- 06 Jan, 2016 16 commits
-
-
Jarod Wilson authored
This is based on the work done by Przemek Rudy in bug 70761 at bugzilla.kernel.org, but with some work done to disentagle and clarify things a bit. Similar to Przemek's work and other drivers, we're adding a padding of 16 here, but we're also disentangling mtu size calculations from max buffer size calculations a bit, and adding ETH_HLEN to the value written into ALX_MTU. Hopefully, with a bit more consistency and clarity, things behave better here. Sadly, I can only test in my alx-driven E2200, which worked just fine before this patch. In comment #58 of bug 70761, Eugene A. Shatokhin reports that this patch does help considerably for a ROSA Linux user of his with an AR8162 network adapter when patched into a 4.1.x-based kernel, with several days of normal operation where wired network previously wasn't usable without setting MTU to 9000 as a work-around. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=70761 CC: "Eugene A. Shatokhin" <eugene.shatokhin@rosalab.ru> CC: Przemek Rudy <prudy1@o2.pl> CC: Jay Cliburn <jcliburn@gmail.com> CC: Chris Snook <chris.snook@gmail.com> CC: netdev@vger.kernel.org Signed-off-by:
Jarod Wilson <jarod@redhat.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Jiri Pirko says: ==================== mlxsw: add offload support for vlan_filtering option Elad says: This patch adds SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING port attribute. When a bridge is offloaded to hardware, the hardware can learn if the bridge is .1Q bridge (VLAN-aware) or not VLAN aware bridge. In order to toggle the mode a user can use sysfs: $ echo 1 > /sys/devices/virtual/net/br0/bridge/vlan_filtering or via iproute2: $ ip link set dev br0 type bridge vlan_filtering 1 --- v1->v2: small fix in patch #1 ==================== Signed-off-by: -
Elad Raz authored
When a vlan is been configured, remeber the untagged mode of the vlan. When displaying the list of configured VLANs, show the untagged attribute. Signed-off-by:
Elad Raz <eladr@mellanox.com> Signed-off-by:
Jiri Pirko <jiri@mellanox.com> Signed-off-by:
-
Elad Raz authored
When a port is bridged, the bridge must be vlan aware bridge (.1Q) or the bridging should be on top of VLAN interfaces (.1D bridge). Signed-off-by:
-
Elad Raz authored
Signed-off-by:
-
Elad Raz authored
Initialize VLANs 0..4095 (Remove init for VID 4096). Signed-off-by:
-
Elad Raz authored
Notifying hardware about newly bridged port vlan-aware changes. Signed-off-by:
-
Elad Raz authored
Notifying hardware about bridge vlan-aware changes. Signed-off-by:
-
Elad Raz authored
Adding vlan_filtering attribute to allow hardware vendor to support vlan-aware bridges. Vlan_filtering is a per-bridge attribute. Signed-off-by:
-
Elad Raz authored
Disallow adding interfaces to a bridge when vlan filtering operation failed. Send the failure code to the user. Signed-off-by:
-
Craig Gallek authored
Fixes: 538950a1 ("soreuseport: setsockopt SO_ATTACH_REUSEPORT_[CE]BPF") Suggested-by:
Daniel Borkmann <daniel@iogearbox.net> Signed-off-by:
Craig Gallek <kraig@google.com> Acked-by:
-
Craig Gallek authored
This socket-lookup path did not pass along the skb in question in my original BPF-based socket selection patch. The skb in the udpN_lib_lookup2 path can be used for BPF-based socket selection just like it is in the 'traditional' udpN_lib_lookup path. udpN_lib_lookup2 kicks in when there are greater than 10 sockets in the same hlist slot. Coincidentally, I chose 10 sockets per reuseport group in my functional test, so the lookup2 path was not excersised. This adds an additional set of tests with 20 sockets. Fixes: 538950a1 ("soreuseport: setsockopt SO_ATTACH_REUSEPORT_[CE]BPF") Fixes: 3ca8e402 ("soreuseport: BPF selection functional test") Suggested-by:
Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
-
Ido Schimmel authored
