summaryrefslogtreecommitdiffstats
path: root/sys/dev/e1000
Commit message (Collapse)AuthorAgeFilesLines
* Re-add opt_inet.h, as we did in r193862 and lost yet again.bz2009-07-141-0/+1
| | | | Approved by: re (kib)
* The new method of reading the mac address from thejfv2009-07-061-1/+36
| | | | | | | RAR(0) register does not work on this old adapter, provide a local routine that does it the older way. Approved by: re
* Type problem when FreeBSD is in a virtualized environment, thejfv2009-06-291-1/+1
| | | | | | | | result was when the RX index wrapped it was converted into some sort of gibberish and written into the RDT register, effectively killing the RX side of the thing :) Approved by: re
* Use if_maddr_rlock()/if_maddr_runlock() rather than IF_ADDR_LOCK()/rwatson2009-06-262-4/+4
| | | | | | | | | | | | | IF_ADDR_UNLOCK() across network device drivers when accessing the per-interface multicast address list, if_multiaddrs. This will allow us to change the locking strategy without affecting our driver programming interface or binary interface. For two wireless drivers, remove unnecessary locking, since they don't actually access the multicast address list. Approved by: re (kib) MFC after: 6 weeks
* Change intr_bind to bus_bind_intr, also limit this tojfv2009-06-251-6/+4
| | | | | multiqueue setup which is not the shipping default for igb (its set to 1).
* need to make intr_bind call architecture specific forjfv2009-06-241-2/+2
| | | | global builds (failing sun4v lint build)
* Fix lint issue.jfv2009-06-241-2/+2
|
* Updates for both the em and igb drivers, add supportjfv2009-06-2419-1505/+2742
| | | | | for multiqueue tx, shared code updates, new device support, and some bug fixes.
* Add opt_inet.h back lost with r190872.bz2009-06-091-0/+1
| | | | | This will bring back improved IPv4 SIOCSIFADDR ioctl handling not re-initializing the interface if avoidable.
* When user_frac in the polling subsystem is low it is going to busy theattilio2009-05-301-11/+22
| | | | | | | | | | | | | | | | | | | | | CPU for too long period than necessary. Additively, interfaces are kept polled (in the tick) even if no more packets are available. In order to avoid such situations a new generic mechanism can be implemented in proactive way, keeping track of the time spent on any packet and fragmenting the time for any tick, stopping the processing as soon as possible. In order to implement such mechanism, the polling handler needs to change, returning the number of packets processed. While the intended logic is not part of this patch, the polling KPI is broken by this commit, adding an int return value and the new flag IFCAP_POLLING_NOCOUNT (which will signal that the return value is meaningless for the installed handler and checking should be skipped). Bump __FreeBSD_version in order to signal such situation. Reviewed by: emaste Sponsored by: Sandvine Incorporated
* Call drbr_stats_update to update ifp stats directly when we bypass the ↵kmacy2009-05-141-3/+6
| | | | buf_ring on transmit
* fix typo in conditionalkmacy2009-04-271-1/+1
|
* collapse the two em_start_locked routines in to onekmacy2009-04-272-48/+24
|
* Correct fat finger mistakejfv2009-04-271-1/+1
|
* igb_txeof also has a case where the watchdog may notjfv2009-04-271-9/+8
| | | | | | get reset when it should be MFC after: 2 weeks
* Thanks for Michael Tuexen for tracking down a path wherejfv2009-04-271-14/+21
| | | | | | | the watchdog timer was not being rearmed in txeof, and also a missing case in the new code. MFC after: 2 weeks
* fix typokmacy2009-04-231-1/+1
|
* fix panic when using msixkmacy2009-04-231-0/+5
| | | | Pointed out by Nate Whitehorn
* Make sure the ALTQ case is handle correctly by using drbr_dequeuekmacy2009-04-231-1/+1
|
* call base if_qflush routine to flush if_sndkmacy2009-04-161-0/+1
|
* Thanks to Michael Tuexen and Randall Scott for providing ajfv2009-04-141-8/+8
| | | | | | | few important bug fixes found while they were doing SCTP development, and that I somehow lost during the scramble. Thanks guys!!
* - define em_transmit and em_qflushkmacy2009-04-142-13/+138
| | | | | | - make buF_ring usage conditional but enabled by default Reviewed by: jfv
* Fix build problem with data format.jfv2009-04-101-2/+2
|
* This delta syncs the em and igb drivers with Intel,jfv2009-04-1022-1042/+1722
| | | | | | | adds header split and SCTP support into the igb driver. Various small improvements and fixes. MFC after: 2 weeks
* Fix a cut/paste bug which prevents us from setting the averagegnn2009-01-131-1/+1
| | | | | | | latency tunable. Reviewed by: jfv MFC after: 1 day
* Restore opt_inet.h include which was lost in the last commit.thompsa2008-12-071-0/+1
|
* Thanks to the reminder from Ganbold, small fix in the RX failurejfv2008-11-271-13/+11
| | | | | path for an infinite loop. Problem originally noticed in ixgbe by Jeff Roberson and fixed there. Thanks to everyone involved.
* This delta is primarily a fix for es2lan devices thatjfv2008-11-2626-1388/+1368
| | | | | | | | | | | | | will sometimes fail to initialize problem due to a lock contention with management hardware. However, in order to deliver that fix it was necessary to take a shared code update as a whole, and this required scattered changes in the core code to be compatible. The em driver now has VLAN HW support added as the igb driver had previously. MFC after: ASAP - in time for 7.1 RELEASE
* Hide AF_INET specific ioctl handling under #ifdef INET.bz2008-11-061-0/+5
| | | | MFC after: 2 months
* Hide AF_INET specific ioctl handling under #ifdef INET.bz2008-11-061-0/+5
| | | | MFC after: 2 months
* Update to igb driver:jfv2008-08-282-289/+183
| | | | | | | | | | | | | | | | | | | - changes in support of the VLAN filter fix to 126850 - removal of a bunch of legacy code that was cruft, if not possibly harmful. - removal of POLLING from this driver, with multiqueue and MSIX it just makes no sense here. - Fix an LRO bug that I've been working on internally, intermittent panics under stress, the problem was releasing the RX ring lock before the LRO flushing. - Following the above fix I now enable LRO by default - For performance reasons increase the default number of RX queues to 4. - Add AIM - "Adaptive Interrupt Moderation", a fancy way of saying that the EITR value is dynamically changed based on the size of packets in the last interrupt interval. - Much goodness to try, enjoy!!
* Data type fixjfv2008-07-311-2/+2
|
* Include netinet/tcp_lro.h, unbreak the buildps2008-07-301-1/+1
|
* Merge of the source for igb and em into dev/e1000, thisjfv2008-07-3035-0/+35053
proved to be necessary to make the static drivers work in EITHER/OR or BOTH configurations. Modules will still build in sys/modules/igb or em as before. This also updates the igb driver for support for the 82576 adapter, adds shared code fixes, and etc.... MFC after: ASAP
OpenPOWER on IntegriCloud