diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-08-31 16:43:06 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-08-31 16:43:06 -0700 |
commit | 9e9fb7655ed585da8f468e29221f0ba194a5f613 (patch) | |
tree | d2c51887389b8297635a5b90d5766897f00fe928 /samples/bpf/xdp_monitor_kern.c | |
parent | 86ac54e79fe09b34c52691a780a6e31d12fa57f4 (diff) | |
parent | 29ce8f9701072fc221d9c38ad952de1a9578f95c (diff) |
Merge tag 'net-next-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:
"Core:
- Enable memcg accounting for various networking objects.
BPF:
- Introduce bpf timers.
- Add perf link and opaque bpf_cookie which the program can read out
again, to be used in libbpf-based USDT library.
- Add bpf_task_pt_regs() helper to access user space pt_regs in
kprobes, to help user space stack unwinding.
- Add support for UNIX sockets for BPF sockmap.
- Extend BPF iterator support for UNIX domain sockets.
- Allow BPF TCP congestion control progs and bpf iterators to call
bpf_setsockopt(), e.g. to switch to another congestion control
algorithm.
Protocols:
- Support IOAM Pre-allocated Trace with IPv6.
- Support Management Component Transport Protocol.
- bridge: multicast: add vlan support.
- netfilter: add hooks for the SRv6 lightweight tunnel driver.
- tcp:
- enable mid-stream window clamping (by user space or BPF)
- allow data-less, empty-cookie SYN with TFO_SERVER_COOKIE_NOT_REQD
- more accurate DSACK processing for RACK-TLP
- mptcp:
- add full mesh path manager option
- add partial support for MP_FAIL
- improve use of backup subflows
- optimize option processing
- af_unix: add OOB notification support.
- ipv6: add IFLA_INET6_RA_MTU to expose MTU value advertised by the
router.
- mac80211: Target Wake Time support in AP mode.
- can: j1939: extend UAPI to notify about RX status.
Driver APIs:
- Add page frag support in page pool API.
- Many improvements to the DSA (distributed switch) APIs.
- ethtool: extend IRQ coalesce uAPI with timer reset modes.
- devlink: control which auxiliary devices are created.
- Support CAN PHYs via the generic PHY subsystem.
- Proper cross-chip support for tag_8021q.
- Allow TX forwarding for the software bridge data path to be
offloaded to capable devices.
Drivers:
- veth: more flexible channels number configuration.
- openvswitch: introduce per-cpu upcall dispatch.
- Add internet mix (IMIX) mode to pktgen.
- Transparently handle XDP operations in the bonding driver.
- Add LiteETH network driver.
- Renesas (ravb):
- support Gigabit Ethernet IP
- NXP Ethernet switch (sja1105):
- fast aging support
- support for "H" switch topologies
- traffic termination for ports under VLAN-aware bridge
- Intel 1G Ethernet
- support getcrosststamp() with PCIe PTM (Precision Time
Measurement) for better time sync
- support Credit-Based Shaper (CBS) offload, enabling HW traffic
prioritization and bandwidth reservation
- Broadcom Ethernet (bnxt)
- support pulse-per-second output
- support larger Rx rings
- Mellanox Ethernet (mlx5)
- support ethtool RSS contexts and MQPRIO channel mode
- support LAG offload with bridging
- support devlink rate limit API
- support packet sampling on tunnels
- Huawei Ethernet (hns3):
- basic devlink support
- add extended IRQ coalescing support
- report extended link state
- Netronome Ethernet (nfp):
- add conntrack offload support
- Broadcom WiFi (brcmfmac):
- add WPA3 Personal with FT to supported cipher suites
- support 43752 SDIO device
- Intel WiFi (iwlwifi):
- support scanning hidden 6GHz networks
- support for a new hardware family (Bz)
- Xen pv driver:
- harden netfront against malicious backends
- Qualcomm mobile
- ipa: refactor power management and enable automatic suspend
- mhi: move MBIM to WWAN subsystem interfaces
Refactor:
- Ambient BPF run context and cgroup storage cleanup.
- Compat rework for ndo_ioctl.
Old code removal:
- prism54 remove the obsoleted driver, deprecated by the p54 driver.
