From fada7fdc83c0bf8755956bff707c42b609223301 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Thu, 6 Jun 2019 13:59:40 -0700 Subject: bpf: Allow bpf_map_lookup_elem() on an xskmap Currently, the AF_XDP code uses a separate map in order to determine if an xsk is bound to a queue. Instead of doing this, have bpf_map_lookup_elem() return a xdp_sock. Rearrange some xdp_sock members to eliminate structure holes. Remove selftest - will be added back in later patch. Signed-off-by: Jonathan Lemon Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/verifier/prevent_map_lookup.c | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c b/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c index bbdba990fefb..da7a4b37cb98 100644 --- a/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c +++ b/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c @@ -28,21 +28,6 @@ .errstr = "cannot pass map_type 18 into func bpf_map_lookup_elem", .prog_type = BPF_PROG_TYPE_SOCK_OPS, }, -{ - "prevent map lookup in xskmap", - .insns = { - BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_EXIT_INSN(), - }, - .fixup_map_xskmap = { 3 }, - .result = REJECT, - .errstr = "cannot pass map_type 17 into func bpf_map_lookup_elem", - .prog_type = BPF_PROG_TYPE_XDP, -}, { "prevent map lookup in stack trace", .insns = { -- cgit v1.2.3 From 91eda5998c313282b5acfcc0b5133556382d0737 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Thu, 6 Jun 2019 13:59:41 -0700 Subject: bpf/tools: sync bpf.h Sync uapi/linux/bpf.h Signed-off-by: Jonathan Lemon Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- tools/include/uapi/linux/bpf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'tools') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7c6aef253173..ae0907d8c03a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3083,6 +3083,10 @@ struct bpf_sock_tuple { }; }; +struct bpf_xdp_sock { + __u32 queue_id; +}; + #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. -- cgit v1.2.3 From 940e7be34ab3d04b7e0b6dd57bdbda1d225c3d8c Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Thu, 6 Jun 2019 13:59:42 -0700 Subject: tools/bpf: Add bpf_map_lookup_elem selftest for xskmap Check that bpf_map_lookup_elem lookup and structure access operats correctly. Signed-off-by: Jonathan Lemon Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/verifier/sock.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c index b31cd2cf50d0..9ed192e14f5f 100644 --- a/tools/testing/selftests/bpf/verifier/sock.c +++ b/tools/testing/selftests/bpf/verifier/sock.c @@ -498,3 +498,21 @@ .result = REJECT, .errstr = "cannot pass map_type 24 into func bpf_map_lookup_elem", }, +{ + "bpf_map_lookup_elem(xskmap, &key); xs->queue_id", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_xdp_sock, queue_id)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_xskmap = { 3 }, + .prog_type = BPF_PROG_TYPE_XDP, + .result = ACCEPT, +}, -- cgit v1.2.3 From 10a13bb40e541d8cb1d5f36403aae3a0f1a2ee58 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Thu, 6 Jun 2019 13:59:43 -0700 Subject: libbpf: remove qidconf and better support external bpf programs. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use the recent change to XSKMAP bpf_map_lookup_elem() to test if there is a xsk present in the map instead of duplicating the work with qidconf. Fix things so callers using XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD bypass any internal bpf maps, so xsk_socket__{create|delete} works properly. Clean up error handling path. Signed-off-by: Jonathan Lemon Acked-by: Song Liu Tested-by: Björn Töpel Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/xsk.c | 103 ++++++++++++++-------------------------------------- 1 file changed, 28 insertions(+), 75 deletions(-) (limited to 'tools') diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 38667b62f1fe..7ef6293b4fd7 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -60,10 +60,8 @@ struct xsk_socket { struct xsk_umem *umem; struct xsk_socket_config config; int fd; - int xsks_map; int ifindex; int prog_fd; - int qidconf_map_fd; int xsks_map_fd; __u32 queue_id; char ifname[IFNAMSIZ]; @@ -265,15 +263,11 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) /* This is the C-program: * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx) * { - * int *qidconf, index = ctx->rx_queue_index; + * int index = ctx->rx_queue_index; * * // A set entry here means that the correspnding queue_id * // has an active AF_XDP socket bound to it. - * qidconf = bpf_map_lookup_elem(&qidconf_map, &index); - * if (!qidconf) - * return XDP_ABORTED; - * - * if (*qidconf) + * if (bpf_map_lookup_elem(&xsks_map, &index)) * return bpf_redirect_map(&xsks_map, index, 0); * * return XDP_PASS; @@ -286,15 +280,10 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_1, -4), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), - BPF_LD_MAP_FD(BPF_REG_1, xsk->qidconf_map_fd), + BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd), BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), - BPF_MOV32_IMM(BPF_REG_0, 0), - /* if r1 == 0 goto +8 */ - BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 8), BPF_MOV32_IMM(BPF_REG_0, 2), - /* r1 = *(u32 *)(r1 + 0) */ - BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, 0), /* if r1 == 0 goto +5 */ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 5), /* r2 = *(u32 *)(r10 - 4) */ @@ -366,18 +355,11 @@ static int xsk_create_bpf_maps(struct xsk_socket *xsk) if (max_queues < 0) return max_queues; - fd = bpf_create_map_name(BPF_MAP_TYPE_ARRAY, "qidconf_map", + fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map", sizeof(int), sizeof(int), max_queues, 0); if (fd < 0) return fd; - xsk->qidconf_map_fd = fd; - fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map", - sizeof(int), sizeof(int), max_queues, 0); - if (fd < 0) { - close(xsk->qidconf_map_fd); - return fd; - } xsk->xsks_map_fd = fd; return 0; @@ -385,10 +367,8 @@ static int xsk_create_bpf_maps(struct xsk_socket *xsk) static void xsk_delete_bpf_maps(struct xsk_socket *xsk) { - close(xsk->qidconf_map_fd); + bpf_map_delete_elem(xsk->xsks_map_fd, &xsk->queue_id); close(xsk->xsks_map_fd); - xsk->qidconf_map_fd = -1; - xsk->xsks_map_fd = -1; } static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) @@ -417,10 +397,9 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) if (err) goto out_map_ids; - for (i = 0; i < prog_info.nr_map_ids; i++) { - if (xsk->qidconf_map_fd != -1 && xsk->xsks_map_fd != -1) - break; + xsk->xsks_map_fd = -1; + for (i = 0; i < prog_info.nr_map_ids; i++) { fd = bpf_map_get_fd_by_id(map_ids[i]); if (fd < 0) continue; @@ -431,11 +410,6 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) continue; } - if (!strcmp(map_info.name, "qidconf_map")) { - xsk->qidconf_map_fd = fd; - continue; - } - if (!strcmp(map_info.name, "xsks_map")) { xsk->xsks_map_fd = fd; continue; @@ -445,40 +419,18 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) } err = 0; - if (xsk->qidconf_map_fd < 0 || xsk->xsks_map_fd < 0) { + if (xsk->xsks_map_fd == -1) err = -ENOENT; - xsk_delete_bpf_maps(xsk); - } out_map_ids: free(map_ids); return err; } -static void xsk_clear_bpf_maps(struct xsk_socket *xsk) -{ - int qid = false; - - bpf_map_update_elem(xsk->qidconf_map_fd, &xsk->queue_id, &qid, 0); - bpf_map_delete_elem(xsk->xsks_map_fd, &xsk->queue_id); -} - static int xsk_set_bpf_maps(struct xsk_socket *xsk) { - int qid = true, fd = xsk->fd, err; - - err = bpf_map_update_elem(xsk->qidconf_map_fd, &xsk->queue_id, &qid, 0); - if (err) - goto out; - - err = bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id, &fd, 0); - if (err) - goto out; - - return 0; -out: - xsk_clear_bpf_maps(xsk); - return err; + return bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id, + &xsk->fd, 0); } static int xsk_setup_xdp_prog(struct xsk_socket *xsk) @@ -497,26 +449,27 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk) return err; err = xsk_load_xdp_prog(xsk); - if (err) - goto out_maps; + if (err) { + xsk_delete_bpf_maps(xsk); + return err; + } } else { xsk->prog_fd = bpf_prog_get_fd_by_id(prog_id); err = xsk_lookup_bpf_maps(xsk); - if (err) - goto out_load; + if (err) { + close(xsk->prog_fd); + return err; + } } err = xsk_set_bpf_maps(xsk); - if (err) - goto out_load; + if (err) { + xsk_delete_bpf_maps(xsk); + close(xsk->prog_fd); + return err; + } return 0; - -out_load: - close(xsk->prog_fd); -out_maps: - xsk_delete_bpf_maps(xsk); - return err; } int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, @@ -643,9 +596,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, goto out_mmap_tx; } - xsk->qidconf_map_fd = -1; - xsk->xsks_map_fd = -1; - + xsk->prog_fd = -1; if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) { err = xsk_setup_xdp_prog(xsk); if (err) @@ -708,8 +659,10 @@ void xsk_socket__delete(struct xsk_socket *xsk) if (!xsk) return; - xsk_clear_bpf_maps(xsk); - xsk_delete_bpf_maps(xsk); + if (xsk->prog_fd != -1) { + xsk_delete_bpf_maps(xsk); + close(xsk->prog_fd); + } optlen = sizeof(off); err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen); -- cgit v1.2.3 From c7cebffea2c7086850e4affeb9f232d34ae30f11 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 10 Jun 2019 10:46:55 -0700 Subject: selftests/bpf: fix constness of source arg for bpf helpers Fix signature of bpf_probe_read and bpf_probe_write_user to mark source pointer as const. This causes warnings during compilation for applications relying on those helpers. Signed-off-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/bpf_helpers.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index e6d243b7cd74..1a5b1accf091 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -31,7 +31,7 @@ static int (*bpf_map_pop_elem)(void *map, void *value) = (void *) BPF_FUNC_map_pop_elem; static int (*bpf_map_peek_elem)(void *map, void *value) = (void *) BPF_FUNC_map_peek_elem; -static int (*bpf_probe_read)(void *dst, int size, void *unsafe_ptr) = +static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) = (void *) BPF_FUNC_probe_read; static unsigned long long (*bpf_ktime_get_ns)(void) = (void *) BPF_FUNC_ktime_get_ns; @@ -62,7 +62,7 @@ static int (*bpf_perf_event_output)(void *ctx, void *map, (void *) BPF_FUNC_perf_event_output; static int (*bpf_get_stackid)(void *ctx, void *map, int flags) = (void *) BPF_FUNC_get_stackid; -static int (*bpf_probe_write_user)(void *dst, void *src, int size) = +static int (*bpf_probe_write_user)(void *dst, const void *src, int size) = (void *) BPF_FUNC_probe_write_user; static int (*bpf_current_task_under_cgroup)(void *map, int index) = (void *) BPF_FUNC_current_task_under_cgroup; -- cgit v1.2.3 From 89cceaa939171fafa153d4bf637b39e396bbd785 Mon Sep 17 00:00:00 2001 From: Hechao Li Date: Mon, 10 Jun 2019 17:43:07 -0700 Subject: selftests/bpf : clean up feature/ when make clean An error "implicit declaration of function 'reallocarray'" can be thrown with the following steps: $ cd tools/testing/selftests/bpf $ make clean && make CC= $ make clean && make CC= The cause is that the feature folder generated by GCC 4.8.5 is not removed, leaving feature-reallocarray being 1, which causes reallocarray not defined when re-compliing with GCC 7.x. This diff adds feature folder to EXTRA_CLEAN to avoid this problem. v2: Rephrase the commit message. Signed-off-by: Hechao Li Acked-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 2b426ae1cdc9..44fb61f4d502 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -279,4 +279,5 @@ $(OUTPUT)/verifier/tests.h: $(VERIFIER_TESTS_DIR) $(VERIFIER_TEST_FILES) ) > $(VERIFIER_TESTS_H)) EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(ALU32_BUILD_DIR) \ - $(VERIFIER_TESTS_H) $(PROG_TESTS_H) $(MAP_TESTS_H) + $(VERIFIER_TESTS_H) $(PROG_TESTS_H) $(MAP_TESTS_H) \ + feature -- cgit v1.2.3 From 6446b3155521aab37f5a2b99ac264803ea7dced8 Mon Sep 17 00:00:00 2001 From: Hechao Li Date: Mon, 10 Jun 2019 17:56:50 -0700 Subject: bpf: add a new API libbpf_num_possible_cpus() Adding a new API libbpf_num_possible_cpus() that helps user with per-CPU map operations. Signed-off-by: Hechao Li Signed-off-by: Daniel Borkmann --- tools/lib/bpf/libbpf.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++ tools/lib/bpf/libbpf.h | 16 ++++++++++++++ tools/lib/bpf/libbpf.map | 1 + 3 files changed, 74 insertions(+) (limited to 'tools') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ba89d9727137..dd8b2cd5d3a7 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -3827,3 +3827,60 @@ void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear) desc->array_offset, addr); } } + +int libbpf_num_possible_cpus(void) +{ + static const char *fcpu = "/sys/devices/system/cpu/possible"; + int len = 0, n = 0, il = 0, ir = 0; + unsigned int start = 0, end = 0; + static int cpus; + char buf[128]; + int error = 0; + int fd = -1; + + if (cpus > 0) + return cpus; + + fd = open(fcpu, O_RDONLY); + if (fd < 0) { + error = errno; + pr_warning("Failed to open file %s: %s\n", + fcpu, strerror(error)); + return -error; + } + len = read(fd, buf, sizeof(buf)); + close(fd); + if (len <= 0) { + error = len ? errno : EINVAL; + pr_warning("Failed to read # of possible cpus from %s: %s\n", + fcpu, strerror(error)); + return -error; + } + if (len == sizeof(buf)) { + pr_warning("File %s size overflow\n", fcpu); + return -EOVERFLOW; + } + buf[len] = '\0'; + + for (ir = 0, cpus = 0; ir <= len; ir++) { + /* Each sub string separated by ',' has format \d+-\d+ or \d+ */ + if (buf[ir] == ',' || buf[ir] == '\0') { + buf[ir] = '\0'; + n = sscanf(&buf[il], "%u-%u", &start, &end); + if (n <= 0) { + pr_warning("Failed to get # CPUs from %s\n", + &buf[il]); + return -EINVAL; + } else if (n == 1) { + end = start; + } + cpus += end - start + 1; + il = ir + 1; + } + } + if (cpus <= 0) { + pr_warning("Invalid #CPUs %d from %s\n", cpus, fcpu); + return -EINVAL; + } + return cpus; +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 1af0d48178c8..2e594a0fa961 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -454,6 +454,22 @@ bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear); LIBBPF_API void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); +/* + * A helper function to get the number of possible CPUs before looking up + * per-CPU maps. Negative errno is returned on failure. + * + * Example usage: + * + * int ncpus = libbpf_num_possible_cpus(); + * if (ncpus < 0) { + * // error handling + * } + * long values[ncpus]; + * bpf_map_lookup_elem(per_cpu_map_fd, key, values); + * + */ +LIBBPF_API int libbpf_num_possible_cpus(void); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 46dcda89df21..2c6d835620d2 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -172,4 +172,5 @@ LIBBPF_0.0.4 { btf_dump__new; btf__parse_elf; bpf_object__load_xattr; + libbpf_num_possible_cpus; } LIBBPF_0.0.3; -- cgit v1.2.3 From ebb886078bae29bd60eba3157dc6edae4bbed3a1 Mon Sep 17 00:00:00 2001 From: Hechao Li Date: Mon, 10 Jun 2019 17:56:51 -0700 Subject: selftests/bpf: remove bpf_util.h from BPF C progs Though currently there is no problem including bpf_util.h in kernel space BPF C programs, in next patch in this stack, I will reuse libbpf_num_possible_cpus() in bpf_util.h thus include libbpf.h in it, which will cause BPF C programs compile error. Therefore I will first remove bpf_util.h from all test BPF programs. This can also make it clear that bpf_util.h is a user-space utility while bpf_helpers.h is a kernel space utility. Signed-off-by: Hechao Li Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/bpf_endian.h | 1 + tools/testing/selftests/bpf/progs/sockmap_parse_prog.c | 1 - tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c | 2 +- tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c | 1 - tools/testing/selftests/bpf/progs/test_sysctl_prog.c | 5 ++++- 5 files changed, 6 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/bpf_endian.h b/tools/testing/selftests/bpf/bpf_endian.h index b25595ea4a78..05f036df8a4c 100644 --- a/tools/testing/selftests/bpf/bpf_endian.h +++ b/tools/testing/selftests/bpf/bpf_endian.h @@ -2,6 +2,7 @@ #ifndef __BPF_ENDIAN__ #define __BPF_ENDIAN__ +#include #include /* LLVM's BPF target selects the endianness of the CPU diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c index ed3e4a551c57..9390e0244259 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c @@ -1,6 +1,5 @@ #include #include "bpf_helpers.h" -#include "bpf_util.h" #include "bpf_endian.h" int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c index 65fbfdb6cd3a..e80484d98a1a 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c @@ -1,6 +1,6 @@ #include + #include "bpf_helpers.h" -#include "bpf_util.h" #include "bpf_endian.h" int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c index bdc22be46f2e..d85c874ef25e 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c @@ -1,6 +1,5 @@ #include #include "bpf_helpers.h" -#include "bpf_util.h" #include "bpf_endian.h" int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c index a295cad805d7..5cbbff416998 100644 --- a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c +++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c @@ -8,7 +8,6 @@ #include #include "bpf_helpers.h" -#include "bpf_util.h" /* Max supported length of a string with unsigned long in base 10 (pow2 - 1). */ #define MAX_ULONG_STR_LEN 0xF @@ -16,6 +15,10 @@ /* Max supported length of sysctl value string (pow2). */ #define MAX_VALUE_STR_LEN 0x40 +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx) { char tcp_mem_name[] = "net/ipv4/tcp_mem"; -- cgit v1.2.3 From 4c587c196d8237169405cbb2195669dbc00fd72b Mon Sep 17 00:00:00 2001 From: Hechao Li Date: Mon, 10 Jun 2019 17:56:52 -0700 Subject: bpf: use libbpf_num_possible_cpus internally Use the newly added bpf_num_possible_cpus() in bpftool and selftests and remove duplicate implementations. Signed-off-by: Hechao Li Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/common.c | 53 ++++------------------------------ tools/testing/selftests/bpf/bpf_util.h | 37 ++++-------------------- 2 files changed, 10 insertions(+), 80 deletions(-) (limited to 'tools') diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index f7261fad45c1..5215e0870bcb 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -21,6 +21,7 @@ #include #include +#include /* libbpf_num_possible_cpus */ #include "main.h" @@ -439,57 +440,13 @@ unsigned int get_page_size(void) unsigned int get_possible_cpus(void) { - static unsigned int result; - char buf[128]; - long int n; - char *ptr; - int fd; - - if (result) - return result; - - fd = open("/sys/devices/system/cpu/possible", O_RDONLY); - if (fd < 0) { - p_err("can't open sysfs possible cpus"); - exit(-1); - } - - n = read(fd, buf, sizeof(buf)); - if (n < 2) { - p_err("can't read sysfs possible cpus"); - exit(-1); - } - close(fd); + int cpus = libbpf_num_possible_cpus(); - if (n == sizeof(buf)) { - p_err("read sysfs possible cpus overflow"); + if (cpus < 0) { + p_err("Can't get # of possible cpus: %s", strerror(-cpus)); exit(-1); } - - ptr = buf; - n = 0; - while (*ptr && *ptr != '\n') { - unsigned int a, b; - - if (sscanf(ptr, "%u-%u", &a, &b) == 2) { - n += b - a + 1; - - ptr = strchr(ptr, '-') + 1; - } else if (sscanf(ptr, "%u", &a) == 1) { - n++; - } else { - assert(0); - } - - while (isdigit(*ptr)) - ptr++; - if (*ptr == ',') - ptr++; - } - - result = n; - - return result; + return cpus; } static char * diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index a29206ebbd13..ec219f84e041 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -6,44 +6,17 @@ #include #include #include +#include /* libbpf_num_possible_cpus */ static inline unsigned int bpf_num_possible_cpus(void) { - static const char *fcpu = "/sys/devices/system/cpu/possible"; - unsigned int start, end, possible_cpus = 0; - char buff[128]; - FILE *fp; - int len, n, i, j = 0; + int possible_cpus = libbpf_num_possible_cpus(); - fp = fopen(fcpu, "r"); - if (!fp) { - printf("Failed to open %s: '%s'!\n", fcpu, strerror(errno)); + if (possible_cpus < 0) { + printf("Failed to get # of possible cpus: '%s'!\n", + strerror(-possible_cpus)); exit(1); } - - if (!fgets(buff, sizeof(buff), fp)) { - printf("Failed to read %s!\n", fcpu); - exit(1); - } - - len = strlen(buff); - for (i = 0; i <= len; i++) { - if (buff[i] == ',' || buff[i] == '\0') { - buff[i] = '\0'; - n = sscanf(&buff[j], "%u-%u", &start, &end); - if (n <= 0) { - printf("Failed to retrieve # possible CPUs!\n"); - exit(1); - } else if (n == 1) { - end = start; - } - possible_cpus += end - start + 1; - j = i + 1; - } - } - - fclose(fp); - return possible_cpus; } -- cgit v1.2.3 From cabd3e889b5772a0dc448ddca9a4b23591640bca Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 13 Jun 2019 10:00:21 +0300 Subject: selftests/bpf: signedness bug in enable_all_controllers() The "len" variable needs to be signed for the error handling to work properly. Fixes: 596092ef8bea ("selftests/bpf: enable all available cgroup v2 controllers") Signed-off-by: Dan Carpenter Acked-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/cgroup_helpers.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index 0d89f0396be4..e95c33e333a4 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -47,7 +47,7 @@ int enable_all_controllers(char *cgroup_path) char buf[PATH_MAX]; char *c, *c2; int fd, cfd; - size_t len; + ssize_t len; snprintf(path, sizeof(path), "%s/cgroup.controllers", cgroup_path); fd = open(path, O_RDONLY); -- cgit v1.2.3 From e55d54f43d3f11718d9e2800225097fda498e141 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 12 Jun 2019 22:04:57 -0700 Subject: libbpf: fix check for presence of associated BTF for map creation Kernel internally checks that either key or value type ID is specified, before using btf_fd. Do the same in libbpf's map creation code for determining when to retry map creation w/o BTF. Reported-by: Dan Carpenter Fixes: fba01a0689a9 ("libbpf: use negative fd to specify missing BTF") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann --- tools/lib/bpf/libbpf.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index dd8b2cd5d3a7..e725fa86b189 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1736,7 +1736,7 @@ bpf_object__create_maps(struct bpf_object *obj) create_attr.key_size = def->key_size; create_attr.value_size = def->value_size; create_attr.max_entries = def->max_entries; - create_attr.btf_fd = -1; + create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; if (bpf_map_type__is_map_in_map(def->type) && @@ -1750,11 +1750,12 @@ bpf_object__create_maps(struct bpf_object *obj) } *pfd = bpf_create_map_xattr(&create_attr); - if (*pfd < 0 && create_attr.btf_fd >= 0) { + if (*pfd < 0 && (create_attr.btf_key_type_id || + create_attr.btf_value_type_id)) { cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", map->name, cp, errno); - create_attr.btf_fd = -1; + create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; map->btf_key_type_id = 0; @@ -2045,7 +2046,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.license = license; load_attr.kern_version = kern_version; load_attr.prog_ifindex = prog->prog_ifindex; - load_attr.prog_btf_fd = prog->btf_fd; + load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0; load_attr.func_info = prog->func_info; load_attr.func_info_rec_size = prog->func_info_rec_size; load_attr.func_info_cnt = prog->func_info_cnt; -- cgit v1.2.3 From 13a748ea6df1fee13fdcbd9d10a3d70f9e188b48 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 13 Jun 2019 15:00:03 -0700 Subject: bpf: Sync asm-generic/socket.h to tools/ SO_DETACH_REUSEPORT_BPF is needed for the test in the next patch. It is defined in the socket.h. Signed-off-by: Martin KaFai Lau Reviewed-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- tools/include/uapi/asm-generic/socket.h | 147 ++++++++++++++++++++++++++++++++ 1 file changed, 147 insertions(+) create mode 100644 tools/include/uapi/asm-generic/socket.h (limited to 'tools') diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h new file mode 100644 index 000000000000..77f7c1638eb1 --- /dev/null +++ b/tools/include/uapi/asm-generic/socket.h @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_GENERIC_SOCKET_H +#define __ASM_GENERIC_SOCKET_H + +#include +#include + +/* For setsockopt(2) */ +#define SOL_SOCKET 1 + +#define SO_DEBUG 1 +#define SO_REUSEADDR 2 +#define SO_TYPE 3 +#define SO_ERROR 4 +#define SO_DONTROUTE 5 +#define SO_BROADCAST 6 +#define SO_SNDBUF 7 +#define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 +#define SO_KEEPALIVE 9 +#define SO_OOBINLINE 10 +#define SO_NO_CHECK 11 +#define SO_PRIORITY 12 +#define SO_LINGER 13 +#define SO_BSDCOMPAT 14 +#define SO_REUSEPORT 15 +#ifndef SO_PASSCRED /* powerpc only differs in these */ +#define SO_PASSCRED 16 +#define SO_PEERCRED 17 +#define SO_RCVLOWAT 18 +#define SO_SNDLOWAT 19 +#define SO_RCVTIMEO_OLD 20 +#define SO_SNDTIMEO_OLD 21 +#endif + +/* Security levels - as per NRL IPv6 - don't actually do anything */ +#define SO_SECURITY_AUTHENTICATION 22 +#define SO_SECURITY_ENCRYPTION_TRANSPORT 23 +#define SO_SECURITY_ENCRYPTION_NETWORK 24 + +#define SO_BINDTODEVICE 25 + +/* Socket filtering */ +#define SO_ATTACH_FILTER 26 +#define SO_DETACH_FILTER 27 +#define SO_GET_FILTER SO_ATTACH_FILTER + +#define SO_PEERNAME 28 + +#define SO_ACCEPTCONN 30 + +#define SO_PEERSEC 31 +#define SO_PASSSEC 34 + +#define SO_MARK 36 + +#define SO_PROTOCOL 38 +#define SO_DOMAIN 39 + +#define SO_RXQ_OVFL 40 + +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS +#define SO_PEEK_OFF 42 + +/* Instruct lower device to use last 4-bytes of skb data as FCS */ +#define SO_NOFCS 43 + +#define SO_LOCK_FILTER 44 + +#define SO_SELECT_ERR_QUEUE 45 + +#define SO_BUSY_POLL 46 + +#define SO_MAX_PACING_RATE 47 + +#define SO_BPF_EXTENSIONS 48 + +#define SO_INCOMING_CPU 49 + +#define SO_ATTACH_BPF 50 +#define SO_DETACH_BPF SO_DETACH_FILTER + +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + +#define SO_CNX_ADVICE 53 + +#define SCM_TIMESTAMPING_OPT_STATS 54 + +#define SO_MEMINFO 55 + +#define SO_INCOMING_NAPI_ID 56 + +#define SO_COOKIE 57 + +#define SCM_TIMESTAMPING_PKTINFO 58 + +#define SO_PEERGROUPS 59 + +#define SO_ZEROCOPY 60 + +#define SO_TXTIME 61 +#define SCM_TXTIME SO_TXTIME + +#define SO_BINDTOIFINDEX 62 + +#define SO_TIMESTAMP_OLD 29 +#define SO_TIMESTAMPNS_OLD 35 +#define SO_TIMESTAMPING_OLD 37 + +#define SO_TIMESTAMP_NEW 63 +#define SO_TIMESTAMPNS_NEW 64 +#define SO_TIMESTAMPING_NEW 65 + +#define SO_RCVTIMEO_NEW 66 +#define SO_SNDTIMEO_NEW 67 + +#define SO_DETACH_REUSEPORT_BPF 68 + +#if !defined(__KERNEL__) + +#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) +/* on 64-bit and x32, avoid the ?: operator */ +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD +#else +#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) +#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) + +#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW) +#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW) +#endif + +#define SCM_TIMESTAMP SO_TIMESTAMP +#define SCM_TIMESTAMPNS SO_TIMESTAMPNS +#define SCM_TIMESTAMPING SO_TIMESTAMPING + +#endif + +#endif /* __ASM_GENERIC_SOCKET_H */ -- cgit v1.2.3 From d30bd78ce8ba1f093aa4877ed06601d0debd872b Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 13 Jun 2019 15:00:05 -0700 Subject: bpf: Add test for SO_REUSEPORT_DETACH_BPF This patch adds a test for the new sockopt SO_REUSEPORT_DETACH_BPF. Signed-off-by: Martin KaFai Lau Reviewed-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- .../testing/selftests/bpf/test_select_reuseport.c | 54 ++++++++++++++++++++++ 1 file changed, 54 insertions(+) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/test_select_reuseport.c b/tools/testing/selftests/bpf/test_select_reuseport.c index 75646d9b34aa..7566c13eb51a 100644 --- a/tools/testing/selftests/bpf/test_select_reuseport.c +++ b/tools/testing/selftests/bpf/test_select_reuseport.c @@ -523,6 +523,58 @@ static void test_pass_on_err(int type, sa_family_t family) printf("OK\n"); } +static void test_detach_bpf(int type, sa_family_t family) +{ +#ifdef SO_DETACH_REUSEPORT_BPF + __u32 nr_run_before = 0, nr_run_after = 0, tmp, i; + struct epoll_event ev; + int cli_fd, err, nev; + struct cmd cmd = {}; + int optvalue = 0; + + printf("%s: ", __func__); + err = setsockopt(sk_fds[0], SOL_SOCKET, SO_DETACH_REUSEPORT_BPF, + &optvalue, sizeof(optvalue)); + CHECK(err == -1, "setsockopt(SO_DETACH_REUSEPORT_BPF)", + "err:%d errno:%d\n", err, errno); + + err = setsockopt(sk_fds[1], SOL_SOCKET, SO_DETACH_REUSEPORT_BPF, + &optvalue, sizeof(optvalue)); + CHECK(err == 0 || errno != ENOENT, "setsockopt(SO_DETACH_REUSEPORT_BPF)", + "err:%d errno:%d\n", err, errno); + + for (i = 0; i < NR_RESULTS; i++) { + err = bpf_map_lookup_elem(result_map, &i, &tmp); + CHECK(err == -1, "lookup_elem(result_map)", + "i:%u err:%d errno:%d\n", i, err, errno); + nr_run_before += tmp; + } + + cli_fd = send_data(type, family, &cmd, sizeof(cmd), PASS); + nev = epoll_wait(epfd, &ev, 1, 5); + CHECK(nev <= 0, "nev <= 0", + "nev:%d expected:1 type:%d family:%d data:(0, 0)\n", + nev, type, family); + + for (i = 0; i < NR_RESULTS; i++) { + err = bpf_map_lookup_elem(result_map, &i, &tmp); + CHECK(err == -1, "lookup_elem(result_map)", + "i:%u err:%d errno:%d\n", i, err, errno); + nr_run_after += tmp; + } + + CHECK(nr_run_before != nr_run_after, + "nr_run_before != nr_run_after", + "nr_run_before:%u nr_run_after:%u\n", + nr_run_before, nr_run_after); + + printf("OK\n"); + close(cli_fd); +#else + printf("%s: SKIP\n", __func__); +#endif +} + static void prepare_sk_fds(int type, sa_family_t family, bool inany) { const int first = REUSEPORT_ARRAY_SIZE - 1; @@ -664,6 +716,8 @@ static void test_all(void) test_pass(type, family); test_syncookie(type, family); test_pass_on_err(type, family); + /* Must be the last test */ + test_detach_bpf(type, family); cleanup_per_test(); printf("\n"); -- cgit v1.2.3 From cd17d77705780e2270937fb3cbd2b985adab3edc Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Wed, 12 Jun 2019 10:30:39 -0700 Subject: bpf/tools: sync bpf.h Add sk to struct bpf_sock_addr and struct bpf_sock_ops. Cc: Martin Lau Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- tools/include/uapi/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index ae0907d8c03a..d0a23476f887 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3247,6 +3247,7 @@ struct bpf_sock_addr { __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. * Stored in network byte order. */ + __bpf_md_ptr(struct bpf_sock *, sk); }; /* User bpf_sock_ops struct to access socket values and specify request ops @@ -3298,6 +3299,7 @@ struct bpf_sock_ops { __u32 sk_txhash; __u64 bytes_received; __u64 bytes_acked; + __bpf_md_ptr(struct bpf_sock *, sk); }; /* Definitions for bpf_sock_ops_cb_flags */ -- cgit v1.2.3 From 69d96519dbf0bfa1868dc8597d4b9b2cdeb009d7 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Wed, 12 Jun 2019 10:30:40 -0700 Subject: selftests/bpf: convert socket_cookie test to sk storage This lets us test that both BPF_PROG_TYPE_CGROUP_SOCK_ADDR and BPF_PROG_TYPE_SOCK_OPS can access underlying bpf_sock. Cc: Martin Lau Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- .../selftests/bpf/progs/socket_cookie_prog.c | 46 ++++++++++++++-------- tools/testing/selftests/bpf/test_socket_cookie.c | 24 +++++------ 2 files changed, 38 insertions(+), 32 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c index 9ff8ac4b0bf6..0db15c3210ad 100644 --- a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c +++ b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c @@ -7,25 +7,35 @@ #include "bpf_helpers.h" #include "bpf_endian.h" +struct socket_cookie { + __u64 cookie_key; + __u32 cookie_value; +}; + struct bpf_map_def SEC("maps") socket_cookies = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u64), - .value_size = sizeof(__u32), - .max_entries = 1 << 8, + .type = BPF_MAP_TYPE_SK_STORAGE, + .key_size = sizeof(int), + .value_size = sizeof(struct socket_cookie), + .map_flags = BPF_F_NO_PREALLOC, }; +BPF_ANNOTATE_KV_PAIR(socket_cookies, int, struct socket_cookie); + SEC("cgroup/connect6") int set_cookie(struct bpf_sock_addr *ctx) { - __u32 cookie_value = 0xFF; - __u64 cookie_key; + struct socket_cookie *p; if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6) return 1; - cookie_key = bpf_get_socket_cookie(ctx); - if (bpf_map_update_elem(&socket_cookies, &cookie_key, &cookie_value, 0)) - return 0; + p = bpf_sk_storage_get(&socket_cookies, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!p) + return 1; + + p->cookie_value = 0xFF; + p->cookie_key = bpf_get_socket_cookie(ctx); return 1; } @@ -33,9 +43,8 @@ int set_cookie(struct bpf_sock_addr *ctx) SEC("sockops") int update_cookie(struct bpf_sock_ops *ctx) { - __u32 new_cookie_value; - __u32 *cookie_value; - __u64 cookie_key; + struct bpf_sock *sk; + struct socket_cookie *p; if (ctx->family != AF_INET6) return 1; @@ -43,14 +52,17 @@ int update_cookie(struct bpf_sock_ops *ctx) if (ctx->op != BPF_SOCK_OPS_TCP_CONNECT_CB) return 1; - cookie_key = bpf_get_socket_cookie(ctx); + if (!ctx->sk) + return 1; + + p = bpf_sk_storage_get(&socket_cookies, ctx->sk, 0, 0); + if (!p) + return 1; - cookie_value = bpf_map_lookup_elem(&socket_cookies, &cookie_key); - if (!cookie_value) + if (p->cookie_key != bpf_get_socket_cookie(ctx)) return 1; - new_cookie_value = (ctx->local_port << 8) | *cookie_value; - bpf_map_update_elem(&socket_cookies, &cookie_key, &new_cookie_value, 0); + p->cookie_value = (ctx->local_port << 8) | p->cookie_value; return 1; } diff --git a/tools/testing/selftests/bpf/test_socket_cookie.c b/tools/testing/selftests/bpf/test_socket_cookie.c index cac8ee57a013..15653b0e26eb 100644 --- a/tools/testing/selftests/bpf/test_socket_cookie.c +++ b/tools/testing/selftests/bpf/test_socket_cookie.c @@ -18,6 +18,11 @@ #define CG_PATH "/foo" #define SOCKET_COOKIE_PROG "./socket_cookie_prog.o" +struct socket_cookie { + __u64 cookie_key; + __u32 cookie_value; +}; + static int start_server(void) { struct sockaddr_in6 addr; @@ -89,8 +94,7 @@ static int validate_map(struct bpf_map *map, int client_fd) __u32 cookie_expected_value; struct sockaddr_in6 addr; socklen_t len = sizeof(addr); - __u32 cookie_value; - __u64 cookie_key; + struct socket_cookie val; int err = 0; int map_fd; @@ -101,17 +105,7 @@ static int validate_map(struct bpf_map *map, int client_fd) map_fd = bpf_map__fd(map); - err = bpf_map_get_next_key(map_fd, NULL, &cookie_key); - if (err) { - log_err("Can't get cookie key from map"); - goto out; - } - - err = bpf_map_lookup_elem(map_fd, &cookie_key, &cookie_value); - if (err) { - log_err("Can't get cookie value from map"); - goto out; - } + err = bpf_map_lookup_elem(map_fd, &client_fd, &val); err = getsockname(client_fd, (struct sockaddr *)&addr, &len); if (err) { @@ -120,8 +114,8 @@ static int validate_map(struct bpf_map *map, int client_fd) } cookie_expected_value = (ntohs(addr.sin6_port) << 8) | 0xFF; - if (cookie_value != cookie_expected_value) { - log_err("Unexpected value in map: %x != %x", cookie_value, + if (val.cookie_value != cookie_expected_value) { + log_err("Unexpected value in map: %x != %x", val.cookie_value, cookie_expected_value); goto err; } -- cgit v1.2.3 From d7fe74f9404a9736e9d4f754c30e43640a822c17 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 17 Jun 2019 12:26:50 -0700 Subject: libbpf: add common min/max macro to libbpf_internal.h Multiple files in libbpf redefine their own definitions for min/max. Let's define them in libbpf_internal.h and use those everywhere. Signed-off-by: Andrii Nakryiko Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- tools/lib/bpf/bpf.c | 7 ++----- tools/lib/bpf/bpf_prog_linfo.c | 5 +---- tools/lib/bpf/btf.c | 3 --- tools/lib/bpf/btf_dump.c | 3 --- tools/lib/bpf/libbpf_internal.h | 7 +++++++ 5 files changed, 10 insertions(+), 15 deletions(-) (limited to 'tools') diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 0d4b4fe10a84..c7d7993c44bb 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -26,10 +26,11 @@ #include #include #include +#include #include #include "bpf.h" #include "libbpf.h" -#include +#include "libbpf_internal.h" /* * When building perf, unistd.h is overridden. __NR_bpf is @@ -53,10 +54,6 @@ # endif #endif -#ifndef min -#define min(x, y) ((x) < (y) ? (x) : (y)) -#endif - static inline __u64 ptr_to_u64(const void *ptr) { return (__u64) (unsigned long) ptr; diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c index 6978314ea7f6..8c67561c93b0 100644 --- a/tools/lib/bpf/bpf_prog_linfo.c +++ b/tools/lib/bpf/bpf_prog_linfo.c @@ -6,10 +6,7 @@ #include #include #include "libbpf.h" - -#ifndef min -#define min(x, y) ((x) < (y) ? (x) : (y)) -#endif +#include "libbpf_internal.h" struct bpf_prog_linfo { void *raw_linfo; diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index b2478e98c367..467224feb43b 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -16,9 +16,6 @@ #include "libbpf_internal.h" #include "hashmap.h" -#define max(a, b) ((a) > (b) ? (a) : (b)) -#define min(a, b) ((a) < (b) ? (a) : (b)) - #define BTF_MAX_NR_TYPES 0x7fffffff #define BTF_MAX_STR_OFFSET 0x7fffffff diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 4b22db77e2cc..7065bb5b2752 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -18,9 +18,6 @@ #include "libbpf.h" #include "libbpf_internal.h" -#define min(x, y) ((x) < (y) ? (x) : (y)) -#define max(x, y) ((x) < (y) ? (y) : (x)) - static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t"; static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 850f7bdec5cb..554a7856dc2d 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -23,6 +23,13 @@ #define BTF_PARAM_ENC(name, type) (name), (type) #define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size) +#ifndef min +# define min(x, y) ((x) < (y) ? (x) : (y)) +#endif +#ifndef max +# define max(x, y) ((x) < (y) ? (y) : (x)) +#endif + extern void libbpf_print(enum libbpf_print_level level, const char *format, ...) __attribute__((format(printf, 2, 3))); -- cgit v1.2.3 From 9c6660d0406f8c32d21957ca9853108513bea8b1 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 17 Jun 2019 12:26:51 -0700 Subject: libbpf: extract BTF loading logic As a preparation for adding BTF-based BPF map loading, extract .BTF and .BTF.ext loading logic. Signed-off-by: Andrii Nakryiko Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- tools/lib/bpf/libbpf.c | 93 +++++++++++++++++++++++++++++--------------------- 1 file changed, 55 insertions(+), 38 deletions(-) (limited to 'tools') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e725fa86b189..49d3a808e754 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1078,6 +1078,58 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) } } +static int bpf_object__load_btf(struct bpf_object *obj, + Elf_Data *btf_data, + Elf_Data *btf_ext_data) +{ + int err = 0; + + if (btf_data) { + obj->btf = btf__new(btf_data->d_buf, btf_data->d_size); + if (IS_ERR(obj->btf)) { + pr_warning("Error loading ELF section %s: %d.\n", + BTF_ELF_SEC, err); + goto out; + } + err = btf__finalize_data(obj, obj->btf); + if (err) { + pr_warning("Error finalizing %s: %d.\n", + BTF_ELF_SEC, err); + goto out; + } + bpf_object__sanitize_btf(obj); + err = btf__load(obj->btf); + if (err) { + pr_warning("Error loading %s into kernel: %d.\n", + BTF_ELF_SEC, err); + goto out; + } + } + if (btf_ext_data) { + if (!obj->btf) { + pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n", + BTF_EXT_ELF_SEC, BTF_ELF_SEC); + goto out; + } + obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, + btf_ext_data->d_size); + if (IS_ERR(obj->btf_ext)) { + pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", + BTF_EXT_ELF_SEC, PTR_ERR(obj->btf_ext)); + obj->btf_ext = NULL; + goto out; + } + bpf_object__sanitize_btf_ext(obj); + } +out: + if (err || IS_ERR(obj->btf)) { + if (!IS_ERR_OR_NULL(obj->btf)) + btf__free(obj->btf); + obj->btf = NULL; + } + return 0; +} + static int bpf_object__elf_collect(struct bpf_object *obj, int flags) { Elf *elf = obj->efile.elf; @@ -1212,44 +1264,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) pr_warning("Corrupted ELF file: index of strtab invalid\n"); return -LIBBPF_ERRNO__FORMAT; } - if (btf_data) { - obj->btf = btf__new(btf_data->d_buf, btf_data->d_size); - if (IS_ERR(obj->btf)) { - pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", - BTF_ELF_SEC, PTR_ERR(obj->btf)); - obj->btf = NULL; - } else { - err = btf__finalize_data(obj, obj->btf); - if (!err) { - bpf_object__sanitize_btf(obj); - err = btf__load(obj->btf); - } - if (err) { - pr_warning("Error finalizing and loading %s into kernel: %d. Ignored and continue.