Private part of allocation is never big enough to warrant size_t.
Space savings:
add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-10 (-10)
function old new delta
alloc_netdev_mqs 1120 1110 -10
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Zerocopy skbs frags are copied when the skb is looped to a local sock.
Commit 1080e512d4 ("net: orphan frags on receive") introduced calls
to skb_orphan_frags to deliver_skb and __netif_receive_skb for this.
With msg_zerocopy, these skbs can also exist in the tx path and thus
loop from dev_queue_xmit_nit. This already calls deliver_skb in its
loop. But it does not orphan before a separate pt_prev->func().
Add the missing skb_orphan_frags_rx.
Changes
v1->v2: handle skb_orphan_frags_rx failure
Fixes: 1f8b977ab3 ("sock: enable MSG_ZEROCOPY")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since XDP's view of the packet includes the MAC header, moving the start-
of-packet with bpf_xdp_adjust_head needs to also update the offset of the
MAC header (which is relative to skb->head, not to the skb->data that was
changed).
Without this, tcpdump sees packets starting from the old MAC header rather
than the new one, at least in my tests on the loopback device.
Fixes: b5cdae3291 ("net: Generic XDP")
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
do_xdp_generic must be called inside rcu critical section with preempt
disabled to ensure BPF programs are valid and per-cpu variables used
for redirect operations are consistent. This patch ensures this is true
and fixes the splat below.
The netif_receive_skb_internal() code path is now broken into two rcu
critical sections. I decided it was better to limit the preempt_enable/disable
block to just the xdp static key portion and the fallout is more
rcu_read_lock/unlock calls. Seems like the best option to me.
[ 607.596901] =============================
[ 607.596906] WARNING: suspicious RCU usage
[ 607.596912] 4.13.0-rc4+ #570 Not tainted
[ 607.596917] -----------------------------
[ 607.596923] net/core/dev.c:3948 suspicious rcu_dereference_check() usage!
[ 607.596927]
[ 607.596927] other info that might help us debug this:
[ 607.596927]
[ 607.596933]
[ 607.596933] rcu_scheduler_active = 2, debug_locks = 1
[ 607.596938] 2 locks held by pool/14624:
[ 607.596943] #0: (rcu_read_lock_bh){......}, at: [<ffffffff95445ffd>] ip_finish_output2+0x14d/0x890
[ 607.596973] #1: (rcu_read_lock_bh){......}, at: [<ffffffff953c8e3a>] __dev_queue_xmit+0x14a/0xfd0
[ 607.597000]
[ 607.597000] stack backtrace:
[ 607.597006] CPU: 5 PID: 14624 Comm: pool Not tainted 4.13.0-rc4+ #570
[ 607.597011] Hardware name: Dell Inc. Precision Tower 5810/0HHV7N, BIOS A17 03/01/2017
[ 607.597016] Call Trace:
[ 607.597027] dump_stack+0x67/0x92
[ 607.597040] lockdep_rcu_suspicious+0xdd/0x110
[ 607.597054] do_xdp_generic+0x313/0xa50
[ 607.597068] ? time_hardirqs_on+0x5b/0x150
[ 607.597076] ? mark_held_locks+0x6b/0xc0
[ 607.597088] ? netdev_pick_tx+0x150/0x150
[ 607.597117] netif_rx_internal+0x205/0x3f0
[ 607.597127] ? do_xdp_generic+0xa50/0xa50
[ 607.597144] ? lock_downgrade+0x2b0/0x2b0
[ 607.597158] ? __lock_is_held+0x93/0x100
[ 607.597187] netif_rx+0x119/0x190
[ 607.597202] loopback_xmit+0xfd/0x1b0
[ 607.597214] dev_hard_start_xmit+0x127/0x4e0
Fixes: d445516966 ("net: xdp: support xdp generic on virtual devices")
Fixes: b5cdae3291 ("net: Generic XDP")
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The mlxsw driver relies on NETDEV_CHANGEUPPER events to configure the
device in case a port is enslaved to a master netdev such as bridge or
bond.
Since the driver ignores events unrelated to its ports and their
uppers, it's possible to engineer situations in which the device's data
path differs from the kernel's.
One example to such a situation is when a port is enslaved to a bond
that is already enslaved to a bridge. When the bond was enslaved the
driver ignored the event - as the bond wasn't one of its uppers - and
therefore a bridge port instance isn't created in the device.
Until such configurations are supported forbid them by checking that the
upper device doesn't have uppers of its own.
Fixes: 0d65fc1304 ("mlxsw: spectrum: Implement LAG port join/leave")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Nogah Frankel <nogahf@mellanox.com>
Tested-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Noticed that busy_poll_stop() also invoke the drivers napi->poll()
function pointer, but didn't have an associated call to trace_napi_poll()
like all other call sites.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If the xdp_do_generic_redirect() call fails, it trigger the
trace_xdp_exception tracepoint. It seems better to use the same
tracepoint trace_xdp_redirect, as the native xdp_do_redirect{,_map} does.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch tries to export some generic xdp helpers to drivers. This
can let driver to do XDP for a specific skb. This is useful for the
case when the packet is hard to be processed at page level directly
(e.g jumbo/GSO frame).
With this patch, there's no need for driver to forbid the XDP set when
configuration is not suitable. Instead, it can defer the XDP for
packets that is hard to be processed directly after skb is created.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Because we remove the UFO support, we will also remove the
CHECKSUM_UNNECESSARY check in skb_needs_check().
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The UDP offload conflict is dealt with by simply taking what is
in net-next where we have removed all of the UFO handling code
entirely.
The TCP conflict was a case of local variables in a function
being removed from both net and net-next.
In netvsc we had an assignment right next to where a missing
set of u64 stats sync object inits were added.
Signed-off-by: David S. Miller <davem@davemloft.net>
skb_warn_bad_offload triggers a warning when an skb enters the GSO
stack at __skb_gso_segment that does not have CHECKSUM_PARTIAL
checksum offload set.
Commit b2504a5dbe ("net: reduce skb_warn_bad_offload() noise")
observed that SKB_GSO_DODGY producers can trigger the check and
that passing those packets through the GSO handlers will fix it
up. But, the software UFO handler will set ip_summed to
CHECKSUM_NONE.
When __skb_gso_segment is called from the receive path, this
triggers the warning again.
Make UFO set CHECKSUM_UNNECESSARY instead of CHECKSUM_NONE. On
Tx these two are equivalent. On Rx, this better matches the
skb state (checksum computed), as CHECKSUM_NONE here means no
checksum computed.
See also this thread for context:
http://patchwork.ozlabs.org/patch/799015/
Fixes: b2504a5dbe ("net: reduce skb_warn_bad_offload() noise")
Signed-off-by: Willem de Bruijn <willemb@google.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>
NETIF_F_RX_UDP_TUNNEL_PORT is special, in that we need to do more than
just flip the bit in dev->features. When disabling we must also clear
currently offloaded ports from the device, and when enabling we must
tell the device to offload the ports it can.
Because vxlan stores its sockets in a hashtable and they are inserted at
the head of per-bucket lists, switching the feature off and then on can
result in a different set of ports being offloaded (depending on the
HW's limits).
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds a new netdevice feature, so that the offloading of RX port for
UDP tunnels can be disabled by the administrator on some netdevices,
using the "rx-udp_tunnel-port-offload" feature in ethtool.
This feature is set for all devices that provide ndo_udp_tunnel_add.
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is no useful return value from dev_close. All paths return 0.
Change dev_close and helper functions to void.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for redirect to xdp generic creating a fall back for
devices that do not yet have support and allowing test infrastructure
using veth pairs to be built.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Tested-by: Andy Gospodarek <andy@greyhouse.net>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
XDP generic allows users to test XDP programs and/or run them with
degraded performance on devices that do not yet support XDP. For
testing I typically test eBPF programs using a set of veth devices.
This allows testing topologies that would otherwise be difficult to
setup especially in the early stages of development.
This patch adds a xdp generic hook to the netif_rx_internal()
function which is called from dev_forward_skb(). With this addition
attaching XDP programs to veth devices works as expected! Also I
noticed multiple drivers using netif_rx(). These devices will also
benefit and generic XDP will work for them as well.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Tested-by: Andy Gospodarek <andy@greyhouse.net>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
__GFP_REPEAT was designed to allow retry-but-eventually-fail semantic to
the page allocator. This has been true but only for allocations
requests larger than PAGE_ALLOC_COSTLY_ORDER. It has been always
ignored for smaller sizes. This is a bit unfortunate because there is
no way to express the same semantic for those requests and they are
considered too important to fail so they might end up looping in the
page allocator for ever, similarly to GFP_NOFAIL requests.
Now that the whole tree has been cleaned up and accidental or misled
usage of __GFP_REPEAT flag has been removed for !costly requests we can
give the original flag a better name and more importantly a more useful
semantic. Let's rename it to __GFP_RETRY_MAYFAIL which tells the user
that the allocator would try really hard but there is no promise of a
success. This will work independent of the order and overrides the
default allocator behavior. Page allocator users have several levels of
guarantee vs. cost options (take GFP_KERNEL as an example)
- GFP_KERNEL & ~__GFP_RECLAIM - optimistic allocation without _any_
attempt to free memory at all. The most light weight mode which even
doesn't kick the background reclaim. Should be used carefully because
it might deplete the memory and the next user might hit the more
aggressive reclaim
- GFP_KERNEL & ~__GFP_DIRECT_RECLAIM (or GFP_NOWAIT)- optimistic
allocation without any attempt to free memory from the current
context but can wake kswapd to reclaim memory if the zone is below
the low watermark. Can be used from either atomic contexts or when
the request is a performance optimization and there is another
fallback for a slow path.
- (GFP_KERNEL|__GFP_HIGH) & ~__GFP_DIRECT_RECLAIM (aka GFP_ATOMIC) -
non sleeping allocation with an expensive fallback so it can access
some portion of memory reserves. Usually used from interrupt/bh
context with an expensive slow path fallback.
- GFP_KERNEL - both background and direct reclaim are allowed and the
_default_ page allocator behavior is used. That means that !costly
allocation requests are basically nofail but there is no guarantee of
that behavior so failures have to be checked properly by callers
(e.g. OOM killer victim is allowed to fail currently).
- GFP_KERNEL | __GFP_NORETRY - overrides the default allocator behavior
and all allocation requests fail early rather than cause disruptive
reclaim (one round of reclaim in this implementation). The OOM killer
is not invoked.
- GFP_KERNEL | __GFP_RETRY_MAYFAIL - overrides the default allocator
behavior and all allocation requests try really hard. The request
will fail if the reclaim cannot make any progress. The OOM killer
won't be triggered.
- GFP_KERNEL | __GFP_NOFAIL - overrides the default allocator behavior
and all allocation requests will loop endlessly until they succeed.
This might be really dangerous especially for larger orders.
Existing users of __GFP_REPEAT are changed to __GFP_RETRY_MAYFAIL
because they already had their semantic. No new users are added.
__alloc_pages_slowpath is changed to bail out for __GFP_RETRY_MAYFAIL if
there is no progress and we have already passed the OOM point.
This means that all the reclaim opportunities have been exhausted except
the most disruptive one (the OOM killer) and a user defined fallback
behavior is more sensible than keep retrying in the page allocator.
[akpm@linux-foundation.org: fix arch/sparc/kernel/mdesc.c]
[mhocko@suse.com: semantic fix]
Link: http://lkml.kernel.org/r/20170626123847.GM11534@dhcp22.suse.cz
[mhocko@kernel.org: address other thing spotted by Vlastimil]
Link: http://lkml.kernel.org/r/20170626124233.GN11534@dhcp22.suse.cz
Link: http://lkml.kernel.org/r/20170623085345.11304-3-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alex Belits <alex.belits@cavium.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: NeilBrown <neilb@suse.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
As Hongjun/Nicolas summarized in their original patch:
"
When a device changes from one netns to another, it's first unregistered,
then the netns reference is updated and the dev is registered in the new
netns. Thus, when a slave moves to another netns, it is first
unregistered. This triggers a NETDEV_UNREGISTER event which is caught by
the bonding driver. The driver calls bond_release(), which calls
dev_set_mtu() and thus triggers NETDEV_CHANGEMTU (the device is still in
the old netns).
"
This is a very special case, because the device is being unregistered
no one should still care about the NETDEV_CHANGEMTU event triggered
at this point, we can avoid broadcasting this event on this path,
and avoid touching inetdev_event()/addrconf_notify() path.
It requires to export __dev_set_mtu() to bonding driver.
Reported-by: Hongjun Li <hongjun.li@6wind.com>
Reported-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
refcount_t type and corresponding API should be
used instead of atomic_t when the variable is used as
a reference counter. This allows to avoid accidental
refcounter overflows that might lead to use-after-free
situations.
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: Hans Liljestrand <ishkamiel@gmail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David Windsor <dwindsor@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Recently I started seeing warnings about pages with refcount -1. The
problem was traced to packets being reused after their head was merged into
a GRO packet by skb_gro_receive(). While bisecting the issue pointed to
commit c21b48cc1b ("net: adjust skb->truesize in ___pskb_trim()") and
I have never seen it on a kernel with it reverted, I believe the real
problem appeared earlier when the option to merge head frag in GRO was
implemented.
Handling NAPI_GRO_FREE_STOLEN_HEAD state was only added to GRO_MERGED_FREE
branch of napi_skb_finish() so that if the driver uses napi_gro_frags()
and head is merged (which in my case happens after the skb_condense()
call added by the commit mentioned above), the skb is reused including the
head that has been merged. As a result, we release the page reference
twice and eventually end up with negative page refcount.
To fix the problem, handle NAPI_GRO_FREE_STOLEN_HEAD in napi_frags_finish()
the same way it's done in napi_skb_finish().
Fixes: d7e8883cfc ("net: make GRO aware of skb->head_frag")
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Similar to the fix provided by Dominik Heidler in commit
9b3dc0a17d ("l2tp: cast l2tp traffic counter to unsigned")
we need to take care of 32bit kernels in dev_get_stats().
When using atomic_long_read(), we add a 'long' to u64 and
might misinterpret high order bit, unless we cast to unsigned.
Fixes: caf586e5f2 ("net: add a core netdev->rx_dropped counter")
Fixes: 015f0688f5 ("net: net: add a core netdev->tx_dropped counter")
Fixes: 6e7333d315 ("net: add rx_nohandler stat counter")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Extend the XDP_ATTACHED_* values to include offloaded mode.
Let drivers report whether program is installed in the driver
or the HW by changing the prog_attached field from bool to
u8 (type of the netlink attribute).
Exploit the fact that the value of XDP_ATTACHED_DRV is 1,
therefore since all drivers currently assign the mode with
double negation:
mode = !!xdp_prog;
no drivers have to be modified.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add an installation-time flag for requesting that the program
be installed only if it can be offloaded to HW.
Internally new command for ndo_xdp is added, this way we avoid
putting checks into drivers since they all return -EINVAL on
an unknown command.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pass XDP flags to the xdp ndo. This will allow drivers to look
at the mode flags and make decisions about offload.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Two entries being added at the same time to the IFLA
policy table, whilst parallel bug fixes to decnet
routing dst handling overlapping with the dst gc removal
in net-next.
Signed-off-by: David S. Miller <davem@davemloft.net>
Since commit 217f697436 ("net: busy-poll: allow preemption in
sk_busy_loop()") there is an explicit do_softirq() invocation after
local_bh_enable() has been invoked.
I don't understand why we need this because local_bh_enable() will
invoke do_softirq() once the softirq counter reached zero and we have
softirq-related work pending.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch removes all dst gc related code and all the dst free
functions
Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Expose prog_id through IFLA_XDP_PROG_ID. This patch
makes modification to generic_xdp. The later patches will
modify other xdp-supported drivers.
prog_id is added to struct net_dev_xdp.
iproute2 patch will be followed. Here is how the 'ip link'
will look like:
> ip link show eth0
3: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 xdp(prog_id:1) qdisc fq_codel state UP mode DEFAULT group default qlen 1000
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes uninitialized symbol warning that
got introduced by the following commit
773fc8f6e8 ("net: rps: send out pending IPI's on CPU hotplug")
Signed-off-by: Ashwanth Goli <ashwanth@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
IPI's from the victim cpu are not handled in dev_cpu_callback.
