Add tracepoints for the following events:
- Add FDB entry
- Delete FDB entry
- Create bridge VLAN
- Cleanup bridge VLAN
- Link port to the bridge
- Unlink port from the bridge
Signed-off-by: Pawel Chmielewski <pawel.chmielewski@intel.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Remove fdb entries always when ageing time expired.
Allow user to set ageing time using port object attribute.
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Port VLAN in this case means push and pop VLAN action on specific vid.
There are a few limitation in hardware:
- push and pop can't be used separately
- if port VLAN is used there can't be any trunk VLANs, because pop
action is done on all traffic received by VSI in port VLAN mode
- port VLAN mode on uplink port isn't supported
Reflect these limitations in code using dev_info to inform the user
about unsupported configuration.
In bridge mode there is a need to configure port vlan without resetting
VFs. To do that implement ice_port_vlan_on/off() functions. They are
only configuring correct vlan_ops to allow setting port vlan.
We also need to clear port vlan without resetting the VF which is not
supported right now. Change it by implementing clear_port_vlan ops.
As previous VLAN configuration isn't always the same, store current
config while creating port vlan and restore it in clear function.
Configuration steps:
- configure switchdev with bridge
- #bridge vlan add dev eth0 vid 120 pvid untagged
- #bridge vlan add dev eth1 vid 120 pvid untagged
- ping from VF0 to VF1
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Add support for matching on VLAN tag in bridge offloads.
Currently only trunk mode is supported.
To enable VLAN filtering (existing FDB entries will be deleted):
ip link set $BR type bridge vlan_filtering 1
To add VLANs to bridge in trunk mode:
bridge vlan add dev $PF1 vid 110-111
bridge vlan add dev $VF1_PR vid 110-111
Signed-off-by: Marcin Szycik <marcin.szycik@intel.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Introduce new "guard" rule upon FDB entry creation.
It matches on src_mac, has valid bit unset, allow_pass_l2 set
and has a nop action.
Previously introduced "forward" rule matches on dst_mac, has valid
bit set, need_pass_l2 set and has a forward action.
With these rules, a packet will be offloaded only if FDB exists in both
directions (RX and TX).
Let's assume link partner sends a packet to VF1: src_mac = LP_MAC,
dst_mac = is VF1_MAC. Bridge adds FDB, two rules are created:
1. Guard rule matching on src_mac == LP_MAC
2. Forward rule matching on dst_mac == LP_MAC
Now VF1 responds with src_mac = VF1_MAC, dst_mac = LP_MAC. Before this
change, only one rule with dst_mac == LP_MAC would have existed, and the
packet would have been offloaded, meaning the bridge wouldn't add FDB in
the opposite direction. Now, the forward rule matches (dst_mac == LP_MAC),
but it has need_pass_l2 set an there is no guard rule with
src_mac == VF1_MAC, so the packet goes through slow-path and the bridge
adds FDB. Two rules are created:
1. Guard rule matching on src_mac == VF1_MAC
2. Forward rule matching on dst_mac == VF1_MAC
Further packets in both directions will be offloaded.
The same example is true in opposite direction (i.e. VF1 is the first to
send a packet out).
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Marcin Szycik <marcin.szycik@intel.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Listen for SWITCHDEV_FDB_{ADD|DEL}_TO_DEVICE events while in switchdev
mode. Accept these events on both uplink and VF PR ports. Add HW
rules in newly created workqueue. FDB entries are stored in rhashtable
for lookup when removing the entry and in the list for cleanup
purpose. Direction of the HW rule depends on the type of the ports
on which the FDB event was received:
ICE_ESWITCH_BR_UPLINK_PORT:
TX rule that forwards the packet to the LAN (egress).
ICE_ESWITCH_BR_VF_REPR_PORT:
RX rule that forwards the packet to the VF associated
with the port representor.
In both cases the rule matches on the dst mac address.
All the FDB entries are stored in the bridge structure.
When the port is removed all the FDB entries associated with
this port are removed as well. This is achieved thanks to the reference
to the port that FDB entry holds.
In the fwd rule we use only one lookup type (MAC address)
but lkups_cnt variable is already introduced because
we will have more lookups in the subsequent patches.
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
With this patch, ice driver is able to track if the port
representors or uplink port were added to the linux bridge in
switchdev mode. Listen for NETDEV_CHANGEUPPER events in order to
detect this. ice_esw_br data structure reflects the linux bridge
and stores all the ports of the bridge (ice_esw_br_port) in
xarray, it's created when the first port is added to the bridge and
freed once the last port is removed. Note that only one bridge is
supported per eswitch.
Bridge port (ice_esw_br_port) can be either a VF port representor
port or uplink port (ice_esw_br_port_type). In both cases bridge port
holds a reference to the VSI, VF's VSI in case of the PR and uplink
VSI in case of the uplink. VSI's index is used as an index to the
xarray in which ports are stored.
Add a check which prevents configuring switchdev mode if uplink is
already added to any bridge. This is needed because we need to listen
for NETDEV_CHANGEUPPER events to record if the uplink was added to
the bridge. Netdevice notifier is registered after eswitch mode
is changed to switchdev.
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
In switchdev mode uplink VSI is supposed to receive all packets that
were not matched by existing filters. If ICE_AQ_VSI_SW_FLAG_LOCAL_LB
bit is unset and we have a filter associated with uplink VSI
which matches on dst mac equal to MAC1, then packets with src mac equal
to MAC1 will be pruned from reaching uplink VSI.
Fix this by updating uplink VSI with ICE_AQ_VSI_SW_FLAG_LOCAL_LB bit
set when configuring switchdev mode.
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
In switchdev mode, uplink VSI is configured to be default
VSI which means it will receive all unmatched packets.
In order to receive vlan packets we need to disable vlan pruning
as well. This is done by dis_rx_filtering vlan op.
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
There is possibility that ice_eswitch_port_start_xmit might be
called while some resources are still not allocated which might
cause NULL pointer dereference. Fix this by checking if switchdev
configuration was finished.
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Don't allow to change promisc mode in switchdev mode.
When switchdev is configured, PF netdev is set to be a
default VSI. This is needed for the slow-path to work correctly.
All the unmatched packets will be directed to PF netdev.
It is possible that this setting might be overwritten by
ndo_set_rx_mode. Prevent this by checking if switchdev is
enabled in ice_set_rx_mode.
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Advanced rules for ctrl VSI will be removed anyway when the
VSI will cleaned up, no need to do it explicitly.
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
VXLAN-GPE does not add an extra inner Ethernet header. Take that into
account when calculating header length.
This causes problems in skb_tunnel_check_pmtu, where incorrect PMTU is
cached.
In the collect_md mode (which is the only mode that VXLAN-GPE
supports), there's no magic auto-setting of the tunnel interface MTU.
It can't be, since the destination and thus the underlying interface
may be different for each packet.
So, the administrator is responsible for setting the correct tunnel
interface MTU. Apparently, the administrators are capable enough to
calculate that the maximum MTU for VXLAN-GPE is (their_lower_MTU - 36).
They set the tunnel interface MTU to 1464. If you run a TCP stream over
such interface, it's then segmented according to the MTU 1464, i.e.
producing 1514 bytes frames. Which is okay, this still fits the lower
MTU.
However, skb_tunnel_check_pmtu (called from vxlan_xmit_one) uses 50 as
the header size and thus incorrectly calculates the frame size to be
1528. This leads to ICMP too big message being generated (locally),
PMTU of 1450 to be cached and the TCP stream to be resegmented.
The fix is to use the correct actual header size, especially for
skb_tunnel_check_pmtu calculation.
Fixes: e1e5314de0 ("vxlan: implement GPE")
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In iavf_adminq_task(), if the function can't acquire the
adapter->crit_lock, it checks if the driver is removing. If so, it simply
exits without re-enabling the interrupt. This is done to ensure that the
task stops processing as soon as possible once the driver is being removed.
However, if the IAVF_FLAG_PF_COMMS_FAILED is set, the function checks this
before attempting to acquire the lock. In this case, the function exits
early and re-enables the interrupt. This will happen even if the driver is
already removing.
Avoid this, by moving the check to after the adapter->crit_lock is
acquired. This way, if the driver is removing, we will not re-enable the
interrupt.
Fixes: fc2e6b3b13 ("iavf: Rework mutexes for better synchronisation")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
In iavf_adminq_task(), if kzalloc() fails to allocate the event.msg_buf,
the function will exit without releasing the adapter->crit_lock.
This is unlikely, but if it happens, the next access to that mutex will
deadlock.
Fix this by moving the unlock to the end of the function, and adding a new
label to allow jumping to the unlock portion of the function exit flow.
Fixes: fc2e6b3b13 ("iavf: Rework mutexes for better synchronisation")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
The debugfs_create_dir() function returns error pointers.
It never returns NULL. Most incorrect error checks were fixed,
but the one in i40e_dbg_init() was forgotten.
Fix the remaining error check.
Fixes: 02e9c29081 ("i40e: debugfs interface")
Signed-off-by: Wang Ming <machel@vivo.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
-----BEGIN PGP SIGNATURE-----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=VRCb
-----END PGP SIGNATURE-----
Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says:
====================
pull-request: bpf-next 2023-07-19
We've added 45 non-merge commits during the last 3 day(s) which contain
a total of 71 files changed, 7808 insertions(+), 592 deletions(-).
The main changes are:
1) multi-buffer support in AF_XDP, from Maciej Fijalkowski,
Magnus Karlsson, Tirthendu Sarkar.
2) BPF link support for tc BPF programs, from Daniel Borkmann.
3) Enable bpf_map_sum_elem_count kfunc for all program types,
from Anton Protopopov.
4) Add 'owner' field to bpf_rb_node to fix races in shared ownership,
Dave Marchevsky.
5) Prevent potential skb_header_pointer() misuse, from Alexei Starovoitov.
* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (45 commits)
bpf, net: Introduce skb_pointer_if_linear().
bpf: sync tools/ uapi header with
selftests/bpf: Add mprog API tests for BPF tcx links
selftests/bpf: Add mprog API tests for BPF tcx opts
bpftool: Extend net dump with tcx progs
libbpf: Add helper macro to clear opts structs
libbpf: Add link-based API for tcx
libbpf: Add opts-based attach/detach/query API for tcx
bpf: Add fd-based tcx multi-prog infra with link support
bpf: Add generic attach/detach/query API for multi-progs
selftests/xsk: reset NIC settings to default after running test suite
selftests/xsk: add test for too many frags
selftests/xsk: add metadata copy test for multi-buff
selftests/xsk: add invalid descriptor test for multi-buffer
selftests/xsk: add unaligned mode test for multi-buffer
selftests/xsk: add basic multi-buffer test
selftests/xsk: transmit and receive multi-buffer packets
xsk: add multi-buffer documentation
i40e: xsk: add TX multi-buffer support
ice: xsk: Tx multi-buffer support
...
====================
Link: https://lore.kernel.org/r/20230719175424.75717-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Set eop bit in TX desc command only for the last descriptor of the
packet and do not set for all preceding descriptors.
Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-17-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Most of this patch is about actually supporting XDP_TX action. Pure Tx
ZC support is only about looking at XDP_PKT_CONTD presence at options
field and based on that generating EOP bit on Tx HW descriptor. This is
that simple due to the implementation on
xsk_tx_peek_release_desc_batch() where we are making sure that last
produced descriptor is an EOP one.
Overwrite xdp_zc_max_segs with a value that defines max scatter-gatter
count on Tx side that HW can handle.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-16-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch is inspired from the multi-buffer support in non-zc path for
i40e as well as from the patch to support zc on ice. Each subsequent
frag is added to skb_shared_info of the first frag for possible xdp_prog
use as well to xsk buffer list for accessing the buffers in af_xdp.
For XDP_PASS, new pages are allocated for frags and contents are copied
from memory backed by xsk_buff_pool.
Replace next_to_clean with next_to_process as done in non-zc path and
advance it for every buffer and change the semantics of next_to_clean to
point to the first buffer of a packet. Driver will use next_to_process
in the same way next_to_clean was used previously.
For the non multi-buffer case, next_to_process and next_to_clean will
always be the same since each packet consists of a single buffer.
Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-14-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This support is strongly inspired by work that introduced multi-buffer
support to regular Rx data path in ice. There are some differences,
though. When adding a frag, besides adding it to skb_shared_info, use
also fresh xsk_buff_add_frag() helper. Reason for doing both things is
that we can not rule out the fact that AF_XDP pipeline could use XDP
program that needs to access frame fragments. Without them being in
skb_shared_info it will not be possible. Another difference is that
XDP_PASS has to allocate a new pages for each frags and copy contents
from memory backed by xsk_buff_pool.
chain_len that is used for programming HW Rx descriptors no longer has
to be limited to 1 when xsk_pool is present - remove this restriction.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-13-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Tony Nguyen says:
====================
Intel Wired LAN Driver Updates 2023-07-14 (i40e)
This series contains updates to i40e driver only.
Ivan Vecera adds waiting for VF to complete initialization on VF related
configuration callbacks.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Tony Nguyen says:
====================
Intel Wired LAN Driver Updates 2023-07-17 (iavf)
This series contains updates to iavf driver only.
Ding Hui fixes use-after-free issue by calling netif_napi_del() for all
allocated q_vectors. He also resolves out-of-bounds issue by not
updating to new values when timeout is encountered.
Marcin and Ahmed change the way resets are handled so that the callback
operating under the RTNL lock will wait for the reset to finish, the
rtnl_lock sensitive functions in reset flow will schedule the netdev update
for later in order to remove circular dependency with the critical lock.
* '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue:
iavf: fix reset task race with iavf_remove()
iavf: fix a deadlock caused by rtnl and driver's lock circular dependencies
Revert "iavf: Do not restart Tx queues after reset task failure"
Revert "iavf: Detach device during reset task"
iavf: Wait for reset in callbacks which trigger it
iavf: use internal state to free traffic IRQs
iavf: Fix out-of-bounds when setting channels on remove
iavf: Fix use-after-free in free_netdev
====================
Link: https://lore.kernel.org/r/20230717175205.3217774-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In normal operation, each populated queue item has
next_to_watch pointing to the last TX desc of the packet,
while each cleaned item has it set to 0. In particular,
next_to_use that points to the next (necessarily clean)
item to use has next_to_watch set to 0.
When the TX queue is used both by an application using
AF_XDP with ZEROCOPY as well as a second non-XDP application
generating high traffic, the queue pointers can get in
an invalid state where next_to_use points to an item
where next_to_watch is NOT set to 0.
However, the implementation assumes at several places
that this is never the case, so if it does hold,
bad things happen. In particular, within the loop inside
of igc_clean_tx_irq(), next_to_clean can overtake next_to_use.
Finally, this prevents any further transmission via
this queue and it never gets unblocked or signaled.
Secondly, if the queue is in this garbled state,
the inner loop of igc_clean_tx_ring() will never terminate,
completely hogging a CPU core.
The reason is that igc_xdp_xmit_zc() reads next_to_use
before acquiring the lock, and writing it back
(potentially unmodified) later. If it got modified
before locking, the outdated next_to_use is written
pointing to an item that was already used elsewhere
(and thus next_to_watch got written).
Fixes: 9acf59a752 ("igc: Enable TX via AF_XDP zero-copy")
Signed-off-by: Florian Kauer <florian.kauer@linutronix.de>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de>
Tested-by: Kurt Kanzenbach <kurt@linutronix.de>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://lore.kernel.org/r/20230717175444.3217831-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add TransmissionOverrun as per defined by IEEE 802.1Q Bridges.
TransmissionOverrun counter shall be incremented if the implementation
detects that a frame from a given queue is still being transmitted by
the MAC when that gate-close event for that queue occurs.
This counter is utilised by the Certification conformance test to
inform the user application whether any packets are currently being
transmitted on a particular queue during a gate-close event.
Intel Discrete I225/I226 have a mechanism to not transmit a packets if
the gate open time is insufficient for the packet transmission by setting
the Strict_End bit. Thus, it is expected for this counter to be always
zero at this moment.
Inspired from enetc_taprio_stats() and enetc_taprio_queue_stats(), now
driver also report the tx_overruns counter per traffic class.
User can get this counter by using below command:
1) tc -s qdisc show dev <interface> root
2) tc -s class show dev <interface>
Test Result (Before):
class mq :1 root
Sent 1289 bytes 20 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
class mq :2 root
Sent 124 bytes 2 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
class mq :3 root
Sent 46028 bytes 86 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
class mq :4 root
Sent 2596 bytes 14 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
Test Result (After):
class taprio 100:1 root
Sent 8491 bytes 38 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
Transmit overruns: 0
class taprio 100:2 root
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
Transmit overruns: 0
class taprio 100:3 root
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
Transmit overruns: 0
class taprio 100:4 root
Sent 994 bytes 11 pkt (dropped 0, overlimits 0 requeues 1)
backlog 0b 0p requeues 1
Transmit overruns: 0
Signed-off-by: Muhammad Husaini Zulkifli <muhammad.husaini.zulkifli@intel.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://lore.kernel.org/r/20230714201428.1718097-1-anthony.l.nguyen@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The reset task is currently scheduled from the watchdog or adminq tasks.
