| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
In RX data-path, use memset() instead of loop assignment
to init the whole skbs_frags array.
Signed-off-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Field is used only locally within the RQ create function.
The use of a local variable is sufficient.
Signed-off-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
In RX data-path, use shift operations instead of a regular multiplication
by stride size, as it is a power of two.
Signed-off-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Bring fast-path fields together, and combine RX WQE mutual
exclusive fields into a union.
Page-reuse and XDP are mutually exclusive and cannot be used at
the same time.
Use a union to combine their footprints.
Signed-off-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Similarly to how we configure the RSB (Receive Status Block) we also
need to set the TSB (Transmit Status Block) based on the host endian.
This was missing from the commit indicated below.
Fixes: 389a06bc534e ("net: systemport: Set correct RSB endian bits based on host")
Signed-off-by: Florian Fainelli <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
priv is being assigned but is never used, so remove it.
Cleans up clang build warning:
"warning: Value stored to 'priv' is never read"
Fixes: ceed73a2cf4a ("drivers: net: ethernet: qualcomm: rmnet: Initial implementation")
Signed-off-by: Colin Ian King <[email protected]>
Acked-by: Subash Abhinov Kasiviswanathan <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Don't populate the arrays port_ids on the stack, instead make them static.
Makes the object code smaller by over 700 bytes:
Before:
text data bss dec hex filename
28785 5832 192 34809 87f9 fman.o
After:
text data bss dec hex filename
27921 5992 192 34105 8539 fman.o
Signed-off-by: Colin Ian King <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Three cases of simple overlapping changes.
Signed-off-by: David S. Miller <[email protected]>
|
|
The mvneta driver and hardware supports IPv6 offload, however it
isn't enabled. Set the NETIF_F_IPV6_CSUM feature to inform the
network layer that this driver can offload IPV6 TCP and UDP
checksums. This change has been tested on an Armada 370 and the
feature support confirmed with several device datasheets
including the Armada XP and Armada 3700.
Signed-off-by: Andrew Pilloud <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
At the end of the do while loop the integer counter retries will
always be zero and so the subsequent check to see if it is zero
is always true and therefore redundant. Remove the redundant check
and always return -EIO on this return path. Also unbreak the literal
string in dev_err message to clean up a checkpatch warning.
Detected by CoverityScan, CID#744279 ("Logically dead code")
Signed-off-by: Colin Ian King <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
This patch adds the GoP link interrupt support for when a port isn't
connected to a PHY. Because of this the phylib callback is never called
and the link status management isn't done. This patch use the GoP link
interrupt in such cases to still have a minimal link management. Without
this patch ports not connected to a PHY cannot work.
Signed-off-by: Antoine Tenart <[email protected]>
Tested-by: Marcin Wojtas <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
There is not necessarily a PHY between the GoP and the physical port.
However, the driver currently makes the "phy" property mandatory,
contrary to what is stated in the device tree bindings. This patch makes
the PHY optional, and aligns the PPv2 driver on its device tree
documentation. However if a PHY is provided, the GoP link interrupt
won't be used.
With this patch switches directly connected to the serdes lanes and SFP
ports on the Armada 8040-db and Armada 7040-db can be used if the link
interrupt is described in the device tree.
Signed-off-by: Antoine Tenart <[email protected]>
Tested-by: Marcin Wojtas <[email protected]>
Reviewed-by: Andrew Lunn <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Convert all RGMII checks to use the phy_interface_mode_is_rgmii()
helper. This is a cosmetic patch.
Signed-off-by: Antoine Tenart <[email protected]>
Reviewed-by: Andrew Lunn <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
When the abort mechanism is invoked a default route directing packets to
the CPU is programmed in all the virtual routers currently in use. This
can result in packet loss in case a new VRF is configured.
Upon abort, program the default route in all virtual routers, whether
they are in use or not.
The patch is directed at net-next since post-abort fixes aren't critical
and packet loss due to a missing default route will be insignificant
compared to packet loss caused by the CPU port policer.
