summaryrefslogtreecommitdiff
path: root/samples
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-05-25 12:22:58 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-05-25 12:22:58 -0700
commit7e062cda7d90543ac8c7700fc7c5527d0c0f22ad (patch)
tree2f1602595d9416be41cc2e88a659ba4c145734b9 /samples
parent5d1772b1739b085721431eef0c0400f3aff01abf (diff)
parent57d7becda9c9e612e6b00676f2eecfac3e719e88 (diff)
Merge tag 'net-next-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Core ---- - Support TCPv6 segmentation offload with super-segments larger than 64k bytes using the IPv6 Jumbogram extension header (AKA BIG TCP). - Generalize skb freeing deferral to per-cpu lists, instead of per-socket lists. - Add a netdev statistic for packets dropped due to L2 address mismatch (rx_otherhost_dropped). - Continue work annotating skb drop reasons. - Accept alternative netdev names (ALT_IFNAME) in more netlink requests. - Add VLAN support for AF_PACKET SOCK_RAW GSO. - Allow receiving skb mark from the socket as a cmsg. - Enable memcg accounting for veth queues, sysctl tables and IPv6. BPF --- - Add libbpf support for User Statically-Defined Tracing (USDTs). - Speed up symbol resolution for kprobes multi-link attachments. - Support storing typed pointers to referenced and unreferenced objects in BPF maps. - Add support for BPF link iterator. - Introduce access to remote CPU map elements in BPF per-cpu map. - Allow middle-of-the-road settings for the kernel.unprivileged_bpf_disabled sysctl. - Implement basic types of dynamic pointers e.g. to allow for dynamically sized ringbuf reservations without extra memory copies. Protocols --------- - Retire port only listening_hash table, add a second bind table hashed by port and address. Avoid linear list walk when binding to very popular ports (e.g. 443). - Add bridge FDB bulk flush filtering support allowing user space to remove all FDB entries matching a condition. - Introduce accept_unsolicited_na sysctl for IPv6 to implement router-side changes for RFC9131. - Support for MPTCP path manager in user space. - Add MPTCP support for fallback to regular TCP for connections that have never connected additional subflows or transmitted out-of-sequence data (partial support for RFC8684 fallback). - Avoid races in MPTCP-level window tracking, stabilize and improve throughput. - Support lockless operation of GRE tunnels with seq numbers enabled. - WiFi support for host based BSS color collision detection. - Add support for SO_TXTIME/SCM_TXTIME on CAN sockets. - Support transmission w/o flow control in CAN ISOTP (ISO 15765-2). - Support zero-copy Tx with TLS 1.2 crypto offload (sendfile). - Allow matching on the number of VLAN tags via tc-flower. - Add tracepoint for tcp_set_ca_state(). Driver API ---------- - Improve error reporting from classifier and action offload. - Add support for listing line cards in switches (devlink). - Add helpers for reporting page pool statistics with ethtool -S. - Add support for reading clock cycles when using PTP virtual clocks, instead of having the driver convert to time before reporting. This makes it possible to report time from different vclocks. - Support configuring low-latency Tx descriptor push via ethtool. - Separate Clause 22 and Clause 45 MDIO accesses more explicitly. New hardware / drivers ---------------------- - Ethernet: - Marvell's Octeon NIC PCI Endpoint support (octeon_ep) - Sunplus SP7021 SoC (sp7021_emac) - Add support for Renesas RZ/V2M (in ravb) - Add support for MediaTek mt7986 switches (in mtk_eth_soc) - Ethernet PHYs: - ADIN1100 industrial PHYs (w/ 10BASE-T1L and SQI reporting) - TI DP83TD510 PHY - Microchip LAN8742/LAN88xx PHYs - WiFi: - Driver for pureLiFi X, XL, XC devices (plfxlc) - Driver for Silicon Labs devices (wfx) - Support for WCN6750 (in ath11k) - Support Realtek 8852ce devices (in rtw89) - Mobile: - MediaTek T700 modems (Intel 5G 5000 M.2 cards) - CAN: - ctucanfd: add support for CTU CAN FD open-source IP core from Czech Technical University in Prague Drivers ------- - Delete a number of old drivers still using virt_to_bus(). - Ethernet NICs: - intel: support TSO on tunnels MPLS - broadcom: support multi-buffer XDP - nfp: support VF rate limiting - sfc: use hardware tx timestamps for more than PTP - mlx5: multi-port eswitch support - hyper-v: add support for XDP_REDIRECT - atlantic: XDP support (including multi-buffer) - macb: improve real-time perf by deferring Tx processing to NAPI - High-speed Ethernet switches: - mlxsw: implement basic line card information querying - prestera: add support for traffic policing on ingress and egress - Embedded Ethernet switches: - lan966x: add support for packet DMA (FDMA) - lan966x: add support for PTP programmable pins - ti: cpsw_new: enable bc/mc storm prevention - Qualcomm 802.11ax WiFi (ath11k): - Wake-on-WLAN support for QCA6390 and WCN6855 - device recovery (firmware restart) support - support setting Specific Absorption Rate (SAR) for WCN6855 - read country code from SMBIOS for WCN6855/QCA6390 - enable keep-alive during WoWLAN suspend - implement remain-on-channel support - MediaTek WiFi (mt76): - support Wireless Ethernet Dispatch offloading packet movement between the Ethernet switch and WiFi interfaces - non-standard VHT MCS10-11 support - mt7921 AP mode support - mt7921 IPv6 NS offload support - Ethernet PHYs: - micrel: ksz9031/ksz9131: cabletest support - lan87xx: SQI support for T1 PHYs - lan937x: add interrupt support for link detection" * tag 'net-next-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1809 commits) ptp: ocp: Add firmware header checks ptp: ocp: fix PPS source selector debugfs reporting ptp: ocp: add .init function for sma_op vector ptp: ocp: vectorize the sma accessor functions ptp: ocp: constify selectors ptp: ocp: parameterize input/output sma selectors ptp: ocp: revise firmware display ptp: ocp: add Celestica timecard PCI ids ptp: ocp: Remove #ifdefs around PCI IDs ptp: ocp: 32-bit fixups for pci start address Revert "net/smc: fix listen processing for SMC-Rv2" ath6kl: Use cc-disable-warning to disable -Wdangling-pointer selftests/bpf: Dynptr tests bpf: Add dynptr data slices bpf: Add bpf_dynptr_read and bpf_dynptr_write bpf: Dynptr support for ring buffers bpf: Add bpf_dynptr_from_mem for local dynptrs bpf: Add verifier support for dynptrs bpf: Suppress 'passing zero to PTR_ERR' warning bpf: Introduce bpf_arch_text_invalidate for bpf_prog_pack ...
