The sunvnet driver doesn't check whether or not a port is connected when
transmitting packets, which results in failures if a port fails to connect
(e.g., due to a version mismatch). The original code also assumes
unnecessarily that the first port is up and a switch, even though there is
a flag for switch ports.
This patch only matches a port if it is connected, and otherwise uses the
switch_port flag to send the packet to a switch port that is up.
Signed-off-by: David L Stevens <david.stevens@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Allow set_settings() to complete succesfully even if link is
not estabilished and port type isn't known yet.
Signed-off-by: Yaniv Rosner <Yaniv.Rosner@qlogic.com>
Signed-off-by: Dmitry Kravkov <Dmitry.Kravkov@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix to return a negative error code from the setting real tx queue
count error handling case instead of 0.
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Acked-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Packets shorter than ETH_ZLEN were not padded with zeroes, hence leaking
potentially sensitive information. This bug has been present since the
driver got accepted in commit 1c1008c793
("net: bcmgenet: add main driver file").
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking fixes from David Miller:
1) Null termination fix in dns_resolver got the pointer dereferncing
wrong, fix from Ben Hutchings.
2) ip_options_compile() has a benign but real buffer overflow when
parsing options. From Eric Dumazet.
3) Table updates can crash in netfilter's nftables if none of the state
flags indicate an actual change, from Pablo Neira Ayuso.
4) Fix race in nf_tables dumping, also from Pablo.
5) GRE-GRO support broke the forwarding path because the segmentation
state was not fully initialized in these paths, from Jerry Chu.
6) sunvnet driver leaks objects and potentially crashes on module
unload, from Sowmini Varadhan.
7) We can accidently generate the same handle for several u32
classifier filters, fix from Cong Wang.
8) Several edge case bug fixes in fragment handling in xen-netback,
from Zoltan Kiss.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (21 commits)
ipv4: fix buffer overflow in ip_options_compile()
batman-adv: fix TT VLAN inconsistency on VLAN re-add
batman-adv: drop QinQ claim frames in bridge loop avoidance
dns_resolver: Null-terminate the right string
xen-netback: Fix pointer incrementation to avoid incorrect logging
xen-netback: Fix releasing header slot on error path
xen-netback: Fix releasing frag_list skbs in error path
xen-netback: Fix handling frag_list on grant op error path
net_sched: avoid generating same handle for u32 filters
net: huawei_cdc_ncm: add "subclass 3" devices
net: qmi_wwan: add two Sierra Wireless/Netgear devices
wan/x25_asy: integer overflow in x25_asy_change_mtu()
net: ppp: fix creating PPP pass and active filters
net/mlx4_en: cq->irq_desc wasn't set in legacy EQ's
sunvnet: clean up objects created in vnet_new() on vnet_exit()
r8169: Enable RX_MULTI_EN for RTL_GIGA_MAC_VER_40
net-gre-gro: Fix a bug that breaks the forwarding path
netfilter: nf_tables: 64bit stats need some extra synchronization
netfilter: nf_tables: set NLM_F_DUMP_INTR if netlink dumping is stale
netfilter: nf_tables: safe RCU iteration on list when dumping
...
Fix a regression introduced by commit 35f6f45 ("net/mlx4_en: Don't use
irq_affinity_notifier to track changes in IRQ affinity map").
When core is started in legacy EQ's (number of IRQ's < rx rings), cq->irq_desc
was NULL. This caused a kernel crash under heavy traffic - when having more
than rx NAPI budget completions.
Fixed to have it set for both EQ modes.
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Nothing cleans up the objects created by
vnet_new(), they are completely leaked.
vnet_exit(), after doing the vio_unregister_driver() to clean
up ports, should call a helper function that iterates over vnet_list
and cleans up those objects. This includes unregister_netdevice()
as well as free_netdev().
