aboutsummaryrefslogtreecommitdiff
path: root/net/kcm/kcmproc.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /net/kcm/kcmproc.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to '')
-rw-r--r--net/kcm/kcmproc.c387
1 files changed, 387 insertions, 0 deletions
diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c
new file mode 100644
index 000000000..25c1007f1
--- /dev/null
+++ b/net/kcm/kcmproc.c
@@ -0,0 +1,387 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/in.h>
+#include <linux/inet.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/proc_fs.h>
+#include <linux/rculist.h>
+#include <linux/seq_file.h>
+#include <linux/socket.h>
+#include <net/inet_sock.h>
+#include <net/kcm.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/tcp.h>
+
+#ifdef CONFIG_PROC_FS
+static struct kcm_mux *kcm_get_first(struct seq_file *seq)
+{
+ struct net *net = seq_file_net(seq);
+ struct kcm_net *knet = net_generic(net, kcm_net_id);
+
+ return list_first_or_null_rcu(&knet->mux_list,
+ struct kcm_mux, kcm_mux_list);
+}
+
+static struct kcm_mux *kcm_get_next(struct kcm_mux *mux)
+{
+ struct kcm_net *knet = mux->knet;
+
+ return list_next_or_null_rcu(&knet->mux_list, &mux->kcm_mux_list,
+ struct kcm_mux, kcm_mux_list);
+}
+
+static struct kcm_mux *kcm_get_idx(struct seq_file *seq, loff_t pos)
+{
+ struct net *net = seq_file_net(seq);
+ struct kcm_net *knet = net_generic(net, kcm_net_id);
+ struct kcm_mux *m;
+
+ list_for_each_entry_rcu(m, &knet->mux_list, kcm_mux_list) {
+ if (!pos)
+ return m;
+ --pos;
+ }
+ return NULL;
+}
+
+static void *kcm_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ void *p;
+
+ if (v == SEQ_START_TOKEN)
+ p = kcm_get_first(seq);
+ else
+ p = kcm_get_next(v);
+ ++*pos;
+ return p;
+}
+
+static void *kcm_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(rcu)
+{
+ rcu_read_lock();
+
+ if (!*pos)
+ return SEQ_START_TOKEN;
+ else
+ return kcm_get_idx(seq, *pos - 1);
+}
+
+static void kcm_seq_stop(struct seq_file *seq, void *v)
+ __releases(rcu)
+{
+ rcu_read_unlock();
+}
+
+struct kcm_proc_mux_state {
+ struct seq_net_private p;
+ int idx;
+};
+
+static void kcm_format_mux_header(struct seq_file *seq)
+{
+ struct net *net = seq_file_net(seq);
+ struct kcm_net *knet = net_generic(net, kcm_net_id);
+
+ seq_printf(seq,
+ "*** KCM statistics (%d MUX) ****\n",
+ knet->count);
+
+ seq_printf(seq,
+ "%-14s %-10s %-16s %-10s %-16s %-8s %-8s %-8s %-8s %s",
+ "Object",
+ "RX-Msgs",
+ "RX-Bytes",
+ "TX-Msgs",
+ "TX-Bytes",
+ "Recv-Q",
+ "Rmem",
+ "Send-Q",
+ "Smem",
+ "Status");
+
+ /* XXX: pdsts header stuff here */
+ seq_puts(seq, "\n");
+}
+
+static void kcm_format_sock(struct kcm_sock *kcm, struct seq_file *seq,
+ int i, int *len)
+{
+ seq_printf(seq,
+ " kcm-%-7u %-10llu %-16llu %-10llu %-16llu %-8d %-8d %-8d %-8s ",
+ kcm->index,
+ kcm->stats.rx_msgs,
+ kcm->stats.rx_bytes,
+ kcm->stats.tx_msgs,
+ kcm->stats.tx_bytes,
+ kcm->sk.sk_receive_queue.qlen,
+ sk_rmem_alloc_get(&kcm->sk),
+ kcm->sk.sk_write_queue.qlen,
+ "-");
+
+ if (kcm->tx_psock)
