If any VF is assigned as the PF is unloaded, do not attempt to
remove its vport or the vswitch.  These will be removed if the
driver binds to the PF again, as an entity reset occurs during
probe.

A 'force' flag is added to efx_ef10_pci_sriov_disable() to
distinguish between disabling SR-IOV and driver unload.
SR-IOV cannot be disabled if VFs are assigned to guests.

If the PF driver is unloaded while VFs are assigned, the driver
may try to bind to the VF again at a later point if the driver
has been reloaded and the VF returns to the same domain as the PF.
In this case, the PF will not have a VF data structure, so the VF
can check this and drop out of probe early.

In this case, efx->vf_count will be zero but VFs will be present.
The user is advised to remove the VF and re-create it. The check
at the beginning of efx_ef10_pci_sriov_disable() that
efx->vf_count is non-zero is removed to allow SR-IOV to be
disabled in this case. Also, if the PF driver is unloaded, it
will disable SR-IOV to remove these unknown VFs.

By not disabling bus-mastering if VFs are still assigned, the VF
will continue to pass traffic after the PF has been removed.

When using the max_vfs module parameter, if VFs are already
present do not try to initialise any more.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When the driver unloads, force the unbind and removal of any
VFs in the host with the PF.  The PF cannot remove vports and
vswitches if they are still being used by a VF driver, and when
unloading the sfc driver the removal order is not guaranteed,
so the instruction from the PF to the VF to unbind enforces a
suitable ordering so that vswitches and vports can be removed.

As a result of this, manually unbinding the driver from a single
PF will result in all of its VFs in the host also being removed.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The ifenslave command to set up a bond runs in an atomic
context, and it queries the stats on the devices that are
being enslaved. A VF needs to make an MCDI call to update
its stats, which is not allowed in atomic context.

The releasing of the stats_lock is moved to the beginning of
the VF stats update function so that in_interrupt() can be
used; it must be taken again before returning from this
function.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The raw_mask array is not initialised, so it needs to be
explicitly set to zero in the 'else' branch.

If the EVB capability is not present, a port cannot have multiple
functions so the per-port MAC stats are correct and should match
the corresponding vadaptor stats, so this redundancy can be
removed from the ethtool stats output.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

MC_CMD_MAC_STATS can be called on a function before a
vadaptor has been created, as the kernel can call into this
through ndo_get_stats/ndo_get_stats64.

If MC_CMD_MAC_STATS is called before the DMA queues have been
setup, so that a vadaptor has not been created yet, firmware
will return ENOENT. This is expected, so suppress the MCDI
error message in this case.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The netdevice statistics (in /proc/net/dev) are per-function
stats so they must use the vadaptor stats. Change the use of
MAC stats to vadaptor stats, and remove any statistics that
can only be measured per-port.  All stats that are removed
will be shown as zeroes when these statistics are displayed.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Firmware does not support a periodic DMA of vadaptor-stats
on VFs, so only update the stats buffer when stats are
requested (when running "ethtool -S" or an ip/ifconfig
command that reports stats).
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

All interfaces will display vadaptor statistics, so set all the
relevant bits in the stats bitmask. Only functions with the
LINKCTRL flag will see other stats, including (per-port) MAC stats.

The vadaptor stats are from rx_unicast to tx_overflow.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The port-id must be known so that the RMON level can be
set for the collection of vadapter stats.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The MAC stats are per-port and will only be displayed on the PF
with control of the link (one per physical port). Vadapter stats
will also be displayed for this PF, so distinguish the MAC stats
by adding a prefix of "port_".
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

On  every adapter there will be one primary PF per adaptor and
one link control PF per port.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change is a stylistic change and does not affect
functionality.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In the case where we have multiple functions (PFs and VFs), this
sysfs entry is useful to identify the physical port corresponding
to the function we are interested in.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

GFP_KERNEL should be used in the thread context
Signed-off-by: NAleksey Makarov <aleksey.makarov@caviumnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This fixes a coccinelle warning:

coccinelle warnings: (new ones prefixed by >>)

>> drivers/net/ethernet/cavium/thunder/nicvf_queues.c:360:1-11: alloc
>> with no test, possible model on line 367

vim +360 drivers/net/ethernet/cavium/thunder/nicvf_queues.c

   354		err = nicvf_alloc_q_desc_mem(nic, &sq->dmem, q_len,
SND_QUEUE_DESC_SIZE,
   355					     NICVF_SQ_BASE_ALIGN_BYTES);
   356		if (err)
   357			return err;
   358
   359		sq->desc = sq->dmem.base;
 > 360		sq->skbuff = kcalloc(q_len, sizeof(u64), GFP_ATOMIC);
   361		sq->head = 0;
   362		sq->tail = 0;
   363		atomic_set(&sq->free_cnt, q_len - 1);
   364		sq->thresh = SND_QUEUE_THRESH;
   365
   366		/* Preallocate memory for TSO segment's header */
 > 367		sq->tso_hdrs = dma_alloc_coherent(&nic->pdev->dev,
   368						  q_len *
TSO_HEADER_SIZE,
   369						  &sq->tso_hdrs_phys,
GFP_KERNEL);
   370		if (!sq->tso_hdrs)
Reported-by: Nkbuild test robot <fengguang.wu@intel.com>
Signed-off-by: NAleksey Makarov <aleksey.makarov@caviumnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