Diffstat (limited to 'samples')
-rw-r--r--samples/bpf/Makefile19
-rw-r--r--samples/bpf/cpustat_user.c1
-rw-r--r--samples/bpf/hbm.c5
-rw-r--r--samples/bpf/ibumad_user.c1
-rw-r--r--samples/bpf/map_perf_test_user.c1
-rw-r--r--samples/bpf/offwaketime_user.c1
-rw-r--r--samples/bpf/sockex2_user.c1
-rw-r--r--samples/bpf/sockex3_user.c1
-rw-r--r--samples/bpf/spintest_user.c1
-rw-r--r--samples/bpf/syscall_tp_user.c4
-rw-r--r--samples/bpf/task_fd_query_user.c1
-rw-r--r--samples/bpf/test_lru_dist.c1
-rw-r--r--samples/bpf/test_map_in_map_user.c1
-rw-r--r--samples/bpf/test_overhead_user.c1
-rw-r--r--samples/bpf/tracex2_user.c1
-rw-r--r--samples/bpf/tracex3_user.c1
-rw-r--r--samples/bpf/tracex4_user.c1
-rw-r--r--samples/bpf/tracex5_user.c1
-rw-r--r--samples/bpf/tracex6_user.c1
-rw-r--r--samples/bpf/xdp1_user.c3
-rw-r--r--samples/bpf/xdp_adjust_tail_user.c1
-rw-r--r--samples/bpf/xdp_monitor_user.c1
-rw-r--r--samples/bpf/xdp_redirect_cpu_user.c1
-rw-r--r--samples/bpf/xdp_redirect_map_multi_user.c1
-rw-r--r--samples/bpf/xdp_redirect_user.c1
-rw-r--r--samples/bpf/xdp_router_ipv4.bpf.c180
-rw-r--r--samples/bpf/xdp_router_ipv4_kern.c186
-rw-r--r--samples/bpf/xdp_router_ipv4_user.c456
-rw-r--r--samples/bpf/xdp_rxq_info_user.c23
-rw-r--r--samples/bpf/xdp_sample_pkts_user.c1
-rw-r--r--samples/bpf/xdp_sample_user.c1
-rw-r--r--samples/bpf/xdp_tx_iptunnel_user.c1
-rw-r--r--samples/bpf/xdpsock_user.c9
-rw-r--r--samples/bpf/xsk_fwd.c7
34 files changed, 419 insertions, 497 deletions
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 38638845db9d..03e3d3529ac9 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -96,7 +96,6 @@ test_cgrp2_sock2-objs := test_cgrp2_sock2.o
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 := $(CGROUP_HELPERS) \
test_current_task_under_cgroup_user.o
trace_event-objs := trace_event_user.o $(TRACE_HELPERS)
@@ -124,6 +123,7 @@ xdp_redirect_cpu-objs := xdp_redirect_cpu_user.o $(XDP_SAMPLE)
xdp_redirect_map-objs := xdp_redirect_map_user.o $(XDP_SAMPLE)
xdp_redirect-objs := xdp_redirect_user.o $(XDP_SAMPLE)
xdp_monitor-objs := xdp_monitor_user.o $(XDP_SAMPLE)
+xdp_router_ipv4-objs := xdp_router_ipv4_user.o $(XDP_SAMPLE)
# Tell kbuild to always build the programs
always-y := $(tprogs-y)
@@ -153,7 +153,6 @@ always-y += parse_varlen.o parse_simple.o parse_ldabs.o
always-y += test_cgrp2_tc_kern.o
always-y += xdp1_kern.o
always-y += xdp2_kern.o
-always-y += xdp_router_ipv4_kern.o
always-y += test_current_task_under_cgroup_kern.o
always-y += trace_event_kern.o
always-y += sampleip_kern.o
@@ -220,6 +219,7 @@ TPROGLDLIBS_xdp_redirect += -lm
TPROGLDLIBS_xdp_redirect_cpu += -lm
TPROGLDLIBS_xdp_redirect_map += -lm
TPROGLDLIBS_xdp_redirect_map_multi += -lm
+TPROGLDLIBS_xdp_router_ipv4 += -lm -pthread
TPROGLDLIBS_tracex4 += -lrt
TPROGLDLIBS_trace_output += -lrt
TPROGLDLIBS_map_perf_test += -lrt
@@ -342,6 +342,7 @@ $(obj)/xdp_redirect_map_multi_user.o: $(obj)/xdp_redirect_map_multi.skel.h
$(obj)/xdp_redirect_map_user.o: $(obj)/xdp_redirect_map.skel.h
$(obj)/xdp_redirect_user.o: $(obj)/xdp_redirect.skel.h
$(obj)/xdp_monitor_user.o: $(obj)/xdp_monitor.skel.h
+$(obj)/xdp_router_ipv4_user.o: $(obj)/xdp_router_ipv4.skel.h
$(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h
$(obj)/hbm_out_kern.o: $(src)/hbm.h $(src)/hbm_kern.h
@@ -368,16 +369,15 @@ VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
$(obj)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL)
ifeq ($(VMLINUX_H),)
+ifeq ($(VMLINUX_BTF),)
+ $(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)",\
+ build the kernel or set VMLINUX_BTF or VMLINUX_H variable)
+endif
$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
else
$(Q)cp "$(VMLINUX_H)" $@
endif
-ifeq ($(VMLINUX_BTF),)
- $(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)",\
- build the kernel or set VMLINUX_BTF variable)
-endif
-
clean-files += vmlinux.h
# Get Clang's default includes on this system, as opposed to those seen by
@@ -399,6 +399,7 @@ $(obj)/xdp_redirect_map_multi.bpf.o: $(obj)/xdp_sample.bpf.o
$(obj)/xdp_redirect_map.bpf.o: $(obj)/xdp_sample.bpf.o
$(obj)/xdp_redirect.bpf.o: $(obj)/xdp_sample.bpf.o
$(obj)/xdp_monitor.bpf.o: $(obj)/xdp_sample.bpf.o
+$(obj)/xdp_router_ipv4.bpf.o: $(obj)/xdp_sample.bpf.o
$(obj)/%.bpf.o: $(src)/%.bpf.c $(obj)/vmlinux.h $(src)/xdp_sample.bpf.h $(src)/xdp_sample_shared.h
@echo " CLANG-BPF " $@
@@ -409,7 +410,8 @@ $(obj)/%.bpf.o: $(src)/%.bpf.c $(obj)/vmlinux.h $(src)/xdp_sample.bpf.h $(src)/x
-c $(filter %.bpf.c,$^) -o $@
LINKED_SKELS := xdp_redirect_cpu.skel.h xdp_redirect_map_multi.skel.h \
- xdp_redirect_map.skel.h xdp_redirect.skel.h xdp_monitor.skel.h
+ xdp_redirect_map.skel.h xdp_redirect.skel.h xdp_monitor.skel.h \
+ xdp_router_ipv4.skel.h
clean-files += $(LINKED_SKELS)
xdp_redirect_cpu.skel.h-deps := xdp_redirect_cpu.bpf.o xdp_sample.bpf.o
@@ -417,6 +419,7 @@ xdp_redirect_map_multi.skel.h-deps := xdp_redirect_map_multi.bpf.o xdp_sample.bp
xdp_redirect_map.skel.h-deps := xdp_redirect_map.bpf.o xdp_sample.bpf.o
xdp_redirect.skel.h-deps := xdp_redirect.bpf.o xdp_sample.bpf.o
xdp_monitor.skel.h-deps := xdp_monitor.bpf.o xdp_sample.bpf.o
+xdp_router_ipv4.skel.h-deps := xdp_router_ipv4.bpf.o xdp_sample.bpf.o
LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.bpf.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
diff --git a/samples/bpf/cpustat_user.c b/samples/bpf/cpustat_user.c
index 96675985e9e0..ab90bb08a2b4 100644
--- a/samples/bpf/cpustat_user.c
+++ b/samples/bpf/cpustat_user.c
@@ -13,7 +13,6 @@
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/time.h>
-#include <sys/resource.h>
#include <sys/wait.h>
#include <bpf/bpf.h>
diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c
index 1fe5bcafb3bc..516fbac28b71 100644
--- a/samples/bpf/hbm.c
+++ b/samples/bpf/hbm.c
@@ -34,7 +34,6 @@
#include <stdio.h>
#include <stdlib.h>
#include <assert.h>
-#include <sys/resource.h>
#include <sys/time.h>
#include <unistd.h>
#include <errno.h>
@@ -46,7 +45,6 @@
#include <bpf/bpf.h>
#include <getopt.h>
-#include "bpf_rlimit.h"
#include "cgroup_helpers.h"
#include "hbm.h"
#include "bpf_util.h"
@@ -510,5 +508,8 @@ int main(int argc, char **argv)
prog = argv[optind];
printf("HBM prog: %s\n", prog != NULL ? prog : "NULL");
+ /* Use libbpf 1.0 API mode */
+ libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+
return run_bpf_prog(prog, cg_id);
}
diff --git a/samples/bpf/ibumad_user.c b/samples/bpf/ibumad_user.c
index 0746ca516097..d074c978aac7 100644
--- a/samples/bpf/ibumad_user.c
+++ b/samples/bpf/ibumad_user.c
@@ -19,7 +19,6 @@
#include <sys/types.h>
#include <limits.h>
-#include <sys/resource.h>
#include <getopt.h>
#include <net/if.h>
diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index e69651a6902f..b6fc174ab1f2 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -13,7 +13,6 @@
#include <signal.h>
#include <string.h>
#include <time.h>
-#include <sys/resource.h>
#include <arpa/inet.h>
#include <errno.h>
diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c
index 73a986876c1a..b6eedcb98fb9 100644
--- a/samples/bpf/offwaketime_user.c
+++ b/samples/bpf/offwaketime_user.c
@@ -8,7 +8,6 @@
#include <linux/perf_event.h>
#include <errno.h>
#include <stdbool.h>
-#include <sys/resource.h>
#include <bpf/libbpf.h>
#include <bpf/bpf.h>
#include "trace_helpers.h"
diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c
index 6a3fd369d3fc..2c18471336f0 100644
--- a/samples/bpf/sockex2_user.c
+++ b/samples/bpf/sockex2_user.c
@@ -7,7 +7,6 @@
#include "sock_example.h"
#include <unistd.h>
#include <arpa/inet.h>
-#include <sys/resource.h>
struct pair {
__u64 packets;
diff --git a/samples/bpf/sockex3_user.c b/samples/bpf/sockex3_user.c
index 6ae99ecc766c..cd6fa79df900 100644
--- a/samples/bpf/sockex3_user.c
+++ b/samples/bpf/sockex3_user.c
@@ -6,7 +6,6 @@
#include "sock_example.h"
#include <unistd.h>
#include <arpa/inet.h>
-#include <sys/resource.h>
struct flow_key_record {
__be32 src;
diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c
index 0d7e1e5a8658..aadac14f748a 100644
--- a/samples/bpf/spintest_user.c
+++ b/samples/bpf/spintest_user.c
@@ -3,7 +3,6 @@
#include <unistd.h>
#include <string.h>
#include <assert.h>
-#include <sys/resource.h>
#include <bpf/libbpf.h>
#include <bpf/bpf.h>
#include "trace_helpers.h"
diff --git a/samples/bpf/syscall_tp_user.c b/samples/bpf/syscall_tp_user.c
index a0ebf1833ed3..7a788bb837fc 100644
--- a/samples/bpf/syscall_tp_user.c
+++ b/samples/bpf/syscall_tp_user.c
@@ -8,7 +8,6 @@
#include <string.h>
#include <linux/perf_event.h>
#include <errno.h>
-#include <sys/resource.h>
#include <bpf/libbpf.h>
#include <bpf/bpf.h>
@@ -36,6 +35,9 @@ static void verify_map(int map_id)
fprintf(stderr, "failed: map #%d returns value 0\n", map_id);
return;
}
+
+ printf("verify map:%d val: %d\n", map_id, val);
+
val = 0;
if (bpf_map_update_elem(map_id, &key, &val, BPF_ANY) != 0) {
fprintf(stderr, "map_update failed: %s\n", strerror(errno));
diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c
index c9a0ca8351fd..424718c0872c 100644
--- a/samples/bpf/task_fd_query_user.c
+++ b/samples/bpf/task_fd_query_user.c
@@ -10,7 +10,6 @@
#include <fcntl.h>
#include <linux/bpf.h>
#include <sys/ioctl.h>
-#include <sys/resource.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <linux/perf_event.h>
diff --git a/samples/bpf/test_lru_dist.c b/samples/bpf/test_lru_dist.c
index 75e877853596..be98ccb4952f 100644
--- a/samples/bpf/test_lru_dist.c
+++ b/samples/bpf/test_lru_dist.c
@@ -13,7 +13,6 @@
#include <sched.h>
#include <sys/wait.h>
#include <sys/stat.h>
-#include <sys/resource.h>
#include <fcntl.h>
#include <stdlib.h>
#include <time.h>
diff --git a/samples/bpf/test_map_in_map_user.c b/samples/bpf/test_map_in_map_user.c
index 472d65c70354..e8b4cc184ac9 100644
--- a/samples/bpf/test_map_in_map_user.c
+++ b/samples/bpf/test_map_in_map_user.c
@@ -2,7 +2,6 @@
/*
* Copyright (c) 2017 Facebook
*/
-#include <sys/resource.h>
#include <sys/socket.h>
#include <arpa/inet.h>
#include <stdint.h>
diff --git a/samples/bpf/test_overhead_user.c b/samples/bpf/test_overhead_user.c
index 4821f9d99c1f..88717f8ec6ac 100644
--- a/samples/bpf/test_overhead_user.c
+++ b/samples/bpf/test_overhead_user.c
@@ -16,7 +16,6 @@
#include <linux/bpf.h>
#include <string.h>
#include <time.h>
-#include <sys/resource.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c
index 1626d51dfffd..dd6205c6b6a7 100644
--- a/samples/bpf/tracex2_user.c
+++ b/samples/bpf/tracex2_user.c
@@ -4,7 +4,6 @@
#include <stdlib.h>
#include <signal.h>
#include <string.h>
-#include <sys/resource.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
diff --git a/samples/bpf/tracex3_user.c b/samples/bpf/tracex3_user.c
index 33e16ba39f25..d5eebace31e6 100644
--- a/samples/bpf/tracex3_user.c
+++ b/samples/bpf/tracex3_user.c
@@ -7,7 +7,6 @@
#include <unistd.h>
#include <stdbool.h>
#include <string.h>
-#include <sys/resource.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
diff --git a/samples/bpf/tracex4_user.c b/samples/bpf/tracex4_user.c
index 566e6440e8c2..227b05a0bc88 100644
--- a/samples/bpf/tracex4_user.c
+++ b/samples/bpf/tracex4_user.c
@@ -8,7 +8,6 @@
#include <stdbool.h>
#include <string.h>
#include <time.h>
-#include <sys/resource.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
diff --git a/samples/bpf/tracex5_user.c b/samples/bpf/tracex5_user.c
index 08dfdc77ad2a..e910dc265c31 100644
--- a/samples/bpf/tracex5_user.c
+++ b/samples/bpf/tracex5_user.c
@@ -7,7 +7,6 @@
#include <sys/prctl.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
-#include <sys/resource.h>
#include "trace_helpers.h"
#ifdef __mips__
diff --git a/samples/bpf/tracex6_user.c b/samples/bpf/tracex6_user.c
index 28296f40c133..8e83bf2a84a4 100644
--- a/samples/bpf/tracex6_user.c
+++ b/samples/bpf/tracex6_user.c
@@ -8,7 +8,6 @@
#include <stdio.h>
#include <stdlib.h>
#include <sys/ioctl.h>
-#include <sys/resource.h>
#include <sys/time.h>
#include <sys/types.h>
#include <sys/wait.h>
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index 631f0cabe139..ac370e638fa3 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -11,7 +11,6 @@
#include <string.h>
#include <unistd.h>
#include <libgen.h>
-#include <sys/resource.h>
#include <net/if.h>
#include "bpf_util.h"
@@ -161,7 +160,7 @@ int main(int argc, char **argv)
}
prog_id = info.id;
- poll_stats(map_fd, 2);
+ poll_stats(map_fd, 1);
return 0;
}
diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c
index b3f6e49676ed..167646077c8f 100644
--- a/samples/bpf/xdp_adjust_tail_user.c
+++ b/samples/bpf/xdp_adjust_tail_user.c
@@ -14,7 +14,6 @@
#include <stdlib.h>
#include <string.h>
#include <net/if.h>
-#include <sys/resource.h>
#include <arpa/inet.h>
#include <netinet/ether.h>
#include <unistd.h>
diff --git a/samples/bpf/xdp_monitor_user.c b/samples/bpf/xdp_monitor_user.c
index fb9391a5ec62..58015eb2ffae 100644
--- a/samples/bpf/xdp_monitor_user.c
+++ b/samples/bpf/xdp_monitor_user.c
@@ -17,7 +17,6 @@ static const char *__doc_err_only__=
#include <ctype.h>
#include <unistd.h>
#include <locale.h>
-#include <sys/resource.h>
#include <getopt.h>
#include <net/if.h>
#include <time.h>
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index 5f74a70a9021..a12381c37d2b 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -21,7 +21,6 @@ static const char *__doc__ =
#include <string.h>
#include <unistd.h>
#include <locale.h>
-#include <sys/resource.h>
