- 07 Aug, 2023 13 commits
-
-
Maher Sanalla authored
For better code readability in the completion IRQ request code, define the cpu lookup per completion vector logic in a separate function. The new method mlx5_cpumask_default_spread() given a vector index 'n' will return the 'nth' cpu. This new method will be used also in the next patch. Signed-off-by:
Maher Sanalla <msanalla@nvidia.com> Reviewed-by:
Shay Drory <shayd@nvidia.com> Reviewed-by:
Moshe Shemesh <moshe@nvidia.com> Signed-off-by:
Saeed Mahameed <saeedm@nvidia.com>
-
Maher Sanalla authored
Currently, create_comp_eqs() function handles the creation of all completion EQs for all the vectors on driver load. While on driver unload, destroy_comp_eqs() performs the equivalent job. In preparation for dynamic EQ creation, replace create_comp_eqs() / destroy_comp_eqs() with create_comp_eq() / destroy_comp_eq() functions which will receive a vector index and allocate/destroy an EQ for that specific vector. Thus, allowing more flexibility in the management of completion EQs. Signed-off-by:
-
Maher Sanalla authored
Use xarray to store the completion EQs instead of a linked list. The xarray offers more scalability, reduced memory overhead, and facilitates the lookup of a certain EQ given a vector index. Signed-off-by:
-
Maher Sanalla authored
Break the completion IRQ request/release functions into per-vector handlers for both PCI devices and SFs in the EQ layer. On EQ table creation, loop over all vectors and request an IRQ for each one using the new per-vector functions. Perform the symmetrical change when releasing IRQs on EQ table cleanup. Signed-off-by:
-
Maher Sanalla authored
Use xarray to store the completion IRQs instead of a fixed-size allocated array as not all completion IRQs will be requested on driver load, but rather on demand when an EQ is created. The xarray offers more scalability, reduced memory overhead, and provides the ability to dynamically resize the array when needed. Signed-off-by:
-
Maher Sanalla authored
Introduce a per-vector completion IRQ request API that requests a single IRQ for a given vector index instead of multiple IRQs request API. On driver load, loop over all completion vectors and request an IRQ for each one via the newly introduced API. Symmetrically, introduce an IRQ release API per vector. On driver unload, loop over all vectors and release each completion IRQ via the new per-vector API. As IRQ vectors will be requested dynamically later in the patchset, add a cpumask of the bounded CPUs to avoid the possible mapping of two IRQs of the same device to the same cpu. Signed-off-by:
-
Maher Sanalla authored
In preparation to allocate completion EQs, add a counter to track the number of completion EQs currently allocated. Store the maximum number of EQs in max_comp_eqs variable. Signed-off-by:
-
Yue Haibing authored
Commit 6ba5a3c5 ("[UDP]: Make full use of proto.h.udp_hash innovation.") removed these implementations but leave declarations. Signed-off-by:
Yue Haibing <yuehaibing@huawei.com> Reviewed-by:
Willem de Bruijn <willemb@google.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Yue Haibing authored
Commit ce0aa27f ("sfp: add sfp-bus to bridge between network devices and sfp cages") declared but never implemented it. Signed-off-by:
-
Yue Haibing authored
Commit f8572d8f ("sysctl net: Remove unused binary sysctl code") left behind this declaration. Signed-off-by:
David Ahern <dsahern@kernel.org> Signed-off-by:
-
Yue Haibing authored
Commit acb67442 ("net: sched: introduce per-block callbacks") implemented these but never used it. Signed-off-by:
-
Yue Haibing authored
pneigh_for_each() is never implemented since the beginning of git history. Signed-off-by:
-
Yue Haibing authored
Commit 3c4d7559 ("tls: kernel TLS support") declared but never implemented these functions. Signed-off-by:
-
- 06 Aug, 2023 16 commits
-
-
Vladimir Oltean authored
