Add support for adaptive TX moderation. This greatly reduces TX interrupt
rate and increases bandwidth, mostly for TCP bandwidth over ARM
architecture (below). There is a slight single stream TCP with very large
message sizes degradation (x86). In this case if there's any moderation on
transmitted packets the bandwidth would reduce due to hitting TCP output limit.
Since this is a synthetic case, this is still worth doing.

Performance improvement (ConnectX-4Lx 40GbE, ARM)
TCP 64B bandwidth with 1-50 streams increased 6-35%.
TCP 64B bandwidth with 100-500 streams increased 20-70%.

Performance improvement (ConnectX-5 100GbE, x86)
Bandwidth: increased up to 40% (1024B with 10s of streams).
Interrupt rate: reduced up to 50% (1024B with 1000s of streams).

Performance degradation (ConnectX-5 100GbE, x86)
Bandwidth: up to 10% decrease single stream TCP (1MB message size from
51Gb/s to 47Gb/s).
Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Interrupt moderation for TX traffic requires different profiles than RX
interrupt moderation. The main goal here is to reduce interrupt rate and
allow better payload aggregation by keeping SKBs in the TX queue a bit
longer. Ping-pong behavior would get a profile with a short timer, so
latency wouldn't increase for these scenarios. There might be a slight
degradation in bandwidth for single stream with large message sizes, since
net.ipv4.tcp_limit_output_bytes is limiting the allowed TX traffic, but
with many streams performance is always improved.
Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Preparation for introducing adaptive TX to net DIM.
Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Similar to commit a2ac9990 ("vhost-net: set packet weight of
tx polling to 2 * vq size"), we need a packet-based limit for
handler_rx, too - elsewhere, under rx flood with small packets,
tx can be delayed for a very long time, even without busypolling.

The pkt limit applied to handle_rx must be the same applied by
handle_tx, or we will get unfair scheduling between rx and tx.
Tying such limit to the queue length makes it less effective for
large queue length values and can introduce large process
scheduler latencies, so a constant valued is used - likewise
the existing bytes limit.

The selected limit has been validated with PVP[1] performance
test with different queue sizes:

queue size		256	512	1024

baseline		366	354	362
weight 128		715	723	670
weight 256		740	745	733
weight 512		600	460	583
weight 1024		423	427	418

A packet weight of 256 gives peek performances in under all the
tested scenarios.

No measurable regression in unidirectional performance tests has
been detected.

[1] https://developers.redhat.com/blog/2017/06/05/measuring-and-comparing-open-vswitch-performance/Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Fixes: b16fb418 ("net: fib_rules: add extack support")
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Fixes: 192dc405 ("selftests: net: add tcp_mmap program")
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Function dca_common_get_tag is local to the source and does not need to be
in global scope, so make it static.

Cleans up sparse warning:
drivers/dca/dca-core.c:273:4: warning: symbol 'dca_common_get_tag' was
not declared. Should it be static?
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

David Ahern says:

====================
net/ipv6: couple of fixes for rcu change to from

So many details... I am thankful for all the robots running the
permutations and tools.

Two bug fixes from the rcu change to rt->from:
1. missing rcu lock in ip6_negative_advice
2. rcu dereferences in 2 sites
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

kbuild test robot reported 2 uses of rt->from not properly accessed
using rcu_dereference:
1. add rcu_dereference_protected to rt6_remove_exception_rt and make
   sure it is always called with rcu lock held.

2. change rt6_do_redirect to take a reference on 'from' when accessed
   the first time so it can be used the sceond time outside of the lock

Fixes: a68886a6 ("net/ipv6: Make from in rt6_info rcu protected")
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

syzbot reported a suspicious rcu_dereference_check:
  __dump_stack lib/dump_stack.c:77 [inline]
  dump_stack+0x1b9/0x294 lib/dump_stack.c:113
  lockdep_rcu_suspicious+0x14a/0x153 kernel/locking/lockdep.c:4592
  rt6_check_expired+0x38b/0x3e0 net/ipv6/route.c:410
  ip6_negative_advice+0x67/0xc0 net/ipv6/route.c:2204
  dst_negative_advice include/net/sock.h:1786 [inline]
  sock_setsockopt+0x138f/0x1fe0 net/core/sock.c:1051
  __sys_setsockopt+0x2df/0x390 net/socket.c:1899
  SYSC_setsockopt net/socket.c:1914 [inline]
  SyS_setsockopt+0x34/0x50 net/socket.c:1911

Add rcu locking around call to rt6_check_expired in
ip6_negative_advice.

