The s6000 Xtensa support has been removed from the kernel in
4006e565. There are no other chips using this driver.

While the Mentor/Alcatel PE-MCXMAC IP core is also used in other
designs (Freescale Gianfar/UCC, QLogic NetXen, Solarflare, Agere
ET-1310, Netlogic XLR/XLS), none of these use this driver as it
heavily depends on the s6000 DMA engine. In fact, there is no
code sharing across any of the aforementioned devices.
Signed-off-by: NDaniel Glöckner <dg@emlix.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Remove the function port_cfg_dis_learn() that is not used anywhere.

This was partially found by using a static code analysis program called cppcheck.
Signed-off-by: NRickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

During driver load in tg3_init_one, if the driver detects DMA activity before
intializing the chip tg3_halt is called. As part of tg3_halt interrupts are
disabled using routine tg3_disable_ints. This routine was using mailbox value
which was not initialized (default value is 0). As a result driver was writing
0x00000001 to pci config space register 0, which is the vendor id / device id.

This driver bug was exposed because of the commit a7877b17a667 (PCI: Check only
the Vendor ID to identify Configuration Request Retry). Also this issue is only
seen in older generation chipsets like 5722 because config space write to offset
0 from driver is possible. The newer generation chips ignore writes to offset 0.
Also without commit a7877b17a667, for these older chips when a GRC reset is
issued the Bootcode would reprogram the vendor id/device id, which is the reason
this bug was masked earlier.

Fixed by initializing the interrupt mailbox registers before calling tg3_halt.

Please queue for -stable.
Reported-by: NNils Holland <nholland@tisys.org>
Reported-by: NMarcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: NPrashant Sreedharan <prashant@broadcom.com>
Signed-off-by: NMichael Chan <mchan@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The changed names are union fields with the same size, so the existing code
still works. But, we now update these variables to the correct names.
Signed-off-by: NHaiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: NK. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The commit d75b1ade (net: less
interrupt masking in NAPI) breaks virtio_net in an insidious way.

It is now required that if the entire budget is consumed when poll
returns, the napi poll_list must remain empty.  However, like some
other drivers virtio_net tries to do a last-ditch check and if
there is more work it will call napi_schedule and then immediately
process some of this new work.  Should the entire budget be consumed
while processing such new work then we will violate the new caller
contract.

This patch fixes this by not touching any work when we reschedule
in virtio_net.

The worst part of this bug is that the list corruption causes other
napi users to be moved off-list.  In my case I was chasing a stall
in IPsec (IPsec uses netif_rx) and I only belatedly realised that it
was virtio_net which caused the stall even though the virtio_net
poll was still functioning perfectly after IPsec stalled.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Acked-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Both stmmac_open() and stmmac_resume() call stmmac_hw_setup(), and
stmmac_hw_setup() call stmmac_init_ptp() unconditionally. However, only
stmmac_release() calls stmmac_release_ptp(). Since stmmac_suspend()
doesn't call stmmac_release_ptp(), stmmac_resume() also needn't call
stmmac_init_ptp().

This patch also fix a "scheduling while atomic" problem when resume
from suspend/hibernation. Because stmmac_init_ptp() will trigger
scheduling while stmmac_resume() hold a spinlock.

Callgraph of "scheduling while atomic":
stmmac_resume() --> stmmac_hw_setup() --> stmmac_init_ptp() -->
stmmac_ptp_register() --> ptp_clock_register() --> device_create() -->
device_create_groups_vargs() --> device_add() --> devtmpfs_create_node()
--> wait_for_common() --> schedule_timeout() --> __schedule()
Signed-off-by: NHuacai Chen <chenhc@lemote.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Hardware always provides compliment of IP pseudo checksum. Stack expects
whole packet checksum without pseudo checksum if CHECKSUM_COMPLETE is set.

