Switch the vport counters to use the new stats group API.
Signed-off-by: Kamal Heib <kamalh@mellanox.com>
Reviewed-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Switch the Q counters to use the new stats group API.
Signed-off-by: Kamal Heib <kamalh@mellanox.com>
Reviewed-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Currently the mlx5e driver has multiple groups of stats, each group is
used for different purposes and it may depend on hardware capabilities
or not. The problem with the current implementation is that there is no
clear API to create a new group of stats.
This change define a new API to create a group of stats and simplifies
the way of handling them by defining a new struct "mlx5e_stats_grp" which
have the following three function pointers:
- get_num_stats() - return the number of counters in the group.
- fill_strings() - fill counters strings within the group.
- fill_stats() - fill counters values within the group.
The above function pointers are used within the ethtool callbaks while
calling "ethtool -S" from userspace. This change also switch the SW
group to use the new API.
Signed-off-by: Kamal Heib <kamalh@mellanox.com>
Reviewed-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Several conflicts here.
NFP driver bug fix adding nfp_netdev_is_nfp_repr() check to
nfp_fl_output() needed some adjustments because the code block is in
an else block now.
Parallel additions to net/pkt_cls.h and net/sch_generic.h
A bug fix in __tcp_retransmit_skb() conflicted with some of
the rbtree changes in net-next.
The tc action RCU callback fixes in 'net' had some overlap with some
of the recent tcf_block reworking.
Signed-off-by: David S. Miller <davem@davemloft.net>
In preparation for unconditionally passing the struct timer_list pointer to
all timer callbacks, switch to using the new timer_setup() and from_timer()
to pass the timer pointer explicitly.
Cc: Saeed Mahameed <saeedm@mellanox.com>
Cc: Matan Barak <matanb@mellanox.com>
Cc: Leon Romanovsky <leonro@mellanox.com>
Cc: netdev@vger.kernel.org
Cc: linux-rdma@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Replace recurring magic number in PPCNT register with a define.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change the HW stats cache to be local. Rename it for better clarity.
It holds the results of the last result of HW stats that are being read
periodically, in order to have answer for stats request immediately.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Previously, tc with ets type and zero bandwidth is not accepted
by driver. This behavior does not follow the IEEE802.1qaz spec.
If there are tcs with ets type and zero bandwidth, these tcs are
assigned to the lowest priority tc_group #0. We equally distribute
100% bw of the tc_group #0 to these zero bandwidth ets tcs.
Also, the non zero bandwidth ets tcs are assigned to tc_group #1.
If there is no zero bandwidth ets tc, the non zero bandwidth ets tcs
are assigned to tc_group #0.
Fixes: cdcf11212b ("net/mlx5e: Validate BW weight values of ETS")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Currently, the encap action offload is handled in the actions parse
function and not in mlx5e_tc_add_fdb_flow() where we deal with all
the other aspects of offloading actions (vlan, modify header) and
the rule itself.
When the neigh update code (mlx5e_tc_encap_flows_add()) recreates the
encap entry and offloads the related flows, we wrongly call again into
mlx5e_tc_add_fdb_flow(), this for itself would cause us to handle
again the offloading of vlans and header re-write which puts things
in non consistent state and step on freed memory (e.g the modify
header parse buffer which is already freed).
Since on error, mlx5e_tc_add_fdb_flow() detaches and may release the
encap entry, it causes a corruption at the neigh update code which goes
over the list of flows associated with this encap entry, or double free
when the tc flow is later deleted by user-space.
When neigh update (mlx5e_tc_encap_flows_del()) unoffloads the flows related
to an encap entry which is now invalid, we do a partial repeat of the eswitch
flow removal code which is wrong too.
To fix things up we do the following:
(1) handle the encap action offload in the eswitch flow add function
mlx5e_tc_add_fdb_flow() as done for the other actions and the rule itself.
(2) modify the neigh update code (mlx5e_tc_encap_flows_add/del) to only
deal with the encap entry and rules delete/add and not with any of
the other offloaded actions.
Fixes: 232c001398 ('net/mlx5e: Add support to neighbour update flow')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
mlx5_ib_add is called during mlx5_pci_resume after a pci error.
Before mlx5_ib_add completes, there are multiple events which trigger
function mlx5_ib_event. This cause kernel panic because mlx5_ib_event
accesses unitialized resources.
The fix is to extend Erez Shitrit's patch <97834eba7c19>
("net/mlx5: Delay events till ib registration ends") to cover
the pci resume code path.
Trace:
mlx5_core 0001:01:00.6: mlx5_pci_resume was called
mlx5_core 0001:01:00.6: firmware version: 16.20.1011
mlx5_core 0001:01:00.6: mlx5_attach_interface:164:(pid 779):
mlx5_ib_event:2996:(pid 34777): warning: event on port 1
mlx5_ib_event:2996:(pid 34782): warning: event on port 1
Unable to handle kernel paging request for data at address 0x0001c104
Faulting instruction address: 0xd000000008f411fc
Oops: Kernel access of bad area, sig: 11 [#1]
...
...
Call Trace:
[c000000fff77bb70] [d000000008f4119c] mlx5_ib_event+0x64/0x470 [mlx5_ib] (unreliable)
[c000000fff77bc60] [d000000008e67130] mlx5_core_event+0xb8/0x210 [mlx5_core]
[c000000fff77bd10] [d000000008e4bd00] mlx5_eq_int+0x528/0x860[mlx5_core]
Fixes: 97834eba7c ("net/mlx5: Delay events till ib registration ends")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
spin_lock/unlock of health->wq_lock should be IRQ safe.
It was changed to spin_lock_irqsave since adding commit 0179720d6b
("net/mlx5: Introduce trigger_health_work function") which uses
spin_lock from asynchronous event (IRQ) context.
Thus, all spin_lock/unlock of health->wq_lock should have been moved
to IRQ safe mode.
However, one occurrence on new code using this lock missed that
change, resulting in possible deadlock:
kernel: Possible unsafe locking scenario:
kernel: CPU0
kernel: ----
kernel: lock(&(&health->wq_lock)->rlock);
kernel: <Interrupt>
kernel: lock(&(&health->wq_lock)->rlock);
kernel: #012 *** DEADLOCK ***
Fixes: 2a0165a034 ("net/mlx5: Cancel delayed recovery work when unloading the driver")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Please do not apply this to mainline directly, instead please re-run the
coccinelle script shown below and apply its output.
For several reasons, it is desirable to use {READ,WRITE}_ONCE() in
preference to ACCESS_ONCE(), and new code is expected to use one of the
former. So far, there's been no reason to change most existing uses of
ACCESS_ONCE(), as these aren't harmful, and changing them results in
churn.
However, for some features, the read/write distinction is critical to
correct operation. To distinguish these cases, separate read/write
accessors must be used. This patch migrates (most) remaining
ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following
coccinelle script:
----
// Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and
// WRITE_ONCE()
// $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch
virtual patch
@ depends on patch @
expression E1, E2;
@@
- ACCESS_ONCE(E1) = E2
+ WRITE_ONCE(E1, E2)
@ depends on patch @
expression E;
@@
- ACCESS_ONCE(E)
+ READ_ONCE(E)
----
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: davem@davemloft.net
Cc: linux-arch@vger.kernel.org
Cc: mpe@ellerman.id.au
Cc: shuah@kernel.org
Cc: snitzer@redhat.com
Cc: thor.thayer@linux.intel.com
Cc: tj@kernel.org
Cc: viro@zeniv.linux.org.uk
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Make the spectrum_mr_tcam.c include the spectrum_mr_tcam.h header file.
