Gen12 Server
• Support Decouple metadata 

o POST Storage.SetEncryptionKey

o PATCH Storage[EncryptionMode]

o PATCH/POST Volume[Encrypted]

• Note: MR controller support SED only. Therefore, Volume[EncryptionTypes] is not writeable during POST (Create) or PATCH (Update). Correspondingly the following Annotations are not populated:

a. EncryptionTypes@Redfish.AllowableValues (Volume Schema)

b. @Redfish.WriteableProperties[EncryptionTypes] (Volume Schema)

c. EncryptionTypes@Redfish.OptionalOnCreate (Volume Capabilities)

d. EncryptionTypes@Redfish.AllowableValues (Volume Capabilities)

e. EncryptionTypes@Redfish.UpdatableAfterCreate (Volume Capabilities)

o POST Volume.ForceEnable

o POST Drive.RevertToOriginalFactoryState

o Note:

• PATCH Volume[Encrypted] can be issued only with option ‘true’ on eligible volumes. PATCH Volume[Encrypted] with option ‘false’ will be failed because a secure volume cannot be changed to an unsecure volume in MR firmware.
• During POST (Create) ‘Encrypted’ option is not allowed for creating a volume with RAIDType=None. This is because MR does not support creating a secure JBOD in one step. After creating the JBOD, PATCH Volume[Encrypted = true] can be issued to create a secure JBOD.
• Whenever user requests to change to EKM, a reboot is a must to obtain the key via UEFI driver.
• Add MR408i-p support
• Added support for UBM10 backplanes
• Support UBM backplane FW version display and FW update when UBM controller is in bootloader state if there is an interruption during FW update
• Support NVMe SSD for Unmap capable Logical Drive. Please note that SATA SSD is not supported for Unmap capable Logical Drive.
• NAND flash refresh improvements

o The algorithm that posts the event "System reset required" after a specified number of days has been removed. The refresh happens after the same specified time and the new events are populated as below:

• Before starting the Nand flash refresh: “NAND refresh in progress: changing WB Logical Drives to WT”
• After the completion of Nand flash refresh: “NAND refresh complete: changing WT virtual disks to WB”
• The above behaviors are applicable only to MR400 controllers and are not applicable to MR200 controllers
• RAID1 Consistency Check Event String Change

o The Event String has been changed from "Consistency Check found inconsistent parity on LD <Ld Id> at strip <Strip Number>" to "Consistency Check found inconsistency on LD <Ld Id> at strip <Strip Number>".

• Support a new controller property, "Spin Down Drives At Shutdown", to control spindown of configured drives during shutdown
• Support for SCSI NVMe Translation Layer Specification version 1.14
• Added HPE ProLiant Compute DL380a Gen12 Server
• Support Decouple metadata 

o POST Storage.SetEncryptionKey
o PATCH Storage[EncryptionMode]
o PATCH/POST Volume[Encrypted]

• Note: MR controller support SED only. Therefore, Volume[EncryptionTypes] is not writeable during POST (Create) or PATCH (Update). Correspondingly the following Annotations are not populated:

a. EncryptionTypes@Redfish.AllowableValues (Volume Schema)

b. @Redfish.WriteableProperties[EncryptionTypes] (Volume Schema)

c. EncryptionTypes@Redfish.OptionalOnCreate (Volume Capabilities)

d. EncryptionTypes@Redfish.AllowableValues (Volume Capabilities)

e. EncryptionTypes@Redfish.UpdatableAfterCreate (Volume Capabilities)

o POST Volume.ForceEnable
o POST Drive.RevertToOriginalFactoryState
o Note:

• PATCH Volume[Encrypted] can be issued only with option ‘true’ on eligible volumes. PATCH Volume[Encrypted] with option ‘false’ will be failed because a secure volume cannot be changed to an unsecure volume in MR firmware.
• During POST (Create) ‘Encrypted’ option is not allowed for creating a volume with RAIDType=None. This is because MR does not support creating a secure JBOD in one step. After creating the JBOD, PATCH Volume[Encrypted = true] can be issued to create a secure JBOD.
• Whenever user requests to change to EKM, a reboot is a must to obtain the key via UEFI driver.
• Add MR408i-p support
• Added support for UBM10 backplanes
• Support UBM backplane FW version display and FW update when UBM controller is in bootloader state if there is an interruption during FW update
• Support NVMe SSD for Unmap capable Logical Drive. Please note that SATA SSD is not supported for Unmap capable Logical Drive.
• NAND flash refresh improvements

o The algorithm that posts the event "System reset required" after a specified number of days has been removed. The refresh happens after the same specified time and the new events are populated as below:

• Before starting the Nand flash refresh: “NAND refresh in progress:changing WB Logical Drives to WT”
• After the completion of Nand flash refresh: “NAND refresh complete changing WT virtual disks to WB”
• The above behaviors are applicable only to MR400 controllers and are not applicable to MR200 controllers
• RAID1 Consistency Check Event String Change

o The Event String has been changed from "Consistency Check found inconsistent parity on LD <Ld Id> at strip <Strip Number>" to "Consistency Check found inconsistency on LD <Ld Id> at strip <Strip Number>".

• Support a new controller property, "Spin Down Drives At Shutdown", to control spindown of configured drives during shutdown
• Support for SCSI NVMe Translation Layer Specification version 1.14

o POST Storage.SetEncryptionKey
o PATCH Storage[EncryptionMode]
o PATCH/POST Volume[Encrypted]

• Note: MR controller support SED only. Therefore, Volume[EncryptionTypes] is not writeable during POST (Create) or PATCH (Update). Correspondingly the following Annotations are not populated:

a. EncryptionTypes@Redfish.AllowableValues (Volume Schema)

b. @Redfish.WriteableProperties[EncryptionTypes] (Volume Schema)

c. EncryptionTypes@Redfish.OptionalOnCreate (Volume Capabilities)

d. EncryptionTypes@Redfish.AllowableValues (Volume Capabilities)

e. EncryptionTypes@Redfish.UpdatableAfterCreate (Volume Capabilities)

o POST Volume.ForceEnable
o POST Drive.RevertToOriginalFactoryState
o Note:

• PATCH Volume[Encrypted] can be issued only with option ‘true’ on eligible volumes. PATCH Volume[Encrypted] with option ‘false’ will be failed because a secure volume cannot be changed to an unsecure volume in MR firmware.
• During POST (Create) ‘Encrypted’ option is not allowed for creating a volume with RAIDType=None. This is because MR does not support creating a secure JBOD in one step. After creating the JBOD, PATCH Volume[Encrypted = true] can be issued to create a secure JBOD.
• Whenever user requests to change to EKM, a reboot is a must to obtain the key via UEFI driver.
• Add MR408i-p support
• Added support for UBM10 backplanes
• Support UBM backplane FW version display and FW update when UBM controller is in bootloader state if there is an interruption during FW update
• Support NVMe SSD for Unmap capable Logical Drive. Please note that SATA SSD is not supported for Unmap capable Logical Drive.
• NAND flash refresh improvements

o The algorithm that posts the event "System reset required" after a specified number of days has been removed. The refresh happens after the same specified time and the new events are populated as below:

• Before starting the Nand flash refresh: “NAND refresh in progress:changing WB Logical Drives to WT”
• After the completion of Nand flash refresh: “NAND refresh complete changing WT virtual disks to WB”
• The above behaviors are applicable only to MR400 controllers and are not applicable to MR200 controllers
• RAID1 Consistency Check Event String Change

o The Event String has been changed from "Consistency Check found inconsistent parity on LD <Ld Id> at strip <Strip Number>" to "Consistency Check found inconsistency on LD <Ld Id> at strip <Strip Number>".

