Various improvements of qdio error reporting to the
upper-layer drivers (qeth, zfcp):

- Split QDIO_ERROR_ACTIVATE_CHECK_CONDITION into:

  QDIO_ERROR_ACTIVATE: qdio termination interrupt
  QDIO_ERROR_GET_BUF_STATE: QIOASSIST eqbs error
  QDIO_ERROR_SET_BUF_STATE: QIOASSIST sqbs error

  Add QDIO_ERROR_FATAL / QDIO_ERROR_TEMPORARY masks
  to ease recovery decision in upper-layer drivers.

- Don't (ab-)use qdio handler errors as return codes
  for do_QDIO but use standard error codes:

  -ENOBUFS: temporary target CC=2 condition
  -EBUSY: unresolved SIGA-W CC=2 busy condition
  -EIO: I/O error (CC=1, CC=3)

- Remove unneeded memory clobber from SIGA-R
- Remove EX_TABLE entry on SIGA-W, we want to see these errors
Reviewed-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NJan Glauber <jang@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

The previous blkt defaults for OSA Express 4 cards produced inadequate
performance for streaming workloads. The present patch will apply a
set of more appropriate defaults.
Signed-off-by: NStefan Raspl <raspl@linux.vnet.ibm.com>
Reviewed-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There exist qeth sysfs blkt attributes to change the default blkt
values. But blkt changes are reset during online setting due to a 2nd
invocation of qeth_determine_capabilites(). This patch makes sure
blkt default values are configured during 1st run of
qeth_determine_capabilities() only. Thus blkt changes are kept
during online setting.
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Reported-by: NHorst Hartmann <horst.hartmann@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Setting an invalid mac-address for a qeth layer2 device returns
with a strange error code:
# ip link set hsi1 address 00:00:00:00:00:01
   RTNETLINK answers: Unknown error 18446744073709486085
Problem is caused by wrong usage of the return_code field within
structure qeth_ipa_cmd.
With this patch the ip command above returns
   SIOCSIFHWADDR: Invalid argument
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

During system startup udev may try to configure devices in
parallel so we have to synchronize discipline module
loading.
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

To send commands on the write channel 8 buffers exist. If all
8 buffers are used, a wait is triggered on the write channel. When
such buffer are freed, a wake_up is needed. This patch adds the
missing wake_up in qeth_release_buffer().
This fix is especially important when running Communications
Controller for Linux on System z.
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add qeth device private ioctl to query the OSA address table.
This helps debugging hw related problems.
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The queue_start_poll function pointer field in struct qdio_initialize
had to change its type and become a vector of function pointers to
support asynchronous delivery of storage blocks so rename the field to
make the type change explicit and ensure no other user of qdio tries
to use the field the old way. During setting up the qdio queues, only
dereference vector elements if the vector is actually allocated.
Signed-off-by: NSteffen Maier <maier@linux.vnet.ibm.com>
Signed-off-by: NEinar Lueck <elelueck@de.ibm.com>
Signed-off-by: NJan Glauber <jang@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

If recovery is triggered in presence of pending asynchronous
deliveries of storage blocks we do a forced cleanup after
the corresponding tasklets are completely stopped and trigger
appropriate notifications for the correspondingerror state.
Signed-off-by: NEinar Lueck <elelueck@de.ibm.com>
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In case there are no system resources to run a recovery we have to clear
recovery bitmasks so a further automatic or manual driven recovery can
fix up the device.
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The patch "qeth: exploit asynchronous delivery of storage blocks"
added a WARN_ON in qeth_schedule_recovery. A device recovery should
not cause a kernel warning. This is obviously a debugging  left-over
that we forgot to remove.
Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NIan Campbell <ian.campbell@citrix.com>
Cc: Ursula Braun <ursula.braun@de.ibm.com>
Cc: Frank Blaschka <blaschka@linux.vnet.ibm.com>
Cc: linux390@de.ibm.com
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: linux-s390@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch extends the HiperSockets device driver to send and receive
af_iucv traffic over HiperSockets transport.
TX: Driver uses new asynchronous delivery of storage blocks to pass
    flow control/congestion information from the HiperSockets microcode
    to the af_iucv socket.
RX: Memory for incoming traffic is preallocated and passed to
    HiperSockets layer. If receiver is not capable to clean its buffers
    shared with HiperSockets and pass new memory to the HiperSockets
    layer this will cause flow control/congestion events on the
    sender.
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NEinar Lueck <elelueck@de.ibm.com>
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch exploits the QDIO support for asynchronous delivery of storage
blocks for Hipersockets. The exploitation is not configured per default and
may be enabled via the function qeth_configure_cq.
Signed-off-by: NEinar Lueck <elelueck@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch introduces support for asynchronous delivery of storage blocks for
Hipersockets. Upper layers may exploit this functionality to reuse SBALs for
which the delivery status is still pending.
Signed-off-by: NEinar Lueck <elelueck@de.ibm.com>
Signed-off-by: NJan Glauber <jang@linux.vnet.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

OSA cards can be configured to support 1 or 4 output queues. This
does not apply to HiperSockets. This patch limits determination of
the configured number of output queues to OSA cards only, but excludes
HiperSockets.
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

- unify vlan and nonvlan rx path
- kill card->vlangrp and qeth_l3_vlan_rx_register
Signed-off-by: NJiri Pirko <jpirko@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The qdio SBAL entry flag is made-up of four different values that are
independent of one another. Some of the bits are reserved by the
hardware and should not be changed by qdio. Currently all four values
are overwritten since the SBAL entry flag is defined as an u32.

