Commit graph

1557 commits

Author SHA1 Message Date
Roland Dreier
db5a7a65c0 mlx4_core: Scale size of MTT table with system RAM
The current driver defaults to 1M MTT segments, where each segment holds
8 MTT entries.  This limits the total memory registered to 8M * PAGE_SIZE
which is 32GB with 4K pages.  Since systems that have much more memory
are pretty common now (at least among systems with InfiniBand hardware),
this limit ends up getting hit in practice quite a bit.

Handle this by having the driver allocate at least enough MTT entries to
cover 2 * totalram pages.

Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-03-12 16:24:59 -07:00
Or Gerlitz
096335b3f9 mlx4_core: Allow dynamic MTU configuration for IB ports
Set the MTU for IB ports in the driver instead of using the firmware
default of 2KB (the driver defaults to 4KB).  Allow for dynamic mtu
configuration through a new, per-port sysfs entry.

Since there's a dependency between the port MTU and the max number of
HW VLs the port can support, apply a mim/max approach, using a loop
that goes down from the highest possible number of VLs to the lowest,
using the firmware return status to know whether the requested number
of VLs is possible with a given MTU.

For now, as with the dynamic link type change / VPI support, the sysfs
entry to change the mtu is exposed only when NOT running in SR-IOV
mode.  To allow changing the MTU for the master in SR-IOV mode,
primary-function-initiated FLR (Function Level Reset) needs to be
implemented.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-03-12 16:24:59 -07:00
Jack Morgenstein
5984be9004 mlx4_core: Report thermal error events
Print an error message when a thermal error async event is reported by the HW.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Dotan Barak <dotanb@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-03-12 16:24:59 -07:00
Roland Dreier
e10903b087 mlx4_core: Fix one more static exported function
Commit 22c8bff6fa ("mlx4_core: Exported functions can't be static")
fixed most of this up, but forgot about mlx4_is_slave_active().  Fix
this one too.

Cc: <stable@vger.kernel.org>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-03-12 16:24:58 -07:00
Richard Cochran
5047fb5d1d r8169: enable transmit time stamping.
This patch has been tested on a machine with the Realtek
RTL8101E/RTL8102E PCI Express Fast Ethernet controller (rev 05).

Cc: Realtek linux nic maintainers <nic_swsd@realtek.com>
Cc: Francois Romieu <romieu@fr.zoreil.com>

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-11 15:43:40 -07:00
David S. Miller
bb092c0db8 Merge branch 'davem-next.r8169' of git://violet.fr.zoreil.com/romieu/linux 2012-03-11 15:34:01 -07:00
Francois Romieu
92a7c4e718 r8169: stop using net_device.{base_addr, irq}.
The driver does not need this leftover of the ISA drivers era.

Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Cc: Hayes Wang <hayeswang@realtek.com>
2012-03-10 22:39:27 +01:00
Francois Romieu
31fa8b1855 r8169: move rtl_cfg_info closer to its caller.
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Cc: Hayes Wang <hayeswang@realtek.com>
2012-03-10 22:39:25 +01:00
Francois Romieu
dc1c00ce70 r8169: move the netpoll handler after the irq handler.
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Cc: Hayes Wang <hayeswang@realtek.com>
2012-03-10 22:39:22 +01:00
Francois Romieu
df43ac7831 r8169: move rtl8169_open after rtl_task it depends on.
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Cc: Hayes Wang <hayeswang@realtek.com>
2012-03-10 22:39:17 +01:00
Francois Romieu
e6b763ea05 r8169: move rtl_set_rx_mode before its rtl_hw_start callers.
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Cc: Hayes Wang <hayeswang@realtek.com>
2012-03-10 22:39:15 +01:00
Francois Romieu
fa9c385ef5 r8169: move net_device_ops beyond the methods it references.
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Cc: Hayes Wang <hayeswang@realtek.com>
2012-03-10 22:38:21 +01:00
Francois Romieu
3b6cf25de2 r8169: move the driver probe method to the end of the driver file.
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Cc: Hayes Wang <hayeswang@realtek.com>
2012-03-10 22:38:18 +01:00
Francois Romieu
e27566ed37 r8169: move the driver removal method to the end of the driver file.
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Cc: Hayes Wang <hayeswang@realtek.com>
2012-03-10 22:38:13 +01:00
Stephen Rothwell
a320757ab8 net: powerpc: remove the legacy iSeries ethernet driver
This driver is specific to the PowerPC legcay iSeries platform which is
being removed.

Cc: David Miller <davem@davemloft.net>
Cc: <netdev@vger.kernel.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-03-09 23:41:26 -05:00
David S. Miller
d503859678 Merge branch 'for-davem' of git://git.kernel.org/pub/scm/linux/kernel/git/bwh/sfc-next 2012-03-09 21:54:28 -05:00
David S. Miller
b2d3298e09 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2012-03-09 14:34:20 -08:00
Takahiroi Shimizu
1a0bdadb4e net/pch_gbe: supports eg20t ptp clock
Supports EG20T ptp clock in the driver

Changes e-mail address.

Adds number.

Signed-off-by: Takahiro Shimizu <tshimizu818@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-09 13:55:38 -08:00
Roopa Prabhu
b8622cbd58 enic: Fix addr valid check in enic_set_vf_mac
zero mac address is a valid address for VIC dynamic vnic and sriov Vf's.
Fix the check in enic_set_vf_mac appropriately

Signed-off-by: Roopa Prabhu <roprabhu@cisco.com>
Signed-off-by: Christian Benvenuti <benve@cisco.com>
Signed-off-by: Sujith Sankar <ssujith@cisco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-08 00:28:19 -08:00
Jack Morgenstein
dcf353b170 mlx4_core: fix bug in modify_cq wrapper for resize flow.
The actual FW command is called in procedure "handle_resize".
Code incorrectly invoked the FW command again (in good flow), in
the modify_cq wrapper function.

Fix by skipping second FW invocation unconditionally for resize.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-08 00:28:01 -08:00
Dan Carpenter
7831545732 atl1c: set ATL1C_WORK_EVENT_RESET bit correctly
ATL1C_WORK_EVENT_RESET is zero so the original code here is a nop.  The
intent was to set the zero bit.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-08 00:27:45 -08:00
Eric Dumazet
09c1d446fe ehea: restore multicast and rx_errors fields
Commit 239c562c94 (ehea: Add 64bit statistics) added a regression,
since we no longer report multicast & rx_errors fields, taken from
port->stats structure. These fields are updated in ehea_update_stats()
every second.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Anton Blanchard <anton@samba.org>
Cc: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Acked-by: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Tested-by: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-08 00:23:04 -08:00
Or Gerlitz
8154c07fe1 mlx4_core: Get rid of redundant ext_port_cap flags
While doing the work for commit a6f7feae6d ("IB/mlx4: pass SMP
vendor-specific attribute MADs to firmware") we realized that the
firmware would respond on all sorts of vendor-specific MADs.
Therefore commit 97285b7817 ("mlx4_core: Add extended port
capabilities support") adds redundant code into the driver, since
there's no real reaon to maintain the extended capabilities of the
port, as they can be queried on demand (e.g the FDR10 capability).

This patch reverts commit 97285b7817 and removes the check for
extended caps from the mlx4_ib driver port query flow.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-03-06 17:25:18 -08:00
Duc Dang
ae5d33723e powerpc/44x: Add more changes for APM821XX EMAC driver
This patch includes:

  Configure EMAC PHY clock source (clock from PHY or internal clock).