So these pending IPI's would be sent to the remote cpu only when
NET_RX is scheduled on the victim cpu and since this trigger is
unpredictable it would result in packet latencies on the remote cpu.
This patch add support to send the pending ipi's of victim cpu.
Signed-off-by: Ashwanth Goli <ashwanth@codeaurora.org>
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>
KMSAN reported a use of uninitialized memory in dev_set_alias(),
which was caused by calling strlcpy() (which in turn called strlen())
on the user-supplied non-terminated string.
Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is need to instruct the HW offloaded path to push certain matched
packets to cpu/kernel for further analysis. So this patch introduces a
new TRAP control action to TC.
For kernel datapath, this action does not make much sense. So with the
same logic as in HW, new TRAP behaves similar to STOLEN. The skb is just
dropped in the datapath (and virtually ejected to an upper level, which
does not exist in case of kernel).
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
When netdev events happen, a rtnetlink_event() handler will send
messages for every event in it's white list. These messages contain
current information about a particular device, but they do not include
the iformation about which event just happened. So, it is impossible
to tell what just happend for these events.
This patch adds a new extension to RTM_NEWLINK message called IFLA_EVENT
that would have an encoding of event that triggered this
message. This would allow the the message consumer to easily determine
if it needs to perform certain actions.
Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since commit b68581778c ("net: Make skb->skb_iif always track
skb->dev") skbs don't have the original index of the interface which
received the packet. This information is now needed for a new control
message related to hardware timestamping.
Instead of adding a new field to skb, we can find the device by the NAPI
ID if it is available, i.e. CONFIG_NET_RX_BUSY_POLL is enabled and the
driver is using NAPI. Add dev_get_by_napi_id() and also skb_napi_id() to
hide the CONFIG_NET_RX_BUSY_POLL ifdef.
CC: Richard Cochran <richardcochran@gmail.com>
Suggested-by: Willem de Bruijn <willemb@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
skb_csum_hwoffload_help() uses netdev features and skb->csum_not_inet to
determine if skb needs software computation of Internet Checksum or crc32c
(or nothing, if this computation can be done by the hardware). Use it in
place of skb_checksum_help() in validate_xmit_skb() to avoid corruption
of non-GSO SCTP packets having skb->ip_summed equal to CHECKSUM_PARTIAL.
While at it, remove references to skb_csum_off_chk* functions, since they
are not present anymore in Linux _ see commit cf53b1da73 ("Revert
"net: Add driver helper functions to determine checksum offloadability"").
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
skb->csum_not_inet carries the indication on which algorithm is needed to
compute checksum on skb in the transmit path, when skb->ip_summed is equal
to CHECKSUM_PARTIAL. If skb carries a SCTP packet and crc32c hasn't been
yet written in L4 header, skb->csum_not_inet is assigned to 1; otherwise,
assume Internet Checksum is needed and thus set skb->csum_not_inet to 0.
Suggested-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This bit was introduced with commit 5a21232983 ("net: Support for
csum_bad in skbuff") to reduce the stack workload when processing RX
packets carrying a wrong Internet Checksum. Up to now, only one driver and
GRO core are setting it.
Suggested-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
skb_crc32c_csum_help is like skb_checksum_help, but it is designed for
checksumming SCTP packets using crc32c (see RFC3309), provided that
libcrc32c.ko has been loaded before. In case libcrc32c is not loaded,
invoking skb_crc32c_csum_help on a skb results in one the following
printouts:
warn_crc32c_csum_update: attempt to compute crc32c without libcrc32c.ko
warn_crc32c_csum_combine: attempt to compute crc32c without libcrc32c.ko
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move tc_classify function to cls_api.c where it belongs, rename it to
fit the namespace.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While working on the iproute2 generic XDP frontend, I noticed that
as of right now it's possible to have native *and* generic XDP
programs loaded both at the same time for the case when a driver
supports native XDP.
The intended model for generic XDP from b5cdae3291 ("net: Generic
XDP") is, however, that only one out of the two can be present at
once which is also indicated as such in the XDP netlink dump part.
The main rationale for generic XDP is to ease accessibility (in
case a driver does not yet have XDP support) and to generically
provide a semantical model as an example for driver developers
wanting to add XDP support. The generic XDP option for an XDP
aware driver can still be useful for comparing and testing both
implementations.
However, it is not intended to have a second XDP processing stage
or layer with exactly the same functionality of the first native
stage. Only reason could be to have a partial fallback for future
XDP features that are not supported yet in the native implementation
and we probably also shouldn't strive for such fallback and instead
encourage native feature support in the first place. Given there's
currently no such fallback issue or use case, lets not go there yet
if we don't need to.
Therefore, change semantics for loading XDP and bail out if the
user tries to load a generic XDP program when a native one is
present and vice versa. Another alternative to bailing out would
be to handle the transition from one flavor to another gracefully,
but that would require to bring the device down, exchange both
types of programs, and bring it up again in order to avoid a tiny
window where a packet could hit both hooks. Given this complicates
the logic for just a debugging feature in the native case, I went
with the simpler variant.
For the dump, remove IFLA_XDP_FLAGS that was added with b5cdae3291
and reuse IFLA_XDP_ATTACHED for indicating the mode. Dumping all
or just a subset of flags that were used for loading the XDP prog
is suboptimal in the long run since not all flags are useful for
dumping and if we start to reuse the same flag definitions for
load and dump, then we'll waste bit space. What we really just
want is to dump the mode for now.
Current IFLA_XDP_ATTACHED semantics are: nothing was installed (0),
a program is running at the native driver layer (1). Thus, add a
mode that says that a program is running at generic XDP layer (2).
Applications will handle this fine in that older binaries will
just indicate that something is attached at XDP layer, effectively
this is similar to IFLA_XDP_FLAGS attr that we would have had
modulo the redundancy.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
After commit b5cdae3291 ("net: Generic XDP") we automatically fall
back to a generic XDP variant if the driver does not support native
XDP. Allow for an option where the user can specify that always the
native XDP variant should be selected and in case it's not supported
by a driver, just bail out.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
We now have memalloc_noreclaim_{save,restore} helpers for robust setting
and clearing of PF_MEMALLOC. Let's convert the code which was using the
generic tsk_restore_flags(). No functional change.
[vbabka@suse.cz: in net/core/sock.c the hunk is missing]
Link: http://lkml.kernel.org/r/20170405074700.29871-4-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Josef Bacik <jbacik@fb.com>
Cc: Lee Duncan <lduncan@suse.com>
Cc: Chris Leech <cleech@redhat.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Boris Brezillon <boris.brezillon@free-electrons.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Wouter Verhelst <w@uter.be>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
fq_alloc_node, alloc_netdev_mqs and netif_alloc* open code kmalloc with
vmalloc fallback. Use the kvmalloc variant instead. Keep the
__GFP_REPEAT flag based on explanation from Eric:
"At the time, tests on the hardware I had in my labs showed that
vmalloc() could deliver pages spread all over the memory and that was
a small penalty (once memory is fragmented enough, not at boot time)"
The way how the code is constructed means, however, that we prefer to go
and hit the OOM killer before we fall back to the vmalloc for requests
<=32kB (with 4kB pages) in the current code. This is rather disruptive
for something that can be achived with the fallback. On the other hand
__GFP_REPEAT doesn't have any useful semantic for these requests. So
the effect of this patch is that requests which fit into 32kB will fall
back to vmalloc easier now.
Link: http://lkml.kernel.org/r/20170306103327.2766-3-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Eric Dumazet <edumazet@google.com>
Cc: David Miller <davem@davemloft.net>
Cc: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull networking updates from David Millar:
"Here are some highlights from the 2065 networking commits that
happened this development cycle:
1) XDP support for IXGBE (John Fastabend) and thunderx (Sunil Kowuri)
2) Add a generic XDP driver, so that anyone can test XDP even if they
lack a networking device whose driver has explicit XDP support
(me).
3) Sparc64 now has an eBPF JIT too (me)
4) Add a BPF program testing framework via BPF_PROG_TEST_RUN (Alexei
Starovoitov)
5) Make netfitler network namespace teardown less expensive (Florian
Westphal)
6) Add symmetric hashing support to nft_hash (Laura Garcia Liebana)
7) Implement NAPI and GRO in netvsc driver (Stephen Hemminger)
8) Support TC flower offload statistics in mlxsw (Arkadi Sharshevsky)
9) Multiqueue support in stmmac driver (Joao Pinto)
10) Remove TCP timewait recycling, it never really could possibly work
well in the real world and timestamp randomization really zaps any
hint of usability this feature had (Soheil Hassas Yeganeh)
11) Support level3 vs level4 ECMP route hashing in ipv4 (Nikolay
Aleksandrov)
12) Add socket busy poll support to epoll (Sridhar Samudrala)
13) Netlink extended ACK support (Johannes Berg, Pablo Neira Ayuso,
and several others)
14) IPSEC hw offload infrastructure (Steffen Klassert)"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2065 commits)
tipc: refactor function tipc_sk_recv_stream()
tipc: refactor function tipc_sk_recvmsg()
net: thunderx: Optimize page recycling for XDP
net: thunderx: Support for XDP header adjustment
net: thunderx: Add support for XDP_TX
net: thunderx: Add support for XDP_DROP
net: thunderx: Add basic XDP support
net: thunderx: Cleanup receive buffer allocation
net: thunderx: Optimize CQE_TX handling
net: thunderx: Optimize RBDR descriptor handling
net: thunderx: Support for page recycling
ipx: call ipxitf_put() in ioctl error path
net: sched: add helpers to handle extended actions
qed*: Fix issues in the ptp filter config implementation.
qede: Fix concurrency issue in PTP Tx path processing.
stmmac: Add support for SIMATIC IOT2000 platform
net: hns: fix ethtool_get_strings overflow in hns driver
tcp: fix wraparound issue in tcp_lp
bpf, arm64: fix jit branch offset related to ldimm64
bpf, arm64: implement jiting of BPF_XADD
...
Fix kdoc parameter spelling from extact to extack.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Drivers usually have a number of restrictions for running XDP
- most common being buffer sizes, LRO and number of rings.
Even though some drivers try to be helpful and print error
messages experience shows that users don't often consult
kernel logs on netlink errors. Try to use the new extended
ack mechanism to carry the message back to user space.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since netif_carrier_on() will do nothing if device's carrier is already
on, so it's unnecessary to do carrier status check.
It's the same for netif_carrier_off().
Signed-off-by: Zhang Shengju <zhangshengju@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Added NULL check to make __dev_kfree_skb_irq consistent with kfree
family of functions.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=195289
Signed-off-by: Myungho Jung <mhjungk@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This provides a generic SKB based non-optimized XDP path which is used
if either the driver lacks a specific XDP implementation, or the user
requests it via a new IFLA_XDP_FLAGS value named XDP_FLAGS_SKB_MODE.
It is arguable that perhaps I should have required something like
this as part of the initial XDP feature merge.
I believe this is critical for two reasons:
1) Accessibility. More people can play with XDP with less
dependencies. Yes I know we have XDP support in virtio_net, but
that just creates another depedency for learning how to use this
facility.
I wrote this to make life easier for the XDP newbies.
2) As a model for what the expected semantics are. If there is a pure
generic core implementation, it serves as a semantic example for
driver folks adding XDP support.
One thing I have not tried to address here is the issue of
XDP_PACKET_HEADROOM, thanks to Daniel for spotting that. It seems
incredibly expensive to do a skb_cow(skb, XDP_PACKET_HEADROOM) or
whatever even if the XDP program doesn't try to push headers at all.
I think we really need the verifier to somehow propagate whether
certain XDP helpers are used or not.
v5:
- Handle both negative and positive offset after running prog
- Fix mac length in XDP_TX case (Alexei)
- Use rcu_dereference_protected() in free_netdev (kbuild test robot)
v4:
- Fix MAC header adjustmnet before calling prog (David Ahern)
- Disable LRO when generic XDP is installed (Michael Chan)
- Bypass qdisc et al. on XDP_TX and record the event (Alexei)
- Do not perform generic XDP on reinjected packets (DaveM)
v3:
- Make sure XDP program sees packet at MAC header, push back MAC
header if we do XDP_TX. (Alexei)
- Elide GRO when generic XDP is in use. (Alexei)
- Add XDP_FLAG_SKB_MODE flag which the user can use to request generic
XDP even if the driver has an XDP implementation. (Alexei)
- Report whether SKB mode is in use in rtnl_xdp_fill() via XDP_FLAGS
attribute. (Daniel)
v2:
- Add some "fall through" comments in switch statements based
upon feedback from Andrew Lunn
- Use RCU for generic xdp_prog, thanks to Johannes Berg.
Tested-by: Andy Gospodarek <andy@greyhouse.net>
Tested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Steffen Klassert says:
====================
pull request (net-next): ipsec-next 2017-04-20
This adds the basic infrastructure for IPsec hardware
offloading, it creates a configuration API and adjusts
the packet path.
1) Add the needed netdev features to configure IPsec offloads.
2) Add the IPsec hardware offloading API.
3) Prepare the ESP packet path for hardware offloading.
4) Add gso handlers for esp4 and esp6, this implements
the software fallback for GSO packets.
5) Add xfrm replay handler functions for offloading.
6) Change ESP to use a synchronous crypto algorithm on
offloading, we don't have the option for asynchronous
returns when we handle IPsec at layer2.
7) Add a xfrm validate function to validate_xmit_skb. This
implements the software fallback for non GSO packets.
8) Set the inner_network and inner_transport members of
the SKB, as well as encapsulation, to reflect the actual
positions of these headers, and removes them only once
encryption is done on the payload.
From Ilan Tayari.
9) Prepare the ESP GRO codepath for hardware offloading.
10) Fix incorrect null pointer check in esp6.
From Colin Ian King.
11) Fix for the GSO software fallback path to detect the
fallback correctly.
From Ilan Tayari.
Please pull or let me know if there are problems.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Constants used for tuning are generally a bad idea, especially as hardware
changes over time. Replace the constant 2 jiffies with sysctl variable
netdev_budget_usecs to enable sysadmins to tune the softirq processing.
Also document the variable.
For example, a very fast machine might tune this to 1000 microseconds,
while my regression testing 486DX-25 needs it to be 4000 microseconds on
a nearly idle network to prevent time_squeeze from being incremented.
Version 2: changed jiffies to microseconds for predictable units.
Signed-off-by: Matthew Whitehead <tedheadster@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts were simply overlapping changes. In the net/ipv4/route.c
case the code had simply moved around a little bit and the same fix
was made in both 'net' and 'net-next'.
In the net/sched/sch_generic.c case a fix in 'net' happened at
the same time that a new argument was added to qdisc_hash_add().
Signed-off-by: David S. Miller <davem@davemloft.net>
When we do IPsec offloading, we need a fallback for
packets that were targeted to be IPsec offloaded but
rerouted to a device that does not support IPsec offload.
For that we add a function that checks the offloading
features of the sending device and and flags the
requirement of a fallback before it calls the IPsec
output function. The IPsec output function adds the IPsec
trailer and does encryption if needed.
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Since dev_change_xdp_fd() is only used in rtnetlink, which must
be built-in, there's no reason to export dev_change_xdp_fd().
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
It is not safe for one thread to modify the ->flags
of another thread as there is no locking that can protect
the update.
So tsk_restore_flags(), which takes a task pointer and modifies
the flags, is an invitation to do the wrong thing.
All current users pass "current" as the task, so no developers have
accepted that invitation. It would be best to ensure it remains
that way.
So rename tsk_restore_flags() to current_restore_flags() and don't
pass in a task_struct pointer. Always operate on current->flags.
Signed-off-by: NeilBrown <neilb@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This reverts commit def12888c1.
As per discussion between Roopa Prabhu and David Ahern, it is
advisable that we instead have the code collect the setlink triggered
events into a bitmask emitted in the IFLA_EVENT netlink attribute.
Signed-off-by: David S. Miller <davem@davemloft.net>
When netdev events happen, a rtnetlink_event() handler will send
messages for every event in it's white list. These messages contain
current information about a particular device, but they do not include
the iformation about which event just happened. The consumer of
the message has to try to infer this information. In some cases
(ex: NETDEV_NOTIFY_PEERS), that is not possible.
This patch adds a new extension to RTM_NEWLINK message called IFLA_EVENT
that would have an encoding of the which event triggered this
message. This would allow the the message consumer to easily determine
if it is interested in a particular event or not.
Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move the core functionality in sk_busy_loop() to napi_busy_loop() and
make it independent of sk.
This enables re-using this function in epoll busy loop implementation.
Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch flips the logic we were using to determine if the busy polling
has timed out. The main motivation for this is that we will need to
support two different possible timeout values in the future and by
recording the start time rather than when we would want to end we can focus
on making the end_time specific to the task be it epoll or socket based
polling.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
checking the return value of sk_busy_loop. As there are only a few
consumers of that data, and the data being checked for can be replaced
with a check for !skb_queue_empty() we might as well just pull the code
out of sk_busy_loop and place it in the spots that actually need it.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is a cleanup/fix for NAPI IDs following the changes that made it
so that sender_cpu and napi_id were doing a better job of sharing the same
location in the sk_buff.
One issue I found is that we weren't validating the napi_id as being valid
before we started trying to setup the busy polling. This change corrects
that by using the MIN_NAPI_ID value that is now used in both allocating the
NAPI IDs, as well as validating them.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When we notify peers of potential changes, it's also good to update
IGMP memberships. For example, during VM migration, updating IGMP
memberships will redirect existing multicast streams to the VM at the
new location.
Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It is now very clear that silly TCP listeners might play with
enabling/disabling timestamping while new children are added
to their accept queue.
Meaning net_enable_timestamp() can be called from BH context
while current state of the static key is not enabled.
Lets play safe and allow all contexts.
The work queue is scheduled only under the problematic cases,
which are the static key enable/disable transition, to not slow down
critical paths.
This extends and improves what we did in commit 5fa8bbda38 ("net: use
a work queue to defer net_disable_timestamp() work")
Fixes: b90e5794c5 ("net: dont call jump_label_dec from irq context")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While playing with mlx4 hardware timestamping of RX packets, I found
that some packets were received by TCP stack with a ~200 ms delay...
Since the timestamp was provided by the NIC, and my probe was added
in tcp_v4_rcv() while in BH handler, I was confident it was not
a sender issue, or a drop in the network.
This would happen with a very low probability, but hurting RPC
workloads.
A NAPI driver normally arms the IRQ after the napi_complete_done(),
after NAPI_STATE_SCHED is cleared, so that the hard irq handler can grab
it.
Problem is that if another point in the stack grabs NAPI_STATE_SCHED bit
while IRQ are not disabled, we might have later an IRQ firing and
finding this bit set, right before napi_complete_done() clears it.
This can happen with busy polling users, or if gro_flush_timeout is
used. But some other uses of napi_schedule() in drivers can cause this
as well.
thread 1 thread 2 (could be on same cpu, or not)
// busy polling or napi_watchdog()
napi_schedule();
...
napi->poll()
device polling:
read 2 packets from ring buffer
Additional 3rd packet is
available.
device hard irq
// does nothing because
NAPI_STATE_SCHED bit is owned by thread 1
napi_schedule();
napi_complete_done(napi, 2);
rearm_irq();
Note that rearm_irq() will not force the device to send an additional
IRQ for the packet it already signaled (3rd packet in my example)
This patch adds a new NAPI_STATE_MISSED bit, that napi_schedule_prep()
can set if it could not grab NAPI_STATE_SCHED
Then napi_complete_done() properly reschedules the napi to make sure
we do not miss something.
Since we manipulate multiple bits at once, use cmpxchg() like in
sk_busy_loop() to provide proper transactions.
In v2, I changed napi_watchdog() to use a relaxed variant of
napi_schedule_prep() : No need to set NAPI_STATE_MISSED from this point.
In v3, I added more details in the changelog and clears
NAPI_STATE_MISSED in busy_poll_stop()
In v4, I added the ideas given by Alexander Duyck in v3 review
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
hrtimer handlers run with masked hard IRQ, we can therefore
use napi_schedule_irqoff()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Steffen Klassert says:
====================
pull request (net-next): ipsec-next 2017-02-16
1) Make struct xfrm_input_afinfo const, nothing writes to it.
From Florian Westphal.
2) Remove all places that write to the afinfo policy backend
and make the struct const then.
From Florian Westphal.
3) Prepare for packet consuming gro callbacks and add
ESP GRO handlers. ESP packets can be decapsulated
at the GRO layer then. It saves a round through
the stack for each ESP packet.
Please note that this has a merge coflict between commit
63fca65d08 ("net: add confirm_neigh method to dst_ops")
from net-next and
3d7d25a68e ("xfrm: policy: remove garbage_collect callback")
a2817d8b27 ("xfrm: policy: remove family field")
from ipsec-next.
The conflict can be solved as it is done in linux-next.
Please pull or let me know if there are problems.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 79e7fff47b ("net: remove support for per driver
ndo_busy_poll()") made them obsolete.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes multiple occurrences of checkpatch WARNING: Missing
a blank line after declarations.
Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix multiple occurrences of checkpatch warning. WARNING: Block
comments use * on subsequent lines. Also make comment blocks
more uniform.
Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes two trivial whitespace errors. Brace should be
on the previous line and trailing statements should be on next line.
Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes multiple occurrences of space before tabs warnings.
More lines of code were moved than required to keep kernel-doc
comments uniform.
Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
The conflict was an interaction between a bug fix in the
netvsc driver in 'net' and an optimization of the RX path
in 'net-next'.
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit 18bfb924f0 ("net: introduce default neigh_construct/destroy
ndo calls for L2 upper devices") we added these ndos to stacked devices
such as team and bond, so that calls will be propagated to mlxsw.
However, previous commit removed the reliance on these ndos and no new
users of these ndos have appeared since above mentioned commit. We can
therefore safely remove this dead code.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
All __napi_complete() callers have been converted to
use the more standard napi_complete_done(),
we can now remove this NAPI method for good.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
My recent change missed fact that UFO would perform a complete
UDP checksum before segmenting in frags.
In this case skb->ip_summed is set to CHECKSUM_NONE.
We need to add this valid case to skb_needs_check()
Fixes: b2504a5dbe ("net: reduce skb_warn_bad_offload() noise")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We added generic support for busy polling in NAPI layer in linux-4.5
No network driver uses ndo_busy_poll() anymore, we can get rid
of the pointer in struct net_device_ops, and its use in sk_busy_loop()
Saves NETIF_F_BUSY_POLL features bit.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Dmitry reported warnings occurring in __skb_gso_segment() [1]
All SKB_GSO_DODGY producers can allow user space to feed
packets that trigger the current check.
We could prevent them from doing so, rejecting packets, but
this might add regressions to existing programs.
It turns out our SKB_GSO_DODGY handlers properly set up checksum
information that is needed anyway when packets needs to be segmented.
By checking again skb_needs_check() after skb_mac_gso_segment(),
we should remove these pesky warnings, at a very minor cost.
With help from Willem de Bruijn
[1]
WARNING: CPU: 1 PID: 6768 at net/core/dev.c:2439 skb_warn_bad_offload+0x2af/0x390 net/core/dev.c:2434
lo: caps=(0x000000a2803b7c69, 0x0000000000000000) len=138 data_len=0 gso_size=15883 gso_type=4 ip_summed=0
Kernel panic - not syncing: panic_on_warn set ...
CPU: 1 PID: 6768 Comm: syz-executor1 Not tainted 4.9.0 #5
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
ffff8801c063ecd8 ffffffff82346bdf ffffffff00000001 1ffff100380c7d2e
ffffed00380c7d26 0000000041b58ab3 ffffffff84b37e38 ffffffff823468f1
ffffffff84820740 ffffffff84f289c0 dffffc0000000000 ffff8801c063ee20
Call Trace:
[<ffffffff82346bdf>] __dump_stack lib/dump_stack.c:15 [inline]
[<ffffffff82346bdf>] dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
[<ffffffff81827e34>] panic+0x1fb/0x412 kernel/panic.c:179
[<ffffffff8141f704>] __warn+0x1c4/0x1e0 kernel/panic.c:542
[<ffffffff8141f7e5>] warn_slowpath_fmt+0xc5/0x100 kernel/panic.c:565
[<ffffffff8356cbaf>] skb_warn_bad_offload+0x2af/0x390 net/core/dev.c:2434
[<ffffffff83585cd2>] __skb_gso_segment+0x482/0x780 net/core/dev.c:2706
[<ffffffff83586f19>] skb_gso_segment include/linux/netdevice.h:3985 [inline]
[<ffffffff83586f19>] validate_xmit_skb+0x5c9/0xc20 net/core/dev.c:2969
[<ffffffff835892bb>] __dev_queue_xmit+0xe6b/0x1e70 net/core/dev.c:3383
[<ffffffff8358a2d7>] dev_queue_xmit+0x17/0x20 net/core/dev.c:3424
[<ffffffff83ad161d>] packet_snd net/packet/af_packet.c:2930 [inline]
[<ffffffff83ad161d>] packet_sendmsg+0x32ed/0x4d30 net/packet/af_packet.c:2955
[<ffffffff834f0aaa>] sock_sendmsg_nosec net/socket.c:621 [inline]
[<ffffffff834f0aaa>] sock_sendmsg+0xca/0x110 net/socket.c:631
[<ffffffff834f329a>] ___sys_sendmsg+0x8fa/0x9f0 net/socket.c:1954
[<ffffffff834f5e58>] __sys_sendmsg+0x138/0x300 net/socket.c:1988
[<ffffffff834f604d>] SYSC_sendmsg net/socket.c:1999 [inline]
[<ffffffff834f604d>] SyS_sendmsg+0x2d/0x50 net/socket.c:1995
[<ffffffff84371941>] entry_SYSCALL_64_fastpath+0x1f/0xc2
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Steffen Klassert says:
====================
pull request (net-next): ipsec-next 2017-02-01
1) Some typo fixes, from Alexander Alemayhu.
2) Don't acquire state lock in get_mtu functions.
The only rece against a dead state does not matter.
From Florian Westphal.
3) Remove xfrm4_state_fini, it is unused for more than
10 years. From Florian Westphal.
4) Various rcu usage improvements. From Florian Westphal.
5) Properly handle crypto arrors in ah4/ah6.
From Gilad Ben-Yossef.
6) Try to avoid skb linearization in esp4 and esp6.
7) The esp trailer is now set up in different places,
add a helper for this.
8) With the upcomming usage of gro_cells in IPsec,
a gro merged skb can have a secpath. Drop it
before freeing or reusing the skb.
9) Add a xfrm dummy network device for napi. With
this we can use gro_cells from within xfrm,
it allows IPsec GRO without impact on the generic
networking code.
Please pull or let me know if there are problems.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
With a followup patch, a gro merged skb can have a secpath.
So drop it before freeing or reusing the skb.
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
netdev_rx_handler_register() checks to see if the handler is already
busy which was recently separated into netdev_is_rx_handler_busy(). So
use the same function inside register() to avoid code duplication.
Essentially this change should be a no-op
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ashizuka reported a highmem oddity and sent a patch for freescale
fec driver.
But the problem root cause is that core networking stack
must ensure no skb with highmem fragment is ever sent through
a device that does not assert NETIF_F_HIGHDMA in its features.
We need to call illegal_highdma() from harmonize_features()
regardless of CSUM checks.
Fixes: ec5f061564 ("net: Kill link between CSUM and SG features.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Pravin Shelar <pshelar@ovn.org>
Reported-by: "Ashizuka, Yuusuke" <ashiduka@jp.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
netif_wake_subqueue() is duplicating the same thing that netif_tx_wake_queue()
does, so make it call it directly after looking up the queue from the index.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On 32bit arches, (skb->end - skb->data) is not 'unsigned int',
so we shall use min_t() instead of min() to avoid a compiler error.
Fixes: 1272ce87fa ("gro: Enter slow-path if there is no tailroom")
Reported-by: kernel test robot <fengguang.wu@intel.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The GRO path has a fast-path where we avoid calling pskb_may_pull
and pskb_expand by directly accessing frag0. However, this should
only be done if we have enough tailroom in the skb as otherwise
we'll have to expand it later anyway.
This patch adds the check by capping frag0_len with the skb tailroom.
Fixes: cb18978cbf ("gro: Open-code final pskb_may_pull")
Reported-by: Slava Shwartsman <slavash@mellanox.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Field tc_at is used only within tc actions to distinguish ingress from
egress processing. A single bit is sufficient for this purpose.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Extract the remaining two fields from tc_verd and remove the __u16
completely. TC_AT and TC_FROM are converted to equivalent two-bit
integer fields tc_at and tc_from. Where possible, use existing
helper skb_at_tc_ingress when reading tc_at. Introduce helper
skb_reset_tc to clear fields.
Not documenting tc_from and tc_at, because they will be replaced
with single bit fields in follow-on patches.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Packets sent by the IFB device skip subsequent tc classification.
A single bit governs this state. Move it out of tc_verd in
anticipation of removing that __u16 completely.
The new bitfield tc_skip_classify temporarily uses one bit of a
hole, until tc_verd is removed completely in a follow-up patch.
Remove the bit hole comment. It could be 2, 3, 4 or 5 bits long.
With that many options, little value in documenting it.
Introduce a helper function to deduplicate the logic in the two
sites that check this bit.
The field tc_skip_classify is set only in IFB on skbs cloned in
act_mirred, so original packet sources do not have to clear the
bit when reusing packets (notably, pktgen and octeon).
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Oftenly, introducing side effects on packet processing on the other half
of the stack by adjusting one of TX/RX via sysctl is not desirable.
There are cases of demand for asymmetric, orthogonal configurability.
This holds true especially for nodes where RPS for RFS usage on top is
configured and therefore use the 'old dev_weight'. This is quite a
common base configuration setup nowadays, even with NICs of superior processing
support (e.g. aRFS).
A good example use case are nodes acting as noSQL data bases with a
large number of tiny requests and rather fewer but large packets as responses.
It's affordable to have large budget and rx dev_weights for the
requests. But as a side effect having this large a number on TX
processed in one run can overwhelm drivers.
This patch therefore introduces an independent configurability via sysctl to
userland.
Signed-off-by: Matthias Tafelmeier <matthias.tafelmeier@gmx.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
ktime is a union because the initial implementation stored the time in
scalar nanoseconds on 64 bit machine and in a endianess optimized timespec
variant for 32bit machines. The Y2038 cleanup removed the timespec variant
and switched everything to scalar nanoseconds. The union remained, but
become completely pointless.
Get rid of the union and just keep ktime_t as simple typedef of type s64.
The conversion was done with coccinelle and some manual mopping up.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
This was entirely automated, using the script by Al:
PATT='^[[:blank:]]*#[[:blank:]]*include[[:blank:]]*<asm/uaccess.h>'
sed -i -e "s!$PATT!#include <linux/uaccess.h>!" \
$(git grep -l "$PATT"|grep -v ^include/linux/uaccess.h)
to do the replacement at the end of the merge window.
Requested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull smp hotplug updates from Thomas Gleixner:
"This is the final round of converting the notifier mess to the state
machine. The removal of the notifiers and the related infrastructure
will happen around rc1, as there are conversions outstanding in other
trees.
The whole exercise removed about 2000 lines of code in total and in
course of the conversion several dozen bugs got fixed. The new
mechanism allows to test almost every hotplug step standalone, so
usage sites can exercise all transitions extensively.
There is more room for improvement, like integrating all the
pointlessly different architecture mechanisms of synchronizing,
setting cpus online etc into the core code"
* 'smp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (60 commits)
tracing/rb: Init the CPU mask on allocation
soc/fsl/qbman: Convert to hotplug state machine
soc/fsl/qbman: Convert to hotplug state machine
zram: Convert to hotplug state machine
KVM/PPC/Book3S HV: Convert to hotplug state machine
arm64/cpuinfo: Convert to hotplug state machine
arm64/cpuinfo: Make hotplug notifier symmetric
mm/compaction: Convert to hotplug state machine
iommu/vt-d: Convert to hotplug state machine
mm/zswap: Convert pool to hotplug state machine
mm/zswap: Convert dst-mem to hotplug state machine
mm/zsmalloc: Convert to hotplug state machine
mm/vmstat: Convert to hotplug state machine
mm/vmstat: Avoid on each online CPU loops
mm/vmstat: Drop get_online_cpus() from init_cpu_node_state/vmstat_cpu_dead()
tracing/rb: Convert to hotplug state machine
oprofile/nmi timer: Convert to hotplug state machine
net/iucv: Use explicit clean up labels in iucv_init()
x86/pci/amd-bus: Convert to hotplug state machine
x86/oprofile/nmi: Convert to hotplug state machine
...
Pull locking updates from Ingo Molnar:
"The tree got pretty big in this development cycle, but the net effect
is pretty good:
115 files changed, 673 insertions(+), 1522 deletions(-)
The main changes were:
- Rework and generalize the mutex code to remove per arch mutex
primitives. (Peter Zijlstra)
- Add vCPU preemption support: add an interface to query the
preemption status of vCPUs and use it in locking primitives - this
optimizes paravirt performance. (Pan Xinhui, Juergen Gross,
Christian Borntraeger)
- Introduce cpu_relax_yield() and remov cpu_relax_lowlatency() to
clean up and improve the s390 lock yielding machinery and its core
kernel impact. (Christian Borntraeger)
- Micro-optimize mutexes some more. (Waiman Long)
- Reluctantly add the to-be-deprecated mutex_trylock_recursive()
interface on a temporary basis, to give the DRM code more time to
get rid of its locking hacks. Any other users will be NAK-ed on
sight. (We turned off the deprecation warning for the time being to
not pollute the build log.) (Peter Zijlstra)
- Improve the rtmutex code a bit, in light of recent long lived
bugs/races. (Thomas Gleixner)
- Misc fixes, cleanups"
* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
x86/paravirt: Fix bool return type for PVOP_CALL()
x86/paravirt: Fix native_patch()
locking/ww_mutex: Use relaxed atomics
locking/rtmutex: Explain locking rules for rt_mutex_proxy_unlock()/init_proxy_locked()
locking/rtmutex: Get rid of RT_MUTEX_OWNER_MASKALL
x86/paravirt: Optimize native pv_lock_ops.vcpu_is_preempted()
locking/mutex: Break out of expensive busy-loop on {mutex,rwsem}_spin_on_owner() when owner vCPU is preempted
locking/osq: Break out of spin-wait busy waiting loop for a preempted vCPU in osq_lock()
Documentation/virtual/kvm: Support the vCPU preemption check
x86/xen: Support the vCPU preemption check
x86/kvm: Support the vCPU preemption check
x86/kvm: Support the vCPU preemption check
kvm: Introduce kvm_write_guest_offset_cached()
locking/core, x86/paravirt: Implement vcpu_is_preempted(cpu) for KVM and Xen guests
locking/spinlocks, s390: Implement vcpu_is_preempted(cpu)
locking/core, powerpc: Implement vcpu_is_preempted(cpu)
sched/core: Introduce the vcpu_is_preempted(cpu) interface
sched/wake_q: Rename WAKE_Q to DEFINE_WAKE_Q
locking/core: Provide common cpu_relax_yield() definition
locking/mutex: Don't mark mutex_trylock_recursive() as deprecated, temporarily
...
RFS is not commonly used, so add a jump label to avoid some conditionals
in fast path.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add an IFLA_XDP_FLAGS attribute that can be passed for setting up
XDP along with IFLA_XDP_FD, which eventually allows user space to
implement typical add/replace/delete logic for programs. Right now,
calling into dev_change_xdp_fd() will always replace previous programs.
When passed XDP_FLAGS_UPDATE_IF_NOEXIST, we can handle this more
graceful when requested by returning -EBUSY in case we try to
attach a new program, but we find that another one is already
attached. This will be used by upcoming front-end for iproute2 as
well.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Typical NAPI drivers use napi_consume_skb(skb) at TX completion time.
This put skb in a percpu special queue, napi_alloc_cache, to get bulk
frees.
It turns out the queue is not flushed and hits the NAPI_SKB_CACHE_SIZE
limit quite often, with skbs that were queued hundreds of usec earlier.
I measured this can take ~6000 nsec to perform one flush.
__kfree_skb_flush() can be called from two points right now :
1) From net_tx_action(), but only for skbs that were queued to
sd->completion_queue.
-> Irrelevant for NAPI drivers in normal operation.
2) From net_rx_action(), but only under high stress or if RPS/RFS has a
pending action.
This patch changes net_rx_action() to perform the flush in all cases and
after more urgent operations happened (like kicking remote CPUS for
RPS/RFS).
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Callers of netpoll_poll_lock() own NAPI_STATE_SCHED
Callers of netpoll_poll_unlock() have BH blocked between
the NAPI_STATE_SCHED being cleared and poll_lock is released.
We can avoid the spinlock which has no contention, and use cmpxchg()
on poll_owner which we need to set anyway.
This removes a possible lockdep violation after the cited commit,
since sk_busy_loop() re-enables BH before calling busy_poll_stop()
Fixes: 217f697436 ("net: busy-poll: allow preemption in sk_busy_loop()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
NAPI drivers use napi_complete_done() or napi_complete() when
they drained RX ring and right before re-enabling device interrupts.
In busy polling, we can avoid interrupts being delivered since
we are polling RX ring in a controlled loop.
Drivers can chose to use napi_complete_done() return value
to reduce interrupts overhead while busy polling is active.
This is optional, legacy drivers should work fine even
if not updated.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Adam Belay <abelay@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Yuval Mintz <Yuval.Mintz@cavium.com>
Cc: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After commit 4cd13c21b2 ("softirq: Let ksoftirqd do its job"),
sk_busy_loop() needs a bit of care :
softirqs might be delayed since we do not allow preemption yet.
This patch adds preemptiom points in sk_busy_loop(),
and makes sure no unnecessary cache line dirtying
or atomic operations are done while looping.
A new flag is added into napi->state : NAPI_STATE_IN_BUSY_POLL
This prevents napi_complete_done() from clearing NAPIF_STATE_SCHED,
so that sk_busy_loop() does not have to grab it again.
Similarly, netpoll_poll_lock() is done one time.
This gives about 10 to 20 % improvement in various busy polling
tests, especially when many threads are busy polling in
configurations with large number of NIC queues.
This should allow experimenting with bigger delays without
hurting overall latencies.
Tested:
On a 40Gb mlx4 NIC, 32 RX/TX queues.
echo 70 >/proc/sys/net/core/busy_read
for i in `seq 1 40`; do echo -n $i: ; ./super_netperf $i -H lpaa24 -t UDP_RR -- -N -n; done
Before: After:
1: 90072 92819
2: 157289 184007
3: 235772 213504
4: 344074 357513
5: 394755 458267
6: 461151 487819
7: 549116 625963
8: 544423 716219
9: 720460 738446
10: 794686 837612
11: 915998 923960
12: 937507 925107
13: 1019677 971506
14: 1046831 1113650
15: 1114154 1148902
16: 1105221 1179263
17: 1266552 1299585
18: 1258454 1383817
19: 1341453 1312194
20: 1363557 1488487
21: 1387979 1501004
22: 1417552 1601683
23: 1550049 1642002
24: 1568876 1601915
25: 1560239 1683607
26: 1640207 1745211
27: 1706540 1723574
28: 1638518 1722036
29: 1734309 1757447
30: 1782007 1855436
31: 1724806 1888539
32: 1717716 1944297
33: 1778716 1869118
34: 1805738 1983466
35: 1815694 2020758
36: 1893059 2035632
37: 1843406 2034653
38: 1888830 2086580
39: 1972827 2143567
40: 1877729 2181851
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Adam Belay <abelay@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Yuval Mintz <Yuval.Mintz@cavium.com>
Cc: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If the bpf program calls bpf_redirect(dev, 0) and dev is
an ipip/ip6tnl, it currently includes the mac header.
e.g. If dev is ipip, the end result is IP-EthHdr-IP instead
of IP-IP.
The fix is to pull the mac header. At ingress, skb_postpull_rcsum()
is not needed because the ethhdr should have been pulled once already
and then got pushed back just before calling the bpf_prog.
At egress, this patch calls skb_postpull_rcsum().
If bpf_redirect(dev, BPF_F_INGRESS) is called,
it also fails now because it calls dev_forward_skb() which
eventually calls eth_type_trans(skb, dev). The eth_type_trans()
will set skb->type = PACKET_OTHERHOST because the mac address
does not match the redirecting dev->dev_addr. The PACKET_OTHERHOST
will eventually cause the ip_rcv() errors out. To fix this,
____dev_forward_skb() is added.
Joint work with Daniel Borkmann.
Fixes: cfc7381b30 ("ip_tunnel: add collect_md mode to IPIP tunnel")
Fixes: 8d79266bc4 ("ip6_tunnel: add collect_md mode to IPv6 tunnels")
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are no more users except from net/core/dev.c
napi_hash_add() can now be static.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Receiving a GSO packet in dev_gro_receive() is not uncommon
in stacked devices, or devices partially implementing LRO/GRO
like bnx2x. GRO is implementing the aggregation the device
was not able to do itself.
Current code causes reorders, like in following case :
For a given flow where sender sent 3 packets P1,P2,P3,P4
Receiver might receive P1 as a single packet, stored in GRO engine.
Then P2-P4 are received as a single GSO packet, immediately given to
upper stack, while P1 is held in GRO engine.
This patch will make sure P1 is given to upper stack, then P2-P4
immediately after.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The flag IFF_NO_QUEUE marks virtual device drivers that doesn't need a
default qdisc attached, given they will be backed by physical device,
that already have a qdisc attached for pushback.
It is still supported to attach a qdisc to a IFF_NO_QUEUE device, as
this can be useful for difference policy reasons (e.g. bandwidth
limiting containers). For this to work, the tx_queue_len need to have
a sane value, because some qdiscs inherit/copy the tx_queue_len
(namely, pfifo, bfifo, gred, htb, plug and sfb).
Commit a813104d92 ("IFF_NO_QUEUE: Fix for drivers not calling
ether_setup()") caught situations where some drivers didn't initialize
tx_queue_len. The problem with the commit was choosing 1 as the
fallback value.
A qdisc queue length of 1 causes more harm than good, because it
creates hard to debug situations for userspace. It gives userspace a
false sense of a working config after attaching a qdisc. As low
volume traffic (that doesn't activate the qdisc policy) works,
like ping, while traffic that e.g. needs shaping cannot reach the
configured policy levels, given the queue length is too small.
This patch change the value to DEFAULT_TX_QUEUE_LEN, given other
IFF_NO_QUEUE devices (that call ether_setup()) also use this value.
Fixes: a813104d92 ("IFF_NO_QUEUE: Fix for drivers not calling ether_setup()")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sending zero checksum is ok for TCP, but not for UDP.
UDPv6 receiver should by default drop a frame with a 0 checksum,
and UDPv4 would not verify the checksum and might accept a corrupted
packet.
Simply replace such checksum by 0xffff, regardless of transport.
This error was caught on SIT tunnels, but seems generic.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds support for setting and using XPS when QoS via traffic
classes is enabled. With this change we will factor in the priority and
traffic class mapping of the packet and use that information to correctly
select the queue.
This allows us to define a set of queues for a given traffic class via
mqprio and then configure the XPS mapping for those queues so that the
traffic flows can avoid head-of-line blocking between the individual CPUs
if so desired.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch updates the code for removing queues from the XPS map and makes
it so that we can apply the code any time we change either the number of
traffic classes or the mapping of a given block of queues. This way we
avoid having queues pulling traffic from a foreign traffic class.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a sysfs attribute for a Tx queue that allows us to determine the
traffic class for a given queue. This will allow us to more easily
determine this in the future. It is needed as XPS will take the traffic
class for a group of queues into account in order to avoid pulling traffic
from one traffic class into another.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The functions for configuring the traffic class to queue mappings have
other effects that need to be addressed. Instead of trying to export a
bunch of new functions just relocate the functions so that we can
instrument them directly with the functionality they will need.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Mostly simple overlapping changes.
For example, David Ahern's adjacency list revamp in 'net-next'
conflicted with an adjacency list traversal bug fix in 'net'.
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking fixes from David Miller:
"Lots of fixes, mostly drivers as is usually the case.
1) Don't treat zero DMA address as invalid in vmxnet3, from Alexey
Khoroshilov.
2) Fix element timeouts in netfilter's nft_dynset, from Anders K.
Pedersen.
3) Don't put aead_req crypto struct on the stack in mac80211, from
Ard Biesheuvel.
4) Several uninitialized variable warning fixes from Arnd Bergmann.
5) Fix memory leak in cxgb4, from Colin Ian King.
6) Fix bpf handling of VLAN header push/pop, from Daniel Borkmann.
7) Several VRF semantic fixes from David Ahern.
8) Set skb->protocol properly in ip6_tnl_xmit(), from Eli Cooper.
9) Socket needs to be locked in udp_disconnect(), from Eric Dumazet.
10) Div-by-zero on 32-bit fix in mlx4 driver, from Eugenia Emantayev.
11) Fix stale link state during failover in NCSCI driver, from Gavin
Shan.
12) Fix netdev lower adjacency list traversal, from Ido Schimmel.
13) Propvide proper handle when emitting notifications of filter
deletes, from Jamal Hadi Salim.
14) Memory leaks and big-endian issues in rtl8xxxu, from Jes Sorensen.
15) Fix DESYNC_FACTOR handling in ipv6, from Jiri Bohac.
16) Several routing offload fixes in mlxsw driver, from Jiri Pirko.
17) Fix broadcast sync problem in TIPC, from Jon Paul Maloy.
18) Validate chunk len before using it in SCTP, from Marcelo Ricardo
Leitner.
19) Revert a netns locking change that causes regressions, from Paul
Moore.
20) Add recursion limit to GRO handling, from Sabrina Dubroca.
21) GFP_KERNEL in irq context fix in ibmvnic, from Thomas Falcon.
22) Avoid accessing stale vxlan/geneve socket in data path, from
Pravin Shelar"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (189 commits)
geneve: avoid using stale geneve socket.
vxlan: avoid using stale vxlan socket.
qede: Fix out-of-bound fastpath memory access
net: phy: dp83848: add dp83822 PHY support
enic: fix rq disable
tipc: fix broadcast link synchronization problem
ibmvnic: Fix missing brackets in init_sub_crq_irqs
ibmvnic: Fix releasing of sub-CRQ IRQs in interrupt context
Revert "ibmvnic: Fix releasing of sub-CRQ IRQs in interrupt context"
arch/powerpc: Update parameters for csum_tcpudp_magic & csum_tcpudp_nofold
net/mlx4_en: Save slave ethtool stats command
net/mlx4_en: Fix potential deadlock in port statistics flow
net/mlx4: Fix firmware command timeout during interrupt test
net/mlx4_core: Do not access comm channel if it has not yet been initialized
net/mlx4_en: Fix panic during reboot
net/mlx4_en: Process all completions in RX rings after port goes up
net/mlx4_en: Resolve dividing by zero in 32-bit system
net/mlx4_core: Change the default value of enable_qos
net/mlx4_core: Avoid setting ports to auto when only one port type is supported
net/mlx4_core: Fix the resource-type enum in res tracker to conform to FW spec
...
netdev_walk_all_lower_dev is not properly walking the lower device
list. Commit 1a3f060c1a made netdev_walk_all_lower_dev similar
to netdev_walk_all_upper_dev_rcu and netdev_walk_all_lower_dev_rcu
but failed to update its netdev_next_lower_dev iterator. This patch
fixes that.
Fixes: 1a3f060c1a ("net: Introduce new api for walking upper and
lower devices")
Reported-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Tested-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When transmitting on a packet socket with PACKET_VNET_HDR and
PACKET_QDISC_BYPASS, validate device support for features requested
in vnet_hdr.
Drop TSO packets sent to devices that do not support TSO or have the
feature disabled. Note that the latter currently do process those
packets correctly, regardless of not advertising the feature.
Because of SKB_GSO_DODGY, it is not sufficient to test device features
with netif_needs_gso. Full validate_xmit_skb is needed.
Switch to software checksum for non-TSO packets that request checksum
offload if that device feature is unsupported or disabled. Note that
similar to the TSO case, device drivers may perform checksum offload
correctly even when not advertising it.
When switching to software checksum, packets hit skb_checksum_help,
which has two BUG_ON checksum not in linear segment. Packet sockets
always allocate at least up to csum_start + csum_off + 2 as linear.
Tested by running github.com/wdebruij/kerneltools/psock_txring_vnet.c
ethtool -K eth0 tso off tx on
psock_txring_vnet -d $dst -s $src -i eth0 -l 2000 -n 1 -q -v
psock_txring_vnet -d $dst -s $src -i eth0 -l 2000 -n 1 -q -v -N
ethtool -K eth0 tx off
psock_txring_vnet -d $dst -s $src -i eth0 -l 1000 -n 1 -q -v -G
psock_txring_vnet -d $dst -s $src -i eth0 -l 1000 -n 1 -q -v -G -N
v2:
- add EXPORT_SYMBOL_GPL(validate_xmit_skb_list)
Fixes: d346a3fae3 ("packet: introduce PACKET_QDISC_BYPASS socket option")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, GRO can do unlimited recursion through the gro_receive
handlers. This was fixed for tunneling protocols by limiting tunnel GRO
to one level with encap_mark, but both VLAN and TEB still have this
problem. Thus, the kernel is vulnerable to a stack overflow, if we
receive a packet composed entirely of VLAN headers.
This patch adds a recursion counter to the GRO layer to prevent stack
overflow. When a gro_receive function hits the recursion limit, GRO is
aborted for this skb and it is processed normally. This recursion
counter is put in the GRO CB, but could be turned into a percpu counter
if we run out of space in the CB.
Thanks to Vladimír Beneš <vbenes@redhat.com> for the initial bug report.
Fixes: CVE-2016-7039
Fixes: 9b174d88c2 ("net: Add Transparent Ethernet Bridging GRO support.")
Fixes: 66e5133f19 ("vlan: Add GRO support for non hardware accelerated vlan")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Adjacency code only has debugs for the insert case. Add debugs for
the remove path and make both consistently worded to make it easier
to follow the insert and removal with reference counts.
In addition, change the BUG to a WARN_ON. A missing adjacency at
removal time is not cause for a panic.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Only direct adjacencies are maintained. All upper or lower devices can
be learned via the new walk API which recursively walks the adj_list for
upper devices or lower devices.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch introduces netdev_walk_all_upper_dev_rcu,
netdev_walk_all_lower_dev and netdev_walk_all_lower_dev_rcu. These
functions recursively walk the adj_list of devices to determine all upper
and lower devices.
The functions take a callback function that is invoked for each device
in the list. If the callback returns non-0, the walk is terminated and
the functions return that code back to callers.
v3
- simplified netdev_has_upper_dev_all_rcu and __netdev_has_upper_dev and
removed typecast as suggested by Stephen
v2
- fixed definition of netdev_next_lower_dev_rcu to mirror the upper_dev
version.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 93409033ae ("net: Add netdev all_adj_list refcnt propagation to
fix panic") propagated the refnr to insert and remove functions tracking
the netdev adjacency graph. However, for the insert path the refnr can
only be 1. Accordingly, remove the refnr argument to make that clear.
ie., the refnr arg in 93409033ae was only needed for the remove path.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Check is for max_mtu but message reports min_mtu.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
extract as much possible uncertainty from a running system at boot time as
possible, hoping to capitalize on any possible variation in CPU operation
(due to runtime data differences, hardware differences, SMP ordering,
thermal timing variation, cache behavior, etc).
At the very least, this plugin is a much more comprehensive example for
how to manipulate kernel code using the gcc plugin internals.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
Comment: Kees Cook <kees@outflux.net>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=1dUK
-----END PGP SIGNATURE-----
Merge tag 'gcc-plugins-v4.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux
Pull gcc plugins update from Kees Cook:
"This adds a new gcc plugin named "latent_entropy". It is designed to
extract as much possible uncertainty from a running system at boot
time as possible, hoping to capitalize on any possible variation in
CPU operation (due to runtime data differences, hardware differences,
SMP ordering, thermal timing variation, cache behavior, etc).
At the very least, this plugin is a much more comprehensive example
for how to manipulate kernel code using the gcc plugin internals"
* tag 'gcc-plugins-v4.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
latent_entropy: Mark functions with __latent_entropy
gcc-plugins: Add latent_entropy plugin
This reverts commit 6ae23ad362.
The code has been in kernel since 4.4 but there are no in tree
code that uses. Unused code is broken code, remove it.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
While looking into an MTU issue with sfc, I started noticing that almost
every NIC driver with an ndo_change_mtu function implemented almost
exactly the same range checks, and in many cases, that was the only
practical thing their ndo_change_mtu function was doing. Quite a few
drivers have either 68, 64, 60 or 46 as their minimum MTU value checked,
and then various sizes from 1500 to 65535 for their maximum MTU value. We
can remove a whole lot of redundant code here if we simple store min_mtu
and max_mtu in net_device, and check against those in net/core/dev.c's
dev_set_mtu().
In theory, there should be zero functional change with this patch, it just
puts the infrastructure in place. Subsequent patches will attempt to start
using said infrastructure, with theoretically zero change in
functionality.
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The __latent_entropy gcc attribute can be used only on functions and
variables. If it is on a function then the plugin will instrument it for
gathering control-flow entropy. If the attribute is on a variable then
the plugin will initialize it with random contents. The variable must
be an integer, an integer array type or a structure with integer fields.
These specific functions have been selected because they are init
functions (to help gather boot-time entropy), are called at unpredictable
times, or they have variable loops, each of which provide some level of
latent entropy.
Signed-off-by: Emese Revfy <re.emese@gmail.com>
[kees: expanded commit message]
Signed-off-by: Kees Cook <keescook@chromium.org>
This is a respin of a patch to fix a relatively easily reproducible kernel
panic related to the all_adj_list handling for netdevs in recent kernels.
The following sequence of commands will reproduce the issue:
ip link add link eth0 name eth0.100 type vlan id 100
ip link add link eth0 name eth0.200 type vlan id 200
ip link add name testbr type bridge
ip link set eth0.100 master testbr
ip link set eth0.200 master testbr
ip link add link testbr mac0 type macvlan
ip link delete dev testbr
This creates an upper/lower tree of (excuse the poor ASCII art):
/---eth0.100-eth0
mac0-testbr-
\---eth0.200-eth0
When testbr is deleted, the all_adj_lists are walked, and eth0 is deleted twice from
the mac0 list. Unfortunately, during setup in __netdev_upper_dev_link, only one
reference to eth0 is added, so this results in a panic.
This change adds reference count propagation so things are handled properly.
Matthias Schiffer reported a similar crash in batman-adv:
https://github.com/freifunk-gluon/gluon/issues/680https://www.open-mesh.org/issues/247
which this patch also seems to resolve.
Signed-off-by: Andrew Collins <acollins@cradlepoint.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
net/netfilter/core.c
net/netfilter/nf_tables_netdev.c
Resolve two conflicts before pull request for David's net-next tree:
1) Between c73c248490 ("netfilter: nf_tables_netdev: remove redundant
ip_hdr assignment") from the net tree and commit ddc8b6027a
("netfilter: introduce nft_set_pktinfo_{ipv4, ipv6}_validate()").
2) Between e8bffe0cf9 ("net: Add _nf_(un)register_hooks symbols") and
Aaron Conole's patches to replace list_head with single linked list.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This commit ensures that the rcu read-side lock is held while the
ingress hook is called. This ensures that a call to nf_hook_slow (and
ultimately nf_ingress) will be read protected.
Signed-off-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Conflicts:
drivers/net/ethernet/mediatek/mtk_eth_soc.c
drivers/net/ethernet/qlogic/qed/qed_dcbx.c
drivers/net/phy/Kconfig
All conflicts were cases of overlapping commits.
Signed-off-by: David S. Miller <davem@davemloft.net>
The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either
built-in or as a module, use that macro instead of open coding the same.
Using the macro makes the code more readable by helping abstract away some
of the Kconfig built-in and module enable details.
Signed-off-by: Javier Martinez Canillas <javier@osg.samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Following few steps will crash kernel -
(a) Create bonding master
> modprobe bonding miimon=50
(b) Create macvlan bridge on eth2
> ip link add link eth2 dev mvl0 address aa:0:0:0:0:01 \
type macvlan
(c) Now try adding eth2 into the bond
> echo +eth2 > /sys/class/net/bond0/bonding/slaves
<crash>
Bonding does lots of things before checking if the device enslaved is
busy or not.
In this case when the notifier call-chain sends notifications, the
bond_netdev_event() assumes that the rx_handler /rx_handler_data is
registered while the bond_enslave() hasn't progressed far enough to
register rx_handler for the new slave.
This patch adds a rx_handler check that can be performed right at the
beginning of the enslave code to avoid getting into this situation.
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After commit 145dd5f9c8 ("net: flush the softnet backlog in process
context"), we can easily batch calls to flush_all_backlogs() for all
devices processed in rollback_registered_many()
Tested:
Before patch, on an idle host.
modprobe dummy numdummies=10000
perf stat -e context-switches -a rmmod dummy
Performance counter stats for 'system wide':
1,211,798 context-switches
1.302137465 seconds time elapsed
After patch:
perf stat -e context-switches -a rmmod dummy
Performance counter stats for 'system wide':
225,523 context-switches
0.721623566 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
switchdev_port_fwd_mark_set() is used to set the 'offload_fwd_mark' of
port netdevs so that packets being flooded by the device won't be
flooded twice.
It works by assigning a unique identifier (the ifindex of the first
bridge port) to bridge ports sharing the same parent ID. This prevents
packets from being flooded twice by the same switch, but will flood
packets through bridge ports belonging to a different switch.
This method is problematic when stacked devices are taken into account,
such as VLANs. In such cases, a physical port netdev can have upper
devices being members in two different bridges, thus requiring two
different 'offload_fwd_mark's to be configured on the port netdev, which
is impossible.
The main problem is that packet and netdev marking is performed at the
physical netdev level, whereas flooding occurs between bridge ports,
which are not necessarily port netdevs.
Instead, packet and netdev marking should really be done in the bridge
driver with the switch driver only telling it which packets it already
forwarded. The bridge driver will mark such packets using the mark
assigned to the ingress bridge port and will prevent the packet from
being forwarded through any bridge port sharing the same mark (i.e.
having the same parent ID).
Remove the current switchdev 'offload_fwd_mark' implementation and
instead implement the proposed method. In addition, make rocker - the
sole user of the mark - use the proposed method.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently in process_backlog(), the process_queue dequeuing is
performed with local IRQ disabled, to protect against
flush_backlog(), which runs in hard IRQ context.
This patch moves the flush operation to a work queue and runs the
callback with bottom half disabled to protect the process_queue
against dequeuing.
Since process_queue is now always manipulated in bottom half context,
the irq disable/enable pair around the dequeue operation are removed.
To keep the flush time as low as possible, the flush
works are scheduled on all online cpu simultaneously, using the
high priority work-queue and statically allocated, per cpu,
work structs.
Overall this change increases the time required to destroy a device
to improve slightly the packets reinjection performances.
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Minor overlapping changes for both merge conflicts.
Resolution work done by Stephen Rothwell was used
as a reference.
Signed-off-by: David S. Miller <davem@davemloft.net>
The idea for type_check in dev_get_nest_level() was to count the number
of nested devices of the same type (currently, only macvlan or vlan
devices).
This prevented the false positive lockdep warning on configurations such
as:
eth0 <--- macvlan0 <--- vlan0 <--- macvlan1
However, this doesn't prevent a warning on a configuration such as:
eth0 <--- macvlan0 <--- vlan0
eth1 <--- vlan1 <--- macvlan1
In this case, all the locks end up with a nesting subclass of 1, so
lockdep thinks that there is still a deadlock:
- in the first case we have (macvlan_netdev_addr_lock_key, 1) and then
take (vlan_netdev_xmit_lock_key, 1)
- in the second case, we have (vlan_netdev_xmit_lock_key, 1) and then
take (macvlan_netdev_addr_lock_key, 1)
By removing the linktype check in dev_get_nest_level() and always
incrementing the nesting depth, lockdep considers this configuration
valid.
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Convert the per-device linked list into a hashtable. The primary
motivation for this change is that currently, we're not tracking all the
qdiscs in hierarchy (e.g. excluding default qdiscs), as the lookup
performed over the linked list by qdisc_match_from_root() is rather
expensive.
The ultimate goal is to get rid of hidden qdiscs completely, which will
bring much more determinism in user experience.
Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
This changes the vfs dentry hashing to mix in the parent pointer at the
_beginning_ of the hash, rather than at the end.
That actually improves both the hash and the code generation, because we
can move more of the computation to the "static" part of the dcache
setup, and do less at lookup runtime.
It turns out that a lot of other hash users also really wanted to mix in
a base pointer as a 'salt' for the hash, and so the slightly extended
interface ends up working well for other cases too.
Users that want a string hash that is purely about the string pass in a
'salt' pointer of NULL.
* merge branch 'salted-string-hash':
fs/dcache.c: Save one 32-bit multiply in dcache lookup
vfs: make the string hashes salt the hash
Add one new netdev op for drivers implementing the BPF_PROG_TYPE_XDP
filter. The single op is used for both setup/query of the xdp program,
modelled after ndo_setup_tc.
Signed-off-by: Brenden Blanco <bblanco@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
An important information for the napi_poll tracepoint is knowing
the work done (packets processed) by the napi_poll() call. Add
both the work done and budget, as they are related.
Handle trace_napi_poll() param change in dropwatch/drop_monitor
and in python perf script netdev-times.py in backward compat way,
as python fortunately supports optional parameter handling.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
L2 upper device needs to propagate neigh_construct/destroy calls down to
lower devices. Do this by defining default ndo functions and use them in
team, bond, bridge and vlan.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add functions that iterate over lower devices and find port device.
As a dependency add netdev_for_each_all_lower_dev and
netdev_for_each_all_lower_dev_rcu macro with
netdev_all_lower_get_next and netdev_all_lower_get_next_rcu shelpers.
Also, add functions to return mlxsw struct according to lower device
found and mlxsw_port struct with a reference to lower device.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Qdisc performance suffers when packets are dropped at enqueue()
time because drops (kfree_skb()) are done while qdisc lock is held,
delaying a dequeue() draining the queue.
Nominal throughput can be reduced by 50 % when this happens,
at a time we would like the dequeue() to proceed as fast as possible.
Even FQ is vulnerable to this problem, while one of FQ goals was
to provide some flow isolation.
This patch adds a 'struct sk_buff **to_free' parameter to all
qdisc->enqueue(), and in qdisc_drop() helper.
I measured a performance increase of up to 12 %, but this patch
is a prereq so that future batches in enqueue() can fly.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The space is missing after ',', and this will introduce much more
noise when checking patch around.
Signed-off-by: Wei Tang <tangwei@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes the checkpatch.pl error to dev.c:
ERROR: do not initialise statics to 0
Signed-off-by: Wei Tang <tangwei@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We always mixed in the parent pointer into the dentry name hash, but we
did it late at lookup time. It turns out that we can simplify that
lookup-time action by salting the hash with the parent pointer early
instead of late.
A few other users of our string hashes also wanted to mix in their own
pointers into the hash, and those are updated to use the same mechanism.
Hash users that don't have any particular initial salt can just use the
NULL pointer as a no-salt.
Cc: Vegard Nossum <vegard.nossum@oracle.com>
Cc: George Spelvin <linux@sciencehorizons.net>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Respect the stack's xmit_recursion limit for calls into dev_queue_xmit().
Currently, they are not handeled by the limiter when attached to clsact's
egress parent, for example, and a buggy program redirecting it to the
same device again could run into stack overflow eventually. It would be
good if we could notify an admin to give him a chance to react. We reuse
xmit_recursion instead of having one private to eBPF, so that the stack's
current recursion depth will be taken into account as well. Follow-up to
commit 3896d655f4 ("bpf: introduce bpf_clone_redirect() helper") and
27b29f6305 ("bpf: add bpf_redirect() helper").
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
When in kdump kernel, reduce memory usage by only using a single Queue
Set for multiqueue devices. So make netif_get_num_default_rss_queues()
return one, when in kdump kernel.
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of using a single bit (__QDISC___STATE_RUNNING)
in sch->__state, use a seqcount.
This adds lockdep support, but more importantly it will allow us
to sample qdisc/class statistics without having to grab qdisc root lock.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Note: Tom Herbert posted almost same patch 3 months back, but for
different reasons.
The reasons we want to get rid of this spin_trylock() are :
1) Under high qdisc pressure, the spin_trylock() has almost no
chance to succeed.
2) We loop multiple times in softirq handler, eventually reaching
the max retry count (10), and we schedule ksoftirqd.
Since we want to adhere more strictly to ksoftirqd being waked up in
the future (https://lwn.net/Articles/687617/), better avoid spurious
wakeups.
3) calls to __netif_reschedule() dirty the cache line containing
q->next_sched, slowing down the owner of qdisc.
4) RT kernels can not use the spin_trylock() here.
With help of busylock, we get the qdisc spinlock fast enough, and
the trylock trick brings only performance penalty.
Depending on qdisc setup, I observed a gain of up to 19 % in qdisc
performance (1016600 pps instead of 853400 pps, using prio+tbf+fq_codel)
("mpstat -I SCPU 1" is much happier now)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <tom@herbertland.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Follow-up for 8a3a4c6e7b ("net: make sch_handle_ingress() drop
monitor ready") to also make the egress side drop monitor ready.
Also here only TC_ACT_SHOT is a clear indication that something
went wrong. Hence don't provide false positives to drop monitors
such as 'perf record -e skb:kfree_skb ...'.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently the VRF driver uses the rx_handler to switch the skb device
to the VRF device. Switching the dev prior to the ip / ipv6 layer
means the VRF driver has to duplicate IP/IPv6 processing which adds
overhead and makes features such as retaining the ingress device index
more complicated than necessary.
This patch moves the hook to the L3 layer just after the first NF_HOOK
for PRE_ROUTING. This location makes exposing the original ingress device
trivial (next patch) and allows adding other NF_HOOKs to the VRF driver
in the future.
dev_queue_xmit_nit is exported so that the VRF driver can cycle the skb
with the switched device through the packet taps to maintain current
behavior (tcpdump can be used on either the vrf device or the enslaved
devices).
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
TC_ACT_STOLEN is used when ingress traffic is mirred/redirected
to say ifb.
Packet is not dropped, but consumed.
Only TC_ACT_SHOT is a clear indication something went wrong.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change makes it so that we will strip the TSO_MANGLEID bit if TSO is
not present. This way we will also handle ECN correctly of TSO is not
present.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
net/ipv4/ip_gre.c
Minor conflicts between tunnel bug fixes in net and
ipv6 tunnel cleanups in net-next.
Signed-off-by: David S. Miller <davem@davemloft.net>
In the case of the mlx4 and mlx5 driver they do not support IPv6 checksum
offload for tunnels. With this being the case we should disable GSO in
addition to the checksum offload features when we find that a device cannot
perform a checksum on a given packet type.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
is_skb_forwardable is not supposed to change anything so constify its
arguments
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There's no need to calculate rps hash if it was not enabled. So this
patch export rps_needed and check it before trying to get rps
hash. Tests (using pktgen to inject packets to guest) shows this can
improve pps about 13% (when rps is disabled).
Before:
~1150000 pps
After:
~1300000 pps
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
----
Changes from V1:
- Fix build when CONFIG_RPS is not set
Signed-off-by: David S. Miller <davem@davemloft.net>
Rename NET_INC_STATS_BH() to __NET_INC_STATS()
and NET_ADD_STATS_BH() to __NET_ADD_STATS()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds support for NETIF_F_TSO_MANGLEID if a given tunnel supports
NETIF_F_TSO. This way if needed a device can then later enable the TSO
with IP ID mangling and the tunnels on top of that device can then also
make use of the IP ID mangling as well.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
skbs given to validate_xmit_skb() should not have a next
pointer anymore.
Also if a packet is dropped, increment dev->tx_dropped
__dev_queue_xmit() no longer has to change tx_dropped in this case.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds support for something I am referring to as GSO partial.
The basic idea is that we can support a broader range of devices for
segmentation if we use fixed outer headers and have the hardware only
really deal with segmenting the inner header. The idea behind the naming
is due to the fact that everything before csum_start will be fixed headers,
and everything after will be the region that is handled by hardware.
With the current implementation it allows us to add support for the
following GSO types with an inner TSO_MANGLEID or TSO6 offload:
NETIF_F_GSO_GRE
NETIF_F_GSO_GRE_CSUM
NETIF_F_GSO_IPIP
NETIF_F_GSO_SIT
NETIF_F_UDP_TUNNEL
NETIF_F_UDP_TUNNEL_CSUM
In the case of hardware that already supports tunneling we may be able to
extend this further to support TSO_TCPV4 without TSO_MANGLEID if the
hardware can support updating inner IPv4 headers.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch does two things.
First it allows TCP to aggregate TCP frames with a fixed IPv4 ID field. As
a result we should now be able to aggregate flows that were converted from
IPv6 to IPv4. In addition this allows us more flexibility for future
implementations of segmentation as we may be able to use a fixed IP ID when
segmenting the flow.
The second thing this does is that it places limitations on the outer IPv4
ID header in the case of tunneled frames. Specifically it forces the IP ID
to be incrementing by 1 unless the DF bit is set in the outer IPv4 header.
This way we can avoid creating overlapping series of IP IDs that could
possibly be fragmented if the frame goes through GRO and is then
resegmented via GSO.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds support for TSO using IPv4 headers with a fixed IP ID
field. This is meant to allow us to do a lossless GRO in the case of TCP
flows that use a fixed IP ID such as those that convert IPv6 header to IPv4
headers.
In addition I am adding a feature that for now I am referring to TSO with
IP ID mangling. Basically when this flag is enabled the device has the
option to either output the flow with incrementing IP IDs or with a fixed
IP ID regardless of what the original IP ID ordering was. This is useful
in cases where the DF bit is set and we do not care if the original IP ID
value is maintained.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After introduction of ndo_features_check(), we believe that very
specific checks for rare features should not be done in core
networking stack.
No driver uses gso_min_segs yet, so we revert this feature and save
few instructions per tx packet in fast path.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes an issue I found in which we were dropping frames if we
had enabled checksums on GRE headers that were encapsulated by either FOU
or GUE. Without this patch I was barely able to get 1 Gb/s of throughput.
With this patch applied I am now at least getting around 6 Gb/s.
The issue is due to the fact that with FOU or GUE applied we do not provide
a transport offset pointing to the GRE header, nor do we offload it in
software as the GRE header is completely skipped by GSO and treated like a
VXLAN or GENEVE type header. As such we need to prevent the stack from
generating it and also prevent GRE from generating it via any interface we
create.
Fixes: c3483384ee ("gro: Allow tunnel stacking in the case of FOU/GUE")
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When signaling that a GRO frame is ready to be processed, the network stack
correctly checks length and aborts processing when a frame is less than 14
bytes. However, such a condition is really indicative of a broken driver,
and should be loudly signaled, rather than silently dropped as the case is
today.
Convert the condition to use net_warn_ratelimited() to ensure the stack
loudly complains about such broken drivers.
Signed-off-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
When the function dev_get_phys_port_name was added it missed a description
for it's len argument. Adding it.
Fixes: db24a9044e ("net: add support for phys_port_name")
Signed-off-by: Luis de Bethencourt <luisbg@osg.samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When drivers express support for TSO of encapsulated packets, they
only mean that they can do it for one layer of encapsulation.
Supporting additional levels would mean updating, at a minimum,
more IP length fields and they are unaware of this.
No encapsulation device expresses support for handling offloaded
encapsulated packets, so we won't generate these types of frames
in the transmit path. However, GRO doesn't have a check for
multiple levels of encapsulation and will attempt to build them.
UDP tunnel GRO actually does prevent this situation but it only
handles multiple UDP tunnels stacked on top of each other. This
generalizes that solution to prevent any kind of tunnel stacking
that would cause problems.
Fixes: bf5a755f ("net-gre-gro: Add GRE support to the GRO stack")
Signed-off-by: Jesse Gross <jesse@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/phy/bcm7xxx.c
drivers/net/phy/marvell.c
drivers/net/vxlan.c
All three conflicts were cases of simple overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
My implementation around IFF_NO_QUEUE driver flag assumed that leaving
tx_queue_len untouched (specifically: not setting it to zero) by drivers
would make it possible to assign a regular qdisc to them without having
to worry about setting tx_queue_len to a useful value. This was only
partially true: I overlooked that some drivers don't call ether_setup()
and therefore not initialize tx_queue_len to the default value of 1000.
Consequently, removing the workarounds in place for that case in qdisc
implementations which cared about it (namely, pfifo, bfifo, gred, htb,
plug and sfb) leads to problems with these specific interface types and
qdiscs.
Luckily, there's already a sanitization point for drivers setting
tx_queue_len to zero, which can be reused to assign the fallback value
most qdisc implementations used, which is 1.
Fixes: 348e3435cb ("net: sched: drop all special handling of tx_queue_len == 0")
Tested-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
The network stack defers SKBs free, in-case free happens in IRQ or
when IRQs are disabled. This happens in __dev_kfree_skb_irq() that
writes SKBs that were free'ed during IRQ to the softirq completion
queue (softnet_data.completion_queue).
These SKBs are naturally delayed, and cleaned up during NET_TX_SOFTIRQ
in function net_tx_action(). Take advantage of this a use the skb
defer and flush API, as we are already in softirq context.
For modern drivers this rarely happens. Although most drivers do call
dev_kfree_skb_any(), which detects the situation and calls
__dev_kfree_skb_irq() when needed. This due to netpoll can call from
IRQ context.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Discovered that network stack were hitting the kmem_cache/SLUB
slowpath when freeing SKBs. Doing bulk free with kmem_cache_free_bulk
can speedup this slowpath.
NAPI context is a bit special, lets take advantage of that for bulk
free'ing SKBs.
In NAPI context we are running in softirq, which gives us certain
protection. A softirq can run on several CPUs at once. BUT the
important part is a softirq will never preempt another softirq running
on the same CPU. This gives us the opportunity to access per-cpu
variables in softirq context.
Extend napi_alloc_cache (before only contained page_frag_cache) to be
a struct with a small array based stack for holding SKBs. Introduce a
SKB defer and flush API for accessing this.
Introduce napi_consume_skb() as replacement for e.g. dev_consume_skb_any()
when running in NAPI context. A small trick to handle/detect if we
are called from netpoll is to see if budget is 0. In that case, we
need to invoke dev_consume_skb_irq().
Joint work with Alexander Duyck.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds an rx_nohandler stat counter, along with a sysfs statistics
node, and copies the counter out via netlink as well.
CC: "David S. Miller" <davem@davemloft.net>
CC: Eric Dumazet <edumazet@google.com>
CC: Jiri Pirko <jiri@mellanox.com>
CC: Daniel Borkmann <daniel@iogearbox.net>
CC: Tom Herbert <tom@herbertland.com>
CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <gospo@cumulusnetworks.com>
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The netdev_stats_to_stats64 function copies the deprecated
net_device_stats format stats into rtnl_link_stats64 for legacy support
purposes, but with the BUILD_BUG_ON as it was, it wasn't possible to
extend rtnl_link_stats64 without also extending net_device_stats. Relax
the BUILD_BUG_ON to only require that rtnl_link_stats64 is larger, and
zero out all the stat counters that aren't present in net_device_stats.
CC: Eric Dumazet <edumazet@google.com>
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
GRO is currently not aware of tunnel metadata generated by lightweight
tunnels and stored in the dst. This leads to two possible problems:
* Incorrectly merging two frames that have different metadata.
* Leaking of allocated metadata from merged frames.
This avoids those problems by comparing the tunnel information before
merging, similar to how we handle other metadata (such as vlan tags),
and releasing any state when we are done.
Reported-by: John <john.phillips5@hpe.com>
Fixes: 2e15ea39 ("ip_gre: Add support to collect tunnel metadata.")
Signed-off-by: Jesse Gross <jesse@kernel.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Skb_gso_segment() uses skb control block during segmentation.
This patch adds 32-bytes room for previous control block which
will be copied into all resulting segments.
This patch fixes kernel crash during fragmenting forwarded packets.
Fragmentation requires valid IP CB in skb for clearing ip options.
Also patch removes custom save/restore in ovs code, now it's redundant.
Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com>
Link: http://lkml.kernel.org/r/CALYGNiP-0MZ-FExV2HutTvE9U-QQtkKSoE--KN=JQE5STYsjAA@mail.gmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
This work adds a generalization of the ingress qdisc as a qdisc holding
only classifiers. The clsact qdisc works on ingress, but also on egress.
In both cases, it's execution happens without taking the qdisc lock, and
the main difference for the egress part compared to prior version of [1]
is that this can be applied with _any_ underlying real egress qdisc (also
classless ones).
Besides solving the use-case of [1], that is, allowing for more programmability
on assigning skb->priority for the mqprio case that is supported by most
popular 10G+ NICs, it also opens up a lot more flexibility for other tc
applications. The main work on classification can already be done at clsact
egress time if the use-case allows and state stored for later retrieval
f.e. again in skb->priority with major/minors (which is checked by most
classful qdiscs before consulting tc_classify()) and/or in other skb fields
like skb->tc_index for some light-weight post-processing to get to the
eventual classid in case of a classful qdisc. Another use case is that
the clsact egress part allows to have a central egress counterpart to
the ingress classifiers, so that classifiers can easily share state (e.g.
in cls_bpf via eBPF maps) for ingress and egress.
Currently, default setups like mq + pfifo_fast would require for this to
use, for example, prio qdisc instead (to get a tc_classify() run) and to
duplicate the egress classifier for each queue. With clsact, it allows
for leaving the setup as is, it can additionally assign skb->priority to
put the skb in one of pfifo_fast's bands and it can share state with maps.
Moreover, we can access the skb's dst entry (f.e. to retrieve tclassid)
w/o the need to perform a skb_dst_force() to hold on to it any longer. In
lwt case, we can also use this facility to setup dst metadata via cls_bpf
(bpf_skb_set_tunnel_key()) without needing a real egress qdisc just for
that (case of IFF_NO_QUEUE devices, for example).
The realization can be done without any changes to the scheduler core
framework. All it takes is that we have two a-priori defined minors/child
classes, where we can mux between ingress and egress classifier list
(dev->ingress_cl_list and dev->egress_cl_list, latter stored close to
dev->_tx to avoid extra cacheline miss for moderate loads). The egress
part is a bit similar modelled to handle_ing() and patched to a noop in
case the functionality is not used. Both handlers are now called
sch_handle_ingress() and sch_handle_egress(), code sharing among the two
doesn't seem practical as there are various minor differences in both
paths, so that making them conditional in a single handler would rather
slow things down.
Full compatibility to ingress qdisc is provided as well. Since both
piggyback on TC_H_CLSACT, only one of them (ingress/clsact) can exist
per netdevice, and thus ingress qdisc specific behaviour can be retained
for user space. This means, either a user does 'tc qdisc add dev foo ingress'
and configures ingress qdisc as usual, or the 'tc qdisc add dev foo clsact'
alternative, where both, ingress and egress classifier can be configured
as in the below example. ingress qdisc supports attaching classifier to any
minor number whereas clsact has two fixed minors for muxing between the
lists, therefore to not break user space setups, they are better done as
two separate qdiscs.
I decided to extend the sch_ingress module with clsact functionality so
that commonly used code can be reused, the module is being aliased with
sch_clsact so that it can be auto-loaded properly. Alternative would have been
to add a flag when initializing ingress to alter its behaviour plus aliasing
to a different name (as it's more than just ingress). However, the first would
end up, based on the flag, choosing the new/old behaviour by calling different
function implementations to handle each anyway, the latter would require to
register ingress qdisc once again under different alias. So, this really begs
to provide a minimal, cleaner approach to have Qdisc_ops and Qdisc_class_ops
by its own that share callbacks used by both.
Example, adding qdisc:
# tc qdisc add dev foo clsact
# tc qdisc show dev foo
qdisc mq 0: root
qdisc pfifo_fast 0: parent :1 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1
qdisc pfifo_fast 0: parent :2 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1
qdisc pfifo_fast 0: parent :3 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1
qdisc pfifo_fast 0: parent :4 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1
qdisc clsact ffff: parent ffff:fff1
Adding filters (deleting, etc works analogous by specifying ingress/egress):
# tc filter add dev foo ingress bpf da obj bar.o sec ingress
# tc filter add dev foo egress bpf da obj bar.o sec egress
# tc filter show dev foo ingress
filter protocol all pref 49152 bpf
filter protocol all pref 49152 bpf handle 0x1 bar.o:[ingress] direct-action
# tc filter show dev foo egress
filter protocol all pref 49152 bpf
filter protocol all pref 49152 bpf handle 0x1 bar.o:[egress] direct-action
A 'tc filter show dev foo' or 'tc filter show dev foo parent ffff:' will
show an empty list for clsact. Either using the parent names (ingress/egress)
or specifying the full major/minor will then show the related filter lists.
Prior work on a mqprio prequeue() facility [1] was done mainly by John Fastabend.
[1] http://patchwork.ozlabs.org/patch/512949/
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add skb_csum_offload_chk driver helper function to determine if a
device with limited checksum offload capabilities is able to offload the
checksum for a given packet.
This patch includes:
- The skb_csum_offload_chk function. Returns true if checksum is
offloadable, else false. Optionally, in the case that the checksum
is not offloable, the function can call skb_checksum_help to resolve
the checksum. skb_csum_offload_chk also returns whether the checksum
refers to an encapsulated checksum.
- Definition of skb_csum_offl_spec structure that caller uses to
indicate rules about what it can offload (e.g. IPv4/v6, TCP/UDP only,
whether encapsulated checksums can be offloaded, whether checksum with
IPv6 extension headers can be offloaded).
- Ancilary functions called skb_csum_offload_chk_help,
skb_csum_off_chk_help_cmn, skb_csum_off_chk_help_cmn_v4_only.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
These netif flags are unnecessary convolutions. It is more
straightforward to just use NETIF_F_HW_CSUM, NETIF_F_IP_CSUM,
and NETIF_F_IPV6_CSUM directly.
This patch also:
- Cleans up can_checksum_protocol
- Simplifies netdev_intersect_features
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The name NETIF_F_ALL_CSUM is a misnomer. This does not correspond to the
set of features for offloading all checksums. This is a mask of the
checksum offload related features bits. It is incorrect to set both
NETIF_F_HW_CSUM and NETIF_F_IP_CSUM or NETIF_F_IPV6 at the same time for
features of a device.
This patch:
- Changes instances of NETIF_F_ALL_CSUM to NETIF_F_CSUM_MASK (where
NETIF_F_ALL_CSUM is being used as a mask).
- Changes bonding, sfc/efx, ipvlan, macvlan, vlan, and team drivers to
use NEITF_F_HW_CSUM in features list instead of NETIF_F_ALL_CSUM.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduce sock->sk_cgrp_data which is a struct sock_cgroup_data.
->sk_cgroup_prioidx and ->sk_classid are moved into it. The struct
and its accessors are defined in cgroup-defs.h. This is to prepare
for overloading the fields with a cgroup pointer.
This patch mostly performs equivalent conversions but the followings
are noteworthy.
* Equality test before updating classid is removed from
sock_update_classid(). This shouldn't make any noticeable
difference and a similar test will be implemented on the helper side
later.
* sock_update_netprioidx() now takes struct sock_cgroup_data and can
be moved to netprio_cgroup.h without causing include dependency
loop. Moved.
* The dummy version of sock_update_netprioidx() converted to a static
inline function while at it.
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
As suggested by Eric, these helpers should have const dev param.
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When lower device like bonding slave, team/bridge port, etc changes its
state, it is useful for others to notice this change. Currently this is
implemented specificly for bonding as NETDEV_BONDING_INFO notifier. This
patch aims to replace this specific usage and make this more generic to
be used for all upper-lower devices.
Introduce NETDEV_CHANGELOWERSTATE netdev notifier type and
netdev_lower_state_changed() helper.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sometimes the drivers and other code would find it handy to know some
internal information about upper device being changed. So allow upper-code
to pass information down to notifier listeners during linking.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eliminate netdev_master_upper_dev_link_private and pass priv directly as
a parameter of netdev_master_upper_dev_link.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
switchdev drivers reflect the newly requested topology to hardware when
CHANGEUPPER is received, after software links were already formed.
However, the operation can fail and user will not be notified, as the
return value of the notifier is not checked.
Add this check and rollback software links if necessary.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
napi_alloc_skb() can return NULL.
We should not crash should this happen.
Fixes: 93f93a4404 ("net: move skb_mark_napi_id() into core networking stack")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
NAPI drivers no longer need to observe a particular protocol
to benefit from busy polling (CONFIG_NET_RX_BUSY_POLL=y)
napi_hash_add() and napi_hash_del() are automatically called
from core networking stack, respectively from
netif_napi_add() and netif_napi_del()
This patch depends on free_netdev() and netif_napi_del() being
called from process context, which seems to be the norm.
Drivers might still prefer to call napi_hash_del() on their
own, since they might combine all the rcu grace periods into
a single one, knowing their NAPI structures lifetime, while
core networking stack has no idea of a possible combining.
Once this patch proves to not bring serious regressions,
we will cleanup drivers to either remove napi_hash_del()
or provide appropriate rcu grace periods combining.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
napi_hash_del() will soon be used from both drivers (if they want)
or core networking stack.
Callers are responsibles to ensure an RCU grace period is respected
before freeing napi structure : napi_hash_del() can signal if
this RCU grace period is needed or not.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We do not often add/delete a napi context.
Moving napi_hash[] into read mostly section avoids potential false sharing.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
netif_tx_napi_add() is a variant of netif_napi_add()
It should be used by drivers that use a napi structure
to exclusively poll TX.
We do not want to add this kind of napi in napi_hash[] in following
patches, adding generic busy polling to all NAPI drivers.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We would like to automatically provide busy polling support
to all NAPI drivers, without them having to implement anything.
skb_mark_napi_id() can be called from napi_gro_receive() and
napi_get_frags().
Few drivers are still calling skb_mark_napi_id() because
they use netif_receive_skb(). They should eventually call
napi_gro_receive() instead. I will leave this to drivers
maintainers.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of having to implement complex ndo_busy_poll() method,
drivers can simply rely on NAPI poll logic.
Busy polling gains are mainly coming from polling itself,
not on exact details on how we poll the device.
ndo_busy_poll() if implemented can avoid touching
napi state, but it adds extra synchronization between
normal napi->poll() and busy poll handler, slowing down
the common path (non busy polling) with extra atomic operations.
In practice few drivers ever got busy poll because of the complexity.
We could go one step further, and make busy polling
available for all NAPI drivers, but this would require
that all netif_napi_del() calls are done in process context
so that we can call synchronize_rcu().
Full audit would be required.
Before this is done, a driver still needs to call :
- skb_mark_napi_id() for each skb provided to the stack.
- napi_hash_add() and napi_hash_del() to allocate a napi_id per napi struct.
- Make sure RCU grace period is respected after napi_hash_del() before
memory containing napi structure is freed.
Followup patch implements busy poll for mlx5 driver as an example.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of blocking BH in whole sk_busy_loop(), block them
only around ->ndo_busy_poll() calls.
This has many benefits.
1) allow tunneled traffic to use busy poll as well as native traffic.
Tunnels handlers usually call netif_rx() and depend on net_rx_action()
being run (from sofirq handler)
2) allow RFS/RPS being used (sending IPI to other cpus if needed)
3) use the 'lets burn cpu cycles' budget to do useful work
(like TX completions, timers, RCU callbacks...)
4) reduce BH latencies, making busy poll a better citizen.
Tested:
Tested with SIT tunnel
lpaa5:~# echo 0 >/proc/sys/net/core/busy_read
lpaa5:~# ./netperf -H 2002:af6:786::1 -t TCP_RR
MIGRATED TCP REQUEST/RESPONSE TEST from ::0 (::) port 0 AF_INET6 to 2002:af6:786::1 () port 0 AF_INET6 : first burst 0
Local /Remote
Socket Size Request Resp. Elapsed Trans.
Send Recv Size Size Time Rate
bytes Bytes bytes bytes secs. per sec
16384 87380 1 1 10.00 37373.93
16384 87380
Now enable busy poll on both hosts
lpaa5:~# echo 70 >/proc/sys/net/core/busy_read
lpaa6:~# echo 70 >/proc/sys/net/core/busy_read
lpaa5:~# ./netperf -H 2002:af6:786::1 -t TCP_RR
MIGRATED TCP REQUEST/RESPONSE TEST from ::0 (::) port 0 AF_INET6 to 2002:af6:786::1 () port 0 AF_INET6 : first burst 0
Local /Remote
Socket Size Request Resp. Elapsed Trans.
Send Recv Size Size Time Rate
bytes Bytes bytes bytes secs. per sec
16384 87380 1 1 10.00 58314.77
16384 87380
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is really little gain from inlining this big function.
We'll soon make it even bigger in following patches.
This means we no longer need to export napi_by_id()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
skb->sender_cpu and skb->napi_id share a common storage,
and we had various bugs about this.
We had to call skb_sender_cpu_clear() in some places to
not leave a prior skb->napi_id and fool netdev_pick_tx()
As suggested by Alexei, we could split the space so that
these errors can not happen.
0 value being reserved as the common (not initialized) value,
let's reserve [1 .. NR_CPUS] range for valid sender_cpu,
and [NR_CPUS+1 .. ~0U] for valid napi_id.
This will allow proper busy polling support over tunnels.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Suggested-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit 00ee592717 ("net: fix __netdev_update_features return
on ndo_set_features failure")
and adds a comment explaining why it's okay to return a value other than
0 upon error. Some drivers might actually change flags and return an
error so it's better to fire a spurious notification rather than miss
these.
CC: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A recent flaw in the netdev feature setting resulted in warnings
like this one from VLAN interfaces:
WARNING: CPU: 1 PID: 4975 at net/core/dev.c:2419 skb_warn_bad_offload+0xbc/0xcb()
: caps=(0x00000000001b5820, 0x00000000001b5829) len=2782 data_len=0 gso_size=1348 gso_type=16 ip_summed=3
The ":" is supposed to be preceded by a driver name, but in this
case it is an empty string since the device has no parent.
There are many types of network devices without a parent. The
anonymous warnings for these devices can be hard to debug. Log
the network device name instead in these cases to assist further
debugging.
This is mostly similar to how __netdev_printk() handles orphan
devices.
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
If ndo_set_features fails __netdev_update_features() will return -1 but
this is wrong because it is expected to return 0 if no features were
changed (see netdev_update_features()), which will cause a netdev
notifier to be called without any actual changes. Fix this by returning
0 if ndo_set_features fails.
Fixes: 6cb6a27c45 ("net: Call netdev_features_change() from netdev_update_features()")
CC: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When __netdev_update_features() was updated to ensure some features are
disabled on new lower devices, an error was introduced for devices which
don't have the ndo_set_features() method set. Before we'll just set the
new features, but now we return an error and don't set them. Fix this by
returning the old behaviour and setting err to 0 when ndo_set_features
is not present.
Fixes: e7868a85e1 ("net/core: ensure features get disabled on new lower devs")
CC: Jarod Wilson <jarod@redhat.com>
CC: Jiri Pirko <jiri@resnulli.us>
CC: Ido Schimmel <idosch@mellanox.com>
CC: Sander Eikelenboom <linux@eikelenboom.it>
CC: Andy Gospodarek <gospo@cumulusnetworks.com>
CC: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Reviewed-by: Jarod Wilson <jarod@redhat.com>
Tested-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: Dave Young <dyoung@redhat.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With moving netdev_sync_lower_features() after the .ndo_set_features
calls, I neglected to verify that devices added *after* a flag had been
disabled on an upper device were properly added with that flag disabled as
well. This currently happens, because we exit __netdev_update_features()
when we see dev->features == features for the upper dev. We can retain the
optimization of leaving without calling .ndo_set_features with a bit of
tweaking and a goto here.
Fixes: fd867d51f8 ("net/core: generic support for disabling netdev features down stack")
CC: "David S. Miller" <davem@davemloft.net>
CC: Eric Dumazet <edumazet@google.com>
CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <gospo@cumulusnetworks.com>
CC: Jiri Pirko <jiri@resnulli.us>
CC: Nikolay Aleksandrov <razor@blackwall.org>
CC: Michal Kubecek <mkubecek@suse.cz>
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: netdev@vger.kernel.org
Reported-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As pointed out by Nikolay and further explained by Geert, the initial
for_each_netdev_feature macro was broken, as feature would get set outside
of the block of code it was intended to run in, thus only ever working for
the first feature bit in the mask. While less pretty this way, this is
tested and confirmed functional with multiple feature bits set in
NETIF_F_UPPER_DISABLES.
[root@dell-per730-01 ~]# ethtool -K bond0 lro off
...
[ 242.761394] bond0: Disabling feature 0x0000000000008000 on lower dev p5p2.
[ 243.552178] bnx2x 0000:06:00.1 p5p2: using MSI-X IRQs: sp 74 fp[0] 76 ... fp[7] 83
[ 244.353978] bond0: Disabling feature 0x0000000000008000 on lower dev p5p1.
[ 245.147420] bnx2x 0000:06:00.0 p5p1: using MSI-X IRQs: sp 62 fp[0] 64 ... fp[7] 71
[root@dell-per730-01 ~]# ethtool -K bond0 gro off
...
[ 251.925645] bond0: Disabling feature 0x0000000000004000 on lower dev p5p2.
[ 252.713693] bnx2x 0000:06:00.1 p5p2: using MSI-X IRQs: sp 74 fp[0] 76 ... fp[7] 83
[ 253.499085] bond0: Disabling feature 0x0000000000004000 on lower dev p5p1.
[ 254.290922] bnx2x 0000:06:00.0 p5p1: using MSI-X IRQs: sp 62 fp[0] 64 ... fp[7] 71
Fixes: fd867d51f ("net/core: generic support for disabling netdev features down stack")
CC: "David S. Miller" <davem@davemloft.net>
CC: Eric Dumazet <edumazet@google.com>
CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <gospo@cumulusnetworks.com>
CC: Jiri Pirko <jiri@resnulli.us>
CC: Nikolay Aleksandrov <razor@blackwall.org>
CC: Michal Kubecek <mkubecek@suse.cz>
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: Geert Uytterhoeven <geert@linux-m68k.org>
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are some netdev features, which when disabled on an upper device,
such as a bonding master or a bridge, must be disabled and cannot be
re-enabled on underlying devices.
This is a rework of an earlier more heavy-handed appraoch, which simply
disables and prevents re-enabling of netdev features listed in a new
define in include/net/netdev_features.h, NETIF_F_UPPER_DISABLES. Any upper
device that disables a flag in that feature mask, the disabling will
propagate down the stack, and any lower device that has any upper device
with one of those flags disabled should not be able to enable said flag.
Initially, only LRO is included for proof of concept, and because this
code effectively does the same thing as dev_disable_lro(), though it will
also activate from the ethtool path, which was one of the goals here.
[root@dell-per730-01 ~]# ethtool -k bond0 |grep large
large-receive-offload: on
[root@dell-per730-01 ~]# ethtool -k p5p1 |grep large
large-receive-offload: on
[root@dell-per730-01 ~]# ethtool -K bond0 lro off
[root@dell-per730-01 ~]# ethtool -k bond0 |grep large
large-receive-offload: off
[root@dell-per730-01 ~]# ethtool -k p5p1 |grep large
large-receive-offload: off
dmesg dump:
[ 1033.277986] bond0: Disabling feature 0x0000000000008000 on lower dev p5p2.
[ 1034.067949] bnx2x 0000:06:00.1 p5p2: using MSI-X IRQs: sp 74 fp[0] 76 ... fp[7] 83
[ 1034.753612] bond0: Disabling feature 0x0000000000008000 on lower dev p5p1.
[ 1035.591019] bnx2x 0000:06:00.0 p5p1: using MSI-X IRQs: sp 62 fp[0] 64 ... fp[7] 71
This has been successfully tested with bnx2x, qlcnic and netxen network
cards as slaves in a bond interface. Turning LRO on or off on the master
also turns it on or off on each of the slaves, new slaves are added with
LRO in the same state as the master, and LRO can't be toggled on the
slaves.
Also, this should largely remove the need for dev_disable_lro(), and most,
if not all, of its call sites can be replaced by simply making sure
NETIF_F_LRO isn't included in the relevant device's feature flags.
Note that this patch is driven by bug reports from users saying it was
confusing that bonds and slaves had different settings for the same
features, and while it won't be 100% in sync if a lower device doesn't
support a feature like LRO, I think this is a good step in the right
direction.
CC: "David S. Miller" <davem@davemloft.net>
CC: Eric Dumazet <edumazet@google.com>
CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <gospo@cumulusnetworks.com>
CC: Jiri Pirko <jiri@resnulli.us>
CC: Nikolay Aleksandrov <razor@blackwall.org>
CC: Michal Kubecek <mkubecek@suse.cz>
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
net/ipv6/xfrm6_output.c
net/openvswitch/flow_netlink.c
net/openvswitch/vport-gre.c
net/openvswitch/vport-vxlan.c
net/openvswitch/vport.c
net/openvswitch/vport.h
The openvswitch conflicts were overlapping changes. One was
the egress tunnel info fix in 'net' and the other was the
vport ->send() op simplification in 'net-next'.
The xfrm6_output.c conflicts was also a simplification
overlapping a bug fix.
Signed-off-by: David S. Miller <davem@davemloft.net>
While transitioning to netdev based vport we broke OVS
feature which allows user to retrieve tunnel packet egress
information for lwtunnel devices. Following patch fixes it
by introducing ndo operation to get the tunnel egress info.
Same ndo operation can be used for lwtunnel devices and compat
ovs-tnl-vport devices. So after adding such device operation
we can remove similar operation from ovs-vport.
Fixes: 614732eaa1 ("openvswitch: Use regular VXLAN net_device device").
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This newly introduced netdevice notifier is called before actual change
upper happens. That provides a possibility for notifier handlers to
know upper change will happen and react to it, including possibility to
forbid the change. That is valuable for drivers which can check if the
upper device linkage is supported and forbid that in case it is not.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
SYN_RECV & TIMEWAIT sockets are not full blown, they do not have a
sk_dst_cache pointer.
Fixes: ca6fb06518 ("tcp: attach SYNACK messages to request sockets instead of listener")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
net/ipv4/arp.c
The net/ipv4/arp.c conflict was one commit adding a new
local variable while another commit was deleting one.
Signed-off-by: David S. Miller <davem@davemloft.net>
The __netdev_find_adj() helper does not use its first argument, only the
device to find and list to walk through.
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Drivers might call napi_disable while not holding the napi instance poll_lock.
In those instances, its possible for a race condition to exist between
poll_one_napi and napi_disable. That is to say, poll_one_napi only tests the
NAPI_STATE_SCHED bit to see if there is work to do during a poll, and as such
the following may happen:
CPU0 CPU1
ndo_tx_timeout napi_poll_dev
napi_disable poll_one_napi
test_and_set_bit (ret 0)
test_bit (ret 1)
reset adapter napi_poll_routine
If the adapter gets a tx timeout without a napi instance scheduled, its possible
for the adapter to think it has exclusive access to the hardware (as the napi
instance is now scheduled via the napi_disable call), while the netpoll code
thinks there is simply work to do. The result is parallel hardware access
leading to corrupt data structures in the driver, and a crash.
Additionaly, there is another, more critical race between netpoll and
napi_disable. The disabled napi state is actually identical to the scheduled
state for a given napi instance. The implication being that, if a napi instance
is disabled, a netconsole instance would see the napi state of the device as
having been scheduled, and poll it, likely while the driver was dong something
requiring exclusive access. In the case above, its fairly clear that not having
the rings in a state ready to be polled will cause any number of crashes.
The fix should be pretty easy. netpoll uses its own bit to indicate that that
the napi instance is in a state of being serviced by netpoll (NAPI_STATE_NPSVC).
We can just gate disabling on that bit as well as the sched bit. That should
prevent netpoll from conducting a napi poll if we convert its set bit to a
test_and_set_bit operation to provide mutual exclusion
Change notes:
V2)
Remove a trailing whtiespace
Resubmit with proper subject prefix
V3)
Clean up spacing nits
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: jmaxwell@redhat.com
Tested-by: jmaxwell@redhat.com
Signed-off-by: David S. Miller <davem@davemloft.net>
Existing bpf_clone_redirect() helper clones skb before redirecting
it to RX or TX of destination netdev.
Introduce bpf_redirect() helper that does that without cloning.
Benchmarked with two hosts using 10G ixgbe NICs.
One host is doing line rate pktgen.
Another host is configured as:
$ tc qdisc add dev $dev ingress
$ tc filter add dev $dev root pref 10 u32 match u32 0 0 flowid 1:2 \
action bpf run object-file tcbpf1_kern.o section clone_redirect_xmit drop
so it receives the packet on $dev and immediately xmits it on $dev + 1
The section 'clone_redirect_xmit' in tcbpf1_kern.o file has the program
that does bpf_clone_redirect() and performance is 2.0 Mpps
$ tc filter add dev $dev root pref 10 u32 match u32 0 0 flowid 1:2 \
action bpf run object-file tcbpf1_kern.o section redirect_xmit drop
which is using bpf_redirect() - 2.4 Mpps
and using cls_bpf with integrated actions as:
$ tc filter add dev $dev root pref 10 \
bpf run object-file tcbpf1_kern.o section redirect_xmit integ_act classid 1
performance is 2.5 Mpps
To summarize:
u32+act_bpf using clone_redirect - 2.0 Mpps
u32+act_bpf using redirect - 2.4 Mpps
cls_bpf using redirect - 2.5 Mpps
For comparison linux bridge in this setup is doing 2.1 Mpps
and ixgbe rx + drop in ip_rcv - 7.8 Mpps
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is immediately motivated by the bridge code that chains functions that
call into netfilter. Without passing net into the okfns the bridge code would
need to guess about the best expression for the network namespace to process
packets in.
As net is frequently one of the first things computed in continuation functions
after netfilter has done it's job passing in the desired network namespace is in
many cases a code simplification.
To support this change the function dst_output_okfn is introduced to
simplify passing dst_output as an okfn. For the moment dst_output_okfn
just silently drops the struct net.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
netif_receive_skb_sk is only called once in the bridge code, replace
it with a bridge specific function that calls netif_receive_skb.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A function with weird arguments that it will never use to accomdate a
netfilter callback prototype is absolutely in the core of the
networking stack. Frankly it does not make sense and it causes a lot
of confusion as to why arguments that are never used are being passed
to the function.
As I am preparing to make a second change to arguments to the okfn even
the names stops making sense.
As I have removed the two callers of this function remove this confusion
from the networking stack.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Printing a warning in alloc_netdev_mqs() if tx_queue_len is zero and
IFF_NO_QUEUE not set is not appropriate since drivers may use one of the
alloc_netdev* macros instead of alloc_etherdev*, thereby not
intentionally leaving tx_queue_len uninitialized. Instead check here if
tx_queue_len is zero and set IFF_NO_QUEUE, so the value of tx_queue_len
can be ignored in net/sched_generic.c.
Fixes: 906470c ("net: warn if drivers set tx_queue_len = 0")
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add info that is passed along with NETDEV_CHANGEUPPER event.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For classifiers getting invoked via tc_classify(), we always need an
extra function call into tc_classify_compat(), as both are being
exported as symbols and tc_classify() itself doesn't do much except
handling of reclassifications when tp->classify() returned with
TC_ACT_RECLASSIFY.
CBQ and ATM are the only qdiscs that directly call into tc_classify_compat(),
all others use tc_classify(). When tc actions are being configured
out in the kernel, tc_classify() effectively does nothing besides
delegating.
We could spare this layer and consolidate both functions. pktgen on
single CPU constantly pushing skbs directly into the netif_receive_skb()
path with a dummy classifier on ingress qdisc attached, improves
slightly from 22.3Mpps to 23.1Mpps.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Due to the introduction of IFF_NO_QUEUE, there is a better way for
drivers to indicate that no qdisc should be attached by default. Though,
the old convention can't be dropped since ignoring that setting would
break drivers still using it. Instead, add a warning so out-of-tree
driver maintainers get a chance to adjust their code before we finally
get rid of any special handling of tx_queue_len == 0.
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix the following typo
- unchainged -> unchanged
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduces a new dst_metadata which enables to carry per packet metadata
between forwarding and processing elements via the skb->dst pointer.
The structure is set up to be a union. Thus, each separate type of
metadata requires its own dst instance. If demand arises to carry
multiple types of metadata concurrently, metadata dst entries can be
made stackable.
The metadata dst entry is refcnt'ed as expected for now but a non
reference counted use is possible if the reference is forced before
queueing the skb.
In order to allow allocating dsts with variable length, the existing
dst_alloc() is split into a dst_alloc() and dst_init() function. The
existing dst_init() function to initialize the subsystem is being
renamed to dst_subsys_init() to make it clear what is what.
The check before ip_route_input() is changed to ignore metadata dsts
and drop the dst inside the routing function thus allowing to interpret
metadata in a later commit.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Just before queuing skb for xmit on port, check if skb has been marked by
switchdev port driver as already fordwarded by device. If so, drop skb. A
non-zero skb->offload_fwd_mark field is set by the switchdev port
driver/device on ingress to indicate the skb has already been forwarded by
the device to egress ports with matching dev->skb_mark. The switchdev port
driver would assign a non-zero dev->offload_skb_mark for each device port
netdev during registration, for example.
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch introduces the proto_down flag that can be used by user space
applications to notify switch drivers that errors have been detected on the
device.
The switch driver can react to protodown notification by doing a phys down
on the associated switch port.
Signed-off-by: Anuradha Karuppiah <anuradhak@cumulusnetworks.com>
Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: Wilson Kok <wkok@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
net/bridge/br_mdb.c
Minor conflict in br_mdb.c, in 'net' we added a memset of the
on-stack 'ip' variable whereas in 'net-next' we assign a new
member 'vid'.
Signed-off-by: David S. Miller <davem@davemloft.net>
Incoming packet should be either in backlog queue or
in RCU read-side section. Otherwise, the final sequence of
flush_backlog() and synchronize_net() may miss packets
that can run without device reference:
CPU 1 CPU 2
skb->dev: no reference
process_backlog:__skb_dequeue
process_backlog:local_irq_enable
on_each_cpu for
flush_backlog => IPI(hardirq): flush_backlog
- packet not found in backlog
CPU delayed ...
synchronize_net
- no ongoing RCU
read-side sections
netdev_run_todo,
rcu_barrier: no
ongoing callbacks
__netif_receive_skb_core:rcu_read_lock
- too late
free dev
process packet for freed dev
Fixes: 6e583ce524 ("net: eliminate refcounting in backlog queue")
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
commit 381c759d99 ("ipv4: Avoid crashing in ip_error")
fixes a problem where processed packet comes from device
with destroyed inetdev (dev->ip_ptr). This is not expected
because inetdev_destroy is called in NETDEV_UNREGISTER
phase and packets should not be processed after
dev_close_many() and synchronize_net(). Above fix is still
required because inetdev_destroy can be called for other
reasons. But it shows the real problem: backlog can keep
packets for long time and they do not hold reference to
device. Such packets are then delivered to upper levels
at the same time when device is unregistered.
Calling flush_backlog after NETDEV_UNREGISTER_FINAL still
accounts all packets from backlog but before that some packets
continue to be delivered to upper levels long after the
synchronize_net call which is supposed to wait the last
ones. Also, as Eric pointed out, processed packets, mostly
from other devices, can continue to add new packets to backlog.
Fix the problem by moving flush_backlog early, after the
device driver is stopped and before the synchronize_net() call.
Then use netif_running check to make sure we do not add more
packets to backlog. We have to do it in enqueue_to_backlog
context when the local IRQ is disabled. As result, after the
flush_backlog and synchronize_net sequence all packets
should be accounted.
Thanks to Eric W. Biederman for the test script and his
valuable feedback!
Reported-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Fixes: 6e583ce524 ("net: eliminate refcounting in backlog queue")
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit e1622baf54.
The side effect of this commit is to add a '@NONE' after each virtual
interface name with a 'ip link'. It may break existing scripts.
Reported-by: Olivier Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Tested-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
User space can crash kernel with
ip link add ifb10 numtxqueues 100000 type ifb
We must replace a BUG_ON() by proper test and return -EINVAL for
crazy values.
Fixes: 60877a32bc ("net: allow large number of tx queues")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
qdisc_bstats_update_cpu() and other helpers were added to support
percpu stats for qdisc.
We want to add percpu stats for tc action, so this patch add common
helpers.
qdisc_bstats_update_cpu() is renamed to qdisc_bstats_cpu_update()
qdisc_qstats_drop_cpu() is renamed to qdisc_qstats_cpu_drop()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 70008aa50e ("skbuff: convert to skb_orphan_frags") replaced
open coded tests of SKBTX_DEV_ZEROCOPY and skb_copy_ubufs with calls
to helper function skb_orphan_frags. Apply that to the last remaining
open coded site.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When we scan a packet for GRO processing, we want to see the most
common packet types in the front of the offload_base list.
So add a priority field so we can handle this properly.
IPv4/IPv6 get the highest priority with the implicit zero priority
field.
Next comes ethernet with a priority of 10, and then we have the MPLS
types with a priority of 15.
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Suggested-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reduce ifdef pollution slightly, no functional change. We can simply
remove the extra alternative definition of handle_ing() and nf_ingress().
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
commit d2788d3488 ("net: sched: further simplify handle_ing")
removed the call to qdisc_enqueue_root().
However, after this removal we no longer set qdisc pkt length.
This breaks traffic policing on ingress.
This is the minimum fix: set qdisc pkt length before tc_classify.
Only setting the length does remove support for 'stab' on ingress, but
as Alexei pointed out:
"Though it was allowed to add qdisc_size_table to ingress, it's useless.
Nothing takes advantage of recomputed qdisc_pkt_len".
Jamal suggested to use qdisc_pkt_len_init(), but as Eric mentioned that
would result in qdisc_pkt_len_init to no longer get inlined due to the
additional 2nd call site.
ingress policing is rare and GRO doesn't really work that well with police
on ingress, as we see packets > mtu and drop skbs that -- without
aggregation -- would still have fitted the policier budget.
Thus to have reliable/smooth ingress policing GRO has to be turned off.
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Fixes: d2788d3488 ("net: sched: further simplify handle_ing")
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
