summaryrefslogtreecommitdiff
path: root/samples
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-12-13 15:47:48 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2022-12-13 15:47:48 -0800
commit7e68dd7d07a28faa2e6574dd6b9dbd90cdeaae91 (patch)
treeae0427c5a3b905f24b3a44b510a9bcf35d9b67a3 /samples
parent1ca06f1c1acecbe02124f14a37cce347b8c1a90c (diff)
parent7c4a6309e27f411743817fe74a832ec2d2798a4b (diff)
Merge tag 'net-next-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Paolo Abeni: "Core: - Allow live renaming when an interface is up - Add retpoline wrappers for tc, improving considerably the performances of complex queue discipline configurations - Add inet drop monitor support - A few GRO performance improvements - Add infrastructure for atomic dev stats, addressing long standing data races - De-duplicate common code between OVS and conntrack offloading infrastructure - A bunch of UBSAN_BOUNDS/FORTIFY_SOURCE improvements - Netfilter: introduce packet parser for tunneled packets - Replace IPVS timer-based estimators with kthreads to scale up the workload with the number of available CPUs - Add the helper support for connection-tracking OVS offload BPF: - Support for user defined BPF objects: the use case is to allocate own objects, build own object hierarchies and use the building blocks to build own data structures flexibly, for example, linked lists in BPF - Make cgroup local storage available to non-cgroup attached BPF programs - Avoid unnecessary deadlock detection and failures wrt BPF task storage helpers - A relevant bunch of BPF verifier fixes and improvements - Veristat tool improvements to support custom filtering, sorting, and replay of results - Add LLVM disassembler as default library for dumping JITed code - Lots of new BPF documentation for various BPF maps - Add bpf_rcu_read_{,un}lock() support for sleepable programs - Add RCU grace period chaining to BPF to wait for the completion of access from both sleepable and non-sleepable BPF programs - Add support storing struct task_struct objects as kptrs in maps - Improve helper UAPI by explicitly defining BPF_FUNC_xxx integer values - Add libbpf *_opts API-variants for bpf_*_get_fd_by_id() functions Protocols: - TCP: implement Protective Load Balancing across switch links - TCP: allow dynamically disabling TCP-MD5 static key, reverting back to fast[er]-path - UDP: Introduce optional per-netns hash lookup table - IPv6: simplify and cleanup sockets disposal - Netlink: support different type policies for each generic netlink operation - MPTCP: add MSG_FASTOPEN and FastOpen listener side support - MPTCP: add netlink notification support for listener sockets events - SCTP: add VRF support, allowing sctp sockets binding to VRF devices - Add bridging MAC Authentication Bypass (MAB) support - Extensions for Ethernet VPN bridging implementation to better support multicast scenarios - More work for Wi-Fi 7 support, comprising conversion of all the existing drivers to internal TX queue usage - IPSec: introduce a new offload type (packet offload) allowing complete header processing and crypto offloading - IPSec: extended ack support for more descriptive XFRM error reporting - RXRPC: increase SACK table size and move processing into a per-local endpoint kernel thread, reducing considerably the required locking - IEEE 802154: synchronous send frame and extended filtering support, initial support for scanning available 15.4 networks - Tun: bump the link speed from 10Mbps to 10Gbps - Tun/VirtioNet: implement UDP segmentation offload support Driver API: - PHY/SFP: improve power level switching between standard level 1 and the higher power levels - New API for netdev <-> devlink_port linkage - PTP: convert existing drivers to new frequency adjustment implementation - DSA: add support for rx offloading - Autoload DSA tagging driver when dynamically changing protocol - Add new PCP and APPTRUST attributes to Data Center Bridging - Add configuration support for 800Gbps link speed - Add devlink port function attribute to enable/disable RoCE and migratable - Extend devlink-rate to support strict prioriry and weighted fair queuing - Add devlink support to directly