When passed the XDP_XMIT_FLUSH flag ixgbe_xdp_xmit now performs the
same kind of ring tail update as in ixgbe_xdp_flush. The update tail
code in ixgbe_xdp_flush is generalized and shared with ixgbe_xdp_xmit.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch only change the API and reject any use of flags. This is an
intermediate step that allows us to implement the flush flag operation
later, for each individual driver in a separate patch.
The plan is to implement flush operation via XDP_XMIT_FLUSH flag
and then remove XDP_XMIT_FLAGS_NONE when done.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Filling in the padding slot in the bpf structure as a bug fix in 'ne'
overlapped with actually using that padding area for something in
'net-next'.
Signed-off-by: David S. Miller <davem@davemloft.net>
The previous code was optimistic, accepting the offload of whole action
chain when there was a single known action (drop/redirect). This results
in offloading a rule which should not be offloaded, because its behavior
cannot be reproduced in the hardware.
For example:
$ tc filter add dev eno1 parent ffff: protocol ip \
u32 ht 800: order 1 match tcp src 42 FFFF \
action mirred egress mirror dev enp1s16 pipe \
drop
The controller is unable to mirror the packet to a VF, but still
offloads the rule by dropping the packet.
Change the approach of the function to a pessimistic one, rejecting the
chain when an unknown action is found. This is better suited for future
extensions.
Note that both recognized actions always return TC_ACT_SHOT, therefore
it is safe to ignore actions behind them.
Signed-off-by: Ondřej Hlavatý <ohlavaty@redhat.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Previously the driver used pcie_get_minimum_link() to warn when the NIC
is in a slot that can't supply as much bandwidth as the NIC could use.
pcie_get_minimum_link() can be misleading because it finds the slowest link
and the narrowest link (which may be different links) without considering
the total bandwidth of each link. For a path with a 16 GT/s x1 link and a
2.5 GT/s x16 link, it returns 2.5 GT/s x1, which corresponds to 250 MB/s of
bandwidth, not the true available bandwidth of about 1969 MB/s for a
16 GT/s x1 link.
Use pcie_print_link_status() to report PCIe link speed and possible
limitations instead of implementing this in the driver itself. This finds
the slowest link in the path to the device by computing the total bandwidth
of each link and compares that with the capabilities of the device.
The dmesg change is:
- PCI Express bandwidth of %dGT/s available
- (Speed:%s, Width: x%d, Encoding Loss:%s)
+ %u.%03u Gb/s available PCIe bandwidth (%s x%d link)
or, if the device is capable of better performance than is available in the
current slot:
- This is not sufficient for optimal performance of this card.
- For optimal performance, at least %dGT/s of bandwidth is required.
- A slot with more lanes and/or higher speed is suggested.
+ %u.%03u Gb/s available PCIe bandwidth, limited by %s x%d link at %s (capable of %u.%03u Gb/s with %s x%d link)
Note that the driver previously used dev_warn() to suggest using a
different slot, but pcie_print_link_status() uses dev_info() because if the
platform has no faster slot available, the user can't do anything about the
warning and may not want to be bothered with it.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexei Starovoitov says:
====================
pull-request: bpf-next 2018-05-24
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Björn Töpel cleans up AF_XDP (removes rebind, explicit cache alignment from uapi, etc).
2) David Ahern adds mtu checks to bpf_ipv{4,6}_fib_lookup() helpers.
3) Jesper Dangaard Brouer adds bulking support to ndo_xdp_xmit.
4) Jiong Wang adds support for indirect and arithmetic shifts to NFP
5) Martin KaFai Lau cleans up BTF uapi and makes the btf_header extensible.
6) Mathieu Xhonneux adds an End.BPF action to seg6local with BPF helpers allowing
to edit/grow/shrink a SRH and apply on a packet generic SRv6 actions.
7) Sandipan Das adds support for bpf2bpf function calls in ppc64 JIT.
8) Yonghong Song adds BPF_TASK_FD_QUERY command for introspection of tracing events.
9) other misc fixes from Gustavo A. R. Silva, Sirio Balmelli, John Fastabend, and Magnus Karlsson
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch change the API for ndo_xdp_xmit to support bulking
xdp_frames.
When kernel is compiled with CONFIG_RETPOLINE, XDP sees a huge slowdown.
Most of the slowdown is caused by DMA API indirect function calls, but
also the net_device->ndo_xdp_xmit() call.
Benchmarked patch with CONFIG_RETPOLINE, using xdp_redirect_map with
single flow/core test (CPU E5-1650 v4 @ 3.60GHz), showed
performance improved:
for driver ixgbe: 6,042,682 pps -> 6,853,768 pps = +811,086 pps
for driver i40e : 6,187,169 pps -> 6,724,519 pps = +537,350 pps
With frames avail as a bulk inside the driver ndo_xdp_xmit call,
further optimizations are possible, like bulk DMA-mapping for TX.
Testing without CONFIG_RETPOLINE show the same performance for
physical NIC drivers.
The virtual NIC driver tun sees a huge performance boost, as it can
avoid doing per frame producer locking, but instead amortize the
locking cost over the bulk.
V2: Fix compile errors reported by kbuild test robot <lkp@intel.com>
V4: Isolated ndo, driver changes and callers.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This reverts commit 6710f970d9.
Gotta love when developers have offline discussions, thinking everyone
is reading their responses/dialog.
The change had the potential for a number of race conditions on
shutdown, which is why we are reverting the change.
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, during device_shutdown() ixgbe holds rtnl_lock for the duration
of lengthy ixgbe_close_suspend(). On machines with multiple ixgbe cards
this lock prevents scaling if device_shutdown() function is multi-threaded.
It is not necessary to hold this lock during ixgbe_close_suspend()
as it is not held when ixgbe_close() is called also during shutdown but for
kexec case.
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Since commit f7f37e7ff2 ("ixgbe: handle close/suspend race with
netif_device_detach/present") ixgbe_close_suspend is called, from
ixgbe_close, only if the device is present, i.e. if it isn't detached.
That exposed a situation where IRQs weren't freed if a PCI error
recovery system opts to remove the device. For such case the pci channel
state is set to pci_channel_io_perm_failure and ixgbe_io_error_detected
was returning PCI_ERS_RESULT_DISCONNECT before calling
ixgbe_close_suspend consequentially not freeing IRQ and crashing when
the remove handler calls pci_disable_device, hitting a BUG_ON at
free_msi_irqs, which asserts that there is no non-free IRQ associated
with the device to be removed:
BUG_ON(irq_has_action(entry->irq + i));
The issue is fixed by calling the ixgbe_close_suspend before evaluate
the pci channel state.
Reported-by: Naresh Bannoth <nbannoth@in.ibm.com>
Reported-by: Abdul Haleem <abdhalee@in.ibm.com>
Signed-off-by: Mauro S M Rodrigues <maurosr@linux.vnet.ibm.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Sparse complains valid conversions between restricted types, force
attribute is used to avoid those warnings.
