kybaaz/linux-xiaomi-chiron
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

networking changes for the 5.10 merge window

Browse source 
Add redirect_neigh() BPF packet redirect helper, allowing to limit stack
 traversal in common container configs and improving TCP back-pressure.
 Daniel reports ~10Gbps => ~15Gbps single stream TCP performance gain.
 
 Expand netlink policy support and improve policy export to user space.
 (Ge)netlink core performs request validation according to declared
 policies. Expand the expressiveness of those policies (min/max length
 and bitmasks). Allow dumping policies for particular commands.
 This is used for feature discovery by user space (instead of kernel
 version parsing or trial and error).
 
 Support IGMPv3/MLDv2 multicast listener discovery protocols in bridge.
 
 Allow more than 255 IPv4 multicast interfaces.
 
 Add support for Type of Service (ToS) reflection in SYN/SYN-ACK
 packets of TCPv6.
 
 In Multi-patch TCP (MPTCP) support concurrent transmission of data
 on multiple subflows in a load balancing scenario. Enhance advertising
 addresses via the RM_ADDR/ADD_ADDR options.
 
 Support SMC-Dv2 version of SMC, which enables multi-subnet deployments.
 
 Allow more calls to same peer in RxRPC.
 
 Support two new Controller Area Network (CAN) protocols -
 CAN-FD and ISO 15765-2:2016.
 
 Add xfrm/IPsec compat layer, solving the 32bit user space on 64bit
 kernel problem.
 
 Add TC actions for implementing MPLS L2 VPNs.
 
 Improve nexthop code - e.g. handle various corner cases when nexthop
 objects are removed from groups better, skip unnecessary notifications
 and make it easier to offload nexthops into HW by converting
 to a blocking notifier.
 
 Support adding and consuming TCP header options by BPF programs,
 opening the doors for easy experimental and deployment-specific
 TCP option use.
 
 Reorganize TCP congestion control (CC) initialization to simplify life
 of TCP CC implemented in BPF.
 
 Add support for shipping BPF programs with the kernel and loading them
 early on boot via the User Mode Driver mechanism, hence reusing all the
 user space infra we have.
 
 Support sleepable BPF programs, initially targeting LSM and tracing.
 
 Add bpf_d_path() helper for returning full path for given 'struct path'.
 
 Make bpf_tail_call compatible with bpf-to-bpf calls.
 
 Allow BPF programs to call map_update_elem on sockmaps.
 
 Add BPF Type Format (BTF) support for type and enum discovery, as
 well as support for using BTF within the kernel itself (current use
 is for pretty printing structures).
 
 Support listing and getting information about bpf_links via the bpf
 syscall.
 
 Enhance kernel interfaces around NIC firmware update. Allow specifying
 overwrite mask to control if settings etc. are reset during update;
 report expected max time operation may take to users; support firmware
 activation without machine reboot incl. limits of how much impact
 reset may have (e.g. dropping link or not).
 
 Extend ethtool configuration interface to report IEEE-standard
 counters, to limit the need for per-vendor logic in user space.
 
 Adopt or extend devlink use for debug, monitoring, fw update
 in many drivers (dsa loop, ice, ionic, sja1105, qed, mlxsw,
 mv88e6xxx, dpaa2-eth).
 
 In mlxsw expose critical and emergency SFP module temperature alarms.
 Refactor port buffer handling to make the defaults more suitable and
 support setting these values explicitly via the DCBNL interface.
 
 Add XDP support for Intel's igb driver.
 
 Support offloading TC flower classification and filtering rules to
 mscc_ocelot switches.
 
 Add PTP support for Marvell Octeontx2 and PP2.2 hardware, as well as
 fixed interval period pulse generator and one-step timestamping in
 dpaa-eth.
 
 Add support for various auth offloads in WiFi APs, e.g. SAE (WPA3)
 offload.
 
 Add Lynx PHY/PCS MDIO module, and convert various drivers which have
 this HW to use it. Convert mvpp2 to split PCS.
 
 Support Marvell Prestera 98DX3255 24-port switch ASICs, as well as
 7-port Mediatek MT7531 IP.
 
 Add initial support for QCA6390 and IPQ6018 in ath11k WiFi driver,
 and wcn3680 support in wcn36xx.
 
 Improve performance for packets which don't require much offloads
 on recent Mellanox NICs by 20% by making multiple packets share
 a descriptor entry.
 
 Move chelsio inline crypto drivers (for TLS and IPsec) from the crypto
 subtree to drivers/net. Move MDIO drivers out of the phy directory.
 
 Clean up a lot of W=1 warnings, reportedly the actively developed
 subsections of networking drivers should now build W=1 warning free.
 
 Make sure drivers don't use in_interrupt() to dynamically adapt their
 code. Convert tasklets to use new tasklet_setup API (sadly this
 conversion is not yet complete).
 
 Signed-off-by: Jakub Kicinski <kuba@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEE6jPA+I1ugmIBA4hXMUZtbf5SIrsFAl+ItRwACgkQMUZtbf5S
 IrtTMg//UxpdR/MirT1DatBU0K/UGAZY82hV7F/UC8tPgjfHZeHvWlDFxfi3YP81
 PtPKbhRZ7DhwBXefUp6nY3UdvjftrJK2lJm8prJUPSsZRye8Wlcb7y65q7/P2y2U
 Efucyopg6RUrmrM0DUsIGYGJgylQLHnMYUl/keCsD4t5Bp4ksyi9R2t5eitGoWzh
 r3QGdbSa0AuWx4iu0i+tqp6Tj0ekMBMXLVb35dtU1t0joj2KTNEnSgABN3prOa8E
 iWYf2erOau68Ogp3yU3miCy0ZU4p/7qGHTtzbcp677692P/ekak6+zmfHLT9/Pjy
 2Stq2z6GoKuVxdktr91D9pA3jxG4LxSJmr0TImcGnXbvkMP3Ez3g9RrpV5fn8j6F
 mZCH8TKZAoD5aJrAJAMkhZmLYE1pvDa7KolSk8WogXrbCnTEb5Nv8FHTS1Qnk3yl
 wSKXuvutFVNLMEHCnWQLtODbTST9DI/aOi6EctPpuOA/ZyL1v3pl+gfp37S+LUTe
 owMnT/7TdvKaTD0+gIyU53M6rAWTtr5YyRQorX9awIu/4Ha0F0gYD7BJZQUGtegp
 HzKt59NiSrFdbSH7UdyemdBF4LuCgIhS7rgfeoUXMXmuPHq7eHXyHZt5dzPPa/xP
 81P0MAvdpFVwg8ij2yp2sHS7sISIRKq17fd1tIewUabxQbjXqPc=
 =bc1U
 -----END PGP SIGNATURE-----

Merge tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:

 - Add redirect_neigh() BPF packet redirect helper, allowing to limit
   stack traversal in common container configs and improving TCP
   back-pressure.

   Daniel reports ~10Gbps => ~15Gbps single stream TCP performance gain.

 - Expand netlink policy support and improve policy export to user
   space. (Ge)netlink core performs request validation according to
   declared policies. Expand the expressiveness of those policies
   (min/max length and bitmasks). Allow dumping policies for particular
   commands. This is used for feature discovery by user space (instead
   of kernel version parsing or trial and error).

 - Support IGMPv3/MLDv2 multicast listener discovery protocols in
   bridge.

 - Allow more than 255 IPv4 multicast interfaces.

 - Add support for Type of Service (ToS) reflection in SYN/SYN-ACK
   packets of TCPv6.

 - In Multi-patch TCP (MPTCP) support concurrent transmission of data on
   multiple subflows in a load balancing scenario. Enhance advertising
   addresses via the RM_ADDR/ADD_ADDR options.

 - Support SMC-Dv2 version of SMC, which enables multi-subnet
   deployments.

 - Allow more calls to same peer in RxRPC.

 - Support two new Controller Area Network (CAN) protocols - CAN-FD and
   ISO 15765-2:2016.

 - Add xfrm/IPsec compat layer, solving the 32bit user space on 64bit
   kernel problem.

 - Add TC actions for implementing MPLS L2 VPNs.

 - Improve nexthop code - e.g. handle various corner cases when nexthop
   objects are removed from groups better, skip unnecessary
   notifications and make it easier to offload nexthops into HW by
   converting to a blocking notifier.

 - Support adding and consuming TCP header options by BPF programs,
   opening the doors for easy experimental and deployment-specific TCP
   option use.

 - Reorganize TCP congestion control (CC) initialization to simplify
   life of TCP CC implemented in BPF.

 - Add support for shipping BPF programs with the kernel and loading
   them early on boot via the User Mode Driver mechanism, hence reusing
   all the user space infra we have.

 - Support sleepable BPF programs, initially targeting LSM and tracing.

 - Add bpf_d_path() helper for returning full path for given 'struct
   path'.

 - Make bpf_tail_call compatible with bpf-to-bpf calls.

 - Allow BPF programs to call map_update_elem on sockmaps.

 - Add BPF Type Format (BTF) support for type and enum discovery, as
   well as support for using BTF within the kernel itself (current use
   is for pretty printing structures).

 - Support listing and getting information about bpf_links via the bpf
   syscall.

 - Enhance kernel interfaces around NIC firmware update. Allow
   specifying overwrite mask to control if settings etc. are reset
   during update; report expected max time operation may take to users;
   support firmware activation without machine reboot incl. limits of
   how much impact reset may have (e.g. dropping link or not).

 - Extend ethtool configuration interface to report IEEE-standard
   counters, to limit the need for per-vendor logic in user space.

 - Adopt or extend devlink use for debug, monitoring, fw update in many
   drivers (dsa loop, ice, ionic, sja1105, qed, mlxsw, mv88e6xxx,
   dpaa2-eth).

 - In mlxsw expose critical and emergency SFP module temperature alarms.
   Refactor port buffer handling to make the defaults more suitable and
   support setting these values explicitly via the DCBNL interface.

 - Add XDP support for Intel's igb driver.

 - Support offloading TC flower classification and filtering rules to
   mscc_ocelot switches.

 - Add PTP support for Marvell Octeontx2 and PP2.2 hardware, as well as
   fixed interval period pulse generator and one-step timestamping in
   dpaa-eth.

 - Add support for various auth offloads in WiFi APs, e.g. SAE (WPA3)
   offload.

 - Add Lynx PHY/PCS MDIO module, and convert various drivers which have
   this HW to use it. Convert mvpp2 to split PCS.

 - Support Marvell Prestera 98DX3255 24-port switch ASICs, as well as
   7-port Mediatek MT7531 IP.

 - Add initial support for QCA6390 and IPQ6018 in ath11k WiFi driver,
   and wcn3680 support in wcn36xx.

 - Improve performance for packets which don't require much offloads on
   recent Mellanox NICs by 20% by making multiple packets share a
   descriptor entry.

 - Move chelsio inline crypto drivers (for TLS and IPsec) from the
   crypto subtree to drivers/net. Move MDIO drivers out of the phy
   directory.

 - Clean up a lot of W=1 warnings, reportedly the actively developed
   subsections of networking drivers should now build W=1 warning free.

 - Make sure drivers don't use in_interrupt() to dynamically adapt their
   code. Convert tasklets to use new tasklet_setup API (sadly this
   conversion is not yet complete).

* tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2583 commits)
  Revert "bpfilter: Fix build error with CONFIG_BPFILTER_UMH"
  net, sockmap: Don't call bpf_prog_put() on NULL pointer
  bpf, selftest: Fix flaky tcp_hdr_options test when adding addr to lo
  bpf, sockmap: Add locking annotations to iterator
  netfilter: nftables: allow re-computing sctp CRC-32C in 'payload' statements
  net: fix pos incrementment in ipv6_route_seq_next
  net/smc: fix invalid return code in smcd_new_buf_create()
  net/smc: fix valid DMBE buffer sizes
  net/smc: fix use-after-free of delayed events
  bpfilter: Fix build error with CONFIG_BPFILTER_UMH
  cxgb4/ch_ipsec: Replace the module name to ch_ipsec from chcr
  net: sched: Fix suspicious RCU usage while accessing tcf_tunnel_info
  bpf: Fix register equivalence tracking.
  rxrpc: Fix loss of final ack on shutdown
  rxrpc: Fix bundle counting for exclusive connections
  netfilter: restore NF_INET_NUMHOOKS
  ibmveth: Identify ingress large send packets.
  ibmveth: Switch order of ibmveth_helper calls.
  cxgb4: handle 4-tuple PEDIT to NAT mode translation
  selftests: Add VRF route leaking tests
  ...
This commit is contained in:
Linus Torvalds 2020-10-15 18:42:13 -07:00
commit 9ff9b0d392
2301 changed files with 130033 additions and 50954 deletions
Download patch file Download diff file Expand all files Collapse all files

1
samples/bpf/.gitignore vendored
View file

@ -50,4 +50,5 @@ xdp_rxq_info
xdp_sample_pkts
xdp_tx_iptunnel
xdpsock
xsk_fwd
testfile.img

36
samples/bpf/Makefile
View file

@ -48,6 +48,7 @@ tprogs-y += syscall_tp
tprogs-y += cpustat
tprogs-y += xdp_adjust_tail
tprogs-y += xdpsock
tprogs-y += xsk_fwd
tprogs-y += xdp_fwd
tprogs-y += task_fd_query
tprogs-y += xdp_sample_pkts
@ -71,12 +72,12 @@ tracex4-objs := tracex4_user.o
tracex5-objs := tracex5_user.o $(TRACE_HELPERS)
tracex6-objs := tracex6_user.o
tracex7-objs := tracex7_user.o
test_probe_write_user-objs := bpf_load.o test_probe_write_user_user.o
trace_output-objs := bpf_load.o trace_output_user.o $(TRACE_HELPERS)
lathist-objs := bpf_load.o lathist_user.o
offwaketime-objs := bpf_load.o offwaketime_user.o $(TRACE_HELPERS)
spintest-objs := bpf_load.o spintest_user.o $(TRACE_HELPERS)
map_perf_test-objs := bpf_load.o map_perf_test_user.o
test_probe_write_user-objs := test_probe_write_user_user.o
trace_output-objs := trace_output_user.o $(TRACE_HELPERS)
lathist-objs := lathist_user.o
offwaketime-objs := offwaketime_user.o $(TRACE_HELPERS)
spintest-objs := spintest_user.o $(TRACE_HELPERS)
map_perf_test-objs := map_perf_test_user.o
test_overhead-objs := bpf_load.o test_overhead_user.o
test_cgrp2_array_pin-objs := test_cgrp2_array_pin.o
test_cgrp2_attach-objs := test_cgrp2_attach.o
@ -86,7 +87,7 @@ xdp1-objs := xdp1_user.o
# reuse xdp1 source intentionally
xdp2-objs := xdp1_user.o
xdp_router_ipv4-objs := xdp_router_ipv4_user.o
test_current_task_under_cgroup-objs := bpf_load.o $(CGROUP_HELPERS) \
test_current_task_under_cgroup-objs := $(CGROUP_HELPERS) \
test_current_task_under_cgroup_user.o
trace_event-objs := trace_event_user.o $(TRACE_HELPERS)
sampleip-objs := sampleip_user.o $(TRACE_HELPERS)
@ -97,13 +98,14 @@ test_map_in_map-objs := test_map_in_map_user.o
per_socket_stats_example-objs := cookie_uid_helper_example.o
xdp_redirect-objs := xdp_redirect_user.o
xdp_redirect_map-objs := xdp_redirect_map_user.o
xdp_redirect_cpu-objs := bpf_load.o xdp_redirect_cpu_user.o
xdp_monitor-objs := bpf_load.o xdp_monitor_user.o
xdp_redirect_cpu-objs := xdp_redirect_cpu_user.o
xdp_monitor-objs := xdp_monitor_user.o
xdp_rxq_info-objs := xdp_rxq_info_user.o
syscall_tp-objs := bpf_load.o syscall_tp_user.o
cpustat-objs := bpf_load.o cpustat_user.o
syscall_tp-objs := syscall_tp_user.o
cpustat-objs := cpustat_user.o
xdp_adjust_tail-objs := xdp_adjust_tail_user.o
xdpsock-objs := xdpsock_user.o
xsk_fwd-objs := xsk_fwd.o
xdp_fwd-objs := xdp_fwd_user.o
task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS)
xdp_sample_pkts-objs := xdp_sample_pkts_user.o $(TRACE_HELPERS)
@ -203,11 +205,14 @@ TPROGLDLIBS_trace_output += -lrt
TPROGLDLIBS_map_perf_test += -lrt
TPROGLDLIBS_test_overhead += -lrt
TPROGLDLIBS_xdpsock += -pthread
TPROGLDLIBS_xsk_fwd += -pthread
# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
# make M=samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
LLC ?= llc
CLANG ?= clang
OPT ?= opt
LLVM_DIS ?= llvm-dis
LLVM_OBJCOPY ?= llvm-objcopy
BTF_PAHOLE ?= pahole
@ -300,6 +305,11 @@ $(obj)/hbm_edt_kern.o: $(src)/hbm.h $(src)/hbm_kern.h
# asm/sysreg.h - inline assembly used by it is incompatible with llvm.
# But, there is no easy way to fix it, so just exclude it since it is
# useless for BPF samples.
# below we use long chain of commands, clang | opt | llvm-dis | llc,
# to generate final object file. 'clang' compiles the source into IR
# with native target, e.g., x64, arm64, etc. 'opt' does bpf CORE IR builtin
# processing (llvm12) and IR optimizations. 'llvm-dis' converts
# 'opt' output to IR, and finally 'llc' generates bpf byte code.
$(obj)/%.o: $(src)/%.c
@echo " CLANG-bpf " $@
$(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(BPF_EXTRA_CFLAGS) \
@ -311,7 +321,9 @@ $(obj)/%.o: $(src)/%.c
-Wno-address-of-packed-member -Wno-tautological-compare \
-Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \
-I$(srctree)/samples/bpf/ -include asm_goto_workaround.h \
-O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf $(LLC_FLAGS) -filetype=obj -o $@
-O2 -emit-llvm -Xclang -disable-llvm-passes -c $< -o - | \
$(OPT) -O2 -mtriple=bpf-pc-linux | $(LLVM_DIS) | \
$(LLC) -march=bpf $(LLC_FLAGS) -filetype=obj -o $@
ifeq ($(DWARF2BTF),y)
$(BTF_PAHOLE) -J $@
endif

36
samples/bpf/cpustat_kern.c
View file

@ -51,28 +51,28 @@ static int cpu_opps[] = { 208000, 432000, 729000, 960000, 1200000 };
#define MAP_OFF_PSTATE_IDX 3
#define MAP_OFF_NUM 4
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(u64),
.max_entries = MAX_CPU * MAP_OFF_NUM,
};
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__type(key, u32);
__type(value, u64);
__uint(max_entries, MAX_CPU * MAP_OFF_NUM);
} my_map SEC(".maps");
/* cstate_duration records duration time for every idle state per CPU */
struct bpf_map_def SEC("maps") cstate_duration = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(u64),
.max_entries = MAX_CPU * MAX_CSTATE_ENTRIES,
};
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__type(key, u32);
__type(value, u64);
__uint(max_entries, MAX_CPU * MAX_CSTATE_ENTRIES);
} cstate_duration SEC(".maps");
/* pstate_duration records duration time for every operating point per CPU */
struct bpf_map_def SEC("maps") pstate_duration = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(u64),
.max_entries = MAX_CPU * MAX_PSTATE_ENTRIES,
};
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__type(key, u32);
__type(value, u64);
__uint(max_entries, MAX_CPU * MAX_PSTATE_ENTRIES);
} pstate_duration SEC(".maps");
/*
* The trace events for cpu_idle and cpu_frequency are taken from:

47
samples/bpf/cpustat_user.c
View file

@ -9,7 +9,6 @@
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include <linux/bpf.h>
#include <locale.h>
#include <sys/types.h>
#include <sys/stat.h>
@ -18,7 +17,9 @@
#include <sys/wait.h>
#include <bpf/bpf.h>
#include "bpf_load.h"
#include <bpf/libbpf.h>
static int cstate_map_fd, pstate_map_fd;
#define MAX_CPU 8
#define MAX_PSTATE_ENTRIES 5
@ -181,21 +182,50 @@ static void int_exit(int sig)
{
cpu_stat_inject_cpu_idle_event();
cpu_stat_inject_cpu_frequency_event();
cpu_stat_update(map_fd[1], map_fd[2]);
cpu_stat_update(cstate_map_fd, pstate_map_fd);
cpu_stat_print();
exit(0);
}
int main(int argc, char **argv)
{
struct bpf_link *link = NULL;
struct bpf_program *prog;
struct bpf_object *obj;
char filename[256];
int ret;
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
obj = bpf_object__open_file(filename, NULL);
if (libbpf_get_error(obj)) {
fprintf(stderr, "ERROR: opening BPF object file failed\n");
return 0;
}
if (load_bpf_file(filename)) {
printf("%s", bpf_log_buf);
return 1;
prog = bpf_object__find_program_by_name(obj, "bpf_prog1");
if (!prog) {
printf("finding a prog in obj file failed\n");
goto cleanup;
}
/* load BPF program */
if (bpf_object__load(obj)) {
fprintf(stderr, "ERROR: loading BPF object file failed\n");
goto cleanup;
}
cstate_map_fd = bpf_object__find_map_fd_by_name(obj, "cstate_duration");
pstate_map_fd = bpf_object__find_map_fd_by_name(obj, "pstate_duration");
if (cstate_map_fd < 0 || pstate_map_fd < 0) {
fprintf(stderr, "ERROR: finding a map in obj file failed\n");
goto cleanup;
}
link = bpf_program__attach(prog);
if (libbpf_get_error(link)) {
fprintf(stderr, "ERROR: bpf_program__attach failed\n");
link = NULL;
goto cleanup;
}
ret = cpu_stat_inject_cpu_idle_event();
@ -210,10 +240,13 @@ int main(int argc, char **argv)
signal(SIGTERM, int_exit);
while (1) {
cpu_stat_update(map_fd[1], map_fd[2]);
cpu_stat_update(cstate_map_fd, pstate_map_fd);
cpu_stat_print();
sleep(5);
}
cleanup:
bpf_link__destroy(link);
bpf_object__close(obj);
return 0;
}

3
samples/bpf/hbm.c
View file

@ -40,6 +40,7 @@
#include <errno.h>
#include <fcntl.h>
#include <linux/unistd.h>
#include <linux/compiler.h>
#include <linux/bpf.h>
#include <bpf/bpf.h>
@ -483,7 +484,7 @@ int main(int argc, char **argv)
"Option -%c requires an argument.\n\n",
optopt);
case 'h':
fallthrough;
__fallthrough;
default:
Usage();
return 0;

24
samples/bpf/lathist_kern.c
View file

@ -18,12 +18,12 @@
* trace_preempt_[on|off] tracepoints hooks is not supported.
*/
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(u64),
.max_entries = MAX_CPU,
};
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__type(key, int);
__type(value, u64);
__uint(max_entries, MAX_CPU);
} my_map SEC(".maps");
SEC("kprobe/trace_preempt_off")
int bpf_prog1(struct pt_regs *ctx)
@ -61,12 +61,12 @@ static unsigned int log2l(unsigned long v)
return log2(v);
}
struct bpf_map_def SEC("maps") my_lat = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(long),
.max_entries = MAX_CPU * MAX_ENTRIES,
};
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__type(key, int);
__type(value, long);
__uint(max_entries, MAX_CPU * MAX_ENTRIES);
} my_lat SEC(".maps");
SEC("kprobe/trace_preempt_on")
int bpf_prog2(struct pt_regs *ctx)

42
samples/bpf/lathist_user.c
View file

@ -6,9 +6,8 @@
#include <unistd.h>
#include <stdlib.h>
#include <signal.h>
#include <linux/bpf.h>
#include <bpf/libbpf.h>
#include <bpf/bpf.h>
#include "bpf_load.h"
#define MAX_ENTRIES 20
#define MAX_CPU 4
@ -81,20 +80,51 @@ static void get_data(int fd)
int main(int argc, char **argv)
{
struct bpf_link *links[2];
struct bpf_program *prog;
struct bpf_object *obj;
char filename[256];
int map_fd, i = 0;
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
obj = bpf_object__open_file(filename, NULL);
if (libbpf_get_error(obj)) {
fprintf(stderr, "ERROR: opening BPF object file failed\n");
return 0;
}
if (load_bpf_file(filename)) {
printf("%s", bpf_log_buf);
return 1;
/* load BPF program */
if (bpf_object__load(obj)) {
fprintf(stderr, "ERROR: loading BPF object file failed\n");
goto cleanup;
}
map_fd = bpf_object__find_map_fd_by_name(obj, "my_lat");
if (map_fd < 0) {
fprintf(stderr, "ERROR: finding a map in obj file failed\n");
goto cleanup;
}
bpf_object__for_each_program(prog, obj) {
links[i] = bpf_program__attach(prog);
if (libbpf_get_error(links[i])) {
fprintf(stderr, "ERROR: bpf_program__attach failed\n");
links[i] = NULL;
goto cleanup;
}
i++;
}
while (1) {
get_data(map_fd[1]);
get_data(map_fd);
print_hist();
sleep(5);
}
cleanup:
for (i--; i >= 0; i--)
bpf_link__destroy(links[i]);
bpf_object__close(obj);
return 0;
}

