This reverts commit 70a640d0da
("net/mlx4_en: Use affinity hint") and commit
c8865b64b0 ("cpumask: Utility function
to set n'th cpu - local cpu first") because these changes break
the build when SMP is disabled amongst other things.
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The “affinity hint” mechanism is used by the user space
daemon, irqbalancer, to indicate a preferred CPU mask for irqs.
Irqbalancer can use this hint to balance the irqs between the
cpus indicated by the mask.
We wish the HCA to preferentially map the IRQs it uses to numa cores
close to it. To accomplish this, we use cpumask_set_cpu_local_first(), that
sets the affinity hint according the following policy:
First it maps IRQs to “close” numa cores. If these are exhausted, the
remaining IRQs are mapped to “far” numa cores.
Signed-off-by: Yuval Atias <yuvala@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This function sets the n'th cpu - local cpu's first.
For example: in a 16 cores server with even cpu's local, will get the
following values:
cpumask_set_cpu_local_first(0, numa, cpumask) => cpu 0 is set
cpumask_set_cpu_local_first(1, numa, cpumask) => cpu 2 is set
...
cpumask_set_cpu_local_first(7, numa, cpumask) => cpu 14 is set
cpumask_set_cpu_local_first(8, numa, cpumask) => cpu 1 is set
cpumask_set_cpu_local_first(9, numa, cpumask) => cpu 3 is set
...
cpumask_set_cpu_local_first(15, numa, cpumask) => cpu 15 is set
Curently this function will be used by multi queue networking devices to
calculate the irq affinity mask, such that as many local cpu's as
possible will be utilized to handle the mq device irq's.
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pablo Neira Ayuso says:
====================
Netfilter/IPVS updates for net-next
This small patchset contains three accumulated Netfilter/IPVS updates,
they are:
1) Refactorize common NAT code by encapsulating it into a helper
function, similarly to what we do in other conntrack extensions,
from Florian Westphal.
2) A minor format string mismatch fix for IPVS, from Masanari Iida.
3) Add quota support to the netfilter accounting infrastructure, now
you can add quotas to accounting objects via the nfnetlink interface
and use them from iptables. You can also listen to quota
notifications from userspace. This enhancement from Mathieu Poirier.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
John W. Linville says:
====================
Please pull this batch of updates intended for 3.16...
For the mac80211 bits, Johannes says:
"Here I just have Heikki's rfkill GPIO cleanups.
The ARM/tegra patch is OK with the maintainer (Stephen). Let me know of
any problems."
and;
"We have a whole bunch of work on CSA by Andrei, Luca and Michal, but
unfortunately it doesn't seem quite complete yet so it's still disabled.
There's some TDLS work from Arik, and the rest is mostly minor fixes and
cleanups."
For the NFC bits, Samuel says:
"This is the NFC pull request for 3.16. We have:
- STMicroeectronics st21nfca support. The st21nfca is an HCI chipset and
thus relies on the HCI stack. This submission provides support for tag
redaer/writer mode (including Type 5) and device tree bindings.
- PM runtime support and a bunch of bug fixes for TI's trf7970a.
- Device tree support for NXP's pn544. Legacy platform data support is
obviously kept intact.
- NFC Tag type 4B support to the NFC Digital stack.
- SOCK_RAW type support to the raw NFC socket, and allow NCI
sniffing from that. This can be extended to report HCI frames and also
proprietarry ones like e.g. the pn533 ones."
For the iwlwifi bits, Emmanuel says:
"Eran continues to work on new devices, Eyal is still digging in
the rate control stuff, and Johannes added new functionality to the
debug system we have in place now along with a few cleanups he made
on the way. That's pretty much it."
and;
"Avri continues to work on the power code and Eran is improving the
NVM handling as a preparations for new devices on which he works
with Liad. Luca cleans up a bit the code while working on CSA. I have
the regular BT Coex stuff and a small lockdep fix. Johannes has his
regular amount of clean ups and improvements, the main one is the
ability to leave 2 chains open to improve diversity and hence the
throughput in high attenuation scenarios."
and;
"The regular amount of housekeeping here. I merged iwlwifi-fixes.git to
be able to add the patch you didn't want in wireless.git at that stage
of the -rc cycle. Luca has a few preparations for CSA implementation
and also what seems to be a bugfix for P2P but hasn't caused issues
we could notice."
For the Atheros bits, Kalle says:
"For ath10k Michal did various small fixes on how we handle
hardware/firmware problems and he also fixed two memory leaks."
Also included are a couple of pulls from the wireless tree to
avoid/resolve merge issues...
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a function to walk the list of subnodes of a mdio bus and look for
a node that matches the phy's address with its 'reg' property. If found,
set the of_node pointer for the phy. This allows auto-probed pyh
devices to be augmented by information passed in via DT.
Signed-off-by: Daniel Mack <zonque@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/bonding/bond_alb.c
drivers/net/ethernet/altera/altera_msgdma.c
drivers/net/ethernet/altera/altera_sgdma.c
net/ipv6/xfrm6_output.c
Several cases of overlapping changes.
The xfrm6_output.c has a bug fix which overlaps the renaming
of skb->local_df to skb->ignore_df.
In the Altera TSE driver cases, the register access cleanups
in net-next overlapped with bug fixes done in net.
Similarly a bug fix to send ALB packets in the bonding driver using
the right source address overlaps with cleanups in net-next.
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking fixes from David Miller:
"It looks like a sizeble collection but this is nearly 3 weeks of bug
fixing while you were away.
