This patch adds a field to the representation of a PTP hardware clock in
order to remember the frequency adjustment value dialed by the user.

Adding this field will let us answer queries in the manner of adjtimex
in a follow on patch.
Signed-off-by: NRichard Cochran <richardcochran@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jeff Kirsher says:

====================
This series contains updates to igb only.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

One-shot mode uses the TCS bit of the status register to discern
whether a transmission was successful or not. On a failed
transmission, the frame is not echoed back.
Signed-off-by: NAndreas Larsson <andreas@gaisler.com>
Acked-by: NWolfgang Grandegger <wg@grandegger.com>
Acked-by: NOliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: NMarc Kleine-Budde <mkl@pengutronix.de>

This change is meant to improve performance on systems that do not require
the DMA unmap calls.  On those systems we do not need to make use of the
unmap address for Tx or the unmap length so we can drop both thereby
reducing the size of the Tx buffer info structure.

In addition I have changed the logic to check for unmap length instead of
unmap address when checking to see if a buffer needs to be unmapped from
DMA use.  The reasons for this change is that on some platforms it is
possible to receive a valid DMA address of 0 from an IOMMU.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Instead of storing the RSS key as a character array we can simplify the
configuration by making it a u32 array.  This allows us to just write one
value per register without any unnecessary operations to construct the
value.

This change will produce the same exact key, the only difference is that I
translated the u8 array to a u32 array which will be correctly ordered on
writes to hardware by the cpu_to_le32 operations that are built into the
writel calls.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch cleans up our RSS indirection table configuration so that we
generate the same table regardless of CPU endianness.  In addition it
changes the table setup so that instead of doing a modulo based setup it is
instead a divisor based setup.  The advantage to this is that we should be
able to take the Rx hash and compute the Rx queue with very little CPU
overhead if needed.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This change makes it so that Tx cleanup is done in a do/while loop instead
of a for loop.  The main motivation behind this is the fact that we should
never be invoked with a budget less than 1 so we can skip checking the
budget before processing the first descriptor.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This change removes the code that was doing the NUMA allocations for the
q_vectors, rings, and ring resources.  The problem is the logic used assumed
that the NUMA nodes were always interleved and that is not always the case.

At some point I hope to add this functionality back in a more controlled
manner in the future.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Due to a hardware issue, on i210 and i211 parts, the TNCRS statistic
provides an invalid value.  This patch changes the update stats function
to increment the stat only for non-i210/i211 parts.
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>

Adapt the pre-existing and assigned VFs code to the ixgbe way introduced
in commit 9297127b.

Instead of searching the enabled VFs we use pci_num_vf to determine enabled VFs.
By comparing to which PF an assigned VF is owned it's possible to decide
whether to leave it enabled or not.
Signed-off-by: NStefan Assmann <sassmann@kpanic.de>
Acked-by: NGreg Rose <gregory.v.rose@intel.com>
Tested-by: NRobert Garrett <robertx.e.garrett@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

In case of error, the function clk_get() returns ERR_PTR()
and never returns NULL pointer. The NULL test in the error
handling should be replaced with IS_ERR().

dpatch engine is used to auto generated this patch.
(https://github.com/weiyj/dpatch)

Cc: stable <stable@vger.kernel.org>
Signed-off-by: NWei Yongjun <yongjun_wei@trendmicro.com.cn>
Acked-by: NWolfgang Grandegger <wg@grandegger.com>
Signed-off-by: NMarc Kleine-Budde <mkl@pengutronix.de>

Rename generic-sounding function dump_mem() to pcan_dump_mem()
so that it does not conflict with the dump_mem() function in
arch/sh/include/asm/kdebug.h.

drivers/net/can/usb/peak_usb/pcan_usb_core.c: error: conflicting types for 'dump_mem':  => 56:6
drivers/net/can/usb/peak_usb/pcan_usb_core.h: error: conflicting types for 'dump_mem':  => 134:6
Signed-off-by: NRandy Dunlap <rdunlap@xenotime.net>
Reported-by: NGeert Uytterhoeven <geert@linux-m68k.org>
Cc: Stephane Grosjean <s.grosjean@peak-system.com>
Cc: Wolfgang Grandegger <wg@grandegger.com>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
[mkl: convert all users of dump_mem(), too]
Signed-off-by: NMarc Kleine-Budde <mkl@pengutronix.de>

Adopt pinctrl support to c_can driver based on c_can device
pointer, pinctrl driver configure SoC pins to d_can mode
according to definitions provided in .dts file.