reading from region memory - New device tree helper to fetch MAC address from nvmem - New big TCP helper to simplify temporary header stripping New hardware / drivers: - Ethernet: - Marvel Octeon CNF95N and CN10KB Ethernet Switches - Marvel Prestera AC5X Ethernet Switch - WangXun 10 Gigabit NIC - Motorcomm yt8521 Gigabit Ethernet - Microchip ksz9563 Gigabit Ethernet Switch - Microsoft Azure Network Adapter - Linux Automation 10Base-T1L adapter - PHY: - Aquantia AQR112 and AQR412 - Motorcomm YT8531S - PTP: - Orolia ART-CARD - WiFi: - MediaTek Wi-Fi 7 (802.11be) devices - RealTek rtw8821cu, rtw8822bu, rtw8822cu and rtw8723du USB devices - Bluetooth: - Broadcom BCM4377/4378/4387 Bluetooth chipsets - Realtek RTL8852BE and RTL8723DS - Cypress.CYW4373A0 WiFi + Bluetooth combo device Drivers: - CAN: - gs_usb: bus error reporting support - kvaser_usb: listen only and bus error reporting support - Ethernet NICs: - Intel (100G): - extend action skbedit to RX queue mapping - implement devlink-rate support - support direct read from memory - nVidia/Mellanox (mlx5): - SW steering improvements, increasing rules update rate - Support for enhanced events compression - extend H/W offload packet manipulation capabilities - implement IPSec packet offload mode - nVidia/Mellanox (mlx4): - better big TCP support - Netronome Ethernet NICs (nfp): - IPsec offload support - add support for multicast filter - Broadcom: - RSS and PTP support improvements - AMD/SolarFlare: - netlink extened ack improvements - add basic flower matches to offload, and related stats - Virtual NICs: - ibmvnic: introduce affinity hint support - small / embedded: - FreeScale fec: add initial XDP support - Marvel mv643xx_eth: support MII/GMII/RGMII modes for Kirkwood - TI am65-cpsw: add suspend/resume support - Mediatek MT7986: add RX wireless wthernet dispatch support - Realtek 8169: enable GRO software interrupt coalescing per default - Ethernet high-speed switches: - Microchip (sparx5): - add support for Sparx5 TC/flower H/W offload via VCAP - Mellanox mlxsw: - add 802.1X and MAC Authentication Bypass offload support - add ip6gre support - Embedded Ethernet switches: - Mediatek (mtk_eth_soc): - improve PCS implementation, add DSA untag support - enable flow offload support - Renesas: - add rswitch R-Car Gen4 gPTP support - Microchip (lan966x): - add full XDP support - add TC H/W offload via VCAP - enable PTP on bridge interfaces - Microchip (ksz8): - add MTU support for KSZ8 series - Qualcomm 802.11ax WiFi (ath11k): - support configuring channel dwell time during scan - MediaTek WiFi (mt76): - enable Wireless Ethernet Dispatch (WED) offload support - add ack signal support - enable coredump support - remain_on_channel support - Intel WiFi (iwlwifi): - enable Wi-Fi 7 Extremely High Throughput (EHT) PHY capabilities - 320 MHz channels support - RealTek WiFi (rtw89): - new dynamic header firmware format support - wake-over-WLAN support" * tag 'net-next-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2002 commits) ipvs: fix type warning in do_div() on 32 bit net: lan966x: Remove a useless test in lan966x_ptp_add_trap() net: ipa: add IPA v4.7 support dt-bindings: net: qcom,ipa: Add SM6350 compatible bnxt: Use generic HBH removal helper in tx path IPv6/GRO: generic helper to remove temporary HBH/jumbo header in driver selftests: forwarding: Add bridge MDB test selftests: forwarding: Rename bridge_mdb test bridge: mcast: Support replacement of MDB port group entries bridge: mcast: Allow user space to specify MDB entry routing protocol bridge: mcast: Allow user space to add (*, G) with a source list and filter mode bridge: mcast: Add support for (*, G) with a source list and filter mode bridge: mcast: Avoid arming group timer when (S, G) corresponds to a source bridge: mcast: Add a flag for user installed source entries bridge: mcast: Expose __br_multicast_del_group_src() bridge: mcast: Expose br_multicast_new_group_src() bridge: mcast: Add a centralized error path bridge: mcast: Place netlink policy before validation functions bridge: mcast: Split (*, G) and (S, G) addition into different functions bridge: mcast: Do not derive entry type from its filter mode ...
