Followup of commit b178bb3d (net: reorder struct sock fields)

Optimize INET input path a bit further, by :

1) moving sk_refcnt close to sk_lock.

This reduces number of dirtied cache lines by one on 64bit arches (and
64 bytes cache line size).

2) moving inet_daddr & inet_rcv_saddr at the beginning of sk

(same cache line than hash / family / bound_dev_if / nulls_node)

This reduces number of accessed cache lines in lookups by one, and dont
increase size of inet and timewait socks.
inet and tw sockets now share same place-holder for these fields.

Before patch :

offsetof(struct sock, sk_refcnt) = 0x10
offsetof(struct sock, sk_lock) = 0x40
offsetof(struct sock, sk_receive_queue) = 0x60
offsetof(struct inet_sock, inet_daddr) = 0x270
offsetof(struct inet_sock, inet_rcv_saddr) = 0x274

After patch :

offsetof(struct sock, sk_refcnt) = 0x44
offsetof(struct sock, sk_lock) = 0x48
offsetof(struct sock, sk_receive_queue) = 0x68
offsetof(struct inet_sock, inet_daddr) = 0x0
offsetof(struct inet_sock, inet_rcv_saddr) = 0x4

compute_score() (udp or tcp) now use a single cache line per ignored
item, instead of two.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Use helper functions to hide all direct accesses, especially writes,
to dst_entry metrics values.

This will allow us to:

1) More easily change how the metrics are stored.

2) Implement COW for metrics.

In particular this will help us put metrics into the inetpeer
cache if that is what we end up doing.  We can make the _metrics
member a pointer instead of an array, initially have it point
at the read-only metrics in the FIB, and then on the first set
grab an inetpeer entry and point the _metrics member there.
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>

drivers/net/can/slcan.c: In function 'slcan_open':
drivers/net/can/slcan.c:568: error: dereferencing pointer to incomplete type
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

Conflicts:
	drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
	net/llc/af_llc.c

Make sure sysctl_tcp_cookie_size is read once in
tcp_cookie_size_check(), or we might return an illegal value to caller
if sysctl_tcp_cookie_size is changed by another cpu.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: William Allen Simpson <william.allen.simpson@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

sysctl_tcp_tso_win_divisor might be set to zero while one cpu runs in
tcp_tso_should_defer(). Make sure we dont allow a divide by zero by
reading sysctl_tcp_tso_win_divisor exactly once.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

In order to set LRO on ehea, the user must set a module parameter, which
is not the standard way to do so. This patch adds a way to set LRO using
the ethtool tool.
Signed-off-by: Breno Leitao <leitao@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Rather than printing the message to the log, use a mib counter to keep
track of the count of occurences of time wait bucket overflow.  Reduces
spam in logs.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

x25 does not decrement the network device reference counts on module unload.
Thus unregistering any pre-existing interface after unloading the x25 module
hangs and results in

 unregister_netdevice: waiting for tap0 to become free. Usage count = 1

This patch decrements the reference counts of all interfaces in x25_link_free,
the way it is already done in x25_link_device_down for NETDEV_DOWN events.
Signed-off-by: Apollon Oikonomopoulos <apollon@noc.grnet.gr>
Signed-off-by: David S. Miller <davem@davemloft.net>

Regarding  benet be_cmd_multicast_set() function, now using
netdev_for_each_mc_addr() helper for mac address copy, but
when copying to req->mac[] did not increase of the index.

Cc: Sathya Perla <sathyap@serverengines.com>
Cc: Subbu Seetharaman <subbus@serverengines.com>
Cc: Sarveshwar Bandi <sarveshwarb@serverengines.com>
Cc: Ajit Khaparde <ajitk@serverengines.com>
Signed-off-by: Joe Jin <joe.jin@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Using the SOCK_DGRAM enum results in
"net-pf-2-proto-SOCK_DGRAM-type-115", so use the numeric value like it
is done in net/dccp.
Signed-off-by: Michal Marek <mmarek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>