Setting dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS is only legal for drivers which were converted to ndo_hwtstamp_get() and ndo_hwtstamp_set(), and it is only there that we call ndo_hwtstamp_set() for a request that otherwise goes to phylib (for stuff like packet traps, which need to be undone if phylib failed, hence the old_cfg logic). The problem is that we end up calling ndo_hwtstamp_get() when we don't need to (even if the SIOCSHWTSTAMP wasn't intended for phylib, or if it was, but the driver didn't set IFF_SEE_ALL_HWTSTAMP_REQUESTS). For those unnecessary conditions, we share a code path with virtual drivers (vlan, macvlan, bonding) where ndo_hwtstamp_get() is implemented as generic_hwtstamp_get_lower(), and may be resolved through generic_hwtstamp_ioctl_lower() if the lower device is unconverted. I.e. this situation: $ ip link add link eno0 name eno0.100 type vlan id 100 $ hwstamp_ctl -i eno0.100 -t 1 We are unprepared to deal with this, because if ndo_hwtstamp_get() is resolved through a legacy ndo_eth_ioctl(SIOCGHWTSTAMP) lower_dev implementation, that needs a non-NULL old_cfg.ifr pointer, and we don't have it. But we don't even need to deal with it either. In the general case, drivers may not even implement SIOCGHWTSTAMP handling, only SIOCSHWTSTAMP, so it makes sense to completely avoid a SIOCGHWTSTAMP call if we can. The solution is to split the single "if" condition into 3 smaller ones, thus separating the decision to call ndo_hwtstamp_get() from the decision to call ndo_hwtstamp_set(). The third "if" condition is identical to the first one, and both are subsets of the second one. Thus, the "cfg" argument of kernel_hwtstamp_config_changed() is always valid. Reported-by:
Eric Dumazet <edumazet@google.com> Closes: https://lore.kernel.org/netdev/CANn89iLOspJsvjPj+y8jikg7erXDomWe8sqHMdfL_2LQSFrPAg@mail.gmail.com/ Fixes: fd770e85 ("net: remove phy_has_hwtstamp() -> phy_mii_ioctl() decision from converted drivers") Signed-off-by:
Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by:
-
Yang Yingliang authored
Use eth_broadcast_addr() to assign broadcast address instead of memset(). Signed-off-by:
Yang Yingliang <yangyingliang@huawei.com> Reviewed-by:
Simon Horman <horms@kernel.org> Signed-off-by:
-
Yu Liao authored
gcc with W=1 reports drivers/net/ethernet/ibm/ibmvnic.c:194:13: warning: variable 'rc' set but not used [-Wunused-but-set-variable] ^ This variable is not used so remove it. Reported-by:kernel test robot <lkp@intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202308040609.zQsSXWXI-lkp@intel.com/Signed-off-by:
Yu Liao <liaoyu15@huawei.com> Reviewed-by:
Nick Child <nnac123@linux.ibm.com> Signed-off-by:
-
Haiyang Zhang authored
Add page pool for RX buffers for faster buffer cycle and reduce CPU usage. The standard page pool API is used. With iperf and 128 threads test, this patch improved the throughput by 12-15%, and decreased the IRQ associated CPU's usage from 99-100% to 10-50%. Signed-off-by:
Haiyang Zhang <haiyangz@microsoft.com> Reviewed-by:
Jesse Brandeburg <jesse.brandeburg@intel.com> Signed-off-by:
-
David S. Miller authored
Rushil Gupta says: ==================== gve: Add QPL mode for DQO descriptor format GVE supports QPL ("queue-page-list") mode where all data is communicated through a set of pre-registered pages. Adding this mode to DQO. ==================== Signed-off-by: -
Rushil Gupta authored
Add a note about QPL and RDA mode Signed-off-by:
Rushil Gupta <rushilg@google.com> Reviewed-by:
Praveen Kaligineedi <pkaligineedi@google.com> Signed-off-by:
Bailey Forrest <bcf@google.com> Signed-off-by:
-
Rushil Gupta authored
The RX path allocates the QPL page pool at queue creation, and tries to reuse these pages through page recycling. This patch ensures that on refill no non-QPL pages are posted to the device. When the driver is running low on free buffers, an ondemand allocation step kicks in that allocates a non-qpl page for SKB business to free up the QPL page in use. gve_try_recycle_buf was moved to gve_rx_append_frags so that driver does not attempt to mark buffer as used if a non-qpl page was allocated ondemand. Signed-off-by:
-
Rushil Gupta authored
Each QPL page is divided into GVE_TX_BUFS_PER_PAGE_DQO buffers. When a packet needs to be transmitted, we break the packet into max GVE_TX_BUF_SIZE_DQO sized chunks and transmit each chunk using a TX descriptor. We allocate the TX buffers from the free list in dqo_tx. We store these TX buffer indices in an array in the pending_packet structure. The TX buffers are returned to the free list in dqo_compl after receiving packet completion or when removing packets from miss completions list. Signed-off-by:
