Tun, tap, virtio, packet and uml vector all use struct virtio_net_hdr
to communicate packet metadata to userspace.
For skbuffs with vlan, the first two return the packet as it may have
existed on the wire, inserting the VLAN tag in the user buffer. Then
virtio_net_hdr.csum_start needs to be adjusted by VLAN_HLEN bytes.
Commit f09e2249c4 ("macvtap: restore vlan header on user read")
added this feature to macvtap. Commit 3ce9b20f19 ("macvtap: Fix
csum_start when VLAN tags are present") then fixed up csum_start.
Virtio, packet and uml do not insert the vlan header in the user
buffer.
When introducing virtio_net_hdr_from_skb to deduplicate filling in
the virtio_net_hdr, the variant from macvtap which adds VLAN_HLEN was
applied uniformly, breaking csum offset for packets with vlan on
virtio and packet.
Make insertion of VLAN_HLEN optional. Convert the callers to pass it
when needed.
Fixes: e858fae2b0 ("virtio_net: use common code for virtio_net_hdr and skb GSO conversion")
Fixes: 1276f24eee ("packet: use common code for virtio_net_hdr and skb GSO conversion")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann says:
====================
pull-request: bpf-next 2018-06-05
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Add a new BPF hook for sendmsg similar to existing hooks for bind and
connect: "This allows to override source IP (including the case when it's
set via cmsg(3)) and destination IP:port for unconnected UDP (slow path).
TCP and connected UDP (fast path) are not affected. This makes UDP support
complete, that is, connected UDP is handled by connect hooks, unconnected
by sendmsg ones.", from Andrey.
2) Rework of the AF_XDP API to allow extending it in future for type writer
model if necessary. In this mode a memory window is passed to hardware
and multiple frames might be filled into that window instead of just one
that is the case in the current fixed frame-size model. With the new
changes made this can be supported without having to add a new descriptor
format. Also, core bits for the zero-copy support for AF_XDP have been
merged as agreed upon, where i40e bits will be routed via Jeff later on.
Various improvements to documentation and sample programs included as
well, all from Björn and Magnus.
3) Given BPF's flexibility, a new program type has been added to implement
infrared decoders. Quote: "The kernel IR decoders support the most
widely used IR protocols, but there are many protocols which are not
supported. [...] There is a 'long tail' of unsupported IR protocols,
for which lircd is need to decode the IR. IR encoding is done in such
a way that some simple circuit can decode it; therefore, BPF is ideal.
[...] user-space can define a decoder in BPF, attach it to the rc
device through the lirc chardev.", from Sean.
4) Several improvements and fixes to BPF core, among others, dumping map
and prog IDs into fdinfo which is a straight forward way to correlate
BPF objects used by applications, removing an indirect call and therefore
retpoline in all map lookup/update/delete calls by invoking the callback
directly for 64 bit archs, adding a new bpf_skb_cgroup_id() BPF helper
for tc BPF programs to have an efficient way of looking up cgroup v2 id
for policy or other use cases. Fixes to make sure we zero tunnel/xfrm
state that hasn't been filled, to allow context access wrt pt_regs in
32 bit archs for tracing, and last but not least various test cases
for fixes that landed in bpf earlier, from Daniel.
5) Get rid of the ndo_xdp_flush API and extend the ndo_xdp_xmit with
a XDP_XMIT_FLUSH flag instead which allows to avoid one indirect
call as flushing is now merged directly into ndo_xdp_xmit(), from Jesper.
6) Add a new bpf_get_current_cgroup_id() helper that can be used in
tracing to retrieve the cgroup id from the current process in order
to allow for e.g. aggregation of container-level events, from Yonghong.
7) Two follow-up fixes for BTF to reject invalid input values and
related to that also two test cases for BPF kselftests, from Martin.
8) Various API improvements to the bpf_fib_lookup() helper, that is,
dropping MPLS bits which are not fully hashed out yet, rejecting
invalid helper flags, returning error for unsupported address
families as well as renaming flowlabel to flowinfo, from David.