  Do not advertise PHY half duplex capability as APM821XX EMAC does not support half duplex mode.

  Add changes to support configuring jumbo frame for APM821XX EMAC.

[ Fix coding style -DaveM ]

Signed-off-by: Duc Dang <dhdang@apm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 17:07:42 -05:00
Vipul Pandya
79421b4eae cxgb4vf: Add support for Chelsio's T480-CR and T440-LP-CR adapters
This patch adds PCI device ids for Chelsio's T480-CR and T440-LP-CR
adapters.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 16:21:17 -05:00
Vipul Pandya
f637d577cf cxgb4: Add support for Chelsio's T480-CR and T440-LP-CR adapters
This patch adds PCI device ids for Chelsio's T480-CR and T440-LP-CR
adapters.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 16:21:17 -05:00
Yevgeny Petrilin
66431a7d45 net/mlx4: defining functions as static
Fixing sparse warnings, the 2 functions are only used in same
file. Defining them as static and not exporting them.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 15:19:18 -05:00
Yevgeny Petrilin
be6736ba1f net/mlx4: remove unused functions
Removing functions that are no longer in use, but still exist

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 15:19:18 -05:00
Yevgeny Petrilin
9a9a232a92 net/mlx4: fixing sparse warnings for not declared, functions
The SET_PORT functions are implemented in port.c, which is part
of mlx4_core, these functions are exported. The functions are in use by
the mlx4_en module (were originally part of mlx4_en).
Their declaration remained in mlx4_en module, moving the declaration to the right location.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 15:19:18 -05:00
Yevgeny Petrilin
2ab573c586 net/mlx4: fixing sparse warnings when copying mac, address to gid entry
The mac should be written as __be64 the gid. The warning was because
we changed the mac parameter, which is u64, by writing result of cpu_to_be64
into it. Fixing by using new variable of type __be64.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 15:19:17 -05:00
Yevgeny Petrilin
39b2c4ebb4 net/mlx4: fix sparse warnings on wrong type for RSS keys
The keys used for the hardware RSS topelitz hash are of type __be32
where the values provided by the driver are from array of u32,
this triggered sparse warning on incorrect type in assignment as of different base types.
Since these values are picked randomly,
the fix is to transform the key to __be32 by executing cpu_to_be_32()

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 15:19:17 -05:00
Or Gerlitz
966684d581 net/mlx4: fix sparse warnings on TX blue flame buffer
The blue flame buffer is defined to be of type void __iomem *
but was passed to mlx4_bf_copy which gets unsigned long * .
This triggered sparse warning on different address spaces,
fix that by changing mlx4_bf_copy first param to be of type void __iomem * .

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 15:19:17 -05:00
Or Gerlitz
4ef2a435be net/mlx4: fix sparse warnings on TX control flags, endianess
Fix sparse warnings on incompatibility between the endianess of the ctrl_flags
field of struct mlx4_en_priv to the srcrb_flags field of struct
mlx4_wqe_ctrl_seg by changing the former to be __be32 instead of u32.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 15:19:17 -05:00
Yevgeny Petrilin
ebf8c9aa03 net/mlx4_en: Saving mem access on data path
Localized the pdev->dev, and using dma_map instead of pci_map
There are multiple map/unmap operations on data path,
optimizing those by saving redundant pointer access.
Those places were identified as hot-spots when running kernel profiling
during some benchmarks.
The fixes had most impact when testing packet rate with small packets,
reducing several % from CPU load, and in some case being the difference
between reaching wire speed or being CPU bound.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 15:19:17 -05:00
Santosh Nayak
6975f4ce5a qla3xxx: ethernet: Silence static checker warning.
Silence the following warning:
"warn: returning -1 instead of -ENOMEM is sloppy".

Signed-off-by: Santosh Nayak <santoshprasadnayak@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 15:19:14 -05:00
Yevgeny Petrilin
1d4526e037 mlx4_core: remove buggy sched_queue masking
Fixes a bug introduced by commit fe9a2603c, where the priority bits
in the schedule queue field were masked out.

Signed-off-by: Amir Vadai <amirv@mellanox.co.il>
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 14:43:50 -05:00
françois romieu
2a15cd2ff4 r8169: runtime resume before shutdown.
With runtime PM, if the ethernet cable is disconnected, the device is
transitioned to D3 state to conserve energy. If the system is shutdown
in this state, any register accesses in rtl_shutdown are dropped on
the floor. As the device was programmed by .runtime_suspend() to wake
on link changes, it is thus brought back up as soon as the link recovers.

Resuming every suspended device through the driver core would slow things
down and it is not clear how many devices really need it now.

Original report and D0 transition patch by Sameer Nanda. Patch has been
changed to comply with advices by Rafael J. Wysocki and the PM folks.

Reported-by: Sameer Nanda <snanda@chromium.org>
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Hayes Wang <hayeswang@realtek.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Acked-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 14:43:49 -05:00
Ben Hutchings
460eeaa03c sfc: Log the part number on probe
During probe of each port, read and log the part number from VPD.
Remove the Falcon-specific board name lookup.

Initial version by Stuart Hodgson <smhodgson@solarflare.com>.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-03-06 18:14:16 +00:00
Ben Hutchings
58f7e57d11 sfc: Remove efx_channel::last_eventq_read_ptr
This member has never been used in a production version of the driver.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-03-06 18:14:15 +00:00
Ben Hutchings
dd40781e3a sfc: Run event/IRQ self-test asynchronously when interface is brought up
Generate a test event on each event queue whenever the interface is
brought up, then after 1 second check that we have either handled a
test event or handled another IRQ for each event queue.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-03-06 18:14:15 +00:00
Ben Hutchings
eee6f6a9e0 sfc: Encapsulate access to efx_{channel,nic}::last_irq_cpu in self-test
Cleanup in preparation for doing an event test on ifup.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-03-06 18:14:15 +00:00
Ben Hutchings
ed74f48087 sfc: Test all event queues in parallel
In case all event queues are broken for some reason, this means it
will only take about a second to check them all, rather than up to 32
seconds.  This may also speed up testing in the successful case.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-03-06 18:14:14 +00:00
Ben Hutchings
93e5dfa59b sfc: Raise self-test timeouts
IRQ latency can be ridiculously high for various reasons, so our
current timeouts of 100 ms or 10 ms are too short.

Change the IRQ and event tests to use polling loops starting with a
delay of 1 tick and doubling that if necessary up to a maximum total
delay of approximately 1 second.

Raise the loopback packet RX timeout to 1 second.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-03-06 18:14:14 +00:00
Ben Hutchings
e7bed9c883 sfc: Remove TX completions from adaptive IRQ scoring
RX and TX completions on the same event queue are generally not associated
with the same flows.  The inclusion of TX completions in the adaptive IRQ
score is more of a source of noise rather than useful feedback.  Therefore,
do not include them in the score, and adjust the default threshold scores
down.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-03-06 18:14:14 +00:00
Ben Hutchings
61321d92fc sfc: Update comments on efx_rx_packet_gro()
The in-tree driver has never supported Driverlink.  The rest of the
comments are rather redundant, but we can usefully state what the
requirements are on the buffer state.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-03-06 18:14:14 +00:00
Ben Hutchings
bdca71ede7 sfc: Remove redundant function efx_nic_has_mc()
This function is now used in only one place, where it always returns
true.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-03-06 18:14:13 +00:00
Robert Stonehouse
2c61c8a787 sfc: Fix calculation of vf_i in map_vi_index()
This was broken during refactoring to use efx_vf_size().

