CC [M] drivers/net/ixgbe/ixgbe_main.o
drivers/net/ixgbe/ixgbe_main.c: In function `ixgbe_intr':
drivers/net/ixgbe/ixgbe_main.c:1290: sorry, unimplemented: inlining failed in call to 'ixgbe_irq_enable': function body not available
drivers/net/ixgbe/ixgbe_main.c:1312: sorry, unimplemented: called from here
make[4]: *** [drivers/net/ixgbe/ixgbe_main.o] Error 1
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Acked-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
So I dug deeper into the DMA problems I had with iwlagn and a kind soul
helped me in that he said something about pci-e alignment and mentioned
the iwl_rx_allocate function to check for crossing 4KB boundaries. Since
there's 8KB A-MPDU support, crossing 4k boundaries didn't seem like
something the device would fail with, but when I looked into the
function for a minute anyway I stumbled over this little gem:
BUG_ON(rxb->dma_addr & (~DMA_BIT_MASK(36) & 0xff));
Clearly, that is a totally bogus check, one would hope the compiler
removes it entirely. (Think about it)
After fixing it, I obviously ran into it, nothing guarantees the
alignment the way you want it, because of the way skbs and their
headroom are allocated. I won't explain that here nor double-check that
I'm right, that goes beyond what most of the CC'ed people care about.
So then I came up with the patch below, and so far my system has
survived minutes with 64K pages, when it would previously fail in
seconds. And I haven't seen a single instance of the TX bug either. But
when you see the patch it'll be pretty obvious to you why.
This should fix the following reported kernel bugs:
http://bugzilla.kernel.org/show_bug.cgi?id=11596http://bugzilla.kernel.org/show_bug.cgi?id=11393http://bugzilla.kernel.org/show_bug.cgi?id=11983
I haven't checked if there are any elsewhere, but I suppose RHBZ will
have a few instances too...
I'd like to ask anyone who is CC'ed (those are people I know ran into
the bug) to try this patch.
I am convinced that this patch is correct in spirit, but I haven't
understood why, for example, there are so many unmap calls. I'm not
entirely convinced that this is the only bug leading to the TX reply
errors.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Before ieee80211_notify_mac() was added, it was presented with the
use case of using it to tell mac80211 that the association may
have been lost because the firmware crashed/reset.
Since then, it has also been used by iwlwifi to (slightly) speed
up re-association after resume, a workaround around the fact that
mac80211 has no suspend/resume handling yet. It is also not used
by any other drivers, so clearly it cannot be necessary for "good
enough" suspend/resume.
Unfortunately, the callback suffers from a severe problem: It only
works for station mode. If suspend/resume happens while in IBSS or
any other mode (but station), then the callback is pointless.
Recently, it has created a number of locking issues, first because
it required rtnl locking rather than RCU due to calling sleeping
functions within the critical section, and now because it's called
by iwlwifi from the mac80211 workqueue that may not use the rtnl
because it is flushed under rtnl.
(cf. http://bugzilla.kernel.org/show_bug.cgi?id=12046)
I think, therefore, that we should take a step back, remove it
entirely for now and add the small feature it provided properly.
For suspend and resume we will need to introduce new hooks, and for
the case where the firmware was reset the driver will probably
simply just pretend it has done a suspend/resume cycle to get
mac80211 to reprogram the hardware completely, not just try to
connect to the current AP again in station mode. When doing so, we
will need to take into account locking issues and possibly defer
to schedule_work from within mac80211 for the resume operation,
while the suspend operation must be done directly.
Proper suspend/resume should also not necessarily try to reconnect
to the current AP, the time spent in suspend may have been short
enough to not be disconnected from the AP, mac80211 will detect
that the AP went out of range quickly if it did, and if the
association is lost then the AP will disassoc as soon as a data
frame is sent. We might also take into account WWOL then, and
have mac80211 program the hardware into such a mode where it is
available and requested.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
skb->tail can't be meant here because it's not the same across 32/64 bit
compilations. This means there's no way the current driver can work on
64-bit architectures.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Cc: stable@kernel.org [2.6.27]
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Several netdev share one adapter here.
