- 09 Dec, 2022 22 commits
-
-
wangchuanlei authored
Add support to count upall packets, when kmod of openvswitch upcall to count the number of packets for upcall succeed and failed, which is a better way to see how many packets upcalled on every interfaces. Signed-off-by:
wangchuanlei <wangchuanlei@inspur.com> Acked-by:
Eelco Chaudron <echaudro@redhat.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Tejun Heo authored
rhashtable currently only does bh-safe synchronization making it impossible to use from irq-safe contexts. Switch it to use irq-safe synchronization to remove the restriction. v2: Update the lock functions to return the ulong flags value and unlock functions to take the value directly instead of passing around the pointer. Suggested by Linus. Signed-off-by:Tejun Heo <tj@kernel.org> Reviewed-by:
David Vernet <dvernet@meta.com> Acked-by:
Josh Don <joshdon@google.com> Acked-by:
Hao Luo <haoluo@google.com> Acked-by:
Barret Rhoden <brho@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by:
-
David S. Miller authored
Pedro Tammela says: ==================== net/sched: retpoline wrappers for tc In tc all qdics, classifiers and actions can be compiled as modules. This results today in indirect calls in all transitions in the tc hierarchy. Due to CONFIG_RETPOLINE, CPUs with mitigations=on might pay an extra cost on indirect calls. For newer Intel cpus with IBRS the extra cost is nonexistent, but AMD Zen cpus and older x86 cpus still go through the retpoline thunk. Known built-in symbols can be optimized into direct calls, thus avoiding the retpoline thunk. So far, tc has not been leveraging this build information and leaving out a performance optimization for some CPUs. In this series we wire up 'tcf_classify()' and 'tcf_action_exec()' with direct calls when known modules are compiled as built-in as an opt-in optimization. We measured these changes in one AMD Zen 4 cpu (Retpoline), one AMD Zen 3 cpu (Retpoline), one Intel 10th Gen CPU (IBRS), one Intel 3rd Gen cpu (Retpoline) and one Intel Xeon CPU (IBRS) using pktgen with 64b udp packets. Our test setup is a dummy device with clsact and matchall in a kernel compiled with every tc module as built-in. We observed a 3-8% speed up on the retpoline CPUs, when going through 1 tc filter, and a 60-100% speed up when going through 100 filters. For the IBRS cpus we observed a 1-2% degradation in both scenarios, we believe the extra branches check introduced a small overhead therefore we added a static key that bypasses the wrapper on kernels not using the retpoline mitigation, but compiled with CONFIG_RETPOLINE. 1 filter: CPU | before (pps) | after (pps) | diff R9 7950X | 5914980 | 6380227 | +7.8% R9 5950X | 4237838 | 4412241 | +4.1% R9 5950X | 4265287 | 4413757 | +3.4% [*] i5-3337U | 1580565 | 1682406 | +6.4% i5-10210U | 3006074 | 3006857 | +0.0% i5-10210U | 3160245 | 3179945 | +0.6% [*] Xeon 6230R | 3196906 | 3197059a | +0.0% Xeon 6230R | 3190392 | 3196153 | +0.01% [*] 100 filters: CPU | before (pps) | after (pps) | diff R9 7950X | 373598 | 820396 | +119.59% R9 5950X | 313469 | 633303 | +102.03% R9 5950X | 313797 | 633150 | +101.77% [*] i5-3337U | 127454 | 211210 | +65.71% i5-10210U | 389259 | 381765 | -1.9% i5-10210U | 408812 | 412730 | +0.9% [*] Xeon 6230R | 415420 | 406612 | -2.1% Xeon 6230R | 416705 | 405869 | -2.6% [*] [*] In these tests we ran pktgen with clone set to 1000. On the 7950x system we also tested the impact of filters if iteration order placement varied, first by compiling a kernel with the filter under test being the first one in the static iteration and then repeating it with being last (of 15 classifiers existing today). We saw a difference of +0.5-1% in pps between being the first in the iteration vs being the last. Therefore we order the classifiers and actions according to relevance per our current thinking. v5->v6: - Address Eric Dumazet suggestions v4->v5: - Rebase v3->v4: - Address Eric Dumazet suggestions v2->v3: - Address suggestions by Jakub, Paolo and Eric - Dropped RFC tag (I forgot to add it on v2) v1->v2: - Fix build errors found by the bots - Address Kuniyuki Iwashima suggestions ==================== Signed-off-by:
-
Pedro Tammela authored
Expose the necessary tc classifier functions and wire up cls_api to use direct calls in retpoline kernels. Signed-off-by:
Pedro Tammela <pctammela@mojatatu.com> Reviewed-by:
Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by:
Victor Nogueira <victor@mojatatu.com> Signed-off-by:
-
Pedro Tammela authored
Expose the necessary tc act functions and wire up act_api to use direct calls in retpoline kernels. Signed-off-by:
-
Pedro Tammela authored
On kernels using retpoline as a spectrev2 mitigation, optimize actions and filters that are compiled as built-ins into a direct call. On subsequent patches we expose the classifiers and actions functions and wire up the wrapper into tc. Signed-off-by:
-
Pedro Tammela authored
The type definition should be visible even in configurations not using CONFIG_NET_CLS_ACT. Signed-off-by:
-
Randy Dunlap authored
Delete a few lines of "depends on PHYLIB" since they are inside an "if PHYLIB / endif # PHYLIB" block, i.e., they are redundant and the other 50+ drivers there don't use "depends on PHYLIB" since it is not needed. Signed-off-by:
Randy Dunlap <rdunlap@infradead.org> Cc: Andrew Lunn <andrew@lunn.ch> Cc: Heiner Kallweit <hkallweit1@gmail.com> Cc: Russell King <linux@armlinux.org.uk> Link: https://lore.kernel.org/r/20221207044257.30036-1-rdunlap@infradead.orgSigned-off-by:
Jakub Kicinski <kuba@kernel.org>
-
Willem de Bruijn authored
Add an option to initialize SOF_TIMESTAMPING_OPT_ID for TCP from write_seq sockets instead of snd_una. This should have been the behavior from the start. Because processes may now exist that rely on the established behavior, do not change behavior of the existing option, but add the right behavior with a new flag. It is encouraged to always set SOF_TIMESTAMPING_OPT_ID_TCP on stream sockets along with the existing SOF_TIMESTAMPING_OPT_ID. Intuitively the contract is that the counter is zero after the setsockopt, so that the next write N results in a notification for the last byte N - 1. On idle sockets snd_una == write_seq and this holds for both. But on sockets with data in transmission, snd_una records the unacked offset in the stream. This depends on the ACK response from the peer. A process cannot learn this in a race free manner (ioctl SIOCOUTQ is one racy approach). write_seq records the offset at the last byte written by the process. This is a better starting point. It matches the intuitive contract in all circumstances, unaffected by external behavior. The new timestamp flag necessitates increasing sk_tsflags to 32 bits. Move the field in struct sock to avoid growing the socket (for some common CONFIG variants). The UAPI interface so_timestamping.flags is already int, so 32 bits wide. Reported-by:
Sotirios Delimanolis <sotodel@meta.com> Signed-off-by:
Willem de Bruijn <willemb@google.com> Link: https://lore.kernel.org/r/20221207143701.29861-1-willemdebruijn.kernel@gmail.comSigned-off-by:
-
Jakub Kicinski authored
Lorenzo Bianconi says: ==================== fix possible deadlock during WED attach Fix a possible deadlock in mtk_wed_attach if mtk_wed_wo_init routine fails. Check wo pointer is properly allocated before running mtk_wed_wo_reset() and mtk_wed_wo_deinit(). ==================== Link: https://lore.kernel.org/r/cover.1670421354.git.lorenzo@kernel.orgSigned-off-by:
-
Lorenzo Bianconi authored
Introduce __mtk_wed_detach() in order to avoid a deadlock in mtk_wed_attach routine if mtk_wed_wo_init fails since both mtk_wed_attach and mtk_wed_detach run holding hw_lock mutex. Fixes: 4c5de09e ("net: ethernet: mtk_wed: add configure wed wo support") Signed-off-by:
Lorenzo Bianconi <lorenzo@kernel.org> Reviewed-by:
Leon Romanovsky <leonro@nvidia.com> Signed-off-by:
-
Lorenzo Bianconi authored