First, all direct calls to schedule the reset task are replaced with the
iavf_schedule_reset(), which is modified to accept the flag showing the
type of reset.
To prevent the reset task from starting once iavf_remove() starts, we need
to check the __IAVF_IN_REMOVE_TASK bit before we schedule it. This is now
easily added to iavf_schedule_reset().
Finally, remove the check for IAVF_FLAG_RESET_NEEDED in the watchdog task.
It is redundant since all callers who set the flag immediately schedules
the reset task.
Fixes: 3ccd54ef44 ("iavf: Fix init state closure on remove")
Fixes: 14756b2ae2 ("iavf: Fix __IAVF_RESETTING state usage")
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
A driver's lock (crit_lock) is used to serialize all the driver's tasks.
Lockdep, however, shows a circular dependency between rtnl and
crit_lock. This happens when an ndo that already holds the rtnl requests
the driver to reset, since the reset task (in some paths) tries to grab
rtnl to either change real number of queues of update netdev features.
[566.241851] ======================================================
[566.241893] WARNING: possible circular locking dependency detected
[566.241936] 6.2.14-100.fc36.x86_64+debug #1 Tainted: G OE
[566.241984] ------------------------------------------------------
[566.242025] repro.sh/2604 is trying to acquire lock:
[566.242061] ffff9280fc5ceee8 (&adapter->crit_lock){+.+.}-{3:3}, at: iavf_close+0x3c/0x240 [iavf]
[566.242167]
but task is already holding lock:
[566.242209] ffffffff9976d350 (rtnl_mutex){+.+.}-{3:3}, at: iavf_remove+0x6b5/0x730 [iavf]
[566.242300]
which lock already depends on the new lock.
[566.242353]
the existing dependency chain (in reverse order) is:
[566.242401]
-> #1 (rtnl_mutex){+.+.}-{3:3}:
[566.242451] __mutex_lock+0xc1/0xbb0
[566.242489] iavf_init_interrupt_scheme+0x179/0x440 [iavf]
[566.242560] iavf_watchdog_task+0x80b/0x1400 [iavf]
[566.242627] process_one_work+0x2b3/0x560
[566.242663] worker_thread+0x4f/0x3a0
[566.242696] kthread+0xf2/0x120
[566.242730] ret_from_fork+0x29/0x50
[566.242763]
-> #0 (&adapter->crit_lock){+.+.}-{3:3}:
[566.242815] __lock_acquire+0x15ff/0x22b0
[566.242869] lock_acquire+0xd2/0x2c0
[566.242901] __mutex_lock+0xc1/0xbb0
[566.242934] iavf_close+0x3c/0x240 [iavf]
[566.242997] __dev_close_many+0xac/0x120
[566.243036] dev_close_many+0x8b/0x140
[566.243071] unregister_netdevice_many_notify+0x165/0x7c0
[566.243116] unregister_netdevice_queue+0xd3/0x110
[566.243157] iavf_remove+0x6c1/0x730 [iavf]
[566.243217] pci_device_remove+0x33/0xa0
[566.243257] device_release_driver_internal+0x1bc/0x240
[566.243299] pci_stop_bus_device+0x6c/0x90
[566.243338] pci_stop_and_remove_bus_device+0xe/0x20
[566.243380] pci_iov_remove_virtfn+0xd1/0x130
[566.243417] sriov_disable+0x34/0xe0
[566.243448] ice_free_vfs+0x2da/0x330 [ice]
[566.244383] ice_sriov_configure+0x88/0xad0 [ice]
[566.245353] sriov_numvfs_store+0xde/0x1d0
[566.246156] kernfs_fop_write_iter+0x15e/0x210
[566.246921] vfs_write+0x288/0x530
[566.247671] ksys_write+0x74/0xf0
[566.248408] do_syscall_64+0x58/0x80
[566.249145] entry_SYSCALL_64_after_hwframe+0x72/0xdc
[566.249886]
other info that might help us debug this:
[566.252014] Possible unsafe locking scenario:
[566.253432] CPU0 CPU1
[566.254118] ---- ----
[566.254800] lock(rtnl_mutex);
[566.255514] lock(&adapter->crit_lock);
[566.256233] lock(rtnl_mutex);
[566.256897] lock(&adapter->crit_lock);
[566.257388]
*** DEADLOCK ***
The deadlock can be triggered by a script that is continuously resetting
the VF adapter while doing other operations requiring RTNL, e.g:
while :; do
ip link set $VF up
ethtool --set-channels $VF combined 2
ip link set $VF down
ip link set $VF up
ethtool --set-channels $VF combined 4
ip link set $VF down
done
Any operation that triggers a reset can substitute "ethtool --set-channles"
As a fix, add a new task "finish_config" that do all the work which
needs rtnl lock. With the exception of iavf_remove(), all work that
require rtnl should be called from this task.
As for iavf_remove(), at the point where we need to call
unregister_netdevice() (and grab rtnl_lock), we make sure the finish_config
task is not running (cancel_work_sync()) to safely grab rtnl. Subsequent
finish_config work cannot restart after that since the task is guarded
by the __IAVF_IN_REMOVE_TASK bit in iavf_schedule_finish_config().
Fixes: 5ac49f3c27 ("iavf: use mutexes for locking of critical sections")
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
This reverts commit 08f1c147b7.