We use netdev->ml_priv of the netdevs point to the first netdev's priv.
Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If segmentation offload is enabled by the host, we currently allocate
maximum sized packet buffers and pass them to the host. This uses up
20 ring entries, allowing us to supply only 20 packet buffers to the
host with a 256 entry ring. This is a huge overhead when receiving
small packets, and is most keenly felt when receiving MTU sized
packets from off-host.
The VIRTIO_NET_F_MRG_RXBUF feature flag is set by hosts which support
using receive buffers which are smaller than the maximum packet size.
In order to transfer large packets to the guest, the host merges
together multiple receive buffers to form a larger logical buffer.
The number of merged buffers is returned to the guest via a field in
the virtio_net_hdr.
Make use of this support by supplying single page receive buffers to
the host. On receive, we extract the virtio_net_hdr, copy 128 bytes of
the payload to the skb's linear data buffer and adjust the fragment
offset to point to the remaining data. This ensures proper alignment
and allows us to not use any paged data for small packets. If the
payload occupies multiple pages, we simply append those pages as
fragments and free the associated skbs.
This scheme allows us to be efficient in our use of ring entries
while still supporting large packets. Benchmarking using netperf from
an external machine to a guest over a 10Gb/s network shows a 100%
improvement from ~1Gb/s to ~2Gb/s. With a local host->guest benchmark
with GSO disabled on the host side, throughput was seen to increase
from 700Mb/s to 1.7Gb/s.
Based on a patch from Herbert Xu.
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (use netdev_priv)
Signed-off-by: David S. Miller <davem@davemloft.net>
Seems like an oversight that we have set-tx-csum and set-sg hooked
up, but not set-tso.
Also leads to the strange situation that if you e.g. disable tx-csum,
then tso doesn't get disabled.
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Each time we re-fill the recv queue with buffers, we allocate
one too many skbs and free it again when adding fails. We should
recycle the pages allocated in this case.
A previous version of this patch made trim_pages() trim trailing
unused pages from skbs with some paged data, but this actually
caused a barely measurable slowdown.
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (use netdev_priv)
Signed-off-by: David S. Miller <davem@davemloft.net>
This change enables ECC correction for the packet buffer on all 82571
silicon.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some users reported that they have machines with BMCs enabled that cannot
receive IPMI traffic after e1000e is loaded.
http://marc.info/?l=e1000-devel&m=121909039127414&w=2http://marc.info/?l=e1000-devel&m=121365543823387&w=2
This fixes the issue if they load with the new parameter = 0 by disabling
crc stripping, but leaves the performance feature on for most users.
Based on work done by Hong Zhang.
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If the driver fails to initialize the first time due to the failure in the
phy_id check the kernel triggers a warn_on on the second try to load the
driver because the driver did not free the msi/x resources in the first
load because of the previous failure in phy_id check.
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
make mdio-gpio work with non OpenFirmware gpio implementation.
Aditional changes to mdio-gpio:
- use gpio_request() and gpio_free()
- place irq[] array in struct mdio_gpio_info
- add module description, author and license
- add note about compiling this driver as module
- rename mdc and mdio function (were ugly names)
- change MII to MDIO in bus name
- add __init __exit to module (un)loading functions
- probe fails if no phys added to the bus
- kzalloc bitbang with sizeof(*bitbang)
Changes since v3:
- keep bus naming "%x" to be compatible with existing drivers.
Changes since v2:
- more #ifdefs reduction
- platform driver will be registered on OF platforms also
- unified platform and OF bus_id to phy%i
Changes since v1:
- removed NO_IRQ
- reduced #idefs
Laurent, please test this driver under OF.