This causes checksum error in nf & ovs.

kernel: qg-19546f09-f2: hw csum failure
kernel: CPU: 9 PID: 0 Comm: swapper/9 Tainted: GF          O--------------   3.10.0-123.8.1.el7.x86_64 #1
kernel: Hardware name: Cisco Systems Inc UCSB-B200-M3/UCSB-B200-M3, BIOS B200M3.2.2.3.0.080820141339 08/08/2014
kernel: ffff881218f40000 df68243feb35e3a8 ffff881237a43ab8 ffffffff815e237b
kernel: ffff881237a43ad0 ffffffff814cd4ca ffff8829ec71eb00 ffff881237a43af0
kernel: ffffffff814c6232 0000000000000286 ffff8829ec71eb00 ffff881237a43b00
kernel: Call Trace:
kernel: <IRQ>  [<ffffffff815e237b>] dump_stack+0x19/0x1b
kernel: [<ffffffff814cd4ca>] netdev_rx_csum_fault+0x3a/0x40
kernel: [<ffffffff814c6232>] __skb_checksum_complete_head+0x62/0x70
kernel: [<ffffffff814c6251>] __skb_checksum_complete+0x11/0x20
kernel: [<ffffffff8155a20c>] nf_ip_checksum+0xcc/0x100
kernel: [<ffffffffa049edc7>] icmp_error+0x1f7/0x35c [nf_conntrack_ipv4]
kernel: [<ffffffff814cf419>] ? netif_rx+0xb9/0x1d0
kernel: [<ffffffffa040eb7b>] ? internal_dev_recv+0xdb/0x130 [openvswitch]
kernel: [<ffffffffa04c8330>] nf_conntrack_in+0xf0/0xa80 [nf_conntrack]
kernel: [<ffffffff81509380>] ? inet_del_offload+0x40/0x40
kernel: [<ffffffffa049e302>] ipv4_conntrack_in+0x22/0x30 [nf_conntrack_ipv4]
kernel: [<ffffffff815005ca>] nf_iterate+0xaa/0xc0
kernel: [<ffffffff81509380>] ? inet_del_offload+0x40/0x40
kernel: [<ffffffff81500664>] nf_hook_slow+0x84/0x140
kernel: [<ffffffff81509380>] ? inet_del_offload+0x40/0x40
kernel: [<ffffffff81509dd4>] ip_rcv+0x344/0x380

Hardware verifies IP & tcp/udp header checksum but does not provide payload
checksum, use CHECKSUM_UNNECESSARY. Set it only if its valid IP tcp/udp packet.

Cc: Jiri Benc <jbenc@redhat.com>
Cc: Stefan Assmann <sassmann@redhat.com>
Reported-by: NSunil Choudhary <schoudha@redhat.com>
Signed-off-by: NGovindarajulu Varadarajan <_govind@gmx.com>
Reviewed-by: NJiri Benc <jbenc@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

when skb_gso_segment returns error, the original skb should be freed
Signed-off-by: NLi RongQing <roy.qing.li@gmail.com>
Acked-by: NDavid L Stevens <david.stevens@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

An earlier commit to resolve an issue with encapsulation offloads missed
setting a bit in the outer netdev features flag. This results in loss of TSO
feature on a VxLAN interface.

Fixes: 630f4b70 ("Export tunnel offloads only when a VxLAN tunnel is created")
Signed-off-by: NSriharsha Basavapatna <sriharsha.basavapatna@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Noticed when debugging ptp.
Signed-off-by: NJiri Benc <jbenc@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit bc96f648 (xen-netback: make
feature-rx-notify mandatory) incorrectly assumed that there were no
frontends in use that did not support this feature.  But the frontend
driver in MiniOS does not and since this is used by (qemu) stubdoms,
these stopped working.

Netback sort of works as-is in this mode except:

- If there are no Rx requests and the internal Rx queue fills, only
  the drain timeout will wake the thread.  The default drain timeout
  of 10 s would give unacceptable pauses.

- If an Rx stall was detected and the internal Rx queue is drained,
  then the Rx thread would never wake.

Handle these two cases (when feature-rx-notify is disabled) by:

- Reducing the drain timeout to 30 ms.