We need to drop the mutex and do a dev_put, so set an error code and break like
the other paths, instead of returning directly.
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Annotate hisax_pci_tbl as '__used' to fix following warning:

  CC      drivers/isdn/hisax/config.o
drivers/isdn/hisax/config.c:1920: warning: ‘hisax_pci_tbl’ defined but not used
Signed-off-by: Namhyung Kim <namhyung@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

It is introduced in:
        commit 0e3125c7
        Author: Neil Horman <nhorman@tuxdriver.com>
        Date:   Tue Nov 16 10:26:47 2010 -0800

        packet: Enhance AF_PACKET implementation to not require high order contiguous memory allocation (v4)
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Some arches don't need flush_dcache_page(), and don't implement it, so
we can eliminate pgv_to_page() calls on those arches.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Avoid some atomic ops on dst refcount, calling dev_queue_xmit_nit()
after skb_dst_drop() in dev_hard_start_xmit().

When queueing a packet into af_packet socket, we drop dst anyway.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

sk_run_filter() doesnt write on skb, change its prototype to reflect
this.

Fix two af_packet comments.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch adds VLAN hardware support for Rhine chips.

The driver uses up to 3 additional bytes of buffer space when extracting
802.1Q headers; PKT_BUF_SZ should still be sufficient.

The initial code was provided by David Lv. I reworked it to use standard
kernel facilities. Coding style clean up mostly follows via-velocity.

Adapted to new interface for VLAN acceleration (per request of Jesse Gross).
Signed-off-by: David Lv <DavidLv@viatech.com.cn>
Signed-off-by: Roger Luethi <rl@hellgate.ch>

 drivers/net/via-rhine.c |  326 +++++++++++++++++++++++++++++++++++++++++++++--
 1 files changed, 312 insertions(+), 14 deletions(-)
Signed-off-by: David S. Miller <davem@davemloft.net>

Le dimanche 05 décembre 2010 à 09:19 +0100, Eric Dumazet a écrit :

> Hmm..
>
> If somebody can explain why RTNL is held in arp_ioctl() (and therefore
> in arp_req_delete()), we might first remove RTNL use in arp_ioctl() so
> that your patch can be applied.
>
> Right now it is not good, because RTNL wont be necessarly held when you
> are going to call arp_invalidate() ?

While doing this analysis, I found a refcount bug in llc, I'll send a
patch for net-2.6

Meanwhile, here is the patch for net-next-2.6

Your patch then can be applied after mine.

Thanks

[PATCH] net: RCU conversion of dev_getbyhwaddr() and arp_ioctl()

dev_getbyhwaddr() was called under RTNL.

Rename it to dev_getbyhwaddr_rcu() and change all its caller to now use
RCU locking instead of RTNL.

Change arp_ioctl() to use RCU instead of RTNL locking.

Note: this fix a dev refcount bug in llc
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Le dimanche 05 décembre 2010 à 12:23 +0100, Eric Dumazet a écrit :
> Le dimanche 05 décembre 2010 à 09:19 +0100, Eric Dumazet a écrit :
>
> > Hmm..
> >
> > If somebody can explain why RTNL is held in arp_ioctl() (and therefore
> > in arp_req_delete()), we might first remove RTNL use in arp_ioctl() so
> > that your patch can be applied.
> >
> > Right now it is not good, because RTNL wont be necessarly held when you
> > are going to call arp_invalidate() ?
>
> While doing this analysis, I found a refcount bug in llc, I'll send a
> patch for net-2.6

Oh well, of course I must first fix the bug in net-2.6, and wait David
pull the fix in net-next-2.6 before sending this rcu conversion.

Note: this patch should be sent to stable teams (2.6.34 and up)

[PATCH net-2.6] llc: fix a device refcount imbalance

commit abf9d537 (llc: add support for SO_BINDTODEVICE) added one
refcount imbalance in llc_ui_bind(), because dev_getbyhwaddr() doesnt
take a reference on device, while dev_get_by_index() does.

Fix this using RCU locking. And since an RCU conversion will be done for
2.6.38 for dev_getbyhwaddr(), put the rcu_read_lock/unlock exactly at
their final place.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: stable@kernel.org
Cc: Octavian Purdila <opurdila@ixiacom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Use the macros already provided by kernel.h file.
Signed-off-by: Thiago Farina <tfransosi@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

If we break the loop when there are still skbs in tq and no skb in
rq, the skbs will be left in txq until new skbs are enqueued into rq.
In rare cases, no new skb is queued, then these skbs will stay in rq
forever.

After this patch, if tq isn't empty when we break the loop, we goto
resched directly.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca>
Signed-off-by: David S. Miller <davem@davemloft.net>

The dev field of ingress queue is forgot to initialized, then NULL
pointer dereference happens in qdisc_alloc().

Move inits of tx queues to netif_alloc_netdev_queues().
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The bug has to do with boundary checks on the initial receive window.
If the initial receive window falls between init_cwnd and the
receive window specified by the user, the initial window is incorrectly
brought down to init_cwnd. The correct behavior is to allow it to
remain unchanged.
Signed-off-by: Nandita Dukkipati <nanditad@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Fix the calculation of the inexact hash-based MAC address filter.
It's 64 bits but current code is missing a ULL.  Results in filtering out
some legitimate packets.
Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch adds support for serial/USB-serial CAN adapters implementing the
LAWICEL ASCII protocol for CAN frame transport over serial lines.

The driver implements the SLCAN line discipline and is heavily based on the
slip.c driver. Therefore the code style remains similar to slip.c to be able
to apply changes of the SLIP driver to the SLCAN driver easily.

For more details see the slcan Kconfig entry.
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Chas Williams <chas@cmf.nrl.navy.mil>
Cc: linux-atm-general@lists.sourceforge.net
Signed-off-by: David S. Miller <davem@davemloft.net>

Rearrange pr_fmt so it compiles.
Signed-off-by: Sjur Braendeland <sjur.brandeland@stericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Call netif_napi_{add,del}() on the NAPI contexts in the new and
old channels, respectively.

Since efx_init_napi() cannot fail, make its return type void.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

If we are using a legacy interrupt, our IRQ may be shared and our
interrupt handler may be called even though interrupts are disabled on
the NIC. When we change ring sizes, we reallocate the event queue and
the interrupt handler may use an invalid pointer when called for
another device's interrupt.

Maintain a legacy_irq_enabled flag and test that at the top of the
interrupt handler.  Note that this problem results from the need to
work around broken INT_ISR0 reads, and does not affect the legacy
interrupt handler for Falcon A1.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Ensure that cmsg->cmsg_type value is valid for qpolicy
that is currently in use.
Signed-off-by: Tomasz Grobelny <tomasz@grobelny.oswiecenia.net>
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>

This patch adds a generic infrastructure for policy-based dequeueing of
TX packets and provides two policies:
 * a simple FIFO policy (which is the default) and
 * a priority based policy (set via socket options).
Both policies honour the tx_qlen sysctl for the maximum size of the write
queue (can be overridden via socket options).

The priority policy uses skb->priority internally to assign an u32 priority
identifier, using the same ranking as SO_PRIORITY. The skb->priority field
is set to 0 when the packet leaves DCCP. The priority is supplied as ancillary
data using cmsg(3), the patch also provides the requisite parsing routines.
Signed-off-by: Tomasz Grobelny <tomasz@grobelny.oswiecenia.net>
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>

This reverts commit 539995d1.

As reported by Stephen Rothwell, this breaks the build.
Signed-off-by: David S. Miller <davem@davemloft.net>

struct net_device has its own struct net_device_stats member, so use
this one instead of a private copy in struct net_local.

Note: This patch was not even compile tested.
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

xemaclite_get_stats() just returns dev->stats so we can leave it out
alltogether and let dev_get_stats() do the job.
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

am79c961_getstats() just returns dev->stats so we can leave it out
alltogether and let dev_get_stats() do the job.
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Acked-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>

Fixes a recent bug on the patch (c6ecf39a)
that disabled the laser on ifconfig down.  Compilers were seeing a enum
mismatch.

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>