Red Hat Enterprise Linux 10

Updated Driver version 10.02.14.00-k1

Red Hat Enterprise Linux 10

Updated Driver version 10.02.14.00-k1

Red Hat Enterprise Linux 10.0

Updated to version 14.4.473.24

Red Hat Enterprise Linux 10.0

Updated to version 14.4.473.24

Red Hat Enterprise Linux 10.0

Updated to version 14.4.473.24

Red Hat Enterprise Linux 10.0

Updated to version 14.4.473.24

Red Hat Enterprise Linux 10.0

Updated to version 14.4.473.24

Red Hat Enterprise Linux 10.0

Updated to version 14.4.473.24

New features and changes included in version 26.44.1036:

• Enabled the get_pf_mac_address function for all available PFs.
• Enhanced traffic management of PTP packets to reduce their impact on regular network traffic.
• 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.

New features and changes included in version 26.44.1036:

• Enabled the get_pf_mac_address function for all available PFs.
• Enhanced traffic management of PTP packets to reduce their impact on regular network traffic.
• 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.

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.

Updated some wordings in the VROC pop-up string for better alignment.

Enabled Bifurcation capability support for system OCP slots.

Enabled VROC options on DL320 Gen12 OEM.

Updated some wordings in the VROC pop-up string for better alignment.

Enabled Bifurcation capability support for system OCP slots.

Enabled VROC options on DL320 Gen12 OEM.

Add help text for "Smooth Cooling" System Configuration (RBSU) option.

Add help text for "Smooth Cooling" System Configuration (RBSU) option.

New features and changes included in version 26.44.1036:

• Enabled the get_pf_mac_address function for all available PFs.
• Enhanced traffic management of PTP packets to reduce their impact on regular network traffic.
• 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.

New features and changes included in version 26.44.1036:

• Enabled the get_pf_mac_address function for all available PFs.
• Enhanced traffic management of PTP packets to reduce their impact on regular network traffic.
• 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.

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.

None

Firmware Dependencies:

None

Enhancements/New Features:

This is the initial version of the firmware.

Known Issues:

None

None

Firmware Dependencies:

None

Enhancements/New Features:

This is the initial version of the firmware.

Known Issues:

None

Red Hat Enterprise Linux 10

Updated Driver version 10.02.14.00-k1

Red Hat Enterprise Linux 10

Updated Driver version 10.02.14.00-k1

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

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

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

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

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

The extracted files are located:

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

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

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

Updated some wordings in the VROC pop-up string for better alignment.

Enabled Bifurcation capability support for system OCP slots.

Enabled VROC options on DL320 Gen12 OEM.

Updated some wordings in the VROC pop-up string for better alignment.

Enabled Bifurcation capability support for system OCP slots.

Enabled VROC options on DL320 Gen12 OEM.

Updated some wordings in the VROC pop-up string for better alignment.

Enabled Bifurcation capability support for system OCP slots.

Enabled VROC options on DL320 Gen12 OEM.

Updated some wordings in the VROC pop-up string for better alignment.

Enabled Bifurcation capability support for system OCP slots.

Enabled VROC options on DL320 Gen12 OEM.

Added help text for "Smooth Cooling" System Configuration (RBSU) option.

Added help text for "Smooth Cooling" System Configuration (RBSU) option.

Red Hat Enterprise Linux 10

Updated Driver version 10.02.14.00-k1

Red Hat Enterprise Linux 10

Updated Driver version 10.02.14.00-k1

• 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.

• 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.

Red Hat Enterprise Linux 10.0

Updated to version 14.4.473.24

Red Hat Enterprise Linux 10.0

Updated to version 14.4.473.24

• 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.

• 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.

• 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.