Diffstat (limited to 'samples')
-rw-r--r--samples/bpf/README.rst6
-rw-r--r--samples/bpf/hbm_edt_kern.c2
-rw-r--r--samples/bpf/sockex3_kern.c95
-rw-r--r--samples/bpf/sockex3_user.c23
-rwxr-xr-xsamples/bpf/test_cgrp2_tc.sh2
-rw-r--r--samples/bpf/tracex2_kern.c4
-rw-r--r--samples/bpf/tracex2_user.c3
-rw-r--r--samples/bpf/xdp1_user.c2
-rw-r--r--samples/bpf/xdp2_kern.c4
-rw-r--r--samples/bpf/xdp_router_ipv4_user.c2
-rw-r--r--samples/pktgen/functions.sh2
11 files changed, 79 insertions, 66 deletions
diff --git a/samples/bpf/README.rst b/samples/bpf/README.rst
index 60c6494adb1b..57f93edd1957 100644
--- a/samples/bpf/README.rst
+++ b/samples/bpf/README.rst
@@ -37,8 +37,8 @@ user, simply call::
make headers_install
-This will creates a local "usr/include" directory in the git/build top
-level directory, that the make system automatically pickup first.
+This will create a local "usr/include" directory in the git/build top
+level directory, that the make system will automatically pick up first.
Compiling
=========
@@ -87,7 +87,7 @@ Cross compiling samples
-----------------------
In order to cross-compile, say for arm64 targets, export CROSS_COMPILE and ARCH
environment variables before calling make. But do this before clean,
-cofiguration and header install steps described above. This will direct make to
+configuration and header install steps described above. This will direct make to
build samples for the cross target::
export ARCH=arm64
diff --git a/samples/bpf/hbm_edt_kern.c b/samples/bpf/hbm_edt_kern.c
index a65b677acdb0..6294f1d716c0 100644
--- a/samples/bpf/hbm_edt_kern.c
+++ b/samples/bpf/hbm_edt_kern.c
@@ -35,7 +35,7 @@
*
* If the credit is below the drop threshold, the packet is dropped. If it
* is a TCP packet, then it also calls tcp_cwr since packets dropped by
- * by a cgroup skb BPF program do not automatically trigger a call to
+ * a cgroup skb BPF program do not automatically trigger a call to
* tcp_cwr in the current kernel code.
*
* This BPF program actually uses 2 drop thresholds, one threshold
diff --git a/samples/bpf/sockex3_kern.c b/samples/bpf/sockex3_kern.c
index b363503357e5..822c13242251 100644
--- a/samples/bpf/sockex3_kern.c
+++ b/samples/bpf/sockex3_kern.c
@@ -17,48 +17,11 @@
#define IP_MF 0x2000
#define IP_OFFSET 0x1FFF
-#define PROG(F) SEC("socket/"__stringify(F)) int bpf_func_##F
-
-struct {
- __uint(type, BPF_MAP_TYPE_PROG_ARRAY);
- __uint(key_size, sizeof(u32));
- __uint(value_size, sizeof(u32));
- __uint(max_entries, 8);
-} jmp_table SEC(".maps");
-
#define PARSE_VLAN 1
#define PARSE_MPLS 2
#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 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);
- break;
- case ETH_P_MPLS_UC:
- case ETH_P_MPLS_MC:
- bpf_tail_call(skb, &jmp_table, PARSE_MPLS);
- break;
- case ETH_P_IP:
- bpf_tail_call(skb, &jmp_table, PARSE_IP);
- break;
- case ETH_P_IPV6:
- bpf_tail_call(skb, &jmp_table, PARSE_IPV6);
- break;
- }
-}
-
struct vlan_hdr {
__be16 h_vlan_TCI;
__be16 h_vlan_encapsulated_proto;
@@ -74,6 +37,8 @@ struct flow_key_record {
__u32 ip_proto;
};
+static inline void parse_eth_proto(struct __sk_buff *skb, u32 proto);
+
static inline int ip_is_fragment(struct __sk_buff *ctx, __u64 nhoff)
{
return load_half(ctx, nhoff + offsetof(struct iphdr, frag_off))
