tx_size was just declared above and set to BIT(tx->order)
Use the declaration instead, which could avoid a pointer deref
Signed-off-by: Koen Vandeputte <koen.vandeputte@ncentric.com>
Backport of a4eef43a12 ("ath79: ag71xx: replace alloc_etherdev with devm_alloc_etherdev")
combined with the initial changes from John Crispin.
Simplifies the code a lot by using the Managed dev API.
Signed-off-by: Koen Vandeputte <koen.vandeputte@ncentric.com>
Backport of 4eaa3626a8 ("ath79: ag71xx: pass correct device pointer to dma functions")
While 4.14 does not contain the warnings,
it still makes sense to use the proper pointers here.
Signed-off-by: Koen Vandeputte <koen.vandeputte@ncentric.com>
All other instances of this identical declaration fetch the
value directly from the ring_order.
Also do it here.
Signed-off-by: Koen Vandeputte <koen.vandeputte@ncentric.com>
ar71xx got lost during final rebase ..
Fixes: b417a0c48d ("ar71xx/ath79: ag71xx: init rings with GFP_KERNEL")
Signed-off-by: Koen Vandeputte <koen.vandeputte@ncentric.com>
Remove references to broken and mostly deprecated phy_ethtool_ioctl, use
new {s,g}et_link_ksettings and add nway_reset which was previously
handled in phy_ethtool_ioctl.
Cc: John Crispin <john@phrozen.org>
Ref: https://bugs.openwrt.org/index.php?do=details&task_id=1982
Signed-off-by: Petr Štetiar <ynezz@true.cz>
This ioctl is currently routed through generic interface code:
dev_ioctl
dev_ethtool
__ethtool_get_link_ksettings
phy_ethtool_ioctl
Cc: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Petr Štetiar <ynezz@true.cz>
It was reported, that latest ar71xx builds have broken networking on
TP-Link TL-WPA8630 and Nanostation M5 XW devices and that by reverting
the offending commit, everything is back to normal.
Fixes: d3506d1 ("ar71xx: ag71xx: fix compile error when enabling debug")
Signed-off-by: Petr Štetiar <ynezz@true.cz>
Starting from kernel 4.5, phy_id needs to be fetched from a different location.
not doing so results in this compile error:
drivers/net/ethernet/atheros/ag71xx/ag71xx_phy.c: In function 'ag71xx_phy_connect_multi':
drivers/net/ethernet/atheros/ag71xx/ag71xx_phy.c:133:35: error: 'struct mdio_device' has no member named 'phy_id'
ag->mii_bus->mdio_map[phy_addr]->phy_id);
^
./include/linux/printk.h:137:18: note: in definition of macro 'no_printk'
printk(fmt, ##__VA_ARGS__); \
^~~~~~~~~~~
drivers/net/ethernet/atheros/ag71xx/ag71xx.h:72:27: note: in expansion of macro 'pr_debug'
#define DBG(fmt, args...) pr_debug(fmt, ## args)
^~~~~~~~
drivers/net/ethernet/atheros/ag71xx/ag71xx_phy.c:130:3: note: in expansion of macro 'DBG'
DBG("%s: PHY found at %s, uid=%08x\n",
^~~
scripts/Makefile.build:326: recipe for target 'drivers/net/ethernet/atheros/ag71xx/ag71xx_phy.o' failed
Signed-off-by: Koen Vandeputte <koen.vandeputte@ncentric.com>
The swconfig load operation always triggers 'apply' function which in
this driver currently clears port mirroring flags effectively undoing
port mirroring configuration.
This fix preserves port mirroring flags during apply.
Signed-off-by: Milan Krstic <milan.krstic@gmail.com>
The QCA955X is affected by a hardware bug which causes link-loss of the
SGMII link between SoC and PHY. This happens on change of link-state or
speed.
It is not really known what causes this bug. It definitely occurs when
using a AR8033 Gigabit Ethernet PHY.
Qualcomm solves this Bug in a similar fashion. We need to apply the fix
on a per-device base via platform-data as performing the fixup work will
break connectivity in case the SGMII interface is connected to a Switch.
This bug was first proposed to be fixed by Sven Eckelmann in 2016.
https://patchwork.ozlabs.org/patch/604782/
Based-on-patch-by: Sven Eckelmann <sven.eckelmann@open-mesh.com>
Signed-off-by: David Bauer <mail@david-bauer.net>
The driver is written in such a way that with a board defintion that
connects a fixed phy, mdio, and switch in a certain way, a kernel oops could
result because of lack of previously probed mdio bus.
This commit allows for easier debugging in this case by casting the
correct blame with serial console messages.
Signed-off-by: Daniel F. Dickinson <cshored@thecshore.com>
It's a little noisier but makes it obvious when the ar7240 switch was
connected to the MDIO bus, and to which phy device (or the failure
to do so).
Signed-off-by: Daniel F. Dickinson <cshored@thecshore.com>
NB: Error only appears with ag71xx debug messages and dynamic printk
enabled. This is probably why no one has caught it before.
Previously phy probe debug messages used old (now wrong) functions
to get the phy name for printing. There was also the chance of
a NULL pointer in the event no phy_device was found.
Signed-off-by: Daniel F. Dickinson <cshored@thecshore.com>
With this change, the timestamp variable is only used in ag71xx_check_dma_stuck. Small tx speedup.
Based on a Qualcomm commit. ag->timestamp = jiffies was not replaced with netif_trans_update(dev) because of this quote:
It should be noted that after this series several instances
of netif_trans_update() are useless (if they occur in
.ndo_start_xmit and driver doesn't set LLTX flag -- stack already
did an update).
From: http://lists.openwall.net/netdev/2016/05/03/87
Signed-off-by: Rosen Penev <rosenp@gmail.com>
Qualcomm claims this improves the D-cache footprint. Origina commit message below:
From: Ben Menchaca <ben.menchaca@qca.qualcomm.com>
Date: Fri, 7 Jun 2013 10:57:28 -0500
Subject: [ag71xx] cluster/align structs for cache perf
Cluster the frequently used, per-packet structures in ag71xx near
to each other, and cacheline-align them. Some other re-ordering
occurred to move "warmer" structures near the per-packet structures.
Signed-off-by: Ben Menchaca <ben.menchaca@qca.qualcomm.com>
Signed-off-by: Rosen Penev <rosenp@gmail.com>
Because the oldest supported kernel version on the ar71xx target is 4.4,
the condition that the kernel version is smaller than 4.2.0 is always
false. Remove the obsolete check from ag71xx_main.c to clean up the code
a bit.
Signed-off-by: Gabor Juhos <juhosg@freemail.hu>
Qualcomm claims this reduces cache misses. Original commit message below:
From: Ben Menchaca <ben.menchaca@qca.qualcomm.com>
Date: Tue, 11 Jun 2013 12:18:46 -0500
Subject: [ag71xx] reduce NAPI weight
In an attempt to increase our cache warmth, we are decreasing NAPI.
This increases the warmth of the reused SKBs.
Signed-off-by: Ben Menchaca <ben.menchaca@qca.qualcomm.com>
Signed-off-by: Rosen Penev <rosenp@gmail.com>
The motivation for this was misguided. It turns out tuning the NAPI weight could be useful for testing purposes. Therefore reverting.
Signed-off-by: Rosen Penev <rosenp@gmail.com>
This reverts commit 13e5e47369.
This commit causes a severe regression in LAN->WAN routing performance
for several devices. This appears to be caused by the extra requirement
to validate the SKB checksum early in the rx path, which the ethernet
hardware does not do
Signed-off-by: Felix Fietkau <nbd@nbd.name>
This add support for kernel 4.9 to the ar71xx target.
It was compile tested with the generic, NAND and mikrotik subtarget.
Multiple members of the community tested it on their boards and did not
report any major problem so far.
Especially the NAND part received some changes to adapt to the new
kernel APIs. The serial driver hack used for the Arduino Yun was not
ported because the kernel changed there a lot.
Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
On a TL-WN710N, this patch increases iperf performance from ~92.5 to ~93.5 mbps. Keep in mind the WN710N is a 100mbps device. I expect greater numbers from gigabit devices.
Signed-off-by: Rosen Penev <rosenp@gmail.com>
ag71xx_ethtool_set_ringparam() will return an uninitialized value on
success.
Found-by: Coverity Scan #1330877
Signed-off-by: Alexander Couzens <lynxis@fe80.eu>