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Reviewed-by: Karl Volz <karl.volz@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The ethernet port on my ASUS A88X Pro mainboard stopped working
several times a day, with messages like these in dmesg:
AMD-Vi: Event logged [IO_PAGE_FAULT device=05:00.0 domain=0x001e address=0x0000000000003000 flags=0x0050]
Searching the web for these messages led me to similar reports about
different hardware supported by r8169, and eventually to commits
3ced8c955e ('r8169: enforce RX_MULTI_EN
for the 8168f.') and eb2dc35d99 ('r8169:
RxConfig hack for the 8168evl'). So I tried this change, and it fixes
the problem for me.
Signed-off-by: Michel Dänzer <michel@daenzer.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Napi id was not marked for gro_skb, this will lead rx busy loop won't
work correctly since they stack never try to call low latency receive
method because of a zero socket napi id. Fix this by marking napi id
for gro_skb.
The transaction rate of 1 byte netperf tcp_rr gets about 50% increased
(from 20531.68 to 30610.88).
Cc: Amir Vadai <amirv@mellanox.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RGMII_MODE_EN bit was defined to 0, while it is actually 6. It was not
much of a problem on older designs where this was a no-op, and the RGMII
data-path would always be enabled, but newer GENET controllers need to
explicitely enable their RGMII data-pad using this bit.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On BE3, if the clear-interrupt bit of the EQ doorbell is not set the first
time it is armed, ocassionally we have observed that the EQ doesn't raise
anymore interrupts even if it is in armed state.
This patch fixes this by setting the clear-interrupt bit when EQs are
armed for the first time in be_open().
Signed-off-by: Suresh Reddy <Suresh.Reddy@emulex.com>
Signed-off-by: Sathya Perla <sathya.perla@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
To properly re-initialize SR-IOV it is necessary to reset the device
even if it is already down. Not doing this may result in Tx unit hangs.
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Stefan Assmann <sassmann@kpanic.de>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On some devices, the internal PLL circuit occasionally provides the
wrong clock frequency after power up. The probability of failure is less
than one failure per 1000 power cycles. When the failure occurs, the
internal clock frequency is around 1/20 of the correct frequency.
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Todd Fujinaka <todd.fujinaka@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In mlx5_core_destroy_mkey(), we must first remove the mr from the
radix tree and then destroy it. Otherwise we might hit a race if the
key was reallocated and we attempted to insert it to the radix tree.
Also handle radix tree insert/delete failures.
Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Reviewed-by: Eli Cohen <elic@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <roland@purestorage.com>
For RTL8411, RTL8111G, RTL8402, RTL8105, and RTL8106, disable the feature
of entering the L2/L3 link state of the PCIe. When the nic starts the process
of entering the L2/L3 link state and the PCI reset occurs before the work
is finished, the work would be queued and continue after the next the PCI
reset occurs. This causes the device stays in L2/L3 link state, and the system
couldn't find the device.
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Acked-by: Francois Romieu <romieu@fr.zoreil.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit fixes the command value generated for CSUM calculation
when running in big endian mode. The Ethernet protocol ID for IP was
being unconditionally byte-swapped in the layer 3 protocol check (with
swab16), which caused the mvneta driver to not function correctly in
big endian mode. This patch byte-swaps the ID conditionally with
htons.
Cc: <stable@vger.kernel.org> # v3.13+
Signed-off-by: Thomas Fitzsimmons <fitzsim@fitzsim.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
As reported by Maggie Mae Roxas, the mvneta driver doesn't behave
properly in 10 Mbit/s mode. This is due to a misconfiguration of the
MVNETA_GMAC_AUTONEG_CONFIG register: bit MVNETA_GMAC_CONFIG_MII_SPEED
must be set for a 100 Mbit/s speed, but cleared for a 10 Mbit/s speed,
which the driver was not properly doing. This commit adjusts that by
setting the MVNETA_GMAC_CONFIG_MII_SPEED bit only in 100 Mbit/s mode,
and relying on the fact that all the speed related bits of this
register are cleared at the beginning of the mvneta_adjust_link()
function.
This problem exists since c5aff18204 ("net: mvneta: driver for
Marvell Armada 370/XP network unit") which is the commit that
introduced the mvneta driver in the kernel.
Cc: <stable@vger.kernel.org> # v3.8+
Fixes: c5aff18204 ("net: mvneta: driver for Marvell Armada 370/XP network unit")
Reported-by: Maggie Mae Roxas <maggie.mae.roxas@gmail.com>
Cc: Maggie Mae Roxas <maggie.mae.roxas@gmail.com>
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It is recommended that TX work not count against the quota.
The cost of TX packet liberation is a minute percentage of what it costs to
process an RX frame. Furthermore, that SKB freeing makes memory available for
other paths in the stack.
Give the TX a larger budget and be more aggressive about cleaning up the Tx
descriptors this budget could be changed using ethtool:
$ ethtool -C eth1 tx-frames-irq <budget>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The add_vxlan_port ndo driver code was wrongly testing whether HW vxlan offloads
are supported by the device instead of checking if they are currently enabled.
This causes the driver to configure the HW parser to conduct matching for vxlan
packets but since no steering rules were set, vxlan packets are dropped on RX.
Fix that by doing the right test, as done in the del_vxlan_port ndo handler.
Fixes: 1b136de ('net/mlx4: Implement vxlan ndo calls')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit 0acf167687.
Breaks the build due to missing reference to phy_resume in
the resulting dwmac-socfpga.o object.
Signed-off-by: David S. Miller <davem@davemloft.net>
deal with a compile warning: comparison between
'enum qe_fltr_largest_external_tbl_lookup_key_size'
and 'enum qe_fltr_tbl_lookup_key_size'
the code:
"if (ug_info->largestexternallookupkeysize ==
QE_FLTR_TABLE_LOOKUP_KEY_SIZE_8_BYTES)"
is warned because different enum, so modify it.
"enum qe_fltr_largest_external_tbl_lookup_key_size
largestexternallookupkeysize;
enum qe_fltr_tbl_lookup_key_size {
QE_FLTR_TABLE_LOOKUP_KEY_SIZE_8_BYTES
= 0x3f, /* LookupKey parsed by the Generate LookupKey
CMD is truncated to 8 bytes */
QE_FLTR_TABLE_LOOKUP_KEY_SIZE_16_BYTES
= 0x5f, /* LookupKey parsed by the Generate LookupKey
CMD is truncated to 16 bytes */
};
/* QE FLTR extended filtering Largest External Table Lookup Key Size */
enum qe_fltr_largest_external_tbl_lookup_key_size {
QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_NONE
= 0x0,/* not used */
QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_8_BYTES
= QE_FLTR_TABLE_LOOKUP_KEY_SIZE_8_BYTES, /* 8 bytes */
QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_16_BYTES
= QE_FLTR_TABLE_LOOKUP_KEY_SIZE_16_BYTES, /* 16 bytes */
};"
Signed-off-by: Zhao Qiang <B45475@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Cppcheck found a case where a local variable was being assigned a value,
but not used. There seems to be no reason to read this register before
assigning a new value, so addressing thie issue.
cppcheck --force --enable=all --inline-suppr . shows ...
Variable 'value' is reassigned a value before the old one has been used.
Signed-off-by: Vince Bridgers <vbridgers2013@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Cppcheck found a duplicate if/then/else case where a receive descriptor
was being processed. This patch corrects that issue.
cppcheck --force --enable=all --inline-suppr .
...
Checking enh_desc.c...
[enh_desc.c:148] -> [enh_desc.c:144]: (style) Found duplicate if expressions.
...
Signed-off-by: Vince Bridgers <vbridgers2013@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds platform init/exit functions and modifications to support
suspend/resume for the Altera Cyclone 5 SOC Ethernet controller. The platform
exit function puts the controller into reset using the socfpga reset
controller driver. The platform init function sets up the Synopsys mac by
first making sure the Ethernet controller is held in reset, programming the
phy mode through external support logic, then deasserts reset through
the socfpga reset manager driver.
Signed-off-by: Vince Bridgers <vbridgers2013@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Need to remove affinity hint at mlx4_en_deactivate_cq() and not at
mlx4_en_destroy_cq() - since affinity_mask might be free'd while still
being used by procfs.
