Using CX-3 in virtualized mode, MAD packets are proxied through the PF
driver. The feed is N tunnel QPs, and what is received from the VFs is
multiplexed out on the wire QP. Since this is a many-to-one scenario, it
is better to have separate initialization parameters for the two usages.
The number of wire and tunnel bufs are yanked up to 2K and 512
respectively. With this set of parameters, a system consisting of eight
physical servers, each with eight VMs and 14 I/O servers (BM), can run
switch fail-over without seeing:
mlx4_ib_demux_mad: failed sending GSI to slave 3 via tunnel qp (-11)
or
mlx4_ib_multiplex_mad: failed sending GSI to wire on behalf of slave 2 (-11)
Fixes: 3cf69cc8db ("IB/mlx4: Add CM paravirtualization")
Link: https://lore.kernel.org/r/20200803061941.1139994-4-haakon.bugge@oracle.com
Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Using CX-3 in virtualized mode, MAD packets are proxied through the PF
driver. However, the handling lacks support of the MRA (Message Receipt
Acknowledgment) packet. When having dynamic debug enabled, we see tons of:
mlx4_ib_multiplex_cm_handler: id{slave: 7, sl_cm_id: 0x8fcb45a0} is NULL! attr_id: 0x11
Fixes: 3cf69cc8db ("IB/mlx4: Add CM paravirtualization")
Link: https://lore.kernel.org/r/20200803061941.1139994-3-haakon.bugge@oracle.com
Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Add missing check for success after call to mlx4_ib_send_to_wire() in
mlx4_ib_multiplex_mad().
Amended the existing pr_debug() in mlx4_ib_multiplex_cm_handler() and
mlx4_ib_demux_cm_handler() with attr_id during a lookup failure.
Removed two noisy pr_debug() in mad.c
Fixes: 3cf69cc8db ("IB/mlx4: Add CM paravirtualization")
Link: https://lore.kernel.org/r/20200803061941.1139994-2-haakon.bugge@oracle.com
Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The following message occurs when running an AI application with TID RDMA
enabled:
hfi1 0000:7f:00.0: hfi1_0: [QP74] hfi1_tid_timeout 4084
hfi1 0000:7f:00.0: hfi1_0: [QP70] hfi1_tid_timeout 4084
The issue happens when TID RDMA WRITE request is followed by an
IB_WR_RDMA_WRITE_WITH_IMM request, the latter could be completed first on
the responder side. As a result, no ACK packet for the latter could be
sent because the TID RDMA WRITE request is still being processed on the
responder side.
When the TID RDMA WRITE request is eventually completed, the requester
will wait for the IB_WR_RDMA_WRITE_WITH_IMM request to be acknowledged.
If the next request is another TID RDMA WRITE request, no TID RDMA WRITE
DATA packet could be sent because the preceding IB_WR_RDMA_WRITE_WITH_IMM
request is not completed yet.
Consequently the IB_WR_RDMA_WRITE_WITH_IMM will be retried but it will be
ignored on the responder side because the responder thinks it has already
been completed. Eventually the retry will be exhausted and the qp will be
put into error state on the requester side. On the responder side, the TID
resource timer will eventually expire because no TID RDMA WRITE DATA
packets will be received for the second TID RDMA WRITE request. There is
also risk of a write-after-write memory corruption due to the issue.
Fix by adding a requester side interlock to prevent any potential data
corruption and TID RDMA protocol error.
Fixes: a0b34f75ec ("IB/hfi1: Add interlock between a TID RDMA request and other requests")
Link: https://lore.kernel.org/r/20200811174931.191210.84093.stgit@awfm-01.aw.intel.com
Cc: <stable@vger.kernel.org> # 5.4.x+
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Driver shall add only the kernel qps to the flush list for clean up.
During async error events from the HW, driver is adding qps to this list
without checking if the qp is kernel qp or not.
Add a check to avoid user qp addition to the flush list.
Fixes: 942c9b6ca8 ("RDMA/bnxt_re: Avoid Hard lockup during error CQE processing")
Fixes: c50866e285 ("bnxt_re: fix the regression due to changes in alloc_pbl")
Link: https://lore.kernel.org/r/1596689148-4023-1-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Pull rdma updates from Jason Gunthorpe:
"A quiet cycle after the larger 5.8 effort. Substantially cleanup and
driver work with a few smaller features this time.