Fixes: a68886a6 ("net/ipv6: Make from in rt6_info rcu protected")
Reported-by: syzbot+2422c9e35796659d2273@syzkaller.appspotmail.com
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Denis Bolotin says:

====================
Add configuration information to register dump and debug data

The purpose of this patchset is to add configuration information to the
debug data collection, which already contains register dump.
The first patch (removing the ptt) is essential because it prevents the
unnecessary ptt acquirement when calling mcp APIs.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Configuration information is added to the debug data collection, in
addition to register dump.
Added qed_dbg_nvm_image() that receives an image type, allocates a
buffer and reads the image. The images are saved in the buffers and the
dump size is updated.
Signed-off-by: Denis Bolotin <denis.bolotin@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Since nvm images attributes are cached during driver load, acquiring ptt
is not needed when calling qed_mcp_get_nvm_image().
Signed-off-by: Denis Bolotin <denis.bolotin@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Move all the core version detection to a common place ("hwif.c") and
implement a table which can be used to lookup the correct callbacks for
each IP version.

This simplifies the initialization flow of each IP version and eases
future implementation of new IP versions.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

There's no benefit in using netif_info et al before the net_device has
been registered. We get messages like
r8169 0000:03:00.0 (unnamed net_device) (uninitialized): [message]
Therefore use dev_info/dev_err instead.

As a side effect we don't need parameter dev for function
rtl8169_get_mac_version() any longer.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

With sk_cookie we can identify a socket, that is very helpful for
traceing and statistic, i.e. tcp tracepiont and ebpf.
So we'd better init it by default for inet socket.
When using it, we just need call atomic64_read(&sk->sk_cookie).
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Roopa Prabhu says:

====================
fib rules extack support

First patch refactors code to move fib rule netlink handling
into a common function. This became obvious when adding
duplicate extack msgs in add and del paths. Second patch
adds extack msgs.

v2 - Dropped the ip route get support and selftests from
     the series to look at the input path some more (as pointed
     out by ido). Will come back to that next week when i have
     some time. resending just the extack part for now.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This reduces code duplication in the fib rule add and del paths.
Get rid of validate_rulemsg. This became obvious when adding duplicate
extack support in fib newrule/delrule error paths.
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

tcp_rcv_space_adjust is called every time data is copied to user space,
introducing a tcp tracepoint for which could show us when the packet is
copied to user.

When a tcp packet arrives, tcp_rcv_established() will be called and with
the existed tracepoint tcp_probe we could get the time when this packet
arrives.
Then this packet will be copied to user, and tcp_rcv_space_adjust will
be called and with this new introduced tracepoint we could get the time
when this packet is copied to user.
With these two tracepoints, we could figure out whether the user program
processes this packet immediately or there's latency.

Hence in the printk message, sk_cookie is printed as a key to relate
tcp_rcv_space_adjust with tcp_probe.

Maybe we could export sockfd in this new tracepoint as well, then we
could relate this new tracepoint with epoll/read/recv* tracepoints, and
finally that could show us the whole lifespan of this packet. But we
could also implement that with pid as these functions are executed in
process context.
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The conversion of rndis friendly name to utf8 uses a standard
kernel routine which is optional in config. Therefore build
would fail for some configurations. Resolve by selecting needed
library.

Fixes: 0fe554a4 ("hv_netvsc: propogate Hyper-V friendly name into interface alias")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Conflicts were simple overlapping changes in microchip
driver.
Signed-off-by: David S. Miller <davem@davemloft.net>

David Ahern says:

====================
net/ipv6: Another followup to the fib6_info change

Last one - for this week.

Patches 1, 2 and 7 are more cleanup patches - removing dead code,
moving code from a header to near its single caller, and updating
function name.

Patches 3-5 do some refactoring leading up to patch 6 which fixes
a NULL dereference. I have only managed to trigger a panic once, so
I can not definitively confirm it addresses the problem but it seems
pretty clear that it is a race on removing a 'from' reference on
an rt6_info and another path using that 'from' value to do
cookie checking.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Dan reported an imbalance in fib6_check on use of f6i and checking
whether it is null. Since fib6_check is only called if f6i is non-null,
remove the unnecessary check.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

When a dst entry is created from a fib entry, the 'from' in rt6_info
is set to the fib entry. The 'from' reference is used most notably for
cookie checking - making sure stale dst entries are updated if the
fib entry is changed.