9) Various fixes and improvements to sockmap BPF kselftests in particular
in proper error detection and data verification, from Prashant.
10) Two arm32 BPF JIT improvements. One is to fix imm range check with
regards to whether immediate fits into 24 bits, and a naming cleanup
to get functions related to rsh handling consistent to those handling
lsh, from Wang.
11) Two compile warning fixes in BPF, one for BTF and a false positive
to silent gcc in stack_map_get_build_id_offset(), from Arnd.
12) Add missing seg6.h header into tools include infrastructure in order
to fix compilation of BPF kselftests, from Mathieu.
13) Several formatting cleanups in the BPF UAPI helper description that
also fix an error during rst2man compilation, from Quentin.
14) Hide an unused variable in sk_msg_convert_ctx_access() when IPv6 is
not built into the kernel, from Yue.
15) Remove a useless double assignment in dev_map_enqueue(), from Colin.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove the ndo_xdp_flush call implementation tun_xdp_flush
as no callers of ndo_xdp_flush are left.
The tun drivers XDP_TX implementation also used tun_xdp_flush (and
tun_xdp_xmit). This is easily solved by passing the XDP_XMIT_FLUSH
flag to tun_xdp_xmit in tun_xdp_tx.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Let user space set whatever it would like to advertise for the
tun interface. Preserve the existing defaults.
Signed-off-by: Chas Williams <3chas3@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When passed the XDP_XMIT_FLUSH flag tun_xdp_xmit now performs the same
kind of socket wake up as in tun_xdp_flush(). The wake up code from
tun_xdp_flush is generalized and shared with tun_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>
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>
When link is down, writes to the device might fail with
-EIO. Userspace needs an indication when the status is resolved. As a
fix, tun_net_open() attempts to wake up writers - but that is only
effective if SOCKWQ_ASYNC_NOSPACE has been set in the past. This is
not the case of vhost_net which only poll for EPOLLOUT after it meets
errors during sendmsg().
This patch fixes this by making sure SOCKWQ_ASYNC_NOSPACE is set when
socket is not writable or device is down to guarantee EPOLLOUT will be
raised in either tun_chr_poll() or tun_sock_write_space() after device
is up.
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: Eric Dumazet <edumazet@google.com>
Fixes: 1bd4978a88 ("tun: honor IFF_UP in tun_get_user()")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
S390 bpf_jit.S is removed in net-next and had changes in 'net',
since that code isn't used any more take the removal.
TLS data structures split the TX and RX components in 'net-next',
put the new struct members from the bug fix in 'net' into the RX
part.
The 'net-next' tree had some reworking of how the ERSPAN code works in
the GRE tunneling code, overlapping with a one-line headroom
calculation fix in 'net'.
Overlapping changes in __sock_map_ctx_update_elem(), keep the bits
that read the prog members via READ_ONCE() into local variables
before using them.
Signed-off-by: David S. Miller <davem@davemloft.net>
After commit b196d88aba ("tun: fix use after free for ptr_ring") we
need clean up tx ring during release(). But unfortunately, it tries to
do the cleanup blindly after socket were destroyed which will lead
another use-after-free. Fix this by doing the cleanup before dropping
the last reference of the socket in __tun_detach().
Reported-by: Andrei Vagin <avagin@virtuozzo.com>
Acked-by: Andrei Vagin <avagin@virtuozzo.com>
Fixes: b196d88aba ("tun: fix use after free for ptr_ring")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We used to initialize ptr_ring during TUNSETIFF, this is because its
size depends on the tx_queue_len of netdevice. And we try to clean it
up when socket were detached from netdevice. A race were spotted when
trying to do uninit during a read which will lead a use after free for
pointer ring. Solving this by always initialize a zero size ptr_ring
in open() and do resizing during TUNSETIFF, and then we can safely do
cleanup during close(). With this, there's no need for the workaround
that was introduced by commit 4df0bfc799 ("tun: fix a memory leak
for tfile->tx_array").
