diff options
Diffstat (limited to 'samples')
| -rw-r--r-- | samples/Kconfig | 2 | ||||
| -rw-r--r-- | samples/bpf/Makefile | 10 | ||||
| -rw-r--r-- | samples/bpf/README.rst | 22 | ||||
| -rw-r--r-- | samples/bpf/bpf_insn.h | 28 | ||||
| -rw-r--r-- | samples/bpf/cookie_uid_helper_example.c | 10 | ||||
| -rw-r--r-- | samples/bpf/sock_example.c | 2 | ||||
| -rw-r--r-- | samples/bpf/test_cgrp2_attach.c | 5 | ||||
| -rw-r--r-- | samples/bpf/xdp_redirect_map_kern.c | 60 | ||||
| -rw-r--r-- | samples/bpf/xdp_redirect_map_user.c | 112 | ||||
| -rw-r--r-- | samples/kprobes/kprobe_example.c | 9 | ||||
| -rw-r--r-- | samples/watch_queue/watch_test.c | 2 |
11 files changed, 211 insertions, 51 deletions
diff --git a/samples/Kconfig b/samples/Kconfig index 0ed6e4d71d87..e76cdfc50e25 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -210,7 +210,7 @@ config SAMPLE_WATCHDOG depends on CC_CAN_LINK config SAMPLE_WATCH_QUEUE - bool "Build example /dev/watch_queue notification consumer" + bool "Build example watch_queue notification API consumer" depends on CC_CAN_LINK && HEADERS_INSTALL help Build example userspace program to use the new mount_notify(), diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 26fc96ca619e..45ceca4e2c70 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -183,6 +183,14 @@ BPF_EXTRA_CFLAGS := $(ARM_ARCH_SELECTOR) TPROGS_CFLAGS += $(ARM_ARCH_SELECTOR) endif +ifeq ($(ARCH), mips) +TPROGS_CFLAGS += -D__SANE_USERSPACE_TYPES__ +ifdef CONFIG_MACH_LOONGSON64 +BPF_EXTRA_CFLAGS += -I$(srctree)/arch/mips/include/asm/mach-loongson64 +BPF_EXTRA_CFLAGS += -I$(srctree)/arch/mips/include/asm/mach-generic +endif +endif + TPROGS_CFLAGS += -Wall -O2 TPROGS_CFLAGS += -Wmissing-prototypes TPROGS_CFLAGS += -Wstrict-prototypes @@ -208,7 +216,7 @@ TPROGLDLIBS_xdpsock += -pthread -lcap 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 +# make M=samples/bpf LLC=~/git/llvm-project/llvm/build/bin/llc CLANG=~/git/llvm-project/llvm/build/bin/clang LLC ?= llc CLANG ?= clang OPT ?= opt diff --git a/samples/bpf/README.rst b/samples/bpf/README.rst index dd34b2d26f1c..60c6494adb1b 100644 --- a/samples/bpf/README.rst +++ b/samples/bpf/README.rst @@ -62,20 +62,26 @@ To generate a smaller llc binary one can use:: -DLLVM_TARGETS_TO_BUILD="BPF" +We recommend that developers who want the fastest incremental builds +use the Ninja build system, you can find it in your system's package +manager, usually the package is ninja or ninja-build. + Quick sniplet for manually compiling LLVM and clang -(build dependencies are cmake and gcc-c++):: +(build dependencies are ninja, cmake and gcc-c++):: - $ git clone http://llvm.org/git/llvm.git - $ cd llvm/tools - $ git clone --depth 1 http://llvm.org/git/clang.git - $ cd ..; mkdir build; cd build - $ cmake .. -DLLVM_TARGETS_TO_BUILD="BPF;X86" - $ make -j $(getconf _NPROCESSORS_ONLN) + $ git clone https://github.com/llvm/llvm-project.git + $ mkdir -p llvm-project/llvm/build + $ cd llvm-project/llvm/build + $ cmake .. -G "Ninja" -DLLVM_TARGETS_TO_BUILD="BPF;X86" \ + -DLLVM_ENABLE_PROJECTS="clang" \ + -DCMAKE_BUILD_TYPE=Release \ + -DLLVM_BUILD_RUNTIME=OFF + $ ninja It is also possible to point make to the newly compiled 'llc' or 'clang' command via redefining LLC or CLANG on the make command line:: - make M=samples/bpf LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang + make M=samples/bpf LLC=~/git/llvm-project/llvm/build/bin/llc CLANG=~/git/llvm-project/llvm/build/bin/clang Cross compiling samples ----------------------- diff --git a/samples/bpf/bpf_insn.h b/samples/bpf/bpf_insn.h index 544237980582..aee04534483a 100644 --- a/samples/bpf/bpf_insn.h +++ b/samples/bpf/bpf_insn.h @@ -134,15 +134,31 @@ struct bpf_insn; .off = OFF, \ .imm = 0 }) -/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */ - -#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \ - ((struct bpf_insn) { \ - .