Commit Graph

212 Commits

Author SHA1 Message Date
Jack F Vogel
83cef45266 Alter the mq_start routine to do a TRYLOCK and call to the locked routine
rather than just queueing. The former code was an attempt at getting
UDP performance up, but there have been customer reports of problems with it,
so the ixgbe approach seems the best solution for now.
2013-08-13 00:25:39 +00:00
Scott Long
c68534f1d5 Update PCI drivers to no longer look at the MEMIO-enabled bit in the PCI
command register.  The lazy BAR allocation code in FreeBSD sometimes
disables this bit when it detects a range conflict, and will re-enable
it on demand when a driver allocates the BAR.  Thus, the bit is no longer
a reliable indication of capability, and should not be checked.  This
results in the elimination of a lot of code from drivers, and also gives
the opportunity to simplify a lot of drivers to use a helper API to set
the busmaster enable bit.

This changes fixes some recent reports of disk controllers and their
associated drives/enclosures disappearing during boot.

Submitted by:	jhb
Reviewed by:	jfv, marius, achadd, achim
MFC after:	1 day
2013-08-12 23:30:01 +00:00
Jack F Vogel
4dc63104ae Improve the MSIX setup code in the drivers, thanks to Marius for
the changes. Make sure that pci_alloc_msix() does give us the vectors
we need and fall back to MSI when it doesn't, also release any that
were allocated when insufficient.

MFC after: 3 days
2013-08-12 22:54:38 +00:00
Jack F Vogel
d0913b7f25 Make the various driver MSIX setup routines fallback to MSI more
gracefully. This change was suggested by Marius Strobl, thank you.

PR: kern/181016
MFC after: ASAP
2013-08-06 21:01:38 +00:00
Jack F Vogel
54a6317360 When the igb driver is static there are cases when early interrupts occur,
resulting in a panic in refresh_mbufs, to prevent this add a check in the
interrupt handler for DRV_RUNNING.

MFC after: 1 day (critical for 9.2)
2013-08-06 18:00:53 +00:00
Jack F Vogel
a1db87ec73 Change the E1000 driver option header handling to match the
ixgbe driver. As it was, when building them as a module INET
and INET6 are not defined. In these drivers it does not cause
a panic, however it does result in different behavior in the
ioctl routine when you are using a module vs static, and I
think the behavior should be the same.

MFC after: 3 days
2013-07-12 22:36:26 +00:00
Luigi Rizzo
4dc07530d7 if_lem.c: make sure that lem_rxeof() can drain the entire rx queue
irrespective of the setting of lem_rx_process_limit, while
	giving a chance to the taskqueue scheduler to act after
	each chunk.
	This makes lem_rxeof similar to the one in if_em.c and if_igb.c .

if_lem.c and if_em.c: add a sysctl to manually configure the
	'itr' moderation register.

Approved by:	Jack Vogel
2013-05-09 17:07:30 +00:00
Luigi Rizzo
1405478115 simplify the code to initialize the RDT while in netmap mode. 2013-05-09 16:57:02 +00:00
Eitan Adler
f7efb9e28e Update Intel email address.
PR:		docs/175349
Submitted by:	Lars Eggert <lars@netapp.com>
Discussed with:	jfv
2013-05-02 01:36:52 +00:00
Luigi Rizzo
9b2e4517d5 use netmap_rx_irq() and netmap_tx_irq() instead of replicating the
logic in the individual driver.
2013-04-30 16:51:58 +00:00
Luigi Rizzo
d61ba75247 use netmap_rx_irq() / netmap_tx_irq() to handle interrupts in
netmap mode, removing the logic from individual drivers.

(note: if_lem.c not updated yet due to some other pending modifications)
2013-04-30 16:18:29 +00:00
Jack F Vogel
386c110e3c Corrections to the RX checksum code, make sure its disabled as
well as enabled when necessary. And simplify the checksum routine
itself, adding UDP bit to the test. Thanks to Kevin Lo for pointing
out the problems and code suggestions.
2013-04-15 17:01:42 +00:00
Jack F Vogel
f0105d2d23 Simplify allocate_legacy code, txr pointer was breaking LEGACY compile,
thanks to Nick Rogers for pointing this out.
2013-04-10 17:51:39 +00:00
Jack F Vogel
3b0b7ffbb9 Correct the multicast handling in the E1000 drivers as was
done in ixgbe, thanks to Mike Karels for this fix. When exiting
promiscuous mode MPE bit was being unconditionally cleared, this
should not be done if we are in MAX multicast groups.
2013-04-03 23:39:54 +00:00
Sean Bruno
8e3ff376cf Update man page for igb(4) with a little bit of information about
hw.igb.num_queues for those so inclined.