+ seq_printf(seq, "Psck-%u ", kcm->tx_psock->index);
+
+ if (kcm->tx_wait)
+ seq_puts(seq, "TxWait ");
+
+ if (kcm->tx_wait_more)
+ seq_puts(seq, "WMore ");
+
+ if (kcm->rx_wait)
+ seq_puts(seq, "RxWait ");
+
+ seq_puts(seq, "\n");
+}
+
+static void kcm_format_psock(struct kcm_psock *psock, struct seq_file *seq,
+ int i, int *len)
+{
+ seq_printf(seq,
+ " psock-%-5u %-10llu %-16llu %-10llu %-16llu %-8d %-8d %-8d %-8d ",
+ psock->index,
+ psock->strp.stats.msgs,
+ psock->strp.stats.bytes,
+ psock->stats.tx_msgs,
+ psock->stats.tx_bytes,
+ psock->sk->sk_receive_queue.qlen,
+ atomic_read(&psock->sk->sk_rmem_alloc),
+ psock->sk->sk_write_queue.qlen,
+ refcount_read(&psock->sk->sk_wmem_alloc));
+
+ if (psock->done)
+ seq_puts(seq, "Done ");
+
+ if (psock->tx_stopped)
+ seq_puts(seq, "TxStop ");
+
+ if (psock->strp.stopped)
+ seq_puts(seq, "RxStop ");
+
+ if (psock->tx_kcm)
+ seq_printf(seq, "Rsvd-%d ", psock->tx_kcm->index);
+
+ if (!psock->strp.paused && !psock->ready_rx_msg) {
+ if (psock->sk->sk_receive_queue.qlen) {
+ if (psock->strp.need_bytes)
+ seq_printf(seq, "RxWait=%u ",
+ psock->strp.need_bytes);
+ else
+ seq_printf(seq, "RxWait ");
+ }
+ } else {
+ if (psock->strp.paused)
+ seq_puts(seq, "RxPause ");
+
+ if (psock->ready_rx_msg)
+ seq_puts(seq, "RdyRx ");
+ }
+
+ seq_puts(seq, "\n");
+}
+
+static void
+kcm_format_mux(struct kcm_mux *mux, loff_t idx, struct seq_file *seq)
+{
+ int i, len;
+ struct kcm_sock *kcm;
+ struct kcm_psock *psock;
+
+ /* mux information */
+ seq_printf(seq,
+ "%-6s%-8s %-10llu %-16llu %-10llu %-16llu %-8s %-8s %-8s %-8s ",
+ "mux", "",
+ mux->stats.rx_msgs,
+ mux->stats.rx_bytes,
+ mux->stats.tx_msgs,
+ mux->stats.tx_bytes,
+ "-", "-", "-", "-");
+
+ seq_printf(seq, "KCMs: %d, Psocks %d\n",
+ mux->kcm_socks_cnt, mux->psocks_cnt);
+
+ /* kcm sock information */
+ i = 0;
+ spin_lock_bh(&mux->lock);
+ list_for_each_entry(kcm, &mux->kcm_socks, kcm_sock_list) {
+ kcm_format_sock(kcm, seq, i, &len);
+ i++;
+ }
+ i = 0;
+ list_for_each_entry(psock, &mux->psocks, psock_list) {
+ kcm_format_psock(psock, seq, i, &len);
+ i++;
+ }
+ spin_unlock_bh(&mux->lock);
+}
+
+static int kcm_seq_show(struct seq_file *seq, void *v)
+{
+ struct kcm_proc_mux_state *mux_state;
+
+ mux_state = seq->private;
+ if (v == SEQ_START_TOKEN) {
+ mux_state->idx = 0;
+ kcm_format_mux_header(seq);
+ } else {
+ kcm_format_mux(v, mux_state->idx, seq);
+ mux_state->idx++;
+ }
+ return 0;
+}
+
+static const struct seq_operations kcm_seq_ops = {
+ .show = kcm_seq_show,
+ .start = kcm_seq_start,
+ .next = kcm_seq_next,
+ .stop = kcm_seq_stop,
+};
+
+static int kcm_stats_seq_show(struct seq_file *seq, void *v)
+{
+ struct kcm_psock_stats psock_stats;
+ struct kcm_mux_stats mux_stats;
+ struct strp_aggr_stats strp_stats;
+ struct kcm_mux *mux;
+ struct kcm_psock *psock;
+ struct net *net = seq->private;
+ struct kcm_net *knet = net_generic(net, kcm_net_id);
+
+ memset(&mux_stats, 0, sizeof(mux_stats));
+ memset(&psock_stats, 0, sizeof(psock_stats));
