Use napi_complete_done() instead of __napi_complete() to :
1) Get support of gro_flush_timeout if opt-in
2) Not rearm interrupts for busy-polling users.
3) use standard NAPI API.
4) Eventually get rid of napi_gro_flush() in the future.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use napi_complete_done() instead of __napi_complete() to :
1) Get support of gro_flush_timeout if opt-in
2) Not rearm interrupts for busy-polling users.
3) use standard NAPI API.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
napi_complete_done() allows to opt-in for gro_flush_timeout,
added back in linux-3.19, commit 3b47d30396
("net: gro: add a per device gro flush timer")
This allows for more efficient GRO aggregation without
sacrifying latencies.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The network stack no longer uses the last_rx member of struct net_device
since the bonding driver switched to use its own private last_rx in
commit 9f24273837 ("bonding: use last_arp_rx in slave_last_rx()").
However, some drivers still (ab)use the field for their own purposes and
some driver just update it without actually using it.
Previously, there was an accompanying comment for the last_rx member
added in commit 4dc89133f4 ("net: add a comment on netdev->last_rx")
which asked drivers not to update is, unless really needed. However,
this commend was removed in commit f8ff080dac ("bonding: remove
useless updating of slave->dev->last_rx"), so some drivers added later
on still did update last_rx.
Remove all usage of last_rx and switch three drivers (sky2, atp and
smc91c92_cs) which actually read and write it to use their own private
copy in netdev_priv.
Compile-tested with allyesconfig and allmodconfig on x86 and arm.
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Cc: Mirko Lindner <mlindner@marvell.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Acked-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The network device operation for reading statistics is only called
in one place, and it ignores the return value. Having a structure
return value is potentially confusing because some future driver could
incorrectly assume that the return value was used.
Fix all drivers with ndo_get_stats64 to have a void function.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
>From the realtek data sheet, the PID0 should be bit 0.
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking fixes from David Miller:
1) Various ipvlan fixes from Eric Dumazet and Mahesh Bandewar.
The most important is to not assume the packet is RX just because
the destination address matches that of the device. Such an
assumption causes problems when an interface is put into loopback
mode.
2) If we retry when creating a new tc entry (because we dropped the
RTNL mutex in order to load a module, for example) we end up with
-EAGAIN and then loop trying to replay the request. But we didn't
reset some state when looping back to the top like this, and if
another thread meanwhile inserted the same tc entry we were trying
to, we re-link it creating an enless loop in the tc chain. Fix from
Daniel Borkmann.
3) There are two different WRITE bits in the MDIO address register for
the stmmac chip, depending upon the chip variant. Due to a bug we
could set them both, fix from Hock Leong Kweh.
4) Fix mlx4 bug in XDP_TX handling, from Tariq Toukan.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
net: stmmac: fix incorrect bit set in gmac4 mdio addr register
r8169: add support for RTL8168 series add-on card.
net: xdp: remove unused bfp_warn_invalid_xdp_buffer()
openvswitch: upcall: Fix vlan handling.
ipv4: Namespaceify tcp_tw_reuse knob
net: korina: Fix NAPI versus resources freeing
net, sched: fix soft lockup in tc_classify
net/mlx4_en: Fix user prio field in XDP forward
tipc: don't send FIN message from connectionless socket
ipvlan: fix multicast processing
ipvlan: fix various issues in ipvlan_process_multicast()
This chip is the same as RTL8168, but its device id is 0x8161.
Signed-off-by: Chun-Hao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This was entirely automated, using the script by Al:
PATT='^[[:blank:]]*#[[:blank:]]*include[[:blank:]]*<asm/uaccess.h>'
sed -i -e "s!$PATT!#include <linux/uaccess.h>!" \
$(git grep -l "$PATT"|grep -v ^include/linux/uaccess.h)
to do the replacement at the end of the merge window.
Requested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Implement ethtooll::nway_restart by utilizing mii_nway_restart.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Mostly simple overlapping changes.
For example, David Ahern's adjacency list revamp in 'net-next'
conflicted with an adjacency list traversal bug fix in 'net'.
