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>
Driver hook points for xdp_rxq_info:
* reg : tun_attach
* unreg: __tun_detach
I've done some manual testing of this tun driver, but I would
appriciate good review and someone else running their use-case tests,
as I'm not 100% sure I understand the tfile->detached semantics.
V2: Removed the skb_array_cleanup() call from V1 by request from Jason Wang.
Cc: Jason Wang <jasowang@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Private destructor could be called when register_netdev() fail with
rtnl lock held. This will lead deadlock in tun_free_netdev() who tries
to hold rtnl_lock. Fixing this by switching to use spinlock to
synchronize.
Fixes: 96f8406162 ("tun: add eBPF based queue selection method")
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The statement no longer serves a purpose.
Commit fa35864e0b ("tuntap: Fix for a race in accessing numqueues")
added the ACCESS_ONCE to avoid a race condition with skb_queue_len.
Commit 436accebb5 ("tuntap: remove unnecessary sk_receive_queue
length check during xmit") removed the affected skb_queue_len check.
Commit 96f8406162 ("tun: add eBPF based queue selection method")
split the function, reading the field a second time in the callee.
The temp variable is now only read once, so just remove it.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch introduces an eBPF based queue selection method. With this,
the policy could be offloaded to userspace completely through a new
ioctl TUNSETSTEERINGEBPF.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Small overlapping change conflict ('net' changed a line,
'net-next' added a line right afterwards) in flexcan.c
Signed-off-by: David S. Miller <davem@davemloft.net>
tun_recvmsg() supports accepting skb by msg_control after
commit ac77cfd425 ("tun: support receiving skb through msg_control"),
the skb if presented should be freed no matter how far it can go
along, otherwise it would be leaked.
This patch fixes several missed cases.
Signed-off-by: Wei Xu <wexu@redhat.com>
Reported-by: Matthew Rosato <mjrosato@linux.vnet.ibm.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since day one of XDP drivers had to remember to free the program
on the remove path. This leads to code duplication and is error
prone. Make the stack query the installed programs on unregister
and if something is installed, remove the program. Freeing of
program attached to XDP generic is moved from free_netdev() as well.
Because the remove will now be called before notifiers are
invoked, BPF offload state of the program will not get destroyed
before uninstall.
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: Daniel Borkmann <daniel@iogearbox.net>
Pull timer updates from Thomas Gleixner:
- The final conversion of timer wheel timers to timer_setup().
A few manual conversions and a large coccinelle assisted sweep and
the removal of the old initialization mechanisms and the related
code.
- Remove the now unused VSYSCALL update code
- Fix permissions of /proc/timer_list. I still need to get rid of that
file completely
- Rename a misnomed clocksource function and remove a stale declaration
* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)
m68k/macboing: Fix missed timer callback assignment
treewide: Remove TIMER_FUNC_TYPE and TIMER_DATA_TYPE casts
timer: Remove redundant __setup_timer*() macros
timer: Pass function down to initialization routines
timer: Remove unused data arguments from macros
timer: Switch callback prototype to take struct timer_list * argument
timer: Pass timer_list pointer to callbacks unconditionally
Coccinelle: Remove setup_timer.cocci
timer: Remove setup_*timer() interface
timer: Remove init_timer() interface
treewide: setup_timer() -> timer_setup() (2 field)
treewide: setup_timer() -> timer_setup()
treewide: init_timer() -> setup_timer()
treewide: Switch DEFINE_TIMER callbacks to struct timer_list *
s390: cmm: Convert timers to use timer_setup()
lightnvm: Convert timers to use timer_setup()
drivers/net: cris: Convert timers to use timer_setup()
drm/vc4: Convert timers to use timer_setup()
block/laptop_mode: Convert timers to use timer_setup()
net/atm/mpc: Avoid open-coded assignment of timer callback function
...
Tuntap and similar devices can inject GSO packets. Accept type
VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively.
Processes are expected to use feature negotiation such as TUNSETOFFLOAD
to detect supported offload types and refrain from injecting other
packets. This process breaks down with live migration: guest kernels
do not renegotiate flags, so destination hosts need to expose all
features that the source host does.
Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677.
This patch introduces nearly(*) no new code to simplify verification.
It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP
insertion and software UFO segmentation.
It does not reinstate protocol stack support, hardware offload
(NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception
of VIRTIO_NET_HDR_GSO_UDP packets in tuntap.
To support SKB_GSO_UDP reappearing in the stack, also reinstate
logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD
by squashing in commit 939912216f ("net: skb_needs_check() removes
CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643
("net: avoid skb_warn_bad_offload false positives on UFO").
(*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id,
ipv6_proxy_select_ident is changed to return a __be32 and this is
assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted
at the end of the enum to minimize code churn.
Tested
Booted a v4.13 guest kernel with QEMU. On a host kernel before this
patch `ethtool -k eth0` shows UFO disabled. After the patch, it is
enabled, same as on a v4.13 host kernel.
A UFO packet sent from the guest appears on the tap device:
host:
nc -l -p -u 8000 &
tcpdump -n -i tap0
guest:
dd if=/dev/zero of=payload.txt bs=1 count=2000
nc -u 192.16.1.1 8000 < payload.txt
Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds,
packets arriving fragmented:
./with_tap_pair.sh ./tap_send_ufo tap0 tap1
(from https://github.com/wdebruij/kerneltools/tree/master/tests)
Changes
v1 -> v2
- simplified set_offload change (review comment)
- documented test procedure
Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com>
Fixes: fb652fdfe8 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.")
Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
rcu_read_lock in tun_build_skb is used to rcu_dereference tun->xdp_prog
safely, rcu_read_unlock should be done in every return path.
Now I could see one place missing it, where it returns NULL in switch-case
XDP_REDIRECT, another palce using rcu_read_lock wrongly, where it returns
NULL in if (xdp_xmit) chunk.
So fix both in this patch.
Fixes: 761876c857 ("tap: XDP support")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
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()
...
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>
Smooth Cong Wang's bug fix into 'net-next'. Basically put
the bulk of the tcf_block_put() logic from 'net' into
tcf_block_put_ext(), but after the offload unbind.
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>
An unaligned alloc_frag->offset caused by previous allocation will
result an unaligned skb->head. This will lead unaligned
skb_shared_info and then unaligned dataref which requires to be
aligned for accessing on some architecture. Fix this by aligning
alloc_frag->offset before the frag refilling.
Fixes: 0bbd7dad34 ("tun: make tun_build_skb() thread safe")
Cc: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Cc: Wei Wei <dotweiba@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Reported-by: Wei Wei <dotweiba@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If the name argument of dev_get_valid_name() contains "%d", it will try
to assign it a unit number in __dev__alloc_name() and return either the
unit number (>= 0) or an error code (< 0).
Considering positive values as error values prevent tun device creations
relying this mechanism, therefor we should only consider negative values
as errors here.
Signed-off-by: Julien Gomes <julien@arista.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
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>
There were quite a few overlapping sets of changes here.
Daniel's bug fix for off-by-ones in the new BPF branch instructions,
along with the added allowances for "data_end > ptr + x" forms
collided with the metadata additions.
Along with those three changes came veritifer test cases, which in
their final form I tried to group together properly. If I had just
trimmed GIT's conflict tags as-is, this would have split up the
meta tests unnecessarily.
In the socketmap code, a set of preemption disabling changes
overlapped with the rename of bpf_compute_data_end() to
bpf_compute_data_pointers().
Changes were made to the mv88e6060.c driver set addr method
which got removed in net-next.
The hyperv transport socket layer had a locking change in 'net'
which overlapped with a change of socket state macro usage
in 'net-next'.
Signed-off-by: David S. Miller <davem@davemloft.net>
Timer is properly armed on demand from tun_flow_update(),
so there is no need to arm it at tun init.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If tun_flow_cleanup() deleted all flows, no need to
arm the timer again. It will be armed next time
tun_flow_update() is called.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tun_flow_cleanup() being a timer callback, it is already
running in BH context.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
syzkaller hit the WARN() in tun_get_user(), providing skb
with payload in fragments only, and nothing in skb->head
GRO layer is fine with this, so relax the check.
Fixes: 90e33d4594 ("tun: enable napi_gro_frags() for TUN/TAP driver")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
register_netdevice() could fail early when we have an invalid
dev name, in which case ->ndo_uninit() is not called. For tun
device, this is a problem because a timer etc. are already
initialized and it expects ->ndo_uninit() to clean them up.
We could move these initializations into a ->ndo_init() so
that register_netdevice() knows better, however this is still
complicated due to the logic in tun_detach().
Therefore, I choose to just call dev_get_valid_name() before
register_netdevice(), which is quicker and much easier to audit.
And for this specific case, it is already enough.
Fixes: 96442e4242 ("tuntap: choose the txq based on rxq")
Reported-by: Dmitry Alexeev <avekceeb@gmail.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@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>
it seems no need to keep tun_get() and __tun_get() at same time.
Signed-off-by: yuan linyu <Linyu.Yuan@alcatel-sbell.com.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a TUN/TAP receive mode that exercises the napi_gro_frags()
interface. This mode is available only in TAP mode, as the interface
expects packets with Ethernet headers.
Furthermore, packets follow the layout of the iovec_iter that was
received. The first iovec is the linear data, and every one after the
first is a fragment. If there are more fragments than the max number,
drop the packet. Additionally, invoke eth_get_headlen() to exercise flow
dissector code and to verify that the header resides in the linear data.
The napi_gro_frags() mode requires setting the IFF_NAPI_FRAGS option.
This is imposed because this mode is intended for testing via tools like
syzkaller and packetdrill, and the increased flexibility it provides can
introduce security vulnerabilities. This flag is accepted only if the
device is in TAP mode and has the IFF_NAPI flag set as well. This is
done because both of these are explicit requirements for correct
operation in this mode.
Signed-off-by: Petar Penkov <peterpenkov96@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: davem@davemloft.net
Cc: ppenkov@stanford.edu
Acked-by: Mahesh Bandewar <maheshb@google,com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Changes TUN driver to use napi_gro_receive() upon receiving packets
rather than netif_rx_ni(). Adds flag IFF_NAPI that enables these
changes and operation is not affected if the flag is disabled. SKBs
are constructed upon packet arrival and are queued to be processed
later.
The new path was evaluated with a benchmark with the following setup:
Open two tap devices and a receiver thread that reads in a loop for
each device. Start one sender thread and pin all threads to different
CPUs. Send 1M minimum UDP packets to each device and measure sending
time for each of the sending methods:
napi_gro_receive(): 4.90s
netif_rx_ni(): 4.90s
netif_receive_skb(): 7.20s
Signed-off-by: Petar Penkov <peterpenkov96@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: davem@davemloft.net
Cc: ppenkov@stanford.edu
Acked-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rename "generic_xdp" to "skb_xdp" to avoid confusing it with the
generic XDP which will be done at netif_receive_skb().
Cc: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We reserve headroom unconditionally which could cause unnecessary
stress on socket memory accounting because of increased trusesize. Fix
this by only reserve extra headroom when XDP is set.
Cc: Jakub Kicinski <kubakici@wp.pl>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
syzkaller reported a double free [1], caused by the fact
that tun driver was not updated properly when priv_destructor
was added.
When/if register_netdevice() fails, priv_destructor() must have been
called already.
[1]
BUG: KASAN: double-free or invalid-free in selinux_tun_dev_free_security+0x15/0x20 security/selinux/hooks.c:5023
CPU: 0 PID: 2919 Comm: syzkaller227220 Not tainted 4.13.0-rc4+ #23
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:16 [inline]
dump_stack+0x194/0x257 lib/dump_stack.c:52
print_address_description+0x7f/0x260 mm/kasan/report.c:252
kasan_report_double_free+0x55/0x80 mm/kasan/report.c:333
kasan_slab_free+0xa0/0xc0 mm/kasan/kasan.c:514
__cache_free mm/slab.c:3503 [inline]
kfree+0xd3/0x260 mm/slab.c:3820
selinux_tun_dev_free_security+0x15/0x20 security/selinux/hooks.c:5023
security_tun_dev_free_security+0x48/0x80 security/security.c:1512
tun_set_iff drivers/net/tun.c:1884 [inline]
__tun_chr_ioctl+0x2ce6/0x3d50 drivers/net/tun.c:2064
tun_chr_ioctl+0x2a/0x40 drivers/net/tun.c:2309
vfs_ioctl fs/ioctl.c:45 [inline]
do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:685
SYSC_ioctl fs/ioctl.c:700 [inline]
SyS_ioctl+0x8f/0xc0 fs/ioctl.c:691
entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x443ff9
RSP: 002b:00007ffc34271f68 EFLAGS: 00000217 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00000000004002e0 RCX: 0000000000443ff9
RDX: 0000000020533000 RSI: 00000000400454ca RDI: 0000000000000003
RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000217 R12: 0000000000401ce0
R13: 0000000000401d70 R14: 0000000000000000 R15: 0000000000000000
Allocated by task 2919:
save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
save_stack+0x43/0xd0 mm/kasan/kasan.c:447
set_track mm/kasan/kasan.c:459 [inline]
kasan_kmalloc+0xaa/0xd0 mm/kasan/kasan.c:551
kmem_cache_alloc_trace+0x101/0x6f0 mm/slab.c:3627
kmalloc include/linux/slab.h:493 [inline]
kzalloc include/linux/slab.h:666 [inline]
selinux_tun_dev_alloc_security+0x49/0x170 security/selinux/hooks.c:5012
security_tun_dev_alloc_security+0x6d/0xa0 security/security.c:1506
tun_set_iff drivers/net/tun.c:1839 [inline]
__tun_chr_ioctl+0x1730/0x3d50 drivers/net/tun.c:2064
tun_chr_ioctl+0x2a/0x40 drivers/net/tun.c:2309
vfs_ioctl fs/ioctl.c:45 [inline]
do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:685
SYSC_ioctl fs/ioctl.c:700 [inline]
SyS_ioctl+0x8f/0xc0 fs/ioctl.c:691
entry_SYSCALL_64_fastpath+0x1f/0xbe
Freed by task 2919:
save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
save_stack+0x43/0xd0 mm/kasan/kasan.c:447
set_track mm/kasan/kasan.c:459 [inline]
kasan_slab_free+0x6e/0xc0 mm/kasan/kasan.c:524
__cache_free mm/slab.c:3503 [inline]
kfree+0xd3/0x260 mm/slab.c:3820
selinux_tun_dev_free_security+0x15/0x20 security/selinux/hooks.c:5023
security_tun_dev_free_security+0x48/0x80 security/security.c:1512
tun_free_netdev+0x13b/0x1b0 drivers/net/tun.c:1563
register_netdevice+0x8d0/0xee0 net/core/dev.c:7605
tun_set_iff drivers/net/tun.c:1859 [inline]
__tun_chr_ioctl+0x1caf/0x3d50 drivers/net/tun.c:2064
tun_chr_ioctl+0x2a/0x40 drivers/net/tun.c:2309
vfs_ioctl fs/ioctl.c:45 [inline]
do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:685
SYSC_ioctl fs/ioctl.c:700 [inline]
SyS_ioctl+0x8f/0xc0 fs/ioctl.c:691
entry_SYSCALL_64_fastpath+0x1f/0xbe
The buggy address belongs to the object at ffff8801d2843b40
which belongs to the cache kmalloc-32 of size 32
The buggy address is located 0 bytes inside of
32-byte region [ffff8801d2843b40, ffff8801d2843b60)
The buggy address belongs to the page:
page:ffffea000660cea8 count:1 mapcount:0 mapping:ffff8801d2843000 index:0xffff8801d2843fc1
flags: 0x200000000000100(slab)
raw: 0200000000000100 ffff8801d2843000 ffff8801d2843fc1 000000010000003f
