- 20 Nov, 2020 40 commits
-
-
Jakub Kicinski authored
Mat Martineau says: ==================== mptcp: More miscellaneous MPTCP fixes Here's another batch of fixup and enhancement patches that we have collected in the MPTCP tree. Patch 1 removes an unnecessary flag and related code. Patch 2 fixes a bug encountered when closing fallback sockets. Patches 3 and 4 choose a better transmit subflow, with a self test. Patch 5 adjusts tracking of unaccepted subflows Patches 6-8 improve handling of long ADD_ADDR options, with a test. Patch 9 more reliably tracks the MPTCP-level window shared with peers. Patch 10 sends MPTCP-level acknowledgements more aggressively, so the peer can send more data without extra delay. ==================== Link: https://lore.kernel.org/r/20201119194603.103158-1-mathew.j.martineau@linux.intel.comSigned-off-by:
Jakub Kicinski <kuba@kernel.org>
-
Paolo Abeni authored
Send timely MPTCP-level ack is somewhat difficult when the insertion into the msk receive level is performed by the worker. It needs TCP-level dup-ack to notify the MPTCP-level ack_seq increase, as both the TCP-level ack seq and the rcv window are unchanged. We can actually avoid processing incoming data with the worker, and let the subflow or recevmsg() send ack as needed. When recvmsg() moves the skbs inside the msk receive queue, the msk space is still unchanged, so tcp_cleanup_rbuf() could end-up skipping TCP-level ack generation. Anyway, when __mptcp_move_skbs() is invoked, a known amount of bytes is going to be consumed soon: we update rcv wnd computation taking them in account. Additionally we need to explicitly trigger tcp_cleanup_rbuf() when recvmsg() consumes a significant amount of the receive buffer. Signed-off-by:
Paolo Abeni <pabeni@redhat.com> Signed-off-by:
Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by:
-
Florian Westphal authored
OoO handling attempts to detect when packet is out-of-window by testing current ack sequence and remaining space vs. sequence number. This doesn't work reliably. Store the highest allowed sequence number that we've announced and use it to detect oow packets. Do this when mptcp options get written to the packet (wire format). For this to work we need to move the write_options call until after stack selected a new tcp window. Acked-by:
Florian Westphal <fw@strlen.de> Signed-off-by:
-
Geliang Tang authored
This patch added IPv6 support for do_transfer, and the test cases for ADD_ADDR IPv6. Acked-by:
Geliang Tang <geliangtang@gmail.com> Signed-off-by:
-
Geliang Tang authored
When ADD_ADDR suboption includes an IPv6 address, the size is 28 octets. It will not fit when other MPTCP suboptions are included in this packet, e.g. DSS. So here we send out an ADD_ADDR dedicated packet to carry only ADD_ADDR suboption, no other MPTCP suboptions. In mptcp_pm_announce_addr, we check whether this is an IPv6 ADD_ADDR. If it is, we set the flag MPTCP_ADD_ADDR_IPV6 to true. Then we call mptcp_pm_nl_add_addr_send_ack to sent out a new pure ACK packet. In mptcp_established_options_add_addr, we check whether this is a pure ACK packet for ADD_ADDR. If it is, we drop all other MPTCP suboptions in this packet, only put ADD_ADDR suboption in it. Suggested-by:
-
Geliang Tang authored
This patch changed the 'add_addr_signal' type from bool to char, so that we could encode the addr type there. Suggested-by:
-
Paolo Abeni authored
This will simplify all operation dealing with subflows before accept time (e.g. data fin processing, add_addr). The join list is already flushed by mptcp_stream_accept() before returning the newly created msk to the user space. This also fixes an potential bug present into the old code: conn_list was manipulated without helding the msk lock in mptcp_stream_accept(). Tested-by:
-
Florian Westphal authored
Add a test case where a link fails with multiple subflows. The expectation is that MPTCP will transmit any data that could not be delivered via the failed link on another subflow. Co-developed-by:
-
Florian Westphal authored
