Use dev_get_by_name_rcu() instead of dev_get_by_name(),
to avoid touching device refcount in hotpath.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
All ioctls() implemented by dev_ifsioc_locked() :
SIOCGIFFLAGS, SIOCGIFMETRIC, SIOCGIFMTU, SIOCGIFHWADDR,
SIOCGIFSLAVE, SIOCGIFMAP, SIOCGIFINDEX & SIOCGIFTXQLEN
can use RCU lock instead of dev_base_lock rwlock
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can avoid touching device refcount in icmp_send(),
using dev_get_by_index_rcu()
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use dev_get_by_index_rcu() instead of __dev_get_by_index() and
dev_base_lock rwlock
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
I tested the recent unregister many changes and got a weird,
nasty and seemingly unrelasted kernel oops. Changing
unregister_netdevice_queue to use list_move_tail fixes
the problem for me.
ip link add type veth
rmmod veth
ls /sys/class/net/
showed one of the veth devices still present.
A subsequent ip link oopsed the box.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some workloads hit dev_base_lock rwlock pretty hard.
We can use RCU lookups to avoid touching this rwlock
(and avoid touching netdevice refcount)
netdevices are already freed after a RCU grace period, so this patch
adds no penalty at device dismantle time.
However, it adds a synchronize_rcu() call in dev_change_name()
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1. Add API Add k8695_get_rx_enable_bit() for get Rx interrupt
enable/status bit.
2. add some comment or document about some functions and variables.
3. update driver version to "1.02"
4. add napi_enable() and napi_disable() in open/close file method.
Signed-off-by: Figo.zhang <figo1802@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move receive processing from event handler to a tasklet.
This should help prevent hangcheck timer from going off
when RDS is under heavy load.
Signed-off-by: Andy Grover <andy.grover@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This issue was discovered by HP's Pradeep and fixed in OFED
1.3, but not fixed in later versions, since the fix's implementation
was not immediately applyable to the later code. This patch should
do the trick for 1.4+ codebases.
Signed-off-by: Andy Grover <andy.grover@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove explicit destruction of passive connection when destroying
active end of the connection. The passive end is also on the
device's connection list, and will thus be cleaned up properly.
Panic was caused by trying to clean it up twice.
Signed-off-by: Andy Grover <andy.grover@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
"At rds_ib_recv_refill_one(), it first executes atomic_read(&rds_ib_allocation)
for if-condition checking,
and then executes atomic_inc(&rds_ib_allocation) if the condition was
not satisfied.
However, if any other code which updates rds_ib_allocation executes
between these two atomic operation executions,
it seems that it may result race condition. (especially when
rds_ib_allocation + 1 == rds_ib_sysctl_max_recv_allocation)"
This patch fixes this by using atomic_inc_unless to eliminate the
possibility of allocating more than rds_ib_sysctl_max_recv_allocation
and then decrementing the count if the allocation fails. It also
makes an identical change to the iwarp transport.
Reported-by: Shin Hong <hongshin@gmail.com>
Signed-off-by: Andy Grover <andy.grover@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RDS currently supports a GET_MR sockopt to establish a
memory region (MR) for a chunk of memory. However, the fastreg
method ties a MR to a particular destination. The GET_MR_FOR_DEST
sockopt allows the remote machine to be specified, and thus
support for fastreg (aka FRWRs).
Note that this patch does *not* do all of this - it simply
implements the new sockopt in terms of the old one, so applications
can begin to use the new sockopt in preparation for cutover to
FRWRs.
Signed-off-by: Andy Grover <andy.grover@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On a 64-bit kernel, skb->tail is an offset, not a pointer. The libertas
usb driver passes it to usb_fill_bulk_urb() anyway, causing interesting
crashes. Fix that by using skb->data instead.
This highlights a problem with usb_fill_bulk_urb(). It doesn't notice
when dma_map_single() fails and return the error to its caller as it
should. In fact it _can't_ currently return the error, since it returns
void.
So this problem was showing up only at unmap time, after we'd already
suffered memory corruption by doing DMA to a bogus address.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Cc: stable@kernel.org
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
When HT debugging is enabled and we receive a DelBA
frame we print out the reason code in the wrong byte
order. Fix that so we don't get weird values printed.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
The addba timer function acquires the sta spinlock,
but at the same time we try to del_timer_sync() it
under the spinlock which can produce deadlocks.
