syzbot reported a lockdep splat in gen_new_estimator() /
est_fetch_counters() when attempting to lock est->stats_lock.
Since est_fetch_counters() is called from BH context from timer
interrupt, we need to block BH as well when calling it from process
context.
Most qdiscs use per cpu counters and are immune to the problem,
but net/sched/act_api.c and net/netfilter/xt_RATEEST.c are using
a spinlock to protect their data. They both call gen_new_estimator()
while object is created and not yet alive, so this bug could
not trigger a deadlock, only a lockdep splat.
Fixes: 1c0d32fde5 ("net_sched: gen_estimator: complete rewrite of rate estimators")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Handle HRESP error by doing a SW reset of RX and TX and
re-initializing the descriptors, RX and TX queue pointers.
Signed-off-by: Harini Katakam <harinik@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On TTC table creation, the indirection TIRs should be used instead of
the inner indirection TIRs.
Fixes: 1ae1df3a11 ("net/mlx5e: Refactor RSS related objects and code")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Reviewed-by: Shalom Lagziel <shaloml@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In current route cache aging logic, if a route has both RTF_EXPIRE and
RTF_GATEWAY set, the route will only be removed if the neighbor cache
has no NTF_ROUTER flag. Otherwise, even if the route has expired, it
won't get deleted.
Fix this logic to always check if the route has expired first and then
do the gateway neighbor cache check if previous check decide to not
remove the exception entry.
Fixes: 1859bac04f ("ipv6: remove from fib tree aged out RTF_CACHE dst")
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When compared to ixgbe and other previous Intel drivers the i40e and i40evf
drivers actually reserve 2 additional descriptors in maybe_stop_tx for
cache line alignment. We need to update DESC_NEEDED to reflect this as
otherwise we are more likely to return TX_BUSY which will cause issues with
things like xmit_more.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Make sure to cancel any pending work that might update driver coalesce
settings when taking down an interface.
Fixes: 6a8788f256 ("bnxt_en: add support for software dynamic interrupt moderation")
Signed-off-by: Andy Gospodarek <gospo@broadcom.com>
Cc: Michael Chan <michael.chan@broadcom.com>
Acked-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Unsolicited IPv6 neighbor advertisements should be sent after DAD
completes. Update ndisc_send_unsol_na to skip tentative, non-optimistic
addresses and have those sent by addrconf_dad_completed after DAD.
Fixes: 4a6e3c5def ("net: ipv6: send unsolicited NA on admin up")
Reported-by: Vivek Venkatraman <vivek@cumulusnetworks.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When the frame check sequence (FCS) is split across the last two frames
of a fragmented packet, part of the FCS gets counted twice, once when
subtracting the FCS, and again when subtracting the previously received
data.
For example, if 1602 bytes are received, and the first fragment contains
the first 1600 bytes (including the first two bytes of the FCS), and the
second fragment contains the last two bytes of the FCS:
'skb->len == 1600' from the first fragment
size = lstatus & BD_LENGTH_MASK; # 1602
size -= ETH_FCS_LEN; # 1598
size -= skb->len; # -2
Since the size is unsigned, it wraps around and causes a BUG later in
the packet handling, as shown below:
kernel BUG at ./include/linux/skbuff.h:2068!
Oops: Exception in kernel mode, sig: 5 [#1]
...
NIP [c021ec60] skb_pull+0x24/0x44
LR [c01e2fbc] gfar_clean_rx_ring+0x498/0x690
Call Trace:
[df7edeb0] [c01e2c1c] gfar_clean_rx_ring+0xf8/0x690 (unreliable)
[df7edf20] [c01e33a8] gfar_poll_rx_sq+0x3c/0x9c
[df7edf40] [c023352c] net_rx_action+0x21c/0x274
[df7edf90] [c0329000] __do_softirq+0xd8/0x240
[df7edff0] [c000c108] call_do_irq+0x24/0x3c
[c0597e90] [c00041dc] do_IRQ+0x64/0xc4
[c0597eb0] [c000d920] ret_from_except+0x0/0x18
--- interrupt: 501 at arch_cpu_idle+0x24/0x5c
Change the size to a signed integer and then trim off any part of the
FCS that was received prior to the last fragment.
Fixes: 6c389fc931 ("gianfar: fix size of scatter-gathered frames")
Signed-off-by: Andy Spencer <aspencer@spacex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Cong Wang says:
====================
net_sched: reflect tx_queue_len change for pfifo_fast
This pathcset restores the pfifo_fast qdisc behavior of dropping
packets based on latest dev->tx_queue_len. Patch 1 introduces
a helper, patch 2 introduces a new Qdisc ops which is called when
we modify tx_queue_len, patch 3 implements this ops for pfifo_fast.
Please see each patch for details.
---
v3: use skb_array_resize_multiple()
v2: handle error case for ->change_tx_queue_len()
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
pfifo_fast used to drop based on qdisc_dev(qdisc)->tx_queue_len,
so we have to resize skb array when we change tx_queue_len.
Other qdiscs which read tx_queue_len are fine because they
all save it to sch->limit or somewhere else in qdisc during init.
They don't have to implement this, it is nicer if they do so
that users don't have to re-configure qdisc after changing
tx_queue_len.
Cc: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduce a new qdisc ops ->change_tx_queue_len() so that
each qdisc could decide how to implement this if it wants.
Previously we simply read dev->tx_queue_len, after pfifo_fast
switches to skb array, we need this API to resize the skb array
when we change dev->tx_queue_len.
To avoid handling race conditions with TX BH, we need to
deactivate all TX queues before change the value and bring them
back after we are done, this also makes implementation easier.
Cc: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch promotes the local change_tx_queue_len() to a core
helper function, dev_change_tx_queue_len(), so that rtnetlink
and net-sysfs could share the code. This also prepares for the
following patch.
Note, the -EFAULT in the original code doesn't make sense,
we should propagate the errno from notifiers.
Cc: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We don't stop device before reset owner, this means we could try to
serve any virtqueue kick before reset dev->worker. This will result a
warn since the work was pending at llist during owner resetting. Fix
this by stopping device during owner reset.
Reported-by: syzbot+eb17c6162478cc50632c@syzkaller.appspotmail.com
Fixes: 3a4d5c94e9 ("vhost_net: a kernel-level virtio server")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Nicolas Dichtel says:
====================
net: Ease to follow an interface that moves to another netns
The goal of this series is to ease the user to follow an interface that
moves to another netns.
After this series, with a patched iproute2:
$ ip netns
bar
foo
$ ip monitor link &
$ ip link set dummy0 netns foo
Deleted 5: dummy0: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default
link/ether 6e:a7:82:35:96:46 brd ff:ff:ff:ff:ff:ff new-nsid 0 new-ifindex 6
=> new nsid: 0, new ifindex: 6 (was 5 in the previous netns)
$ ip link set eth1 netns bar
Deleted 3: eth1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN group default
link/ether 52:54:01:12:34:57 brd ff:ff:ff:ff:ff:ff new-nsid 1 new-ifindex 3
=> new nsid: 1, new ifindex: 3 (same ifindex)
$ ip netns
bar (id: 1)
foo (id: 0)
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The goal is to let the user follow an interface that moves to another
netns.
CC: Jiri Benc <jbenc@redhat.com>
CC: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The user should be able to follow any interface that moves to another
netns. There is no reason to hide physical interfaces.
CC: Jiri Benc <jbenc@redhat.com>
CC: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It was found that ethtool provides unexisting module name while
it queries the specified network device for associated driver
information. Then user tries to unload that module by provided
module name and fails.
This happens because ethtool reads value of DRV_NAME macro,
while module name is defined at the driver's Makefile.
This patch is to correct Cavium CN88xx Thunder NIC driver names
(DRV_NAME macro) 'thunder-nicvf' to 'nicvf' and 'thunder-nic'
to 'nicpf', sync bgx and xcv driver names accordingly to their
module names.
Signed-off-by: Vadim Lomovtsev <Vadim.Lomovtsev@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Michael S. Tsirkin says:
====================
ptr_ring fixes
This fixes a bunch of issues around ptr_ring use in net core.
One of these: "tap: fix use-after-free" is also needed on net,
but can't be backported cleanly.
I will post a net patch separately.
Lightly tested - Jason, could you pls confirm this
addresses the security issue you saw with ptr_ring?
Testing reports would be appreciated too.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Tested-by: Jason Wang <jasowang@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Offset 128 overlaps the last word of the redzone.
Use 132 which is always beyond that.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We don't rely on lockless guarantees, but it
seems cleaner than inverting __ptr_ring_peek.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In theory compiler could tear queue loads or stores in two. It does not
seem to be happening in practice but it seems easier to convert the
cases where this would be a problem to READ/WRITE_ONCE than worry about
it.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
__skb_array_empty should use __ptr_ring_empty since that's the only
legal lockless function.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit bcecb4bbf8.
If we try to allocate an extra entry as the above commit did, and when
the requested size is UINT_MAX, addition overflows causing zero size to
be passed to kmalloc().
kmalloc then returns ZERO_SIZE_PTR with a subsequent crash.
Reported-by: syzbot+87678bcf753b44c39b67@syzkaller.appspotmail.com
Cc: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Similar to bcecb4bbf8 ("net: ptr_ring: otherwise safe empty checks can
overrun array bounds") a lockless use of __ptr_ring_full might
cause an out of bounds access.
We can fix this, but it's easier to just disallow lockless
__ptr_ring_full for now.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Lockless access to __ptr_ring_full is only legal if ring is
never resized, otherwise it might cause use-after free errors.
Simply drop the lockless test, we'll drop the packet
a bit later when produce fails.
Fixes: 362899b8 ("macvtap: switch to use skb array")
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Lockless __ptr_ring_empty requires that consumer head is read and
written at once, atomically. Annotate accordingly to make sure compiler
does it correctly. Switch locked callers to __ptr_ring_peek which does
not support the lockless operation.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The only function safe to call without locks
is __ptr_ring_empty. Move documentation about
lockless use there to make sure people do not
try to use __ptr_ring_peek outside locks.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The comment near __ptr_ring_peek says:
* If ring is never resized, and if the pointer is merely
* tested, there's no need to take the lock - see e.g. __ptr_ring_empty.
but this was in fact never possible since consumer_head would sometimes
point outside the ring. Refactor the code so that it's always
pointing within a ring.
Fixes: c5ad119fb6 ("net: sched: pfifo_fast use skb_array")
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If a sk_v6_rcv_saddr is !IPV6_ADDR_ANY and !IPV6_ADDR_MAPPED, it
implicitly implies it is an ipv6only socket. However, in inet6_bind(),
this addr_type checking and setting sk->sk_ipv6only to 1 are only done
after sk->sk_prot->get_port(sk, snum) has been completed successfully.
This inconsistency between sk_v6_rcv_saddr and sk_ipv6only confuses
the 'get_port()'.
In particular, when binding SO_REUSEPORT UDP sockets,
udp_reuseport_add_sock(sk,...) is called. udp_reuseport_add_sock()
checks "ipv6_only_sock(sk2) == ipv6_only_sock(sk)" before adding sk to
sk2->sk_reuseport_cb. In this case, ipv6_only_sock(sk2) could be
1 while ipv6_only_sock(sk) is still 0 here. The end result is,
reuseport_alloc(sk) is called instead of adding sk to the existing
sk2->sk_reuseport_cb.
It can be reproduced by binding two SO_REUSEPORT UDP sockets on an
IPv6 address (!ANY and !MAPPED). Only one of the socket will
receive packet.
The fix is to set the implicit sk_ipv6only before calling get_port().
The original sk_ipv6only has to be saved such that it can be restored
in case get_port() failed. The situation is similar to the
inet_reset_saddr(sk) after get_port() has failed.
Thanks to Calvin Owens <calvinowens@fb.com> who created an easy
reproduction which leads to a fix.
Fixes: e32ea7e747 ("soreuseport: fast reuseport UDP socket selection")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Christian Brauner says:
====================
rtnetlink: enable IFLA_IF_NETNSID for RTM_{DEL,SET}LINK
Based on the previous discussion this enables passing a IFLA_IF_NETNSID
property along with RTM_SETLINK and RTM_DELLINK requests. The patch for
RTM_NEWLINK will be sent out in a separate patch since there are more
corner-cases to think about.
Changelog 2018-01-24:
* Preserve old behavior and report -ENODEV when either ifindex or ifname is
provided and IFLA_GROUP is set. Spotted by Wolfgang Bumiller.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
- Backwards Compatibility:
If userspace wants to determine whether RTM_DELLINK supports the
IFLA_IF_NETNSID property they should first send an RTM_GETLINK request
with IFLA_IF_NETNSID on lo. If either EACCESS is returned or the reply
does not include IFLA_IF_NETNSID userspace should assume that
IFLA_IF_NETNSID is not supported on this kernel.
If the reply does contain an IFLA_IF_NETNSID property userspace
can send an RTM_DELLINK with a IFLA_IF_NETNSID property. If they receive
EOPNOTSUPP then the kernel does not support the IFLA_IF_NETNSID property
with RTM_DELLINK. Userpace should then fallback to other means.
- Security:
Callers must have CAP_NET_ADMIN in the owning user namespace of the
target network namespace.
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
- Backwards Compatibility:
If userspace wants to determine whether RTM_SETLINK supports the
IFLA_IF_NETNSID property they should first send an RTM_GETLINK request
with IFLA_IF_NETNSID on lo. If either EACCESS is returned or the reply
does not include IFLA_IF_NETNSID userspace should assume that
IFLA_IF_NETNSID is not supported on this kernel.
If the reply does contain an IFLA_IF_NETNSID property userspace
can send an RTM_SETLINK with a IFLA_IF_NETNSID property. If they receive
EOPNOTSUPP then the kernel does not support the IFLA_IF_NETNSID property
with RTM_SETLINK. Userpace should then fallback to other means.
To retain backwards compatibility the kernel will first check whether a
IFLA_NET_NS_PID or IFLA_NET_NS_FD property has been passed. If either
one is found it will be used to identify the target network namespace.
This implies that users who do not care whether their running kernel
supports IFLA_IF_NETNSID with RTM_SETLINK can pass both
IFLA_NET_NS_{FD,PID} and IFLA_IF_NETNSID referring to the same network
namespace.
- Security:
Callers must have CAP_NET_ADMIN in the owning user namespace of the
target network namespace.
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RTM_{NEW,SET}LINK already allow operations on other network namespaces
by identifying the target network namespace through IFLA_NET_NS_{FD,PID}
properties. This is done by looking for the corresponding properties in
do_setlink(). Extend do_setlink() to also look for the IFLA_IF_NETNSID
property. This introduces no functional changes since all callers of
do_setlink() currently block IFLA_IF_NETNSID by reporting an error before
they reach do_setlink().
This introduces the helpers:
static struct net *rtnl_link_get_net_by_nlattr(struct net *src_net, struct
nlattr *tb[])
static struct net *rtnl_link_get_net_capable(const struct sk_buff *skb,
struct net *src_net,
struct nlattr *tb[], int cap)
to simplify permission checks and target network namespace retrieval for
RTM_* requests that already support IFLA_NET_NS_{FD,PID} but get extended
to IFLA_IF_NETNSID. To perserve backwards compatibility the helpers look
for IFLA_NET_NS_{FD,PID} properties first before checking for
IFLA_IF_NETNSID.
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Major changes:
wil6210
* add PCI device id for Talyn
* support flashless device
ath9k
* improve RSSI/signal accuracy on AR9003 series
mt76
* validate CCMP PN from received frames to avoid replay attacks
qtnfmac
* support 64-bit network stats
* report more hardware information to kernel log and some via ethtool
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJaa1x7AAoJEG4XJFUm622bdc8H/3JSWFnXlkrQvjZzL1NWR0Hn
vUYou/W04mgzYtXIcscNL3otDa9TGwLW6Sr5wP0MDH/TGU9zXoEZxBxnYy4zq4np
7ZP7M6VsOzOhlNNsTcNAiMGyObtIT4btrfKlmp2yvf3Sra7nHNJJmprFeuyH3f02
vk5ZQWjMcEAe0afBGPcHrzndoAvVqIHHOAbM/w694n/8cdT8edcQeQ8rwlFO6ENU
db9yqkr4RvjWv9oJwa2us6d0lolJDk8ATWhDTyZL40X9yk84XR7E0jMdN5LQ/CJj
CCCMWsDYjUpEDUJVmwLdXzGavgo43QAs9a+O+z7MDJ4uwqYkZh3rzQZay+dYLKk=
=D4LX
-----END PGP SIGNATURE-----
Merge tag 'wireless-drivers-next-for-davem-2018-01-26' of git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next
Kalle Valo says:
====================
wireless-drivers-next patches for 4.16
Major changes:
wil6210
* add PCI device id for Talyn
* support flashless device
ath9k
* improve RSSI/signal accuracy on AR9003 series
mt76
* validate CCMP PN from received frames to avoid replay attacks
qtnfmac
* support 64-bit network stats
* report more hardware information to kernel log and some via ethtool
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
efx_default_channel_want_txqs() is only used in efx.c, while
efx_ptp_want_txqs() and efx_ptp_channel_type (a struct) are only used
in ptp.c. In all cases these symbols should be static.
Fixes: 2935e3c382 ("sfc: on 8000 series use TX queues for TX timestamps")
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
[ecree@solarflare.com: rewrote commit message]
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jeff Kirsher says:
====================
40GbE Intel Wired LAN Driver Updates 2018-01-26
This series contains updates to i40e and i40evf.
Michal updates the driver to pass critical errors from the firmware to
the caller.
Patryk fixes an issue of creating multiple identical filters with the
same location, by simply moving the functions so that we remove the
existing filter and then add the new filter.
Paweł adds back in the ability to turn off offloads when VLAN is set for
the VF driver. Fixed an issue where the number of TC queue pairs was
exceeding MSI-X vectors count, causing messages about invalid TC mapping
and wrong selected Tx queue.
Alex cleans up the i40e/i40evf_set_itr_per_queue() by dropping all the
unneeded pointer chases. Puts to use the reg_idx value, which was going
unused, so that we can avoid having to compute the vector every time
throughout the driver.
Upasana enable the driver to display LLDP information on the vSphere Web
Client by exposing DCB parameters.
Alice converts our flags from 32 to 64 bit size, since we have added
more flags.
Dave implements a private ethtool flag to disable the processing of LLDP
packets by the firmware, so that the firmware will not consume LLDPDU
and cause them to be sent up the stack.
Alan adds a mechanism for detecting/storing the flag for processing of
LLDP packets by the firmware, so that its current state is persistent
across reboots/reloads of the driver.
Avinash fixes kdump with i40e due to resource constraints. We were
enabling VMDq and iWARP when we just have a single CPU, which was
starving kdump for the lack of IRQs.
Jake adds support to program the fragmented IPv4 input set PCTYPE.
Fixed the reported masks to properly report that the entire field is
masked, since we had accidentally swapped the mask values for the IPv4
addresses with the L4 port numbers.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexei Starovoitov says:
====================
pull-request: bpf-next 2018-01-26
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) A number of extensions to tcp-bpf, from Lawrence.
- direct R or R/W access to many tcp_sock fields via bpf_sock_ops
- passing up to 3 arguments to bpf_sock_ops functions
- tcp_sock field bpf_sock_ops_cb_flags for controlling callbacks
- optionally calling bpf_sock_ops program when RTO fires
- optionally calling bpf_sock_ops program when packet is retransmitted
- optionally calling bpf_sock_ops program when TCP state changes
- access to tclass and sk_txhash
- new selftest
2) div/mod exception handling, from Daniel.
One of the ugly leftovers from the early eBPF days is that div/mod
operations based on registers have a hard-coded src_reg == 0 test
in the interpreter as well as in JIT code generators that would
return from the BPF program with exit code 0. This was basically
adopted from cBPF interpreter for historical reasons.
There are multiple reasons why this is very suboptimal and prone
to bugs. To name one: the return code mapping for such abnormal
program exit of 0 does not always match with a suitable program
type's exit code mapping. For example, '0' in tc means action 'ok'
where the packet gets passed further up the stack, which is just
undesirable for such cases (e.g. when implementing policy) and
also does not match with other program types.
After considering _four_ different ways to address the problem,
we adapt the same behavior as on some major archs like ARMv8:
X div 0 results in 0, and X mod 0 results in X. aarch64 and
aarch32 ISA do not generate any traps or otherwise aborts
of program execution for unsigned divides.
Given the options, it seems the most suitable from
all of them, also since major archs have similar schemes in
place. Given this is all in the realm of undefined behavior,
we still have the option to adapt if deemed necessary.
3) sockmap sample refactoring, from John.
4) lpm map get_next_key fixes, from Yonghong.
5) test cleanups, from Alexei and Prashant.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Jeff Kirsher says:
====================
10GbE Intel Wired LAN Driver Updates 2018-01-26
This series contains updates to ixgbe and ixgbevf.
Emil updates ixgbevf to match ixgbe functionality, starting with the
consolidating of functions that represent logical steps in the receive
process so we can later update them more easily. Updated ixgbevf to
only synchronize the length of the frame, which will typically be the
MTU or smaller. Updated the VF driver to use the length of the packet
instead of the DD status bit to determine if a new descriptor is ready
to be processed, which saves on reads and we can save time on
initialization. Added support for DMA_ATTR_SKIP_CPU_SYNC/WEAK_ORDERING
to help improve performance on some platforms. Updated the VF driver to
do bulk updates of the page reference count instead of just incrementing
it by one reference at a time. Updated the VF driver to only go through
the region of the receive ring that was designated to be cleaned up,
rather than process the entire ring.
Colin Ian King adds the use of ARRAY_SIZE() on various arrays.
Miroslav Lichvar fixes an issue where ethtool was reporting timestamping
filters unsupported for X550, which is incorrect.
Paul adds support for reporting 5G link speed for some devices.
Dan Carpenter fixes a typo where && was used when it should have been
||.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The "return 0" instruction follows other return instruction
and it makes it impossible to execute, hence remove it.
Fixes: 00fc0c51e3 ("rocker: Change world_ops API and implementation to be switchdev independant")
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Yonghong Song says:
====================
A kernel page fault which happens in lpm map trie_get_next_key is reported
by syzbot and Eric. The issue was introduced by commit b471f2f1de
("bpf: implement MAP_GET_NEXT_KEY command for LPM_TRIE map").
Patch #1 fixed the issue in the kernel and patch #2 adds a multithreaded
test case in tools/testing/selftests/bpf/test_lpm_map.
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The new test will spawn four threads, doing map update, delete, lookup
and get_next_key in parallel. It is able to reproduce the issue in the
previous commit found by syzbot and Eric Dumazet.
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Commit b471f2f1de ("bpf: implement MAP_GET_NEXT_KEY command
for LPM_TRIE map") introduces a bug likes below:
if (!rcu_dereference(trie->root))
return -ENOENT;
if (!key || key->prefixlen > trie->max_prefixlen) {
root = &trie->root;
goto find_leftmost;
}
......
find_leftmost:
for (node = rcu_dereference(*root); node;) {
In the code after label find_leftmost, it is assumed
that *root should not be NULL, but it is not true as
it is possbile trie->root is changed to NULL by an
asynchronous delete operation.
The issue is reported by syzbot and Eric Dumazet with the
below error log:
......
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
(ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 8033 Comm: syz-executor3 Not tainted 4.15.0-rc8+ #4
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:trie_get_next_key+0x3c2/0xf10 kernel/bpf/lpm_trie.c:682
......
This patch fixed the issue by use local rcu_dereferenced
pointer instead of *(&trie->root) later on.
Fixes: b471f2f1de ("bpf: implement MAP_GET_NEXT_KEY command or LPM_TRIE map")
Reported-by: syzbot <syzkaller@googlegroups.com>
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Daniel Borkmann says:
====================
This set contains a small cleanup in cBPF prologue generation and
otherwise fixes an outstanding issue related to BPF to BPF calls
and exception handling. For details please see related patches.
Last but not least, BPF selftests is extended with several new
test cases.
Thanks!
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Update selftests to relfect recent changes and add various new
test cases.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Since we've changed div/mod exception handling for src_reg in
eBPF verifier itself, remove the leftovers from arm32 JIT.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Shubham Bansal <illusionist.neo@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The verifier in both cBPF and eBPF reject div/mod by 0 imm,
so this can never load. Remove emitting such test and reject
it from being JITed instead (the latter is actually also not
needed, but given practice in sparc64, ppc64 today, so
doesn't hurt to add it here either).
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Daney <david.daney@cavium.com>
Reviewed-by: David Daney <david.daney@cavium.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Eric Dumazet