- 25 May, 2015 36 commits
-
-
Florian Westphal authored
since commit 6aafeef0 ("netfilter: push reasm skb through instead of original frag skbs") we will end up sometimes re-fragmenting skbs that we've reassembled. ipv6 defrag preserves the original skbs using the skb frag list, i.e. as long as the skb frag list is preserved there is no problem since we keep original geometry of fragments intact. However, in the rare case where the frag list is munged or skb is linearized, we might send larger fragments than what we originally received. A router in the path might then send packet-too-big errors even if sender never sent fragments exceeding the reported mtu: mtu 1500 - 1500:1400 - 1400:1280 - 1280 A R1 R2 B 1 - A sends to B, fragment size 1400 2 - R2 sends pkttoobig error for 1280 3 - A sends to B, fragment size 1280 4 - R2 sends pkttoobig error for 1280 again because it sees fragments of size 1400. make sure ip6_fragment always caps MTU at largest packet size seen when defragmented skb is forwarded. Acked-by:
Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by:
Florian Westphal <fw@strlen.de> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Shailendra Verma authored
The variable irq_coalesce is bool type. So assign the value true instead of 1. Signed-off-by:
Shailendra Verma <shailendra.capricorn@gmail.com> Signed-off-by:
-
Shailendra Verma authored
The variable separate_tx_rx_irq is bool type so assigning true instead of 1. Signed-off-by:
-
David S. Miller authored
Martin KaFai Lau says: ==================== ipv6: Only create RTF_CACHE route after encountering pmtu exception v4 -> v5: - Patch 1 is new. Clean up the ipv6_select_ident() and ip6_fragment(). - Further simplify the newly added rt6_get_pcpu_route(). If there is a 'prev' after cmpxchg, return prev instead of the newly created percpu clone. v3 -> v4: - Patch 8 is new. It keeps track of the DST_NOCACHE routes in a list to handle the iface down/unregister event. - Remove rcu from the newly added rt6i_pcpu variable. It is not needed because it has already been protected by the existing reader/writer lock. - Thanks to 'Julian Anastasov <ja@ssi.bg>' for testing the FLOWI_FLAG_KNOWN_NH patches. v2 -> v3: - Patch 5 to 7 are new. They take care of cases where the daddr in skb is not the one used to do the route look-up. There is also related changes to rt6_nexthop() since v2 which is in patch 2/9. Thanks to 'Julian Anastasov <ja@ssi.bg>' for pointing it out. - Fix a few problems in __ip6_rt_update_pmtu(), like setting the expire and mtu before inserting to the tree and don't do dst_destroy() after tree insertion failure. Also update the rt6i_pmtu in fib6_add_rt2node(). Thanks to 'Steffen Klassert <steffen.klassert@secunet.com>' for pointing it out. - Merge ip6_pmtu_rt_cache_alloc() into ip6_rt_cache_alloc(). v1 -> v2: - Move the /128 route bug fixes to another series (accepted). - Create a function for checking (rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY)). - Avoid shuffling the skb network_header. Instead, change the function signature to take iph instead of skb. - Many Thanks to 'Hannes Frederic Sowa <hannes@stressinduktion.org>' on reviewing v1 and v2 and giving advice. --Martin ~~~ start: v1 compose message (with the out-dated parts removed) ~~~ This series is to avoid creating a RTF_CACHE route whenever we are consulting the fib6 tree with a new destination. Instead, only create RTF_CACHE route when we see a pmtu exception. Out of all ipv6 RTF_CACHE routes that are created, the percentage that has a different mtu is very small. In one of our end-user facing proxy server, only 1k out of 80k RTF_CACHE routes have a smaller MTU. For our DC traffic, there is no mtu exception. A large fib6 tree has problems like, 'ip -6 r show' takes a long time. gc may kick in too often. Also, when a service has restarted and a lot of new TCP conn requests come in, it creates pressure on the tree by inserting a lot of RTF_CACHE in a short time and it currently requires a write lock to do that. The first few patches are prep works to remove assumption that the returned rt is always RTF_CACHE. The patch 'ipv6: Only create RTF_CACHE routes after encountering pmtu exception' do the lazy RTF_CACHE route creation. The following patches added percpu rt to compensate the performance loss after doing the RTF_CACHE lazy creation. Here is some numbers of the udpflood test. The udpflood has been slightly modified to have a time limit instead of count limit. A /64 via gateway route is used for the test. Each udpflood uses 10000 dst addresses. The dst addresses of different udpflood processes do not overlap with each other. 1 16M 15M 10 61M 61M 20 65M 62M 40 88M 83M ~~~ end: v1 compose message ~~~ ==================== Signed-off-by: -