• Support a new controller property, "Spin Down Drives At Shutdown", to control spindown of configured drives during shutdown
• Support for SCSI NVMe Translation Layer Specification version 1.14

バージョン20.43.1014には、以下の新機能と変更が含まれます。

• eSwitchマネージャーごとに選択されたすべての機能でエラーCQEイベントを示すオプションが追加されました。この表示は、エラーに関する関連情報 (シンドローム、function_id、タイムスタンプ、QP番号など) を含む新しいWQEとして定義されます。
• 拡張カーネルロックダウン権限セット。新しいHCA機能ビットマスクフィールドtool_partial_capを使用して、ツール (権限TOOLS_RESORCES) によって次のサブ操作を呼び出すことができるようになりました。

5つのサブ操作は次のとおりです。

• QUERY_HCA_CAPと他の機能
• QUERY_VUIDと直接データ
• QUERY_ROCE_ADDRESSと他のvport
• SET_HCA_CAPと他の機能
• POSTPONE_CONNECTED_QP_TIMEOUTと他のvport

新しく追加された機能は次のとおりです。

• tool_partial_cap.postpone_conn_qp_timeout_other_vport,
• tool_partial_cap.set_hca_cap_other_func
• tool_partial_cap.query_roce_addr_other_vport
• tool_partial_cap.query_vuid_direct_data
• tool_partial_cap.query_hca_cap_other_func

New features and changes included in version 20.43.1014:

• Added the option to indicate an error CQE event on every selected function per eSwitch manager. This indication is defined as a new WQE including the relevant information about the error (such as: syndrome, function_id, timestamp, QPs num etc.).
• Extended kernel lockdown permission set. The following sub-operations can now be called by tools (permission TOOLS_RESORCES) using new HCA capability bitmask field: tool_partial_cap.

The 5 sub-operations are:

• QUERY_HCA_CAP with other function
• QUERY_VUID with direct data
• QUERY_ROCE_ADDRESS with other vport
• SET_HCA_CAP with other function
• POSTPONE_CONNECTED_QP_TIMEOUT with other vport

The new added caps are:

• tool_partial_cap.postpone_conn_qp_timeout_other_vport,
• tool_partial_cap.set_hca_cap_other_func
• tool_partial_cap.query_roce_addr_other_vport
• tool_partial_cap.query_vuid_direct_data
• tool_partial_cap.query_hca_cap_other_func

バージョン20.43.1014には、以下の新機能と変更が含まれます。

• eSwitchマネージャーごとに選択されたすべての機能でエラーCQEイベントを示すオプションが追加されました。この表示は、エラーに関する関連情報 (シンドローム、function_id、タイムスタンプ、QP番号など) を含む新しいWQEとして定義されます。
• 拡張カーネルロックダウン権限セット。新しいHCA機能ビットマスクフィールドtool_partial_capを使用して、ツール (権限TOOLS_RESORCES) によって次のサブ操作を呼び出すことができるようになりました。

5つのサブ操作は次のとおりです。

• QUERY_HCA_CAPと他の機能
• QUERY_VUIDと直接データ
• QUERY_ROCE_ADDRESSと他のvport
• SET_HCA_CAPと他の機能
• POSTPONE_CONNECTED_QP_TIMEOUTと他のvport

新しく追加された機能は次のとおりです。

• tool_partial_cap.postpone_conn_qp_timeout_other_vport,
• tool_partial_cap.set_hca_cap_other_func
• tool_partial_cap.query_roce_addr_other_vport
• tool_partial_cap.query_vuid_direct_data
• tool_partial_cap.query_hca_cap_other_func

New features and changes included in version 20.43.1014:

• Added the option to indicate an error CQE event on every selected function per eSwitch manager. This indication is defined as a new WQE including the relevant information about the error (such as: syndrome, function_id, timestamp, QPs num etc.).
• Extended kernel lockdown permission set. The following sub-operations can now be called by tools (permission TOOLS_RESORCES) using new HCA capability bitmask field: tool_partial_cap.

The 5 sub-operations are:

• QUERY_HCA_CAP with other function
• QUERY_VUID with direct data
• QUERY_ROCE_ADDRESS with other vport
• SET_HCA_CAP with other function
• POSTPONE_CONNECTED_QP_TIMEOUT with other vport

The new added caps are:

• tool_partial_cap.postpone_conn_qp_timeout_other_vport,
• tool_partial_cap.set_hca_cap_other_func
• tool_partial_cap.query_roce_addr_other_vport
• tool_partial_cap.query_vuid_direct_data
• tool_partial_cap.query_hca_cap_other_func

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

ファームウェアの依存関係：

機能強化/新しい機能：

このバージョンは、Intel uPLR1ガイダンスに準拠しています。

既知の問題点：

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR1 guidance.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

ファームウェアの依存関係：

機能強化/新しい機能：

このバージョンは、Intel uPLR1ガイダンスに準拠しています。

既知の問題点：

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR1 guidance.

Known Issues:

None

Firmware Dependencies:

None

Enhancements/New Features:

This is the initial verison of the firmware.

Known Issues:

None

None

Firmware Dependencies:

None

Enhancements/New Features:

This is the initial verison of the firmware.

Known Issues:

None

Red Hat Enterprise Linux 9.5

ドライバーをバージョン10.02.12.01-k1にアップデートしました

Red Hat Enterprise Linux 9.5

Updated Driver version 10.02.12.01-k1

ファームウェアの依存関係：

機能強化/新しい機能：

このバージョンは、Intel uPLR3ガイダンスに準拠しています。

既知の問題点:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

ファームウェアの依存関係：

機能強化/新しい機能：

このバージョンは、Intel uPLR3ガイダンスに準拠しています。

既知の問題点:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

New features and changes included in version 22.43.1014:

• Added a recovery step in case of CQ doorbell getting lost during VF migration.
• Added the option to indicate an error CQE event on every selected function per eSwitch manager. This indication is defined as a new WQE including the relevant information about the error (such as: syndrome, function_id, timestamp, QPs num etc.). The feature is configured using a new general object: RDMA-Telemetry object, and depends on the following new caps:

HCA_CAP.rdma_telemetry_notification_types and HCA_CAP.rdma_telemetry .

• Extended kernel lockdown permission set. The following sub-operations can now be called by tools (permission TOOLS_RESORCES) using new HCA capability bitmask field: tool_partial_cap.

The 5 sub-operations are:

• QUERY_HCA_CAP with other function
• QUERY_VUID with direct data
• QUERY_ROCE_ADDRESS with other vport
• SET_HCA_CAP with other function
• POSTPONE_CONNECTED_QP_TIMEOUT with other vport

The new added caps are:

• tool_partial_cap.postpone_conn_qp_timeout_other_vport,
• tool_partial_cap.set_hca_cap_other_func
• tool_partial_cap.query_roce_addr_other_vport
• tool_partial_cap.query_vuid_direct_data
• tool_partial_cap.query_hca_cap_other_func

• Added 'table_type_valid' and 'table_type' fields to the steering action (STC) "Jump To Flow" table parameters to enable the user to jump from NIC_TX to FDB_TX and bypass the ACL table.
• Enabled hop reduction by bypassing NIC domain in various use cases. Such action reduces the number of hops (improves PPS) to deal with mass number of flows and devices. To enable this new capability, a new STC action type "JUMP_TO_FDB_RX" was added to allow jumping into the RX side of a table.
• Added support for QoS scheduling across multiple E-Switches grouped in a LAG. VPort members of a Physical Function can be added to a rate group from another Physical Function and rate limits of the group will apply to those VPort members as well.
• Increased the maximum number of supported "ARC-IN" from 1 to 8 and "ARCOUT" from 3 to 8 for the dynamic flex parser.

New features and changes included in version 22.43.1014:

• Added a recovery step in case of CQ doorbell getting lost during VF migration.
• Added the option to indicate an error CQE event on every selected function per eSwitch manager. This indication is defined as a new WQE including the relevant information about the error (such as: syndrome, function_id, timestamp, QPs num etc.). The feature is configured using a new general object: RDMA-Telemetry object, and depends on the following new caps:

HCA_CAP.rdma_telemetry_notification_types and HCA_CAP.rdma_telemetry .

