This new counter tracks number of pages that we allocated for one port.
lpaa24:~# ethtool -S eth0 | egrep 'rx_alloc_pages|rx_packets'
rx_packets: 306755183
rx_alloc_pages: 932897
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Same technique than some Intel drivers, for arches where PAGE_SIZE = 4096
In most cases, pages are reused because they were consumed
before we could loop around the RX ring.
This brings back performance, and is even better,
a single TCP flow reaches 30Gbit on my hosts.
v2: added full memset() in mlx4_en_free_frag(), as Tariq found it was needed
if we switch to large MTU, as priv->log_rx_info can dynamically be changed.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use of order-3 pages is problematic in some cases.
This patch might add three kinds of regression :
1) a CPU performance regression, but we will add later page
recycling and performance should be back.
2) TCP receiver could grow its receive window slightly slower,
because skb->len/skb->truesize ratio will decrease.
This is mostly ok, we prefer being conservative to not risk OOM,
and eventually tune TCP better in the future.
This is consistent with other drivers using 2048 per ethernet frame.
3) Because we allocate one page per RX slot, we consume more
memory for the ring buffers. XDP already had this constraint anyway.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We will soon use order-0 pages, and frag truesize will more precisely
match real sizes.
In the new model, we prefer to use <= 2048 bytes fragments, so that
we can use page-recycle technique on PAGE_SIZE=4096 arches.
We will still pack as much frames as possible on arches with big
pages, like PowerPC.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We only need to store the page and dma address.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
No need to duplicate it per RX queue / frags.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Using per frag storage for frag_prefix_size is really silly.
mlx4_en_complete_rx_desc() has all needed info already.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is really a port attribute, no need to duplicate it per
RX queue and per frag.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
No need to duplicate it for all queues and frags.
num_frags & log_rx_info become u8 to save space.
u8 accesses are a bit faster than u16 anyway.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The cited commit makes a great job of finding optimal shift/multiplier
values assuming a 10 seconds wrap around, but forgot to change the
overflow_period computation.
It overflows in cyclecounter_cyc2ns(), and the final result is 804 ms,
which is silly.
Lets simply use 5 seconds, no need to recompute this, given how it is
supposed to work.
Later, we will use a timer instead of a work queue, since the new RX
allocation schem will no longer need mlx4_en_recover_from_oom() and the
service_task firing every 250 ms.
Fixes: 31c128b66e ("net/mlx4_en: Choose time-stamping shift value according to HW frequency")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Eugenia Emantayev <eugenia@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Or we might miss the fact that a page was allocated from memory reserves.
Fixes: dceeab0e52 ("mlx4: support __GFP_MEMALLOC for rx")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When creating EQs to handle CQ completion events for the PF
or for VFs, we create enough EQE entries to handle completions
for the max number of CQs that can use that EQ.
When SRIOV is activated, the max number of CQs a VF (or the PF) can
obtain is its CQ quota (determined by the Hypervisor resource tracker).
Therefore, when creating an EQ, the number of EQE entries that the VF
should request for that EQ is the CQ quota value (and not the total
number of CQs available in the FW).
Under SRIOV, the PF, also must use its CQ quota, because
the resource tracker also controls how many CQs the PF can obtain.
Using the FW total CQs instead of the CQ quota when creating EQs resulted
wasting MTT entries, due to allocating more EQEs than were needed.
Fixes: 5a0d0a6161 ("mlx4: Structures and init/teardown for VF resource quotas")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Reported-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the VF driver, module parameter mlx4_log_num_mgm_entry_size was
mistakenly overwritten -- and in a manner which overrode the
device-managed flow steering option encoded in the parameter.
log_num_mgm_entry_size is a global module parameter which
affects all ConnectX-3 PFs installed on that host.
If a VF changes log_num_mgm_entry_size, this will affect all PFs
which are probed subsequent to the change (by disabling DMFS for
those PFs).
Fixes: 3c439b5586 ("mlx4_core: Allow choosing flow steering mode")
Signed-off-by: Majd Dibbiny <majd@mellanox.com>
Reviewed-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Spoofcheck can't be enabled if VF MAC is zero.
Vice versa, can't zero MAC if spoofcheck is on.
Fixes: 8f7ba3ca12 ('net/mlx4: Add set VF mac address support')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As ENOTSUPP is specific to NFS, change the return error value to
EOPNOTSUPP in various places in the mlx4 driver.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Suggested-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since mlx4 NIC are used on PowerPC with 64K pages, we need to adapt
MLX4_EN_ALLOC_PREFER_ORDER definition.
Otherwise, a fragment sitting in an out of order TCP queue can hold
0.5 Mbytes and it is a serious OOM risk.
Fixes: 51151a16a6 ("mlx4: allow order-0 memory allocations in RX path")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1) In the case where rate == priv->pkt_rate_low == priv->pkt_rate_high,
mlx4_en_auto_moderation() does a divide by zero.
2) We want to properly change the moderation parameters if rx_frames
was changed (like in ethtool -C eth0 rx-frames 16)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
All rx and rx netdev interrupts are handled by respectively
by mlx4_en_rx_irq() and mlx4_en_tx_irq() which simply schedule a NAPI.
But mlx4_eq_int() also fires a tasklet to service all items that were
queued via mlx4_add_cq_to_tasklet(), but this handler was not called
unless user cqe was handled.
This is very confusing, as "mpstat -I SCPU ..." show huge number of
tasklet invocations.
This patch saves this overhead, by carefully firing the tasklet directly
from mlx4_add_cq_to_tasklet(), removing four atomic operations per IRQ.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Using a reader-writer lock in fast path is silly, when we can
instead use RCU or a seqlock.
For mlx4 hwstamp clock, a seqlock is the way to go, removing
two atomic operations and false sharing.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The conflict was an interaction between a bug fix in the
netvsc driver in 'net' and an optimization of the RX path
in 'net-next'.
Signed-off-by: David S. Miller <davem@davemloft.net>
mlx4 may schedule napi from a workqueue. Afterwards, softirqs are not run
in a deterministic time frame and the following message may be logged:
NOHZ: local_softirq_pending 08
The problem is the same as what was described in commit ec13ee8014
("virtio_net: invoke softirqs after __napi_schedule") and this patch
applies the same fix to mlx4.
Fixes: 07841f9d94 ("net/mlx4_en: Schedule napi when RX buffers allocation fails")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Benjamin Poirier <bpoirier@suse.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a "||" vs "|" typo here so we test 0x1 instead of 0x6.
Fixes: 1f8176f735 ("net/mlx4_en: Check the enabling pptx/pprx flags in SET_PORT wrapper flow")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After calling mlx4_en_try_alloc_resources (e.g. by changing the
number of rx-queues with ethtool -L), the existing xdp_prog becomes
inactive.
The bug is that the xdp_prog ptr has not been carried over from
the old rx-queues to the new rx-queues
Fixes: 47a38e1550 ("net/mlx4_en: add support for fast rx drop bpf program")
Cc: Brenden Blanco <bblanco@plumgrid.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some Hypervisors detach VFs from VMs by instantly causing an FLR event
to be generated for a VF.
In the mlx4 case, this will cause that VF's comm channel to be disabled
before the VM has an opportunity to invoke the VF device's "shutdown"
method.
The result is that the VF driver on the VM will experience a command
timeout during the shutdown process when the Hypervisor does not deliver
a command-completion event to the VM.
To avoid FW command timeouts on the VM when the driver's shutdown method
is invoked, we detect the absence of the VF's comm channel at the very
start of the shutdown process. If the comm-channel has already been
disabled, we cause all FW commands during the device shutdown process to
immediately return success (and thus avoid all command timeouts).
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Make sure pptx/pprx mask flag is set using new fields upon set port
request. In addition, move this code into a helper function for better
code readability.
Signed-off-by: Shaker Daibes <shakerd@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Make sure MTU mask flag is set using new field upon set port
request. In addition, move this code into a helper function for better
code readability.
Signed-off-by: Shaker Daibes <shakerd@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When starting the port, driver will inform Firmware about the actual MTU
which does not include implicit headers, such as FCS or VLAN tags.
Signed-off-by: Shaker Daibes <shakerd@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This feature will allow the user to disable auto negotiation
on the port for mlx4 devices while setting the speed is limited
to 1GbE speeds.
Other speeds will not be accepted in autoneg off mode.
This functionality is permitted providing that the firmware
is compatible with this feature.
The above is determined by querying a new dedicated capability
bit in the device.
Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Avoid reading num_tc directly from struct net_device, but use
the helper function netdev_get_num_tc.
Fixes: bc6a4744b8 ("net/mlx4_en: num cores tx rings for every UP")
Fixes: f5b6345ba8 ("net/mlx4_en: User prio mapping gets corrupted when changing number of channels")
Signed-off-by: Alaa Hleihel <alaa@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to aid debugging of functions that take a resource but
don't put it, add the last function name that successfully grabbed
this resource.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The device revision field returned by the NodeInfo MAD is incorrect
on ConnectX3 devices.
This patch is driver side handling to complete a FW fix added at 2.11.1172.
INIT_HCA - bit at offset 0x0C.12 is set to 1 so that FW will report
correct device revision.
Older FW versions won't be affected from turning on that bit,
no capability bit is needed.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conform the following warning:
WARNING: ENOSYS means 'invalid syscall nr' and nothing else.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This work adds a number of tracepoints to paths that are either
considered slow-path or exception-like states, where monitoring or
inspecting them would be desirable.
For bpf(2) syscall, tracepoints have been placed for main commands
when they succeed. In XDP case, tracepoint is for exceptions, that
is, f.e. on abnormal BPF program exit such as unknown or XDP_ABORTED
return code, or when error occurs during XDP_TX action and the packet
could not be forwarded.