-
Rushil Gupta authored
GVE supports QPL ("queue-page-list") mode where all data is communicated through a set of pre-registered pages. Adding this mode to DQO descriptor format. Add checks, abi-changes and device options to support QPL mode for DQO in addition to GQI. Also, use pages-per-qpl supplied by device-option to control the size of the "queue-page-list". Signed-off-by: -
David S. Miller authored
Eric Dumazet says: ==================== tcp: set few options locklessly This series is avoiding the socket lock for six TCP options. They are not heavily used, but this exercise can give ideas for other parts of TCP/IP stack :) ==================== Signed-off-by: -
Eric Dumazet authored
rskq_defer_accept field can be read/written without the need of holding the socket lock. Signed-off-by:
Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by:
-
Eric Dumazet authored
tp->linger2 can be set locklessly as long as readers use READ_ONCE(). Signed-off-by:
-
Eric Dumazet authored
tp->keepalive_probes can be set locklessly, readers are already taking care of this field being potentially set by other threads. Signed-off-by:
-
Eric Dumazet authored
tp->keepalive_intvl can be set locklessly, readers are already taking care of this field being potentially set by other threads. Signed-off-by:
-
Eric Dumazet authored
icsk->icsk_user_timeout can be set locklessly, if all read sides use READ_ONCE(). Signed-off-by:
-
Eric Dumazet authored
icsk->icsk_syn_retries can safely be set without locking the socket. We have to add READ_ONCE() annotations in tcp_fastopen_synack_timer() and tcp_write_timeout(). Signed-off-by:
-
- 05 Aug, 2023 7 commits
-
-
Jakub Kicinski authored
Merge tag 'wireless-next-2023-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next Kalle Valo says: ==================== wireless-next patches for v6.6 The first pull request for v6.6 and only driver patches this time. Nothing special really standing out, it has been quiet most likely due to vacations. Major changes: rtl8xxxu - enable AP mode for: RTL8192FU, RTL8710BU (RTL8188GU), RTL8192EU and RTL8723BU mwifiex - allow moving to a different namespace mt76 - preparation for mt7925 support - mt7981 support ath12k - Extremely High Throughput (EHT) PHY support for Wi-Fi 7 * tag 'wireless-next-2023-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next: (172 commits) wifi: rtw89: return failure if needed firmware elements are not recognized wifi: rtw89: add to parse firmware elements of BB and RF tables wifi: rtw89: introduce infrastructure of firmware elements wifi: rtw89: add firmware suit for BB MCU 0/1 wifi: rtw89: add firmware parser for v1 format wifi: rtw89: introduce v1 format of firmware header wifi: rtw89: support firmware log with formatted text wifi: rtw89: recognize log format from firmware file wifi: ath12k: avoid deadlock by change ieee80211_queue_work for regd_update_work wifi: ath12k: add handler for scan event WMI_SCAN_EVENT_DEQUEUED wifi: ath12k: relax list iteration in ath12k_mac_vif_unref() wifi: ath12k: configure puncturing bitmap wifi: ath12k: parse WMI service ready ext2 event wifi: ath12k: add MLO header in peer association wifi: ath12k: peer assoc for 320 MHz wifi: ath12k: add WMI support for EHT peer wifi: ath12k: prepare EHT peer assoc parameters wifi: ath12k: add EHT PHY modes wifi: ath12k: propagate EHT capabilities to userspace wifi: ath12k: WMI support to process EHT capabilities ... ==================== Link: https://lore.kernel.org/r/87msz7j942.fsf@kernel.orgSigned-off-by:
Jakub Kicinski <kuba@kernel.org>
-
Jakub Kicinski authored
Kuniyuki Iwashima says: ==================== tcp: Disable header prediction for MD5. The 1st patch disable header prediction for MD5 flow and the 2nd patch updates the stale comment in tcp_parse_options(). ==================== Link: https://lore.kernel.org/r/20230803224552.69398-1-kuniyu@amazon.comSigned-off-by:
-
Kuniyuki Iwashima authored
Since commit 9ea88a15 ("tcp: md5: check md5 signature without socket lock"), the MD5 option is checked in tcp_v[46]_rcv(). Signed-off-by:
Kuniyuki Iwashima <kuniyu@amazon.com> Reviewed-by:
-
Kuniyuki Iwashima authored
TCP socket saves the minimum required header length in tcp_header_len of struct tcp_sock, and later the value is used in __tcp_fast_path_on() to generate a part of TCP header in tcp_sock(sk)->pred_flags. In tcp_rcv_established(), if the incoming packet has the same pattern with pred_flags, we enter the fast path and skip full option parsing. The MD5 option is parsed in tcp_v[46]_rcv(), so we need not parse it again later in tcp_rcv_established() unless other options exist. We add TCPOLEN_MD5SIG_ALIGNED to tcp_header_len in two paths to avoid the slow path. For passive open connections with MD5, we add TCPOLEN_MD5SIG_ALIGNED to tcp_header_len in tcp_create_openreq_child() after 3WHS. On the other hand, we do it in tcp_connect_init() for active open connections. However, the value is overwritten while processing SYN+ACK or crossed SYN in tcp_rcv_synsent_state_process(). These two cases will have the wrong value in pred_flags and never go into the fast path. We could update tcp_header_len in tcp_rcv_synsent_state_process(), but a test with slightly modified netperf which uses MD5 for each flow shows that the slow path is actually a bit faster than the fast path. On c5.4xlarge EC2 instance (16 vCPU, 32 GiB mem) $ for i in {1..10}; do ./super_netperf $(nproc) -H localhost -l 10 -- -m 256 -M 256; done Avg of 10 * 36e68ead : 10.376 Gbps * all fast path : 10.374 Gbps (patch v2, See Link) * all slow path : 10.394 Gbps The header prediction is not worth adding complexity for MD5, so let's disable it for MD5. Link: https://lore.kernel.org/netdev/20230803042214.38309-1-kuniyu@amazon.com/Signed-off-by: -
Russell King (Oracle) authored
Move marking the PHY as being on a SFP module into the SFP code between getting the PHY device (and thus initialising the phy_device structure) and registering the discovered device. This means that PHY drivers can use phy_on_sfp() in their match and get_features methods. Signed-off-by:
Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Link: https://lore.kernel.org/r/E1qRaga-001vKt-8X@rmk-PC.armlinux.org.ukSigned-off-by:
-
Yue Haibing authored
Commit c3d2ed93 ("mlxsw: Remove old parsing depth infrastructure") left behind mlxsw_sp_nve_inc_parsing_depth_get()/mlxsw_sp_nve_inc_parsing_depth_put(). And commit 532b49e4 ("mlxsw: spectrum_span: Derive SBIB from maximum port speed & MTU") remove mlxsw_sp_span_port_mtu_update()/mlxsw_sp_span_speed_update_work() but leave the declarations. Signed-off-by:
Ido Schimmel <idosch@nvidia.com> Link: https://lore.kernel.org/r/20230803142047.42660-1-yuehaibing@huawei.comSigned-off-by:
-
Yue Haibing authored
ixgbe_napi_add_all()/ixgbe_napi_del_all() are declared but never implemented in commit 92915f71 ("ixgbevf: Driver main and ethool interface module and main header") Signed-off-by:
-
- 04 Aug, 2023 4 commits
-
-
Yue Haibing authored
Commit d021c344 ("VSOCK: Introduce VM Sockets") declared but never implemented vsock_release_pending(). Also vsock_init_tap() never implemented since introduction in commit 531b3748 ("VSOCK: Add vsockmon tap functions"). Signed-off-by:
Stefano Garzarella <sgarzare@redhat.com> Link: https://lore.kernel.org/r/20230803134507.22660-1-yuehaibing@huawei.comSigned-off-by:
-
Yue Haibing authored
Commit d8d9ba8d ("net: 802: remove dead leftover after ipx driver removal") remove these implementations but leave the declarations. Signed-off-by:
-
Eric Dumazet authored
After commit 098a697b ("tcp_metrics: Use a single hash table for all network namespaces.") we can avoid calling tcp_net_metrics_init() for each new netns. Instead, rename tcp_net_metrics_init() to tcp_metrics_hash_alloc(), and move it to __init section. Also move tcpmhash_entries to __initdata section. Signed-off-by:
-
Yue Haibing authored
Commit 1e6e7610 ("net: hns3: configure promisc mode for VF asynchronously") left behind hclge_inform_vf_promisc_info() declaration. And commit 68c0a5c7 ("net: hns3: Add HNS3 IMP(Integrated Mgmt Proc) Cmd Interface Support") declared but never implemented hclge_cmd_mdio_write() and hclge_cmd_mdio_read(). Signed-off-by:
-