In case a subflow path is blocked, MPTCP-level retransmit may not take place anymore because such subflow is likely to have unacked data left in its write queue. Ignore subflows that have experienced loss and test next candidate. Fixes: 3b1d6210 ("mptcp: implement and use MPTCP-level retransmission") Signed-off-by:
-
Paolo Abeni authored
We need to cope with some more state transition for fallback sockets, or could still end-up moving to TCP_CLOSE too early and avoid spooling some pending data Fixes: e16163b6 ("mptcp: refactor shutdown and close") Signed-off-by:
-
Paolo Abeni authored
Only mptcp_close() can actually cancel the workqueue, no need to add and use this flag. Reviewed-by:
Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by:
-
Jakub Kicinski authored
Ido Schimmel says: ==================== mlxsw: Add support for nexthop objects This patch set adds support for nexthop objects in mlxsw. Nexthop objects are treated as another front-end for programming nexthops, in addition to the existing IPv4 and IPv6 front-ends. Patch #1 registers a listener to the nexthop notification chain and parses the nexthop information into the existing mlxsw data structures that are already used by the IPv4 and IPv6 front-ends. Blackhole nexthops are currently rejected. Support will be added in a follow-up patch set. Patch #2 extends mlxsw to resolve its internal nexthop objects from the nexthop identifier encoded in the FIB info of the notified routes. Patch #3 finally removes the limitation of rejecting routes that use nexthop objects. Patch #4 adds a selftest. Patches #5-#8 add generic forwarding selftests that can be used with veth pairs or physical loopbacks. ==================== Link: https://lore.kernel.org/r/20201119130848.407918-1-idosch@idosch.orgSigned-off-by:
-
Ido Schimmel authored
Add a nexthop objects version of gre_multipath.sh. Unlike the original test, it also tests IPv6 overlay which is not possible with the legacy nexthop implementation. See commit 9a2ad362 ("selftests: forwarding: gre_multipath: Drop IPv6 tests") for more info. Signed-off-by:
Ido Schimmel <idosch@nvidia.com> Signed-off-by:
-
Ido Schimmel authored
In a similar fashion to router_multipath.sh and its nexthop objects version router_mpath_nh.sh, create a nexthop objects version of router.sh. It reuses the same topology, but uses device-only nexthop objects instead of legacy ones. Signed-off-by:
-
Ido Schimmel authored
In addition to IPv4 multipath tests with IPv4 nexthops, also test IPv4 multipath with nexthops that use IPv6 link-local addresses. Signed-off-by:
-
Ido Schimmel authored
routing_nh_obj() is used to configure the nexthop objects employed by the test, but it is called twice resulting in "RTNETLINK answers: File exists" messages. Remove the first call, so that the function is only called after setup_wait(), when all the interfaces are up and ready. Signed-off-by:
-
Ido Schimmel authored
Test that unsupported nexthop objects are rejected and that offload indication is correctly set on: nexthop objects, nexthop group objects and routes associated these objects. Signed-off-by:
-
Ido Schimmel authored
Now that the driver supports nexthop objects, the check is no longer necessary. Remove it. Signed-off-by:
Jiri Pirko <jiri@nvidia.com> Signed-off-by:
-
Ido Schimmel authored
If the FIB info (i.e, 'struct fib_info', 'struct fib6_info') uses a nexthop object, then use the object's identifier to resolve the nexthop group. Signed-off-by:
-
Ido Schimmel authored
Register a listener to the nexthop notification chain and parse notified nexthop objects into the existing mlxsw nexthop data structures. Signed-off-by:
-
Christian Eggers authored
If dsa_switch_ops::port_txtstamp() returns false, clone will be freed immediately. Shouldn't store a pointer to freed memory. Signed-off-by:
Christian Eggers <ceggers@arri.de> Reviewed-by:
Vladimir Oltean <olteanv@gmail.com> Tested-by:
Florian Fainelli <f.fainelli@gmail.com> Link: https://lore.kernel.org/r/20201119110906.25558-1-ceggers@arri.deSigned-off-by:
-
Jakub Kicinski authored
Antonio Cardace says: ==================== netdevsim: add ethtool coalesce and ring settings Output of ethtool-ring.sh and ethtool-coalesce.sh selftests: # ./ethtool-ring.sh PASSED all 4 checks # ./ethtool-coalesce.sh PASSED all 22 checks # ./ethtool-pause.sh PASSED all 7 checks ==================== Link: https://lore.kernel.org/r/20201118204522.5660-1-acardace@redhat.comSigned-off-by:
-
Antonio Cardace authored
Add scripts to test ring and coalesce settings of netdevsim. Signed-off-by:
Antonio Cardace <acardace@redhat.com> Signed-off-by:
-
Antonio Cardace authored
As pointed out by Michal Kubecek, getting the name with the previous approach was racy, it's better and easier to get the name of the device with this patch's approach. Essentialy the function doesn't need to exist anymore as it's a simple 'ls' command. Signed-off-by:
-
Antonio Cardace authored
Factor out some useful functions so that they can be reused by other ethtool-netdevsim scripts. Signed-off-by:
-
Antonio Cardace authored
Add ethtool ring and coalesce settings support for testing. Signed-off-by:
Michal Kubecek <mkubecek@suse.cz> Signed-off-by:
-
Antonio Cardace authored
This will help the refactoring in the next commit when coalesce and ring settings are added. Signed-off-by:
-
Antonio Cardace authored
This bitmask represents all existing coalesce parameters. Signed-off-by:
-
Randy Dunlap authored
Fix build of net/core/stream.o when CONFIG_INET is not enabled. Fixes these build errors (sample): ld: net/core/stream.o: in function `sk_stream_write_space': (.text+0x27e): undefined reference to `tcp_stream_memory_free' ld: (.text+0x29c): undefined reference to `tcp_stream_memory_free' ld: (.text+0x2ab): undefined reference to `tcp_stream_memory_free' ld: net/core/stream.o: in function `sk_stream_wait_memory': (.text+0x5a1): undefined reference to `tcp_stream_memory_free' ld: (.text+0x5bf): undefined reference to `tcp_stream_memory_free' Fixes: 1c5f2ced ("tcp: avoid indirect call to tcp_stream_memory_free()") Signed-off-by:
Randy Dunlap <rdunlap@infradead.org> Reported-by:
-
Colin Ian King authored
The call to pc_delete_flow can kfree the iter object, so the following dev_err message that accesses iter->entry can accessmemory that has just been kfree'd. Fix this by adding a temporary variable 'entry' that has a copy of iter->entry and also use this when indexing into the array mcam->entry2target_pffunc[]. Also print the unsigned value using the %u format specifier rather than %d. Addresses-Coverity: ("Read from pointer after free") Fixes: 55307fcb ("octeontx2-af: Add mbox messages to install and delete MCAM rules") Signed-off-by:Colin Ian King <colin.king@canonical.com> Link: https://lore.kernel.org/r/20201118143803.463297-1-colin.king@canonical.comSigned-off-by:
-
Colin Ian King authored
Currently the variable err may be uninitialized if several of the if statements are not executed in function nix_tx_vtag_decfg and a garbage value in err is returned. Fix this by initialized ret at the start of the function. Addresses-Coverity: ("Uninitialized scalar variable") Fixes: 9a946def ("octeontx2-af: Modify nix_vtag_cfg mailbox to support TX VTAG entries") Signed-off-by: -
Colin Ian King authored
The shifting of the u16 result from ntohs(proto) by 16 bits to the left will be promoted to a 32 bit signed int and then sign-extended to a u64. In the event that the top bit of the return from ntohs(proto) is set then all then all the upper 32 bits of a 64 bit long end up as also being set because of the sign-extension. Fix this by casting to a u64 long before the shift. Addresses-Coverity: ("Unintended sign extension") Fixes: f0c2982a ("octeontx2-pf: Add support for SR-IOV management function") Signed-off-by: -
Jakub Kicinski authored
Srujana Challa says: ==================== Add Support for Marvell OcteonTX2 Cryptographic This patchset adds support for CPT in OcteonTX2 admin function(AF). CPT is a cryptographic accelerator unit and it includes microcoded Giga Cipher engines. OcteonTX2 SOC's resource virtualization unit (RVU) supports multiple physical and virtual functions. Each of the PF/VF's functionality is determined by what kind of resources are attached to it. When the CPT block is attached to a VF, it can function as a security device. The following document provides an overview of the hardware and different drivers for the OcteonTX2 SOC: https://www.kernel.org/doc/Documentation/networking/device_drivers/marvell/octeontx2.rst This patch series includes: - Patch to update existing Marvell sources to support CPT. - Patch that adds mailbox messages to the admin function (AF) driver, to configure CPT HW registers. - Patch to provide debug information about CPT. ==================== Link: https://lore.kernel.org/r/20201118114416.28307-1-schalla@marvell.comSigned-off-by:
-
Srujana Challa authored
Add entries to debugfs at /sys/kernel/debug/octeontx2/cpt. cpt_pc: dump cpt performance HW registers. Usage: cat /sys/kernel/debug/octeontx2/cpt/cpt_pc cpt_ae_sts: show cpt asymmetric engines current state Usage: cat /sys/kernel/debug/octeontx2/cpt/cpt_ae_sts cpt_se_sts: show cpt symmetric engines current state Usage: cat /sys/kernel/debug/octeontx2/cpt/cpt_se_sts cpt_engines_info: dump cpt engine control registers. Usage: cat /sys/kernel/debug/octeontx2/cpt/cpt_engines_info cpt_lfs_info: dump cpt lfs control registers. Usage: cat /sys/kernel/debug/octeontx2/cpt/cpt_lfs_info cpt_err_info: dump cpt error registers. Usage: cat /sys/kernel/debug/octeontx2/cpt/cpt_err_info Signed-off-by:
Suheil Chandran <schandran@marvell.com> Signed-off-by:
Srujana Challa <schalla@marvell.com> Signed-off-by:
-
Srujana Challa authored
On OcteonTX2 SoC, the admin function (AF) is the only one with all priviliges to configure HW and alloc resources, PFs and it's VFs have to request AF via mailbox for all their needs. This patch adds a mailbox interface for CPT PFs and VFs to allocate resources for cryptography. It also adds hardware CPT AF register defines. Signed-off-by:
Lukasz Bartosik <lbartosik@marvell.com> Signed-off-by:
-
Srujana Challa authored
On OcteonTX2 platform CPT instruction enqueue and NIX packet send are only possible via LMTST operations which uses LDEOR instruction. This patch moves lmt flush function from OcteonTX2 nic driver to include/linux/soc since it will be used by OcteonTX2 CPT and NIC driver for LMTST. Signed-off-by:
-
Tariq Toukan authored
Performance analysis counters are maintained under the MLX4_EN_PERF_STAT definition, which is never set. Clean them up, with all related structures and logic. Signed-off-by:
Tariq Toukan <tariqt@nvidia.com> Reviewed-by:
Moshe Shemesh <moshe@nvidia.com> Link: https://lore.kernel.org/r/20201118103427.4314-1-tariqt@nvidia.comSigned-off-by:
-
Paolo Abeni authored
The static checker is fooled by the non-static locking scheme implemented by the mentioned helpers. Let's make its life easier adding some unconditional annotation so that the helpers are now interpreted as a plain spinlock from sparse. v1 -> v2: - add __releases() annotation to unlock_sock_fast() Signed-off-by:
-
Lorenzo Bianconi authored
Convert netsec driver to xdp_return_frame_bulk APIs. Rely on xdp_return_frame_rx_napi for XDP_TX in order to try to recycle the page in the "in-irq" page_pool cache. Co-developed-by:
Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by:
Lorenzo Bianconi <lorenzo@kernel.org> Link: https://lore.kernel.org/r/01487b8f5167d62649339469cdd0c6d8df885902.1605605531.git.lorenzo@kernel.orgSigned-off-by:
-
Numan Siddique authored
There is no easy way to distinguish if a conntracked tcp packet is marked invalid because of tcp_in_window() check error or because it doesn't belong to an existing connection. With this patch, openvswitch sets liberal tcp flag for the established sessions so that out of window packets are not marked invalid. A helper function - nf_ct_set_tcp_be_liberal(nf_conn) is added which sets this flag for both the directions of the nf_conn. Suggested-by:
Numan Siddique <nusiddiq@redhat.com> Acked-by:
-