48
samples/bpf/offwaketime_kern.c
View file

@ -28,38 +28,38 @@ struct key_t {
u32 tret;
};
struct bpf_map_def SEC("maps") counts = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(struct key_t),
.value_size = sizeof(u64),
.max_entries = 10000,
};
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__type(key, struct key_t);
__type(value, u64);
__uint(max_entries, 10000);
} counts SEC(".maps");
struct bpf_map_def SEC("maps") start = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(u32),
.value_size = sizeof(u64),
.max_entries = 10000,
};
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__type(key, u32);
__type(value, u64);
__uint(max_entries, 10000);
} start SEC(".maps");
struct wokeby_t {
char name[TASK_COMM_LEN];
u32 ret;
};
struct bpf_map_def SEC("maps") wokeby = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(u32),
.value_size = sizeof(struct wokeby_t),
.max_entries = 10000,
};
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__type(key, u32);
__type(value, struct wokeby_t);
__uint(max_entries, 10000);
} wokeby SEC(".maps");
struct bpf_map_def SEC("maps") stackmap = {
.type = BPF_MAP_TYPE_STACK_TRACE,
.key_size = sizeof(u32),
.value_size = PERF_MAX_STACK_DEPTH * sizeof(u64),
.max_entries = 10000,
};
struct {
__uint(type, BPF_MAP_TYPE_STACK_TRACE);
__uint(key_size, sizeof(u32));
__uint(value_size, PERF_MAX_STACK_DEPTH * sizeof(u64));
__uint(max_entries, 10000);
} stackmap SEC(".maps");
#define STACKID_FLAGS (0 | BPF_F_FAST_STACK_CMP)

66
samples/bpf/offwaketime_user.c
View file

@ -5,19 +5,19 @@
#include <unistd.h>
#include <stdlib.h>
#include <signal.h>
#include <linux/bpf.h>
#include <string.h>
#include <linux/perf_event.h>
#include <errno.h>
#include <assert.h>
#include <stdbool.h>
#include <sys/resource.h>
#include <bpf/libbpf.h>
#include "bpf_load.h"
#include <bpf/bpf.h>
#include "trace_helpers.h"
#define PRINT_RAW_ADDR 0
/* counts, stackmap */
static int map_fd[2];
static void print_ksym(__u64 addr)
{
struct ksym *sym;
@ -52,14 +52,14 @@ static void print_stack(struct key_t *key, __u64 count)
int i;
printf("%s;", key->target);
if (bpf_map_lookup_elem(map_fd[3], &key->tret, ip) != 0) {
if (bpf_map_lookup_elem(map_fd[1], &key->tret, ip) != 0) {
printf("---;");
} else {
for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--)
print_ksym(ip[i]);
}
printf("-;");
if (bpf_map_lookup_elem(map_fd[3], &key->wret, ip) != 0) {
if (bpf_map_lookup_elem(map_fd[1], &key->wret, ip) != 0) {
printf("---;");
} else {
for (i = 0; i < PERF_MAX_STACK_DEPTH; i++)
@ -96,23 +96,54 @@ static void int_exit(int sig)
int main(int argc, char **argv)
{
struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
struct bpf_object *obj = NULL;
struct bpf_link *links[2];
struct bpf_program *prog;
int delay = 1, i = 0;
char filename[256];
int delay = 1;
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
setrlimit(RLIMIT_MEMLOCK, &r);
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
if (setrlimit(RLIMIT_MEMLOCK, &r)) {
perror("setrlimit(RLIMIT_MEMLOCK)");
return 1;
}
if (load_kallsyms()) {
printf("failed to process /proc/kallsyms\n");
return 2;
}
if (load_bpf_file(filename)) {
printf("%s", bpf_log_buf);
return 1;
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
obj = bpf_object__open_file(filename, NULL);
if (libbpf_get_error(obj)) {
fprintf(stderr, "ERROR: opening BPF object file failed\n");
obj = NULL;
goto cleanup;
}
/* load BPF program */
if (bpf_object__load(obj)) {
fprintf(stderr, "ERROR: loading BPF object file failed\n");
goto cleanup;
}
map_fd[0] = bpf_object__find_map_fd_by_name(obj, "counts");
map_fd[1] = bpf_object__find_map_fd_by_name(obj, "stackmap");
if (map_fd[0] < 0 || map_fd[1] < 0) {
fprintf(stderr, "ERROR: finding a map in obj file failed\n");
goto cleanup;
}
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
bpf_object__for_each_program(prog, obj) {
links[i] = bpf_program__attach(prog);
if (libbpf_get_error(links[i])) {
fprintf(stderr, "ERROR: bpf_program__attach failed\n");
links[i] = NULL;
goto cleanup;
}
i++;
}
if (argc > 1)
@ -120,5 +151,10 @@ int main(int argc, char **argv)
sleep(delay);
print_stacks(map_fd[0]);
cleanup:
for (i--; i >= 0; i--)
bpf_link__destroy(links[i]);
bpf_object__close(obj);
return 0;
}

20
samples/bpf/sockex3_kern.c
View file

@ -31,28 +31,30 @@ struct {
#define PARSE_IP 3
#define PARSE_IPV6 4
/* protocol dispatch routine.
* It tail-calls next BPF program depending on eth proto
* Note, we could have used:
* bpf_tail_call(skb, &jmp_table, proto);
* but it would need large prog_array
/* Protocol dispatch routine. It tail-calls next BPF program depending
* on eth proto. Note, we could have used ...
*
* bpf_tail_call(skb, &jmp_table, proto);
*
* ... but it would need large prog_array and cannot be optimised given
* the map key is not static.
*/
static inline void parse_eth_proto(struct __sk_buff *skb, u32 proto)
{
switch (proto) {
case ETH_P_8021Q:
case ETH_P_8021AD:
bpf_tail_call(skb, &jmp_table, PARSE_VLAN);
bpf_tail_call_static(skb, &jmp_table, PARSE_VLAN);
break;
case ETH_P_MPLS_UC:
case ETH_P_MPLS_MC:
bpf_tail_call(skb, &jmp_table, PARSE_MPLS);
bpf_tail_call_static(skb, &jmp_table, PARSE_MPLS);
break;
case ETH_P_IP:
bpf_tail_call(skb, &jmp_table, PARSE_IP);
bpf_tail_call_static(skb, &jmp_table, PARSE_IP);
break;
case ETH_P_IPV6:
bpf_tail_call(skb, &jmp_table, PARSE_IPV6);
bpf_tail_call_static(skb, &jmp_table, PARSE_IPV6);
break;
}
}

6
samples/bpf/sockex3_user.c
View file

@ -29,8 +29,8 @@ int main(int argc, char **argv)
struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
struct bpf_program *prog;
struct bpf_object *obj;
const char *section;
char filename[256];
const char *title;
FILE *f;
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
@ -58,8 +58,8 @@ int main(int argc, char **argv)
bpf_object__for_each_program(prog, obj) {
fd = bpf_program__fd(prog);
title = bpf_program__title(prog, false);
if (sscanf(title, "socket/%d", &key) != 1) {
section = bpf_program__section_name(prog);
if (sscanf(section, "socket/%d", &key) != 1) {
fprintf(stderr, "ERROR: finding prog failed\n");
goto cleanup;
}

36
samples/bpf/spintest_kern.c
View file

@ -12,25 +12,25 @@
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(long),
.value_size = sizeof(long),
.max_entries = 1024,
};
struct bpf_map_def SEC("maps") my_map2 = {
.type = BPF_MAP_TYPE_PERCPU_HASH,
.key_size = sizeof(long),
.value_size = sizeof(long),
.max_entries = 1024,
};
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__type(key, long);
__type(value, long);
__uint(max_entries, 1024);
} my_map SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
__uint(key_size, sizeof(long));
__uint(value_size, sizeof(long));
__uint(max_entries, 1024);
} my_map2 SEC(".maps");
struct bpf_map_def SEC("maps") stackmap = {
.type = BPF_MAP_TYPE_STACK_TRACE,
.key_size = sizeof(u32),
.value_size = PERF_MAX_STACK_DEPTH * sizeof(u64),
.max_entries = 10000,
};
struct {
__uint(type, BPF_MAP_TYPE_STACK_TRACE);
__uint(key_size, sizeof(u32));
__uint(value_size, PERF_MAX_STACK_DEPTH * sizeof(u64));
__uint(max_entries, 10000);
} stackmap SEC(".maps");
#define PROG(foo) \
int foo(struct pt_regs *ctx) \

68
samples/bpf/spintest_user.c
View file

@ -1,40 +1,77 @@
// SPDX-License-Identifier: GPL-2.0
#include <stdio.h>
#include <unistd.h>
#include <linux/bpf.h>
#include <string.h>
#include <assert.h>
#include <sys/resource.h>
#include <bpf/libbpf.h>
#include "bpf_load.h"
#include <bpf/bpf.h>
#include "trace_helpers.h"
int main(int ac, char **argv)
{
struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
char filename[256], symbol[256];
struct bpf_object *obj = NULL;
struct bpf_link *links[20];
long key, next_key, value;
char filename[256];
struct bpf_program *prog;
int map_fd, i, j = 0;
const char *section;
struct ksym *sym;
int i;
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
setrlimit(RLIMIT_MEMLOCK, &r);
if (setrlimit(RLIMIT_MEMLOCK, &r)) {
perror("setrlimit(RLIMIT_MEMLOCK)");
return 1;
}
if (load_kallsyms()) {
printf("failed to process /proc/kallsyms\n");
return 2;
}
if (load_bpf_file(filename)) {
printf("%s", bpf_log_buf);
return 1;
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
obj = bpf_object__open_file(filename, NULL);
if (libbpf_get_error(obj)) {
fprintf(stderr, "ERROR: opening BPF object file failed\n");
obj = NULL;
goto cleanup;
}
/* load BPF program */
if (bpf_object__load(obj)) {
fprintf(stderr, "ERROR: loading BPF object file failed\n");
goto cleanup;
}
map_fd = bpf_object__find_map_fd_by_name(obj, "my_map");
if (map_fd < 0) {
fprintf(stderr, "ERROR: finding a map in obj file failed\n");
goto cleanup;
}
bpf_object__for_each_program(prog, obj) {
section = bpf_program__section_name(prog);
if (sscanf(section, "kprobe/%s", symbol) != 1)
continue;
/* Attach prog only when symbol exists */
if (ksym_get_addr(symbol)) {
links[j] = bpf_program__attach(prog);
if (libbpf_get_error(links[j])) {
fprintf(stderr, "bpf_program__attach failed\n");
links[j] = NULL;
goto cleanup;
}
j++;
}
}
for (i = 0; i < 5; i++) {
key = 0;
printf("kprobing funcs:");
while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) {
bpf_map_lookup_elem(map_fd[0], &next_key, &value);
while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) {
bpf_map_lookup_elem(map_fd, &next_key, &value);
assert(next_key == value);
sym = ksym_search(value);
key = next_key;
@ -48,10 +85,15 @@ int main(int ac, char **argv)
if (key)
printf("\n");
key = 0;
while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0)
bpf_map_delete_elem(map_fd[0], &next_key);
while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0)
bpf_map_delete_elem(map_fd, &next_key);
sleep(1);
}
cleanup:
for (j--; j >= 0; j--)
bpf_link__destroy(links[j]);
bpf_object__close(obj);
return 0;
}

24
samples/bpf/syscall_tp_kern.c
View file

@ -18,19 +18,19 @@ struct syscalls_exit_open_args {
long ret;
};
struct bpf_map_def SEC("maps") enter_open_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(u32),
.max_entries = 1,
};
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__type(key, u32);
__type(value, u32);
__uint(max_entries, 1);
} enter_open_map SEC(".maps");
struct bpf_map_def SEC("maps") exit_open_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(u32),
.max_entries = 1,
};
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__type(key, u32);
__type(value, u32);
__uint(max_entries, 1);
} exit_open_map SEC(".maps");
static __always_inline void count(void *map)
{