Fix possible NULL pointer dereference in mtk_wed_detach routine checking wo pointer is properly allocated before running mtk_wed_wo_reset() and mtk_wed_wo_deinit(). Even if it is just a theoretical issue at the moment check wo pointer is not NULL in mtk_wed_mcu_msg_update. Moreover, honor mtk_wed_mcu_send_msg return value in mtk_wed_wo_reset() Fixes: 79968444 ("net: ethernet: mtk_wed: introduce wed wo support") Fixes: 4c5de09e ("net: ethernet: mtk_wed: add configure wed wo support") Signed-off-by:
-
Colin Ian King authored
There is a spelling mistake in a nn_dp_warn message. Fix it. Signed-off-by:
Colin Ian King <colin.i.king@gmail.com> Reviewed-by:
Simon Horman <simon.horman@corigine.com> Link: https://lore.kernel.org/r/20221207094312.2281493-1-colin.i.king@gmail.comSigned-off-by:
-
Björn Töpel authored
The BPF Makefile in net/bpf did incorrect path substitution for O=dir builds, e.g. make O=/tmp/kselftest headers make O=/tmp/kselftest -C tools/testing/selftests would fail in selftest builds [1] net/ with clang-16: error: no such file or directory: 'kselftest/net/bpf/nat6to4.c' clang-16: error: no input files Add a pattern prerequisite and an order-only-prerequisite (for creating the directory), to resolve the issue. [1] https://lore.kernel.org/all/202212060009.34CkQmCN-lkp@intel.com/Reported-by:
kernel test robot <lkp@intel.com> Fixes: 837a3d66 ("selftests: net: Add cross-compilation support for BPF programs") Signed-off-by:
Björn Töpel <bjorn@rivosinc.com> Link: https://lore.kernel.org/r/20221206102838.272584-1-bjorn@kernel.orgSigned-off-by:
-
Jakub Kicinski authored
Petr Machata says: ==================== mlxsw: Add Spectrum-1 ip6gre support Ido Schimmel writes: Currently, mlxsw only supports ip6gre offload on Spectrum-2 and newer ASICs. Spectrum-1 can also offload ip6gre tunnels, but it needs double entry router interfaces (RIFs) for the RIFs representing these tunnels. In addition, the RIF index needs to be even. This is handled in patches #1-#3. The implementation can otherwise be shared between all Spectrum generations. This is handled in patches #4-#5. Patch #6 moves a mlxsw ip6gre selftest to a shared directory, as ip6gre is no longer only supported on Spectrum-2 and newer ASICs. This work is motivated by users that require multiple GRE tunnels that all share the same underlay VRF. Currently, mlxsw only supports decapsulation based on the underlay destination IP (i.e., not taking the GRE key into account), so users need to configure these tunnels with different source IPs and IPv6 addresses are easier to spare than IPv4. Tested using existing ip6gre forwarding selftests. ==================== Link: https://lore.kernel.org/r/cover.1670414573.git.petrm@nvidia.comSigned-off-by:
-
Ido Schimmel authored
Now that Spectrum-1 gained ip6gre support we can move the test out of the Spectrum-2 directory. Signed-off-by:
Ido Schimmel <idosch@nvidia.com> Reviewed-by:
Amit Cohen <amcohen@nvidia.com> Signed-off-by:
Petr Machata <petrm@nvidia.com> Signed-off-by:
-
Ido Schimmel authored
As explained in the previous patch, the existing Spectrum-2 ip6gre implementation can be reused for Spectrum-1. Change the Spectrum-1 ip6gre operations structure to use the common operations. Signed-off-by:
-
Ido Schimmel authored
There are two main differences between Spectrum-1 and newer ASICs in terms of IP-in-IP support: 1. In Spectrum-1, RIFs representing ip6gre tunnels require two entries in the RIF table. 2. In Spectrum-2 and newer ASICs, packets ingress the underlay (during encapsulation) and egress the underlay (during decapsulation) via a special generic loopback RIF. The first difference was handled in previous patches by adding the 'double_rif_entry' field to the Spectrum-1 operations structure of ip6gre RIFs. The second difference is handled during RIF creation, by only creating a generic loopback RIF in Spectrum-2 and newer ASICs. Therefore, the ip6gre operations can be shared between Spectrum-1 and newer ASIC in a similar fashion to how the ipgre operations are shared. Rename the operations to not be Spectrum-2 specific and move them earlier in the file so that they could later be used for Spectrum-1. Signed-off-by:
-
Ido Schimmel authored
In Spectrum-1, loopback router interfaces (RIFs) used for IP-in-IP encapsulation with an IPv6 underlay require two RIF entries and the RIF index must be even. Prepare for this change by extending the RIF parameters structure with a 'double_entry' field that indicates if the RIF being created requires two RIF entries or not. Only set it for RIFs representing ip6gre tunnels in Spectrum-1. Signed-off-by:
-
Ido Schimmel authored
Currently, each router interface (RIF) consumes one entry in the RIFs table. This is going to change in subsequent patches where some RIFs will consume two table entries. Prepare for this change by parametrizing the RIF allocation size. For now, always pass '1'. Signed-off-by:
-
Ido Schimmel authored
Currently, each router interface (RIF) consumes one entry in the RIFs table and there are no alignment constraints. This is going to change in subsequent patches where some RIFs will consume two table entries and their indexes will need to be aligned to the allocation size (even). Prepare for this change by converting the RIF index allocation to use gen_pool with the 'gen_pool_first_fit_order_align' algorithm. No Kconfig changes necessary as mlxsw already selects 'GENERIC_ALLOCATOR'. Signed-off-by:
-
git://git.kernel.org/pub/scm/linux/kernel/git/netdev/netJakub Kicinski authored
No conflicts. Signed-off-by:
-
- 08 Dec, 2022 18 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/netdev/netLinus Torvalds authored
Pull networking fixes from Jakub Kicinski: "Including fixes from bluetooth, can and netfilter. Current release - new code bugs: - bonding: ipv6: correct address used in Neighbour Advertisement parsing (src vs dst typo) - fec: properly scope IRQ coalesce setup during link up to supported chips only Previous releases - regressions: - Bluetooth fixes for fake CSR clones (knockoffs): - re-add ERR_DATA_REPORTING quirk - fix crash when device is replugged - Bluetooth: - silence a user-triggerable dmesg error message - L2CAP: fix u8 overflow, oob access - correct vendor codec definition - fix support for Read Local Supported Codecs V2 - ti: am65-cpsw: fix RGMII configuration at SPEED_10 - mana: fix race on per-CQ variable NAPI work_done Previous releases - always broken: - af_unix: diag: fetch user_ns from in_skb in unix_diag_get_exact(), avoid null-deref - af_can: fix NULL pointer dereference in can_rcv_filter - can: slcan: fix UAF with a freed work - can: can327: flush TX_work on ldisc .close() - macsec: add missing attribute validation for offload - ipv6: avoid use-after-free in ip6_fragment() - nft_set_pipapo: actually validate intervals in fields after the first one - mvneta: prevent oob access in mvneta_config_rss() - ipv4: fix incorrect route flushing when table ID 0 is used, or when source address is deleted - phy: mxl-gpy: add workaround for IRQ bug on GPY215B and GPY215C" * tag 'net-6.1-rc9' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (77 commits) net: dsa: sja1105: avoid out of bounds access in sja1105_init_l2_policing() s390/qeth: fix use-after-free in hsci macsec: add missing attribute validation for offload net: mvneta: Fix an out of bounds check net: thunderbolt: fix memory leak in tbnet_open() ipv6: avoid use-after-free in ip6_fragment() net: plip: don't call kfree_skb/dev_kfree_skb() under spin_lock_irq() net: phy: mxl-gpy: add MDINT workaround net: dsa: mv88e6xxx: accept phy-mode = "internal" for internal PHY ports xen/netback: don't call kfree_skb() under spin_lock_irqsave() dpaa2-switch: Fix memory leak in dpaa2_switch_acl_entry_add() and dpaa2_switch_acl_entry_remove() ethernet: aeroflex: fix potential skb leak in greth_init_rings() tipc: call tipc_lxc_xmit without holding node_read_lock can: esd_usb: Allow REC and TEC to return to zero can: can327: flush TX_work on ldisc .close() can: slcan: fix freed work crash can: af_can: fix NULL pointer dereference in can_rcv_filter net: dsa: sja1105: fix memory leak in sja1105_setup_devlink_regions() ipv4: Fix incorrect route flushing when table ID 0 is used ipv4: Fix incorrect route flushing when source address is deleted ... -
Jakub Kicinski authored
Eric Dumazet says: ==================== mlx4: better BIG-TCP support mlx4 uses a bounce buffer in TX whenever the tx descriptors wrap around the right edge of the ring. Size of this bounce buffer was hard coded and can be increased if/when needed. ==================== Link: https://lore.kernel.org/r/20221207141237.2575012-1-edumazet@google.comSigned-off-by:
-
Eric Dumazet authored
Test against MLX4_MAX_DESC_TXBBS only matters if the TX bounce buffer is going to be used. Signed-off-by:
Eric Dumazet <edumazet@google.com> Cc: Wei Wang <weiwan@google.com> Reviewed-by:
Tariq Toukan <tariqt@nvidia.com> Signed-off-by:
-
Eric Dumazet authored
Google production kernel has increased MAX_SKB_FRAGS to 45 for BIG-TCP rollout. Unfortunately mlx4 TX bounce buffer is not big enough whenever an skb has up to 45 page fragments. This can happen often with TCP TX zero copy, as one frag usually holds 4096 bytes of payload (order-0 page). Tested: Kernel built with MAX_SKB_FRAGS=45 ip link set dev eth0 gso_max_size 185000 netperf -t TCP_SENDFILE I made sure that "ethtool -G eth0 tx 64" was properly working, ring->full_size being set to 15. Signed-off-by:
Wei Wang <weiwan@google.com> Reviewed-by:
-
Eric Dumazet authored
MAX_DESC_SIZE is really the size of the bounce buffer used when reaching the right side of TX ring buffer. MAX_DESC_TXBBS get a MLX4_ prefix. Signed-off-by:
-
Jakub Kicinski authored
Saeed Mahameed says: ==================== Support tc police jump conform-exceed attribute The tc police action conform-exceed option defines how to handle packets which exceed or conform to the configured bandwidth limit. One of the possible conform-exceed values is jump, which skips over a specified number of actions. This series adds support for conform-exceed jump action. The series adds platform support for branching actions by providing true/false flow attributes to the branching action. This is necessary for supporting police jump, as each branch may execute a different action list. The first five patches are preparation patches: - Patches 1 and 2 add support for actions with no destinations (e.g. drop) - Patch 3 refactor the code for subsequent function reuse - Patch 4 defines an abstract way for identifying terminating actions - Patch 5 updates action list validations logic considering branching actions The following three patches introduce an interface for abstracting branching actions: - Patch 6 introduces an abstract api for defining branching actions - Patch 7 generically instantiates the branching flow attributes using the abstract API Patch 8 adds the platform support for jump actions, by executing the following sequence: a. Store the jumping flow attr b. Identify the jump target action while iterating the actions list. c. Instantiate a new flow attribute after the jump target action. This is the flow attribute that the branching action should jump to. d. Set the target post action id on: d.1. The jumping attribute, thus realizing the jump functionality. d.2. The attribute preceding the target jump attr, if not terminating. The next patches apply the platform's branching attributes to the police action: - Patch 9 is a refactor patch - Patch 10 initializes the post meter table with the red/green flow attributes, as were initialized by the platform - Patch 11 enables the offload of meter actions using jump conform-exceed value. ==================== Link: https://lore.kernel.org/all/20221203221337.29267-1-saeed@kernel.org/Signed-off-by: -
Oz Shlomo authored
Separate the matchall police action validation from flower validation. Isolate the action validation logic in the police action parser. Signed-off-by:
Oz Shlomo <ozsh@nvidia.com> Reviewed-by:
Roi Dayan <roid@nvidia.com> Signed-off-by:
Saeed Mahameed <saeedm@nvidia.com> Link: https://lore.kernel.org/r/20221203221337.29267-12-saeed@kernel.orgSigned-off-by:
-
Oz Shlomo authored
Instantiate the post meter actions with the platform initialized branching action attributes. Signed-off-by:
-
Oz Shlomo authored
Currently post meter supports only the pipe/drop conform-exceed policy. This assumption is reflected in several variable names. Rename the following variables as a pre-step for using the generalized branching action platform. Rename fwd_green_rule/drop_red_rule to green_rule/red_rule respectively. Repurpose red_counter/green_counter to act_counter/drop_counter to allow police conform-exceed configurations that do not drop. Signed-off-by:
-
Oz Shlomo authored
Identify the jump target action when iterating the action list. Initialize the jump target attr with the jumping attribute during the parsing phase. Initialize the jumping attr post action with the target during the offload phase. Signed-off-by:
-
Oz Shlomo authored
Initialize flow attribute for drop, accept, pipe and jump branching actions. Instantiate a flow attribute instance according to the specified branch control action. Store the branching attributes on the branching action flow attribute during the parsing phase. Then, during the offload phase, allocate the relevant mod header objects to the branching actions. Signed-off-by:
-
Oz Shlomo authored
Extend the act tc api to set the branch control params aligning with the police conform/exceed use case. Signed-off-by:
-
Oz Shlomo authored
Currently the entire flow action list is validate for offload limitations. For example, flow with both forward and drop actions are declared invalid due to hardware restrictions. However, a multi-table hardware model changes the limitations from a flow scope to a single flow attribute scope. Apply offload limitations to flow attributes instead of the entire flow. Signed-off-by:
-
Oz Shlomo authored
Extend act api to identify actions that terminate action list. Pre-step for terminating branching actions. Signed-off-by:
-
Oz Shlomo authored
After the tc action parsing phase the flow attribute is initialized with relevant eswitch offload objects such as tunnel, vlan, header modify and counter attributes. The post processing is done both for fdb and post-action attributes. Reuse the flow attribute post parsing logic by both fdb and post-action offloads. Signed-off-by:
-
Oz Shlomo authored
Currently create_flow_handle() assumes a null dest pointer when there are no destinations. This might not be the case as the caller may pass an allocated dest array while setting the dest_num parameter to 0. Assert null dest array for flow rules that have no destinations (e.g. drop rule). Signed-off-by:
Mark Bloch <mbloch@nvidia.com> Signed-off-by:
-
Oz Shlomo authored
Rules with drop action are not required to have a destination. Currently the destination list is allocated with the maximum number of destinations and passed to the fs_core layer along with the actual number of destinations. Remove redundant passing of dest pointer when count of dest is 0. Signed-off-by:
-
git://git.kernel.org/pub/scm/linux/kernel/git/hid/hidLinus Torvalds authored
Pull HID fixes from Jiri Kosina: "A regression fix for handling Logitech HID++ devices and memory corruption fixes: - regression fix (revert) for catch-all handling of Logitech HID++ Bluetooth devices; there are devices that turn out not to work with this, and the root cause is yet to be properly understood. So we are dropping it for now, and it will be revisited for 6.2 or 6.3 (Benjamin Tissoires) - memory corruption fix in HID core (ZhangPeng) - memory corruption fix in hid-lg4ff (Anastasia Belova) - Kconfig fix for I2C_HID (Benjamin Tissoires) - a few device-id specific quirks that piggy-back on top of the important fixes above" * tag 'for-linus-2022120801' of git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid: Revert "HID: logitech-hidpp: Enable HID++ for all the Logitech Bluetooth devices" Revert "HID: logitech-hidpp: Remove special-casing of Bluetooth devices" HID: usbhid: Add ALWAYS_POLL quirk for some mice HID: core: fix shift-out-of-bounds in hid_report_raw_event HID: uclogic: Add HID_QUIRK_HIDINPUT_FORCE quirk HID: fix I2C_HID not selected when I2C_HID_OF_ELAN is HID: hid-lg4ff: Add check for empty lbuf HID: ite: Enable QUIRK_TOUCHPAD_ON_OFF_REPORT on Acer Aspire Switch V 10 HID: uclogic: Fix frame templates for big endian architectures
-
