Commit Graph

3665 Commits

Author SHA1 Message Date
Ryan Stone
7d309e8e40 Fix reference to free memory in ixgbe/if_media.c
When ixgbe receives an interrupt indicating that a new optical module
may have been inserted, it discards all of its current media types
by calling ifmedia_removeall() and then creates a new set of media
types for the supported media on the new module.  However,
ifmedia_removeall() was maintaining a pointer to whatever the
current media type was before the call to ifmedia_removealL().
The result of this was that any attempt to read the current media
type of the interface (e.g. via ifconfig) would return potentially
garbage data from free memory (or if one were particularly unlucky
on an architecture that does not malloc() from a direct map, page
fault the kernel).

Fix this by NULL'ing out the current media field in if_media.c,
and have ixgbe update the current media type after recreating
them.

Submitted by:	Matt Joras <matt.joras AT gmail DOT com>
Reviewed by:	sbruno, erj
MFC after:	1 week
Sponsored by:	Dell EMC Isilon
Differential Revision:	https://reviews.freebsd.org/D9164
2017-01-20 17:16:48 +00:00
Hans Petter Selasky
f3e7afe2d7 Implement kernel support for hardware rate limited sockets.
- Add RATELIMIT kernel configuration keyword which must be set to
enable the new functionality.

- Add support for hardware driven, Receive Side Scaling, RSS aware, rate
limited sendqueues and expose the functionality through the already
established SO_MAX_PACING_RATE setsockopt(). The API support rates in
the range from 1 to 4Gbytes/s which are suitable for regular TCP and
UDP streams. The setsockopt(2) manual page has been updated.

- Add rate limit function callback API to "struct ifnet" which supports
the following operations: if_snd_tag_alloc(), if_snd_tag_modify(),
if_snd_tag_query() and if_snd_tag_free().

- Add support to ifconfig to view, set and clear the IFCAP_TXRTLMT
flag, which tells if a network driver supports rate limiting or not.

- This patch also adds support for rate limiting through VLAN and LAGG
intermediate network devices.

- How rate limiting works:

1) The userspace application calls setsockopt() after accepting or
making a new connection to set the rate which is then stored in the
socket structure in the kernel. Later on when packets are transmitted
a check is made in the transmit path for rate changes. A rate change
implies a non-blocking ifp->if_snd_tag_alloc() call will be made to the
destination network interface, which then sets up a custom sendqueue
with the given rate limitation parameter. A "struct m_snd_tag" pointer is
returned which serves as a "snd_tag" hint in the m_pkthdr for the
subsequently transmitted mbufs.

2) When the network driver sees the "m->m_pkthdr.snd_tag" different
from NULL, it will move the packets into a designated rate limited sendqueue
given by the snd_tag pointer. It is up to the individual drivers how the rate
limited traffic will be rate limited.

3) Route changes are detected by the NIC drivers in the ifp->if_transmit()
routine when the ifnet pointer in the incoming snd_tag mismatches the
one of the network interface. The network adapter frees the mbuf and
returns EAGAIN which causes the ip_output() to release and clear the send
tag. Upon next ip_output() a new "snd_tag" will be tried allocated.

4) When the PCB is detached the custom sendqueue will be released by a
non-blocking ifp->if_snd_tag_free() call to the currently bound network
interface.

Reviewed by:		wblock (manpages), adrian, gallatin, scottl (network)
Differential Revision:	https://reviews.freebsd.org/D3687
Sponsored by:		Mellanox Technologies
MFC after:		3 months
2017-01-18 13:31:17 +00:00
Sean Bruno
4ecb427a49 Fix hangs in a uniprocessor configuration (qemu, virtualbox, real hw).
sys/net/iflib.c:
  Add ctx to filter_info and don't skpi interrupt early on unless we're on an
  SMP system

sys/kern/subr_gtaskqueue.c:
  Skip smp check if we're running UP

Submitted by:	Matt Macy <mmacy@nextbsd.org>
Reported by:	emaste bde
2017-01-15 00:50:10 +00:00
Sean Bruno
5b51fcfc7a Remove unused mtx_held() macro. 2017-01-09 23:41:10 +00:00
Sepherosa Ziehau
cc5bb78be1 if: Defer the if_up until the ifnet.if_ioctl is called.
This ensures the interface is initialized by the interface driver
before it can be used by the rest of the system.