Signed-off-by: Ido Schimmel <[email protected]>
Signed-off-by: Jiri Pirko <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
I relied on the fact that anycast routes use the loopback device as
their nexthop device to trap packets hitting them to the CPU.
After commit 4832c30d5458 ("net: ipv6: put host and anycast routes on
device with address") this is no longer the case and such routes are
programmed with a forward action (note the 'offload' flag):
anycast cafe:: dev enp3s0np7 proto kernel metric 0 offload pref medium
This will prevent the router from locally receiving packets destined to
the Subnet-Router anycast address.
Fix this by specifically programming anycast routes with action trap,
which results in the following output:
anycast cafe:: dev enp3s0np7 proto kernel metric 0 pref medium
Fixes: 4832c30d5458 ("net: ipv6: put host and anycast routes on device with address")
Signed-off-by: Ido Schimmel <[email protected]>
Signed-off-by: Jiri Pirko <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
The mlxsw driver relies on NETDEV_CHANGEUPPER events to configure the
device in case a port is enslaved to a master netdev such as bridge or
bond.
Since the driver ignores events unrelated to its ports and their
uppers, it's possible to engineer situations in which the device's data
path differs from the kernel's.
One example to such a situation is when a port is enslaved to a bond
that is already enslaved to a bridge. When the bond was enslaved the
driver ignored the event - as the bond wasn't one of its uppers - and
therefore a bridge port instance isn't created in the device.
Until such configurations are supported forbid them by checking that the
upper device doesn't have uppers of its own.
Fixes: 0d65fc13042f ("mlxsw: spectrum: Implement LAG port join/leave")
Signed-off-by: Ido Schimmel <[email protected]>
Reported-by: Nogah Frankel <[email protected]>
Tested-by: Nogah Frankel <[email protected]>
Signed-off-by: Jiri Pirko <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Add support for controlling IPv6 neighbor counters via dpipe.
Signed-off-by: Arkadi Sharshevsky <[email protected]>
Signed-off-by: Jiri Pirko <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Add support for setting counters on IPv6 neighbors based on dpipe's host6
table counter status.
Signed-off-by: Arkadi Sharshevsky <[email protected]>
Signed-off-by: Jiri Pirko <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Add support for IPv6 host table dump.
Signed-off-by: Arkadi Sharshevsky <[email protected]>
Signed-off-by: Jiri Pirko <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Change the host entry filler helper to be applicable for both IPv4/6
addresses.
Signed-off-by: Arkadi Sharshevsky <[email protected]>
Signed-off-by: Jiri Pirko <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Add helper for accessing destination IP in case of IPv6 neighbor.
Signed-off-by: Arkadi Sharshevsky <[email protected]>
Signed-off-by: Jiri Pirko <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Add IPv6 host table initial support. The action behavior for both IPv4/6
tables is the same, thus the same action dump op is used. Neighbors with
link local address are ignored.
Signed-off-by: Arkadi Sharshevsky <[email protected]>
Signed-off-by: Jiri Pirko <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Neighbors with link local addresses are not offloaded to the host table,
yet, the are maintained in the driver for adjacency table usage. When
dumping the IPv6 host neighbors this link local neighbors should be
ignored. This patch exports this helper for dpipe usage.
Signed-off-by: Arkadi Sharshevsky <[email protected]>
Signed-off-by: Jiri Pirko <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
mlx5-updates-2017-08-31 (GRE Offloads support)
This series provides the support for MPLS RSS and GRE TX offloads and
RSS support.
The first patch from Gal and Ariel provides the mlx5 driver support for
ConnectX capability to perform IP version identification and matching in
order to distinguish between IPv4 and IPv6 without the need to specify the
encapsulation type, thus perform RSS in MPLS automatically without
specifying MPLS ethertyoe. This patch will also serve for inner GRE IPv4/6
classification for inner GRE RSS.
2nd patch from Gal, Adds the TX offloads support for GRE tunneled packets,
by reporting the needed netdev features.
3rd patch from Gal, Adds GRE inner RSS support by creating the needed device
resources (Steering Tables/rules and traffic classifiers) to Match GRE traffic
and perform RSS hashing on the inner headers.
