- 26 Mar, 2014 28 commits
-
-
Vipul Pandya authored
This patch adds TX and RX checksum offload support. Signed-off-by:
Vipul Pandya <vipul.pandya@samsung.com> Neatening-by:
Joe Perches <joe@perches.com> Signed-off-by:
Byungho An <bh74.an@samsung.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Vipul Pandya authored
Enable TSO during initialization for each DMA channels Signed-off-by:
-
Girish K S authored
Added support for the EEE(Energy Efficient Ethernet) in 10G ethernet driver. Signed-off-by:
Girish K S <ks.giri@samsung.com> Neatening-by:
-
Siva Reddy authored
This patch adds support for Samsung 10Gb ethernet driver(sxgbe). - sxgbe core initialization - Tx and Rx support - MDIO support - ISRs for Tx and Rx - ifconfig support to driver Signed-off-by:
Siva Reddy Kallam <siva.kallam@samsung.com> Signed-off-by:
-
dingtianhong authored
Remove the unnecessary log and add net_ratelimit to the others, in order to avoid spam the log. Cc: Joe Perches <joe@perches.com> Cc: Jay Vosburgh <fubar@us.ibm.com> Cc: Veaceslav Falico <vfalico@redhat.com> Cc: Andy Gospodarek <andy@greyhouse.net> Signed-off-by:
Ding Tianhong <dingtianhong@huawei.com> Signed-off-by:
-
dingtianhong authored
The bond send arp request to indicate that the slave is active, and if the bond dev is a vlan dev, it will set the vlan tag in skb to notice the vlan group, but the bond could only send a skb with 802.1q proto, not support for QinQ. So add outer tag for lower vlan tag and inner tag for upper vlan tag to support QinQ, The new skb will be consist of two vlan tag just like this: dst mac | src mac | outer vlan tag | inner vlan tag | data | ..... If We don't need QinQ, the inner vlan tag could be set to 0 and use outer vlan tag as a normal vlan group. Using "ip link" to configure the bond for QinQ and add test log: ip link add link bond0 bond0.20 type vlan proto 802.1ad id 20 ip link add link bond0.20 bond0.20.200 type vlan proto 802.1q id 200 ifconfig bond0.20 11.11.20.36/24 ifconfig bond0.20.200 11.11.200.36/24 echo +11.11.200.37 > /sys/class/net/bond0/bonding/arp_ip_target 90:e2:ba:07:4a:5c (oui Unknown) > Broadcast, ethertype 802.1Q-QinQ (0x88a8),length 50: vlan 20, p 0,ethertype 802.1Q, vlan 200, p 0, ethertype ARP, Ethernet (len 6), IPv4 (len 4), Request who-has 11.11.200.37 tell 11.11.200.36, length 28 90:e2:ba:06:f9:86 (oui Unknown) > 90:e2:ba:07:4a:5c (oui Unknown), ethertype 802.1Q-QinQ (0x88a8), length 50: vlan 20, p 0, ethertype 802.1Q, vlan 200, p 0, ethertype ARP, Ethernet (len 6), IPv4 (len 4), Reply 11.11.200.37 is-at 90:e2:ba:06:f9:86 (oui Unknown), length 28 v1->v2: remove the comment "TODO: QinQ?". Cc: Jay Vosburgh <fubar@us.ibm.com> Cc: Veaceslav Falico <vfalico@redhat.com> Cc: Andy Gospodarek <andy@greyhouse.net> Signed-off-by:
-
dingtianhong authored
It may spam if the system is out of the memory, add ratelimit for it. Signed-off-by:
-
dingtianhong authored
Add unlikely() micro to the unlikely conditions in the bond xmit path for slight optimization. Signed-off-by:
-
Zoltan Kiss authored
Ian made some late comments about the grant mapping series, I incorporated the functional outcomes into this patch: - use callback_param macro to shorten access to pending_tx_info in xenvif_fill_frags() and xenvif_tx_submit() - print an error message in xenvif_idx_unmap() before panic Signed-off-by:
Zoltan Kiss <zoltan.kiss@citrix.com> Signed-off-by:
-
Zoltan Kiss authored
Ian made some late comments about the grant mapping series, I incorporated the non-functional outcomes into this patch: - typo fixes in a comment of xenvif_free(), and add another one there as well - typo fix for comment of rx_drain_timeout_msecs - remove stale comment before calling xenvif_grant_handle_reset() Signed-off-by:
-
Zoltan Kiss authored
Since the early days TX stops if there isn't enough free pending slots to consume a maximum sized (slot-wise) packet. Probably the reason for that is to avoid the case when we don't have enough free pending slot in the ring to finish the packet. But if we make sure that the pending ring has the same size as the shared ring, that shouldn't really happen. The frontend can only post packets which fit the to the free space of the shared ring. If it doesn't, the frontend has to stop, as it can only increase the req_prod when the whole packet fits onto the ring. This patch avoid using this checking, makes sure the 2 ring has the same size, and remove a checking from the callback. As now we don't stop the NAPI instance on this condition, we don't have to wake it up if we free pending slots up. Signed-off-by:
-
Florian Fainelli authored
The AFE_RX_LP_COUNTER kept the last 3 bits set, which would not properly clear the EEE LPI mode errors bits. Make sure that those bits are set to 0 to ensure the PHY timing is always good even during EEE wake-up. Signed-off-by:
Florian Fainelli <f.fainelli@gmail.com> Signed-off-by:
-
Florian Fainelli authored
Writing first to the AFE registers, and then the VCO, RCAL, RC_CAL registers turned out to unveil some spurious MDIO read/write failures which would make the workaround partially applied. The fix is to write first to the VCO, RCAL, RC_CAL registers, and then write to the AFE registers. Signed-off-by:
-
Florian Fainelli authored
Define constants for the various registers used in bcm7xxx_28nm_afe_config_init() to help clarify what this workaround is about. Signed-off-by:
-
Joe Perches authored
Casting a pointer to a pointer of the same type is pointless, so remove these unnecessary casts. Done via coccinelle script: $ cat typecast_2.cocci @@ type T; T *foo; @@ - (T *)foo + foo Signed-off-by:
Shahed Shaikh <shahed.shaikh@qlogic.com> Signed-off-by:
-
Joe Perches authored
Casting a pointer to a pointer of the same type is pointless, so remove these unnecessary casts. Done via coccinelle script: $ cat typecast_2.cocci @@ type T; T *foo; @@ - (T *)foo + foo Signed-off-by:
-
Joe Perches authored
Casting a pointer to a pointer of the same type is pointless, so remove these unnecessary casts. Done via coccinelle script: $ cat typecast_2.cocci @@ type T; T *foo; @@ - (T *)foo + foo Signed-off-by:
Vince Bridgers <vbridgers2013@gmail.com> Signed-off-by:
-
Joe Perches authored
Using addressof then casting to the original type is pointless, so remove these unnecessary casts. Done via coccinelle script: $ cat typecast.cocci @@ type T; T foo; @@ - (T *)&foo + &foo Signed-off-by:
-
Fabio Estevam authored
Having the kernel to print: "smsc911x: Driver version 2008-10-21" on every boot is not very useful, so remove the print of the driver version. Signed-off-by:
Fabio Estevam <fabio.estevam@freescale.com> Signed-off-by:
-
Fabio Estevam authored
With debug enabled we get the following message: smsc911x smsc911x (unregistered net_device): couldn't get clock -2 As the device has not been registered at this point, it is better to use dev_dbg() instead of netdev_dbg(). CC: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> Suggested-by:
Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> Signed-off-by:
-
Yuval Mintz authored
Currently, if a VF's Rx Mode will be configured to support promiscuous mode the PF will comply, causing the VF to actually become promiscuous. This will enable the VF to see all unicast traffic which might be intended for other VMs, which we believe should not be possible. This patch will cause the hypervisor to ignore the VF's request for changes in its Rx mode (other than disabling it), preventing it from becoming promiscuous. Reported-by:
Yoann Juet <yoann.juet@univ-nantes.fr> Signed-off-by:
Yuval Mintz <Yuval.Mintz@qlogic.com> Signed-off-by:
Ariel Elior <Ariel.Elior@qlogic.com> Signed-off-by:
-
Yuval Mintz authored
VFs are currently showing port statistics, although they can't really access those - thus all such statistics will always show a value of 0. This patch removes said statistics from the VF's view as to not confuse the user. Signed-off-by:
-
Yuval Mintz authored
Since we now posses a workqueue dedicated for sriov, the paradigm that sriov- related tasks cannot sleep is no longer correct. The VFOP mechanism was the one previously supporting said paradigm - the sriov related tasks were broken into segments which did not require sleep, and the mechanism re-scheduled the next segment whenever possible. This patch remvoes the VFOP mechanism altogether - the resulting code is a much easier to follow code; The segments are gathered into straight-forward functions which sleep whenever neccessary. Signed-off-by:
-
Yuval Mintz authored
The bnx2x sriov mechanisms were done in the bnx2x slowpath workitem which runs on the bnx2x's workqueue; This workitem is also responsible for the bottom half of interrupt handling in the driver, and specifically it also receives FW notifications of ramrod completions, allowing other flows to progress. The original design of the sriov reltaed-flows was based on the notion such flows must not sleep, since their context is the slowpath workitem. Otherwise, we might reach timeouts - those flows may wait for ramrod completion that will never arrive as the workitem wlll not be re-scheduled until that same flow will be over. In more recent time bnx2x started supporting features in which the VF interface can be configured by the tools accessing the PF on the hypervisor. This support created possible races on the VF-PF lock (which is taken either when the PF is handling a VF message or when the PF is doing some slowpath work on behalf of the VF) which may cause timeouts on the VF side and lags on the PF side. This patch changes the scheme - it creates a new workqueue for sriov related tasks and moves all handling currently done in the slowpath task into the the new workqueue. Signed-off-by:
-
Yuval Mintz authored