PR:		kern/177384
Submitted by:	hiren.panchasara@gmail.com
Reviewed by:	sbruno@
Approved by:	jfv@
Obtained from:	Yahoo! Inc.
MFC after:	2 weeks
2013-04-03 21:55:19 +00:00
Jack F Vogel
be2095895a Change the define in the header to eliminate unnecessary data
when using LEGACY TX.
2013-03-29 18:46:13 +00:00
Jack F Vogel
c05891a6da Change defines in the igb driver to allow an easier selection of
the older if_start/non-multiqueue interface from the stack. This
is not the default, but can be turned on in the Makefile now regardless
of the OS level to allow either testing or use of ALTQ.

MFC after: one week
2013-03-29 18:25:45 +00:00
Jack F Vogel
6ab6bfe32f Refresh on the shared code for the E1000 drivers.
- bear with me, there are lots of white space changes, I would not
    do them, but I am a mere consumer of this stuff and if these drivers
    are to stay in shape they need to be taken.

em driver changes: support for the new i217/i218 interfaces

igb driver changes:
  - TX mq start has a quick turnaround to the stack
  - Link/media handling improvement
  - When link status changes happen the current flow control state
    will now be displayed.
  - A few white space/style changes.

lem driver changes:
  - the shared code uncovered a bogus write to the RLPML register
    (which does not exist in this hardware) in the vlan code,this
    is removed.
2013-02-21 00:25:45 +00:00
Randall Stewart
ded5ea6a25 This fixes a out-of-order problem with several
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
2013-02-07 15:20:54 +00:00
Sofian Brabez
61bfd86762 Use DEVMETHOD_END macro defined in sys/bus.h instead of {0, 0} sentinel on device_method_t arrays
Reviewed by:	cognet
Approved by:	cognet
2013-01-30 18:01:20 +00:00
Steven Hartland
31e85bd9cd Fixed mbuf free when receive structures fail to allocate.
This prevents quad igb card on high core machines, without any nmbcluster or
igb queue tuning wedging the boot process if all nics are configured.

Reviewed by:	jfv
Approved by:	pjd (mentor)
MFC after:	1 week
2013-01-12 16:05:55 +00:00
Gleb Smirnoff
c6499eccad Mechanically substitute flags from historic mbuf allocator with
malloc(9) flags in sys/dev.
2012-12-04 09:32:43 +00:00
Gleb Smirnoff
9c402aeb41 drbr_enqueue() awlays consumes mbuf, no matter did it
fail or not. The mbuf pointer is no longer valid, so
can't be reused after.

  Fix igb_mq_start() where mbuf pointer was used after
drbr_enqueue().

  This eventually leads us to all invocations of
igb_mq_start_locked() called with third argument as NULL.
This allows us to simplify this function.

Submitted by:	Karim Fodil-Lemelin <fodillemlinkarim gmail.com>
Reviewed by:	jfv
2012-11-26 20:03:57 +00:00
Eitan Adler
2da1951583 Now that device disabling is generic, remove extraneous code from the
device drivers that used to provide this feature.

This is a subset of 241856 (which was reverted)

Reviewed by:	des
Approved by:	cperciva (implicit)
MFC after:	1 week
2012-10-22 22:29:48 +00:00
Eitan Adler
a8de37b024 This isn't functionally identical. In some cases a hint to disable
unit 0 would in fact disable all units.

This reverts r241856

Approved by: cperciva (implicit)
2012-10-22 13:06:09 +00:00
Eitan Adler
76b7512247 Now that device disabling is generic, remove extraneous code from the
device drivers that used to provide this feature.

Reviewed by:	des
Approved by:	cperciva
MFC after:	1 week
2012-10-22 03:41:14 +00:00
Eitan Adler
db702c59cf remove duplicate semicolons where possible.
Approved by:	cperciva
MFC after:	1 week
2012-10-22 03:00:37 +00:00
Gleb Smirnoff
063efed28c The drbr(9) API appeared to be so unclear, that most drivers in
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
2012-09-28 18:28:27 +00:00
John Baldwin
aceb040376 Merge similar fixes from 223198 from igb to ixgbe:
- Use a dedicated task to handle deferred transmits from the if_transmit
  method instead of reusing the existing per-queue interrupt task.
  Reusing the per-queue interrupt task could result in both an interrupt
  thread and the taskqueue thread trying to handle received packets on a
  single queue resulting in out-of-order packet processing and lock
  contention.
- Don't define ixgbe_start() at all where if_transmit is used.

