Commit Graph

193 Commits

Author SHA1 Message Date
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 The mbuf pointer is no longer valid, so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
John Baldwin
c3173381be Properly handle failures in igb_setup_msix() by returning 0 if MSI or MSI-X
allocation fails.

Reviewed by:	jfv
MFC after:	2 weeks
2012-03-01 22:13:10 +00:00
Luigi Rizzo
64ae02c365 A bunch of netmap fixes:
USERSPACE:
1. add support for devices with different number of rx and tx queues;

2. add better support for zero-copy operation, adding an extra field
   to the netmap ring to indicate how many buffers we have already processed
   but not yet released (with help from Eddie Kohler);

3. The two changes above unfortunately require an API change, so while
   at it add a version field and some spares to the ioctl() argument
   to help detect mismatches.

4. update the manual page for the two changes above;

5. update sample applications in tools/tools/netmap

KERNEL:

1. simplify the internal structures moving the global wait queues
   to the 'struct netmap_adapter';

2. simplify the functions that map kring<->nic ring indexes

3. normalize device-specific code, helps mainteinance;

4. start exploring the impact of micro-optimizations (prefetch etc.)
   in the ixgbe driver.
   Use 'legacy' descriptors on the tx ring and prefetch slots gives
   about 20% speedup at 900 MHz. Another 7-10% would come from removing
   the explict calls to bus_dmamap* in the core (they are effectively
   NOPs in this case, but it takes expensive load of the per-buffer
   dma maps to figure out that they are all NULL.

   Rx performance not investigated.

I am postponing the MFC so i can import a few more improvements
before merging.
2012-02-27 19:05:01 +00:00
Luigi Rizzo
5644ccec61 (This commit only touches code within the DEV_NETMAP blocks)
Introduce some functions to map NIC ring indexes into netmap ring
indexes and vice versa. This way we can implement the bound
checks only in one place (and hopefully in a correct way).

On passing, make the code and comments more uniform across the
various drivers.
2012-02-15 23:13:29 +00:00
Eitan Adler
c6618b7f79 GS105v3 exhibit the same behavior
PR:			docs/135999
Submitted by:	Boris Kochergin <spawky@acm.poly.edu>
No objection from:	jfv
Approved by:	cperciva
MFC after:		3 days
2012-01-29 14:52:42 +00:00
Luigi Rizzo
ce9f43b467 clear the pointer after freeing the mbuf. Without that, we
risk a double free if the subsequent mbuf allocation fails.
This bug is not netmap-related and was introduced in  rev. 228387
2012-01-12 17:30:44 +00:00
Luigi Rizzo
467bd5c2cb fix the initialization of the rings when netmap is used,
to adapt it to the changes in  228387 .
Now the code is similar to the one used in other drivers.
Not applicable to stable/9 and stable/8
2012-01-12 17:28:00 +00:00
Luigi Rizzo
6e10c8b8c5 small code cleanup in preparation for future modifications in
the memory allocator used by netmap. No functional change,
two small bug fixes:
- in if_re.c add a missing bus_dmamap_sync()
- in netmap.c comment out a spurious free() in an error handling block
2012-01-10 19:57:23 +00:00
Kevin Lo
5bbe0c5357 ether_ifattach() sets if_mtu to ETHERMTU, don't bother set it again
Reviewed by:	yongari
2012-01-07 09:41:57 +00:00
Robert Watson
19d52de5f4 When extracting the VLAN tag from if_em and if_lem receive descriptor
rings, copy the whole VLAN tag, not just the VLAN ID.  This fixes a
problem in which VLAN priority information was dropped when using
offloaded VLAN processing with these drivers.

Discussed with:	jfv, rrs
Sponsored by:	ADARA Networks, Inc.
MFC after:	3 days
2012-01-05 17:30:15 +00:00
Luigi Rizzo
2d0d326d91 put back netmap support, deleted by mistake in a previous commit 2011-12-22 15:33:41 +00:00
John Baldwin
ef93f57495 Restore the sysctl changes from 223676 and 227309 lost in the previous
import:
- Add read-only sysctls for all of the tunables supported by the igb and
  em drivers.
- Make the per-instance 'enable_aim' sysctl truly per-instance by having it
  change a per-instance variable (which is used to control AIM) rather
  than having all of the per-instance sysctls operate on a single global
  variable.

While here, restore the previously existing hw.igb.rx_processing_limit
tunable as it is very useful to be able to set a default tunable that
applies to all adapters in the system.
2011-12-21 20:10:11 +00:00
Matthew D Fleming
30a497c860 Consistently use types in e1000 driver code:
- Two struct members eee_disable are used in a function that expects
   an int *, so declare them int, not bool.
 - igb_tx_ctx_setup() returns a boolean value, so declare it bool, not int.
 - igb_header_split is passed to TUNABLE_INT, so delcare it int, not bool.
 - igb_tso_setup() returns a bool, so declare it bool, not boolean_t.
 - Do not re-define bool/true/false if the symbols already exist.

MFC after:	2 weeks
Sponsored by:	Isilon Systems, LLC
2011-12-12 18:27:34 +00:00
Jack F Vogel
62aca36544 Last change still had an issue, one more time... 2011-12-11 18:46:14 +00:00
Jack F Vogel
133f283b45 Correct LINT build issues in the ioctl code. 2011-12-11 09:37:25 +00:00
Jack F Vogel
96b38ade36 Fix NETMAP code problem in the build. 2011-12-10 18:00:53 +00:00
Jack F Vogel
fd33ce416e Part 2 of 2 New deltas for the 1G drivers.
There have still been intermittent problems with apparent TX
hangs for some customers. These have been problematic to reproduce
but I believe these changes will address them. Testing on a number
of fronts have been positive.

EM: there is an important 'chicken bit' fix for 82574 in the shared
code this is supported in the core here.
    - The TX path has been tightened up to improve performance. In
      particular UDP with jumbo frames was having problems, and the
      changes here have improved that.
    - OACTIVE has been used more carefully on the theory that some
      hangs may be due to a problem in this interaction
    - Problems with the RX init code, the "lazy" allocation and
      ring initialization has been found to cause problems in some
      newer client systems, and as it really is not that big a win
      (its not in a hot path) it seems best to remove it.
    - HWTSO was broken when VLAN HWTAGGING or HWFILTER is used, I
      found this was due to an error in setting up the descriptors
      in em_xmit.

IGB:
    - TX is also improved here. With multiqueue I realized its very
      important to handle OACTIVE only under the CORE lock so there
      are no races between the queues.
    - Flow Control handling was broken in a couple ways, I have changed
      and I hope improved that in this delta.
    - UDP also had a problem in the TX path here, it was change to
      improve that.
    - On some hardware, with the driver static, a weird stray interrupt
      seems to sometimes fire and cause a panic in the RX mbuf refresh
      code. This is addressed by setting interrupts late in the init
      path, and also to set all interrupts bits off at the start of that.
2011-12-10 07:08:52 +00:00
Jack F Vogel
4dab5c3769 Part 1 of two parts, this is the shared code changes in
support of new deltas for both em and igb drivers.

Note that I am not able to track all the bugs fixed in
this code, I am a consumer of it as a component of my
core drivers. It is important to keep the FreeBSD drivers
up to date with it however.

One important note is there is a key fix for 82574 in this
update. Also, there are lots of white space changes, I am
not happy about them but have no control over it :)
2011-12-10 06:55:02 +00:00
Luigi Rizzo
579a6e3c4e add netmap support for "em", "lem", "igb" and "re".
On my hardware, "em" in netmap mode does about 1.388 Mpps
on one card (on an Asus motherboard), and 1.1 Mpps on another
card (PCIe bus). Both seem to be NIC-limited, because
i have the same rate even with the CPU running at 150 MHz.

On the "re" driver the tx throughput is around 420-450 Kpps
on various (8111C and the like) chipsets. On the Rx side
performance seems much better, and i can receive the full
load generated by the "em" cards.

"igb" is untested as i don't have the hardware.
2011-12-05 15:33:13 +00:00
Ed Schouten
6472ac3d8a Mark all SYSCTL_NODEs static that have no corresponding SYSCTL_DECLs.
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.
2011-11-07 15:43:11 +00:00