Apply the cgroup of the owner task to the created vhost worker.

Based on patches from Sridhar Samudrala's and Tejun Heo.
Later we'll need to also apply cpumask and probably priority
of the owner process.

Discussion on the best way to do this is still ongoing.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Sridhar Samudrala <samudrala.sridhar@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>

Replace vhost_workqueue with per-vhost kthread.  Other than callback
argument change from struct work_struct * to struct vhost_work *,
there's no visible change to vhost_poll_*() interface.

This conversion is to make each vhost use a dedicated kthread so that
resource control via cgroup can be applied.

Partially based on Sridhar Samudrala's patch.

* Updated to use sub structure vhost_work instead of directly using
  vhost_poll at Michael's suggestion.

* Added flusher wake_up() optimization at Michael's suggestion.

Changes by MST:
* Converted atomics/barrier use to a spinlock.
* Create thread on SET_OWNER
* Fix flushing
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Cc: Sridhar Samudrala <samudrala.sridhar@gmail.com>

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

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

Use for_each_pci_dev() to simplify the code.
Signed-off-by: NKulikov Vasiliy <segooon@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add and use a few neatening macros
Remove PFX
Add #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
Convert printk(KERN_ERR to pr_err(

$ size drivers/net/qlge/built-in.o.*
  text	   data	    bss	    dec	    hex	filename
 116456	   2312	  25712	 144480	  23460	drivers/net/qlge/built-in.o.old
 114909	   2312	  25728	 142949	  22e65	drivers/net/qlge/built-in.o.new
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Get rid of own implementation of hex_to_bin().
Signed-off-by: NAndy Shevchenko <ext-andriy.shevchenko@nokia.com>
Acked-by: NDivy Le Ray <divy@chelsio.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NGiuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix bug in setup_sge_queues() where we were incorrectly only allocating a
single "Queue Set" for MSI mode.
Signed-off-by: NCasey Leedom <leedom@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix off-by-one error in checking for the end of the mailbox response delay
array.  We ended up walking off the end and, if we were unlucky, we'd end up
pulling in a 0 and never terminate the mailbox response delay loop ...
Signed-off-by: NCasey Leedom <leedom@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NMichael Chan <mchan@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

smp_mb() inside bnx2_tx_avail() is used twice in the normal
bnx2_start_xmit() path (see illustration below).  The full memory
barrier is only necessary during race conditions with tx completion.
We can speed up the tx path by replacing smp_mb() in bnx2_tx_avail()
with a compiler barrier.  The compiler barrier is to force the
compiler to fetch the tx_prod and tx_cons from memory.

In the race condition between bnx2_start_xmit() and bnx2_tx_int(),
we have the following situation:

bnx2_start_xmit()                       bnx2_tx_int()
    if (!bnx2_tx_avail())
            BUG();

    ...

    if (!bnx2_tx_avail())
            netif_tx_stop_queue();          update_tx_index();
            smp_mb();                       smp_mb();
            if (bnx2_tx_avail())            if (netif_tx_queue_stopped() &&
                    netif_tx_wake_queue();      bnx2_tx_avail())

With smp_mb() removed from bnx2_tx_avail(), we need to add smp_mb() to
bnx2_start_xmit() as shown above to properly order netif_tx_stop_queue()
and bnx2_tx_avail() to check the ring index.  If it is not strictly
ordered, the tx queue can be stopped forever.

This improves performance by about 5% with 2 ports running bi-directional
64-byte packets.
Reviewed-by: NBenjamin Li <benli@broadcom.com>
Reviewed-by: NMatt Carlson <mcarlson@broadcom.com>
Signed-off-by: NMichael Chan <mchan@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Based on original patch by Breno Leitão <leitao@linux.vnet.ibm.com>.

Allocate the actual number of vectors and make use of fewer vectors
if pci_enable_msix() returns > 0.  We must allocate one additional
vector for the cnic driver.

Cc: Breno Leitão <leitao@linux.vnet.ibm.com>
Reviewed-by: NBenjamin Li <benli@broadcom.com>
Reviewed-by: NMatt Carlson <mcarlson@broadcom.com>
Signed-off-by: NMichael Chan <mchan@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We were using the wrong tx multicast counter instead of the rx multicast
counter.
Reported-by: NPeter Snellman <peter.snellman@cinnober.com>
Reviewed-by: NBenjamin Li <benli@broadcom.com>
Reviewed-by: NMatt Carlson <mcarlson@broadcom.com>
Signed-off-by: NMichael Chan <mchan@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Bump the version string to better reflect what is in the driver.
Signed-off-by: NDon Skidmore <donald.c.skidmore@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The FCoE protocol stack may hold a lock when this gets called.
Signed-off-by: NYi Zou <yi.zou@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When FCoE is disabled, there is a race condition that FCoE offload is
turned off but the FCoE protocol driver is still queuing I/O thinking
offload support still exists. This patch toggles off corresponding FCoE
netdev feature flags and notify the FCoE stack first, allowing FCoE
protocol stack driver to update its flags upon NETDEV_FEAT_CHANGE so no
I/O will be using offload.