When a fib entry is deleted, the pcpu routes on it are walked releasing
the fib6_info reference. This is needed for the fib6_info cleanup to
happen and to make sure all device references are released in a timely
manner.

There is a race window when a FIB entry is deleted and the 'from' on the
pcpu route is dropped and the pcpu route hits a cookie check. Handle
this race using rcu on from.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Code move only; no functional change intended.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

A later patch protects 'from' in rt6_info and this simplifies the
locking needed by it.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

A later patch protects 'from' in rt6_info and this simplifies the
locking needed by it.

With the move, the fib6_info_hold for the uncached_rt is no longer
needed since the rcu_lock is still held.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

rt6_get_cookie_safe takes a fib6_info and checks the sernum of
the node. Update the name to reflect its purpose.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

rt6_clean_expires and rt6_set_expires are no longer used. Removed them.
rt6_update_expires has 1 caller in route.c, so move it from the header.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-04-21

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Initial work on BPF Type Format (BTF) is added, which is a meta
   data format which describes the data types of BPF programs / maps.
   BTF has its roots from CTF (Compact C-Type format) with a number
   of changes to it. First use case is to provide a generic pretty
   print capability for BPF maps inspection, later work will also
   add BTF to bpftool. pahole support to convert dwarf to BTF will
   be upstreamed as well (https://github.com/iamkafai/pahole/tree/btf),
   from Martin.

2) Add a new xdp_bpf_adjust_tail() BPF helper for XDP that allows
   for changing the data_end pointer. Only shrinking is currently
   supported which helps for crafting ICMP control messages. Minor
   changes in drivers have been added where needed so they recalc
   the packet's length also when data_end was adjusted, from Nikita.

3) Improve bpftool to make it easier to feed hex bytes via cmdline
   for map operations, from Quentin.

4) Add support for various missing BPF prog types and attach types
   that have been added to kernel recently but neither to bpftool
   nor libbpf yet. Doc and bash completion updates have been added
   as well for bpftool, from Andrey.

5) Proper fix for avoiding to leak info stored in frame data on page
   reuse for the two bpf_xdp_adjust_{head,meta} helpers by disallowing
   to move the pointers into struct xdp_frame area, from Jesper.

6) Follow-up compile fix from BTF in order to include stdbool.h in
   libbpf, from Björn.

7) Few fixes in BPF sample code, that is, a typo on the netdevice
   in a comment and fixup proper dump of XDP action code in the
   tracepoint exception, from Wang and Jesper.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Pull thermal fixes from Eduardo Valentin:
 "A couple of fixes for the thermal subsystem"

* 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal:
  dt-bindings: thermal: Remove "cooling-{min|max}-level" properties
  dt-bindings: thermal: remove no longer needed samsung thermal properties

Pull MMC fixes from Ulf Hansson:
 "A couple of MMC host fixes:

   - sdhci-pci: Fixup tuning for AMD for eMMC HS200 mode

   - renesas_sdhi_internal_dmac: Avoid data corruption by limiting
     DMA RX"

* tag 'mmc-v4.17-3' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc:
  mmc: renesas_sdhi_internal_dmac: limit DMA RX for old SoCs
  mmc: sdhci-pci: Only do AMD tuning for HS200

Pull MD fixes from Shaohua Li:
 "Three small fixes for MD:

   - md-cluster fix for faulty device from Guoqing

   - writehint fix for writebehind IO for raid1 from Mariusz

   - a live lock fix for interrupted recovery from Yufen"

* tag 'md/4.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md:
  raid1: copy write hint from master bio to behind bio
  md/raid1: exit sync request if MD_RECOVERY_INTR is set
  md-cluster: don't update recovery_offset for faulty device

In do_mount() when the MS_* flags are being converted to MNT_* flags,
MS_RDONLY got accidentally convered to SB_RDONLY.

Undo this change.

Fixes: e462ec50 ("VFS: Differentiate mount flags (MS_*) from internal superblock flags")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

AFS server records get removed from the net->fs_servers tree when
they're deleted, but not from the net->fs_addresses{4,6} lists, which
can lead to an oops in afs_find_server() when a server record has been
removed, for instance during rmmod.

Fix this by deleting the record from the by-address lists before posting
it for RCU destruction.

