Commit Graph

277 Commits

Author SHA1 Message Date
Sean Bruno
e373323fe2 Revert 287914,287762.
Reports of breakage on igb(4) have been narrowed down to 287762 and 287914
is an dependant change.

Submitted by:	erj
2015-09-19 18:22:59 +00:00
Sean Bruno
25fd5dd9a0 Add Intel Skylake/I219 Support
- New em(4) device in currently shipping products

Differential Revision:	https://reviews.freebsd.org/D3163
Submitted by:	erj@freebsd.org
Reviewed by:	jfv@freebsd.org
MFC after:	2 weeks
Sponsored by:	Intel Corporation
2015-09-17 15:11:45 +00:00
Sean Bruno
a44aa8e030 Update em(4) with D3162 after testing further on hardware that failed
to attach with the last version of this commit. This commit fixes
attach failures on "ICH8" class devices via modifications to
e1000_init_nvm_params_ich8lan()

-   Fix compiler warning in 80003es2lan.c
-   Add return value handler for e1000_*_kmrn_reg_80003es2lan
-   Fix usage of DEBUGOUT
-   Remove unnecessary variable initializations.
-   Removed unused variables (complaints from gcc).
-   Edit defines in 82571.h.
-   Add workaround for igb hw errata.
-   Shared code changes for Skylake/I219 support.
-   Remove unused OBFF and LTR functions.

Tested by some of the folks that reported breakage in previous incarnation.
Thanks to AllanJude, gjb, gnn, tijl for tempting fate with their machines.

Submitted by:	erj@freebsd.org
MFC after:	2 weeks
Differential Revision:	https://reviews.freebsd.org/D3162
2015-09-13 18:26:05 +00:00
Sean Bruno
c597a0199e Revert last two commits to em(4)/igb(4). Reports are coming in that
this breaks initialization and reads from EEPROM on boot/driver load.

r287469 is being reverted as a dependancy on r287467
2015-09-05 21:12:19 +00:00
Sean Bruno
98ae230f07 em(4): Add Skylake/I219 support.
- driver rev 7.5.2
- use new functions em_flush* for i219 devices

Differential Revision:	https://reviews.freebsd.org/D3163
Submitted by:	erj jfv
Reviewed by:	jfv
MFC after:	1 month
Relnotes:	Yes
Sponsored by:	Intel Corporation
2015-09-04 17:21:55 +00:00
Sean Bruno
67ebffd348 e1000: Shared code updates
-    Fix compiler warning in 80003es2lan.c
-    Add return value handler for e1000_*_kmrn_reg_80003es2lan
-    Fix usage of DEBUGOUT
-    Remove unnecessary variable initializations.
-    Removed unused variables (complaints from gcc).
-    Edit defines in 82571.h.
-    Add workaround for igb hw errata.
-    Shared code changes for Skylake/I219 support.
-    Remove unused OBFF and LTR functions.

Differential Revision:	https://reviews.freebsd.org/D3162
Submitted by:	erj
MFC after:	1 month
Sponsored by:	Intel Corporation
2015-09-04 16:30:48 +00:00
Sean Bruno
02415af2ee igb(4): Update and fix HW errata
- HW errata workaround for IPv6 offload w/ extension headers
- Edited start of if_igb.c (Device IDs / #includes) to match ixgbe/ixl

Differential Revision:	https://reviews.freebsd.org/D3165
Submitted by:	erj
MFC after:	1 month
Sponsored by:	Intel Corporation
2015-09-04 16:07:27 +00:00
Sean Bruno
fac8243601 Restrict tso_max to IP_MAXPACKET to avoid the panic reported in:
https://lists.freebsd.org/pipermail/freebsd-current/2015-August/057192.html

Submitted by:	pyunyh@gmail.com
MFC after:	2 weeks
2015-08-31 19:12:10 +00:00
Sean Bruno
48600901a8 Style/whitespace cleanup in shared/common code.
Differential Revision:	https://reviews.freebsd.org/D3159
Submitted by:	erj
MFC after:	2 weeks
2015-08-24 16:32:57 +00:00
Sean Bruno
7c669ab6cc Bump all copywrite dates to 2015
Differential Revision:	https://reviews.freebsd.org/D3160
Submitted by:	erj
MFC after:	2 weeks
Sponsored by:	Intel Corportation
2015-08-16 20:13:58 +00:00
Sean Bruno
d2635c677b e1000/if_lem.c bump to 1.1.0
- deprecate fbsd 8