• Extended kernel lockdown permission set. The following sub-operations can now be called by tools (permission TOOLS_RESORCES) using new HCA capability bitmask field: tool_partial_cap.

The 5 sub-operations are:

• QUERY_HCA_CAP with other function
• QUERY_VUID with direct data
• QUERY_ROCE_ADDRESS with other vport
• SET_HCA_CAP with other function
• POSTPONE_CONNECTED_QP_TIMEOUT with other vport

The new added caps are:

• tool_partial_cap.postpone_conn_qp_timeout_other_vport,
• tool_partial_cap.set_hca_cap_other_func
• tool_partial_cap.query_roce_addr_other_vport
• tool_partial_cap.query_vuid_direct_data
• tool_partial_cap.query_hca_cap_other_func

• Added 'table_type_valid' and 'table_type' fields to the steering action (STC) "Jump To Flow" table parameters to enable the user to jump from NIC_TX to FDB_TX and bypass the ACL table.
• Enabled hop reduction by bypassing NIC domain in various use cases. Such action reduces the number of hops (improves PPS) to deal with mass number of flows and devices. To enable this new capability, a new STC action type "JUMP_TO_FDB_RX" was added to allow jumping into the RX side of a table.
• Added support for QoS scheduling across multiple E-Switches grouped in a LAG. VPort members of a Physical Function can be added to a rate group from another Physical Function and rate limits of the group will apply to those VPort members as well.
• Increased the maximum number of supported "ARC-IN" from 1 to 8 and "ARCOUT" from 3 to 8 for the dynamic flex parser.

バージョン22.42.1000には、以下の新機能と変更が含まれます。

• HCA_CAPが不正なドライバーに、HCA_CAP.max_num_eqsで許可された数を超えるEQの作成を許可しないようにしました。
• 定義された期間メモリページの保持を有効/無効にする新しいコマンドインターフェイス"メモリスローリリース"を追加しました。タイマーが期限切れになると、ファームウェアはページをドライバーに返します。
• access_register PRM コマンドを使用して、さまざまなドライバー経由でMVTSレジスタのサポートを追加しました。
• SF上のMSI-Xは、PFのMSI-Xベクトルを介して受信できるようになりました。

New features and changes included in version 22.42.1000:

• Prevented HCA_CAP from allowing rogue drivers to create more EQs than the number allowed in the HCA_CAP.max_num_eqs.
• Added a new command interface "Memory slow release" to enable/disable holding memory pages for a defined period of time. Once the timer expires, the firmware will return the pages to the driver.
• Added support for MVTS register via a miscellaneous driver using the access_register PRM command.
• MSI-X on SF can be received now through the PF's MSI-X vector.

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel Catlow RPL-E PLR2 and Intel Catlow RPL-E Refresh PV guidance.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel Catlow RPL-E PLR2 and Intel Catlow RPL-E Refresh PV guidance.

Known Issues:

このバージョンのServer Platform Services（SPS）ファームウェアには、Intel Xeon E-2400シリーズプロセッサー用の最新パッケージが含まれています。このバージョンのSPSは、システムROM 1.60_09-05-2024と組み合わせる必要があります。

ファームウェアの依存関係：

なし

機能強化/新しい機能：

このバージョンには、Intel Xeon E-2400シリーズプロセッサー用の最新のServer Platform Servicesファームウェアが含まれています。

このバージョンは、Intel PLR1ガイダンスに準拠しています。

既知の問題点：

なし

This version of the Server Platform Services (SPS) Firmware contains the latest package for the Intel Xeon E-2400 series processors. This version of the SPS should be paired with System ROM 1.60_09-05-2024.

Firmware Dependencies:

None

Enhancements/New Features:

This version contains the latest Server Platform Services firmware for the Intel Xeon E-2400 series processors.

This version is in compliance with Intel PLR1 guidance.

Known Issues:

None

Red Hat Enterprise Linux 9.5

14.4.329.9にアップデートされたバージョン

Red Hat Enterprise Linux 9.5

Version updated to 14.4.329.9

• [Beta] Added support for QoS scheduling across multiple E-Switches grouped in a LAG. VPort members of a Physical Function can be added to a rate group from another Physical Function and rate limits of the group will apply to those VPort members as well.
• Added kernel support for monitoring RDMA events from userspace. Using the netlink or the RDMA tool, users will be able to monitor the InfiniBand device events and changes such as device register, device unregister and netdev attachment/detachment.
• Added the “irqs” directory inside the SF sysfs directory to provide the users information about the mapping of SFs and their IRQs.
• Added support for setting a maximum number of completion EQs for SFs.
• Added support for up to 23 bits for uar_page_index in create_cq flow. This allows the user to perform create_cq with a uar_page_index larger than 2^16 as supported by the hardware/firmware.
• [Beta] Added support for specifying bandwidth proportions between traffic classes (TC) in the devlink-rate API. This new option allows users to allocate bandwidth across multiple traffic classes in a single command. This feature provides a more granular control over traffic management, especially for scenarios requiring Enhanced Transmission Selection. Users can now define a specific bandwidth share for each traffic class, such as allocating 20% for TC0 (TCP/UDP) and 80% for TC5 (RoCE).

• [Beta] Added support for QoS scheduling across multiple E-Switches grouped in a LAG. VPort members of a Physical Function can be added to a rate group from another Physical Function and rate limits of the group will apply to those VPort members as well.
• Added kernel support for monitoring RDMA events from userspace. Using the netlink or the RDMA tool, users will be able to monitor the InfiniBand device events and changes such as device register, device unregister and netdev attachment/detachment.
• Added the “irqs” directory inside the SF sysfs directory to provide the users information about the mapping of SFs and their IRQs.
• Added support for setting a maximum number of completion EQs for SFs.
• Added support for up to 23 bits for uar_page_index in create_cq flow. This allows the user to perform create_cq with a uar_page_index larger than 2^16 as supported by the hardware/firmware.
• [Beta] Added support for specifying bandwidth proportions between traffic classes (TC) in the devlink-rate API. This new option allows users to allocate bandwidth across multiple traffic classes in a single command. This feature provides a more granular control over traffic management, especially for scenarios requiring Enhanced Transmission Selection. Users can now define a specific bandwidth share for each traffic class, such as allocating 20% for TC0 (TCP/UDP) and 80% for TC5 (RoCE).

• EQの作成を回避するためにSF開始/ブートフローを変更しました。これで、EQはユーザー/システムQPによって要求された場合にのみ作成されるようになります。
• [ベータ] fwctl は、安全なファームウェアインターフェイスをユーザー空間に直接公開するという、増加傾向にあるパターンに共通のルールと秩序をもたらすことを目的とした新しいサブシステムです。fwctlは、デバイスのデバッグ、構成、プロビジョニングに重点を置いています。fwctlはデフォルトではインストールされないため、インストールコマンドに "--fwctl" を追加することでインストールできます。
• req_transport_retries_exceededカウンター (QP カウンターごと) を公開します。これはRDMA統計を使用して確認でき、リクエスターがトランスポート再試行超過エラーを検出した回数を示します。
• 複数のNUMAノードで実行される同じポートの複数のSocket-Direct PFに対して単一のnetdev抽象化を作成します。この単一のnetdevは、上位層の複雑さなしに、各NUMAノード上のトラフィックをローカルに処理します。これにより、マルチNUMAシステムにおけるアプリケーションの局所性とパフォーマンスが向上します。
• devlink dev show/devlink port showコマンドを通じてdevlinkインスタンス間の関係を表示するためのdevlink-nestedオプションが追加されました。devlinkポートショーは、SFがアクティブ化されるタイミングを確認するために使用され、SF補助デバイスdevlinkインスタンスとeSwitch 代表 devlink ポート間の関係を表示します。Devlinkスケーラブル機能 (SF) アクティブ化コマンドは、SFアクティブ化の部分的な並列化を有効にする前に受信され、時間を短縮します。
• すべてのポートにオフロードされるルールの数を8から32に拡張しました。これにより、VLANトラフィックなどの一時的なルールをオフロードする際の柔軟性が向上し、ポート間のオフロード共有が容易になります。