raw: ffffea0006626a40 ffffea00066141a0 ffff8801dbc00100
page dumped because: kasan: bad access detected
Memory state around the buggy address:
ffff8801d2843a00: fb fb fb fb fc fc fc fc fb fb fb fb fc fc fc fc
ffff8801d2843a80: 00 00 00 fc fc fc fc fc fb fb fb fb fc fc fc fc
>ffff8801d2843b00: 00 00 00 00 fc fc fc fc fb fb fb fb fc fc fc fc
^
ffff8801d2843b80: fb fb fb fb fc fc fc fc fb fb fb fb fc fc fc fc
ffff8801d2843c00: fb fb fb fb fc fc fc fc fb fb fb fb fc fc fc fc
==================================================================
Fixes: cf124db566 ("net: Fix inconsistent teardown and release of private netdev state.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tun_build_skb() is not thread safe since it uses per queue page frag,
this will break things when multiple threads are sending through same
queue. Switch to use per-thread generator (no lock involved).
Fixes: 66ccbc9c87 ("tap: use build_skb() for small packet")
Tested-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
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>
Although sizeof is an operator in C. The kernel coding style convention
is to always use it like a function and add parenthesis.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch tries to implement XDP for tun. The implementation was
split into two parts:
- fast path: small and no gso packet. We try to do XDP at page level
before build_skb(). For XDP_TX, since creating/destroying queues
were completely under control of userspace, it was implemented
through generic XDP helper after skb has been built. This could be
optimized in the future.
- slow path: big or gso packet. We try to do it after skb was created
through generic XDP helpers.
Test were done through pktgen with small packets.
xdp1 test shows ~41.1% improvement:
Before: ~1.7Mpps
After: ~2.3Mpps
xdp_redirect to ixgbe shows ~60% improvement:
Before: ~0.8Mpps
After: ~1.38Mpps
Suggested-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We use tun_alloc_skb() which calls sock_alloc_send_pskb() to allocate
skb in the past. This socket based method is not suitable for high
speed userspace like virtualization which usually:
- ignore sk_sndbuf (INT_MAX) and expect to receive the packet as fast as
possible
- don't want to be block at sendmsg()
To eliminate the above overheads, this patch tries to use build_skb()
for small packet. We will do this only when the following conditions
are all met:
- TAP instead of TUN
- sk_sndbuf is INT_MAX
- caller don't want to be blocked
- zerocopy is not used
- packet size is smaller enough to use build_skb()
Pktgen from guest to host shows ~11% improvement for rx pps of tap:
Before: ~1.70Mpps
After : ~1.88Mpps
What's more important, this makes it possible to implement XDP for tap
before creating skbs.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Prepare the datapath for refcounted ubuf_info. Clone ubuf_info with
skb_zerocopy_clone() wherever needed due to skb split, merge, resize
or clone.
Split skb_orphan_frags into two variants. The split, merge, .. paths
support reference counted zerocopy buffers, so do not do a deep copy.
Add skb_orphan_frags_rx for paths that may loop packets to receive
sockets. That is not allowed, as it may cause unbounded latency.
Deep copy all zerocopy copy buffers, ref-counted or not, in this path.
The exact locations to modify were chosen by exhaustively searching
through all code that might modify skb_frag references and/or the
the SKBTX_DEV_ZEROCOPY tx_flags bit.
The changes err on the safe side, in two ways.
(1) legacy ubuf_info paths virtio and tap are not modified. They keep
a 1:1 ubuf_info to sk_buff relationship. Calls to skb_orphan_frags
still call skb_copy_ubufs and thus copy frags in this case.
(2) not all copies deep in the stack are addressed yet. skb_shift,
skb_split and skb_try_coalesce can be refined to avoid copying.
These are not in the hot path and this patch is hairy enough as
is, so that is left for future refinement.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Two minor conflicts in virtio_net driver (bug fix overlapping addition
of a helper) and MAINTAINERS (new driver edit overlapping revamp of
PHY entry).
Signed-off-by: David S. Miller <davem@davemloft.net>
There is some codes of tun/tap module which did not check the return
value of register_netdevice_notifier. Add the check now.
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for extended error reporting.
Signed-off-by: Matthias Schiffer <mschiffer@universe-factory.net>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Network devices can allocate reasources and private memory using
netdev_ops->ndo_init(). However, the release of these resources
can occur in one of two different places.
Either netdev_ops->ndo_uninit() or netdev->destructor().
The decision of which operation frees the resources depends upon
whether it is necessary for all netdev refs to be released before it
is safe to perform the freeing.
netdev_ops->ndo_uninit() presumably can occur right after the
NETDEV_UNREGISTER notifier completes and the unicast and multicast
address lists are flushed.
netdev->destructor(), on the other hand, does not run until the
netdev references all go away.
Further complicating the situation is that netdev->destructor()
almost universally does also a free_netdev().
This creates a problem for the logic in register_netdevice().
Because all callers of register_netdevice() manage the freeing
of the netdev, and invoke free_netdev(dev) if register_netdevice()
fails.
If netdev_ops->ndo_init() succeeds, but something else fails inside
of register_netdevice(), it does call ndo_ops->ndo_uninit(). But
it is not able to invoke netdev->destructor().
This is because netdev->destructor() will do a free_netdev() and
then the caller of register_netdevice() will do the same.
However, this means that the resources that would normally be released
by netdev->destructor() will not be.
Over the years drivers have added local hacks to deal with this, by
invoking their destructor parts by hand when register_netdevice()
fails.
Many drivers do not try to deal with this, and instead we have leaks.
Let's close this hole by formalizing the distinction between what
private things need to be freed up by netdev->destructor() and whether
the driver needs unregister_netdevice() to perform the free_netdev().
netdev->priv_destructor() performs all actions to free up the private
resources that used to be freed by netdev->destructor(), except for
free_netdev().
netdev->needs_free_netdev is a boolean that indicates whether
free_netdev() should be done at the end of unregister_netdevice().
Now, register_netdevice() can sanely release all resources after
ndo_ops->ndo_init() succeeds, by invoking both ndo_ops->ndo_uninit()
and netdev->priv_destructor().
And at the end of unregister_netdevice(), we invoke
netdev->priv_destructor() and optionally call free_netdev().
Signed-off-by: David S. Miller <davem@davemloft.net>
Tun actually expects a symmetric hash for queue selecting to work
correctly, otherwise packets belongs to a single flow may be
redirected to the wrong queue. So this patch switch to use
__skb_get_hash_symmetric().
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch makes tun_recvmsg() can receive from skb from its caller
through msg_control. Vhost_net will be the first user.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch exports skb_array through tun_get_skb_array(). Caller can
then manipulate skb array directly.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/ethernet/broadcom/genet/bcmmii.c
drivers/net/hyperv/netvsc.c
kernel/bpf/hashtab.c
Almost entirely overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
Added missing logic in tun driver, which prevents apps to set
offloads using tun ioctl, if offloads were previously disabled via ethtool
Signed-off-by: Yaroslav Isakov <yaroslav.isakov@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/ethernet/broadcom/genet/bcmgenet.c
net/core/sock.c
Conflicts were overlapping changes in bcmgenet and the
lockdep handling of sockets.
Signed-off-by: David S. Miller <davem@davemloft.net>