Also, indicate FCoE offload flags in vlan_features in ixgbe_probe once
and do not toggle them in ixgbe_fcoe_enable/disable so when FCoE is
created on the VLAN interface, vlan_transfer_features() would properly
update the VLAN netdev features flag and notify the FCoE protocol driver
for NETDEV_FEAT_CHANGE.
Signed-off-by: NYi Zou <yi.zou@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change removes UDP from the supported protocols for RSS hashing.  The
reason for removing this protocol is because IP fragmentation was causing a
network flow to be broken into two streams, one for fragmented, and one for
non-fragmented and this in turn was causing out-of-order issues.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Acked-by: NDon Skidmore <donald.c.skidmore@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Set the DPF bit when PFC is enabled.  This will discard
PFC frames so they do not get passed up the stack.

The DPF bit is set for flow control, but not priority
flow control this brings pfc inline with fc.
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Signed-off-by: NDon Skidmore <donald.c.skidmore@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change makes it possible to limit the number of descriptors down to 48
per ring.  The reason for this change is to address a variation on hardware
errata 10 for 82546GB in which descriptors will be lost if more than 32
descriptors are fetched and the PCI-X MRBC is 512.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NEmil Tantilov <emil.s.tantilov@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/82596.c: In function 'i596_open':
drivers/net/82596.c:1044: warning: label 'err_irq_dev' defined but not used

Caused by "82596: free resources on error"
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As reported by Andrew:

drivers/net/ks8842.c: In function 'ks8842_handle_rx':
drivers/net/ks8842.c:428: warning: 'status' may be used uninitialized in this function

Just use the 32-bit status for all reads, and delete the useless
cast to 'int' when reading a u16 into 'len'.
Reported-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

On SMP systems, the SMSC911x registers may be accessed by multiple CPUs
and this seems to put the chip in an inconsistent state. The patch adds
spinlocks to the smsc911x_reg_read, smsc911x_reg_write,
smsc911x_rx_readfifo and smsc911x_tx_writefifo functions.
Signed-off-by: NCatalin Marinas <catalin.marinas@arm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/bonding/bond_main.c:179:12: warning: ‘disable_netpoll’
defined but not used
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ARCH_PNX010X doesn't exist in Kconfig, therefore removing all
references for it from the source code/Kconfig.
Signed-off-by: NChristoph Egger <siccegge@cs.fau.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Respect the interrupt type set in VM configuration.

When interrupt type is not auto, do not ignore the interrupt type set from
VM configuration.
Signed-off-by: NShreyas Bhatewara <sbhatewara@vmware.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Hold rtnl_lock to get the right link state.

While asynchronously resetting the device, hold rtnl_lock to get the
right value from netif_running. If a reset is scheduled, and the device
goes thru close and open, it may happen that reset and open may run in
parallel. Holding rtnl_lock will avoid this.
Signed-off-by: NShreyas Bhatewara <sbhatewara@vmware.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After commit ad1afb00 (vlan_dev: VLAN 0 should be treated
as "no vlan tag" (802.1p packet)),
bond_inet6addr_event() might be called with a NULL bond->vlgrp pointer, and
a non empty bond->vlan_list. vlan_group_get_device() is dereferencing a NULL pointer.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The memory for the private data is allocated using kzalloc in
alloc_etherdev (or alloc_netdev_mq respectively) so there is no need to
set it to 0 again.
Signed-off-by: NTobias Klauser <tklauser@distanz.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds a new networking option to allow hardware time stamps
from PHY devices. When enabled, likely candidates among incoming and
outgoing network packets are offered to the PHY driver for possible
time stamping. When accepted by the PHY driver, incoming packets are
deferred for later delivery by the driver.

The patch also adds phylib driver methods for the SIOCSHWTSTAMP ioctl
and callbacks for transmit and receive time stamping. Drivers may
optionally implement these functions.
Signed-off-by: NRichard Cochran <richard.cochran@omicron.at>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The phy_mii_ioctl() function unnecessarily throws away the original ifreq.
We need access to the ifreq in order to support PHYs that can perform
hardware time stamping.

Two maverick drivers filter the ioctl commands passed to phy_mii_ioctl().
This is unnecessary since phylib will check the command in any case.
Signed-off-by: NRichard Cochran <richard.cochran@omicron.at>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

probe_irq_off() returns the first irq found or if two irqs are found
then it returns the negative of the first irq found.  We can cast
dev->irq to an int so that the test for negative values works.
Signed-off-by: NDan Carpenter <error27@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

pci_get_domain_bus_and_slot: caller must decrement the
reference count by calling pci_dev_put().
Signed-off-by: NAmit Kumar Salecha <amit.salecha@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change initializes the state of link at the time when driver is
loaded. The ethtool output for 'link detected' and 'link speed'
is thus valid even before the interface is brought up.
Signed-off-by: NShreyas Bhatewara <sbhatewara@vmware.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use DMA API as PCI equivalents will be deprecated. This change also allow
to allocate with GFP_KERNEL in some places.
Signed-off-by: NStanislaw Gruszka <sgruszka@redhat.com>
Acked-by: NMichael Chan <mchan@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NStanislaw Gruszka <sgruszka@redhat.com>
Acked-by: NMichael Chan <mchan@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The order of freeing the IRQ and freeing the device in firmware
in ibmveth_close can cause the adapter to become unusable after a
subsequent ibmveth_open.  Only a reboot of the OS will make the
network device usable again. This is seen when cycling the adapter
up and down while there is network activity.

There is a window where an IRQ will be left unserviced (H_EOI will not
be called).  The solution is to make a VIO_IRQ_DISABLE h_call, free the
device with firmware, and then call free_irq.
Signed-off-by: NRobert Jennings <rcj@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The rt2x00dev->intf_work workqueue is never initialized when a driver is
probed for a non-existent device (in this case rt2500usb). On such a
path we call rt2x00lib_remove_dev() to free any resources initialized
during the probe before we use INIT_WORK to initialize the workqueue.
This causes lockdep to get confused since the lock used in the workqueue
hasn't been initialized yet but is now being acquired during
cancel_work_sync() called by rt2x00lib_remove_dev().

Fix this by initializing the workqueue first before we attempt to probe
the device. This should make lockdep happy and avoid breaking any
assumptions about how the library cleans up after a probe fails.

phy0 -> rt2x00lib_probe_dev: Error - Failed to allocate device.
INFO: trying to register non-static key.
the code is fine but needs lockdep annotation.
turning off the locking correctness validator.
Pid: 2027, comm: modprobe Not tainted 2.6.35-rc5+ #60
Call Trace:
 [<ffffffff8105fe59>] register_lock_class+0x152/0x31f
 [<ffffffff81344a00>] ? usb_control_msg+0xd5/0x111
 [<ffffffff81061bde>] __lock_acquire+0xce/0xcf4
 [<ffffffff8105f6fd>] ? trace_hardirqs_off+0xd/0xf
 [<ffffffff81492aef>] ?  _raw_spin_unlock_irqrestore+0x33/0x41
 [<ffffffff810628d5>] lock_acquire+0xd1/0xf7
 [<ffffffff8104f037>] ? __cancel_work_timer+0x99/0x17e
 [<ffffffff8104f06e>] __cancel_work_timer+0xd0/0x17e
 [<ffffffff8104f037>] ? __cancel_work_timer+0x99/0x17e
 [<ffffffff8104f136>] cancel_work_sync+0xb/0xd
 [<ffffffffa0096675>] rt2x00lib_remove_dev+0x25/0xb0 [rt2x00lib]
 [<ffffffffa0096bf7>] rt2x00lib_probe_dev+0x380/0x3ed [rt2x00lib]
 [<ffffffff811d78a7>] ? __raw_spin_lock_init+0x31/0x52
 [<ffffffffa00bbd2c>] ? T.676+0xe/0x10 [rt2x00usb]
 [<ffffffffa00bbe4f>] rt2x00usb_probe+0x121/0x15e [rt2x00usb]
 [<ffffffff813468bd>] usb_probe_interface+0x151/0x19e
 [<ffffffff812ea08e>] driver_probe_device+0xa7/0x136
 [<ffffffff812ea167>] __driver_attach+0x4a/0x66
 [<ffffffff812ea11d>] ? __driver_attach+0x0/0x66
 [<ffffffff812e96ca>] bus_for_each_dev+0x54/0x89
 [<ffffffff812e9efd>] driver_attach+0x19/0x1b
 [<ffffffff812e9b64>] bus_add_driver+0xb4/0x204
 [<ffffffff812ea41b>] driver_register+0x98/0x109
 [<ffffffff813465dd>] usb_register_driver+0xb2/0x173
 [<ffffffffa00ca000>] ? rt2500usb_init+0x0/0x20 [rt2500usb]
 [<ffffffffa00ca01e>] rt2500usb_init+0x1e/0x20 [rt2500usb]
 [<ffffffff81000203>] do_one_initcall+0x6d/0x17a
 [<ffffffff8106cae8>] sys_init_module+0x9c/0x1e0
 [<ffffffff8100296b>] system_call_fastpath+0x16/0x1b
Signed-off-by: NStephen Boyd <bebarino@gmail.com>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

Guest can trigger packet truncation by posting
a very short buffer and disabling buffer merging.
Convert pr_err to pr_debug to avoid log from filling
up when this happens.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Fix SGE resource resource deallocation bug.  Forgot to increment the RXQ and
TXQ cursors in the loop ...
Signed-off-by: NCasey Leedom <leedom@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>