of the newer drivers. The basic problem was
that the driver was pulling the mbuf off the
drbr ring and then when sending with xmit(), encounting
a full transmit ring. Thus the lower layer
xmit() function would return an error, and the
drivers would then append the data back on to the ring.
For TCP this is a horrible scenario sure to bring
on a fast-retransmit.
The fix is to use drbr_peek() to pull the data pointer
but not remove it from the ring. If it fails then
we either call the new drbr_putback or drbr_advance
method. Advance moves it forward (we do this sometimes
when the xmit() function frees the mbuf). When
we succeed we always call advance. The
putback will always copy the mbuf back to the top
of the ring. Note that the putback *cannot* be used
with a drbr_dequeue() only with drbr_peek(). We most
of the time, in putback, would not need to copy it
back since most likey the mbuf is still the same, but
sometimes xmit() functions will change the mbuf via
a pullup or other call. So the optimial case for
the single consumer is to always copy it back. If
we ever do a multiple_consumer (for lagg?) we
will need a test and atomic in the put back possibly
a seperate putback_mc() in the ring buf.
Reviewed by: jhb@freebsd.org, jlv@freebsd.org
tree used it incorrectly, which lead to inaccurate overrated
if_obytes accounting. The drbr(9) used to update ifnet stats on
drbr_enqueue(), which is not accurate since enqueuing doesn't
imply successful processing by driver. Dequeuing neither mean
that. Most drivers also called drbr_stats_update() which did
accounting again, leading to doubled if_obytes statistics. And
in case of severe transmitting, when a packet could be several
times enqueued and dequeued it could have been accounted several
times.
o Thus, make drbr(9) API thinner. Now drbr(9) merely chooses between
ALTQ queueing or buf_ring(9) queueing.
- It doesn't touch the buf_ring stats any more.
- It doesn't touch ifnet stats anymore.
- drbr_stats_update() no longer exists.
o buf_ring(9) handles its stats itself:
- It handles br_drops itself.
- br_prod_bytes stats are dropped. Rationale: no one ever
reads them but update of a common counter on every packet
negatively affects performance due to excessive cache
invalidation.
- buf_ring_enqueue_bytes() reduced to buf_ring_enqueue(), since
we no longer account bytes.
o Drivers handle their stats theirselves: if_obytes, if_omcasts.
o mlx4(4), igb(4), em(4), vxge(4), oce(4) and ixv(4) no longer
use drbr_stats_update(), and update ifnet stats theirselves.
o bxe(4) was the most correct driver, it didn't call
drbr_stats_update(), thus it was the only driver accurate under
moderate load. Now it also maintains stats itself.
o ixgbe(4) had already taken stats from hardware, so just
- drop software stats updating.
- take multicast packet count from hardware as well.
o mxge(4) just no longer needs NO_SLOW_STATS define.
o cxgb(4), cxgbe(4) need no change, since they obtain stats
from hardware.
Reviewed by: jfv, gnn
functions instead of using the IF_ADDR_LOCK directly. The wrapper
functions are the supported interface for device drivers.
Reviewed by: bz, philip
MFC after: 1 week
one. Interestingly, these are actually the default for quite some time
(bus_generic_driver_added(9) since r52045 and bus_generic_print_child(9)
since r52045) but even recently added device drivers do this unnecessarily.
Discussed with: jhb, marcel
- While at it, use DEVMETHOD_END.
Discussed with: jhb
- Also while at it, use __FBSDID.
The SYSCTL_NODE macro defines a list that stores all child-elements of
that node. If there's no SYSCTL_DECL macro anywhere else, there's no
reason why it shouldn't be static.
increase robustness (no more calls to panic(9)) and simplify
code.
- Allocate RX/TX data structures as a single buffer rather than
an array of 4KB pages to simplify code.
- Fixed LRO (aka TPA) code. Removed kernel module parameter and
support enabling disabling LRO through ifconfig(8) command line.
LRO is still disabled by default but should be enabled for best
performance on an endpoint device.
- Fixed statistcs code and removed kernel module parameter (stats
should just work).
- Added many software counters to help identify the cause of some
performance issues.
- Streamlined adapter internal init/stop code paths.
- Fiddled with debug code (adding some here, removing some there).
- Continued style(9) adjustments.
- Use bus_bind_intr() to bind interrupt to a CPU when RSS/TSS is used.
- Use M_DONTWAIT for RSS/TSS buffer allocation.
- Add statistic to track max DRBR queue depth.
- Fix problem in bxe_change_mtu() which referenced the old MTU size
in a debug print statement.
MFC after: Two weeks
- Centralize PCI resource allocation/release.
- Enable flowid (TSS) support.
- Added "per-fastpath" locks and watchdog timeouts.
- Fixed problem where the CQ producer index was advanced beyond
the size of the CQ ring during initialization.
- Replaced hard-coded debug levels in some debug print statements.
- More style(9) fixes.
MFC after: Two weeks
chain to be corrupted.
- Removed many console print warnings and replaced with driver maintained
counters.
- Several style(9) fixes.
MFC after: One week.