@@ -189,7 +154,8 @@ static __always_inline void parse_ip_proto(struct __sk_buff *skb,
}
}
-PROG(PARSE_IP)(struct __sk_buff *skb)
+SEC("socket")
+int bpf_func_ip(struct __sk_buff *skb)
{
struct globals *g = this_cpu_globals();
__u32 nhoff, verlen, ip_proto;
@@ -217,7 +183,8 @@ PROG(PARSE_IP)(struct __sk_buff *skb)
return 0;
}
-PROG(PARSE_IPV6)(struct __sk_buff *skb)
+SEC("socket")
+int bpf_func_ipv6(struct __sk_buff *skb)
{
struct globals *g = this_cpu_globals();
__u32 nhoff, ip_proto;
@@ -240,7 +207,8 @@ PROG(PARSE_IPV6)(struct __sk_buff *skb)
return 0;
}
-PROG(PARSE_VLAN)(struct __sk_buff *skb)
+SEC("socket")
+int bpf_func_vlan(struct __sk_buff *skb)
{
__u32 nhoff, proto;
@@ -256,7 +224,8 @@ PROG(PARSE_VLAN)(struct __sk_buff *skb)
return 0;
}
-PROG(PARSE_MPLS)(struct __sk_buff *skb)
+SEC("socket")
+int bpf_func_mpls(struct __sk_buff *skb)
{
__u32 nhoff, label;
@@ -279,7 +248,49 @@ PROG(PARSE_MPLS)(struct __sk_buff *skb)
return 0;
}
-SEC("socket/0")
+struct {
+ __uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+ __uint(key_size, sizeof(u32));
+ __uint(max_entries, 8);
+ __array(values, u32 (void *));
+} prog_array_init SEC(".maps") = {
+ .values = {
+ [PARSE_VLAN] = (void *)&bpf_func_vlan,
+ [PARSE_IP] = (void *)&bpf_func_ip,
+ [PARSE_IPV6] = (void *)&bpf_func_ipv6,
+ [PARSE_MPLS] = (void *)&bpf_func_mpls,
+ },
+};
+
+/* Protocol dispatch routine. It tail-calls next BPF program depending
+ * on eth proto. Note, we could have used ...
+ *
+ * bpf_tail_call(skb, &prog_array_init, 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, &prog_array_init, PARSE_VLAN);
+ break;
+ case ETH_P_MPLS_UC:
+ case ETH_P_MPLS_MC:
+ bpf_tail_call(skb, &prog_array_init, PARSE_MPLS);
+ break;
+ case ETH_P_IP:
+ bpf_tail_call(skb, &prog_array_init, PARSE_IP);
+ break;
+ case ETH_P_IPV6:
+ bpf_tail_call(skb, &prog_array_init, PARSE_IPV6);
+ break;
+ }
+}
+
+SEC("socket")
int main_prog(struct __sk_buff *skb)
{
__u32 nhoff = ETH_HLEN;
diff --git a/samples/bpf/sockex3_user.c b/samples/bpf/sockex3_user.c
index cd6fa79df900..56044acbd25d 100644
--- a/samples/bpf/sockex3_user.c
+++ b/samples/bpf/sockex3_user.c
@@ -24,10 +24,9 @@ struct pair {
int main(int argc, char **argv)
{
- int i, sock, key, fd, main_prog_fd, jmp_table_fd, hash_map_fd;
+ int i, sock, fd, main_prog_fd, hash_map_fd;
struct bpf_program *prog;
struct bpf_object *obj;
- const char *section;
char filename[256];
FILE *f;
@@ -45,26 +44,24 @@ int main(int argc, char **argv)
goto cleanup;
}
- jmp_table_fd = bpf_object__find_map_fd_by_name(obj, "jmp_table");
hash_map_fd = bpf_object__find_map_fd_by_name(obj, "hash_map");
- if (jmp_table_fd < 0 || hash_map_fd < 0) {
+ if (hash_map_fd < 0) {
fprintf(stderr, "ERROR: finding a map in obj file failed\n");
goto cleanup;
}
+ /* find BPF main program */
+ main_prog_fd = 0;
bpf_object__for_each_program(prog, obj) {
fd = bpf_program__fd(prog);
- section = bpf_program__section_name(prog);
- if (sscanf(section, "socket/%d", &key) != 1) {
- fprintf(stderr, "ERROR: finding prog failed\n");
- goto cleanup;
- }
-
- if (key == 0)
+ if (!strcmp(bpf_program__name(prog), "main_prog"))
main_prog_fd = fd;
- else
- bpf_map_update_elem(jmp_table_fd, &key, &fd, BPF_ANY);
+ }
+
+ if (main_prog_fd == 0) {
+ fprintf(stderr, "ERROR: can't find main_prog\n");
+ goto cleanup;
}
sock = open_raw_sock("lo");