Reported-by: syzbot+e8b902c3c3fadf0a9dba@syzkaller.appspotmail.com
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Fixes: 1576d98605 ("tun: switch to use skb array for tx")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since net ns of tun device is assigned on the device creation,
and it never changes, we do not need to use any lock to get it
from alive tun.
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann says:
====================
pull-request: bpf-next 2018-04-21
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Initial work on BPF Type Format (BTF) is added, which is a meta
data format which describes the data types of BPF programs / maps.
BTF has its roots from CTF (Compact C-Type format) with a number
of changes to it. First use case is to provide a generic pretty
print capability for BPF maps inspection, later work will also
add BTF to bpftool. pahole support to convert dwarf to BTF will
be upstreamed as well (https://github.com/iamkafai/pahole/tree/btf),
from Martin.
2) Add a new xdp_bpf_adjust_tail() BPF helper for XDP that allows
for changing the data_end pointer. Only shrinking is currently
supported which helps for crafting ICMP control messages. Minor
changes in drivers have been added where needed so they recalc
the packet's length also when data_end was adjusted, from Nikita.
3) Improve bpftool to make it easier to feed hex bytes via cmdline
for map operations, from Quentin.
4) Add support for various missing BPF prog types and attach types
that have been added to kernel recently but neither to bpftool
nor libbpf yet. Doc and bash completion updates have been added
as well for bpftool, from Andrey.
5) Proper fix for avoiding to leak info stored in frame data on page
reuse for the two bpf_xdp_adjust_{head,meta} helpers by disallowing
to move the pointers into struct xdp_frame area, from Jesper.
6) Follow-up compile fix from BTF in order to include stdbool.h in
libbpf, from Björn.
7) Few fixes in BPF sample code, that is, a typo on the netdevice
in a comment and fixup proper dump of XDP action code in the
tracepoint exception, from Wang and Jesper.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, the tun driver, in absence of an eBPF steering program,
always compute the rxhash in its rx path, even when such value
is later unused due to additional checks (
This changeset moves the all the related checks just before the
__skb_get_hash_symmetric(), so that the latter is no more computed
when unneeded.
Also replace an unneeded RCU section with rcu_access_pointer().
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
w/ bpf_xdp_adjust_tail helper xdp's data_end pointer could be changed as
well (only "decrease" of pointer's location is going to be supported).
changing of this pointer will change packet's size.
for tun driver we need to adjust XDP_PASS handling by recalculating
length of the packet if it was passed to the TCP/IP stack
(in case if after xdp's prog run data_end pointer was adjusted)
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Nikita V. Shirokov <tehnerd@tehnerd.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Bogus trimming in tun_net_xmit() causes truncated vlan packets.
skb->len is correct whether or not skb_vlan_tag_present() is true. There
is no more reason to adjust the skb length on xmit in this driver than
any other driver. tun_put_user() adds 4 bytes to the total for tagged
packets because it transmits the tag inline to userspace. This is
similar to a nic transmitting the tag inline on the wire.
Reproducing the bug by sending any tagged packet through back-to-back
connected tap interfaces:
socat TUN,tun-type=tap,iff-up,tun-name=in TUN,tun-type=tap,iff-up,tun-name=out &
ip link add link in name in.20 type vlan id 20
ip addr add 10.9.9.9/24 dev in.20
ip link set in.20 up
tshark -nxxi in -f arp -c1 2>/dev/null &
tshark -nxxi out -f arp -c1 2>/dev/null &
ping -c 1 10.9.9.5 >/dev/null 2>&1
The output from the 'in' and 'out' interfaces are different when the
bug is present:
Capturing on 'in'
0000 ff ff ff ff ff ff 76 cf 76 37 d5 0a 81 00 00 14 ......v.v7......
0010 08 06 00 01 08 00 06 04 00 01 76 cf 76 37 d5 0a ..........v.v7..
0020 0a 09 09 09 00 00 00 00 00 00 0a 09 09 05 ..............
Capturing on 'out'
0000 ff ff ff ff ff ff 76 cf 76 37 d5 0a 81 00 00 14 ......v.v7......
