As time passed, available memory increased faster than number of
concurrent tcp sockets.

As a result, a machine with 4GB of ram gets a hash table
with 524288 slots, using 8388608 bytes of memory.

Lets change that by a 16x factor (one slot for 128 KB of ram)

Even if a small machine needs a _lot_ of sockets, tcp lookups are now
very efficient, using one cache line per socket.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Ben Hutchings says:

====================
1. More workarounds for TX queue flush failures that can occur during
   interface reconfiguration.
2. Fix spurious failure of a firmware request running during a system
   clock change, e.g. ntpd started at the same time as driver load.
3. Fix inconsistent statistics after a firmware upgrade.
4. Fix a variable (non-)initialisation in offline self-test that can
   make it more disruptive than intended.
5. Fix a race that can (at least) cause an assertion failure.
6. Miscellaneous cleanup.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jeff Kirsher says:

====================
This series contains updates to ixgbe, igb and e1000e.  Majority of the
changes are against igb.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change makes it so that only the first fragment in a series of fragments
will have the L4 header pulled.  Previously we were always pulling the L4
header as well and in the case of UDP this can harm performance since only the
first fragment will have the header, the rest just contain data which should
be left in the paged portion of the packet.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NStephen Ko <stephen.s.ko@intel.com>
Tested-by: NMarcus Dennis <marcusx.e.dennis@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Update comments to conform to the preferred style for networking code as
described in ./Documentation/CodingStyle and checked for in the recently
added checkpatch NETWORKING_BLOCK_COMMENT_STYLE test.
Signed-off-by: NBruce Allan <bruce.w.allan@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch enables flow control to be set in SerDes autoneg mode.  This is
done the way it is done for copper, but relies on a different set of register/bit
checks since this is all done within the MAC registers.
Signed-off-by: NCarolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch unsets the sigdetect bit for SERDES loopback tests on 82580 and
i350 parts.  The loopback test can fail on these parts without this
setting.
Signed-off-by: NCarolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Due to a hw errata, the global device reset doesn't always work on 82580
devices.  This patch works around the problem not trying to do a global
device reset on these devices.
Signed-off-by: NCarolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch refactors the functions in e1000_i210.c in order to remove need
for prototypes.
Signed-off-by: NCarolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch allows software acquires and releases NVM resource for
writing each EEPROM page, instead of holding semaphore for the whole
data block which is too long and could trigger write fails on
unpredictable addresses.
Signed-off-by: NAkeem G Abodunrin <akeem.g.abodunrin@intel.com>
Tested-by: NJeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The i211 has an integrated secure space to store configuration information that is
usually stored in an EEPROM or flash type device. This patch updates the
read functions to return values or appropriate error codes to prevent
unnecessary init failures on some configuration schemes.
Signed-off-by: NCarolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: NJeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch replaces calls to copy_to_user, copy_from_user, and the associated
logic, with calls to simple_read_from_buffer and simple_write_to_buffer
respectively.  This was done to eliminate warnings generated by the Smatch
static analysis tool.

v2- Fix return values based community feedback
Reported-by: NDan Carpenter <dan.carpenter@oracle.com>
CC: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NJosh Hay <joshua.a.hay@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Most of the module parameters treated as boolean are currently exposed
as type int or uint.  Defining them with the proper type is useful
documentation for both users and developers.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

efx_mcdi_poll() uses get_seconds() to read the current time and to
implement a polling timeout.  The use of this function was chosen
partly because it could easily be replaced in a co-sim environment
with a macro that read the simulated time.

Unfortunately the real get_seconds() returns the system time (real
time) which is subject to adjustment by e.g. ntpd.  If the system time
is adjusted forward during a polled MCDI operation, the effective
timeout can be shorter than the intended 10 seconds, resulting in a
spurious failure.  It is also possible for a backward adjustment to
delay detection of a areal failure.

Use jiffies instead, and change MCDI_RPC_TIMEOUT to be denominated in
jiffies.  Also correct rounding of the timeout: check time > finish
(or rather time_after(time, finish)) and not time >= finish.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

The assertion of netif_device_present() at the top of
efx_hard_start_xmit() may fail if we don't do this.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

We sometimes hit a "failed to flush" timeout on some TX queues, but the
flushes have completed and the flush completion events seem to go missing.
In this case, we can check the TX_DESC_PTR_TBL register and drain the
queues if the flushes had finished.

