Yevgeny Petrilin [Tue, 24 Aug 2010 03:45:20 +0000 (03:45 +0000)]
mlx4_en: Setting actual RX ring size
When configuring HW resources, the RX ring size that is passed should be the actual
size that depends on number of buffers that we succeeded to allocate.
The mask for ring size should also be configured accordingly
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il> Signed-off-by: David S. Miller <davem@davemloft.net>
Yevgeny Petrilin [Tue, 24 Aug 2010 03:45:05 +0000 (03:45 +0000)]
mlx4_en: Fixed incorrect unmapping on RX flow.
When allocating new fragments to replace the ones that would be passed to the stack,
The fragments that should be replaced, are the ones that were already used.
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il> Signed-off-by: David S. Miller <davem@davemloft.net>
Simon Horman [Mon, 23 Aug 2010 16:26:41 +0000 (16:26 +0000)]
net: increase the size of priv_flags and add IFF_OVS_DATAPATH
IFF_OVS_DATAPATH is a place-holder for the Open vSwitch datapath
which I am preparing to submit for merging.
As all 16 bits of priv_flags are already assigned flags, also increase
the size of priv_flags to 32 bits.
Unfortunately, by my calculations this increases the size of
struct net_device by 4 bytes on 32bit architectures and
8 bytes on 64 bit architectures. I couldn't see an obvious
way to avoid that.
Cc: Jesse Gross <jesse@nicira.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
The SNMP daemon uses ethtool to determine the speed of
network interfaces. This fails on Debian (and probably elsewhere)
because for security SNMP daemon runs as non-root user (snmp).
Note: A similar patch was rejected previously because of a concern about
the possibility that on some hardware querying the ethtool settings
requires access to the PHY and could slow the machine down. But the
security risk of requiring SNMP daemon (and related services)
to run as root far out weighs the risk of denial-of-service.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Mon, 23 Aug 2010 07:14:36 +0000 (07:14 +0000)]
net: copy_rtnl_link_stats64() simplification
No need to use a temporary struct rtnl_link_stats64 variable,
just copy the source to skb buffer.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Reviewed-by: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
cxgb4: handle Rx/Tx queue ranges not starting at 0
Currently the driver assumes that queue IDs start at 0 but that's true
only for function 0. To support operation on other functions get the
start of the queue ranges from FW and offset accordingly.
Signed-off-by: Dimitris Michailidis <dm@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Gerrit Renker [Sun, 22 Aug 2010 19:41:40 +0000 (19:41 +0000)]
dccp ccid-2: Replace broken RTT estimator with better algorithm
The current CCID-2 RTT estimator code is in parts broken and lags behind the
suggestions in RFC2988 of using scaled variants for SRTT/RTTVAR.
That code is replaced by the present patch, which reuses the Linux TCP RTT
estimator code.
Further details:
----------------
1. The minimum RTO of previously one second has been replaced with TCP's, since
RFC4341, sec. 5 says that the minimum of 1 sec. (suggested in RFC2988, 2.4)
is not necessary. Instead, the TCP_RTO_MIN is used, which agrees with DCCP's
concept of a default RTT (RFC 4340, 3.4).
2. The maximum RTO has been set to DCCP_RTO_MAX (64 sec), which agrees with
RFC2988, (2.5).
3. De-inlined the function ccid2_new_ack().
4. Added a FIXME: the RTT is sampled several times per Ack Vector, which will
give the wrong estimate. It should be replaced with one sample per Ack.
However, at the moment this can not be resolved easily, since
- it depends on TX history code (which also needs some work),
- the cleanest solution is not to use the `sent' time at all (saves 4 bytes
per entry) and use DCCP timestamps / elapsed time to estimated the RTT,
which however is non-trivial to get right (but needs to be done).
Reasons for reusing the Linux TCP estimator algorithm:
------------------------------------------------------
Some time was spent to find a better alternative, using basic RFC2988 as a first
step. Further analysis and experimentation showed that the Linux TCP RTO
estimator is superior to a basic RFC2988 implementation. A summary is on
http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/ccid2/rto_estimator/
In addition, this estimator fared well in a recent empirical evaluation:
Rewaskar, Sushant, Jasleen Kaur and F. Donelson Smith.