This adds support in a new management feature which needs the driver versions (bnx2x, bnx2fc and bnx2i) loaded for each interface. Signed-off-by:
-
Thomas Gleixner authored
The module is about to go away. Make sure everything is stopped safely before we pull the plug. Signed-off-by:
Thomas Gleixner <tglx@linutronix.de> Cc: Chas Williams <chas@cmf.nrl.navy.mil> Cc: atm <linux-atm-general@lists.sourceforge.net> Cc: netdev <netdev@vger.kernel.org> Signed-off-by:
-
Thomas Gleixner authored
The device is about to vanish. So we need to make sure that the timer is completely stopped and the callback is not running on another CPU. Signed-off-by:
-
Matan Barak authored
The code which is dealing with SRIOV alias GUIDs in the mlx4 IB driver has some logic which operated according to the maximal possible active functions (PF + VFs). After the single port VFs code integration this resulted in a flow of false-positive warnings going to the kernel log after the PF driver started the alias GUID work. Fix it by referring to the actual number of functions. Signed-off-by:
Matan Barak <matanb@mellanox.com> Signed-off-by:
Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by:
-
- 25 Mar, 2014 12 commits
-
-
David S. Miller authored
This fixes: drivers/net/xen-netback/netback.c: In function ‘xenvif_tx_dealloc_action’: drivers/net/xen-netback/netback.c:1573:8: warning: format ‘%x’ expects argument of type ‘unsigned int’, but argument 3 has type ‘long int’ [-Wformat=] Signed-off-by: -
Zoltan Kiss authored
This reverts commit e9275f5e . This commit is the last in the netback grant mapping series, and it tries to do more aggressive aggreagtion of unmap operations. However practical use showed almost no positive effect, whilst with certain frontends it causes significant performance regression. Signed-off-by:
Ian Campbell <ian.campbell@citrix.com> Signed-off-by:
-
Eric W. Biederman authored
Replace dev_kfree_skb with dev_kfree_skb_any in start_xmit which can be called in hard irq and other contexts. start_xmit only frees skbs that it is dropping. Signed-off-by:"Eric W. Biederman" <ebiederm@xmission.com>
-
Eric W. Biederman authored
Replace dev_kfree_skb with dev_kfree_skb_any in cvm_oct_xmit_pow which can be called in hard irq and other contexts, on the code paths that drop packets. Replace dev_kfree_skb with dev_consume_skb_any in cvm_oct_xmit_pow which can be called in hard irq and other contexts, on the code path where the packet is transmitted successfully. Signed-off-by: -
Eric W. Biederman authored
Replace dev_kfree_skb with dev_consume_skb_any in wl_send and wl_send_dma which can be called in hard irq and other contexts, on the code paths where the skb was transmitted successfully. Replace dev_kfree_skb with dev_kfree_skb_any in wl_send_dmay which can be called in hard irq and other contexts, on the code path where a skb is dropped. Signed-off-by: -
Eric W. Biederman authored
Replace dev_kfree_skb with dev_kfree_skb_any in xennet_start_xmit which can be called in hard irq and other contexts. xennet_start_xmit only fress skbs which it drops. Signed-off-by: -
Eric W. Biederman authored
Replace dev_kfree_skb with dev_kfree_skb_any in vmnet3_tx_xmit which can be called in hard irq and other contexts. vmnet3_tx_xmit only frees skbs that it has dropped. Signed-off-by: -
Eric W. Biederman authored
Replace dev_kfree_skb with dev_consume_skb_any in xemaclite_send which can be called in hard irq and other contexts. xemacelite_send only frees skbs that it has successfully transmitted. Signed-off-by: -
Eric W. Biederman authored
Replace dev_kfree_skb with dev_kfree_skb_any in velocity_xmit that can be called in hard irq and other contexts. Packets are freed and dropped in velocity_xmit when they are too fragmented and can not be linearized. Signed-off-by: -
Eric W. Biederman authored
Replace dev_kfree_skb with dev_kfree_skb_any in rhine_start_tx which can be called in hard irq and other contexts. Packets are only freed in rhine_start_tx if they are dropped. Replace dev_kfree_skb with dev_consume_skb_any in rhine_tx that can be called in hard irq and other contexts. rhine_tx handles successfully transmitted packets. Signed-off-by: -
Eric W. Biederman authored
Replace dev_kfree_skb with dev_consume_skb_any in spider_net_release_tx_chain which can be called in hard irq and other contexts. dev_consume_skb_any was choosen as it preserves the current dev_kfree_skb semantics (dev_kfree_skb is consume_skb) and is because it is correct most of the time as most packets will have been successfully transmitted not dropeed. Signed-off-by: -
Eric W. Biederman authored
Replace kfree_skb with dev_consume_skb_any in tile_net_tx and tile_net_tx_tso which can be called in hard irq and other contexts. At the point where the skbs are freed a packet has been successfully transmitted so dev_consume_skb_any is the appropriate variant to use. Signed-off-by:
-