0010 08 06 00 01 08 00 06 04 00 01 76 cf 76 37 d5 0a ..........v.v7..
0020 0a 09 09 09 00 00 00 00 00 00 ..........
Fixes: aff3d70a07 ("tun: allow to attach ebpf socket filter")
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
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>
The tuntap driver invented it's own driver specific way of queuing
XDP packets, by storing the xdp_buff information in the top of
the XDP frame data.
Convert it over to use the more generic xdp_frame structure. The
main problem with the in-driver method is that the xdp_rxq_info pointer
cannot be trused/used when dequeueing the frame.
V3: Remove check based on feedback from Jason
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
I added dumping of link information about tun devices over netlink in
commit 1ec010e705 ("tun: export flags, uid, gid, queue information
over netlink"), but didn't add the missing netlink notifications when
the device's exported properties change.
This patch adds notifications when owner/group or flags are modified,
when queues are attached/detached, and when a tun fd is closed.
Reported-by: Thomas Haller <thaller@redhat.com>
Fixes: 1ec010e705 ("tun: export flags, uid, gid, queue information over netlink")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Otherwise, register_netdevice advertises the creation of the device with
the default flags, instead of what the user requested.
Reported-by: Thomas Haller <thaller@redhat.com>
Fixes: 1ec010e705 ("tun: export flags, uid, gid, queue information over netlink")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fun set of conflict resolutions here...
For the mac80211 stuff, these were fortunately just parallel
adds. Trivially resolved.
In drivers/net/phy/phy.c we had a bug fix in 'net' that moved the
function phy_disable_interrupts() earlier in the file, whilst in
'net-next' the phy_error() call from this function was removed.
In net/ipv4/xfrm4_policy.c, David Ahern's changes to remove the
'rt_table_id' member of rtable collided with a bug fix in 'net' that
added a new struct member "rt_mtu_locked" which needs to be copied
over here.
The mlxsw driver conflict consisted of net-next separating
the span code and definitions into separate files, whilst
a 'net' bug fix made some changes to that moved code.
The mlx5 infiniband conflict resolution was quite non-trivial,
the RDMA tree's merge commit was used as a guide here, and
here are their notes:
====================
Due to bug fixes found by the syzkaller bot and taken into the for-rc
branch after development for the 4.17 merge window had already started
being taken into the for-next branch, there were fairly non-trivial
merge issues that would need to be resolved between the for-rc branch
and the for-next branch. This merge resolves those conflicts and
provides a unified base upon which ongoing development for 4.17 can
be based.
Conflicts:
drivers/infiniband/hw/mlx5/main.c - Commit 42cea83f95
(IB/mlx5: Fix cleanup order on unload) added to for-rc and
commit b5ca15ad7e (IB/mlx5: Add proper representors support)
add as part of the devel cycle both needed to modify the
init/de-init functions used by mlx5. To support the new
representors, the new functions added by the cleanup patch
needed to be made non-static, and the init/de-init list
added by the representors patch needed to be modified to
match the init/de-init list changes made by the cleanup
patch.
Updates:
drivers/infiniband/hw/mlx5/mlx5_ib.h - Update function
prototypes added by representors patch to reflect new function
names as changed by cleanup patch
drivers/infiniband/hw/mlx5/ib_rep.c - Update init/de-init
stage list to match new order from cleanup patch
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Now we have ndo_xdp_xmit, switch to use it instead of the slow generic
XDP TX routine. XDP_TX on TAP gets ~20% improvements from ~1.5Mpps to
~1.8Mpps on 2.60GHz Core(TM) i7-5600U.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After commit fc72d1d54d ("tuntap: XDP transmission"), we can
actually queueing XDP pointers in the pointer ring, so we should
examine the pointer type before freeing the pointer.
Fixes: fc72d1d54d ("tuntap: XDP transmission")
Reported-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
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>
We don't flush batched XDP packets through xdp_do_flush_map(), this
will cause packets stall at TX queue. Consider we don't do XDP on NAPI
poll(), the only possible fix is to call xdp_do_flush_map()
immediately after xdp_do_redirect().