- wan: remove sbni/granch driver"
* tag 'net-next-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1715 commits)
net: Add depends on OF_NET for LiteX's LiteETH
ipv6: seg6: remove duplicated include
net: hns3: remove unnecessary spaces
net: hns3: add some required spaces
net: hns3: clean up a type mismatch warning
net: hns3: refine function hns3_set_default_feature()
ipv6: remove duplicated 'net/lwtunnel.h' include
net: w5100: check return value after calling platform_get_resource()
net/mlxbf_gige: Make use of devm_platform_ioremap_resourcexxx()
net: mdio: mscc-miim: Make use of the helper function devm_platform_ioremap_resource()
net: mdio-ipq4019: Make use of devm_platform_ioremap_resource()
fou: remove sparse errors
ipv4: fix endianness issue in inet_rtm_getroute_build_skb()
octeontx2-af: Set proper errorcode for IPv4 checksum errors
octeontx2-af: Fix static code analyzer reported issues
octeontx2-af: Fix mailbox errors in nix_rss_flowkey_cfg
octeontx2-af: Fix loop in free and unmap counter
af_unix: fix potential NULL deref in unix_dgram_connect()
dpaa2-eth: Replace strlcpy with strscpy
octeontx2-af: Use NDC TX for transmit packet data
...
Diffstat (limited to 'samples/bpf/xdp_monitor_kern.c')
-rw-r--r-- | samples/bpf/xdp_monitor_kern.c | 257 |
1 files changed, 0 insertions, 257 deletions
diff --git a/samples/bpf/xdp_monitor_kern.c b/samples/bpf/xdp_monitor_kern.c deleted file mode 100644 index 5c955b812c47..000000000000 --- a/samples/bpf/xdp_monitor_kern.c +++ /dev/null @@ -1,257 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Copyright(c) 2017-2018 Jesper Dangaard Brouer, Red Hat Inc. - * - * XDP monitor tool, based on tracepoints - */ -#include <uapi/linux/bpf.h> -#include <bpf/bpf_helpers.h> - -struct { - __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); - __type(key, u32); - __type(value, u64); - __uint(max_entries, 2); - /* TODO: have entries for all possible errno's */ -} redirect_err_cnt SEC(".maps"); - -#define XDP_UNKNOWN XDP_REDIRECT + 1 -struct { - __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); - __type(key, u32); - __type(value, u64); - __uint(max_entries, XDP_UNKNOWN + 1); -} exception_cnt SEC(".maps"); - -/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_redirect/format - * Code in: kernel/include/trace/events/xdp.h - */ -struct xdp_redirect_ctx { - u64 __pad; // First 8 bytes are not accessible by bpf code - int prog_id; // offset:8; size:4; signed:1; - u32 act; // offset:12 size:4; signed:0; - int ifindex; // offset:16 size:4; signed:1; - int err; // offset:20 size:4; signed:1; - int to_ifindex; // offset:24 size:4; signed:1; - u32 map_id; // offset:28 size:4; signed:0; - int map_index; // offset:32 size:4; signed:1; -}; // offset:36 - -enum { - XDP_REDIRECT_SUCCESS = 0, - XDP_REDIRECT_ERROR = 1 -}; - -static __always_inline -int xdp_redirect_collect_stat(struct xdp_redirect_ctx *ctx) -{ - u32 key = XDP_REDIRECT_ERROR; - int err = ctx->err; - u64 *cnt; - - if (!err) - key = XDP_REDIRECT_SUCCESS; - - cnt = bpf_map_lookup_elem(&redirect_err_cnt, &key); - if (!cnt) - return 1; - *cnt += 1; - - return 0; /* Indicate event was filtered (no further processing)*/ - /* - * Returning 1 here would allow e.g. a perf-record tracepoint - * to see and record these events, but it doesn't work well - * in-practice as stopping perf-record also unload this - * bpf_prog. Plus, there is additional overhead of doing so. - */ -} - -SEC("tracepoint/xdp/xdp_redirect_err") -int trace_xdp_redirect_err(struct xdp_redirect_ctx *ctx) -{ - return xdp_redirect_collect_stat(ctx); -} - - -SEC("tracepoint/xdp/xdp_redirect_map_err") -int trace_xdp_redirect_map_err(struct xdp_redirect_ctx *ctx) -{ - return xdp_redirect_collect_stat(ctx); -} - -/* Likely unloaded when prog starts */ -SEC("tracepoint/xdp/xdp_redirect") -int trace_xdp_redirect(struct xdp_redirect_ctx *ctx) -{ - return xdp_redirect_collect_stat(ctx); -} - -/* Likely unloaded when prog starts */ -SEC("tracepoint/xdp/xdp_redirect_map") -int trace_xdp_redirect_map(struct xdp_redirect_ctx *ctx) -{ - return xdp_redirect_collect_stat(ctx); -} - -/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_exception/format - * Code in: kernel/include/trace/events/xdp.h - */ -struct xdp_exception_ctx { - u64 __pad; // First 8 bytes are not accessible by bpf code - int prog_id; // offset:8; size:4; signed:1; - u32 act; // offset:12; size:4; signed:0; - int ifindex; // offset:16; size:4; signed:1; -}; - -SEC("tracepoint/xdp/xdp_exception") -int trace_xdp_exception(struct xdp_exception_ctx *ctx) -{ - u64 *cnt; - u32 key; - - key = ctx->act; - if (key > XDP_REDIRECT) - key = XDP_UNKNOWN; - - cnt = bpf_map_lookup_elem(&exception_cnt, &key); - if (!cnt) - return 1; - *cnt += 1; - - return 0; -} - -/* Common stats data record shared with _user.c */ -struct datarec { - u64 processed; - u64 dropped; - u64 info; - u64 err; -}; -#define MAX_CPUS 64 - -struct { - __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); - __type(key, u32); - __type(value, struct datarec); - __uint(max_entries, MAX_CPUS); -} cpumap_enqueue_cnt SEC(".maps"); - -struct { - __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); - __type(key, u32); - __type(value, struct datarec); - __uint(max_entries, 1); -} cpumap_kthread_cnt SEC(".maps"); - -/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_enqueue/format - * Code in: kernel/include/trace/events/xdp.h - */ -struct cpumap_enqueue_ctx { - u64 __pad; // First 8 bytes are not accessible by bpf code - int map_id; // offset:8; size:4; signed:1; - u32 act; // offset:12; size:4; signed:0; - int cpu; // offset:16; size:4; signed:1; - unsigned int drops; // offset:20; size:4; signed:0; - unsigned int processed; // offset:24; size:4; signed:0; - int to_cpu; // offset:28; size:4; signed:1; -}; - -SEC("tracepoint/xdp/xdp_cpumap_enqueue") -int trace_xdp_cpumap_enqueue(struct cpumap_enqueue_ctx *ctx) -{ - u32 to_cpu = ctx->to_cpu; - struct datarec *rec; - - if (to_cpu >= MAX_CPUS) - return 1; - - rec = bpf_map_lookup_elem(&cpumap_enqueue_cnt, &to_cpu); - if (!rec) - return 0; - rec->processed += ctx->processed; - rec->dropped += ctx->drops; - - /* Record bulk events, then userspace can calc average bulk size */ - if (ctx->processed > 0) - rec->info += 1; - - return 0; -} - -/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_kthread/format - * Code in: kernel/include/trace/events/xdp.h - */ -struct cpumap_kthread_ctx { - u64 __pad; // First 8 bytes are not accessible by bpf code - int map_id; // offset:8; size:4; signed:1; - u32 act; // offset:12; size:4; signed:0; - int cpu; // offset:16; size:4; signed:1; - unsigned int drops; // offset:20; size:4; signed:0; - unsigned int processed; // offset:24; size:4; signed:0; - int sched; // offset:28; size:4; signed:1; -}; - -SEC("tracepoint/xdp/xdp_cpumap_kthread") -int trace_xdp_cpumap_kthread(struct cpumap_kthread_ctx *ctx) -{ - struct datarec *rec; - u32 key = 0; - - rec = bpf_map_lookup_elem(&cpumap_kthread_cnt, &key); - if (!rec) - return 0; - rec->processed += ctx->processed; - rec->dropped += ctx->drops; - - /* Count times kthread yielded CPU via schedule call */ - if (ctx->sched) - rec->info++; - - return 0; -} - -struct { - __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); - __type(key, u32); - __type(value, struct datarec); - __uint(max_entries, 1); -} devmap_xmit_cnt SEC(".maps"); - -/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_devmap_xmit/format - * Code in: kernel/include/trace/events/xdp.h - */ -struct devmap_xmit_ctx { - u64 __pad; // First 8 bytes are not accessible by bpf code - int from_ifindex; // offset:8; size:4; signed:1; - u32 act; // offset:12; size:4; signed:0; - int to_ifindex; // offset:16; size:4; signed:1; - int drops; // offset:20; size:4; signed:1; - int sent; // offset:24; size:4; signed:1; - int err; // offset:28; size:4; signed:1; -}; - -SEC("tracepoint/xdp/xdp_devmap_xmit") -int trace_xdp_devmap_xmit(struct devmap_xmit_ctx *ctx) -{ - struct datarec *rec; - u32 key = 0; - - rec = bpf_map_lookup_elem(&devmap_xmit_cnt, &key); - if (!rec) - return 0; - rec->processed += ctx->sent; - rec->dropped += ctx->drops; - - /* Record bulk events, then userspace can calc average bulk size */ - rec->info += 1; - - /* Record error cases, where no frame were sent */ - if (ctx->err) - rec->err++; - - /* Catch API error of drv ndo_xdp_xmit sent more than count */ - if (ctx->drops < 0) - rec->err++; - - return 1; -} |