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>
