tg3_get_invariants(), among other things, discovers whether or not
the device is MSI-X capable and how many interrupts it supports.
This discovery needs to happen before registering NAPI instances with
netdev.  This patch moves the code block that calls napi_add later in
tg3_init_one() so that tg3_get_invariants() has a chance to run first.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch gives all non-zero MSIX vectors their own NAPI handler.  This
will make NAPI handling for those vectors slightly more efficient.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

By default, the 5717 (and future chips) break up PCIe DMA packets across
cacheline boundaries.  This isn't necessary on x86.  This patch
selectively loosens the restriction.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The A0 revision of the 5717 has problems with short packet fragments.
It needs to use the tg3_start_xmit_dma_bug() routine.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The 5717 sets up TSO slightly differently in the transmit path.  It
looks like this method will be the new way of doing things.  This patch
defines a flag to indicate this.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch consolidates the TSO capability discovery code into its own
code block.  The code that decides whether or not to allow TSO is then
cleaned up.  Finally, the patch consolidates all MSI and MSIX
capability code into a single code block.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

We need room for another TSO flag and it would be most efficient if it
resided in tg3_flags2.  This patch moves the TG3_FLG2_PROTECTED_NVRAM
to tg3_flags3 to make room.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch converts tg3_start_xmit_dma_bug() to accomodate multiple NAPI
instances.  This is prep work for a later patch in this series.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch avoids reprogramming the RCB NIC addresses for all 5755 and
later devices.  The address is incorrect for 5717 devices and should be
correct by default for all other affected devices.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch adds the 5717 phy ID.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Recent changes in the TX error propagation require additional checking
and masking of values returned from hard_start_xmit(), mainly to
separate cases where skb was consumed. This aim can be simplified by
changing the order of NETDEV_TX and NET_XMIT codes, because the latter
are treated similarly to negative (ERRNO) values.

After this change much simpler dev_xmit_complete() is also used in
sch_direct_xmit(), so it is moved to netdevice.h.

Additionally NET_RX definitions in netdevice.h are moved up from
between TX codes to avoid confusion while reading the TX comment.
Signed-off-by: Jarek Poplawski <jarkao2@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drop the version parts not needed for in-tree driver
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Use device id number directly accompany with
comment rather then a #define
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Check the return value of ndo_select_queue(). If the value isn't smaller
than the real_num_tx_queues, print a warning message, and reset it to zero.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
----
Signed-off-by: David S. Miller <davem@davemloft.net>

Changing MAINTAINERS for netxen nic driver.
Signed-off-by: Amit Kumar Salecha <amit.salecha@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

My last commit introduced an typo causing the
compat_ioctl function to do nothing useful.
The obvious way for an ioctl function to work
is to look at the command, not the argument first.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Taken from socketcan-svn, fixed remaining todos, cleaned up, tested with a
phyCORE-MPC5200B-IO and a custom board.
Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
Cc: Wolfgang Grandegger <wg@grandegger.com>
Cc: Grant Likely <grant.likely@secretlab.ca>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

tx_bytes value must be updated by skb length before skb is freed.
Signed-off-by: Ursula Braun <ursula.braun@de.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The cu3088-driver used as common base for lcs- and ctcm-devices
makes it difficult to assign the appropriate driver to an lcs-device
or a ctcm-device. This patch eliminates the cu3088-driver and thus
the root device "cu3088". Path /sys/devices/cu3088 is replaced with
the pathes /sys/devices/lcs and /sys/devices/ctcm.

Patch is based on a proposal from Cornelia Huck.

Cc: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Ursula Braun <ursula.braun@de.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

State transition to DEV_STATE_STOPPED indicates all outstanding I/O has
finished. Add wait queue to wait for this state.
Signed-off-by: Frank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: Ursula Braun <ursula.braun@de.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

If iucv_work_queue is not empty during kernel freeze, a kernel panic
occurs. This suspend-patch adds flushing of the work queue for
pending connection requests and severing of remaining pending
connections.
Signed-off-by: Ursula Braun <ursula.braun@de.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

While investigating for network latencies, I found inet_getid() was a
contention point for some workloads, as inet_peer_idlock is shared
by all inet_getid() users regardless of peers.