Signed-off-by: Cathy Zhou <cathy.zhou@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
After many years of having a ~30 line copyright and license header to our
source files, we are finally able to reduce that to one line with the
advent of the SPDX identifier.
Also caught a few files missing the SPDX license identifier, so fixed
them up.
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Acked-by: Shannon Nelson <shannon.nelson@oracle.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The original implementation for macvlan offload has us performing a full
port reset every time we added a new macvlan. This shouldn't be necessary
and can be avoided with a few behavior changes.
This patches updates the logic for the queues so that we have essentially 3
possible configurations for macvlan offload. They consist of 15 macvlans
with 4 queues per macvlan, 31 macvlans with 2 queues per macvlan, and 63
macvlans with 1 queue per macvlan. As macvlans are added you will encounter
up to 3 total resets if you add all the way up to 63, and after that the
device will stay in the mode supporting up to 63 macvlans until the L2FW
flag is cleared.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch drops the real_adapter member from the fwd_adapter structure.
The general idea behind the change is that the real_adapter is carrying
unnecessary data since we could always just grab the adapter structure
from netdev_priv(macvlan->lowerdev) if we really needed to get at it.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Both the ixgbe and fm10k drivers support destination filtering.
Instead of adding a ton of complexity to support either source or passthru
mode we can instead just avoid offloading them for now. Doing this we avoid
leaking packets into interfaces that aren't meant to receive them.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Drop dead code now that we shouldn't be receiving broadcast or multicast
frames on the queues associated to the macvlan netdev.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This change makes it so that we use a software path for packets that are
going to be locally switched between two macvlan interfaces on the same
device. In addition we resort to software replication of broadcast and
multicast packets instead of offloading that to hardware.
The general idea is that using the device for east/west traffic local to
the system is extremely inefficient. We can only support up to whatever the
PCIe limit is for any given device so this caps us at somewhere around 20G
for devices supported by ixgbe. This is compounded even further when you
take broadcast and multicast into account as a single 10G port can come to
a crawl as a packet is replicated up to 60+ times in some cases. In order
to get away from that I am implementing changes so that we handle
broadcast/multicast replication and east/west local traffic all in
software.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This change renames the fwd_priv member to accel_priv as this more
accurately reflects the actual purpose of this value. In addition I am
adding an accessor which will allow us to further abstract this in the
future if needed.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Drop the code for handling macvlan specific unicast lists. It isn't needed
since we don't take any efforts to maintain it when we bring the interface
up and it takes the slow path anyway.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Changing API ndo_xdp_xmit to take a struct xdp_frame instead of struct
xdp_buff. This brings xdp_return_frame and ndp_xdp_xmit in sync.
This builds towards changing the API further to become a bulk API,
because xdp_buff is not a queue-able object while xdp_frame is.
V4: Adjust for commit 59655a5b6c ("tuntap: XDP_TX can use native XDP")
V7: Adjust for commit d9314c474d ("i40e: add support for XDP_REDIRECT")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Changing API xdp_return_frame() to take struct xdp_frame as argument,
seems like a natural choice. But there are some subtle performance
details here that needs extra care, which is a deliberate choice.
When de-referencing xdp_frame on a remote CPU during DMA-TX
completion, result in the cache-line is change to "Shared"
state. Later when the page is reused for RX, then this xdp_frame
cache-line is written, which change the state to "Modified".
This situation already happens (naturally) for, virtio_net, tun and
cpumap as the xdp_frame pointer is the queued object. In tun and
cpumap, the ptr_ring is used for efficiently transferring cache-lines
(with pointers) between CPUs. Thus, the only option is to
de-referencing xdp_frame.
It is only the ixgbe driver that had an optimization, in which it can
avoid doing the de-reference of xdp_frame. The driver already have
TX-ring queue, which (in case of remote DMA-TX completion) have to be
transferred between CPUs anyhow. In this data area, we stored a
struct xdp_mem_info and a data pointer, which allowed us to avoid
de-referencing xdp_frame.
To compensate for this, a prefetchw is used for telling the cache
coherency protocol about our access pattern. My benchmarks show that
this prefetchw is enough to compensate the ixgbe driver.
V7: Adjust for commit d9314c474d ("i40e: add support for XDP_REDIRECT")
V8: Adjust for commit bd658dda42 ("net/mlx5e: Separate dma base address
and offset in dma_sync call")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use the IDA infrastructure for getting a cyclic increasing ID number,
that is used for keeping track of each registered allocator per
RX-queue xdp_rxq_info. Instead of using the IDR infrastructure, which
uses a radix tree, use a dynamic rhashtable, for creating ID to
pointer lookup table, because this is faster.
The problem that is being solved here is that, the xdp_rxq_info
pointer (stored in xdp_buff) cannot be used directly, as the
guaranteed lifetime is too short. The info is needed on a
(potentially) remote CPU during DMA-TX completion time . In an
xdp_frame the xdp_mem_info is stored, when it got converted from an
xdp_buff, which is sufficient for the simple page refcnt based recycle
schemes.
For more advanced allocators there is a need to store a pointer to the
registered allocator. Thus, there is a need to guard the lifetime or
validity of the allocator pointer, which is done through this
rhashtable ID map to pointer. The removal and validity of of the
allocator and helper struct xdp_mem_allocator is guarded by RCU. The
allocator will be created by the driver, and registered with
xdp_rxq_info_reg_mem_model().
It is up-to debate who is responsible for freeing the allocator
pointer or invoking the allocator destructor function. In any case,
this must happen via RCU freeing.
Use the IDA infrastructure for getting a cyclic increasing ID number,
that is used for keeping track of each registered allocator per
RX-queue xdp_rxq_info.
V4: Per req of Jason Wang
- Use xdp_rxq_info_reg_mem_model() in all drivers implementing
XDP_REDIRECT, even-though it's not strictly necessary when
allocator==NULL for type MEM_TYPE_PAGE_SHARED (given it's zero).
V6: Per req of Alex Duyck
- Introduce rhashtable_lookup() call in later patch
V8: Address sparse should be static warnings (from kbuild test robot)
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Extend struct ixgbe_tx_buffer to store the xdp_mem_info.
Notice that this could be optimized further by putting this into
a union in the struct ixgbe_tx_buffer, but this patchset
works towards removing this again. Thus, this is not done.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The current page counting scheme assumes that the reference count
cannot decrease until the received frame is sent to the upper layers
of the networking stack. This assumption does not hold for the
XDP_REDIRECT action, since a page (pointed out by xdp_buff) can have
its reference count decreased via the xdp_do_redirect call.
To work around that, we now start off by a large page count and then
don't allow a refcount less than two.
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Fix things up to support TSO offload in conjunction
with IPsec hw offload. This raises throughput with
IPsec offload on to nearly line rate.
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Since the ipsec data fields will be zero anyway in the non-ipsec
case, we can remove the conditional jump.
Suggested-by: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
With the patch
commit f8aa2696b4af ("esp: check the NETIF_F_HW_ESP_TX_CSUM bit before segmenting")
we no longer need to protect ourself from checksum
offload requests on IPsec packets, so we can remove
the check in our .ndo_features_check callback.