54
samples/bpf/syscall_tp_user.c
View file

@ -5,16 +5,12 @@
#include <unistd.h>
#include <fcntl.h>
#include <stdlib.h>
#include <signal.h>
#include <linux/bpf.h>
#include <string.h>
#include <linux/perf_event.h>
#include <errno.h>
#include <assert.h>
#include <stdbool.h>
#include <sys/resource.h>
#include <bpf/libbpf.h>
#include <bpf/bpf.h>
#include "bpf_load.h"
/* This program verifies bpf attachment to tracepoint sys_enter_* and sys_exit_*.
* This requires kernel CONFIG_FTRACE_SYSCALLS to be set.
@ -49,16 +45,44 @@ static void verify_map(int map_id)
static int test(char *filename, int num_progs)
{
int i, fd, map0_fds[num_progs], map1_fds[num_progs];
int map0_fds[num_progs], map1_fds[num_progs], fd, i, j = 0;
struct bpf_link *links[num_progs * 4];
struct bpf_object *objs[num_progs];
struct bpf_program *prog;
for (i = 0; i < num_progs; i++) {
if (load_bpf_file(filename)) {
fprintf(stderr, "%s", bpf_log_buf);
return 1;
objs[i] = bpf_object__open_file(filename, NULL);
if (libbpf_get_error(objs[i])) {
fprintf(stderr, "opening BPF object file failed\n");
objs[i] = NULL;
goto cleanup;
}
printf("prog #%d: map ids %d %d\n", i, map_fd[0], map_fd[1]);
map0_fds[i] = map_fd[0];
map1_fds[i] = map_fd[1];
/* load BPF program */
if (bpf_object__load(objs[i])) {
fprintf(stderr, "loading BPF object file failed\n");
goto cleanup;
}
map0_fds[i] = bpf_object__find_map_fd_by_name(objs[i],
"enter_open_map");
map1_fds[i] = bpf_object__find_map_fd_by_name(objs[i],
"exit_open_map");
if (map0_fds[i] < 0 || map1_fds[i] < 0) {
fprintf(stderr, "finding a map in obj file failed\n");
goto cleanup;
}
bpf_object__for_each_program(prog, objs[i]) {
links[j] = bpf_program__attach(prog);
if (libbpf_get_error(links[j])) {
fprintf(stderr, "bpf_program__attach failed\n");
links[j] = NULL;
goto cleanup;
}
j++;
}
printf("prog #%d: map ids %d %d\n", i, map0_fds[i], map1_fds[i]);
}
/* current load_bpf_file has perf_event_open default pid = -1
@ -80,6 +104,12 @@ static int test(char *filename, int num_progs)
verify_map(map1_fds[i]);
}
cleanup:
for (j--; j >= 0; j--)
bpf_link__destroy(links[j]);
for (i--; i >= 0; i--)
bpf_object__close(objs[i]);
return 0;
}

2
samples/bpf/task_fd_query_kern.c
View file

@ -10,7 +10,7 @@ int bpf_prog1(struct pt_regs *ctx)
return 0;
}
SEC("kretprobe/blk_account_io_completion")
SEC("kretprobe/blk_account_io_done")
int bpf_prog2(struct pt_regs *ctx)
{
return 0;

2
samples/bpf/task_fd_query_user.c
View file

@ -314,7 +314,7 @@ int main(int argc, char **argv)
/* test two functions in the corresponding *_kern.c file */
CHECK_AND_RET(test_debug_fs_kprobe(0, "blk_mq_start_request",
BPF_FD_TYPE_KPROBE));
CHECK_AND_RET(test_debug_fs_kprobe(1, "blk_account_io_completion",
CHECK_AND_RET(test_debug_fs_kprobe(1, "blk_account_io_done",
BPF_FD_TYPE_KRETPROBE));
/* test nondebug fs kprobe */

27
samples/bpf/test_current_task_under_cgroup_kern.c
View file

@ -10,23 +10,24 @@
#include <linux/version.h>
#include <bpf/bpf_helpers.h>
#include <uapi/linux/utsname.h>
#include "trace_common.h"
struct bpf_map_def SEC("maps") cgroup_map = {
.type = BPF_MAP_TYPE_CGROUP_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(u32),
.max_entries = 1,
};
struct {
__uint(type, BPF_MAP_TYPE_CGROUP_ARRAY);
__uint(key_size, sizeof(u32));
__uint(value_size, sizeof(u32));
__uint(max_entries, 1);
} cgroup_map SEC(".maps");
struct bpf_map_def SEC("maps") perf_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(u64),
.max_entries = 1,
};
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__type(key, u32);
__type(value, u64);
__uint(max_entries, 1);
} perf_map SEC(".maps");
/* Writes the last PID that called sync to a map at index 0 */
SEC("kprobe/sys_sync")
SEC("kprobe/" SYSCALL(sys_sync))
int bpf_prog1(struct pt_regs *ctx)
{
u64 pid = bpf_get_current_pid_tgid();

52
samples/bpf/test_current_task_under_cgroup_user.c
View file

@ -4,10 +4,9 @@
#define _GNU_SOURCE
#include <stdio.h>
#include <linux/bpf.h>
#include <unistd.h>
#include <bpf/bpf.h>
#include "bpf_load.h"
#include <bpf/libbpf.h>
#include "cgroup_helpers.h"
#define CGROUP_PATH "/my-cgroup"
@ -15,13 +14,44 @@
int main(int argc, char **argv)
{
pid_t remote_pid, local_pid = getpid();
int cg2, idx = 0, rc = 0;
struct bpf_link *link = NULL;
struct bpf_program *prog;
int cg2, idx = 0, rc = 1;
struct bpf_object *obj;
char filename[256];
int map_fd[2];
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
if (load_bpf_file(filename)) {
printf("%s", bpf_log_buf);
return 1;
obj = bpf_object__open_file(filename, NULL);
if (libbpf_get_error(obj)) {
fprintf(stderr, "ERROR: opening BPF object file failed\n");
return 0;
}
prog = bpf_object__find_program_by_name(obj, "bpf_prog1");
if (!prog) {
printf("finding a prog in obj file failed\n");
goto cleanup;
}
/* load BPF program */
if (bpf_object__load(obj)) {
fprintf(stderr, "ERROR: loading BPF object file failed\n");
goto cleanup;
}
map_fd[0] = bpf_object__find_map_fd_by_name(obj, "cgroup_map");
map_fd[1] = bpf_object__find_map_fd_by_name(obj, "perf_map");
if (map_fd[0] < 0 || map_fd[1] < 0) {
fprintf(stderr, "ERROR: finding a map in obj file failed\n");
goto cleanup;
}
link = bpf_program__attach(prog);
if (libbpf_get_error(link)) {
fprintf(stderr, "ERROR: bpf_program__attach failed\n");
link = NULL;
goto cleanup;
}
if (setup_cgroup_environment())
@ -70,12 +100,14 @@ int main(int argc, char **argv)
goto err;
}
goto out;
err:
rc = 1;
rc = 0;
out:
err:
close(cg2);
cleanup_cgroup_environment();
cleanup:
bpf_link__destroy(link);
bpf_object__close(obj);
return rc;
}

7
samples/bpf/test_map_in_map_kern.c
View file

@ -103,10 +103,9 @@ static __always_inline int do_inline_hash_lookup(void *inner_map, u32 port)
return result ? *result : -ENOENT;
}
SEC("kprobe/" SYSCALL(sys_connect))
SEC("kprobe/__sys_connect")
int trace_sys_connect(struct pt_regs *ctx)
{
struct pt_regs *real_regs = (struct pt_regs *)PT_REGS_PARM1_CORE(ctx);
struct sockaddr_in6 *in6;
u16 test_case, port, dst6[8];
int addrlen, ret, inline_ret, ret_key = 0;
@ -114,8 +113,8 @@ int trace_sys_connect(struct pt_regs *ctx)
void *outer_map, *inner_map;
bool inline_hash = false;
in6 = (struct sockaddr_in6 *)PT_REGS_PARM2_CORE(real_regs);
addrlen = (int)PT_REGS_PARM3_CORE(real_regs);
in6 = (struct sockaddr_in6 *)PT_REGS_PARM2_CORE(ctx);
addrlen = (int)PT_REGS_PARM3_CORE(ctx);
if (addrlen != sizeof(*in6))
return 0;

12
samples/bpf/test_probe_write_user_kern.c
View file

@ -13,12 +13,12 @@
#include <bpf/bpf_core_read.h>
#include "trace_common.h"
struct bpf_map_def SEC("maps") dnat_map = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(struct sockaddr_in),
.value_size = sizeof(struct sockaddr_in),
.max_entries = 256,
};
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__type(key, struct sockaddr_in);
__type(value, struct sockaddr_in);
__uint(max_entries, 256);
} dnat_map SEC(".maps");
/* kprobe is NOT a stable ABI
* kernel functions can be removed, renamed or completely change semantics.

49
samples/bpf/test_probe_write_user_user.c
View file

@ -1,21 +1,22 @@
// SPDX-License-Identifier: GPL-2.0
#include <stdio.h>
#include <assert.h>
#include <linux/bpf.h>
#include <unistd.h>
#include <bpf/bpf.h>
#include "bpf_load.h"
#include <bpf/libbpf.h>
#include <sys/socket.h>
#include <string.h>
#include <netinet/in.h>
#include <arpa/inet.h>
int main(int ac, char **argv)
{
int serverfd, serverconnfd, clientfd;
socklen_t sockaddr_len;
struct sockaddr serv_addr, mapped_addr, tmp_addr;
struct sockaddr_in *serv_addr_in, *mapped_addr_in, *tmp_addr_in;
struct sockaddr serv_addr, mapped_addr, tmp_addr;
int serverfd, serverconnfd, clientfd, map_fd;
struct bpf_link *link = NULL;
struct bpf_program *prog;
struct bpf_object *obj;
socklen_t sockaddr_len;
char filename[256];
char *ip;
@ -24,10 +25,35 @@ int main(int ac, char **argv)
tmp_addr_in = (struct sockaddr_in *)&tmp_addr;
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
obj = bpf_object__open_file(filename, NULL);
if (libbpf_get_error(obj)) {
fprintf(stderr, "ERROR: opening BPF object file failed\n");
return 0;
}
if (load_bpf_file(filename)) {
printf("%s", bpf_log_buf);
return 1;
prog = bpf_object__find_program_by_name(obj, "bpf_prog1");
if (libbpf_get_error(prog)) {
fprintf(stderr, "ERROR: finding a prog in obj file failed\n");
goto cleanup;
}
/* load BPF program */
if (bpf_object__load(obj)) {
fprintf(stderr, "ERROR: loading BPF object file failed\n");
goto cleanup;
}
map_fd = bpf_object__find_map_fd_by_name(obj, "dnat_map");
if (map_fd < 0) {
fprintf(stderr, "ERROR: finding a map in obj file failed\n");
goto cleanup;
}
link = bpf_program__attach(prog);
if (libbpf_get_error(link)) {
fprintf(stderr, "ERROR: bpf_program__attach failed\n");
link = NULL;
goto cleanup;
}
assert((serverfd = socket(AF_INET, SOCK_STREAM, 0)) > 0);
@ -51,7 +77,7 @@ int main(int ac, char **argv)
mapped_addr_in->sin_port = htons(5555);
mapped_addr_in->sin_addr.s_addr = inet_addr("255.255.255.255");
assert(!bpf_map_update_elem(map_fd[0], &mapped_addr, &serv_addr, BPF_ANY));
assert(!bpf_map_update_elem(map_fd, &mapped_addr, &serv_addr, BPF_ANY));
assert(listen(serverfd, 5) == 0);
@ -75,5 +101,8 @@ int main(int ac, char **argv)
/* Is the server's getsockname = the socket getpeername */
assert(memcmp(&serv_addr, &tmp_addr, sizeof(struct sockaddr_in)) == 0);
cleanup:
bpf_link__destroy(link);
bpf_object__close(obj);
return 0;
}

15
samples/bpf/trace_output_kern.c
View file

@ -2,15 +2,16 @@
#include <linux/version.h>
#include <uapi/linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include "trace_common.h"
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(u32),
.max_entries = 2,
};
struct {
__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
__uint(key_size, sizeof(int));
__uint(value_size, sizeof(u32));
__uint(max_entries, 2);
} my_map SEC(".maps");
SEC("kprobe/sys_write")
SEC("kprobe/" SYSCALL(sys_write))
int bpf_prog1(struct pt_regs *ctx)
{
struct S {