• Changed the SF initiation/boot flow to avoid EQ creations. Now EQ will be created only when required by the user/system QPs.
• [Beta] fwctl is a new subsystem intended to bring some common rules and order to the growing pattern of exposing a secure firmware interface directly to the userspace. fwctl focuses on debugging, configuration and provisioning of the device. As fwctl is not installed by default, you can install it by adding "--fwctl" to the installation command.
• Exposes the req_transport_retries_exceeded counter (per QP counter). It can be seen using the RDMA statistics, and shows the number of times the requester detected transport retries exceed error.
• Creates a single netdev abstraction for multiple Socket-Direct PFs of the same port that run on multiple NUMA nodes. This single netdev handles traffic locally on each of the NUMA nodes without upper layer complexities. This improves the applications' locality and performance in a multi-NUMA system.
• Added devlink-nested option to show relationships between devlink instances through devlink dev show/devlink port show commands. The devlink port show is used to check when SFs are activated, and shows the relationship between SF auxiliary device devlink instance and the eSwitch representor devlink port. Devlink Scalable Function (SF) activate command is received before enabling a partial parallelization of the SFs activation, and reduces time.
• Extended the number of rules to be offloaded to all ports from 8 to 32. This allows greater flexibility when offloading temporary rules like VLAN traffic and ease the offload sharing between the ports.

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

このバージョンのServer Platform Services（SPS）ファームウェアには、第4世代および第5世代Intel® Xeon®スケーラブルプロセッサーの最新パッケージが含まれています。このバージョンのSPSは、システムROM 2.20と組み合わせる必要があります。

ファームウェアの依存関係：

なし

機能強化/新しい機能：

このバージョンは、Intel uPLR1ガイダンスに準拠しています。

既知の問題点：

なし

This version of the Server Platform Services (SPS) Firmware contains the latest package for 4th and 5th Generation Intel® Xeon® Scalable Processors. This version of the SPS should be paired with System ROM 2.20.

Firmware Dependencies:

None

Enhancements/New Features:

This version is in compliance with Intel uPLR1 guidance.

Known Issues:

None

バージョン16.35.4030には、以下の新機能と変更が含まれます。

• 特定の宛先に向けられたトラフィックのQPタイムアウト「再試行超過」エラーを延期するためのサポートが追加されました。この新しい機能により、ライブマイグレーションによるダウンタイム中に宛先への接続が切断されることが防止されます。

New features and changes included in version 16.35.4030:

• Added support for postponing QP timeout "retry exceeded" errors for traffic directed at specific destinations. This new capability prevents broken connections for destinations in downtime because of live migration.

バージョン16.35.4030には、以下の新機能と変更が含まれます。

• 特定の宛先に向けられたトラフィックのQPタイムアウト「再試行超過」エラーを延期するためのサポートが追加されました。この新しい機能により、ライブマイグレーションによるダウンタイム中に宛先への接続が切断されることが防止されます。

New features and changes included in version 16.35.4030:

• Added support for postponing QP timeout "retry exceeded" errors for traffic directed at specific destinations. This new capability prevents broken connections for destinations in downtime because of live migration.

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

このバージョンのServer Platform Services（SPS）ファームウェアには、第4世代および第5世代Intel® Xeon®スケーラブルプロセッサーの最新パッケージが含まれています。このバージョンのSPSは、システムROM 2.20と組み合わせる必要があります。

ファームウェアの依存関係：

なし

機能強化/新しい機能：

このバージョンは、Intel uPLR1ガイダンスに準拠しています。

既知の問題点：

なし

This version of the Server Platform Services (SPS) Firmware contains the latest package for 4th and 5th Generation Intel® Xeon® Scalable Processors. This version of the SPS should be paired with System ROM 2.20.

Firmware Dependencies:

None

Enhancements/New Features:

This version is in compliance with Intel uPLR1 guidance.

Known Issues:

None

バージョン26.43.1014にアップグレードされました

Upgraded to version 26.43.1014

• Enhanced firmware reset flow for Sync1 utilizing community-accepted hot reset kernel flow.

• Enhanced firmware reset flow for Sync1 utilizing community-accepted hot reset kernel flow.

このコンポーネントはFIPSが有効になっています。

This Component is FIPs enabled.

このコンポーネントはFIPSが有効になっています。

This Component is FIPs enabled.

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

ファームウェアの依存関係：

機能強化/新しい機能：

このバージョンは、Intel uPLR1ガイダンスに準拠しています。

既知の問題点：

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR1 guidance.

Known Issues:

rawドライバーファイルは、Smartコンポーネントを解凍し、その後Emulexインストーラーを解凍することによって取得することができます。  次のコマンドを使用します。

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

解凍されたファイルは次に置かれます。

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

各キットのフォルダーは、それに続くアーキテクチャーとOSフォルダーを持ちます。  例、

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

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

rawドライバーファイルは、Smartコンポーネントを解凍し、その後Emulexインストーラーを解凍することによって取得することができます。  次のコマンドを使用します。

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

解凍されたファイルは次に置かれます。

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

各キットのフォルダーは、それに続くアーキテクチャーとOSフォルダーを持ちます。  例、

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


 

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


 

o POST Storage.SetEncryptionKey

o PATCH Storage[EncryptionMode]

o PATCH/POST Volume[Encrypted]

• Note: MR controller support SED only. Therefore, Volume[EncryptionTypes] is not writeable during POST (Create) or PATCH (Update). Correspondingly the following Annotations are not populated:

a. EncryptionTypes@Redfish.AllowableValues (Volume Schema)

b. @Redfish.WriteableProperties[EncryptionTypes] (Volume Schema)

c. EncryptionTypes@Redfish.OptionalOnCreate (Volume Capabilities)

d. EncryptionTypes@Redfish.AllowableValues (Volume Capabilities)

e. EncryptionTypes@Redfish.UpdatableAfterCreate (Volume Capabilities)

o POST Volume.ForceEnable

o POST Drive.RevertToOriginalFactoryState

o Note:

• PATCH Volume[Encrypted] can be issued only with option ‘true’ on eligible volumes. PATCH Volume[Encrypted] with option ‘false’ will be failed because a secure volume cannot be changed to an unsecure volume in MR firmware.
• During POST (Create) ‘Encrypted’ option is not allowed for creating a volume with RAIDType=None. This is because MR does not support creating a secure JBOD in one step. After creating the JBOD, PATCH Volume[Encrypted = true] can be issued to create a secure JBOD.
• Whenever user requests to change to EKM, a reboot is a must to obtain the key via UEFI driver.
• Add MR408i-p support
• Added support for UBM10 backplanes
• Support UBM backplane FW version display and FW update when UBM controller is in bootloader state if there is an interruption during FW update
• Support NVMe SSD for Unmap capable Logical Drive. Please note that SATA SSD is not supported for Unmap capable Logical Drive.
• NAND flash refresh improvements

o The algorithm that posts the event "System reset required" after a specified number of days has been removed. The refresh happens after the same specified time and the new events are populated as below:

• Before starting the Nand flash refresh: “NAND refresh in progress: changing WB Logical Drives to WT”
• After the completion of Nand flash refresh: “NAND refresh complete: changing WT virtual disks to WB”
• The above behaviors are applicable only to MR400 controllers and are not applicable to MR200 controllers
• RAID1 Consistency Check Event String Change

o The Event String has been changed from "Consistency Check found inconsistent parity on LD <Ld Id> at strip <Strip Number>" to "Consistency Check found inconsistency on LD <Ld Id> at strip <Strip Number>".

• Support a new controller property, "Spin Down Drives At Shutdown", to control spindown of configured drives during shutdown
• Support for SCSI NVMe Translation Layer Specification version 1.14
• Added HPE ProLiant Compute DL380a Gen12 Server
• Support Decouple metadata 

o POST Storage.SetEncryptionKey

o PATCH Storage[EncryptionMode]

o PATCH/POST Volume[Encrypted]

• Note: MR controller support SED only. Therefore, Volume[EncryptionTypes] is not writeable during POST (Create) or PATCH (Update). Correspondingly the following Annotations are not populated:

a. EncryptionTypes@Redfish.AllowableValues (Volume Schema)

b. @Redfish.WriteableProperties[EncryptionTypes] (Volume Schema)

c. EncryptionTypes@Redfish.OptionalOnCreate (Volume Capabilities)

d. EncryptionTypes@Redfish.AllowableValues (Volume Capabilities)

e. EncryptionTypes@Redfish.UpdatableAfterCreate (Volume Capabilities)

o POST Volume.ForceEnable

o POST Drive.RevertToOriginalFactoryState

o Note:

• PATCH Volume[Encrypted] can be issued only with option ‘true’ on eligible volumes. PATCH Volume[Encrypted] with option ‘false’ will be failed because a secure volume cannot be changed to an unsecure volume in MR firmware.
• During POST (Create) ‘Encrypted’ option is not allowed for creating a volume with RAIDType=None. This is because MR does not support creating a secure JBOD in one step. After creating the JBOD, PATCH Volume[Encrypted = true] can be issued to create a secure JBOD.
• Whenever user requests to change to EKM, a reboot is a must to obtain the key via UEFI driver.
• Add MR408i-p support
• Added support for UBM10 backplanes
• Support UBM backplane FW version display and FW update when UBM controller is in bootloader state if there is an interruption during FW update
• Support NVMe SSD for Unmap capable Logical Drive. Please note that SATA SSD is not supported for Unmap capable Logical Drive.
• NAND flash refresh improvements

o The algorithm that posts the event "System reset required" after a specified number of days has been removed. The refresh happens after the same specified time and the new events are populated as below:

• Before starting the Nand flash refresh: “NAND refresh in progress: changing WB Logical Drives to WT”
• After the completion of Nand flash refresh: “NAND refresh complete: changing WT virtual disks to WB”
• The above behaviors are applicable only to MR400 controllers and are not applicable to MR200 controllers
• RAID1 Consistency Check Event String Change

o The Event String has been changed from "Consistency Check found inconsistent parity on LD <Ld Id> at strip <Strip Number>" to "Consistency Check found inconsistency on LD <Ld Id> at strip <Strip Number>".

• Support a new controller property, "Spin Down Drives At Shutdown", to control spindown of configured drives during shutdown
• Support for SCSI NVMe Translation Layer Specification version 1.14
• Added HPE ProLiant Compute DL380a Gen12 Server
• Support Decouple metadata 

o POST Storage.SetEncryptionKey

o PATCH Storage[EncryptionMode]

o PATCH/POST Volume[Encrypted]

• Note: MR controller support SED only. Therefore, Volume[EncryptionTypes] is not writeable during POST (Create) or PATCH (Update). Correspondingly the following Annotations are not populated:

a. EncryptionTypes@Redfish.AllowableValues (Volume Schema)

b. @Redfish.WriteableProperties[EncryptionTypes] (Volume Schema)

c. EncryptionTypes@Redfish.OptionalOnCreate (Volume Capabilities)

d. EncryptionTypes@Redfish.AllowableValues (Volume Capabilities)

e. EncryptionTypes@Redfish.UpdatableAfterCreate (Volume Capabilities)

o POST Volume.ForceEnable

o POST Drive.RevertToOriginalFactoryState

o Note:

• PATCH Volume[Encrypted] can be issued only with option ‘true’ on eligible volumes. PATCH Volume[Encrypted] with option ‘false’ will befailed because a secure volume cannot be changed to an unsecurevolume in MR firmware.
• During POST (Create) ‘Encrypted’ option is not allowed for creating a volume with RAIDType=None. This is because MR does not support creating a secure JBOD in one step. After creating the JBOD, PATCH Volume [Encrypted = true] can be issued to create a secure JBOD.
• Whenever user requests to change to EKM, a reboot is a must to obtain the key via UEFI driver.

• Add MR408i-p support
• Added support for UBM10 backplanes
• Support UBM backplane FW version display and FW update when UBM controller is in bootloader state if there is an interruption during FW update
• Support NVMe SSD for Unmap capable Logical Drive. Please note that SATA SSD is not supported for Unmap capable Logical Drive.
• NAND flash refresh improvements

o The algorithm that posts the event "System reset required" after a specified  number of days has been removed. The refresh happens after the same specified time and the new events are populated as below:

• Before starting the Nand flash refresh: “NAND refresh in progress:changing WB Logical Drives to WT”
• After the completion of Nand flash refresh: “NAND refresh complete:changing WT virtual disks to WB”
• The above behaviors are applicable only to MR400 controllers and are not applicable to MR200 controllers
• RAID1 Consistency Check Event String Change

o The Event String has been changed from "Consistency Check found inconsistent parity on LD <Ld Id> at strip <Strip Number>" to "Consistency Check found inconsistency on LD <Ld Id> at strip <Strip Number>".

• Support a new controller property, "Spin Down Drives At Shutdown", to control spindown of configured drives during shutdown
• Support for SCSI NVMe Translation Layer Specification version 1.14

o POST Storage.SetEncryptionKey

o PATCH Storage[EncryptionMode]

o PATCH/POST Volume[Encrypted]

• Note: MR controller support SED only. Therefore, Volume[EncryptionTypes] is not writeable during POST (Create) or PATCH (Update). Correspondingly the following Annotations are not populated:

a. EncryptionTypes@Redfish.AllowableValues (Volume Schema)

b. @Redfish.WriteableProperties[EncryptionTypes] (Volume Schema)

c. EncryptionTypes@Redfish.OptionalOnCreate (Volume Capabilities)

d. EncryptionTypes@Redfish.AllowableValues (Volume Capabilities)

e. EncryptionTypes@Redfish.UpdatableAfterCreate (Volume Capabilities)

o POST Volume.ForceEnable

o POST Drive.RevertToOriginalFactoryState

o Note:

• PATCH Volume[Encrypted] can be issued only with option ‘true’ on eligible volumes. PATCH Volume[Encrypted] with option ‘false’ will befailed because a secure volume cannot be changed to an unsecurevolume in MR firmware.
• During POST (Create) ‘Encrypted’ option is not allowed for creating a volume with RAIDType=None. This is because MR does not support creating a secure JBOD in one step. After creating the JBOD, PATCH Volume [Encrypted = true] can be issued to create a secure JBOD.
• Whenever user requests to change to EKM, a reboot is a must to obtain the key via UEFI driver.

• Add MR408i-p support
• Added support for UBM10 backplanes
• Support UBM backplane FW version display and FW update when UBM controller is in bootloader state if there is an interruption during FW update
• Support NVMe SSD for Unmap capable Logical Drive. Please note that SATA SSD is not supported for Unmap capable Logical Drive.
• NAND flash refresh improvements

o The algorithm that posts the event "System reset required" after a specified  number of days has been removed. The refresh happens after the same specified time and the new events are populated as below:

• Before starting the Nand flash refresh: “NAND refresh in progress:changing WB Logical Drives to WT”
• After the completion of Nand flash refresh: “NAND refresh complete:changing WT virtual disks to WB”
• The above behaviors are applicable only to MR400 controllers and are not applicable to MR200 controllers
• RAID1 Consistency Check Event String Change

o The Event String has been changed from "Consistency Check found inconsistent parity on LD <Ld Id> at strip <Strip Number>" to "Consistency Check found inconsistency on LD <Ld Id> at strip <Strip Number>".

• Support a new controller property, "Spin Down Drives At Shutdown", to control spindown of configured drives during shutdown
• Support for SCSI NVMe Translation Layer Specification version 1.14

New features and changes included in version 26.43.1014:

• Added a recovery step in case of CQ doorbell getting lost during VF migration.
• Added the option to indicate an error CQE event on every selected function per eSwitch manager. This indication is defined as a new WQE including the relevant information about the error (such as: syndrome, function_id, timestamp, QPs num etc.). The feature is configured using a new general object: RDMA-Telemetry object, and depends on the following new caps:

HCA_CAP.rdma_telemetry_notification_types and HCA_CAP.rdma_telemetry.

