When the noted patch below extending the reference taken by
rxe_get_dev_from_net() in rxe_udp_encap_recv() until each skb is freed it
was not matched by a reference in the loopback path resulting in
underflows.
Fixes: 899aba891c ("RDMA/rxe: Fix FIXME in rxe_udp_encap_recv()")
Link: https://lore.kernel.org/r/20210304192048.2958-1-rpearson@hpe.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
-----BEGIN PGP SIGNATURE-----
iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAmAppPgeHHRvcnZhbGRz
QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGeXYH/imZPBd4A1jIMehN
5HV2A53Z+MXmmaMuGj9X1KV6vsf55/xB+IhOoFdtRAIsO8c2yYSCO8i4+4R0XfYA
+/YFJeq672rojQnmh6XbpR8dugaAV7CUHy6n7KDsyvtT6EOCpwFSwkOb4X3tBRX6
TlYgm2d/xgV/wRHSgLVugK0MdFCLMAnyb7mkPfar9QrMgG1BiDKLq07xmwnS23On
TkqpJ9yZ/rJpUrrUqQYPShSO/FmA+fSfWs0CDv7EIrJ40LUScD6PZxSHWTIHtjLk
E4jFda6wuqLRVWsBwaBzUIdD0zk7X5quHRzEpbC5ga16SK6yrWvE5YJJXCguIEuZ
f3FMRYs=
=CAjn
-----END PGP SIGNATURE-----
Merge tag 'v5.11' into rdma.git for-next
Linux 5.11
Merged to resolve conflicts with RDMA rc commits
- drivers/infiniband/sw/rxe/rxe_net.c
The final logic is to call rxe_get_dev_from_net() again with the master
netdev if the packet was rx'd on a vlan. To keep the elimination of the
local variables requires a trivial edit to the code in -rc
Link: https://lore.kernel.org/r/20210210131542.215ea67c@canb.auug.org.au
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
rxe_udp_encap_recv() drops the reference to rxe->ib_dev taken by
rxe_get_dev_from_net() which should be held until each received skb is
freed. This patch moves the calls to ib_device_put() to each place a
received skb is freed. It also takes references to the ib_device for each
cloned skb created to process received multicast packets.
Fixes: 4c173f596b ("RDMA/rxe: Use ib_device_get_by_netdev() instead of open coding")
Link: https://lore.kernel.org/r/20210128233318.2591-1-rpearson@hpe.com
Signed-off-by: Bob Pearson <rpearson@hpe.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
rxe_net.c sends packets at the IP layer with skb->data pointing at the IP
header but receives packets from a UDP tunnel with skb->data pointing at
the UDP header. On the loopback path this was not correctly accounted
for. This patch corrects for this by using sbk_pull() to strip the IP
header from the skb on received packets.
Fixes: 8700e3e7c4 ("Soft RoCE driver")
Link: https://lore.kernel.org/r/20210128182301.16859-1-rpearson@hpe.com
Signed-off-by: Bob Pearson <rpearson@hpe.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
This reverts commit b2d2440430.
It's true that creating rxe on top of 802.1q interfaces doesn't work.
Thus, commit fd49ddaf7e ("RDMA/rxe: prevent rxe creation on top of vlan
interface") was absolutely correct.
But b2d2440430 was incorrect assuming that with this change, RDMA and
VLAN don't work togehter at all. It just has to be set up
differently. Rather than creating rxe on top of the VLAN interface, rxe
must be created on top of the physical interface. RDMA then works just
fine through VLAN interfaces on top of that physical interface, via the
"upper device" logic.
This is hard to see in the rxe logic because it never talks about vlan,
but instead rxe carefully selects upper vlan netdevices when working with
packets which in turn imply certain vlan tagging. This is all done
correctly and interacts with the gid table with VLAN support the same as
real HW does.
b2d2440430 broke this setup deliberately and should thus be
reverted. Also, b2d2440430 removed rxe_dma_device(), so adapt the revert
to discard that hunk.
