Vivien Didelot [Wed, 6 Apr 2016 15:55:04 +0000 (11:55 -0400)]
net: dsa: make the FDB add function return void
The switchdev design implies that a software error should not happen in
the commit phase since it must have been previously reported in the
prepare phase. If an hardware error occurs during the commit phase,
there is nothing switchdev can do about it.
The DSA layer separates port_fdb_prepare and port_fdb_add for simplicity
and convenience. If an hardware error occurs during the commit phase,
there is no need to report it outside the DSA driver itself.
Make the DSA port_fdb_add routine return void for explicitness.
Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Vivien Didelot [Wed, 6 Apr 2016 15:55:03 +0000 (11:55 -0400)]
net: dsa: make the STP state function return void
The DSA layer doesn't care about the return code of the port_stp_update
routine, so make it void in the layer and the DSA drivers.
Replace the useless dsa_slave_stp_update function with a
dsa_slave_stp_state function used to reply to the switchdev
SWITCHDEV_ATTR_ID_PORT_STP_STATE attribute.
In the meantime, rename port_stp_update to port_stp_state_set to
explicit the state change.
Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Vivien Didelot [Wed, 6 Apr 2016 15:06:20 +0000 (11:06 -0400)]
net: dsa: document missing functions
Add description for the missing port_vlan_prepare, port_fdb_prepare,
port_fdb_dump functions in the DSA documentation.
Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 8 Apr 2016 20:42:31 +0000 (16:42 -0400)]
Merge tag 'mac80211-next-for-davem-2016-04-06' of git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next
Johannes Berg says:
====================
For the 4.7 cycle, we have a number of changes:
* Bob's mesh mode rhashtable conversion, this includes
the rhashtable API change for allocation flags
* BSSID scan, connect() command reassoc support (Jouni)
* fast (optimised data only) and support for RSS in mac80211 (myself)
* various smaller changes
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann [Tue, 5 Apr 2016 20:33:17 +0000 (22:33 +0200)]
bpf, verifier: further improve search pruning
The verifier needs to go through every path of the program in
order to check that it terminates safely, which can be quite a
lot of instructions that need to be processed f.e. in cases with
more branchy programs. With search pruning from f1bca824dabb ("bpf:
add search pruning optimization to verifier") the search space can
already be reduced significantly when the verifier detects that
a previously walked path with same register and stack contents
terminated already (see verifier's states_equal()), so the search
can skip walking those states.
When working with larger programs of > ~2000 (out of max 4096)
insns, we found that the current limit of 32k instructions is easily
hit. For example, a case we ran into is that the search space cannot
be pruned due to branches at the beginning of the program that make
use of certain stack space slots (STACK_MISC), which are never used
in the remaining program (STACK_INVALID). Therefore, the verifier
needs to walk paths for the slots in STACK_INVALID state, but also
all remaining paths with a stack structure, where the slots are in
STACK_MISC, which can nearly double the search space needed. After
various experiments, we find that a limit of 64k processed insns is
a more reasonable choice when dealing with larger programs in practice.
This still allows to reject extreme crafted cases that can have a
much higher complexity (f.e. > ~300k) within the 4096 insns limit
due to search pruning not being able to take effect.
Furthermore, we found that a lot of states can be pruned after a
call instruction, f.e. we were able to reduce the search state by
~35% in some cases with this heuristic, trade-off is to keep a bit
more states in env->explored_states. Usually, call instructions
have a number of preceding register assignments and/or stack stores,
where search pruning has a better chance to suceed in states_equal()
test. The current code marks the branch targets with STATE_LIST_MARK
in case of conditional jumps, and the next (t + 1) instruction in
case of unconditional jump so that f.e. a backjump will walk it. We
also did experiments with using t + insns[t].off + 1 as a marker in
the unconditionally jump case instead of t + 1 with the rationale
that these two branches of execution that converge after the label
might have more potential of pruning. We found that it was a bit
better, but not necessarily significantly better than the current
state, perhaps also due to clang not generating back jumps often.
Hence, we left that as is for now.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
devlink: share user_ptr pointer for both devlink and devlink_port
Ptr to devlink structure can be easily obtained from
devlink_port->devlink. So share user_ptr[0] pointer for both and leave
user_ptr[1] free for other users.
Signed-off-by: Jiri Pirko <jiri@mellanox.com> Reviewed-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
mlxsw: Move devlink port registration into common core code
Remove devlink port reg/unreg from spectrum and switchx2 code and rather
do the common work in core. That also ensures code separation where
devlink is only used in core.c.
Signed-off-by: Jiri Pirko <jiri@mellanox.com> Reviewed-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
devlink: remove implicit type set in port register
As we rely on caller zeroing or correctly set the struct before the call,
this implicit type set is either no-op (DEVLINK_PORT_TYPE_NOTSET is 0)
or it rewrites wanted value. So remove this.
Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 8 Apr 2016 19:26:07 +0000 (15:26 -0400)]
Merge branch 'nfp-mtu-buffer-reconfig'
Jakub Kicinski says:
====================
MTU/buffer reconfig changes
I re-discussed MPLS/MTU internally, dropped it from the patch 1,
re-tested everything, found out I forgot about debugfs pointers,
fixed that as well.
v5:
- don't reserve space in RX buffers for MPLS label stack
(patch 1);
- fix debugfs pointers to ring structures (patch 5).
v4:
- cut down on unrelated patches;
- don't "close" the device on error path.
--- v4 cover letter
Previous series included some not entirely related patches,
this one is cut down. Main issue I'm trying to solve here
is that .ndo_change_mtu() in nfpvf driver is doing full
close/open to reallocate buffers - which if open fails
can result in device being basically closed even though
the interface is started. As suggested by you I try to move
towards a paradigm where the resources are allocated first
and the MTU change is only done once I'm certain (almost)
nothing can fail. Almost because I need to communicate
with FW and that can always time out.
Patch 1 fixes small issue. Next 10 patches reorganize things
so that I can easily allocate new rings and sets of buffers
while the device is running. Patches 13 and 15 reshape the
.ndo_change_mtu() and ethtool's ring-resize operation into
desired form.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Thu, 7 Apr 2016 18:39:46 +0000 (19:39 +0100)]
nfp: convert .ndo_change_mtu() to prepare/commit paradigm
When changing MTU on running device first allocate new rings
and buffers and once it succeeds proceed with changing MTU.
Allocation of new rings is not really necessary for this
operation - it's done to keep the code simple and because
size of the extra ring memory is quite small compared to
the size of buffers.
Operation can still fail midway through if FW communication
times out. In that case we retry with old MTU (rings).
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Thu, 7 Apr 2016 18:39:45 +0000 (19:39 +0100)]
nfp: propagate list buffer size in struct rx_ring
Free list buffer size needs to be propagated to few functions
as a parameter and added to struct nfp_net_rx_ring since soon
some of the functions will be reused to manage rings with
buffers of size different than nn->fl_bufsz.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Thu, 7 Apr 2016 18:39:44 +0000 (19:39 +0100)]
nfp: sync ring state during FW reconfiguration
FW reconfiguration in .ndo_open()/.ndo_stop() should reset/
restore queue state. Since we need IRQs to be disabled when
filling rings on RX path we have to move disable_irq() from
.ndo_open() all the way up to IRQ allocation.
nfp_net_start_vec() becomes trivial now so it's inlined.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Thu, 7 Apr 2016 18:39:42 +0000 (19:39 +0100)]
nfp: move filling ring information to FW config
nfp_net_[rt]x_ring_{alloc,free} should only allocate or free
ring resources without touching the device. Move setting
parameters in the BAR to separate functions. This will make
it possible to reuse alloc/free functions to allocate new
rings while the device is running.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Thu, 7 Apr 2016 18:39:41 +0000 (19:39 +0100)]
nfp: preallocate RX buffers early in .ndo_open
We want the .ndo_open() to have following structure:
- allocate resources;
- configure HW/FW;
- enable the device from stack perspective.
Therefore filling RX rings needs to be moved to the beginning
of .ndo_open().
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Thu, 7 Apr 2016 18:39:40 +0000 (19:39 +0100)]
nfp: reorganize initial filling of RX rings
Separate allocation of buffers from giving them to FW,
thanks to this it will be possible to move allocation
earlier on .ndo_open() path and reuse buffers during
runtime reconfiguration.
Similar to TX side clean up the spill of functionality
from flush to freeing the ring. Unlike on TX side,
RX ring reset does not free buffers from the ring.
Ring reset means only that FW pointers are zeroed and
buffers on the ring must be placed in [0, cnt - 1)
positions.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Thu, 7 Apr 2016 18:39:39 +0000 (19:39 +0100)]
nfp: cleanup tx ring flush and rename to reset
Since we never used flush without freeing the ring later
the functionality of the two operations is mixed.
Rename flush to ring reset and move there all the things
which have to be done after FW ring state is cleared.
While at it do some clean-ups.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Thu, 7 Apr 2016 18:39:37 +0000 (19:39 +0100)]
nfp: make *x_ring_init do all the init
nfp_net_[rt]x_ring_init functions used to be called from probe
path only and some of their functionality was spilled to the
call site. In order to reuse them for ring reconfiguration
we need them to do all the init.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Thu, 7 Apr 2016 18:39:36 +0000 (19:39 +0100)]
nfp: break up nfp_net_{alloc|free}_rings
nfp_net_{alloc|free}_rings contained strange mix of allocations
and vector initialization. Remove it, declare vector init as
a separate function and handle allocations explicitly.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Thu, 7 Apr 2016 18:39:35 +0000 (19:39 +0100)]
nfp: move link state interrupt request/free calls
We need to be able to disable the link state interrupt when
the device is brought down. We used to just free the IRQ
at the beginning of .ndo_stop(). As we now move towards
more ordered .ndo_open()/.ndo_stop() paths LSC allocation
should be placed in the "allocate resource" section.