[bwh: Minor fixes to coding style]
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

If the MC reboots then the stats it reports to us will have been
reset.  We need to reset ours to get efx_update_diff_stat() working
properly.

(Ideally we would maintain stats across the reboot, but as this should
only happen immediately after a firmware upgrade it's not really worth
the trouble.)
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Currently we initialise the newly allocated buffer to all-1s, which is
important for event queues but not for descriptor queues.  And since
we also do that in efx_nic_init_eventq(), it is completely pointless
to do it here.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

efx_writed_table() uses a step of 16 bytes but efx_readd_table() uses
a step of 4 bytes.  Why are they different?

Firstly, register access is asymmetric:

- The EVQ_RPTR table and RX_INDIRECTION_TBL can (or must?) be written
  as dwords even though they have a step size of 16 bytes, unlike
  most other CSRs.
- In general, a read of any width is valid for registers, so long as
  it does not cross register boundaries.  There is also no latching
  behaviour in the BIU, contrary to rumour.

We write to the EVQ_RPTR table with efx_writed_table() but never read
it back as it's write-only.  We write to the RX_INDIRECTION_TBL with
efx_writed_table(), but only read it back for the register dump, where
we use efx_reado_table() as for any other table with step size of 16.

We read MC_TREG_SMEM with efx_readd_table() for the register dump, but
normally read and write it with efx_readd() and efx_writed() using
offsets calculated in bytes.

Since these functions are trivial and have few callers, it's clearer
to open-code them at the call sites.  While we're at it, update the
comments on the BIU behaviour again.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

efx_mcdi_rpc_start() returns a negative value on error or zero on
success.  However one caller that can't properly handle failure then
does WARN_ON(rc > 0).  Change it to WARN_ON(rc < 0).
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Receiving pause frames can block TX queue flushes.  Earlier changes
work around this by reconfiguring the MAC during flushes for VFs, but
during flushes for the PF we would only change the fc_disable counter.
Unless the MAC is reconfigured for some other reason during the flush
(which I would not expect to happen) this had no effect at all.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Add necessary cast when setting a bogus checksum.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

sparse has got a bit more picky since I last ran it over this.  Add
forced casts for use of ~0 as a big-endian value.  Undo the pointless
optimisation of parameter validation with '|'; using '||' avoids these
warnings.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

commit 68835aba (net: optimize INET input path further)
moved some fields used for tcp/udp sockets lookup in the first cache
line of struct sock_common.

This patch moves inet_dport/inet_num as well, filling a 32bit hole
on 64 bit arches and reducing number of cache line misses in lookups.

Also change INET_MATCH()/INET_TW_MATCH() to perform the ports match
before addresses match, as this check is more discriminant.

Remove the hash check from MATCH() macros because we dont need to
re validate the hash value after taking a refcount on socket, and
use likely/unlikely compiler hints, as the sk_hash/hash check
makes the following conditional tests 100% predicted by cpu.

Introduce skc_addrpair/skc_portpair pair values to better
document the alignment requirements of the port/addr pairs
used in the various MATCH() macros, and remove some casts.

The namespace check can also be done at last.

This slightly improves TCP/UDP lookup times.

IP/TCP early demux needs inet->rx_dst_ifindex and
TCP needs inet->min_ttl, lets group them together in same cache line.

With help from Ben Hutchings & Joe Perches.

Idea of this patch came after Ling Ma proposal to move skc_hash
to the beginning of struct sock_common, and should allow him
to submit a final version of his patch. My tests show an improvement
doing so.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Joe Perches <joe@perches.com>
Cc: Ling Ma <ling.ma.program@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This message indicates an error returned from the host when changing MAC address.
Reported-by: NMichal Kubecek <mkubecek@suse.com>
Signed-off-by: NHaiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: NK. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Unlike LRO, GRO requires that vlan tags be removed before
aggregation can occur.  Since the myri10ge NIC does not support
hardware vlan tag offload, we must remove the tag in the driver
to achieve performance comparable to LRO for vlan tagged frames.