- Disabling Rx stall detection.
Reported-by: NJohn <jw@nuclearfallout.net>
Tested-by: NJohn <jw@nuclearfallout.net>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Reviewed-by: NWei Liu <wei.liu2@citrix.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

QSA module was getting decoded as QSFP module in ethtool get settings, this
patch fixes it.
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The current implementations all use dev_uc_add_excl() and such whose API
doesn't support vlans, so we can't make it with NICs HW for now.

Fixes: f6f6424b ('net: make vid as a parameter for ndo_fdb_add/ndo_fdb_del')
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: NJiri Pirko <jiri@resnulli.us>
Acked-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This commit contains 2 fixes for the 128B CQE/EQE stride feaure.
Wei found that mlx4_QUERY_HCA function marked the wrong capability
in flags (64B CQE/EQE), when CQE/EQE stride feature was enabled.
Also added small fix in initial CQE ownership bit assignment, when CQE
is size is not default 32B.

Fixes: 77507aa2 (net/mlx4: Enable CQE/EQE stride support)
Signed-off-by: NWei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: NIdo Shamay <idos@mellanox.com>
Signed-off-by: NAmir Vadai <amirv@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Do camera capture test on i.MX6q sabresd board, and save the capture data to
nfs rootfs. The command is:
gst-launch-1.0 -e imxv4l2src device=/dev/video1 num-buffers=2592000 ! tee name=t !
queue ! imxv4l2sink sync=false t. ! queue ! vpuenc ! queue ! mux. pulsesrc num-buffers=3720937
blocksize=4096 ! 'audio/x-raw, rate=44100, channels=2' ! queue ! imxmp3enc ! mpegaudioparse !
queue ! mux. qtmux name=mux ! filesink location=video_recording_long.mov

After about 10 hours running, there have net watchdog timeout kernel dump:
...
WARNING: CPU: 0 PID: 0 at net/sched/sch_generic.c:264 dev_watchdog+0x2b4/0x2d8()
NETDEV WATCHDOG: eth0 (fec): transmit queue 0 timed out
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.14.24-01051-gdb840b7 #440
[<80014e6c>] (unwind_backtrace) from [<800118ac>] (show_stack+0x10/0x14)
[<800118ac>] (show_stack) from [<806ae3f0>] (dump_stack+0x78/0xc0)
[<806ae3f0>] (dump_stack) from [<8002b504>] (warn_slowpath_common+0x68/0x8c)
[<8002b504>] (warn_slowpath_common) from [<8002b558>] (warn_slowpath_fmt+0x30/0x40)
[<8002b558>] (warn_slowpath_fmt) from [<8055e0d4>] (dev_watchdog+0x2b4/0x2d8)
[<8055e0d4>] (dev_watchdog) from [<800352d8>] (call_timer_fn.isra.33+0x24/0x8c)
[<800352d8>] (call_timer_fn.isra.33) from [<800354c4>] (run_timer_softirq+0x184/0x220)
[<800354c4>] (run_timer_softirq) from [<8002f420>] (__do_softirq+0xc0/0x22c)
[<8002f420>] (__do_softirq) from [<8002f804>] (irq_exit+0xa8/0xf4)
[<8002f804>] (irq_exit) from [<8000ee5c>] (handle_IRQ+0x54/0xb4)
[<8000ee5c>] (handle_IRQ) from [<80008598>] (gic_handle_irq+0x28/0x5c)
[<80008598>] (gic_handle_irq) from [<800123c0>] (__irq_svc+0x40/0x74)
Exception stack(0x80d27f18 to 0x80d27f60)
7f00:                                                       80d27f60 0000014c
7f20: 8858c60e 0000004d 884e4540 0000004d ab7250d0 80d34348 00000000 00000000
7f40: 00000001 00000000 00000017 80d27f60 800702a4 80476e6c 600f0013 ffffffff
[<800123c0>] (__irq_svc) from [<80476e6c>] (cpuidle_enter_state+0x50/0xe0)
[<80476e6c>] (cpuidle_enter_state) from [<80476fa8>] (cpuidle_idle_call+0xac/0x154)
[<80476fa8>] (cpuidle_idle_call) from [<8000f174>] (arch_cpu_idle+0x8/0x44)
[<8000f174>] (arch_cpu_idle) from [<80064c54>] (cpu_startup_entry+0x100/0x158)
[<80064c54>] (cpu_startup_entry) from [<80cd8a9c>] (start_kernel+0x304/0x368)
---[ end trace 09ebd32fb032f86d ]---
...