55
samples/bpf/trace_output_user.c
View file

@ -1,23 +1,10 @@
// SPDX-License-Identifier: GPL-2.0-only
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <stdbool.h>
#include <string.h>
#include <fcntl.h>
#include <poll.h>
#include <linux/perf_event.h>
#include <linux/bpf.h>
#include <errno.h>
#include <assert.h>
#include <sys/syscall.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <time.h>
#include <signal.h>
#include <bpf/libbpf.h>
#include "bpf_load.h"
#include "perf-sys.h"
static __u64 time_get_ns(void)
{
@ -57,20 +44,48 @@ static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size)
int main(int argc, char **argv)
{
struct perf_buffer_opts pb_opts = {};
struct bpf_link *link = NULL;
struct bpf_program *prog;
struct perf_buffer *pb;
struct bpf_object *obj;
int map_fd, ret = 0;
char filename[256];
FILE *f;
int ret;
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
obj = bpf_object__open_file(filename, NULL);
if (libbpf_get_error(obj)) {
fprintf(stderr, "ERROR: opening BPF object file failed\n");
return 0;
}
if (load_bpf_file(filename)) {
printf("%s", bpf_log_buf);
return 1;
/* load BPF program */
if (bpf_object__load(obj)) {
fprintf(stderr, "ERROR: loading BPF object file failed\n");
goto cleanup;
}
map_fd = bpf_object__find_map_fd_by_name(obj, "my_map");
if (map_fd < 0) {
fprintf(stderr, "ERROR: finding a map in obj file failed\n");
goto cleanup;
}
prog = bpf_object__find_program_by_name(obj, "bpf_prog1");
if (libbpf_get_error(prog)) {
fprintf(stderr, "ERROR: finding a prog in obj file failed\n");
goto cleanup;
}
link = bpf_program__attach(prog);
if (libbpf_get_error(link)) {
fprintf(stderr, "ERROR: bpf_program__attach failed\n");
link = NULL;
goto cleanup;
}
pb_opts.sample_cb = print_bpf_output;
pb = perf_buffer__new(map_fd[0], 8, &pb_opts);
pb = perf_buffer__new(map_fd, 8, &pb_opts);
ret = libbpf_get_error(pb);
if (ret) {
printf("failed to setup perf_buffer: %d\n", ret);
@ -84,5 +99,9 @@ int main(int argc, char **argv)
while ((ret = perf_buffer__poll(pb, 1000)) >= 0 && cnt < MAX_CNT) {
}
kill(0, SIGINT);
cleanup:
bpf_link__destroy(link);
bpf_object__close(obj);
return ret;
}

2
samples/bpf/tracex3_kern.c
View file

@ -49,7 +49,7 @@ struct {
__uint(max_entries, SLOTS);
} lat_map SEC(".maps");
SEC("kprobe/blk_account_io_completion")
SEC("kprobe/blk_account_io_done")
int bpf_prog2(struct pt_regs *ctx)
{
long rq = PT_REGS_PARM1(ctx);

6
samples/bpf/tracex5_user.c
View file

@ -39,8 +39,8 @@ int main(int ac, char **argv)
struct bpf_program *prog;
struct bpf_object *obj;
int key, fd, progs_fd;
const char *section;
char filename[256];
const char *title;
FILE *f;
setrlimit(RLIMIT_MEMLOCK, &r);
@ -78,9 +78,9 @@ int main(int ac, char **argv)
}
bpf_object__for_each_program(prog, obj) {
title = bpf_program__title(prog, false);
section = bpf_program__section_name(prog);
/* register only syscalls to PROG_ARRAY */
if (sscanf(title, "kprobe/%d", &key) != 1)
if (sscanf(section, "kprobe/%d", &key) != 1)
continue;
fd = bpf_program__fd(prog);

60
samples/bpf/xdp_monitor_kern.c
View file

@ -6,21 +6,21 @@
#include <uapi/linux/bpf.h>
#include <bpf/bpf_helpers.h>
struct bpf_map_def SEC("maps") redirect_err_cnt = {
.type = BPF_MAP_TYPE_PERCPU_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(u64),
.max_entries = 2,
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 bpf_map_def SEC("maps") exception_cnt = {
.type = BPF_MAP_TYPE_PERCPU_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(u64),
.max_entries = XDP_UNKNOWN + 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
@ -129,19 +129,19 @@ struct datarec {
};
#define MAX_CPUS 64
struct bpf_map_def SEC("maps") cpumap_enqueue_cnt = {
.type = BPF_MAP_TYPE_PERCPU_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(struct datarec),
.max_entries = MAX_CPUS,
};
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 bpf_map_def SEC("maps") cpumap_kthread_cnt = {
.type = BPF_MAP_TYPE_PERCPU_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(struct datarec),
.max_entries = 1,
};
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
@ -210,12 +210,12 @@ int trace_xdp_cpumap_kthread(struct cpumap_kthread_ctx *ctx)
return 0;
}
struct bpf_map_def SEC("maps") devmap_xmit_cnt = {
.type = BPF_MAP_TYPE_PERCPU_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(struct datarec),
.max_entries = 1,
};
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

159
samples/bpf/xdp_monitor_user.c
View file

@ -26,12 +26,37 @@ static const char *__doc_err_only__=
#include <net/if.h>
#include <time.h>
#include <signal.h>
#include <bpf/bpf.h>
#include "bpf_load.h"
#include <bpf/libbpf.h>
#include "bpf_util.h"
enum map_type {
REDIRECT_ERR_CNT,
EXCEPTION_CNT,
CPUMAP_ENQUEUE_CNT,
CPUMAP_KTHREAD_CNT,
DEVMAP_XMIT_CNT,
};
static const char *const map_type_strings[] = {
[REDIRECT_ERR_CNT] = "redirect_err_cnt",
[EXCEPTION_CNT] = "exception_cnt",
[CPUMAP_ENQUEUE_CNT] = "cpumap_enqueue_cnt",
[CPUMAP_KTHREAD_CNT] = "cpumap_kthread_cnt",
[DEVMAP_XMIT_CNT] = "devmap_xmit_cnt",
};
#define NUM_MAP 5
#define NUM_TP 8
static int tp_cnt;
static int map_cnt;
static int verbose = 1;
static bool debug = false;
struct bpf_map *map_data[NUM_MAP] = {};
struct bpf_link *tp_links[NUM_TP] = {};
struct bpf_object *obj;
static const struct option long_options[] = {
{"help", no_argument, NULL, 'h' },
@ -41,6 +66,16 @@ static const struct option long_options[] = {
{0, 0, NULL, 0 }
};
static void int_exit(int sig)
{
/* Detach tracepoints */
while (tp_cnt)
bpf_link__destroy(tp_links[--tp_cnt]);
bpf_object__close(obj);
exit(0);
}
/* C standard specifies two constants, EXIT_SUCCESS(0) and EXIT_FAILURE(1) */
#define EXIT_FAIL_MEM 5
@ -483,23 +518,23 @@ static bool stats_collect(struct stats_record *rec)
* this can happen by someone running perf-record -e
*/
fd = map_data[0].fd; /* map0: redirect_err_cnt */
fd = bpf_map__fd(map_data[REDIRECT_ERR_CNT]);
for (i = 0; i < REDIR_RES_MAX; i++)
map_collect_record_u64(fd, i, &rec->xdp_redirect[i]);
fd = map_data[1].fd; /* map1: exception_cnt */
fd = bpf_map__fd(map_data[EXCEPTION_CNT]);
for (i = 0; i < XDP_ACTION_MAX; i++) {
map_collect_record_u64(fd, i, &rec->xdp_exception[i]);
}
fd = map_data[2].fd; /* map2: cpumap_enqueue_cnt */
fd = bpf_map__fd(map_data[CPUMAP_ENQUEUE_CNT]);
for (i = 0; i < MAX_CPUS; i++)
map_collect_record(fd, i, &rec->xdp_cpumap_enqueue[i]);
fd = map_data[3].fd; /* map3: cpumap_kthread_cnt */
fd = bpf_map__fd(map_data[CPUMAP_KTHREAD_CNT]);
map_collect_record(fd, 0, &rec->xdp_cpumap_kthread);
fd = map_data[4].fd; /* map4: devmap_xmit_cnt */
fd = bpf_map__fd(map_data[DEVMAP_XMIT_CNT]);
map_collect_record(fd, 0, &rec->xdp_devmap_xmit);
return true;
@ -598,8 +633,8 @@ static void stats_poll(int interval, bool err_only)
/* TODO Need more advanced stats on error types */
if (verbose) {
printf(" - Stats map0: %s\n", map_data[0].name);
printf(" - Stats map1: %s\n", map_data[1].name);
printf(" - Stats map0: %s\n", bpf_map__name(map_data[0]));
printf(" - Stats map1: %s\n", bpf_map__name(map_data[1]));
printf("\n");
}
fflush(stdout);
@ -618,44 +653,51 @@ static void stats_poll(int interval, bool err_only)
static void print_bpf_prog_info(void)
{
int i;
struct bpf_program *prog;
struct bpf_map *map;
int i = 0;
/* Prog info */
printf("Loaded BPF prog have %d bpf program(s)\n", prog_cnt);
for (i = 0; i < prog_cnt; i++) {
printf(" - prog_fd[%d] = fd(%d)\n", i, prog_fd[i]);
printf("Loaded BPF prog have %d bpf program(s)\n", tp_cnt);
bpf_object__for_each_program(prog, obj) {
printf(" - prog_fd[%d] = fd(%d)\n", i, bpf_program__fd(prog));
i++;
}
i = 0;
/* Maps info */
printf("Loaded BPF prog have %d map(s)\n", map_data_count);
for (i = 0; i < map_data_count; i++) {
char *name = map_data[i].name;
int fd = map_data[i].fd;
printf("Loaded BPF prog have %d map(s)\n", map_cnt);
bpf_object__for_each_map(map, obj) {
const char *name = bpf_map__name(map);
int fd = bpf_map__fd(map);
printf(" - map_data[%d] = fd(%d) name:%s\n", i, fd, name);
i++;
}
/* Event info */
printf("Searching for (max:%d) event file descriptor(s)\n", prog_cnt);
for (i = 0; i < prog_cnt; i++) {
if (event_fd[i] != -1)
printf(" - event_fd[%d] = fd(%d)\n", i, event_fd[i]);
printf("Searching for (max:%d) event file descriptor(s)\n", tp_cnt);
for (i = 0; i < tp_cnt; i++) {
int fd = bpf_link__fd(tp_links[i]);
if (fd != -1)
printf(" - event_fd[%d] = fd(%d)\n", i, fd);
}
}
int main(int argc, char **argv)
{
struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
struct bpf_program *prog;
int longindex = 0, opt;
int ret = EXIT_SUCCESS;
char bpf_obj_file[256];
int ret = EXIT_FAILURE;
enum map_type type;
char filename[256];
/* Default settings: */
bool errors_only = true;
int interval = 2;
snprintf(bpf_obj_file, sizeof(bpf_obj_file), "%s_kern.o", argv[0]);
/* Parse commands line args */
while ((opt = getopt_long(argc, argv, "hDSs:",
long_options, &longindex)) != -1) {
@ -672,40 +714,79 @@ int main(int argc, char **argv)
case 'h':
default:
usage(argv);
return EXIT_FAILURE;
return ret;
}
}
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
if (setrlimit(RLIMIT_MEMLOCK, &r)) {
perror("setrlimit(RLIMIT_MEMLOCK)");
return EXIT_FAILURE;
return ret;
}
if (load_bpf_file(bpf_obj_file)) {
printf("ERROR - bpf_log_buf: %s", bpf_log_buf);
return EXIT_FAILURE;
/* Remove tracepoint program when program is interrupted or killed */
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
obj = bpf_object__open_file(filename, NULL);
if (libbpf_get_error(obj)) {
printf("ERROR: opening BPF object file failed\n");
obj = NULL;
goto cleanup;
}
if (!prog_fd[0]) {
printf("ERROR - load_bpf_file: %s\n", strerror(errno));
return EXIT_FAILURE;
/* load BPF program */
if (bpf_object__load(obj)) {
printf("ERROR: loading BPF object file failed\n");
goto cleanup;
}
for (type = 0; type < NUM_MAP; type++) {
map_data[type] =
bpf_object__find_map_by_name(obj, map_type_strings[type]);
if (libbpf_get_error(map_data[type])) {
printf("ERROR: finding a map in obj file failed\n");
goto cleanup;
}
map_cnt++;
}
bpf_object__for_each_program(prog, obj) {
tp_links[tp_cnt] = bpf_program__attach(prog);
if (libbpf_get_error(tp_links[tp_cnt])) {
printf("ERROR: bpf_program__attach failed\n");
tp_links[tp_cnt] = NULL;
goto cleanup;
}
tp_cnt++;
}
if (debug) {
print_bpf_prog_info();
}
/* Unload/stop tracepoint event by closing fd's */
/* Unload/stop tracepoint event by closing bpf_link's */
if (errors_only) {
/* The prog_fd[i] and event_fd[i] depend on the
* order the functions was defined in _kern.c
/* The bpf_link[i] depend on the order of
* the functions was defined in _kern.c
*/
close(event_fd[2]); /* tracepoint/xdp/xdp_redirect */
close(prog_fd[2]); /* func: trace_xdp_redirect */
close(event_fd[3]); /* tracepoint/xdp/xdp_redirect_map */
close(prog_fd[3]); /* func: trace_xdp_redirect_map */
bpf_link__destroy(tp_links[2]); /* tracepoint/xdp/xdp_redirect */
tp_links[2] = NULL;
bpf_link__destroy(tp_links[3]); /* tracepoint/xdp/xdp_redirect_map */
tp_links[3] = NULL;
}
stats_poll(interval, errors_only);
ret = EXIT_SUCCESS;
cleanup:
/* Detach tracepoints */
while (tp_cnt)
bpf_link__destroy(tp_links[--tp_cnt]);
bpf_object__close(obj);
return ret;
}