No need to cast void* to u8*: pointer arithmetics
works same way for both.
Signed-off-by: NAleksey Makarov <aleksey.makarov@caviumnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This fixes a copypaste bug that was discovered by a static analysis
tool:

The patch 4863dea3: "net: Adding support for Cavium ThunderX
network controller" from May 26, 2015, leads to the following static
checker warning:

        drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c:517
nicvf_set_rxfh()
        warn: we tested 'hkey' before and it was 'false'

drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
   506          /* We do not allow change in unsupported parameters */
   507          if (hkey ||
                    ^^^^
We return here.

   508              (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc !=
ETH_RSS_HASH_TOP))
   509                  return -EOPNOTSUPP;
   510
   511          rss->enable = true;
   512          if (indir) {
   513                  for (idx = 0; idx < rss->rss_size; idx++)
   514                          rss->ind_tbl[idx] = indir[idx];
   515          }
   516
   517          if (hkey) {
                    ^^^^
So this is dead code.

   518                  memcpy(rss->key, hkey, RSS_HASH_KEY_SIZE *
sizeof(u64));
   519                  nicvf_set_rss_key(nic);
   520          }
   521
   522          nicvf_config_rss(nic);
   523          return 0;
   524  }

regards,
dan carpenter
Reported-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NAleksey Makarov <aleksey.makarov@caviumnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This fixes sparse messages like this:

drivers/net/ethernet/cavium/thunder/nicvf_main.c:1141:26: sparse: symbol
'nicvf_get_stats64' was not declared. Should it be static?

Also remove unused declarations
Reported-by: Nkbuild test robot <fengguang.wu@intel.com>
Signed-off-by: NAleksey Makarov <aleksey.makarov@caviumnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

They were left from development stage
Reported-by: Nkbuild test robot <fengguang.wu@intel.com>
Signed-off-by: NAleksey Makarov <aleksey.makarov@caviumnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This fixes sparse message:

drivers/net/ethernet/cavium/thunder/nicvf_main.c:385:40: sparse: cast to
restricted __le64
Reported-by: Nkbuild test robot <fengguang.wu@intel.com>
Signed-off-by: NAleksey Makarov <aleksey.makarov@caviumnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This fixes sparse message:

drivers/net/ethernet/cavium/thunder/nicvf_main.c:153:25: sparse: cast to
restricted __le64
Reported-by: Nkbuild test robot <fengguang.wu@intel.com>
Signed-off-by: NAleksey Makarov <aleksey.makarov@caviumnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This fixes sparse messages like this:

drivers/net/ethernet/cavium/thunder/thunder_bgx.c:897:24: sparse:
constant 0x300000000000 is so big it is long
Reported-by: Nkbuild test robot <fengguang.wu@intel.com>
Signed-off-by: NAleksey Makarov <aleksey.makarov@caviumnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There are duplicate NODE_ID macro definitions. Move all of them to
nic.h for usage in nic and bgx driver and introduce nic_get_node_id()
helper function.

This patch also fixes 64bit mask which should have been ULL by
reworking the node calculation.
Signed-off-by: NRobert Richter <rrichter@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adds vnic driver register related changes for T6 adapter
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adds NIC driver related changes for T6 adapter. Register related
changes, MC related changes, VF related changes, doorbell related
changes, debugfs changes, etc
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adds new macro is_t6 and adds the register address range for T6 adapter
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Remove support for legacy ndo ops
.ndo_vlan_rx_add_vid/.ndo_vlan_rx_kill_vid.  Rocker will use
bridge_setlink/dellink exclusively for VLAN add/del operations.

The legacy ops are needed if using 8021q driver module to setup VLANs on
the port.  But an alternative exists in using bridge_setlink/delink to
setup VLANs, which doesn't depend on 8021q module.  So rocker will switch
to the newer setlink/dellink ops.  VLANs can added/delete from the port,
regardless if port is bridged or not, using the bridge commands:

	bridge vlan [add|del] vid VID dev DEV self

(Yes, I agree it's confusing to use the "bridge" command to set a VLAN on a
non-bridged port).

Using setlink/dellink over legacy ops let's us handle the stacked driver
case automatically.  It's built-in.  setlink also pass additional flags
(PVID, egress untagged) that aren't available with the legacy ops.
Signed-off-by: NScott Feldman <sfeldma@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When the port joins a bridge, the port's internal VLAN ID needs to change
to the bridge's internal VLAN ID.  Likewise, when leaving the bridge, the
internal VLAN ID reverts back the port's original internal VLAN ID.  (The
internal VLAN ID is used by device to internally mark untagged pkts with
some VLAN, which will eventually be removed on egress...think PVID).  When
the internal VLAN ID changes, we need to update the VLAN table entries and
the router MAC entries for IP/IPv6 to reflect the new internal VLAN ID.