One way to fix this is to make ip_id_count an atomic_t instead
of __u16, and use atomic_add_return().

In order to keep sizeof(struct inet_peer) = 64 on 64bit arches
tcp_ts_stamp is also converted to __u32 instead of "unsigned long".
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

When handling large number of netdevices, inet6_dump_addr()
is very slow because it has O(N^2) complexity.

Instead of scanning one single list, we can use the NETDEV_HASHENTRIES
sub lists of the dev_index hash table, and RCU lookups.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The first "node" is supposed to be the cursor used in the for_each.

The second "node" is ment literally and should not be macro expanded:
it's the name of the hlist_node field from the inet_bind_bucket.

This currently works because when inet_bind_bucket_for_each is called
it's argument is still "node".
Signed-off-by: Lucian Adrian Grijincu <lgrijincu@ixiacom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Stephen Hemminger a écrit :
> On Thu, 12 Nov 2009 15:11:36 +0100
> Eric Dumazet <eric.dumazet@gmail.com> wrote:
>
>> When handling large number of netdevices, inet_dump_ifaddr()
>> is very slow because it has O(N^2) complexity.
>>
>> Instead of scanning one single list, we can use the NETDEV_HASHENTRIES
>> sub lists of the dev_index hash table, and RCU lookups.
>>
>> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
>
> You might be able to make RCU critical section smaller by moving
> it into loop.
>

Indeed. But we dump at most one skb (<= 8192 bytes ?), so rcu_read_lock
holding time is small, unless we meet many netdevices without
addresses. I wonder if its really common...

Thanks

[PATCH net-next-2.6] ipv4: speedup inet_dump_ifaddr()

When handling large number of netdevices, inet_dump_ifaddr()
is very slow because it has O(N2) complexity.

Instead of scanning one single list, we can use the NETDEV_HASHENTRIES
sub lists of the dev_index hash table, and RCU lookups.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch pairs similar-numbered Rx and Tx queues onto a single
MSI-X vector.  For example, Tx queue 0 and Rx queue 0's interrupt
with be ethX-RxTx-0.  This allows for more efficient cleanup, since
fewer interrupts will be firing during device operation.  It also
helps with a cleaner CPU affinity for IRQ affinity.
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch makes it so that we only recycle pages when they are from the
local NUMA node.  Non-local pages are freed and replaced with locally
allocated pages.
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>

We were previously only checking the first tx ring to see if it had any
packets in it when the link when down.  However we should be checking all
of the rings so this patch makes it so that all of the rings are now being
checked.
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>

This patch removes unused variables total_tx_bytes, total_tx_packets,
total_rx_bytes, and total_rx_packets from the adapter struct.
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>

This patch does some refactoring work that I felt was needed after reviewing
the changes recently submitted relating to the replacement of net_stats with
netdev->stats.

This patch essentially creates two different collections of stats.  The
first handles the adapter specific states and is stored in gstring_stats,
and the second is for netdev specific stats and is stored in
gstring_net_stats.
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>

This patch makes it so that nics such as 82576 and newer can support more
hardware queues when there are more than 4 cpus by combining a tx/rx queue
pair onto one interrupt so that 8 queue pairs can be supported and thus
allow for more queues.
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>

Current code is quite large and making igb_probe difficult to read.
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>

Change the type for the ring size values to u16 and use min/max_t instead of
min/max.
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>

To fix the bug of checking on signed return value using unsigned statement.
Thanks Roel Kluin for digging out it.
Signed-off-by: Roel Kluin <roel.kluin@gmail.com>
Signed-off-by: Wan ZongShun <mcuos.com@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

We need to use next_det_device_rcu() in RCU protected section.

We also can avoid in_dev_get()/in_dev_put() overhead (code size mainly)
in rcu_read_lock() sections.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>