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \ +/* + * Atomic operations: + * + * BPF_ADD *(uint *) (dst_reg + off16) += src_reg + * BPF_AND *(uint *) (dst_reg + off16) &= src_reg + * BPF_OR *(uint *) (dst_reg + off16) |= src_reg + * BPF_XOR *(uint *) (dst_reg + off16) ^= src_reg + * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); + * BPF_AND | BPF_FETCH src_reg = atomic_fetch_and(dst_reg + off16, src_reg); + * BPF_OR | BPF_FETCH src_reg = atomic_fetch_or(dst_reg + off16, src_reg); + * BPF_XOR | BPF_FETCH src_reg = atomic_fetch_xor(dst_reg + off16, src_reg); + * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) + * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) + */ + +#define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ - .imm = 0 }) + .imm = OP }) + +/* Legacy alias */ +#define BPF_STX_XADD(SIZE, DST, SRC, OFF) BPF_ATOMIC_OP(SIZE, BPF_ADD, DST, SRC, OFF) /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ diff --git a/samples/bpf/cookie_uid_helper_example.c b/samples/bpf/cookie_uid_helper_example.c index deb0e3e0324d..cc3bce8d3aac 100644 --- a/samples/bpf/cookie_uid_helper_example.c +++ b/samples/bpf/cookie_uid_helper_example.c @@ -147,12 +147,12 @@ static void prog_load(void) */ BPF_MOV64_REG(BPF_REG_9, BPF_REG_0), BPF_MOV64_IMM(BPF_REG_1, 1), - BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1, - offsetof(struct stats, packets)), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_9, BPF_REG_1, + offsetof(struct stats, packets)), BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6, offsetof(struct __sk_buff, len)), - BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1, - offsetof(struct stats, bytes)), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_9, BPF_REG_1, + offsetof(struct stats, bytes)), BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct __sk_buff, len)), BPF_EXIT_INSN(), @@ -313,7 +313,7 @@ int main(int argc, char *argv[]) print_table(); printf("\n"); sleep(1); - }; + } } else if (cfg_test_cookie) { udp_client(); } diff --git a/samples/bpf/sock_example.c b/samples/bpf/sock_example.c index 00aae1d33fca..23d1930e1927 100644 --- a/samples/bpf/sock_example.c +++ b/samples/bpf/sock_example.c @@ -54,7 +54,7 @@ static int test_sock(void) BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), BPF_MOV64_IMM(BPF_REG_1, 1), /* r1 = 1 */ - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_1, 0), BPF_MOV64_IMM(BPF_REG_0, 0), /* r0 = 0 */ BPF_EXIT_INSN(), }; diff --git a/samples/bpf/test_cgrp2_attach.c b/samples/bpf/test_cgrp2_attach.c index 20fbd1241db3..390ff38d2ac6 100644 --- a/samples/bpf/test_cgrp2_attach.c +++ b/samples/bpf/test_cgrp2_attach.c @@ -53,7 +53,7 @@ static int prog_load(int map_fd, int verdict) BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), BPF_MOV64_IMM(BPF_REG_1, 1), /* r1 = 1 */ - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_1, 0), /* Count bytes */ BPF_MOV64_IMM(BPF_REG_0, MAP_KEY_BYTES), /* r0 = 1 */ @@ -64,7 +64,8 @@ static int prog_load(int map_fd, int verdict) BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6, offsetof(struct __sk_buff, len)), /* r1 = skb->len */ - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ + + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_1, 0), BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ BPF_EXIT_INSN(), diff --git a/samples/bpf/xdp_redirect_map_kern.c b/samples/bpf/xdp_redirect_map_kern.c index 6489352ab7a4..a92b8e567bdd 100644 --- a/samples/bpf/xdp_redirect_map_kern.c +++ b/samples/bpf/xdp_redirect_map_kern.c @@ -19,12 +19,22 @@ #include <linux/ipv6.h> #include <bpf/bpf_helpers.h> +/* The 2nd xdp prog on egress does not support skb mode, so we define two + * maps, tx_port_general and tx_port_native. + */ 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"); +} tx_port_general SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 100); +} tx_port_native SEC(".maps"); /* Count RX packets, as XDP bpf_prog doesn't get direct TX-success * feedback. Redirect TX errors can be caught via a tracepoint. @@ -36,6 +46,14 @@ struct { __uint(max_entries, 1); } rxcnt SEC(".maps"); +/* map to store egress interface mac address */ +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, __be64); + __uint(max_entries, 1); +} tx_mac SEC(".maps"); + static void swap_src_dst_mac(void *data) { unsigned short *p = data; @@ -52,17 +70,16 @@ static void swap_src_dst_mac(void *data) p[5] = dst[2]; } -SEC("xdp_redirect_map") -int xdp_redirect_map_prog(struct xdp_md *ctx) +static __always_inline int xdp_redirect_map(struct xdp_md *ctx, void *redirect_map) { void *data_end = (void *)(long)ctx->data_end; void *data = (void *)(long)ctx->data; struct ethhdr *eth = data; int rc = XDP_DROP; - int vport, port = 0, m = 0; long *value; u32 key = 0; u64 nh_off; + int vport; nh_off = sizeof(*eth); if (data + nh_off > data_end) @@ -79,7 +96,40 @@ int xdp_redirect_map_prog(struct xdp_md *ctx) swap_src_dst_mac(data); /* send packet out physical port */ - return bpf_redirect_map(&tx_port, vport, 0); + return bpf_redirect_map(redirect_map, vport, 0); +} + +SEC("xdp_redirect_general") +int xdp_redirect_map_general(struct xdp_md *ctx) +{ + return xdp_redirect_map(ctx, &tx_port_general); +} + +SEC("xdp_redirect_native") +int xdp_redirect_map_native(struct xdp_md *ctx) +{ + return xdp_redirect_map(ctx, &tx_port_native); +} + +SEC("xdp_devmap/map_prog") +int xdp_redirect_map_egress(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + __be64 *mac; + u32 key = 0; + u64 nh_off; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return XDP_DROP; + + mac = bpf_map_lookup_elem(&tx_mac, &key); + if (mac) + __builtin_memcpy(eth->h_source, mac, ETH_ALEN); + + return XDP_PASS; } /* Redirect require an XDP bpf_prog loaded on the TX device */ diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c index 31131b6e7782..0e8192688dfc 100644 --- a/samples/bpf/xdp_redirect_map_user.c +++ b/samples/bpf/xdp_redirect_map_user.c @@ -14,6 +14,10 @@ #include <unistd.h> #include <libgen.h> #include <sys/resource.h> +#include <sys/ioctl.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <netinet/in.h> #include "bpf_util.h" #include <bpf/bpf.h> @@ -22,6 +26,7 @@ static int ifindex_in; static int ifindex_out; static bool ifindex_out_xdp_dummy_attached = true; +static bool xdp_devmap_attached; static __u32 prog_id; static __u32 dummy_prog_id; @@ -83,6 +88,32 @@ static void poll_stats(int interval, int ifindex) } } +static int get_mac_addr(unsigned int ifindex_out, void *mac_addr) +{ + char ifname[IF_NAMESIZE]; + struct ifreq ifr; + int fd, ret = -1; + + fd = socket(AF_INET, SOCK_DGRAM, 0); + if (fd < 0) + return ret; + + if (!if_indextoname(ifindex_out, ifname)) + goto err_out; + + strcpy(ifr.ifr_name, ifname); + + if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0) + goto err_out; + + memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char)); + ret = 0; + +err_out: + close(fd); + return ret; +} + static void usage(const char *prog) { fprintf(stderr, @@ -90,24 +121,26 @@ static void usage(const char *prog) "OPTS:\n" " -S use skb-mode\n" " -N enforce native mode\n" - " -F force loading prog\n", + " -F force loading prog\n" + " -X load xdp program on egress\n", prog); } int main(int argc, char **argv) { struct bpf_prog_load_attr prog_load_attr = { - .prog_type = BPF_PROG_TYPE_XDP, + .prog_type = BPF_PROG_TYPE_UNSPEC, }; - struct bpf_program *prog, *dummy_prog; + struct bpf_program *prog, *dummy_prog, *devmap_prog; + int prog_fd, dummy_prog_fd, devmap_prog_fd = 0; + int tx_port_map_fd, tx_mac_map_fd; + struct bpf_devmap_val devmap_val; struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); - int prog_fd, dummy_prog_fd; - const char *optstr = "FSN"; + const char *optstr = "FSNX"; struct bpf_object *obj; int ret, opt, key = 0; char filename[256]; - int tx_port_map_fd; while ((opt = getopt(argc, argv, optstr)) != -1) { switch (opt) { @@ -120,14 +153,21 @@ int main(int argc, char **argv) case 'F': xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; break; + case 'X': + xdp_devmap_attached = true; + break; default: usage(basename(argv[0])); return 1; } } - if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) + if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) { xdp_flags |= XDP_FLAGS_DRV_MODE; + } else if (xdp_devmap_attached) { + printf("Load xdp program on egress with SKB mode not supported yet\n"); + return 1; + } if (optind == argc) { printf("usage: %s <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n", argv[0]); @@ -150,24 +190,28 @@ int main(int argc, char **argv) if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) return 1; - prog = bpf_program__next(NULL, obj); - dummy_prog = bpf_program__next(prog, obj); - if (!prog || !dummy_prog) { - printf("finding a prog in obj file