This patch makes use of the common rocker_port_vlan_add/del functions to
make sure the tables are updated for the current internal VLAN ID.
Signed-off-by: NScott Feldman <sfeldma@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

On port probe, install by default untagged VLAN support.  This is
equivalent to running the command:

	bridge vlan add vid 0 dev DEV self

A user could, if they wanted, manaully removing untagged support from the
port by running the command:

	bridge vlan del vid 0 dev DEV self

But installing it by default on port initialization gives the normal
expected behavior.
Signed-off-by: NScott Feldman <sfeldma@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Basic house keeping: If there is an error adding the router MAC for this
vlan, removing the just installed VLAN table entry to leave device in same
state as before failure.
Signed-off-by: NScott Feldman <sfeldma@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When allocating the array of rocker port pointers, zero the array values so
we can test for !NULL to see if port is allocated/registered.  We'll need
this later when installing untagged VLAN support for each port, during port
probe.  It's a long story, but to install a VLAN (vid=0 for untagged, in
this case) on a port, we'll need to scan other ports to see if the VLAN
group for that VLAN has been setup.  To scan the other ports, we need to
walk the port array.
Signed-off-by: NScott Feldman <sfeldma@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Remove unused function cxgb4_enable_db_coalescing() and
cxgb4_disable_db_coalescing()
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The rocker (switch) of a rocker_port may be trivially obtained from
the latter it seems cleaner not to pass the former to a function when
the latter is being passed anyway.

rocker_port_rx_proc() is omitted from this change as it is a hot path case.
Signed-off-by: NSimon Horman <simon.horman@netronome.com>
Acked-by: NScott Feldman <sfeldma@gmail.com>
Acked-by: NAndy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The driver allocates one page for each buffer on the rx ring, which is
too much on architectures like ppc64 and can cause unexpected allocation
failures when the system is under stress.  Now, we keep a memory pool
per queue, and if the architecture's PAGE_SIZE is greater than 4k, we
fragment pages and assign each 4k segment to a ring element, which
reduces the overall memory consumption on such architectures.  This
helps avoiding errors like the example below:

[bnx2x_alloc_rx_sge:435(eth1)]Can't alloc sge
[c00000037ffeb900] [d000000075eddeb4] .bnx2x_alloc_rx_sge+0x44/0x200 [bnx2x]
[c00000037ffeb9b0] [d000000075ee0b34] .bnx2x_fill_frag_skb+0x1ac/0x460 [bnx2x]
[c00000037ffebac0] [d000000075ee11f0] .bnx2x_tpa_stop+0x160/0x2e8 [bnx2x]
[c00000037ffebb90] [d000000075ee1560] .bnx2x_rx_int+0x1e8/0xc30 [bnx2x]
[c00000037ffebcd0] [d000000075ee2084] .bnx2x_poll+0xdc/0x3d8 [bnx2x] (unreliable)
Signed-off-by: NGabriel Krisman Bertazi <krisman@linux.vnet.ibm.com>
Acked-by: NYuval Mintz <Yuval.Mintz@qlogic.com>
Reviewed-by: NLino Sanfilippo <LinoSanfilippo@gmx.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit dff173de ("bnx2x: Fix statistics locking scheme") changed the
bnx2x locking around statistics state into using a mutex - but the lock
is being accessed via a timer which is forbidden.

[If compiled with CONFIG_DEBUG_MUTEXES, logs show a warning about
accessing the mutex in interrupt context]

This moves the implementation into using a semaphore [with size '1']
instead.
Signed-off-by: NYuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: NAriel Elior <Ariel.Elior@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When we come to tear things down in netback_remove() and generate the
uevent it is possible that the xenstore directory has already been
removed (details below).

In such cases netback_uevent() won't be able to read the hotplug
script and will write a xenstore error node.

A recent change to the hypervisor exposed this race such that we now
sometimes lose it (where apparently we didn't ever before).

Instead read the hotplug script configuration during setup and use it
for the lifetime of the backend device.

The apparently more obvious fix of moving the transition to
state=Closed in netback_remove() to after the uevent does not work
because it is possible that we are already in state=Closed (in
reaction to the guest having disconnected as it shutdown). Being
already in Closed means the toolstack is at liberty to start tearing
down the xenstore directories. In principal it might be possible to
arrange to unregister the device sooner (e.g on transition to Closing)
such that xenstore would still be there but this state machine is
fragile and prone to anger...

A modern Xen system only relies on the hotplug uevent for driver
domains, when the backend is in the same domain as the toolstack it
will run the necessary setup/teardown directly in the correct sequence
wrt xenstore changes.
Signed-off-by: NIan Campbell <ian.campbell@citrix.com>
Acked-by: NWei Liu <wei.liu2@citrix.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>