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
IRQ affinity notifier can only have a single notifier - cpu_rmap
notifier. Can't use it to track changes in IRQ affinity map.
Detect IRQ affinity changes by comparing CPU to current IRQ affinity map
during NAPI poll thread.
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Ben Hutchings <ben@decadent.org.uk>
Fixes: 2eacc23 ("net/mlx4_core: Enforce irq affinity changes immediatly")
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Hardware will provide this information as soon as we will start
processing incoming packets, so there is no need to set the RX buffer
length during buffer allocation.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We use the PHY library which will determine the link state for us, make
sure we start with a carrier off until libphy has completed the link
training.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As soon as register_netdev() is called, the network device notifiers are
running which means that other parts of the kernel, or user-space
programs can call the network device ndo_open() callback and use the
interface.
Disable the Ethernet device clock before we register the network device
such that we do not create the following situation:
CPU0 CPU1
register_netdev()
bcmgenet_open()
clk_prepare_enable()
clk_disable_unprepare()
and leave the hardware block gated off, while we think it should be
gated on.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Although we do not limit the number of packets the TX completion
function bcm_sysport_tx_reclaim() is allowed to reclaim, we were still
using its return value as-is. This means that we could hit the WARN() in
net/core/dev.c where work_done >= budget.
Make sure we do exit the NAPI context when the TX ring is empty, and
pretend there was no work to do.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The UniMAC CMD_SW_RESET bit is not a self-clearing bit, so we need to
assert it, wait a bit and clear it manually. As a result, umac_reset()
is updated not to return any value. The previous version of the code
simply wrote 0 to the CMD register, which would make the busy-waiting
loop exit immediately, having zero effect.
By writing 0 to the CMD register, we were clearing all bits in the CMD
register, and not using the hardware reset default values which are
set on purpose.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The SYSTEMPORT Ethernet MAC supports multicast just fine, it just lacks
any sort of Unicast/Broadcast/Multicasting filtering at the Ethernet MAC
level since that is handled by the front end Ethernet switch, but that
is properly handled by bcm_sysport_set_rx_mode().
Some user-space applications might be relying on the presence of this
flag to prevent using multicast sockets, this also prevents that
interface from joining the IPv6 all-router mcast group.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While it is legal to kfree(NULL), it is not wise to use :
put_page(virt_to_head_page(NULL))
BUG: unable to handle kernel paging request at ffffeba400000000
IP: [<ffffffffc01f5928>] virt_to_head_page+0x36/0x44 [bnx2x]
Reported-by: Michel Lespinasse <walken@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ariel Elior <ariel.elior@qlogic.com>
Fixes: d46d132cc0 ("bnx2x: use netdev_alloc_frag()")
Signed-off-by: David S. Miller <davem@davemloft.net>
MSI-X should use PCI_MSIX_FLAGS not PCI_MSI_FLAGS.
Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If the mdio probe function fails in emac_open, the interrupt we just requested
isn't freed. If emac_open is called again, for example because we try to set up
the interface again, the kernel will oops because the interrupt wasn't properly
released.
Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Cc: <stable@vger.kernel.org> # 3.11+
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 3f85944fe2 ("net: Add sysfs file
for port number") introduce dev_port to network devices. cxgb4 adapters
have multiple ports on the same PCI function, and used dev_id to
identify those ports. That use was removed by commit
8c367fcbe6 ("cxgb4: Do not set
net_device::dev_id to VI index"), since dev_id should be used only when
devices share the same MAC address.
Using dev_port for cxgb4 allows different ports on the same PCI function
to be identified.
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 506724c463 "tg3: Override clock,
link aware and link idle mode during NVRAM dump" changed the timeout
value for nvram command execution from 100ms to 1ms. But the 1ms
timeout value was only sufficient for nvram read operations but not
write operations for most of the devices supported by tg3 driver.
This patch sets the MAX to 50ms. Also it uses usleep_range instead
of udelay.
Signed-off-by: Prashant Sreedharan <prashant@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Suggested-by: David Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The driver (on PF or VF) needs to detect if the function is in qnq mode for
a HW hack in be_rx_compl_get() to work.
The driver queries this information using the GET_PROFILE_CONFIG cmd
(since the commit below can caused this regression.) But this cmd is not
available on VFs and so the VFs fail to detect qnq mode. This causes
vlan traffic to not work.
The fix is to use the the adapter->function_mode value queried via
QUERY_FIRMWARE_CONFIG cmd on both PFs and VFs to detect the qnq mode.
Also QNQ_MODE was incorrectly named FLEX10_MODE; correcting that too as the
fix reads much better with the name change.
Fixes: f93f160b5 ("refactor multi-channel config code for Skyhawk-R chip")
Signed-off-by: Suresh Reddy <Suresh.Reddy@emulex.com>
Signed-off-by: Sathya Perla <sathya.perla@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Single ported VF are currently not supported on configurations where
one or both ports are IB. When we hit this case, the relevant flow in
the driver didn't return error and jumped to the wrong label. Fix that.
Fixes: dd41cc3 ('net/mlx4: Adapt num_vfs/probed_vf params for single port VF')
Reported-by: Shirley Ma <shirley.ma@oracle.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It now takes up to 60 seconds to detect cable (un)plug on ADMtek Comet chips.
That's too slow and might cause people to think that it doesn't work at all.
Poll link status every 2 seconds instead of 60 for ADMtek Comet chips.
That should be fast enough while not stressing the system too much.
Tested with ADMtek AN983B.
Signed-off-by: Ondrej Zary <linux@rainbow-software.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit 629c9a8fd0 (drivers: net: cpsw: Add
default vlan for dual emac case also), api cpsw_add_default_vlan() also
changes the port vlan which is required to seperate the ports which results
in the following behavior
In Dual EMAC mode, when both the Etnernet connected is connected to same
switch, it creates a loop in the switch and when a broadcast packet is
received it is forwarded to the other port which stalls the whole switch
and needs a reset/power cycle to the switch to recover. So intead of using
the api, add only the default VLAN entry in dual EMAC case.
Cc: Yegor Yefremov <yegorslists@googlemail.com>
Cc: Felipe Balbi <balbi@ti.com>
Signed-off-by: Mugunthan V N <mugunthanvnm@ti.com>
Tested-by: Yegor Yefremov <yegorslists@googlemail.com>
Tested-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit d3f6f3a1d8 ("tg3: Prevent page
allocation failure during TSO workaround") modified driver logic
to use tg3_tso_bug() for any TSO fragment that hits hardware bug
conditions thus the patch increased the scope of work for tg3_tso_bug()
to cover devices that support NETIF_F_TSO6 as well. Prior to the
patch, tg3_tso_bug() would only be used on devices supporting
NETIF_F_TSO.
A regression was introduced for IPv6 packets requiring the workaround.
To properly perform GSO on SKBs with TCPV6 gso_type, we need to call
skb_gso_segment() with NETIF_F_TSO6 feature flag cleared, or the
function will return NULL and cause a kernel oops as tg3 is not handling
a NULL return value. This patch fixes the problem.
Signed-off-by: Prashant Sreedharan <prashant@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Added FUJITSU SIEMENS A8NE-FM to the list of 32bit DMA boards
>From Tomi O.:
After I added an entry to this MB into the skge.c
driver in order to enable the mentioned 64bit dma disable quirk,
the network data corruptions ended and everything is fine again.
Signed-off-by: Mirko Lindner <mlindner@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The commit 96c50caa51 (net: fec: Enable IP header hardware checksum)
enable HW IP header checksum for IPV4 and IPV6, which causes IPV6 TCP/UDP
cannot work. (The issue is reported by Russell King)
For FEC IP header checksum function: Insert IP header checksum. This "IINS"
bit is written by the user. If set, IP accelerator calculates the IP header
checksum and overwrites the IINS corresponding header field with the calculated
value. The checksum field must be cleared by user, otherwise the checksum
always is 0xFFFF.
So the previous patch clear IP header checksum field regardless of IP frame
type.
In fact, IP HW detect the packet as IPV6 type, even if the "IINS" bit is set,
the IP accelerator is not triggered to calculates IPV6 header checksum because
IPV6 frame format don't have checksum.