Martin KaFai Lau authored
After the patch 'ipv6: Only create RTF_CACHE routes after encountering pmtu exception', we need to compensate the performance hit (bouncing dst->__refcnt). Signed-off-by:
Martin KaFai Lau <kafai@fb.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Julian Anastasov <ja@ssi.bg> Signed-off-by:
-
Martin KaFai Lau authored
This patch breaks up ip6_rt_copy() into ip6_rt_copy_init() and ip6_rt_cache_alloc(). In the later patch, we need to create a percpu rt6_info copy. Hence, refactor the common rt6_info init codes to ip6_rt_copy_init(). Signed-off-by:
-
Martin KaFai Lau authored
This patch keeps track of the DST_NOCACHE routes in a list and replaces its dev with loopback during the iface down/unregister event. Signed-off-by:
-
Martin KaFai Lau authored
This patch always creates RTF_CACHE clone with DST_NOCACHE when FLOWI_FLAG_KNOWN_NH is set so that the rt6i_dst is set to the fl6->daddr. Signed-off-by:
Julian Anastasov <ja@ssi.bg> Tested-by:
-
Martin KaFai Lau authored
The neighbor look-up used to depend on the rt6i_gateway (if there is a gateway) or the rt6i_dst (if it is a RTF_CACHE clone) as the nexthop address. Note that rt6i_dst is set to fl6->daddr for the RTF_CACHE clone where fl6->daddr is the one used to do the route look-up. Now, we only create RTF_CACHE clone after encountering exception. When doing the neighbor look-up with a route that is neither a gateway nor a RTF_CACHE clone, the daddr in skb will be used as the nexthop. In some cases, the daddr in skb is not the one used to do the route look-up. One example is in ip_vs_dr_xmit_v6() where the real nexthop server address is different from the one in the skb. This patch is going to follow the IPv4 approach and ask the ip6_pol_route() callers to set the FLOWI_FLAG_KNOWN_NH properly. In the next patch, ip6_pol_route() will honor the FLOWI_FLAG_KNOWN_NH and create a RTF_CACHE clone. Signed-off-by:
-
Martin KaFai Lau authored
Instead of doing the rt6->rt6i_node check whenever we need to get the route's cookie. Refactor it into rt6_get_cookie(). It is a prep work to handle FLOWI_FLAG_KNOWN_NH and also percpu rt6_info later. Signed-off-by:
-
Martin KaFai Lau authored
This patch creates a RTF_CACHE routes only after encountering a pmtu exception. After ip6_rt_update_pmtu() has inserted the RTF_CACHE route to the fib6 tree, the rt->rt6i_node->fn_sernum is bumped which will fail the ip6_dst_check() and trigger a relookup. Signed-off-by:
-
Martin KaFai Lau authored
A prep work for creating RTF_CACHE on exception only. After this patch, the same condition (rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY)) is checked twice. This redundancy will be removed in the later patch. Signed-off-by:
-
Martin KaFai Lau authored
When creating a RTF_CACHE route, RTF_ANYCAST is set based on rt6i_dst. Also, rt6i_gateway is always set to the nexthop while the nexthop could be a gateway or the rt6i_dst.addr. After removing the rt6i_dst and rt6i_src dependency in the last patch, we also need to stop the caller from depending on rt6i_gateway and RTF_ANYCAST. Signed-off-by:
-
Martin KaFai Lau authored
This patch removes the assumptions that the returned rt is always a RTF_CACHE entry with the rt6i_dst and rt6i_src containing the destination and source address. The dst and src can be recovered from the calling site. We may consider to rename (rt6i_dst, rt6i_src) to (rt6i_key_dst, rt6i_key_src) later. Signed-off-by:
-
Martin KaFai Lau authored
This patch changes the ipv6_select_ident() signature to return a fragment id instead of taking a whole frag_hdr as a param to only set the frag_hdr->identification. It also cleans up ip6_fragment() to obtain the fragment id at the beginning instead of using multiple "if" later to check fragment id has been generated or not. Signed-off-by:
-
Hariprasad Shenai authored
Add support for flashing 10GBaseT adapter with BCM 84834 PHY and Aquantia AQ1202 PHY. Updating of the PHY firmware must happen before the INITIALIZE_CMD. Signed-off-by:
Hariprasad Shenai <hariprasad@chelsio.com> Signed-off-by:
-
Daniel Borkmann authored
Add two more eBPF test cases for JITs, i.e. the second one revealed a bug in the x86_64 JIT compiler, where only an int3 filled image from the allocator was emitted and later wrongly set by the compiler as the bpf_func program code since optimization pass boundary was surpassed w/o actually emitting opcodes. Interpreter: [ 45.782892] test_bpf: #242 BPF_MAXINSNS: Very long jump backwards jited:0 11 PASS [ 45.783062] test_bpf: #243 BPF_MAXINSNS: Edge hopping nuthouse jited:0 14705 PASS After x86_64 JIT (fixed): [ 80.495638] test_bpf: #242 BPF_MAXINSNS: Very long jump backwards jited:1 6 PASS [ 80.495957] test_bpf: #243 BPF_MAXINSNS: Edge hopping nuthouse jited:1 17157 PASS Reference: http://thread.gmane.org/gmane.linux.network/364729Signed-off-by:
Daniel Borkmann <daniel@iogearbox.net> Acked-by:
Alexei Starovoitov <ast@plumgrid.com> Signed-off-by:
-
David S. Miller authored
Tom Lendacky says: ==================== amd-xgbe: AMD XGBE driver updates 2015-05-22 The following patches are included in this driver update series: - Retrieve and set an additional hardware feature setting - Fix the initial mode/speed determination when auto-negotiation is disabled - Add additional netif_dbg support to the driver This patch series is based on net-next. ==================== Signed-off-by: -
Lendacky, Thomas authored
Change more netdev_dbg statements over to netif_dbg and add some new netif_dbg statements to the driver. Signed-off-by:
Tom Lendacky <thomas.lendacky@amd.com> Signed-off-by:
-
Lendacky, Thomas authored
When the ethtool command is used to set the speed of the device while the device is down, the check to set the initial mode may fail when the device is brought up, causing failure to bring the device up. Update the code to set the initial mode based on the desired speed if auto-negotiation is disabled. Signed-off-by:
-
Lendacky, Thomas authored
The device private data structure contains all the defined hardware features for the device. However one of the features is not set. Even though the feature is not currently used, set it to avoid future issues of the feature being checked thinking it has been properly set. Signed-off-by:
-
Florian Westphal authored
Send icmp pmtu error if we find that the largest fragment of df-skb exceeded the output path mtu. The ip output path will still catch this later on but we can avoid the forward/postrouting hook traversal by rejecting right away. This is what ipv6 already does. Acked-by:
-
David S. Miller authored
Hannes Frederic Sowa says: ==================== net: af_unix: zerocopy stream bits This series implements zerocopy support for AF_UNIX SOCK_STREAM sockets. Changelog in the specific patches. Thanks to all the reviewers! ==================== Signed-off-by: -
Hannes Frederic Sowa authored
unix_stream_recvmsg is refactored to unix_stream_read_generic in this patch and enhanced to deal with pipe splicing. The refactoring is inneglible, we mostly have to deal with a non-existing struct msghdr argument. Signed-off-by:
-
Hannes Frederic Sowa authored
Prepare skb_splice_bits to be able to deal with AF_UNIX sockets. AF_UNIX sockets don't use lock_sock/release_sock and thus we have to use a callback to make the locking and unlocking configureable. Signed-off-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
-
Hannes Frederic Sowa authored
This patch implements sendpage support for AF_UNIX SOCK_STREAM sockets. This is also required for a complete splice implementation. The implementation is a bit tricky because we append to already existing skbs and so have to hold unix_sk->readlock to protect the reading side from either advancing UNIXCB.consumed or freeing the skb at the socket receive tail. Signed-off-by:
-
Hannes Frederic Sowa authored
Signed-off-by:
-
David S. Miller authored