During initialization, when creating the send descriptor queues (SDQs), we specify the CPU egress traffic class of each SDQ. The maximum number of classes of this type is different in the two ASICs supported by this PCI driver. New firmware versions check this value is set correctly, which causes errors on the Spectrum ASIC, as its max exposed egress traffic class is lower than 7. Solve this by setting this field to 3, which is an acceptable value for both ASICs. Note that we currently do not expose the QoS capabilities of the ASICs, so setting this to an hardcoded value is OK for now. Signed-off-by:
Ido Schimmel <idosch@mellanox.com> Signed-off-by:
-
David S. Miller authored
Merge tag 'wireless-drivers-next-for-davem-2016-01-05' of git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next Kalle Valo says: ==================== brcfmac * fix IBSS which got broken over time * new USB id for bcm43242 dongle * arp offload configuration through inet notifier ath9k * add random number generator support (CONFIG_ATH9K_HWRNG) iwlwifi * Make scan parameters low latency aware * Fix in the NL80211_FEATURE_FULL_AP_CLIENT_STATE state case * Fix enable injection mode (Chaya Rachel) * Various cleanups (Dan / Julia / myself) * Allow to stay more time on popular channels (David Spinadel) * Bug fixes for D0i3 (Eliad / Luca) * Fixes for GO uAPSD (myself) * Start of TSO support (myself) * Rate control bug fixes (Eyal / Gregory) * Start the work on 9000 devices (Johannes / Sara / Oren) * Start the work on a new Tx queue allocation model (Liad) * Debug infrastructure enhancements (Golan) mwifiex * add a debugfs file for chip reset * advertise SMS4 cipher suite * increase ap and station interface limit to 3 * enable MSI support on newer pcie devices (8897 onwards) rtlwifi * fix lots of module parameter usage ==================== Signed-off-by:
-
Arnd Bergmann authored
gcc fails to see that the use of the 'last_offset' variable in hns_nic_reuse_page() is used correctly and issues a bogus warning: drivers/net/ethernet/hisilicon/hns/hns_enet.c: In function 'hns_nic_reuse_page': drivers/net/ethernet/hisilicon/hns/hns_enet.c:541:6: warning: 'last_offset' may be used uninitialized in this function [-Wmaybe-uninitialized] This simplifies the function to make it more obvious what is going on to both readers and compilers, which makes the warning go away. Signed-off-by:
Arnd Bergmann <arnd@arndb.de> Signed-off-by:
-
Florian Westphal authored
The only user was removed in commit 029f7f3b ("netfilter: ipv6: nf_defrag: avoid/free clone operations"). Signed-off-by:
Florian Westphal <fw@strlen.de> Signed-off-by:
-
- 05 Jan, 2016 24 commits
-
-
xypron.glpk@gmx.de authored
IOCTL SIOCRTMSG does nothing but return EINVAL. So comment it as unused. SIOCRTMSG is only used in: * net/ipv4/af_inet.c * include/uapi/linux/sockios.h inet_ioctl calls ip_rt_ioctl. ip_rt_ioctl only handles SIOCADDRT and SIOCDELRT and returns -EINVAL otherwise. Signed-off-by:
Heinrich Schuchardt <xypron.glpk@gmx.de> Signed-off-by:
-
David S. Miller authored
Saeed Mahameed says: ==================== Introduce mlx5 ethernet timestamping This patch series introduces the support for ConnectX-4 timestamping and the PTP kernel interface. Changes from V2: net/mlx5_core: Introduce access function to read internal_timer - Remove one line function - Change function name net/mlx5e: Add HW timestamping (TS) support: - Data path performance optimization (caching tstamp struct in rq,sq) - Change read/write_lock_irqsave to read/write_lock - Move ioctl functions to en_clock file - Changed overflow start algorithm according to comments from Richard - Move timestamp init/cleanup to open/close ndos. In details: 1st patch prevents the driver from modifying skb->data and SKB CB in device xmit function. 2nd patch adds the needed low level helpers for: - Fetching the hardware clock (hardware internal timer) - Parsing CQEs timestamps - Device frequency capability 3rd patch adds new en_clock.c file that handles all needed timestamping operations: - Internal clock structure initialization and other helper functions - Added the needed ioctl for setting/getting the current timestamping configuration. - used this configuration in RX/TX data path to fill the SKB with the timestamp. 4th patch Introduces PTP (PHC) support. ==================== Signed-off-by: -