A Performance Study of Loss Detection/Recovery in Real-world TCP
Implementations. Proceedings of 15th IEEE International
Conference on Network Protocols (ICNP-07), 2007.
Thus there is significant benefit in reusing the existing TCP code.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
Gerrit Renker [Sun, 22 Aug 2010 19:41:39 +0000 (19:41 +0000)]
dccp ccid-2: Simplify dec_pipe and rearming of RTO timer
This removes the dec_pipe function and improves the way the RTO timer is rearmed
when a new acknowledgment comes in.
Details and justification for removal:
--------------------------------------
1) The BUG_ON in dec_pipe is never triggered: pipe is only decremented for TX
history entries between tail and head, for which it had previously been
incremented in tx_packet_sent; and it is not decremented twice for the same
entry, since it is
- either decremented when a corresponding Ack Vector cell in state 0 or 1
was received (and then ccid2s_acked==1),
- or it is decremented when ccid2s_acked==0, as part of the loss detection
in tx_packet_recv (and hence it can not have been decremented earlier).
2) Restarting the RTO timer happens for every single entry in each Ack Vector
parsed by tx_packet_recv (according to RFC 4340, 11.4 this can happen up to
16192 times per Ack Vector).
3) The RTO timer should not be restarted when all outstanding data has been
acknowledged. This is currently done similar to (2), in dec_pipe, when
pipe has reached 0.
The patch onsolidates the code which rearms the RTO timer, combining the
segments from new_ack and dec_pipe. As a result, the code becomes clearer
(compare with tcp_rearm_rto()).
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
Gerrit Renker [Sun, 22 Aug 2010 19:41:38 +0000 (19:41 +0000)]
dccp ccid-2: Remove redundant sanity tests
This removes the ccid2_hc_tx_check_sanity function: it is redundant.
Details:
The tx_check_sanity function performs three tests:
1) it checks that the circular TX list is sorted
- in ascending order of sequence number (ccid2s_seq)
- and time (ccid2s_sent),
- in the direction from `tail' (hctx_seqt) to `head' (hctx_seqh);
2) it ensures that the entire list has the length seqbufc * CCID2_SEQBUF_LEN;
3) it ensures that pipe equals the number of packets that were not
marked `acked' (ccid2s_acked) between `tail' and `head'.
The following argues that each of these tests is redundant, this can be verified
by going through the code.
(1) is not necessary, since both time and GSS increase from one packet to the
next, so that subsequent insertions in tx_packet_sent (which advance the `head'
pointer) will be in ascending order of time and sequence number.
In (2), the length of the list is always equal to seqbufc times CCID2_SEQBUF_LEN
(set to 1024) unless allocation caused an earlier failure, because:
* at initialisation (tx_init), there is one chunk of size 1024 and seqbufc=1;
* subsequent calls to tx_alloc_seq take place whenever head->next == tail in
tx_packet_sent; then a new chunk of size 1024 is inserted between head and
tail, and seqbufc is incremented by one.
To show that (3) is redundant requires looking at two cases.
The `pipe' variable of the TX socket is incremented only in tx_packet_sent, and
decremented in tx_packet_recv. When head == tail (TX history empty) then pipe
should be 0, which is the case directly after initialisation and after a
retransmission timeout has occurred (ccid2_hc_tx_rto_expire).
The first case involves parsing Ack Vectors for packets recorded in the live
portion of the buffer, between tail and head. For each packet marked by the
receiver as received (state 0) or ECN-marked (state 1), pipe is decremented by
one, so for all such packets the BUG_ON in tx_check_sanity will not trigger.
The second case is the loss detection in the second half of tx_packet_recv,
below the comment "Check for NUMDUPACK".
The first while-loop here ensures that the sequence number of `seqp' is either
above or equal to `high_ack', or otherwise equal to the highest sequence number
sent so far (of the entry head->prev, as head points to the next unsent entry).
The next while-loop ("while (1)") counts the number of acked packets starting
from that position of seqp, going backwards in the direction from head->prev to
tail. If NUMDUPACK=3 such packets were counted within this loop, `seqp' points
to the last acknowledged packet of these, and the "if (done == NUMDUPACK)" block
is entered next.
The while-loop contained within that block in turn traverses the list backwards,
from head to tail; the position of `seqp' is saved in the variable `last_acked'.