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Add status register reads and delay between reads to ixgbe_check_remove.
Registers can read 0xFFFFFFFF during PCI reset, which causes the driver
to remove the adapter. The additional status register reads can reduce the
chance of this race condition.
If the status register is not 0xFFFFFFFF, then ixgbe_check_remove returns
the value of the register being read.
Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
All of the conflicts were cases of overlapping changes.
In net/core/devlink.c, we have to make care that the
resouce size_params have become a struct member rather
than a pointer to such an object.
Signed-off-by: David S. Miller <davem@davemloft.net>
Add check for build_skb enabled ring in ixgbe_dma_sync_frag().
In that case &skb_shinfo(skb)->frags[0] may not always be set which
can lead to a crash. Instead we derive the page offset from skb->data.
Fixes: 42073d91a2
("ixgbe: Have the CPU take ownership of the buffers sooner")
CC: stable <stable@vger.kernel.org>
Reported-by: Ambarish Soman <asoman@redhat.com>
Suggested-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On hardware which supports timestamping all packets, the timestamps are
recorded in the packet buffer, and the driver no longer uses or reads
the registers. This makes the logic for checking and clearing Rx
timestamp hangs meaningless.
If we run the ixgbe_ptp_rx_hang() function in this case, then the driver
will continuously spam the log output with "Clearing Rx timestamp hang".
These messages are spurious, and confusing to end users.
The original code in commit a9763f3cb5 ("ixgbe: Update PTP to support
X550EM_x devices", 2015-12-03) did have a flag PTP_RX_TIMESTAMP_IN_REGISTER
which was intended to be used to avoid the Rx timestamp hang check,
however it did not actually check the flag before calling the function.
Do so now in order to stop the checks and prevent the spurious log
messages.
Fixes: a9763f3cb5 ("ixgbe: Update PTP to support X550EM_x devices", 2015-12-03)
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
commit 2de6aa3a66 ("ixgbe: Add support for padding packet")
Uses RXDCTL.RLPML to limit the maximum frame size on Rx when using
build_skb. Unfortunately that register does not work on 82599.
Added an explicit check to avoid setting this register on 82599 MAC.
Extended the comment related to the setting of RXDCTL.RLPML to better
explain its purpose.
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Since 5G link speed is supported by some devices, add reporting of 5G link
speed.
Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Make use of tc_cls_can_offload_and_chain0() to set extack msg in case
ethtool tc offload flag is not set or chain unsupported.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With all the support code in place we can now link in the ipsec
offload operations and set the ESP feature flag for the XFRM
subsystem to see.
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Add a simple statistic to count the ipsec offloads.
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
If the skb has a security association referenced in the skb, then
set up the Tx descriptor with the ipsec offload bits. While we're
here, we fix an oddly named field in the context descriptor struct.
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
If the chip sees and decrypts an ipsec offload, set up the skb
sp pointer with the ralated SA info. Since the chip is rude
enough to keep to itself the table index it used for the
decryption, we have to do our own table lookup, using the
hash for speed.
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
On a chip reset most of the table contents are lost, so must be
restored. This scans the driver's ipsec tables and restores both
the filled and empty table slots to their pre-reset values.
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Add the functions for setting up and removing offloaded SAs (Security
Associations) with the x540 hardware. We set up the callback structure
but we don't yet set the hardware feature bit to be sure the XFRM service
won't actually try to use us for an offload yet.
The software tables are made up to mimic the hardware tables to make it
easier to track what's in the hardware, and the SA table index is used
for the XFRM offload handle. However, there is a hashing field in the
Rx SA tracking that will be used to facilitate faster table searches in
the Rx fast path.
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Add a few routines to make access to the ipsec registers just a little
easier, and throw in the beginnings of an initialization.
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Recent checks added for formatting kernel-doc comments are causing warnings
if W= is run with a non-zero value. This patch fixes function comments to
resolve warnings when W=1 is used.
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This update makes it so that we report the actual number of Tx queues via
real_num_tx_queues but are still restricted to RSS on only the first pool
by setting num_tc equal to 1. Doing this locks us into only having the
ability to setup XPS on the queues in that pool, and only those queues
should be used for transmitting anything other than macvlan traffic.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This change makes it so that instead of bringing rings up/down for various
we just update the netdev pointer for the Rx ring and set or clear the MAC
filter for the interface. By doing it this way we can avoid a number of
races and issues in the code as things were getting messy with the macvlan
clean-up racing with the interface clean-up to bring the rings down on
shutdown.
With this change we opt to leave the rings owned by the PF interface for
both Tx and Rx and just direct the packets once they are received to the
macvlan netdev.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
We should not be stopping/starting the upper devices Tx queues when
handling a macvlan offload. Instead we should be stopping and starting
traffic on our own queues.
In order to prevent us from doing this I am updating the code so that we no
longer change the queue configuration on the upper device, nor do we update
the queue_index on our own device. Instead we can just use the queue index
for our local device and not update the netdev in the case of the transmit
rings.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
We shouldn't be recording the Rx queue on macvlan offloaded frames since
the macvlan is normally brought up as a single queue device, and it will
trigger warnings for RPS if we have recorded queue IDs larger than the
"real_num_rx_queues" value recorded for the device.
Instead we should be recording the macvlan statistics since we are
bypassing the normal macvlan statistics that would have been generated by
the receive path.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The code throughout ixgbe was assuming that dev->num_tc was populated and
configured with the driver, when in fact this can be configured via mqprio
without any hardware coordination other than restricting us to the real
number of Tx queues we advertise.
Instead of handling things this way we need to keep a local copy of the
number of TCs in use so that we don't accidentally pull in the TC
configuration from mqprio when it is configured in software mode.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
We might as well configure the limit to default to 1 pool always for the
interface. This accounts for the fact that the PF counts as 1 pool if
SR-IOV is enabled, and in general we are always running in 1 pool mode when
RSS or DCB is enabled as well, though we don't need to actually evaluate
any of the VMDq features in those cases.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The macvlan driver itself will validate the MAC address that is configured
for a given interface. There is no need for us to verify it again.
Instead we should be checking to verify that we actually allocate the filter
and have not run out of resources to configure a MAC rule in our filter
table.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The l2 acceleration private pointer isn't needed in the ring struct. It
isn't really used anywhere other than to test and see if we are supporting
an offloaded macvlan netdev, and it is much easier to test netdev for not
being ixgbe based to verify that.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch simplifies the check for Tx pending traffic and makes it more
holistic as there being any difference between next_to_use and
next_to_clean is much more informative than if head and tail are equal, as
it is possible for us to either not update tail, or not be notified of
completed work in which case next_to_clean would not be equal to head.
In addition the simplification makes it so that we don't have to read
hardware which allows us to drop a number of variables that were previously
being used in the call.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This change is a fix of the macvlan offload so that we correctly handle
macvlan offloaded devices. Specifically we were configuring our limits based
on the assumption that we were going to max out the RSS indices for every
mode. As a result when we went to 15 or more macvlan interfaces we were
forced into the 2 queue RSS mode on VFs even though they could have still
supported 4.
This change splits the logic up so that we limit either the total number of
macvlan instances if DCB is enabled, or limit the number of RSS queues used
per macvlan (instead of per pool) if SR-IOV is enabled. By doing this we
can make best use of the part.
In addition I have increased the maximum number of supported interfaces to
63 with one queue per offloaded interface as this more closely reflects the
actual values supported by the interface.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The num_rx_pools value is overwritten when we reinitialize the queue
configuration. In reality we shouldn't need to be updating the value since
it is redone every time we call into ixgbe_setup_tc so for now just drop
the spots where we were incrementing or decrementing the value.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
In order for RSS to work on the macvlan pools of the X550 we need to
populate the MRQC, RETA, and RSS key values for each pool. This patch makes
it so that we now take care of that.
In addition I have dropped the macvlan specific configuration of psrtype
since it is redundant with the code that already exists for configuring
this value.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
When SR-IOV was enabled the macvlan offload was configuring several filters
with the wrong pool value. This would result in the macvlan interfaces not
being able to receive traffic that had to pass over the physical interface.
To fix it wrap the pool argument in the VMDQ_P macro which will add the
necessary offset to get to the actual VMDq pool
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The InterruptThrottleRate has been removed from ixgbe. Then Update
the comment.
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Extend FW version reporting by displaying information from the iSCSI
or OEM block in the EEPROM.
This will allow us to more accurately identify the FW.
Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
On module insert advertise highest capable link speed. If module is
capable of 10G, then advertise 10G, else advertise modules capable
link speeds.
Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This enum is no longer needed after
commit: b4ded8327f ("ixgbe: Update adaptive ITR algorithm")
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Previously we only enabled the reception of multicast packets when
wake on multicast is set, but we also need this to allow waking with
IPv6 magic packets.
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
tcfm_dev always points to the correct netdev and we already
hold a refcnt, so no need to use tcfm_ifindex to lookup again.
If we would support moving target netdev across netns, using
pointer would be better than ifindex.
This also fixes dumping obsolete ifindex, now after the
target device is gone we just dump 0 as ifindex.
Cc: Jiri Pirko <jiri@mellanox.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes an issue seen on Power systems with ixgbe which results
in skb list corruption and an eventual kernel oops. The following is what
was observed:
CPU 1 CPU2
============================ ============================
1: ixgbe_xmit_frame_ring ixgbe_clean_tx_irq
2: first->skb = skb eop_desc = tx_buffer->next_to_watch
3: ixgbe_tx_map read_barrier_depends()
4: wmb check adapter written status bit
5: first->next_to_watch = tx_desc napi_consume_skb(tx_buffer->skb ..);
6: writel(i, tx_ring->tail);
The read_barrier_depends is insufficient to ensure that tx_buffer->skb does not
get loaded prior to tx_buffer->next_to_watch, which then results in loading
a stale skb pointer. This patch replaces the read_barrier_depends with
smp_rmb to ensure loads are ordered with respect to the load of
tx_buffer->next_to_watch.
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Acked-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>
Pull networking updates from David Miller:
"Highlights:
1) Maintain the TCP retransmit queue using an rbtree, with 1GB
windows at 100Gb this really has become necessary. From Eric
Dumazet.
2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.
3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
Lunn.
4) Add meter action support to openvswitch, from Andy Zhou.
5) Add a data meta pointer for BPF accessible packets, from Daniel
Borkmann.
6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.
7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.
8) More work to move the RTNL mutex down, from Florian Westphal.
9) Add 'bpftool' utility, to help with bpf program introspection.
From Jakub Kicinski.
10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
Dangaard Brouer.
11) Support 'blocks' of transformations in the packet scheduler which
can span multiple network devices, from Jiri Pirko.
12) TC flower offload support in cxgb4, from Kumar Sanghvi.
13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
Leitner.
14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.
15) Add RED qdisc offloadability, and use it in mlxsw driver. From
Nogah Frankel.
16) eBPF based device controller for cgroup v2, from Roman Gushchin.
17) Add some fundamental tracepoints for TCP, from Song Liu.
18) Remove garbage collection from ipv6 route layer, this is a
significant accomplishment. From Wei Wang.
19) Add multicast route offload support to mlxsw, from Yotam Gigi"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
tcp: highest_sack fix
geneve: fix fill_info when link down
bpf: fix lockdep splat
net: cdc_ncm: GetNtbFormat endian fix
openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
netem: remove unnecessary 64 bit modulus
netem: use 64 bit divide by rate
tcp: Namespace-ify sysctl_tcp_default_congestion_control
net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
ipv6: set all.accept_dad to 0 by default
uapi: fix linux/tls.h userspace compilation error
usbnet: ipheth: prevent TX queue timeouts when device not ready
vhost_net: conditionally enable tx polling
uapi: fix linux/rxrpc.h userspace compilation errors
net: stmmac: fix LPI transitioning for dwmac4
atm: horizon: Fix irq release error
net-sysfs: trigger netlink notification on ifalias change via sysfs
openvswitch: Using kfree_rcu() to simplify the code
openvswitch: Make local function ovs_nsh_key_attr_size() static
openvswitch: Fix return value check in ovs_meter_cmd_features()
...
Change TC_SETUP_MQPRIO to TC_SETUP_QDISC_MQPRIO to match the new
convention.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ndo_xdp is a control path callback for setting up XDP in the
driver. We can reuse it for other forms of communication
between the eBPF stack and the drivers. Rename the callback
and associated structures and definitions.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This restores the original behaviour before the block callbacks were
introduced. Allow the drivers to do binding of block always, no matter
if the NETIF_F_HW_TC feature is on or off. Move the check to the block
callback which is called for rule insertion.
Reported-by: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
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>
This patch is a partial revert of "ixgbe: Don't bother clearing buffer
memory for descriptor rings". Specifically I messed up the exception
handling path a bit and this resulted in us incorrectly adding the count
back in when we didn't need to.
In order to make this simpler I am reverting most of the exception handling
path change and instead just replacing the bit that was handled by the
unmap_and_free call.
Fixes: ffed21bcee ("ixgbe: Don't bother clearing buffer memory for descriptor rings")
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.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>
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 u32 offloads to block callbacks.
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. Switches test of .data field to
.function, since .data will be going away.
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: intel-wired-lan@lists.osuosl.org
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
In case where AER recovery fails the device is left in a down state.
Consecutive AER error injection can lead to a double IRQ free.
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The following change is meant to update the adaptive ITR algorithm to
better support the needs of the network. Specifically with this change what
I have done is make it so that our ITR algorithm will try to prevent either
starving a socket buffer for memory in the case of Tx, or overrunning an Rx
socket buffer on receive.
In addition a side effect of the calculations used is that we should
function better with new features such as XDP which can handle small
packets at high rates without needing to lock us into NAPI polling mode.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The ixgbe driver have page recycle scheme based around the RX-ring
queue, where a RX page is shared between two packets. Based on the
refcnt, the driver can determine if the RX-page is currently only used
by a single packet, if so it can then directly refill/recycle the
RX-slot by with the opposite "side" of the page.
While this is a clever trick, it is hard to determine when this
recycling is successful and when it fails. Adding a counter, which is
available via ethtool --statistics as 'alloc_rx_page'. Which counts
the number of times the recycle fails and the real page allocator is
invoked. When interpreting the stats, do remember that every alloc
will serve two packets.
The counter is collected per rx_ring, but is summed and ethtool
exported as 'alloc_rx_page'. It would be relevant to know what
rx_ring that cannot keep up, but that can be exported later if
someone experience a need for this.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Just like when the last VF is removed, we need to restore normal
operations after the last macvlan offload is removed, else we
get stuck in single queue operations.
To test:
ethtool -l eth1 # note the number of queues in use, ~= cpus
ethtool -K eth1 l2-fwd-offload on
ip link add mv1 link eth1 type macvlan mode bridge
ip link set dev mv1 up
ip link del mv1
ethtool -l eth1 # are we back to the same # of queues, or stuck on 1?
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
In ixgbe_clear_udp_tunnel_port(), we read the IXGBE_VXLANCTRL register
and then try to mask some bits out of the value, using the logical
instead of bitwise and operator.
Fixes: a21d0822ff ("ixgbe: add support for geneve Rx offload")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
In cases where PHY register access is not supported, don't mislead
a caller into thinking that it is supported by returning a PHY
address. Instead, return -EOPNOTSUPP when PHY access is not
supported.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Implement support for transferring XDP meta data into skb for
ixgbe driver; before calling into the program, xdp.data_meta points
to xdp.data, where on program return with pass verdict, we call
into skb_metadata_set().
We implement this for the default ixgbe_build_skb() variant. For the
ixgbe_construct_skb() that is used when legacy-rx buffer mananagement
mode is turned on via ethtool, I found that XDP gets 0 headroom, so
neither xdp_adjust_head() nor xdp_adjust_meta() can be used with this.
Just add a comment with explanation for this operating mode.
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>
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>
For XDP_REDIRECT the use of return code -EINVAL is confusing, as it is
used in three different cases. (1) When the index or ifindex lookup
fails, and in the ixgbe driver (2) when link is down and (3) when XDP
have not been enabled.
The return code can be picked up by the tracepoint xdp:xdp_redirect
for diagnosing why XDP_REDIRECT isn't working. Thus, there is a need
different return codes to tell the issues apart.
I'm considering using a specific err-code scheme for XDP_REDIRECT
instead of using these errno codes.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use errno -ENOSPC ("No space left on device") when the XDP xmit
have no space left on the TX ring buffer, instead of -ENOMEM.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The offending commit used a newly added helper function.
But the logic is wrong. Without this fix, the affected NICs
can't do HW offload. Error -EOPNOTSUPP will be returned directly.
Fixes: a2e8da9378 ("net/sched: use newly added classid identity helpers")
Signed-off-by: Chris Mi <chrism@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of checking handle, which does not have the inner class
information and drivers wrongly assume clsact->egress as ingress, use
the newly introduced classid identification helpers.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Get rid of struct tc_to_netdev which is now just unnecessary container
and rather pass per-type structures down to drivers directly.
Along with that, consolidate the naming of per-type structure variables
in cls_*.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As ndo_setup_tc is generic offload op for whole tc subsystem, does not
really make sense to have cls-specific args. So move them under
cls_common structurure which is embedded in all cls structs.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Let __ixgbe_setup_tc be a splitter for specific setup_tc types and push out
cls_u32 and mqprio specific codes into separate functions. Also change
the return values so they are the same as in the rest of the drivers.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since the type is always present, push it to be a separate argument to
ndo_setup_tc. On the way, name the type enum and use it for arg type.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The rest of the helpers are named tcf_exts_*, so change the name of
the action number helpers to be aligned. While at it, change to inline
functions.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The MAC register NW_MNG_IF_SEL fields have been redefined for
X553. These changes impact the iXFI driver code flow. Since iXFI is
only supported in X552, add MAC checks for iXFI flows.
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
For performance reasons we want to avoid updating the tail pointer in
the driver tx ring as much as possible. To accomplish this we add
batching support to the redirect path in XDP.
This adds another ndo op "xdp_flush" that is used to inform the driver
that it should bump the tail pointer on the TX ring.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds a trace event for xdp redirect which may help when debugging
XDP programs that use redirect bpf commands.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are optimizations we can add after the basic feature is
enabled. But, for now keep the patch simple.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support to ixgbe to report bpf_prog ID during XDP_QUERY_PROG.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
We call pci_set_drvdata immediately after calling register_netdev,
which leaves a window where tasks writing to the sriov_numvfs sysfs
attribute can sneak in and crash the kernel. register_netdev cleans
up after itself so placing pci_set_drvdata immediately before it
should preserve the intent of commit 0fb6a55cc3 ("ixgbe: fix crash
on rmmod after probe fail").
Fixes: 0fb6a55cc3 ("ixgbe: fix crash on rmmod after probe fail")
Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Update ixgbe version number.
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The ixgbe driver has logic to handle only one Tx timestamp at a time,
using a state bit lock to avoid multiple requests at once.
It may be possible, if incredibly unlikely, that a Tx timestamp event is
requested but never completes. Since we use an interrupt scheme to
determine when the Tx timestamp occurred we would never clear the state
bit in this case.
Add an ixgbe_ptp_tx_hang() function similar to the already existing
ixgbe_ptp_rx_hang() function. This function runs in the watchdog routine
and makes sure we eventually recover from this case instead of
permanently disabling Tx timestamps.
Note: there is no currently known way to cause this without hacking the
driver code to force it.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The ixgbe driver can only handle one Tx timestamp request at a time.
This means it is possible for an application timestamp request to be
ignored.
There is no easy way for an administrator to determine if this occurred.
Add a new statistic which tracks this, tx_hwtstamp_skipped.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The ixgbe driver uses a state bit lock to avoid handling more than one Tx
timestamp request at once. This is required because hardware is limited
to a single set of registers for Tx timestamps.
The state bit lock is not properly cleaned up during
ixgbe_xmit_frame_ring() if the transmit fails such as due to DMA or TSO
failure. In some hardware this results in blocking timestamps until the
service task times out. In other hardware this results in a permanent
lock of the timestamp bit because we never receive an interrupt
indicating the timestamp occurred, since indeed the packet was never
transmitted.
Fix this by checking for DMA and TSO errors in ixgbe_xmit_frame_ring() and
properly cleaning up after ourselves when these occur.
Reported-by: Reported-by: David Mirabito <davidm@metamako.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
We need to push the chain index down to the drivers, so they have the
information to which chain the rule belongs. For now, no driver supports
multichain offload, so only chain 0 is supported. This is needed to
prevent chain squashes during offload for now. Later this will be used
to implement multichain offload.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds/changes fall through comments to address new warnings
produced by gcc 7.
Fixed formatting on a couple of comments in the function.
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The following warning is now shown as a result of new checks added for
gcc 7:
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c: In function ‘ixgbe_open’:
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c:3118:13: warning: ‘%d’ directive output may be truncated writing between 1 and 10 bytes into a region of size between 3 and 18 [-Wformat-truncation=]
"%s-%s-%d", netdev->name, "TxRx", ri++);
^~
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c:3118:6: note: directive argument in the range [0, 2147483647]
"%s-%s-%d", netdev->name, "TxRx", ri++);
^~~~~~~~~~
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c:3117:4: note: ‘snprintf’ output between 8 and 32 bytes into a destination of size 24
snprintf(q_vector->name, sizeof(q_vector->name) - 1,
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
"%s-%s-%d", netdev->name, "TxRx", ri++);
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Resolve this warning by making a couple of changes.
- Don't reserve space for the null terminator. Since snprintf adds the
null terminator automatically, there is no need for us to reserve a byte
for it.
- Change a couple variables that can never be negative from int to
unsigned int.
While we're making changes to the format string, move the constant strings
into the format string instead of providing them as specifiers.
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The thermal sensor event logic is messed up, because it can execute
the code when there is no thermal event. The current logic is that
it will exit when !capable && !event whereas it really should exit
when !capable || !event. For one thing, it means that the service
task is doing too much work. It probably has some other symptoms as
well. So, correct the logic, simplifying to only execute when there
is a thermal event. The capable check is redundant.
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>
This will ensure that VF-to-VF traffic on the same PF
is filtered to allow RSS operation.
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch advertises TSO & GSO features in netdev->mpls_features.
In ixgbe(vf)_tso() where we set up segmentation offload, the IP
header will be the inner network header when eth_p_mpls() indicates
the Ethernet protocol is MPLS (UC or MC).
Suggested-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Scott Peterson <scott.d.peterson@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=eE4D
-----END PGP SIGNATURE-----
Merge tag 'pci-v4.12-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci
Pull PCI updates from Bjorn Helgaas:
- add framework for supporting PCIe devices in Endpoint mode (Kishon
Vijay Abraham I)
- use non-postable PCI config space mappings when possible (Lorenzo
Pieralisi)
- clean up and unify mmap of PCI BARs (David Woodhouse)
- export and unify Function Level Reset support (Christoph Hellwig)
- avoid FLR for Intel 82579 NICs (Sasha Neftin)
- add pci_request_irq() and pci_free_irq() helpers (Christoph Hellwig)
- short-circuit config access failures for disconnected devices (Keith
Busch)
- remove D3 sleep delay when possible (Adrian Hunter)
- freeze PME scan before suspending devices (Lukas Wunner)
- stop disabling MSI/MSI-X in pci_device_shutdown() (Prarit Bhargava)
- disable boot interrupt quirk for ASUS M2N-LR (Stefan Assmann)
- add arch-specific alignment control to improve device passthrough by
avoiding multiple BARs in a page (Yongji Xie)
- add sysfs sriov_drivers_autoprobe to control VF driver binding
(Bodong Wang)
- allow slots below PCI-to-PCIe "reverse bridges" (Bjorn Helgaas)
- fix crashes when unbinding host controllers that don't support
removal (Brian Norris)
- add driver for MicroSemi Switchtec management interface (Logan
Gunthorpe)
- add driver for Faraday Technology FTPCI100 host bridge (Linus
Walleij)
- add i.MX7D support (Andrey Smirnov)
- use generic MSI support for Aardvark (Thomas Petazzoni)
- make Rockchip driver modular (Brian Norris)
- advertise 128-byte Read Completion Boundary support for Rockchip
(Shawn Lin)
- advertise PCI_EXP_LNKSTA_SLC for Rockchip root port (Shawn Lin)
- convert atomic_t to refcount_t in HV driver (Elena Reshetova)
- add CPU IRQ affinity in HV driver (K. Y. Srinivasan)
- fix PCI bus removal in HV driver (Long Li)
- add support for ThunderX2 DMA alias topology (Jayachandran C)
- add ThunderX pass2.x 2nd node MCFG quirk (Tomasz Nowicki)
- add ITE 8893 bridge DMA alias quirk (Jarod Wilson)
- restrict Cavium ACS quirk only to CN81xx/CN83xx/CN88xx devices
(Manish Jaggi)
* tag 'pci-v4.12-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (146 commits)
PCI: Don't allow unbinding host controllers that aren't prepared
ARM: DRA7: clockdomain: Change the CLKTRCTRL of CM_PCIE_CLKSTCTRL to SW_WKUP
MAINTAINERS: Add PCI Endpoint maintainer
Documentation: PCI: Add userguide for PCI endpoint test function
tools: PCI: Add sample test script to invoke pcitest
tools: PCI: Add a userspace tool to test PCI endpoint
Documentation: misc-devices: Add Documentation for pci-endpoint-test driver
misc: Add host side PCI driver for PCI test function device
PCI: Add device IDs for DRA74x and DRA72x
dt-bindings: PCI: dra7xx: Add DT bindings to enable unaligned access
PCI: dwc: dra7xx: Workaround for errata id i870
dt-bindings: PCI: dra7xx: Add DT bindings for PCI dra7xx EP mode
PCI: dwc: dra7xx: Add EP mode support
PCI: dwc: dra7xx: Facilitate wrapper and MSI interrupts to be enabled independently
dt-bindings: PCI: Add DT bindings for PCI designware EP mode
PCI: dwc: designware: Add EP mode support
Documentation: PCI: Add binding documentation for pci-test endpoint function
ixgbe: Use pcie_flr() instead of duplicating it
IB/hfi1: Use pcie_flr() instead of duplicating it
PCI: imx6: Fix spelling mistake: "contol" -> "control"
...
The RSS key is being repopulated every time the interface is brought up
regardless of whether there is an existing value. If the user sets the RSS
key and the interface is brought up (e.g. reset), the user specified RSS
key will be overwritten.
This patch changes the rss_key to a pointer so we can check to see if the
key has been populated and preserve it accordingly.
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Add support for new 1000Base-T device based on X550EM_X MAC
type. All PHY operations are disabled as the PHY is controlled
by FW.
Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Current XDP implementation hits the tail on every XDP_TX return
code. This patch changes driver behavior to only hit the tail after
packet processing is complete.
With this patch I can run XDP drop programs @ 14+Mpps and XDP_TX
programs are at ~13.5Mpps.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
A couple design choices were made here. First I use a new ring
pointer structure xdp_ring[] in the adapter struct instead of
pushing the newly allocated XDP TX rings into the tx_ring[]
structure. This means we have to duplicate loops around rings
in places we want to initialize both TX rings and XDP rings.
But by making it explicit it is obvious when we are using XDP
rings and when we are using TX rings. Further we don't have
to do ring arithmatic which is error prone. As a proof point
for doing this my first patches used only a single ring structure
and introduced bugs in FCoE code and macvlan code paths.
Second I am aware this is not the most optimized version of
this code possible. I want to get baseline support in using
the most readable format possible and then once this series
is included I will optimize the TX path in another series
of patches.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Basic XDP drop support for ixgbe. Uses READ_ONCE/xchg semantics on XDP
programs instead of RCU primitives as suggested by Daniel Borkmann and
Alex Duyck.
v2: fix the build issues seen w/ XDP when page sizes are larger than 4K
and made minor fixes based on feedback from Jakub Kicinski
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
I just found that when we had changed the Rx path to check for length
instead of the DD bit we introduced an issue in ixgbe_dump since we were no
longer clearing the status bits.
To correct this I am updating ixgbe_dump to look for the length bits in the
descriptor since that is what we are using in the Rx path.
Fixes: c3630cc40b ("ixgbe: Use length to determine if descriptor is done")
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch increases the headroom allocated when using build_skb on a
system with 4K pages. Specifically the breakdown of headroom versus cache
size is as follows:
L1 Cache Size Headroom
64 192
64, NET_IP_ALIGN == 2 194
128 128
128, NET_IP_ALIGN == 2 130
256 512
256, NET_IP_ALIGN == 2 258
I stopped at supporting only a cache line size of 256 as that was the
largest cache size I could find supported in the kernel.
With this we are guaranteeing at least 128 bytes of headroom to spare in
the frame. This should be enough for us to insert a couple of IPv6 headers
if needed which is likely enough room for anything XDP should need.
I'm leaving the padding for systems with pages larger than 4K unmodified
for now. XDP currently isn't really setup to work on those types of
systems so we can cross that bridge when we get there.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Avoid setting adapter->num_vfs early in the init code path when
using the max_vfs module parameter by passing it to ixgbe_enable_sriov()
as a function parameter.
This fixes an issue where if we failed to allocate vfinfo in
__ixgbe_enable_sriov() the driver will crash with NULL pointer in
ixgbe_disable_sriov() when attempting to free the vfinfo struct based
on adapter->num_vfs. Also it cleans up the assignment of adapter->num_vfs
since now it will only be set in __ixgbe_enable_sriov() and cleared in
ixgbe_disable_sriov().
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch add support for X552 XFI backplane interface. The XFI
backplane requires a custom tuned link. HW/FW owns the link config
for XF backplane and SW must not interfere with it.
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
As pr_cont output can be interleaved by other processes,
using pr_cont should be avoided where possible.
Miscellanea:
- Use a temporary pointer to hold the next descriptions and
consolidate the pr_cont uses
- Use the temporary buffer to hold the 8 u32 register values and
emit those in a single go
- Coalesce formats and logging neatening around those changes
- Fix a defective output for the rx ring entry description when
also emitting rx_buffer_info data
This reduces overall object size a tiny bit too.
$ size drivers/net/ethernet/intel/ixgbe/*.o*
text data bss dec hex filename
62167 728 12 62907 f5bb drivers/net/ethernet/intel/ixgbe/ixgbe_main.o.new
62273 728 12 63013 f625 drivers/net/ethernet/intel/ixgbe/ixgbe_main.o.old
Signed-off-by: Joe Perches <joe@perches.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
There was a typo that I had left in the code comments for the igb and ixgbe
functions that enabled build_skb support.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The configurable priority to traffic class mapping and the user specified
queue ranges are used to configure the traffic class, overriding the
hardware defaults when the 'hw' option is set to 0. However, when the 'hw'
option is non-zero, the hardware QOS defaults are used.
This patch makes it so that we can pass the data the user provided to
ndo_setup_tc. This allows us to pull in the queue configuration if the
user requested it as well as any additional hardware offload type
requested by using a value other than 1 for the hw value.
Finally it also provides a means for the device driver to return the level
supported for the offload type via the qopt->hw value. Previously we were
just always assuming the value to be 1, in the future values beyond just 1
may be supported.
Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On architectures that have a cache line size larger than 64 Bytes we start
running into issues where the amount of headroom for the frame starts
shrinking.
The size of skb_shared_info on a system with a 64B L1 cache line size is
320. This increases to 384 with a 128B cache line, and 512 with a 256B
cache line.
In addition the NET_SKB_PAD value increases as well consistent with the
cache line size. As a result when we get to a 256B cache line as seen on
the s390 we end up 768 bytes used by padding and shared info leaving us
with only 1280 bytes to use for data storage. On architectures such as
this we should default to using 3K Rx buffers out of a 8K page instead of
trying to do 1.5K buffers out of a 4K page.
To take all of this into account I have added one small check so that we
compare the max_frame to the amount of actual data we can store. This was
already occurring for igb, but I had overlooked it for ixgbe as it doesn't
have strict limits for 82599 once we enable jumbo frames. By adding this
check we will automatically enable 3K Rx buffers as soon as the maximum
frame size we can handle drops below the standard Ethernet MTU.
I also went through and fixed one small typo that I found where I had left
an IGB in a variable name due to a copy/paste error.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Currently ixgbe_set_rxfh() updates the rss_key copy in the driver
memory, but does not push the new value into the h/w. This commit
add a new helper for the latter operation and call it in
ixgbe_set_rxfh(), so that the h/w rss key value can be really
updated via ethtool.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch makes it so that we don't need to bother with clearing the
memory out for the descriptor rings. The general idea is to only free
buffers associated with buffers in use which are located between the
next_to_clean and next_to_use or next_to_alloc values. Everything outside
of those regions can be safely ignored since they should have no buffers
associated with them.
The advantage to doing things this way is that is should speed up bring-up
and tear-down of the rings. Specifically we can avoid the 512 or more
cycles required to memset the rings in tear-down. In the bring-up phase we
then clear the memory as a part of initialization. The general idea is
that the clearing in initialization can act as a prefetch of sorts for the
buffer info structures so they are in the local CPU when we go to populate
them. This should help to improve overall time needed to perform a
suspend/resume.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch adds build_skb support to the Rx path. There are several
advantages to this change.
1. It avoids the memcpy and skb->head allocation for small packets which
improves performance by about 5% in my tests.
2. It avoids the memcpy, skb->head allocation, and eth_get_headlen
for larger packets improving performance by about 10% in my tests.
3. For VXLAN packets it allows the full header to be in skb->data which
improves the performance by as much as 30% in some of my tests.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch adds support for providing a buffer with headroom and tailroom
to allow for shared info, NET_SKB_PAD, and NET_IP_ALIGN. With this
combined with the DMA changes we can start using build_skb to build frames
around an incoming Rx buffer instead of having to memcpy the headers.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
We are going to be expanding the number of Rx paths in the driver. Instead
of duplicating all that code I am pulling it apart into separate functions
so that we don't have so much code duplication.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This change makes it so that we use the length of the packet instead of the
DD status bit to determine if a new descriptor is ready to be processed.
The obvious advantage is that it cuts down on reads as we don't really even
need the DD bit if going from a 0 to a non-zero value on size is enough to
inform us that the packet has been completed.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
In order to support build_skb with jumbo frames it will be necessary to use
3K buffers for the Rx path with 8K pages backing them. This is needed on
architectures that implement 4K pages because we can't support 2K buffers
plus padding in a 4K page.
In the case of systems that support page sizes larger than 4K the 3K
attribute will only be applied to FCoE as we can fall back to using just 2K
buffers and adding the padding.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Batch the page count updates instead of doing them one at a time. By doing
this we can improve the overall performance as the atomic increment
operations can be expensive due to the fact that on x86 they are locked
operations which can cause stalls. By doing bulk updates we can
consolidate the stall which should help to improve the overall receive
performance.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch adds support for DMA_ATTR_SKIP_CPU_SYNC and
DMA_ATTR_WEAK_ORDERING. By enabling both of these for the Rx path we are
able to see performance improvements on architectures that implement either
one due to the fact that page mapping and unmapping only has to sync what
is actually being used instead of the entire buffer. In addition by
enabling the weak ordering attribute enables a performance improvement for
architectures that can associate a memory ordering with a DMA buffer such
as Sparc.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
On some platforms, syncing a buffer for DMA is expensive. Rather than
sync the whole 2K receive buffer, only synchronise the length of the
frame, which will typically be the MTU, or a much smaller TCP ACK.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch consolidates the code for the ixgbe driver so that it is more
inline with what is already in igb. The general idea is to just
consolidate functions that represent logical steps in the Rx process so we
can later update them more easily.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Update the driver version to reflect the new devices that it
supports.
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>
Since dcbnl_ops is global, it should be prefixed by ixgbe_
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
In linux-4.5, busy polling was implemented in core
NAPI stack, meaning that all custom implementation can
be removed from drivers.
Not only we remove lot's of code, we also remove one lock
operation in fast path, and allow GRO to do its job.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The network stack no longer uses the last_rx member of struct net_device
since the bonding driver switched to use its own private last_rx in
commit 9f24273837 ("bonding: use last_arp_rx in slave_last_rx()").
However, some drivers still (ab)use the field for their own purposes and
some driver just update it without actually using it.
Previously, there was an accompanying comment for the last_rx member
added in commit 4dc89133f4 ("net: add a comment on netdev->last_rx")
which asked drivers not to update is, unless really needed. However,
this commend was removed in commit f8ff080dac ("bonding: remove
useless updating of slave->dev->last_rx"), so some drivers added later
on still did update last_rx.
Remove all usage of last_rx and switch three drivers (sky2, atp and
smc91c92_cs) which actually read and write it to use their own private
copy in netdev_priv.
Compile-tested with allyesconfig and allmodconfig on x86 and arm.
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Cc: Mirko Lindner <mlindner@marvell.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Acked-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The network device operation for reading statistics is only called
in one place, and it ignores the return value. Having a structure
return value is potentially confusing because some future driver could
incorrectly assume that the return value was used.
Fix all drivers with ndo_get_stats64 to have a void function.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Implement support for devices that have firmware-controlled PHYs.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Make sure that we free the IRQs in ixgbe_io_error_detected() when
responding to an PCIe AER error and also restore them when the
interface recovers from it.
Previously it was possible to trigger BUG_ON() check in free_msix_irqs()
in the case where we call ixgbe_remove() after a failed recovery from
AER error because the interrupts were not freed.
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
When an interface is part of a namespace it is possible that
ixgbe_close() may be called while __ixgbe_shutdown() is running
which ends up in a double free WARN and/or a BUG in free_msi_irqs().
To handle this situation we extend the rtnl_lock() to protect the
call to netif_device_detach() and ixgbe_clear_interrupt_scheme()
in __ixgbe_shutdown() and check for netif_device_present()
to avoid clearing the interrupts second time in ixgbe_close();
Also extend the rtnl lock in ixgbe_resume() to netif_device_attach().
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Some x550 devices require the driver version reported to its firmware; this
patch sends the driver version string to the firmware through the host
interface command for x550 devices.
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Couple conflicts resolved here:
1) In the MACB driver, a bug fix to properly initialize the
RX tail pointer properly overlapped with some changes
to support variable sized rings.
2) In XGBE we had a "CONFIG_PM" --> "CONFIG_PM_SLEEP" fix
overlapping with a reorganization of the driver to support
ACPI, OF, as well as PCI variants of the chip.
3) In 'net' we had several probe error path bug fixes to the
stmmac driver, meanwhile a lot of this code was cleaned up
and reorganized in 'net-next'.
4) The cls_flower classifier obtained a helper function in
'net-next' called __fl_delete() and this overlapped with
Daniel Borkamann's bug fix to use RCU for object destruction
in 'net'. It also overlapped with Jiri's change to guard
the rhashtable_remove_fast() call with a check against
tc_skip_sw().
5) In mlx4, a revert bug fix in 'net' overlapped with some
unrelated changes in 'net-next'.
6) In geneve, a stale header pointer after pskb_expand_head()
bug fix in 'net' overlapped with a large reorganization of
the same code in 'net-next'. Since the 'net-next' code no
longer had the bug in question, there was nothing to do
other than to simply take the 'net-next' hunks.
Signed-off-by: David S. Miller <davem@davemloft.net>
In the case of IPIP and SIT tunnel frames the outer transport header
offset is actually set to the same offset as the inner transport header.
This results in the lco_csum call not doing any checksum computation over
the inner IPv4/v6 header data.
In order to account for that I am updating the code so that we determine
the location to start the checksum ourselves based on the location of the
IPv4 header and the length.
Fixes: b83e30104b ("ixgbe/ixgbevf: Add support for GSO partial")
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For some Tx paths (e.g., tpacket_snd()), ixgbe_atr may be
passed down an sk_buff that has the network and transport
header in the paged data, so it needs to make sure these
headers are available in the headlen bytes to calculate the
l4_proto.
This patch expect that network and transport headers are
already available in the non-paged header dat. The assumption
is that the caller has set this up if l4_proto based Tx
steering is desired.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Commit 9f12df906c ("ixgbe: Store VXLAN port number in network order")
incorrectly checks for hdr.ipv4->protocol != IPPROTO_UDP
in ixgbe_atr(). This check should be for "==" instead.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Fix an issue where set_phy_power was NULL for X550 copper devices
because get_invariants was called before hw->device_id was set.
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Introduce ixgbe_link_operations struct with the following changes:
read_i2c_combined => read_link
read_i2c_combined_unlocked => read_link_unlocked
write_i2c_combined => write_link
write_i2c_combined_unlocked => write_link_unlocked
This will allow X550EM_a to override these methods for MDIO access
while X550EM_x provides methods to use I2C combined access. This
also adds a new structure, ixgbe_link_info, to hold information
about the link. Initially this is just method pointers and a bus
address.
The functions involved in combined I2C accesses were moved from
ixgbe_phy.c to ixgbe_x550.c. The underlying functions that carry
out the combined I2C accesses were left in ixgbe_phy.c because
they share some functions with other I2C methods.
v2 - set hw->link.ops in probe.
v3 - check ii->link_ops before setting it since we don't have it
for all devices.
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