Merge tag 'wireless-drivers-next-for-davem-2015-05-21' of git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next Kalle Valo says: ==================== ath10k: * enable channel 144 on 5 GHz * enable Adaptive Noise Immunity (ANI) by default * add Wake on Wireless LAN (WOW) patterns support * add basic Tunneled Direct Link Setup (TDLS) support * add multi-channel support for QCA6174 * enable IBSS RSN support * enable Bluetooth Coexistance whenever firmware supports it * add more versatile way to set bitrates used by the firmware ath9k: * spectral scan: add support for multiple FFT frames per report iwlwifi: * major rework of the scan code (Luca) * some work on the thermal code (Chaya Rachel) * some work on the firwmare debugging infrastructure brcmfmac: * SDIO suspend and resume fixes * wiphy band info and changes in regulatory settings * add support for BCM4324 SDIO and BCM4358 PCIe * enable support of PCIe devices on router platforms (Hante) ==================== Signed-off-by:
-
David S. Miller authored
Or Gerlitz says: ==================== mlx4: Enable single ported VFs over IB ports This series further enhances the support for mlx4 single ported VFs introduced in 3.15 to work over IB ports too. Just as quick reminder, the ConnectX3 device family exposes one PCI device which serves both ports. This can be non-optimal under virtualization schemes where the admin would like the VF to expose one interface to the VM, etc. Since all the VF interaction with the firmware passes through the PF driver, we can emulate to the VF they have one port, and further create a set of the VFs which act on port1 of the device and another set which acts on port2. ==================== Signed-off-by: -
Or Gerlitz authored
Remove the limitation that disallows configuring single ported VFs in the presence of IB ports, after addressing the issues that prevented that to work. SMI (QP0) requests/responses are still not supported for single ported IB VFs. Signed-off-by:
Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by:
Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by:
-
Or Gerlitz authored
It's legal for drivers to provide the QP port through the QPC schedule-queue field on the reset-to-init QP state change. Add adjusting of the schedule queue port in the SRIOV wrapper for that operation too. Signed-off-by:
-
Or Gerlitz authored
Some VF drivers flow set the schedule queue in the QP context but without setting none of OPTPAR_SCHED_QUEUE or OPTPAR_PRIMARY_ADDR_PATH. To allow for such non-modified drivers to function as single ported IB VFs, we must adjust the schedule queue port whenever being set, e.g as currently done for single ported Eth VFs. Signed-off-by:
-
Or Gerlitz authored
As part of enabling single ported VFs over IB ports we need to handle some of the flows for generting EQ events for VFs which don't come into play under Eth ports. This mainly includes port management events derived from changes of the phyiscal port (lid change, client re-register, down/up, etc), VF pkey table changes and VF guid changes initiated by the IB driver. (1) make sure that events are generated only for VFs sitting on the relevant physical port (under the ALL_SLAVES flow). (2) before generating the event, convert from physical (one or two) to VF port (always equals one). Signed-off-by: -
Or Gerlitz authored
When multiplexling a MAD sent from VF, we should convert the port used by the guest to send the packet to the actual physical port which will be used to transmit the packet, before building the relevant address-handle (AH). This is needed under VPI for single ported VFs, since the code that builds the AH (mlx4_ib_query_ah()) makes decisions based on the input port. If we use the port number provided by the guest, it might have different protocol vs. the one this packat has to go from, and hence the result could be wrong. So far, the conversion was done after the AH was built and it worked for single ported Eth VFs which were not enabled under VPI. When adding support for single ported IB VFs and VPI, we hit that. Fixes: 449fc488 ('net/mlx4: Adapt code for N-Port VF') Signed-off-by:
-
Or Gerlitz authored
Single port VFs always provide port = 1 (even if the actual physical port used is port 2). As such, we need to convert the port provided by the VF to the physical port before calling into the firmware. It turns out that the Linux mlx4 VF RoCE driver maintains a copy of the GID table and hence this change became critical only for single ported IB VFs, but it could be needed for other RoCE VF drivers too. Fixes: 449fc488 ('net/mlx4: Adapt code for N-Port VF') Signed-off-by:
-
Geert Uytterhoeven authored
Signed-off-by:
Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by:
-
- 23 May, 2015 4 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller authored
Conflicts: drivers/net/ethernet/cadence/macb.c drivers/net/phy/phy.c include/linux/skbuff.h net/ipv4/tcp.c net/switchdev/switchdev.c Switchdev was a case of RTNH_H_{EXTERNAL --> OFFLOAD} renaming overlapping with net-next changes of various sorts. phy.c was a case of two changes, one adding a local variable to a function whilst the second was removing one. tcp.c overlapped a deadlock fix with the addition of new tcp_info statistic values. macb.c involved the addition of two zyncq device entries. skbuff.h involved adding back ipv4_daddr to nf_bridge_info whilst net-next changes put two other existing members of that struct into a union. Signed-off-by: -
David S. Miller authored
Jesper Dangaard Brouer says: ==================== pktgen: cleanups and introducing new samples/pktgen scripts v3: - Aborted v2 send due it was not generating diff stat (this is a bug in stg-mail, if not in the root directory) v2: address nitpicks from Cong Wang - Remove useless cat's, but keep them for old pgset() - Comment on: Due to pgctrl, cannot use exit code $? from grep - Use arithmetic compare in pktgen_sample03_burst_single_flow.sh This patchset is focused on making pktgen easier to use and better documented. It contains a number of documentation updates and minor changes to pktgen. The major contribution is introduction of common helper function for sample scripts. Instead of the old pgset() function, three new shell functions for configuring the different components of pktgen are introduced: pg_ctrl(), pg_thread() and pg_set(). The new functions correspond to pktgens different components. * pg_ctrl() control "pgctrl" (/proc/net/pktgen/pgctrl) * pg_thread() control the kernel threads and binding to devices * pg_set() control setup of individual devices Helpers also provide consistent parameter parsing across the sample scripts. Usage example: ./pktgen_sample01_simple.sh -i eth41 -m 00:12:C0:02:AC:5A -d 192.168.41.2 Usage: ./pktgen_sample01_simple.sh [-vx] -i ethX -i : ($DEV) output interface/device (required) -s : ($PKT_SIZE) packet size -d : ($DEST_IP) destination IP -m : ($DST_MAC) destination MAC-addr -t : ($THREADS) threads to start -c : ($SKB_CLONE) SKB clones send before alloc new SKB -b : ($BURST) HW level bursting of SKBs -v : ($VERBOSE) verbose -x : ($DEBUG) debug These scripts are borrowed from: https://github.com/netoptimizer/network-testing/tree/master/pktgen ==================== Signed-off-by:
-
Jesper Dangaard Brouer authored
This script pktgen_bench_xmit_mode_netif_receive.sh is a benchmark script, which can be used for benchmarking part of the network stack. This can be used for performance improving or catching regression in that area. The script is developed for benchmarking ingress qdisc path, original idea by Alexei Starovoitov. This script don't really need any hardware. This is achieved via the recently introduced stack inject feature "xmit_mode netif_receive". See commit 62f64aed ("pktgen: introduce xmit_mode '<start_xmit|netif_receive>'"). Signed-off-by:
Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by:
-
Jesper Dangaard Brouer authored
Add the pktgen samples script pktgen_sample03_burst_single_flow.sh that demonstrates how to acheive maximum performance. If correctly tuned[1] single CPU 10Gbit/s wirespeed small pkts is possible[2] which is 14.88Mpps. The trick is to take advantage of the "burst" feature introduced in commit 38b2cf29 ("net: pktgen: packet bursting via skb->xmit_more"). [1] http://netoptimizer.blogspot.dk/2014/06/pktgen-for-network-overload-testing.html [2] http://netoptimizer.blogspot.dk/2014/10/unlocked-10gbps-tx-wirespeed-smallest.htmlSigned-off-by:
-