In device specific device tree file 'pinctrl-names = "default";'
and 'pinctrl-0 = <&d_can1_pins>;' needs to add to configure pins
from c_can driver. d_can1_pins node contains the pinmux/config
details of d_can L/H pins.
Signed-off-by: NAnilKumar Ch <anilkumar@ti.com>
Acked-by: NTony Lindgren <tony@atomide.com>
Signed-off-by: NMarc Kleine-Budde <mkl@pengutronix.de>

Adds suspend resume support to DCAN driver which enables
DCAN power down mode bit (PDR). Then DCAN will ack the local
power-down mode by setting PDA bit in STATUS register.
Signed-off-by: NAnilKumar Ch <anilkumar@ti.com>
Signed-off-by: NMarc Kleine-Budde <mkl@pengutronix.de>

Add Runtime PM support to C_CAN/D_CAN controller. The runtime PM
APIs control clocks for C_CAN/D_CAN IP and prevent access to the
register of C_CAN/D_CAN IP when clock is turned off.
Signed-off-by: NAnilKumar Ch <anilkumar@ti.com>
Signed-off-by: NMarc Kleine-Budde <mkl@pengutronix.de>

Add device tree support to C_CAN/D_CAN controller and usage details
are added to device tree documentation. Driver was tested on AM335x
EVM.
Signed-off-by: NAnilKumar Ch <anilkumar@ti.com>
For the of binding doc:
Reviewed-by: NStephen Warren <swarren@nvidia.com>
Signed-off-by: NMarc Kleine-Budde <mkl@pengutronix.de>

Modify c_can device names from *_CAN_DEVTYPE to BOSCH_*_CAN to make
use of same names for array indexes in c_can_id_table[] as well as
device names.

This patch also add indexes to c_can_id_table array.
Signed-off-by: NAnilKumar Ch <anilkumar@ti.com>
Signed-off-by: NMarc Kleine-Budde <mkl@pengutronix.de>

Since (9f00d977 netlink: hide struct module parameter in netlink_kernel_create),
linux/netlink.h includes linux/module.h because of the use of THIS_MODULE.

Use linux/export.h instead, as suggested by Stephen Rothwell, which is
significantly smaller and defines THIS_MODULES.
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit eb716c54 ("sunbmac: remove
unnecessary setting of skb->dev") caused the local varible 'dev'
in bigmac_init_rings to become unused.  And now the compiler
warns about it.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

On some hw, link is not up during adding iface to team. That causes event
not being sent to userspace and that may cause confusion.
Fix this bug by sending port changed event once it's added to team.
Signed-off-by: NJiri Pirko <jiri@resnulli.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

On small systems (e.g. embedded ones) IP addresses are often configured
by bootloaders and get assigned to kernel via parameter "ip=".  If set to
"ip=dhcp", even nameserver entries from DHCP daemons are handled. These
entries exported in /proc/net/pnp are commonly linked by /etc/resolv.conf.

To configure nameservers for networks without DHCP, this patch adds option
<dns0-ip> and <dns1-ip> to kernel-parameter 'ip='.
Signed-off-by: NChristoph Fritz <chf.fritz@googlemail.com>
Tested-by: NJan Weitzel <j.weitzel@phytec.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

One of the modes of Huawei E367 has this QMI/wwan interface:

 I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=01 Prot=07 Driver=(none)
 E:  Ad=83(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
 E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
 E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=4ms

Huawei use subclass and protocol to identify vendor specific
functions, so adding a new vendor rule for this combination.

The Pantech devices UML290 (106c:3718) and P4200 (106c:3721) use
the same subclass to identify the QMI/wwan function.  Replace the
existing device specific UML290 entries with generic vendor matching,
adding support for the Pantech P4200.

The ZTE MF683 has 6 vendor specific interfaces, all using
ff/ff/ff for cls/sub/prot.  Adding a match on interface #5 which
is a QMI/wwan interface.

Cc: Fangxiaozhi (Franko) <fangxiaozhi@huawei.com>
Cc: Thomas Schäfer <tschaefer@t-online.de>
Cc: Dan Williams <dcbw@redhat.com>
Cc: Shawn J. Goff <shawn7400@gmail.com>
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When CONFIG_IPV6=m and CONFIG_L2TP=y, I got the following compile error:

  LD      init/built-in.o
net/built-in.o: In function `l2tp_xmit_core':
l2tp_core.c:(.text+0x147781): undefined reference to `inet6_csk_xmit'
net/built-in.o: In function `l2tp_tunnel_create':
(.text+0x149067): undefined reference to `udpv6_encap_enable'
net/built-in.o: In function `l2tp_ip6_recvmsg':
l2tp_ip6.c:(.text+0x14e991): undefined reference to `ipv6_recv_error'
net/built-in.o: In function `l2tp_ip6_sendmsg':
l2tp_ip6.c:(.text+0x14ec64): undefined reference to `fl6_sock_lookup'
l2tp_ip6.c:(.text+0x14ed6b): undefined reference to `datagram_send_ctl'
l2tp_ip6.c:(.text+0x14eda0): undefined reference to `fl6_sock_lookup'
l2tp_ip6.c:(.text+0x14ede5): undefined reference to `fl6_merge_options'
l2tp_ip6.c:(.text+0x14edf4): undefined reference to `ipv6_fixup_options'
l2tp_ip6.c:(.text+0x14ee5d): undefined reference to `fl6_update_dst'
l2tp_ip6.c:(.text+0x14eea3): undefined reference to `ip6_dst_lookup_flow'
l2tp_ip6.c:(.text+0x14eee7): undefined reference to `ip6_dst_hoplimit'
l2tp_ip6.c:(.text+0x14ef8b): undefined reference to `ip6_append_data'
l2tp_ip6.c:(.text+0x14ef9d): undefined reference to `ip6_flush_pending_frames'
l2tp_ip6.c:(.text+0x14efe2): undefined reference to `ip6_push_pending_frames'
net/built-in.o: In function `l2tp_ip6_destroy_sock':
l2tp_ip6.c:(.text+0x14f090): undefined reference to `ip6_flush_pending_frames'
l2tp_ip6.c:(.text+0x14f0a0): undefined reference to `inet6_destroy_sock'
net/built-in.o: In function `l2tp_ip6_connect':
l2tp_ip6.c:(.text+0x14f14d): undefined reference to `ip6_datagram_connect'
net/built-in.o: In function `l2tp_ip6_bind':
l2tp_ip6.c:(.text+0x14f4fe): undefined reference to `ipv6_chk_addr'
net/built-in.o: In function `l2tp_ip6_init':
l2tp_ip6.c:(.init.text+0x73fa): undefined reference to `inet6_add_protocol'
l2tp_ip6.c:(.init.text+0x740c): undefined reference to `inet6_register_protosw'
net/built-in.o: In function `l2tp_ip6_exit':
l2tp_ip6.c:(.exit.text+0x1954): undefined reference to `inet6_unregister_protosw'
l2tp_ip6.c:(.exit.text+0x1965): undefined reference to `inet6_del_protocol'
net/built-in.o:(.rodata+0xf2d0): undefined reference to `inet6_release'
net/built-in.o:(.rodata+0xf2d8): undefined reference to `inet6_bind'
net/built-in.o:(.rodata+0xf308): undefined reference to `inet6_ioctl'
net/built-in.o:(.data+0x1af40): undefined reference to `ipv6_setsockopt'
net/built-in.o:(.data+0x1af48): undefined reference to `ipv6_getsockopt'
net/built-in.o:(.data+0x1af50): undefined reference to `compat_ipv6_setsockopt'
net/built-in.o:(.data+0x1af58): undefined reference to `compat_ipv6_getsockopt'
make: *** [vmlinux] Error 1

This is due to l2tp uses symbols from IPV6, so when IPV6
is a module, l2tp is not allowed to be builtin.