Signed-off-by: David S. Miller <davem@davemloft.net>
8139cp: min_mtu 60, max_mtu 4096
8139too: min_mtu 68, max_mtu 1770
r8169: min_mtu 60, max_mtu depends on chipset, 1500 to 9k-ish
CC: netdev@vger.kernel.org
CC: Realtek linux nic maintainers <nic_swsd@realtek.com>
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
PCI devices that are 64-bit DMA capable should set the coherent
DMA mask as well as the streaming DMA mask. On some architectures,
these are managed separately, and so the coherent DMA mask will be
left at its default value of 32 if it is not set explicitly. This
results in errors such as
r8169 Gigabit Ethernet driver 2.3LK-NAPI loaded
hwdev DMA mask = 0x00000000ffffffff, dev_addr = 0x00000080fbfff000
swiotlb: coherent allocation failed for device 0000:02:00.0 size=4096
CPU: 0 PID: 1062 Comm: systemd-udevd Not tainted 4.8.0+ #35
Hardware name: AMD Seattle/Seattle, BIOS 10:53:24 Oct 13 2016
on systems without memory that is 32-bit addressable by PCI devices.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Francois Romieu <romieu@fr.zoreil.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With centralized MTU checking, there's nothing productive done by
eth_change_mtu that isn't already done in dev_set_mtu, so mark it as
deprecated and remove all usage of it in the kernel. All callers have been
audited for calls to alloc_etherdev* or ether_setup directly, which means
they all have a valid dev->min_mtu and dev->max_mtu. Now eth_change_mtu
prints out a netdev_warn about being deprecated, for the benefit of
out-of-tree drivers that might be utilizing it.
Of note, dvb_net.c actually had dev->mtu = 4096, while using
eth_change_mtu, meaning that if you ever tried changing it's mtu, you
couldn't set it above 1500 anymore. It's now getting dev->max_mtu also set
to 4096 to remedy that.
v2: fix up lantiq_etop, missed breakage due to drive not compiling on x86
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When cp_rx_poll does not get enough packet, it will check the rx
interrupt status again. If so, it will jumpt to rx_status_loop again.
But the goto jump resets the rx variable as zero too.
As a result, it causes one possible deadloop. Assume this case,
rx_status_loop only gets the packet count which is less than budget,
and (cpr16(IntrStatus) & cp_rx_intr_mask) condition is always true.
It causes the deadloop happens and system is blocked.
Signed-off-by: Gao Feng <fgao@ikuai8.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If tx timeout event occur, kernel will call rtl8139_tx_timeout_task() to reset
hardware. But in this function, driver does not stop tx and rx function before
reset hardware, that will cause system hang.
In this patch, add stop tx and rx function before reset hardware.
Signed-off-by: Chunhao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When there is no AC power, NIC may not work after changing mac address.
Please refer to following link.
http://www.spinics.net/lists/netdev/msg356572.html
This issue is caused by runtime power management. When there is no AC
power, if we put NIC down (ifconfig down), the driver will be in runtime
suspend state and hardware will be put into D3 state. During this time,
driver cannot access hardware regisers. So if you set new mac address
during this time, it will not be set to hardware. After resume, NIC will
keep using the old mac address and the network will not work normally.
In this patch I add detecting runtime pm status when setting mac address.
If driver is in runtime suspend state, it will skip setting mac address, keep
the new mac address, and set the new mac address during runtime resume.
Signed-off-by: Chunhao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Not to call rtl8169_update_counters() to dump tally counter when driver
is in runtime suspend state.
Calling rtl8169_update_counters() in runtime suspend state will produce
warning message "rtl_counters_cond == 1 (loop: 1000, delay: 10)".
Signed-off-by: Chunhao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
NIC will be put into D3 state during runtime suspend state. When set or
get hardware wol setting, driver will write or read hardware registers.
If we set or get hardware wol setting in runtime suspend state, because
NIC will in D3 state, the hardware registers read by driver will return all
0xff. That will let driver thinking register flag is not toggled and
then prints the warning message "rtl_counters_cond == 1 (loop: 1000,
delay: 10)" to kernel log.
For fixing this issue, add checking driver's pm runtime status in
rtl8169_get_wol() and rtl8169_set_wol().
Signed-off-by: Chunhao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The current logic around the 'use_dac' module parameter prevents the
r81969 driver from being loadable on 64-bit systems without any RAM
below 4 GB when the parameter is left at its default value.
So introduce a new default value -1 which indicates that 64-bit DMA
should be enabled on sufficiently recent PCIe chips, i.e., versions
RTL_GIGA_MAC_VER_18 or later. Explicit param values of 0 or 1 retain
the existing behavior of unconditionally enabling/disabling 64-bit DMA
on 64-bit architectures (i.e., regardless of the type and version of the
chip)
Since PCIe chips do not need to CPlusCmd Dual Address Cycle to be set,
make that conditional on the device type as well.