• Extended kernel lockdown permission set. The following sub-operations can now be called by tools (permission TOOLS_RESORCES) using new HCA capability bitmask field: tool_partial_cap.

The 5 sub-operations are:

• QUERY_HCA_CAP with other function
• QUERY_VUID with direct data
• QUERY_ROCE_ADDRESS with other vport
• SET_HCA_CAP with other function
• POSTPONE_CONNECTED_QP_TIMEOUT with other vport

The new added caps are:

• tool_partial_cap.postpone_conn_qp_timeout_other_vport,
• tool_partial_cap.set_hca_cap_other_func
• tool_partial_cap.query_roce_addr_other_vport
• tool_partial_cap.query_vuid_direct_data
• tool_partial_cap.query_hca_cap_other_func

• Added 'table_type_valid' and 'table_type' fields to the steering action (STC) "Jump To Flow" table parameters to enable the user to jump from NIC_TX to FDB_TX and bypass the ACL table.
• Enabled hop reduction by bypassing NIC domain in various use cases. Such action r educes the number of hops (improves PPS) to deal with mass number of flows and devices. To enable this new capability, a new STC action type "JUMP_TO_FDB_RX" was added to allow jumping into the RX side of a table.

New features and changes included in version 26.43.1014:

• Added a recovery step in case of CQ doorbell getting lost during VF migration.
• Added the option to indicate an error CQE event on every selected function per eSwitch manager. This indication is defined as a new WQE including the relevant information about the error (such as: syndrome, function_id, timestamp, QPs num etc.). The feature is configured using a new general object: RDMA-Telemetry object, and depends on the following new caps:

HCA_CAP.rdma_telemetry_notification_types and HCA_CAP.rdma_telemetry.

• Extended kernel lockdown permission set. The following sub-operations can now be called by tools (permission TOOLS_RESORCES) using new HCA capability bitmask field: tool_partial_cap.

The 5 sub-operations are:

• QUERY_HCA_CAP with other function
• QUERY_VUID with direct data
• QUERY_ROCE_ADDRESS with other vport
• SET_HCA_CAP with other function
• POSTPONE_CONNECTED_QP_TIMEOUT with other vport

The new added caps are:

• tool_partial_cap.postpone_conn_qp_timeout_other_vport,
• tool_partial_cap.set_hca_cap_other_func
• tool_partial_cap.query_roce_addr_other_vport
• tool_partial_cap.query_vuid_direct_data
• tool_partial_cap.query_hca_cap_other_func

• Added 'table_type_valid' and 'table_type' fields to the steering action (STC) "Jump To Flow" table parameters to enable the user to jump from NIC_TX to FDB_TX and bypass the ACL table.
• Enabled hop reduction by bypassing NIC domain in various use cases. Such action r educes the number of hops (improves PPS) to deal with mass number of flows and devices. To enable this new capability, a new STC action type "JUMP_TO_FDB_RX" was added to allow jumping into the RX side of a table.

バージョン26.42.1000には、以下の新機能と変更が含まれます。

• HCA_CAPが不正なドライバーに、HCA_CAP.max_num_eqsで許可された数を超えるEQの作成を許可しないようにしました。
• eswスケジューリング機能を使用するときに、内部ループバックトラフィックが物理ポートネットワークリンク速度を超えないように、論理ポートレートリミッターを削除しました。
• 定義された期間メモリページの保持を有効/無効にする新しいコマンドインターフェイス"メモリスローリリース"を追加しました。タイマーが期限切れになると、ファームウェアはページをドライバーに返します。
• access_register PRM コマンドを使用して、さまざまなドライバー経由でMVTSレジスタのサポートを追加しました。

New features and changes included in version 26.42.1000:

• Prevented HCA_CAP from allowing rogue drivers to create more EQs than the number allowed in the HCA_CAP.max_num_eqs.
• Removed the logical port rate limiter to prevent the internal loopback traffic from exceeding the physical port network link speed when using the esw scheduling feature.
• Added a new command interface "Memory slow release" to enable/disable holding memory pages for a defined period of time. Once the timer expires, the firmware will return the pages to the driver.
• Added support for MVTS register via a miscellaneous driver using the access_register PRM command.

    o /cx show spindownatshutdown
    o /cx set spindownatshutdown {[sashdd=<on|off>] [satahdd=<on|off>]
        [sasssd=<on|off>] [satassd=<on|off>] [nvmessd=<on|off>]}

• Adjust the RAID1 consistency related error message
• Added HPE ProLiant Compute DL380a Gen12 Server support

    o /cx show spindownatshutdown
    o /cx set spindownatshutdown {[sashdd=<on|off>] [satahdd=<on|off>]
        [sasssd=<on|off>] [satassd=<on|off>] [nvmessd=<on|off>]}

• Adjust the RAID1 consistency related error message
• Added HPE ProLiant Compute DL380a Gen12 Server support

    o /cx show spindownatshutdown
    o /cx set spindownatshutdown {[sashdd=<on|off>] [satahdd=<on|off>]
        [sasssd=<on|off>] [satassd=<on|off>] [nvmessd=<on|off>]}

• Adjust the RAID1 consistency related error message

    o /cx show spindownatshutdown
    o /cx set spindownatshutdown {[sashdd=<on|off>] [satahdd=<on|off>]
        [sasssd=<on|off>] [satassd=<on|off>] [nvmessd=<on|off>]}

• Adjust the RAID1 consistency related error message

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

ファームウェアの依存関係：

機能強化/新しい機能：

このバージョンは、Intel uPLR1ガイダンスに準拠しています。

既知の問題点：

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR1 guidance.

Known Issues:

• [Beta] Added support for QoS scheduling across multiple E-Switches grouped in a LAG. VPort members of a Physical Function can be added to a rate group from another Physical Function and rate limits of the group will apply to those VPort members as well.
• Added kernel support for monitoring RDMA events from userspace. Using the netlink or the RDMA tool, users will be able to monitor the InfiniBand device events and changes such as device register, device unregister and netdev attachment/detachment.
• Added the “irqs” directory inside the SF sysfs directory to provide the users information about the mapping of SFs and their IRQs.
• Added support for setting a maximum number of completion EQs for SFs.
• Added support for up to 23 bits for uar_page_index in create_cq flow. This allows the user to perform create_cq with a uar_page_index larger than 2^16 as supported by the hardware/firmware.
• [Beta] Added support for specifying bandwidth proportions between traffic classes (TC) in the devlink-rate API. This new option allows users to allocate bandwidth across multiple traffic classes in a single command. This feature provides a more granular control over traffic management, especially for scenarios requiring Enhanced Transmission Selection. Users can now define a specific bandwidth share for each traffic class, such as allocating 20% for TC0 (TCP/UDP) and 80% for TC5 (RoCE).

• [Beta] Added support for QoS scheduling across multiple E-Switches grouped in a LAG. VPort members of a Physical Function can be added to a rate group from another Physical Function and rate limits of the group will apply to those VPort members as well.
• Added kernel support for monitoring RDMA events from userspace. Using the netlink or the RDMA tool, users will be able to monitor the InfiniBand device events and changes such as device register, device unregister and netdev attachment/detachment.
• Added the “irqs” directory inside the SF sysfs directory to provide the users information about the mapping of SFs and their IRQs.
• Added support for setting a maximum number of completion EQs for SFs.
• Added support for up to 23 bits for uar_page_index in create_cq flow. This allows the user to perform create_cq with a uar_page_index larger than 2^16 as supported by the hardware/firmware.
• [Beta] Added support for specifying bandwidth proportions between traffic classes (TC) in the devlink-rate API. This new option allows users to allocate bandwidth across multiple traffic classes in a single command. This feature provides a more granular control over traffic management, especially for scenarios requiring Enhanced Transmission Selection. Users can now define a specific bandwidth share for each traffic class, such as allocating 20% for TC0 (TCP/UDP) and 80% for TC5 (RoCE).