Cc: David Miller <davem@davemloft.net>
Signed-off-by: NCong Wang <amwang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jeff Kirsher says:

====================
This series contains updates to igb and ixgbevf.

v2: updated patch description in 04 patch (ixgbevf: scheduling while
    atomic in reset hw path)
 ...
Akeem G. Abodunrin (1):
  igb: Support to enable EEE on all eee_supported devices

Alexander Duyck (2):
  igb: Remove artificial restriction on RQDPC stat reading
  ixgbevf: Add support for VF API negotiation

John Fastabend (1):
  ixgbevf: scheduling while atomic in reset hw path
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Remove unnecessary temporary variable and #ifdef DEBUG block.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The dbg() USB macro is so old, it predates me.  The USB networking drivers are
the last hold-out using this macro, and we want to get rid of it, so replace
the usage of it with the proper netdev_dbg() or dev_dbg() (depending on the
context) calls.

Some places we end up using a local variable for the debug call, so also
convert the other existing dev_* calls to use it as well, to save tiny amounts
of code space.
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Both tcp_timewait_state_process and tcp_check_req use the same basic
construct of

	struct tcp_options received tmp_opt;
	tmp_opt.saw_tstamp = 0;

then call

	tcp_parse_options

However if they are fed a frame containing a TCP_SACK then tbe code
behaviour is undefined because opt_rx->sack_ok is undefined data.

This ought to be documented if it is intentional.
Signed-off-by: NAlan Cox <alan@linux.intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NChristoph Paasch <christoph.paasch@uclouvain.be>
Acked-by: NH.K. Jerry Chu <hkchu@google.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add rtnl_link_ops to IPoIB, with the first usage being child device
create/delete through them. Childs devices are now either legacy ones,
created/deleted through the ipoib sysfs entries, or RTNL ones.

Adding support for RTNL childs involved refactoring of ipoib_vlan_add
which is now used by both the sysfs and the link_ops code.

Also, added ndo_uninit entry to support calling unregister_netdevice_queue
from the rtnl dellink entry. This required removal of calls to
ipoib_dev_cleanup from the driver in flows which use unregister_netdevice,
since the networking core will invoke ipoib_uninit which does exactly that.
Signed-off-by: NErez Shitrit <erezsh@mellanox.co.il>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Ben Hutchings says:

====================
1. Extension to PPS/PTP to allow for PHC devices where pulses are
   subject to a variable but measurable delay.
2. PPS/PTP/PHC support for Solarflare boards with a timestamping
   peripheral.
3. MTD support for updating the timestamping peripheral on those boards.
4. Fix for potential over-length requests to firmware.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In ixgbevf_reset_hw_vf() msleep is called while holding mbx_lock
resulting in a schedule while atomic bug with trace below.

This patch uses mdelay instead.

BUG: scheduling while atomic: ip/6539/0x00000002
2 locks held by ip/6539:
 #0:  (rtnl_mutex){+.+.+.}, at: [<ffffffff81419cc3>] rtnl_lock+0x17/0x19
 #1:  (&(&adapter->mbx_lock)->rlock){+.+...}, at: [<ffffffffa0030855>] ixgbevf_reset+0x30/0xc1 [ixgbevf]
Modules linked in: ixgbevf ixgbe mdio libfc scsi_transport_fc 8021q scsi_tgt garp stp llc cpufreq_ondemand acpi_cpufreq freq_table mperf ipv6 uinput igb coretemp hwmon crc32c_intel ioatdma i2c_i801 shpchp microcode lpc_ich mfd_core i2c_core joydev dca pcspkr serio_raw pata_acpi ata_generic usb_storage pata_jmicron
Pid: 6539, comm: ip Not tainted 3.6.0-rc3jk-net-next+ #104
Call Trace:
 [<ffffffff81072202>] __schedule_bug+0x6a/0x79
 [<ffffffff814bc7e0>] __schedule+0xa2/0x684
 [<ffffffff8108f85f>] ? trace_hardirqs_off+0xd/0xf
 [<ffffffff814bd0c0>] schedule+0x64/0x66
 [<ffffffff814bb5e2>] schedule_timeout+0xa6/0xca
 [<ffffffff810536b9>] ? lock_timer_base+0x52/0x52
 [<ffffffff812629e0>] ? __udelay+0x15/0x17
 [<ffffffff814bb624>] schedule_timeout_uninterruptible+0x1e/0x20
 [<ffffffff810541c0>] msleep+0x1b/0x22
 [<ffffffffa002e723>] ixgbevf_reset_hw_vf+0x90/0xe5 [ixgbevf]
 [<ffffffffa0030860>] ixgbevf_reset+0x3b/0xc1 [ixgbevf]
 [<ffffffffa0032fba>] ixgbevf_open+0x43/0x43e [ixgbevf]
 [<ffffffff81409610>] ? dev_set_rx_mode+0x2e/0x33
 [<ffffffff8140b0f1>] __dev_open+0xa0/0xe5
 [<ffffffff814097ed>] __dev_change_flags+0xbe/0x142
 [<ffffffff8140b01c>] dev_change_flags+0x21/0x56
 [<ffffffff8141a843>] do_setlink+0x2e2/0x7f4
 [<ffffffff81016e36>] ? native_sched_clock+0x37/0x39
 [<ffffffff8141b0ac>] rtnl_newlink+0x277/0x4bb
 [<ffffffff8141aee9>] ? rtnl_newlink+0xb4/0x4bb
 [<ffffffff812217d1>] ? selinux_capable+0x32/0x3a
 [<ffffffff8104fb17>] ? ns_capable+0x4f/0x67
 [<ffffffff81419cc3>] ? rtnl_lock+0x17/0x19
 [<ffffffff81419f28>] rtnetlink_rcv_msg+0x236/0x253
 [<ffffffff81419cf2>] ? rtnetlink_rcv+0x2d/0x2d
 [<ffffffff8142fd42>] netlink_rcv_skb+0x43/0x94
 [<ffffffff81419ceb>] rtnetlink_rcv+0x26/0x2d
 [<ffffffff8142faf1>] netlink_unicast+0xee/0x174
 [<ffffffff81430327>] netlink_sendmsg+0x26a/0x288
 [<ffffffff813fb04f>] ? rcu_read_unlock+0x56/0x67
 [<ffffffff813f5e6d>] __sock_sendmsg_nosec+0x58/0x61
 [<ffffffff813f81b7>] __sock_sendmsg+0x3d/0x48
 [<ffffffff813f8339>] sock_sendmsg+0x6e/0x87
 [<ffffffff81107c9f>] ? might_fault+0xa5/0xac
 [<ffffffff81402a72>] ? copy_from_user+0x2a/0x2c
 [<ffffffff81402e62>] ? verify_iovec+0x54/0xaa
 [<ffffffff813f9834>] __sys_sendmsg+0x206/0x288
 [<ffffffff810694fa>] ? up_read+0x23/0x3d
 [<ffffffff811307e5>] ? fcheck_files+0xac/0xea
 [<ffffffff8113095e>] ? fget_light+0x3a/0xb9
 [<ffffffff813f9a2e>] sys_sendmsg+0x42/0x60
 [<ffffffff814c5ba9>] system_call_fastpath+0x16/0x1b

CC: Eric Dumazet <edumazet@google.com>
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Tested-By: NRobert Garrett <robertx.e.garrett@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This change makes it so that the VF can support the PF/VF API negotiation
protocol.  Specifically in this case we are adding support for API 1.0
which will mean that the VF is capable of cleaning up buffers that span
multiple descriptors without triggering an error.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NSibai Li <sibai.li@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Current implementation enables EEE on only i350 device. This patch enables
EEE on all eee_supported devices. Also, configured LPI clock to keep
running before EEE is enabled on i210 and i211 devices.
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>

For some reason the reading of the RQDPC register was being artificially
limited to 4K.  Instead of limiting the value we should read the value and
add the full amount.  Otherwise this can lead to a misleading number of
dropped packets when the actual value is in fact much higher.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NJeff Pieper   <jeffrey.e.pieper@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The r8169 driver currently limits the DMA burst for TX to 1024 bytes. I have
a box where this prevents the interface from using the gigabit line to its full
potential. This patch solves the problem by setting TX_DMA_BURST to unlimited.

The box has an ASRock B75M motherboard with on-board RTL8168evl/8111evl
(XID 0c900880). TSO is enabled.

I used netperf (TCP_STREAM test) to measure the dependency of TX throughput
on MTU. I did it for three different values of TX_DMA_BURST ('5'=512, '6'=1024,
'7'=unlimited). This chart shows the results:
http://michich.fedorapeople.org/r8169/r8169-effects-of-TX_DMA_BURST.png

Interesting points:
 - With the current DMA burst limit (1024):
   - at the default MTU=1500 I get only 842 Mbit/s.
   - when going from small MTU, the performance rises monotonically with
     increasing MTU only up to a peak at MTU=1076 (908 MBit/s). Then there's
     a sudden drop to 762 MBit/s from which the throughput rises monotonically
     again with further MTU increases.
 - With a smaller DMA burst limit (512):
   - there's a similar peak at MTU=1076 and another one at MTU=564.
 - With unlimited DMA burst:
   - at the default MTU=1500 I get nice 940 Mbit/s.
   - the throughput rises monotonically with increasing MTU with no strange
     peaks.

Notice that the peaks occur at MTU sizes that are multiples of the DMA burst
limit plus 52. Why 52? Because:
  20 (IP header) + 20 (TCP header) + 12 (TCP options) = 52

The Realtek-provided r8168 driver (v8.032.00) uses unlimited TX DMA burst too,
except for CFG_METHOD_1 where the TX DMA burst is set to 512 bytes.
CFG_METHOD_1 appears to be the oldest MAC version of "RTL8168B/8111B",
i.e. RTL_GIGA_MAC_VER_11 in r8169. Not sure if this MAC version really needs
the smaller burst limit, or if any other versions have similar requirements.
Signed-off-by: NMichal Schmidt <mschmidt@redhat.com>
Acked-by: NFrancois Romieu <romieu@fr.zoreil.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Michal Kubeček <mkubecek@suse.cz>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: NCong Wang <amwang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Michal Kubeček <mkubecek@suse.cz>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: NCong Wang <amwang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Two years ago, Shan Wei tried to fix this:
http://patchwork.ozlabs.org/patch/43905/

The problem is that RFC2460 requires an ICMP Time
Exceeded -- Fragment Reassembly Time Exceeded message should be
sent to the source of that fragment, if the defragmentation
times out.

"
   If insufficient fragments are received to complete reassembly of a
   packet within 60 seconds of the reception of the first-arriving
   fragment of that packet, reassembly of that packet must be
   abandoned and all the fragments that have been received for that
   packet must be discarded.  If the first fragment (i.e., the one
   with a Fragment Offset of zero) has been received, an ICMP Time
   Exceeded -- Fragment Reassembly Time Exceeded message should be
   sent to the source of that fragment.
"

As Herbert suggested, we could actually use the standard IPv6
reassembly code which follows RFC2460.

With this patch applied, I can see ICMP Time Exceeded sent
from the receiver when the sender sent out 3/4 fragmented
IPv6 UDP packet.

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Michal Kubeček <mkubecek@suse.cz>
Cc: David Miller <davem@davemloft.net>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: netfilter-devel@vger.kernel.org
Signed-off-by: NCong Wang <amwang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As pointed by Michal, it is necessary to add a new
namespace for nf_conntrack_reasm code, this prepares
for the second patch.

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Michal Kubeček <mkubecek@suse.cz>
Cc: David Miller <davem@davemloft.net>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: netfilter-devel@vger.kernel.org
Signed-off-by: NCong Wang <amwang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In netpoll tx path, we miss the chance of calling ->ndo_select_queue(),
thus could cause problems when bonding is involved.

This patch makes dev_pick_tx() extern (and rename it to netdev_pick_tx())
to let netpoll call it in netpoll_send_skb_on_dev().
Reported-by: NSylvain Munaut <s.munaut@whatever-company.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: NCong Wang <amwang@redhat.com>
Tested-by: NSylvain Munaut <s.munaut@whatever-company.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>