151
samples/bpf/xdp_redirect_cpu_user.c
View file

@ -37,18 +37,35 @@ static __u32 prog_id;
static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
static int n_cpus;
static int cpu_map_fd;
static int rx_cnt_map_fd;
static int redirect_err_cnt_map_fd;
static int cpumap_enqueue_cnt_map_fd;
static int cpumap_kthread_cnt_map_fd;
static int cpus_available_map_fd;
static int cpus_count_map_fd;
static int cpus_iterator_map_fd;
static int exception_cnt_map_fd;
enum map_type {
CPU_MAP,
RX_CNT,
REDIRECT_ERR_CNT,
CPUMAP_ENQUEUE_CNT,
CPUMAP_KTHREAD_CNT,
CPUS_AVAILABLE,
CPUS_COUNT,
CPUS_ITERATOR,
EXCEPTION_CNT,
};
static const char *const map_type_strings[] = {
[CPU_MAP] = "cpu_map",
[RX_CNT] = "rx_cnt",
[REDIRECT_ERR_CNT] = "redirect_err_cnt",
[CPUMAP_ENQUEUE_CNT] = "cpumap_enqueue_cnt",
[CPUMAP_KTHREAD_CNT] = "cpumap_kthread_cnt",
[CPUS_AVAILABLE] = "cpus_available",
[CPUS_COUNT] = "cpus_count",
[CPUS_ITERATOR] = "cpus_iterator",
[EXCEPTION_CNT] = "exception_cnt",
};
#define NUM_TP 5
struct bpf_link *tp_links[NUM_TP] = { 0 };
#define NUM_MAP 9
struct bpf_link *tp_links[NUM_TP] = {};
static int map_fds[NUM_MAP];
static int tp_cnt = 0;
/* Exit return codes */
@ -111,7 +128,7 @@ static void print_avail_progs(struct bpf_object *obj)
bpf_object__for_each_program(pos, obj) {
if (bpf_program__is_xdp(pos))
printf(" %s\n", bpf_program__title(pos, false));
printf(" %s\n", bpf_program__section_name(pos));
}
}
@ -527,20 +544,20 @@ static void stats_collect(struct stats_record *rec)
{
int fd, i;
fd = rx_cnt_map_fd;
fd = map_fds[RX_CNT];
map_collect_percpu(fd, 0, &rec->rx_cnt);
fd = redirect_err_cnt_map_fd;
fd = map_fds[REDIRECT_ERR_CNT];
map_collect_percpu(fd, 1, &rec->redir_err);
fd = cpumap_enqueue_cnt_map_fd;
fd = map_fds[CPUMAP_ENQUEUE_CNT];
for (i = 0; i < n_cpus; i++)
map_collect_percpu(fd, i, &rec->enq[i]);
fd = cpumap_kthread_cnt_map_fd;
fd = map_fds[CPUMAP_KTHREAD_CNT];
map_collect_percpu(fd, 0, &rec->kthread);
fd = exception_cnt_map_fd;
fd = map_fds[EXCEPTION_CNT];
map_collect_percpu(fd, 0, &rec->exception);
}
@ -565,7 +582,7 @@ static int create_cpu_entry(__u32 cpu, struct bpf_cpumap_val *value,
/* Add a CPU entry to cpumap, as this allocate a cpu entry in
* the kernel for the cpu.
*/
ret = bpf_map_update_elem(cpu_map_fd, &cpu, value, 0);
ret = bpf_map_update_elem(map_fds[CPU_MAP], &cpu, value, 0);
if (ret) {
fprintf(stderr, "Create CPU entry failed (err:%d)\n", ret);
exit(EXIT_FAIL_BPF);
@ -574,21 +591,21 @@ static int create_cpu_entry(__u32 cpu, struct bpf_cpumap_val *value,
/* Inform bpf_prog's that a new CPU is available to select
* from via some control maps.
*/
ret = bpf_map_update_elem(cpus_available_map_fd, &avail_idx, &cpu, 0);
ret = bpf_map_update_elem(map_fds[CPUS_AVAILABLE], &avail_idx, &cpu, 0);
if (ret) {
fprintf(stderr, "Add to avail CPUs failed\n");
exit(EXIT_FAIL_BPF);
}
/* When not replacing/updating existing entry, bump the count */
ret = bpf_map_lookup_elem(cpus_count_map_fd, &key, &curr_cpus_count);
ret = bpf_map_lookup_elem(map_fds[CPUS_COUNT], &key, &curr_cpus_count);
if (ret) {
fprintf(stderr, "Failed reading curr cpus_count\n");
exit(EXIT_FAIL_BPF);
}
if (new) {
curr_cpus_count++;
ret = bpf_map_update_elem(cpus_count_map_fd, &key,
ret = bpf_map_update_elem(map_fds[CPUS_COUNT], &key,
&curr_cpus_count, 0);
if (ret) {
fprintf(stderr, "Failed write curr cpus_count\n");
@ -612,7 +629,7 @@ static void mark_cpus_unavailable(void)
int ret, i;
for (i = 0; i < n_cpus; i++) {
ret = bpf_map_update_elem(cpus_available_map_fd, &i,
ret = bpf_map_update_elem(map_fds[CPUS_AVAILABLE], &i,
&invalid_cpu, 0);
if (ret) {
fprintf(stderr, "Failed marking CPU unavailable\n");
@ -665,68 +682,37 @@ static void stats_poll(int interval, bool use_separators, char *prog_name,
free_stats_record(prev);
}
static struct bpf_link * attach_tp(struct bpf_object *obj,
const char *tp_category,
const char* tp_name)
static int init_tracepoints(struct bpf_object *obj)
{
struct bpf_program *prog;
struct bpf_link *link;
char sec_name[PATH_MAX];
int len;
len = snprintf(sec_name, PATH_MAX, "tracepoint/%s/%s",
tp_category, tp_name);
if (len < 0)
exit(EXIT_FAIL);
bpf_object__for_each_program(prog, obj) {
if (bpf_program__is_tracepoint(prog) != true)
continue;
prog = bpf_object__find_program_by_title(obj, sec_name);
if (!prog) {
fprintf(stderr, "ERR: finding progsec: %s\n", sec_name);
exit(EXIT_FAIL_BPF);
tp_links[tp_cnt] = bpf_program__attach(prog);
if (libbpf_get_error(tp_links[tp_cnt])) {
tp_links[tp_cnt] = NULL;
return -EINVAL;
}
tp_cnt++;
}
link = bpf_program__attach_tracepoint(prog, tp_category, tp_name);
if (libbpf_get_error(link))
exit(EXIT_FAIL_BPF);
return link;
}
static void init_tracepoints(struct bpf_object *obj) {
tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_redirect_err");
tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_redirect_map_err");
tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_exception");
tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_cpumap_enqueue");
tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_cpumap_kthread");
return 0;
}
static int init_map_fds(struct bpf_object *obj)
{
/* Maps updated by tracepoints */
redirect_err_cnt_map_fd =
bpf_object__find_map_fd_by_name(obj, "redirect_err_cnt");
exception_cnt_map_fd =
bpf_object__find_map_fd_by_name(obj, "exception_cnt");
cpumap_enqueue_cnt_map_fd =
bpf_object__find_map_fd_by_name(obj, "cpumap_enqueue_cnt");
cpumap_kthread_cnt_map_fd =
bpf_object__find_map_fd_by_name(obj, "cpumap_kthread_cnt");
enum map_type type;
/* Maps used by XDP */
rx_cnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rx_cnt");
cpu_map_fd = bpf_object__find_map_fd_by_name(obj, "cpu_map");
cpus_available_map_fd =
bpf_object__find_map_fd_by_name(obj, "cpus_available");
cpus_count_map_fd = bpf_object__find_map_fd_by_name(obj, "cpus_count");
cpus_iterator_map_fd =
bpf_object__find_map_fd_by_name(obj, "cpus_iterator");
for (type = 0; type < NUM_MAP; type++) {
map_fds[type] =
bpf_object__find_map_fd_by_name(obj,
map_type_strings[type]);
if (cpu_map_fd < 0 || rx_cnt_map_fd < 0 ||
redirect_err_cnt_map_fd < 0 || cpumap_enqueue_cnt_map_fd < 0 ||
cpumap_kthread_cnt_map_fd < 0 || cpus_available_map_fd < 0 ||
cpus_count_map_fd < 0 || cpus_iterator_map_fd < 0 ||
exception_cnt_map_fd < 0)
return -ENOENT;
if (map_fds[type] < 0)
return -ENOENT;
}
return 0;
}
@ -795,13 +781,13 @@ int main(int argc, char **argv)
bool stress_mode = false;
struct bpf_program *prog;
struct bpf_object *obj;
int err = EXIT_FAIL;
char filename[256];
int added_cpus = 0;
int longindex = 0;
int interval = 2;
int add_cpu = -1;
int opt, err;
int prog_fd;
int opt, prog_fd;
int *cpu, i;
__u32 qsize;
@ -824,24 +810,29 @@ int main(int argc, char **argv)
}
if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
return EXIT_FAIL;
return err;
if (prog_fd < 0) {
fprintf(stderr, "ERR: bpf_prog_load_xattr: %s\n",
strerror(errno));
return EXIT_FAIL;
return err;
}
init_tracepoints(obj);
if (init_tracepoints(obj) < 0) {
fprintf(stderr, "ERR: bpf_program__attach failed\n");
return err;
}
if (init_map_fds(obj) < 0) {
fprintf(stderr, "bpf_object__find_map_fd_by_name failed\n");
return EXIT_FAIL;
return err;
}
mark_cpus_unavailable();
cpu = malloc(n_cpus * sizeof(int));
if (!cpu) {
fprintf(stderr, "failed to allocate cpu array\n");
return EXIT_FAIL;
return err;
}
memset(cpu, 0, n_cpus * sizeof(int));
@ -960,14 +951,12 @@ int main(int argc, char **argv)
prog = bpf_object__find_program_by_title(obj, prog_name);
if (!prog) {
fprintf(stderr, "bpf_object__find_program_by_title failed\n");
err = EXIT_FAIL;
goto out;
}
prog_fd = bpf_program__fd(prog);
if (prog_fd < 0) {
fprintf(stderr, "bpf_program__fd failed\n");
err = EXIT_FAIL;
goto out;
}
@ -986,6 +975,8 @@ int main(int argc, char **argv)
stats_poll(interval, use_separators, prog_name, mprog_name,
&value, stress_mode);
err = EXIT_OK;
out:
free(cpu);
return err;

12
samples/bpf/xdp_sample_pkts_kern.c
View file

@ -5,14 +5,12 @@
#include <bpf/bpf_helpers.h>
#define SAMPLE_SIZE 64ul
#define MAX_CPUS 128
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(u32),
.max_entries = MAX_CPUS,
};
struct {
__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
__uint(key_size, sizeof(int));
__uint(value_size, sizeof(u32));
} my_map SEC(".maps");
SEC("xdp_sample")
int xdp_sample_prog(struct xdp_md *ctx)

1
samples/bpf/xdp_sample_pkts_user.c
View file

@ -18,7 +18,6 @@
#include "perf-sys.h"
#define MAX_CPUS 128
static int if_idx;
static char *if_name;
static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;