#include <sys/sysinfo.h>
#include <getopt.h>
#include <net/if.h>
diff --git a/samples/bpf/xdp_redirect_map_multi_user.c b/samples/bpf/xdp_redirect_map_multi_user.c
index 315314716121..9e24f2705b67 100644
--- a/samples/bpf/xdp_redirect_map_multi_user.c
+++ b/samples/bpf/xdp_redirect_map_multi_user.c
@@ -15,7 +15,6 @@ static const char *__doc__ =
#include <net/if.h>
#include <unistd.h>
#include <libgen.h>
-#include <sys/resource.h>
#include <sys/ioctl.h>
#include <sys/types.h>
#include <sys/socket.h>
diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c
index 7af5b07a7523..8663dd631b6e 100644
--- a/samples/bpf/xdp_redirect_user.c
+++ b/samples/bpf/xdp_redirect_user.c
@@ -18,7 +18,6 @@ static const char *__doc__ =
#include <unistd.h>
#include <libgen.h>
#include <getopt.h>
-#include <sys/resource.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
#include "bpf_util.h"
diff --git a/samples/bpf/xdp_router_ipv4.bpf.c b/samples/bpf/xdp_router_ipv4.bpf.c
new file mode 100644
index 000000000000..248119ca7938
--- /dev/null
+++ b/samples/bpf/xdp_router_ipv4.bpf.c
@@ -0,0 +1,180 @@
+/* Copyright (C) 2017 Cavium, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#include "vmlinux.h"
+#include "xdp_sample.bpf.h"
+#include "xdp_sample_shared.h"
+
+#define ETH_ALEN 6
+#define ETH_P_8021Q 0x8100
+#define ETH_P_8021AD 0x88A8
+
+struct trie_value {
+ __u8 prefix[4];
+ __be64 value;
+ int ifindex;
+ int metric;
+ __be32 gw;
+};
+
+/* Key for lpm_trie */
+union key_4 {
+ u32 b32[2];
+ u8 b8[8];
+};
+
+struct arp_entry {
+ __be64 mac;
+ __be32 dst;
+};
+
+struct direct_map {
+ struct arp_entry arp;
+ int ifindex;
+ __be64 mac;
+};
+
+/* Map for trie implementation */
+struct {
+ __uint(type, BPF_MAP_TYPE_LPM_TRIE);
+ __uint(key_size, 8);
+ __uint(value_size, sizeof(struct trie_value));
+ __uint(max_entries, 50);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+} lpm_map SEC(".maps");
+
+/* Map for ARP table */
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __type(key, __be32);
+ __type(value, __be64);
+ __uint(max_entries, 50);
+} arp_table SEC(".maps");
+
+/* Map to keep the exact match entries in the route table */
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __type(key, __be32);
+ __type(value, struct direct_map);
+ __uint(max_entries, 50);
+} exact_match SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(int));
+ __uint(max_entries, 100);
+} tx_port SEC(".maps");
+
+SEC("xdp")
+int xdp_router_ipv4_prog(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct ethhdr *eth = data;
+ u64 nh_off = sizeof(*eth);
+ struct datarec *rec;
+ __be16 h_proto;
+ u32 key = 0;
+
+ rec = bpf_map_lookup_elem(&rx_cnt, &key);
+ if (rec)
+ NO_TEAR_INC(rec->processed);
+
+ if (data + nh_off > data_end)
+ goto drop;
+
+ h_proto = eth->h_proto;
+ if (h_proto == bpf_htons(ETH_P_8021Q) ||
+ h_proto == bpf_htons(ETH_P_8021AD)) {
+ struct vlan_hdr *vhdr;
+
+ vhdr = data + nh_off;
+ nh_off += sizeof(struct vlan_hdr);
+ if (data + nh_off > data_end)
+ goto drop;
+
+ h_proto = vhdr->h_vlan_encapsulated_proto;
+ }
+
+ switch (bpf_ntohs(h_proto)) {
+ case ETH_P_ARP:
+ if (rec)
+ NO_TEAR_INC(rec->xdp_pass);
+ return XDP_PASS;
+ case ETH_P_IP: {
+ struct iphdr *iph = data + nh_off;
+ struct direct_map *direct_entry;
+ __be64 *dest_mac, *src_mac;
+ int forward_to;
+
+ if (iph + 1 > data_end)
+ goto drop;
+
+ direct_entry = bpf_map_lookup_elem(&exact_match, &iph->daddr);
+
+ /* Check for exact match, this would give a faster lookup */
+ if (direct_entry && direct_entry->mac &&
+ direct_entry->arp.mac) {
+ src_mac = &direct_entry->mac;
+ dest_mac = &direct_entry->arp.mac;
+ forward_to = direct_entry->ifindex;
+ } else {
+ struct trie_value *prefix_value;
+ union key_4 key4;
+
+ /* Look up in the trie for lpm */
+ key4.b32[0] = 32;
+ key4.b8[4] = iph->daddr & 0xff;
+ key4.b8[5] = (iph->daddr >> 8) & 0xff;
+ key4.b8[6] = (iph->daddr >> 16) & 0xff;
+ key4.b8[7] = (iph->daddr >> 24) & 0xff;
+
+ prefix_value = bpf_map_lookup_elem(&lpm_map, &key4);
+ if (!prefix_value)
+ goto drop;
+
+ forward_to = prefix_value->ifindex;
+ src_mac = &prefix_value->value;
+ if (!src_mac)
+ goto drop;
+
+ dest_mac = bpf_map_lookup_elem(&arp_table, &iph->daddr);
+ if (!dest_mac) {
+ if (!prefix_value->gw)
+ goto drop;
+
+ dest_mac = bpf_map_lookup_elem(&arp_table,
+ &prefix_value->gw);
+ }
+ }
+
+ if (src_mac && dest_mac) {
+ int ret;
+
+ __builtin_memcpy(eth->h_dest, dest_mac, ETH_ALEN);
+ __builtin_memcpy(eth->h_source, src_mac, ETH_ALEN);
+
+ ret = bpf_redirect_map(&tx_port, forward_to, 0);
+ if (ret == XDP_REDIRECT) {
+ if (rec)
+ NO_TEAR_INC(rec->xdp_redirect);
+ return ret;
+ }
+ }
+ }
+ default:
+ break;
+ }
+drop:
+ if (rec)
+ NO_TEAR_INC(rec->xdp_drop);
+
+ return XDP_DROP;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_router_ipv4_kern.c b/samples/bpf/xdp_router_ipv4_kern.c
deleted file mode 100644
index b37ca2b13063..000000000000
--- a/samples/bpf/xdp_router_ipv4_kern.c
+++ /dev/null
@@ -1,186 +0,0 @@
-/* Copyright (C) 2017 Cavium, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License
- * as published by the Free Software Foundation.
- */
-#define KBUILD_MODNAME "foo"
-#include <uapi/linux/bpf.h>
-#include <linux/in.h>
-#include <linux/if_ether.h>
-#include <linux/if_packet.h>
-#include <linux/if_vlan.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <bpf/bpf_helpers.h>
-#include <linux/slab.h>
-#include <net/ip_fib.h>
-
-struct trie_value {
- __u8 prefix[4];
- __be64 value;
- int ifindex;
- int metric;
- __be32 gw;
-};
-
-/* Key for lpm_trie*/
-union key_4 {
- u32 b32[2];
- u8 b8[8];
-};
-
-struct arp_entry {
- __be64 mac;
- __be32 dst;
-};
-
-struct direct_map {
- struct arp_entry arp;
- int ifindex;
- __be64 mac;
-};
-
-/* Map for trie implementation*/
-struct {
- __uint(type, BPF_MAP_TYPE_LPM_TRIE);
- __uint(key_size, 8);
- __uint(value_size, sizeof(struct trie_value));
- __uint(max_entries, 50);
- __uint(map_flags, BPF_F_NO_PREALLOC);
-} lpm_map SEC(".maps");
-
-/* Map for counter*/
-struct {
- __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
- __type(key, u32);
- __type(value, u64);
- __uint(max_entries, 256);
-} rxcnt SEC(".maps");
-
-/* Map for ARP table*/
-struct {
- __uint(type, BPF_MAP_TYPE_HASH);
- __type(key, __be32);
- __type(value, __be64);
- __uint(max_entries, 50);
-} arp_table SEC(".maps");
-
-/* Map to keep the exact match entries in the route table*/
-struct {
- __uint(type, BPF_MAP_TYPE_HASH);
- __type(key, __be32);
- __type(value, struct direct_map);
- __uint(max_entries, 50);
-} exact_match SEC(".maps");
-
-struct {
- __uint(type, BPF_MAP_TYPE_DEVMAP);
- __uint(key_size, sizeof(int));
- __uint(value_size, sizeof(int));
- __uint(max_entries, 100);
-} tx_port SEC(".maps");
-
-/* Function to set source and destination mac of the packet */
-static inline void set_src_dst_mac(void *data, void *src, void *dst)
-{
- unsigned short *source = src;
- unsigned short *dest = dst;
- unsigned short *p = data;
-
- __builtin_memcpy(p, dest, 6);
- __builtin_memcpy(p + 3, source, 6);
-}
-
-/* Parse IPV4 packet to get SRC, DST IP and protocol */
-static inline int parse_ipv4(void *data, u64 nh_off, void *data_end,
- __be32 *src, __be32 *dest)
-{
- struct iphdr *iph = data + nh_off;
-
- if (iph + 1 > data_end)
- return 0;
- *src = iph->saddr;
- *dest = iph->daddr;
- return iph->protocol;
-}
-
-SEC("xdp_router_ipv4")
-int xdp_router_ipv4_prog(struct xdp_md *ctx)
-{
- void *data_end = (void *)(long)ctx->data_end;
- __be64 *dest_mac = NULL, *src_mac = NULL;
- void *data = (void *)(long)ctx->data;
- struct trie_value *prefix_value;
- int rc = XDP_DROP, forward_to;
- struct ethhdr *eth = data;
- union key_4 key4;
- long *value;
- u16 h_proto;
- u32 ipproto;
- u64 nh_off;
-
- nh_off = sizeof(*eth);
- if (data + nh_off > data_end)
- return rc;
-
- h_proto = eth->h_proto;
-
- if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) {
- struct vlan_hdr *vhdr;
-
- vhdr = data + nh_off;
- nh_off += sizeof(struct vlan_hdr);
- if (data + nh_off > data_end)
- return rc;
- h_proto = vhdr->h_vlan_encapsulated_proto;
- }
- if (h_proto == htons(ETH_P_ARP)) {
- return XDP_PASS;
- } else if (h_proto == htons(ETH_P_IP)) {
- struct direct_map *direct_entry;
- __be32 src_ip = 0, dest_ip = 0;
-
- ipproto = parse_ipv4(data, nh_off, data_end, &src_ip, &dest_ip);
- direct_entry = bpf_map_lookup_elem(&exact_match, &dest_ip);
- /* Check for exact match, this would give a faster lookup*/
- if (direct_entry && direct_entry->mac && direct_entry->arp.mac) {
- src_mac = &direct_entry->mac;
- dest_mac = &direct_entry->arp.mac;
- forward_to = direct_entry->ifindex;
- } else {
- /* Look up in the trie for lpm*/
- key4.b32[0] = 32;
- key4.b8[4] = dest_ip & 0xff;
- key4.b8[5] = (dest_ip >> 8) & 0xff;
- key4.b8[6] = (dest_ip >> 16) & 0xff;
- key4.b8[7] = (dest_ip >> 24) & 0xff;
- prefix_value = bpf_map_lookup_elem(&lpm_map, &key4);
- if (!prefix_value)
- return XDP_DROP;
- src_mac = &prefix_value->value;
- if (!src_mac)
- return XDP_DROP;
- dest_mac = bpf_map_lookup_elem(&arp_table, &dest_ip);
- if (!dest_mac) {
- if (!prefix_value->gw)
- return XDP_DROP;
- dest_ip = prefix_value->gw;
- dest_mac = bpf_map_lookup_elem(&arp_table, &dest_ip);
- }
- forward_to = prefix_value->ifindex;
- }
- } else {
- ipproto = 0;
- }
- if (src_mac && dest_mac) {
- set_src_dst_mac(data, src_mac, dest_mac);
- value = bpf_map_lookup_elem(&rxcnt, &ipproto);
- if (value)
- *value += 1;
- return bpf_redirect_map(&tx_port, forward_to, 0);
- }
- return rc;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c
index 6dae87d83e1c..294fc15ad1cb 100644
--- a/samples/bpf/xdp_router_ipv4_user.c
+++ b/samples/bpf/xdp_router_ipv4_user.c
@@ -22,72 +22,41 @@
#include <sys/syscall.h>
#include "bpf_util.h"
#include <bpf/libbpf.h>
-#include <sys/resource.h>
#include <libgen.h>
+#include <getopt.h>
+#include <pthread.h>
+#include "xdp_sample_user.h"
+#include "xdp_router_ipv4.skel.h"
-int sock, sock_arp, flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-static int total_ifindex;
-static int *ifindex_list;
-static __u32 *prog_id_list;
-char buf[8192];
+static const char *__doc__ =
+"XDP IPv4 router implementation\n"
+"Usage: xdp_router_ipv4 <IFNAME-0> ... <IFNAME-N>\n";
+
+static char buf[8192];
static int lpm_map_fd;
-static int rxcnt_map_fd;
static int arp_table_map_fd;
static int exact_match_map_fd;
static int tx_port_map_fd;
-static int get_route_table(int rtm_family);
-static void int_exit(int sig)
-{
- __u32 prog_id = 0;
- int i = 0;
+static bool routes_thread_exit;
+static int interval = 5;
- for (i = 0; i < total_ifindex; i++) {
- if (bpf_xdp_query_id(ifindex_list[i], flags, &prog_id)) {
- printf("bpf_xdp_query_id on iface %d failed\n",
- ifindex_list[i]);
- exit(1);
- }
- if (prog_id_list[i] == prog_id)
- bpf_xdp_detach(ifindex_list[i], flags, NULL);
- else if (!prog_id)
- printf("couldn't find a prog id on iface %d\n",
- ifindex_list[i]);
- else
- printf("program on iface %d changed, not removing\n",
- ifindex_list[i]);
- prog_id = 0;
- }
- exit(0);
-}
+static int mask = SAMPLE_RX_CNT | SAMPLE_REDIRECT_ERR_MAP_CNT |
+ SAMPLE_DEVMAP_XMIT_CNT_MULTI | SAMPLE_EXCEPTION_CNT;
-static void close_and_exit(int sig)
-{
- close(sock);
- close(sock_arp);
+DEFINE_SAMPLE_INIT(xdp_router_ipv4);
- int_exit(0);
-}
+static const struct option long_options[] = {
+ { "help", no_argument, NULL, 'h' },
+ { "skb-mode", no_argument, NULL, 'S' },
+ { "force", no_argument, NULL, 'F' },
+ { "interval", required_argument, NULL, 'i' },
+ { "verbose", no_argument, NULL, 'v' },
+ { "stats", no_argument, NULL, 's' },
+ {}
+};
-/* Get the mac address of the interface given interface name */
-static __be64 getmac(char *iface)
-{
- struct ifreq ifr;
- __be64 mac = 0;
- int fd, i;
-
- fd = socket(AF_INET, SOCK_DGRAM, 0);
- ifr.ifr_addr.sa_family = AF_INET;
- strncpy(ifr.ifr_name, iface, IFNAMSIZ - 1);
- if (ioctl(fd, SIOCGIFHWADDR, &ifr) < 0) {
- printf("ioctl failed leaving....\n");
- return -1;
- }
- for (i = 0; i < 6 ; i++)
- *((__u8 *)&mac + i) = (__u8)ifr.ifr_hwaddr.sa_data[i];
- close(fd);
- return mac;
-}
+static int get_route_table(int rtm_family);
static int recv_msg(struct sockaddr_nl sock_addr, int sock)
{
@@ -130,7 +99,6 @@ static void read_route(struct nlmsghdr *nh, int nll)
int i;
struct route_table {
int dst_len, iface, metric;
- char *iface_name;
__be32 dst, gw;
__be64 mac;
} route;
@@ -145,17 +113,7 @@ static void read_route(struct nlmsghdr *nh, int nll)
__be64 mac;
} direct_entry;
- if (nh->nlmsg_type == RTM_DELROUTE)
- printf("DELETING Route entry\n");
- else if (nh->nlmsg_type == RTM_GETROUTE)
- printf("READING Route entry\n");
- else if (nh->nlmsg_type == RTM_NEWROUTE)
- printf("NEW Route entry\n");
- else
- printf("%d\n", nh->nlmsg_type);
-
memset(&route, 0, sizeof(route));
- printf("Destination Gateway Genmask Metric Iface\n");
for (; NLMSG_OK(nh, nll); nh = NLMSG_NEXT(nh, nll)) {
rt_msg = (struct rtmsg *)NLMSG_DATA(nh);
rtm_family = rt_msg->rtm_family;
@@ -192,11 +150,7 @@ static void read_route(struct nlmsghdr *nh, int nll)
route.gw = atoi(gws);
route.iface = atoi(ifs);
route.metric = atoi(metrics);
- route.iface_name = alloca(sizeof(char *) * IFNAMSIZ);
- route.iface_name = if_indextoname(route.iface, route.iface_name);
- route.mac = getmac(route.iface_name);
- if (route.mac == -1)
- int_exit(0);
+ assert(get_mac_addr(route.iface, &route.mac) == 0);
assert(bpf_map_update_elem(tx_port_map_fd,