Reviewed by:	jhb, karels, gnn
MFC after:	3 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D8905
2017-01-06 05:10:49 +00:00
Adrian Chadd
f69a29b5f9 [net80211] add VHT media types in the media layer. 2017-01-05 04:49:23 +00:00
Sean Bruno
1248952a50 2017 IFLIB updates in preparation for commits to e1000 and ixgbe.
- iflib - add checksum in place support (mmacy)
- iflib - initialize IP for TSO (going to be needed for e1000) (mmacy)
- iflib - move isc_txrx from shared context to softc context (mmacy)
- iflib - Normalize checks in TXQ drainage. (shurd)
- iflib - Fix queue capping checks (mmacy)
- iflib - Fix invalid assert, em can need 2 sentinels (mmacy)
- iflib - let the driver determine what capabilities are set and what
          tx csum flags are used (mmacy)
- add INVARIANTS debugging hooks to gtaskqueue enqueue (mmacy)
- update bnxt(4) to support the changes to iflib (shurd)

Some other various, sundry updates.  Slightly more verbose changelog:

Submitted by:	mmacy@nextbsd.org
Reviewed by:	shurd
mFC after:
Sponsored by:	LimeLight Networks and Dell EMC Isilon
2017-01-02 00:56:33 +00:00
Alan Somers
8a73c85db3 Remove stray debugging code from r310180
Reported by:	rstone
Pointy hat to:	asomers
MFC after:	3 weeks
X-MFC-with:	310180
Sponsored by:	Spectra Logic Corp
2016-12-20 15:45:53 +00:00
Alan Somers
d9fa2d67eb Fix panic during lagg destruction with simultaneous status check
If you run "ifconfig lagg0 destroy" and "ifconfig lagg0" at the same time a
page fault may result. The first process will destroy ifp->if_lagg in
lagg_clone_destroy (called by if_clone_destroy). Then the second process
will observe that ifp->if_lagg is NULL at the top of lagg_port_ioctl and
goto fallback: where it will promptly dereference ifp->if_lagg anyway.

The solution is to repeat the NULL check for ifp->if_lagg

MFC after:	4 weeks
Sponsored by:	Spectra Logic Corp
Differential Revision:	https://reviews.freebsd.org/D8512
2016-12-16 22:39:30 +00:00
Adrian Chadd
fdbc9e6e82 [net80211] start laying down the foundation for 11ac support.
This is a work in progress and some of this stuff may change;
but hopefully I'm laying down enough stuff and space in fields
to allow it to grow without another major recompile.

We'll see!

* Add a net80211 PHY type for VHT 2G and VHT 5G.

  Note - yes, VHT is supposed to be for 5GHZ, however some vendors
  (*cough* most of them) support some subset of VHT rate support
  in 2GHz.  No - not 80MHz wide channels, but at least some MCS8-9
  support, maybe some beamforming, and maybe some longer A-MPDU
  aggregates.  I don't want to even think about MU-MIMO on 2GHz.

* Add an ifmedia placeholder type for VHT rates.

* Add channel flags for VHT, VHT20/40U/40D/80/80+80/160
* Add channel macros for the above
* Add ieee80211_channel fields for the VHT information and flags,
  along with some padding (so this struct definitely grows.)
* Add a phy type flag for VHT - 'v'

* Bump the number of channels to a much higher amount - until we get
  something like the linux mac80211 chanctx abstraction (where the
  stack provides a current channel configuration via callbacks,
  versus the driver ever checking ic->ic_curchan or similar) we'll
  have to populate VHT+HT combinations.

Eg, there'll likely be a full set of duplicate VHT20/40 channels to match
HT channels.  There will also be a full set of duplicate VHT80 channels -
note that for VHT80, its assumed you're doing VHT40 as a base, so we
don't need a duplicate of VHT80 + 20MHz only primary channels, only
a duplicate of all the VHT40 combinations.

I don't want to think about VHT80+80 or VHT160 for now - and I won't,
as the current device I'm doing 11ac bringup on (QCA9880) only does
VHT80.

I'll likely revisit the channel configuration and scanning related
stuff after I get VHT20/40 up.

* Add vht flags and the basic MCS rate setup to ieee80211com, ieee80211vap
  and ieee80211_node in preparation for 11ac configuration.
  There is zero code that uses this right now.
* Whilst here, add some more placeholders in case I need to extend
  out things by some uint32_t flag sized fields.  Hopefully I won't!

What I haven't yet done:

* any of the code that uses this
* any of the beamforming related fields
* any of the MU-MIMO fields required for STA/AP operation
* any of the IE fields in beacon frame / probe request/response handling
  and the calculations required for shifting beacon contents around
  when the TIM grows/shrinks

This will require a full rebuild of net80211 related programs -
ifconfig, hostapd, wpa_supplicant.
2016-12-16 04:43:31 +00:00
Luiz Otavio O Souza
8f1c8ade60 Fix the typos and style(9) in comment.
MFC after:	2 weeks
Sponsored by:	Rubicon Communications, LLC (Netgate)
2016-12-08 18:18:48 +00:00
Fabien Thomas
bf4356266d IPsec RFC6479 support for replay window sizes up to 2^32 - 32 packets.
Since the previous algorithm, based on bit shifting, does not scale
with large replay windows, the algorithm used here is based on
RFC 6479: IPsec Anti-Replay Algorithm without Bit Shifting.
The replay window will be fast to be updated, but will cost as many bits
in RAM as its size.

The previous implementation did not provide a lock on the replay window,
which may lead to replay issues.

Reviewed by:	ae
Obtained from:	emeric.poupon@stormshield.eu
Sponsored by:	Stormshield
Differential Revision:	https://reviews.freebsd.org/D8468
2016-11-25 14:44:49 +00:00
Sean Bruno
da69b8f9d1 iflib updates and fixes:
-    reset gen on down
-    initialize admin task statically
-    drain mp_ring on down
-    don't drop context lock on stop
-    reset error stats on down
-    fix typo in min_latency sysctl
-    return ENOBUFS from if_transmit if the driver isn't running or the link is down

Submitted by:	mmacy@nextbsd.org
Reviewed by:	shurd
MFC after:	2 days
Sponsored by:	Isilon and Limelight Networks
Differential Revision:	https://reviews.freebsd.org/D8558
2016-11-18 04:19:21 +00:00
Mark Johnston
55dfce589c Plug a lock leak in sysctl_ifmalist().
Fix style in the local variable declarations.

PR:		214542
MFC after:	1 week
2016-11-15 19:23:48 +00:00
Ryan Stone
ab607f28e3 Don't read if_counters with if_addr_lock held
Calling into an ifnet implementation with the if_addr_lock already
held can cause a LOR and potentially a deadlock, as ifnet
implementations typically can take the if_addr_lock after their
own locks during configuration.  Refactor a sysctl handler that
was violating this to read if_counter data in a temporary buffer
before the if_addr_lock is taken, and then copying the data
in its final location later, when the if_addr_lock is held.

PR: 194109
Reported by: Jean-Sebastien Pedron
MFC after: 2 weeks
Differential Revision:	https://reviews.freebsd.org/D8498
Reviewed by: sbruno
2016-11-12 19:03:23 +00:00
Luigi Rizzo
844a6f0c53 Various fixes for ptnet/ptnetmap (passthrough of netmap ports). In detail:
- use PCI_VENDOR and PCI_DEVICE ids from a publicly allocated range
  (thanks to RedHat)
- export memory pool information through PCI registers
- improve mechanism for configuring passthrough on different hypervisors
Code is from Vincenzo Maffione as a follow up to his GSOC work.
2016-10-27 09:46:22 +00:00
Sepherosa Ziehau
14a31e99d7 hyperv/hn: Define empty packet filter.
MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D8342
2016-10-27 04:55:19 +00:00
Bryan Drewery
921e5f5675 Remove excess CTLFLAG_VNET
Sponsored by:	Dell EMC Isilon
2016-10-26 23:40:07 +00:00
Sepherosa Ziehau
121e98e697 hyperv/hn: Fix RX filter settings.
MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D8313
2016-10-24 05:10:35 +00:00
Sepherosa Ziehau
970ead008d hyperv/hn: Add network change support.
Currently the network change is simulated by link status changes.

MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D8295
2016-10-21 08:02:05 +00:00
Jung-uk Kim
69d410eeb1 Implement BPF_MOD and BPF_XOR instructions.
These two ALU instructions first appeared on Linux.  Then, libpcap adopted
and made them available since 1.6.2.  Now more platforms including NetBSD
have them in kernel.  So do we.
 --이 줄 이하는 자동으로 제거됩니다--
2016-10-21 06:55:07 +00:00
Andrew Gallatin
eedb49598b Clear mbuf hashtype on loopback when RSS is enabled.
The hashtype on an outgoing mbuf reflects the correct hash on the
transmit side of the connection.  If this hash persists on loopback,
the receiving RSS/PCBGROUP code will use it to look up the pcbgroup
for the transmit side, which will often not match the pcbgroup for the
receive side of the connection.  This leads to TCP connections
hanging, and dropping the SYN/ACK packet.   This is essentially
the same as having a hardware network card generate mbufs with an
incorrect RSS hash.