+ memset(&strp_stats, 0, sizeof(strp_stats));
+
+ mutex_lock(&knet->mutex);
+
+ aggregate_mux_stats(&knet->aggregate_mux_stats, &mux_stats);
+ aggregate_psock_stats(&knet->aggregate_psock_stats,
+ &psock_stats);
+ aggregate_strp_stats(&knet->aggregate_strp_stats,
+ &strp_stats);
+
+ list_for_each_entry(mux, &knet->mux_list, kcm_mux_list) {
+ spin_lock_bh(&mux->lock);
+ aggregate_mux_stats(&mux->stats, &mux_stats);
+ aggregate_psock_stats(&mux->aggregate_psock_stats,
+ &psock_stats);
+ aggregate_strp_stats(&mux->aggregate_strp_stats,
+ &strp_stats);
+ list_for_each_entry(psock, &mux->psocks, psock_list) {
+ aggregate_psock_stats(&psock->stats, &psock_stats);
+ save_strp_stats(&psock->strp, &strp_stats);
+ }
+
+ spin_unlock_bh(&mux->lock);
+ }
+
+ mutex_unlock(&knet->mutex);
+
+ seq_printf(seq,
+ "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s\n",
+ "MUX",
+ "RX-Msgs",
+ "RX-Bytes",
+ "TX-Msgs",
+ "TX-Bytes",
+ "TX-Retries",
+ "Attach",
+ "Unattach",
+ "UnattchRsvd",
+ "RX-RdyDrops");
+
+ seq_printf(seq,
+ "%-8s %-10llu %-16llu %-10llu %-16llu %-10u %-10u %-10u %-10u %-10u\n",
+ "",
+ mux_stats.rx_msgs,
+ mux_stats.rx_bytes,
+ mux_stats.tx_msgs,
+ mux_stats.tx_bytes,
+ mux_stats.tx_retries,
+ mux_stats.psock_attach,
+ mux_stats.psock_unattach_rsvd,
+ mux_stats.psock_unattach,
+ mux_stats.rx_ready_drops);
+
+ seq_printf(seq,
+ "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s\n",
+ "Psock",
+ "RX-Msgs",
+ "RX-Bytes",
+ "TX-Msgs",
+ "TX-Bytes",
+ "Reserved",
+ "Unreserved",
+ "RX-Aborts",
+ "RX-Intr",
+ "RX-Unrecov",
+ "RX-MemFail",
+ "RX-NeedMor",
+ "RX-BadLen",
+ "RX-TooBig",
+ "RX-Timeout",
+ "TX-Aborts");
+
+ seq_printf(seq,
+ "%-8s %-10llu %-16llu %-10llu %-16llu %-10llu %-10llu %-10u %-10u %-10u %-10u %-10u %-10u %-10u %-10u %-10u\n",
+ "",
+ strp_stats.msgs,
+ strp_stats.bytes,
+ psock_stats.tx_msgs,
+ psock_stats.tx_bytes,
+ psock_stats.reserved,
+ psock_stats.unreserved,
+ strp_stats.aborts,
+ strp_stats.interrupted,
+ strp_stats.unrecov_intr,
+ strp_stats.mem_fail,
+ strp_stats.need_more_hdr,
+ strp_stats.bad_hdr_len,
+ strp_stats.msg_too_big,
+ strp_stats.msg_timeouts,
+ psock_stats.tx_aborts);
+
+ return 0;
+}
+
+static int kcm_proc_init_net(struct net *net)
+{
+ if (!proc_create_net_single("kcm_stats", 0444, net->proc_net,
+ kcm_stats_seq_show, NULL))
+ goto out_kcm_stats;
+
+ if (!proc_create_net("kcm", 0444, net->proc_net, &kcm_seq_ops,
+ sizeof(struct kcm_proc_mux_state)))
+ goto out_kcm;
+
+ return 0;
+
+out_kcm:
+ remove_proc_entry("kcm_stats", net->proc_net);
+out_kcm_stats:
+ return -ENOMEM;
+}
+
+static void kcm_proc_exit_net(struct net *net)
+{
+ remove_proc_entry("kcm", net->proc_net);
+ remove_proc_entry("kcm_stats", net->proc_net);
+}
+
+static struct pernet_operations kcm_net_ops = {
+ .init = kcm_proc_init_net,
+ .exit = kcm_proc_exit_net,
+};
+
+int __init kcm_proc_init(void)
+{
+ return register_pernet_subsys(&kcm_net_ops);
+}
+
+void __exit kcm_proc_exit(void)
+{
+ unregister_pernet_subsys(&kcm_net_ops);
+}
+
+#endif /* CONFIG_PROC_FS */