For each packet not marked as `acked', a congestion event is triggered within
the loop, and pipe is decremented. The loop terminates when `seqp' has reached
`tail', whereupon tail is set to the position previously stored in `last_acked'.
Thus, between `last_acked' and the previous position of `tail',
- pipe has been decremented earlier if the packet was marked as state 0 or 1;
- pipe was decremented if the packet was not marked as acked.
That is, pipe has been decremented by the number of packets between `last_acked'
and the previous position of `tail'. As a consequence, pipe now again reflects
the number of packets which have not (yet) been acked between the new position
of tail (at `last_acked') and head->prev, or 0 if head==tail. The result is that
the BUG_ON condition in check_sanity will also not be triggered, hence the test
(3) is also redundant.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
Gerrit Renker [Sun, 22 Aug 2010 19:41:37 +0000 (19:41 +0000)]
dccp ccid-3: No more CCID control blocks in LISTEN state
The CCIDs are activated as last of the features, at the end of the handshake,
were the LISTEN state of the master socket is inherited into the server
state of the child socket. Thus, the only states visible to CCIDs now are
OPEN/PARTOPEN, and the closing states.
This allows to remove tests which were previously necessary to protect
against referencing a socket in the listening state (in CCID-3), but which
now have become redundant.
As a further byproduct of enabling the CCIDs only after the connection has been
fully established, several typecast-initialisations of ccid3_hc_{rx,tx}_sock
can now be eliminated:
* the CCID is loaded, so it is not necessary to test if it is NULL,
* if it is possible to load a CCID and leave the private area NULL, then this
is a bug, which should crash loudly - and earlier,
* the test for state==OPEN || state==PARTOPEN now reduces only to the closing
phase (e.g. when the node has received an unexpected Reset).
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: David S. Miller <davem@davemloft.net>
Gerrit Renker [Sun, 22 Aug 2010 19:41:36 +0000 (19:41 +0000)]
ccid: ccid-2/3 code cosmetics
This patch collects cosmetics-only changes to separate these from
code changes:
* update with regard to CodingStyle and whitespace changes,
* documentation:
- adding/revising comments,
- remove CCID-3 RX socket documentation which is either
duplicate or refers to fields that no longer exist,
* expand embedded tfrc_tx_info struct inline for consistency,
removing indirections via #define.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
Ian Campbell [Wed, 18 Aug 2010 23:27:49 +0000 (23:27 +0000)]
xen: use less generic names in netfront driver.
All Xen frontend drivers have a couple of identically named functions which
makes figuring out which device went wrong from a stacktrace harder than it
needs to be. Rename them to something specificto the device type.
Signed-off-by: Ian Campbell <ian.campbell@citrix.com> Cc: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Signed-off-by: David S. Miller <davem@davemloft.net>
tcp: allow effective reduction of TCP's rcv-buffer via setsockopt
Via setsockopt it is possible to reduce the socket RX buffer
(SO_RCVBUF). TCP method to select the initial window and window scaling
option in tcp_select_initial_window() currently misbehaves and do not
consider a reduced RX socket buffer via setsockopt.
Even though the server's RX buffer is reduced via setsockopt() to 256
byte (Initial Window 384 byte => 256 * 2 - (256 * 2 / 4)) the window
scale option is still 7:
Within tcp_select_initial_window() the original space argument - a
representation of the rx buffer size - is expanded during
tcp_select_initial_window(). Only sysctl_tcp_rmem[2], sysctl_rmem_max
and window_clamp are considered to calculate the initial window.
This patch adjust the window_clamp argument if the user explicitly
reduce the receive buffer.
Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Cc: David S. Miller <davem@davemloft.net> Cc: Patrick McHardy <kaber@trash.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Carsten Paeth <calle@calle.de> Cc: Karsten Keil <isdn@linux-pingi.de> Signed-off-by: David S. Miller <davem@davemloft.net>
Simon Horman [Sun, 22 Aug 2010 17:35:32 +0000 (17:35 +0000)]
bridge: is PACKET_LOOPBACK unlikely()?
While looking at using netdev_rx_handler_register for openvswitch Jesse
Gross suggested that an unlikely() might be worthwhile in that code.
I'm interested to see if its appropriate for the bridge code.