There might have a race in napi_schedule(), leaving interrupts disabled forever.
After these patch, the case still work more than 40 hours running.
Signed-off-by: NFugang Duan <B38611@freescale.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After d75b1ade (net: less interrupt
masking in NAPI) the napi instance is removed from the per-cpu list
prior to calling the n->poll(), and is only requeued if all of the
budget was used.  This inadvertently broke netfront because netfront
does not use NAPI correctly.

If netfront had not used all of its budget it would do a final check
for any Rx responses and avoid calling napi_complete() if there were
more responses.  It would still return under budget so it would never
be rescheduled.  The final check would also not re-enable the Rx
interrupt.

Additionally, xenvif_poll() would also call napi_complete() /after/
enabling the interrupt.  This resulted in a race between the
napi_complete() and the napi_schedule() in the interrupt handler.  The
use of local_irq_save/restore() avoided by race iff the handler is
running on the same CPU but not if it was running on a different CPU.

Fix both of these by always calling napi_compete() if the budget was
not all used, and then calling napi_schedule() if the final checks
says there's more work.
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Otherwise we get things like:

warning: (NET_DSA_BCM_SF2 && BCMGENET && SYSTEMPORT) selects FIXED_PHY which has unmet direct dependencies (NETDEVICES && PHYLIB=y)

In order to make this work we have to rename fixed.c to fixed_phy.c
because the regulator drivers already have a module named "fixed.o".
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use TUNSETVNETLE/TUNGETVNETLE instead.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use TUNSETVNETLE/TUNGETVNETLE instead.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

flags field in ifreq is only 16 bit wide, but
we read it as a 32 bit value.
If userspace doesn't zero-initialize unused fields,
this will lead to failures.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is no need to do the following:

select FIXED_PHY if NET_DSA_BCM_SF2=y, as this implies that we will not be
able to build and/or run the driver correctly when built as a module,
which is no longer an issue since commit 37e9a690 ("net: phy: export
fixed_phy_register()").

Fixes: 246d7f77 ("net: dsa: add Broadcom SF2 switch driver")
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is no need to do the following:

select FIXED_PHY if SYSTEMPORT=y, as this implies that we will not be able
to build and/or run the driver correctly when built as a module, which
is no longer an issue since commit 37e9a690 ("net: phy: export
fixed_phy_register()")

Fixes: a3862db2 ("net: systemport: hook SYSTEMPORT driver in the build")
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is no need to do the following:

select FIXED_PHY if BCMGENET=y, as this implies that we will not be able
to build and/or run the driver correctly when built as a module, which
is no longer an issue since commit 37e9a690 ("net: phy: export
fixed_phy_register()")

Fixes: b0ba512e225d ("net: bcmgenet: enable driver to work without device tree"
Fixes: bdaa53bd ("net: bcmgenet: hook into the build system")
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

* Add a handler function pointer in the mlx5_core_qp struct for page
  fault events. Handle page fault events by calling the handler
  function, if not NULL.
* Add on-demand paging capability query command.
* Export command for resuming QPs after page faults.
* Add various constants related to paging support.
Signed-off-by: NSagi Grimberg <sagig@mellanox.com>
Signed-off-by: NShachar Raindel <raindel@mellanox.com>
Signed-off-by: NHaggai Eran <haggaie@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Move check for DPDP out of the loop to make the code more readable.
Signed-off-by: NYuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

The setting of this flag was missed in previous modifications.
Signed-off-by: NLarry Finger <Larry.Finger@lwfinger.net>
Cc: Stable <stable@vger.kernel.org>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

Debug code prints the fifo name via custom dev_warn() wrappers. The
fifo_names array is only non-zero when debugging is manually enabled,
which is all well and good. However, it's *not* good that this array
uses zero-length arrays in the non-debug case, and so it doesn't
actually have any memory allocated to it. This means that as far as we
know, fifo_names[i] actually points to garbage memory.

