On current net-next-2.6, when Linux receives ICMP Type: 3, Code: 4
(Destination unreachable (Fragmentation needed)),

  icmp_unreach
    -> ip_rt_frag_needed
         (peer->pmtu_expires is set here)
    -> tcp_v4_err
         -> do_pmtu_discovery
              -> ip_rt_update_pmtu
                   (peer->pmtu_expires is already set,
                    so check_peer_pmtu is skipped.)
                   -> check_peer_pmtu

check_peer_pmtu is skipped and MTU is not updated.

To fix this, let check_peer_pmtu execute unconditionally.
And some minor fixes
1) Avoid potential peer->pmtu_expires set to be zero.
2) In check_peer_pmtu, argument of time_before is reversed.
3) check_peer_pmtu expects peer->pmtu_orig is initialized as zero,
   but not initialized.
Signed-off-by: NHiroaki SHIMODA <shimoda.hiroaki@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This function no longer exists.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We will change the externally visible APIs next.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

To start doing these conversions, we need to add some temporary
flow4_* macros which will eventually go away when all the protocol
code paths are changed to work on AF specific flowi objects.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is just a shorthand which will help in passing around AF
specific flow structures as generic ones.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now we have struct flowi4, flowi6, and flowidn for each address
family.  And struct flowi is just a union of them all.

It might have been troublesome to convert flow_cache_uli_match() but
as it turns out this function is completely unused and therefore can
be simply removed.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Create two sets of port member accessors, one set prefixed by fl4_*
and the other prefixed by fl6_*

This will let us to create AF optimal flow instances.

It will work because every context in which we access the ports,
we have to be fully aware of which AF the flowi is anyways.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This will be used when we have seperate flowi types.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Pull out the AF independent members of struct flowi into a
new struct flowi_common
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

I intend to turn struct flowi into a union of AF specific flowi
structs.  There will be a common structure that each variant includes
first, much like struct sock_common.

This is the first step to move in that direction.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is only one caller of xfrm_bundle_ok(), and that always passes these
parameters as NULL.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Move tos, scope, proto, and flags to the beginning of
the structure.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The idea here is this minimizes the number of places one has to edit
in order to make changes to how flows are defined and used.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Merge branch 'for-davem' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next-2.6

The PFC configuration is not cleared until the device is reset. This
has not been a problem because setting DCB attributes forced a
hardware reset. Now that we no longer require this reset to occur
PFC remains configured even after being disabled until the
device is reset.

This removes a goto in the PFC hardware set routines for 82598 and
82599 devices that was short circuiting the clear.
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Implemented ixgbe_ndo_set_vf_bw function which is being used by iproute2
tool. In addition, updated ixgbe_ndo_get_vf_config function to show the
actual rate limit to the user.

The rate limitation can be configured only when the link is up and the
link speed is 10Gb.
The rate limit value can be 0 or ranged between 11 and actual link
speed measured in Mbps. A value of '0' disables the rate limit for
this specific VF.

iproute2 usage will be 'ip link set ethX vf Y rate Z'.
After the command is made, the rate will be changed instantly.
To view the current rate limit, use 'ip link show ethX'.

The rates will be zeroed only upon driver reload or a link speed change.

This feature is being supported by 82599 and X540 devices.
Signed-off-by: NLior Levy <lior.levy@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

DCB provides a guaranteed bandwidth in the case with 0%
bandwidth then no bandwidth is guaranteed. However the
traffic class should still be able to transmit traffic.
For this to work the traffic class must be given the
minimum credits required to send a frame.
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

VF Free Running Timer register name missing an F.
Signed-off-by: NEmil Tantilov <emil.s.tantilov@intel.com>
Acked-by: NGreg Rose <gregory.v.rose@intel.com>
Tested-by: NEvan Swanson <evan.swanson@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This change updates the PHY setup code to support 100Mbps capable PHYs
as well as 10G and 1Gbps.
Signed-off-by: NEmil Tantilov <emil.s.tantilov@intel.com>
Tested-by: NStephen Ko <stephen.s.ko@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The VF mailbox polling for acks and messages would reset the timer to zero
on a timeout. Under heavy load a timeout may actually occur without being
the result of an error and when this occurs it is not practical to perform
a full VF driver reset on every message timeout. Instead, just return an
error (which is already done) and the VF driver will have an opportunity
to retry the operation.
Signed-off-by: NEmil Tantilov <emil.s.tantilov@intel.com>
Acked-by: NGreg Rose <gregory.v.rose@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

DCB settings are cleared in the hardware across link events
during ifup ixgbe reprograms the hardware for DCB if it is
enabled. Now that we have two modes CEE or IEEE we need to
use the correct set of configuration data.