Eran Ben Elisha authored
Add a PHC support to the mlx5_en driver. Use reader/writer spinlocks to protect the timecounter since every packet received needs to call timecounter_cycle2time() when timestamping is enabled. This can become a performance bottleneck with RSS and multiple receive queues if normal spinlocks are used. The driver has been tested with both Documentation/ptp/testptp and the linuxptp project (http://linuxptp.sourceforge.net/) on a Mellanox ConnectX-4 card. Signed-off-by:
Eran Ben Elisha <eranbe@mellanox.com> Cc: Richard Cochran <richardcochran@gmail.com> Signed-off-by:
Saeed Mahameed <saeedm@mellanox.com> Acked-by:
Richard Cochran <richardcochran@gmail.com> Signed-off-by:
-
Eran Ben Elisha authored
Add support for enable/disable HW timestamping for incoming and/or outgoing packets. To enable/disable HW timestamping appropriate ioctl should be used. Currently HWTSTAMP_FILTER_ALL/NONE and HWTSAMP_TX_ON/OFF only are supported. Make all relevant changes in RX/TX flows to consider TS request and plant HW timestamps into relevant structures. Add internal clock for converting hardware timestamp to nanoseconds. In addition, add a service task to catch internal clock overflow, to make sure timestamping is accurate. Signed-off-by:
-
Eran Ben Elisha authored
A preparation step which adds support for reading the hardware internal timer and the hardware timestamping from the CQE. In addition, advertize device_frequency_khz HCA capability. Signed-off-by:
-
Achiad Shochat authored
If the SKB is cloned, or has an elevated users count, someone else can be looking at it at the same time. Signed-off-by:
Achiad Shochat <achiad@mellanox.com> Signed-off-by:
-
David S. Miller authored
Xin Long says: ==================== sctp: use transport hashtable to replace association's with rhashtable for telecom center, the usual case is that a server is connected by thousands of clients. but if the server with only one enpoint(udp style) use the same sport and dport to communicate with every clients, and every assoc in server will be hashed in the same chain of global assoc hashtable due to currently we choose dport and sport as the hash key. when a packet is received, sctp_rcv try to find the assoc with sport and dport, since that chain is too long to find it fast, it make the performance turn to very low, some test data is as follow: in server: $./ss [start a udp style server there] in client: $./cc [start 2500 sockets to connect server with same port and different ip, and use one of them to send data to server] ===== test on net-next -- perf top server: 55.73% [kernel] [k] sctp_assoc_is_match 6.80% [kernel] [k] sctp_assoc_lookup_paddr 4.81% [kernel] [k] sctp_v4_cmp_addr 3.12% [kernel] [k] _raw_spin_unlock_irqrestore 1.94% [kernel] [k] sctp_cmp_addr_exact client: 46.01% [kernel] [k] sctp_endpoint_lookup_assoc 5.55% libc-2.17.so [.] __libc_calloc 5.39% libc-2.17.so [.] _int_free 3.92% libc-2.17.so [.] _int_malloc 3.23% [kernel] [k] __memset -- spent time time is 487s, send pkt is 10000000 we need to change the way to calculate the hash key, to use lport + rport + paddr as the hash key can avoid this issue. besides, this patchset will use transport hashtable to replace association hashtable to lookup with rhashtable api. get transport first then get association by t->asoc. and also it will make tcp style work better. ===== test with this patchset: -- perf top server: 15.98% [kernel] [k] _raw_spin_unlock_irqrestore 9.92% [kernel] [k] __pv_queued_spin_lock_slowpath 7.22% [kernel] [k] copy_user_generic_string 2.38% libpthread-2.17.so [.] __recvmsg_nocancel 1.88% [kernel] [k] sctp_recvmsg client: 11.90% [kernel] [k] sctp_hash_cmp 8.52% [kernel] [k] rht_deferred_worker 4.94% [kernel] [k] __pv_queued_spin_lock_slowpath 3.95% [kernel] [k] sctp_bind_addr_match 2.49% [kernel] [k] __memset -- spent time time is 22s, send pkt is 10000000 ==================== Signed-off-by: -
Xin Long authored
sctp_endpoint_lookup_assoc is called in the protection of sock lock there is no need to call local_bh_disable in this function. so remove them. Signed-off-by:
Xin Long <lucien.xin@gmail.com> Signed-off-by:
Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by:
-
Xin Long authored
transport hashtable will replace the association hashtable, so association hashtable is not used in sctp any more, so drop the codes about that. Signed-off-by:
-
Xin Long authored
Traversal the transport rhashtable, get the association only once through the condition assoc->peer.primary_path != transport. Signed-off-by:
-
Xin Long authored
apply lookup apis to two functions, for __sctp_endpoint_lookup_assoc and __sctp_lookup_association, it's invoked in the protection of sock lock, it will be safe, but sctp_lookup_association need to call rcu_read_lock() and to detect the t->dead to protect it. Signed-off-by:
-
Xin Long authored
tranport hashtbale will replace the association hashtable to do the lookup for transport, and then get association by t->assoc, rhashtable apis will be used because of it's resizable, scalable and using rcu. lport + rport + paddr will be the base hashkey to locate the chain, with net to protect one netns from another, then plus the laddr to compare to get the target. this patch will provider the lookup functions: - sctp_epaddr_lookup_transport - sctp_addrs_lookup_transport hash/unhash functions: - sctp_hash_transport - sctp_unhash_transport init/destroy functions: - sctp_transport_hashtable_init - sctp_transport_hashtable_destroy Signed-off-by:
-
David S. Miller authored
Craig Gallek says: ==================== Faster SO_REUSEPORT This series contains two optimizations for the SO_REUSEPORT feature: Faster lookup when selecting a socket for an incoming packet and the ability to select the socket from the group using a BPF program. This series only includes the UDP path. I plan to submit a follow-up including the TCP path if the implementation in this series is acceptable. Changes in v4: - pskb_may_pull is unnecessary with pskb_pull (per Alexei Starovoitov) Changes in v3: - skb_pull_inline -> pskb_pull (per Alexei Starovoitov) - reuseport_attach* -> sk_reuseport_attach* and simple return statement syntax change (per Daniel Borkmann) Changes in v2: - Fix ARM build; remove unnecessary include. - Handle case where protocol header is not in linear section (per Alexei Starovoitov). ==================== Signed-off-by: -
Craig Gallek authored
This program will build classic and extended BPF programs and validate the socket selection logic when used with SO_ATTACH_REUSEPORT_CBPF and SO_ATTACH_REUSEPORT_EBPF. It also validates the re-programing flow and several edge cases. Signed-off-by:
Alexei Starovoitov <ast@kernel.org> Signed-off-by:
-
Craig Gallek authored
Expose socket options for setting a classic or extended BPF program for use when selecting sockets in an SO_REUSEPORT group. These options can be used on the first socket to belong to a group before bind or on any socket in the group after bind. This change includes refactoring of the existing sk_filter code to allow reuse of the existing BPF filter validation checks. Signed-off-by:
-
Craig Gallek authored
Include a struct sock_reuseport instance when a UDP socket binds to a specific address for the first time with the reuseport flag set. When selecting a socket for an incoming UDP packet, use the information available in sock_reuseport if present. This required adding an additional field to the UDP source address equality function to differentiate between exact and wildcard matches. The original use case allowed wildcard matches when checking for existing port uses during bind. The new use case of adding a socket to a reuseport group requires exact address matching. Performance test (using a machine with 2 CPU sockets and a total of 48 cores): Create reuseport groups of varying size. Use one socket from this group per user thread (pinning each thread to a different core) calling recvmmsg in a tight loop. Record number of messages received per second while saturating a 10G link. 10 sockets: 18% increase (~2.8M -> 3.3M pkts/s) 20 sockets: 14% increase (~2.9M -> 3.3M pkts/s) 40 sockets: 13% increase (~3.0M -> 3.4M pkts/s) This work is based off a similar implementation written by Ying Cai <ycai@google.com> for implementing policy-based reuseport selection. Signed-off-by:
-
Craig Gallek authored
struct sock_reuseport is an optional shared structure referenced by each socket belonging to a reuseport group. When a socket is bound to an address/port not yet in use and the reuseport flag has been set, the structure will be allocated and attached to the newly bound socket. When subsequent calls to bind are made for the same address/port, the shared structure will be updated to include the new socket and the newly bound socket will reference the group structure. Usually, when an incoming packet was destined for a reuseport group, all sockets in the same group needed to be considered before a dispatching decision was made. With this structure, an appropriate socket can be found after looking up just one socket in the group. This shared structure will also allow for more complicated decisions to be made when selecting a socket (eg a BPF filter). This work is based off a similar implementation written by Ying Cai <ycai@google.com> for implementing policy-based reuseport selection. Signed-off-by:
-
David S. Miller authored
Jiri Pirko says: ==================== mlxsw: couple of fixes Couple of fixes from Ido. ==================== Signed-off-by: -
Ido Schimmel authored
Bridge port attributes are offloaded to hardware when invoked with SELF flag set, but it really makes no sense to reflect them when port is not bridged. Allow a user to change these attribute only when port is bridged and initialize them correctly when joining or leaving a bridge. Signed-off-by:
-
Ido Schimmel authored
Set the bridge status of physical ports in the appropriate functions, to be consistent with LAG join/leave and vPorts joining/leaving bridge. Also, remove the error messages in these two functions, as we already emit errors in both the single functions they call. Signed-off-by:
-
Ido Schimmel authored
It is possible for us to fail when joining or leaving a bridge, so let the user know about that by returning NOTIFY_BAD, as already done for LAG join/leave and 802.1D bridges. Signed-off-by:
-
Ido Schimmel authored
We set PVID to 1 in mlxsw_sp_port_vlan_init(), so we can remove this statement. Signed-off-by:
-
Julia Lawall authored
The cphy_ops structures are never modified, so declare them as const. Done with the help of Coccinelle. Signed-off-by:
Julia Lawall <Julia.Lawall@lip6.fr> Signed-off-by:
-
Arnd Bergmann authored
ARM allmodconfig fails because of the addition of the FMAN driver: drivers/built-in.o: In function `dtsec_restart_autoneg': binder.c:(.text+0x173328): undefined reference to `mdiobus_read' binder.c:(.text+0x173348): undefined reference to `mdiobus_write' drivers/built-in.o: In function `dtsec_config': binder.c:(.text+0x173d24): undefined reference to `of_phy_find_device' drivers/built-in.o: In function `init_phy': binder.c:(.text+0x1763b0): undefined reference to `of_phy_connect' drivers/built-in.o: In function `stop': binder.c:(.text+0x176014): undefined reference to `phy_stop' drivers/built-in.o: In function `start': binder.c:(.text+0x176078): undefined reference to `phy_start' The reason is that the driver uses PHYLIB, but that is a loadable module here, and fman itself is built-in. This patch makes it possible to configure fman as a module as well so we don't change the status of PHYLIB in an allmodconfig kernel, and it adds a 'select PHYLIB' statement to ensure that phylib is always built-in when fman is. The driver uses "builtin_platform_driver(fman_driver);", which means it cannot be unloaded, but it's still possible to have it as a loadable module that gets loaded once and never removed. Signed-off-by:
-