I've seen this in my log:

[ 4601.205511] brcmsmac bcma0:1: wl0: brcms_c_d11hdrs_mac80211: �GeL txop exceeded phylen 137/256 dur 1602/1504

So let's give this array space enough to fill it with a NULL byte.
Signed-off-by: NBrian Norris <computersforpeace@gmail.com>
Cc: Brett Rudley <brudley@broadcom.com>
Cc: Arend van Spriel <arend@broadcom.com>
Cc: "Franky (Zhenhui) Lin" <frankyl@broadcom.com>
Cc: Hante Meuleman <meuleman@broadcom.com>
Cc: "John W. Linville" <linville@tuxdriver.com>
Cc: linux-wireless@vger.kernel.org
Cc: brcm80211-dev-list@broadcom.com
Cc: netdev@vger.kernel.org
Acked-by: NArend van Spriel <arend@broadcom.com>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

Fixes the following sparse warning:

drivers/net/wireless/rtlwifi/rtl8192cu/hw.c:1595:6: warning:
 symbol 'usb_cmd_send_packet' was not declared. Should it be static?
Signed-off-by: NWei Yongjun <yongjun_wei@trendmicro.com.cn>
Acked-by: NLarry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

Replace a misspelled function name by %s and then __func__.

8821 was written as 8812.

This was done using Coccinelle, including the use of Levenshtein distance,
as proposed by Rasmus Villemoes.
Signed-off-by: NJulia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

Replace a misspelled function name by %s and then __func__.

This was done using Coccinelle, including the use of Levenshtein distance,
as proposed by Rasmus Villemoes.
Signed-off-by: NJulia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

Replace a misspelled function name by %s and then __func__.

This was done using Coccinelle, including the use of Levenshtein distance,
as proposed by Rasmus Villemoes.
Signed-off-by: NJulia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

Inside macb_probe(), when devm_request_irq() fails on queue q, there is no need
to call devm_free_irq() on queues 0..q-1 because the managed device resources
are released later when calling free_netdev().

Also removing devm_free_irq() call from macb_remove() for the same reason.
Signed-off-by: NCyrille Pitchen <cyrille.pitchen@atmel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

fix a bug introduced by the multiqueue support patch:
"net/macb: add TX multiqueue support for gem"

the "bp" pointer to the netdev private data was dereferenced and used after the
associated memory had been freed by calling free_netdev().
Signed-off-by: NCyrille Pitchen <cyrille.pitchen@atmel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If CONFIG_OF is not set:

drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c: In function ‘sti_dwmac_parse_data’:
drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c:318: warning: ‘rs’ is used uninitialized in this function

of_property_read_string() will return -ENOSYS in this case, and rs will
be an uninitialized pointer.

While the fallback clock selection is already selected correctly in this
case, the string comparisons should be skipped too, else the system will
crash while dereferencing the uninitialized pointer.
Signed-off-by: NGeert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If GPIOLIB=n the following build errors occur:

drivers/net/ethernet/smsc/smc91x.c: In function 'try_toggle_control_gpio':
drivers/net/ethernet/smsc/smc91x.c:2204:2: error: implicit declaration of function 'devm_gpiod_get_index' [-Werror=implicit-function-declaration]
drivers/net/ethernet/smsc/smc91x.c:2204:7: warning: assignment makes pointer from integer without a cast [enabled by default]
drivers/net/ethernet/smsc/smc91x.c:2213:2: error: implicit declaration of function 'gpiod_direction_output' [-Werror=implicit-function-declaration]
drivers/net/ethernet/smsc/smc91x.c:2216:3: error: implicit declaration of function 'devm_gpiod_put' [-Werror=implicit-function-declaration]
drivers/net/ethernet/smsc/smc91x.c:2222:2: error: implicit declaration of function 'gpiod_set_value_cansleep' [-Werror=implicit-function-declaration]

Fix this by letting the driver depend on GPIOLIB if OF is selected.

