NAME
jme
—
JMicron Gigabit/Fast Ethernet
driver
SYNOPSIS
To compile this driver into the kernel, place the following lines in your kernel configuration file:
device miibus
device jme
Alternatively, to load the driver as a module at boot time, place the following line in loader.conf(5):
if_jme_load="YES"
DESCRIPTION
Thejme
device driver provides support for JMicron
JMC250 PCI Express Gigabit Ethernet controllers and JMicron JMC260 PCI Express
Fast Ethernet controllers.
All LOMs supported by the jme
driver have
TCP/UDP/IP checksum offload for both transmit and receive, TCP segmentation
offload (TSO), receive side scaling (RSS), multiple vector MSI-X, hardware
VLAN tag stripping/insertion features, an interrupt coalescing/moderation
mechanism as well as a 64-bit multicast hash filter. Up to 4 reception
queues can be enabled. By default, the jme
driver
will try enabling as many reception queues as allowed by the number of CPUs
in the system.
The JMC250 also supports Jumbo Frames (up to 9216 bytes), which can be configured via the interface MTU setting. Selecting an MTU larger than 1500 bytes with the ifconfig(8) utility configures the adapter to receive and transmit Jumbo Frames.
The jme
driver supports the following
media types:
autoselect
- Enable autoselection of the media type and options. The user can manually override the autoselected mode by adding media options to rc.conf(5).
10baseT/UTP
- Set 10Mbps operation.
100baseTX
- Set 100Mbps (Fast Ethernet) operation.
1000baseT
- Set 1000baseT operation over twisted pair.
The jme
driver supports the following
media options:
full-duplex
- Force full duplex operation.
half-duplex
- Force half duplex operation.
For more information on configuring this device, see
ifconfig(8). The jme
driver supports
polling(4).
Loader Tunables
By default, the driver will use MSI-X if it is supported. This behavior can be turned off by setting the following tunable: (X is the device unit number):
hw.jme.msix.enable=0 hw.jmeX.msix.enable=0
If MSI-X is disabled, the driver will use MSI if it is supported. This behavior can be turned off by setting the following tunable:
hw.jme.msi.enable=0 hw.jmeX.msi.enable=0
If MSI is used, MSI's target CPU can be changed by the following tunable:
hw.jmeX.msi.cpu
The maximum allowed value for this tunable is the number of CPUs minus one.
Number of reception queues that can be enabled:
hw.jme.rx_ring_count hw.jmeX.rx_ring_count
Maximum allowed value for these tunables is 4. Setting these tunables to 0 allows driver to enable as many reception queues as allowed by the number of CPUs.
Number of reception descriptors that can be used:
hw.jme.rx_desc_count hw.jmeX.rx_desc_count
Maximum allowed value for these tunables is 1024.
Number of transmission descriptors that can be used:
hw.jme.tx_desc_count hw.jmeX.tx_desc_count
Maximum allowed value for these tunables is 1024.
MIB Variables
A number of per-interface variables are implemented in the dev.jme.X branch of the sysctl(3) MIB.
- tx_coal_to
- Maximum amount of time to delay for TX completion interrupt in units of 1us. The accepted range is 1 to 65535, the default is 250 (250us).
- tx_coal_pkt
- Maximum number of packets to fire TX completion interrupt. The accepted range is 0 to 255, the default is 128. Packet count based TX interrupt coalescing could be disabled by setting this variable to 0.
- rx_coal_to
- Maximum amount of time to delay for RX completion interrupt in units of 1us. The accepted range is 1 to 65535, the default is 150 (150us).
- rx_coal_pkt
- Maximum number of packets to fire RX completion interrupt. The accepted range is 0 to 255, the default is 64. Packet count based RX interrupt coalescing could be disabled by setting this variable to 0.
- rx_desc_count
- Number of RX descriptors per-ring (read-only). Use the tunable hw.jme.rx_desc_count to configure it.
- tx_desc_count
- Number of TX descriptors (read-only). Use the tunable hw.jme.tx_desc_count to configure it.
- rx_ring_count
- Number of RX rings (read-only). Use the tunable hw.jme.rx_ring_count to configure it.
- tx_wreg
- The number of transmission descriptors should be setup before the hardware register is written. Setting this value too high will have negative effect on transmission timeliness. Setting this value too low will hurt overall transmission due to the frequent hardware register writing.
SEE ALSO
altq(4), arp(4), ifmedia(4), miibus(4), netintro(4), ng_ether(4), polling(4), vlan(4), ifconfig(8)
HISTORY
The jme
driver was written by
Pyun YongHyeon
<yongari@FreeBSD.org>.
It first appeared in FreeBSD 7.1 and was imported
into DragonFly 2.1. Sepherosa
Ziehau added the receive side scaling and multiple vector MSI-X
support to DragonFly.