Cc: Realtek linux nic maintainers <nic_swsd@realtek.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
For pcie nic, after setting link speed and there is no link driver does not need
to do phy reset until link up.
For some pcie nics, to do this will also reset phy speed down counter and prevent
phy from auto speed down.
This patch fix the issue reported in following link.
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1547151
Signed-off-by: Chunhao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For RTL8168G/RTL8168H/RTL8411B/RTL8107E, enable this flag to eliminate
message "AMD-Vi: Event logged [IO_PAGE_FAULT device=01:00.0 domain=0x0002
address=0x0000000000003000 flags=0x0050] in dmesg.
Signed-off-by: Chunhao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There will be a log spam when there is no cable plugged. Please refer to
following links. https://bugzilla.kernel.org/show_bug.cgi?id=104351https://bugzilla.kernel.org/show_bug.cgi?id=107421
This issue is caused by runtime power management. When there is no cable
plugged, the driver will be suspend (runtime suspend) by OS and NIC will be
put into the D3 state. During this time, if OS call rtl8169_get_stats64()
to dump tally counter, because NIC is in D3 state, the register value read
by driver will return all 0xff. This will let driver think tally counter
flag is not toggled and then sends the warning message "rtl_counters_cond
== 1 (loop: 1000, delay: 10)" to kernel log.
For fixing this issue, 1.add checking driver's pm runtime status in
rtl8169_get_stats64(). 2.dump tally counter before going runtime suspend
for counter accuracy in runtime suspend.
Signed-off-by: Chunhao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are typos in setting RTL8168H hardware parameters. If system install
another version driver that may cuase system hang.
Signed-off-by: Chunhao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The original way is wrong, it always writes ephy reg 0x03.
Signed-off-by: Chunhao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The PHY PFM register is in PHY page 0x0a44 register 0x11, not 0x14.
Signed-off-by: Chunhao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The register for setting D3code PFM mode is MISC_1, not DLLPR.
Signed-off-by: Chunhao Lin <hau@realtek.com>
Reviewed-by: Francois Romieu <romieu@fr.zoreil.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The vlaue of RTL8168H PHY register "rg_saw_cnt" only valid from bit0 to bit13.
When read this register, add bitwise-anding its value with 0x3fff.
Signed-off-by: Chunhao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In function "rtl8168h_2_hw_phy_config", there is a typo in setting
RTL8168H PHY parameter.
Signed-off-by: Chunhao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Fixes: d7d2d89d4b ("r8169: Add software counter for multicast packages")
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Corinna Vinschen <vinschen@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Many drivers initialize uselessly n_priv_flags, n_stats, testinfo_len,
eedump_len & regdump_len fields in their .get_drvinfo() ethtool op.
It's not necessary as these fields is filled in ethtool_get_drvinfo().
v2: removed unused variable
v3: removed another unused variable
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The function can return negative value.
The problem has been detected using proposed semantic patch
scripts/coccinelle/tests/assign_signed_to_unsigned.cocci [1].
[1]: http://permalink.gmane.org/gmane.linux.kernel/2046107
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When fixing the TSO support I noticed we just mask ->gso_size with the
MSSMask value and don't care about the consequences.
Provide a .ndo_features_check() method which drops the NETIF_F_TSO
feature for any skb which would exceed the maximum, and thus forces it
to be segmented by software.
Then we can stop the masking in cp_start_xmit(), and just WARN if the
maximum is exceeded, which should now never happen.
Finally, Francois Romieu noticed that we didn't even have the right
value for MSSMask anyway; it should be 0x7ff (11 bits) not 0xfff.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
I fixed TSO. Hardware checksum and scatter/gather also appear to be
working correctly both on real hardware and in QEMU's emulation.
Let's enable them by default and see if anyone screams...
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We are seeing unexplained TX timeouts under heavy load. Let's try to get
a better idea of what's going on.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The low 16 bits of the 'opts1' field in the TX descriptor are supposed
to still contain the buffer length when the descriptor is handed back to
us. In practice, at least on my hardware, they don't. So stash the
original value of the opts1 field and get the length to unmap from
there.