Note, this in fact won't try to batch packets through devmap, we could
address in the future.
Reported-by: Christoffer Dall <christoffer.dall@linaro.org>
Fixes: 761876c857 ("tap: XDP support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Except for tuntap, all other drivers' XDP was implemented at NAPI
poll() routine in a bh. This guarantees all XDP operation were done at
the same CPU which is required by e.g BFP_MAP_TYPE_PERCPU_ARRAY. But
for tuntap, we do it in process context and we try to protect XDP
processing by RCU reader lock. This is insufficient since
CONFIG_PREEMPT_RCU can preempt the RCU reader critical section which
breaks the assumption that all XDP were processed in the same CPU.
Fixing this by simply disabling preemption during XDP processing.
Fixes: 761876c857 ("tap: XDP support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit 762c330d67. The
reason is we try to batch packets for devmap which causes calling
xdp_do_flush() in the process context. Simply disabling preemption
may not work since process may move among processors which lead
xdp_do_flush() to miss some flushes on some processors.
So simply revert the patch, a follow-up patch will add the xdp flush
correctly.
Reported-by: Christoffer Dall <christoffer.dall@linaro.org>
Fixes: 762c330d67 ("tuntap: add missing xdp flush")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
<Mark Rutland reported>
While fuzzing arm64 v4.16-rc1 with Syzkaller, I've been hitting a
misaligned atomic in __skb_clone:
atomic_inc(&(skb_shinfo(skb)->dataref));
where dataref doesn't have the required natural alignment, and the
atomic operation faults. e.g. i often see it aligned to a single
byte boundary rather than a four byte boundary.
AFAICT, the skb_shared_info is misaligned at the instant it's
allocated in __napi_alloc_skb() __napi_alloc_skb()
</end of report>
Problem is caused by tun_napi_alloc_frags() using
napi_alloc_frag() with user provided seg sizes,
leading to other users of this API getting unaligned
page fragments.
Since we would like to not necessarily add paddings or alignments to
the frags that tun_napi_alloc_frags() attaches to the skb, switch to
another page frag allocator.
As a bonus skb_page_frag_refill() can use GFP_KERNEL allocations,
meaning that we can not deplete memory reserves as easily.
Fixes: 90e33d4594 ("tun: enable napi_gro_frags() for TUN/TAP driver")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds possibility to get tun device's net namespace fd
in the same way we allow to do that for sockets.
Socket ioctl numbers do not intersect with tun-specific, and there
is already SIOCSIFHWADDR used in tun code. So, SIOCGSKNS number
is choosen instead of custom-made for this functionality.
Note, that open_related_ns() uses plain get_net_ns() and it's safe
(net can't be already dead at this moment):
tun socket is allocated via sk_alloc() with zero last arg (kern = 0).
So, each alive socket increments net::count, and the socket is definitely
alive during ioctl syscall.
Also, common variable net is introduced, so small cleanup in TUNSETIFF
is made.
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is the mindless scripted replacement of kernel use of POLL*
variables as described by Al, done by this script:
for V in IN OUT PRI ERR RDNORM RDBAND WRNORM WRBAND HUP RDHUP NVAL MSG; do
L=`git grep -l -w POLL$V | grep -v '^t' | grep -v /um/ | grep -v '^sa' | grep -v '/poll.h$'|grep -v '^D'`
for f in $L; do sed -i "-es/^\([^\"]*\)\(\<POLL$V\>\)/\\1E\\2/" $f; done
done
with de-mangling cleanups yet to come.
NOTE! On almost all architectures, the EPOLL* constants have the same
values as the POLL* constants do. But they keyword here is "almost".
For various bad reasons they aren't the same, and epoll() doesn't
actually work quite correctly in some cases due to this on Sparc et al.
The next patch from Al will sort out the final differences, and we
should be all done.