[bwh: Keep using efx_vf_size()]
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-03-06 18:14:13 +00:00
Tom Herbert
5cb917bc4f tg3: Fix to use multi queue BQL interfaces
Fix tg3 to use BQL multi queue related netdev interfaces since the
device supports multi queue.

Signed-off-by: Tom Herbert <therbert@google.com>
Reported-by: Christoph Lameter <cl@gentwo.org>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 01:19:08 -05:00
Junchang Wang
9184a22701 8139too: Add 64bit statistics
Switch to use ndo_get_stats64 to get 64bit statistics.
Two sync entries are used (one for Rx and one for Tx).

Signed-off-by: Junchang Wang <junchangwang@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-06 00:04:16 -05:00
David S. Miller
f6a1ad4295 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Conflicts:
	drivers/net/vmxnet3/vmxnet3_drv.c

Small vmxnet3 conflict with header size bug fix in 'net'.

Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-05 21:16:26 -05:00
Igor Maravic
036dafa28d r8169: add byte queue limit support.
Nothing fancy:
- sent bytes count is notified in the start_xmit path right before
  updating the owner bit in the hardware Tx descriptor (E. Dumazet)
- avoid useless tp->dev dereferencing in start_xmit (E. Dumazet)

Use of netdev_reset_queue is favored over proper accounting in
rtl8169_tx_clear_range since the latter would need more work for the
same result (nb: said accounting degenerates to nothing in xmit_frags).

Signed-off-by: Igor Maravic <igorm@etf.rs>
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
2012-03-06 00:24:26 +01:00
Junchang Wang
8027aa245b r8169: add 64bit statistics.
Switch to use ndo_get_stats64 to get 64bit statistics.
Two sync entries are used (one for Rx and one for Tx).

Signed-off-by: Junchang Wang <junchangwang@gmail.com>
Reviewed-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
2012-03-06 00:23:51 +01:00
Santosh Nayak
9d1dfc06b1 qla3xxx: ethernet: Fix bogus interrupt state flag.
In 'ql_adapter_initialize'
the first call for 'spin_unlock_irqrestore()' is with hw_flags = 0,
which is as good as 'spin_unlock_irq()' (unconditional interrupt
enabling). If this is intended, then for better performance
'spin_unlock_irqrestore()' can be replaced with 'spin_unlock_irq()'
and 'spin_lock_irqsave()' can be replaced by 'spin_lock_irq()

Signed-off-by: Santosh Nayak <santoshprasadnayak@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-05 16:50:52 -05:00
Eric Dumazet
18f973af3e mlx4_en: remove sparse errors
Fix new sparse errors introduced in commit 6221217199 (mlx4_en: dont
change mac_header on xmit)

Reported-by: Or Gerlitz <or.gerlitz@gmail.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-05 16:42:45 -05:00
Matt Carlson
0b47150671 tg3: Recode PCI MRRS adjustment as a PCI quirk
This patch recodes the MRRS cap for 5719 A0 devices as a PCI quirk.

Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-04 20:54:01 -05:00
Paul Gortmaker
e19a82c18f ucc_geth: separate out rx/tx ring alloc and free operations
Factor out the the existing allocation and free operations
so that they can be used individually.

This is to improve code readability, and also to prepare for
possible future changes like better error recovery and more
dynamic configuration (e.g on-the-fly resizing of the rings).

This change represents a straight up relocation of the existing
code into separate routines without changing any of the contained
code itself.  Local variables are relocated as necessary.

Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-04 20:54:01 -05:00
Michael Chan
2fae5e3670 tg3: Fix poor tx performance on 57766 after MTU change
GRC reset causes the read DMA engine to go into a mode that breaks up
requests into 256 bytes.  A PHY reset is required to bring it back to
the normal mode.

Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-04 20:39:31 -05:00
Michael Chan
6541b806b5 tg3: Add memory barriers to sync BD data
for weak memory model architectures to ensure that the chip will DMA
valid BD data.

Signed-off-by: Michael Chan <mchan@broadcom.com>
Reviewed-by: Benjamin Li <benli@broadcom.com>
Reviewed-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-04 20:39:31 -05:00
Michael Chan
c441b45676 tg3: Fix jumbo loopback test on 5719
Loopback on 9K packet fails because the chip has a DMA limit of 4K.  The
loopback test logic uses a single BD for simplicity.  Fix it by reducing
the jumbo packet size to the DMA limit.

Signed-off-by: Michael Chan <mchan@broadcom.com>
Reviewed-by: Benjamin Li <benli@broadcom.com>
Reviewed-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-04 20:39:31 -05:00
John Fastabend
2b88f2de30 net: dcb: getnumtcs()/setnumtcs() should return an int
{g|s}etnumtcs() today returns a u8 that is only used by the DCB code
to verify no error occurred. Today the driver implementations return
negative error codes which end up being non-zero so the logic works
out but triggers some sparse warnings.

To fix the sparse warnings convert the return value to an int.

CC: Eilon Greenstein <eilong@broadcom.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-03-02 18:16:49 -08:00
John Fastabend
89d27a3c0a ixgbe: dcb: check setup_tc return codes
dcb netlink code calls setup_tc to init hardware traffic classes
to use for DCB. At some call sites the return values are not
checked for errors and in one case may return -EINVAL back to
the net/dcbnl.c caller which is expecting a u8.

This fixes some smatch hits and although failures are never
seen in practive its best to check return codes.

Reported-by: Dan Carenter <dan.carpenter@oracle.com>
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-03-02 18:11:24 -08:00
Ben Greear
6f66342c1e e100: Show short v/s long rx length errors in ethtool stats.
Signed-off-by: Ben Greear <greearb@candelatech.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-03-02 18:09:27 -08:00
Ben Greear
d24d65eda9 e100: Fix rx-over-length statistics.
The old code would += the total errors every time
stats were gathered.  Instead, keep a count of short-pkt
and long-pkt counters and then simply add them together
for the rx-over-length stat.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-03-02 18:07:52 -08:00
françois romieu
9c5028e9da r8169: corrupted IP fragments fix for large mtu.
Noticed with the 8168d (-vb-gr, aka RTL_GIGA_MAC_VER_26).

ConfigX registers should only be written while the Config9346 lock
is held.

Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Reported-by: Nick Bowler <nbowler@elliptictech.com>
Cc: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-02 19:10:06 -05:00
stephen hemminger
3f2010b2ad packetengines: fix config default
As part of the big network driver reorg, each vendor directory defaults to
yes, so that older config's can migrate correctly. Looks like this one
got missed.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-02 19:05:47 -05:00
David S. Miller
b4017c5368 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Conflicts:
	drivers/net/ethernet/broadcom/tg3.c

Conflicts in the statistics regression bug fix from 'net',
but happily Matt Carlson originally posted the fix against
'net-next' so I used that to resolve this.

Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-01 17:57:40 -05:00
Dan Carpenter
413708bbaf enic: fix an endian bug in enic_probe()
"num_vfs" is a u32 but we only use the high 16 bits and the low 16bits
are left as zero.  That isn't a problem for little endian systems but it
will break on big endian ones.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-01 17:23:42 -05:00
Dan Carpenter
73f98eab9b pch_gbe: memory corruption calling pch_gbe_validate_option()
pch_gbe_validate_option() modifies 32 bits of memory but we pass
&hw->phy.autoneg_advertised which only has 16 bits and &hw->mac.fc
which only has 8 bits.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-01 17:23:42 -05:00
Roland Dreier
97767a87f3 be2net: Remove unused OFFSET_IN_PAGE() macro
Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-01 17:21:49 -05:00
Alexander Duyck
24ddd96780 ixgbe: Fix comments that are out of date or formatted incorrectly
This patch corrects several comments that are either incorrect or formatted
incorrectly for multiline comments.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-29 23:22:29 -08:00
Don Skidmore
c466d7a733 ixgbe: fix spelling errors
Correct spelling error caught with codespell.py.

Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-29 23:21:07 -08:00
Alexander Duyck
9e0c5648d9 ixgbe: Minor formatting and comment corrections for ixgbe_xmit_frame_ring
This patch is meant to address several minor issues in
ixgbe_xmit_frame_ring.  Specifically it adds a comment explaining the TXSW
flag, and correctly wraps a line over 80 characters.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-29 23:19:08 -08:00
Bruce Allan
bb9c5ee15b e1000e: use msleep instead of mdelay
The e1000_link_stall_workaround_lv() function is always called in non-
atomic context so it should use msleep instead of mdelay.  Also, remove
unnecessary #include <linux/delay.h>.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-29 23:14:19 -08:00
Bruce Allan
3d3a167656 e1000e: cleanup whitespace and indentation
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-29 23:12:45 -08:00
Bruce Allan
06c24b915c e1000e: cleanup incorrect filename in comment
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-29 23:11:47 -08:00
Ben Greear
0bf61e66a0 e100: Support RXALL feature flag.
This allows the NIC to receive packets with bad FCS
and other errors.  Good for sniffing packets on flakey
networks.

v4:  Only flax rx-over-length errors if pkt is beyond
   maximum expected packet size, not just beyond the MTU.
   This matches the existing logic for this counter.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-29 23:00:45 -08:00
Ben Greear
75f58a5376 e100: Support sending custom Ethernet CRC
This can aid with testing the RX logic for bad
CRCs.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-29 22:59:53 -08:00
Ben Greear
719cdac54e e100: Support RXFCS feature flag.
This allows e100 to be configured to append the
Ethernet FCS to the skb.

Useful for sniffing networks.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-29 22:36:56 -08:00
Matt Carlson
65ec698d13 tg3: Fix tg3_get_stats64 for 5700 / 5701 devs
tg3_get_stats64() takes tp->lock when dealing with non-serdes bcm5700
and bcm5701 devices.  However, functions that call tg3_halt() have
already acquired tp->lock.  When tg3_get_stats64() is called in
tg3_halt(), deadlock will occur.

This patch fixes the problem by separating the stat gathering code into
a new tg3_get_nstats() function.  tg3_get_stats64() is recoded to call
this function and take tp->lock.  The code that takes tp->lock in
tg3_calc_crc_errors() has been removed.  Function signatures have been
cleaned up too.

Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-29 13:46:05 -05:00
David S. Miller
9100eb012a mac89x0: Fix build error.
Need to use the new 'saddr' variable not the void 'addr' in
set_mac_address().

Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-28 15:48:42 -05:00
David S. Miller
ff4783ce78 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Conflicts:
	drivers/net/ethernet/sfc/rx.c

Overlapping changes in drivers/net/ethernet/sfc/rx.c, one to change
the rx_buf->is_page boolean into a set of u16 flags, and another to
adjust how ->ip_summed is initialized.

Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-26 21:55:51 -05:00
Linus Torvalds
203738e548 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
1) ICMP sockets leave err uninitialized but we try to return it for the
   unsupported MSG_OOB case, reported by Dave Jones.

2) Add new Zaurus device ID entries, from Dave Jones.

3) Pointer calculation in hso driver memset is wrong, from Dan
   Carpenter.

4) ks8851_probe() checks unsigned value as negative, fix also from Dan
   Carpenter.

5) Fix crashes in atl1c driver due to TX queue handling, from Eric
   Dumazet.  I anticipate some TX side locking fixes coming in the near
   future for this driver as well.

6) The inline directive fix in Bluetooth which was breaking the build
   only with very new versions of GCC, from Johan Hedberg.

7) Fix crashes in the ATP CLIP code due to ARP cleanups this merge
   window, reported by Meelis Roos and fixed by Eric Dumazet.

8) JME driver doesn't flush RX FIFO correctly, from Guo-Fu Tseng.

9) Some ip6_route_output() callers test the return value for NULL, but
   this never happens as the convention is to return a dst entry with
   dst->error set.  Fixes from RonQing Li.

10) Logitech Harmony 900 should be handled by zaurus driver not
   cdc_ether, update white lists and black lists accordingly.  From
   Scott Talbert.

11) Receiving from certain kinds of devices there won't be a MAC header,
   so there is no MAC header to fixup in the IPSEC code, and if we try
   to do it we'll crash.  Fix from Eric Dumazet.

12) Port type array indexing off-by-one in mlx4 driver, fix from Yevgeny
   Petrilin.

13) Fix regression in link-down handling in davinci_emac which causes
   all RX descriptors to be freed up and therefore RX to wedge
   completely, from Christian Riesch.

14) It took two attempts, but ctnetlink soft lockups seem to be
   cured now, from Pablo Neira Ayuso.

15) Endianness bug fix in ENIC driver, from Santosh Nayak.

16) The long ago conversion of the PPP fragmentation code over to
   abstracted SKB list handling wasn't perfect, once we get an
   out of sequence SKB we don't flush the rest of them like we
   should.  From Ben McKeegan.

17) Fix regression of ->ip_summed initialization in sfc driver.
   From Ben Hutchings.

18) Bluetooth timeout mistakenly using msecs instead of jiffies,
   from Andrzej Kaczmarek.

19) Using _sync variant of work cancellation results in deadlocks,
   use the non _sync variants instead.  From Andre Guedes.

20) Bluetooth rfcomm code had reference counting problems leading
   to crashes, fix from Octavian Purdila.

21) The conversion of netem over to classful qdisc handling added
   two bugs to netem_dequeue(), fixes from Eric Dumazet.

22) Missing pci_iounmap() in ATM Solos driver.  Fix from Julia Lawall.

23) b44_pci_exit() should not have __exit tag since it's invoked from
   non-__exit code.  From Nikola Pajkovsky.

24) The conversion of the neighbour hash tables over to RCU added a
   race, fixed here by adding the necessary reread of tbl->nht, fix
   from Michel Machado.

25) When we added VF (virtual function) attributes for network device
   dumps, this potentially bloats up the size of the dump of one
   network device such that the dump size is too large for the buffer
   allocated by properly written netlink applications.

   In particular, if you add 255 VFs to a network device, parts of
   GLIBC stop working.

   To fix this, we add an attribute that is used to turn on these
   extended portions of the network device dump.  Sophisticaed
   applications like 'ip' that want to see this stuff  will be changed
   to set the attribute, whereas things like GLIBC that don't care
   about VFs simply will not, and therefore won't be busted by the
   mere presence of VFs on a network device.