Thanks to Eric Duzamet for his help simplifying the original patch.
Signed-off-by: NAndrew Gallatin <gallatin@myri.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Convert myri10ge from LRO to GRO, and simplify the driver by removing
various LRO-related code which is no longer needed including
ndo_fix_features op, custom skb building from frags, and LRO
header parsing.
Signed-off-by: NAndrew Gallatin <gallatin@myri.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Delivery to the following recipient failed permanently:

     vtun@office.satix.net

Technical details of permanent failure:
DNS Error: Domain name not found

Of course:
$ host office.satix.net
Host office.satix.net not found: 3(NXDOMAIN)

===========

And "Change of Email Address Notification":
Old Address        New Address           Email Subject
------------------------------------------------------
maxk@qualcomm.com  maxk@qti.qualcomm.com "tuntap: multiqueue...
Signed-off-by: NJiri Slaby <jslaby@suse.cz>
Cc: Maxim Krasnyansky <maxk@qti.qualcomm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

These macros, while reducing the amount of code, hide flow control
and make the code more confusing to follow and review.  This patch
expands them.  It should have no functional effect on the driver.
Signed-off-by: NSteve Glendinning <steve.glendinning@shawell.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch fixes a bug introduced in bbd9f9ee which could prevent
some wakeups from working correctly if multiple wol options were
selected.

This helper function calculates a 16-bit crc and shifts it into
either the high or low 16 bits of a u32 so the caller can or it
directly into place.  The function previously had a u16 return
type so would always have returned zero when filter was odd.
Signed-off-by: NSteve Glendinning <steve.glendinning@shawell.net>
Reported-by: NBjorn Mork <bjorn@mork.no>
Cc: Joe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As pointed out by Bjorn Mork, the generic "usb" driver sets this
for us so no need to directly set it in this driver.
Signed-off-by: NSteve Glendinning <steve.glendinning@shawell.net>
Cc: Bjorn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch ensures that if we fail to suspend the LAN9500 device
we call usbnet_resume before returning failure, instead of
leaving the usbnet driver in an unusable state.
Signed-off-by: NSteve Glendinning <steve.glendinning@shawell.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch fixes a buffer overflow introduced by bbd9f9ee, where
the filter_mask array is accessed beyond its bounds.

Updated to also add a check for kzalloc failure, as reported by
Bjorn Mork and Joe Perches.
Reported-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NSteve Glendinning <steve.glendinning@shawell.net>
Cc: Bjorn Mork <bjorn@mork.no>
Cc: Joe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

These macros, while reducing the amount of code, hide flow control
and make the code more confusing to follow and review.  This patch
expands them.  It should have no functional effect on the driver.
Signed-off-by: NSteve Glendinning <steve.glendinning@shawell.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If usbnet_suspend returns an error we don't want to call
usbnet_resume to clean up, but instead just return the error.

If usbnet_suspend *does* succeed, and we have a problem further
on, the desired behaviour is still to call usbnet_resume
to clean up before returning.
Signed-off-by: NSteve Glendinning <steve.glendinning@shawell.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If the variable parameter length provided in the mandatory
heartbeat information parameter exceeds the calculated payload
length the packet has been corrupted. Reply with a parameter
length protocol violation message.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Acked-by: NNeil Horman <nhorman@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch removes an unused parameter (src_net) from rtnl_create_link()
method and from the method single invocation, in veth.
This parameter was used in the past when calling
ops->get_tx_queues(src_net, tb) in rtnl_create_link().
The get_tx_queues() member of rtnl_link_ops was replaced by two methods,
get_num_tx_queues() and get_num_rx_queues(), which do not get any
parameter. This was done in commit d40156aa by
Jiri Pirko ("rtnl: allow to specify different num for rx and tx queue count").
Signed-off-by: NRami Rosen <ramirose@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Included changes:
- Use the new ETH_P_BATMAN define instead of the private BATADV_ETH_P_BATMAN
Signed-off-by: NDavid S. Miller <davem@davemloft.net>