Improvement:
Testing 8 TCP streams bandwidth over GRE:
System: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
NIC: Mellanox Technologies MT28800 Family [ConnectX-5 Ex]
Before: 21.3 Gbps (Single RQ)
Now : 90.5 Gbps (RSS spread on 8 RQs)
====================
Signed-off-by: David S. Miller <[email protected]>
|
|
Fix crash in linux PF driver when BARs have been cleared/de-programmed;
fail early init (prior to mapping BARs) if the BAR0 or
BAR1 registers are zero.
This situation can arise when the PF is added to a VM (PCI pass-through),
then a PF FLR is issued (in the VM). After this occurs, the BAR registers
will be zero. If we attempt to load the PF driver in the host
(after VM has been shutdown), the host can reset.
Signed-off-by: Rick Farrington <[email protected]>
Signed-off-by: Raghu Vatsavayi <[email protected]>
Signed-off-by: Felix Manlunas <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
Mellanox, mlx5 fixes 2017-08-30
This series contains some misc fixes to the mlx5 driver.
Please pull and let me know if there's any problem.
For -stable:
Kernels >= 4.12
net/mlx5e: Fix CQ moderation mode not set properly
net/mlx5e: Don't override user RSS upon set channels
Kernels >= 4.11
net/mlx5e: Properly resolve TC offloaded ipv6 vxlan tunnel source address
Kernels >= 4.10
net/mlx5e: Fix DCB_CAP_ATTR_DCBX capability for DCBNL getcap
net/mlx5e: Check for qos capability in dcbnl_initialize
Kernels >= 4.9
net/mlx5e: Fix dangling page pointer on DMA mapping error
Kernels >= 4.8
net/mlx5e: Fix inline header size for small packets
net/mlx5: E-Switch, Unload the representors in the correct order
net/mlx5: Fix arm SRQ command for ISSI version 0
====================
Signed-off-by: David S. Miller <[email protected]>
|
|
Introduce a new flow table and indirect TIRs which are used to hash the
inner packet headers of GRE tunneled packets.
When a GRE tunneled packet is received, the TTC flow table will match
the new IPv4/6->GRE rules which will forward it to the inner TTC table.
The inner TTC is similar to its counterpart outer TTC table, but
matching the inner packet headers instead of the outer ones (and does
not include the new IPv4/6->GRE rules).
The new rules will not add steering hops since they are added to an
already existing flow group which will be matched regardless of this
patch. Non GRE traffic will not be affected.
The inner flow table will forward the packet to inner indirect TIRs
which hash the inner packet and thus result in RSS for the tunneled
packets.
Testing 8 TCP streams bandwidth over GRE:
System: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
NIC: Mellanox Technologies MT28800 Family [ConnectX-5 Ex]
Before: 21.3 Gbps (Single RQ)
Now : 90.5 Gbps (RSS spread on 8 RQs)
Signed-off-by: Gal Pressman <[email protected]>
Reviewed-by: Or Gerlitz <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Add TX offloads support for GRE tunneled packets by reporting the needed
netdev features.
Signed-off-by: Gal Pressman <[email protected]>
Reviewed-by: Or Gerlitz <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
This change adds the ability for flow steering to classify IPv4/6
packets with MPLS tag (Ethertype 0x8847 and 0x8848) as standard IP
packets and hit IPv4/6 classification steering rules.
Since IP packets with MPLS tag header have MPLS ethertype, they
missed the IPv4/6 ethertype rule and ended up hitting the default
filter forwarding all the packets to the same single RQ (No RSS).
Since our device is able to look past the MPLS tag and identify the
next protocol we introduce this solution which replaces ethertype
matching by the device's capability to perform IP version
identification and matching in order to distinguish between IPv4 and
IPv6.
Therefore, when driver is performing flow steering configuration on the
device it will use IP version matching in IP classified rules instead
of ethertype matching which will cause relevant MPLS tagged packets to
hit this rule as well.
If the device doesn't support IP version matching the driver will fall back
to use legacy ethertype matching in the steering as before.
Signed-off-by: Gal Pressman <[email protected]>
Signed-off-by: Ariel Levkovich <[email protected]>
Reviewed-by: Or Gerlitz <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Trivial fix to spelling mistake in DP_NOTICE message
Signed-off-by: Colin Ian King <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
This patch removes the wrong check being done for the phy device being
returned by the mdiobus_get_phy() function. This function never returns
the error pointers.
Fixes: 256727da7395 ("net: hns3: Add MDIO support to HNS3 Ethernet
Driver for hip08 SoC")
Reported-by: Dan Carpenter <[email protected]>
Signed-off-by: Salil Mehta <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Make this const as it is never modified.
Signed-off-by: Bhumika Goyal <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
This patch adds logic to reconfigure the comphy/GoP/MAC when the link
state is updated at runtime. This is very useful on boards where many
link speed are supported: depending on what is negotiated the PPv2
driver will automatically reconfigures the link between the PHY and the
MAC.
Signed-off-by: Antoine Tenart <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
When using the XLG MAC, it does not make sense to force the GMAC autoneg
parameters. This patch adds checks to only set the GMAC autoneg
parameters when needed (i.e. when not using the XLG MAC).
Signed-off-by: Antoine Tenart <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
When the link status changes, the phylib calls the link_event function
in the mvpp2 driver. Before this patch only the egress/ingress transmit
was enabled/disabled. This patch adds more functionality to the link
status management code by enabling/disabling the port per-cpu
interrupts, and the port itself. The queues are now stopped as well, and
the netif carrier helpers are called.
Signed-off-by: Antoine Tenart <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
The link_event function is somewhat complicated. This cosmetic patch
simplifies it.
Signed-off-by: Antoine Tenart <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
On some platforms, the comphy is between the MAC GoP and the PHYs. The
mvpp2 driver currently relies on the firmware/bootloader to configure
the comphy. As a comphy driver was added to the generic PHY framework,
this patch uses it in the mvpp2 driver to configure the comphy at boot
time to avoid relying on the bootloader.
Signed-off-by: Antoine Tenart <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
RmNet driver provides a transport agnostic MAP (multiplexing and
aggregation protocol) support in embedded module. Module provides
virtual network devices which can be attached to any IP-mode
physical device. This will be used to provide all MAP functionality
on future hardware in a single consistent location.
Signed-off-by: Subash Abhinov Kasiviswanathan <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
cq_period_mode assignment was mistakenly removed so it was always set to "0",
which is EQE based moderation, regardless of the device CAPs and
requested value in ethtool.
Fixes: 6a9764efb255 ("net/mlx5e: Isolate open_channels from priv->params")
Signed-off-by: Tal Gilboa <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Fix inline header size, make sure it is not greater than skb len.
This bug effects small packets, for example L2 packets with size < 18.
Fixes: ae76715d153e ("net/mlx5e: Check the minimum inline header mode before xmit")
Signed-off-by: Moshe Shemesh <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
When changing from switchdev to legacy mode, all the representor port
devices (uplink nic and reps) are cleaned up. Part of this cleaning
process is removing the neigh entries and the hash table containing them.
However, a representor neigh entry might be linked to the uplink port
hash table and if the uplink nic is cleaned first the cleaning of the
representor will end up in null deref.
Fix that by unloading the representors in the opposite order of load.
Fixes: cb67b832921c ("net/mlx5e: Introduce SRIOV VF representors")
Signed-off-by: Shahar Klein <[email protected]>
Reviewed-by: Roi Dayan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Currently if vxlan tunnel ipv6 src isn't supplied the driver fails to
resolve it as part of the route lookup. The resulting encap header
is left with a zeroed out ipv6 src address so the packets are sent
with this src ip.
Use an appropriate route lookup API that also resolves the source
ipv6 address if it's not supplied.
Fixes: ce99f6b97fcd ('net/mlx5e: Support SRIOV TC encapsulation offloads for IPv6 tunnels')
Signed-off-by: Paul Blakey <[email protected]>
Reviewed-by: Or Gerlitz <[email protected]>
Reviewed-by: Roi Dayan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Currently, increasing the number of combined channels is changing
the RSS spread to use the new created channels.
Prevent the RSS spread change in case the user explicitly declare it,
to avoid overriding user configuration.
Tested:
when RSS default:
# ethtool -L ens8 combined 4
RSS spread will change and point to 4 channels.
# ethtool -X ens8 equal 4
# ethtool -L ens8 combined 6
RSS will not change after increasing the number of the channels.
Fixes: 8bf368620486 ('ethtool: ensure channel counts are within bounds during SCHANNELS')
Signed-off-by: Inbar Karmy <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Function mlx5e_dealloc_rx_wqe is using page pointer value as an
indication to valid DMA mapping. In case that the mapping failed, we
released the page but kept the dangling pointer. Store the page pointer
only after the DMA mapping passed to avoid invalid page DMA unmap.
Fixes: bc77b240b3c5 ("net/mlx5e: Add fragmented memory support for RX multi packet WQE")
Signed-off-by: Eran Ben Elisha <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
MLX5_INTERFACE_STATE_SHUTDOWN is not used in the code.
Fixes: 5fc7197d3a25 ("net/mlx5: Add pci shutdown callback")
Signed-off-by: Huy Nguyen <[email protected]>
Reviewed-by: Daniel Jurgens <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
There is an issue where the firmware fails during mlx5_load_one,
the health_care timer detects the issue and schedules a health_care call.
Then the mlx5_load_one detects the issue, cleans up and quits. Then
the health_care starts and calls mlx5_unload_one to clean up the resources
that no longer exist and causes kernel panic.
The root cause is that the bit MLX5_INTERFACE_STATE_DOWN is not set
after mlx5_load_one fails. The solution is removing the bit
MLX5_INTERFACE_STATE_DOWN and quit mlx5_unload_one if the
bit MLX5_INTERFACE_STATE_UP is not set. The bit MLX5_INTERFACE_STATE_DOWN
is redundant and we can use MLX5_INTERFACE_STATE_UP instead.
Fixes: 5fc7197d3a25 ("net/mlx5: Add pci shutdown callback")
Signed-off-by: Huy Nguyen <[email protected]>
Reviewed-by: Daniel Jurgens <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Support for ISSI version 0 was recently broken as the arm_srq_cmd
command, which is used only for ISSI version 0, was given the opcode
for ISSI version 1 instead of ISSI version 0.
Change arm_srq_cmd to use the correct command opcode for ISSI version
0.
Fixes: af1ba291c5e4 ('{net, IB}/mlx5: Refactor internal SRQ API')
Signed-off-by: Noa Osherovich <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Current code doesn't report DCB_CAP_DCBX_HOST capability when query
through getcap. User space lldptool expects capability to have HOST mode
set when it wants to configure DCBX CEE mode. In absence of HOST mode
capability, lldptool fails to switch to CEE mode.
This fix returns DCB_CAP_DCBX_HOST capability when port's DCBX
controlled mode is under software control.
Fixes: 3a6a931dfb8e ("net/mlx5e: Support DCBX CEE API")
Signed-off-by: Huy Nguyen <[email protected]>
Reviewed-by: Parav Pandit <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
qos capability is the master capability bit that determines
if the DCBX is supported for the PCI function. If this bit is off,
driver cannot run any dcbx code.
Fixes: e207b7e99176 ("net/mlx5e: ConnectX-4 firmware support for DCBX")
Signed-off-by: Huy Nguyen <[email protected]>
Reviewed-by: Parav Pandit <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
It is quite common for ti_cm_get_macid() to fail on some of the
platforms it is invoked on. They include any platform where
mac address is not part of SoC register space.
On these platforms, mac address is read and populated in
device-tree by bootloader. An example is TI DA850.
Downgrade the severity of message to "information", so it does
not spam logs when 'quiet' boot is desired.
Signed-off-by: Sekhar Nori <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|