Split the SBAL entry flag into four u8's as defined by the hardware
and don't touch the reserved bits.
Signed-off-by: NJan Glauber <jang@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Fill in the owner of qeth's ccw device driver.
Signed-off-by: NSebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch improves FFDC (first failure data capture) by requesting
a hardware trace in case the device driver, the hardware or a user
detects an error.
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Set rx csum default to hw checksumming again.
Remove sysfs interface for rx csum (checksumming) and TSO (large_send).
With the new hw_features it does not work to keep the old sysfs
interface in parallel. Convert options.checksum_type to new hw_features.
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fixes generated by 'codespell' and manually reviewed.
Signed-off-by: NLucas De Marchi <lucas.demarchi@profusion.mobi>

Remove the owner and name members of struct
ccwgroup_driver and convert all drivers to store
this data in the embedded struct device_driver.
Signed-off-by: NSebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Remove the owner and name members of struct
ccw_driver and convert all drivers to store
this data in the embedded struct device_driver.
Signed-off-by: NSebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

This patch turns on RX checksum and GRO by default. To improve
receiving performance and reduce congestion in case of network
bursts we also increase the default number of inbound buffers.
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If a qeth device is set offline, data and control subchannels are
cleared, which means removal of all IP Assist Primitive settings
implicitly. There is no need to delete those settings explicitly.
This patch removes all IP Assist invocations from offline.
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For OSA the CHPARM-definition determines the number of available
outbound queues.
A CHPARM-change may occur while a Linux system with probed
OSA device is in suspend state. This patch enables proper
resuming of an OSA device in this case.
Signed-off-by: NUrsula braun <ursula.braun@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For HiperSockets the framesize-definition determines the selected
mtu-size and the size of the allocated qdio buffers.
A framesize-change may occur while a Linux system with probed
HiperSockets device is in suspend state. This patch enables proper
resuming of a HiperSockets device in this case.
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

HiperSockets and OSA hardware report a maximum MTU size. Add checking
to reject larger MTUs than allowed by hardware.
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The used buffers counter is not incremented in case of an error so
the counter can become negative. Increment the used buffers counter
before checking for errors.
Signed-off-by: NJan Glauber <jang@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Introduce a scan treshold for the qdio outbound queues. By setting the
threshold the driver can tell qdio after how much used SBALs qdio
should schedule the outbound tasklet that scans the queue for finished
SBALs. The threshold is specific by the drivers because a
Hipersockets device is much faster in utilizing outbound buffers than a
ZFCP or OSA device.

The default values after how many used SBALs the tasklet should run are:

OSA:          > 31 SBALs
Hipersockets: > 7 SBALs
zfcp:         > 55 SBALs
Signed-off-by: NJan Glauber <jang@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

The used buffers counter is not incremented in case of an error so
the counter can become negative. Increment the used buffers counter
before checking for errors.
Signed-off-by: NJan Glauber <jang@linux.vnet.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

QDIO is running independent from netdevice state. We are not
allowed to schedule NAPI in case the netdevice is not open.
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For a certain Hipersockets specific error code in the xmit path, the
qeth driver tries to invoke dev_queue_xmit again.
Commit 79640a4c introduces a busylock
causing locking problems in case of re-invoked dev_queue_xmit by qeth.
This patch removes the attempts to retry packet sending with
dev_queue_xmit from the qeth driver.
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds NAPI support to the qeth layer 2 and layer 3
discipline. It is important to understand that we can not enable/disable
IRQs as usual, we have to use the corresponding new QDIO interface.
Also to not overdraw the budget we have to stop and restart buffer
processing at any point during processing a bulk of QDIO buffers.
Having the driver NAPI enabled it is possible to turn on GRO for the
layer 3 discipline.
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)

// <smpl>
@@
expression from,to,size,flag;
position p;
identifier l1,l2;
@@

-  to = \(kmalloc@p\|kzalloc@p\)(size,flag);
+  to = memdup_user(from,size);
   if (
-      to==NULL
+      IS_ERR(to)
                 || ...) {
   <+... when != goto l1;
-  -ENOMEM
+  PTR_ERR(to)
   ...+>
   }
-  if (copy_from_user(to, from, size) != 0) {
-    <+... when != goto l2;
-    -EFAULT
-    ...+>
-  }
// </smpl>
Signed-off-by: NJulia Lawall <julia@diku.dk>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Reply callback functions in qeth should return zero if command
response consists of one part only, otherwise qeth continues
waiting for further parts of the command response.
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If qeth issues an ipa command, but for some reasons the response
never comes back, qeth reaches a timeout.
Reset the irq_pending flag of the write channel in timeout handling
code and trigger a recovery to avoid endless looping for the following
ipa command.
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch serializes device removal and other sysfs-triggered
configurations by moving removal of sysfs-attributes to the beginning
of the remove functions. And it serializes online/offline setting
and discipline-switching (causing reestablishing of the net_device)
by making use of a new discipline mutex.
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The qeth IP address flag setting is possible when device is
offline. When setting device online afterwards the current set
IP addresses have to be correctly registered with the device
regarding the IP address takeover attribute.
Signed-off-by: NKlaus-Dieter Wacker <kdwacker@de.ibm.com>
Signed-off-by: NFrank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>