There are other ways we could have worked out the length, but I actually
want a stash of the opts1 field anyway so that I can dump it alongside
the contents of the descriptor ring when we suffer a TX timeout.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We calculate the value of the opts1 descriptor field in three different
places. With two different behaviours when given an invalid packet to
be checksummed — none of them correct. Sort that out.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When sending a TSO frame in multiple buffers, we were neglecting to set
the first descriptor up in TSO mode.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After a certain amount of staring at the debug output of this driver, I
realised it was lying to me.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If an RX interrupt was already received but NAPI has not yet run when
the RX timeout happens, we end up in cp_tx_timeout() with RX interrupts
already disabled. Blindly re-enabling them will cause an IRQ storm.
(This is made particularly horrid by the fact that cp_interrupt() always
returns that it's handled the interrupt, even when it hasn't actually
done anything. If it didn't do that, the core IRQ code would have
detected the storm and handled it, I'd have had a clear smoking gun
backtrace instead of just a spontaneously resetting router, and I'd have
at *least* two days of my life back. Changing the return value of
cp_interrupt() will be argued about under separate cover.)
Unconditionally leave RX interrupts disabled after the reset, and
schedule NAPI to check the receive ring and re-enable them.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Unless we reset the RX config, on real hardware I don't seem to receive
any packets after a TX timeout.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This can be called from cp_tx_timeout() with interrupts disabled.
Spotted by Francois Romieu <romieu@fr.zoreil.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=104031
Fixes: 6e85d5ad36
Based on the discussion starting at
http://www.spinics.net/lists/netdev/msg342193.html
Tested locally on RTL8168evl/8111evl with various concurrent processes
accessing /proc/net/dev while changing the link state as well as
removing/reloading the r8169 module.
Signed-off-by: Corinna Vinschen <vinschen@redhat.com>
Tested-by: poma <pomidorabelisima@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The multicast hardware counter on 8168/8111 chips is only 32 bit while the
statistics in struct rtnl_link_stats64 are 64 bit. Given that statistics
are requested on an irregular basis, an overflow of the hardware counter
can go unnoticed. To count even very large numbers of multicast packets
reliably, add a software counter and remove previously applied code to
fill the multicast field requested by @rtl8169_get_stats64 with the values
read from the rx_multicast hardware counter.
Signed-off-by: Corinna Vinschen <vinschen@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The r8169 driver collects statistical information returned by
@get_stats64 by counting them in the driver itself, even though many
(but not all) of the values are already collected by tally counters
(TCs) in the NIC. Some of these TC values are not returned by
@get_stats64. Especially the received multicast packages are missing
from /proc/net/dev.
Rectify this by fetching the TCs and returning them from
rtl8169_get_stats64.
The counters collected in the driver obviously disappear as soon as the
driver is unloaded so after a driver is loaded the counters always start
at 0. The TCs on the other hand are only reset by a power cycle. Without
further considerations the values collected by the driver would not match
up against the TC values.
This patch introduces a new function rtl8169_reset_counters which
resets the TCs. Also, since rtl8169_reset_counters shares most of
its code with rtl8169_update_counters, refactor the shared code into
two new functions rtl8169_map_counters and rtl8169_unmap_counters.
Unfortunately chip versions prior to RTL_GIGA_MAC_VER_19 don't allow
to reset the TCs programatically. Therefore introduce an addition to
the rtl8169_private struct and a function rtl8169_init_counter_offsets
to store the TCs at first rtl_open. Use these values as offsets in
rtl8169_get_stats64. Propagate a failure to reset *and* update the
counters up to rtl_open and emit a warning message, if so.
Signed-off-by: Corinna Vinschen <vinschen@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Enforcing this flag in RxConfig for the mentioned chips fixes netdev
watchdog issues prepended with AMD IOMMU message(s) like:
AMD-Vi: Event logged [IO_PAGE_FAULT device=01:00.0 domain=0x001d address=0x0000000000003000 flags=0x0050]
Note that this flag is also set in Realtek's own driver for these chips.
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Tested-by: Alexander Lindqvist <alexander@bitspace.se>
Acked-by: Francois Romieu <romieu@fr.zoreil.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This howto made sense in the 1990s when users had to manually configure
ISA cards with jumpers or vendor utilities, but with the implementation
of PCI it became increasingly less and less relevant, to the point where
it has been well over a decade since I last updated it. And there is
no value in anyone else taking over updating it either.
However the references to it continue to spread as boiler plate text
from one Kconfig file into the next. We are not doing end users any
favours by pointing them at this old document, so lets kill it with
fire, once and for all, to hopefully stop any further spread.
No code is changed in this commit, just Kconfig help text.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet