Commit Graph

32 Commits

Author SHA1 Message Date
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
dcd7b3b269 Some RSS issues discovered by Adrian, missing header, variable
names fat fingered, incorrect hash config setup. Thanks :)

MFC after: 1 week
2015-01-16 19:11:58 +00:00
Jack F Vogel
df1d7a71d4 Cleanup some bogus code in the RSS config, and add the include
for the rss option file. And bump the version.

MFC after:	1 week
2015-01-13 22:13:30 +00:00
Jack F Vogel
6b30e6ae6c Complete the RX side RSS code: parse the encoded portion of the RX
descriptor to determine the correct hash type.

MFC after:1 week
2015-01-13 18:56:29 +00:00
Bjoern A. Zeeb
a2cf30b916 Move the vsi variable outside of the #ifdef block to unbreak NOIP kernels
after r277084.

MFC after:	6 days
X-MFC with:	r277084
2015-01-13 14:15:00 +00:00
Jack F Vogel
845a028fa3 Missing RSS support added, this fixes the build, but the code
in the RX side was complicated by recent changes and will need
some further tweaking.
2015-01-12 20:59:07 +00:00
Jack F Vogel
393c4bb1ba Intel I40E driver updates:
if_ixl to version 1.3.0, if_ixlv to version 1.2.0
	- Major change in both drivers is to add RSS support
	- In ixl fix some interface speed related issues, dual
	  speed was not changing correctly, KR/X media was not
	  displaying correctly (this has a workaround until a
	  more robust media handling is in place)
	- Add a warning when using Dell NPAR and the speed is
	  less than 10G
	- Wrap a queue hung message in IXL_DEBUG, as it is non-fatal,
	  and without tuning can display excessively

MFC after: 1 week
2015-01-12 18:43:34 +00:00
Jack F Vogel
f247dc2523 Update to the shared code for Intel I40E drivers in preparation
for the ixl 1.3.0 and ixlv 1.2.0 revisions.

MFC after:	1 week
2015-01-12 18:32:45 +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
Bjoern A. Zeeb
20dc9e1740 After r274205 unbreak NOIP kernels. vsi is now also used outside
address family specific blocks so move it out from under the condition.

MFC after:	6 days
X-MFC with:	r274205
2014-11-07 11:34:06 +00:00
Jack F Vogel
3fa969c8ac Add header file missing from last commit.
Submitted by: jfv
MFC after: 1 week
2014-11-07 04:47:46 +00:00
Jack F Vogel
e5100ee278 Update the Intel i40e drivers, ixl version 1.2.8, ixlv version 1.1.18
-Improved VF stability, thanks to changes from Ryan Stone,
	 and Juniper.
	- RSS fixes in the ixlv driver
	- link detection in the ixlv driver
	- New sysctl's added in ixl and ixlv
	- reset timeout increased for ixlv
	- stability fixes in detach
	- correct media reporting
	- Coverity warnings fixed
	- Many small bug fixes
	- VF Makefile modified - nvm shared code needed
	- remove unused sleep channels in ixlv_sc struct

Submitted by: Eric Joyner (committed by jfv)
MFC after:	1 week
2014-11-06 23:45:05 +00:00
Jim Harris
83a4c3f99e ixl: remove i40e_register_x710_int.h
This file is not used by the FreeBSD ixl driver.

Submitted by:	Eric Joyner <eric.joyner@intel.com>
MFC after:	3 days
2014-10-21 18:00:56 +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
Ryan Stone
cf3c0c32d2 Ensure that ixl_flush() uses a defined register on VFs
In some code that is shared between the ixl(4) and ixlv(4) drivers,
a macro hard-coded a register offset that was not valid on ixlv devices.
Fix this by having each driver define a variable that contains the correct
offset.

Reviewed by:	Eric Joyner <ricera10 AT gmail.com>
MFC after:	3 days
Sponsored by:	Sandvine Inc
2014-09-29 17:51:39 +00:00
Gleb Smirnoff
4b443922e0 Convert driver to if_get_counter method.
Submitted by:	rstone
Reviewed by:	Eric Joyner <ricera10 gmail.com>
2014-09-27 20:54:57 +00:00
Bjoern A. Zeeb
a401d28ee8 Given we are restricting ixl(4) to 64bit platforms now backout the change
r270820 to common (shared) Intel code no longer needed.

MFC after:	3 days
2014-09-23 08:39:08 +00:00
Bjoern A. Zeeb
b3f7259b25 Hide LRO code under #ifdef INET/INET6 to allow NOIP kernel to compile.
While the code comments indicate that LRO is currently only supported
for IPv4/TCP, we'll still compile it in for IPv6.

MFC after:	3 days
2014-09-21 00:05:44 +00:00
Bjoern A. Zeeb
7e0dde7d54 Properly hide calls to ARP under #ifdef INET to allow IPv6-only
kernels to compile.

MFC atfer:	3 days
2014-09-20 08:34:56 +00:00
Bjoern A. Zeeb
d94ca7cf07 Revert r270808, which were changes to common code (i40e_alloc.h).
Rather than #define-ing common code function calls to OS-dependent
ones, make the osdep versions match the common code expectations,
adjust the FreeBSD specific code to use those, and remove the
#defines.

In the FreeBSD specific code, use "i40e_mem_reserved" for the
now expected but unused argument to i40e_allocate_dma_mem().

Reviewed by:	gnn, eric.joyner intel.com
MFC after:	3 days
2014-09-18 21:13:03 +00:00
Bjoern A. Zeeb
ea022094f2 For consistency with the shared header file (and to avoid confusion
with mbufs normally called *m in one place), rename the function
arguments to "mem".

This is a non-functional change.

Reviewed by:	gnn, eric.joyner intel.com
MFC after:	3 days
2014-09-18 08:56:25 +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
Bjoern A. Zeeb
452fd26522 Try to also unbreak powerpc complaining about
"cast from pointer to integer of different size".

MFC after:	3 days
X-MFC with:	r270755
2014-08-29 14:38:57 +00:00
Bjoern A. Zeeb
3ad95447c8 These functions are #defined to "osdep" specific names without the "_mem"
extension.  Provide prototypes for the actual implementations.
Correct function arguments to match the implementations.

MFC after:	3 days
X-MFC with:	r270755
2014-08-29 12:48:38 +00:00
Bjoern A. Zeeb
b555c6140d Properly place #ifdef INET and #ifdef INET6 around variable declarations
and code to make the code compile.

Give the function seems to be slightly mixed with csum and tso,
make it non-fatal if we try to setup thing on a kernel without IP
support.  In practise the printf on the console will probably still
make your machine unhappy.

MFC after:	3 days
X-MFC with:	r270755
2014-08-29 12:45:14 +00:00
Bjoern A. Zeeb
f894ad8848 Properly handle prefetch only for amd64 and i386 as we do elsewhere.
In general theraven is right that we should factr this out and provide
a general and per-arch implementation that everything can use.

MFC after:	3 days
X-MFC with:	r270755
2014-08-29 12:40:01 +00:00
Bjoern A. Zeeb
ff21e856ec First try on fixing some more compile errors without actually testing:
- use proper __FreeBSD_version check and more importantly check for __am64__
  to be defined.  Whether the FreeBSD(_version) checks are needed is a
  different question.
- cast uint64_t to uintmax_t and use %jx for printing.

Note: there are more values that could be printed in that status function
	but leave that for the future;  printf doesn't seem to be the right
	way to do it anyway.
Note: there is more breakage related to i40e_allocate_dma*() having
	conflicting declarations, so more fixes to come.

PR:		193112
MFC after:	3 days
X-MFC with:	r270755
2014-08-29 09:37:18 +00:00
Jack F Vogel
2f4959ab6a Fix the NOINET and NOINET6 builds.
MFC after:3 days
2014-08-29 00:33:31 +00:00
Jack F Vogel
1f873f1805 Remove the DEV_NETMAP code from the ixl drivers, it was a placeholder
and not yet ready to be defined, and its causing build errors.

MFC after:	3 days
2014-08-28 22:52:20 +00:00
Jack F Vogel
5c34b900df Some corrections, reformating, and additional info about the VF
driver in the README.

MFC after: 1 day
2014-08-28 21:45:07 +00:00
Steven Hartland
13b408044d Fix build breakage caused by ixl driver
Fix missing includes and invalid vars in ixl / ixlv driver added by r270346
which caused build failures for GENERIC kernel after it was made default
by r270755.

X-MFC-With: r270346 / r270755
Sponsored by:	Multiplay
2014-08-28 18:59:39 +00:00
Jack F Vogel
61ae650d55 Update to the Intel Base driver for the Intel XL710 Ethernet Controller Family
- It was decided to change the driver name to if_ixl for FreeBSD
	- This release adds the VF Driver to the tree, it can be built into
	  the kernel or as the if_ixlv module
	- The VF driver is independent for the first time, this will be
	  desireable when full SRIOV capability is added to the OS.
	- Thanks to my new coworker Eric Joyner for his superb work in
	  both the core and vf driver code.

Enjoy everyone!

Submitted by:	jack.vogel@intel.com and eric.joyner@intel.com
MFC after:	3 days (hoping to make 10.1)
2014-08-22 18:59:19 +00:00