virtio attempts to clear the MTU feature bit if the value is out of the
supported range, but this has no real effect since FEATURES_OK has
already been set.
Fix this up by checking the MTU in the new validate callback.
Fixes: 14de9d114a ("virtio-net: Add initial MTU advice feature")
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
If one enables e.g. jumbo frames without mergeable
buffers, packets won't fit in 1500 byte buffers
we use. Switch to big packet mode instead.
TODO: make sizing more exact, possibly extend small
packet mode to use larger pages.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
In case an XDP program is attached, reserve XDP_PACKET_HEADROOM
bytes at the beginning of the packet for the program to play
with.
Modify the XDP logic in the driver to fill-in the missing bits
and re-calculate offsets and length after the program has finished
running to properly reflect the current status of the packet.
We can then go and remove the limitation of not supporting XDP programs
where xdp_adjust_head is set.
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Driver currently doesn't support any headroom; The only 'available'
space it has in the head of the buffer is due to the placement
offset.
In order to allow [later] support of XDP adjustment of headroom,
modify the the ingress flow to properly handle a scenario where
the packets would have such.
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Current implementation of VFs is very tight in regard to queue
resources. VFs support for XDP would require quite a bit of additional
infrastructure in qede and qed [sharing of queue-zones between queues,
more VF cids, mapping of the doorbell bar, etc.].
For now, prevent XDP programs from being attached to VFs.
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Driver is currently using dma_unmap_single() with the address it
passed to device for the purpose of forwarding, but the XDP
transmission buffer was originally a page allocated for the rx-queue.
The mapped address is likely to differ from the original mapped
address due to the placement offset.
This difference is going to get even bigger once we support headroom.
Cache the original mapped address of the page, and use it for unmapping
of the buffer when completion arrives for the XDP forwarded packet.
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, each time an ingress packet is passed to networking stack
the driver increments a per-queue SW statistic.
As we want to have additional fields in the first cache-line of the
Rx-queue struct, change flow so this statistic would be updated once per
NAPI run. We will later push the statistic to a different cache line.
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When the driver is removed or shut down, close any attached clients
(i.e. i40iw). This prevents a panic seen sometimes on forced driver
removal or system shutdown when iWarp is running.
Change-ID: I4f6161e5a73ffbb2fd5883567b007310302bfcb5
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
In some cases, a client (i40iw) may already be present when probe is
called. Check for this, and add a client instance if necessary.
Change-ID: I2009312694b7ad81f1023919e4c6c86181f21689
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
When the driver is unloaded, we need to remove the client instance,
otherwise we leak memory.
Change-ID: If1e7882ac1f6ce15d004722fafbe31afbe0adc9a
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch adds a capability negotiation between VF and PF using ENCAP/
ENCAP_CSUM offload flags in order for the VF to support outer checksum
and TSO offloads for encapsulated packets. These capabilities were assumed
by default and enabled in current hardware. Going forward, these features
needs to be negotiated with PF before advertising to the stack.
Additionally, strip out the mac.type checks for X722 since outer checksums
are enabled based on the ENCAP_CSUM offload negotiation flag and maintain
consistency between drivers in how the features are configured.
Change-ID: Ie380a6f57eca557a2bb575b66b12fae36d308920
Signed-off-by: Preethi Banala <preethi.banala@intel.com>
Signed-off-by: Alan Brady <alan.brady@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The HW incorrectly calculates the frame size without the vlan
tag and compares that against 64. It will thus flag 64-bytes
frames with a vlan tag as 60-bytes frames "runt" packets
which we'll then drop. Thus we end up dropping ARP packets
on vlan's ...
It does that whether vlan tag stripping is enabled or not.
This works around it by ignoring the "runt" error bit of the
frame has been vlan tagged and is at least 60 bytes.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Directly access the fields when needed. The accessors add clutter
not clarity and in some cases cause unnecessary read-modify-write
type access on the slow (uncached) descriptor memory.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The current driver receive path allocates pages and stashes
them into SKB fragments. This is not particularly useful as
we don't support jumbo frames (which wouldn't be great with
the small FIFOs on all the known implementations) anyway.
It also makes us flush the caches and allocate more memory
for RX than necessary.
So set our RX buf to our max packet size instead (which we
bump to 1536 bytes to account for packets with vlan tags
etc...) like most other ethernet drivers.
Then allocate skbs when populating the receive ring and DMA
directly into them.
This simplifies the RX path further.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
We don't handle fragmented RX packets, so the "looping"
helpers to locate the first segment of a packet or to
drop a packet aren't actually helping.
Take them out and simplify ftgmac100_rx_packet() further
as a result.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The fast path has a single unlikely() test for any error bit,
calling into a helper that sets the appropriate statistics.
The various netdev_info aren't particularly interesting. If
we want to differentiate the various length errors later we
can introduce driver specific stats using ethtool.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Read the descriptor field only once and check for IP header
checksum errors as well
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can occasionally fail to allocate new RX buffers at
runtime or when starting the driver. At the moment the
latter just fails to open which is fine but the former
leaves stale DMA pointers in the ring.