The reason this hasn't been noticed before is that the fileserver keeps
probing the local cache manager, thereby keeping the service record
alive, so the oops would only happen when a fileserver eventually gets
bored and stops pinging or if the module gets rmmod'd and a call comes
in from the fileserver during the window between the server records
being destroyed and the socket being closed.

The oops looks something like:

  BUG: unable to handle kernel NULL pointer dereference at 000000000000001c
  ...
  Workqueue: kafsd afs_process_async_call [kafs]
  RIP: 0010:afs_find_server+0x271/0x36f [kafs]
  ...
  Call Trace:
   afs_deliver_cb_init_call_back_state3+0x1f2/0x21f [kafs]
   afs_deliver_to_call+0x1ee/0x5e8 [kafs]
   afs_process_async_call+0x5b/0xd0 [kafs]
   process_one_work+0x2c2/0x504
   worker_thread+0x1d4/0x2ac
   kthread+0x11f/0x127
   ret_from_fork+0x24/0x30

Fixes: d2ddc776 ("afs: Overhaul volume and server record caching and fileserver rotation")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Pull networking fixes from David Miller:

 1) Unbalanced refcounting in TIPC, from Jon Maloy.

 2) Only allow TCP_MD5SIG to be set on sockets in close or listen state.
    Once the connection is established it makes no sense to change this.
    From Eric Dumazet.

 3) Missing attribute validation in neigh_dump_table(), also from Eric
    Dumazet.

 4) Fix address comparisons in SCTP, from Xin Long.

 5) Neigh proxy table clearing can deadlock, from Wolfgang Bumiller.

 6) Fix tunnel refcounting in l2tp, from Guillaume Nault.

 7) Fix double list insert in team driver, from Paolo Abeni.

 8) af_vsock.ko module was accidently made unremovable, from Stefan
    Hajnoczi.

 9) Fix reference to freed llc_sap object in llc stack, from Cong Wang.

10) Don't assume netdevice struct is DMA'able memory in virtio_net
    driver, from Michael S. Tsirkin.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (62 commits)
  net/smc: fix shutdown in state SMC_LISTEN
  bnxt_en: Fix memory fault in bnxt_ethtool_init()
  virtio_net: sparse annotation fix
  virtio_net: fix adding vids on big-endian
  virtio_net: split out ctrl buffer
  net: hns: Avoid action name truncation
  docs: ip-sysctl.txt: fix name of some ipv6 variables
  vmxnet3: fix incorrect dereference when rxvlan is disabled
  llc: hold llc_sap before release_sock()
  MAINTAINERS: Direct networking documentation changes to netdev
  atm: iphase: fix spelling mistake: "Tansmit" -> "Transmit"
  net: qmi_wwan: add Wistron Neweb D19Q1
  net: caif: fix spelling mistake "UKNOWN" -> "UNKNOWN"
  net: stmmac: Disable ACS Feature for GMAC >= 4
  net: mvpp2: Fix DMA address mask size
  net: change the comment of dev_mc_init
  net: qualcomm: rmnet: Fix warning seen with fill_info
  tun: fix vlan packet truncation
  tipc: fix infinite loop when dumping link monitor summary
  tipc: fix use-after-free in tipc_nametbl_stop
  ...

Pull vfs fixes from Al Viro:
 "Assorted fixes.

  Some of that is only a matter with fault injection (broken handling of
  small allocation failure in various mount-related places), but the
  last one is a root-triggerable stack overflow, and combined with
  userns it gets really nasty ;-/"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  Don't leak MNT_INTERNAL away from internal mounts
  mm,vmscan: Allow preallocating memory for register_shrinker().
  rpc_pipefs: fix double-dput()
  orangefs_kill_sb(): deal with allocation failures
  jffs2_kill_sb(): deal with failed allocations
  hypfs_kill_super(): deal with failed allocations

Merge tag 'ecryptfs-4.17-rc2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tyhicks/ecryptfs

Pull eCryptfs fixes from Tyler Hicks:
 "Minor cleanups and a bug fix to completely ignore unencrypted
  filenames in the lower filesystem when filename encryption is enabled
  at the eCryptfs layer"

* tag 'ecryptfs-4.17-rc2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tyhicks/ecryptfs:
  eCryptfs: don't pass up plaintext names when using filename encryption
  ecryptfs: fix spelling mistake: "cadidate" -> "candidate"
  ecryptfs: lookup: Don't check if mount_crypt_stat is NULL