Signed-off-by: Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reported by Stephen Rothwell:
drivers/net/dm9000.c:1450: error: expected ')' before ';' token
drivers/net/dm9000.c:1455: error: expected ';' before '}' token
Signed-off-by: David S. Miller <davem@davemloft.net>
PHYID returns 0xffff and not 0xffffffff when not found and in some
case(at91sam9263) 0x0. Maybe this patch could be useful.
Signed-off-by: Giulio Benetti <giulio.benetti@micronovasrl.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The e100 driver triggers BUG_ON(buf->direction != dir)
by doing pci_map_single(..., PCI_DMA_BIDIRECTIONAL)
and pci_dma_sync_single_for_device(..., PCI_DMA_TODEVICE).
Changing the DMA direction, especially with dmabounce will result
in unexpected behaviour.
Reported-by: Anders Grafstrom <grfstrm@users.sourceforge.net>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use dev_printk() instead of printk() to give a little more context
and use consistent format.
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Removed debug print statements and improved conditionals around informational statements.
Signed-off-by: Ron Mercer <ron.mercer@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since dev->power.should_wakeup bit is used by the PCI core to
decide whether the device should wake up the system from sleep
states, set/unset this bit whenever WOL is enabled/disabled using
igb_set_wol(). Accordingly, use device_can_wakeup() for checking
if wake-up is supported by the device.
Signed-off-by: "Rafael J. Wysocki" <rjw@sisk.pl>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since dev->power.should_wakeup bit is used by the PCI core to
decide whether the device should wake up the system from sleep
states, set/unset this bit whenever WOL is enabled/disabled using
e1000_set_wol(). Accordingly, use device_can_wakeup() for checking
if wake-up is supported by the device.
Signed-off-by: "Rafael J. Wysocki" <rjw@sisk.pl>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since dev->power.should_wakeup bit is used by the PCI core to
decide whether the device should wake up the system from sleep
states, set/unset this bit whenever WOL is enabled/disabled using
e1000_set_wol(). Accordingly, use device_can_wakeup() for checking
if wake-up is supported by the device.
Signed-off-by: "Rafael J. Wysocki" <rjw@sisk.pl>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Make pegasus driver not allocate a workqueue until the driver
is bound to some device, which will need that workqueue if
the device is brought up. This conserves resources when the
driver is linked but there's no pegasus device connected.
Also shrink the runtime footprint a smidgeon by moving some
init-only code into its proper section, and move an obnoxious
(frequent and meaningless) message to be debug-only.
Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
netif_carrier_off() is sufficient to stop Tx into the driver. Stopping the Tx
queues is redundant and unnecessary. By the same token, netif_carrier_on()
will be sufficient to re-enable Tx, so waking the queues is unnecessary.
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch will add support for the Marvell 88E1118 PHY which supports gigabit ethernet among other things.
Signed-off-by: Ron Madrid <ron_madrid@sbcglobal.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Before the change the driver reported the same pause parameters
for all the ports, even only one of them was modified.
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 46abc02175 ("phylib: give mdio
buses a device tree presence") added a call to device_unregister() in
a situation where the caller did not intend for the device to be
freed yet, but apart from just unregistering the device from the
system, device_unregister() does an additional put_device() that is
intended to free it.
The right function to use in this situation is device_del(), which
unregisters the device from the system like device_unregister() does,
but without dropping the reference count an additional time.
Bug report from Bryan Wu <cooloney@kernel.org>.
Signed-off-by: Lennert Buytenhek <buytenh@marvell.com>
Tested-by: Bryan Wu <cooloney@kernel.org>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
Of the various WOL options provided in include/linux/ethtool.h, the
L1 NIC supports only magic packet. Remove all options except magic
packet from the atl1 driver.
Signed-off-by: Jay Cliburn <jcliburn@gmail.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
Inverting the crc after calling ether_crc_le() is unnecessary and breaks
multicast. Remove it.
Tested-by: David Madore <david.madore@ens.fr>
Signed-off-by: Jay Cliburn <jcliburn@gmail.com>
Cc: stable@kernel.org
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
We weren't unmapping DMA memory, which will break when gianfar gets used
on systems with more than 32-bits of memory. Also, it's just plain wrong.
Signed-off-by: Andy Fleming <afleming@freescale.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
p_{tx,rx}_fw_statistics_pram are special: they're available only when
a device is open. If the device is closed, we should just fill the data
with zeroes.
Fixes the following oops:
root@b1:~# ifconfig eth1 down
root@b1:~# ethtool -S eth1
Unable to handle kernel paging request for data at address 0x00000000
Faulting instruction address: 0xc01e1dcc
Oops: Kernel access of bad area, sig: 11 [#1]
[...]
NIP [c01e1dcc] uec_get_ethtool_stats+0x98/0x124
LR [c0287cc8] ethtool_get_stats+0xfc/0x23c
Call Trace:
[cfaadde0] [c0287ca8] ethtool_get_stats+0xdc/0x23c (unreliable)
[cfaade20] [c0288340] dev_ethtool+0x2fc/0x588
[cfaade50] [c0285648] dev_ioctl+0x290/0x33c
[cfaadea0] [c0272238] sock_ioctl+0x80/0x2ec
[cfaadec0] [c00b5ae4] vfs_ioctl+0x40/0xc0
[cfaadee0] [c00b5fa8] do_vfs_ioctl+0x78/0x20c
[cfaadf10] [c00b617c] sys_ioctl+0x40/0x74
[cfaadf40] [c00142d8] ret_from_syscall+0x0/0x38
[...]
---[ end trace b941007b2dfb9759 ]---
Segmentation fault
p.s. While at it, also remove u64 casts, they aren't needed.
Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
This driver is pretty mature, and the worst of the known
problems has been fixed (the 32-bit failures due to readq
implementation).
So let's finally give it a version of 1.0
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds support for the Sun CP3260 ATCA blade which is
a N2 based ATCA blade with 2 NIU ports. The NIU ports do not
have on-board PHY.
Signed-off-by: Santwona Behera <santwona.behera@sun.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support to drivers/net/usb/asix.c for the Cables-to-Go "USB 2.0 to
10/100 Ethernet Adapter". USB id 0b95:772a.
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
We have some reasons to kill netdev->priv:
1. netdev->priv is equal to netdev_priv().
2. netdev_priv() wraps the calculation of netdev->priv's offset, obviously
netdev_priv() is more flexible than netdev->priv.
But we cann't kill netdev->priv, because so many drivers reference to it
directly.
This patch is a safe convert for netdev->priv to netdev_priv(netdev).
Since all of the netdev->priv is only for read.
But it is too big to be sent in one mail.
I split it to 4 parts and make every part smaller than 100,000 bytes,
which is max size allowed by vger.
Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We have some reasons to kill netdev->priv:
1. netdev->priv is equal to netdev_priv().
2. netdev_priv() wraps the calculation of netdev->priv's offset, obviously
netdev_priv() is more flexible than netdev->priv.
But we cann't kill netdev->priv, because so many drivers reference to it
directly.
This patch is a safe convert for netdev->priv to netdev_priv(netdev).
Since all of the netdev->priv is only for read.
But it is too big to be sent in one mail.
I split it to 4 parts and make every part smaller than 100,000 bytes,
which is max size allowed by vger.
Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We have some reasons to kill netdev->priv:
1. netdev->priv is equal to netdev_priv().
2. netdev_priv() wraps the calculation of netdev->priv's offset, obviously
netdev_priv() is more flexible than netdev->priv.
But we cann't kill netdev->priv, because so many drivers reference to it
directly.
This patch is a safe convert for netdev->priv to netdev_priv(netdev).
Since all of the netdev->priv is only for read.
But it is too big to be sent in one mail.
I split it to 4 parts and make every part smaller than 100,000 bytes,
which is max size allowed by vger.
Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We have some reasons to kill netdev->priv:
1. netdev->priv is equal to netdev_priv().
2. netdev_priv() wraps the calculation of netdev->priv's offset, obviously
netdev_priv() is more flexible than netdev->priv.
But we cann't kill netdev->priv, because so many drivers reference to it
directly.
This patch is a safe convert for netdev->priv to netdev_priv(netdev).
Since all of the netdev->priv is only for read.
But it is too big to be sent in one mail.
I split it to 4 parts and make every part smaller than 100,000 bytes,
which is max size allowed by vger.
Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix bnx2 so that netpoll works properly. Specifically:
1) Fix parameters to bnx2_interrupt to be a struct bnx2_napi rather than a
struct net_device
2) Fix poll_controller method to check every queue in the rx case so frames
aren't missed
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Benjamin Li <benli@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move all related timeout constants to the same location. BNX2
prefix is also added to make them more consistent.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Benjamin Li <benli@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The default rx buffer water marks for XOFF/XON are for 1500 MTU. At
larger MTUs, these water marks need to be adjusted for effective
flow control.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Benjamin Li <benli@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On some quad-port cards that cannot support WoL on all ports due
to excessive power consumption, the driver needs to restrict WoL
on some ports by checking VAUX_PRESET bit.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Benjamin Li <benli@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Benjamin Li <benli@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This fixes a TX hang reported by Jesper Dangaard Brouer.
When an architecutre cannot provide a fully functional
64-bit atomic readq/writeq, the driver must implement
it's own. This is because only the driver can say whether
doing something like using two 32-bit reads to implement
the full 64-bit read will actually work properly.
In particular one of the issues is whether the top 32-bits
or the bottom 32-bits of the 64-bit register should be read
first. There could be side effects, and in fact that is
exactly the problem here.
The TX_CS register has counters in the upper 32-bits and
state bits in the lower 32-bits. A read clears the state
bits.
We would read the counter half before the state bit half.
That first read would clear the state bits, and then the
driver thinks that no interrupts are pending because the
interrupt indication state bits are seen clear every time.
Fix this by reading the bottom half before the upper half.
Tested-by: Jesper Dangaard Brouer <jdb@comx.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Like mac80211 did, this driver makes 'clever' use of skb->cb to pass
information along with an skb as it is requeued from the virtual device
to the physical wireless device. Unfortunately, that trick no longer
works...
Unlike mac80211, code complexity and driver apathy makes this hack
the best option we have in the short run. Hopefully someone will
eventually be motivated to code a proper fix before all the effected
hardware dies.
(Above text by me. Johannes officially disavows all knowledge of this
hack. -- JWL)
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Cc: stable@kernel.org
Signed-off-by: John W. Linville <linville@tuxdriver.com>
the Sitecom 0001 v4 with product id 0x0df6:0028, uses Realtek's
RTL8187B and work fine with new 2.6.27 driver.
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Ivan Kuten <ivan.kuten@promwad.com>
Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
When the iw_cxgb3 module's cxgb3_client "add" func gets called by the
cxgb3 module, the iwarp driver ends up calling the ethtool ops
get_drvinfo function in cxgb3 to get the fw version and other info.
Currently the iwarp driver grabs the rtnl lock around this down call
to serialize. As of 2.6.27 or so, things changed such that the rtnl
lock is held around the call to the netdev driver open function. Also
the cxgb3_client "add" function doesn't get called if the device is
down.
So, if you load cxgb3, then load iw_cxgb3, then ifconfig up the
device, the iw_cxgb3 add func gets called with the rtnl_lock held. If
you load cxgb3, ifconfig up the device, then load iw_cxgb3, the add
func gets called without the rtnl_lock held. The former causes the
deadlock, the latter does not.
In addition, there are iw_cxgb3 sysfs handlers that also can call down
into cxgb3 to gather the fw and hw versions. These can be called
concurrently on different processors and at any time. Thus we need to
push this serialization down in the cxgb3 driver get_drvinfo func.
The fix is to remove rtnl lock usage, and use a per-device lock in cxgb3.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Acked-by: Divy Le Ray <divy@chelsio.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Alexey Dobriyan