404
samples/bpf/xdpsock_user.c
View file

@ -11,6 +11,7 @@
#include <linux/if_xdp.h>
#include <linux/if_ether.h>
#include <linux/ip.h>
#include <linux/limits.h>
#include <linux/udp.h>
#include <arpa/inet.h>
#include <locale.h>
@ -78,6 +79,11 @@ static int opt_pkt_count;
static u16 opt_pkt_size = MIN_PKT_SIZE;
static u32 opt_pkt_fill_pattern = 0x12345678;
static bool opt_extra_stats;
static bool opt_quiet;
static bool opt_app_stats;
static const char *opt_irq_str = "";
static u32 irq_no;
static int irqs_at_init = -1;
static int opt_poll;
static int opt_interval = 1;
static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP;
@ -90,18 +96,7 @@ static bool opt_need_wakeup = true;
static u32 opt_num_xsks = 1;
static u32 prog_id;
struct xsk_umem_info {
struct xsk_ring_prod fq;
struct xsk_ring_cons cq;
struct xsk_umem *umem;
void *buffer;
};
struct xsk_socket_info {
struct xsk_ring_cons rx;
struct xsk_ring_prod tx;
struct xsk_umem_info *umem;
struct xsk_socket *xsk;
struct xsk_ring_stats {
unsigned long rx_npkts;
unsigned long tx_npkts;
unsigned long rx_dropped_npkts;
@ -118,6 +113,41 @@ struct xsk_socket_info {
unsigned long prev_rx_full_npkts;
unsigned long prev_rx_fill_empty_npkts;
unsigned long prev_tx_empty_npkts;
};
struct xsk_driver_stats {
unsigned long intrs;
unsigned long prev_intrs;
};
struct xsk_app_stats {
unsigned long rx_empty_polls;
unsigned long fill_fail_polls;
unsigned long copy_tx_sendtos;
unsigned long tx_wakeup_sendtos;
unsigned long opt_polls;
unsigned long prev_rx_empty_polls;
unsigned long prev_fill_fail_polls;
unsigned long prev_copy_tx_sendtos;
unsigned long prev_tx_wakeup_sendtos;
unsigned long prev_opt_polls;
};
struct xsk_umem_info {
struct xsk_ring_prod fq;
struct xsk_ring_cons cq;
struct xsk_umem *umem;
void *buffer;
};
struct xsk_socket_info {
struct xsk_ring_cons rx;
struct xsk_ring_prod tx;
struct xsk_umem_info *umem;
struct xsk_socket *xsk;
struct xsk_ring_stats ring_stats;
struct xsk_app_stats app_stats;
struct xsk_driver_stats drv_stats;
u32 outstanding_tx;
};
@ -172,18 +202,151 @@ static int xsk_get_xdp_stats(int fd, struct xsk_socket_info *xsk)
return err;
if (optlen == sizeof(struct xdp_statistics)) {
xsk->rx_dropped_npkts = stats.rx_dropped;
xsk->rx_invalid_npkts = stats.rx_invalid_descs;
xsk->tx_invalid_npkts = stats.tx_invalid_descs;
xsk->rx_full_npkts = stats.rx_ring_full;
xsk->rx_fill_empty_npkts = stats.rx_fill_ring_empty_descs;
xsk->tx_empty_npkts = stats.tx_ring_empty_descs;
xsk->ring_stats.rx_dropped_npkts = stats.rx_dropped;
xsk->ring_stats.rx_invalid_npkts = stats.rx_invalid_descs;
xsk->ring_stats.tx_invalid_npkts = stats.tx_invalid_descs;
xsk->ring_stats.rx_full_npkts = stats.rx_ring_full;
xsk->ring_stats.rx_fill_empty_npkts = stats.rx_fill_ring_empty_descs;
xsk->ring_stats.tx_empty_npkts = stats.tx_ring_empty_descs;
return 0;
}
return -EINVAL;
}
static void dump_app_stats(long dt)
{
int i;
for (i = 0; i < num_socks && xsks[i]; i++) {
char *fmt = "%-18s %'-14.0f %'-14lu\n";
double rx_empty_polls_ps, fill_fail_polls_ps, copy_tx_sendtos_ps,
tx_wakeup_sendtos_ps, opt_polls_ps;
rx_empty_polls_ps = (xsks[i]->app_stats.rx_empty_polls -
xsks[i]->app_stats.prev_rx_empty_polls) * 1000000000. / dt;
fill_fail_polls_ps = (xsks[i]->app_stats.fill_fail_polls -
xsks[i]->app_stats.prev_fill_fail_polls) * 1000000000. / dt;
copy_tx_sendtos_ps = (xsks[i]->app_stats.copy_tx_sendtos -
xsks[i]->app_stats.prev_copy_tx_sendtos) * 1000000000. / dt;
tx_wakeup_sendtos_ps = (xsks[i]->app_stats.tx_wakeup_sendtos -
xsks[i]->app_stats.prev_tx_wakeup_sendtos)
* 1000000000. / dt;
opt_polls_ps = (xsks[i]->app_stats.opt_polls -
xsks[i]->app_stats.prev_opt_polls) * 1000000000. / dt;
printf("\n%-18s %-14s %-14s\n", "", "calls/s", "count");
printf(fmt, "rx empty polls", rx_empty_polls_ps, xsks[i]->app_stats.rx_empty_polls);
printf(fmt, "fill fail polls", fill_fail_polls_ps,
xsks[i]->app_stats.fill_fail_polls);
printf(fmt, "copy tx sendtos", copy_tx_sendtos_ps,
xsks[i]->app_stats.copy_tx_sendtos);
printf(fmt, "tx wakeup sendtos", tx_wakeup_sendtos_ps,
xsks[i]->app_stats.tx_wakeup_sendtos);
printf(fmt, "opt polls", opt_polls_ps, xsks[i]->app_stats.opt_polls);
xsks[i]->app_stats.prev_rx_empty_polls = xsks[i]->app_stats.rx_empty_polls;
xsks[i]->app_stats.prev_fill_fail_polls = xsks[i]->app_stats.fill_fail_polls;
xsks[i]->app_stats.prev_copy_tx_sendtos = xsks[i]->app_stats.copy_tx_sendtos;
xsks[i]->app_stats.prev_tx_wakeup_sendtos = xsks[i]->app_stats.tx_wakeup_sendtos;
xsks[i]->app_stats.prev_opt_polls = xsks[i]->app_stats.opt_polls;
}
}
static bool get_interrupt_number(void)
{
FILE *f_int_proc;
char line[4096];
bool found = false;
f_int_proc = fopen("/proc/interrupts", "r");
if (f_int_proc == NULL) {
printf("Failed to open /proc/interrupts.\n");
return found;
}
while (!feof(f_int_proc) && !found) {
/* Make sure to read a full line at a time */
if (fgets(line, sizeof(line), f_int_proc) == NULL ||
line[strlen(line) - 1] != '\n') {
printf("Error reading from interrupts file\n");
break;
}
/* Extract interrupt number from line */
if (strstr(line, opt_irq_str) != NULL) {
irq_no = atoi(line);
found = true;
break;
}
}
fclose(f_int_proc);
return found;
}
static int get_irqs(void)
{
char count_path[PATH_MAX];
int total_intrs = -1;
FILE *f_count_proc;
char line[4096];
snprintf(count_path, sizeof(count_path),
"/sys/kernel/irq/%i/per_cpu_count", irq_no);
f_count_proc = fopen(count_path, "r");
if (f_count_proc == NULL) {
printf("Failed to open %s\n", count_path);
return total_intrs;
}
if (fgets(line, sizeof(line), f_count_proc) == NULL ||
line[strlen(line) - 1] != '\n') {
printf("Error reading from %s\n", count_path);
} else {
static const char com[2] = ",";
char *token;
total_intrs = 0;
token = strtok(line, com);
while (token != NULL) {
/* sum up interrupts across all cores */
total_intrs += atoi(token);
token = strtok(NULL, com);
}
}
fclose(f_count_proc);
return total_intrs;
}
static void dump_driver_stats(long dt)
{
int i;
for (i = 0; i < num_socks && xsks[i]; i++) {
char *fmt = "%-18s %'-14.0f %'-14lu\n";
double intrs_ps;
int n_ints = get_irqs();
if (n_ints < 0) {
printf("error getting intr info for intr %i\n", irq_no);
return;
}
xsks[i]->drv_stats.intrs = n_ints - irqs_at_init;
intrs_ps = (xsks[i]->drv_stats.intrs - xsks[i]->drv_stats.prev_intrs) *
1000000000. / dt;
printf("\n%-18s %-14s %-14s\n", "", "intrs/s", "count");
printf(fmt, "irqs", intrs_ps, xsks[i]->drv_stats.intrs);
xsks[i]->drv_stats.prev_intrs = xsks[i]->drv_stats.intrs;
}
}
static void dump_stats(void)
{
unsigned long now = get_nsecs();
@ -193,67 +356,83 @@ static void dump_stats(void)
prev_time = now;
for (i = 0; i < num_socks && xsks[i]; i++) {
char *fmt = "%-15s %'-11.0f %'-11lu\n";
char *fmt = "%-18s %'-14.0f %'-14lu\n";
double rx_pps, tx_pps, dropped_pps, rx_invalid_pps, full_pps, fill_empty_pps,
tx_invalid_pps, tx_empty_pps;
rx_pps = (xsks[i]->rx_npkts - xsks[i]->prev_rx_npkts) *
rx_pps = (xsks[i]->ring_stats.rx_npkts - xsks[i]->ring_stats.prev_rx_npkts) *
1000000000. / dt;
tx_pps = (xsks[i]->tx_npkts - xsks[i]->prev_tx_npkts) *
tx_pps = (xsks[i]->ring_stats.tx_npkts - xsks[i]->ring_stats.prev_tx_npkts) *
1000000000. / dt;
printf("\n sock%d@", i);
print_benchmark(false);
printf("\n");
printf("%-15s %-11s %-11s %-11.2f\n", "", "pps", "pkts",
printf("%-18s %-14s %-14s %-14.2f\n", "", "pps", "pkts",
dt / 1000000000.);
printf(fmt, "rx", rx_pps, xsks[i]->rx_npkts);
printf(fmt, "tx", tx_pps, xsks[i]->tx_npkts);
printf(fmt, "rx", rx_pps, xsks[i]->ring_stats.rx_npkts);
printf(fmt, "tx", tx_pps, xsks[i]->ring_stats.tx_npkts);
xsks[i]->prev_rx_npkts = xsks[i]->rx_npkts;
xsks[i]->prev_tx_npkts = xsks[i]->tx_npkts;
xsks[i]->ring_stats.prev_rx_npkts = xsks[i]->ring_stats.rx_npkts;
xsks[i]->ring_stats.prev_tx_npkts = xsks[i]->ring_stats.tx_npkts;
if (opt_extra_stats) {
if (!xsk_get_xdp_stats(xsk_socket__fd(xsks[i]->xsk), xsks[i])) {
dropped_pps = (xsks[i]->rx_dropped_npkts -
xsks[i]->prev_rx_dropped_npkts) * 1000000000. / dt;
rx_invalid_pps = (xsks[i]->rx_invalid_npkts -
xsks[i]->prev_rx_invalid_npkts) * 1000000000. / dt;
tx_invalid_pps = (xsks[i]->tx_invalid_npkts -
xsks[i]->prev_tx_invalid_npkts) * 1000000000. / dt;
full_pps = (xsks[i]->rx_full_npkts -
xsks[i]->prev_rx_full_npkts) * 1000000000. / dt;
fill_empty_pps = (xsks[i]->rx_fill_empty_npkts -
xsks[i]->prev_rx_fill_empty_npkts)
* 1000000000. / dt;
tx_empty_pps = (xsks[i]->tx_empty_npkts -
xsks[i]->prev_tx_empty_npkts) * 1000000000. / dt;
dropped_pps = (xsks[i]->ring_stats.rx_dropped_npkts -
xsks[i]->ring_stats.prev_rx_dropped_npkts) *
1000000000. / dt;
rx_invalid_pps = (xsks[i]->ring_stats.rx_invalid_npkts -
xsks[i]->ring_stats.prev_rx_invalid_npkts) *
1000000000. / dt;
tx_invalid_pps = (xsks[i]->ring_stats.tx_invalid_npkts -
xsks[i]->ring_stats.prev_tx_invalid_npkts) *
1000000000. / dt;
full_pps = (xsks[i]->ring_stats.rx_full_npkts -
xsks[i]->ring_stats.prev_rx_full_npkts) *
1000000000. / dt;
fill_empty_pps = (xsks[i]->ring_stats.rx_fill_empty_npkts -
xsks[i]->ring_stats.prev_rx_fill_empty_npkts) *
1000000000. / dt;
tx_empty_pps = (xsks[i]->ring_stats.tx_empty_npkts -
xsks[i]->ring_stats.prev_tx_empty_npkts) *
1000000000. / dt;
printf(fmt, "rx dropped", dropped_pps,
xsks[i]->rx_dropped_npkts);
xsks[i]->ring_stats.rx_dropped_npkts);
printf(fmt, "rx invalid", rx_invalid_pps,
xsks[i]->rx_invalid_npkts);
xsks[i]->ring_stats.rx_invalid_npkts);
printf(fmt, "tx invalid", tx_invalid_pps,
xsks[i]->tx_invalid_npkts);
xsks[i]->ring_stats.tx_invalid_npkts);
printf(fmt, "rx queue full", full_pps,
xsks[i]->rx_full_npkts);
xsks[i]->ring_stats.rx_full_npkts);
printf(fmt, "fill ring empty", fill_empty_pps,
xsks[i]->rx_fill_empty_npkts);
xsks[i]->ring_stats.rx_fill_empty_npkts);
printf(fmt, "tx ring empty", tx_empty_pps,
xsks[i]->tx_empty_npkts);
xsks[i]->ring_stats.tx_empty_npkts);
xsks[i]->prev_rx_dropped_npkts = xsks[i]->rx_dropped_npkts;
xsks[i]->prev_rx_invalid_npkts = xsks[i]->rx_invalid_npkts;
xsks[i]->prev_tx_invalid_npkts = xsks[i]->tx_invalid_npkts;
xsks[i]->prev_rx_full_npkts = xsks[i]->rx_full_npkts;
xsks[i]->prev_rx_fill_empty_npkts = xsks[i]->rx_fill_empty_npkts;
xsks[i]->prev_tx_empty_npkts = xsks[i]->tx_empty_npkts;
xsks[i]->ring_stats.prev_rx_dropped_npkts =
xsks[i]->ring_stats.rx_dropped_npkts;
xsks[i]->ring_stats.prev_rx_invalid_npkts =
xsks[i]->ring_stats.rx_invalid_npkts;
xsks[i]->ring_stats.prev_tx_invalid_npkts =
xsks[i]->ring_stats.tx_invalid_npkts;
xsks[i]->ring_stats.prev_rx_full_npkts =
xsks[i]->ring_stats.rx_full_npkts;
xsks[i]->ring_stats.prev_rx_fill_empty_npkts =
xsks[i]->ring_stats.rx_fill_empty_npkts;
xsks[i]->ring_stats.prev_tx_empty_npkts =
xsks[i]->ring_stats.tx_empty_npkts;
} else {
printf("%-15s\n", "Error retrieving extra stats");
}
}
}
if (opt_app_stats)
dump_app_stats(dt);
if (irq_no)
dump_driver_stats(dt);
}
static bool is_benchmark_done(void)
@ -613,7 +792,16 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
{
struct xsk_umem_info *umem;
struct xsk_umem_config cfg = {
.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
/* We recommend that you set the fill ring size >= HW RX ring size +
* AF_XDP RX ring size. Make sure you fill up the fill ring
* with buffers at regular intervals, and you will with this setting
* avoid allocation failures in the driver. These are usually quite
* expensive since drivers have not been written to assume that
* allocation failures are common. For regular sockets, kernel
* allocated memory is used that only runs out in OOM situations
* that should be rare.
*/
.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS * 2,
.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
.frame_size = opt_xsk_frame_size,
.frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM,
@ -640,13 +828,13 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
u32 idx;
ret = xsk_ring_prod__reserve(&umem->fq,
XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx);
if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
XSK_RING_PROD__DEFAULT_NUM_DESCS * 2, &idx);
if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS * 2)
exit_with_error(-ret);
for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++)
for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS * 2; i++)
*xsk_ring_prod__fill_addr(&umem->fq, idx++) =
i * opt_xsk_frame_size;
xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS * 2);
}
static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem,
@ -683,6 +871,17 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem,
if (ret)
exit_with_error(-ret);
xsk->app_stats.rx_empty_polls = 0;
xsk->app_stats.fill_fail_polls = 0;
xsk->app_stats.copy_tx_sendtos = 0;
xsk->app_stats.tx_wakeup_sendtos = 0;
xsk->app_stats.opt_polls = 0;
xsk->app_stats.prev_rx_empty_polls = 0;
xsk->app_stats.prev_fill_fail_polls = 0;
xsk->app_stats.prev_copy_tx_sendtos = 0;
xsk->app_stats.prev_tx_wakeup_sendtos = 0;
xsk->app_stats.prev_opt_polls = 0;
return xsk;
}
@ -709,6 +908,9 @@ static struct option long_options[] = {
{"tx-pkt-size", required_argument, 0, 's'},
{"tx-pkt-pattern", required_argument, 0, 'P'},
{"extra-stats", no_argument, 0, 'x'},
{"quiet", no_argument, 0, 'Q'},
{"app-stats", no_argument, 0, 'a'},
{"irq-string", no_argument, 0, 'I'},
{0, 0, 0, 0}
};
@ -744,6 +946,9 @@ static void usage(const char *prog)
" Min size: %d, Max size %d.\n"
" -P, --tx-pkt-pattern=nPacket fill pattern. Default: 0x%x\n"
" -x, --extra-stats Display extra statistics.\n"
" -Q, --quiet Do not display any stats.\n"
" -a, --app-stats Display application (syscall) statistics.\n"
" -I, --irq-string Display driver interrupt statistics for interface associated with irq-string.\n"
"\n";
fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE,
opt_batch_size, MIN_PKT_SIZE, MIN_PKT_SIZE,
@ -759,7 +964,7 @@ static void parse_command_line(int argc, char **argv)
opterr = 0;
for (;;) {
c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:x",
c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:xQaI:",
long_options, &option_index);
if (c == -1)
break;
@ -842,6 +1047,22 @@ static void parse_command_line(int argc, char **argv)
break;
case 'x':
opt_extra_stats = 1;
break;
case 'Q':
opt_quiet = 1;
break;
case 'a':
opt_app_stats = 1;
break;
case 'I':
opt_irq_str = optarg;
if (get_interrupt_number())
irqs_at_init = get_irqs();
if (irqs_at_init < 0) {
fprintf(stderr, "ERROR: Failed to get irqs for %s\n", opt_irq_str);
usage(basename(argv[0]));
}
break;
default:
usage(basename(argv[0]));
@ -888,8 +1109,15 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk,
if (!xsk->outstanding_tx)
return;
if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx))
/* In copy mode, Tx is driven by a syscall so we need to use e.g. sendto() to
* really send the packets. In zero-copy mode we do not have to do this, since Tx
* is driven by the NAPI loop. So as an optimization, we do not have to call
* sendto() all the time in zero-copy mode for l2fwd.
*/
if (opt_xdp_bind_flags & XDP_COPY) {
xsk->app_stats.copy_tx_sendtos++;
kick_tx(xsk);
}
ndescs = (xsk->outstanding_tx > opt_batch_size) ? opt_batch_size :
xsk->outstanding_tx;
@ -904,8 +1132,10 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk,
while (ret != rcvd) {
if (ret < 0)
exit_with_error(-ret);
if (xsk_ring_prod__needs_wakeup(&umem->fq))
if (xsk_ring_prod__needs_wakeup(&umem->fq)) {
xsk->app_stats.fill_fail_polls++;
ret = poll(fds, num_socks, opt_timeout);
}
ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
}
@ -916,7 +1146,7 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk,
xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
xsk_ring_cons__release(&xsk->umem->cq, rcvd);
xsk->outstanding_tx -= rcvd;
xsk->tx_npkts += rcvd;
xsk->ring_stats.tx_npkts += rcvd;
}
}
@ -929,14 +1159,16 @@ static inline void complete_tx_only(struct xsk_socket_info *xsk,
if (!xsk->outstanding_tx)
return;
if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx))
if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx)) {
xsk->app_stats.tx_wakeup_sendtos++;
kick_tx(xsk);
}
rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx);
if (rcvd > 0) {
xsk_ring_cons__release(&xsk->umem->cq, rcvd);
xsk->outstanding_tx -= rcvd;
xsk->tx_npkts += rcvd;
xsk->ring_stats.tx_npkts += rcvd;
}
}
@ -948,8 +1180,10 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds)
rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx);
if (!rcvd) {
if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq))
if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) {
xsk->app_stats.rx_empty_polls++;
ret = poll(fds, num_socks, opt_timeout);
}
return;
}
@ -957,8 +1191,10 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds)
while (ret != rcvd) {
if (ret < 0)
exit_with_error(-ret);
if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq))
if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) {
xsk->app_stats.fill_fail_polls++;
ret = poll(fds, num_socks, opt_timeout);
}
ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
}
@ -976,7 +1212,7 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds)
xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
xsk_ring_cons__release(&xsk->rx, rcvd);
xsk->rx_npkts += rcvd;
xsk->ring_stats.rx_npkts += rcvd;
}
static void rx_drop_all(void)
@ -991,6 +1227,8 @@ static void rx_drop_all(void)
for (;;) {
if (opt_poll) {
for (i = 0; i < num_socks; i++)
xsks[i]->app_stats.opt_polls++;
ret = poll(fds, num_socks, opt_timeout);
if (ret <= 0)
continue;
@ -1004,7 +1242,7 @@ static void rx_drop_all(void)
}
}
static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb, int batch_size)
static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size)
{
u32 idx;
unsigned int i;
@ -1017,14 +1255,14 @@ static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb, int batch_size)
for (i = 0; i < batch_size; i++) {
struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx,
idx + i);
tx_desc->addr = (frame_nb + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT;
tx_desc->addr = (*frame_nb + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT;
tx_desc->len = PKT_SIZE;
}
xsk_ring_prod__submit(&xsk->tx, batch_size);
xsk->outstanding_tx += batch_size;
frame_nb += batch_size;
frame_nb %= NUM_FRAMES;
*frame_nb += batch_size;
*frame_nb %= NUM_FRAMES;
complete_tx_only(xsk, batch_size);
}
@ -1071,6 +1309,8 @@ static void tx_only_all(void)
int batch_size = get_batch_size(pkt_cnt);
if (opt_poll) {
for (i = 0; i < num_socks; i++)
xsks[i]->app_stats.opt_polls++;
ret = poll(fds, num_socks, opt_timeout);
if (ret <= 0)
continue;
@ -1080,7 +1320,7 @@ static void tx_only_all(void)
}
for (i = 0; i < num_socks; i++)
tx_only(xsks[i], frame_nb[i], batch_size);
tx_only(xsks[i], &frame_nb[i], batch_size);
pkt_cnt += batch_size;
@ -1102,8 +1342,10 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds)
rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx);
if (!rcvd) {
if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq))
if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) {
xsk->app_stats.rx_empty_polls++;
ret = poll(fds, num_socks, opt_timeout);
}
return;
}
@ -1111,8 +1353,11 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds)
while (ret != rcvd) {
if (ret < 0)
exit_with_error(-ret);
if (xsk_ring_prod__needs_wakeup(&xsk->tx))
complete_tx_l2fwd(xsk, fds);
if (xsk_ring_prod__needs_wakeup(&xsk->tx)) {
xsk->app_stats.tx_wakeup_sendtos++;
kick_tx(xsk);
}
ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx);
}
@ -1134,7 +1379,7 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds)
xsk_ring_prod__submit(&xsk->tx, rcvd);
xsk_ring_cons__release(&xsk->rx, rcvd);
xsk->rx_npkts += rcvd;
xsk->ring_stats.rx_npkts += rcvd;
xsk->outstanding_tx += rcvd;
}
@ -1150,6 +1395,8 @@ static void l2fwd_all(void)
for (;;) {
if (opt_poll) {
for (i = 0; i < num_socks; i++)
xsks[i]->app_stats.opt_polls++;
ret = poll(fds, num_socks, opt_timeout);
if (ret <= 0)
continue;
@ -1271,9 +1518,11 @@ int main(int argc, char **argv)
setlocale(LC_ALL, "");
ret = pthread_create(&pt, NULL, poller, NULL);
if (ret)
exit_with_error(ret);
if (!opt_quiet) {
ret = pthread_create(&pt, NULL, poller, NULL);
if (ret)
exit_with_error(ret);
}
prev_time = get_nsecs();
start_time = prev_time;
@ -1287,7 +1536,8 @@ int main(int argc, char **argv)
benchmark_done = true;
pthread_join(pt, NULL);
if (!opt_quiet)
pthread_join(pt, NULL);
xdpsock_cleanup();

1085
samples/bpf/xsk_fwd.c Normal file
View file

File diff suppressed because it is too large Load diff