&route.iface, &route.iface, 0) == 0);
if (rtm_family == AF_INET) {
@@ -207,7 +161,6 @@ static void read_route(struct nlmsghdr *nh, int nll)
int metric;
__be32 gw;
} *prefix_value;
- struct in_addr dst_addr, gw_addr, mask_addr;
prefix_key = alloca(sizeof(*prefix_key) + 3);
prefix_value = alloca(sizeof(*prefix_value));
@@ -235,17 +188,6 @@ static void read_route(struct nlmsghdr *nh, int nll)
for (i = 0; i < 4; i++)
prefix_key->data[i] = (route.dst >> i * 8) & 0xff;
- dst_addr.s_addr = route.dst;
- printf("%-16s", inet_ntoa(dst_addr));
-
- gw_addr.s_addr = route.gw;
- printf("%-16s", inet_ntoa(gw_addr));
-
- mask_addr.s_addr = htonl(~(0xffffffffU >> route.dst_len));
- printf("%-16s%-7d%s\n", inet_ntoa(mask_addr),
- route.metric,
- route.iface_name);
-
if (bpf_map_lookup_elem(lpm_map_fd, prefix_key,
prefix_value) < 0) {
for (i = 0; i < 4; i++)
@@ -261,13 +203,6 @@ static void read_route(struct nlmsghdr *nh, int nll)
) == 0);
} else {
if (nh->nlmsg_type == RTM_DELROUTE) {
- printf("deleting entry\n");
- printf("prefix key=%d.%d.%d.%d/%d",
- prefix_key->data[0],
- prefix_key->data[1],
- prefix_key->data[2],
- prefix_key->data[3],
- prefix_key->prefixlen);
assert(bpf_map_delete_elem(lpm_map_fd,
prefix_key
) == 0);
@@ -331,14 +266,14 @@ static int get_route_table(int rtm_family)
sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
if (sock < 0) {
- printf("open netlink socket: %s\n", strerror(errno));
- return -1;
+ fprintf(stderr, "open netlink socket: %s\n", strerror(errno));
+ return -errno;
}
memset(&sa, 0, sizeof(sa));
sa.nl_family = AF_NETLINK;
if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
- printf("bind to netlink: %s\n", strerror(errno));
- ret = -1;
+ fprintf(stderr, "bind netlink socket: %s\n", strerror(errno));
+ ret = -errno;
goto cleanup;
}
memset(&req, 0, sizeof(req));
@@ -357,15 +292,15 @@ static int get_route_table(int rtm_family)
msg.msg_iovlen = 1;
ret = sendmsg(sock, &msg, 0);
if (ret < 0) {
- printf("send to netlink: %s\n", strerror(errno));
- ret = -1;
+ fprintf(stderr, "send to netlink: %s\n", strerror(errno));
+ ret = -errno;
goto cleanup;
}
memset(buf, 0, sizeof(buf));
nll = recv_msg(sa, sock);
if (nll < 0) {
- printf("recv from netlink: %s\n", strerror(nll));
- ret = -1;
+ fprintf(stderr, "recv from netlink: %s\n", strerror(nll));
+ ret = nll;
goto cleanup;
}
nh = (struct nlmsghdr *)buf;
@@ -395,14 +330,7 @@ static void read_arp(struct nlmsghdr *nh, int nll)
__be64 mac;
} direct_entry;
- if (nh->nlmsg_type == RTM_GETNEIGH)
- printf("READING arp entry\n");
- printf("Address HwAddress\n");
for (; NLMSG_OK(nh, nll); nh = NLMSG_NEXT(nh, nll)) {
- struct in_addr dst_addr;
- char mac_str[18];
- int len = 0, i;
-
rt_msg = (struct ndmsg *)NLMSG_DATA(nh);
rt_attr = (struct rtattr *)RTM_RTA(rt_msg);
ndm_family = rt_msg->ndm_family;
@@ -424,13 +352,6 @@ static void read_arp(struct nlmsghdr *nh, int nll)
arp_entry.dst = atoi(dsts);
arp_entry.mac = atol(mac);
- dst_addr.s_addr = arp_entry.dst;
- for (i = 0; i < 6; i++)
- len += snprintf(mac_str + len, 18 - len, "%02llx%s",
- ((arp_entry.mac >> i * 8) & 0xff),
- i < 5 ? ":" : "");
- printf("%-16s%s\n", inet_ntoa(dst_addr), mac_str);
-
if (ndm_family == AF_INET) {
if (bpf_map_lookup_elem(exact_match_map_fd,
&arp_entry.dst,
@@ -481,14 +402,14 @@ static int get_arp_table(int rtm_family)
sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
if (sock < 0) {
- printf("open netlink socket: %s\n", strerror(errno));
- return -1;
+ fprintf(stderr, "open netlink socket: %s\n", strerror(errno));
+ return -errno;
}
memset(&sa, 0, sizeof(sa));
sa.nl_family = AF_NETLINK;
if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
- printf("bind to netlink: %s\n", strerror(errno));
- ret = -1;
+ fprintf(stderr, "bind netlink socket: %s\n", strerror(errno));
+ ret = -errno;
goto cleanup;
}
memset(&req, 0, sizeof(req));
@@ -506,15 +427,15 @@ static int get_arp_table(int rtm_family)
msg.msg_iovlen = 1;
ret = sendmsg(sock, &msg, 0);
if (ret < 0) {
- printf("send to netlink: %s\n", strerror(errno));
- ret = -1;
+ fprintf(stderr, "send to netlink: %s\n", strerror(errno));
+ ret = -errno;
goto cleanup;
}
memset(buf, 0, sizeof(buf));
nll = recv_msg(sa, sock);
if (nll < 0) {
- printf("recv from netlink: %s\n", strerror(nll));
- ret = -1;
+ fprintf(stderr, "recv from netlink: %s\n", strerror(nll));
+ ret = nll;
goto cleanup;
}
nh = (struct nlmsghdr *)buf;
@@ -527,24 +448,17 @@ cleanup:
/* Function to keep track and update changes in route and arp table
* Give regular statistics of packets forwarded
*/
-static int monitor_route(void)
+static void *monitor_routes_thread(void *arg)
{
- unsigned int nr_cpus = bpf_num_possible_cpus();
- const unsigned int nr_keys = 256;
struct pollfd fds_route, fds_arp;
- __u64 prev[nr_keys][nr_cpus];
struct sockaddr_nl la, lr;
- __u64 values[nr_cpus];
+ int sock, sock_arp, nll;
struct nlmsghdr *nh;
- int nll, ret = 0;
- int interval = 5;
- __u32 key;
- int i;
sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
if (sock < 0) {
- printf("open netlink socket: %s\n", strerror(errno));
- return -1;
+ fprintf(stderr, "open netlink socket: %s\n", strerror(errno));
+ return NULL;
}
fcntl(sock, F_SETFL, O_NONBLOCK);
@@ -552,17 +466,19 @@ static int monitor_route(void)
lr.nl_family = AF_NETLINK;
lr.nl_groups = RTMGRP_IPV6_ROUTE | RTMGRP_IPV4_ROUTE | RTMGRP_NOTIFY;
if (bind(sock, (struct sockaddr *)&lr, sizeof(lr)) < 0) {
- printf("bind to netlink: %s\n", strerror(errno));
- ret = -1;
- goto cleanup;
+ fprintf(stderr, "bind netlink socket: %s\n", strerror(errno));
+ close(sock);
+ return NULL;
}
+
fds_route.fd = sock;
fds_route.events = POLL_IN;
sock_arp = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
if (sock_arp < 0) {
- printf("open netlink socket: %s\n", strerror(errno));
- return -1;
+ fprintf(stderr, "open netlink socket: %s\n", strerror(errno));
+ close(sock);
+ return NULL;
}
fcntl(sock_arp, F_SETFL, O_NONBLOCK);
@@ -570,51 +486,44 @@ static int monitor_route(void)
la.nl_family = AF_NETLINK;
la.nl_groups = RTMGRP_NEIGH | RTMGRP_NOTIFY;
if (bind(sock_arp, (struct sockaddr *)&la, sizeof(la)) < 0) {
- printf("bind to netlink: %s\n", strerror(errno));
- ret = -1;
+ fprintf(stderr, "bind netlink socket: %s\n", strerror(errno));
goto cleanup;
}
+
fds_arp.fd = sock_arp;
fds_arp.events = POLL_IN;
- memset(prev, 0, sizeof(prev));
- do {
- signal(SIGINT, close_and_exit);
- signal(SIGTERM, close_and_exit);
+ /* dump route and arp tables */
+ if (get_arp_table(AF_INET) < 0) {
+ fprintf(stderr, "Failed reading arp table\n");
+ goto cleanup;
+ }
- sleep(interval);
- for (key = 0; key < nr_keys; key++) {
- __u64 sum = 0;
-
- assert(bpf_map_lookup_elem(rxcnt_map_fd,