Scripted-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When using devmap to redirect packets between interfaces,
xdp_do_flush() is usually a must to flush any batched
packets. Unfortunately this is missed in current tuntap
implementation.
Unlike most hardware driver which did XDP inside NAPI loop and call
xdp_do_flush() at then end of each round of poll. TAP did it in the
context of process e.g tun_get_user(). So fix this by count the
pending redirected packets and flush when it exceeds NAPI_POLL_WEIGHT
or MSG_MORE was cleared by sendmsg() caller.
With this fix, xdp_redirect_map works again between two TAPs.
Fixes: 761876c857 ("tap: XDP support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking updates from David Miller:
1) Significantly shrink the core networking routing structures. Result
of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf
2) Add netdevsim driver for testing various offloads, from Jakub
Kicinski.
3) Support cross-chip FDB operations in DSA, from Vivien Didelot.
4) Add a 2nd listener hash table for TCP, similar to what was done for
UDP. From Martin KaFai Lau.
5) Add eBPF based queue selection to tun, from Jason Wang.
6) Lockless qdisc support, from John Fastabend.
7) SCTP stream interleave support, from Xin Long.
8) Smoother TCP receive autotuning, from Eric Dumazet.
9) Lots of erspan tunneling enhancements, from William Tu.
10) Add true function call support to BPF, from Alexei Starovoitov.
11) Add explicit support for GRO HW offloading, from Michael Chan.
12) Support extack generation in more netlink subsystems. From Alexander
Aring, Quentin Monnet, and Jakub Kicinski.
13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
Russell King.
14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.
15) Many improvements and simplifications to the NFP driver bpf JIT,
from Jakub Kicinski.
16) Support for ipv6 non-equal cost multipath routing, from Ido
Schimmel.
17) Add resource abstration to devlink, from Arkadi Sharshevsky.
18) Packet scheduler classifier shared filter block support, from Jiri
Pirko.
19) Avoid locking in act_csum, from Davide Caratti.
20) devinet_ioctl() simplifications from Al viro.
21) More TCP bpf improvements from Lawrence Brakmo.
22) Add support for onlink ipv6 route flag, similar to ipv4, from David
Ahern.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
tls: Add support for encryption using async offload accelerator
ip6mr: fix stale iterator
net/sched: kconfig: Remove blank help texts
openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
tcp_nv: fix potential integer overflow in tcpnv_acked
r8169: fix RTL8168EP take too long to complete driver initialization.
qmi_wwan: Add support for Quectel EP06
rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
ipmr: Fix ptrdiff_t print formatting
ibmvnic: Wait for device response when changing MAC
qlcnic: fix deadlock bug
tcp: release sk_frag.page in tcp_disconnect
ipv4: Get the address of interface correctly.
net_sched: gen_estimator: fix lockdep splat
net: macb: Handle HRESP error
net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
ipv6: addrconf: break critical section in addrconf_verify_rtnl()
ipv6: change route cache aging logic
i40e/i40evf: Update DESC_NEEDED value to reflect larger value
bnxt_en: cleanup DIM work on device shutdown
...
Pull poll annotations from Al Viro:
"This introduces a __bitwise type for POLL### bitmap, and propagates
the annotations through the tree. Most of that stuff is as simple as
'make ->poll() instances return __poll_t and do the same to local
variables used to hold the future return value'.
Some of the obvious brainos found in process are fixed (e.g. POLLIN
misspelled as POLL_IN). At that point the amount of sparse warnings is
low and most of them are for genuine bugs - e.g. ->poll() instance
deciding to return -EINVAL instead of a bitmap. I hadn't touched those
in this series - it's large enough as it is.
Another problem it has caught was eventpoll() ABI mess; select.c and
eventpoll.c assumed that corresponding POLL### and EPOLL### were
equal. That's true for some, but not all of them - EPOLL### are
arch-independent, but POLL### are not.
The last commit in this series separates userland POLL### values from
the (now arch-independent) kernel-side ones, converting between them
in the few places where they are copied to/from userland. AFAICS, this
is the least disruptive fix preserving poll(2) ABI and making epoll()
work on all architectures.
