net/sfc: factor out libefx-based Rx datapath

[dpdk.git] / doc / guides / nics / sfc_efx.rst

diff --git a/doc/guides/nics/sfc_efx.rst b/doc/guides/nics/sfc_efx.rst
index eb9d26d..2d7a241 100644 (file)
--- a/doc/guides/nics/sfc_efx.rst
+++ b/doc/guides/nics/sfc_efx.rst
@@ -44,7 +44,7 @@ SFC EFX PMD has support for:
 
 - Multiple transmit and receive queues
 
 
 - Multiple transmit and receive queues
 

-- Link state information
+- Link state information including link status change interrupt

 
 - IPv4/IPv6 TCP/UDP transmit checksum offload
 
 
 - IPv4/IPv6 TCP/UDP transmit checksum offload
 


@@ -53,14 +53,42 @@ SFC EFX PMD has support for:
 - Extended statistics (see Solarflare Server Adapter User's Guide for
   the statistics description)
 
 - Extended statistics (see Solarflare Server Adapter User's Guide for
   the statistics description)
 

+- Basic flow control
+
+- MTU update
+
+- Jumbo frames up to 9K
+
+- Promiscuous mode
+
+- Allmulticast mode
+
+- TCP segmentation offload (TSO)
+
+- Multicast MAC filter
+
+- IPv4/IPv6 TCP/UDP receive checksum offload
+
+- Received packet type information
+
+- Receive side scaling (RSS)
+
+- RSS hash
+
+- Scattered Rx DMA for packet that are larger that a single Rx descriptor
+
+- Deferred receive and transmit queue start
+
+- Transmit VLAN insertion (if running firmware variant supports it)
+
+- Flow API
+

 
 Non-supported Features
 ----------------------
 
 The features not yet supported include:
 
 
 Non-supported Features
 ----------------------
 
 The features not yet supported include:
 

-- Link status change interrupt
-

 - Receive queue interupts
 
 - Priority-based flow control
 - Receive queue interupts
 
 - Priority-based flow control


@@ -75,8 +103,6 @@ The features not yet supported include:
 
 - VLAN stripping
 
 
 - VLAN stripping
 

-- Scattered receive
-

 - LRO
 
 
 - LRO
 
 


@@ -90,6 +116,49 @@ required in the receive buffer.
 It should be taken into account when mbuf pool for receive is created.
 
 
 It should be taken into account when mbuf pool for receive is created.
 
 

+Flow API support
+----------------
+
+Supported attributes:
+
+- Ingress
+
+Supported pattern items:
+
+- VOID
+
+- ETH (exact match of source/destination addresses, individual/group match
+  of destination address, EtherType)
+
+- VLAN (exact match of VID, double-tagging is supported)
+
+- IPV4 (exact match of source/destination addresses,
+  IP transport protocol)
+
+- IPV6 (exact match of source/destination addresses,
+  IP transport protocol)
+
+- TCP (exact match of source/destination ports)
+
+- UDP (exact match of source/destination ports)
+
+Supported actions:
+
+- VOID
+
+- QUEUE
+
+Validating flow rules depends on the firmware variant.
+
+Ethernet destinaton individual/group match
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Ethernet item supports I/G matching, if only the corresponding bit is set
+in the mask of destination address. If destinaton address in the spec is
+multicast, it matches all multicast (and broadcast) packets, oherwise it
+matches unicast packets that are not filtered by other flow rules.
+
+

 Supported NICs
 --------------
 
 Supported NICs
 --------------
 


@@ -157,6 +226,13 @@ whitelist option like "-w 02:00.0,arg1=value1,...".
 Case-insensitive 1/y/yes/on or 0/n/no/off may be used to specify
 boolean parameters value.
 
 Case-insensitive 1/y/yes/on or 0/n/no/off may be used to specify
 boolean parameters value.
 

+- ``rx_datapath`` [auto|efx] (default **auto**)
+
+  Choose receive datapath implementation.
+  **auto** allows the driver itself to make a choice based on firmware
+  features available and required by the datapath implementation.
+  **efx** chooses libefx-based datapath which supports Rx scatter.
+

 - ``perf_profile`` [auto|throughput|low-latency] (default **throughput**)
 
   Choose hardware tunning to be optimized for either throughput or
 - ``perf_profile`` [auto|throughput|low-latency] (default **throughput**)
 
   Choose hardware tunning to be optimized for either throughput or


@@ -173,3 +249,12 @@ boolean parameters value.
   Enable extra logging of the communication with the NIC's management CPU.
   The logging is done using RTE_LOG() with INFO level and PMD type.
   The format is consumed by the Solarflare netlogdecode cross-platform tool.
   Enable extra logging of the communication with the NIC's management CPU.
   The logging is done using RTE_LOG() with INFO level and PMD type.
   The format is consumed by the Solarflare netlogdecode cross-platform tool.

+
+- ``stats_update_period_ms`` [long] (default **1000**)
+
+  Adjust period in milliseconds to update port hardware statistics.
+  The accepted range is 0 to 65535. The value of **0** may be used
+  to disable periodic statistics update. One should note that it's
+  only possible to set an arbitrary value on SFN8xxx provided that
+  firmware version is 6.2.1.1033 or higher, otherwise any positive
+  value will select a fixed update period of **1000** milliseconds