diff --git a/samples/bpf/test_cgrp2_tc.sh b/samples/bpf/test_cgrp2_tc.sh
index 12faf5847e22..395573be6ae8 100755
--- a/samples/bpf/test_cgrp2_tc.sh
+++ b/samples/bpf/test_cgrp2_tc.sh
@@ -115,7 +115,7 @@ do_exit() {
if [ "$DEBUG" == "yes" ] && [ "$MODE" != 'cleanuponly' ]
then
echo "------ DEBUG ------"
- echo "mount: "; mount | egrep '(cgroup2|bpf)'; echo
+ echo "mount: "; mount | grep -E '(cgroup2|bpf)'; echo
echo "$CGRP2_TC_LEAF: "; ls -l $CGRP2_TC_LEAF; echo
if [ -d "$BPF_FS_TC_SHARE" ]
then
diff --git a/samples/bpf/tracex2_kern.c b/samples/bpf/tracex2_kern.c
index 5bc696bac27d..93e0b7680b4f 100644
--- a/samples/bpf/tracex2_kern.c
+++ b/samples/bpf/tracex2_kern.c
@@ -22,14 +22,14 @@ struct {
/* kprobe is NOT a stable ABI. If kernel internals change this bpf+kprobe
* example will no longer be meaningful
*/
-SEC("kprobe/kfree_skb")
+SEC("kprobe/kfree_skb_reason")
int bpf_prog2(struct pt_regs *ctx)
{
long loc = 0;
long init_val = 1;
long *value;
- /* read ip of kfree_skb caller.
+ /* read ip of kfree_skb_reason caller.
* non-portable version of __builtin_return_address(0)
*/
BPF_KPROBE_READ_RET_IP(loc, ctx);
diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c
index dd6205c6b6a7..089e408abd7a 100644
--- a/samples/bpf/tracex2_user.c
+++ b/samples/bpf/tracex2_user.c
@@ -146,7 +146,8 @@ int main(int ac, char **argv)
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
- /* start 'ping' in the background to have some kfree_skb events */
+ /* start 'ping' in the background to have some kfree_skb_reason
+ * events */
f = popen("ping -4 -c5 localhost", "r");
(void) f;
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index ac370e638fa3..281dc964de8d 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -51,7 +51,7 @@ static void poll_stats(int map_fd, int interval)
sleep(interval);
- while (bpf_map_get_next_key(map_fd, &key, &key) != -1) {
+ while (bpf_map_get_next_key(map_fd, &key, &key) == 0) {
__u64 sum = 0;
assert(bpf_map_lookup_elem(map_fd, &key, values) == 0);
diff --git a/samples/bpf/xdp2_kern.c b/samples/bpf/xdp2_kern.c
index 3332ba6bb95f..67804ecf7ce3 100644
--- a/samples/bpf/xdp2_kern.c
+++ b/samples/bpf/xdp2_kern.c
@@ -112,6 +112,10 @@ int xdp_prog1(struct xdp_md *ctx)
if (ipproto == IPPROTO_UDP) {
swap_src_dst_mac(data);
+
+ if (bpf_xdp_store_bytes(ctx, 0, pkt, sizeof(pkt)))
+ return rc;
+
rc = XDP_TX;
}
diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c
index 683913bbf279..9d41db09c480 100644
--- a/samples/bpf/xdp_router_ipv4_user.c
+++ b/samples/bpf/xdp_router_ipv4_user.c
@@ -162,7 +162,7 @@ static void read_route(struct nlmsghdr *nh, int nll)
__be32 gw;
} *prefix_value;
- prefix_key = alloca(sizeof(*prefix_key) + 3);
+ prefix_key = alloca(sizeof(*prefix_key) + 4);
prefix_value = alloca(sizeof(*prefix_value));
prefix_key->prefixlen = 32;
diff --git a/samples/pktgen/functions.sh b/samples/pktgen/functions.sh
index 933194257a24..dd4e53ae9b73 100644
--- a/samples/pktgen/functions.sh
+++ b/samples/pktgen/functions.sh
@@ -191,7 +191,7 @@ function extend_addr6()
fi
# if shrink '::' occurs multiple, it's malformed.
- shrink=( $(egrep -o "$sep{2,}" <<< $addr) )
+ shrink=( $(grep -E -o "$sep{2,}" <<< $addr) )
if [[ ${#shrink[@]} -ne 0 ]]; then
if [[ ${#shrink[@]} -gt 1 || ( ${shrink[0]} != $sep2 ) ]]; then
err 5 "Invalid IP6 address: $1"