Fixes: b2d2440430 ("RDMA/rxe: Remove VLAN code leftovers from RXE")
Link: https://lore.kernel.org/r/20210120161913.7347-1-mwilck@suse.com
Signed-off-by: Martin Wilck <mwilck@suse.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
This moves siw and rxe to be virtual devices in the device tree:
lrwxrwxrwx 1 root root 0 Nov 6 13:55 /sys/class/infiniband/rxe0 -> ../../devices/virtual/infiniband/rxe0/
Previously they were trying to parent themselves to the physical device of
their attached netdev, which doesn't make alot of sense.
My hope is this will solve some weird syzkaller hits related to sysfs as
it could be possible that the parent of a netdev is another netdev, eg
under bonding or some other syzkaller found netdev configuration.
Nesting a ib_device under anything but a physical device is going to cause
inconsistencies in sysfs during destructions.
Link: https://lore.kernel.org/r/0-v1-dcbfc68c4b4a+d6-virtual_dev_jgg@nvidia.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Since the commit fd49ddaf7e ("RDMA/rxe: prevent rxe creation on top of
vlan interface") does not permit rxe on top of vlan device, all the stuff
related with vlan should be removed.
Fixes: fd49ddaf7e ("RDMA/rxe: prevent rxe creation on top of vlan interface")
Link: https://lore.kernel.org/r/1604326422-18625-1-git-send-email-yanjunz@nvidia.com
Signed-off-by: Zhu Yanjun <yanjunz@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The patch referenced below has a typo that results in using the wrong L2
header size for outbound traffic. (V4 <-> V6).
It also breaks kernel-side RC traffic because they use AVs that use
RDMA_NETWORK_XXX enums instead of RXE_NETWORK_TYPE_XXX enums. Fix this by
transcoding between these enum types.
Fixes: e0d696d201 ("RDMA/rxe: Move the definitions for rxe_av.network_type to uAPI")
Link: https://lore.kernel.org/r/20201016211343.22906-1-rpearson@hpe.com
Signed-off-by: Bob Pearson <rpearson@hpe.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
RXE was wrongly using an internal kernel enum as part of its uAPI, split
this out into a dedicated uAPI enum just for RXE. It only uses the IPv4
and IPv6 values.
This was exposed by changing the internal kernel enum definition which
broke RXE.
Fixes: 1c15b4f2a4 ("RDMA/core: Modify enum ib_gid_type and enum rdma_network_type")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Instead of returning IB_LINK_LAYER_ETHERNET from rxe_link_layer, return it
directly from get_link_layer callback and remove rxe_link_layer().
Fixes: 8700e3e7c4 ("Soft RoCE driver")
Link: https://lore.kernel.org/r/20200705104313.283034-5-kamalheib1@gmail.com
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
ipv6_stub uses the ip6_dst_lookup function to allow other modules to
perform IPv6 lookups. However, this function skips the XFRM layer
entirely.
All users of ipv6_stub->ip6_dst_lookup use ip_route_output_flow (via the
ip_route_output_key and ip_route_output helpers) for their IPv4 lookups,
which calls xfrm_lookup_route(). This patch fixes this inconsistent
behavior by switching the stub to ip6_dst_lookup_flow, which also calls
xfrm_lookup_route().
This requires some changes in all the callers, as these two functions
take different arguments and have different return types.
Fixes: 5f81bd2e5d ("ipv6: export a stub for IPv6 symbols used by vxlan")
Reported-by: Xiumei Mu <xmu@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use rdma_read_gid_attr_ndev_rcu() to access netdevice attached to GID
entry under rcu lock.
This ensures that while working on the netdevice of the GID, it doesn't
get freed.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Always consider the skb reserve space based on netdevice of the GID
attribute, regardless of vlan or non vlan netdevice.
Fixes: 43c9fc509f ("rdma_rxe: make rxe work over 802.1q VLAN devices")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
In the function rxe_init_packet, based on av->network_type, skb->protocol
is set to ipv4 or ipv6. The functions rxe_prepare and rxe_send are called
after the functin rxe_init_packet. So in these functions,
av->network_type can be replaced with skb->protocol.
The functions are in the xmit fast path. So with skb->protocol, the
performance will be better.
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add support for the RDMA_NLDEV_CMD_NEWLINK/DELLINK messages which allow
dynamically adding new RXE links. Deprecate the old module options for
now.
Cc: Moni Shoua <monis@mellanox.com>
Reviewed-by: Yanjun Zhu <yanjun.zhu@oracle.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Since rxe allows unregistration from other threads the rxe pointer can
become invalid any moment after ib_register_driver returns. This could
cause a user triggered use after free.
Add another driver callback to be called right after the device becomes
registered to complete any device setup required post-registration. This
callback has enough core locking to prevent the device from becoming
unregistered.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
rxe has an open coded version of this that is not as safe as the core
version. This lets us eliminate the internal device list entirely from
rxe.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
rxe does not have correct locking for its registration/unregistration
paths, use the core code to handle it instead. In this mode
ib_unregister_device will also do the dealloc, so rxe is required to do
clean up from a callback.
The core code ensures that unregistration is done only once, and generally
takes care of locking and concurrency problems for rxe.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Currently a packet is marked for loopback only if the source and
destination addresses equals. This is not enough when multiple gids are
present in rxe device's gid table and the traffic is from one gid to
another. Fix it by marking the packet for loopback if the destination MAC
address is equal to the source MAC address.
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Tested-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
All callers to ib_alloc_device() provide a larger size than struct
ib_device and rely on the fact that struct ib_device is embedded in their
driver specific structure as the first member.
Provide a safer variant of ib_alloc_device() that checks and enforces this
approach to make sure the drivers are using it right.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Same code is executed in both rxe_param_set_add and rxe_notify functions.
Make one function and call it from both places.
Since both callers already have a rxe object use it directly instead of
deriving it from the net device.
Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
link_down is self-explanatory.
rdma_sends and rdma_recvs count the number of RDMA Send and RDMA Receive
operations completed successfully. This is different from the existing
sent_pkts and rcvd_pkts counters because the existing counters measure
packets, not RDMA operations.
ack_deffered is renamed to ack_deferred to fix the spelling.
out_of_sequence is renamed to out_of_seq_request to make clear that it is
counting only requests and not other packets which can be out of sequence.
Signed-off-by: Andrew Boyer <andrew.boyer@dell.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
In ib_query_port(), use the netdev's IFF_UP flag to determine phys_state
(flag set = down = POLLING, flag clear = disabled = DISABLED).
Callers can then use the phys_state field to distinguish between links
which have a dead partner, cable missing, etc., from links which are
turned off on the local node. This is useful for HA and supportability.
Signed-off-by: Andrew Boyer <andrew.boyer@dell.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
This function is not in use - delete it.
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
These return the same thing but dev_name is a more conventional use of the
kernel API.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Kernel convention is that a driver for a subsystem will print using
dev_* on the subsystem's struct device, or with dev_* on the physical
device. Drivers should rarely use a pr_* function.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
rxe_prepare() is called on an skb which has ndev already initialized by
rxe_init_packet().
Therefore avoid querying the GID attribute again and use the available
netdevice from the skb->dev.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Tested-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Select the source udp port number for a QP based on the
source QPN. This provides a better spread of traffic
across NIC RX queues for RC/UC QPs.
Signed-off-by: Vijay Immanuel <vijayi@attalasystems.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Do not call sk_dst_set() on every packet transfer because
that calls sk_tx_queue_clear(), which clears the tx queue.
A QP must stay on the same tx queue to maintain packet order.
Signed-off-by: Vijay Immanuel <vijayi@attalasystems.com>
Acked-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
rxe_netdev_from_av can now be done by the core code directly from the
gid_attrs, no need for a helper in the driver.
ib_find_cached_gid_by_port can be switched to use the rdma version here as
well.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The function rxe_remove_all is only used in this modules.
There is no other modules that call this function. So it
is not necessary to export it.
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Use the recently introduced helper to replace the pattern of
skb_put_zero/__skb_put() && memset().
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
The function rxe_release_udp_tunnel is only used in rxe_net.c.
So it is necessary to make this function as static.
CC: Srinivas Eeda <srinivas.eeda@oracle.com>
CC: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
The variable rxe_net_notifier is only used in the file rxe_net.c. So
remove it from rxe_net.h file and make it static in the file rxe_net.c.
CC: Srinivas Eeda <srinivas.eeda@oracle.com>
CC: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This patch fixes RDMA/rxe over 802.1q VLAN devices.