Instead, use a scratch page and have all RX ring descriptors
point to it by default unless a proper buffer can be allocated.
It will help later on when re-initializing the whole ring
at runtime on link changes since there is no clean failure
path there unlike open().
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
We don't support jumbo frames, we will never receive a
fragmented packet, the RX buffer is always big enough,
if not then it's a runaway packet that can be dropped.
So take out the loop that handles such things in
ftgmac100_rx_packet() which will help with subsequent
simplifications and improvements to the RX path
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
RX moderation default parameters shouldn't be set in
mlx5e_build_rx_cq_param since it would reset the values every time on
netdev open/close. Instead, it should be set in
mlx5e_set_rx_cq_mode_params which is called on driver load only.
Fixes: 6a9764efb2 ("net/mlx5e: Isolate open_channels from priv->params")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reuse the code for mlx5e_alloc_cq and mlx5e_alloc_drop_cq, as they
have a similar flow.
Prior to this patch, the CQEs in the "drop CQ" were not initialized,
fixed
it with the shared flow of alloc CQ. This is not a critical bug as the
RQ connected to this CQ never moved to RTS, but still better to have
this right.
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Add the board id (PSID) to the firmware-version field
in the ethtool -i (driver information).
The PSID is shown in parentheses, next to the fw-version.
$ ethtool -i ens6
firmware-version: 12.14.1101 (MT_2190110032)
Signed-off-by: Inbar Karmy <inbark@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
FW version should be reported as X.Y.ZZZZ, add leading zeroes to sub
minor in order to fix it.
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Make mlx5e_modify_rqs_vsd a static function and remove from en.h in
order to reduce redundant exposure of functions.
Signed-off-by: Guy Ergas <guye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Add support for rx-fcs flag from ethtool.
In case this flag is set, update all RQs to scatter the FCS data into
the packet.
Signed-off-by: Guy Ergas <guye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Rename the ConnectX-5 PCIe 4.0 to be ConnectX-5 Ex.
Also add the upcoming ConnectX-6 and it's VF IDs to the list.
Signed-off-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
No need to maintain the various open archipelagos as a list -
The maximal number of them is known, and we can use the CID
as key for random-access into the array.
Signed-off-by: Michal Kalderon <Michal.Kalderon@caviumc.om>
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Management firmware can query for some basic iSCSI-related statistics.
Provide those just as we do for other protocols.
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that management firmware is capable of telling us the number of CQs
available for a given PF, qed needs to communicate the number to qedi
so it would know have many to use.
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Firmware provides a statistic for the number of out-of-order isles
it used - fill it in the iscsi-related statistics.
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Before initializing the chip's engine, driver currently closes a set
of registers on the HW's ingress flow to prevent packets from slipping
in while they're not supposed to.
This configuration is insufficient, as there are some scenarios where
packets would still arrive even when said registers are set,
but the management firmware already closes other per-port registers
that do suffice, making this setting unnecessray.
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Default HW configuration is optimal for an architecture where cache
line size is 64B.
During chip initialization, properly initialize the cache line size
in HW to avoid possible redundant PCI transactions.
Signed-off-by: Tomer Tayar <Tomer.Tayar@cavium.com>
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to access HW registers driver needs to acquire a PTT entry
[mapping between bar memory and internal chip address].
Since acquiring PTT entries could fail [at least in theory] as their
number is finite and other flows can hold them, we reserve special PTT
entries for 'important' enough flows - ones we want to guarantee that
would not be susceptible to such issues.
One such special entry is the 'main' PTT which is meant to be used in
flows such as chip initialization and de-initialization.
However, there are other flows that are also using that same entry
for their own purpose, and might run concurrently with the original
flows [notice that for most cases using the main-ptt by mistake, such
a race is still impossible, at least today].
This patch re-organizes the various functions that currently use the
main_ptt in one of two ways:
- If a function shouldn't use the main_ptt it starts acquiring and
releasing it's own PTT entry and use it instead. Notice if those
functions previously couldn't fail, they now can [as acquisition
might fail].
- Change the prototypes so that the main_ptt would be received as
a parameter [instead of explicitly accessing it].
This prevents the future risk of adding codes that introduces new
use-cases for flows using the main_ptt, ones that might be in race
with the actual 'main' flows.
Signed-off-by: Rahul Verma <Rahul.Verma@cavium.com>
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
PTT entries are per-hwfn; If some errneous flow is trying
to use a PTT belonging to a differnet hwfn warn user, as this
can break every register accessing flow later and is very hard
to root-cause.
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit f6988cb63a ("team: don't call netdev_change_features under
team->lock") fixed the issue calling netdev_change_features under
team->lock for team_compute_features.
But there are still two places where it calls netdev_change_features
under team->lock, team_port_add and team_port_del. It may cause a
dead lock when the slave port with LRO enabled is added.
This patch is to fix this dead lock by moving netdev_change_features
out of team_port_add and team_port_del, and call it after unlocking
the team lock.
Reported-by: Patrick Talbert <ptalbert@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jeff Kirsher says:
====================
100GbE Intel Wired LAN Driver Updates 2017-04-05
This series contains updates to fm10k only.
Phil Turnbull from Oracle fixes an issue where the argument provided to
FM10K_REMOVED macro was not what was expecting.
Jake modifies the driver to replace the bitwise operators and defines with
a BITMAP and enumeration values to avoid race conditions. Also future
proof the driver so that developers do not have to remember to re-size the
bitmaps when adding new values. Fixed the wording of a code comment to
avoid stating that we return a value for a void function.
Ngai-Mint makes sure that when configuring the receive ring, we make sure
the receive queue is disabled. Fixed an issue where interfaces were
resetting because the transmit mailbox FIFO was becoming full since the
host was not ready, so ensure the host is ready before queueing up
mailbox messages.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
While unlikely, this makes sure any format strings in the device name
can't exposure information via the resulting workqueue name.
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
While unlikely, this makes sure the workqueue name won't be processed
as a format string.
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
When qedr is enabled, qed would try dividing the msi-x vectors between
L2 and RoCE, starting with L2 and providing it with sufficient vectors
for its queues.
Problem is qed would also do that for storage partitions, and as those
don't need queues it would lead qed to award those partitions with 0
msi-x vectors, causing them to believe theye're using INTa and
preventing them from operating.
Fixes: 51ff17251c ("qed: Add support for RoCE hw init")
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Dan's static checker reported the following:
drivers/net/dsa/dsa_loop.c:223 dsa_loop_port_vlan_dump()
error: uninitialized symbol 'err'.
which could happen if we do hit the continue statement for each iteration of
the loop. Initialize err to 0 here.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Fixes: 98cd1552ea ("net: dsa: Mock-up driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Dan's static analyzer reported the following:
drivers/net/dsa/dsa_loop.c:181 dsa_loop_port_vlan_del()
error: XXX uninitialized symbol 'pvid'.
we were missing the assignment of pvid to ps->vid, so add that.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Fixes: 98cd1552ea ("net: dsa: Mock-up driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There seems to be a missing break on the OOO_LB_TC case, pq_id
is being assigned and then re-assigned on the fall through default
case and that seems suspect.
Detected by CoverityScan, CID#1424402 ("Missing break in switch")
Fixes: b5a9ee7cf3 ("qed: Revise QM cofiguration")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Yuval Mintz <Yuval.Mintz@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 9008ae0748 ("net/mlx5e: Minimize mlx5e_{open/close}_locked")
copied the calls to netif_set_real_num_{tx,rx}_queues from
mlx5e_open_locked to mlx5e_activate_priv_channels and wraps them in an
if condition to test for netdev->real_num_{tx,rx}_queues.
But netdev->real_num_rx_queues is conditionally compiled in if CONFIG_SYSFS
is set. Without CONFIG_SYSFS the build fails:
drivers/net/ethernet/mellanox/mlx5/core/en_main.c: In function 'mlx5e_activate_priv_channels':
drivers/net/ethernet/mellanox/mlx5/core/en_main.c:2515:12: error: 'struct net_device' has no member named 'real_num_rx_queues'; did you mean 'real_num_tx_queues'?
Fix this by unconditionally call netif_set_real_num{tx,rx}_queues like before
commit 9008ae0748.
Fixes: 9008ae0748 ("net/mlx5e: Minimize mlx5e_{open/close}_locked")
Signed-off-by: Tobias Regnery <tobias.regnery@gmail.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
First, don't look at the interrupt status in the poll loop
to decide what to poll. It's wrong. If we have run out of
budget, we may still have RX packets to unqueue but no more
RX interrupt pending.
So instead move the code looking at the interrupt status
into the interrupt handler where it belongs. That avoids a slow
MMIO read in the NAPI fast path. We keep the abnormal interrupts
enabled while NAPI is scheduled.
While at it, actually do something useful in the "error" cases:
On AHB bus error, trigger the new reset task, that's about all
we can do. On RX packet fifo or descriptor overflows, we need
to restart the MAC after having freed things up. So set a flag
that NAPI will see and use to perform that restart after
harvesting the RX ring.
Finally, we shouldn't complete NAPI if there are still outgoing
packets that will need harvesting. Waiting for more interrupts
is less efficient than letting NAPI run a while longer while
the queue drains.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The interrupt is neither enabled nor registered when the interface
isn't running (regardless of whether we use nc-si or not) so the
test isn't useful.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The HW requires a full MAC reset when changing the speed.
Additionally the Aspeed documentation spells out that the
MAC needs to be reset twice with a 10us interval.
We thus move the speed setting and top level reset code
into a new ftgmac100_reset_and_config_mac() function which
handles both. Move the ring pointers initialization there
too in order to reflect the HW change.
Also reduce the timeout for the MAC reset as it shouldn't
take more than 300 clock cycles according to the doc.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