• [ConnectX-7] Multi-host LAG: When using a multi-host deployment, each host is assigned unique ports and PFs and manages its own LAG.
• Hardware GRO: Hardware Generic Receive Offload (GRO) reduces CPU overhead and improves throughput by offloading the task of reassembling incoming network packets from the CPU.
• Precision Time Measurement (PTM): Precision Time Measurement (PTM) enhances clock synchronization accuracy between the NIC's hardware clock and the system's host clock. It addresses inaccuracies caused by asymmetric PCIe request and response times, which can affect PTP.
• Transport RDMA Steering Domain: Transport RDMA steering domain in the kernel allows users to create steering tables and rules using the new domain types FS_FT_RDMA_TRANSPORT_RX and FS_FT_RDMA_TRANSPORT_TX, with support for both DevX commands and the added functionality in mlx5dv_create_flow_matcher().
• DevX QPs Parallel Cleanup: Reduces cleanup (kill) time of user-space applications that use DevX QPs, without requiring any changes on the user's end. When using a kernel that includes this patch, DevX QP destruction upon cleanup will be sent to the firmware in parallel, rather than serially as before, resulting in faster cleanup times. The more DevX QPs the application has, the more noticeable the improvement will be.
• Flow Control for Solicited MADs: Implements flow control for solicited MADs in the MAD layer to prevent loss due to insufficient resources at the receiver. Both the client and server function as receivers: the server handles incoming requests, while the client receives the responses.
• Increased the default TX queue length in IPoIB to enhance qdisc queueing and reduce CPU spikes.
• The "--defltprio" flag has been deprecated and removed from the mlnx_qos tool.

• [ConnectX-7] Multi-host LAG: When using a multi-host deployment, each host is assigned unique ports and PFs and manages its own LAG.
• Hardware GRO: Hardware Generic Receive Offload (GRO) reduces CPU overhead and improves throughput by offloading the task of reassembling incoming network packets from the CPU.
• Precision Time Measurement (PTM): Precision Time Measurement (PTM) enhances clock synchronization accuracy between the NIC's hardware clock and the system's host clock. It addresses inaccuracies caused by asymmetric PCIe request and response times, which can affect PTP.
• Transport RDMA Steering Domain: Transport RDMA steering domain in the kernel allows users to create steering tables and rules using the new domain types FS_FT_RDMA_TRANSPORT_RX and FS_FT_RDMA_TRANSPORT_TX, with support for both DevX commands and the added functionality in mlx5dv_create_flow_matcher().
• DevX QPs Parallel Cleanup: Reduces cleanup (kill) time of user-space applications that use DevX QPs, without requiring any changes on the user's end. When using a kernel that includes this patch, DevX QP destruction upon cleanup will be sent to the firmware in parallel, rather than serially as before, resulting in faster cleanup times. The more DevX QPs the application has, the more noticeable the improvement will be.
• Flow Control for Solicited MADs: Implements flow control for solicited MADs in the MAD layer to prevent loss due to insufficient resources at the receiver. Both the client and server function as receivers: the server handles incoming requests, while the client receives the responses.
• Increased the default TX queue length in IPoIB to enhance qdisc queueing and reduce CPU spikes.
• The "--defltprio" flag has been deprecated and removed from the mlnx_qos tool.

• [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).

• 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.

• 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.

Updated some wordings in the VROC pop-up string for better alignment.

Enabled Bifurcation capability support for system OCP slots.

Enabled VROC options on DL320 Gen12 OEM.

Updated some wordings in the VROC pop-up string for better alignment.

Enabled Bifurcation capability support for system OCP slots.

Enabled VROC options on DL320 Gen12 OEM.

Add help text for "Smooth Cooling" System Configuration (RBSU) option.

Add help text for "Smooth Cooling" System Configuration (RBSU) option.