- Driver updates for hfi1, rxe, mlx5, hns, qedr, usnic, bnxt_re
- Removal of dead or redundant code across the drivers
- RAW resource tracker dumps to include a device specific data blob
for device objects to aide device debugging
- Further advance the IOCTL interface, remove the ability to turn it
off. Add QUERY_CONTEXT, QUERY_MR, and QUERY_PD commands
- Remove stubs related to devices with no pkey table
- A shared CQ scheme to allow multiple ULPs to share the CQ rings of
a device to give higher performance
- Several more static checker, syzkaller and rare crashers fixed"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (121 commits)
RDMA/mlx5: Fix flow destination setting for RDMA TX flow table
RDMA/rxe: Remove pkey table
RDMA/umem: Add a schedule point in ib_umem_get()
RDMA/hns: Fix the unneeded process when getting a general type of CQE error
RDMA/hns: Fix error during modify qp RTS2RTS
RDMA/hns: Delete unnecessary memset when allocating VF resource
RDMA/hns: Remove redundant parameters in set_rc_wqe()
RDMA/hns: Remove support for HIP08_A
RDMA/hns: Refactor hns_roce_v2_set_hem()
RDMA/hns: Remove redundant hardware opcode definitions
RDMA/netlink: Remove CAP_NET_RAW check when dump a raw QP
RDMA/include: Replace license text with SPDX tags
RDMA/rtrs: remove WQ_MEM_RECLAIM for rtrs_wq
RDMA/rtrs-clt: add an additional random 8 seconds before reconnecting
RDMA/cma: Execute rdma_cm destruction from a handler properly
RDMA/cma: Remove unneeded locking for req paths
RDMA/cma: Using the standard locking pattern when delivering the removal event
RDMA/cma: Simplify DEVICE_REMOVAL for internal_id
RDMA/efa: Add EFA 0xefa1 PCI ID
RDMA/efa: User/kernel compatibility handshake mechanism
...
Pull networking updates from David Miller:
1) Support 6Ghz band in ath11k driver, from Rajkumar Manoharan.
2) Support UDP segmentation in code TSO code, from Eric Dumazet.
3) Allow flashing different flash images in cxgb4 driver, from Vishal
Kulkarni.
4) Add drop frames counter and flow status to tc flower offloading,
from Po Liu.
5) Support n-tuple filters in cxgb4, from Vishal Kulkarni.
6) Various new indirect call avoidance, from Eric Dumazet and Brian
Vazquez.
7) Fix BPF verifier failures on 32-bit pointer arithmetic, from
Yonghong Song.
8) Support querying and setting hardware address of a port function via
devlink, use this in mlx5, from Parav Pandit.
9) Support hw ipsec offload on bonding slaves, from Jarod Wilson.
10) Switch qca8k driver over to phylink, from Jonathan McDowell.
11) In bpftool, show list of processes holding BPF FD references to
maps, programs, links, and btf objects. From Andrii Nakryiko.
12) Several conversions over to generic power management, from Vaibhav
Gupta.
13) Add support for SO_KEEPALIVE et al. to bpf_setsockopt(), from Dmitry
Yakunin.
14) Various https url conversions, from Alexander A. Klimov.
15) Timestamping and PHC support for mscc PHY driver, from Antoine
Tenart.
16) Support bpf iterating over tcp and udp sockets, from Yonghong Song.
17) Support 5GBASE-T i40e NICs, from Aleksandr Loktionov.
18) Add kTLS RX HW offload support to mlx5e, from Tariq Toukan.
19) Fix the ->ndo_start_xmit() return type to be netdev_tx_t in several
drivers. From Luc Van Oostenryck.
20) XDP support for xen-netfront, from Denis Kirjanov.
21) Support receive buffer autotuning in MPTCP, from Florian Westphal.
22) Support EF100 chip in sfc driver, from Edward Cree.
23) Add XDP support to mvpp2 driver, from Matteo Croce.
24) Support MPTCP in sock_diag, from Paolo Abeni.
25) Commonize UDP tunnel offloading code by creating udp_tunnel_nic
infrastructure, from Jakub Kicinski.
26) Several pci_ --> dma_ API conversions, from Christophe JAILLET.
27) Add FLOW_ACTION_POLICE support to mlxsw, from Ido Schimmel.