To fix this, always del_timer_sync() the timer in
ieee80211_process_addba_resp() and add it again
after checking the conditions, if necessary.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
The patch e43419f9:
ath9k: downgrade assert in rc.c for invalid rate
downgraded an ASSERT to a WARN_ON() but also misplaced a
semicolon at the end of the second check. What this did
was force the rate control code to always return the rate
even if we should have warned about it. Since this should
not have happened anymore anyway this fix isn't critical
as the proper rate would have been returned anyway.
Cc: stable@kernel.org
Reported-by: Jiri Slaby <jirislaby@gmail.com>
Signed-off-by: Luis R. Rodriguez <lrodriguez@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
b43 allocates a bouncebuffer, if the supplied TX skb is in an invalid
memory range for DMA.
However, this is broken in that it fails to copy over some metadata to the
new skb.
This patch fixes three problems:
* Failure to adjust the ieee80211_tx_info pointer to the new buffer.
This results in a kmemcheck warning.
* Failure to copy the skb cb, which contains ieee80211_tx_info, to the new skb.
This results in breakage of various TX-status postprocessing (Rate control).
* Failure to transfer the queue mapping.
This results in the wrong queue being stopped on saturation and can result in queue overflow.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Tested-by: Christian Casteyde <casteyde.christian@free.fr>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
The IBSS code leaks a BSS struct after telling
cfg80211 about a given BSS by passing a frame.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
For non-monitor interfaces, the syntax for alloc_ieee80211/free_80211
is wrong. Because alloc_ieee80211 only creates (wiphy_new) a wiphy, but
free_80211() does wiphy_unregister() also. This is only correct when
the later wiphy_register() is called successfully, which apparently
is not the case for your fw doesn't exist one.
Signed-off-by: Zhu Yi <yi.zhu@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
- Don't call rtnl_link_unregister if rtnl_link_register fails
- Set .priv_size so we aren't stomping on uninitialized memory
when we use netdev_priv, on bond devices created with
ip link add type bond.
Signed-off-by: Eric W. Biederman <ebiederm@aristanetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This implements a basic set of rtnl link ops and takes advantage of
the fact that rtnl_link_unregister kills all of the surviving
devices to all us to kill bond_free_all. A module alias
is added so ip link add can pull in the bonding module.
Signed-off-by: Eric W. Biederman <ebiederm@aristanetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Manually inline the code from bond_deinit to bond_uninit. bond_uninit
is the only caller and it is short.
Move the call of bond_release_all from the netdev notifier into
bond_uninit. The call site is effectively the same and performing
the call explicitly allows all the paths for destroying a
bonding device to behave the same way.
Signed-off-by: Eric W. Biederman <ebiederm@aristanetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Stop calling dev_get_by_name to see if the bond device already
exists. register_netdevice already does that.
Stop calling bond_deinit if register_netdevice fails as bond_uninit
is guaranteed to be called if bond_init succeeds.
Signed-off-by: Eric W. Biederman <ebiederm@aristanetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch delegates the work of creating the sysfs groups
to the netdev layer and ultimately to the device layer. This
closes races between uevents.
Signed-off-by: Eric W. Biederman <ebiederm@aristanetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This isn't beautifully abstracted, but it is simple,
simplifies uses and so far is only needed for the bonding driver.
Signed-off-by: Eric W. Biederman <ebiederm@aristanetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Nathan Neulinger noticed that gretap devices get their MAC address
from the local IP address, which results in invalid MAC addresses
half of the time.
This is because gretap is still using the tunnel netdev ops rather
than the correct tap netdev ops struct.
This patch also fixes changelink to not clobber the MAC address
for the gretap case.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Stephen Hemminger <shemminger@vyatta.com>
Tested-by: Nathan Neulinger <nneul@mst.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Before bringing up a sky2 interface up ethtool reports
"Link detected: yes". Do as ixgbe does and netif_carrier_off() on
probe().
Signed-off-by: Brandon Philips <bphilips@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
On UDP sockets, we must call skb_free_datagram() with socket locked,
or risk sk_forward_alloc corruption. This requirement is not respected
in SUNRPC.
Add a convenient helper, skb_free_datagram_locked() and use it in SUNRPC
Reported-by: Francis Moreau <francis.moro@gmail.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Small cleanup of __dev_get_by_name() and __dev_get_by_index()
to use hlist_for_each_entry() : They'll look like their _rcu variant.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit 23289a37e2
(net: add a list_head parameter to dellink() method),
I forgot to actually use this parameter in veth_dellink.
I remember feeling a bit uncomfortable about veth_close(),
because it does :
netif_carrier_off(dev);
netif_carrier_off(priv->peer);
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The temporary copy of the VLAN group is not neccessary since the lower device
is already in the process of being unregistered, if it was neccessary the
memset of the global group would introduce a race condition.
With this removed, the changes to the original code are only a few lines, so
remove the new function and move the code back into vlan_device_event().
Signed-off-by: Patrick McHardy <kaber@trash.net>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For USB 3.0 it is necessary that all drivers use the standard
API to reset a configuration. This removes a home-grown
implementation.
Signed-off-by: Oliver Neukum <oliver@neukum.org>
Hi David,
please take this for the next merge window.
Regards
Oliver
Signed-off-by: David S. Miller <davem@davemloft.net>
struct ax25_ctl_struct member `arg' is unsigned and cannot be less
than 0.
Signed-off-by: Roel Kluin <roel.kluin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tentative support for newer Marvell hardware including
the Yukon-2 Optima chip. Do not have hatdware to test this yet,
code is based on vendor driver.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Changes related to support of Yukon supreme chip.
Don't have this chip version to test on,
these are reverse engineered from the vendor (GPL) driver.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Program the receive pause thresholds differently depending on
chip version. This cloned from from the vendor (GPL) driver.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds infrastructure for the newer chip versions and workarounds.
Extracted from the vendor (GPL) driver.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is a new ID that just showed up in latest vendor driver.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
pcnet_cs,serial_cs:
add cis of PreMax ethernet pcmcia card,
and some Sierra Wireless serial card(AC555, AC7xx, AC8xx).
use PROD_ID for AC7xx, because MANF_ID of AC7xx and AC8xx are the same.
Signed-off-by: Ken Kawasaki <ken_kawasaki@spring.nifty.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
r8169 card drop incoming VLAN tagged MTU byte large jumbo frames
It looks to compare current and maximal packet sizes hardware use
'<' operator, not '<='.
Bug introduced by commit fdd7b4c330
("r8169: fix crash when large packets are received")
Signed-off-by: Raimonds Cicans <ray@apollo.lv>
Signed-off-by: David S. Miller <davem@davemloft.net>
Policy routing is not looked up by mark on reverse path filtering.
This fixes it.
Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca>
Signed-off-by: David S. Miller <davem@davemloft.net>
struct sk_buff kmemcheck annotations enlarged this structure by 8/16 bytes
Fix this by moving 'protocol' inside flags1 bitfield,
and queue_mapping inside flags2 bitfield.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch reworks a previous workaround (commit 7d3cabbcc) for an issue
in hardware where noise on the interconnect between the MAC and PHY could
be generated by a lower power mode (K1) at 1000Mbps resulting in bad
packets. Disable K1 while at 1000 Mbps but keep it enabled for 10/100Mbps
and when the cable is disconnected. The original version of this
workaround was found to be incomplete.
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On PCH-based (82577/82578) and some ICH8-based parts (82566) there is an
issue with the hardware automatically configuring the PHY with contents
from the EEPROM after the PHY is reset, so do the configuration by the
driver instead. This was already similarly done for some 82566 parts in
e1000_phy_hw_reset_ich8lan() but needs to be done after other resets,
so move the PHY configuration code to its own function and call after
all PHY resets.
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A change in how PHYs are electrically isolated caused all PHYs to be
isolated followed by reverting that isolation for the selected PHY.
Unfortunately, isolating the selected PHY for even a short period of
time can result in DHCP negotiation taking more than 10 seconds on certain
embedded configurations delaying boot time as reported by Bernhard Kaindl.
This patch reverts the change to how PHYs are isolated yet still works
around the issue for 82552 needing the selected PHY's BMCR register to
be written after the unused PHYs are isolated. This code is moved below
the setting of nic->phy ID in order to do the 82552-specific workaround.
Cc: Bernhard Kaindl <bernhard.kaindl@gmx.net>
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet