jme: Use ringmap to do MSI-X cpu assignment and fill redirect table.

kernel: Use the new auto-created sysctl ctx/tree in various drivers.

Everywhere where we formerly rolled a hw.fooX.* per-device ctx/tree
ourselves.

This commit switches it to dev.foo.X.*

jme: Enable PHY calibration to fix compat issue w/ certain switches

EA settings are obtained from JMicron Linux driver.

See-also: FreeBSD PR kern/177400

jme: Avoid using magic number for TX register writing aggregation

jme: Improve tiny packets transmission performance on low frequency CPU

Update TXCSR register a little bit often; mainly to improve timeliness of
packets transmission:
The TXCSR register is updated

jme: Improve tiny packets transmission performance on low frequency CPU

Update TXCSR register a little bit often; mainly to improve timeliness of
packets transmission:
The TXCSR register is updated after certain amount of TX descriptors are
added to the hardware TX ring. The default value of the amount of TX
descriptors are 16. This value could be further tuned by per-device sysctl
node hw.jmeX.tx_wreg.

The default value improves tiny packets transmission performance w/ JMC250
on AMD970@2200Mhz (831Kpps -> 911Kpps), on AMD970@800Mhz (484Kpps -> 834Kpps)
and it does not increase CPU usage on AMD970@3500Mhz (CPU usage stays @26%,
JMC250 could only do 911Kpps).

show more ...

jme: Put TX related stuffs into struct jme_txdata

While I'm here, add more comment

jme: Move uncommonly accessed fields to the end of the struct

jme: Rework MSI-X mapping, so RX MSI-X need not read register

RX empty event rarely happens (I didn't see it even if the card is
sinking full speed tiny packets on one RX ring). Put the RX empty
ev

jme: Rework MSI-X mapping, so RX MSI-X need not read register

RX empty event rarely happens (I didn't see it even if the card is
sinking full speed tiny packets on one RX ring). Put the RX empty
events into independent MSI-X, so the hot path RX MSI-X need not
read register at all.

show more ...

jme: Remove unused macros

jme: Change polling(4) support to ifpoll support

While I'm here, fix the disable/enable intr handing.

jme: Record number of times that RX ring becomes empty

jme: Allow MSI-X be evenly spreaded across CPUs

jme: Add TSO support

jme: Cache align RX/TX data structure

jme: Only main serializer is needed for timeout callback

This reduces periodic contention against TX/RX path.

jme: Don't immediately recycle the TX descriptor even if it is owned by us.

This chip will always update the TX descriptor's 32bits fields in order,
so even if the status field has been updated, i.e

jme: Don't immediately recycle the TX descriptor even if it is owned by us.

This chip will always update the TX descriptor's 32bits fields in order,
so even if the status field has been updated, i.e. OWN is cleared, it still
does not mean that the buflen field has been updated. To avoid this race
we don't immediately recycle the currently checking TX descriptor. Instead,
next TX descriptor's OWN bit is checked, if it is cleared, then the updating
of the currently checked TX descrptor is really done.

This is intended to fix the seldom watchdog timeout that was observed on this
chip.

Thank devinchiu@jmicron.com very much for providing necessary information.

show more ...

jme: Don't reuse the RX descriptor if the RSS is not set by the hardware

Reenable RSS; it is stable enough now.

jme: Save physical address of RX buffer, which will be used upon error

jme: Increase alignment of TX/RX descriptor ring to the cacheline size

Round up TX/RX ring size to cacheline size too.

jme: Move TX descriptor count into chain_data

Improve CPU cache utilization

jme: Move RX ring count and RX descriptor count into rxdata

Improve CPU cache utilization

jme: Pass rxdata to RX functions

jme: Change how IFCAP_RSS is handled

- Number of RX rings being used is not changed.
- Hardware is always setup w/ RSS support.
- If IFCAP_RSS is not enabled, we simply don't use the RSS hash provid

jme: Change how IFCAP_RSS is handled

- Number of RX rings being used is not changed.
- Hardware is always setup w/ RSS support.
- If IFCAP_RSS is not enabled, we simply don't use the RSS hash provided
by the hardware.

show more ...

jme: Support multiple MSI-X interrupt model

jme: Split ifnet serializer; in preparation for multiple MSI-X support