28) Add SK_LOOKUP bpf program type, from Jakub Sitnicki.
29) Refactor a lot of networking socket option handling code in order to
avoid set_fs() calls, from Christoph Hellwig.
30) Add rfc4884 support to icmp code, from Willem de Bruijn.
31) Support TBF offload in dpaa2-eth driver, from Ioana Ciornei.
32) Support XDP_REDIRECT in qede driver, from Alexander Lobakin.
33) Support PCI relaxed ordering in mlx5 driver, from Aya Levin.
34) Support TCP syncookies in MPTCP, from Flowian Westphal.
35) Fix several tricky cases of PMTU handling wrt. briding, from Stefano
Brivio.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2056 commits)
net: thunderx: initialize VF's mailbox mutex before first usage
usb: hso: remove bogus check for EINPROGRESS
usb: hso: no complaint about kmalloc failure
hso: fix bailout in error case of probe
ip_tunnel_core: Fix build for archs without _HAVE_ARCH_IPV6_CSUM
selftests/net: relax cpu affinity requirement in msg_zerocopy test
mptcp: be careful on subflow creation
selftests: rtnetlink: make kci_test_encap() return sub-test result
selftests: rtnetlink: correct the final return value for the test
net: dsa: sja1105: use detected device id instead of DT one on mismatch
tipc: set ub->ifindex for local ipv6 address
ipv6: add ipv6_dev_find()
net: openvswitch: silence suspicious RCU usage warning
Revert "vxlan: fix tos value before xmit"
ptp: only allow phase values lower than 1 period
farsync: switch from 'pci_' to 'dma_' API
wan: wanxl: switch from 'pci_' to 'dma_' API
hv_netvsc: do not use VF device if link is down
dpaa2-eth: Fix passing zero to 'PTR_ERR' warning
net: macb: Properly handle phylink on at91sam9x
...
For RDMA TX flow table, set destination type to be 'port' and prevent
creation of flows with TIR destination.
As RDMA TX is an egress flow table the rules on this flow table should
not forward traffic back to the NIC and should set the destination to be
the port.
Without the setting of this destination type flow rules on the RDMA TX
flow tables are not created as FW invokes a syndrome for undefined
destination for the rule.
Fixes: 24670b1a31 ("net/mlx5: Add support for RDMA TX steering")
Link: https://lore.kernel.org/r/20200803055849.14947-1-leon@kernel.org
Signed-off-by: Michael Guralnik <michaelgur@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Scatter CQE feature relies on two flags MLX5_QP_FLAG_SCATTER_CQE and
MLX5_QP_FLAG_ALLOW_SCATTER_CQE, both of them can be provided without
relation to device capability.
Relax global validity check to allow MLX5_QP_FLAG_ALLOW_SCATTER_CQE QP
flag.
Existing user applications are failing on this new validity check.
Fixes: 90ecb37a75 ("RDMA/mlx5: Change scatter CQE flag to be set like other vendor flags")
Fixes: 37518fa49f ("RDMA/mlx5: Process all vendor flags in one place")
Link: https://lore.kernel.org/r/20200728120255.805733-1-leon@kernel.org
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Introduce a mechanism that performs an handshake between the userspace
provider and kernel driver which verifies that the user supports all
required features in order to operate correctly.
The handshake verifies the needed functionality by comparing the reported
device caps and the provider caps. If the device reports a non-zero
capability the appropriate comp mask is required from the userspace
provider in order to allocate the context.
Link: https://lore.kernel.org/r/20200722140312.3651-4-galpress@amazon.com
Reviewed-by: Shadi Ammouri <sammouri@amazon.com>
Reviewed-by: Yossi Leybovich <sleybo@amazon.com>
Signed-off-by: Gal Pressman <galpress@amazon.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Currently n_rq_elems is being assigned to params.elem_size instead of the
field params.num_elems. Coverity is detecting this as a double assingment
to params.elem_size and reporting this as an usused value on the first
assignment. Fix this.
Addresses-Coverity: ("Unused value")
Fixes: b6db3f71c9 ("qed: simplify chain allocation with init params struct")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Main changes are 200G support and fixing the definitions of discard and
error counters to match the hardware definitions.
