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: NParav Pandit <parav@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason 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: 43c9fc50 ("rdma_rxe: make rxe work over 802.1q VLAN devices")
Signed-off-by: NParav Pandit <parav@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason 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: NZhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: NJason 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: NYanjun Zhu <yanjun.zhu@oracle.com>
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NJason 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: NJason 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: NJason 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: NJason Gunthorpe <jgg@mellanox.com>

The core API handles the locking correctly and is faster if there are
multiple devices.
Signed-off-by: NJason 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: NKamal Heib <kamalheib1@gmail.com>
Reviewed-by: NYuval Shaia <yuval.shaia@oracle.com>
Tested-by: NYuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: NJason 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: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason 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: NYuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com> 
Reviewed-by: NBart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: NJason 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: NAndrew Boyer <andrew.boyer@dell.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>
Signed-off-by: NJason 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: NAndrew Boyer <andrew.boyer@dell.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

This function is not in use - delete it.
Signed-off-by: NKamal Heib <kamalheib1@gmail.com>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

These return the same thing but dev_name is a more conventional use of the
kernel API.
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>
Reviewed-by: NLeon 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: NJason 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: NParav Pandit <parav@mellanox.com>
Reviewed-by: NDaniel Jurgens <danielj@mellanox.com>
Reviewed-by: NYuval Shaia <yuval.shaia@oracle.com>
Tested-by: NYuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: NZhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug 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: NVijay Immanuel <vijayi@attalasystems.com>
Signed-off-by: NDoug 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: NVijay Immanuel <vijayi@attalasystems.com>
Acked-by: NMoni Shoua <monis@mellanox.com>
Signed-off-by: NJason 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: NParav Pandit <parav@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason 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: NZhu Yanjun <yanjun.zhu@oracle.com>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Use the recently introduced helper to replace the pattern of
skb_put_zero/__skb_put() && memset().
Signed-off-by: NYueHaibing <yuehaibing@huawei.com>
Reviewed-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

It always returns 0. Change return type to void.
Signed-off-by: NYuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: NZhu Yanjun <yanjun.zhu@oracle.com>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: NDoug 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: NZhu Yanjun <yanjun.zhu@oracle.com>
Reviewed-by: NYuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: NDoug 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: NZhu Yanjun <yanjun.zhu@oracle.com>
Reviewed-by: NBart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: NYuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: NJason 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: NMartin Wilck <mwilck@suse.com>
Reviewed-by: NMoni Shoua <monis@mellanox.com>
Signed-off-by: NDoug 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: NZhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: NDoug 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: NZhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: NDoug 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: NZhu Yanjun <yanjun.zhu@oracle.com>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug 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: 8700e3e7 ("Soft RoCE driver")
Signed-off-by: NAndrew Boyer <andrew.boyer@dell.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Fixes: 4ed6ad1e ("IB/rxe: Cache dst in QP instead of getting it...")
Signed-off-by: NAndrew Boyer <andrew.boyer@dell.com>
Reviewed-by: NYuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Otherwise the reference count goes negative as IPv6 packets complete.

Fixes: 4ed6ad1e ("IB/rxe: Cache dst in QP instead of getting it...")
Signed-off-by: NAndrew Boyer <andrew.boyer@dell.com>
Signed-off-by: NDoug 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: 4ed6ad1e ("IB/rxe: Cache dst in QP instead of getting it...")
Signed-off-by: NAndrew Boyer <andrew.boyer@dell.com>
Signed-off-by: NDoug 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: fda85ce9 ("IB/rxe: Fix kernel panic from skb destructor")
Signed-off-by: NAndrew Boyer <andrew.boyer@dell.com>
Acked-by: NMoni Shoua <monis@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

In the time between rxe_send has finished and skb destructor
called, the QP's ref count might be 0, leading to a possible
QP destruction. This will lead to a kernel panic when the destructor
dereferences the QP.

The operation of incrementing QP ref count at rxe_send and decrementing
from skb destructor will prevent this crash.

BUG: unable to handle kernel NULL pointer dereference at 000000000000072c
IP: [<ffffffffa05df765>] rxe_skb_tx_dtor+0x15/0x50 [rdma_rxe]
PGD 0 [16240.211178]
Oops: 0002 [#1] SMP
CPU: 3 PID: 0 Comm: swapper/3 Tainted: G           OE   4.9.0-mlnx #1
Hardware name: Red Hat KVM, BIOS Bochs 01/01/2011
task: ffff88042d6b1480 task.stack: ffffc90001904000
RIP: 0010:[<ffffffffa05df765>]  [<ffffffffa05df765>] rxe_skb_tx_dtor+0x15/0x50 [rdma_rxe]
RSP: 0018:ffff88043fcc3df0  EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff880429684700 RCX: ffff88042d248200
RDX: 00000000ffffffff RSI: 00000000fffffe01 RDI: ffff880429684700
RBP: ffff88043fcc3e00 R08: ffff88043fcda240 R09: 00000000ff2d1de6
R10: 0000000000000000 R11: 00000000f49cf6fe R12: ffff880429684700
R13: ffffffff81893f96 R14: ffffffff817d66f0 R15: ffff880427f74200
FS:  0000000000000000(0000) GS:ffff88043fcc0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000000000072c CR3: 000000041d3df000 CR4: 00000000000006e0
Stack:
 ffffffff817b29cf ffff880429684700 ffff88043fcc3e18 ffffffff817b42c2
 ffff880429684700 ffff88043fcc3e40 ffffffff817b4332 ffff880429684700
 ffff880427f74238 ffff880427f74228 ffff88043fcc3e58 ffffffff81893f96
Call Trace:
 <IRQ> [16240.336345]  [<ffffffff817b29cf>] ? skb_release_head_state+0x4f/0xb0
 [<ffffffff817b42c2>] skb_release_all+0x12/0x30
 [<ffffffff817b4332>] kfree_skb+0x32/0x90
 [<ffffffff81893f96>] ndisc_error_report+0x36/0x40
 [<ffffffff817d4de1>] neigh_invalidate+0x81/0xf0
 [<ffffffff817d68f7>] neigh_timer_handler+0x207/0x2b0
 [<ffffffff81109295>] call_timer_fn+0x35/0x120
 [<ffffffff81109db7>] run_timer_softirq+0x1d7/0x460
 [<ffffffff8106155e>] ? kvm_sched_clock_read+0x1e/0x30
 [<ffffffff810366b9>] ? sched_clock+0x9/0x10
 [<ffffffff810cfed2>] ? sched_clock_cpu+0x72/0xa0
 [<ffffffff818dd537>] __do_softirq+0xd7/0x289
 [<ffffffff810a6c95>] irq_exit+0xb5/0xc0
 [<ffffffff818dd372>] smp_apic_timer_interrupt+0x42/0x50
 [<ffffffff818dc682>] apic_timer_interrupt+0x82/0x90
 <EOI> [16240.395776]  [<ffffffff818da156>] ? native_safe_halt+0x6/0x10
 [<ffffffff818d9e6e>] default_idle+0x1e/0xd0
 [<ffffffff8103797f>] arch_cpu_idle+0xf/0x20
 [<ffffffff818da2c5>] default_idle_call+0x35/0x40
 [<ffffffff810e3eb5>] cpu_startup_entry+0x185/0x210
 [<ffffffff81050433>] start_secondary+0x103/0x130
RIP  [<ffffffffa05df765>] rxe_skb_tx_dtor+0x15/0x50 [rdma_rxe]

Fixes: 8700e3e7 ("Soft RoCE driver")
Signed-off-by: NYonatan Cohen <yonatanc@mellanox.com>
Reviewed-by: NMoni Shoua <monis@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: NDoug 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: NYuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>

In RC QP there is no need to resolve the outgoing interface
for each packet, as this does not change during QP life cycle.

Instead cache the interface on the socket and use that one.
This improves performance by 12% by sparing redundant
calls to rxe_find_route.

ib_send_bw -d rxe0  -x 1 -n 9000 -e  -s $((1024 * 1024 )) -l 100

----------------------------------------------------------------------------------------
|        | bytes   | iterations | BW peak[MB/sec] | BW average[MB/sec] | MsgRate[Mpps] |
----------------------------------------------------------------------------------------
| before | 1048576 | 9000       | inf             | 551.21             | 0.000551      |
| after  | 1048576 | 9000       | inf             | 615.54             | 0.000616      |
----------------------------------------------------------------------------------------

Fixes: 8700e3e7 ("Soft RoCE driver")
Signed-off-by: NYonatan Cohen <yonatanc@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

This patch makes use of is_vlan_dev() function instead of flag
comparison which is exactly done by is_vlan_dev() helper function.
Signed-off-by: NParav Pandit <parav@mellanox.com>
Reviewed-by: NDaniel Jurgens <danielj@mellanox.com>
Acked-by: NStephen Hemminger <stephen@networkplumber.org>
Acked-by: NJon Maxwell <jmaxwell37@gmail.com>
Acked-by: NJohannes Thumshirn <jth@kernel.org>
Acked-by: NHaiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The first argument of list_add_tail is the new item and the second
is the head of the list. Fix the code to pass arguments in the
right order, otherwise not all the rxe devices will be removed
during teardown.

Fixes: 8700e3e7 ('Soft RoCE driver')
Signed-off-by: NMaor Gottlieb <maorg@mellanox.com>
Reviewed-by: NMoni Shoua <monis@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Neither rxe->ifc_ops nor any of the function pointers in struct
struct rxe_ifc_ops ever change. Hence remove the rxe->ifc_ops
indirection mechanism.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NAndrew Boyer <andrew.boyer@dell.com>
Cc: Moni Shoua <monis@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>