Fixes: 7d2911c4 ("net: smc91x: Fix gpios for device tree based booting")
Cc: Tony Lindgren <tony@atomide.com>
Signed-off-by: NTobias Klauser <tklauser@distanz.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

To be future-proof and for better readability the time comparisons are
modified to use time_before, time_after, and time_after_eq instead of
plain, error-prone math.
Signed-off-by: NAsaf Vertz <asaf.vertz@tandemg.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

To support asymmetric EQ allocations, we should query the device
capabilities prior to enabling SRIOV. As a side effect of adding that,
we are dumping the PF device capabilities twice. Avoid that by moving
the printing into a helper function which is called once.

Fixes: 7ae0e400 ('net/mlx4_core: Flexible (asymmetric) allocation of
		     EQs and MSI-X vectors for PF/VFs')
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The current mlx4_load_one has a memory leak as it always allocates
dev_cap, but frees it only on error.

In addition, even if VFs exist when mlx4_load_one is called,
we still need to notify probed VFs that we're loading (by
incrementing pf_loading).

Fixes: a0eacca9 ('net/mlx4_core: Refactor mlx4_load_one')
Signed-off-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

gem devices designed with multiqueue CANNOT work without this patch.

When probing a gem device, the driver must first prepare and enable the
peripheral clock before accessing I/O registers. The second step is to read the
MID register to find whether the device is a gem or an old macb IP.
For gem devices, it reads the Design Configuration Register 6 (DCFG6) to
compute to total number of queues, whereas macb devices always have a single
queue.
Only then it can call alloc_etherdev_mq() with the correct number of queues.
This is the reason why the order of some initializations has been changed in
macb_probe().
Eventually, the dedicated IRQ and TX ring buffer descriptors are initialized
for each queue.

For backward compatibility reasons, queue0 uses the legacy registers ISR, IER,
IDR, IMR, TBQP and RBQP. On the other hand, the other queues use new registers
ISR[1..7], IER[1..7], IDR[1..7], IMR[1..7], TBQP[1..7] and RBQP[1..7].
Except this hardware detail there is no real difference between queue0 and the
others. The driver hides that thanks to the struct macb_queue.
This structure allows us to share a common set of functions for all the queues.

Besides when a TX error occurs, the gem MUST be halted before writing any of
the TBQP registers to reset the relevant queue. An immediate side effect is
that the other queues too aren't processed anymore by the gem.
So macb_tx_error_task() calls netif_tx_stop_all_queues() to notify the Linux
network engine that all transmissions are stopped.

Also macb_tx_error_task() now calls spin_lock_irqsave() to prevent the
interrupt handlers of the other queues from running as each of them may wake
its associated queue up (please refer to macb_tx_interrupt()).

Finally, as all queues have previously been stopped, they should be restarted
calling netif_tx_start_all_queues() and setting the TSTART bit into the Network
Control Register. Before this patch, when dealing with a single queue, the
driver used to defer the reset of the faulting queue and the write of the
TSTART bit until the next call of macb_start_xmit().
As explained before, this bit is now set by macb_tx_error_task() too. That's
why the faulting queue MUST be reset by setting the TX_USED bit in its first
buffer descriptor before writing the TSTART bit.

Queue 0 always exits and is the lowest priority when other queues are available.
The higher the index of the queue is, the higher its priority is.

When transmitting frames, the TX queue is selected by the skb->queue_mapping
value. So queue discipline can be used to define the queue priority policy.
Signed-off-by: NCyrille Pitchen <cyrille.pitchen@atmel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Calls to tasklet_hi_enable are replaced by calls to
tasklet_enable since the 2 functions are redundant.
Signed-off-by: NQuentin Lambert <lambert.quentin@gmail.com>
Signed-off-by: NValentin Rothberg <valentinrothberg@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>