1) Fix crashes over IPSEC tunnels with NAT, the latter can reroute
the packet through a non-IPSEC protected path and the code has to
be able to handle SKBs attached to routes lacking an attached xfrm
state. From Steffen Klassert.
2) Fix OOPSs in ipv4 and ipv6 ipsec layers for unsupported
sub-protocols, also from Steffen Klassert.
3) Set local_df on fragmented netfilter skbs otherwise we won't be
able to forward successfully, from Florian Westphal.
4) cdc_mbim ipv6 neighbour code does __vlan_find_dev_deep without
holding RCU lock, from Bjorn Mork.
5) local_df test in ip_may_fragment is inverted, from Florian
Westphal.
6) jme driver doesn't check for DMA mapping failures, from Neil
Horman.
7) qlogic driver doesn't calculate number of TX queues properly, from
Shahed Shaikh.
8) fib_info_cnt can drift irreversibly positive if we fail to
allocate the fi->fib_metrics array, from Sergey Popovich.
9) Fix use after free in ip6_route_me_harder(), also from Sergey
Popovich.
10) When SYSCTL is disabled, we don't handle local_port_range and
ping_group_range defaults properly at all, from Cong Wang.
11) Unaccelerated VLAN tagged frames improperly handled by cdc_mbim
driver, fix from Bjorn Mork.
12) cassini driver needs nested lock annotations for TX locking, from
Emil Goode.
13) On init error ipv6 VTI driver can unregister pernet ops twice,
oops. Fix from Mahtias Krause.
14) If macvlan device is down, don't propagate IFF_ALLMULTI changes,
from Peter Christensen.
15) Missing NULL pointer check while parsing netlink config options in
ip6_tnl_validate(). From Susant Sahani.
16) Fix handling of neighbour entries during ipv6 router reachability
probing, from Duan Jiong.
17) x86 and s390 JIT address randomization has some address
calculation bugs leading to crashes, from Alexei Starovoitov and
Heiko Carstens.
18) Clear up those uglies with nop patching and net_get_random_once(),
from Hannes Frederic Sowa.
19) Option length miscalculated in ip6_append_data(), fix also from
Hannes Frederic Sowa.
20) A while ago we fixed a race during device unregistry when a
namespace went down, turns out there is a second place that needs
similar protection. From Cong Wang.
21) In the new Altera TSE driver multicast filtering isn't working,
disable it and just use promisc mode until the cause is found.
From Vince Bridgers.
22) When we disable router enabling in ipv6 we have to flush the
cached routes explicitly, from Duan Jiong.
23) NBMA tunnels should not cache routes on the tunnel object because
the key is variable, from Timo Teräs.
24) With stacked devices GRO information in skb->cb[] can be not setup
properly, make sure it is in all code paths. From Eric Dumazet.
25) Really fix stacked vlan locking, multiple levels of nesting with
intervening non-vlan devices are possible. From Vlad Yasevich.
26) Fallback ipip tunnel device's mtu is not setup properly, from
Steffen Klassert.
27) The packet scheduler's tcindex filter can crash because we
structure copy objects with list_head's inside, oops. From Cong
Wang.
28) Fix CHECKSUM_COMPLETE handling for ipv6 GRE tunnels, from Eric
Dumazet.
29) In some configurations 'itag' in __mkroute_input() can end up
being used uninitialized because of how fib_validate_source()
works. Fix it by explitly initializing itag to zero like all the
other fib_validate_source() callers do, from Li RongQing"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (116 commits)
batman: fix a bogus warning from batadv_is_on_batman_iface()
ipv4: initialise the itag variable in __mkroute_input
bonding: Send ALB learning packets using the right source
bonding: Don't assume 802.1Q when sending alb learning packets.
net: doc: Update references to skb->rxhash
stmmac: Remove unbalanced clk_disable call
ipv6: gro: fix CHECKSUM_COMPLETE support
net_sched: fix an oops in tcindex filter
can: peak_pci: prevent use after free at netdev removal
ip_tunnel: Initialize the fallback device properly
vlan: Fix build error wth vlan_get_encap_level()
can: c_can: remove obsolete STRICT_FRAME_ORDERING Kconfig option
MAINTAINERS: Pravin Shelar is Open vSwitch maintainer.
bnx2x: Convert return 0 to return rc
bonding: Fix alb mode to only use first level vlans.
bonding: Fix stacked device detection in arp monitoring
macvlan: Fix lockdep warnings with stacked macvlan devices
vlan: Fix lockdep warning with stacked vlan devices.
net: Allow for more then a single subclass for netif_addr_lock
net: Find the nesting level of a given device by type.
...
The sk_unattached_filter_create() API is used by BPF filters that
are not directly attached or related to sockets, and are used in
team, ptp, xt_bpf, cls_bpf, etc. As such all users do their own
internal managment of obtaining filter blocks and thus already
have them in kernel memory and set up before calling into
sk_unattached_filter_create(). As a result, due to __user annotation
in sock_fprog, sparse triggers false positives (incorrect type in
assignment [different address space]) when filters are set up before
passing them to sk_unattached_filter_create(). Therefore, let
sk_unattached_filter_create() API use sock_fprog_kern to overcome
this issue.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Lets get rid of this macro. After commit 5bcfedf06f ("net: filter:
simplify label names from jump-table"), labels have become more
readable due to omission of BPF_ prefix but at the same time more
generic, so that things like `git grep -n` would not find them. As
a middle path, lets get rid of the DL macro as it's not strictly
needed and would otherwise just hide the full name.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RFC 6935 permits zero checksums to be used in IPv6 however this is
recommended only for certain tunnel protocols, it does not make
checksums completely optional like they are in IPv4.
This patch restricts the use of IPv6 zero checksums that was previously
intoduced. no_check6_tx and no_check6_rx have been added to control
the use of checksums in UDP6 RX and TX path. The normal
sk_no_check_{rx,tx} settings are not used (this avoids ambiguity when
dealing with a dual stack socket).
A helper function has been added (udp_set_no_check6) which can be
called by tunnel impelmentations to all zero checksums (send on the
socket, and accept them as valid).
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
o min_tx_rate puts lower limit on the VF bandwidth. VF is guaranteed
to have a bandwidth of at least this value.
max_tx_rate puts cap on the VF bandwidth. VF can have a bandwidth
of up to this value.
o A new handler set_vf_rate for attr IFLA_VF_RATE has been introduced
which takes 4 arguments:
netdev, VF number, min_tx_rate, max_tx_rate
o ndo_set_vf_rate replaces ndo_set_vf_tx_rate handler.
o Drivers that currently implement ndo_set_vf_tx_rate should now call
ndo_set_vf_rate instead and reject attempt to set a minimum bandwidth
greater than 0 for IFLA_VF_TX_RATE when IFLA_VF_RATE is not yet
implemented by driver.
o If user enters only one of either min_tx_rate or max_tx_rate, then,
userland should read back the other value from driver and set both
for IFLA_VF_RATE.
Drivers that have not yet implemented IFLA_VF_RATE should always
return min_tx_rate as 0 when read from ip tool.
o If both IFLA_VF_TX_RATE and IFLA_VF_RATE options are specified, then
IFLA_VF_RATE should override.
o Idea is to have consistent display of rate values to user.
o Usage example: -
./ip link set p4p1 vf 0 rate 900
./ip link show p4p1
32: p4p1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode
DEFAULT qlen 1000
link/ether 00:0e:1e:08:b0:f0 brd ff:ff:ff:ff:ff:ff
vf 0 MAC 3e:a0:ca:bd:ae:5a, tx rate 900 (Mbps), max_tx_rate 900Mbps
vf 1 MAC f6:c6:7c:3f:3d:6c
vf 2 MAC 56:32:43:98:d7:71
vf 3 MAC d6:be:c3:b5:85:ff
vf 4 MAC ee:a9:9a:1e:19:14
vf 5 MAC 4a:d0:4c:07:52:18
vf 6 MAC 3a:76:44:93:62:f9
vf 7 MAC 82:e9:e7:e3:15:1a
./ip link set p4p1 vf 0 max_tx_rate 300 min_tx_rate 200
./ip link show p4p1
32: p4p1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode
DEFAULT qlen 1000
link/ether 00:0e:1e:08:b0:f0 brd ff:ff:ff:ff:ff:ff
vf 0 MAC 3e:a0:ca:bd:ae:5a, tx rate 300 (Mbps), max_tx_rate 300Mbps,
min_tx_rate 200Mbps
vf 1 MAC f6:c6:7c:3f:3d:6c
vf 2 MAC 56:32:43:98:d7:71
vf 3 MAC d6:be:c3:b5:85:ff
vf 4 MAC ee:a9:9a:1e:19:14
vf 5 MAC 4a:d0:4c:07:52:18
vf 6 MAC 3a:76:44:93:62:f9
vf 7 MAC 82:e9:e7:e3:15:1a
./ip link set p4p1 vf 0 max_tx_rate 600 rate 300
./ip link show p4p1
32: p4p1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode
DEFAULT qlen 1000
link/ether 00:0e:1e:08:b0:f brd ff:ff:ff:ff:ff:ff
vf 0 MAC 3e:a0:ca:bd:ae:5, tx rate 600 (Mbps), max_tx_rate 600Mbps,
min_tx_rate 200Mbps
vf 1 MAC f6:c6:7c:3f:3d:6c
vf 2 MAC 56:32:43:98:d7:71
vf 3 MAC d6:be:c3:b5:85:ff
vf 4 MAC ee:a9:9a:1e:19:14
vf 5 MAC 4a:d0:4c:07:52:18
vf 6 MAC 3a:76:44:93:62:f9
vf 7 MAC 82:e9:e7:e3:15:1a
Signed-off-by: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull scheduler fixes from Ingo Molnar:
"The biggest commit is an irqtime accounting loop latency fix, the rest
are misc fixes all over the place: deadline scheduling, docs, numa,
balancer and a bad to-idle latency fix"
* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/numa: Initialize newidle balance stats in sd_numa_init()
sched: Fix updating rq->max_idle_balance_cost and rq->next_balance in idle_balance()
sched: Skip double execution of pick_next_task_fair()
sched: Use CPUPRI_NR_PRIORITIES instead of MAX_RT_PRIO in cpupri check
sched/deadline: Fix memory leak
sched/deadline: Fix sched_yield() behavior
sched: Sanitize irq accounting madness
sched/docbook: Fix 'make htmldocs' warnings caused by missing description
Pull perf fixes from Ingo Molnar:
"The biggest changes are fixes for races that kept triggering Trinity
crashes, plus liblockdep build fixes and smaller misc fixes.
The liblockdep bits in perf/urgent are a pull mistake - they should
have been in locking/urgent - but by the time I noticed other commits
were added and testing was done :-/ Sorry about that"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf: Fix a race between ring_buffer_detach() and ring_buffer_attach()
perf: Prevent false warning in perf_swevent_add
perf: Limit perf_event_attr::sample_period to 63 bits
tools/liblockdep: Remove all build files when doing make clean
tools/liblockdep: Build liblockdep from tools/Makefile
perf/x86/intel: Fix Silvermont's event constraints
perf: Fix perf_event_init_context()
perf: Fix race in removing an event
In commit ad86622b47 ("wait: swap EXIT_ZOMBIE and EXIT_DEAD to hide
EXIT_TRACE from user-space") the order of task state definitions were
changed: EXIT_DEAD and EXIT_ZOMBIE were swapped. Though the charterers
for the states in TASK_STATE_TO_CHAR_STR string were not updated. This
patch synchronizes the string to the order of definitions.
Signed-off-by: Masatake YAMATO <yamato@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
use_prio was added as part of an infrastructure for running FCoE in A0 mode.
FCoE didn't get into Mellanox Upstream driver, and when it will, it won't be
using A0 steering mode.
Therefore we can safely deprecate this module parameter without hurting any
existing user.
CC: Carol Soto <clsoto@linux.vnet.ibm.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
All in-tree drivers have been converted to use the new pair of
functions: of_is_fixed_phy_link() plus of_phy_register_fixed_link(), we
can now safely remove of_phy_connect_fixed_link.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When combining real_dev's features and vlan_features, simple
bitwise AND is used. This doesn't work well for checksum
offloading features as if one set has NETIF_F_HW_CSUM and the
other NETIF_F_IP_CSUM and/or NETIF_F_IPV6_CSUM, we end up with
no checksum offloading. However, from the logical point of view
(how can_checksum_protocol() works), NETIF_F_HW_CSUM contains
the functionality of NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM so
that the result should be IP/IPV6.
Add helper function netdev_intersect_features() implementing
this logic and use it in vlan_dev_fix_features().
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is the NFC pull request for 3.16. We have:
- STMicroeectronics st21nfca support. The st21nfca is an HCI chipset and
thus relies on the HCI stack. This submission provides support for tag
redaer/writer mode (including Type 5) and device tree bindings.
- PM runtime support and a bunch of bug fixes for TI's trf7970a.
- Device tree support for NXP's pn544. Legacy platform data support is
obviously kept intact.
- NFC Tag type 4B support to the NFC Digital stack.
- SOCK_RAW type support to the raw NFC socket, and allow NCI
sniffing from that. This can be extended to report HCI frames and also
proprietarry ones like e.g. the pn533 ones.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=cSl+
-----END PGP SIGNATURE-----
Merge tag 'nfc-next-3.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/sameo/nfc-next
Samuel Ortiz <sameo@linux.intel.com> says:
"NFC: 3.16: First pull request
This is the NFC pull request for 3.16. We have:
- STMicroeectronics st21nfca support. The st21nfca is an HCI chipset and
thus relies on the HCI stack. This submission provides support for tag
redaer/writer mode (including Type 5) and device tree bindings.
- PM runtime support and a bunch of bug fixes for TI's trf7970a.
- Device tree support for NXP's pn544. Legacy platform data support is
obviously kept intact.
- NFC Tag type 4B support to the NFC Digital stack.
- SOCK_RAW type support to the raw NFC socket, and allow NCI
sniffing from that. This can be extended to report HCI frames and also
proprietarry ones like e.g. the pn533 ones."
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Experience with the recent e114a710aa ("tcp: fix cwnd limited
checking to improve congestion control") has shown that there are
common cases where that commit can cause cwnd to be much larger than
necessary. This leads to TSO autosizing cooking skbs that are too
large, among other things.
The main problems seemed to be:
(1) That commit attempted to predict the future behavior of the
connection by looking at the write queue (if TSO or TSQ limit
sending). That prediction sometimes overestimated future outstanding
packets.
(2) That commit always allowed cwnd to grow to twice the number of
outstanding packets (even in congestion avoidance, where this is not
needed).
This commit improves both of these, by:
(1) Switching to a measurement-based approach where we explicitly
track the largest number of packets in flight during the past window
("max_packets_out"), and remember whether we were cwnd-limited at the
moment we finished sending that flight.
(2) Only allowing cwnd to grow to twice the number of outstanding
packets ("max_packets_out") in slow start. In congestion avoidance
mode we now only allow cwnd to grow if it was fully utilized.
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Kernel API for classic BPF socket filters is:
sk_unattached_filter_create() - validate classic BPF, convert, JIT
SK_RUN_FILTER() - run it
sk_unattached_filter_destroy() - destroy socket filter
Cleanup internal BPF kernel API as following:
sk_filter_select_runtime() - final step of internal BPF creation.
Try to JIT internal BPF program, if JIT is not available select interpreter
SK_RUN_FILTER() - run it
sk_filter_free() - free internal BPF program
Disallow direct calls to BPF interpreter. Execution of the BPF program should
be done with SK_RUN_FILTER() macro.
Example of internal BPF create, run, destroy:
struct sk_filter *fp;
fp = kzalloc(sk_filter_size(prog_len), GFP_KERNEL);
memcpy(fp->insni, prog, prog_len * sizeof(fp->insni[0]));
fp->len = prog_len;
sk_filter_select_runtime(fp);
SK_RUN_FILTER(fp, ctx);
sk_filter_free(fp);
Sockets, seccomp, testsuite, tracing are using different ways to populate
sk_filter, so first steps of program creation are not common.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Here are two driver core (well, sysfs) fixes for 3.15-rc6 that resolve
some reported issues and a regression from 3.13.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)
iEUEABECAAYFAlN8LzgACgkQMUfUDdst+ynJnQCeKQt7KdEBlHAKI5/iP2IQVNNx
KG8AmMepPCjpp9/MbrFQnx3miGgNEug=
=813a
-----END PGP SIGNATURE-----
Merge tag 'driver-core-3.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core
Pull driver core fixes from Greg KH:
"Here are two driver core (well, sysfs) fixes for 3.15-rc6 that resolve
some reported issues and a regression from 3.13"
* tag 'driver-core-3.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core:
sysfs: make sure read buffer is zeroed
kernfs, sysfs, cgroup: restrict extra perm check on open to sysfs
Pull more cgroup fixes from Tejun Heo:
"Three more patches to fix cgroup_freezer breakage due to the recent
cgroup internal locking changes - an operation cgroup_freezer was
using now requires sleepable context and cgroup_freezer was invoking
that while holding a spin lock. cgroup_freezer was using an overly
elaborate hierarchical locking scheme.
While it's possible to convert the hierarchical spinlocks directly to
mutexes, this patch simplifies the overall locking so that it uses a
global mutex. This has the added benefit of avoiding iterating
potentially huge number of tasks under a spinlock. While the patch is
on the larger side in the devel cycle, the changes made are mostly
straight-forward and the locking logic is a lot simpler afterwards"
* 'for-3.15-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cgroup: fix rcu_read_lock() leak in update_if_frozen()
cgroup_freezer: replace freezer->lock with freezer_mutex
cgroup: introduce task_css_is_root()
This branch contains bug fixes important to get into v3.15. There is a
fix for modifying properties seen during early boot, a fix for an
incorrect prototype when CONFIG_OF=n, and a couple of corrections to
device tree memory nodes on a few platforms.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=kY49
-----END PGP SIGNATURE-----
Merge tag 'dt-for-linus' of git://git.secretlab.ca/git/linux
Pull device tree fixes from Grant Likely:
"Drivercore bugfixes for v3.15
This branch contains bug fixes important to get into v3.15. There is
a fix for modifying properties seen during early boot, a fix for an
incorrect prototype when CONFIG_OF=n, and a couple of corrections to
device tree memory nodes on a few platforms"
* tag 'dt-for-linus' of git://git.secretlab.ca/git/linux:
mips: dts: Fix missing device_type="memory" property in memory nodes
arm: dts: Fix missing device_type="memory" for ste-ccu8540
of: fix CONFIG_OF=n prototype of of_node_full_name()
of: make of_update_property() usable earlier in the boot process
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iEYEABECAAYFAlN5tPcACgkQjTAFq1RaXHPSsgCgltm13xcL165QR6A1uKw+r37h
Dt0AnAuJNFvks5HiYZSdGa9GRreoF+uG
=qgHD
-----END PGP SIGNATURE-----
Merge tag 'linux-can-next-for-3.16-20140519' of git://gitorious.org/linux-can/linux-can-next
Marc Kleine-Budde says:
====================
pull-request: can-next 2014-05-19
this is a pull request of 13 patches for net-next/master.
A patch by Dan Carpenter fixes a coccinelle warning in the mcp251x
driver. Jean Delvare contributes three patches to tightening the
Kconfig dependencies for some drivers. Then come three patches by Pavel
Machek that improve the c_can driver support on the socfpga platform.
Sergei Shtylyov's patch brings support for the CAN hardware found on
Renesas R-Car CAN controllers. Four patches by Oliver Hartkopp, the
first cleans up the guard macros in the CAN headers the other three
improve the EFF frame filtering. Maximilian Schneider's patch adds
support for the GS_USB CAN devices.
Signed-off-by: David S. Miller <davem@davemloft.net>
The upper timer_interval limit is arbitrary and much higher
than anything usable in the real world. Reducing it from 15s
to ~4s to make the timer_interval fit in an u32 does not make
much difference. The limit is still outside the practical
bounds.
This eliminates the need for a 64bit timer_interval, fixing a
build error related to 64bit division:
drivers/built-in.o: In function `cdc_ncm_get_coalesce':
ak8975.c:(.text+0x1ac994): undefined reference to `__aeabi_uldivmod'
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
The new function vlan_get_encap_level() uses vlan_dev_priv()
which is only conditionally avaialble when VLAN support is
enabled. Make vlan_get_encap_level() conditionally available
as well.
Fixes: 44a4085538 ("bonding: Fix stacked device detection in arp monitoring")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
CC: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull irq fixes from Thomas Gleixner:
"Two small updates from the irq departement:
- Provide missing inline stub for a SMP only function
- Add sub-maintainer for the drivers/irqchip/ part of the irq
subsystem. YAY!"
* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
MAINTAINERS: Add co-maintainer for drivers/irqchip
genirq: Provide irq_force_affinity fallback for non-SMP
Some devices may have different features despite sharing the same ID
(e.g. PCI ID). For example 14e4:4331 is usually a dual band, but this
can be "limited". Device with "pci/x/y/devid=0x4332" supports 2.4 GHz
only. Similarly 0x4333 will mean support for 5 GHz only.
Add entry in SPROM so info described above can be extracted and stored.
Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Acked-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Alexander noticed that we use RCU iteration on rb->event_list but do
not use list_{add,del}_rcu() to add,remove entries to that list, nor
do we observe proper grace periods when re-using the entries.
Merge ring_buffer_detach() into ring_buffer_attach() such that
attaching to the NULL buffer is detaching.
Furthermore, ensure that between any 'detach' and 'attach' of the same
event we observe the required grace period, but only when strictly
required. In effect this means that only ioctl(.request =
PERF_EVENT_IOC_SET_OUTPUT) will wait for a grace period, while the
normal initial attach and final detach will not be delayed.
This patch should, I think, do the right thing under all
circumstances, the 'normal' cases all should never see the extra grace
period, but the two cases:
1) PERF_EVENT_IOC_SET_OUTPUT on an event which already has a
ring_buffer set, will now observe the required grace period between
removing itself from the old and attaching itself to the new buffer.
This case is 'simple' in that both buffers are present in
perf_event_set_output() one could think an unconditional
synchronize_rcu() would be sufficient; however...
2) an event that has a buffer attached, the buffer is destroyed
(munmap) and then the event is attached to a new/different buffer
using PERF_EVENT_IOC_SET_OUTPUT.
This case is more complex because the buffer destruction does:
ring_buffer_attach(.rb = NULL)
followed by the ioctl() doing:
ring_buffer_attach(.rb = foo);
and we still need to observe the grace period between these two
calls due to us reusing the event->rb_entry list_head.
In order to make 2 happen we use Paul's latest cond_synchronize_rcu()
call.
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Reported-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140507123526.GD13658@twins.programming.kicks-ass.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Armin pointed me to the fact that the identifier which is used to ensure the
unique include processing in lunux/include/uapi/linux/can.h is CAN_H.
This clashed with his own source as includes from libraries and APIs should
use an underscore '_' at the identifier start.
This patch fixes the protection identifiers in all CAN relavant includes.
Reported-by: Armin Burchardt <armin@uni-bremen.de>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Add support for the CAN controller found in Renesas R-Car SoCs.
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Calling netif_carrier_{on,off} is sufficient. There is no need
to duplicate the carrier state in a driver specific flag.
Acked-by: Enrico Mioso <mrkiko.rs@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
Lots of devices request much larger buffers than reasonable. This
cause real problems for users of hosts with limited resources.
Reducing the default buffer size to 16kB for such devices is
a reasonable trade-off between allowing them to aggregate traffic
and avoiding memory exhaustion on resource restrained hosts.
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
To have an idea of the effects of the protocol coalescing
it's useful to have some counters showing the different
aspects.
Due to the asymmetrical usbnet interface the netdev
rx_bytes counter has been counting real received payload,
while the tx_bytes counter has included the NCM/MBIM
framing overhead. This overhead can be many times the
payload because of the aggressive padding strategy of
this driver, and will vary a lot depending on device
and traffic.
With very few exceptions, users are only interested in
the payload size. Having an somewhat accurate payload
byte counter is particularly important for mobile
broadband devices, which many NCM devices and of course
all MBIM devices are. Users and userspace applications
will use this counter to monitor account quotas.
Having protocol specific counters for the overhead, we are
now able to correct the tx_bytes netdev counter so that
it shows the real payload
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
We pad frames larger than X to maximum size for devices which
don't need a ZLP after maximum sized frames. This allows the
device to optimize its transfers for one fixed buffer size.
X was arbitrarily set at 512 bytes regardless of real buffer
maximum, causing extreme overheads due to excessive padding of
larger tx buffers. Limit the padding to at most 3 full USB
packets, still allowing the overhead to payload ratio of 3/1.
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
Many newer NCM and MBIM devices will request a maximum tx
datagram count which is much smaller than our hard-coded
absolute max. We can reduce the overhead without sacrificing
any of the simplicity for these devices, by simply using the
true negotiated count in when calculated the maximum NTH and
NDP header sizes.
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
Datagram coalescing is an integral part of the NCM and MBIM
protocols, intended to reduce the interrupt load primarily
on the device end of the USB link. As with all coalescing
solutions, there is a trade-off between buffering and
interrupts.
The current defaults are based on the assumption that device
side buffers should be the limiting factor. However, many
modern high speed LTE modems suffers from buffer-bloat,
making this assumption fail. This results in sub-optimal
performance due to excessive coalescing. And in cases where
such modems are connected to cheap embedded hosts there is
often severe buffer allocation issues, giving very noticeable
performance degradation .
A start on improving this is going from build time hard
coded limits to per device user configurable limits. The
ethtool coalescing API was selected as user interface
because, although the tuned values are buffer sizes, these
settings directly control datagram coalescing.
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
Prior to commit fbd929f2dc
bonding: support QinQ for bond arp interval
the arp monitoring code allowed for proper detection of devices
stacked on top of vlans. Since the above commit, the
code can still detect a device stacked on top of single
vlan, but not a device stacked on top of Q-in-Q configuration.
The search will only set the inner vlan tag if the route
device is the vlan device. However, this is not always the
case, as it is possible to extend the stacked configuration.
With this patch it is possible to provision devices on
top Q-in-Q vlan configuration that should be used as
a source of ARP monitoring information.
For example:
ip link add link bond0 vlan10 type vlan proto 802.1q id 10
ip link add link vlan10 vlan100 type vlan proto 802.1q id 100
ip link add link vlan100 type macvlan
Note: This patch limites the number of stacked VLANs to 2,
just like before. The original, however had another issue
in that if we had more then 2 levels of VLANs, we would end
up generating incorrectly tagged traffic. This is no longer
possible.
Fixes: fbd929f2dc (bonding: support QinQ for bond arp interval)
CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@redhat.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: Ding Tianhong <dingtianhong@huawei.com>
CC: Patric McHardy <kaber@trash.net>
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit dc8eaaa006.
vlan: Fix lockdep warning when vlan dev handle notification
Instead we use the new new API to find the lock subclass of
our vlan device. This way we can support configurations where
vlans are interspersed with other devices:
bond -> vlan -> macvlan -> vlan
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently netif_addr_lock_nested assumes that there can be only
a single nesting level between 2 devices. However, if we
have multiple devices of the same type stacked, this fails.
For example:
eth0 <-- vlan0.10 <-- vlan0.10.20
A more complicated configuration may stack more then one type of
device in different order.
Ex:
eth0 <-- vlan0.10 <-- macvlan0 <-- vlan1.10.20 <-- macvlan1
This patch adds an ndo_* function that allows each stackable
device to report its nesting level. If the device doesn't
provide this function default subclass of 1 is used.
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Multiple devices in the kernel can be stacked/nested and they
need to know their nesting level for the purposes of lockdep.
This patch provides a generic function that determines a nesting
level of a particular device by its type (ex: vlan, macvlan, etc).
We only care about nesting of the same type of devices.
For example:
eth0 <- vlan0.10 <- macvlan0 <- vlan1.20
The nesting level of vlan1.20 would be 1, since there is another vlan
in the stack under it.
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds user-visible interfaces for the llsec infrastructure.
For the added methods, the only major difference between all add/remove
implementation lies in how the specific object is parsed, and for dump
requests, how objects are written into netlink messages.
To save on boilerplate code, table dumps are routed through a helper
function that handles netlink dump state, leaving the actual dumping
code to care only about iterating over the table to be dumped and
filling netlink messages. For add/remove methods, the boilerplate
required to work is not quite as large, but still enough to also move
into a local helper.
Signed-off-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some Ethernet MACs have a "fixed link", and are not connected to a
normal MDIO-managed PHY device. For those situations, a Device Tree
binding allows to describe a "fixed link" using a special PHY node.
This patch adds:
* A documentation for the fixed PHY Device Tree binding.
* An of_phy_is_fixed_link() function that an Ethernet driver can call
on its PHY phandle to find out whether it's a fixed link PHY or
not. It should typically be used to know if
of_phy_register_fixed_link() should be called.
* An of_phy_register_fixed_link() function that instantiates the
fixed PHY into the PHY subsystem, so that when the driver calls
of_phy_connect(), the PHY device associated to the OF node will be
found.
These two additional functions also support the old fixed-link Device
Tree binding used on PowerPC platforms, so that ultimately, the
network device drivers for those platforms could be converted to use
of_phy_is_fixed_link() and of_phy_register_fixed_link() instead of
of_phy_connect_fixed_link(), while keeping compatibility with their
respective Device Tree bindings.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The existing fixed_phy_add() function has several drawbacks that
prevents it from being used as is for OF-based declaration of fixed
PHYs:
* The address of the PHY on the fake bus needs to be passed, while a
dynamic allocation is desired.
* Since the phy_device instantiation is post-poned until the next
mdiobus scan, there is no way to associate the fixed PHY with its
OF node, which later prevents of_phy_connect() from finding this
fixed PHY from a given OF node.
To solve this, this commit introduces fixed_phy_register(), which will
allocate an available PHY address, add the PHY using fixed_phy_add()
and instantiate the phy_device structure associated with the provided
OF node.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
Tested-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds UPDATE_QP SRIOV wrapper support.
The mechanism is a general one, but currently only source MAC
index changes are allowed for VFs.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This eliminates a 1-bit left shift in every single caller,
and makes the inner loop of the CRC computation more efficient.
Renamed crc7 to crc7_be (big-endian) since the interface changed.
Also purged #include <linux/crc7.h> from files that don't use it at all.
Signed-off-by: George Spelvin <linux@horizon.com>
Reviewed-by: Pavel Machek <pavel@ucw.cz>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Maps all internal BPF instructions into x86_64 instructions.
This patch replaces original BPF x64 JIT with internal BPF x64 JIT.
sysctl net.core.bpf_jit_enable is reused as on/off switch.
Performance:
1. old BPF JIT and internal BPF JIT generate equivalent x86_64 code.
No performance difference is observed for filters that were JIT-able before
Example assembler code for BPF filter "tcpdump port 22"
original BPF -> old JIT: original BPF -> internal BPF -> new JIT:
0: push %rbp 0: push %rbp
1: mov %rsp,%rbp 1: mov %rsp,%rbp
4: sub $0x60,%rsp 4: sub $0x228,%rsp
8: mov %rbx,-0x8(%rbp) b: mov %rbx,-0x228(%rbp) // prologue
12: mov %r13,-0x220(%rbp)
19: mov %r14,-0x218(%rbp)
20: mov %r15,-0x210(%rbp)
27: xor %eax,%eax // clear A
c: xor %ebx,%ebx 29: xor %r13,%r13 // clear X
e: mov 0x68(%rdi),%r9d 2c: mov 0x68(%rdi),%r9d
12: sub 0x6c(%rdi),%r9d 30: sub 0x6c(%rdi),%r9d
16: mov 0xd8(%rdi),%r8 34: mov 0xd8(%rdi),%r10
3b: mov %rdi,%rbx
1d: mov $0xc,%esi 3e: mov $0xc,%esi
22: callq 0xffffffffe1021e15 43: callq 0xffffffffe102bd75
27: cmp $0x86dd,%eax 48: cmp $0x86dd,%rax
2c: jne 0x0000000000000069 4f: jne 0x000000000000009a
2e: mov $0x14,%esi 51: mov $0x14,%esi
33: callq 0xffffffffe1021e31 56: callq 0xffffffffe102bd91
38: cmp $0x84,%eax 5b: cmp $0x84,%rax
3d: je 0x0000000000000049 62: je 0x0000000000000074
3f: cmp $0x6,%eax 64: cmp $0x6,%rax
42: je 0x0000000000000049 68: je 0x0000000000000074
44: cmp $0x11,%eax 6a: cmp $0x11,%rax
47: jne 0x00000000000000c6 6e: jne 0x0000000000000117
49: mov $0x36,%esi 74: mov $0x36,%esi
4e: callq 0xffffffffe1021e15 79: callq 0xffffffffe102bd75
53: cmp $0x16,%eax 7e: cmp $0x16,%rax
56: je 0x00000000000000bf 82: je 0x0000000000000110
58: mov $0x38,%esi 88: mov $0x38,%esi
5d: callq 0xffffffffe1021e15 8d: callq 0xffffffffe102bd75
62: cmp $0x16,%eax 92: cmp $0x16,%rax
65: je 0x00000000000000bf 96: je 0x0000000000000110
67: jmp 0x00000000000000c6 98: jmp 0x0000000000000117
69: cmp $0x800,%eax 9a: cmp $0x800,%rax
6e: jne 0x00000000000000c6 a1: jne 0x0000000000000117
70: mov $0x17,%esi a3: mov $0x17,%esi
75: callq 0xffffffffe1021e31 a8: callq 0xffffffffe102bd91
7a: cmp $0x84,%eax ad: cmp $0x84,%rax
7f: je 0x000000000000008b b4: je 0x00000000000000c2
81: cmp $0x6,%eax b6: cmp $0x6,%rax
84: je 0x000000000000008b ba: je 0x00000000000000c2
86: cmp $0x11,%eax bc: cmp $0x11,%rax
89: jne 0x00000000000000c6 c0: jne 0x0000000000000117
8b: mov $0x14,%esi c2: mov $0x14,%esi
90: callq 0xffffffffe1021e15 c7: callq 0xffffffffe102bd75
95: test $0x1fff,%ax cc: test $0x1fff,%rax
99: jne 0x00000000000000c6 d3: jne 0x0000000000000117
d5: mov %rax,%r14
9b: mov $0xe,%esi d8: mov $0xe,%esi
a0: callq 0xffffffffe1021e44 dd: callq 0xffffffffe102bd91 // MSH
e2: and $0xf,%eax
e5: shl $0x2,%eax
e8: mov %rax,%r13
eb: mov %r14,%rax
ee: mov %r13,%rsi
a5: lea 0xe(%rbx),%esi f1: add $0xe,%esi
a8: callq 0xffffffffe1021e0d f4: callq 0xffffffffe102bd6d
ad: cmp $0x16,%eax f9: cmp $0x16,%rax
b0: je 0x00000000000000bf fd: je 0x0000000000000110
ff: mov %r13,%rsi
b2: lea 0x10(%rbx),%esi 102: add $0x10,%esi
b5: callq 0xffffffffe1021e0d 105: callq 0xffffffffe102bd6d
ba: cmp $0x16,%eax 10a: cmp $0x16,%rax
bd: jne 0x00000000000000c6 10e: jne 0x0000000000000117
bf: mov $0xffff,%eax 110: mov $0xffff,%eax
c4: jmp 0x00000000000000c8 115: jmp 0x000000000000011c
c6: xor %eax,%eax 117: mov $0x0,%eax
c8: mov -0x8(%rbp),%rbx 11c: mov -0x228(%rbp),%rbx // epilogue
cc: leaveq 123: mov -0x220(%rbp),%r13
cd: retq 12a: mov -0x218(%rbp),%r14
131: mov -0x210(%rbp),%r15
138: leaveq
139: retq
On fully cached SKBs both JITed functions take 12 nsec to execute.
BPF interpreter executes the program in 30 nsec.
The difference in generated assembler is due to the following:
Old BPF imlements LDX_MSH instruction via sk_load_byte_msh() helper function
inside bpf_jit.S.
New JIT removes the helper and does it explicitly, so ldx_msh cost
is the same for both JITs, but generated code looks longer.
New JIT has 4 registers to save, so prologue/epilogue are larger,
but the cost is within noise on x64.
Old JIT checks whether first insn clears A and if not emits 'xor %eax,%eax'.
New JIT clears %rax unconditionally.
2. old BPF JIT doesn't support ANC_NLATTR, ANC_PAY_OFFSET, ANC_RANDOM
extensions. New JIT supports all BPF extensions.
Performance of such filters improves 2-4 times depending on a filter.
The longer the filter the higher performance gain.
Synthetic benchmarks with many ancillary loads see 20x speedup
which seems to be the maximum gain from JIT
Notes:
. net.core.bpf_jit_enable=2 + tools/net/bpf_jit_disasm is still functional
and can be used to see generated assembler
. there are two jit_compile() functions and code flow for classic filters is:
sk_attach_filter() - load classic BPF
bpf_jit_compile() - try to JIT from classic BPF
sk_convert_filter() - convert classic to internal
bpf_int_jit_compile() - JIT from internal BPF
seccomp and tracing filters will just call bpf_int_jit_compile()
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