As it is, it's simply broken on sparc - try to give it EPOLLWRNORM and
it will trigger only on what would've triggered EPOLLWRBAND on other
architectures. EPOLLWRBAND and EPOLLRDHUP, OTOH, are never triggered
at all on sparc. With this patch they should work consistently on all
architectures"
* 'misc.poll' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (37 commits)
make kernel-side POLL... arch-independent
eventpoll: no need to mask the result of epi_item_poll() again
eventpoll: constify struct epoll_event pointers
debugging printk in sg_poll() uses %x to print POLL... bitmap
annotate poll(2) guts
9p: untangle ->poll() mess
->si_band gets POLL... bitmap stored into a user-visible long field
ring_buffer_poll_wait() return value used as return value of ->poll()
the rest of drivers/*: annotate ->poll() instances
media: annotate ->poll() instances
fs: annotate ->poll() instances
ipc, kernel, mm: annotate ->poll() instances
net: annotate ->poll() instances
apparmor: annotate ->poll() instances
tomoyo: annotate ->poll() instances
sound: annotate ->poll() instances
acpi: annotate ->poll() instances
crypto: annotate ->poll() instances
block: annotate ->poll() instances
x86: annotate ->poll() instances
...
Similarly to tx ring, xdp_rxq_info is only registered
when !tfile->detached, so we need to avoid calling
xdp_rxq_info_unreg() twice too. The helper tun_cleanup_tx_ring()
already checks for this properly, so it is correct to put
xdp_rxq_info_unreg() just inside there.
Reported-by: syzbot+1c788d7ce0f0888f1d7f@syzkaller.appspotmail.com
Fixes: 8565d26bcb ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net")
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes the following sparse warnings:
drivers/net/tun.c:2241:15: error: incompatible types in comparison expression (different address spaces)
Fixes: cd5681d7d8 ("tuntap: rename struct tun_steering_prog to struct tun_prog")
Cc: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The BPF verifier conflict was some minor contextual issue.
The TUN conflict was less trivial. Cong Wang fixed a memory leak of
tfile->tx_array in 'net'. This is an skb_array. But meanwhile in
net-next tun changed tfile->tx_arry into tfile->tx_ring which is a
ptr_ring.
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch allows userspace to attach eBPF filter to tun. This will
allow to implement VM dataplane filtering in a more efficient way
compared to cBPF filter by allowing either qemu or libvirt to
attach eBPF filter to tun.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
To be reused by other eBPF program other than queue selection.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tfile->tun could be detached before we close the tun fd,
via tun_detach_all(), so it should not be used to check for
tfile->tx_array.
As Jason suggested, we probably have to clean it up
unconditionally both in __tun_deatch() and tun_detach_all(),
but this requires to check if it is initialized or not.
Currently skb_array_cleanup() doesn't have such a check,
so I check it in the caller and introduce a helper function,
it is a bit ugly but we can always improve it in net-next.
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Fixes: 1576d98605 ("tun: switch to use skb array for tx")
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch implements XDP transmission for TAP. Since we can't create
new queues for TAP during XDP set, exist ptr_ring was reused for
queuing XDP buffers. To differ xdp_buff from sk_buff, TUN_XDP_FLAG
(0x1UL) was encoded into lowest bit of xpd_buff pointer during
ptr_ring_produce, and was decoded during consuming. XDP metadata was
stored in the headroom of the packet which should work in most of
cases since driver usually reserve enough headroom. Very minor changes
were done for vhost_net: it just need to peek the length depends on
the type of pointer.
Tests were done on two Intel E5-2630 2.40GHz machines connected back
to back through two 82599ES. Traffic were generated/received through
MoonGen/testpmd(rxonly). It reports ~20% improvements when
xdp_redirect_map is doing redirection from ixgbe to TAP (from 2.50Mpps
to 3.05Mpps)
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch switches to use ptr_ring instead of skb_array. This will be
used to enqueue different types of pointers by encoding type into
lower bits.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Willem de Bruijn