Netdev is no longer being detached during reset, so this fix can be
reverted. We leave the removal of "hacky" IFF_UP flag update.
Signed-off-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
This reverts commit aa626da947.
Detaching device during reset was not fully fixing the rtnl locking issue,
as there could be a situation where callback was already in progress before
detaching netdev.
Furthermore, detaching netdevice causes TX timeouts if traffic is running.
To reproduce:
ip netns exec ns1 iperf3 -c $PEER_IP -t 600 --logfile /dev/null &
while :; do
for i in 200 7000 400 5000 300 3000 ; do
ip netns exec ns1 ip link set $VF1 mtu $i
sleep 2
done
sleep 10
done
Currently, callbacks such as iavf_change_mtu() wait for the reset.
If the reset fails to acquire the rtnl_lock, they schedule the netdev
update for later while continuing the reset flow. Operations like MTU
changes are performed under the rtnl_lock. Therefore, when the operation
finishes, another callback that uses rtnl_lock can start.
Signed-off-by: Dawid Wesierski <dawidx.wesierski@intel.com>
Signed-off-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
There was a fail when trying to add the interface to bonding
right after changing the MTU on the interface. It was caused
by bonding interface unable to open the interface due to
interface being in __RESETTING state because of MTU change.
Add new reset_waitqueue to indicate that reset has finished.
Add waiting for reset to finish in callbacks which trigger hw reset:
iavf_set_priv_flags(), iavf_change_mtu() and iavf_set_ringparam().
We use a 5000ms timeout period because on Hyper-V based systems,
this operation takes around 3000-4000ms. In normal circumstances,
it doesn't take more than 500ms to complete.
Add a function iavf_wait_for_reset() to reuse waiting for reset code and
use it also in iavf_set_channels(), which already waits for reset.
We don't use error handling in iavf_set_channels() as this could
cause the device to be in incorrect state if the reset was scheduled
but hit timeout or the waitng function was interrupted by a signal.
Fixes: 4e5e6b5d9d ("iavf: Fix return of set the new channel count")
Signed-off-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Co-developed-by: Dawid Wesierski <dawidx.wesierski@intel.com>
Signed-off-by: Dawid Wesierski <dawidx.wesierski@intel.com>
Signed-off-by: Sylwester Dziedziuch <sylwesterx.dziedziuch@intel.com>
Signed-off-by: Kamil Maziarz <kamil.maziarz@intel.com>
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
If the system tries to close the netdev while iavf_reset_task() is
running, __LINK_STATE_START will be cleared and netif_running() will
return false in iavf_reinit_interrupt_scheme(). This will result in
iavf_free_traffic_irqs() not being called and a leak as follows:
[7632.489326] remove_proc_entry: removing non-empty directory 'irq/999', leaking at least 'iavf-enp24s0f0v0-TxRx-0'
[7632.490214] WARNING: CPU: 0 PID: 10 at fs/proc/generic.c:718 remove_proc_entry+0x19b/0x1b0
is shown when pci_disable_msix() is later called. Fix by using the
internal adapter state. The traffic IRQs will always exist if
state == __IAVF_RUNNING.
Fixes: 5b36e8d04b ("i40evf: Enable VF to request an alternate queue allocation")
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Commit 028daf8011 ("i40e: Fix attach VF to VM issue") fixed
a race between i40e_ndo_set_vf_mac() and i40e_reset_vf() during
an attachment of VF device to VM. This issue is not related to
setting MAC address only but also VLAN assignment to particular
VF because the newer libvirt sets configured MAC address as well
as an optional VLAN. The same behavior is also for i40e's
.ndo_set_vf_rate and .ndo_set_vf_spoofchk where the callbacks
just check if the VF was initialized but not wait for the finish
of pending reset.
Reproducer:
[root@host ~]# virsh attach-interface guest hostdev --managed 0000:02:02.0 --mac 52:54:00:b4:aa:bb
error: Failed to attach interface
error: Cannot set interface MAC/vlanid to 52:54:00:b4:aa:bb/0 for ifname enp2s0f0 vf 0: Resource temporarily unavailable
Fix this issue by using i40e_check_vf_init_timeout() helper to check
whether a reset of particular VF was finished in i40e's
.ndo_set_vf_vlan, .ndo_set_vf_rate and .ndo_set_vf_spoofchk callbacks.
Tested-by: Ma Yuying <yuma@redhat.com>
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Move the check for VF inited state (with optional up-to 300ms
timeout to separate helper i40e_check_vf_init_timeout() that
will be used in the following commit.
Tested-by: Ma Yuying <yuma@redhat.com>
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Since commit 6624e780a5 ("ice: split ice_vsi_setup into smaller
functions") ice_vsi_release does things twice. There is unregister
netdev which is unregistered in ice_deinit_eth also.
It also unregisters the devlink_port twice which is also unregistered
in ice_deinit_eth(). This double deregistration is hidden because
devl_port_unregister ignores the return value of xa_erase.
[ 68.642167] Call Trace:
[ 68.650385] ice_devlink_destroy_pf_port+0xe/0x20 [ice]
[ 68.655656] ice_vsi_release+0x445/0x690 [ice]
[ 68.660147] ice_deinit+0x99/0x280 [ice]
[ 68.664117] ice_remove+0x1b6/0x5c0 [ice]
[ 171.103841] Call Trace:
[ 171.109607] ice_devlink_destroy_pf_port+0xf/0x20 [ice]
[ 171.114841] ice_remove+0x158/0x270 [ice]
[ 171.118854] pci_device_remove+0x3b/0xc0
[ 171.122779] device_release_driver_internal+0xc7/0x170
[ 171.127912] driver_detach+0x54/0x8c
[ 171.131491] bus_remove_driver+0x77/0xd1
[ 171.135406] pci_unregister_driver+0x2d/0xb0
[ 171.139670] ice_module_exit+0xc/0x55f [ice]
Fixes: 6624e780a5 ("ice: split ice_vsi_setup into smaller functions")
Signed-off-by: Petr Oros <poros@redhat.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
The insertion of an empty frame was introduced with
commit db0b124f02 ("igc: Enhance Qbv scheduling by using first flag bit")
in order to ensure that the current cycle has at least one packet if
there is some packet to be scheduled for the next cycle.
