The vxlan add/delete port NDOs are called under rcu lock.
The current mlx5e implementation can potentially block in these
calls, which is not allowed. Move to using the mlx5e workqueue
to handle these NDOs.
Fixes: b3f63c3d5e ('net/mlx5e: Add netdev support for VXLAN tunneling')
Signed-off-by: Matthew Finlay <matt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Implement a mlx5e workqueue to handle all mlx5e specific tasks. Move
all tasks currently using the system workqueue to the new workqueue.
This is in preparation for vxlan using the mlx5e workqueue in order to
schedule port add/remove operations.
Signed-off-by: Matthew Finlay <matt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When MLX5_EN=y MLX5_CORE=y and VXLAN=m there is a linker error for
vxlan_get_rx_port() due to the fact that VXLAN is a module. Change Kconfig
to select VXLAN when MLX5_CORE=y. When MLX5_CORE=m there is no dependency
on the value of VXLAN.
Fixes: b3f63c3d5e ('net/mlx5e: Add netdev support for VXLAN tunneling')
Signed-off-by: Matthew Finlay <matt@mellanox.com>
Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When freeing UAR the driver tries to unmap uar->map and uar->bf_map
which are mutually exclusive thus always unmapping a NULL pointer.
Make sure we only call iounmap() once, for the actual mapping.
Fixes: 0ba422410b ('net/mlx5: Fix global UAR mapping')
Signed-off-by: Gal Pressman <galp@mellanox.com>
Reported-by: Doron Tsur <doront@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The ethtool api {get|set}_settings is deprecated.
We move the fec_mpc52xx driver to new api {get|set}_link_ksettings.
Signed-off-by: Philippe Reynes <tremyfr@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The ethtool api {get|set}_settings is deprecated.
We move the fs-enet driver to new api {get|set}_link_ksettings.
Signed-off-by: Philippe Reynes <tremyfr@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The ethtool api {get|set}_settings is deprecated.
We move the ucc driver to new api {get|set}_link_ksettings.
Signed-off-by: Philippe Reynes <tremyfr@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The ethtool api {get|set}_settings is deprecated.
We move the gianfar driver to new api {get|set}_link_ksettings.
Signed-off-by: Philippe Reynes <tremyfr@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The vsock_transport structure is never modified, so declare it as const.
Done with the help of Coccinelle.
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
The xgene_cle_ops structure is never modified, so declare it as const.
Done with the help of Coccinelle.
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Acked-by: Iyappan Subramanian <isubramanian@apm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In presence of inelastic flows and stress, we can call
fq_codel_drop() for every packet entering fq_codel qdisc.
fq_codel_drop() is quite expensive, as it does a linear scan
of 4 KB of memory to find a fat flow.
Once found, it drops the oldest packet of this flow.
Instead of dropping a single packet, try to drop 50% of the backlog
of this fat flow, with a configurable limit of 64 packets per round.
TCA_FQ_CODEL_DROP_BATCH_SIZE is the new attribute to make this
limit configurable.
With this strategy the 4 KB search is amortized to a single cache line
per drop [1], so fq_codel_drop() no longer appears at the top of kernel
profile in presence of few inelastic flows.
[1] Assuming a 64byte cache line, and 1024 buckets
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dave Taht <dave.taht@gmail.com>
Cc: Jonathan Morton <chromatix99@gmail.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Dave Taht
Signed-off-by: David S. Miller <davem@davemloft.net>
Aligning the reception data size is not required.
Signed-off-by: Kazuya Mizuguchi <kazuya.mizuguchi.ks@renesas.com>
Signed-off-by: Yoshihiro Kaneko <ykaneko0929@gmail.com>
Tested-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 7e12978 ("HID: wacom: break out wacom_intuos_get_tool_type") by accident
removed stylus_in_proximity flag for Intuos series while shuffling the code
around.
Fix that by reintroducing that flag setting in wacom_intuos_inout(), where
it originally was.
Fixes: 7e12978 ("HID: wacom: break out wacom_intuos_get_tool_type")
Signed-off-by: Ping Cheng <pingc@wacom.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
The fuse mailing list seems not to be open anymore. The discussion on
fuse-devel@... is mostly userspace related anyway.
Reported-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Major changes:
brcmfmac
* add support for nl80211 BSS_SELECT feature
mwifiex
* add platform specific wakeup interrupt support
ath10k
* implement set_tsf() for 10.2.4 branch
* remove rare MSI range support
* remove deprecated firmware API 1 support
ath9k
* add module parameter to invert LED polarity
wcn36xx
* fixes to get the driver properly working on Dragonboard 410c
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.11 (GNU/Linux)
iQEcBAABAgAGBQJXJztPAAoJEG4XJFUm622beSAIAKIw8zGcs7DWd/AGd9z8D7L5
DeO6fxhiu/05AU3d1jM7Rp/Z5hZ42s41PDjRN1lkZJaF4Squa7XOxuB35JlPd+o8
2S21lvaM6ABraSEcDdYL++rglXFL65gIesv/W4TuxqdJCmi9fL7ie7ccplQH17bi
KyY3ePihHZPOR8aXMRbdEzTEjjPFaO/LlAghHPw5WKmVy7FkFKSyFR8muFEPnKEl
DSBWmG6GqRQaHUuVl1QOmoEEqiv7h85D+YqwKiy/xEM4Yw5Rmt5n5pj02KA0i4y5
IRZs59I/8zdAgDgBd+liVeBw9Gp2xAV5R8afOTdzViBDrqCbDCwNq6OPG1GmkLw=
=lyGT
-----END PGP SIGNATURE-----
Merge tag 'wireless-drivers-next-for-davem-2016-05-02' of git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next
Kalle Valo says:
====================
wireless-drivers patches for 4.7
Major changes:
brcmfmac
* add support for nl80211 BSS_SELECT feature
mwifiex
* add platform specific wakeup interrupt support
ath10k
* implement set_tsf() for 10.2.4 branch
* remove rare MSI range support
* remove deprecated firmware API 1 support
ath9k
* add module parameter to invert LED polarity
wcn36xx
* fixes to get the driver properly working on Dragonboard 410c
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This was recently reported to me, and reproduced on the latest net kernel,
when attempting to run netperf from a host that had a netem qdisc attached
to the egress interface:
[ 788.073771] ---------------------[ cut here ]---------------------------
[ 788.096716] WARNING: at net/core/dev.c:2253 skb_warn_bad_offload+0xcd/0xda()
[ 788.129521] bnx2: caps=(0x00000001801949b3, 0x0000000000000000) len=2962
data_len=0 gso_size=1448 gso_type=1 ip_summed=3
[ 788.182150] Modules linked in: sch_netem kvm_amd kvm crc32_pclmul ipmi_ssif
ghash_clmulni_intel sp5100_tco amd64_edac_mod aesni_intel lrw gf128mul
glue_helper ablk_helper edac_mce_amd cryptd pcspkr sg edac_core hpilo ipmi_si
i2c_piix4 k10temp fam15h_power hpwdt ipmi_msghandler shpchp acpi_power_meter
pcc_cpufreq nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c
sd_mod crc_t10dif crct10dif_generic mgag200 syscopyarea sysfillrect sysimgblt
i2c_algo_bit drm_kms_helper ahci ata_generic pata_acpi ttm libahci
crct10dif_pclmul pata_atiixp tg3 libata crct10dif_common drm crc32c_intel ptp
serio_raw bnx2 r8169 hpsa pps_core i2c_core mii dm_mirror dm_region_hash dm_log
dm_mod
[ 788.465294] CPU: 16 PID: 0 Comm: swapper/16 Tainted: G W
------------ 3.10.0-327.el7.x86_64 #1
[ 788.511521] Hardware name: HP ProLiant DL385p Gen8, BIOS A28 12/17/2012
[ 788.542260] ffff880437c036b8 f7afc56532a53db9 ffff880437c03670
ffffffff816351f1
[ 788.576332] ffff880437c036a8 ffffffff8107b200 ffff880633e74200
ffff880231674000
[ 788.611943] 0000000000000001 0000000000000003 0000000000000000
ffff880437c03710
[ 788.647241] Call Trace:
[ 788.658817] <IRQ> [<ffffffff816351f1>] dump_stack+0x19/0x1b
[ 788.686193] [<ffffffff8107b200>] warn_slowpath_common+0x70/0xb0
[ 788.713803] [<ffffffff8107b29c>] warn_slowpath_fmt+0x5c/0x80
[ 788.741314] [<ffffffff812f92f3>] ? ___ratelimit+0x93/0x100
[ 788.767018] [<ffffffff81637f49>] skb_warn_bad_offload+0xcd/0xda
[ 788.796117] [<ffffffff8152950c>] skb_checksum_help+0x17c/0x190
[ 788.823392] [<ffffffffa01463a1>] netem_enqueue+0x741/0x7c0 [sch_netem]
[ 788.854487] [<ffffffff8152cb58>] dev_queue_xmit+0x2a8/0x570
[ 788.880870] [<ffffffff8156ae1d>] ip_finish_output+0x53d/0x7d0
...
The problem occurs because netem is not prepared to handle GSO packets (as it
uses skb_checksum_help in its enqueue path, which cannot manipulate these
frames).
The solution I think is to simply segment the skb in a simmilar fashion to the
way we do in __dev_queue_xmit (via validate_xmit_skb), with some minor changes.
When we decide to corrupt an skb, if the frame is GSO, we segment it, corrupt
the first segment, and enqueue the remaining ones.
tested successfully by myself on the latest net kernel, to which this applies
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Jamal Hadi Salim <jhs@mojatatu.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: netem@lists.linux-foundation.org
CC: eric.dumazet@gmail.com
CC: stephen@networkplumber.org
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Locally generated TCP GSO packets having to go through a GRE/SIT/IPIP
tunnel have to go through an expensive skb_unclone()
Reallocating skb->head is a lot of work.
Test should really check if a 'real clone' of the packet was done.
TCP does not care if the original gso_type is changed while the packet
travels in the stack.
This adds skb_header_unclone() which is a variant of skb_clone()
using skb_header_cloned() check instead of skb_cloned().
This variant can probably be used from other points.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
- a fix for our Distributed ARP Table that makes sure that the input
provided to the hash function during a query is the same as the one
provided during an insert (so to prevent false negatives), by Antonio
Quartulli
- a fix for our new protocol implementation B.A.T.M.A.N. V that ensures
that a hard interface is properly re-activated when it is brought down
and then up again, by Antonio Quartulli
- two fixes respectively to the reference counting of the tt_local_entry
and neigh_node objects, by Sven Eckelmann. Such bug is rather severe
as it would prevent the netdev objects references by batman-adv from
being released after shutdown.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2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=ksVs
-----END PGP SIGNATURE-----
Merge tag 'batman-adv-fix-for-davem' of git://git.open-mesh.org/linux-merge
Antonio Quartulli says:
====================
In this small batch of patches you have:
- a fix for our Distributed ARP Table that makes sure that the input
provided to the hash function during a query is the same as the one
provided during an insert (so to prevent false negatives), by Antonio
Quartulli
- a fix for our new protocol implementation B.A.T.M.A.N. V that ensures
that a hard interface is properly re-activated when it is brought down
and then up again, by Antonio Quartulli
- two fixes respectively to the reference counting of the tt_local_entry
and neigh_node objects, by Sven Eckelmann. Such bug is rather severe
as it would prevent the netdev objects references by batman-adv from
being released after shutdown.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
- trans_timeout is incremented when tx queue timed out (tx watchdog).
- tx_maxrate is set via sysfs
Moving tx_maxrate to read-mostly part shrinks the struct by 64 bytes.
While at it, also move trans_timeout (it is out-of-place in the
'write-mostly' part).
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Nikolay Aleksandrov says:
====================
bridge: per-vlan stats
This set adds support for bridge per-vlan statistics.
In order to be able to dump statistics for many vlans we need a way to
continue dumping after reaching maximum size, thus patches 01 and 02 extend
the new stats API with a per-device extended link stats attribute and
callback which can save its local state and continue where it left off
afterwards. I considered using the already existing "fill_xstats" callback
but it gets confusing since we need to separate the linkinfo dump from the
new stats api dump and adding a flag/argument to do that just looks messy.
I don't think the rtnl_link_ops size is an issue, so adding these seemed
like the cleaner approach.
Patches 03 and 04 add the stats support and netlink dump support
respectively. The stats accounting is controlled via a bridge option which
is default off, thus the performance impact is kept minimal.
I've tested this set with both old and modified iproute2, kmemleak on and
some traffic stress tests while adding/removing vlans and ports.
v3:
- drop the RCU pvid patch and remove one pointer fetch as requested
- make stats accounting optional with default to off, the option is in the
same cache line as vlan_proto and vlan_enabled, so it is already fetched
before the fast path check thus the performance impact is minimal, this
also allows us to avoid one vlan lookup and return early when using pvid
- rebased and retested
v2:
- Improve the error checking, rename lidx to prividx and save the current
idx user instead of restricting it to one in patch 01
- squash patch 02 into 01 and remove the restriction
- add callback descriptions, improve the size calculation and change the
xstats message structure to have an embedding level per rtnl link type
so we can avoid one call to get the link type (and thus filter on it)
and also each link type can now have any number of private attributes
inside
- fix a problem where the vlan stats are not dumped if the bridge has 0
vlans on it but has vlans on the ports, add bridge link type private
attributes and also add paddings for future extensions to avoid at least
a few netlink attributes and improve struct alignment
- drop the is_skb_forwardable argument constifying patch as it's not
needed anymore, but it's a nice cleanup which I'll send separately
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a new LINK_XSTATS_TYPE_BRIDGE attribute and implement the
RTM_GETSTATS callbacks for IFLA_STATS_LINK_XSTATS (fill_linkxstats and
get_linkxstats_size) in order to export the per-vlan stats.
The paddings were added because soon these fields will be needed for
per-port per-vlan stats (or something else if someone beats me to it) so
avoiding at least a few more netlink attributes.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for per-VLAN Tx/Rx statistics. Every global vlan context gets
allocated a per-cpu stats which is then set in each per-port vlan context
for quick access. The br_allowed_ingress() common function is used to
account for Rx packets and the br_handle_vlan() common function is used
to account for Tx packets. Stats accounting is performed only if the
bridge-wide vlan_stats_enabled option is set either via sysfs or netlink.
A struct hole between vlan_enabled and vlan_proto is used for the new
option so it is in the same cache line. Currently it is binary (on/off)
but it is intentionally restricted to exactly 0 and 1 since other values
will be used in the future for different purposes (e.g. per-port stats).
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add callbacks to calculate the size and fill link extended statistics
which can be split into multiple messages and are dumped via the new
rtnl stats API (RTM_GETSTATS) with the IFLA_STATS_LINK_XSTATS attribute.
Also add that attribute to the idx mask check since it is expected to
be able to save state and resume dumping (e.g. future bridge per-vlan
stats will be dumped via this attribute and callbacks).
Each link type should nest its private attributes under the per-link type
attribute. This allows to have any number of separated private attributes
and to avoid one call to get the dev link type.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The new prividx argument allows the current dumping device to save a
private state counter which would enable it to continue dumping from
where it left off. And the idxattr is used to save the current idx user
so multiple prividx using attributes can be requested at the same time
as suggested by Roopa Prabhu.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tom Herbert says:
====================
net: Cleanup IPv6 ip tunnels
The IPv6 tunnel code is very different from IPv4 code. There is a lot
of redundancy with the IPv4 code, particularly in the GRE tunneling.
This patch set cleans up the tunnel code to make the IPv6 code look
more like the IPv4 code and use common functions between the two
stacks where possible.
This work should make it easier to maintain and extend the IPv6 ip
tunnels.
Items in this patch set:
- Cleanup IPv6 tunnel receive path (ip6_tnl_rcv). Includes using
gro_cells and exporting ip6_tnl_rcv so the ip6_gre can call it
- Move GRE functions to common header file (tx functions) or
gre_demux.c (rx functions like gre_parse_header)
- Call common GRE functions from IPv6 GRE
- Create ip6_tnl_xmit (to be like ip_tunnel_xmit)
Tested:
Ran super_netperf tests for TCP_RR and TCP_STREAM for:
- IPv4 over gre, gretap, gre6, gre6tap
- IPv6 over gre, gretap, gre6, gre6tap
- ipip
- ip6ip6
- ipip/gue
- IPv6 over gre/gue
- IPv4 over gre/gue
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Changes in GREv6 transmit path:
- Call gre_checksum, remove gre6_checksum
- Rename ip6gre_xmit2 to __gre6_xmit
- Call gre_build_header utility function
- Call ip6_tnl_xmit common function
- Call ip6_tnl_change_mtu, eliminate ip6gre_tunnel_change_mtu
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A few generic changes to generalize tunnels in IPv6:
- Export ip6_tnl_change_mtu so that it can be called by ip6_gre
- Add tun_hlen to ip6_tnl structure.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Create common functions for both IPv4 and IPv6 GRE in transmit. These
are put into gre.h.
Common functions are for:
- GRE checksum calculation. Move gre_checksum to gre.h.
- Building a GRE header. Move GRE build_header and rename
gre_build_header.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch renames ip6_tnl_xmit2 to ip6_tnl_xmit and exports it. Other
users like GRE will be able to call this. The original ip6_tnl_xmit
function is renamed to ip6_tnl_start_xmit (this is an ndo_start_xmit
function).
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
- Create gre_rcv function. This calls gre_parse_header and ip6gre_rcv.
- Call ip6_tnl_rcv. Doing this and using gre_parse_header eliminates
most of the code in ip6gre_rcv.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Several of the GRE functions defined in net/ipv4/ip_gre.c are usable
for IPv6 GRE implementation (that is they are protocol agnostic).
These include:
- GRE flag handling functions are move to gre.h
- GRE build_header is moved to gre.h and renamed gre_build_header
- parse_gre_header is moved to gre_demux.c and renamed gre_parse_header
- iptunnel_pull_header is taken out of gre_parse_header. This is now
done by caller. The header length is returned from gre_parse_header
in an int* argument.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some basic changes to make IPv6 tunnel receive path look more like
IPv4 path:
- Make ip6_tnl_rcv non-static so that GREv6 and others can call it
- Make ip6_tnl_rcv look like ip_tunnel_rcv
- Switch to gro_cells_receive
- Make ip6_tnl_rcv non-static and export it
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet says:
====================
net: make TCP preemptible
Most of TCP stack assumed it was running from BH handler.
This is great for most things, as TCP behavior is very sensitive
to scheduling artifacts.
However, the prequeue and backlog processing are problematic,
as they need to be flushed with BH being blocked.
To cope with modern needs, TCP sockets have big sk_rcvbuf values,
in the order of 16 MB, and soon 32 MB.
This means that backlog can hold thousands of packets, and things
like TCP coalescing or collapsing on this amount of packets can
lead to insane latency spikes, since BH are blocked for too long.
It is time to make UDP/TCP stacks preemptible.
Note that fast path still runs from BH handler.
v2: Added "tcp: make tcp_sendmsg() aware of socket backlog"
to reduce latency problems of large sends.
v3: Fixed a typo in tcp_cdg.c
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Large sendmsg()/write() hold socket lock for the duration of the call,
unless sk->sk_sndbuf limit is hit. This is bad because incoming packets
are parked into socket backlog for a long time.
Critical decisions like fast retransmit might be delayed.
Receivers have to maintain a big out of order queue with additional cpu
overhead, and also possible stalls in TX once windows are full.
Bidirectional flows are particularly hurt since the backlog can become
quite big if the copy from user space triggers IO (page faults)
Some applications learnt to use sendmsg() (or sendmmsg()) with small
chunks to avoid this issue.
Kernel should know better, right ?
Add a generic sk_flush_backlog() helper and use it right
before a new skb is allocated. Typically we put 64KB of payload
per skb (unless MSG_EOR is requested) and checking socket backlog
every 64KB gives good results.
As a matter of fact, tests with TSO/GSO disabled give very nice
results, as we manage to keep a small write queue and smaller
perceived rtt.
Note that sk_flush_backlog() maintains socket ownership,
so is not equivalent to a {release_sock(sk); lock_sock(sk);},
to ensure implicit atomicity rules that sendmsg() was
giving to (possibly buggy) applications.
In this simple implementation, I chose to not call tcp_release_cb(),
but we might consider this later.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Socket backlog processing is a major latency source.
With current TCP socket sk_rcvbuf limits, I have sampled __release_sock()
holding cpu for more than 5 ms, and packets being dropped by the NIC
once ring buffer is filled.
All users are now ready to be called from process context,
we can unblock BH and let interrupts be serviced faster.
cond_resched_softirq() could be removed, as it has no more user.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
sctp_inq_push() will soon be called without BH being blocked
when generic socket code flushes the socket backlog.
It is very possible SCTP can be converted to not rely on BH,
but this needs to be done by SCTP experts.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
UDP uses the generic socket backlog code, and this will soon
be changed to not disable BH when protocol is called back.
We need to use appropriate SNMP accessors.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
DCCP uses the generic backlog code, and this will soon
be changed to not disable BH when protocol is called back.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
AFAIK, nothing in current TCP stack absolutely wants BH
being disabled once socket is owned by a thread running in
process context.
As mentioned in my prior patch ("tcp: give prequeue mode some care"),
processing a batch of packets might take time, better not block BH
at all.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
We want to to make TCP stack preemptible, as draining prequeue
and backlog queues can take lot of time.
Many SNMP updates were assuming that BH (and preemption) was disabled.
Need to convert some __NET_INC_STATS() calls to NET_INC_STATS()
and some __TCP_INC_STATS() to TCP_INC_STATS()
Before using this_cpu_ptr(net->ipv4.tcp_sk) in tcp_v4_send_reset()
and tcp_v4_send_ack(), we add an explicit preempt disabled section.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Iyappan Subramanian says:
====================
drivers: net: xgene: fix: Get channel number from device binding
This patch set adds 'channel' property to get ethernet to CPU channel number,
thus decoupling the Linux driver from static resource selection.
v2: Address review comments from v1
- removed irq reference from Linux driver
- added 'channel' property to get ethernet to CPU channel number
v1:
- Initial version
====================
Signed-off-by: Iyappan Subramanian <isubramanian@apm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Added 'channel' property, describing ethernet to CPU channel number.
Signed-off-by: Iyappan Subramanian <isubramanian@apm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch gets ethernet to CPU channel (prefetch buffer number) from
the newly added 'channel' property, thus decoupling Linux driver from
resource management.
Signed-off-by: Iyappan Subramanian <isubramanian@apm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is a fairly minimal fixup to the horribly bad behavior of hash_64()
with certain input patterns.
In particular, because the multiplicative value used for the 64-bit hash
was intentionally bit-sparse (so that the multiply could be done with
shifts and adds on architectures without hardware multipliers), some
bits did not get spread out very much. In particular, certain fairly
common bit ranges in the input (roughly bits 12-20: commonly with the
most information in them when you hash things like byte offsets in files
or memory that have block factors that mean that the low bits are often
zero) would not necessarily show up much in the result.
There's a bigger patch-series brewing to fix up things more completely,
but this is the fairly minimal fix for the 64-bit hashing problem. It
simply picks a much better constant multiplier, spreading the bits out a
lot better.
NOTE! For 32-bit architectures, the bad old hash_64() remains the same
for now, since 64-bit multiplies are expensive. The bigger hashing
cleanup will replace the 32-bit case with something better.
The new constants were picked by George Spelvin who wrote that bigger
cleanup series. I just picked out the constants and part of the comment
from that series.
Cc: stable@vger.kernel.org
Cc: George Spelvin <linux@horizon.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull MD fixes from Shaohua Li:
"This update includes several trival fixes. The only important one is
to fix MD bio merge, which has big performance impact"
* tag 'md/4.6-rc6-fix' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md:
raid5: delete unnecessary warnning
MD: make bio mergeable
md/raid0: remove empty line printk from dump_zones
md/raid0: fix uninitialized variable bug
Pull UDF fix from Jan Kara:
"A fix of a regression in UDF that got introduced in 4.6-rc1 by one of
the charset encoding fixes"
* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
udf: Fix conversion of 'dstring' fields to UTF8
- A serious ACPI fix targeted for stable: lookup strings
were being free:ed.
- Revert two patches from the RCAR driver.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=x3jf
-----END PGP SIGNATURE-----
Merge tag 'gpio-v4.6-4' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio
Pull GPIO fixes from Linus Walleij:
"Here are some late but important fixes for the v4.6 kernel series.
ACPI and RCAR, so two driver fixes (PM related) and a self-evident
string lookup fix for ACPI GPIOs:
- A serious ACPI fix targeted for stable: lookup strings were being
free'd.
- Revert two patches from the RCAR driver"
* tag 'gpio-v4.6-4' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio:
gpiolib-acpi: Duplicate con_id string when adding it to the crs lookup list
Revert "gpio: rcar: Fine-grained Runtime PM support"
Revert "gpio: rcar: Add Runtime PM handling for interrupts"
Pull networking fixes from David Miller:
1) MODULE_FIRMWARE firmware string not correct for iwlwifi 8000 chips,
from Sara Sharon.
2) Fix SKB size checks in batman-adv stack on receive, from Sven
Eckelmann.
3) Leak fix on mac80211 interface add error paths, from Johannes Berg.
4) Cannot invoke napi_disable() with BH disabled in myri10ge driver,
fix from Stanislaw Gruszka.
5) Fix sign extension problem when computing feature masks in
net_gso_ok(), from Marcelo Ricardo Leitner.
6) lan78xx driver doesn't count packets and packet lengths in its
statistics properly, fix from Woojung Huh.
7) Fix the buffer allocation sizes in pegasus USB driver, from Petko
Manolov.
8) Fix refcount overflows in bpf, from Alexei Starovoitov.
9) Unified dst cache handling introduced a preempt warning in
ip_tunnel, fix by resetting rather then setting the cached route.
From Paolo Abeni.
10) Listener hash collision test fix in soreuseport, from Craig Gallak
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (47 commits)
gre: do not pull header in ICMP error processing
net: Implement net_dbg_ratelimited() for CONFIG_DYNAMIC_DEBUG case
tipc: only process unicast on intended node
cxgb3: fix out of bounds read
net/smscx5xx: use the device tree for mac address
soreuseport: Fix TCP listener hash collision
net: l2tp: fix reversed udp6 checksum flags
ip_tunnel: fix preempt warning in ip tunnel creation/updating
samples/bpf: fix trace_output example
bpf: fix check_map_func_compatibility logic
bpf: fix refcnt overflow
drivers: net: cpsw: use of_phy_connect() in fixed-link case
dt: cpsw: phy-handle, phy_id, and fixed-link are mutually exclusive
drivers: net: cpsw: don't ignore phy-mode if phy-handle is used
drivers: net: cpsw: fix segfault in case of bad phy-handle
drivers: net: cpsw: fix parsing of phy-handle DT property in dual_emac config
MAINTAINERS: net: Change maintainer for GRETH 10/100/1G Ethernet MAC device driver
gre: reject GUE and FOU in collect metadata mode
pegasus: fixes reported packet length
pegasus: fixes URB buffer allocation size;
...
Pull sparc fixes from David Miller:
1) Fix panics with SR-IOV, from Babu Moger.
2) Wire up preadv2/pwritev2.
3) Allow proper auto-loading of VIO devices, from John Paul Adrian
Glaubitz.
4) Recognize Sonoma cpus, from Khalid Aziz.
5) Fix bootup regressions caused by syscall trace fixes made recently.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc:
sparc64: Fix bootup regressions on some Kconfig combinations.
sparc64: recognize and support Sonoma CPU type
sparc: Implement and wire up vio_hotplug for vio.
sparc: Implement and wire up modalias_show for vio.
sparc/pci: Refactor dev_archdata initialization into pci_init_dev_archdata
sparc/defconfigs: Remove CONFIG_IPV6_PRIVACY
sparc: Write up preadv2/pwritev2 syscalls.
sparc/PCI: Fix for panic while enabling SR-IOV