   Thanks to the tireless work of Greg Rose on this fix.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (53 commits)
  sfc: Fix assignment of ip_summed for pre-allocated skbs
  ppp: fix 'ppp_mp_reconstruct bad seq' errors
  enic: Fix endianness bug.
  gre: fix spelling in comments
  netfilter: ctnetlink: fix soft lockup when netlink adds new entries (v2)
  Revert "netfilter: ctnetlink: fix soft lockup when netlink adds new entries"
  davinci_emac: Do not free all rx dma descriptors during init
  mlx4_core: Fixing array indexes when setting port types
  phy: IC+101G and PHY_HAS_INTERRUPT flag
  netdev/phy/icplus: Correct broken phy_init code
  ipsec: be careful of non existing mac headers
  Move Logitech Harmony 900 from cdc_ether to zaurus
  hso: memsetting wrong data in hso_get_count()
  netfilter: ip6_route_output() never returns NULL.
  ethernet/broadcom: ip6_route_output() never returns NULL.
  ipv6: ip6_route_output() never returns NULL.
  jme: Fix FIFO flush issue
  atm: clip: remove clip_tbl
  ipv4: ping: Fix recvmsg MSG_OOB error handling.
  rtnetlink: Fix problem with buffer allocation
  ...
2012-02-26 12:47:17 -08:00
Eric Dumazet
6221217199 mlx4_en: dont change mac_header on xmit
A driver xmit function is not allowed to change skb without special
care.

mlx4_en_xmit() should not call skb_reset_mac_header() and instead should
use skb->data to access ethernet header.

This removes a dumb test : if (ethh && ethh->h_dest)

Also remove this slow mlx4_en_mac_to_u64() call, we can use
get_unaligned() to get faster code.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-26 14:22:05 -05:00
Eli Cohen
a5bbe892da mlx4: Enforce device max FMR maps in FMR alloc
ConnectX devices have a limit on the number of mappings that can be
done on an FMR before having to call sync_tpt.  The current
mlx4_ib driver reports the limit correctly in max_map_per_fmr in
.query_device(), but mlx4_core doesn't check it when actually
allocating FMRs.

Add a max_fmr_maps field to struct mlx4_caps and enforce this maximum
value on FMR allocations.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-02-26 01:43:37 -08:00
Bruce Allan
e85e36390c e1000e: rename e1000e_reload_nvm() and call as function pointer
Rename e1000e_reload_nvm() to e1000e_reload_nvm_generic() to signify the
function is used for more than one MAC-family type, and set and use it as a
MAC ops function pointer to be consistent with the driver design.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 21:43:21 -08:00
Bruce Allan
0d37678e16 e1000e: cleanup - remove unnecessary variable
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 21:42:41 -08:00
Bruce Allan
b20caa80e8 e1000e: use true/false for boolean send_xon, do not assume always true
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 21:41:44 -08:00
Bruce Allan
b2a50e1a1d e1000e: cleanup comment in e1000_hash_mc_addr()
Remove reference to non-existant function.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 21:41:01 -08:00
Bruce Allan
57cde7630c e1000e: rename e1000e_config_collision_dist() and call as function pointer
Rename e1000e_config_collision_dist() to
e1000e_config_collision_dist_generic() to signify the function is used for
more than one MAC-family type, and set and use it as a MAC ops function
pointer to be consistent with the driver design.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 21:39:52 -08:00
Bruce Allan
6e3c807504 e1000e: comment correction in e1000e_set_kmrn_lock_loss_workaround_ich8lan
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 21:39:04 -08:00
Bruce Allan
944ce011cf e1000e: cleanup calls to setup_physical_interface function pointer
Call the MAC ops setup_physical_interface function pointer instead of the
MAC-family-specific function to conform to the rest of the driver design.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 21:38:13 -08:00
Bruce Allan
44abd5c127 e1000e: cleanup use of check_reset_block function pointer
Replace e1000_check_reset_block() inline function with calls to the PHY ops
check_reset_block function pointer.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 21:36:53 -08:00
Bruce Allan
48768329ef e1000e: cleanup use of check_mng_mode function pointer
Replace e1000_check_mng_mode() inline function with calls to the MAC ops
check_mng_mode function pointer.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 21:35:53 -08:00
Bruce Allan
1a46b40fbb e1000e: cleanup: rename e1000e_setup_link() and call as function pointer
Rename e1000e_setup_link() to e1000e_setup_link_generic() to signify the
function is used for more than one MAC-family type.  The 82571-family has
a custom setup_link function which also calls the generic function.  The
ich8lan-family has a custom function which should just be called via the
function pointer.  The 80003es2lan-family just uses the generic function.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 21:34:15 -08:00
Bruce Allan
d1964eb138 e1000e: cleanup: rename e1000e_id_led_init() and call as function pointer
Rename e1000e_id_led_init() to e1000e_id_led_init_generic() to signify the
function is used for more than one MAC-family type.  For the ich8lan MAC
family, some MACs use the generic function and others use the function
e1000_id_led_init_pchlan().  In all cases where e1000e_id_led_init() was
called directly, change to call the function pointer to be consistent with
the driver design.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 21:32:49 -08:00
Linus Torvalds
b52b80023f One InfiniBand/RDMA regression fix for 3.3:
- mlx4 SR-IOV changes added static exported functions, which doesn't
    build on powerpc at least.  Fix from Doug Ledford for this.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.11 (GNU/Linux)
 
 iQIcBAABCAAGBQJPSEe5AAoJEENa44ZhAt0hIoUP/jwpxojruN8c7PuJesp3sne2
 45xxH0OsPSFdYTBnNZGtL3MWnzp88YjoggRvrKGmiEc/vitDTveL8/j+jFatl/d5
 o5yBq9wsSKgU3jJiczT21WBOIg2I8KGgdWozNSO8rUl++fHJGgH1sCSmf8biomnk
 dlHZbA4ZszH1bxHh406GK/+cP5jjKlTLqkixz/156fsopMxzHBaJycOmzSPpHl9s
 ykrVv3n/mhrc3zBgx5y9aU+LhcchZH6CBQOzLBks1c4w8AFXTxIMAQRhkBVnDksi
 zZhg5E05zRkynr27zebNnu6Y6hfWamfCHkM6krJLXL/QRfN0LmoLvdtW2HRffrHW
 9eOzEdmh9i5wHSeH5zhQAE17yttpWQCNN1thGv3oe2uGj7ItmtA1yc/5q8opwBU3
 bl4/saNVdK8DGtpGZjCmPBnsOl9IgMmYMn5haRmOhDvD4/B93OHl+2iQi50vPJHS
 bBvYG03OTHYs9QexDANDv3Q9VmxGRCBXcZkQblAqofgO3dLgCQdddwn0VHt9xDfK
 5Hp31vPs5pGfT6AkPHREHNNvj27Ve1erjrODNVI/Qr2CIkaoiQ/6oR+9ZMrAFsnb
 uyhNDzt4yuMrfA3T/7sAITL6hFLkVHYL2lSorFr5BXZ4cusYlzUYHRbtiR17Vsye
 1KNTElxLI9fmD5xJSY6N
 =mHhD
 -----END PGP SIGNATURE-----

Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband

One InfiniBand/RDMA regression fix for 3.3:

 - mlx4 SR-IOV changes added static exported functions, which doesn't
   build on powerpc at least.  Fix from Doug Ledford for this.

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
  mlx4_core: Exported functions can't be static
2012-02-24 20:03:14 -08:00
David S. Miller
b072342e26 Merge branch 'sfc-3.3' of git://git.kernel.org/pub/scm/linux/kernel/git/bwh/sfc 2012-02-24 22:12:44 -05:00
Ben Hutchings
ff3bc1e752 sfc: Fix assignment of ip_summed for pre-allocated skbs
When pre-allocating skbs for received packets, we set ip_summed =
CHECKSUM_UNNCESSARY.  We used to change it back to CHECKSUM_NONE when
the received packet had an incorrect checksum or unhandled protocol.

Commit bc8acf2c8c ('drivers/net: avoid
some skb->ip_summed initializations') mistakenly replaced the latter
assignment with a DEBUG-only assertion that ip_summed ==
CHECKSUM_NONE.  This assertion is always false, but it seems no-one
has exercised this code path in a DEBUG build.

Fix this by moving our assignment of CHECKSUM_UNNECESSARY into
efx_rx_packet_gro().

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-02-25 00:10:22 +00:00
Santosh Nayak
21ca54e99b enic: Fix endianness bug.
Sparse complaints the endian bug.

Signed-off-by: Santosh Nayak <santoshprasadnayak@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 17:53:03 -05:00
Danny Kukawka
2d5ba83551 xscale/ixp2000/ixpdev: print MAC via printk format specifier
Print MAC/dev_addr via printk extended format specifier %pM
instead of custom code.

Signed-off-by: Danny Kukawka <danny.kukawka@bisect.de>
Acked-by: Lennert Buytenhek <kernel@wantstofly.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 15:41:00 -05:00
Danny Kukawka
d558950efc sun/sunqe: print MAC via printk format specifier
Print MAC/dev_addr via printk extended format specifier %pM
instead of custom code.

Signed-off-by: Danny Kukawka <danny.kukawka@bisect.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 15:40:59 -05:00
Danny Kukawka
f794e7efe4 ixgbevf: print MAC via printk format specifier
Print MAC/dev_addr via printk extended format specifier %pM
instead of custom code.

Signed-off-by: Danny Kukawka <danny.kukawka@bisect.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 15:40:59 -05:00
Danny Kukawka
bbf7bd2f04 dec/tulip/de4x5: print MAC via printk format specifier
Print MAC/dev_addr via printk extended format specifier %pM
instead of custom code.

Signed-off-by: Danny Kukawka <danny.kukawka@bisect.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 15:40:59 -05:00
Danny Kukawka
66dc92eddf cirrus/mac89x0: print MAC via printk format specifier
Print MAC/dev_addr via printk extended format specifier %pM instead
of custom code.

Use memcpy to set the address to dev->dev_addr in set_mac_address,
instead of mxing it up in a for loop with printing a debug msg.

Check also if the given address is valid.

Signed-off-by: Danny Kukawka <danny.kukawka@bisect.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 15:40:59 -05:00
Danny Kukawka
f27fd49962 amd/hplance.c: print MAC via printk format specifier
Print MAC/dev_addr via printk extended format specifier %pM
instead of custom code.

Signed-off-by: Danny Kukawka <danny.kukawka@bisect.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 15:40:59 -05:00
Tushar Dave
e29b5d8f08 v2 e1000: Neaten e1000_dump function
Use pr_<level> for printk
Use temporary instead of multiple pr_conts
Coalesce formats.

Save a few bytes of object code too:

$ size drivers/net/ethernet/intel/e1000/e1000_main.o*
   text	   data	    bss	    dec	    hex	filename
  60507	    369	  14120	  74996	  124f4
drivers/net/ethernet/intel/e1000/e1000_main.o.new
  60717	    369	  14176	  75262	  125fe
drivers/net/ethernet/intel/e1000/e1000_main.o.old

Removed printing of pktdata.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Tushar Dave <tushar.n.dave@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 02:03:43 -08:00
Joe Perches
542c3f4ea9 e1000: Neaten e1000_config_dsp_after_link_change
Separate a complicated bit of e1000_config_dsp_after_link_change
into a new static function e1000_1000Mb_check_cable_length.

Reduces indentation and adds a bit of clarity.

Signed-off-by: Joe Perches <joe@perches.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 02:02:13 -08:00
Bruce Allan
dffcdde769 e1000e: cosmetic comment changes to make lines less than 80 characters
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 01:59:37 -08:00
Bruce Allan
b4d8e21dd8 e1000e: cosmetic change to boolean comparisons
Recent discussions on LKML, kernel-janitors, linux-wireless and netdev
have suggested boolean comparisons should use logical operators instead of
equality comparisons with true/false.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 01:58:27 -08:00
Ben Greear
79d0c1d26e r8169: Support RX-FCS flag.
This allows the NIC to receive the Ethernet FCS
and pass it up the stack, allowing sniffers and
other interested programs to inspect the FCS.

Signed-off-by: Ben Greear <greearb@candelatech.com>
2012-02-24 01:56:32 -08:00
Ben Greear
6bbe021d40 r8169: Support RX-ALL flag.
This allows the NIC to receive packets with bad FCS and
Runts, which can help when sniffing.

NOTE:  r8169, at least on my NIC, silently drops packets
with bad FCS instead of counting them.  It seems they are
only received in any fashion if the RxCRC flag is set
(which this patch allows).

Signed-off-by: Ben Greear <greearb@candelatech.com>
2012-02-24 01:56:27 -08:00
Ben Greear
eeb69aa443 8139too: Support RX-FCS flag.
This allows the NIC to pass the Ethernet FCS on up
the stack, and is useful when sniffing networks.

Signed-off-by: Ben Greear <greearb@candelatech.com>
2012-02-24 01:56:24 -08:00
Ben Greear
d95089dc54 8139too: Support RX-ALL logic.
This allows the NIC to receive Runts and frames with bad
Ethernet Frame Checksums (FCS).

Useful to sniffing & diagnosing bad networks.

Signed-off-by: Ben Greear <greearb@candelatech.com>
2012-02-24 01:56:08 -08:00
Ben Greear
b0d1562c82 e1000: Support RX-FCS flag.
This allows the NIC to pass the Ethernet Frame Checksum
(FCS) up the stack.  Useful when sniffing packets.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 01:53:39 -08:00
Ben Greear
11a78dcf35 e1000: Support sending custom Ethernet CRC.
Good for testing the RX logic for bad CRC handling.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 01:45:57 -08:00
Ben Greear
cf955e6c96 e1000e: Support RXALL feature flag.
This allows the NIC to receive all frames available, including
those with bad FCS, un-matched vlans, ethernet control frames,
and more.

Tested by sending frames with bad FCS.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 01:44:50 -08:00
Ben Greear
943146de22 e1000e: Support sending custom Ethernet CRC.
This can aid with testing the RX logic for bad
CRCs.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 01:41:00 -08:00
Ben Greear
0184039a4b e1000e: Support RXFCS feature flag.
This enables enabling/disabling reception of the Ethernet
FCS.  This can be useful when sniffing packets.

For e1000e, enabling RXFCS can change the default
behaviour for how the NIC handles CRC.  Disabling RXFCS
will take the NIC back to defaults, which can be configured
as part of the module options.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2012-02-24 01:23:06 -08:00
Christian Riesch
5d69703263 davinci_emac: Do not free all rx dma descriptors during init
This patch fixes a regression that was introduced by

commit 0a5f384677
davinci_emac: Add Carrier Link OK check in Davinci RX Handler

Said commit adds a check whether the carrier link is ok. If the link is
not ok, the skb is freed and no new dma descriptor added to the rx dma
channel. This causes trouble during initialization when the carrier
status has not yet been updated. If a lot of packets are received while
netif_carrier_ok returns false, all dma descriptors are freed and the
rx dma transfer is stopped.