Differential Revision:	https://reviews.freebsd.org/D3164
Submitted by:	erj
MFC after:	2 weeks
Sponsored by:	Intel Corporation
2015-08-16 20:10:43 +00:00
Sean Bruno
df40405fab Increase EM_MAX_SCATTER to 64 such that the size of em_xmit()::segs[EM_MAX_SCATTER]
doesn't get overrun by things like NFS that can and do shove more than 32 segs when
being used with em(4) and TSO4.

Update tso handling code in em_xmit() with update from jhb@ in email thread:
https://lists.freebsd.org/pipermail/freebsd-net/2014-July/039306.html

set ifp->if_hw_tsomax, ifp->if_hw_tsomaxsegcount & ifp->if_hw_tsomaxsegsize
to appropriate values.

Define a TSO workaround "magic" number  of 4 that is used to avoid an
alignment issue in hardware.

Change a couple of integer values that were used as booleans to actual
bool types.

Ensure that em_enable_intr() enables the appropriate mask of interrupts
and not just a hardcoded define of values.

PR:		200221 199174 195078
Differential Revision:	https://reviews.freebsd.org/D3192
Reviewed by:	erj jhb hiren
MFC after:	2 weeks
Sponsored by:	Limelight Networks
2015-08-16 19:43:44 +00:00
Sean Bruno
38be29d321 Add capability to disable CRC stripping. This breaks IPMI/BMC capabilities on certain adatpers.
Linux has been doing the exact same thing since 2008

eb7c3adb1c

PR:	161277
Differential Revision:	https://reviews.freebsd.org/D3282
Submitted by:	Fravadona@gmail.com
Reviewed by:	erj wblock
MFC after:	2 weeks
Relnotes:	yes
Sponsored by:	Limelight Networks
2015-08-16 19:06:23 +00:00
Hans Petter Selasky
577c341353 Free mbufs when busdma loading fails.
Reviewed by:	erj, sbruno
MFC after:	1 month
2015-08-01 20:40:37 +00:00
Sean Bruno
a82cd51680 Remove unused txd_saved.
Intialize txd_upper, txd_lower and txd_used at declaration.

Differential Revision:	D3174
Reviewed by:	erj hiren
MFC after:	2 weeks
Sponsored by:	Limelight Networks
2015-07-25 19:24:33 +00:00
Sean Bruno
f46fb03de7 Add an adapter CORE lock in the DDB hook em_dump_queue to avoid WITNESS
panic in em_init_locked() while debugging.

MFC after:	2 weeks
Sponsored by:	Limelight Networks
2015-07-16 16:32:57 +00:00
Kevin Lo
f7c698e20d Fix typo in register definition.
Submitted by:	James Hung
Reviewed by:	sbruno
2015-07-16 08:03:23 +00:00
Luigi Rizzo
847bf38369 Sync netmap sources with the version in our private tree.
This commit contains large contributions from Giuseppe Lettieri and
Stefano Garzarella, is partly supported by grants from Verisign and Cisco,
and brings in the following:

- fix zerocopy monitor ports and introduce copying monitor ports
  (the latter are lower performance but give access to all traffic
  in parallel with the application)

- exclusive open mode, useful to implement solutions that recover
  from crashes of the main netmap client (suggested by Patrick Kelsey)

- revised memory allocator in preparation for the 'passthrough mode'
  (ptnetmap) recently presented at bsdcan. ptnetmap is described in
        S. Garzarella, G. Lettieri, L. Rizzo;
        Virtual device passthrough for high speed VM networking,
        ACM/IEEE ANCS 2015, Oakland (CA) May 2015
        http://info.iet.unipi.it/~luigi/research.html

- fix rx CRC handing on ixl

- add module dependencies for netmap when building drivers as modules

- minor simplifications to device-specific routines (*txsync, *rxsync)

- general code cleanup (remove unused variables, introduce macros
  to access rings and remove duplicate code,

Applications do not need to be recompiled, unless of course
they want to use the new features (monitors and exclusive open).