This patch checks the dcbx_cap bits and then enables the
device in the correct mode.
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch adds support to use the priority assignment
table in the ieee_ets structure to map priorities to
traffic classes. Previously ixgbe only supported a
1:1 mapping. Now we can enable and disable hardware
DCB support when multiple traffic classes are actually
being used. This allows the default case all priorities
mapped to traffic class 0 to work in normal hardware
mode and utilize the full packet buffer.

This patch does not address putting the hardware in
4TC mode so packet buffer space may be underutilized
in this case. A follow up patch can address this
optimization. But at least we have the hooks to do
this now.

Also CEE will behave as it always has and map priorities
1:1 with traffic classes.
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The patch below  allowed IEEE 802.1Qaz and CEE DCB hardware
configurations to use common hardware set routines,

commit 88eb696cc6a7af8f9272266965b1a4dd7d6a931b
Author: John Fastabend <john.r.fastabend@intel.com>
Date:   Thu Feb 10 03:02:11 2011 -0800

    ixgbe: DCB, abstract out dcb_config from DCB hardware configuration

However the case when CEE link strict and group strict
are set was missed and are currently being mapped
incorrectly in some configurations.

This patch resolves this.
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

RSS had previously been disabled when DCB was enabled because
DCB was single queued per traffic class. Now that DCB implements
multiple Tx/Rx rings per traffic class enable RSS.

Here RSS hashes across the queues in the traffic class.
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain.@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch adds the ndo_tc_setup to ixgbe. By default we set
the device to use strict priority.
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain.@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This enables multiple {Tx|Rx} rings per traffic class while in DCB
mode. In order to get this working as expected the tc_to_tx net
device mapping is configured as well as the prio_tc_map.

skb priorities are mapped across a range of queue pairs to get
a distribution per traffic class. The maximum number of
queue pairs used while in DCB mode is capped at 64. The hardware
max is actually 128 queues but 64 is sufficient for now and
allocating more seemed a bit excessive. It is easy enough to
increase the cap later if need be.

To get the 802.1Q priority tags inserted correctly ixgbe was
previously using the skb queue_mapping field to directly set
the 802.1Q priority. This no longer works because we have removed
the 1:1 mapping between queues and traffic class. Each ring
is aligned with an 802.1Qaz traffic class so here we add an
extra field to the ring struct to identify the 802.1Q traffic
class. This uses an extra byte of the ixgbe_ring struct
fortunately there was a 2byte hole,

struct ixgbe_ring {
        void *                     desc;                 /*     0     8 */
        struct device *            dev;                  /*     8     8 */
        struct net_device *        netdev;               /*    16     8 */
        union {
                struct ixgbe_tx_buffer * tx_buffer_info; /*           8 */
                struct ixgbe_rx_buffer * rx_buffer_info; /*           8 */
        };                                               /*    24     8 */
        long unsigned int          state;                /*    32     8 */
        u8                         atr_sample_rate;      /*    40     1 */
        u8                         atr_count;            /*    41     1 */
        u16                        count;                /*    42     2 */
        u16                        rx_buf_len;           /*    44     2 */
        u16                        next_to_use;          /*    46     2 */
        u16                        next_to_clean;        /*    48     2 */
        u8                         queue_index;          /*    50     1 */
        u8                         reg_idx;              /*    51     1 */
        u16                        work_limit;           /*    52     2 */

        /* XXX 2 bytes hole, try to pack */

        u8 *                       tail;                 /*    56     8 */
        /* --- cacheline 1 boundary (64 bytes) --- */

Now we can set the VLAN priority directly and it will be
correct. User space can indicate the 802.1Qaz priority
using the SO_PRIORITY setsocket() option and QOS layer will
steer the skb to the correct rings. Additionally using
the multiq qdisc with a queue_mapping action works as
well.
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>