• EQの作成を回避するためにSF開始/ブートフローを変更しました。これで、EQはユーザー/システムQPによって要求された場合にのみ作成されるようになります。
• [ベータ] fwctl は、安全なファームウェアインターフェイスをユーザー空間に直接公開するという、増加傾向にあるパターンに共通のルールと秩序をもたらすことを目的とした新しいサブシステムです。fwctlは、デバイスのデバッグ、構成、プロビジョニングに重点を置いています。fwctlはデフォルトではインストールされないため、インストールコマンドに "--fwctl" を追加することでインストールできます。
• req_transport_retries_exceededカウンター (QP カウンターごと) を公開します。これはRDMA統計を使用して確認でき、リクエスターがトランスポート再試行超過エラーを検出した回数を示します。
• 複数のNUMAノードで実行される同じポートの複数のSocket-Direct PFに対して単一のnetdev抽象化を作成します。この単一のnetdevは、上位層の複雑さなしに、各NUMAノード上のトラフィックをローカルに処理します。これにより、マルチNUMAシステムにおけるアプリケーションの局所性とパフォーマンスが向上します。
• devlink dev show/devlink port showコマンドを通じてdevlinkインスタンス間の関係を表示するためのdevlink-nestedオプションが追加されました。devlinkポートショーは、SFがアクティブ化されるタイミングを確認するために使用され、SF補助デバイスdevlinkインスタンスとeSwitch 代表 devlink ポート間の関係を表示します。Devlinkスケーラブル機能 (SF) アクティブ化コマンドは、SFアクティブ化の部分的な並列化を有効にする前に受信され、時間を短縮します。
• すべてのポートにオフロードされるルールの数を8から32に拡張しました。これにより、VLANトラフィックなどの一時的なルールをオフロードする際の柔軟性が向上し、ポート間のオフロード共有が容易になります。

• Changed the SF initiation/boot flow to avoid EQ creations. Now EQ will be created only when required by the user/system QPs.
• [Beta] fwctl is a new subsystem intended to bring some common rules and order to the growing pattern of exposing a secure firmware interface directly to the userspace. fwctl focuses on debugging, configuration and provisioning of the device. As fwctl is not installed by default, you can install it by adding "--fwctl" to the installation command.
• Exposes the req_transport_retries_exceeded counter (per QP counter). It can be seen using the RDMA statistics, and shows the number of times the requester detected transport retries exceed error.
• Creates a single netdev abstraction for multiple Socket-Direct PFs of the same port that run on multiple NUMA nodes. This single netdev handles traffic locally on each of the NUMA nodes without upper layer complexities. This improves the applications' locality and performance in a multi-NUMA system.
• Added devlink-nested option to show relationships between devlink instances through devlink dev show/devlink port show commands. The devlink port show is used to check when SFs are activated, and shows the relationship between SF auxiliary device devlink instance and the eSwitch representor devlink port. Devlink Scalable Function (SF) activate command is received before enabling a partial parallelization of the SFs activation, and reduces time.
• Extended the number of rules to be offloaded to all ports from 8 to 32. This allows greater flexibility when offloading temporary rules like VLAN traffic and ease the offload sharing between the ports.

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel Catlow RPL-E PLR2 and Intel Catlow RPL-E Refresh PV guidance.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel Catlow RPL-E PLR2 and Intel Catlow RPL-E Refresh PV guidance.

Known Issues:

このバージョンのServer Platform Services（SPS）ファームウェアには、Intel Xeon E-2400シリーズプロセッサー用の最新パッケージが含まれています。このバージョンのSPSは、システムROM 1.60_09-05-2024と組み合わせる必要があります。

ファームウェアの依存関係：

なし

機能強化/新しい機能：

このバージョンには、Intel Xeon E-2400シリーズプロセッサー用の最新のServer Platform Servicesファームウェアが含まれています。

このバージョンは、Intel PLR1ガイダンスに準拠しています。

既知の問題点：

なし

This version of the Server Platform Services (SPS) Firmware contains the latest package for the Intel Xeon E-2400 series processors. This version of the SPS should be paired with System ROM 1.60_09-05-2024.

Firmware Dependencies:

None

Enhancements/New Features:

This version contains the latest Server Platform Services firmware for the Intel Xeon E-2400 series processors.

This version is in compliance with Intel PLR1 guidance.

Known Issues:

None

• PLDM プラットフォーム監視および制御 (タイプ 2) コマンドは、PLDMプラットフォーム監視および制御仕様 (DSP0248) のv1.3.0に準拠しています。 

• RedfishおよびストレージリソースRDEアクション操作を使用したボリュームの作成/削除の長期実行タスクのサポート。

• PLDM Platform Monitoring and Control (Type 2) commands comply with v1.3.0 of the PLDM Platform Monitoring and Control Specification (DSP0248). 

• Long-running task support for volume creation/deletion using Redfish and storage resource RDE action operations.

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR3 guidance.

Known Issues:

ファームウェアの依存関係：

機能強化/新しい機能：

このバージョンは、Intel uPLR1ガイダンスに準拠しています。

既知の問題点：

Firmware Dependencies:

Enhancements/New Features:

This version is in compliance with Intel uPLR1 guidance.

Known Issues:

• Increased the RX lossless buffer size to delay the transmission of Pause/PFC frames during NIC congestion.
• Added support for SyncE at 1G link speed.
• Added a new mechanism for allocations and deallocations flows to enhance parallelism.
• When using a multi-host deployment, each host is assigned unique ports and PFs and manages its own LAG.
• Added support for a new synchronized flow, including a tool and driver, to perform a fwreset on setups with a PCIe switch configuration.
• Unified PTP is now supported across different VFs on the same PF.
• Added support for new MADs: PortRecoveryPolicyConfig and PortRecoveryPolicyCounters . During the PHY recovery process, the firmware core will indicate the  port_logical_state as Active.
• Added a new NV config (SM_DISABLE, default 0) which, when enabled, blocks SMP traffic that does not originate from the SM.
• Added the ability to set cable length as a parameter in the PFCC access register. The cable length is used in the calculation of RX lossless buffer parameters, including size, Xoff, and Xon thresholds.

• Increased the RX lossless buffer size to delay the transmission of Pause/PFC frames during NIC congestion.
• Added support for SyncE at 1G link speed.
• Added a new mechanism for allocations and deallocations flows to enhance parallelism.
• When using a multi-host deployment, each host is assigned unique ports and PFs and manages its own LAG.
• Added support for a new synchronized flow, including a tool and driver, to perform a fwreset on setups with a PCIe switch configuration.
• Unified PTP is now supported across different VFs on the same PF.
• Added support for new MADs: PortRecoveryPolicyConfig and PortRecoveryPolicyCounters . During the PHY recovery process, the firmware core will indicate the  port_logical_state as Active.
• Added a new NV config (SM_DISABLE, default 0) which, when enabled, blocks SMP traffic that does not originate from the SM.
• Added the ability to set cable length as a parameter in the PFCC access register. The cable length is used in the calculation of RX lossless buffer parameters, including size, Xoff, and Xon thresholds.