Without it, I observed the following behavior:
a) adding a VLAN device to RXE via rxe_net_add() creates a non-functional
RDMA device. This is caused by the logic in enum_all_gids_of_dev_cb() /
is_eth_port_of_netdev(), which only considers networks connected to
"upper devices" of the configured network device, resulting in an empty
set of gids for a VLAN interface that is an "upper device" itself.
Later attempts to connect via this rdma device fail in cma_acuire_dev()
because no gids can be resolved.
b) adding the master device of the VLAN device instead seems to work
initially, target addresses via VLAN devices are resolved successfully.
But the connection times out because no 802.1q VLAN headers are
inserted in the ethernet packets, which are therefore never received.
This happens because the RXE layer sends the packets via the master
device rather than the VLAN device.
The problem could be solved by changing either a) or b). My thinking was
that the logic in a) was created deliberately, thus I decided to work on
b). It turns out that the information about the VLAN interface for the gid
at hand is available in the AV information. My patch converts the RXE code
to use this netdev instead of rxe->ndev. With this change, RXE over vlan
works on my test system.
Signed-off-by: Martin Wilck <mwilck@suse.com>
Reviewed-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
In the function rxe_send, the variable rxe is not used in it.
So it should be removed.
CC: Srinivas Eeda <srinivas.eeda@oracle.com>
CC: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
In xmit, there is a skb_clone. This function copies the struct sk_buff.
And some parameters are changed to the new skb. Then the new skb is sent
while the old skb is freed.
While the function skb_clone is removed, the parameter changes are made on
the old skb, then the old skb is sent. It can also work well.
The following tests are made.
server client
--------- ---------
|1.1.1.1|<----rxe-channel--->|1.1.1.2|
--------- ---------
On server: rping -s -a 1.1.1.1 -v -C 1000 -S 512
On client: rping -c -a 1.1.1.1 -v -C 1000 -S 512
The kernel config CONFIG_DEBUG_KMEMLEAK is enabled on both server
and client.
This test runs for several hours. There is no memory leak and the whole
system can work well.
As the above network, the following tests are made.
Server: ibv_rc_pingpong -d rxe0 -g 1
Client: ibv_rc_pingpong -d rxe0 -g 1 1.1.1.1
The result on Server.
Before:
8192000 bytes in 0.88 seconds = 74.36 Mbit/sec
1000 iters in 0.88 seconds = 881.30 usec/iter
After:
8192000 bytes in 0.81 seconds = 81.15 Mbit/sec
1000 iters in 0.81 seconds = 807.62 usec/iter
The throughput is enhanced and the latency is reduced.
CC: Srinivas Eeda <srinivas.eeda@oracle.com>
CC: Joe Jin <joe.jin@oracle.com>
CC: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
The variable recv_sockets is only used in the file rxe_net.c. So
it is better to add static type to it.
CC: Srinivas Eeda <srinivas.eeda@oracle.com>
CC: Joe Jin <joe.jin@oracle.com>
CC: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Without this fix, ports configured on top of ixgbe miss link up
notifications. ibv_query_port() will continue to return IBV_PORT_DOWN even
though the port is up and working.
Fixes: 8700e3e7c4 ("Soft RoCE driver")
Signed-off-by: Andrew Boyer <andrew.boyer@dell.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
To successfully match an IPv6 path, the path cookie must match. Store it
in the QP so that the IPv6 path can be reused.
Replace open-coded version of dst_check() with the actual call, fixing the
logic. The open-coded version skips the check call if dst->obsolete is 0
(DST_OBSOLETE_NONE), proceeding to replace the route. DST_OBSOLETE_NONE
means that the route may continue to be used, though.
Fixes: 4ed6ad1eb3 ("IB/rxe: Cache dst in QP instead of getting it...")
Signed-off-by: Andrew Boyer <andrew.boyer@dell.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
The network stack will call nskb's destructor, rxe_skb_tx_dtor(), if the
packet gets dropped by ip_local_out()/ip6_local_out(). Thus we need to add
the QP ref before output to avoid extra dereferences during network
congestion. This could lead to unwanted destruction of the QP.
Fix up the skb_out accounting, too.
Fixes: fda85ce912 ("IB/rxe: Fix kernel panic from skb destructor")
Signed-off-by: Andrew Boyer <andrew.boyer@dell.com>
Acked-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
This logic seems to be duplicated in (at least) three separate files.
Move it to one place so code can be re-use.
Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