Red Hat Enterprise Linux 10

Updated Driver version 10.02.14.00-k1

Red Hat Enterprise Linux 10

Updated Driver version 10.02.14.00-k1

• [ConnectX-7] Multi-host LAG: When using a multi-host deployment, each host is assigned unique ports and PFs and manages its own LAG.
• Hardware GRO: Hardware Generic Receive Offload (GRO) reduces CPU overhead and improves throughput by offloading the task of reassembling incoming network packets from the CPU.
• Precision Time Measurement (PTM): Precision Time Measurement (PTM) enhances clock synchronization accuracy between the NIC's hardware clock and the system's host clock. It addresses inaccuracies caused by asymmetric PCIe request and response times, which can affect PTP.
• Transport RDMA Steering Domain: Transport RDMA steering domain in the kernel allows users to create steering tables and rules using the new domain types FS_FT_RDMA_TRANSPORT_RX and FS_FT_RDMA_TRANSPORT_TX, with support for both DevX commands and the added functionality in mlx5dv_create_flow_matcher().
• DevX QPs Parallel Cleanup: Reduces cleanup (kill) time of user-space applications that use DevX QPs, without requiring any changes on the user's end. When using a kernel that includes this patch, DevX QP destruction upon cleanup will be sent to the firmware in parallel, rather than serially as before, resulting in faster cleanup times. The more DevX QPs the application has, the more noticeable the improvement will be.
• Flow Control for Solicited MADs: Implements flow control for solicited MADs in the MAD layer to prevent loss due to insufficient resources at the receiver. Both the client and server function as receivers: the server handles incoming requests, while the client receives the responses.
• Increased the default TX queue length in IPoIB to enhance qdisc queueing and reduce CPU spikes.
• The "--defltprio" flag has been deprecated and removed from the mlnx_qos tool.

• [ConnectX-7] Multi-host LAG: When using a multi-host deployment, each host is assigned unique ports and PFs and manages its own LAG.
• Hardware GRO: Hardware Generic Receive Offload (GRO) reduces CPU overhead and improves throughput by offloading the task of reassembling incoming network packets from the CPU.
• Precision Time Measurement (PTM): Precision Time Measurement (PTM) enhances clock synchronization accuracy between the NIC's hardware clock and the system's host clock. It addresses inaccuracies caused by asymmetric PCIe request and response times, which can affect PTP.
• Transport RDMA Steering Domain: Transport RDMA steering domain in the kernel allows users to create steering tables and rules using the new domain types FS_FT_RDMA_TRANSPORT_RX and FS_FT_RDMA_TRANSPORT_TX, with support for both DevX commands and the added functionality in mlx5dv_create_flow_matcher().
• DevX QPs Parallel Cleanup: Reduces cleanup (kill) time of user-space applications that use DevX QPs, without requiring any changes on the user's end. When using a kernel that includes this patch, DevX QP destruction upon cleanup will be sent to the firmware in parallel, rather than serially as before, resulting in faster cleanup times. The more DevX QPs the application has, the more noticeable the improvement will be.
• Flow Control for Solicited MADs: Implements flow control for solicited MADs in the MAD layer to prevent loss due to insufficient resources at the receiver. Both the client and server function as receivers: the server handles incoming requests, while the client receives the responses.
• Increased the default TX queue length in IPoIB to enhance qdisc queueing and reduce CPU spikes.
• The "--defltprio" flag has been deprecated and removed from the mlnx_qos tool.

• [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).

Updated some wordings in the VROC pop-up string for better alignment.

Enabled Bifurcation capability support for system OCP slots.

Enabled VROC options on DL320 Gen12 OEM.

Updated some wordings in the VROC pop-up string for better alignment.

Enabled Bifurcation capability support for system OCP slots.

Enabled VROC options on DL320 Gen12 OEM.

Added help text for "Smooth Cooling" System Configuration (RBSU) option.

Added help text for "Smooth Cooling" System Configuration (RBSU) option.

• 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.

• 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.

• 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.

• [ConnectX-7] Multi-host LAG: When using a multi-host deployment, each host is assigned unique ports and PFs and manages its own LAG.
• Hardware GRO: Hardware Generic Receive Offload (GRO) reduces CPU overhead and improves throughput by offloading the task of reassembling incoming network packets from the CPU.
• Precision Time Measurement (PTM): Precision Time Measurement (PTM) enhances clock synchronization accuracy between the NIC's hardware clock and the system's host clock. It addresses inaccuracies caused by asymmetric PCIe request and response times, which can affect PTP.
• Transport RDMA Steering Domain: Transport RDMA steering domain in the kernel allows users to create steering tables and rules using the new domain types FS_FT_RDMA_TRANSPORT_RX and FS_FT_RDMA_TRANSPORT_TX, with support for both DevX commands and the added functionality in mlx5dv_create_flow_matcher().
• DevX QPs Parallel Cleanup: Reduces cleanup (kill) time of user-space applications that use DevX QPs, without requiring any changes on the user's end. When using a kernel that includes this patch, DevX QP destruction upon cleanup will be sent to the firmware in parallel, rather than serially as before, resulting in faster cleanup times. The more DevX QPs the application has, the more noticeable the improvement will be.
• Flow Control for Solicited MADs: Implements flow control for solicited MADs in the MAD layer to prevent loss due to insufficient resources at the receiver. Both the client and server function as receivers: the server handles incoming requests, while the client receives the responses.
• Increased the default TX queue length in IPoIB to enhance qdisc queueing and reduce CPU spikes.
• The "--defltprio" flag has been deprecated and removed from the mlnx_qos tool.

• [ConnectX-7] Multi-host LAG: When using a multi-host deployment, each host is assigned unique ports and PFs and manages its own LAG.
• Hardware GRO: Hardware Generic Receive Offload (GRO) reduces CPU overhead and improves throughput by offloading the task of reassembling incoming network packets from the CPU.
• Precision Time Measurement (PTM): Precision Time Measurement (PTM) enhances clock synchronization accuracy between the NIC's hardware clock and the system's host clock. It addresses inaccuracies caused by asymmetric PCIe request and response times, which can affect PTP.
• Transport RDMA Steering Domain: Transport RDMA steering domain in the kernel allows users to create steering tables and rules using the new domain types FS_FT_RDMA_TRANSPORT_RX and FS_FT_RDMA_TRANSPORT_TX, with support for both DevX commands and the added functionality in mlx5dv_create_flow_matcher().
• DevX QPs Parallel Cleanup: Reduces cleanup (kill) time of user-space applications that use DevX QPs, without requiring any changes on the user's end. When using a kernel that includes this patch, DevX QP destruction upon cleanup will be sent to the firmware in parallel, rather than serially as before, resulting in faster cleanup times. The more DevX QPs the application has, the more noticeable the improvement will be.
• Flow Control for Solicited MADs: Implements flow control for solicited MADs in the MAD layer to prevent loss due to insufficient resources at the receiver. Both the client and server function as receivers: the server handles incoming requests, while the client receives the responses.
• Increased the default TX queue length in IPoIB to enhance qdisc queueing and reduce CPU spikes.
• The "--defltprio" flag has been deprecated and removed from the mlnx_qos tool.

• 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.

Red Hat Enterprise Linux 10.0

Updated to version 14.4.473.25

Red Hat Enterprise Linux 10.0

Updated to version 14.4.473.25

Updated some wordings in the VROC pop-up string for better alignment.

Enabled Bifurcation capability support for system OCP slots.

Enabled VROC options on DL320 Gen12 OEM.

Updated some wordings in the VROC pop-up string for better alignment.

Enabled Bifurcation capability support for system OCP slots.

Enabled VROC options on DL320 Gen12 OEM.

Add help text for "Smooth Cooling" System Configuration (RBSU) option.

Add help text for "Smooth Cooling" System Configuration (RBSU) option.

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

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

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

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

This Component is FIPs enabled.

This Component is FIPs enabled.

This Component is FIPs enabled.

This Component is FIPs enabled.

Firmware Dependencies:

Enhancements/New Features:

This is the initial version of the firmware.

Known Issues:

Firmware Dependencies:

Enhancements/New Features:

This is the initial version of the firmware.

Known Issues:

New features and changes included in version 22.44.1036:

• Unified PTP is now supported across different VFs on the same PF.
• 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.

New features and changes included in version 22.44.1036:

• Unified PTP is now supported across different VFs on the same PF.
• 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.

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.