• PCIeテレメトリ (NSMタイプ2) のサポートが追加されました。
• PCC NPソリューションをACEハードウェアプラットフォームからDPAハードウェアプラットフォームに移行しました。新しい機能は、次のモードに適用できます: 1) PCC_INT_EN=TrueかつPCC_INT_NP_RTT_DATA_MODE=INGRESS_BYTE 2) PCC_INT_EN=TrueかつPCC_INT_NP_RTT_DATA_MODE=NO_DATA。最初のモードは、RTT応答でZTRCC RXバイトをサポートするために使用されます。
• eSwitchマネージャーごとに選択されたすべての機能でエラーCQEイベントを示すオプションが追加されました。この表示は、エラーに関する関連情報 (シンドローム、function_id、タイムスタンプ、QP番号など) を含む新しいWQEとして定義されます。
• 拡張カーネルロックダウン権限セット。新しいHCA機能ビットマスクフィールドtool_partial_capを使用して、ツール (権限TOOLS_RESORCES) によって次のサブ操作を呼び出すことができるようになりました。

5つのサブ操作は次のとおりです。

• QUERY_HCA_CAPと他の機能
• QUERY_VUIDと直接データ
• QUERY_ROCE_ADDRESSと他のvport
• SET_HCA_CAPと他の機能
• POSTPONE_CONNECTED_QP_TIMEOUTと他のvport

新しく追加された機能は次のとおりです。

• tool_partial_cap.postpone_conn_qp_timeout_other_vport,
• tool_partial_cap.set_hca_cap_other_func
• tool_partial_cap.query_roce_addr_other_vport
• tool_partial_cap.query_vuid_direct_data
• tool_partial_cap.query_hca_cap_other_func

• LAGにグループ化された複数のE-SwitchにわたるQoSスケジューリングのサポートが追加されました。ある物理機能のVPortメンバーを、別の物理機能からのレートグループに追加することができ、グループのレート制限はそれらのVPortメンバーにも適用されます。
• ステアリングアクション (STC) の"Jump To Flow"テーブルパラメーターに'table_type_valid'および'table_type'フィールドが追加され、ユーザーがNIC_TXからFDB_TXにジャンプしてACLテーブルをバイパスできるようになりました。
• さまざまなユースケースでNICドメインをバイパスすることでホップ削減を可能にしました。このようなアクションにより、大量のフローとデバイスを処理するためのホップ数が削減されます (PPSが向上します)。この新しい機能を有効にするために、テーブルのRX側にジャンプできるようにする新しいSTCアクションタイプ"JUMP_TO_FDB_RX"が追加されました。
• 動的フレックスパーサーでサポートされる"ARC-IN"の最大数を1から8に、"ARC-OUT"の最大数を3から8に増やしました。
• PCC ZTR_RTTCにレートとラウンドトリップ時間 (RTT) のヒストグラムサポートが追加されました。
• VF移行中にCQドアベルが失われた場合に備えて回復手順を追加しました。
• VGAゲインとCTLEのためのPCIe Gen4/5の新しい静的構成を変更しました。
• Gen4/5開始点のCTLEおよびVGAゲインを変更しました。
• SPDMのRDT値を増加しました。

• Added support for PCIe Telemetry (NSM Type 2).
• Migrated PCC NP solution from ACE hardware platform to DPA hardware platform. The new capability is applicable to the following modes: 1) PCC_INT_EN=True and PCC_INT_NP_RTT_DATA_MODE=INGRESS_BYTE 2) PCC_INT_EN=True and PCC_INT_NP_RTT_DATA_MODE=NO_DATA. The first mode is used to support ZTRCC RX bytes in RTT response.
• Added the option to indicate an error CQE event on every selected function per eSwitch manager. This indication is defined as a new WQE including the relevant information about the error (such as: syndrome, function_id, timestamp, QPs num etc.).
• Extended kernel lockdown permission set. The following sub-operations can now be called by tools (permission TOOLS_RESORCES) using new HCA capability bitmask field: tool_partial_cap.

The 5 sub-operations are:

• QUERY_HCA_CAP with other function
• QUERY_VUID with direct data
• QUERY_ROCE_ADDRESS with other vport
• SET_HCA_CAP with other function
• POSTPONE_CONNECTED_QP_TIMEOUT with other vport

The new added caps are:

• tool_partial_cap.postpone_conn_qp_timeout_other_vport,
• tool_partial_cap.set_hca_cap_other_func
• tool_partial_cap.query_roce_addr_other_vport
• tool_partial_cap.query_vuid_direct_data
• tool_partial_cap.query_hca_cap_other_func

• Added support for QoS scheduling across multiple E-Switches grouped in a LAG. VPort members of a Physical Function can be added to a rate group from another Physical Function and rate limits of the group will apply to those VPort members as well.
• Added 'table_type_valid' and 'table_type' fields to the steering action (STC) "Jump To Flow" table parameters to enable the user to jump from NIC_TX to FDB_TX and bypass the ACL table.
• Enabled hop reduction by bypassing NIC domain in various use cases. Such action reduces the number of hops (improves PPS) to deal with mass number of flows and devices. To enable this new capability, a new STC action type "JUMP_TO_FDB_RX" was added to allow jumping into the RX side of a table.
• Increased the maximum number of supported "ARC-IN" from 1 to 8 and "ARC-OUT" from 3 to 8 for the dynamic flex parser.
• Added histogram support for rate and Round-Trip Time (RTT) in PCC ZTR_RTTC.
• Added a recovery step in case of CQ doorbell getting lost during VF migration.
• Changed PCIe Gen4/5 new static configuration for VGA gain and CTLE.
• Changed the CTLE and VGA gain for Gen4/5 starting point.
• Increased SPDM's RDT value.

• [ベータ] LAGにグループ化された複数のE-SwitchにわたるQoSスケジューリングのサポートが追加されました。ある物理機能のVPortメンバーを、別の物理機能からのレートグループに追加することができ、グループのレート制限はそれらのVPortメンバーにも適用されます。
• ユーザースペースからRDMAイベントを監視するためのカーネルサポートが追加されました。netlinkまたはRDMAツールを使用すると、ユーザーはデバイスの登録、デバイスの登録解除、netdevの接続/切断などのInfiniBandデバイスのイベントと変更を監視できます。
• SFとそのIRQのマッピングに関する情報をユーザーに提供するために、SF sysfsディレクトリ内に"irqs"ディレクトリを追加しました。
• SFの完了EQの最大数を設定するためのサポートが追加されました。
• create_cqフローのuar_page_indexに対する最大23ビットのサポートが追加されました。これにより、ユーザーは、ハードウェア/ファームウェアでサポートされている2^16より大きいuar_page_indexを使用してcreate_cqを実行できるようになります。
• [ベータ] devlink-rate APIのトラフィッククラス (TC) 間の帯域幅比率を指定するためのサポートが追加されました。この新しいオプションにより、ユーザーは単一のコマンドで複数のトラフィッククラスにわたって帯域幅を割り当てることができます。この機能により、特に拡張伝送選択を必要とするシナリオにおいて、トラフィック管理をより細かく制御できるようになります。ユーザーは、TC0 (TCP/UDP) に20%、TC5 (RoCE) に80%を割り当てるなど、トラフィッククラスごとに特定の帯域幅のシェアを定義できるようになりました。

• [Beta] Added support for QoS scheduling across multiple E-Switches grouped in a LAG. VPort members of a Physical Function can be added to a rate group from another Physical Function and rate limits of the group will apply to those VPort members as well.
• Added kernel support for monitoring RDMA events from userspace. Using the netlink or the RDMA tool, users will be able to monitor the InfiniBand device events and changes such as device register, device unregister and netdev attachment/detachment.
• Added the “irqs” directory inside the SF sysfs directory to provide the users information about the mapping of SFs and their IRQs.
• Added support for setting a maximum number of completion EQs for SFs.
• Added support for up to 23 bits for uar_page_index in create_cq flow. This allows the user to perform create_cq with a uar_page_index larger than 2^16 as supported by the hardware/firmware.
• [Beta] Added support for specifying bandwidth proportions between traffic classes (TC) in the devlink-rate API. This new option allows users to allocate bandwidth across multiple traffic classes in a single command. This feature provides a more granular control over traffic management, especially for scenarios requiring Enhanced Transmission Selection. Users can now define a specific bandwidth share for each traffic class, such as allocating 20% for TC0 (TCP/UDP) and 80% for TC5 (RoCE).

Red Hat Enterprise Linux 9.5

14.4.329.9にアップデートされたバージョン

Red Hat Enterprise Linux 9.5

Version updated to 14.4.329.9