Both have been split into separate event headers, and can be further
extended. Worst case, if they unexpectedly should get into our way in
future, they can also removed [1]. Of course, these tracepoints (like
any other) can be analyzed by eBPF itself, etc. Example output:
# ./perf record -a -e bpf:* sleep 10
# ./perf script
sock_example 6197 [005] 283.980322: bpf:bpf_map_create: map type=ARRAY ufd=4 key=4 val=8 max=256 flags=0
sock_example 6197 [005] 283.980721: bpf:bpf_prog_load: prog=a5ea8fa30ea6849c type=SOCKET_FILTER ufd=5
sock_example 6197 [005] 283.988423: bpf:bpf_prog_get_type: prog=a5ea8fa30ea6849c type=SOCKET_FILTER
sock_example 6197 [005] 283.988443: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[06 00 00 00] val=[00 00 00 00 00 00 00 00]
[...]
sock_example 6197 [005] 288.990868: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[01 00 00 00] val=[14 00 00 00 00 00 00 00]
swapper 0 [005] 289.338243: bpf:bpf_prog_put_rcu: prog=a5ea8fa30ea6849c type=SOCKET_FILTER
[1] https://lwn.net/Articles/705270/
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
To make the code clearer, use rb_entry() instead of container_of() to
deal with rbtree.
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 04aeb56a17 ("net/mlx4_en: allocate non 0-order pages for RX
ring with __GFP_NOMEMALLOC") added code that appears to be not needed at
that time, since mlx4 never used __GFP_MEMALLOC allocations anyway.
As using memory reserves is a must in some situations (swap over NFS or
iSCSI), this patch adds this flag.
Note that this driver does not reuse pages (yet) so we do not have to
add anything else.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Boundaries checks for the number of RX, TX, other and combined channels
should be checked by the caller and not in the driver.
In addition, remove wrong memset on get channels as it overrides the cmd
field in the requester struct.
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When running SRIOV, warnings for SRQ LIMIT events flood the Hypervisor's
message log when (correct, normally operating) apps use SRQ LIMIT events
as a trigger to post WQEs to SRQs.
Add more information to the existing debug printout for SRQ_LIMIT, and
output the warning messages only for the SRQ CATAS ERROR event.
Fixes: acba2420f9 ("mlx4_core: Add wrapper functions and comm channel and slave event support to EQs")
Fixes: e0debf9cb5 ("mlx4_core: Reduce warning message for SRQ_LIMIT event to debug level")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Save the qp context flags byte containing the flag disabling vlan stripping
in the RESET to INIT qp transition, rather than in the INIT to RTR
transition. Per the firmware spec, the flags in this byte are active
in the RESET to INIT transition.
As a result of saving the flags in the incorrect qp transition, when
switching dynamically from VGT to VST and back to VGT, the vlan
remained stripped (as is required for VST) and did not return to
not-stripped (as is required for VGT).
Fixes: f0f829bf42 ("net/mlx4_core: Add immediate activate for VGT->VST->VGT")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In function mlx4_cq_completion() and mlx4_cq_event(), the
radix_tree_lookup requires a rcu_read_lock.
This is mandatory: if another core frees the CQ, it could
run the radix_tree_node_rcu_free() call_rcu() callback while
its being used by the radix tree lookup function.
Additionally, in function mlx4_cq_event(), since we are adding
the rcu lock around the radix-tree lookup, we no longer need to take
the spinlock. Also, the synchronize_irq() call for the async event
eliminates the need for incrementing the cq reference count in
mlx4_cq_event().
Other changes:
1. In function mlx4_cq_free(), replace spin_lock_irq with spin_lock:
we no longer take this spinlock in the interrupt context.
The spinlock here, therefore, simply protects against different
threads simultaneously invoking mlx4_cq_free() for different cq's.
2. In function mlx4_cq_free(), we move the radix tree delete to before
the synchronize_irq() calls. This guarantees that we will not
access this cq during any subsequent interrupts, and therefore can
safely free the CQ after the synchronize_irq calls. The rcu_read_lock
in the interrupt handlers only needs to protect against corrupting the
radix tree; the interrupt handlers may access the cq outside the
rcu_read_lock due to the synchronize_irq calls which protect against
premature freeing of the cq.
3. In function mlx4_cq_event(), we change the mlx_warn message to mlx4_dbg.
4. We leave the cq reference count mechanism in place, because it is
still needed for the cq completion tasklet mechanism.
Fixes: 6d90aa5cf1 ("net/mlx4_core: Make sure there are no pending async events when freeing CQ")
Fixes: 225c7b1fee ("IB/mlx4: Add a driver Mellanox ConnectX InfiniBand adapters")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Disable BH around the call to napi_schedule() to avoid following warning
[ 52.095499] NOHZ: local_softirq_pending 08
[ 52.421291] NOHZ: local_softirq_pending 08
[ 52.608313] NOHZ: local_softirq_pending 08
Fixes: 8d59de8f7b ("net/mlx4_en: Process all completions in RX rings after port goes up")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Erez Shitrit <erezsh@mellanox.com>
Cc: Eugenia Emantayev <eugenia@mellanox.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit b45f0674b9 ("mlx4: xdp: Allow raising MTU up to one page minus eth and vlan hdrs"),
it changed EOPNOTSUPP to ENOTSUPP by mistake. This patch fixes it.
Fixes: b45f0674b9 ("mlx4: xdp: Allow raising MTU up to one page minus eth and vlan hdrs")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The network device operation for reading statistics is only called
in one place, and it ignores the return value. Having a structure
return value is potentially confusing because some future driver could
incorrectly assume that the return value was used.
Fix all drivers with ndo_get_stats64 to have a void function.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Demoting simple flow steering rule priority (for DPDK) was achieved by
wrapping FW commands MLX4_QP_FLOW_STEERING_ATTACH/DETACH for the PF
as well, and forcing the priority to MLX4_DOMAIN_NIC in the wrapper
function for the PF and all VFs.
In function mlx4_ib_create_flow(), this change caused the main rule
creation for the PF to be wrapped, while it left the associated
tunnel steering rule creation unwrapped for the PF.
This mismatch caused rule deletion failures in mlx4_ib_destroy_flow()
for the PF when the detach wrapper function did not find the associated
tunnel-steering rule (since creation of that rule for the PF did not
go through the wrapper function).
Fix this by setting MLX4_QP_FLOW_STEERING_ATTACH/DETACH to be "native"
(so that the PF invocation does not go through the wrapper), and perform
the required priority demotion for the PF in the mlx4_ib_create_flow()
code path.
Fixes: 48564135cb ("net/mlx4_core: Demote simple multicast and broadcast flow steering rules")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
is_power_of_2 expects unsigned long and we pass u64 max_val_cycles,
this will be truncated on 32 bit systems, and the result is not what we
were expecting.
div_u64 expects u32 as a second argument and we pass
max_val_cycles_rounded which is u64 hence it will always be truncated.
Fix was tested on both 64 and 32 bit systems and got same results for
max_val_cycles and max_val_cycles_rounded.
Fixes: 4850cf4581 ("net/mlx4_en: Resolve dividing by zero in 32-bit system")
Signed-off-by: Slava Shwartsman <slavash@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch removes BUG_ON() macro from mlx4_alloc_icm_coherent()
by checking DMA address alignment in advance and performing proper
folding in case of error.
Fixes: 5b0bf5e25e ("mlx4_core: Support ICM tables in coherent memory")
Reported-by: Ozgur Karatas <okaratas@member.fsf.org>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Single send WQE in RX buffer should be stamped with software
ownership in order to prevent the flow of QP in error in FW
once UPDATE_QP is called.
Fixes: 9f519f68cf ('mlx4_en: Not using Shared Receive Queues')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
mlx4_QP_FLOW_STEERING_DETACH_wrapper first removes the steering
rule (which results in freeing the rule structure), and then
references a field in this struct (the qp number) when releasing the
busy-status on the rule's qp.
Since this memory was freed, it could reallocated and changed.
Therefore, the qp number in the struct may be incorrect,
so that we are releasing the incorrect qp. This leaves the rule's qp
in the busy state (and could possibly release an incorrect qp as well).
Fix this by saving the qp number in a local variable, for use after
removing the steering rule.
Fixes: 2c473ae7e5 ("net/mlx4_core: Disallow releasing VF QPs which have steering rules")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking fixes from David Miller:
1) Various ipvlan fixes from Eric Dumazet and Mahesh Bandewar.
The most important is to not assume the packet is RX just because
the destination address matches that of the device. Such an
assumption causes problems when an interface is put into loopback
mode.
2) If we retry when creating a new tc entry (because we dropped the
RTNL mutex in order to load a module, for example) we end up with
-EAGAIN and then loop trying to replay the request. But we didn't
reset some state when looping back to the top like this, and if
another thread meanwhile inserted the same tc entry we were trying
to, we re-link it creating an enless loop in the tc chain. Fix from
Daniel Borkmann.
3) There are two different WRITE bits in the MDIO address register for
the stmmac chip, depending upon the chip variant. Due to a bug we
could set them both, fix from Hock Leong Kweh.
4) Fix mlx4 bug in XDP_TX handling, from Tariq Toukan.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
net: stmmac: fix incorrect bit set in gmac4 mdio addr register
r8169: add support for RTL8168 series add-on card.
net: xdp: remove unused bfp_warn_invalid_xdp_buffer()
openvswitch: upcall: Fix vlan handling.
ipv4: Namespaceify tcp_tw_reuse knob
net: korina: Fix NAPI versus resources freeing
net, sched: fix soft lockup in tc_classify
net/mlx4_en: Fix user prio field in XDP forward
tipc: don't send FIN message from connectionless socket
ipvlan: fix multicast processing
ipvlan: fix various issues in ipvlan_process_multicast()
There is no point in having an extra type for extra confusion. u64 is
unambiguous.
Conversion was done with the following coccinelle script:
@rem@
@@
-typedef u64 cycle_t;
@fix@
typedef cycle_t;
@@
-cycle_t
+u64
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: John Stultz <john.stultz@linaro.org>
The user prio field is wrong (and overflows) in the XDP forward
flow.
This is a result of a bad value for num_tx_rings_p_up, which should
account all XDP TX rings, as they operate for the same user prio.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reported-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=ut0k
-----END PGP SIGNATURE-----
Merge tag 'pci-v4.10-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci
Pull PCI updates from Bjorn Helgaas:
"PCI changes:
- add support for PCI on ARM64 boxes with ACPI. We already had this
for theoretical spec-compliant hardware; now we're adding quirks
for the actual hardware (Cavium, HiSilicon, Qualcomm, X-Gene)
- add runtime PM support for hotplug ports
- enable runtime suspend for Intel UHCI that uses platform-specific
wakeup signaling
- add yet another host bridge registration interface. We hope this is
extensible enough to subsume the others
- expose device revision in sysfs for DRM
- to avoid device conflicts, make sure any VF BAR updates are done
before enabling the VF
- avoid unnecessary link retrains for ASPM
- allow INTx masking on Mellanox devices that support it
- allow access to non-standard VPD for Chelsio devices
- update Broadcom iProc support for PAXB v2, PAXC v2, inbound DMA,
etc
- update Rockchip support for max-link-speed
- add NVIDIA Tegra210 support
- add Layerscape LS1046a support
- update R-Car compatibility strings
- add Qualcomm MSM8996 support
- remove some uninformative bootup messages"
* tag 'pci-v4.10-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (115 commits)
PCI: Enable access to non-standard VPD for Chelsio devices (cxgb3)
PCI: Expand "VPD access disabled" quirk message
PCI: pciehp: Remove loading message
PCI: hotplug: Remove hotplug core message
PCI: Remove service driver load/unload messages
PCI/AER: Log AER IRQ when claiming Root Port
PCI/AER: Log errors with PCI device, not PCIe service device
PCI/AER: Remove unused version macros
PCI/PME: Log PME IRQ when claiming Root Port
PCI/PME: Drop unused support for PMEs from Root Complex Event Collectors
PCI: Move config space size macros to pci_regs.h
x86/platform/intel-mid: Constify mid_pci_platform_pm
PCI/ASPM: Don't retrain link if ASPM not possible
PCI: iproc: Skip check for legacy IRQ on PAXC buses
PCI: pciehp: Leave power indicator on when enabling already-enabled slot
PCI: pciehp: Prioritize data-link event over presence detect
PCI: rcar: Add gen3 fallback compatibility string for pcie-rcar
PCI: rcar: Use gen2 fallback compatibility last
PCI: rcar-gen2: Use gen2 fallback compatibility last
PCI: rockchip: Move the deassert of pm/aclk/pclk after phy_init()
..
Pull timer updates from Thomas Gleixner:
"The time/timekeeping/timer folks deliver with this update:
- Fix a reintroduced signed/unsigned issue and cleanup the whole
signed/unsigned mess in the timekeeping core so this wont happen
accidentaly again.
- Add a new trace clock based on boot time
- Prevent injection of random sleep times when PM tracing abuses the
RTC for storage
- Make posix timers configurable for real tiny systems
- Add tracepoints for the alarm timer subsystem so timer based
suspend wakeups can be instrumented
- The usual pile of fixes and updates to core and drivers"
* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
timekeeping: Use mul_u64_u32_shr() instead of open coding it
timekeeping: Get rid of pointless typecasts
timekeeping: Make the conversion call chain consistently unsigned
timekeeping_Force_unsigned_clocksource_to_nanoseconds_conversion
alarmtimer: Add tracepoints for alarm timers
trace: Update documentation for mono, mono_raw and boot clock
trace: Add an option for boot clock as trace clock
timekeeping: Add a fast and NMI safe boot clock
timekeeping/clocksource_cyc2ns: Document intended range limitation
timekeeping: Ignore the bogus sleep time if pm_trace is enabled
selftests/timers: Fix spelling mistake "Asyncrhonous" -> "Asynchronous"
clocksource/drivers/bcm2835_timer: Unmap region obtained by of_iomap
clocksource/drivers/arm_arch_timer: Map frame with of_io_request_and_map()
arm64: dts: rockchip: Arch counter doesn't tick in system suspend
clocksource/drivers/arm_arch_timer: Don't assume clock runs in suspend
posix-timers: Make them configurable
posix_cpu_timers: Move the add_device_randomness() call to a proper place
timer: Move sys_alarm from timer.c to itimer.c
ptp_clock: Allow for it to be optional
Kconfig: Regenerate *.c_shipped files after previous changes
...
Reserve XDP_PACKET_HEADROOM for packet and enable bpf_xdp_adjust_head()
support. This patch only affects the code path when XDP is active.
After testing, the tx_dropped counter is incremented if the xdp_prog sends
more than wire MTU.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When XDP is active in mlx4, mlx4 is using one page/pkt.
At the same time (i.e. when XDP is active), it is currently
limiting MTU to be FRAG_SZ0 - ETH_HLEN - (2 * VLAN_HLEN)
which is 1514 in x86. AFAICT, we can at least raise the MTU
limit up to PAGE_SIZE - ETH_HLEN - (2 * VLAN_HLEN) which this
patch is doing. It will be useful in the next patch which
allows XDP program to extend the packet by adding new header(s).
Note: In the earlier XDP patches, there is already existing guard
to ensure the page/pkt scheme only applies when XDP is active
in mlx4.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch allows XDP prog to extend/remove the packet
data at the head (like adding or removing header). It is
done by adding a new XDP helper bpf_xdp_adjust_head().
It also renames bpf_helper_changes_skb_data() to
bpf_helper_changes_pkt_data() to better reflect
that XDP prog does not work on skb.
This patch adds one "xdp_adjust_head" bit to bpf_prog for the
XDP-capable driver to check if the XDP prog requires
bpf_xdp_adjust_head() support. The driver can then decide
to error out during XDP_SETUP_PROG.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since offset is zero, it's not necessary to use set function. Reset
function is straightforward, and will remove the unnecessary add
operation in set function.
Signed-off-by: Zhang Shengju <zhangshengju@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Couple conflicts resolved here:
1) In the MACB driver, a bug fix to properly initialize the
RX tail pointer properly overlapped with some changes
to support variable sized rings.
2) In XGBE we had a "CONFIG_PM" --> "CONFIG_PM_SLEEP" fix
overlapping with a reorganization of the driver to support
ACPI, OF, as well as PCI variants of the chip.
3) In 'net' we had several probe error path bug fixes to the
stmmac driver, meanwhile a lot of this code was cleaned up
and reorganized in 'net-next'.
4) The cls_flower classifier obtained a helper function in
'net-next' called __fl_delete() and this overlapped with
Daniel Borkamann's bug fix to use RCU for object destruction
in 'net'. It also overlapped with Jiri's change to guard
the rhashtable_remove_fast() call with a check against
tc_skip_sw().
5) In mlx4, a revert bug fix in 'net' overlapped with some
unrelated changes in 'net-next'.
6) In geneve, a stale header pointer after pskb_expand_head()
bug fix in 'net' overlapped with a large reorganization of
the same code in 'net-next'. Since the 'net-next' code no
longer had the bug in question, there was nothing to do
other than to simply take the 'net-next' hunks.
Signed-off-by: David S. Miller <davem@davemloft.net>
My recent commit to get more precise rx/tx counters in ndo_get_stats64()
can lead to crashes at device dismantle, as Jesper found out.
We must prevent mlx4_en_fold_software_stats() trying to access
tx/rx rings if they are deleted.
Fix this by adding a test against priv->port_up in
mlx4_en_fold_software_stats()
Calling mlx4_en_fold_software_stats() from mlx4_en_stop_port()
allows us to eventually broadcast the latest/current counters to
rtnetlink monitors.
Fixes: 40931b8511 ("mlx4: give precise rx/tx bytes/packets counters")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-and-bisected-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Saeed Mahameed <saeedm@dev.mellanox.co.il>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In mlx4_alloc_cmd_mailbox(), pci_pool_alloc() followed by memset will be
replaced by pci_pool_zalloc()
Signed-off-by: Souptick joarder <jrdr.linux@gmail.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
mlx4 stats are chaotic because a deferred work queue is responsible
to update them every 250 ms.
Even sampling stats every one second with "sar -n DEV 1" gives
variations like the following :
lpaa23:~# sar -n DEV 1 10 | grep eth0 | cut -c1-65
07:39:22 eth0 146877.00 3265554.00 9467.15 4828168.50
07:39:23 eth0 146587.00 3260329.00 9448.15 4820445.98
07:39:24 eth0 146894.00 3259989.00 9468.55 4819943.26
07:39:25 eth0 110368.00 2454497.00 7113.95 3629012.17 <<>>
07:39:26 eth0 146563.00 3257502.00 9447.25 4816266.23
07:39:27 eth0 145678.00 3258292.00 9389.79 4817414.39
07:39:28 eth0 145268.00 3253171.00 9363.85 4809852.46
07:39:29 eth0 146439.00 3262185.00 9438.97 4823172.48
07:39:30 eth0 146758.00 3264175.00 9459.94 4826124.13
07:39:31 eth0 146843.00 3256903.00 9465.44 4815381.97
Average: eth0 142827.50 3179259.70 9206.30 4700578.16
This patch allows rx/tx bytes/packets counters being folded at the
time we need stats.
We now can fetch stats every 1 ms if we want to check NIC behavior
on a small time window. It is also easier to detect anomalies.
lpaa23:~# sar -n DEV 1 10 | grep eth0 | cut -c1-65
07:42:50 eth0 142915.00 3177696.00 9212.06 4698270.42
07:42:51 eth0 143741.00 3200232.00 9265.15 4731593.02
07:42:52 eth0 142781.00 3171600.00 9202.92 4689260.16
07:42:53 eth0 143835.00 3192932.00 9271.80 4720761.39
07:42:54 eth0 141922.00 3165174.00 9147.64 4679759.21
07:42:55 eth0 142993.00 3207038.00 9216.78 4741653.05
07:42:56 eth0 141394.06 3154335.64 9113.85 4663731.73
07:42:57 eth0 141850.00 3161202.00 9144.48 4673866.07
07:42:58 eth0 143439.00 3180736.00 9246.05 4702755.35
07:42:59 eth0 143501.00 3210992.00 9249.99 4747501.84
Average: eth0 142835.66 3182165.93 9206.98 4704874.08
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In procedure mlx4_flow_steer_promisc_add(), several fields
were left uninitialized in the rule structure.
Correctly initialize these fields.
Fixes: 592e49dda8 ("net/mlx4: Implement promiscuous mode with device managed flow-steering")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Per RX ring packets/bytes counters are not protected by global
priv->stats_lock.
Better not confuse the reader, and use READ_ONCE() to show we read
these counters without surrounding synchronization.
Interrupt moderation is best effort, and we do not really care of
ultra precise counters.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
udplite conflict is resolved by taking what 'net-next' did
which removed the backlog receive method assignment, since
it is no longer necessary.
Two entries were added to the non-priv ethtool operations
switch statement, one in 'net' and one in 'net-next, so
simple overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
Make sure mlx4_en_free_resources is called under the netdev state lock.
This is needed since RCU dereference of XDP prog should be protected.
Fixes: 326fe02d1e ("net/mlx4_en: protect ring->xdp_prog with rcu_read_lock")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reported-by: Sagi Grimberg <sagi@grimberg.me>
CC: Brenden Blanco <bblanco@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While stressing a 40Gbit mlx4 NIC with busy polling, I found false
sharing in mlx4 driver that can be easily avoided.
This patch brings an additional 7 % performance improvement in UDP_RR
workload.
1) If we received no frame during one mlx4_en_process_rx_cq()
invocation, no need to call mlx4_cq_set_ci() and/or dirty ring->cons
2) Do not refill rx buffers if we have plenty of them.
This avoids false sharing and allows some bulk/batch optimizations.
Page allocator and its locks will thank us.
Finally, mlx4_en_poll_rx_cq() should not return 0 if it determined
cpu handling NIC IRQ should be changed. We should return budget-1
instead, to not fool net_rx_action() and its netdev_budget.
v2: keep AVG_PERF_COUNTER(... polled) even if polled is 0
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We added a bunch of new Mellanox device ID definitions because they'll be
used by INTx quirks. Use them in the mlx4 ID table also so grep can find
both places. No functional change intended.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
There is no need calling napi_hash_del()+synchronize_rcu() before
calling netif_napi_del()
netif_napi_del() does this already.
Using napi_hash_del() in a driver is useful only when dealing with
a batch of NAPI structures, so that a single synchronize_rcu() can
be used. mlx4_en_deactivate_cq() is deactivating a single NAPI.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Do not rearm interrupts if we are busy polling.
mlx4 uses separate CQ for TX and RX, so number of TX interrupts
does not change, unfortunately.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Adam Belay <abelay@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Yuval Mintz <Yuval.Mintz@cavium.com>
Cc: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to break the hard dependency between the PTP clock subsystem and
ethernet drivers capable of being clock providers, this patch provides
simple PTP stub functions to allow linkage of those drivers into the
kernel even when the PTP subsystem is configured out. Drivers must be
ready to accept NULL from ptp_clock_register() in that case.
And to make it possible for PTP to be configured out, the select statement
in those driver's Kconfig menu entries is converted to the new "imply"
statement. This way the PTP subsystem may have Kconfig dependencies of
its own, such as POSIX_TIMERS, without having to make those ethernet
drivers unavailable if POSIX timers are cconfigured out. And when support
for POSIX timers is selected again then the default config option for PTP
clock support will automatically be adjusted accordingly.
The pch_gbe driver is a bit special as it relies on extra code in
drivers/ptp/ptp_pch.c. Therefore we let the make process descend into
drivers/ptp/ even if PTP_1588_CLOCK is unselected.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Edward Cree <ecree@solarflare.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <john.stultz@linaro.org>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Cc: Paul Bolle <pebolle@tiscali.nl>
Cc: linux-kbuild@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: Michal Marek <mmarek@suse.com>
Link: http://lkml.kernel.org/r/1478841010-28605-4-git-send-email-nicolas.pitre@linaro.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Commit 67f8b1dcb9 ("net/mlx4_en: Refactor the XDP forwarding rings
scheme") added a bug in that the prog's reference count is not dropped
in the error path when mlx4_en_try_alloc_resources() is failing from
mlx4_xdp_set().
We previously took bpf_prog_add(prog, priv->rx_ring_num - 1), that we
need to release again. Earlier in the call path, dev_change_xdp_fd()
itself holds a reference to the prog as well (hence the '- 1' in the
bpf_prog_add()), so a simple atomic_sub() is safe to use here. When
an error is propagated, then bpf_prog_put() is called eventually from
dev_change_xdp_fd()
Fixes: 67f8b1dcb9 ("net/mlx4_en: Refactor the XDP forwarding rings scheme")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit 9d2afba058.
The original issue would possibly exist if an external module
tried calling our "ethtool_ops" without checking if it still
exists.
The right way of solving it is by simply doing the check in
the caller side.
Currently, no action is required as there's no such use case.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
XDP statistics are reported in ethtool, in total and per ring,
as follows:
- xdp_drop: the number of packets dropped by xdp.
- xdp_tx: the number of packets forwarded by xdp.
- xdp_tx_full: the number of times an xdp forward failed
due to a full tx xdp ring.
In addition, all packets that are dropped/forwarded by XDP
are no longer accounted in rx_packets/rx_bytes of the ring,
so that they count traffic that is passed to the stack.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Separately manage the two types of TX rings: regular ones, and XDP.
Upon an XDP set, do not borrow regular TX rings and convert them
into XDP ones, but allocate new ones, unless we hit the max number
of rings.
Which means that in systems with smaller #cores we will not consume
the current TX rings for XDP, while we are still in the num TX limit.
XDP TX rings counters are not shown in ethtool statistics.
Instead, XDP counters will be added to the respective RX rings
in a downstream patch.
This has no performance implications.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Support XDP CQ type, and refactor the CQ type enum.
Rename the is_tx field to match the change.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Mostly simple overlapping changes.
For example, David Ahern's adjacency list revamp in 'net-next'
conflicted with an adjacency list traversal bug fix in 'net'.
Signed-off-by: David S. Miller <davem@davemloft.net>
Following the previous patch, as an optimization, the slave will
not even bother sending the DUMP_ETH_STATS command over the
comm channel.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
mlx4_en_DUMP_ETH_STATS took the *counter mutex* and then
called the FW command, with WRAPPED attribute. As a result, the fw command
is wrapped on the Hypervisor when it calls mlx4_en_DUMP_ETH_STATS.
The FW command wrapper flow on the hypervisor takes the *slave_cmd_mutex*
during processing.
At the same time, a VF could be in the process of coming up, and could
call mlx4_QUERY_FUNC_CAP. On the hypervisor, the command flow takes the
*slave_cmd_mutex*, then executes mlx4_QUERY_FUNC_CAP_wrapper.
mlx4_QUERY_FUNC_CAP wrapper calls mlx4_get_default_counter_index(),
which takes the *counter mutex*. DEADLOCK.
The fix is that the DUMP_ETH_STATS fw command should be called with
the NATIVE attribute, so that on the hypervisor, this command does not
enter the wrapper flow.
Since the Hypervisor no longer goes through the wrapper code, we also
simply return 0 in mlx4_DUMP_ETH_STATS_wrapper (i.e.the function succeeds,
but the returned data will be all zeroes).
No need to test if it is the Hypervisor going through the wrapper.
Fixes: f9baff509f ("mlx4_core: Add "native" argument to mlx4_cmd ...")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently interrupt test that is part of ethtool selftest runs the
check over all interrupt vectors of the device.
In mlx4_en package part of interrupt vectors are uninitialized since
mlx4_ib doesn't exist. This causes NOP FW command to time out.
Change logic to test current port interrupt vectors only.
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the Hypervisor, there are several FW commands which are invoked
before the comm channel is initialized (in mlx4_multi_func_init).
These include MOD_STAT_CONFIG, QUERY_DEV_CAP, INIT_HCA, and others.
If any of these commands fails, say with a timeout, the Hypervisor
driver enters the internal error reset flow. In this flow, the driver
attempts to notify all slaves via the comm channel that an internal error
has occurred.
Since the comm channel has not yet been initialized (i.e., mapped via
ioremap), this will cause dereferencing a NULL pointer.
To fix this, do not access the comm channel in the internal error flow
if it has not yet been initialized.
Fixes: 55ad359225 ("net/mlx4_core: Enable device recovery flow with SRIOV")
Fixes: ab9c17a009 ("mlx4_core: Modify driver initialization flow to accommodate SRIOV for Ethernet")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix a kernel panic that occurs as a result of an asynchronous event
handled in roce_gid_mgmt:
mlx4_en_get_drvinfo is called and accesses freed resources.
This happens in a shutdown flow only, since pci device is destroyed
while netdevice is still alive.
Fixes: c27a02cd94 ("mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC")
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently there is a race between incoming traffic and
initialization flow. HW is able to receive the packets
after INIT_PORT is done and unicast steering is configured.
Before we set priv->port_up NAPI is not scheduled and
receive queues become full. Therefore we never get
new interrupts about the completions.
This issue could happen if running heavy traffic during
bringing port up.
The resolution is to schedule NAPI once port_up is set.
If receive queues were full this will process all cqes
and release them.
Fixes: c27a02cd94 ("mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC")
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When doing roundup_pow_of_two for large enough number with
bit 31, an overflow will occur and a value equal to 1 will
be returned. In this case 1 will be subtracted from the return
value and division by zero will be reached.
Fixes: 31c128b66e ("net/mlx4_en: Choose time-stamping shift value according to HW frequency")
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change the default status of quality of service back to disabled,
as it hurts performance in some cases.
Fixes: 38438f7c7e ("net/mlx4: Set enhanced QoS support by default when ...")
Signed-off-by: Moshe Lazer <moshel@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When only one port type is supported, it should be read only.
We reject changing requests, even to the auto sense mode.
Fixes: 27bf91d6a0 ("mlx4_core: Add link type autosensing")
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The resource type enum in the resource tracker was incorrect.
RES_EQ was put in the position of RES_NPORT_ID (a FC resource).
Since the remaining resources maintain their current values,
and RES_EQ is not passed from slaves to the hypervisor in any
FW command, this change affects only the hypervisor.
Therefore, there is no backwards-compatibility issue.
Fixes: 623ed84b1f ("mlx4_core: initial header-file changes for SRIOV support")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is an old warning about mlx4_SW2HW_EQ_wrapper on x86:
ethernet/mellanox/mlx4/resource_tracker.c: In function ‘mlx4_SW2HW_EQ_wrapper’:
ethernet/mellanox/mlx4/resource_tracker.c:3071:10: error: ‘eq’ may be used uninitialized in this function [-Werror=maybe-uninitialized]
The problem here is that gcc won't track the state of the variable
across a spin_unlock. Moving the assignment out of the lock is
safe here and avoids the warning.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In cases where the number of tx rings is not a multiple of the number of
rx rings, the tx completion event will be handled on a different core
from the transmit and population of the ring. Races on the ring will
lead to a double-free of the page, and possibly other corruption.
The rings are initialized by default with a valid multiple of rings,
based on the number of cpus, therefore an invalid configuration requires
ethtool to change the ring layout. For instance 'ethtool -L eth0 rx 9 tx
8' will cause packets received on rx0, and XDP_TX'd to tx48, to be
completed on cpu3 (48 % 9 == 3).
Resolve this discrepancy by shifting the irq for the xdp tx queues to
start again from 0, modulo rx_ring_num.
Fixes: 9ecc2d8617 ("net/mlx4_en: add xdp forwarding and data write support")
Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Brenden Blanco <bblanco@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
- Updates to mlx5
- Updates to mlx4 (two conflicts, both minor and easily resolved)
- Updates to iw_cxgb4 (one conflict, not so obvious to resolve, proper
resolution is to keep the code in cxgb4_main.c as it is in Linus'
tree as attach_uld was refactored and moved into cxgb4_uld.c)
- Improvements to uAPI (moved vendor specific API elements to uAPI area)
- Add hns-roce driver and hns and hns-roce ACPI reset support
- Conversion of all rdma code away from deprecated
create_singlethread_workqueue
- Security improvement: remove unsafe ib_get_dma_mr (breaks lustre in
staging)
-----BEGIN PGP SIGNATURE-----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=LC+S
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma
Pull main rdma updates from Doug Ledford:
"This is the main pull request for the rdma stack this release. The
code has been through 0day and I had it tagged for linux-next testing
for a couple days.
Summary:
- updates to mlx5
- updates to mlx4 (two conflicts, both minor and easily resolved)
- updates to iw_cxgb4 (one conflict, not so obvious to resolve,
proper resolution is to keep the code in cxgb4_main.c as it is in
Linus' tree as attach_uld was refactored and moved into
cxgb4_uld.c)
- improvements to uAPI (moved vendor specific API elements to uAPI
area)
- add hns-roce driver and hns and hns-roce ACPI reset support
- conversion of all rdma code away from deprecated
create_singlethread_workqueue
- security improvement: remove unsafe ib_get_dma_mr (breaks lustre in
staging)"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (75 commits)
staging/lustre: Disable InfiniBand support
iw_cxgb4: add fast-path for small REG_MR operations
cxgb4: advertise support for FR_NSMR_TPTE_WR
IB/core: correctly handle rdma_rw_init_mrs() failure
IB/srp: Fix infinite loop when FMR sg[0].offset != 0
IB/srp: Remove an unused argument
IB/core: Improve ib_map_mr_sg() documentation
IB/mlx4: Fix possible vl/sl field mismatch in LRH header in QP1 packets
IB/mthca: Move user vendor structures
IB/nes: Move user vendor structures
IB/ocrdma: Move user vendor structures
IB/mlx4: Move user vendor structures
IB/cxgb4: Move user vendor structures
IB/cxgb3: Move user vendor structures
IB/mlx5: Move and decouple user vendor structures
IB/{core,hw}: Add constant for node_desc
ipoib: Make ipoib_warn ratelimited
IB/mlx4/alias_GUID: Remove deprecated create_singlethread_workqueue
IB/ipoib_verbs: Remove deprecated create_singlethread_workqueue
IB/ipoib: Remove deprecated create_singlethread_workqueue
...
In MLX qp packets, the LRH (built by the driver) has both a VL field
and an SL field. When building a QP1 packet, the VL field should
reflect the SLtoVL mapping and not arbitrarily contain zero (as is
done now). This bug causes credit problems in IB switches at
high rates of QP1 packets.
The fix is to cache the SL to VL mapping in the driver, and look up
the VL mapped to the SL provided in the send request when sending
QP1 packets.
For FW versions which support generating a port_management_config_change
event with subtype sl-to-vl-table-change, the driver uses that event
to update its sl-to-vl mapping cache. Otherwise, the driver snoops
incoming SMP mads to update the cache.
There remains the case where the FW is running in secure-host mode
(so no QP0 packets are delivered to the driver), and the FW does not
generate the sl2vl mapping change event. To support this case, the
driver updates (via querying the FW) its sl2vl mapping cache when
running in secure-host mode when it receives either a Port Up event
or a client-reregister event (where the port is still up, but there
may have been an opensm failover).
OpenSM modifies the sl2vl mapping before Port Up and Client-reregister
events occur, so if there is a mapping change the driver's cache will
be properly updated.
Fixes: 225c7b1fee ("IB/mlx4: Add a driver Mellanox ConnectX InfiniBand adapters")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
This also can address following UBSAN warnings:
[ 36.640343] ================================================================================
[ 36.648772] UBSAN: Undefined behaviour in drivers/net/ethernet/mellanox/mlx4/fw.c:857:26
[ 36.656853] shift exponent 64 is too large for 32-bit type 'int'
[ 36.663348] ================================================================================
[ 36.671783] ================================================================================
[ 36.680213] UBSAN: Undefined behaviour in drivers/net/ethernet/mellanox/mlx4/fw.c:861:27
[ 36.688297] shift exponent 35 is too large for 32-bit type 'int'
[ 36.694702] ================================================================================
Tested:
reboot with UBSAN, no warning.
Signed-off-by: David Decotigny <decot@googlers.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move the vf to VST 802.1ad mode (mlx4 VST QinQ mode) by setting vf vlan
protocol to 802.1ad.
VST 802.1ad mode in mlx4, is used for STAG strip/insertion by PF, while
the CTAG is set by the VF.
Read current vlan protocol as part of the vf configuration state.
Upon setting vf vlan protocol to 802.1ad, we use a mechanism of handshake
to verify that both the vf and the pf driver version support it.
The handshake uses the command QUERY_FUNC_CAP:
- The vf sets a pre-defined support bit in input modifier.
- A pf that supports the feature sends the request to the vf through a
pre-defined field in the output mailbox.
- In case vf does not support the feature, the pf will fail the control
command (in this case, IP link tool command to set the vf vlan
protocol to 802.1ad).
No change in VST 802.1Q mode.
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduce new rtnl UAPI that exposes a list of vlans per VF, giving
the ability for user-space application to specify it for the VF, as an
option to support 802.1ad.
We adjusted IP Link tool to support this option.
For future use cases, the new UAPI supports multiple vlans. For now we
limit the list size to a single vlan in kernel.
Add IFLA_VF_VLAN_LIST in addition to IFLA_VF_VLAN to keep backward
compatibility with older versions of IP Link tool.
Add a vlan protocol parameter to the ndo_set_vf_vlan callback.
We kept 802.1Q as the drivers' default vlan protocol.
Suitable ip link tool command examples:
Set vf vlan protocol 802.1ad:
ip link set eth0 vf 1 vlan 100 proto 802.1ad
Set vf to VST (802.1Q) mode:
ip link set eth0 vf 1 vlan 100 proto 802.1Q
Or by omitting the new parameter
ip link set eth0 vf 1 vlan 100
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In Ethernet VF, disable vlan HW acceleration on VF
while it is set to VF vlan protocol 802.1ad mode.
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Check device capability to support VF vlan protocol 802.1ad mode.
Add vport attribute vlan protocol.
Init vport vlan protocol by default to 802.1Q.
Add update QP support for VF vlan protocol 802.1ad.
Add func capability vlan_offload_disable to disable all
vlan HW acceleration on VF while the VF is set to VF vlan protocol
802.1ad mode.
No change in VF vlan protocol 802.1Q (VST) mode.
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Separate QUERY_FUNC_CAP flags0 from QUERY_FUNC_CAP flags, as 'flags' is
already used for another set of flags in FUNC CAP, while phv bit should be
part of a different set of flags.
Remove QUERY_FUNC_CAP port_flags field, as it is not in use.
Fixes: 77fc29c4bb ('net/mlx4_core: Preparations for 802.1ad VLAN support')
Fixes: 5cc914f108 ('mlx4_core: Added FW commands and their wrappers for supporting SRIOV')
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Drivers must be ready to accept NULL from ptp_clock_register() if the
PTP clock subsystem is configured out.
This patch documents that and ensures that all drivers cope well
with a NULL return.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
Reviewed-by: Eugenia Emantayev <eugenia@mellanox.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch cleans devlink resources by calling devlink_port_unregister()
to avoid the following issues:
- Kernel panic when triggering reset flow.
- Memory leak due to unfreed resources in mlx4_init_port_info().
Fixes: 09d4d087cd ("mlx4: Implement devlink interface")
Signed-off-by: Kamal Heib <kamalh@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When switching from polling-based fw commands to event-based fw
commands, there is a race condition which could cause a fw command
in another task to hang: that task will keep waiting for the polling
sempahore, but may never be able to acquire it. This is due to
mlx4_cmd_use_events, which "down"s the sempahore back to 0.
During driver initialization, this is not a problem, since no other
tasks which invoke FW commands are active.
However, there is a problem if the driver switches to polling mode
and then back to event mode during normal operation.
The "test_interrupts" feature does exactly that.
Running "ethtool -t <eth device> offline" causes the PF driver to
temporarily switch to polling mode, and then back to event mode.
(Note that for VF drivers, such switching is not performed).
Fix this by adding a read-write semaphore for protection when
switching between modes.
Fixes: 225c7b1fee ("IB/mlx4: Add a driver Mellanox ConnectX InfiniBand adapters")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Radix tree lookup can be performed without locking.
Fixes: 225c7b1fee ("IB/mlx4: Add a driver Mellanox ConnectX InfiniBand adapters")
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Suggested-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use tabs instead of spaces before if statement, no functional change.
Fixes: e7c1c2c462 ("mlx4_en: Added self diagnostics test implementation")
Signed-off-by: Kamal Heib <kamalh@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add likely/unlikely hints to improve branch predictions
in the RX data-path.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Correct drop handling for XDP_TX on TX failure, were recently added in
commit 95357907ae ("mlx4: fix XDP_TX is acting like XDP_PASS on TX
ring full").
The change missed an opportunity for recycling the RX page, instead of
going through the page allocator, like the regular XDP_DROP action does.
This patch cease the opportunity, by going through the XDP_DROP case.
Fixes: 95357907ae ("mlx4: fix XDP_TX is acting like XDP_PASS on TX ring full")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The XDP_TX action can fail transmitting the frame in case the TX ring
is full or port is down. In case of TX failure it should drop the
frame, and not as now call 'break' which is the same as XDP_PASS.
Fixes: 9ecc2d8617 ("net/mlx4_en: add xdp forwarding and data write support")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Brenden Blanco <bblanco@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If an error occurs in mlx4_init_eq_table the index used in the
err_out_unmap label is one too big which results in a panic in
mlx4_free_eq. This patch fixes the index in the error path.
Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/ethernet/mediatek/mtk_eth_soc.c
drivers/net/ethernet/qlogic/qed/qed_dcbx.c
drivers/net/phy/Kconfig
All conflicts were cases of overlapping commits.
Signed-off-by: David S. Miller <davem@davemloft.net>
When port is down, tx drop counter update is not needed.
Updating the counter in this case can cause a kernel
panic as when the port is down, ring can be NULL.
Fixes: 63a664b7e9 ("net/mlx4_en: fix tx_dropped bug")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds a capability check before enabling DCBX.
In addition, it re-organizes the relevant data structures,
and fixes a typo in a define.
Fixes: af7d518526 ("net/mlx4_en: Add DCB PFC support through CEE netlink commands")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
mlx4_en_dcbnl_set_state() returns u8, the return value from
mlx4_en_setup_tc() could be negative in case of failure, so fix that.
Fixes: af7d518526 ("net/mlx4_en: Add DCB PFC support through CEE netlink commands")
Signed-off-by: Kamal Heib <kamalh@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
mlx4_en_dcbnl_set_all() returns u8, so return value can't be negative in
case of failure.
Fixes: af7d518526 ("net/mlx4_en: Add DCB PFC support through CEE netlink commands")
Signed-off-by: Kamal Heib <kamalh@mellanox.com>
Signed-off-by: Rana Shahout <ranas@mellanox.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Depending on the preempt mode, the bpf_prog stored in xdp_prog may be
freed despite the use of call_rcu inside bpf_prog_put. The situation is
possible when running in PREEMPT_RCU=y mode, for instance, since the rcu
callback for destroying the bpf prog can run even during the bh handling
in the mlx4 rx path.
Several options were considered before this patch was settled on:
Add a napi_synchronize loop in mlx4_xdp_set, which would occur after all
of the rings are updated with the new program.
This approach has the disadvantage that as the number of rings
increases, the speed of update will slow down significantly due to
napi_synchronize's msleep(1).
Add a new rcu_head in bpf_prog_aux, to be used by a new bpf_prog_put_bh.
The action of the bpf_prog_put_bh would be to then call bpf_prog_put
later. Those drivers that consume a bpf prog in a bh context (like mlx4)
would then use the bpf_prog_put_bh instead when the ring is up. This has
the problem of complexity, in maintaining proper refcnts and rcu lists,
and would likely be harder to review. In addition, this approach to
freeing must be exclusive with other frees of the bpf prog, for instance
a _bh prog must not be referenced from a prog array that is consumed by
a non-_bh prog.
The placement of rcu_read_lock in this patch is functionally the same as
putting an rcu_read_lock in napi_poll. Actually doing so could be a
potentially controversial change, but would bring the implementation in
line with sk_busy_loop (though of course the nature of those two paths
is substantially different), and would also avoid future copy/paste
problems with future supporters of XDP. Still, this patch does not take
that opinionated option.
Testing was done with kernels in either PREEMPT_RCU=y or
CONFIG_PREEMPT_VOLUNTARY=y+PREEMPT_RCU=n modes, with neither exhibiting
any drawback. With PREEMPT_RCU=n, the extra call to rcu_read_lock did
not show up in the perf report whatsoever, and with PREEMPT_RCU=y the
overhead of rcu_read_lock (according to perf) was the same before/after.
In the rx path, rcu_read_lock is eventually called for every packet
from netif_receive_skb_internal, so the napi poll call's rcu_read_lock
is easily amortized.
v2:
Remove extra rcu_read_lock in mlx4_en_process_rx_cq body
Annotate xdp_prog with __rcu, and convert all usages to rcu_assign or
rcu_dereference[_protected] as appropriate.
Add explicit mutex lock around rcu_assign instead of xchg loop.
Fixes: d576acf0a2 ("net/mlx4_en: add page recycle to prepare rx ring for tx support")
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Brenden Blanco <bblanco@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
- Updates/fixes for iw_cxgb4 driver
- Updates/fixes for mlx5 driver
- Add flow steering and RSS API
- Add hardware stats to mlx4 and mlx5 drivers
- Add firmware version API for RDMA driver use
- Add the rxe driver (this is a software RoCE driver that makes any
Ethernet device a RoCE device)
- Fixes for i40iw driver
- Support for send only multicast joins in the cma layer
- Other minor fixes
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=oZOO
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma
Pull base rdma updates from Doug Ledford:
"Round one of 4.8 code: while this is mostly normal, there is a new
driver in here (the driver was hosted outside the kernel for several
years and is actually a fairly mature and well coded driver). It
amounts to 13,000 of the 16,000 lines of added code in here.
Summary:
- Updates/fixes for iw_cxgb4 driver
- Updates/fixes for mlx5 driver
- Add flow steering and RSS API
- Add hardware stats to mlx4 and mlx5 drivers
- Add firmware version API for RDMA driver use
- Add the rxe driver (this is a software RoCE driver that makes any
Ethernet device a RoCE device)
- Fixes for i40iw driver
- Support for send only multicast joins in the cma layer
- Other minor fixes"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (72 commits)
Soft RoCE driver
IB/core: Support for CMA multicast join flags
IB/sa: Add cached attribute containing SM information to SA port
IB/uverbs: Fix race between uverbs_close and remove_one
IB/mthca: Clean up error unwind flow in mthca_reset()
IB/mthca: NULL arg to pci_dev_put is OK
IB/hfi1: NULL arg to sc_return_credits is OK
IB/mlx4: Add diagnostic hardware counters
net/mlx4: Query performance and diagnostics counters
net/mlx4: Add diagnostic counters capability bit
Use smaller 512 byte messages for portmapper messages
IB/ipoib: Report SG feature regardless of HW UD CSUM capability
IB/mlx4: Don't use GFP_ATOMIC for CQ resize struct
IB/hfi1: Disable by default
IB/rdmavt: Disable by default
IB/mlx5: Fix port counter ID association to QP offset
IB/mlx5: Fix iteration overrun in GSI qps
i40iw: Add NULL check for puda buffer
i40iw: Change dup_ack_thresh to u8
i40iw: Remove unnecessary check for moving CQ head
...
Add a function to query diagnostics counters from the firmware.
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Add a bit that indicates if the firmware supports per port
diagnostic counters.
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Merge drm updates from Dave Airlie:
"This is the main drm pull request for 4.8.
I'm down with a cold at the moment so hopefully this isn't in too bad
a state, I finished pulling stuff last week mostly (nouveau fixes just
went in today), so only this message should be influenced by illness.
Apologies to anyone who's major feature I missed :-)
Core:
Lockless GEM BO freeing
Non-blocking atomic work
Documentation changes (rst/sphinx)
Prep for new fencing changes
Simple display helpers
Master/auth changes
Register/unregister rework
Loads of trivial patches/fixes.
New stuff:
ARM Mali display driver (not the 3D chip)
sii902x RGB->HDMI bridge
Panel:
Support for new panels
Improved backlight support
Bridge:
Convert ADV7511 to bridge driver
ADV7533 support
TC358767 (DSI/DPI to eDP) encoder chip support
i915:
BXT support enabled by default
GVT-g infrastructure
GuC command submission and fixes
BXT workarounds
SKL/BKL workarounds
Demidlayering device registration
Thundering herd fixes
Missing pci ids
Atomic updates
amdgpu/radeon:
ATPX improvements for better dGPU power control on PX systems
New power features for CZ/BR/ST
Pipelined BO moves and evictions in TTM
GPU scheduler improvements
GPU reset improvements
Overclocking on dGPUs with amdgpu
Polaris powermanagement enabled
nouveau:
GK20A/GM20B volt and clock improvements.
Initial support for GP100/GP104 GPUs, GP104 will not yet support
acceleration due to NVIDIA having not released firmware for them as of yet.
exynos:
Exynos5433 SoC with IOMMU support.
vc4:
Shader validation for branching
imx-drm:
Atomic mode setting conversion
Reworked DMFC FIFO allocation
External bridge support
analogix-dp:
RK3399 eDP support
Lots of fixes.
rockchip:
Lots of small fixes.
msm:
DT bindings cleanups
Shrinker and madvise support
ASoC HDMI codec support
tegra:
Host1x driver cleanups
SOR reworking for DP support
Runtime PM support
omapdrm:
PLL enhancements
Header refactoring
Gamma table support
arcgpu:
Simulator support
virtio-gpu:
Atomic modesetting fixes.
rcar-du:
Misc fixes.
mediatek:
MT8173 HDMI support
sti:
ASOC HDMI codec support
Minor fixes
fsl-dcu:
Suspend/resume support
Bridge support
amdkfd:
Minor fixes.
etnaviv:
Enable GPU clock gating
hisilicon:
Vblank and other fixes"
* tag 'drm-for-v4.8' of git://people.freedesktop.org/~airlied/linux: (1575 commits)
drm/nouveau/gr/nv3x: fix instobj write offsets in gr setup
drm/nouveau/acpi: fix lockup with PCIe runtime PM
drm/nouveau/acpi: check for function 0x1B before using it
drm/nouveau/acpi: return supported DSM functions
drm/nouveau/acpi: ensure matching ACPI handle and supported functions
drm/nouveau/fbcon: fix font width not divisible by 8
drm/amd/powerplay: remove enable_clock_power_gatings_tasks from initialize and resume events
drm/amd/powerplay: move clockgating to after ungating power in pp for uvd/vce
drm/amdgpu: add query device id and revision id into system info entry at CGS
drm/amdgpu: add new definition in bif header
drm/amd/powerplay: rename smum header guards
drm/amdgpu: enable UVD context buffer for older HW
drm/amdgpu: fix default UVD context size
drm/amdgpu: fix incorrect type of info_id
drm/amdgpu: make amdgpu_cgs_call_acpi_method as static
drm/amdgpu: comment out unused defaults_staturn_pro static const structure to fix the build
drm/amdgpu: enable UVD VM only on polaris
drm/amdgpu: increase timeout of IB test
drm/amdgpu: add destroy session when generate VCE destroy msg.
drm/amd: fix deadlock of job_list_lock V2
...
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJXlRXSAAoJEHm+PkMAQRiGG/gH/0Z8O4zWOsrwO+X1mRToRDBH
joFOjAmCVe83T1VpF5LYNB+9+owL/dEDt6+ZIswnhH7AfQPjs4RqwS4PcuMbCDVO
+mDm0PmfcKaYcQZrB2Z2OwIzRNnfCTVcsDPhIHwuIHk0m4z/xuGZonD8KoAj0+tO
3yJF6sbE1KubDVjOb+lmZZSP3cXA0pDXrNhkYhE4Tsr8fiihGjeXSNJ8t2zPLjxo
W3MPqo0rzDvQsOwoF4TWHHagVaFSJlhLBBgqu33fI7uO3jtfQD2G8wG68JCND1j3
qbMoBfTLFV/yQmSIJUt0Wv1axaCcwnjpweEB35A/GEeZ0mNB1rDdoBeI1eKEQkc=
=DGFC
-----END PGP SIGNATURE-----
Backmerge tag 'v4.7' into drm-next
Linux 4.7
As requested by Daniel Vetter as the conflicts were getting messy.
Verify that the device state is registered before un-registering it.
This check is required to prevent an OOPS on flows that do
re-registration of the device and its previous state was
unregistered.
Fixes: 225c7b1fee ("IB/mlx4: Add a driver Mellanox ConnectX InfiniBand adapters")
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For consistency, and in order to hint at the synchronous nature of the
xdp_prog field, use READ_ONCE in the destroy path of the ring. All
occurrences should now use either READ_ONCE or xchg.
Signed-off-by: Brenden Blanco <bblanco@plumgrid.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
A user will now be able to loop packets back out of the same port using
a bpf program attached to xdp hook. Updates to the packet contents from
the bpf program is also supported.
For the packet write feature to work, the rx buffers are now mapped as
bidirectional when the page is allocated. This occurs only when the xdp
hook is active.
When the program returns a TX action, enqueue the packet directly to a
dedicated tx ring, so as to avoid completely any locking. This requires
the tx ring to be allocated 1:1 for each rx ring, as well as the tx
completion running in the same softirq.
Upon tx completion, this dedicated tx ring recycles pages without
unmapping directly back to the original rx ring. In steady state tx/drop
workload, effectively 0 page allocs/frees will occur.
In order to separate out the paths between free and recycle, a
free_tx_desc func pointer is introduced that is optionally updated
whenever recycle_ring is activated. By default the original free
function is always initialized.
Signed-off-by: Brenden Blanco <bblanco@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In preparation for writing the tx descriptor from multiple functions,
create a helper for both normal and blueflame access.
Signed-off-by: Brenden Blanco <bblanco@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The mlx4 driver by default allocates order-3 pages for the ring to
consume in multiple fragments. When the device has an xdp program, this
behavior will prevent tx actions since the page must be re-mapped in
TODEVICE mode, which cannot be done if the page is still shared.
Start by making the allocator configurable based on whether xdp is
running, such that order-0 pages are always used and never shared.
Since this will stress the page allocator, add a simple page cache to
each rx ring. Pages in the cache are left dma-mapped, and in drop-only
stress tests the page allocator is eliminated from the perf report.
Note that setting an xdp program will now require the rings to be
reconfigured.
Before:
26.91% ksoftirqd/0 [mlx4_en] [k] mlx4_en_process_rx_cq
17.88% ksoftirqd/0 [mlx4_en] [k] mlx4_en_alloc_frags
6.00% ksoftirqd/0 [mlx4_en] [k] mlx4_en_free_frag
4.49% ksoftirqd/0 [kernel.vmlinux] [k] get_page_from_freelist
3.21% swapper [kernel.vmlinux] [k] intel_idle
2.73% ksoftirqd/0 [kernel.vmlinux] [k] bpf_map_lookup_elem
2.57% swapper [mlx4_en] [k] mlx4_en_process_rx_cq
After:
31.72% swapper [kernel.vmlinux] [k] intel_idle
8.79% swapper [mlx4_en] [k] mlx4_en_process_rx_cq
7.54% swapper [kernel.vmlinux] [k] poll_idle
6.36% swapper [mlx4_core] [k] mlx4_eq_int
4.21% swapper [kernel.vmlinux] [k] tasklet_action
4.03% swapper [kernel.vmlinux] [k] cpuidle_enter_state
3.43% swapper [mlx4_en] [k] mlx4_en_prepare_rx_desc
2.18% swapper [kernel.vmlinux] [k] native_irq_return_iret
1.37% swapper [kernel.vmlinux] [k] menu_select
1.09% swapper [kernel.vmlinux] [k] bpf_map_lookup_elem
Signed-off-by: Brenden Blanco <bblanco@plumgrid.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for the BPF_PROG_TYPE_XDP hook in mlx4 driver.
In tc/socket bpf programs, helpers linearize skb fragments as needed
when the program touches the packet data. However, in the pursuit of
speed, XDP programs will not be allowed to use these slower functions,
especially if it involves allocating an skb.
Therefore, disallow MTU settings that would produce a multi-fragment
packet that XDP programs would fail to access. Future enhancements could
be done to increase the allowable MTU.
The xdp program is present as a per-ring data structure, but as of yet
it is not possible to set at that granularity through any ndo.
Signed-off-by: Brenden Blanco <bblanco@plumgrid.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes the lost of Ethernet port on low memory system,
when driver frees its resources and fails to allocate new resources.
Issue could happen while changing number of channels, rings size or
changing the timestamp configuration.
This fix is necessary because of removing vmap use in the code.
When vmap was in use driver could allocate non-contiguous memory
and make it contiguous with vmap. Now it could fail to allocate
a large chunk of contiguous memory and lose the port.
Current code tries to allocate new resources and then upon success
frees the old resources.
Fixes: 73898db043 ('net/mlx4: Avoid wrong virtual mappings')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Filters cleanup should be done once before destroying net device,
since filters list is contained in the private data.
Fixes: 1eb8c695bd ('net/mlx4_en: Add accelerated RFS support')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Silent a few smatch warnings about indentation.
This include the removal of a 'return' statement in 'resource_tracker.c'.
This 'return' will still be performed when breaking out of the
corresponding 'switch' block.
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Several cases of overlapping changes, except the packet scheduler
conflicts which deal with the addition of the free list parameter
to qdisc_enqueue().
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds support for reading and updating priority flow
control (PFC) attributes in the driver via netlink.
Signed-off-by: Rana Shahout <ranas@mellanox.com>
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This allows a clean shutdown, even if some netdev clients do not
release their reference from this netdev. It is enough to release
the HW resources only as the kernel is shutting down.
Fixes: 2ba5fbd62b ('net/mlx4_core: Handle AER flow properly')
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Modify mlx4_en_vlan_rx_[add/kill]_vid to return error value in case of
failure.
Fixes: 8e586137e6 ('net: make vlan ndo_vlan_rx_[add/kill]_vid return error value')
Signed-off-by: Kamal Heib <kamalh@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change replaces the network device operations for adding or removing a
VXLAN port with operations that are more generically defined to be used for
any UDP offload port but provide a type. As such by just adding a line to
verify that the offload type is VXLAN we can maintain the same
functionality.
In addition I updated the socket address family check so that instead of
excluding IPv6 we instead abort of type is not IPv4. This makes much more
sense as we should only be supporting IPv4 outer addresses on this
hardware.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The mlx4e driver does not support more than one port for VXLAN offload. As
such expecting the hardware to offload other ports is invalid since it
appears the parsing logic is used to perform Tx checksum and segmentation
offloads. Use the vxlan_port number to determine in which cases we can
apply the offload and in which cases we can not.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Maciej Żenczykowski reported lockdep warning a spinlock
was not registered before being held in mlx4_cmd_wake_completions()
cmd.context_lock initialization is not at the right place.
1) mlx4_cmd_use_events() can be called multiple times.
Calling spin_lock_init() on a live spinlock can lead
to hangs.
2) mlx4_cmd_wake_completions() can be called while lock
has not been initialized.
Lockdep complains, and current logic is not race prone.
It seems better to move the initialization earlier in
mlx4_load_one()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Maciej Żenczykowski <maze@google.com>
Cc: Eugenia Emantayev <eugenia@mellanox.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
mlx4 RSS is limited to spread incoming packets to a power of two number
of queues.
An uniformly distibuted traffic would be split on queues 0 to N-1, N
being a power of two, each queue having a 1/N weight.
If number of RX queues is not a power of two, upper RX queues do not
receive traffic.
ethtool -x is lying, because it pretends some queues have higher weight.
Before patch:
lpaa24:~# ethtool -L eth1 rx 24
lpaa24:~# ethtool -x eth1
RX flow hash indirection table for eth1 with 24 RX ring(s):
0: 0 1 2 3 4 5 6 7
8: 8 9 10 11 12 13 14 15
16: 0 1 2 3 4 5 6 7
RSS hash key:
e0:7c:3a:89:07:55:b6:58:69:cc:f4:e5:24:62:e3:25:88:6c:42:5b:d2:cb:9a:d2:e0:06:e1:dc:f9:09:a1:89:0f:a0:30:43:73:6f:0c:b6
If this information was correct, user space tools could expect queues 0
to 7 to receive twice more traffic than queues 8 to 15
After patch :
lpaa24:~# ethtool -L eth1 rx 24
lpaa24:~# ethtool -x eth1
RX flow hash indirection table for eth1 with 24 RX ring(s):
0: 0 1 2 3 4 5 6 7
8: 8 9 10 11 12 13 14 15
RSS hash key:
da:7b:09:60:f1:ac:67:b4:d0:72:d4:ec:a2:e5:80:0a:ad:50:22:1a:f8:f9:66:54:5f:22:45:c3:88:f4:57:82:c1:c1:90:ed:70:cb:40:ce
lpaa24:~# ethtool -X eth1 equal 8
lpaa24:~# ethtool -x eth1
RX flow hash indirection table for eth1 with 24 RX ring(s):
0: 0 1 2 3 4 5 6 7
8: 0 1 2 3 4 5 6 7
RSS hash key:
da:7b:09:60:f1:ac:67:b4:d0:72:d4:ec:a2:e5:80:0a:ad:50:22:1a:f8:f9:66:54:5f:22:45:c3:88:f4:57:82:c1:c1:90:ed:70:cb:40:ce
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Maciej Żenczykowski <maze@google.com>
Cc: Eugenia Emantayev <eugenia@mellanox.com>
Cc: Wei Wang <weiwan@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
I am not sure mlx4_en_netpoll() is doing anything useful right now.
mlx4 has different NAPI structures for RX and TX, and netpoll only wants
to drain TX queues.
Lets schedule NAPI polls on TX, not RX.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJXVJo5AAoJEHm+PkMAQRiGjioH/3H8Q26FP83Bprhrh3y5EYmz
QSWbq5f5XHGVp4sqc45qdozklh11PrMPkNJQPT2HCTgmtzgeTX5EW9TFaQM/Ubrm
NeYnBW0tTcLP2PhfOyOIJOjE3R1oEYIRQ7zzdOZleViYaqAW2g0frYK0l8AY/KAv
z9mJ8s7xieqSzNTyKNfDPIciT/mO2KMbEHu92EiAkjeCfhuVxUO6PR4wLeZb/85H
I/cOFupU1166xeOZUR0lltvPMz8JznOUB0pg2Ma67TqsNGsPPfsmxEPFlALTTJk/
0V/hVyL4BgvO22LXwMoIxnUcwq/F3ZtlDJRhubeX7m5aS9x2Pb5mQ/g1ko0CXJA=
=5hXk
-----END PGP SIGNATURE-----
Backmerge tag 'v4.7-rc2' into drm-next
Daniel has a pull request that relies on stuff in fixes that are in rc2.
drm-intel-next-2016-05-22:
- cmd-parser support for direct reg->reg loads (Ken Graunke)
- better handle DP++ smart dongles (Ville)
- bxt guc fw loading support (Nick Hoathe)
- remove a bunch of struct typedefs from dpll code (Ander)
- tons of small work all over to avoid casting between drm_device and the i915
dev struct (Tvrtko&Chris)
- untangle request retiring from other operations, also fixes reset stat corner
cases (Chris)
- skl atomic watermark support from Matt Roper, yay!
- various wm handling bugfixes from Ville
- big pile of cdclck rework for bxt/skl (Ville)
- CABC (Content Adaptive Brigthness Control) for dsi panels (Jani&Deepak M)
- nonblocking atomic commits for plane-only updates (Maarten Lankhorst)
- bunch of PSR fixes&improvements
- untangle our map/pin/sg_iter code a bit (Dave Gordon)
drm-intel-next-2016-05-08:
- refactor stolen quirks to share code between early quirks and i915 (Joonas)
- refactor gem BO/vma funcstion (Tvrtko&Dave)
- backlight over DPCD support (Yetunde Abedisi)
- more dsi panel sequence support (Jani)
- lots of refactoring around handling iomaps, vma, ring access and related
topics culmulating in removing the duplicated request tracking in the execlist
code (Chris & Tvrtko) includes a small patch for core iomapping code
- hw state readout for bxt dsi (Ramalingam C)
- cdclk cleanups (Ville)
- dedupe chv pll code a bit (Ander)
- enable semaphores on gen8+ for legacy submission, to be able to have a direct
comparison against execlist on the same platform (Chris) Not meant to be used
for anything else but performance tuning
- lvds border bit hw state checker fix (Jani)
- rpm vs. shrinker/oom-notifier fixes (Praveen Paneri)
- l3 tuning (Imre)
- revert mst dp audio, it's totally non-functional and crash-y (Lyude)
- first official dmc for kbl (Rodrigo)
- and tons of small things all over as usual
* 'drm-intel-next' of git://anongit.freedesktop.org/drm-intel: (194 commits)
drm/i915: Revert async unpin and nonblocking atomic commit
drm/i915: Update DRIVER_DATE to 20160522
drm/i915: Inline sg_next() for the optimised SGL iterator
drm/i915: Introduce & use new lightweight SGL iterators
drm/i915: optimise i915_gem_object_map() for small objects
drm/i915: refactor i915_gem_object_pin_map()
drm/i915/psr: Implement PSR2 w/a for gen9
drm/i915/psr: Use ->get_aux_send_ctl functions
drm/i915/psr: Order DP aux transactions correctly
drm/i915/psr: Make idle_frames sensible again
drm/i915/psr: Try to program link training times correctly
drm/i915/userptr: Convert to drm_i915_private
drm/i915: Allow nonblocking update of pageflips.
drm/i915: Check for unpin correctness.
Reapply "drm/i915: Avoid stalling on pending flips for legacy cursor updates"
drm/i915: Make unpin async.
drm/i915: Prepare connectors for nonblocking checks.
drm/i915: Pass atomic states to fbc update functions.
drm/i915: Remove reset_counter from intel_crtc.
drm/i915: Remove queue_flip pointer.
...
We simply can use the standard net_device stats.
We do not need to clear fields that are already 0.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
mlx4 uses a private struct net_device_stats in a vain attempt
to avoid races.
This is buggy because multiple cpus could call mlx4_en_get_stats()
at the same time, so ret_stats can not guarantee stable results.
To fix this, we need to switch to ndo_get_stats64() as this
method provides per-thread storage.
This allows to reduce mlx4_en_priv bloat.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
mlx4_en_clear_stats() clears about everything but few TX ring
fields are missing :
- queue_stopped, wake_queue, tso_packets, xmit_more
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1) mlx4_en_xmit() can increment priv->stats.tx_dropped, but this variable
is overwritten in mlx4_en_DUMP_ETH_STATS().
2) This increment was not SMP safe, as a port might have many TX queues.
Add a per TX ring tx_dropped to fix these issues.
This is u32 as mlx4_en_DUMP_ETH_STATS() will add a 32bit field.
So lets avoid bugs with SNMP agents having to cope with partial
overwraps. (One of these agents being bond_fold_stats())
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Willem de Bruijn <willemb@google.com>
Cc: Eugenia Emantayev <eugenia@mellanox.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