However, the current implementation does not properly check if
a packet is already scheduled for the current cycle. Currently,
an empty packet is always inserted if and only if
txtime >= end_of_cycle && txtime > last_tx_cycle
but since last_tx_cycle is always either the end of the current
cycle (end_of_cycle) or the end of a previous cycle, the
second part (txtime > last_tx_cycle) is always true unless
txtime == last_tx_cycle.
What actually needs to be checked here is if the last_tx_cycle
was already written within the current cycle, so an empty frame
should only be inserted if and only if
txtime >= end_of_cycle && end_of_cycle > last_tx_cycle.
This patch does not only avoid an unnecessary insertion, but it
can actually be harmful to insert an empty packet if packets
are already scheduled in the current cycle, because it can lead
to a situation where the empty packet is actually processed
as the first packet in the upcoming cycle shifting the packet
with the first_flag even one cycle into the future, finally leading
to a TX hang.
The TX hang can be reproduced on a i225 with:
sudo tc qdisc replace dev enp1s0 parent root handle 100 taprio \
num_tc 1 \
map 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 \
queues 1@0 \
base-time 0 \
sched-entry S 01 300000 \
flags 0x1 \
txtime-delay 500000 \
clockid CLOCK_TAI
sudo tc qdisc replace dev enp1s0 parent 100:1 etf \
clockid CLOCK_TAI \
delta 500000 \
offload \
skip_sock_check
and traffic generator
sudo trafgen -i traffic.cfg -o enp1s0 --cpp -n0 -q -t1400ns
with traffic.cfg
#define ETH_P_IP 0x0800
{
/* Ethernet Header */
0x30, 0x1f, 0x9a, 0xd0, 0xf0, 0x0e, # MAC Dest - adapt as needed
0x24, 0x5e, 0xbe, 0x57, 0x2e, 0x36, # MAC Src - adapt as needed
const16(ETH_P_IP),
/* IPv4 Header */
0b01000101, 0, # IPv4 version, IHL, TOS
const16(1028), # IPv4 total length (UDP length + 20 bytes (IP header))
const16(2), # IPv4 ident
0b01000000, 0, # IPv4 flags, fragmentation off
64, # IPv4 TTL
17, # Protocol UDP
csumip(14, 33), # IPv4 checksum
/* UDP Header */
10, 0, 48, 1, # IP Src - adapt as needed
10, 0, 48, 10, # IP Dest - adapt as needed
const16(5555), # UDP Src Port
const16(6666), # UDP Dest Port
const16(1008), # UDP length (UDP header 8 bytes + payload length)
csumudp(14, 34), # UDP checksum
/* Payload */
fill('W', 1000),
}
and the observed message with that is for example
igc 0000:01:00.0 enp1s0: Detected Tx Unit Hang
Tx Queue <0>
TDH <32>
TDT <3c>
next_to_use <3c>
next_to_clean <32>
buffer_info[next_to_clean]
time_stamp <ffff26a8>
next_to_watch <00000000632a1828>
jiffies <ffff27f8>
desc.status <1048000>
Fixes: db0b124f02 ("igc: Enhance Qbv scheduling by using first flag bit")
Signed-off-by: Florian Kauer <florian.kauer@linutronix.de>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
It is possible (verified on a running system) that frames are processed
by igc_tx_launchtime with a txtime before the start of the cycle
(baset_est).
However, the result of txtime - baset_est is written into a u32,
leading to a wrap around to a positive number. The following
launchtime > 0 check will only branch to executing launchtime = 0
if launchtime is already 0.
Fix it by using a s32 before checking launchtime > 0.
Fixes: db0b124f02 ("igc: Enhance Qbv scheduling by using first flag bit")
Signed-off-by: Florian Kauer <florian.kauer@linutronix.de>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
The flags IGC_TXQCTL_STRICT_CYCLE and IGC_TXQCTL_STRICT_END
prevent the packet transmission over slot and cycle boundaries.
This is important for taprio offload where the slots and
cycles correspond to the slots and cycles configured for the
network.
However, the Qbv offload feature of the i225 is also used for
enabling TX launchtime / ETF offload. In that case, however,
the cycle has no meaning for the network and is only used
internally to adapt the base time register after a second has
passed.
Enabling strict mode in this case would unnecessarily prevent
the transmission of certain packets (i.e. at the boundary of a
second) and thus interferes with the ETF qdisc that promises
transmission at a certain point in time.
Similar to ETF, this also applies to CBS offload that also should
not be influenced by strict mode unless taprio offload would be
enabled at the same time.
This fully reverts
commit d8f45be01d ("igc: Use strict cycles for Qbv scheduling")
but its commit message only describes what was already implemented
before that commit. The difference to a plain revert of that commit
is that it now copes with the base_time = 0 case that was fixed with
commit e17090eb24 ("igc: allow BaseTime 0 enrollment for Qbv")
In particular, enabling strict mode leads to TX hang situations
under high traffic if taprio is applied WITHOUT taprio offload
but WITH ETF offload, e.g. as in
sudo tc qdisc replace dev enp1s0 parent root handle 100 taprio \
num_tc 1 \
map 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 \
queues 1@0 \
base-time 0 \
sched-entry S 01 300000 \
flags 0x1 \
txtime-delay 500000 \
clockid CLOCK_TAI
sudo tc qdisc replace dev enp1s0 parent 100:1 etf \
clockid CLOCK_TAI \
delta 500000 \
offload \
skip_sock_check
and traffic generator
sudo trafgen -i traffic.cfg -o enp1s0 --cpp -n0 -q -t1400ns
with traffic.cfg
#define ETH_P_IP 0x0800
{
/* Ethernet Header */
0x30, 0x1f, 0x9a, 0xd0, 0xf0, 0x0e, # MAC Dest - adapt as needed
0x24, 0x5e, 0xbe, 0x57, 0x2e, 0x36, # MAC Src - adapt as needed
const16(ETH_P_IP),
/* IPv4 Header */
0b01000101, 0, # IPv4 version, IHL, TOS
const16(1028), # IPv4 total length (UDP length + 20 bytes (IP header))
const16(2), # IPv4 ident
0b01000000, 0, # IPv4 flags, fragmentation off
64, # IPv4 TTL
17, # Protocol UDP
csumip(14, 33), # IPv4 checksum
/* UDP Header */
10, 0, 48, 1, # IP Src - adapt as needed
10, 0, 48, 10, # IP Dest - adapt as needed
const16(5555), # UDP Src Port
const16(6666), # UDP Dest Port
const16(1008), # UDP length (UDP header 8 bytes + payload length)
csumudp(14, 34), # UDP checksum
/* Payload */
fill('W', 1000),
}
and the observed message with that is for example
igc 0000:01:00.0 enp1s0: Detected Tx Unit Hang
Tx Queue <0>
TDH <d0>
TDT <f0>
next_to_use <f0>
next_to_clean <d0>
buffer_info[next_to_clean]
time_stamp <ffff661f>
next_to_watch <00000000245a4efb>
jiffies <ffff6e48>
desc.status <1048000>
Fixes: d8f45be01d ("igc: Use strict cycles for Qbv scheduling")
Signed-off-by: Florian Kauer <florian.kauer@linutronix.de>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Since commit e17090eb24 ("igc: allow BaseTime 0 enrollment for Qbv")
it is possible to enable taprio offload with a basetime of 0.
However, the check if taprio offload is already enabled (and thus -EALREADY
should be returned for igc_save_qbv_schedule) still relied on
adapter->base_time > 0.
This can be reproduced as follows:
# TAPRIO offload (flags == 0x2) and base-time = 0
sudo tc qdisc replace dev enp1s0 parent root handle 100 stab overhead 24 taprio \
num_tc 1 \
map 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 \
queues 1@0 \
base-time 0 \
sched-entry S 01 300000 \
flags 0x2
# The second call should fail with "Error: Device failed to setup taprio offload."
# But that only happens if base-time was != 0
sudo tc qdisc replace dev enp1s0 parent root handle 100 stab overhead 24 taprio \
num_tc 1 \
map 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 \
queues 1@0 \
base-time 0 \
sched-entry S 01 300000 \
flags 0x2
Fixes: e17090eb24 ("igc: allow BaseTime 0 enrollment for Qbv")
Signed-off-by: Florian Kauer <florian.kauer@linutronix.de>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Only set adapter->taprio_offload_enable after validating the arguments.
Otherwise, it stays set even if the offload was not enabled.
Since the subsequent code does not get executed in case of invalid
arguments, it will not be read at first.
However, by activating and then deactivating another offload
(e.g. ETF/TX launchtime offload), taprio_offload_enable is read
and erroneously keeps the offload feature of the NIC enabled.
This can be reproduced as follows:
# TAPRIO offload (flags == 0x2) and negative base-time leading to expected -ERANGE
sudo tc qdisc replace dev enp1s0 parent root handle 100 stab overhead 24 taprio \
num_tc 1 \
map 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 \
queues 1@0 \
base-time -1000 \
sched-entry S 01 300000 \
flags 0x2
# IGC_TQAVCTRL is 0x0 as expected (iomem=relaxed for reading register)
sudo pcimem /sys/bus/pci/devices/0000:01:00.0/resource0 0x3570 w*1
# Activate ETF offload
sudo tc qdisc replace dev enp1s0 parent root handle 6666 mqprio \
num_tc 3 \
map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 \
queues 1@0 1@1 2@2 \
hw 0
sudo tc qdisc add dev enp1s0 parent 6666:1 etf \
clockid CLOCK_TAI \
delta 500000 \
offload
# IGC_TQAVCTRL is 0x9 as expected
sudo pcimem /sys/bus/pci/devices/0000:01:00.0/resource0 0x3570 w*1
# Deactivate ETF offload again
sudo tc qdisc delete dev enp1s0 parent 6666:1
# IGC_TQAVCTRL should now be 0x0 again, but is observed as 0x9
sudo pcimem /sys/bus/pci/devices/0000:01:00.0/resource0 0x3570 w*1
Fixes: e17090eb24 ("igc: allow BaseTime 0 enrollment for Qbv")
Signed-off-by: Florian Kauer <florian.kauer@linutronix.de>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
In the current implementation the flags adapter->qbv_enable
and IGC_FLAG_TSN_QBV_ENABLED have a similar name, but do not
have the same meaning. The first one is used only to indicate
taprio offload (i.e. when igc_save_qbv_schedule was called),
while the second one corresponds to the Qbv mode of the hardware.
However, the second one is also used to support the TX launchtime
feature, i.e. ETF qdisc offload. This leads to situations where
adapter->qbv_enable is false, but the flag IGC_FLAG_TSN_QBV_ENABLED
is set. This is prone to confusion.
The rename should reduce this confusion. Since it is a pure
rename, it has no impact on functionality.
Fixes: e17090eb24 ("igc: allow BaseTime 0 enrollment for Qbv")
Signed-off-by: Florian Kauer <florian.kauer@linutronix.de>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tony Nguyen says:
====================
Intel Wired LAN Driver Updates 2023-07-05 (igc)
This series contains updates to igc driver only.
Husaini adds check to increment Qbv change error counter only on taprio
Qbvs. He also removes delay during Tx ring configuration and
resolves Tx hang that could occur when transmitting on a gate to be
closed.
Prasad Koya reports ethtool link mode as TP (twisted pair).
Tee Min corrects value for max SDU.
Aravindhan ensures that registers for PPS are always programmed to occur
in future.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
I225/6 hardware can be programmed to start PPS output once
the time in Target Time registers is reached. The time
programmed in these registers should always be into future.
Only then PPS output is triggered when SYSTIM register
reaches the programmed value. There are two modes in i225/6
hardware to program PPS, pulse and clock mode.
There were issues reported where PPS is not generated when
start time is in past.
Example 1, "echo 0 0 0 2 0 > /sys/class/ptp/ptp0/period"
In the current implementation, a value of '0' is programmed
into Target time registers and PPS output is in pulse mode.
Eventually an interrupt which is triggered upon SYSTIM
register reaching Target time is not fired. Thus no PPS
output is generated.
Example 2, "echo 0 0 0 1 0 > /sys/class/ptp/ptp0/period"
Above case, a value of '0' is programmed into Target time
registers and PPS output is in clock mode. Here, HW tries to
catch-up the current time by incrementing Target Time
register. This catch-up time seem to vary according to
programmed PPS period time as per the HW design. In my
experiments, the delay ranged between few tens of seconds to
few minutes. The PPS output is only generated after the
Target time register reaches current time.
In my experiments, I also observed PPS stopped working with
below test and could not recover until module is removed and
loaded again.
1) echo 0 <future time> 0 1 0 > /sys/class/ptp/ptp1/period
2) echo 0 0 0 1 0 > /sys/class/ptp/ptp1/period
3) echo 0 0 0 1 0 > /sys/class/ptp/ptp1/period
After this PPS did not work even if i re-program with proper
values. I could only get this back working by reloading the
driver.
This patch takes care of calculating and programming
appropriate future time value into Target Time registers.
Fixes: 5e91c72e56 ("igc: Fix PPS delta between two synchronized end-points")
Signed-off-by: Aravindhan Gunasekaran <aravindhan.gunasekaran@intel.com>
Reviewed-by: Muhammad Husaini Zulkifli <muhammad.husaini.zulkifli@intel.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
IEEE 802.1Q does not have clear definitions of what constitutes an
SDU (Service Data Unit), but IEEE Std 802.3 clause 3.1.2 does define
the MAC service primitives and clause 3.2.7 does define the MAC Client
Data for Q-tagged frames.
It shows that the mac_service_data_unit (MSDU) does NOT contain the
preamble, destination and source address, or FCS. The MSDU does contain
the length/type field, MAC client data, VLAN tag and any padding
data (prior to the FCS).
Thus, the maximum 802.3 frame size that is allowed to be transmitted
should be QueueMaxSDU (MSDU) + 16 (6 byte SA + 6 byte DA + 4 byte FCS).
Fixes: 92a0dcb842 ("igc: offload queue max SDU from tc-taprio")
Signed-off-by: Tan Tee Min <tee.min.tan@linux.intel.com>
Reviewed-by: Muhammad Husaini Zulkifli <muhammad.husaini.zulkifli@intel.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
set TP bit in the 'supported' and 'advertising' fields. i225/226 parts
only support twisted pair copper.
Fixes: 8c5ad0dae9 ("igc: Add ethtool support")
Signed-off-by: Prasad Koya <prasad@arista.com>
Acked-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
If a user schedules a Gate Control List (GCL) to close one of
the QBV gates while also transmitting a packet to that closed gate,
TX Hang will be happen. HW would not drop any packet when the gate
is closed and keep queuing up in HW TX FIFO until the gate is re-opened.
This patch implements the solution to drop the packet for the closed
gate.
This patch will also reset the adapter to perform SW initialization
for each 1st Gate Control List (GCL) to avoid hang.
This is due to the HW design, where changing to TSN transmit mode
requires SW initialization. Intel Discrete I225/6 transmit mode
cannot be changed when in dynamic mode according to Software User
Manual Section 7.5.2.1. Subsequent Gate Control List (GCL) operations
will proceed without a reset, as they already are in TSN Mode.
Step to reproduce:
DUT:
1) Configure GCL List with certain gate close.
BASE=$(date +%s%N)
tc qdisc replace dev $IFACE parent root handle 100 taprio \
num_tc 4 \
map 0 1 2 3 3 3 3 3 3 3 3 3 3 3 3 3 \
queues 1@0 1@1 1@2 1@3 \
base-time $BASE \
sched-entry S 0x8 500000 \
sched-entry S 0x4 500000 \
flags 0x2
2) Transmit the packet to closed gate. You may use udp_tai
application to transmit UDP packet to any of the closed gate.
./udp_tai -i <interface> -P 100000 -p 90 -c 1 -t <0/1> -u 30004
Fixes: ec50a9d437 ("igc: Add support for taprio offloading")
Co-developed-by: Tan Tee Min <tee.min.tan@linux.intel.com>
Signed-off-by: Tan Tee Min <tee.min.tan@linux.intel.com>
Tested-by: Chwee Lin Choong <chwee.lin.choong@intel.com>
Signed-off-by: Muhammad Husaini Zulkifli <muhammad.husaini.zulkifli@intel.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
