- 07 Aug, 2017 40 commits
-
-
Jiri Pirko authored
prio is not cls_flower specific, but it is meaningful for all classifiers. Seems that only mlxsw cares about the value. Obviously, cls offload in other drivers is broken. Signed-off-by:
Jiri Pirko <jiri@mellanox.com> Acked-by:
Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jiri Pirko authored
As ndo_setup_tc is generic offload op for whole tc subsystem, does not really make sense to have cls-specific args. So move them under cls_common structurure which is embedded in all cls structs. Signed-off-by:
-
Jiri Pirko authored
Similar to the rest offloaders of mqprio, no need to check handle. Signed-off-by:
-
Jiri Pirko authored
Change the flows a bit in preparation of follow-up changes in ndo_setup_tc args. Also, change the error code to align with the rest of the drivers. Signed-off-by:
-
Jiri Pirko authored
Let dsa_slave_setup_tc be a splitter for specific setup_tc types and push out cls_matchall specific code into a separate function. Signed-off-by:
Florian Fainelli <f.fainelli@gmail.com> Signed-off-by:
-
Jiri Pirko authored
To sync-up with the naming in the rest of the driver, rename the cls arg. Signed-off-by:
-
Jiri Pirko authored
Let mlxsw_sp_setup_tc be a splitter for specific setup_tc types and push out cls_flower and cls_matchall specific codes into separate functions. Signed-off-by:
-
Jiri Pirko authored
Let mlx5e_rep_setup_tc (former mlx5e_rep_ndo_setup_tc) be a splitter for specific setup_tc types and push out cls_flower specific code into a separate function. Signed-off-by:
-
Jiri Pirko authored
Let mlx5e_setup_tc (former mlx5e_ndo_setup_tc) be a splitter for specific setup_tc types and push out cls_flower and mqprio specific codes into separate functions. Also change the return values so they are the same as in the rest of the drivers. Signed-off-by:
-
Jiri Pirko authored
Let __ixgbe_setup_tc be a splitter for specific setup_tc types and push out cls_u32 and mqprio specific codes into separate functions. Also change the return values so they are the same as in the rest of the drivers. Signed-off-by:
-
Jiri Pirko authored
Let cxgb_setup_tc be a splitter for specific setup_tc types and push out cls_u32 specific code into a separate function. Signed-off-by:
-
Jiri Pirko authored
Since this is specific to flower now, make it part of the flower offload struct. Signed-off-by:
-
Jiri Pirko authored
In order to be aligned with the rest of the types, rename TC_SETUP_MATCHALL to TC_SETUP_CLSMATCHALL. Signed-off-by:
-
Jiri Pirko authored
Since the type is always present, push it to be a separate argument to ndo_setup_tc. On the way, name the type enum and use it for arg type. Signed-off-by:
-
David S. Miller authored
Xin Long says: ==================== sctp: remove typedefs from structures part 5 As we know, typedef is suggested not to use in kernel, even checkpatch.pl also gives warnings about it. Now sctp is using it for many structures. All this kind of typedef's using should be removed. This patchset is the part 5 to remove all typedefs in include/net/sctp/constants.h. Just as the part 1-4, No any code's logic would be changed in these patches, only cleaning up. ==================== Signed-off-by: -
Xin Long authored
This patch is to remove the typedef sctp_subtype_t, and replace with union sctp_subtype in the places where it's using this typedef. Note that it doesn't fix many indents although it should, as sctp_disposition_t's removal would mess them up again. So better to fix them when removing sctp_disposition_t in later patch. Signed-off-by:
Xin Long <lucien.xin@gmail.com> Signed-off-by:
-
Xin Long authored
This patch is to remove the typedef sctp_event_t, and replace with enum sctp_event in the places where it's using this typedef. Signed-off-by:
-
Xin Long authored
This patch is to remove the typedef sctp_event_timeout_t, and replace with enum sctp_event_timeout in the places where it's using this typedef. Signed-off-by:
-
Xin Long authored
This patch is to remove the typedef sctp_event_other_t, and replace with enum sctp_event_other in the places where it's using this typedef. Signed-off-by:
-
Xin Long authored
This patch is to remove the typedef sctp_event_primitive_t, and replace with enum sctp_event_primitive in the places where it's using this typedef. Signed-off-by:
-
Xin Long authored
This patch is to remove the typedef sctp_state_t, and replace with enum sctp_state in the places where it's using this typedef. Signed-off-by:
-
Xin Long authored
This patch is to remove the typedef sctp_ierror_t, and replace with enum sctp_ierror in the places where it's using this typedef. Signed-off-by:
-
Xin Long authored
This patch is to remove the typedef sctp_xmit_t, and replace with enum sctp_xmit in the places where it's using this typedef. Signed-off-by:
-
Xin Long authored
This patch is to remove the typedef sctp_sock_state_t, and replace with enum sctp_sock_state in the places where it's using this typedef. Signed-off-by:
-
Xin Long authored
This patch is to remove the typedef sctp_transport_cmd_t, and replace with enum sctp_transport_cmd in the places where it's using this typedef. Signed-off-by:
-
Xin Long authored
This patch is to remove the typedef sctp_scope_t, and replace with enum sctp_scope in the places where it's using this typedef. Signed-off-by:
-
Xin Long authored
This patch is to remove the typedef sctp_scope_policy_t and keep it's members as an anonymous enum. It is also to define SCTP_SCOPE_POLICY_MAX to replace the num 3 in sysctl.c to make codes clear. Signed-off-by:
-
Xin Long authored
This patch is to remove the typedef sctp_retransmit_reason_t, and replace with enum sctp_retransmit_reason in the places where it's using this typedef. Signed-off-by:
-
Xin Long authored
This patch is to remove the typedef sctp_lower_cwnd_t, and replace with enum sctp_lower_cwnd in the places where it's using this typedef. Signed-off-by:
-
Alexandru Gagniuc authored
Signed-off-by:
Alexandru Gagniuc <alex.g@adaptrum.com> Signed-off-by:
-
Alexandru Gagniuc authored
Before the GMAC on the Anarion chip can be used, the PHY interface selection must be configured with the DWMAC block in reset. This layer covers a block containing only two registers. Although it is possible to model this as a reset controller and use the "resets" property of stmmac, it's much more intuitive to include this in the glue layer instead. At this time only RGMII is supported, because it is the only mode which has been validated hardware-wise. Signed-off-by:
-
stephen hemminger authored
With new transparent VF support, it is possible to get a deadlock when some of the deferred work is running and the unregister_vf is trying to cancel the work element. The solution is to use trylock and reschedule (similar to bonding and team device). Reported-by:
Vitaly Kuznetsov <vkuznets@redhat.com> Fixes: 0c195567 ("netvsc: transparent VF management") Signed-off-by:
Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by:
-
Florian Fainelli authored
During testing with a background iperf pushing 1Gbit/sec worth of traffic and having both ifconfig and ethtool collect statistics, we could see quite frequent deadlocks. Convert the often accessed DSA slave network devices statistics to per-cpu 64-bit statistics to remove these deadlocks and provide fast efficient statistics updates. Fixes: f613ed66 ("net: dsa: Add support for 64-bit statistics") Signed-off-by:
-
David S. Miller authored
Yuchung Cheng says: ==================== tcp cwnd undo refactor This patch series consolidate similar cwnd undo functions implemented by various congestion control by using existing tcp socket state variable. The first patch fixes a corner case in of cwnd undo in Reno and HTCP. Since the bug has existed for many years and is very minor, we consider this patch set more suitable for net-next as the major change is the refactor itself. - v1->v2 Fix trivial compile errors ==================== Signed-off-by: -
Yuchung Cheng authored
Most TCP congestion controls are using identical logic to undo cwnd except BBR. This patch consolidates these similar functions to the one used currently by Reno and others. Suggested-by:
Neal Cardwell <ncardwell@google.com> Signed-off-by:
Yuchung Cheng <ycheng@google.com> Signed-off-by:
-
Yuchung Cheng authored
Using ssthresh to revert cwnd is less reliable when ssthresh is bounded to 2 packets. This patch uses an existing variable in TCP "prior_cwnd" that snapshots the cwnd right before entering fast recovery and RTO recovery in Reno. This fixes the issue discussed in netdev thread: "A buggy behavior for Linux TCP Reno and HTCP" https://www.spinics.net/lists/netdev/msg444955.htmlSuggested-by:
Wei Sun <unlcsewsun@gmail.com> Signed-off-by:
-
kiki good authored
When using Broadcom Systemport device in 32bit Platform, ifconfig can only report up to 4G tx,rx status, which will be wrapped to 0 when the number of incoming or outgoing packets exceeds 4G, only taking around 2 hours in busy network environment (such as streaming). Therefore, it makes hard for network diagnostic tool to get reliable statistical result, so the patch is used to add 64bit support for Broadcom Systemport device in 32bit Platform. This patch provides 64bit statistics capability on both ethtool and ifconfig. Signed-off-by:
Jianming.qiao <kiki-good@hotmail.com> Signed-off-by:
-
Intiyaz Basha authored
Moving PF module param console_bitmask to lio_main.c for consistency. Signed-off-by:
Intiyaz Basha <intiyaz.basha@cavium.com> Signed-off-by:
Felix Manlunas <felix.manlunas@cavium.com> Signed-off-by:
-
Intiyaz Basha authored
There's supposed to be a one-to-one correspondence between the 18 macros that #define the OCT_DEV states (in octeon_device.h) and the strings in the oct_dev_state_str array, but there are only 14 strings in the array. Add the missing strings (so they become 18 in total), and also revise some incorrect/outdated text of existing strings. Signed-off-by:
-
David S. Miller authored
Russell King says: ==================== phylink and sfp support This patch series introduces generic support for SFP sockets found on various Marvell based platforms. The idea here is to provide common SFP socket support which can be re-used by network drivers as appropriate, rather than each network driver having to re-implement SFP socket support. SFP sockets typically use other system resources, eg, I2C buses to read identifying information, and GPIOs to monitor socket state and control the socket. Meanwhile, some network drivers drive multiple ethernet ports from one instantiation of the driver. It is not desirable to block the initialisation of a network driver (thus denying other ports from being operational) if the resources for the SFP socket are not yet available. This means that an element of independence between the SFP support code and the driver is required. More than that, SFP modules effectively bring hotplug PHYs to networking - SFP copper modules normally contain a standard PHY accessed over the I2C bus, and it is desirable to read their state so network drivers can be appropriately configured. To add to the complexity, SFP modules can be connected in at least two places: 1. Directly to the serdes output of a MAC with no intervening PHY. For example: mvneta ----> SFP socket 2. To a PHY, for example: mvpp2 ---> PHY ---> copper | `-----> SFP socket This code supports both setups, although it's not fully implemented with scenario (2). Moreover, the link presented by the SFP module can be one of the 10Gbase-R family (for SFP+ sockets), SGMII or 1000base-X (for SFP sockets) depending on the module, and network drivers need to reconfigure themselves accordingly for the link to come up. For example, if the MAC is configured for SGMII and a fibre module is plugged in, the link won't come up until the MAC is reconfigured for 1000base-X mode. The SFP code manages the SFP socket - detecting the module, reading the identifying information, and managing the control and status signals. Importantly, it disables the SFP module transmitter when the MAC is down, so that the laser is turned off (but that is not a guarantee.) phylink provides the mechanisms necessary to manage the link modes, based on the SFP module type, and supports hot-plugging of the PHY without needing the MAC driver to be brought up and down on transitions. phylink also supports the classical static PHY and fixed-link modes. I currently (but not included in this series) have code to convert mvneta to use phylink, and the out of tree mvpp2x driver. I have nothing for the mvpp2 driver at present as that driver is only recently becoming functional on 10G hardware, and is missing a lot of features that are necessary to make things work correctly. ==================== Signed-off-by:
-