Those willing to try this code on stable/10 can just update the
sys/dev/netmap/*, sys/net/netmap* with the version in HEAD
and apply the small patches to individual device drivers.

MFC after:	1 month
Sponsored by:	(partly) Verisign, Cisco
2015-07-10 05:51:36 +00:00
Sean Bruno
23c9098b2a Change EM_MULTIQUEUE to a real kernconf entry and enable support for
up to 2 rx/tx queues for the 82574.

Program the 82574 to enable 5 msix vectors, assign 1 to each rx queue,
1 to each tx queue and 1 to the link handler.

Inspired by DragonFlyBSD, enable some RSS logic for handling tx queue
handling/processing.

Move multiqueue handler functions so that they line up better in a diff
review to if_igb.c

Always enqueue tx work to be done in em_mq_start, if unable to acquire
the TX lock, then this will be processed in the background later by the
taskqueue.  Remove mbuf argument from em_start_mq_locked() as the work
is always enqueued.  (stolen from igb)

Setup TARC, TXDCTL and RXDCTL registers for better performance and stability
in multiqueue and singlequeue implementations. Handle Intel errata  3 and
generic multiqueue behavior with the initialization of TARC(0) and TARC(1)

Bind interrupt threads to cpus in order.  (stolen from igb)

Add 2 new DDB functions, one to display the queue(s) and their settings and
one to reset the adapter.  Primarily used for debugging.

In the multiqueue configuration, bump RXD and TXD ring size to max for the
adapter (4096).  Setup an RDTR of 64 and an RADV of 128 in multiqueue configuration
to cut down on the number of interrupts.  RADV was arbitrarily set to 2x RDTR
and can be adjusted as needed.

Cleanup the display in top a bit to make it clearer where the taskqueue threads
are running and what they should be doing.

Ensure that both queues are processed by em_local_timer() by writing them both
to the IMS register to generate soft interrupts.

Ensure that an soft interrupt is generated when em_msix_link() is run so that
any races between assertion of the link/status interrupt and a rx/tx interrupt
are handled.

Document existing tuneables: hw.em.eee_setting, hw.em.msix, hw.em.smart_pwr_down, hw.em.sbp

Document use of hw.em.num_queues and the new kernel option EM_MULTIQUEUE

Thanks to Intel for their continued support of FreeBSD.

Reviewed by:	erj jfv hiren gnn wblock
Obtained from:	Intel Corporation
MFC after:	2 weeks
Relnotes:	Yes
Sponsored by:	Limelight Networks
Differential Revision:	https://reviews.freebsd.org/D1994
2015-06-03 18:01:09 +00:00
Sean Bruno
b7a728aaba Simplify hang detection by stealing the techniques used in ixl(4) and
applying them to em(4).

Rely on iterations through the local timer, and the tx queue state to
determine if an actual hang has occurred. Any time a descriptor is used
(packet sent), the tx queue is flagged as busy. Then when txeof runs, it
either clears the flag when all is clean, or resets it to 1 if ANY are
cleaned, if nothing is cleaned it increments the flag.

Local timer simply checks to see if busy ever reaches MAX (10, which
is compile time configurable), and then sets it as HUNG, at that point
there is one more timer cycle in which to have any cleans, if not a
watchdog reset will occur.

Differential Revision:	https://reviews.freebsd.org/D2019
Submitted by:	jfv
Reviewed by:	hiren
Obtained from:	Intel Corporation
MFC after:	2 weeks
Relnotes:	Yes
Sponsored by:	Limelight Networks
2015-06-02 18:28:41 +00:00
Sean Bruno
316f4c880a Bump rx_overruns when indicated by the ICR mask.
PR:		199716
MFC after:	3 days
Sponsored by:	Limelight Networks
2015-05-22 17:01:43 +00:00
John Baldwin
625d12c609 Various fixes to the stats in igb(4), ixgbe(4), and ixl(4).
- Use hardware counters for ifnet stats in igb(4) when possible.  This
  ensures these stats include packets that bypass the regular stack via
  netmap.
- Don't derefence values off the end of the igb(4) VF stats structure.
  Instead, add a dedicated if_get_counter method for igb(4) VF interfaces.
- Report missed packets on igb(4) as input queue drops rather than an
  input error.
- Report bug_ring drop counts as output queue drops for igb(4) and ixgbe(4).
- Export the buf_ring drop stats for individual rings via sysctl on
  ixgbe(4).
- Fix a typo that in ixl(4) that caused output queue drops to be reported
  as input queue drops and input queue drops to be unreported.

Differential Revision:	https://reviews.freebsd.org/D2402
Reviewed by:	jfv, rstone (6)
Sponsored by:	Norse Corp, Inc.
2015-04-30 18:23:38 +00:00
Hiren Panchasara
270538b2b6 For igb(4), when we are doing multiqueue, we are all setup to have full 32bit
RSS hash from the card. We do not need to hide that under "ifdef RSS" and should
expose that by default so others like lagg(4) can use that and avoid hashing the
traffic by themselves.
While here, improve comments and get rid of hidden/unimplemented RSS support
code for UDP.

Differential Revision:	https://reviews.freebsd.org/D2296
Reviewed by:	jfv, erj
Discussed with:	adrian
Sponsored by:	Limelight Networks
2015-04-21 20:24:15 +00:00
Adrian Chadd
977dc4e243 Migrate using CPU_ZERO() + CPU_SET() -> CPU_SETOF().
Tested:

* ixgbe, igb, RSS enabled

Submitted by:	jhb
Sponsored by:	Norse Corp, Inc.
2015-02-25 21:44:53 +00:00
Adrian Chadd
9756bd5982 Change uses of taskqueue_start_threads_pinned() -> taskqueue_start_threads_cpuset()
Differential Revision:	https://reviews.freebsd.org/D1897
Reviewed by:	jfv
2015-02-24 22:17:12 +00:00
Adrian Chadd
b2bdc62a95 Refactor / restructure the RSS code into generic, IPv4 and IPv6 specific
bits.

The motivation here is to eventually teach netisr and potentially
other networking subsystems a bit more about how RSS work queues / buckets
are configured so things have a hope of auto-configuring in the future.

* net/rss_config.[ch] takes care of the generic bits for doing
  configuration, hash function selection, etc;
* topelitz.[ch] is now in net/ rather than netinet/;
* (and would be in libkern if it didn't directly include RSS_KEYSIZE;
  that's a later thing to fix up.)
* netinet/in_rss.[ch] now just contains the IPv4 specific methods;
* and netinet/in6_rss.[ch] now just contains the IPv6 specific methods.

This should have no functional impact on anyone currently using
the RSS support.

Differential Revision:	D1383
Reviewed by:	gnn, jfv (intel driver bits)
2015-01-18 18:06:40 +00:00
Jack F Vogel
4da1bbcda5 Revert r275136, it was not approved, it was sloppy, if a feature
like this is needed please resubmit for Intel's approval.
2014-12-02 23:02:57 +00:00
Hans Petter Selasky
c25290420e Start process of removing the use of the deprecated "M_FLOWID" flag
from the FreeBSD network code. The flag is still kept around in the
"sys/mbuf.h" header file, but does no longer have any users. Instead
the "m_pkthdr.rsstype" field in the mbuf structure is now used to
decide the meaning of the "m_pkthdr.flowid" field. To modify the
"m_pkthdr.rsstype" field please use the existing "M_HASHTYPE_XXX"
macros as defined in the "sys/mbuf.h" header file.

This patch introduces new behaviour in the transmit direction.
Previously network drivers checked if "M_FLOWID" was set in "m_flags"
before using the "m_pkthdr.flowid" field. This check has now now been
replaced by checking if "M_HASHTYPE_GET(m)" is different from
"M_HASHTYPE_NONE". In the future more hashtypes will be added, for
example hashtypes for hardware dedicated flows.

"M_HASHTYPE_OPAQUE" indicates that the "m_pkthdr.flowid" value is
valid and has no particular type. This change removes the need for an
"if" statement in TCP transmit code checking for the presence of a
valid flowid value. The "if" statement mentioned above is now a direct
variable assignment which is then later checked by the respective
network drivers like before.

Additional notes:
- The SCTP code changes will be committed as a separate patch.
- Removal of the "M_FLOWID" flag will also be done separately.
- The FreeBSD version has been bumped.

MFC after:	1 month
Sponsored by:	Mellanox Technologies
2014-12-01 11:45:24 +00:00
Alfred Perlstein
56c14bca7e Make igb and ixgbe check tunables at probe time.
This allows one to make a kernel module to tune the
number of queues before the driver loads.

This is needed so that a module at SI_SUB_CPU can set
tunables for these drivers to take.  Otherwise getenv
is called too early by the TUNABLE macros.

Reviewed by: smh
Phabric: https://reviews.freebsd.org/D1149
2014-11-26 20:19:36 +00:00
Hans Petter Selasky
f0188618f2 Fix multiple incorrect SYSCTL arguments in the kernel:
- Wrong integer type was specified.

- Wrong or missing "access" specifier. The "access" specifier
sometimes included the SYSCTL type, which it should not, except for
procedural SYSCTL nodes.

- Logical OR where binary OR was expected.

- Properly assert the "access" argument passed to all SYSCTL macros,
using the CTASSERT macro. This applies to both static- and dynamically
created SYSCTLs.

- Properly assert the the data type for both static and dynamic
SYSCTLs. In the case of static SYSCTLs we only assert that the data
pointed to by the SYSCTL data pointer has the correct size, hence
there is no easy way to assert types in the C language outside a
C-function.

- Rewrote some code which doesn't pass a constant "access" specifier
when creating dynamic SYSCTL nodes, which is now a requirement.

- Updated "EXAMPLES" section in SYSCTL manual page.

MFC after:	3 days
Sponsored by:	Mellanox Technologies
2014-10-21 07:31:21 +00:00
John Baldwin
8423f42aa8 Various fixes to stats:
- Read the counts of received, dropped, and transmitted management
  packets and add sysctl nodes for them.
- Fix the total octets received/transmitted to read all 64 bits of
  the counters.
- Add missing sysctl nodes for rlec, tncrs, fcruc, tor, and tot.
- Remove spurious spaces.

Reviewed by:	Eric Joyner @ Intel
MFC after:	1 week
2014-10-10 16:36:25 +00:00
Gleb Smirnoff
bd071d4d19 - Remove empty wrappers ether_poll_[de]register_drv(). [1]
- Move polling(9) declarations out of ifq.h back to if_var.h
  they are absolutely unrelated to queues.

Submitted by:	Mikhail <mp lenta.ru> [1]
2014-09-28 14:05:18 +00:00
Gleb Smirnoff
5d53210ced - Provide igb_get_counter() to return counters that are not collected,
but taken from hardware.
- Mechanically convert to if_inc_counter() the rest of counters.
2014-09-19 11:49:41 +00:00
Adrian Chadd
0936a8208b Fix the handling of EOP in status descriptors for if_igb(4) and don't
double-free mbufs.

Like ixgbe(4) chipsets, EOP is only set on the final descriptor
in a chain of descriptors.  So, to free the whole list of descriptors,
we should free the current slot _and_ the assembled list of descriptors
that make up the fragment list.

The existing code was setting discard once it saw EOP + an error status;
it then freed all the subsequent descriptors until the next EOP. That's
totally the wrong order.
2014-09-18 16:20:17 +00:00
Gleb Smirnoff
df3601781d - Use if_inc_counter() to increment various counters.
- Do not ever set a counter to a value. For those counters
  that we don't increment, but return directly from hardware
  create cases in if_get_counter() method.

Sponsored by:	Netflix
Sponsored by:	Nginx, Inc.
2014-09-18 15:56:14 +00:00
Adrian Chadd
1c2427605c Set DROP_EN on each RX queue if transmit flow-control is disabled.
This allows the NIC to drop frames on the receive queue and not
cause the MAC to block on receiving to _any_ queue.

Tested:

igb0@pci0:5:0:0:        class=0x020000 card=0x152115d9 chip=0x15218086 rev=0x01 hdr=0x00
    vendor     = 'Intel Corporation'
    device     = 'I350 Gigabit Network Connection'
    class      = network
    subclass   = ethernet

Discussed with: Eric Joyner <eric.joyner@intel.com>

MFC after:	1 week
Sponsored by:	Norse Corp, Inc.
2014-09-15 19:53:49 +00:00
Gleb Smirnoff
09a8241fc9 It is actually possible to have if_t a typedef to non-void type,
and keep both converted to drvapi and non-converted drivers
compilable.

o Make if_t typedef to struct ifnet *.
o Remove shim functions.

Sponsored by:	Netflix
Sponsored by:	Nginx, Inc.
2014-08-31 12:48:13 +00:00
Gleb Smirnoff
1bffa9511f Use define from if_var.h to access a field inside struct if_data,
that resides in struct ifnet.

Sponsored by:	Nginx, Inc.
2014-08-30 19:55:54 +00:00
Luigi Rizzo
4bf50f18eb Update to the current version of netmap.
Mostly bugfixes or features developed in the past 6 months,
so this is a 10.1 candidate.

Basically no user API changes (some bugfixes in sys/net/netmap_user.h).

In detail:

1. netmap support for virtio-net, including in netmap mode.
  Under bhyve and with a netmap backend [2] we reach over 1Mpps
  with standard APIs (e.g. libpcap), and 5-8 Mpps in netmap mode.

2. (kernel) add support for multiple memory allocators, so we can
  better partition physical and virtual interfaces giving access
  to separate users. The most visible effect is one additional
  argument to the various kernel functions to compute buffer
  addresses. All netmap-supported drivers are affected, but changes
  are mechanical and trivial

3. (kernel) simplify the prototype for *txsync() and *rxsync()
  driver methods. All netmap drivers affected, changes mostly mechanical.

4. add support for netmap-monitor ports. Think of it as a mirroring
  port on a physical switch: a netmap monitor port replicates traffic
  present on the main port. Restrictions apply. Drive carefully.

5. if_lem.c: support for various paravirtualization features,
  experimental and disabled by default.
  Most of these are described in our ANCS'13 paper [1].
  Paravirtualized support in netmap mode is new, and beats the
  numbers in the paper by a large factor (under qemu-kvm,
  we measured gues-host throughput up to 10-12 Mpps).

A lot of refactoring and additional documentation in the files
in sys/dev/netmap, but apart from #2 and #3 above, almost nothing
of this stuff is visible to other kernel parts.

Example programs in tools/tools/netmap have been updated with bugfixes
and to support more of the existing features.

This is meant to go into 10.1 so we plan an MFC before the Aug.22 deadline.

A lot of this code has been contributed by my colleagues at UNIPI,
including Giuseppe Lettieri, Vincenzo Maffione, Stefano Garzarella.

MFC after:	3 days.
2014-08-16 15:00:01 +00:00
Adrian Chadd
fa4be7cc42 Fix the igb(4) redirection table to correctly populate.
This is similar to the ixgbe(4) fix.

Tested:

* Intel I350 gigabit adapter
2014-07-23 05:40:28 +00:00
Hiren Panchasara
eee92ad073 The description is a bit misleading. Trying to make it more obvious.
Phabric:    https://phabric.freebsd.org/D435
Reviewed by:	gnn
2014-07-18 16:25:35 +00:00
Rick Macklem
e2ade3b6f7 Move the "retry:" label so that the calls to m_pullup() are
not done after the call to m_defrag(). This fixes a problem
where m_pullup() would prepend an mbuf to the list created
by m_defrag() making the chain greater than 32 again.

Tested by:	rcarter@pinyon.org
Reviewed by:	yongari, jfv
MFC after:	2 weeks
2014-07-15 23:32:13 +00:00
Mark Johnston
58e6549541 Correct the setting of the VID in transmit descriptors when hardware VLAN
tagging is enabled. This was broken in r266978.

Reported by:	gjb
Tested by:	gjb
2014-07-10 16:46:46 +00:00
Adrian Chadd
8c0d2adf3f Initialise these variables so gcc doesn't complain.
Submitted by:	luigi
2014-06-30 23:34:36 +00:00
Adrian Chadd
1d72a9bea9 Add initial RSS awareness to the igb(4) driver.
The igb(4) hardware is capable of RSS hashing RX packets and doing RSS
queue selection for up to 8 queues.  (I believe some hardware is limited
to 4 queues, but I haven't tested on that.)

However, even if multi-queue is enabled for igb(4), the RX path doesn't use
the RSS flowid from the received descriptor.  It just uses the MSIX queue id.

This patch does a handful of things if RSS is enabled:

* Instead of using a random key at boot, fetch the RSS key from the RSS code
  and program that in to the RSS redirection table.

  That whole chunk of code should be double checked for endian correctness.

* Use the RSS queue mapping to CPU ID to figure out where to thread pin
  the RX swi thread and the taskqueue threads for each queue.

* The software queue is now really an "RSS bucket".

* When programming the RSS indirection table, use the RSS code to
  figure out which RSS bucket each slot in the indirection table maps
  to.

* When transmitting, use the flowid RSS mapping if the mbuf has
  an RSS aware hash.  The existing method wasn't guaranteed to align
  correctly with the destination RSS bucket (and thus CPU ID.)

This code warns if the number of RSS buckets isn't the same as the
automatically configured number of hardware queues.  The administrator
will have to tweak one of them for better performance.

There's currently no way to re-balance the RSS indirection table after
startup.  I'll worry about that later.

Additionally, it may be worthwhile to always use the full 32 bit flowid if
multi-queue is enabled.  It'll make things like lagg(4) behave better with
respect to traffic distribution.
2014-06-30 04:34:59 +00:00
Hans Petter Selasky
af3b2549c4 Pull in r267961 and r267973 again. Fix for issues reported will follow. 2014-06-28 03:56:17 +00:00
Glen Barber
37a107a407 Revert r267961, r267973:
These changes prevent sysctl(8) from returning proper output,
such as:

 1) no output from sysctl(8)
 2) erroneously returning ENOMEM with tools like truss(1)
    or uname(1)
 truss: can not get etype: Cannot allocate memory
2014-06-27 22:05:21 +00:00
Hans Petter Selasky
3da1cf1e88 Extend the meaning of the CTLFLAG_TUN flag to automatically check if
there is an environment variable which shall initialize the SYSCTL
during early boot. This works for all SYSCTL types both statically and
dynamically created ones, except for the SYSCTL NODE type and SYSCTLs
which belong to VNETs. A new flag, CTLFLAG_NOFETCH, has been added to
be used in the case a tunable sysctl has a custom initialisation
function allowing the sysctl to still be marked as a tunable. The
kernel SYSCTL API is mostly the same, with a few exceptions for some
special operations like iterating childrens of a static/extern SYSCTL
node. This operation should probably be made into a factored out
common macro, hence some device drivers use this. The reason for
changing the SYSCTL API was the need for a SYSCTL parent OID pointer
and not only the SYSCTL parent OID list pointer in order to quickly
generate the sysctl path. The motivation behind this patch is to avoid
parameter loading cludges inside the OFED driver subsystem. Instead of
adding special code to the OFED driver subsystem to post-load tunables
into dynamically created sysctls, we generalize this in the kernel.

Other changes:
- Corrected a possibly incorrect sysctl name from "hw.cbb.intr_mask"
to "hw.pcic.intr_mask".
- Removed redundant TUNABLE statements throughout the kernel.
- Some minor code rewrites in connection to removing not needed
TUNABLE statements.
- Added a missing SYSCTL_DECL().
- Wrapped two very long lines.
- Avoid malloc()/free() inside sysctl string handling, in case it is
called to initialize a sysctl from a tunable, hence malloc()/free() is
not ready when sysctls from the sysctl dataset are registered.
- Bumped FreeBSD version to indicate SYSCTL API change.

MFC after:	2 weeks
Sponsored by:	Mellanox Technologies
2014-06-27 16:33:43 +00:00
Jack F Vogel
8cc64f1e21 Sync the E1000 shared code with Intel internal, this adds fixes,
and more importantly, new I218 adapter support to the em driver.

MFC after: 1 week
2014-06-26 21:33:32 +00:00
John Baldwin
46e89834dc - Don't compare bus_dma map pointers for static DMA allocations against
NULL to determine if bus_dmamap_unload() or bus_dmamem_free() should be
  called.  Instead, check the associated bus and virtual addresses.
- Don't clear static DMA maps to NULL.

Reviewed by:	jfv
2014-06-12 11:15:19 +00:00