The bug occurs when the board is connected to a network with lots of
traffic and the ifconfig down/up is done, e.g., when reconfiguring
the interface with DHCP.

The bug can be reproduced by flood pinging the davinci board while doing
ifconfig eth0 down
ifconfig eth0 up
on the board.

After that, the rx path stops working and the overrun value reported
by ifconfig is counting up.

This patch reverts commit 0a5f384677
and instead issues warnings only if cpdma_chan_submit returns -ENOMEM.

Signed-off-by: Christian Riesch <christian.riesch@omicron.at>
Cc: <stable@vger.kernel.org>
Cc: Hegde, Vinay <vinay.hegde@ti.com>
Cc: Cyril Chemparathy <cyril@ti.com>
Cc: Sascha Hauer <s.hauer@pengutronix.de>
Tested-by: Rajashekhara, Sudhakar <sudhakar.raj@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 03:25:10 -05:00
Christian Riesch
7c3a95a15a davinci_mdio: Correct bitmask for clock divider value
The CLKDIV bitfield in the MDIO Control Register is a 16 bit field,
therefore the CLKDIV value may range from 0 to 0xffff.

Signed-off-by: Christian Riesch <christian.riesch@omicron.at>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 03:24:18 -05:00
Christian Riesch
b4ad042813 davinci_cpdma: Fix channel number written to teardown registers
chan->chan_num is 0..CPDMA_MAX_CHANNELS-1 for tx channels and
CPDMA_MAX_CHANNELS..2*CPDMA_MAX_CHANNELS-1 for rx channels. However,
the rx and tx teardown registers expect zero based channel numbering.

Since the upper bits of the registers are reserved, the teardown also
worked before, this patch is cleanup only.

Signed-off-by: Christian Riesch <christian.riesch@omicron.at>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 03:23:37 -05:00
Yevgeny Petrilin
1e0f03d57d mlx4_core: Fixing array indexes when setting port types
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 01:52:45 -05:00
Sathya Perla
d708f6039b be2net: update driver version
Signed-off-by: Sathya Perla <sathya.perla@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 01:50:16 -05:00
Sathya Perla
1ca7ba921e be2net: enable RSS for ipv6 pkts
Signed-off-by: Sathya Perla <sathya.perla@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 01:50:16 -05:00
Sathya Perla
1cfafab965 be2net: reset queue address after freeing
This will prevent double free in some cases where be_clear() is called
for cleanup when be_setup() fails half-way.

Signed-off-by: Sathya Perla <sathya.perla@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 01:50:16 -05:00
Sathya Perla
0ae57bb3df be2net: fix tx completion cleanup
As a part of be_close(), instead of waiting for a max of 200ms for each TXQ,
wait for a total of 200ms for completions from all TXQs to arrive.

Signed-off-by: Sathya Perla <sathya.perla@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 01:50:16 -05:00
Sathya Perla
191eb75631 be2net: cancel be_worker during EEH recovery
EEH recovery involves ring cleanup and re-creation. The worker
thread must not run during EEH cleanup/resume.

Signed-off-by: Sathya Perla <sathya.perla@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-24 01:50:16 -05:00
Danny Kukawka
504f9b5a6b ethernet: unify return value of .ndo_set_mac_address if address is invalid
Unify return value of .ndo_set_mac_address if the given address
isn't valid. Return -EADDRNOTAVAIL as eth_mac_addr() already does
if is_valid_ether_addr() fails.

Signed-off-by: Danny Kukawka <danny.kukawka@bisect.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-23 17:03:20 -05:00
David S. Miller
32d219ed61 Merge branch 'for-davem' of git://git.kernel.org/pub/scm/linux/kernel/git/bwh/sfc-next 2012-02-23 14:30:46 -05:00
Doug Ledford
22c8bff6fa mlx4_core: Exported functions can't be static
At least on powerpc, it breaks the build if exported functions are
static.  Fix some static exported functions introduced with the mlx4
SR-IOV support added in 3.3-rc1.

Signed-off-by: Doug Ledford <dledford@redhat.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-02-22 23:00:38 -08:00
Matt Carlson
21f7638e6f tg3: Create timer helper functions
This patch seeks to clean up the timer related code.  It begins by
moving one-time timer setup code from tg3_open() to tg3_init_one().
It then creates a function that encapsulates the code needed to start
the timer.  A tg3_timer_stop() function was added for parity.  Finally,
this patch moves all the timer functions to a more suitable location.

Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-23 01:57:17 -05:00
Matt Carlson
c71013597d tg3: Clear RECOVERY_PENDING with reset_task_cancel
If an error happens in the tx completion thread, tg3_reset_task will be
scheduled and TX_RECOVERY_PENDING will be set.  The TX_RECOVERY_PENDING
flag causes tg3_poll[_msix] to return early before doing much of its
work.  Tg3_reset_task() gets canceled when the configuration of the
device is changing, which always results in a chip reset.  When this
happens, the TX_RECOVERY_PENDING flag may be left set, which would
unnecessarily hinder tg3_poll from doing work.  This patch fixes the
problem.

Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-23 01:57:17 -05:00
Matt Carlson
d13ba512cb tg3: Remove SPEED_UNKNOWN checks
tg3_phy_copper_begin() has code that configures the link
advertisements through the use of the link_config.speed and
link_config.duplex members.  The driver does not internally use these
members in this way, nor is it (currently) permitted via the ethtool
interface.  This patch removes the dead code.

Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-23 01:57:17 -05:00
Matt Carlson
34655ad638 tg3: Fix link check in tg3_adjust_link
The tg3 driver tried to detect link changes by comparing the tg3 local
active_speed member with SPEED_UNKNOWN (or formerly SPEED_INVALID).
This check is not correct, since phylib will never set its speed member
to either of these two values.  The code only appeared to work because
tg3 initializes active_speed to SPEED_INVALID during tg3_init_one.  This
patch introduces a new "old_link" tg3 member and then compares the
phy_device's link member against it to detect link state changes.

Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-23 01:57:17 -05:00
Ben Hutchings
73e0026fb2 sfc: Correct efx_for_each_possible_channel_tx_queue() to skip non-TX channels
efx_for_each_possible_channel_tx_queue() should do nothing for RX-only
or extra channels.  The current definition results in allocating
additional unused hardware TX queues when using the mqprio qdisc and
either separate_tx_channels or SR-IOV.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-02-23 00:45:50 +00:00
Ben Hutchings
2d0cc56da3 sfc: Minor formatting cleanup
Fix some indentation and line continuations.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-02-22 20:48:38 +00:00
Ben Hutchings
c92aaff18e sfc: Reverse initial buffer table allocation to allow for later resizing
We have a very simple way of allocating buffer table entries to
queues, which is just to take the next one available.  The extra
channels are the highest numbered channels but they need to be
allocated the lowest entries so that the traffic channels can be
allocated new entries without any collisions.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-02-22 20:48:08 +00:00
Ben Hutchings
01cb543db8 sfc: Correct validation of peer_page_count in efx_vfdi_set_status_page()
efx_vfdi_set_status_page() validates the peer page count by
calculating the size of a request containing that many addresses and
comparing that with the maximum valid request size (4KB).  The
calculation involves a multiplication that may overflow on a 32-bit
system.