There are a number of places which can set the hash on transmit,
so the simplest fix is to simply clear the hash at loopback time.
Clearing the hash allows a new, correct hash to be calculated in
software on the receive side.

Reviewed by:	jtl
Discussed with:	adrian
Sponsored by:	Netflix
2016-10-20 13:48:29 +00:00
Kevin Lo
b95d46da24 Fix typo in comment. 2016-10-19 02:24:57 +00:00
Luigi Rizzo
a2a7409151 remove stale and unused code from various files
fix build on 32 bit platforms
simplify logic in netmap_virt.h

The commands (in net/netmap.h) to configure communication with the
hypervisor may be revised soon.
At the moment they are unused so this will not be a change of API.
2016-10-18 16:18:25 +00:00
Luigi Rizzo
6ad42d71b2 remove trailing whitespace. No code changes. 2016-10-18 15:41:57 +00:00
Sean Bruno
2fe66646bd Set default capabilities at attach.
ref: 6425f45e5f

Submitted by:	mmacy@nextbsd.org
2016-10-18 14:02:45 +00:00
Sean Bruno
add6f7d069 When deciding whether or not to call tqg_attach_cpu(), reference rid
directly.

ref: c9b47b468b

Submitted by:	mmacy@nextbsd.org
2016-10-18 13:29:30 +00:00
Sean Bruno
8b2a1db901 Toggle v4/v6 rxcsum together
Only re-init if driver is running

ref: 106518e874

Submitted by:	mmacy@nextbsd.org
2016-10-18 13:22:44 +00:00
Sean Bruno
aa3c5dd8a8 Fix misusage of CPU_FFS when binding queues to cpus
ref: 922d0bdf22

Submitted by:	mmacy@nextbsd.org
2016-10-18 13:12:19 +00:00
Luigi Rizzo
a82ab41168 add a missing header. 2016-10-16 18:27:41 +00:00
Luigi Rizzo
37e3a6d349 Import the current version of netmap, aligned with the one on github.
This commit, long overdue, contains contributions in the last 2 years
from Stefano Garzarella, Giuseppe Lettieri, Vincenzo Maffione, including:
+ fixes on monitor ports
+ the 'ptnet' virtual device driver, and ptnetmap backend, for
  high speed virtual passthrough on VMs (bhyve fixes in an upcoming commit)
+ improved emulated netmap mode
+ more robust error handling
+ removal of stale code
+ various fixes to code and documentation (some mixup between RX and TX
  parameters, and private and public variables)

We also include an additional tool, nmreplay, which is functionally
equivalent to tcpreplay but operating on netmap ports.
2016-10-16 14:13:32 +00:00
Sepherosa Ziehau
368bf0c2c6 ifnet: Use if_link_state snapshot to invoke ifnet_link_event
So that everyone in this task have consistent view of link state.

Reviewed by:	ae
MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D8214
2016-10-12 01:52:29 +00:00
Andrey V. Elsukov
199511bcdd Make LLTABLE list lock private for if_llatbl.c
Rename lock and macros to reflect that it protects V_lltables list.
2016-10-11 17:41:13 +00:00
Sepherosa Ziehau
65ca331080 hyperv/hn: Fix checksum offload settings
The _correct_ way to identify the supported checksum offloading and
TSO parameters is to query OID_TCP_OFFLOAD_HARDWARE_CAPABILITIES.

MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D8088
2016-10-10 05:41:39 +00:00
Andrey V. Elsukov
abe95d87ee Replace rw_init/rw_destroy with corresponding macros.
Obtained from:	Yandex LLC
2016-10-06 14:42:06 +00:00
Kevin Lo
c2b5ba7661 Remove an alias if_list, use if_link consistently.
Reviewed by:	tuexen
Differential Revision:	https://reviews.freebsd.org/D8075
2016-10-06 00:51:27 +00:00
Sepherosa Ziehau
1a3c881209 hyperv/hn: Add stubs for OFFLOAD_CURRENT_CONFIG and NETWORK_CHANGE status
MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D8068
2016-09-30 06:58:45 +00:00
Kevin Lo
decb239dff Remove the compatibility macro if_addrlist.
Since if_addrlist is used only for ipfilter(4), add a macro if_addrlist
in ip_compat.h.

Reviewed by:	cy
Differential Revision:	https://reviews.freebsd.org/D8059
2016-09-29 05:37:45 +00:00
Kevin Lo
c7641cd18d Remove ifa_list, use ifa_link (structure field) instead.
While here, prefer if_addrhead (FreeBSD) to if_addrlist (BSD compat) naming
for the interface address list in sctp_bsd_addr.c

Reviewed by:	tuexen
Differential Revision:	https://reviews.freebsd.org/D8051
2016-09-28 13:29:11 +00:00
Kevin Lo
3ff511d316 Remove a comment about the size of the ifnet structure.
Reviewed by:	adrian
Differential Revision:	https://reviews.freebsd.org/D8036
2016-09-27 08:11:09 +00:00
Kristof Provost
f18598a43e bridge: Fix fragment handling and memory leak
Fragmented UDP and ICMP packets were corrupted if a firewall with reassembling
feature (like pf'scrub) is enabled on the bridge.  This patch fixes corrupted
packet problem and the panic (triggered easly with low RAM) as explain in PR
185633.

bridge_pfil and bridge_fragment relationship:

bridge_pfil() receive (IN direction) packets and sent it to the firewall The
firewall can be configured for reassembling fragmented packet (like pf'scrubing)
in one mbuf chain when bridge_pfil() need to send this reassembled packet to the
outgoing interface, it needs to re-fragment it by using bridge_fragment()
bridge_fragment() had to split this mbuf (using ip_fragment) first then
had to M_PREPEND each packet in the mbuf chain for adding Ethernet
header.

But M_PREPEND can sometime create a new mbuf on the begining of the mbuf chain,
then the "main" pointer of this mbuf chain should be updated and this case is
tottaly forgotten. The original bridge_fragment code (Revision 158140,
2006 April 29) came from OpenBSD, and the call to bridge_enqueue was
embedded.  But on FreeBSD, bridge_enqueue() is done after bridge_fragment(),
then the original OpenBSD code can't work as-it of FreeBSD.

PR:		185633
Submitted by:	Olivier Cochard-Labbé
Differential Revision:	https://reviews.freebsd.org/D7780
2016-09-24 07:09:43 +00:00
Kevin Lo
c3bef61e58 Remove the 4.3BSD compatible macro m_copy(), use m_copym() instead.
Reviewed by:	gnn
Differential Revision:	https://reviews.freebsd.org/D7878
2016-09-15 07:41:48 +00:00
Sepherosa Ziehau
b349357819 hyperv/hn: Stringent RNDIS packet message length/offset check.
While I'm here, use definition in net/rndis.h

MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D7782
2016-09-06 03:20:06 +00:00
Sepherosa Ziehau
a8197ee35e net/rndis: Define RNDIS status message, which could be sent by device.
MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D7757
2016-09-05 04:56:56 +00:00
Sepherosa Ziehau
772b86ba12 net/rndis: Define common message header for RNDIS messages.
And avoid RNDIS_HEADER_OFFSET hardcoding.

Reviewed by:	hps
MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D7739
2016-09-02 05:57:13 +00:00
Sepherosa Ziehau
178228a10e net/rndis: Add comment for rndis_comp_hdr
Reviewed by:	hps
MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D7738
2016-09-02 05:49:38 +00:00
Sepherosa Ziehau
46ebd74ce1 net/rndis: Define types for RNDIS pktinfo rm_type field.
They are defined by NDIS spec, so the NDIS prefix.

Reviewed by:	hps
MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D7717
2016-09-01 07:17:06 +00:00
Sepherosa Ziehau
f320cbed5a net/vlan: Shift for pri is 13 (pri mask 0xe000) not 1.
Reviewed by:	araujo, hps
MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D7710
2016-09-01 06:32:35 +00:00
Sepherosa Ziehau
6f67f21938 net/rndis: Define per-packet-info for RNDIS packet message
MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D7708
2016-09-01 05:40:13 +00:00
Sepherosa Ziehau
947175ca10 net/rndis: Add comment for rndis_set_parameter
MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D7705
2016-09-01 05:15:04 +00:00