So this results in the IPV6 frame being corrupted.
The patch just add software detect the current packet type, if it is IPV6
frame, it don't clear IP header checksum field.
Cc: Russell King <linux@arm.linux.org.uk>
Reported-and-tested-by: Russell King <linux@arm.linux.org.uk>
Signed-off-by: Fugang Duan <B38611@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
'i' is unused in tile_net_dev_init() after commit d581ebf5a1
("net: tile: Use helpers from linux/etherdevice.h to check/set MAC").
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking updates from David Miller:
1) Seccomp BPF filters can now be JIT'd, from Alexei Starovoitov.
2) Multiqueue support in xen-netback and xen-netfront, from Andrew J
Benniston.
3) Allow tweaking of aggregation settings in cdc_ncm driver, from Bjørn
Mork.
4) BPF now has a "random" opcode, from Chema Gonzalez.
5) Add more BPF documentation and improve test framework, from Daniel
Borkmann.
6) Support TCP fastopen over ipv6, from Daniel Lee.
7) Add software TSO helper functions and use them to support software
TSO in mvneta and mv643xx_eth drivers. From Ezequiel Garcia.
8) Support software TSO in fec driver too, from Nimrod Andy.
9) Add Broadcom SYSTEMPORT driver, from Florian Fainelli.
10) Handle broadcasts more gracefully over macvlan when there are large
numbers of interfaces configured, from Herbert Xu.
11) Allow more control over fwmark used for non-socket based responses,
from Lorenzo Colitti.
12) Do TCP congestion window limiting based upon measurements, from Neal
Cardwell.
13) Support busy polling in SCTP, from Neal Horman.
14) Allow RSS key to be configured via ethtool, from Venkata Duvvuru.
15) Bridge promisc mode handling improvements from Vlad Yasevich.
16) Don't use inetpeer entries to implement ID generation any more, it
performs poorly, from Eric Dumazet.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1522 commits)
rtnetlink: fix userspace API breakage for iproute2 < v3.9.0
tcp: fixing TLP's FIN recovery
net: fec: Add software TSO support
net: fec: Add Scatter/gather support
net: fec: Increase buffer descriptor entry number
net: fec: Factorize feature setting
net: fec: Enable IP header hardware checksum
net: fec: Factorize the .xmit transmit function
bridge: fix compile error when compiling without IPv6 support
bridge: fix smatch warning / potential null pointer dereference
via-rhine: fix full-duplex with autoneg disable
bnx2x: Enlarge the dorq threshold for VFs
bnx2x: Check for UNDI in uncommon branch
bnx2x: Fix 1G-baseT link
bnx2x: Fix link for KR with swapped polarity lane
sctp: Fix sk_ack_backlog wrap-around problem
net/core: Add VF link state control policy
net/fsl: xgmac_mdio is dependent on OF_MDIO
net/fsl: Make xgmac_mdio read error message useful
net_sched: drr: warn when qdisc is not work conserving
...
Add software TSO support for FEC.
This feature allows to improve outbound throughput performance.
Tested on imx6dl sabresd board, running iperf tcp tests shows:
- 16.2% improvement comparing with FEC SG patch
- 82% improvement comparing with NO SG & TSO patch
$ ethtool -K eth0 tso on
$ iperf -c 10.192.242.167 -t 3 &
[ 3] local 10.192.242.108 port 35388 connected with 10.192.242.167 port 5001
[ ID] Interval Transfer Bandwidth
[ 3] 0.0- 3.0 sec 181 MBytes 506 Mbits/sec
During the testing, CPU loading is 30%.
Since imx6dl FEC Bandwidth is limited to SOC system bus bandwidth, the
performance with SW TSO is a milestone.
CC: Ezequiel Garcia <ezequiel.garcia@free-electrons.com>
CC: Eric Dumazet <eric.dumazet@gmail.com>
CC: David Laight <David.Laight@ACULAB.COM>
CC: Li Frank <B20596@freescale.com>
Signed-off-by: Fugang Duan <B38611@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David L Stevens