Tested by:	Vijay Singh
Reviewed by:	jfv
MFC after:	2 weeks
2012-09-26 18:11:43 +00:00
Sean Bruno
126a39ce60 This patch fixes a nit in the em, lem, and igb driver statistics. Increment
adapter->dropped_pkts instead of if_ierrors because if_ierrors is
overwritten by hw stats collection.

Submitted by:	Andrew Boyer <aboyer@averesystems.com>
Reviewed by:	Jack F Vogel <jfv@freebsd.org>
MFC after:	2 weeks
2012-09-23 22:53:39 +00:00
Gavin Atkinson
e935190a33 Switch some PCI register reads from using magic numbers to using the names
defined in pcireg.h

MFC after:	1 week
2012-09-19 12:27:23 +00:00
Gavin Atkinson
389c8bd51e Align the PCI Express #defines with the style used for the PCI-X
#defines.  This also has the advantage that it makes the names more
compact, iand also allows us to correct the non-uniform naming of
the PCIM_LINK_* defines, making them all consistent amongst themselves.

This is a mostly mechanical rename:
  s/PCIR_EXPRESS_/PCIER_/g
  s/PCIM_EXP_/PCIEM_/g
  s/PCIM_LINK_/PCIEM_LINK_/g

When this is MFC'd, #defines will be added for the old names to assist
out-of-tree drivers.

Discussed with:	jhb
MFC after:	1 week
2012-09-18 22:04:59 +00:00
Eitan Adler
96240c89f0 Correct double "the the"
Approved by:	cperciva
MFC after:	3 days
2012-09-14 21:28:56 +00:00
Jack F Vogel
252781f47d Customer report of a panic on boot due to the old
"m_getjcl:invalid cluster type" that occurred some
time back with the igb driver. This happens often when
booting over the net. I believe the NIC hardware is left
in a warm state when handed over to the driver, and a stray
RX interrupt happens earlier than the code is prepared for
it to happen. This change was verified to fix the problem,
its kind of a bandaid... but it is similar to what was done
in the igb code.
2012-08-15 17:12:40 +00:00
Jack F Vogel
724f79462b Make the polling interface in igb able to handle
multiqueue, and correct the rxdone handling. Update
the polling man page to include igb as well.

Thanks to Mark Johnston for these changes.
2012-08-06 22:43:49 +00:00
Jack F Vogel
6aa4d618ca Correct the mq_start routine to avoid out-of-order
packet delivery, always enqueue when possible. Also
correct the DEPLETED test as multiple bits might be
set.  Thanks to Randall Stewart for the changes!
2012-08-06 20:44:05 +00:00
Sean Bruno
8844c80848 CPU_NEXT() already handles wrapping around to the beginning. Also, in a
system with sparse CPU IDs, you can have a valid CPU ID > mp_ncpus (e.g. if
you have two CPUs 0 and 4, with mp_maxid == 4 and mp_ncpus == 2).

Introduced at svn r235210

Submitted by:	jhb@
Reviewed by:	jfv@
2012-08-02 00:00:34 +00:00
Jack F Vogel
b4750260cd Clean up some unused leftover code from em
Make IRQ style a tuneable
Fix lock handling in the interrupt handler

MFC after:3 days
2012-07-31 18:44:10 +00:00
Luigi Rizzo
fc1fa1f2fe remove some extra testing code that slipped into the previous commit
Reported-by: Alexander Motin
2012-07-25 12:51:33 +00:00
Luigi Rizzo
8d1717963b Use legacy interrupts as a default. This gives up to 10% speedup
when used in qemu (and this driver is for non-PCIe cards,
so probably its largest use is in virtualized environments).

Approved by:	Jack Vogel
MFC after:	3 days
2012-07-25 11:28:15 +00:00
Jack F Vogel
fcc144ad4e Change the interface to the Energy Efficient Ethernet (EEE)
setting in the igb and em driver. This was necessitated by
a shared code change that I was given late in the game, a data
type changed from bool to int, in the last update I dealt with
it by a cast, but it was pointed out (thanks jhb) that there
was a potential problem with this. John suggested this safer
approach, and it is fine with me...

MFC after:2 days (to catch the 9.1 update)
2012-07-07 20:21:05 +00:00
Jack F Vogel
996922aeee Correct small regressions pointed out by jhb, thanks John.
MFC after:5 days
2012-07-05 23:36:17 +00:00
Jack F Vogel
ab5d036272 Sync with Intel internal source:
shared code update and small changes in core required
Add support for new i210/i211 devices
Improve queue calculation based on mac type

MFC after:5 days
2012-07-05 20:26:57 +00:00
John Baldwin
03b0ca8b28 Commit a portion of 233708 I missed earlier and don't include the
definition of igb_start() and igb_start_locked() (nor set if_start in
the ifnet) when igb(4) uses if_transmit.
2012-06-01 15:52:41 +00:00
Kevin Lo
4d8b94d278 Initialize "error" to zero when it's declared in em_setup_receive_ring() 2012-05-11 03:15:22 +00:00
Sean Bruno
daf8162d1f Modify the binding of queues to attach to as many CPUs
as possible when using more than one igb(4) adapter.  This
means that queues will not be bound to the same CPUs if
there are more CPUs availble.

This is only applicable to a system that has multiple interfaces.

Obtained from:	Yahoo! Inc.
MFC after:	3 days
2012-05-10 00:00:28 +00:00
Ed Maste
a3d2552747 Fix cut-and-paste comment error
Submitted by:	sbruno
2012-04-25 02:05:14 +00:00
John Baldwin
8546e82467 Reapply r223198 which was reverted in the previous vendor import. Some
portions were already reapplied in r233708:
- Use a dedicated task to handle deferred transmits from the if_transmit
  method instead of reusing the existing per-queue interrupt task.
  Reusing the per-queue interrupt task could result in both an interrupt
  thread and the taskqueue thread trying to handle received packets on a
  single queue resulting in out-of-order packet processing.
- Call ether_ifdetach() earlier in igb_detach().
- Drain tasks and free taskqueues during igb_detach().

MFC after:	1 week
2012-04-11 21:33:45 +00:00
John Baldwin
d8a8648379 Fix a few issues with transmit handling in em(4) and igb(4):
- Do not define the foo_start() methods or set if_start in the ifnet if
  multiq transmit is enabled.  Also, set if_transmit and if_qflush before
  ether_ifattach rather than after when multiq transmit is enabled.  This
  helps to ensure that the drivers never try to mix different transmit
  methods.
- Properly restart transmit during resume.  igb(4) was not restarting it
  at all, and em(4) was restarting even if the link was down and was
  calling the wrong method if multiq transmit was enabled.
- Remove all the 'more' handling for transmit completions.  Transmit
  completion processing does not have a processing limit, so it always
  runs to completion and never has more work to do when it returns.
  Instead, the previous code was returning 'true' anytime there were
  packets in the queue that weren't still in the process of being
  transmitted.  The effect was that the driver would continuously
  reschedule a task to process TX completions in effect running at 100%
  CPU polling the hardware until it finished transmitting all of the
  packets in the ring.  Now it will just wait for the next TX completion
  interrupt.
- Restart packet transmission when the link becomes active.
- Fix the MSI-X queue interrupt handlers to restart packet transmission if
  there are pending packets in the relevant software queue (IFQ or buf_ring)
  after processing TX completions.  This is the root cause for the OACTIVE
  hangs as if the MSI-X queue handler drained all the pending packets from
  the TX ring, nothing would ever restart it.  As such, remove some
  previously-added workarounds to reschedule a task to poll the TX ring
  anytime OACTIVE was set.

Tested by:	sbruno
Reviewed by:	jfv
MFC after:	1 week
2012-03-30 19:54:48 +00:00
Marius Strobl
b3f46df007 Initialize the mutexes used for the NVM and the swflag as MTX_DUPOK in
order to avoid otherwise harmless witness warnings when these are acquired
at the same time and due to both using MTX_NETWORK_LOCK as their type.
The right fix actually would be to use different, descriptive types for
these. However, the latter would require undesirable changes to the shared
code base. Another approach would be to just supply NULL as the type, which
was deemed as less desirable though as it would cause the unique but cryptic
name also to be used for the type and to diverge from the type used by other
network device drivers.

MFC after:	1 week
2012-03-24 15:15:34 +00:00