We use kcalloc() to allocate memory to store the addresses; that also
does a multiplication and it does check for integer overflow, so any
values larger than 0x1fffffff will be rejected.  However, values in
the range [0x1fffffffc, 0x1fffffff] pass boh tests and result in an
attempt to allocate nearly 4GB on the heap.  This should be rejected
rather quickly as it's obviously impossible on a 32-bit system, and
indeed the maximum possible heap allocation is 32MB.  Still, let's
make absolutely sure by fixing the initial validation.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-02-22 20:48:08 +00:00
Ben Hutchings
c3cb2a8741 sfc: Specify that the VFDI status page has page alignment and size
This requirement was meant to be implied in the name 'status page'.
One out-of-tree VF driver allocates a buffer using the structure size
and not a full page - hence the current odd specification - but in
practice that allocation will be padded and aligned to at least 4KB.
Therefore, we can specify this and have the option to extend the
structure up to 4KB without worrying about VF drivers using odd-shaped
buffers.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2012-02-22 20:48:07 +00:00
RongQing.Li
0541743b4b ethernet/broadcom: ip6_route_output() never returns NULL.
ip6_route_output() never returns NULL, so it is wrong to
check if the return value is NULL.

Signed-off-by: RongQing.Li <roy.qing.li@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-22 15:30:14 -05:00
Danny Kukawka
b049aadca3 3com/typhoon: reuse eth_mac_addr()
Use eth_mac_addr() for .ndo_set_mac_address, remove
typhoon_set_mac_address() since it do currently the same as
eth_mac_addr(). Additional advantage: eth_mac_addr() already
checks if the given address is valid.

Signed-off-by: Danny Kukawka <danny.kukawka@bisect.de>
Acked-by: Dave Dillow <dave@thedillows.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-22 14:46:37 -05:00
Guo-Fu Tseng
ba9adbe67e jme: Fix FIFO flush issue
Set the RX FIFO flush watermark lower.
According to Federico and JMicron's reply,
setting it to 16QW would be stable on most platforms.
Otherwise, user might experience packet drop issue.

CC: stable@kernel.org
Reported-by: Federico Quagliata <federico@quagliata.org>
Fixed-by: Federico Quagliata <federico@quagliata.org>
Signed-off-by: Guo-Fu Tseng <cooldavid@cooldavid.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-22 14:44:41 -05:00
Davidlohr Bueso
f274fd9a03 tg3: remove IRQF_SAMPLE_RANDOM flag
This driver is the last user of the IRQF_SAMPLE_RANDOM flag for net drivers, and since add_*_randomness
interfaces have now deprecated the flag as a source of external noise, we can remove it.

Signed-off-by: Davidlohr Bueso <dave@gnu.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-22 14:43:48 -05:00
Yevgeny Petrilin
3d8f93083b mlx4: Setting new port types after all interfaces unregistered
In port type change flow, need to set the new port types only after
all interfaces have finished the unregister process.
Otherwise, during unregister, one of the interfaces might issue a SET_PORT
command with wrong port types, it can cause bad FW behavior.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-21 15:27:24 -05:00
Yevgeny Petrilin
730c41d5ba mlx4: Replacing pool_lock with mutex
Under the spinlock we call request_irq(), which allocates memory with GFP_KERNEL,
This causes the following trace when DEBUG_SPINLOCK is enabled, it can cause
the following trace:

 BUG: spinlock wrong CPU on CPU#2, ethtool/2595
 lock: ffff8801f9cbc2b0, .magic: dead4ead, .owner: ethtool/2595, .owner_cpu: 0
 Pid: 2595, comm: ethtool Not tainted 3.0.18 #2
 Call Trace:
 spin_bug+0xa2/0xf0
 do_raw_spin_unlock+0x71/0xa0
 _raw_spin_unlock+0xe/0x10
 mlx4_assign_eq+0x12b/0x190 [mlx4_core]
 mlx4_en_activate_cq+0x252/0x2d0 [mlx4_en]
 ? mlx4_en_activate_rx_rings+0x227/0x370 [mlx4_en]
 mlx4_en_start_port+0x189/0xb90 [mlx4_en]
 mlx4_en_set_ringparam+0x29a/0x340 [mlx4_en]
 dev_ethtool+0x816/0xb10
 ? dev_get_by_name_rcu+0xa4/0xe0
 dev_ioctl+0x2b5/0x470
 handle_mm_fault+0x1cd/0x2d0
 sock_do_ioctl+0x5d/0x70
 sock_ioctl+0x79/0x2f0
 do_vfs_ioctl+0x8c/0x340
 sys_ioctl+0xa1/0xb0
 system_call_fastpath+0x16/0x1b

Replacing with mutex, which is enough in this case.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-21 15:27:23 -05:00
Dmitry Kravkov
0b0a635f79 bnx2x: update driver version to 1.72.10-0
Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-20 19:34:08 -05:00
Dmitry Kravkov
fe603b4d68 bnx2x: add gro_check
The patch provides workaround for BUG in FW 7.2.16,
which in GRO mode may miscalculate buffer and
place on SGE one frag less than it could.
It may happen only for some MTUs, we mark these MTUs
with gro_check flag during device initialization or
MTU change.

Next FW should include fix for the issue and the
patch could be reverted.

Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-20 19:34:08 -05:00
Michael Chan
e65de0716f cnic: update for FW 7.2.xx
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-20 19:34:08 -05:00
Dmitry Kravkov
621b4d66b2 use FW 7.2.16
The patch integrates FW 7.2.16 HSI and implements driver
part of GRO flow.

FW 7.2.16 adds the ability to aggregate packets for GRO
(and not just LRO) and also fixes some bugs.

1. Added new aggregation mode: GRO. In this mode packets are aggregated
   such that the original packets can be reconstructed by the OS.
2. 57712 HW bug workaround - initialized all CAM TM registers to 0x32.
3. Adding the FCoE statistics structures to the BNX2X HSI.
4. Wrong configuration of TX HW input buffer size may cause theoretical
   performance effect. Performed configuration fix.
5. FCOE - Arrival of packets beyond task IO size can lead to crash.
   Fix firmware data-in flow.
6. iSCSI - In rare cases of on-chip termination the graceful termination
   timer hangs, and the termination doesn't complete. Firmware fix to MSL
   timer tolerance.
7. iSCSI - Chip hangs when target sends FIN out-of-order or with isles
   open at the initiator side. Firmware implementation corrected to drop
   FIN received out-of-order or with isles still open.
8. iSCSI - Chip hangs when in case of retransmission not aligned to 4-bytes
   from the beginning of iSCSI PDU. Firmware implementation corrected
   to support arbitrary aligned retransmissions.
9. iSCSI - Arrival of target-initiated NOP-IN during intense ISCSI traffic
   might lead to crash. Firmware fix to relevant flow.

Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-20 19:34:07 -05:00
Jack Morgenstein
3d7474734b mlx4_core: Do not map BF area if capability is 0
BF can be disabled in some cases, the capability field, bf_reg_size is set
to zero in this case. Don't map the BF area in this case, it would cause
failures.  In addition, leaving the BF area unmapped
also alerts the ETH driver to not use BF.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-20 19:26:34 -05:00