Cleans up sparse warning:
symbol 'mlxsw_sp_mr_tcam_ops' was not declared. Should it be static?
Fixes: 0e14c7777a ("mlxsw: spectrum: Add the multicast routing hardware logic")
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The function is only used internally in spectrum_mr.c and is not declared
in the header file, thus make it static.
Cleans up sparse warning:
symbol 'mlxsw_sp_mr_dev_vif_lookup' was not declared. Should it be static?
Fixes: c011ec1bbf ("mlxsw: spectrum: Add the multicast routing offloading logic")
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix various endianness issues in comparisons and assignments. The fix is
entirely cosmetic as all the values fixed are endianness-agnostic.
Cleans up sparse warnings:
spectrum_mr.c:156:49: warning: restricted __be32 degrades to integer
spectrum_mr.c:206:26: warning: restricted __be32 degrades to integer
spectrum_mr.c:212:31: warning: incorrect type in assignment (different
base types)
spectrum_mr.c:212:31: expected restricted __be32 [usertype] addr4
spectrum_mr.c:212:31: got unsigned int
spectrum_mr.c:214:32: warning: incorrect type in assignment (different
base types)
spectrum_mr.c:214:32: expected restricted __be32 [usertype] addr4
spectrum_mr.c:214:32: got unsigned int
spectrum_mr.c:461:16: warning: restricted __be32 degrades to integer
spectrum_mr.c:461:49: warning: restricted __be32 degrades to integer
Fixes: c011ec1bbf ("mlxsw: spectrum: Add the multicast routing offloading logic")
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
During the dump the per netlink packet entry counter should be zeroed out
when new packet is created.
Fixes: 190d38a52a ("mlxsw: spectrum_dpipe: Add support for adjacency table dump")
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Reported-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The KVD linear is currently partitioned into two partitions. One for
single entries and another for groups of 32 entries.
Add another partition consisting of groups of 512 entries which will
allow us to more accurately represent the nexthop weights in non-equal
cost multi-path routing.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The memory region where adjacency entries (nexthops) are stored is
called the KVD linear and is configured during initialization with a
size of 64K.
Extend this area with 32K more entries, that will be partitioned into 64
groups of 0.5K entries, thereby allowing us to support weighted nexthops
with high accuracy.
Change the ratio between both types of hash entries, so as to prevent
reduction in the number of double hash entries, which are used for IPv6
neighbours and routes with a prefix length greater than 64.
Note that the user will be able to control all these sizes once the
devlink resource manager is introduced.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Up until now the driver assumed all the nexthops have an equal weight
and wrote each to a single adjacency entry.
This patch takes the `weight` parameter into account and populates the
adjacency group according to the relative weight of each nexthop.
Specifically, the weights of all the nexthops that should be offloaded
are first normalized and then used to calculate the upper adjacency
index of each nexthop. This is done according to the hash-threshold
algorithm used by the kernel for IPv4 multi-path routing.
Adjacency groups are currently limited to 32 entries which limits the
weights that can be used, but follow-up patches will introduce groups of
512 entries.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The device has certain restrictions regarding the size of an adjacency
group.
Have the router determine the size of the adjacency group according to
available KVDL allocation sizes and these restrictions.
This was not needed until now since only allocations of up 32 entries
were supported and these are all valid sizes for an adjacency group.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As the first step towards non-equal-cost multi-path support, store each
nexthop's weight.
For IPv6 nexthops always set the weight to 1, as it only supports ECMP.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The current KVDL allocation API allows the user to specify the requested
number of entries, but the user has no way of knowing how many entries
were actually allocated.
This works because existing users (e.g., router) request the exact
number they end up using. With the introduction of large adjacency
groups, this will change, as the router will have the ability to choose
from several allocation sizes, where larger allocations provide higher
accuracy with respect to requested weights and better resilience against
nexthop failures.
One option is to have the router try several allocations of descending
size until one succeeds, but a better way is to simply allow it to query
the actual allocation size and then size its request accordingly.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The KVD linear (KVDL) allocator currently consists of a very large
bitmap that reflects the KVDL's usage. The boundaries of each partition
as well as their allocation size are represented using defines.
This representation requires us to patch all the functions that act on a
partition whenever the partitioning scheme is changed. In addition, it
does not enable the dynamic configuration of the KVDL using the
up-coming resource manager.
Add objects to represent these partitions as well as the accompanying
code that acts on them to perform allocations and de-allocations.
In the following patches, this will allow us to easily add another
partition as well as new operations to act on these partitions.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The adjacency group size is part of the match on the adjacency group and
should therefore be exposed using dpipe.
When non-equal-cost multi-path support will be introduced, the group's
size will help users understand the exact number of adjacency entries
each nexthop occupies, as a nexthop will no longer correspond to a
single entry.
The output for a multi-path route with two nexthops, one with weight 255
and the second 1 will be:
Example:
$ devlink dpipe table dump pci/0000:01:00.0 name mlxsw_adj
pci/0000:01:00.0:
index 0
match_value:
type field_exact header mlxsw_meta field adj_index value 65536
type field_exact header mlxsw_meta field adj_size value 512
type field_exact header mlxsw_meta field adj_hash_index value 0
action_value:
type field_modify header ethernet field destination mac value e4:1d:2d:a5:f3:64
type field_modify header mlxsw_meta field erif_port mapping ifindex mapping_value 3 value 1
index 1
match_value:
type field_exact header mlxsw_meta field adj_index value 65536
type field_exact header mlxsw_meta field adj_size value 512
type field_exact header mlxsw_meta field adj_hash_index value 510
action_value:
type field_modify header ethernet field destination mac value e4:1d:2d:a5:f3:65
type field_modify header mlxsw_meta field erif_port mapping ifindex mapping_value 4 value 2
Thus, the first nexthop occupies 510 adjacency entries and the second 2,
which leads to a ratio of 255 to 1.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There were quite a few overlapping sets of changes here.
Daniel's bug fix for off-by-ones in the new BPF branch instructions,
along with the added allowances for "data_end > ptr + x" forms
collided with the metadata additions.
Along with those three changes came veritifer test cases, which in
their final form I tried to group together properly. If I had just
trimmed GIT's conflict tags as-is, this would have split up the
meta tests unnecessarily.
In the socketmap code, a set of preemption disabling changes
overlapped with the rename of bpf_compute_data_end() to
bpf_compute_data_pointers().
Changes were made to the mv88e6060.c driver set addr method
which got removed in net-next.
The hyperv transport socket layer had a locking change in 'net'
which overlapped with a change of socket state macro usage
in 'net-next'.
Signed-off-by: David S. Miller <davem@davemloft.net>
atomic_t variables are currently used to implement reference
counters with the following properties:
- counter is initialized to 1 using atomic_set()
- a resource is freed upon counter reaching zero
- once counter reaches zero, its further
increments aren't allowed
- counter schema uses basic atomic operations
(set, inc, inc_not_zero, dec_and_test, etc.)
Such atomic variables should be converted to a newly provided
refcount_t type and API that prevents accidental counter overflows
and underflows. This is important since overflows and underflows
can lead to use-after-free situation and be exploitable.
The variable fs_node.refcount is used as pure reference counter.
Convert it to refcount_t and fix up the operations.
Suggested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: David Windsor <dwindsor@gmail.com>
Reviewed-by: Hans Liljestrand <ishkamiel@gmail.com>
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
atomic_t variables are currently used to implement reference
counters with the following properties:
- counter is initialized to 1 using atomic_set()
- a resource is freed upon counter reaching zero
- once counter reaches zero, its further
increments aren't allowed
- counter schema uses basic atomic operations
(set, inc, inc_not_zero, dec_and_test, etc.)
Such atomic variables should be converted to a newly provided
refcount_t type and API that prevents accidental counter overflows
and underflows. This is important since overflows and underflows
can lead to use-after-free situation and be exploitable.
The variable mlx5_cq.refcount is used as pure reference counter.
Convert it to refcount_t and fix up the operations.
Suggested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: David Windsor <dwindsor@gmail.com>
Reviewed-by: Hans Liljestrand <ishkamiel@gmail.com>
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
atomic_t variables are currently used to implement reference
counters with the following properties:
- counter is initialized to 1 using atomic_set()
- a resource is freed upon counter reaching zero
- once counter reaches zero, its further
increments aren't allowed
- counter schema uses basic atomic operations
(set, inc, inc_not_zero, dec_and_test, etc.)
Such atomic variables should be converted to a newly provided
refcount_t type and API that prevents accidental counter overflows
and underflows. This is important since overflows and underflows
can lead to use-after-free situation and be exploitable.
The variable mlx4_srq.refcount is used as pure reference counter.
Convert it to refcount_t and fix up the operations.
Suggested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: David Windsor <dwindsor@gmail.com>
Reviewed-by: Hans Liljestrand <ishkamiel@gmail.com>
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
atomic_t variables are currently used to implement reference
counters with the following properties:
- counter is initialized to 1 using atomic_set()
- a resource is freed upon counter reaching zero
- once counter reaches zero, its further
increments aren't allowed
- counter schema uses basic atomic operations
(set, inc, inc_not_zero, dec_and_test, etc.)
Such atomic variables should be converted to a newly provided
refcount_t type and API that prevents accidental counter overflows
and underflows. This is important since overflows and underflows
can lead to use-after-free situation and be exploitable.
The variable mlx4_qp.refcount is used as pure reference counter.
Convert it to refcount_t and fix up the operations.
Suggested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: David Windsor <dwindsor@gmail.com>
Reviewed-by: Hans Liljestrand <ishkamiel@gmail.com>
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
atomic_t variables are currently used to implement reference
counters with the following properties:
- counter is initialized to 1 using atomic_set()
- a resource is freed upon counter reaching zero
- once counter reaches zero, its further
increments aren't allowed
- counter schema uses basic atomic operations
(set, inc, inc_not_zero, dec_and_test, etc.)
Such atomic variables should be converted to a newly provided
refcount_t type and API that prevents accidental counter overflows
and underflows. This is important since overflows and underflows
can lead to use-after-free situation and be exploitable.
The variable mlx4_cq.refcount is used as pure reference counter.
Convert it to refcount_t and fix up the operations.
Suggested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: David Windsor <dwindsor@gmail.com>
Reviewed-by: Hans Liljestrand <ishkamiel@gmail.com>
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Spectrum tunnels do not default to ttl of "inherit" like the Linux ones
do. Configure TIGCR on router init so that the TTL of tunnel packets is
copied from the overlay packets.
Fixes: ee954d1a91 ("mlxsw: spectrum_router: Support GRE tunnels")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The TIGCR register is used for setting up the IPinIP Tunnel
configuration.
Fixes: ee954d1a91 ("mlxsw: spectrum_router: Support GRE tunnels")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
All drivers are converted to use block callbacks for TC_SETUP_CLS*.
So it is now safe to remove the calls to ndo_setup_tc from cls_*
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Benefit from the newly introduced block callback infrastructure and
convert ndo_setup_tc calls for flower offloads to block callbacks.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Benefit from the newly introduced block callback infrastructure and
convert ndo_setup_tc calls for flower offloads to block callbacks.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Benefit from the newly introduced block callback infrastructure and
convert ndo_setup_tc calls for matchall and flower offloads to block
callbacks.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use container_of to convert the generic fib_notifier_info into
the event specific data structure.
Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add extack argument down to mlxsw_sp_rif_create and mlxsw_sp_vr_create
to set an error message on RIF or VR overflow. Now on overflow of
either resource the user gets an informative message as opposed to
failing with EBUSY.
Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for inetaddr_validator and inet6addr_validator. The
notifiers provide a means for validating ipv4 and ipv6 addresses
before the addresses are installed and on failure the error
is propagated back to the user.
Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/infiniband/hw/cxgb4/cm.c
drivers/infiniband/hw/qib/qib_driver.c
drivers/infiniband/hw/qib/qib_mad.c
There were minor fixups needed in these files. Just minor context diffs
due to patches from independent sources touching the same basic area.
Signed-off-by: Doug Ledford <dledford@redhat.com>
The early for-next branch was based on v4.14-rc2, while the shared pull
request I got from Mellanox used a v4.14-rc4 base. I'm making the
branch that was the shared Mellanox pull request the new for-next branch
and merging the early for-next branch into it.
Signed-off-by: Doug Ledford <dledford@redhat.com>
When an EMAD is transmitted, a timeout work item is scheduled with a
delay of 200ms, so that another EMAD will be retried until a maximum of
five retries.
In certain situations, it's possible for the function waiting on the
EMAD to be associated with a work item that is queued on the same
workqueue (`mlxsw_core`) as the timeout work item. This results in
flushing a work item on the same workqueue.
According to commit e159489baa ("workqueue: relax lockdep annotation
on flush_work()") the above may lead to a deadlock in case the workqueue
has only one worker active or if the system in under memory pressure and
the rescue worker is in use. The latter explains the very rare and
random nature of the lockdep splats we have been seeing:
[ 52.730240] ============================================
[ 52.736179] WARNING: possible recursive locking detected
[ 52.742119] 4.14.0-rc3jiri+ #4 Not tainted
[ 52.746697] --------------------------------------------
[ 52.752635] kworker/1:3/599 is trying to acquire lock:
[ 52.758378] (mlxsw_core_driver_name){+.+.}, at: [<ffffffff811c4fa4>] flush_work+0x3a4/0x5e0
[ 52.767837]
but task is already holding lock:
[ 52.774360] (mlxsw_core_driver_name){+.+.}, at: [<ffffffff811c65c4>] process_one_work+0x7d4/0x12f0
[ 52.784495]
other info that might help us debug this:
[ 52.791794] Possible unsafe locking scenario:
[ 52.798413] CPU0
[ 52.801144] ----
[ 52.803875] lock(mlxsw_core_driver_name);
[ 52.808556] lock(mlxsw_core_driver_name);
[ 52.813236]
*** DEADLOCK ***
[ 52.819857] May be due to missing lock nesting notation
[ 52.827450] 3 locks held by kworker/1:3/599:
[ 52.832221] #0: (mlxsw_core_driver_name){+.+.}, at: [<ffffffff811c65c4>] process_one_work+0x7d4/0x12f0
[ 52.842846] #1: ((&(&bridge->fdb_notify.dw)->work)){+.+.}, at: [<ffffffff811c65c4>] process_one_work+0x7d4/0x12f0
[ 52.854537] #2: (rtnl_mutex){+.+.}, at: [<ffffffff822ad8e7>] rtnl_lock+0x17/0x20
[ 52.863021]
stack backtrace:
[ 52.867890] CPU: 1 PID: 599 Comm: kworker/1:3 Not tainted 4.14.0-rc3jiri+ #4
[ 52.875773] Hardware name: Mellanox Technologies Ltd. "MSN2100-CB2F"/"SA001017", BIOS 5.6.5 06/07/2016
[ 52.886267] Workqueue: mlxsw_core mlxsw_sp_fdb_notify_work [mlxsw_spectrum]
[ 52.894060] Call Trace:
[ 52.909122] __lock_acquire+0xf6f/0x2a10
[ 53.025412] lock_acquire+0x158/0x440
[ 53.047557] flush_work+0x3c4/0x5e0
[ 53.087571] __cancel_work_timer+0x3ca/0x5e0
[ 53.177051] cancel_delayed_work_sync+0x13/0x20
[ 53.182142] mlxsw_reg_trans_bulk_wait+0x12d/0x7a0 [mlxsw_core]
[ 53.194571] mlxsw_core_reg_access+0x586/0x990 [mlxsw_core]
[ 53.225365] mlxsw_reg_query+0x10/0x20 [mlxsw_core]
[ 53.230882] mlxsw_sp_fdb_notify_work+0x2a3/0x9d0 [mlxsw_spectrum]
[ 53.237801] process_one_work+0x8f1/0x12f0
[ 53.321804] worker_thread+0x1fd/0x10c0
[ 53.435158] kthread+0x28e/0x370
[ 53.448703] ret_from_fork+0x2a/0x40
[ 53.453017] mlxsw_spectrum 0000:01:00.0: EMAD retries (2/5) (tid=bf4549b100000774)
[ 53.453119] mlxsw_spectrum 0000:01:00.0: EMAD retries (5/5) (tid=bf4549b100000770)
[ 53.453132] mlxsw_spectrum 0000:01:00.0: EMAD reg access failed (tid=bf4549b100000770,reg_id=200b(sfn),type=query,status=0(operation performed))
[ 53.453143] mlxsw_spectrum 0000:01:00.0: Failed to get FDB notifications
Fix this by creating another workqueue for EMAD timeouts, thereby
preventing the situation of a work item trying to flush a work item
queued on the same workqueue.
Fixes: caf7297e7a ("mlxsw: core: Introduce support for asynchronous EMAD register access")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Formerly, IPIP entries were created lazily by next hops that referenced
an offloadable IP-in-IP netdevice. However now that they are created
eagerly as a reaction to events on such netdevices, the reference
counting is useless. Hence drop it.
The routes whose next hops reference an offloaded IP-in-IP netdevice
actually linger around a bit after their device is unregistered.
However, mlxsw_sp_ipip_entry_destroy() also destroys the backing
loopback, and mlxsw_sp_rif_destroy() transitively (via
mlxsw_sp_nexthop_rif_gone_sync()) calls mlxsw_sp_nexthop_ipip_fini(),
which unlinks the IPIP entry from a next hop. Thus no dangling pointers
are left behind for the brief window after netdevice is gone, but routes
not yet.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
IPIP entries are created as soon as an offloadable device is created.
That means that when such a device is later moved to a different VRF,
the loopback device that backs the tunnel is wrong.
Thus when an offloadable encapsulating netdevice moves from one VRF to
another, make sure that the loopback is updated as necessary.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Current code for offloading IP-in-IP tunneling assumes that there is no
decap without encap. But that's never true for IPv6 overlays, and is not
true for IPv4 ones either, if net.ipv4.conf.*.rp_filter is unset.
To support decap-only tunnels, an IPIP entry is now created as soon as
an offloadable tunneling device is created. When that netdevice is up'd,
a decap route is looked up and possibly offloaded. Thus decap is not
handled implicitly as part of mlxsw_sp_ipip_entry_get() call anymore,
but needs to be done explicitly after the get, if desired.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
So far, all netdevice notifications that the driver cared about were
related to its own ports, and mlxsw_sp could be retrieved from the
netdevice's private data. For IP-in-IP offloading however, the driver
cares about events on foreign netdevices, and getting at mlxsw_sp or
router data structures from the handler is inconvenient.
Therefore move the netdevice notifier blocks from global scope to struct
mlxsw_sp to allow retrieval from the notifier block pointer itself.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Saeed Mahameed says:
====================
mlx5-updates-2017-10-11: IPoIB Multi Pkey support
This series provides the support for IPoIB Multi Pkey.
InfiniBand Pkeys are the equivalent of Ethernet vlans.
Currently IPoIB device driver supports only default Pkey and IPoIB Pkey child
interfaces are not supported with IPoIB offloads mode, this series will add
the support for that by allowing creating mlx5 multiple IPoIB netdevices with
a non-default Pkey.
mlx5 IPoIB Pkey child interface is smaller version of mlx5i IPoIB interfaces and shares
most of its resources with the parent IPoIB interface, namely RX steering and ring
queue resources.
The only mlx5 resources a child Pkey interface will be creating are the TX rings,
since they should be assigned to a specific Pkey.
mlx5i Pkey netdev is implemented via new mlx5e netdev profile implemented in
mlx5/core/ipoib/ipoib_vlan.c.
The series starts with a refactoring of mlx5e PTP and mlx5 clock implementation
to move the code to be part of mlx5 core rather than mlx5e netdevice, in order to
make mlx5 clock and PTP registration part of the core to be shared with mlx5e
master Ethernet netdev/IPoIB parent netdev and mlx5_ib in the near future.
Add the support for attaching multiple underlay QPs for the different Pkeys
in mlx5 core RX steering.
Add Pkey index to rdma_netdev to add the ability to set PKEY index to lower
IPoIB offload netdev.
Use hash-table to map between DQPN (Destination QP number) to child netdev
for the IPoIB parent netdev to forward RX packets to the corresponding
child Pkey netdev, since the RX rings are shared.
The reset of the series adds the ipoib child Pkey: mlx5e netdev profile,
netdev nods implementation and minimal set of ethtool callbacks.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Resources such as FT, QPN HT and mdev resources should be allocated
only by parent netdev. Shared resources are allocated and freed by the
parent interface since the parent is always present and created
before the IPoIB PKEY sub-interface.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Similar to VLAN interfaces child interfaces have limited ethtool
support. In current code the main limitation that does not
allow child interface ethtool configuration is due to shared
resources which are managed by the parent.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Child interface ndos will be called to support child interface
specific behaviour.
ndo_init flow:
-Acquire shared QPN to net-device HT from parent
-Continue with the same flow as parent interface
ndo_open flow:
-Initialize child underlay QP and connect to shared FT
-Create child send TIS
-Open child send channels
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Child interface profile will be called to support child interface
specific behaviour. The child code is sparse compared to the parent
since the RX channels are shared between the interfaces.
Creating a septate profile for child and parent will make a smother
code with a better ability for future expansion.
The profile stuct is exposed to the parent using a getter function.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
This change is needed for PKEY support, since the RQs are shared
between the child interface and the parent. The parent is responsible
for NAPI and the precessing of RX completions. Using the dqpn in the
completion descriptor we set the corresponding child IPoIB netdevice
on the SKB.
The mapping between the dqpn and the netdevice is done using a HT,
each mlx5 IPoIB interface registers its mapping on creation.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Added a function to set PKEY index to IPoIB device driver using the
already present set_id function. PKEY index is attached to the QP
during state modification.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Previous support allowed connecting only a single QPN to the FT.
Now using a linked list multiple QPNs can be attached to the same FT.
Supporting attaching multiple underlay QPs is required for PKEY
support in which child and parent share the same FT.
The actual attaching/detaching FW commands will be called inside the
function symmetrically.
This change requires a change in IPoIB open and close functions, the
attaching/detaching to/from the FT is done each time we open/close.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
During the creation of the underlay QP the PKEY index is unknown, the
PKEY index is known only when calling ndo_open.
PKEY index attached to the QP during state modification.
Splitting the functions will also make the code symmetric and more
readable. This split is also required for later PKEY support to be
called with the PKEY index during ndo_open.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
PTP code is moved to core section of mlx5 driver in order to share
it between ethernet and infiniband. This movement involves the following
changes:
- Change mlx5e_ prefix to be mlx5_
- Add clock structs to Core
- Add clock object to mlx5_core_dev
- Call Init/Uninit clock from core init/cleanup
- Rename mlx5e_tstamp to be mlx5_clock
Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Eitan Rabin <rabin@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
en_clock.c renamed clock.c and moved to lib/ as first step
towards relocating code to core part of the driver to allow
sharing between Ethernet and Infiniband.
Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Eitan Rabin <rabin@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
In XDP_TX, some fields in tx_info and tx_desc are constants across
all entries of the different XDP_TX rings.
Assign values to these fields on ring creation time, rather than in
data-path.
Patchset performance tests:
Tested on ConnectX3Pro, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
Single queue no-RSS optimization ON.
XDP_TX packet rate:
------------------------------
Before | After | Gain |
13.7 Mpps | 14.0 Mpps | %2.2 |
------------------------------
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Function mlx4_en_tx_write_desc() is not optimized to use of XDP xmit.
Use the relevant parts inline instead.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The struct net_device parameter was passed only to extract
struct mlx4_en_priv out of it.
Here we pass the priv parameter directly.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The only user of cls_flower->egress_dev is mlx5. So do the conversion
there alongside with the code originating the call in cls_flower
function fl_hw_replace_filter to the newly introduced egress device
callback infrastucture.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove limitation of netif_get_num_default_rss_queues()
from logic of RX rings default number.
Signed-off-by: Inbar Karmy <inbark@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Limit the number of RX rings by the number of cores
in the system.
Signed-off-by: Inbar Karmy <inbark@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Limit the number of TX rings per UP by the number of cores
in the system.
Signed-off-by: Inbar Karmy <inbark@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In TX data-path, we intentionally do not byte-swap, as documented
in code and in the cited commit log.
This fixes sparse warning:
en_tx.c:720:23: warning: incorrect type in argument 1 (different base types)
en_tx.c:720:23: expected unsigned int [unsigned] [usertype] <noident>
en_tx.c:720:23: got restricted __be32 [usertype] doorbell_qpn
Fixes: 492f5add4b ("net/mlx4_en: Doorbell is byteswapped in Little Endian archs")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix the following SPARSE warning, in MLX4_GET() macro:
drivers/net/ethernet/mellanox/mlx4/fw.c:233:9: warning: cast to restricted __be64
Fixes: 17d5ceb6e4 ("net/mlx4_core: Fix unaligned accesses")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Should take care of the endianness before assigning to params2 field.
Fixes: 53f33ae295 ("net/mlx4_core: Port aggregation upper layer interface")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Support the SWITCHDEV_ATTR_ID_BRIDGE_MROUTER port attribute switchdev
notification.
To do that, add the mrouter flag to struct mlxsw_sp_bridge_device, which
indicates whether the bridge device was set to be mrouter port. This field
is set when:
- A new bridge is created, where the value is taken from the kernel
bridge value.
- A switchdev SWITCHDEV_ATTR_ID_BRIDGE_MROUTER notification is sent.
In addition, change the bridge MID entries to include the router port when
the bridge device is configured to be mrouter port. The MID entries are
updated in the following cases:
- When a new MID entry is created, update the router port according to the
bridge mrouter state.
- When a SWITCHDEV_ATTR_ID_BRIDGE_MROUTER notification is sent, update all
the bridge's MID entries.
This is aligned with the case where a bridge slave is configured to be
mrouter port.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In Spectrum, MDB entries point to MID entries, that indicate which ports a
packet should be forwarded to. Add the support in creating MID entries that
forward the packet to the Spectrum router port.
This will be later used to handle the bridge mrouter port switchdev
notifications.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In Spectrum hardware, the router port is a virtual port that is the gateway
to the routing mechanism. Hence, in order for a packet to be L3 forwarded,
it must first be L2 forwarded to the router port inside the hardware.
Further patches in this patchset are going to introduce support in bridge
device used as an mrouter port. In this case, the router port index will be
needed in order to update the MDB entries to include the router port. Thus,
export the mlxsw_sp_router_port function, which returns the index of the
Spectrum router port.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In preparation for unconditionally passing the struct timer_list pointer to
all timer callbacks, switch to using the new timer_setup() and from_timer()
to pass the timer pointer explicitly.
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: netdev@vger.kernel.org
Cc: linux-rdma@vger.kernel.org
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Saeed Mahameed says:
====================
Mellanox, mlx5 updates 2017-10-06
This series includes some shared code updates for kernel 4.15 to both
net-next and rdma-next trees.
The series includes mlx5 low level flow steering updates and optimizations
to support firmware command parallelism for flow steering requests from
Maor Gottlieb and two other small fixes from Matan and Maor.
One fix from Matan adds error handling for when the destination
list of the flow steering rule is full.
Maor introduced a patch to avoid NULL pointer dereference on steering cleanup.
Then Some refactoring patches needed by the series for code sharing purposes.
and split the Flow Table Entry (FTE) and Flow Group (FG) creation code to two parts:
1) Object allocation - allocate the steering node and initialize
its resources.
2) The firmware command execution.
This change will give us the ability to take write lock on the
parent node (e.g. FG for FTE creating) only on the software data struct allocation
and creation part of the procedure where the synchronization is really required,
and will allow us to execute multiple firmware commands simultaneously and overcome the
firmware bottleneck.
Refactor the locking scheme of the mlx5 core flow steering as follows:
1) Replace the mutex lock with readers-writers semaphore and take
the write lock only when necessary (e.g. allocating a new flow
table entry index or adding a node to the parent's children list).
When we try to find a suitable child in the parent's children list
(e.g. search for flow group with the same match_criteria of the rule)
then we only take the read lock.
2) Add versioning mechanism - each steering entity (FT, FG, FTE, DST)
will have an incremental version. The version is increased when the
entity is changed (e.g. when a new FTE was added to FG - the FG's
version is increased).
Versioning is used in order to determine if the last traverse of an
entity's children is valid or a rescan under write lock is required.
Last patch adds FGs and FTEs memory pool, It is useful because these objects
are not small and could be allocated/deallocated many times.
This support improves the insertion rate of steering rules
from ~5k/sec to ~40k/sec.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The code that actually takes care of bridge offload introduces a few
more non-trivial constraints with regards to bridge enslavements.
Propagate extack there to indicate the reason.
$ ip link add link enp1s0np1 name enp1s0np1.10 type vlan id 10
$ ip link add link enp1s0np1 name enp1s0np1.20 type vlan id 20
$ ip link add name br0 type bridge
$ ip link set dev enp1s0np1.10 master br0
$ ip link set dev enp1s0np1.20 master br0
Error: spectrum: Can not bridge VLAN uppers of the same port.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Similar to physical ports, enslavement of VLAN devices can also fail.
Use extack to indicate why the enslavement failed.
$ ip link add link enp1s0np1 name enp1s0np1.10 type vlan id 10
$ ip link add name bond0 type bond mode 802.3ad
$ ip link set dev enp1s0np1.10 master bond0
Error: spectrum: VLAN devices only support bridge and VRF uppers.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit fc922bb0dd ("mlxsw: spectrum_router: Use one LPM tree for
all virtual routers") I increased the scale of supported VRFs by having
all of them share the same LPM tree.
In order to avoid look-ups for prefix lengths that don't exist, each
route removal would trigger an aggregation across all the active virtual
routers to see which prefix lengths are in use and which aren't and
structure the tree accordingly.
With the way the data structures are currently laid out, this is a very
expensive operation. When preformed repeatedly - due to the invocation
of the abort mechanism - and with enough VRFs, this can result in a hung
task.
For now, avoid this optimization until it can be properly re-added in
net-next.
Fixes: fc922bb0dd ("mlxsw: spectrum_router: Use one LPM tree for all virtual routers")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: David Ahern <dsa@cumulusnetworks.com>
Tested-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
mlxsw fails device enslavement for a number of reasons. Use the extack
facility to return an error message to the user stating why the enslave
is failing.
Messages are prefixed with "spectrum" so users know it is a constraint
imposed by the hardware driver. For example:
$ ip li add br0.11 link br0 type vlan id 11
$ ip li set swp11 master br0
Error: spectrum: Enslaving a port to a device that already has an upper device is not supported.
Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Tested-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We accidentally return success if the kmalloc_array() call fails.
Fixes: 0e14c7777a ("mlxsw: spectrum: Add the multicast routing hardware logic")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Yotam Gigi <yotamg@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
mlxsw_afa_block_create() doesn't return error pointers, it returns NULL
on error.
Fixes: 0e14c7777a ("mlxsw: spectrum: Add the multicast routing hardware logic")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Yotam Gigi <yotamg@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add the support of trap-and-forward route action in the multicast routing
offloading logic. A route will be set to trap-and-forward action if one (or
more) of its output interfaces is not offload-able, i.e. does not have a
valid Spectrum RIF.
This way, a route with mixed output VIFs list, which contains both
offload-able and un-offload-able devices can go through partial offloading
in hardware, and the rest will be done in the kernel ipmr module.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In addition to the current multicast route actions, which include trap
route action and a forward route action, add the trap-and-forward multicast
route action, and implement it in the multicast routing hardware logic.
To implement that, add a trap-and-forward ACL action as the last action in
the route flexible action set. The used trap is the ACL2 trap, which marks
the packets with offload_mr_forward_mark, to prevent the packet from being
forwarded again by the kernel.
Note: At that stage the offloading logic does not support trap-and-forward
multicast routes. This patch adds the support only in the hardware logic.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When a multicast route is configured with trap-and-forward action, the
packets should be marked with skb->offload_mr_fwd_mark, in order to prevent
the packets from being forwarded again by the kernel ipmr module.
Due to this, it is not possible to use the already existing multicast trap
(MLXSW_TRAP_ID_ACL1) as the packet should be marked differently. Add the
MLXSW_TRAP_ID_ACL2 which is for trap-and-forward multicast routes, and set
the offload_mr_fwd_mark skb field in its handler.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use trap/discard flex action to implement trap and forward. The action will
later be used for multicast routing, as the multicast routing mechanism is
done using ACL flexible actions in Spectrum hardware. Using that action, it
will be possible to implement a trap-and-forward route.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When considering whether to set RTNH_F_OFFLOAD flag on an IPv6 route,
mlxsw_sp_fib6_entry_offload_set() looks up the mlxsw_sp_nexthop
corresponding to a given route, and decides based on whether the next
hop's offloaded flag was set. When looking for the matching next hop, it
also takes into account the device of the route, which must match next
hop's RIF.
IPIP next hops however hitherto didn't set the RIF. As a result, IPv6
routes forwarding traffic to IP-in-IP netdevices are never marked as
offloaded, even when they actually are.
Thus track RIF of IPIP next hops the same way as that of ETHERNET next
hops.
Fixes: 8f28a30976 ("mlxsw: spectrum_router: Support IPv6 overlay encap")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When creating a new RIF, bumping RIF count of the containing VR is the
last thing to be done. Symmetrically, when destroying a RIF, RIF count
is first dropped and only then the rest of the cleanup proceeds.
That's a problem for loopback RIFs. Those hold two VR references: one
for overlay and one for underlay. mlxsw_sp_rif_destroy() releases the
overlay one, and the deconfigure() callback the underlay one. But if
both overlay and underlay are the same, and if there are no other
artifacts holding the VR alive, this put actually destroys the VR. Later
on, when mlxsw_sp_rif_destroy() calls mlxsw_sp_vr_put() for the same VR,
the VR will already have been released and the kernel crashes with NULL
pointer dereference.
The underlying problem is that the RIF under destruction ends up
referencing the overlay VR much longer than it claims: all the way until
the call to mlxsw_sp_vr_put(). So line up the reference counting
properly to reflect this. Make corresponding changes in
mlxsw_sp_rif_create() as well for symmetry.
Fixes: 6ddb7426a7 ("mlxsw: spectrum_router: Introduce loopback RIFs")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the unlikely event that mfc->mfc_un.res.ttls[i] is 255 for all
values of i from 0 to MAXIVS-1, the err is not set at all and hence
has a garbage value on the error return at the end of the function,
so initialize it to 0. Also, the error return check on err and goto
to err: inside the for loop makes it impossible for err to be zero
at the end of the for loop, so we can remove the redundant err check
at the end of the loop.
Detected by CoverityScan CID#1457207 ("Unitialized scalar value")
Fixes: c011ec1bbf ("mlxsw: spectrum: Add the multicast routing offloading logic")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Yotam Gigi <yotamg@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of calculating the offloads counters, count them explicitly.
The calculations done for these counters would result in bugs in some
cases, for example:
When running TCP traffic over a VXLAN tunnel with TSO enabled the following
counters would increase:
tx_csum_partial: 1,333,284
tx_csum_partial_inner: 29,286
tx4_csum_partial_inner: 384
tx7_csum_partial_inner: 8
tx9_csum_partial_inner: 34
tx10_csum_partial_inner: 26,807
tx11_csum_partial_inner: 287
tx12_csum_partial_inner: 27
tx16_csum_partial_inner: 6
tx25_csum_partial_inner: 1,733
Seems like tx_csum_partial increased out of nowhere.
The issue is in the following calculation in mlx5e_update_sw_counters:
s->tx_csum_partial = s->tx_packets - tx_offload_none - s->tx_csum_partial_inner;
While tx_packets increases by the number of GSO segments for each SKB,
tx_csum_partial_inner will only increase by one, resulting in wrong
tx_csum_partial counter.
Fixes: bfe6d8d1d4 ("net/mlx5e: Reorganize ethtool statistics")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Toggling of C-tag VLAN filter should not affect the "any S-tag" steering rule.
Fixes: 8a271746a2 ("net/mlx5e: Receive s-tagged packets in promiscuous mode")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Use the correct formatting for netdev features.
Fixes: 0e405443e8 ("net/mlx5e: Improve set features ndo resiliency")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Encap entries cached by the driver could be invalidated due to
tunnel destination neighbour state changes.
When attempting to offload a flow that uses a cached encap entry,
we must check the entry validity and defer the offloading
if the entry exists but not valid.
When EAGAIN is returned, the flow offloading to hardware takes place
by the neigh update code when the tunnel destination neighbour
becomes connected.
Fixes: 232c001398 ("net/mlx5e: Add support to neighbour update flow")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
When offloading header re-write, the HW may need to adjust checksums along
the packet. For IP traffic, and a case where we are asked to modify fields in
the IP header, current HW supports that only for TCP and UDP. Enforce it, in
this case fail the offloading attempt for non TCP/UDP packets.
Fixes: d7e75a325c ('net/mlx5e: Add offloading of E-Switch TC pedit (header re-write) actions')
Fixes: 2f4fe4cab0 ('net/mlx5e: Add offloading of NIC TC pedit (header re-write) actions')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
In case the neighbour for the tunnel destination isn't valid,
we send a neighbour update request but we free the encap
header buffer. This is wrong, because we still need it for
allocating a HW encap entry once the neighbour is available.
Fix that by skipping freeing it if we wait for neighbour.
Fixes: 232c001398 ('net/mlx5e: Add support to neighbour update flow')
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Added check for the maximal number of flow counters attached
to rule (FTE).
Fixes: bd5251dbf1 ('net/mlx5_core: Introduce flow steering destination of type counter')
Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Currently, FPGA capability is located in (mdev)->caps.hca_cur,
change the location to be (mdev)->caps.fpga,
since hca_cur is reserved for HCA device capabilities.
Fixes: e29341fb3a ("net/mlx5: FPGA, Add basic support for Innova")
Signed-off-by: Inbar Karmy <inbark@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
When cleaning rdma netdevice we need to save the mdev pointer
because priv is released when we release netdev.
This bug was found using the kernel address sanitizer (KASAN).
use-after-free in mlx5_rdma_netdev_free+0xe3/0x100 [mlx5_core]
Fixes: 48935bbb7a ("net/mlx5e: IPoIB, Add netdevice profile skeleton")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Make the Spectrum router logic not ignore the RTNL_FAMILY_IPMR FIB
notifications.
Past commits added the IPMR VIF and MFC add/del notifications via the
fib_notifier chain. In addition, a code for handling these notifications in
the Spectrum router logic was added. Make the Spectrum router logic not
ignore these notifications and forward the requests to the Spectrum
multicast router offloading logic.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Due to the fact that multicast routes hold the minimum MTU of all the
egress RIFs and trap packets that don't meet it, notify the mulitcast
router code on RIF MTU changes.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add functionality for calling the multicast routing offloading logic upon
MFC and VIF add and delete notifications. In addition, call the multicast
routing upon RIF addition and deletion events.
As the multicast routing offload logic may sleep, the actual calls are done
in a deferred work. To ensure the MFC object is not freed in that interval,
a reference is held to it. In case of a failure, the abort mechanism is
used, which ejects all the routes from the hardware and triggers the
traffic to flow through the kernel.
Note: At that stage, the FIB notifications are still ignored, and will be
enabled in a further patch.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, the mlxsw Spectrum driver offloads only either the RT_TABLE_MAIN
FIB table or the VRF tables, so the RT_TABLE_LOCAL table is squashed to the
RT_TABLE_MAIN table to allow local routes to be offloaded too.
By default, multicast MFC routes which are not assigned to any user
requested table are put in the RT_TABLE_DEFAULT table.
Due to the fact that offloading multicast MFC routes support in Spectrum
router logic is going to be introduced soon, squash the default table to
MAIN too.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Implement the multicast routing hardware API introduced in previous patch
for the specific spectrum hardware.
The spectrum hardware multicast routes are written using the RMFT2 register
and point to an ACL flexible action set. The actions used for multicast
routes are:
- Counter action, which allows counting bytes and packets on multicast
routes.
- Multicast route action, which provide RPF check and do the actual packet
duplication to a list of RIFs.
- Trap action, in the case the route action specified by the called is
trap.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add the multicast router offloading logic, which is in charge of handling
the VIF and MFC notifications and translating it to the hardware logic API.
The offloading logic has to overcome several obstacles in order to safely
comply with the kernel multicast router user API:
- It must keep track of the mapping between VIFs to netdevices. The user
can add an MFC cache entry pointing to a VIF, delete the VIF and add
re-add it with a different netdevice. The offloading logic has to handle
this in order to be compatible with the kernel logic.
- It must keep track of the mapping between netdevices to spectrum RIFs,
as the current hardware implementation assume having a RIF for every
port in a multicast router.
- It must handle routes pointing to pimreg device to be trapped to the
kernel, as the packet should be delivered to userspace.
- It must handle routes pointing tunnel VIFs. The current implementation
does not support multicast forwarding to tunnels, thus routes that point
to a tunnel should be trapped to the kernel.
- It must be aware of proxy multicast routes, which include both (*,*)
routes and duplicate routes. Currently proxy routes are not offloaded
and trigger the abort mechanism: removal of all routes from hardware and
triggering the traffic to go through the kernel.
The multicast routing offloading logic also updates the counters of the
offloaded MFC routes in a periodic work.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Propagate error instead of doing WARN_ON right away.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for controlling nexthop counters via dpipe.
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for adjacency table dump.
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for setting counters on nexthops based on dpipe's adjacency
table counter status. This patch also adds the ability for getting the
counter value, which will be used by the dpipe adjacency table dump
implementation in the next patches.
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to add the ability for setting counters on nexthops the RATR
register should be extended.
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add initial support for router adjacency table. The table does lookup
based on the nexthop-group index and the local nexthop offset. After
locating the nexthop entry it sets the destination MAC address and the
egress RIF.
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is done as a preparation before introducing the ability to dump the
adjacency table via dpipe, and to count the table size. The current table
implementation avoids tunnel entries, thus a helper for checking if
the nexthop group contains tunnel entries is also provided. The mlxsw's
nexthop representative struct stays private to the router module.
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use list_is_last helper to check for last neighbor.
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Keep nexthops in a linked list for easy access.
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds field for mlxsw's meta header which will be used to
describe the match/action behavior of the adjacency table.
The fields are:
1. Adj_index - The global index of the nexthop group in the adjacency
table.
2. Adj_hash_index - Local index offset which is based on packets hash
mod the nexthop group size.
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix indentation in mlxsw_meta header's description.
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This work enables generic transfer of metadata from XDP into skb. The
basic idea is that we can make use of the fact that the resulting skb
must be linear and already comes with a larger headroom for supporting
bpf_xdp_adjust_head(), which mangles xdp->data. Here, we base our work
on a similar principle and introduce a small helper bpf_xdp_adjust_meta()
for adjusting a new pointer called xdp->data_meta. Thus, the packet has
a flexible and programmable room for meta data, followed by the actual
packet data. struct xdp_buff is therefore laid out that we first point
to data_hard_start, then data_meta directly prepended to data followed
by data_end marking the end of packet. bpf_xdp_adjust_head() takes into
account whether we have meta data already prepended and if so, memmove()s
this along with the given offset provided there's enough room.
xdp->data_meta is optional and programs are not required to use it. The
rationale is that when we process the packet in XDP (e.g. as DoS filter),
we can push further meta data along with it for the XDP_PASS case, and
give the guarantee that a clsact ingress BPF program on the same device
can pick this up for further post-processing. Since we work with skb
there, we can also set skb->mark, skb->priority or other skb meta data
out of BPF, thus having this scratch space generic and programmable
allows for more flexibility than defining a direct 1:1 transfer of
potentially new XDP members into skb (it's also more efficient as we
don't need to initialize/handle each of such new members). The facility
also works together with GRO aggregation. The scratch space at the head
of the packet can be multiple of 4 byte up to 32 byte large. Drivers not
yet supporting xdp->data_meta can simply be set up with xdp->data_meta
as xdp->data + 1 as bpf_xdp_adjust_meta() will detect this and bail out,
such that the subsequent match against xdp->data for later access is
guaranteed to fail.
The verifier treats xdp->data_meta/xdp->data the same way as we treat
xdp->data/xdp->data_end pointer comparisons. The requirement for doing
the compare against xdp->data is that it hasn't been modified from it's
original address we got from ctx access. It may have a range marking
already from prior successful xdp->data/xdp->data_end pointer comparisons
though.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add memory pool allocation for flow groups and flow
table entry.
It is useful because these objects are not small and could
be allocated/deallocated many times.
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Allocation of new FTE is a massive operation, part of
it could be done without taking the flow group write lock.
Split the FTE allocation to two functions of actions which
need to be under lock and action which don't have.
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Most of the time spent on adding new flow steering rule
is executing the firmware command.
The most common action is adding a new flow steering entry.
In order to enhance the update rate we parallelize the
commands by doing the following:
1) Replace the mutex lock with readers-writers semaphore and take
the write lock only when necessary (e.g. allocating a new flow
table entry index or adding a node to the parent's children list).
When we try to find a suitable child in the parent's children list
(e.g. search for flow group with the same match_criteria of the rule)
then we only take the read lock.
2) Add versioning mechanism - each steering entity (FT, FG, FTE, DST)
will have an incremental version. The version is increased when the
entity is changed (e.g. when a new FTE was added to FG - the FG's
version is increased).
Versioning is used in order to determine if the last traverse of an
entity's children is valid or a rescan under write lock is required.
This support improves the insertion rate of steering rules
from ~5k/sec to ~40k/sec.
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Currently, steering object is protected by mutex lock, replace
the mutex lock with reader/writer semaphore .
In this patch we still use only write semaphore. In downstream
patches we will switch part of the write locks to read locks.
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Split the creation code to two parts:
1) Object allocation - allocate the steering node and initialize
its resources.
2) The firmware command execution.
Adding active flag to each node - this flag indicates if the
object exists in the hardware or not, if not we don't free
the hardware resource in error flow.
This change will give us the ability to take write lock on the
parent node (e.g. FG for FTE creationg) only on the first part.
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Refactor the code and export the build of the matched flow groups
list to separate function.
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
When new flow table entry is added, we search for free index
in the flow group and not in the flow table, therefore we can move
the allocator from flow table to flow group.
In downstream patches it will enable us to lock smaller part
of the steering tree.
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
On cleanup, when the node is the last child of parent then it calls to
tree_put_node on the parent, if the parent's reference count
is decremented to 0 (for e.g. when deleting last destination of FTE)
then we free the parent as well and vice versa. In such a case
we will try to free the parent node again.
Increment the parent reference count before cleaning it's children
will prevent implicit release of the parent object.
Fixes: 0da2d66666 ('net/mlx5: Properly remove all steering objects')
signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Currently, when a flow steering rule is added, we look for a FTE with
an identical value. If we find a match, we try to merge the required
destinations with the existing ones. In a case where the existing
destination list is full, the code should return an error to its
consumer. However, the current code just tries to create another FTE.
Fixing that by returning an error in this special scenario.
Fixes: f478be79a22e ("net/mlx5: Add hash table for flow groups in flow table")
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
IS_ERR() already implies unlikely(), so it can be omitted.
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use setup_timer function instead of initializing timer with the
function and data fields.
Signed-off-by: Allen Pais <allen.lkml@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use setup_timer function instead of initializing timer with the
function and data fields.
Signed-off-by: Allen Pais <allen.lkml@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When a mrouter is registered or leaves a mid, don't update the HW.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In mdb flush the port is being removed from all the mids it is registered
to. But if the port is mrouter, all the mids floods to it.
This patch remove mrouter ports from mids it is not registered to in the
mdb flush.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Whenever a port starts / stops being mrouter, update all the mdb entries
in the HW to flood / stop flooding mc packets there.
The change should happen only if the port is not in the mid. (If it is,
the mid should flood mc packets to this port anyway)
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When mc is enabled, whenever a mc packet doesn't hit any mdb entry it is
being flood to the ports marked as mrouters. However, all mc packets should
be flooded to them even if they match an entry in the mdb.
This patch adds the mrouter ports to every mdb entry that is being written
to the HW.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When a port is being removed from a bridge, flush the bridge mdb to remove
the mids of that port.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When multicast is disabled, flood mc packets only to port that are marked
BR_MCAST_FLOOD (instead to all).
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use the generic mc flood function to decide whether to flood mc to a port
when mc is being enabled / disabled.
Move this function in the file to avoid forward declaration.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove all the mdb entries from the HW when mc is being disabled and
re-write them when it is being enabled.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Don't write multicast related data to the HW when mc is disabled.
Also, don't allocate mid id to new mids (so the remove function could know
that they weren't wrote to the HW)
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Break mid deletion into two function, so it will be possible in the future
to delete a mid entry for other reasons then switchdev command (like port
deletion).
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Attach mid getting and releasing mid id to the HW write / remove, and add
a flag to indicate whether the mid is in the HW. It is done because mid id
is also HW index to this mid.
This change allows adding in the following patches the ability to have a
mid in the mdb cache but not in the HW. It will be useful for being able
to disable the multicast.
It means that the mdb is being written / delete to the HW in the mid
allocation / removing function, not after them.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Break the smid write function into two, one that cleans the ports that
might be still written there and one that changes an exiting mid entry.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of saving all the mids in the same list, save them per vlan
device. This change allows a more efficient mid find.
Also, in the next patches, there will be added a lot of loops over all the
mids in bridge device for multicast disable, mrouter change and ndb flush.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since there is a bitmap for the ports registered to each mid, there is no
need for a ref count, since it will always be the number of set bits in
this bitmap. Any check of the ref count was replaced with checking if the
bitmap is empty.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a bitmap of ports to the mid struct to hold the ports that are
registered to this mid.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change the naming of mc_router to mrouter to keep consistency.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add three new traps needed for multicast routing:
- PIM: Trap for PIM protocol control packets.
- RPF: Trap for packets that fail the RPF check on a specific hardware
route entry.
- MULTICAST: Generic trap for multicast. It is used for routes that trap
the packets to the CPU.
The RPF and MULTICAST traps have rate limiters as these traps may have
line-rate of packets trapped. The PIM trap has a rate limiter similarly to
other L3 control protocols. The rate limiters are implemented by adding
three new trap groups for the newly introduced traps.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The mlxsw_sp_rif struct, defined as private struct in spectrum_router.c
will be used in the multicast router source file. Due to the fact that the
dev field will be needed by the multicast router logic, add an access
function to it.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