failed\n"); - return 1; + if (xdp_flags & XDP_FLAGS_SKB_MODE) { + prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_general"); + tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port_general"); + } else { + prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_native"); + tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port_native"); + } + dummy_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_dummy_prog"); + if (!prog || dummy_prog < 0 || tx_port_map_fd < 0) { + printf("finding prog/dummy_prog/tx_port_map in obj file failed\n"); + goto out; } - /* bpf_prog_load_xattr gives us the pointer to first prog's fd, - * so we're missing only the fd for dummy prog - */ + prog_fd = bpf_program__fd(prog); dummy_prog_fd = bpf_program__fd(dummy_prog); - if (prog_fd < 0 || dummy_prog_fd < 0) { + if (prog_fd < 0 || dummy_prog_fd < 0 || tx_port_map_fd < 0) { printf("bpf_prog_load_xattr: %s\n", strerror(errno)); return 1; } - tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port"); + tx_mac_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_mac"); rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt"); - if (tx_port_map_fd < 0 || rxcnt_map_fd < 0) { + if (tx_mac_map_fd < 0 || rxcnt_map_fd < 0) { printf("bpf_object__find_map_fd_by_name failed\n"); return 1; } @@ -199,11 +243,39 @@ int main(int argc, char **argv) } dummy_prog_id = info.id; + /* Load 2nd xdp prog on egress. */ + if (xdp_devmap_attached) { + unsigned char mac_addr[6]; + + devmap_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_egress"); + if (!devmap_prog) { + printf("finding devmap_prog in obj file failed\n"); + goto out; + } + devmap_prog_fd = bpf_program__fd(devmap_prog); + if (devmap_prog_fd < 0) { + printf("finding devmap_prog fd failed\n"); + goto out; + } + + if (get_mac_addr(ifindex_out, mac_addr) < 0) { + printf("get interface %d mac failed\n", ifindex_out); + goto out; + } + + ret = bpf_map_update_elem(tx_mac_map_fd, &key, mac_addr, 0); + if (ret) { + perror("bpf_update_elem tx_mac_map_fd"); + goto out; + } + } + signal(SIGINT, int_exit); signal(SIGTERM, int_exit); - /* populate virtual to physical port map */ - ret = bpf_map_update_elem(tx_port_map_fd, &key, &ifindex_out, 0); + devmap_val.ifindex = ifindex_out; + devmap_val.bpf_prog.fd = devmap_prog_fd; + ret = bpf_map_update_elem(tx_port_map_fd, &key, &devmap_val, 0); if (ret) { perror("bpf_update_elem"); goto out; diff --git a/samples/kprobes/kprobe_example.c b/samples/kprobes/kprobe_example.c index 365905cb24b1..331dcf151532 100644 --- a/samples/kprobes/kprobe_example.c +++ b/samples/kprobes/kprobe_example.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * NOTE: This example is works on x86 and powerpc. * Here's a sample kernel module showing the use of kprobes to dump a * stack trace and selected registers when kernel_clone() is called. * @@ -44,6 +43,10 @@ static int __kprobes handler_pre(struct kprobe *p, struct pt_regs *regs) " pstate = 0x%lx\n", p->symbol_name, p->addr, (long)regs->pc, (long)regs->pstate); #endif +#ifdef CONFIG_ARM + pr_info("<%s> pre_handler: p->addr = 0x%p, pc = 0x%lx, cpsr = 0x%lx\n", + p->symbol_name, p->addr, (long)regs->ARM_pc, (long)regs->ARM_cpsr); +#endif #ifdef CONFIG_S390 pr_info("<%s> pre_handler: p->addr, 0x%p, ip = 0x%lx, flags = 0x%lx\n", p->symbol_name, p->addr, regs->psw.addr, regs->flags); @@ -73,6 +76,10 @@ static void __kprobes handler_post(struct kprobe *p, struct pt_regs *regs, pr_info("<%s> post_handler: p->addr = 0x%p, pstate = 0x%lx\n", p->symbol_name, p->addr, (long)regs->pstate); #endif +#ifdef CONFIG_ARM + pr_info("<%s> post_handler: p->addr = 0x%p, cpsr = 0x%lx\n", + p->symbol_name, p->addr, (long)regs->ARM_cpsr); +#endif #ifdef CONFIG_S390 pr_info("<%s> pre_handler: p->addr, 0x%p, flags = 0x%lx\n", p->symbol_name, p->addr, regs->flags); diff --git a/samples/watch_queue/watch_test.c b/samples/watch_queue/watch_test.c index 46e618a897fe..8c6cb57d5cfc 100644 --- a/samples/watch_queue/watch_test.c +++ b/samples/watch_queue/watch_test.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Use /dev/watch_queue to watch for notifications. +/* Use watch_queue API to watch for notifications. * * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) |