- &key, values) == 0);
- for (i = 0; i < nr_cpus; i++)
- sum += (values[i] - prev[key][i]);
- if (sum)
- printf("proto %u: %10llu pkt/s\n",
- key, sum / interval);
- memcpy(prev[key], values, sizeof(values));
- }
+ if (get_route_table(AF_INET) < 0) {
+ fprintf(stderr, "Failed reading route table\n");
+ goto cleanup;
+ }
+ while (!routes_thread_exit) {
memset(buf, 0, sizeof(buf));
if (poll(&fds_route, 1, 3) == POLL_IN) {
nll = recv_msg(lr, sock);
if (nll < 0) {
- printf("recv from netlink: %s\n", strerror(nll));
- ret = -1;
+ fprintf(stderr, "recv from netlink: %s\n",
+ strerror(nll));
goto cleanup;
}
nh = (struct nlmsghdr *)buf;
- printf("Routing table updated.\n");
read_route(nh, nll);
}
+
memset(buf, 0, sizeof(buf));
if (poll(&fds_arp, 1, 3) == POLL_IN) {
nll = recv_msg(la, sock_arp);
if (nll < 0) {
- printf("recv from netlink: %s\n", strerror(nll));
- ret = -1;
+ fprintf(stderr, "recv from netlink: %s\n",
+ strerror(nll));
goto cleanup;
}
@@ -622,132 +531,169 @@ static int monitor_route(void)
read_arp(nh, nll);
}
- } while (1);
+ sleep(interval);
+ }
+
cleanup:
+ close(sock_arp);
close(sock);
- return ret;
+ return NULL;
}
-static void usage(const char *prog)
+static void usage(char *argv[], const struct option *long_options,
+ const char *doc, int mask, bool error,
+ struct bpf_object *obj)
{
- fprintf(stderr,
- "%s: %s [OPTS] interface name list\n\n"
- "OPTS:\n"
- " -S use skb-mode\n"
- " -F force loading prog\n",
- __func__, prog);
+ sample_usage(argv, long_options, doc, mask, error);
}
-int main(int ac, char **argv)
+int main(int argc, char **argv)
{
- struct bpf_prog_info info = {};
- __u32 info_len = sizeof(info);
- const char *optstr = "SF";
- struct bpf_program *prog;
- struct bpf_object *obj;
- char filename[256];
- char **ifname_list;
- int prog_fd, opt;
- int err, i = 1;
-
- snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
-
- total_ifindex = ac - 1;
- ifname_list = (argv + 1);
-
- while ((opt = getopt(ac, argv, optstr)) != -1) {
+ bool error = true, generic = false, force = false;
+ int opt, ret = EXIT_FAIL_BPF;
+ struct xdp_router_ipv4 *skel;
+ int i, total_ifindex = argc - 1;
+ char **ifname_list = argv + 1;
+ pthread_t routes_thread;
+ int longindex = 0;
+
+ if (libbpf_set_strict_mode(LIBBPF_STRICT_ALL) < 0) {
+ fprintf(stderr, "Failed to set libbpf strict mode: %s\n",
+ strerror(errno));
+ goto end;
+ }
+
+ skel = xdp_router_ipv4__open();
+ if (!skel) {
+ fprintf(stderr, "Failed to xdp_router_ipv4__open: %s\n",
+ strerror(errno));
+ goto end;
+ }
+
+ ret = sample_init_pre_load(skel);
+ if (ret < 0) {
+ fprintf(stderr, "Failed to sample_init_pre_load: %s\n",
+ strerror(-ret));
+ ret = EXIT_FAIL_BPF;
+ goto end_destroy;
+ }
+
+ ret = xdp_router_ipv4__load(skel);
+ if (ret < 0) {
+ fprintf(stderr, "Failed to xdp_router_ipv4__load: %s\n",
+ strerror(errno));
+ goto end_destroy;
+ }
+
+ ret = sample_init(skel, mask);
+ if (ret < 0) {
+ fprintf(stderr, "Failed to initialize sample: %s\n", strerror(-ret));
+ ret = EXIT_FAIL;
+ goto end_destroy;
+ }
+
+ while ((opt = getopt_long(argc, argv, "si:SFvh",
+ long_options, &longindex)) != -1) {
switch (opt) {
+ case 's':
+ mask |= SAMPLE_REDIRECT_MAP_CNT;
+ total_ifindex--;
+ ifname_list++;
+ break;
+ case 'i':
+ interval = strtoul(optarg, NULL, 0);
+ total_ifindex -= 2;
+ ifname_list += 2;
+ break;
case 'S':
- flags |= XDP_FLAGS_SKB_MODE;
+ generic = true;
total_ifindex--;
ifname_list++;
break;
case 'F':
- flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+ force = true;
total_ifindex--;
ifname_list++;
break;
+ case 'v':
+ sample_switch_mode();
+ total_ifindex--;
+ ifname_list++;
+ break;
+ case 'h':
+ error = false;
default:
- usage(basename(argv[0]));
- return 1;
+ usage(argv, long_options, __doc__, mask, error, skel->obj);
+ goto end_destroy;
}
}
- if (!(flags & XDP_FLAGS_SKB_MODE))
- flags |= XDP_FLAGS_DRV_MODE;
-
- if (optind == ac) {
- usage(basename(argv[0]));
- return 1;
+ ret = EXIT_FAIL_OPTION;
+ if (optind == argc) {
+ usage(argv, long_options, __doc__, mask, true, skel->obj);
+ goto end_destroy;
}
- obj = bpf_object__open_file(filename, NULL);
- if (libbpf_get_error(obj))
- return 1;
-
- prog = bpf_object__next_program(obj, NULL);
- bpf_program__set_type(prog, BPF_PROG_TYPE_XDP);
-
- printf("\n******************loading bpf file*********************\n");
- err = bpf_object__load(obj);
- if (err) {
- printf("bpf_object__load(): %s\n", strerror(errno));
- return 1;
+ lpm_map_fd = bpf_map__fd(skel->maps.lpm_map);
+ if (lpm_map_fd < 0) {
+ fprintf(stderr, "Failed loading lpm_map %s\n",
+ strerror(-lpm_map_fd));
+ goto end_destroy;
}
- prog_fd = bpf_program__fd(prog);
-
- lpm_map_fd = bpf_object__find_map_fd_by_name(obj, "lpm_map");
- rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt");
- arp_table_map_fd = bpf_object__find_map_fd_by_name(obj, "arp_table");
- exact_match_map_fd = bpf_object__find_map_fd_by_name(obj,
- "exact_match");
- tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port");
- if (lpm_map_fd < 0 || rxcnt_map_fd < 0 || arp_table_map_fd < 0 ||
- exact_match_map_fd < 0 || tx_port_map_fd < 0) {
- printf("bpf_object__find_map_fd_by_name failed\n");
- return 1;
+ arp_table_map_fd = bpf_map__fd(skel->maps.arp_table);
+ if (arp_table_map_fd < 0) {
+ fprintf(stderr, "Failed loading arp_table_map_fd %s\n",
+ strerror(-arp_table_map_fd));
+ goto end_destroy;
}
-
- ifindex_list = (int *)calloc(total_ifindex, sizeof(int *));
- for (i = 0; i < total_ifindex; i++) {
- ifindex_list[i] = if_nametoindex(ifname_list[i]);
- if (!ifindex_list[i]) {
- printf("Couldn't translate interface name: %s",
- strerror(errno));
- return 1;
- }
+ exact_match_map_fd = bpf_map__fd(skel->maps.exact_match);
+ if (exact_match_map_fd < 0) {
+ fprintf(stderr, "Failed loading exact_match_map_fd %s\n",
+ strerror(-exact_match_map_fd));
+ goto end_destroy;
+ }
+ tx_port_map_fd = bpf_map__fd(skel->maps.tx_port);
+ if (tx_port_map_fd < 0) {
+ fprintf(stderr, "Failed loading tx_port_map_fd %s\n",
+ strerror(-tx_port_map_fd));
+ goto end_destroy;
}
- prog_id_list = (__u32 *)calloc(total_ifindex, sizeof(__u32 *));
- for (i = 0; i < total_ifindex; i++) {
- if (bpf_xdp_attach(ifindex_list[i], prog_fd, flags, NULL) < 0) {
- printf("link set xdp fd failed\n");
- int recovery_index = i;
- for (i = 0; i < recovery_index; i++)
- bpf_xdp_detach(ifindex_list[i], flags, NULL);
+ ret = EXIT_FAIL_XDP;
+ for (i = 0; i < total_ifindex; i++) {
+ int index = if_nametoindex(ifname_list[i]);
- return 1;
+ if (!index) {
+ fprintf(stderr, "Interface %s not found %s\n",
+ ifname_list[i], strerror(-tx_port_map_fd));
+ goto end_destroy;
}
- err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
- if (err) {
- printf("can't get prog info - %s\n", strerror(errno));
- return err;
- }
- prog_id_list[i] = info.id;
- memset(&info, 0, sizeof(info));
- printf("Attached to %d\n", ifindex_list[i]);
+ if (sample_install_xdp(skel->progs.xdp_router_ipv4_prog,
+ index, generic, force) < 0)
+ goto end_destroy;
}
- signal(SIGINT, int_exit);
- signal(SIGTERM, int_exit);
- printf("\n*******************ROUTE TABLE*************************\n");
- get_route_table(AF_INET);
- printf("\n*******************ARP TABLE***************************\n");
- get_arp_table(AF_INET);
- if (monitor_route() < 0) {
- printf("Error in receiving route update");
- return 1;
+ ret = pthread_create(&routes_thread, NULL, monitor_routes_thread, NULL);
+ if (ret) {
+ fprintf(stderr, "Failed creating routes_thread: %s\n", strerror(-ret));
+ ret = EXIT_FAIL;
+ goto end_destroy;
}
- return 0;
+ ret = sample_run(interval, NULL, NULL);
+ routes_thread_exit = true;
+
+ if (ret < 0) {
+ fprintf(stderr, "Failed during sample run: %s\n", strerror(-ret));
+ ret = EXIT_FAIL;
+ goto end_thread_wait;
+ }
+ ret = EXIT_OK;
+
+end_thread_wait:
+ pthread_join(routes_thread, NULL);
+end_destroy:
+ xdp_router_ipv4__destroy(skel);
+end:
+ sample_exit(ret);
}
diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c
index f2d90cba5164..08f5331d2b00 100644
--- a/samples/bpf/xdp_rxq_info_user.c
+++ b/samples/bpf/xdp_rxq_info_user.c
@@ -14,11 +14,10 @@ static const char *__doc__ = " XDP RX-queue info extract example\n\n"
#include <string.h>
#include <unistd.h>
#include <locale.h>
-#include <sys/resource.h>
#include <getopt.h>
#include <net/if.h>
#include <time.h>
-
+#include <limits.h>
#include <arpa/inet.h>
#include <linux/if_link.h>
@@ -44,6 +43,9 @@ static struct bpf_map *rx_queue_index_map;
#define EXIT_FAIL_BPF 4
#define EXIT_FAIL_MEM 5
+#define FAIL_MEM_SIG INT_MAX
+#define FAIL_STAT_SIG (INT_MAX - 1)
+
static const struct option long_options[] = {
{"help", no_argument, NULL, 'h' },
{"dev", required_argument, NULL, 'd' },
@@ -77,6 +79,12 @@ static void int_exit(int sig)
printf("program on interface changed, not removing\n");
}
}
+
+ if (sig == FAIL_MEM_SIG)
+ exit(EXIT_FAIL_MEM);
+ else if (sig == FAIL_STAT_SIG)
+ exit(EXIT_FAIL);
+
exit(EXIT_OK);
}
@@ -141,7 +149,8 @@ static char* options2str(enum cfg_options_flags flag)
if (flag & READ_MEM)
return "read";
fprintf(stderr, "ERR: Unknown config option flags");
- exit(EXIT_FAIL);
+ int_exit(FAIL_STAT_SIG);
+ return "unknown";
}
static void usage(char *argv[])
@@ -174,7 +183,7 @@ static __u64 gettime(void)
res = clock_gettime(CLOCK_MONOTONIC, &t);
if (res < 0) {
fprintf(stderr, "Error with gettimeofday! (%i)\n", res);
- exit(EXIT_FAIL);
+ int_exit(FAIL_STAT_SIG);
}
return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
}
@@ -202,7 +211,7 @@ static struct datarec *alloc_record_per_cpu(void)
array = calloc(nr_cpus, sizeof(struct datarec));
if (!array) {
fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus);
- exit(EXIT_FAIL_MEM);
+ int_exit(FAIL_MEM_SIG);
}
return array;
}
@@ -215,7 +224,7 @@ static struct record *alloc_record_per_rxq(void)
array = calloc(nr_rxqs, sizeof(struct record));
if (!array) {
fprintf(stderr, "Mem alloc error (nr_rxqs:%u)\n", nr_rxqs);
- exit(EXIT_FAIL_MEM);
+ int_exit(FAIL_MEM_SIG);
}
return array;
}
@@ -229,7 +238,7 @@ static struct stats_record *alloc_stats_record(void)
rec = calloc(1, sizeof(struct stats_record));
if (!rec) {
fprintf(stderr, "Mem alloc error\n");
- exit(EXIT_FAIL_MEM);
+ int_exit(FAIL_MEM_SIG);
}
rec->rxq = alloc_record_per_rxq();
for (i = 0; i < nr_rxqs; i++)
diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c
index 0a2b3e997aed..7df7163239ac 100644
--- a/samples/bpf/xdp_sample_pkts_user.c
+++ b/samples/bpf/xdp_sample_pkts_user.c
@@ -12,7 +12,6 @@
#include <signal.h>
#include <bpf/libbpf.h>
#include <bpf/bpf.h>
-#include <sys/resource.h>
#include <libgen.h>
#include <linux/if_link.h>
diff --git a/samples/bpf/xdp_sample_user.c b/samples/bpf/xdp_sample_user.c
index c4332d068b91..158682852162 100644
--- a/samples/bpf/xdp_sample_user.c
+++ b/samples/bpf/xdp_sample_user.c
@@ -25,7 +25,6 @@
#include <string.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
-#include <sys/resource.h>
#include <sys/signalfd.h>
#include <sys/sysinfo.h>
#include <sys/timerfd.h>
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
index 2e811e4331cc..307baef6861a 100644
--- a/samples/bpf/xdp_tx_iptunnel_user.c
+++ b/samples/bpf/xdp_tx_iptunnel_user.c
@@ -10,7 +10,6 @@
#include <stdlib.h>
#include <string.h>
#include <net/if.h>
-#include <sys/resource.h>
#include <arpa/inet.h>
#include <netinet/ether.h>
#include <unistd.h>
diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index 6f3fe30ad283..be7d2572e3e6 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -25,7 +25,6 @@
#include <string.h>
#include <sys/capability.h>
#include <sys/mman.h>
-#include <sys/resource.h>
#include <sys/socket.h>
#include <sys/types.h>
#include <sys/un.h>
@@ -1886,7 +1885,6 @@ int main(int argc, char **argv)
{
struct __user_cap_header_struct hdr = { _LINUX_CAPABILITY_VERSION_3, 0 };
struct __user_cap_data_struct data[2] = { { 0 } };
- struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
bool rx = false, tx = false;
struct sched_param schparam;
struct xsk_umem_info *umem;
@@ -1917,11 +1915,8 @@ int main(int argc, char **argv)
data[1].effective, data[1].inheritable, data[1].permitted);
}
} else {
- if (setrlimit(RLIMIT_MEMLOCK, &r)) {
- fprintf(stderr, "ERROR: setrlimit(RLIMIT_MEMLOCK) \"%s\"\n",
- strerror(errno));
- exit(EXIT_FAILURE);
- }
+ /* Use libbpf 1.0 API mode */
+ libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
if (opt_num_xsks > 1)
load_xdp_program(argv, &obj);
diff --git a/samples/bpf/xsk_fwd.c b/samples/bpf/xsk_fwd.c
index 2220509588a0..2324e18ccc7e 100644
--- a/samples/bpf/xsk_fwd.c
+++ b/samples/bpf/xsk_fwd.c
@@ -10,7 +10,6 @@
#include <stdlib.h>
#include <string.h>
#include <sys/mman.h>
-#include <sys/resource.h>
#include <sys/socket.h>
#include <sys/types.h>
#include <time.h>
@@ -131,7 +130,6 @@ static struct bpool *
bpool_init(struct bpool_params *params,
struct xsk_umem_config *umem_cfg)
{
- struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
u64 n_slabs, n_slabs_reserved, n_buffers, n_buffers_reserved;
u64 slabs_size, slabs_reserved_size;
u64 buffers_size, buffers_reserved_size;
@@ -140,9 +138,8 @@ bpool_init(struct bpool_params *params,
u8 *p;
int status;
- /* mmap prep. */
- if (setrlimit(RLIMIT_MEMLOCK, &r))
- return NULL;
+ /* Use libbpf 1.0 API mode */
+ libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
/* bpool internals dimensioning. */
n_slabs = (params->n_buffers + params->n_buffers_per_slab - 1) /