Since the IRQ can't be freed early in .ndo_stop(), it is
disabled instead.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Thu, 7 Apr 2016 18:39:34 +0000 (19:39 +0100)]
nfp: correct RX buffer length calculation
When calculating the RX buffer length we need to account
for up to 2 VLAN tags. Rounding up to 1k is an relic of
a distant past and can be removed. While at it also remove
trivial print statement.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 8 Apr 2016 16:13:30 +0000 (12:13 -0400)]
Merge branch '10GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says:
====================
10GbE Intel Wired LAN Driver Updates 2016-04-07
This series contains updates to ixgbe and ixgbevf.
This entire series (except for one patch from Alex) comes from Mark and
is mainly to add support for our new MAC (x550em_a).
So let's get Alex's patch out of the way first before we cover Mark's
many changes. Alex does his enable bulk free in transmit cleanup for
ixgbe and ixgbevf, like his has done for all of our other drivers.
First Mark cleans up registers that were not being used, so do some
house cleaning. Then to avoid casting lan_id and func fields, just
make them u8 since they only hold small values anyways. Found and
fixed an issue where on read operations it could be possible to
modify locations beyond the length passed in, so change the check
to round up in the same way. Cleaned up the interface for issuing
firmware commands to use a void * instead of a u32 * which eliminates
a number of casts. Added support for the new MAC and provided method
pointers and use them to access IOSF-attached devices, since the
new MAC will also need a new access method. Added support for SFPs
with an external retimer and for an SGMII backplane interface.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 8 Apr 2016 01:04:27 +0000 (21:04 -0400)]
Merge branch 'bpf-tracepoints'
Alexei Starovoitov says:
====================
allow bpf attach to tracepoints
Hi Steven, Peter,
v1->v2: addressed Peter's comments:
- fixed wording in patch 1, added ack
- refactored 2nd patch into 3:
2/10 remove unused __perf_addr macro which frees up
an argument in perf_trace_buf_submit
3/10 split perf_trace_buf_prepare into alloc and update parts, so that bpf
programs don't have to pay performance penalty for update of struct trace_entry
which is not going to be accessed by bpf
4/10 actual addition of bpf filter to perf tracepoint handler is now trivial
and bpf prog can be used as proper filter of tracepoints
v1 cover:
last time we discussed bpf+tracepoints it was a year ago [1] and the reason
we didn't proceed with that approach was that bpf would make arguments
arg1, arg2 to trace_xx(arg1, arg2) call to be exposed to bpf program
and that was considered unnecessary extension of abi. Back then I wanted
to avoid the cost of buffer alloc and field assign part in all
of the tracepoints, but looks like when optimized the cost is acceptable.
So this new apporach doesn't expose any new abi to bpf program.
The program is looking at tracepoint fields after they were copied
by perf_trace_xx() and described in /sys/kernel/debug/tracing/events/xxx/format
We made a tool [2] that takes arguments from /sys/.../format and works as:
$ tplist.py -v random:urandom_read
int got_bits;
int pool_left;
int input_left;
Then these fields can be copy-pasted into bpf program like:
struct urandom_read {
__u64 hidden_pad;
int got_bits;
int pool_left;
int input_left;
};
and the program can use it:
SEC("tracepoint/random/urandom_read")
int bpf_prog(struct urandom_read *ctx)
{
return ctx->pool_left > 0 ? 1 : 0;
}
This way the program can access tracepoint fields faster than
equivalent bpf+kprobe program, which is the main goal of these patches.
Patch 1-4 are simple changes in perf core side, please review.
I'd like to take the whole set via net-next tree, since the rest of
the patches might conflict with other bpf work going on in net-next
and we want to avoid cross-tree merge conflicts.
Alternatively we can put patches 1-4 into both tip and net-next.
Patch 9 is an example of access to tracepoint fields from bpf prog.
Patch 10 is a micro benchmark for bpf+kprobe vs bpf+tracepoint.
Note that for actual tracing tools the user doesn't need to
run tplist.py and copy-paste fields manually. The tools do it
automatically. Like argdist tool [3] can be used as:
$ argdist -H 't:block:block_rq_complete():u32:nr_sector'
where 'nr_sector' is name of tracepoint field taken from
/sys/kernel/debug/tracing/events/block/block_rq_complete/format
and appropriate bpf program is generated on the fly.
samples/bpf: add tracepoint vs kprobe performance tests
the first microbenchmark does
fd=open("/proc/self/comm");
for() {
write(fd, "test");
}
and on 4 cpus in parallel:
writes per sec
base (no tracepoints, no kprobes) 930k
with kprobe at __set_task_comm() 420k
with tracepoint at task:task_rename 730k
For kprobe + full bpf program manully fetches oldcomm, newcomm via bpf_probe_read.
For tracepint bpf program does nothing, since arguments are copied by tracepoint.
2nd microbenchmark does:
fd=open("/dev/urandom");
for() {
read(fd, buf);
}
and on 4 cpus in parallel:
reads per sec
base (no tracepoints, no kprobes) 300k
with kprobe at urandom_read() 279k
with tracepoint at random:urandom_read 290k
bpf progs attached to kprobe and tracepoint are noop.
Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
during bpf program loading remember the last byte of ctx access
and at the time of attaching the program to tracepoint check that
the program doesn't access bytes beyond defined in tracepoint fields
This also disallows access to __dynamic_array fields, but can be
relaxed in the future.
Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
perf, bpf: allow bpf programs attach to tracepoints
introduce BPF_PROG_TYPE_TRACEPOINT program type and allow it to be attached
to the perf tracepoint handler, which will copy the arguments into
the per-cpu buffer and pass it to the bpf program as its first argument.
The layout of the fields can be discovered by doing
'cat /sys/kernel/debug/tracing/events/sched/sched_switch/format'
prior to the compilation of the program with exception that first 8 bytes
are reserved and not accessible to the program. This area is used to store
the pointer to 'struct pt_regs' which some of the bpf helpers will use:
+---------+
| 8 bytes | hidden 'struct pt_regs *' (inaccessible to bpf program)
+---------+
| N bytes | static tracepoint fields defined in tracepoint/format (bpf readonly)
+---------+
| dynamic | __dynamic_array bytes of tracepoint (inaccessible to bpf yet)
+---------+
Not that all of the fields are already dumped to user space via perf ring buffer
and broken application access it directly without consulting tracepoint/format.
Same rule applies here: static tracepoint fields should only be accessed
in a format defined in tracepoint/format. The order of fields and
field sizes are not an ABI.
Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: David S. Miller <davem@davemloft.net>
perf: split perf_trace_buf_prepare into alloc and update parts
split allows to move expensive update of 'struct trace_entry' to later phase.
Repurpose unused 1st argument of perf_tp_event() to indicate event type.
While splitting use temp variable 'rctx' instead of '*rctx' to avoid
unnecessary loads done by the compiler due to -fno-strict-aliasing
Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: David S. Miller <davem@davemloft.net>
now all calls to perf_trace_buf_submit() pass 0 as 4th
argument which will be repurposed in the next patch which will
change the meaning of 1st arg of perf_tp_event() to event_type
Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: David S. Miller <davem@davemloft.net>
avoid memset in perf_fetch_caller_regs, since it's the critical path of all tracepoints.
It's called from perf_sw_event_sched, perf_event_task_sched_in and all of perf_trace_##call
with this_cpu_ptr(&__perf_regs[..]) which are zero initialized by perpcu init logic and
subsequent call to perf_arch_fetch_caller_regs initializes the same fields on all archs,
so we can safely drop memset from all of the above cases and move it into
perf_ftrace_function_call that calls it with stack allocated pt_regs.
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Mark Rustad [Fri, 1 Apr 2016 19:18:51 +0000 (12:18 -0700)]
ixgbe: Bump version number
Update ixgbe version number.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Fri, 1 Apr 2016 19:18:35 +0000 (12:18 -0700)]
ixgbe: Add support for SFPs with retimer
Add support for SFPs with an external retimer.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Fri, 1 Apr 2016 19:18:30 +0000 (12:18 -0700)]
ixgbe: Introduce function to control MDIO speed
Move code that controls MDIO speed into a new function because
there will be more MACs that need the control.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Fri, 1 Apr 2016 19:18:25 +0000 (12:18 -0700)]
ixgbe: Read and parse NW_MNG_IF_SEL register
Read the IXGBE_NW_MNG_IF_SEL register and use it to set interface
attributes.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Fri, 1 Apr 2016 19:18:20 +0000 (12:18 -0700)]
ixgbe: Read and set instance id
Read the instance number from EEPROM and save it for later use.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Fri, 1 Apr 2016 19:18:14 +0000 (12:18 -0700)]
ixgbe: Use new methods for PHY access
Now x550em_a devices will use a new method for PHY access that will
get the firmware token for each access.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Fri, 1 Apr 2016 19:18:09 +0000 (12:18 -0700)]
ixgbe: Add support for x550em_a 10G MAC type
Add support for x550em_a 10G MAC type to the ixgbe driver. The new
MAC includes new firmware commands that need to be used to control
PHY and IOSF access, so that support is also added. The interface
supported is a native SFP+ interface.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Fri, 1 Apr 2016 19:18:04 +0000 (12:18 -0700)]
ixgbe: Use method pointer to access IOSF devices
Provide method pointers and use them to access IOSF-attached
devices. A new MAC will introduce a new access method.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Fri, 1 Apr 2016 19:17:59 +0000 (12:17 -0700)]
ixgbe: Add definitions for x550em_a 10G MAC
Add definitions for a x550em_a 10G MAC device with a native SFP
interface.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Mon, 21 Mar 2016 18:21:31 +0000 (11:21 -0700)]
ixgbe: Add support for single-port X550 device
Add support for a single-port X550 device.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Mon, 7 Mar 2016 17:30:09 +0000 (09:30 -0800)]
ixgbe/ixgbevf: Add support for bulk free in Tx cleanup & cleanup boolean logic
This patch enables bulk free in Tx cleanup for ixgbevf and cleans up the
boolean logic in the polling routines for ixgbe and ixgbevf in the hopes of
avoiding any mix-ups similar to what occurred with i40e and i40evf.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Mon, 14 Mar 2016 18:06:02 +0000 (11:06 -0700)]
ixgbe: Take manageability semaphore for firmware commands
We need to take the manageability semaphore when issuing firmware
commands to avoid problems. With this in place, the semaphore is
no longer taken in the ixgbe_set_fw_drv_ver_generic function, since
it will now always be taken by the ixgbe_host_interface_command
function.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Mon, 14 Mar 2016 18:05:57 +0000 (11:05 -0700)]
ixgbe: Clean up interface for firmware commands
Clean up the interface for issuing firmware commands to use a
void * instead of a u32 *. This eliminates a number of casts.
Also clean up ixgbe_host_interface_command in a few other ways,
eliminating comparisons with 0, redundant parens and minor
formatting issues.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Mon, 14 Mar 2016 18:05:51 +0000 (11:05 -0700)]
ixgbe: Correct length check for round up
The function ixgbe_host_interface_command actually uses a multiple
of word sized buffer to do its business, but only checks against
the actual length passed in. This means that on read operations it
could be possible to modify locations beyond the length passed in.
Change the check to round up in the same way, just to avoid any
possible hazard.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Mon, 14 Mar 2016 18:05:46 +0000 (11:05 -0700)]
ixgbe: Change the lan_id and func fields to a u8 to avoid casts
Since the lan_id and func fields only ever hold small values, make
them u8 to avoid casts used to silence warnings.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Mon, 14 Mar 2016 18:05:40 +0000 (11:05 -0700)]
ixgbe: Delete some unused register definitions
I noticed the SRAMREL registers are not referenced for any device,
so delete the definitions.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
I forgot to add inline to lockdep_sock_is_held, so it generated all
kinds of build warnings if not build with lockdep support.
Reported-by: kbuild test robot <fengguang.wu@intel.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Thu, 7 Apr 2016 21:00:14 +0000 (17:00 -0400)]
Merge branch 'tipc-next'
Jon Maloy says:
====================
tipc: some small fixes
When fix a minor buffer leak, and ensure that bearers filter packets
correctly while they are being shut down.
v2: Corrected typos in commit #3, as per feedback from S. Shtylyov
v3: Removed commit #3 from the series. Improved version will be
re-submitted later.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 7 Apr 2016 14:09:14 +0000 (10:09 -0400)]
tipc: stricter filtering of packets in bearer layer
Resetting a bearer/interface, with the consequence of resetting all its
pertaining links, is not an atomic action. This becomes particularly
evident in very large clusters, where a lot of traffic may happen on the
remaining links while we are busy shutting them down. In extreme cases,
we may even see links being re-created and re-established before we are
finished with the job.
To solve this, we now introduce a solution where we temporarily detach
the bearer from the interface when the bearer is reset. This inhibits
all packet reception, while sending still is possible. For the latter,
we use the fact that the device's user pointer now is zero to filter out
which packets can be sent during this situation; i.e., outgoing RESET
messages only. This filtering serves to speed up the neighbors'
detection of the loss event, and saves us from unnecessary probing.
Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 7 Apr 2016 14:09:13 +0000 (10:09 -0400)]
tipc: eliminate buffer leak in bearer layer
When enabling a bearer we create a 'neigbor discoverer' instance by
calling the function tipc_disc_create() before the bearer is actually
registered in the list of enabled bearers. Because of this, the very
first discovery broadcast message, created by the mentioned function,
is lost, since it cannot find any valid bearer to use. Furthermore,
the used send function, tipc_bearer_xmit_skb() does not free the given
buffer when it cannot find a bearer, resulting in the leak of exactly
one send buffer each time a bearer is enabled.
This commit fixes this problem by introducing two changes:
1) Instead of attemting to send the discovery message directly, we let
tipc_disc_create() return the discovery buffer to the calling
function, tipc_enable_bearer(), so that the latter can send it
when the enabling sequence is finished.
2) In tipc_bearer_xmit_skb(), as well as in the two other transmit
functions at the bearer layer, we now free the indicated buffer or
buffer chain when a valid bearer cannot be found.
Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Thu, 7 Apr 2016 20:53:37 +0000 (16:53 -0400)]
Merge branch 'gro-in-udp'
Tom Herbert says:
====================
udp: GRO in UDP sockets
This patch set adds GRO functions (gro_receive and gro_complete) to UDP
sockets and removes udp_offload infrastructure.
Add GRO functions (gro_receive and gro_complete) to UDP sockets. In
udp_gro_receive and udp_gro_complete a socket lookup is done instead of
looking up the port number in udp_offloads. If a socket is found and
there are GRO functions for it then those are called. This feature
allows binding GRO functions to more than just a port number.
Eventually, we will be able to use this technique to allow application
defined GRO for an application protocol by attaching BPF porgrams to UDP
sockets for doing GRO.
In order to implement these functions, we added exported
udp6_lib_lookup_skb and udp4_lib_lookup_skb functions in ipv4/udp.c and
ipv6/udp.c. Also, inet_iif and references to skb_dst() were changed to
check that dst is set in skbuf before derefencing. In the GRO path there
is now a UDP socket lookup performed before dst is set, to the get the
device in that case we simply use skb->dev.
Tested:
Ran various combinations of VXLAN and GUE TCP_STREAM and TCP_RR tests.
Did not see any material regression.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Tom Herbert [Tue, 5 Apr 2016 15:22:51 +0000 (08:22 -0700)]
udp: Add GRO functions to UDP socket
This patch adds GRO functions (gro_receive and gro_complete) to UDP
sockets. udp_gro_receive is changed to perform socket lookup on a
packet. If a socket is found the related GRO functions are called.
This features obsoletes using UDP offload infrastructure for GRO
(udp_offload). This has the advantage of not being limited to provide
offload on a per port basis, GRO is now applied to whatever individual
UDP sockets are bound to. This also allows the possbility of
"application defined GRO"-- that is we can attach something like
a BPF program to a UDP socket to perfrom GRO on an application
layer protocol.
Signed-off-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Tom Herbert [Tue, 5 Apr 2016 15:22:50 +0000 (08:22 -0700)]
udp: Add udp6_lib_lookup_skb and udp4_lib_lookup_skb
Add externally visible functions to lookup a UDP socket by skb. This
will be used for GRO in UDP sockets. These functions also check
if skb->dst is set, and if it is not skb->dev is used to get dev_net.
This allows calling lookup functions before dst has been set on the
skbuff.
Signed-off-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Thu, 7 Apr 2016 20:44:15 +0000 (16:44 -0400)]
Merge branch 'sock-lockdep-tightening'
Hannes Frederic Sowa says:
====================
sock: lockdep tightening
First patch is from Eric Dumazet and improves lockdep accuracy for
socket locks. After that, second patch introduces lockdep_sock_is_held
and uses it. Final patch reverts and reworks the lockdep fix from Daniel
in the filter code, as we now have tighter lockdep support.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
tun: use socket locks for sk_{attach,detatch}_filter
This reverts commit 5a5abb1fa3b05dd ("tun, bpf: fix suspicious RCU usage
in tun_{attach, detach}_filter") and replaces it to use lock_sock around
sk_{attach,detach}_filter. The checks inside filter.c are updated with
lockdep_sock_is_held to check for proper socket locks.
It keeps the code cleaner by ensuring that only one lock governs the
socket filter instead of two independent locks.
Cc: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
net: introduce lockdep_is_held and update various places to use it
The socket is either locked if we hold the slock spin_lock for
lock_sock_fast and unlock_sock_fast or we own the lock (sk_lock.owned
!= 0). Check for this and at the same time improve that the current
thread/cpu is really holding the lock.
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
During release_sock we use callbacks to finish the processing
of outstanding skbs on the socket. We actually are still locked,
sk_locked.owned == 1, but we already told lockdep that the mutex
is released. This could lead to false positives in lockdep for
lockdep_sock_is_held (we don't hold the slock spinlock during processing
the outstanding skbs).
I took over this patch from Eric Dumazet and tested it.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Thu, 7 Apr 2016 05:07:34 +0000 (22:07 -0700)]
tcp/dccp: fix inet_reuseport_add_sock()
David Ahern reported panics in __inet_hash() caused by my recent commit.
The reason is inet_reuseport_add_sock() was still using
sk_nulls_for_each_rcu() instead of sk_for_each_rcu().
SO_REUSEPORT enabled listeners were causing an instant crash.
While chasing this bug, I found that I forgot to clear SOCK_RCU_FREE
flag, as it is inherited from the parent at clone time.
Fixes: 3b24d854cb35 ("tcp/dccp: do not touch listener sk_refcnt under synflood") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: David Ahern <dsa@cumulusnetworks.com> Tested-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Thu, 7 Apr 2016 15:50:30 +0000 (11:50 -0400)]
Merge branch '1GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says:
====================
1GbE Intel Wired LAN Driver Updates 2016-04-06
This series contains updates to e1000, e1000e, igb and Kconfig.
Alex fixes igb where we were casting the MAC address as __beXX and then
passing it into le32_to_cpu, when we could simply cast as __lexx to
maintain consistency since it is already little endian. Then enabled
bulk free in transmit cleanup for igb.
John Holland enables igb to pickup the MAC address from a device tree
blob when CONFIG_OF has been enabled.
Doron Shikmoni fixes a bug in the output of "ethtool -m ethX" where
the data byte appeared duplicated.
Stefan fixes up e1000 and e1000e ethtool offline tests which were calling
dev_close() which causes IFF_UP to be cleared which removes teh interface
routes and some addresses, so use ndo_stop() instead.
Jiri Benc cleans up some old links in the Kconfig for Intel drivers where
we referred to a URL which is no longer valid. I am so glad Jiri has the
time in his day to spend clicking on and testing all the URL links in the
the kernel.
Arika Chen reverts the addition of a 'rtnl_unlock()' which had a unmatched
'rtnl_lock()' call before it.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Thu, 7 Apr 2016 04:06:38 +0000 (00:06 -0400)]
Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says:
====================
40GbE Intel Wired LAN Driver Updates 2016-04-06
This series contains updates to i40e and i40evf.
Deepthi adds a debug message to display the MSIx vector count for hardware
capabilities.
Shannon removed the setting of debug_mask at startup to take care of an
issue where all the device capabilities getting printed when we had not
asked for it. Moved the NVM status out of the admin queue structure,
since it should really stay with the other NVM data structures.
Akeem added the flush routine to the end of the reset flow to avoid
problems in the pass-through routines.
Jesse moves a local variable deeper into the depths of the driver
where the light is low and the context is great. Then cleaned up
the tx_ring argument since it was not making good arguments. Improved
performance by not "checking for FCoE" by re-ordering the FCoE checks.
Anjali adds the support for changing a VF from non-trusted to trusted
and vice-versa.
Mitch adds opcodes and structures to support RSS configuration by PF
driver on behalf of the VF driver. Fixed how the VLAN feature flags
are set.
Kiran added defines for RSS, flow director, flexible payload and IPv6.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit 3eb14ea8d958 ("igb: Fix a deadlock in
igb_sriov_reinit")
It is the same as commit f468adc944ef ("igb: missing rtnl_unlock in
igb_sriov_reinit()")
There is no rtnl_lock() in igb_resume before, rtnl_unlock will cause a
deadlock.
Signed-off-by: Arika Chen <arika.chen@huawei.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The Kconfig for Intel NICs references two different URLs for the "Adapter
& Driver ID Guide". Neither of those two links works. The current URL seems
to be
http://www.intel.com/content/www/us/en/support/network-and-i-o/ethernet-products/000005584.html
but given it's apparently constantly changing, there's no point in having it
in the help text.
Just keep a generic pointer to http://support.intel.com. Hopefully, this one
will have a longer live. It still works, at least.
Furthermore, remove a link to "the latest Intel PRO/100 network driver for
Linux", this has no place in the mainline kernel and the latest Linux driver
it offers is from 2006, anyway.
Signed-off-by: Jiri Benc <jbenc@redhat.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mitch Williams [Fri, 1 Apr 2016 20:34:31 +0000 (13:34 -0700)]
i40evf: properly handle VLAN features
Correctly set the VLAN feature flags after setting the rest of the
netdev flags. And don't set them in hw_features, because these can't be
controlled by the VF driver.
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Shannon Nelson [Fri, 1 Apr 2016 10:56:11 +0000 (03:56 -0700)]
i40e: Move NVM event wait check to NVM code
The logic that checks AQ events for NVM done events is better kept
in nvm.c with the rest of the nvmupdate handling code.
Change-ID: I2ea58980df8ecaa3726b28a37bff3dfcb8df03dc Signed-off-by: Shannon Nelson <shannon.nelson@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mitch Williams [Fri, 1 Apr 2016 10:56:10 +0000 (03:56 -0700)]
i40e: Add RSS configuration to virtual channel
Add opcodes and structures to support RSS configuration by PF driver on
behalf of the VF drivers. This reduces complexity in the VF driver and
allows us to support future hardware designs without modifying the VF
driver.
Change-ID: I8c75765c630eacb71f95967f1109a198542593ac Signed-off-by: Mitch Williams <mitch.a.williams@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Shannon Nelson [Fri, 1 Apr 2016 10:56:09 +0000 (03:56 -0700)]
i40e: Move NVM variable out of AQ struct
The NVM update status info should stay collected together, not
spread across different structs.
Change-ID: Ic16f9e9fd79945d865bb7226184c889884585025 Signed-off-by: Shannon Nelson <shannon.nelson@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Shannon Nelson [Fri, 1 Apr 2016 10:56:08 +0000 (03:56 -0700)]
i40e: Restrict VF poll mode to only single function mode devices
The VFs can request their queues to be set up into polling mode, rather
than interrupt mode, which works well for supporting things like DPDK,
but this should not be available when working in an multi-function
support device.
Change-ID: Id36792e4e7422db8f2033336507211f68f14ff6f Signed-off-by: Shannon Nelson <shannon.nelson@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch adds hook to support changing a VF from not-trusted
to trusted and vice-versa. Fixed the wrappers and function prototype.
Changed the dmesg to reflex the current state better. This patch also
disables turning on/off trusted VF in MFP mode.
Change-ID: Ibcd910935c01f0be1f3fdd6d427230291ee92ebe Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
As it turns out, calling into other files from hot path hurts
performance a lot. In this case the majority of the time we
call "check FCoE" and the packet is *not* FCoE, but this call
was taking 5% of our total cycles spent on receive.
Change-ID: I080552c26e7060bc7b78504dc2763f6f0b3d8c76 Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch moves the HW flush routine to the end of the reset flow,
after the completion of writing to the device VFLR registers- the
benefit is to avoid problems in the passthrough routines.
Change-ID: Ieb56866f21895e6c1fc514b7328c3df79807a57c Signed-off-by: Akeem G Abodunrin <akeem.g.abodunrin@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Shannon Nelson [Fri, 1 Apr 2016 10:56:02 +0000 (03:56 -0700)]
i40e: Leave debug_mask cleared at init
Don't set our internal debug_mask at startup unless we get specific signal
to from the debug module parameter.
This should take care of the issue with all the device capabilities getting
printed even when we hadn't asked for the debug info.
Change-ID: I7fbc6bd8b11ed9b0631ec018ff36015a04100b6c Signed-off-by: Shannon Nelson <shannon.nelson@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Stefan Assmann [Wed, 3 Feb 2016 08:20:51 +0000 (09:20 +0100)]
e1000: call ndo_stop() instead of dev_close() when running offline selftest
Calling dev_close() causes IFF_UP to be cleared which will remove the
interfaces routes and some addresses. That's probably not what the user
intended when running the offline selftest. Besides this does not happen
if the interface is brought down before the test, so the current
behaviour is inconsistent.
Instead call the net_device_ops ndo_stop function directly and avoid
touching IFF_UP at all.
Signed-off-by: Stefan Assmann <sassmann@kpanic.de> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
David S. Miller [Wed, 6 Apr 2016 21:24:21 +0000 (17:24 -0400)]
Merge branch 'mlxsw-dcb'
Jiri Pirko says:
====================
mlxsw: Introduce support for Data Center Bridging
Ido says:
This patchset introduces support for Quality of Service (QoS) as part of the
IEEE Data Center Bridiging (DCB) standards.
Patches 1-9 do the required device initialization. Specifically, patches 1-6
initialize the ports' headroom buffers, which are used at ingress to store
incoming packets while they go through the switch's pipeline. Patches 7-9
complete them by initializing the egress scheduling.
The pipeline mentioned above determines the packet's egress port(s) and
traffic class. Ideally, once out of the pipeline the packet moves to the
switch's shared buffer (to be introduced in Jiri's patchset, currently
default values are used) and scheduled for transmission according to its
traffic class. The egress scheduling is configured according to the 802.1Qaz
standard, which is part of the DCB infrastructure supported by Linux. This
is introduced in patches 10-12.
Even after going through the pipeline packets are not always eligible to
enter the shared buffer. This is determined by the amount of available space
and the quotas associated with the packet. However, if flow control is
enabled and the packet is associated with the lossless flow, then it will
stay in the headroom and won't be discarded. This is introduced in patches
13-17.
Please check individual commit messages for more info, as I tried to keep
them pretty detailed.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Implement the appropriate DCB ops and allow a user to configure certain
traffic classes as lossless.
The operation configures PFC for both the egress (respecting PFC frames)
and ingress (sending PFC frames) parts of the port.
At egress, when a PFC frame is received for a PFC enabled priority, then
all the priorities mapped to the same TC are stopped.
At ingress, the priority group (PG) buffers to which the enabled PFC
priorities are mapped are configured to be lossless. PFC frames will be
transmitted when the Xoff threshold is crossed.
The user-supplied delay parameter is used to determine the PG's size
according to the following formula:
PG_SIZE = PG_SIZE_LOSSY + delay * CELL_FACTOR + MTU
In the worst case scenario the delay will be made up of packets that
are all of size CELL_SIZE + 1, which means each packet will require
almost twice its true size when buffered in the switch. We therefore
multiply this value by the "cell factor", which is close to 2.
Another MTU is added in case the transmitting host already started
transmitting a maximum length frame when the PFC packet was received.
As with PAUSE enabled ports, when the port's MTU is changed both the
PGs' size and threshold are adjusted 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>
projects / mirror_ubuntu-bionic-kernel.git / log