Cc: Jesse Gross <jesse@nicira.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
John Feeney [Sun, 22 Aug 2010 17:45:53 +0000 (17:45 +0000)]
bnx2: Add PCI Advanced Error Reporting support.
Signed-off-by: John Feeney <jfeeney@redhat.com> Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: Benjamin Li <benli@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Dmitry Kozlov [Sun, 22 Aug 2010 06:05:39 +0000 (23:05 -0700)]
PPTP: PPP over IPv4 (Point-to-Point Tunneling Protocol)
PPP: introduce "pptp" module which implements point-to-point tunneling protocol using pppox framework
NET: introduce the "gre" module for demultiplexing GRE packets on version criteria
(required to pptp and ip_gre may coexists)
NET: ip_gre: update to use the "gre" module
This patch introduces then pptp support to the linux kernel which
dramatically speeds up pptp vpn connections and decreases cpu usage in
comparison of existing user-space implementation
(poptop/pptpclient). There is accel-pptp project
(https://sourceforge.net/projects/accel-pptp/) to utilize this module,
it contains plugin for pppd to use pptp in client-mode and modified
pptpd (poptop) to build high-performance pptp NAS.
There was many changes from initial submitted patch, most important are:
1. using rcu instead of read-write locks
2. using static bitmap instead of dynamically allocated
3. using vmalloc for memory allocation instead of BITS_PER_LONG + __get_free_pages
4. fixed many coding style issues
Thanks to Eric Dumazet.
Signed-off-by: Dmitry Kozlov <xeb@mail.ru> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net/sched: add ACT_CSUM action to update packets checksums
net/sched: add ACT_CSUM action to update packets checksums
ACT_CSUM can be called just after ACT_PEDIT in order to re-compute some
altered checksums in IPv4 and IPv6 packets. The following checksums are
supported by this patch:
- IPv4: IPv4 header, ICMP, IGMP, TCP, UDP & UDPLite
- IPv6: ICMPv6, TCP, UDP & UDPLite
It's possible to request in the same action to update different kind of
checksums, if the packets flow mix TCP, UDP and UDPLite, ...
An example of usage is done in the associated iproute2 patch.
Version 3 changes:
- remove useless goto instructions
- improve IPv6 hop options decoding
Version 2 changes:
- coding style correction
- remove useless arguments of some functions
- use stack in tcf_csum_dump()
- add tcf_csum_skb_nextlayer() to factor code
Signed-off-by: Gregoire Baron <baronchon@n7mm.org> Acked-by: jamal <hadi@cyberus.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Thu, 19 Aug 2010 06:10:45 +0000 (06:10 +0000)]
net: build_ehash_secret() and rt_bind_peer() cleanups
Now cmpxchg() is available on all arches, we can use it in
build_ehash_secret() and rt_bind_peer() instead of using spinlocks.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
Dan Carpenter [Thu, 19 Aug 2010 08:52:44 +0000 (08:52 +0000)]
qlge: pull NULL check ahead of dereference
There was a dereference before NULL check issue introduced in 1e213303d
"qlge: Add tx multiqueue support." I've pulled the NULL check of
"net_rsp" forward a couple lines to avoid that.
Also Ron Mercer says that the early exit should be above the index
write. ql_write_cq_idx(rx_ring);
Signed-off-by: Dan Carpenter <error27@gmail.com> Signed-off-by: Ron Mercer <ron.mercer@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Tobias Klauser [Wed, 18 Aug 2010 22:10:34 +0000 (22:10 +0000)]
ep93xx_eth: Use net_device_stats from struct net_device
struct net_device has its own struct net_device_stats member, so use
this one instead of a private copy in the ep93xx_priv struct. As the new
ndo_get_stats function would just return dev->stats we can omit it.
Signed-off-by: Tobias Klauser <tklauser@distanz.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
Fw can get stuck while holding pci semaphore. Driver will not
be able to perform fw initialization, without this lock.
Release semaphore forcefully in that case.
Signed-off-by: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com> Signed-off-by: Amit Kumar Salecha <amit.salecha@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Sony Chacko [Thu, 19 Aug 2010 05:08:31 +0000 (05:08 +0000)]
qlcnic: firmware initialization update
Cleanup legacy code which is not valid for Qlogic
CNA adapters.
Signed-off-by: Sony Chacko <sony.chacko@qlogic.com> Signed-off-by: Amit Kumar Salecha <amit.salecha@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Sony Chacko [Thu, 19 Aug 2010 05:08:27 +0000 (05:08 +0000)]
qlcnic: support anti mac spoofing
Administrator can configure to drop packet in transmit,
if it doesn't match interface mac address, in case of virtual function.
Signed-off-by: Sony Chacko <sony.chacko@qlogic.com> Signed-off-by: Amit Kumar Salecha <amit.salecha@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Rajesh Borundia [Thu, 19 Aug 2010 05:08:26 +0000 (05:08 +0000)]
qlcnic: configure offload setting on eswitch
Device is not capable of enabling/disabling offload setting per
port in case of Nic Partition.So offload settings needs to be
enabled/disabled per eswitch and it will affect all the function
on that eswitch.
Signed-off-by: Rajesh Borundia <rajesh.borundia@qlogic.com> Signed-off-by: Amit Kumar Salecha <amit.salecha@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Rajesh Borundia [Thu, 19 Aug 2010 05:08:25 +0000 (05:08 +0000)]
qlcnic: configure port on eswitch
o Nic partition capable devices has embedded switch, this needs to support
various features like external switch.
Signed-off-by: Rajesh Borundia <rajesh.borundia@qlogic.com> Signed-off-by: Amit Kumar Salecha <amit.salecha@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:40:54 +0000 (13:40 +0000)]
ixgbe: rewrite ethtool test to use standard config functions
This change makes it so that the ethtool loopback test uses the standard
ring configuration and allocation functions. As a result the loopback test
will be much more effective at testing core driver functionality.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:40:31 +0000 (13:40 +0000)]
ixgbe: update all DESC_ADV macros to accept a ring pointer
All of the DESC_ADV macros are currently needing the pointers to be
de-referenced before accessing the ring. Instead of having to add all of
the asterisks it is easier to just update the macro to expect a pointer to
the ring.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:40:06 +0000 (13:40 +0000)]
ixgbe: combine Rx into into ixgbe_configure_rx
The Rx init is currently split over ixgbe_configure, ixgbe_configure_rx,
and ixgbe_up_complete. Instead of leaving it split over 3 function it is
easier to consolidate them all into ixgbe_configure_rx.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:39:43 +0000 (13:39 +0000)]
ixgbe: pull all Tx init into ixgbe_configure_tx
The Tx init was spread out over ixgbe_configure, ixgbe_configure_tx, and
ixgbe_up_complete. This change combines all of that into the
ixgbe_configure_tx function in order to simplify the Tx init path.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:39:20 +0000 (13:39 +0000)]
ixgbe: move all GPIE register config into a single function
This change moves all GPIE register configuration into a single function.
The advantage of this is that we can avoid a number of unnecessary
read/modify/write cycles on the register.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:38:57 +0000 (13:38 +0000)]
ixgbe: Move virtualization config into a separate function
This change moves the configuration that was done in configure_rx into a
separate virtualization configuration function.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:38:34 +0000 (13:38 +0000)]
ixgbe: move all Rx DMA control register writes to one central location
This change moves all of the Rx DMA control register writes to one central
location. This should help to avoid accidentally overwriting existing
settings.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:38:11 +0000 (13:38 +0000)]
ixgbe: Move max frame size and Rx buffer length configuration into a function
This change consolidates all of the Rx max frame size and Rx buffer length
configuration into a single function.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:37:48 +0000 (13:37 +0000)]
ixgbe: remove redundant configuration of vmolr, rename generic variable
The vmolr is configured already in ixgbe_set_rx_mode for the PF so there is
no need to set it again in ixgbe_configure_rx.
Instead of using the variable name reg, it is easier to just rename it to
gcr_ext to reflect the register contents that the variable holds.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:37:21 +0000 (13:37 +0000)]
ixgbe: bump PS header size to 512 bytes
Bump the header size for packet split to 512 bytes since this makes the
best use of the 1k buffer that is allocated for any skb 512 bytes or
smaller.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:36:49 +0000 (13:36 +0000)]
ixgbe: combine accesses to FCTRL register into ixgbe_set_rx_mode
We are accessing the FCTRL register in multiple spots in the init path and
we can simplify things by combining the configuration all into
ixgbe_set_rx_mode.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:36:27 +0000 (13:36 +0000)]
ixgbe: pull PSRTYPE configuration into a separate function
The configuration of PSRTYPE was being done conditionally on if packet
split is enabled or not. It can be configured always since it will not
have any effect when packet split is not enabled.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:36:05 +0000 (13:36 +0000)]
ixgbe: pull ring configuration into it's own function
These changes add ixgbe_configure_rx_ring which is used to setup the base
function pointers for the ring.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:35:41 +0000 (13:35 +0000)]
ixgbe: consolidate all setting of MRQC into one function
This change simplifies the configuration of MRQC by consolidating the
setting of it into one function. As such the register is no longer set in
multiple places which should make any future changes easier to work with.
In addition we can combine RSS related register writes into the call since
enabling all of those bits without enabling RSS itself in MRQC should have
no effect.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:35:12 +0000 (13:35 +0000)]
ixgbe: move Tx ring configuration into a separate function
This patch moves the Tx ring configuration into a separate function. In
addition the function drops the setting of the head writeback RO bit since
head writeback is no longer used within ixgbe.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:34:50 +0000 (13:34 +0000)]
ixgbe: move configuration of the MTQC register into it's own function
This patch moves the configuration of the MTQC register into it's own
function call similar to ixgbe_setup_mrqc.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:34:27 +0000 (13:34 +0000)]
ixgbe: combine two modifications of TXDCTL into one
In ixgbe_up_complete we were doing a read-modify-write of TXDCTL followed
by another one just a few lines further down. Instead of performing two
separate read-modify-writes it would make more sense to combine the two
into one.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:34:04 +0000 (13:34 +0000)]
ixgbe: move setting of GSO size for 82598 into ixgbe_configure_dcb
We are unnecessarily modifying the GSO size for all HW when we don't need
to. The code can be simplified by moving the check for DCB and the
adjustment of the GSO size for 82598 into ixgbe_configure_dcb.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Thu, 19 Aug 2010 13:33:41 +0000 (13:33 +0000)]
ixgbe: remove redundant DMA alignment code
This patch removes the redundant DMA alignment code from the Rx buffer
allocation path. This code is no longer necessary since all x86 buffers
are now DMA aligned due to recent changes to NET_IP_ALIGN and NET_SKB_PAD.
It also moves the setting of the Rx queue value into the allocation path
since it is more likely that the queue mapping will still be in the cache
at the time of allocation. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Don Skidmore [Thu, 19 Aug 2010 13:33:16 +0000 (13:33 +0000)]
ixgbe: cleanup ixgbe_get_drvinfo to be extra careful with buffer boundaries
Make the code in ixgbe_get_drvinfo more protected against buffer overflow
boundaries by using snprintf and sizeof with snprintf.
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Bruce Allan [Thu, 19 Aug 2010 22:48:52 +0000 (15:48 -0700)]
e1000e: don't check for alternate MAC addr on parts that don't support it
From: Bruce Allan <bruce.w.allan@intel.com>
The alternate MAC address feature is only supported by 80003ES2LAN and
82571 LOMs as well as a couple 82571 mezzanine cards. Checking for an
alternate MAC address on other parts can fail leading to the driver not
able to load. This patch limits the check for an alternate MAC address
to be done only for parts that support the feature.
This issue has been around since support for the feature was introduced
to the e1000e driver in 2.6.34.
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com> Reported-by: Fabio Varesano <fax8@users.sourceforge.net> Cc: stable@kernel.org Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Bruce Allan [Thu, 19 Aug 2010 22:48:30 +0000 (15:48 -0700)]
e1000e: disable ASPM L1 on 82573
On the e1000-devel mailing list, Nils Faerber reported latency issues with
the 82573 LOM on a ThinkPad X60. It was found to be caused by ASPM L1;
disabling it resolves the latency. The issue is present in kernels back
to 2.6.34 and possibly 2.6.33.
Reported-by: Nils Faerber <nils.faerber@kernelconcepts.de> Signed-off-by: Bruce Allan <bruce.w.allan@intel.com> Cc: stable@kernel.org Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
projects / linux-beck.git / log