Because the HWRM_PORT_PHY_QCFG message size has now exceeded the max.
encapsulated response message size of 96 bytes from the PF to the VF,
we now need to cap this message to 96 bytes for forwarding. The forwarded
response only needs to contain the basic link status and speed information
and can be capped without adding the new information.
v2: Fix bnxt_re compile error.
Cc: Selvin Xavier <selvin.xavier@broadcom.com>
Reviewed-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Reviewed-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Meir Lichtinger says:
====================
ConnectX-7 supports setting relaxed ordering read/write mkey attribute by
UMR, indicated by new HCA capabilities, so extend mlx5_ib driver to
configure UMR control segment
====================
Based on the mlx5-next branch at
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux
due to dependencies.
* branch 'mlx5_uar':
RDMA/mlx5: Set mkey relaxed ordering by UMR with ConnectX-7
RDMA/mlx5: Use MLX5_SET macro instead of local structure
RDMA/mlx5: ConnectX-7 new capabilities to set relaxed ordering by UMR
Up to ConnectX-7 UMR is not used when user passes relaxed ordering access
flag. ConnectX-7 supports setting relaxed ordering read/write mkey
attribute by UMR, indicated by new HCA capabilities.
With ConnectX-7 driver uses UMR when user set relaxed ordering access
flag, in contrast to previous silicon models. Specifically it includes
setting relvant flags of mkey context mask in UMR control segment, and
relaxed ordering write and read flags in UMR mkey context segment.
Link: https://lore.kernel.org/r/20200716105248.1423452-4-leon@kernel.org
Signed-off-by: Meir Lichtinger <meirl@mellanox.com>
Reviewed-by: Michael Guralnik <michaelgur@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The UDP reuseport conflict was a little bit tricky.
The net-next code, via bpf-next, extracted the reuseport handling
into a helper so that the BPF sk lookup code could invoke it.
At the same time, the logic for reuseport handling of unconnected
sockets changed via commit efc6b6f6c3
which changed the logic to carry on the reuseport result into the
rest of the lookup loop if we do not return immediately.
This requires moving the reuseport_has_conns() logic into the callers.
While we are here, get rid of inline directives as they do not belong
in foo.c files.
The other changes were cases of more straightforward overlapping
modifications.
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently the SQ is set to a ready state when the RAW QP is modified to
INIT. When the TIS is modified, e.g. to change the lag_tx_affinity, then
SQs which are already in the ready state will not be affected.
Open a window to modify the SQ behavior by setting the SQ as ready only
when QP was modified to RTS.
Link: https://lore.kernel.org/r/20200716105416.1423826-1-leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Extend current infrastructure to store chain page size in a struct
and use it in all functions instead of fixed QED_CHAIN_PAGE_SIZE.
Its value remains the default one, but can be overridden in
qed_chain_init_params before chain allocation.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
To simplify qed_chain_alloc() prototype and call sites, introduce struct
qed_chain_init_params to specify chain params, and pass a pointer to
filled struct to the actual qed_chain_alloc() instead of a long list
of separate arguments.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Prefetch work in mlx5_ib_prefetch_mr_work can be queued and able to run
concurrently with destruction of the implicit MR. The num_deferred_work
was intended to serialize this, but there is a race:
CPU0 CPU1
mlx5_ib_free_implicit_mr()
xa_erase(odp_mkeys)
synchronize_srcu()
__xa_erase(implicit_children)
mlx5_ib_prefetch_mr_work()
pagefault_mr()
pagefault_implicit_mr()
implicit_get_child_mr()
xa_cmpxchg()
atomic_dec_and_test(num_deferred_mr)
wait_event(imr->q_deferred_work)
ib_umem_odp_release(odp_imr)
kfree(odp_imr)
At this point in mlx5_ib_free_implicit_mr() the implicit_children list is
supposed to be empty forever so that destroy_unused_implicit_child_mr()
and related are not and will not be running.
Since it is not empty the destroy_unused_implicit_child_mr() flow ends up
touching deallocated memory as mlx5_ib_free_implicit_mr() already tore down the
imr parent.
The solution is to flush out the prefetch wq by driving num_deferred_work
to zero after creation of new prefetch work is blocked.
Fixes: 5256edcb98 ("RDMA/mlx5: Rework implicit ODP destroy")
Link: https://lore.kernel.org/r/20200719065435.130722-1-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
