Testing xmit_more support with netperf and connected UDP sockets,
I found strange dst refcount false sharing.
Current handling of IFF_XMIT_DST_RELEASE is not optimal.
Dropping dst in validate_xmit_skb() is certainly too late in case
packet was queued by cpu X but dequeued by cpu Y
The logical point to take care of drop/force is in __dev_queue_xmit()
before even taking qdisc lock.
As Julian Anastasov pointed out, need for skb_dst() might come from some
packet schedulers or classifiers.
This patch adds new helper to cleanly express needs of various drivers
or qdiscs/classifiers.
Drivers that need skb_dst() in their ndo_start_xmit() should call
following helper in their setup instead of the prior :
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
->
netif_keep_dst(dev);
Instead of using a single bit, we use two bits, one being
eventually rebuilt in bonding/team drivers.
The other one, is permanent and blocks IFF_XMIT_DST_RELEASE being
rebuilt in bonding/team. Eventually, we could add something
smarter later.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
The Linux kernel coding style guidelines suggest not using typedefs
for structure types. This patch gets rid of the typedefs for
fr_hdr and pvc_device. Also, the names of the structs are changed to
drop the _t, to make the name look less typedef-like.
The following Coccinelle semantic patch detects the case fr_hdr and a
similar one detects the case for pvc_device.
@tn1@
type td;
@@
typedef struct { ... } td;
@script:python tf@
td << tn1.td;
tdres;
@@
coccinelle.tdres = td;
@@
type tn1.td;
identifier tf.tdres;
@@
-typedef
struct
+ tdres
{ ... }
-td
;
@@
type tn1.td;
identifier tf.tdres;
@@
-td
+ struct tdres
Signed-off-by: Himangi Saraogi <himangi774@gmail.com>
Acked-by: Julia Lawall <julia.lawall@lip6.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
Replace usage of random_ether_addr() with eth_hw_addr_random()
to set addr_assign_type correctly to NET_ADDR_RANDOM.
Change the trivial cases.
v2: adapt to renamed eth_hw_addr_random()
Signed-off-by: Danny Kukawka <danny.kukawka@bisect.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
After the last patch, We are left in a state in which only drivers calling
ether_setup have IFF_TX_SKB_SHARING set (we assume that drivers touching real
hardware call ether_setup for their net_devices and don't hold any state in
their skbs. There are a handful of drivers that violate this assumption of
course, and need to be fixed up. This patch identifies those drivers, and marks
them as not being able to support the safe transmission of skbs by clearning the
IFF_TX_SKB_SHARING flag in priv_flags
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Karsten Keil <isdn@linux-pingi.de>
CC: "David S. Miller" <davem@davemloft.net>
CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: Patrick McHardy <kaber@trash.net>
CC: Krzysztof Halasa <khc@pm.waw.pl>
CC: "John W. Linville" <linville@tuxdriver.com>
CC: Greg Kroah-Hartman <gregkh@suse.de>
CC: Marcel Holtmann <marcel@holtmann.org>
CC: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use pr_fmt, pr_<level> and netdev_<level> as appropriate.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Force dev_alloc_name() to be called from register_netdevice() by
dev_get_valid_name(). That allows to remove multiple explicit
dev_alloc_name() calls.
The possibility to call dev_alloc_name in advance remains.
This also fixes veth creation regresion caused by
84c49d8c3e
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
cleanup patch.
Use new __packed annotation in drivers/net/
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Added a space separating some if keywords from the following
parenthesis to conform to the CodingStyle.
Signed-off-by: Rudy Matela <rudy.matela@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is the result of an automatic spatch transformation to convert
all ndo_start_xmit() return values of 0 to NETDEV_TX_OK.
Some occurences are missed by the automatic conversion, those will be
handled in a seperate patch.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
One point of contention in high network loads is the dst_release() performed
when a transmited skb is freed. This is because NIC tx completion calls
dev_kree_skb() long after original call to dev_queue_xmit(skb).
CPU cache is cold and the atomic op in dst_release() stalls. On SMP, this is
quite visible if one CPU is 100% handling softirqs for a network device,
since dst_clone() is done by other cpus, involving cache line ping pongs.
It seems right place to release dst is in dev_hard_start_xmit(), for most
devices but ones that are virtual, and some exceptions.
David Miller suggested to define a new device flag, set in alloc_netdev_mq()
(so that most devices set it at init time), and carefuly unset in devices
which dont want a NULL skb->dst in their ndo_start_xmit().
List of devices that must clear this flag is :
- loopback device, because it calls netif_rx() and quoting Patrick :
"ip_route_input() doesn't accept loopback addresses, so loopback packets
already need to have a dst_entry attached."
- appletalk/ipddp.c : needs skb->dst in its xmit function
- And all devices that call again dev_queue_xmit() from their xmit function
(as some classifiers need skb->dst) : bonding, vlan, macvlan, eql, ifb, hdlc_fr
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Base versions handle constant folding now.
Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Also remove unneeded last_rx update from Synclink drivers.
Synclink part mostly by Stephen Hemminger.
Signed-off-by: Krzysztof Hałasa <khc@pm.waw.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
For killing directly reference of netdev->priv, use netdev->ml_priv to replace it.
Because the private pvc data comes from add_pvc() and can't be allocated in
alloc_netdev().
Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com>
Acked-by: Krzysztof Halasa <khc@pm.waw.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove no longer needed struct pvc_desc in FR code.
Requires "WAN: convert drivers to use built-in netdev_stats" patch.
Signed-off-by: Krzysztof Hałasa <khc@pm.waw.pl>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
There is no point in using separate net_device_stats structs when
the one in struct net_device is present. Compiles.
Signed-off-by: Krzysztof Hałasa <khc@pm.waw.pl>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
Commit 4c13eb6657 ([ETH]: Make
eth_type_trans set skb->dev like the other *_type_trans) removed
skb->dev assignment from hdlc_fr.c:fr_rx(). Unfortunately it was also
needed for cases other than eth_type_trans().
Adding it back.
It's quite serious and may be a security risk as it causes a wrong
input interface indication (the physical hdlcX instead of logical
pvcX). Probably -stable class fix.
Signed-off-by: Krzysztof Halasa <khc@pm.waw.pl>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
The local variable "prefix" is never used anymore, and the content of
this string appears a bit later, directly in a call to "alloc_netdev"
after doing exactly the same if/else test. So there seems to be no
point keeping those 4 lines anymore.
Signed-off-by: Cédric Augonnet <cedric.augonnet@ens-lyon.org>
Signed-off-by: Krzysztof Hałasa <khc@pm.waw.pl>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
Generic HDLC now uses random_ether_addr() for generating MAC addresse
for Ethernet-alike interfaces.
Signed-off-by: Krzysztof Halasa <khc@pm.waw.pl>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
So that it is also an offset from skb->head, reduces its size from 8 to 4 bytes
on 64bit architectures, allowing us to combine the 4 bytes hole left by the
layer headers conversion, reducing struct sk_buff size to 256 bytes, i.e. 4
64byte cachelines, and since the sk_buff slab cache is SLAB_HWCACHE_ALIGN...
:-)
Many calculations that previously required that skb->{transport,network,
mac}_header be first converted to a pointer now can be done directly, being
meaningful as offsets or pointers.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For the common, open coded 'skb->nh.raw = skb->data' operation, so that we can
later turn skb->nh.raw into a offset, reducing the size of struct sk_buff in
64bit land while possibly keeping it as a pointer on 32bit.
This one touches just the most simple case, next will handle the slightly more
"complex" cases.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
One less thing for drivers writers to worry about.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Switching HDLC devices from Ethernet-framing mode caused stale ethernet
function assignments within net_device.
Signed-off-by: Krzysztof Halasa <khc@pm.waw.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch enables building of individual WAN protocol support
routines (parts of generic HDLC) as separate modules.
All protocol-private definitions are moved from hdlc.h file
to protocol drivers. User-space interface and interface
between generic HDLC and underlying low-level HDLC drivers
are unchanged.
Signed-off-by: Krzysztof Halasa <khc@pm.waw.pl>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch converts generic HDLC (and WAN drivers using it) from
hdlc_set_carrier() to netif_dormant*() interface.
WAN hardware drivers should now use netif_carrier_on|off() like
other network drivers.
Signed-off-by: Krzysztof Halasa <khc@pm.waw.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
As we are currently unable to fix the problem with carrier and protocol
state signaling in net core I've to disable netif_carrier_off()
calls used by WAN protocol drivers. The attached patch should make
them working again.
The remaining netif_carrier_*() calls in hdlc_fr.c are fine as they
don't touch the physical device.
Signed-off-by: Krzysztof Halasa <khc@pm.waw.pl>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This patch contains possible cleanups including the following:
- make needlessly global code static
- #if 0 the following unused global function:
- sdladrv.c: sdla_intde
- remove the following unused global variable:
- lmc_media.c: lmc_t1_cables
- remove the following unneeded EXPORT_SYMBOL's:
- cycx_drv.c: cycx_inten
- sdladrv.c: sdla_inten
- sdladrv.c: sdla_intde
- sdladrv.c: sdla_intack
- sdladrv.c: sdla_intr
- syncppp.c: sppp_input
- syncppp.c: sppp_change_mtu
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>
The attached patch updates generic HDLC to version 1.18.
FR Cisco LMI production-tested. Please apply to Linux 2.6. Thanks.
Changes:
- doc updates
- added Cisco LMI support to Frame-Relay code
- cleaned hdlc_fr.c a bit, removed some orphaned #defines etc.
- fixed a problem with non-functional LMI in FR DCE mode.
- changed diagnostic messages to better conform to FR standards
- all protocols: information about carrier changes (DCD line) is now
printed to kernel logs.
Signed-Off-By: Krzysztof Halasa <khc@pm.waw.pl>
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