\n", - BTF_ELF_SEC, err); - btf__free(obj->btf); - obj->btf = NULL; - err = 0; - } - } - } - if (btf_ext_data) { - if (!obj->btf) { - pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n", - BTF_EXT_ELF_SEC, BTF_ELF_SEC); - } else { - obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, - btf_ext_data->d_size); - if (IS_ERR(obj->btf_ext)) { - pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", - BTF_EXT_ELF_SEC, - PTR_ERR(obj->btf_ext)); - obj->btf_ext = NULL; - } else { - bpf_object__sanitize_btf_ext(obj); - } - } - } + err = bpf_object__load_btf(obj, btf_data, btf_ext_data); + if (err) + return err; if (bpf_object__has_maps(obj)) { err = bpf_object__init_maps(obj, flags); if (err) -- cgit v1.2.3 From 01b29d1dc9a06e2cdc6a0172d35605eb0300ecb2 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 17 Jun 2019 12:26:52 -0700 Subject: libbpf: streamline ELF parsing error-handling Simplify ELF parsing logic by exiting early, as there is no common clean up path to execute. That makes it unnecessary to track when err was set and when it was cleared. It also reduces nesting in some places. Signed-off-by: Andrii Nakryiko Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- tools/lib/bpf/libbpf.c | 44 ++++++++++++++++++++------------------------ 1 file changed, 20 insertions(+), 24 deletions(-) (limited to 'tools') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 49d3a808e754..7ee44d8877c5 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1154,24 +1154,21 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) if (gelf_getshdr(scn, &sh) != &sh) { pr_warning("failed to get section(%d) header from %s\n", idx, obj->path); - err = -LIBBPF_ERRNO__FORMAT; - goto out; + return -LIBBPF_ERRNO__FORMAT; } name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name); if (!name) { pr_warning("failed to get section(%d) name from %s\n", idx, obj->path); - err = -LIBBPF_ERRNO__FORMAT; - goto out; + return -LIBBPF_ERRNO__FORMAT; } data = elf_getdata(scn, 0); if (!data) { pr_warning("failed to get section(%d) data from %s(%s)\n", idx, name, obj->path); - err = -LIBBPF_ERRNO__FORMAT; - goto out; + return -LIBBPF_ERRNO__FORMAT; } pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n", idx, name, (unsigned long)data->d_size, @@ -1182,10 +1179,14 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) err = bpf_object__init_license(obj, data->d_buf, data->d_size); + if (err) + return err; } else if (strcmp(name, "version") == 0) { err = bpf_object__init_kversion(obj, data->d_buf, data->d_size); + if (err) + return err; } else if (strcmp(name, "maps") == 0) { obj->efile.maps_shndx = idx; } else if (strcmp(name, BTF_ELF_SEC) == 0) { @@ -1196,11 +1197,10 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) if (obj->efile.symbols) { pr_warning("bpf: multiple SYMTAB in %s\n", obj->path); - err = -LIBBPF_ERRNO__FORMAT; - } else { - obj->efile.symbols = data; - obj->efile.strtabidx = sh.sh_link; + return -LIBBPF_ERRNO__FORMAT; } + obj->efile.symbols = data; + obj->efile.strtabidx = sh.sh_link; } else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) { if (sh.sh_flags & SHF_EXECINSTR) { if (strcmp(name, ".text") == 0) @@ -1214,6 +1214,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) pr_warning("failed to alloc program %s (%s): %s", name, obj->path, cp); + return err; } } else if (strcmp(name, ".data") == 0) { obj->efile.data = data; @@ -1225,8 +1226,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) pr_debug("skip section(%d) %s\n", idx, name); } } else if (sh.sh_type == SHT_REL) { + int nr_reloc = obj->efile.nr_reloc; void *reloc = obj->efile.reloc; - int nr_reloc = obj->efile.nr_reloc + 1; int sec = sh.sh_info; /* points to other section */ /* Only do relo for section with exec instructions */ @@ -1236,28 +1237,24 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) continue; } - reloc = reallocarray(reloc, nr_reloc, + reloc = reallocarray(reloc, nr_reloc + 1, sizeof(*obj->efile.reloc)); if (!reloc) { pr_warning("realloc failed\n"); - err = -ENOMEM; - } else { - int n = nr_reloc - 1; + return -ENOMEM; + } - obj->efile.reloc = reloc; - obj->efile.nr_reloc = nr_reloc; + obj->efile.reloc = reloc; + obj->efile.nr_reloc++; - obj->efile.reloc[n].shdr = sh; - obj->efile.reloc[n].data = data; - } + obj->efile.reloc[nr_reloc].shdr = sh; + obj->efile.reloc[nr_reloc].data = data; } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) { obj->efile.bss = data; obj->efile.bss_shndx = idx; } else { pr_debug("skip section(%d) %s\n", idx, name); } - if (err) - goto out; } if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) { @@ -1270,10 +1267,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) if (bpf_object__has_maps(obj)) { err = bpf_object__init_maps(obj, flags); if (err) - goto out; + return err; } err = bpf_object__init_prog_names(obj); -out: return err; } -- cgit v1.2.3 From bf82927125dd25003d76ed5541da704df21de57a Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 17 Jun 2019 12:26:53 -0700 Subject: libbpf: refactor map initialization User and global data maps initialization has gotten pretty complicated and unnecessarily convoluted. This patch splits out the logic for global data map and user-defined map initialization. It also removes the restriction of pre-calculating how many maps will be initialized, instead allowing to keep adding new maps as they are discovered, which will be used later for BTF-defined map definitions. Signed-off-by: Andrii Nakryiko Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- tools/lib/bpf/libbpf.c | 247 ++++++++++++++++++++++++++----------------------- 1 file changed, 133 insertions(+), 114 deletions(-) (limited to 'tools') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 7ee44d8877c5..88609dca4f7d 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -234,6 +234,7 @@ struct bpf_object { size_t nr_programs; struct bpf_map *maps; size_t nr_maps; + size_t maps_cap; struct bpf_secdata sections; bool loaded; @@ -763,21 +764,51 @@ int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, return -ENOENT; } -static bool bpf_object__has_maps(const struct bpf_object *obj) +static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) { - return obj->efile.maps_shndx >= 0 || - obj->efile.data_shndx >= 0 || - obj->efile.rodata_shndx >= 0 || - obj->efile.bss_shndx >= 0; + struct bpf_map *new_maps; + size_t new_cap; + int i; + + if (obj->nr_maps < obj->maps_cap) + return &obj->maps[obj->nr_maps++]; + + new_cap = max(4ul, obj->maps_cap * 3 / 2); + new_maps = realloc(obj->maps, new_cap * sizeof(*obj->maps)); + if (!new_maps) { + pr_warning("alloc maps for object failed\n"); + return ERR_PTR(-ENOMEM); + } + + obj->maps_cap = new_cap; + obj->maps = new_maps; + + /* zero out new maps */ + memset(obj->maps + obj->nr_maps, 0, + (obj->maps_cap - obj->nr_maps) * sizeof(*obj->maps)); + /* + * fill all fd with -1 so won't close incorrect fd (fd=0 is stdin) + * when failure (zclose won't close negative fd)). + */ + for (i = obj->nr_maps; i < obj->maps_cap; i++) { + obj->maps[i].fd = -1; + obj->maps[i].inner_map_fd = -1; + } + + return &obj->maps[obj->nr_maps++]; } static int -bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map, - enum libbpf_map_type type, Elf_Data *data, - void **data_buff) +bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, + Elf_Data *data, void **data_buff) { - struct bpf_map_def *def = &map->def; char map_name[BPF_OBJ_NAME_LEN]; + struct bpf_map_def *def; + struct bpf_map *map; + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); map->libbpf_type = type; map->offset = ~(typeof(map->offset))0; @@ -789,6 +820,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map, return -ENOMEM; } + def = &map->def; def->type = BPF_MAP_TYPE_ARRAY; def->key_size = sizeof(int); def->value_size = data->d_size; @@ -808,29 +840,58 @@ bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map, return 0; } -static int bpf_object__init_maps(struct bpf_object *obj, int flags) +static int bpf_object__init_global_data_maps(struct bpf_object *obj) +{ + int err; + + if (!obj->caps.global_data) + return 0; + /* + * Populate obj->maps with libbpf internal maps. + */ + if (obj->efile.data_shndx >= 0) { + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA, + obj->efile.data, + &obj->sections.data); + if (err) + return err; + } + if (obj->efile.rodata_shndx >= 0) { + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA, + obj->efile.rodata, + &obj->sections.rodata); + if (err) + return err; + } + if (obj->efile.bss_shndx >= 0) { + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS, + obj->efile.bss, NULL); + if (err) + return err; + } + return 0; +} + +static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) { - int i, map_idx, map_def_sz = 0, nr_syms, nr_maps = 0, nr_maps_glob = 0; - bool strict = !(flags & MAPS_RELAX_COMPAT); Elf_Data *symbols = obj->efile.symbols; + int i, map_def_sz = 0, nr_maps = 0, nr_syms; Elf_Data *data = NULL; - int ret = 0; + Elf_Scn *scn; + + if (obj->efile.maps_shndx < 0) + return 0; if (!symbols) return -EINVAL; - nr_syms = symbols->d_size / sizeof(GElf_Sym); - - if (obj->efile.maps_shndx >= 0) { - Elf_Scn *scn = elf_getscn(obj->efile.elf, - obj->efile.maps_shndx); - if (scn) - data = elf_getdata(scn, NULL); - if (!scn || !data) { - pr_warning("failed to get Elf_Data from map section %d\n", - obj->efile.maps_shndx); - return -EINVAL; - } + scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx); + if (scn) + data = elf_getdata(scn, NULL); + if (!scn || !data) { + pr_warning("failed to get Elf_Data from map section %d\n", + obj->efile.maps_shndx); + return -EINVAL; } /* @@ -840,16 +901,8 @@ static int bpf_object__init_maps(struct bpf_object *obj, int flags) * * TODO: Detect array of map and report error. */ - if (obj->caps.global_data) { - if (obj->efile.data_shndx >= 0) - nr_maps_glob++; - if (obj->efile.rodata_shndx >= 0) - nr_maps_glob++; - if (obj->efile.bss_shndx >= 0) - nr_maps_glob++; - } - - for (i = 0; data && i < nr_syms; i++) { + nr_syms = symbols->d_size / sizeof(GElf_Sym); + for (i = 0; i < nr_syms; i++) { GElf_Sym sym; if (!gelf_getsym(symbols, i, &sym)) @@ -858,79 +911,56 @@ static int bpf_object__init_maps(struct bpf_object *obj, int flags) continue; nr_maps++; } - - if (!nr_maps && !nr_maps_glob) - return 0; - /* Assume equally sized map definitions */ - if (data) { - pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path, - nr_maps, data->d_size); - - map_def_sz = data->d_size / nr_maps; - if (!data->d_size || (data->d_size % nr_maps) != 0) { - pr_warning("unable to determine map definition size " - "section %s, %d maps in %zd bytes\n", - obj->path, nr_maps, data->d_size); - return -EINVAL; - } - } - - nr_maps += nr_maps_glob; - obj->maps = calloc(nr_maps, sizeof(obj->maps[0])); - if (!obj->maps) { - pr_warning("alloc maps for object failed\n"); - return -ENOMEM; - } - obj->nr_maps = nr_maps; - - for (i = 0; i < nr_maps; i++) { - /* - * fill all fd with -1 so won't close incorrect - * fd (fd=0 is stdin) when failure (zclose won't close - * negative fd)). - */ - obj->maps[i].fd = -1; - obj->maps[i].inner_map_fd = -1; + pr_debug("maps in %s: %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + + map_def_sz = data->d_size / nr_maps; + if (!data->d_size || (data->d_size % nr_maps) != 0) { + pr_warning("unable to determine map definition size " + "section %s, %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + return -EINVAL; } - /* - * Fill obj->maps using data in "maps" section. - */ - for (i = 0, map_idx = 0; data && i < nr_syms; i++) { + /* Fill obj->maps using data in "maps" section. */ + for (i = 0; i < nr_syms; i++) { GElf_Sym sym; const char *map_name; struct bpf_map_def *def; + struct bpf_map *map; if (!gelf_getsym(symbols, i, &sym)) continue; if (sym.st_shndx != obj->efile.maps_shndx) continue; - map_name = elf_strptr(obj->efile.elf, - obj->efile.strtabidx, + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + + map_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, sym.st_name); if (!map_name) { pr_warning("failed to get map #%d name sym string for obj %s\n", - map_idx, obj->path); + i, obj->path); return -LIBBPF_ERRNO__FORMAT; } - obj->maps[map_idx].libbpf_type = LIBBPF_MAP_UNSPEC; - obj->maps[map_idx].offset = sym.st_value; + map->libbpf_type = LIBBPF_MAP_UNSPEC; + map->offset = sym.st_value; if (sym.st_value + map_def_sz > data->d_size) { pr_warning("corrupted maps section in %s: last map \"%s\" too small\n", obj->path, map_name); return -EINVAL; } - obj->maps[map_idx].name = strdup(map_name); - if (!obj->maps[map_idx].name) { + map->name = strdup(map_name); + if (!map->name) { pr_warning("failed to alloc map name\n"); return -ENOMEM; } - pr_debug("map %d is \"%s\"\n", map_idx, - obj->maps[map_idx].name); + pr_debug("map %d is \"%s\"\n", i, map->name); def = (struct bpf_map_def *)(data->d_buf + sym.st_value); /* * If the definition of the map in the object file fits in @@ -939,7 +969,7 @@ static int bpf_object__init_maps(struct bpf_object *obj, int flags) * calloc above. */ if (map_def_sz <= sizeof(struct bpf_map_def)) { - memcpy(&obj->maps[map_idx].def, def, map_def_sz); + memcpy(&map->def, def, map_def_sz); } else { /* * Here the map structure being read is bigger than what @@ -959,37 +989,30 @@ static int bpf_object__init_maps(struct bpf_object *obj, int flags) return -EINVAL; } } - memcpy(&obj->maps[map_idx].def, def, - sizeof(struct bpf_map_def)); + memcpy(&map->def, def, sizeof(struct bpf_map_def)); } - map_idx++; } + return 0; +} - if (!obj->caps.global_data) - goto finalize; +static int bpf_object__init_maps(struct bpf_object *obj, int flags) +{ + bool strict = !(flags & MAPS_RELAX_COMPAT); + int err; - /* - * Populate rest of obj->maps with libbpf internal maps. - */ - if (obj->efile.data_shndx >= 0) - ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], - LIBBPF_MAP_DATA, - obj->efile.data, - &obj->sections.data); - if (!ret && obj->efile.rodata_shndx >= 0) - ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], - LIBBPF_MAP_RODATA, - obj->efile.rodata, - &obj->sections.rodata); - if (!ret && obj->efile.bss_shndx >= 0) - ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], - LIBBPF_MAP_BSS, - obj->efile.bss, NULL); -finalize: - if (!ret) + err = bpf_object__init_user_maps(obj, strict); + if (err) + return err; + + err = bpf_object__init_global_data_maps(obj); + if (err) + return err; + + if (obj->nr_maps) { qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map); - return ret; + } + return 0; } static bool section_have_execinstr(struct bpf_object *obj, int idx) @@ -1262,14 +1285,10 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) return -LIBBPF_ERRNO__FORMAT; } err = bpf_object__load_btf(obj, btf_data, btf_ext_data); - if (err) - return err; - if (bpf_object__has_maps(obj)) { + if (!err) err = bpf_object__init_maps(obj, flags); - if (err) - return err; - } - err = bpf_object__init_prog_names(obj); + if (!err) + err = bpf_object__init_prog_names(obj); return err; } -- cgit v1.2.3 From db48814bd2833ee231f48bd2030082369b88f9ef Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 17 Jun 2019 12:26:54 -0700 Subject: libbpf: identify maps by section index in addition to offset To support maps to be defined in multiple sections, it's important to identify map not just by offset within its section, but section index as well. This patch adds tracking of section index. For global data, we record section index of corresponding .data/.bss/.rodata ELF section for uniformity, and thus don't need a special value of offset for those maps. Signed-off-by: Andrii Nakryiko Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- tools/lib/bpf/libbpf.c | 40 +++++++++++++++++++++++++--------------- 1 file changed, 25 insertions(+), 15 deletions(-) (limited to 'tools') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 88609dca4f7d..b1f3ab4b39b3 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -207,7 +207,8 @@ static const char * const libbpf_type_to_btf_name[] = { struct bpf_map { int fd; char *name; - size_t offset; + int sec_idx; + size_t sec_offset; int map_ifindex; int inner_map_fd; struct bpf_map_def def; @@ -647,7 +648,9 @@ static int compare_bpf_map(const void *_a, const void *_b) const struct bpf_map *a = _a; const struct bpf_map *b = _b; - return a->offset - b->offset; + if (a->sec_idx != b->sec_idx) + return a->sec_idx - b->sec_idx; + return a->sec_offset - b->sec_offset; } static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) @@ -800,7 +803,7 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) static int bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, - Elf_Data *data, void **data_buff) + int sec_idx, Elf_Data *data, void **data_buff) { char map_name[BPF_OBJ_NAME_LEN]; struct bpf_map_def *def; @@ -811,7 +814,8 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, return PTR_ERR(map); map->libbpf_type = type; - map->offset = ~(typeof(map->offset))0; + map->sec_idx = sec_idx; + map->sec_offset = 0; snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name, libbpf_type_to_btf_name[type]); map->name = strdup(map_name); @@ -819,6 +823,8 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, pr_warning("failed to alloc map name\n"); return -ENOMEM; } + pr_debug("map '%s' (global data): at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); def = &map->def; def->type = BPF_MAP_TYPE_ARRAY; @@ -851,6 +857,7 @@ static int bpf_object__init_global_data_maps(struct bpf_object *obj) */ if (obj->efile.data_shndx >= 0) { err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA, + obj->efile.data_shndx, obj->efile.data, &obj->sections.data); if (err) @@ -858,6 +865,7 @@ static int bpf_object__init_global_data_maps(struct bpf_object *obj) } if (obj->efile.rodata_shndx >= 0) { err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA, + obj->efile.rodata_shndx, obj->efile.rodata, &obj->sections.rodata); if (err) @@ -865,6 +873,7 @@ static int bpf_object__init_global_data_maps(struct bpf_object *obj) } if (obj->efile.bss_shndx >= 0) { err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS, + obj->efile.bss_shndx, obj->efile.bss, NULL); if (err) return err; @@ -948,7 +957,10 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) } map->libbpf_type = LIBBPF_MAP_UNSPEC; - map->offset = sym.st_value; + map->sec_idx = sym.st_shndx; + map->sec_offset = sym.st_value; + pr_debug("map '%s' (legacy): at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); if (sym.st_value + map_def_sz > data->d_size) { pr_warning("corrupted maps section in %s: last map \"%s\" too small\n", obj->path, map_name); @@ -1448,9 +1460,13 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, if (maps[map_idx].libbpf_type != type) continue; if (type != LIBBPF_MAP_UNSPEC || - maps[map_idx].offset == sym.st_value) { - pr_debug("relocation: find map %zd (%s) for insn %u\n", - map_idx, maps[map_idx].name, insn_idx); + (maps[map_idx].sec_idx == sym.st_shndx && + maps[map_idx].sec_offset == sym.st_value)) { + pr_debug("relocation: found map %zd (%s, sec_idx %d, offset %zu) for insn %u\n", + map_idx, maps[map_idx].name, + maps[map_idx].sec_idx, + maps[map_idx].sec_offset, + insn_idx); break; } } @@ -3468,13 +3484,7 @@ bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name) struct bpf_map * bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset) { - int i; - - for (i = 0; i < obj->nr_maps; i++) { - if (obj->maps[i].offset == offset) - return &obj->maps[i]; - } - return ERR_PTR(-ENOENT); + return ERR_PTR(-ENOTSUP); } long libbpf_get_error(const void *ptr) -- cgit v1.2.3 From 063183bf0486c7e61a2b454896bba2f7908b4ab0 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 17 Jun 2019 12:26:55 -0700 Subject: libbpf: split initialization and loading of BTF Libbpf does sanitization of BTF before loading it into kernel, if kernel doesn't support some of newer BTF features. This removes some of the important information from BTF (e.g., DATASEC and VAR description), which will be used for map construction. This patch splits BTF processing into initialization step, in which BTF is initialized from ELF and all the original data is still preserved; and sanitization/loading step, which ensures that BTF is safe to load into kernel. This allows to use full BTF information to construct maps, while still loading valid BTF into older kernels. Signed-off-by: Andrii Nakryiko Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- tools/lib/bpf/libbpf.c | 34 ++++++++++++++++++++++++---------- 1 file changed, 24 insertions(+), 10 deletions(-) (limited to 'tools') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index b1f3ab4b39b3..da942ab2f06a 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1113,7 +1113,7 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) } } -static int bpf_object__load_btf(struct bpf_object *obj, +static int bpf_object__init_btf(struct bpf_object *obj, Elf_Data *btf_data, Elf_Data *btf_ext_data) { @@ -1132,13 +1132,6 @@ static int bpf_object__load_btf(struct bpf_object *obj, BTF_ELF_SEC, err); goto out; } - bpf_object__sanitize_btf(obj); - err = btf__load(obj->btf); - if (err) { - pr_warning("Error loading %s into kernel: %d.\n", - BTF_ELF_SEC, err); - goto out; - } } if (btf_ext_data) { if (!obj->btf) { @@ -1154,7 +1147,6 @@ static int bpf_object__load_btf(struct bpf_object *obj, obj->btf_ext = NULL; goto out; } - bpf_object__sanitize_btf_ext(obj); } out: if (err || IS_ERR(obj->btf)) { @@ -1165,6 +1157,26 @@ out: return 0; } +static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) +{ + int err = 0; + + if (!obj->btf) + return 0; + + bpf_object__sanitize_btf(obj); + bpf_object__sanitize_btf_ext(obj); + + err = btf__load(obj->btf); + if (err) { + pr_warning("Error loading %s into kernel: %d.\n", + BTF_ELF_SEC, err); + btf__free(obj->btf); + obj->btf = NULL; + } + return 0; +} + static int bpf_object__elf_collect(struct bpf_object *obj, int flags) { Elf *elf = obj->efile.elf; @@ -1296,9 +1308,11 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) pr_warning("Corrupted ELF file: index of strtab invalid\n"); return -LIBBPF_ERRNO__FORMAT; } - err = bpf_object__load_btf(obj, btf_data, btf_ext_data); + err = bpf_object__init_btf(obj, btf_data, btf_ext_data); if (!err) err = bpf_object__init_maps(obj, flags); + if (!err) + err = bpf_object__sanitize_and_load_btf(obj); if (!err) err = bpf_object__init_prog_names(obj); return err; -- cgit v1.2.3 From abd29c9314595b1ee5ec6c61d7c49a497ffb30a3 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 17 Jun 2019 12:26:56 -0700 Subject: libbpf: allow specifying map definitions using BTF This patch adds support for a new way to define BPF maps. It relies on BTF to describe mandatory and optional attributes of a map, as well as captures type information of key and value naturally. This eliminates the need for BPF_ANNOTATE_KV_PAIR hack and ensures key/value sizes are always in sync with the key/value type. Relying on BTF, this approach allows for both forward and backward compatibility w.r.t. extending supported map definition features. By default, any unrecognized attributes are treated as an error, but it's possible relax this using MAPS_RELAX_COMPAT flag. New attributes, added in the future will need to be optional. The outline of the new map definition (short, BTF-defined maps) is as follows: 1. All the maps should be defined in .maps ELF section. It's possible to have both "legacy" map definitions in `maps` sections and BTF-defined maps in .maps sections. Everything will still work transparently. 2. The map declaration and initialization is done through a global/static variable of a struct type with few mandatory and extra optional fields: - type field is mandatory and specified type of BPF map; - key/value fields are mandatory and capture key/value type/size information; - max_entries attribute is optional; if max_entries is not specified or initialized, it has to be provided in runtime through libbpf API before loading bpf_object; - map_flags is optional and if not defined, will be assumed to be 0. 3. Key/value fields should be **a pointer** to a type describing key/value. The pointee type is assumed (and will be recorded as such and used for size determination) to be a type describing key/value of the map. This is done to save excessive amounts of space allocated in corresponding ELF sections for key/value of big size. 4. As some maps disallow having BTF type ID associated with key/value, it's possible to specify key/value size explicitly without associating BTF type ID with it. Use key_size and value_size fields to do that (see example below). Here's an example of simple ARRAY map defintion: struct my_value { int x, y, z; }; struct { int type; int max_entries; int *key; struct my_value *value; } btf_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, .max_entries = 16, }; This will define BPF ARRAY map 'btf_map' with 16 elements. The key will be of type int and thus key size will be 4 bytes. The value is struct my_value of size 12 bytes. This map can be used from C code exactly the same as with existing maps defined through struct bpf_map_def. Here's an example of STACKMAP definition (which currently disallows BTF type IDs for key/value): struct { __u32 type; __u32 max_entries; __u32 map_flags; __u32 key_size; __u32 value_size; } stackmap SEC(".maps") = { .type = BPF_MAP_TYPE_STACK_TRACE, .max_entries = 128, .map_flags = BPF_F_STACK_BUILD_ID, .key_size = sizeof(__u32), .value_size = PERF_MAX_STACK_DEPTH * sizeof(struct bpf_stack_build_id), }; This approach is naturally extended to support map-in-map, by making a value field to be another struct that describes inner map. This feature is not implemented yet. It's also possible to incrementally add features like pinning with full backwards and forward compatibility. Support for static initialization of BPF_MAP_TYPE_PROG_ARRAY using pointers to BPF programs is also on the roadmap. Signed-off-by: Andrii Nakryiko Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- tools/lib/bpf/btf.h | 1 + tools/lib/bpf/libbpf.c | 353 +++++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 345 insertions(+), 9 deletions(-) (limited to 'tools') diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index ba4ffa831aa4..88a52ae56fc6 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -17,6 +17,7 @@ extern "C" { #define BTF_ELF_SEC ".BTF" #define BTF_EXT_ELF_SEC ".BTF.ext" +#define MAPS_ELF_SEC ".maps" struct btf; struct btf_ext; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index da942ab2f06a..585e3a2f1eb4 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -262,6 +262,7 @@ struct bpf_object { } *reloc; int nr_reloc; int maps_shndx; + int btf_maps_shndx; int text_shndx; int data_shndx; int rodata_shndx; @@ -514,6 +515,7 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf = obj_buf; obj->efile.obj_buf_sz = obj_buf_sz; obj->efile.maps_shndx = -1; + obj->efile.btf_maps_shndx = -1; obj->efile.data_shndx = -1; obj->efile.rodata_shndx = -1; obj->efile.bss_shndx = -1; @@ -1007,6 +1009,312 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) return 0; } +static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, + __u32 id) +{ + const struct btf_type *t = btf__type_by_id(btf, id); + + while (true) { + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + t = btf__type_by_id(btf, t->type); + break; + default: + return t; + } + } +} + +static bool get_map_field_int(const char *map_name, + const struct btf *btf, + const struct btf_type *def, + const struct btf_member *m, + const void *data, __u32 *res) { + const struct btf_type *t = skip_mods_and_typedefs(btf, m->type); + const char *name = btf__name_by_offset(btf, m->name_off); + __u32 int_info = *(const __u32 *)(const void *)(t + 1); + + if (BTF_INFO_KIND(t->info) != BTF_KIND_INT) { + pr_warning("map '%s': attr '%s': expected INT, got %u.\n", + map_name, name, BTF_INFO_KIND(t->info)); + return false; + } + if (t->size != 4 || BTF_INT_BITS(int_info) != 32 || + BTF_INT_OFFSET(int_info)) { + pr_warning("map '%s': attr '%s': expected 32-bit non-bitfield integer, " + "got %u-byte (%d-bit) one with bit offset %d.\n", + map_name, name, t->size, BTF_INT_BITS(int_info), + BTF_INT_OFFSET(int_info)); + return false; + } + if (BTF_INFO_KFLAG(def->info) && BTF_MEMBER_BITFIELD_SIZE(m->offset)) { + pr_warning("map '%s': attr '%s': bitfield is not supported.\n", + map_name, name); + return false; + } + if (m->offset % 32) { + pr_warning("map '%s': attr '%s': unaligned fields are not supported.\n", + map_name, name); + return false; + } + + *res = *(const __u32 *)(data + m->offset / 8); + return true; +} + +static int bpf_object__init_user_btf_map(struct bpf_object *obj, + const struct btf_type *sec, + int var_idx, int sec_idx, + const Elf_Data *data, bool strict) +{ + const struct btf_type *var, *def, *t; + const struct btf_var_secinfo *vi; + const struct btf_var *var_extra; + const struct btf_member *m; + const void *def_data; + const char *map_name; + struct bpf_map *map; + int vlen, i; + + vi = (const struct btf_var_secinfo *)(const void *)(sec + 1) + var_idx; + var = btf__type_by_id(obj->btf, vi->type); + var_extra = (const void *)(var + 1); + map_name = btf__name_by_offset(obj->btf, var->name_off); + vlen = BTF_INFO_VLEN(var->info); + + if (map_name == NULL || map_name[0] == '\0') { + pr_warning("map #%d: empty name.\n", var_idx); + return -EINVAL; + } + if ((__u64)vi->offset + vi->size > data->d_size) { + pr_warning("map '%s' BTF data is corrupted.\n", map_name); + return -EINVAL; + } + if (BTF_INFO_KIND(var->info) != BTF_KIND_VAR) { + pr_warning("map '%s': unexpected var kind %u.\n", + map_name, BTF_INFO_KIND(var->info)); + return -EINVAL; + } + if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && + var_extra->linkage != BTF_VAR_STATIC) { + pr_warning("map '%s': unsupported var linkage %u.\n", + map_name, var_extra->linkage); + return -EOPNOTSUPP; + } + + def = skip_mods_and_typedefs(obj->btf, var->type); + if (BTF_INFO_KIND(def->info) != BTF_KIND_STRUCT) { + pr_warning("map '%s': unexpected def kind %u.\n", + map_name, BTF_INFO_KIND(var->info)); + return -EINVAL; + } + if (def->size > vi->size) { + pr_warning("map '%s': invalid def size.\n", map_name); + return -EINVAL; + } + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + map->name = strdup(map_name); + if (!map->name) { + pr_warning("map '%s': failed to alloc map name.\n", map_name); + return -ENOMEM; + } + map->libbpf_type = LIBBPF_MAP_UNSPEC; + map->def.type = BPF_MAP_TYPE_UNSPEC; + map->sec_idx = sec_idx; + map->sec_offset = vi->offset; + pr_debug("map '%s': at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); + + def_data = data->d_buf + vi->offset; + vlen = BTF_INFO_VLEN(def->info); + m = (const void *)(def + 1); + for (i = 0; i < vlen; i++, m++) { + const char *name = btf__name_by_offset(obj->btf, m->name_off); + + if (!name) { + pr_warning("map '%s': invalid field #%d.\n", + map_name, i); + return -EINVAL; + } + if (strcmp(name, "type") == 0) { + if (!get_map_field_int(map_name, obj->btf, def, m, + def_data, &map->def.type)) + return -EINVAL; + pr_debug("map '%s': found type = %u.\n", + map_name, map->def.type); + } else if (strcmp(name, "max_entries") == 0) { + if (!get_map_field_int(map_name, obj->btf, def, m, + def_data, &map->def.max_entries)) + return -EINVAL; + pr_debug("map '%s': found max_entries = %u.\n", + map_name, map->def.max_entries); + } else if (strcmp(name, "map_flags") == 0) { + if (!get_map_field_int(map_name, obj->btf, def, m, + def_data, &map->def.map_flags)) + return -EINVAL; + pr_debug("map '%s': found map_flags = %u.\n", + map_name, map->def.map_flags); + } else if (strcmp(name, "key_size") == 0) { + __u32 sz; + + if (!get_map_field_int(map_name, obj->btf, def, m, + def_data, &sz)) + return -EINVAL; + pr_debug("map '%s': found key_size = %u.\n", + map_name, sz); + if (map->def.key_size && map->def.key_size != sz) { + pr_warning("map '%s': conflictling key size %u != %u.\n", + map_name, map->def.key_size, sz); + return -EINVAL; + } + map->def.key_size = sz; + } else if (strcmp(name, "key") == 0) { + __s64 sz; + + t = btf__type_by_id(obj->btf, m->type); + if (!t) { + pr_warning("map '%s': key type [%d] not found.\n", + map_name, m->type); + return -EINVAL; + } + if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + pr_warning("map '%s': key spec is not PTR: %u.\n", + map_name, BTF_INFO_KIND(t->info)); + return -EINVAL; + } + sz = btf__resolve_size(obj->btf, t->type); + if (sz < 0) { + pr_warning("map '%s': can't determine key size for type [%u]: %lld.\n", + map_name, t->type, sz); + return sz; + } + pr_debug("map '%s': found key [%u], sz = %lld.\n", + map_name, t->type, sz); + if (map->def.key_size && map->def.key_size != sz) { + pr_warning("map '%s': conflictling key size %u != %lld.\n", + map_name, map->def.key_size, sz); + return -EINVAL; + } + map->def.key_size = sz; + map->btf_key_type_id = t->type; + } else if (strcmp(name, "value_size") == 0) { + __u32 sz; + + if (!get_map_field_int(map_name, obj->btf, def, m, + def_data, &sz)) + return -EINVAL; + pr_debug("map '%s': found value_size = %u.\n", + map_name, sz); + if (map->def.value_size && map->def.value_size != sz) { + pr_warning("map '%s': conflictling value size %u != %u.\n", + map_name, map->def.value_size, sz); + return -EINVAL; + } + map->def.value_size = sz; + } else if (strcmp(name, "value") == 0) { + __s64 sz; + + t = btf__type_by_id(obj->btf, m->type); + if (!t) { + pr_warning("map '%s': value type [%d] not found.\n", + map_name, m->type); + return -EINVAL; + } + if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + pr_warning("map '%s': value spec is not PTR: %u.\n", + map_name, BTF_INFO_KIND(t->info)); + return -EINVAL; + } + sz = btf__resolve_size(obj->btf, t->type); + if (sz < 0) { + pr_warning("map '%s': can't determine value size for type [%u]: %lld.\n", + map_name, t->type, sz); + return sz; + } + pr_debug("map '%s': found value [%u], sz = %lld.\n", + map_name, t->type, sz); + if (map->def.value_size && map->def.value_size != sz) { + pr_warning("map '%s': conflictling value size %u != %lld.\n", + map_name, map->def.value_size, sz); + return -EINVAL; + } + map->def.value_size = sz; + map->btf_value_type_id = t->type; + } else { + if (strict) { + pr_warning("map '%s': unknown field '%s'.\n", + map_name, name); + return -ENOTSUP; + } + pr_debug("map '%s': ignoring unknown field '%s'.\n", + map_name, name); + } + } + + if (map->def.type == BPF_MAP_TYPE_UNSPEC) { + pr_warning("map '%s': map type isn't specified.\n", map_name); + return -EINVAL; + } + + return 0; +} + +static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict) +{ + const struct btf_type *sec = NULL; + int nr_types, i, vlen, err; + const struct btf_type *t; + const char *name; + Elf_Data *data; + Elf_Scn *scn; + + if (obj->efile.btf_maps_shndx < 0) + return 0; + + scn = elf_getscn(obj->efile.elf, obj->efile.btf_maps_shndx); + if (scn) + data = elf_getdata(scn, NULL); + if (!scn || !data) { + pr_warning("failed to get Elf_Data from map section %d (%s)\n", + obj->efile.maps_shndx, MAPS_ELF_SEC); + return -EINVAL; + } + + nr_types = btf__get_nr_types(obj->btf); + for (i = 1; i <= nr_types; i++) { + t = btf__type_by_id(obj->btf, i); + if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC) + continue; + name = btf__name_by_offset(obj->btf, t->name_off); + if (strcmp(name, MAPS_ELF_SEC) == 0) { + sec = t; + break; + } + } + + if (!sec) { + pr_warning("DATASEC '%s' not found.\n", MAPS_ELF_SEC); + return -ENOENT; + } + + vlen = BTF_INFO_VLEN(sec->info); + for (i = 0; i < vlen; i++) { + err = bpf_object__init_user_btf_map(obj, sec, i, + obj->efile.btf_maps_shndx, + data, strict); + if (err) + return err; + } + + return 0; +} + static int bpf_object__init_maps(struct bpf_object *obj, int flags) { bool strict = !(flags & MAPS_RELAX_COMPAT); @@ -1016,6 +1324,10 @@ static int bpf_object__init_maps(struct bpf_object *obj, int flags) if (err) return err; + err = bpf_object__init_user_btf_maps(obj, strict); + if (err) + return err; + err = bpf_object__init_global_data_maps(obj); if (err) return err; @@ -1113,10 +1425,16 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) } } +static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj) +{ + return obj->efile.btf_maps_shndx >= 0; +} + static int bpf_object__init_btf(struct bpf_object *obj, Elf_Data *btf_data, Elf_Data *btf_ext_data) { + bool btf_required = bpf_object__is_btf_mandatory(obj); int err = 0; if (btf_data) { @@ -1150,10 +1468,18 @@ static int bpf_object__init_btf(struct bpf_object *obj, } out: if (err || IS_ERR(obj->btf)) { + if (btf_required) + err = err ? : PTR_ERR(obj->btf); + else + err = 0; if (!IS_ERR_OR_NULL(obj->btf)) btf__free(obj->btf); obj->btf = NULL; } + if (btf_required && !obj->btf) { + pr_warning("BTF is required, but is missing or corrupted.\n"); + return err == 0 ? -ENOENT : err; + } return 0; } @@ -1173,6 +1499,8 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) BTF_ELF_SEC, err); btf__free(obj->btf); obj->btf = NULL; + if (bpf_object__is_btf_mandatory(obj)) + return err; } return 0; } @@ -1236,6 +1564,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) return err; } else if (strcmp(name, "maps") == 0) { obj->efile.maps_shndx = idx; + } else if (strcmp(name, MAPS_ELF_SEC) == 0) { + obj->efile.btf_maps_shndx = idx; } else if (strcmp(name, BTF_ELF_SEC) == 0) { btf_data = data; } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) { @@ -1355,7 +1685,8 @@ static bool bpf_object__shndx_is_data(const struct bpf_object *obj, static bool bpf_object__shndx_is_maps(const struct bpf_object *obj, int shndx) { - return shndx == obj->efile.maps_shndx; + return shndx == obj->efile.maps_shndx || + shndx == obj->efile.btf_maps_shndx; } static bool bpf_object__relo_in_known_section(const struct bpf_object *obj, @@ -1399,14 +1730,14 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, prog->nr_reloc = nrels; for (i = 0; i < nrels; i++) { - GElf_Sym sym; - GElf_Rel rel; - unsigned int insn_idx; - unsigned int shdr_idx; struct bpf_insn *insns = prog->insns; enum libbpf_map_type type; + unsigned int insn_idx; + unsigned int shdr_idx; const char *name; size_t map_idx; + GElf_Sym sym; + GElf_Rel rel; if (!gelf_getrel(data, i, &rel)) { pr_warning("relocation: failed to get %d reloc\n", i); @@ -1500,14 +1831,18 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, return 0; } -static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) +static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) { struct bpf_map_def *def = &map->def; __u32 key_type_id = 0, value_type_id = 0; int ret; + /* if it's BTF-defined map, we don't need to search for type IDs */ + if (map->sec_idx == obj->efile.btf_maps_shndx) + return 0; + if (!bpf_map__is_internal(map)) { - ret = btf__get_map_kv_tids(btf, map->name, def->key_size, + ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size, def->value_size, &key_type_id, &value_type_id); } else { @@ -1515,7 +1850,7 @@ static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) * LLVM annotates global data differently in BTF, that is, * only as '.data', '.bss' or '.rodata'. */ - ret = btf__find_by_name(btf, + ret = btf__find_by_name(obj->btf, libbpf_type_to_btf_name[map->libbpf_type]); } if (ret < 0) @@ -1805,7 +2140,7 @@ bpf_object__create_maps(struct bpf_object *obj) map->inner_map_fd >= 0) create_attr.inner_map_fd = map->inner_map_fd; - if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) { + if (obj->btf && !bpf_map_find_btf_info(obj, map)) { create_attr.btf_fd = btf__fd(obj->btf); create_attr.btf_key_type_id = map->btf_key_type_id; create_attr.btf_value_type_id = map->btf_value_type_id; -- cgit v1.2.3 From 9e3d709c47ca3d10df461635b350edef94f3cf11 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 17 Jun 2019 12:26:57 -0700 Subject: selftests/bpf: add test for BTF-defined maps Add file test for BTF-defined map definition. Signed-off-by: Andrii Nakryiko Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/progs/test_btf_newkv.c | 73 ++++++++++++++++++++++ tools/testing/selftests/bpf/test_btf.c | 10 +-- 2 files changed, 76 insertions(+), 7 deletions(-) create mode 100644 tools/testing/selftests/bpf/progs/test_btf_newkv.c (limited to 'tools') diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c new file mode 100644 index 000000000000..28c16bb583b6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ +#include +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +struct ipv_counts { + unsigned int v4; + unsigned int v6; +}; + +/* just to validate we can handle maps in multiple sections */ +struct bpf_map_def SEC("maps") btf_map_legacy = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(long long), + .max_entries = 4, +}; + +BPF_ANNOTATE_KV_PAIR(btf_map_legacy, int, struct ipv_counts); + +struct { + int *key; + struct ipv_counts *value; + unsigned int type; + unsigned int max_entries; +} btf_map SEC(".maps") = { + .type = BPF_MAP_TYPE_ARRAY, + .max_entries = 4, +}; + +struct dummy_tracepoint_args { + unsigned long long pad; + struct sock *sock; +}; + +__attribute__((noinline)) +static int test_long_fname_2(struct dummy_tracepoint_args *arg) +{ + struct ipv_counts *counts; + int key = 0; + + if (!arg->sock) + return 0; + + counts = bpf_map_lookup_elem(&btf_map, &key); + if (!counts) + return 0; + + counts->v6++; + + /* just verify we can reference both maps */ + counts = bpf_map_lookup_elem(&btf_map_legacy, &key); + if (!counts) + return 0; + + return 0; +} + +__attribute__((noinline)) +static int test_long_fname_1(struct dummy_tracepoint_args *arg) +{ + return test_long_fname_2(arg); +} + +SEC("dummy_tracepoint") +int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +{ + return test_long_fname_1(arg); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 289daf54dec4..8351cb5f4a20 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -4016,13 +4016,9 @@ struct btf_file_test { }; static struct btf_file_test file_tests[] = { -{ - .file = "test_btf_haskv.o", -}, -{ - .file = "test_btf_nokv.o", - .btf_kv_notfound = true, -}, + { .file = "test_btf_haskv.o", }, + { .file = "test_btf_newkv.o", }, + { .file = "test_btf_nokv.o", .btf_kv_notfound = true, }, }; static int do_test_file(unsigned int test_num) -- cgit v1.2.3 From f654407481e9bbba7039e939163ef60f9d5e43ba Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 17 Jun 2019 12:26:58 -0700 Subject: selftests/bpf: switch BPF_ANNOTATE_KV_PAIR tests to BTF-defined maps Switch tests that already rely on BTF to BTF-defined map definitions. Signed-off-by: Andrii Nakryiko Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/progs/netcnt_prog.c | 22 ++++---- tools/testing/selftests/bpf/progs/test_map_lock.c | 22 ++++---- .../selftests/bpf/progs/test_send_signal_kern.c | 22 ++++---- .../selftests/bpf/progs/test_sock_fields_kern.c | 60 +++++++++++++--------- tools/testing/selftests/bpf/progs/test_spin_lock.c | 33 ++++++------ 5 files changed, 87 insertions(+), 72 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/progs/netcnt_prog.c b/tools/testing/selftests/bpf/progs/netcnt_prog.c index 9f741e69cebe..a25c82a5b7c8 100644 --- a/tools/testing/selftests/bpf/progs/netcnt_prog.c +++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c @@ -10,24 +10,22 @@ #define REFRESH_TIME_NS 100000000 #define NS_PER_SEC 1000000000 -struct bpf_map_def SEC("maps") percpu_netcnt = { +struct { + __u32 type; + struct bpf_cgroup_storage_key *key; + struct percpu_net_cnt *value; +} percpu_netcnt SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, - .key_size = sizeof(struct bpf_cgroup_storage_key), - .value_size = sizeof(struct percpu_net_cnt), }; -BPF_ANNOTATE_KV_PAIR(percpu_netcnt, struct bpf_cgroup_storage_key, - struct percpu_net_cnt); - -struct bpf_map_def SEC("maps") netcnt = { +struct { + __u32 type; + struct bpf_cgroup_storage_key *key; + struct net_cnt *value; +} netcnt SEC(".maps") = { .type = BPF_MAP_TYPE_CGROUP_STORAGE, - .key_size = sizeof(struct bpf_cgroup_storage_key), - .value_size = sizeof(struct net_cnt), }; -BPF_ANNOTATE_KV_PAIR(netcnt, struct bpf_cgroup_storage_key, - struct net_cnt); - SEC("cgroup/skb") int bpf_nextcnt(struct __sk_buff *skb) { diff --git a/tools/testing/selftests/bpf/progs/test_map_lock.c b/tools/testing/selftests/bpf/progs/test_map_lock.c index af8cc68ed2f9..40d9c2853393 100644 --- a/tools/testing/selftests/bpf/progs/test_map_lock.c +++ b/tools/testing/selftests/bpf/progs/test_map_lock.c @@ -11,29 +11,31 @@ struct hmap_elem { int var[VAR_NUM]; }; -struct bpf_map_def SEC("maps") hash_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct hmap_elem *value; +} hash_map SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(int), - .value_size = sizeof(struct hmap_elem), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(hash_map, int, struct hmap_elem); - struct array_elem { struct bpf_spin_lock lock; int var[VAR_NUM]; }; -struct bpf_map_def SEC("maps") array_map = { +struct { + __u32 type; + __u32 max_entries; + int *key; + struct array_elem *value; +} array_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(struct array_elem), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(array_map, int, struct array_elem); - SEC("map_lock_demo") int bpf_map_lock_test(struct __sk_buff *skb) { diff --git a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c index 45a1a1a2c345..6ac68be5d68b 100644 --- a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c +++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c @@ -4,24 +4,26 @@ #include #include "bpf_helpers.h" -struct bpf_map_def SEC("maps") info_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 *value; +} info_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(info_map, __u32, __u64); - -struct bpf_map_def SEC("maps") status_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 *value; +} status_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(status_map, __u32, __u64); - SEC("send_signal_demo") int bpf_send_signal_test(void *ctx) { diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c index 1c39e4ccb7f1..c3d383d650cb 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c @@ -27,31 +27,43 @@ enum bpf_linum_array_idx { __NR_BPF_LINUM_ARRAY_IDX, }; -struct bpf_map_def SEC("maps") addr_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct sockaddr_in6 *value; +} addr_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct sockaddr_in6), .max_entries = __NR_BPF_ADDR_ARRAY_IDX, }; -struct bpf_map_def SEC("maps") sock_result_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct bpf_sock *value; +} sock_result_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct bpf_sock), .max_entries = __NR_BPF_RESULT_ARRAY_IDX, }; -struct bpf_map_def SEC("maps") tcp_sock_result_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct bpf_tcp_sock *value; +} tcp_sock_result_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct bpf_tcp_sock), .max_entries = __NR_BPF_RESULT_ARRAY_IDX, }; -struct bpf_map_def SEC("maps") linum_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} linum_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = __NR_BPF_LINUM_ARRAY_IDX, }; @@ -60,26 +72,26 @@ struct bpf_spinlock_cnt { __u32 cnt; }; -struct bpf_map_def SEC("maps") sk_pkt_out_cnt = { +struct { + __u32 type; + __u32 map_flags; + int *key; + struct bpf_spinlock_cnt *value; +} sk_pkt_out_cnt SEC(".maps") = { .type = BPF_MAP_TYPE_SK_STORAGE, - .key_size = sizeof(int), - .value_size = sizeof(struct bpf_spinlock_cnt), - .max_entries = 0, .map_flags = BPF_F_NO_PREALLOC, }; -BPF_ANNOTATE_KV_PAIR(sk_pkt_out_cnt, int, struct bpf_spinlock_cnt); - -struct bpf_map_def SEC("maps") sk_pkt_out_cnt10 = { +struct { + __u32 type; + __u32 map_flags; + int *key; + struct bpf_spinlock_cnt *value; +} sk_pkt_out_cnt10 SEC(".maps") = { .type = BPF_MAP_TYPE_SK_STORAGE, - .key_size = sizeof(int), - .value_size = sizeof(struct bpf_spinlock_cnt), - .max_entries = 0, .map_flags = BPF_F_NO_PREALLOC, }; -BPF_ANNOTATE_KV_PAIR(sk_pkt_out_cnt10, int, struct bpf_spinlock_cnt); - static bool is_loopback6(__u32 *a6) { return !a6[0] && !a6[1] && !a6[2] && a6[3] == bpf_htonl(1); diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c index 40f904312090..0a77ae36d981 100644 --- a/tools/testing/selftests/bpf/progs/test_spin_lock.c +++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c @@ -10,30 +10,29 @@ struct hmap_elem { int test_padding; }; -struct bpf_map_def SEC("maps") hmap = { +struct { + __u32 type; + __u32 max_entries; + int *key; + struct hmap_elem *value; +} hmap SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(int), - .value_size = sizeof(struct hmap_elem), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(hmap, int, struct hmap_elem); - - struct cls_elem { struct bpf_spin_lock lock; volatile int cnt; }; -struct bpf_map_def SEC("maps") cls_map = { +struct { + __u32 type; + struct bpf_cgroup_storage_key *key; + struct cls_elem *value; +} cls_map SEC(".maps") = { .type = BPF_MAP_TYPE_CGROUP_STORAGE, - .key_size = sizeof(struct bpf_cgroup_storage_key), - .value_size = sizeof(struct cls_elem), }; -BPF_ANNOTATE_KV_PAIR(cls_map, struct bpf_cgroup_storage_key, - struct cls_elem); - struct bpf_vqueue { struct bpf_spin_lock lock; /* 4 byte hole */ @@ -42,14 +41,16 @@ struct bpf_vqueue { unsigned int rate; }; -struct bpf_map_def SEC("maps") vqueue = { +struct { + __u32 type; + __u32 max_entries; + int *key; + struct bpf_vqueue *value; +} vqueue SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(struct bpf_vqueue), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(vqueue, int, struct bpf_vqueue); #define CREDIT_PER_NS(delta, rate) (((delta) * rate) >> 20) SEC("spin_lock_demo") -- cgit v1.2.3 From df0b7792598291128fcca66b039fd027be25c10a Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 17 Jun 2019 12:26:59 -0700 Subject: selftests/bpf: convert tests w/ custom values to BTF-defined maps Convert a bulk of selftests that have maps with custom (not integer) key and/or value. Signed-off-by: Andrii Nakryiko Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/progs/bpf_flow.c | 18 +++++-- .../selftests/bpf/progs/socket_cookie_prog.c | 11 ++-- .../selftests/bpf/progs/test_get_stack_rawtp.c | 27 +++++++--- .../testing/selftests/bpf/progs/test_global_data.c | 27 ++++++---- tools/testing/selftests/bpf/progs/test_l4lb.c | 45 ++++++++++------ .../selftests/bpf/progs/test_l4lb_noinline.c | 45 ++++++++++------ .../bpf/progs/test_select_reuseport_kern.c | 45 +++++++++++----- .../selftests/bpf/progs/test_stacktrace_build_id.c | 44 +++++++++++----- .../selftests/bpf/progs/test_stacktrace_map.c | 40 ++++++++++----- .../testing/selftests/bpf/progs/test_tcp_estats.c | 9 ++-- .../testing/selftests/bpf/progs/test_tcpbpf_kern.c | 18 ++++--- .../selftests/bpf/progs/test_tcpnotify_kern.c | 18 +++++-- tools/testing/selftests/bpf/progs/test_xdp.c | 18 ++++--- .../selftests/bpf/progs/test_xdp_noinline.c | 60 +++++++++++++--------- 14 files changed, 285 insertions(+), 140 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 81ad9a0b29d0..849f42e548b5 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -57,17 +57,25 @@ struct frag_hdr { __be32 identification; }; -struct bpf_map_def SEC("maps") jmp_table = { +struct { + __u32 type; + __u32 max_entries; + __u32 key_size; + __u32 value_size; +} jmp_table SEC(".maps") = { .type = BPF_MAP_TYPE_PROG_ARRAY, + .max_entries = 8, .key_size = sizeof(__u32), .value_size = sizeof(__u32), - .max_entries = 8 }; -struct bpf_map_def SEC("maps") last_dissection = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct bpf_flow_keys *value; +} last_dissection SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct bpf_flow_keys), .max_entries = 1, }; diff --git a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c index 0db15c3210ad..6aabb681fb9a 100644 --- a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c +++ b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c @@ -12,15 +12,16 @@ struct socket_cookie { __u32 cookie_value; }; -struct bpf_map_def SEC("maps") socket_cookies = { +struct { + __u32 type; + __u32 map_flags; + int *key; + struct socket_cookie *value; +} socket_cookies SEC(".maps") = { .type = BPF_MAP_TYPE_SK_STORAGE, - .key_size = sizeof(int), - .value_size = sizeof(struct socket_cookie), .map_flags = BPF_F_NO_PREALLOC, }; -BPF_ANNOTATE_KV_PAIR(socket_cookies, int, struct socket_cookie); - SEC("cgroup/connect6") int set_cookie(struct bpf_sock_addr *ctx) { diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c index f6d9f238e00a..aaa6ec250e15 100644 --- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c @@ -15,17 +15,25 @@ struct stack_trace_t { struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP]; }; -struct bpf_map_def SEC("maps") perfmap = { +struct { + __u32 type; + __u32 max_entries; + __u32 key_size; + __u32 value_size; +} perfmap SEC(".maps") = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .max_entries = 2, .key_size = sizeof(int), .value_size = sizeof(__u32), - .max_entries = 2, }; -struct bpf_map_def SEC("maps") stackdata_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct stack_trace_t *value; +} stackdata_map SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct stack_trace_t), .max_entries = 1, }; @@ -47,10 +55,13 @@ struct bpf_map_def SEC("maps") stackdata_map = { * issue and avoid complicated C programming massaging. * This is an acceptable workaround since there is one entry here. */ -struct bpf_map_def SEC("maps") rawdata_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 (*value)[2 * MAX_STACK_RAWTP]; +} rawdata_map SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = MAX_STACK_RAWTP * sizeof(__u64) * 2, .max_entries = 1, }; diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c index 5ab14e941980..866cc7ddbe43 100644 --- a/tools/testing/selftests/bpf/progs/test_global_data.c +++ b/tools/testing/selftests/bpf/progs/test_global_data.c @@ -7,17 +7,23 @@ #include "bpf_helpers.h" -struct bpf_map_def SEC("maps") result_number = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 *value; +} result_number SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), .max_entries = 11, }; -struct bpf_map_def SEC("maps") result_string = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + const char (*value)[32]; +} result_string SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = 32, .max_entries = 5, }; @@ -27,10 +33,13 @@ struct foo { __u64 c; }; -struct bpf_map_def SEC("maps") result_struct = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct foo *value; +} result_struct SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct foo), .max_entries = 5, }; diff --git a/tools/testing/selftests/bpf/progs/test_l4lb.c b/tools/testing/selftests/bpf/progs/test_l4lb.c index 1e10c9590991..848cbb90f581 100644 --- a/tools/testing/selftests/bpf/progs/test_l4lb.c +++ b/tools/testing/selftests/bpf/progs/test_l4lb.c @@ -169,38 +169,53 @@ struct eth_hdr { unsigned short eth_proto; }; -struct bpf_map_def SEC("maps") vip_map = { +struct { + __u32 type; + __u32 max_entries; + struct vip *key; + struct vip_meta *value; +} vip_map SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct vip), - .value_size = sizeof(struct vip_meta), .max_entries = MAX_VIPS, }; -struct bpf_map_def SEC("maps") ch_rings = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} ch_rings SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = CH_RINGS_SIZE, }; -struct bpf_map_def SEC("maps") reals = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct real_definition *value; +} reals SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct real_definition), .max_entries = MAX_REALS, }; -struct bpf_map_def SEC("maps") stats = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct vip_stats *value; +} stats SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct vip_stats), .max_entries = MAX_VIPS, }; -struct bpf_map_def SEC("maps") ctl_array = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct ctl_value *value; +} ctl_array SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct ctl_value), .max_entries = CTL_MAP_SIZE, }; diff --git a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c index ba44a14e6dc4..c63ecf3ca573 100644 --- a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c @@ -165,38 +165,53 @@ struct eth_hdr { unsigned short eth_proto; }; -struct bpf_map_def SEC("maps") vip_map = { +struct { + __u32 type; + __u32 max_entries; + struct vip *key; + struct vip_meta *value; +} vip_map SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct vip), - .value_size = sizeof(struct vip_meta), .max_entries = MAX_VIPS, }; -struct bpf_map_def SEC("maps") ch_rings = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} ch_rings SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = CH_RINGS_SIZE, }; -struct bpf_map_def SEC("maps") reals = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct real_definition *value; +} reals SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct real_definition), .max_entries = MAX_REALS, }; -struct bpf_map_def SEC("maps") stats = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct vip_stats *value; +} stats SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct vip_stats), .max_entries = MAX_VIPS, }; -struct bpf_map_def SEC("maps") ctl_array = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct ctl_value *value; +} ctl_array SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct ctl_value), .max_entries = CTL_MAP_SIZE, }; diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c index 5b54ec637ada..435a9527733e 100644 --- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c @@ -21,38 +21,55 @@ int _version SEC("version") = 1; #define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) #endif -struct bpf_map_def SEC("maps") outer_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 key_size; + __u32 value_size; +} outer_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY_OF_MAPS, + .max_entries = 1, .key_size = sizeof(__u32), .value_size = sizeof(__u32), - .max_entries = 1, }; -struct bpf_map_def SEC("maps") result_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} result_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = NR_RESULTS, }; -struct bpf_map_def SEC("maps") tmp_index_ovr_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + int *value; +} tmp_index_ovr_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(int), .max_entries = 1, }; -struct bpf_map_def SEC("maps") linum_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} linum_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 1, }; -struct bpf_map_def SEC("maps") data_check_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct data_check *value; +} data_check_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct data_check), .max_entries = 1, }; diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c index d86c281e957f..fcf2280bb60c 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c @@ -8,34 +8,50 @@ #define PERF_MAX_STACK_DEPTH 127 #endif -struct bpf_map_def SEC("maps") control_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} control_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 1, }; -struct bpf_map_def SEC("maps") stackid_hmap = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} stackid_hmap SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 16384, }; -struct bpf_map_def SEC("maps") stackmap = { +typedef struct bpf_stack_build_id stack_trace_t[PERF_MAX_STACK_DEPTH]; + +struct { + __u32 type; + __u32 max_entries; + __u32 map_flags; + __u32 key_size; + __u32 value_size; +} stackmap SEC(".maps") = { .type = BPF_MAP_TYPE_STACK_TRACE, - .key_size = sizeof(__u32), - .value_size = sizeof(struct bpf_stack_build_id) - * PERF_MAX_STACK_DEPTH, .max_entries = 128, .map_flags = BPF_F_STACK_BUILD_ID, + .key_size = sizeof(__u32), + .value_size = sizeof(stack_trace_t), }; -struct bpf_map_def SEC("maps") stack_amap = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + /* there seems to be a bug in kernel not handling typedef properly */ + struct bpf_stack_build_id (*value)[PERF_MAX_STACK_DEPTH]; +} stack_amap SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct bpf_stack_build_id) - * PERF_MAX_STACK_DEPTH, .max_entries = 128, }; diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c index af111af7ca1a..7ad09adbf648 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c @@ -8,31 +8,47 @@ #define PERF_MAX_STACK_DEPTH 127 #endif -struct bpf_map_def SEC("maps") control_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} control_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 1, }; -struct bpf_map_def SEC("maps") stackid_hmap = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} stackid_hmap SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 16384, }; -struct bpf_map_def SEC("maps") stackmap = { +typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; + +struct { + __u32 type; + __u32 max_entries; + __u32 key_size; + __u32 value_size; +} stackmap SEC(".maps") = { .type = BPF_MAP_TYPE_STACK_TRACE, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH, .max_entries = 16384, + .key_size = sizeof(__u32), + .value_size = sizeof(stack_trace_t), }; -struct bpf_map_def SEC("maps") stack_amap = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 (*value)[PERF_MAX_STACK_DEPTH]; +} stack_amap SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH, .max_entries = 16384, }; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_estats.c b/tools/testing/selftests/bpf/progs/test_tcp_estats.c index bee3bbecc0c4..df98f7e32832 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_estats.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_estats.c @@ -148,10 +148,13 @@ struct tcp_estats_basic_event { struct tcp_estats_conn_id conn_id; }; -struct bpf_map_def SEC("maps") ev_record_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct tcp_estats_basic_event *value; +} ev_record_map SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u32), - .value_size = sizeof(struct tcp_estats_basic_event), .max_entries = 1024, }; diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index c7c3240e0dd4..38e10c9fd996 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -14,17 +14,23 @@ #include "bpf_endian.h" #include "test_tcpbpf.h" -struct bpf_map_def SEC("maps") global_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct tcpbpf_globals *value; +} global_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct tcpbpf_globals), .max_entries = 4, }; -struct bpf_map_def SEC("maps") sockopt_results = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + int *value; +} sockopt_results SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(int), .max_entries = 2, }; diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c index ec6db6e64c41..d073d37d4e27 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c @@ -14,18 +14,26 @@ #include "bpf_endian.h" #include "test_tcpnotify.h" -struct bpf_map_def SEC("maps") global_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct tcpnotify_globals *value; +} global_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct tcpnotify_globals), .max_entries = 4, }; -struct bpf_map_def SEC("maps") perf_event_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 key_size; + __u32 value_size; +} perf_event_map SEC(".maps") = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .max_entries = 2, .key_size = sizeof(int), .value_size = sizeof(__u32), - .max_entries = 2, }; int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c index 5e7df8bb5b5d..ec3d2c1c8cf9 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp.c +++ b/tools/testing/selftests/bpf/progs/test_xdp.c @@ -22,17 +22,23 @@ int _version SEC("version") = 1; -struct bpf_map_def SEC("maps") rxcnt = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 *value; +} rxcnt SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), .max_entries = 256, }; -struct bpf_map_def SEC("maps") vip2tnl = { +struct { + __u32 type; + __u32 max_entries; + struct vip *key; + struct iptnl_info *value; +} vip2tnl SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct vip), - .value_size = sizeof(struct iptnl_info), .max_entries = MAX_IPTNL_ENTRIES, }; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c index 4fe6aaad22a4..d2eddb5553d1 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c @@ -163,52 +163,66 @@ struct lb_stats { __u64 v1; }; -struct bpf_map_def __attribute__ ((section("maps"), used)) vip_map = { +struct { + __u32 type; + __u32 max_entries; + struct vip_definition *key; + struct vip_meta *value; +} vip_map SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct vip_definition), - .value_size = sizeof(struct vip_meta), .max_entries = 512, - .map_flags = 0, }; -struct bpf_map_def __attribute__ ((section("maps"), used)) lru_cache = { +struct { + __u32 type; + __u32 max_entries; + __u32 map_flags; + struct flow_key *key; + struct real_pos_lru *value; +} lru_cache SEC(".maps") = { .type = BPF_MAP_TYPE_LRU_HASH, - .key_size = sizeof(struct flow_key), - .value_size = sizeof(struct real_pos_lru), .max_entries = 300, .map_flags = 1U << 1, }; -struct bpf_map_def __attribute__ ((section("maps"), used)) ch_rings = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} ch_rings SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 12 * 655, - .map_flags = 0, }; -struct bpf_map_def __attribute__ ((section("maps"), used)) reals = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct real_definition *value; +} reals SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct real_definition), .max_entries = 40, - .map_flags = 0, }; -struct bpf_map_def __attribute__ ((section("maps"), used)) stats = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct lb_stats *value; +} stats SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct lb_stats), .max_entries = 515, - .map_flags = 0, }; -struct bpf_map_def __attribute__ ((section("maps"), used)) ctl_array = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct ctl_value *value; +} ctl_array SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct ctl_value), .max_entries = 16, - .map_flags = 0, }; struct eth_hdr { -- cgit v1.2.3 From a324aae32fa9bfdd03e89078e20ebcbd7737fda5 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 17 Jun 2019 15:48:58 -0700 Subject: libbpf: constify getter APIs Add const qualifiers to bpf_object/bpf_program/bpf_map arguments for getter APIs. There is no need for them to not be const pointers. Verified that make -C tools/lib/bpf make -C tools/testing/selftests/bpf make -C tools/perf all build without warnings. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann --- tools/lib/bpf/libbpf.c | 80 ++++++++++++++++++++++++++------------------------ tools/lib/bpf/libbpf.h | 62 +++++++++++++++++++------------------- 2 files changed, 72 insertions(+), 70 deletions(-) (limited to 'tools') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 585e3a2f1eb4..8ce3beba8551 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1663,7 +1663,8 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx) } struct bpf_program * -bpf_object__find_program_by_title(struct bpf_object *obj, const char *title) +bpf_object__find_program_by_title(const struct bpf_object *obj, + const char *title) { struct bpf_program *pos; @@ -2589,8 +2590,8 @@ out: return err; } -static bool bpf_program__is_function_storage(struct bpf_program *prog, - struct bpf_object *obj) +static bool bpf_program__is_function_storage(const struct bpf_program *prog, + const struct bpf_object *obj) { return prog->idx == obj->efile.text_shndx && obj->has_pseudo_calls; } @@ -3296,17 +3297,17 @@ bpf_object__next(struct bpf_object *prev) return next; } -const char *bpf_object__name(struct bpf_object *obj) +const char *bpf_object__name(const struct bpf_object *obj) { return obj ? obj->path : ERR_PTR(-EINVAL); } -unsigned int bpf_object__kversion(struct bpf_object *obj) +unsigned int bpf_object__kversion(const struct bpf_object *obj) { return obj ? obj->kern_version : 0; } -struct btf *bpf_object__btf(struct bpf_object *obj) +struct btf *bpf_object__btf(const struct bpf_object *obj) { return obj ? obj->btf : NULL; } @@ -3327,13 +3328,14 @@ int bpf_object__set_priv(struct bpf_object *obj, void *priv, return 0; } -void *bpf_object__priv(struct bpf_object *obj) +void *bpf_object__priv(const struct bpf_object *obj) { return obj ? obj->priv : ERR_PTR(-EINVAL); } static struct bpf_program * -__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward) +__bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj, + bool forward) { size_t nr_programs = obj->nr_programs; ssize_t idx; @@ -3358,7 +3360,7 @@ __bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward) } struct bpf_program * -bpf_program__next(struct bpf_program *prev, struct bpf_object *obj) +bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj) { struct bpf_program *prog = prev; @@ -3370,7 +3372,7 @@ bpf_program__next(struct bpf_program *prev, struct bpf_object *obj) } struct bpf_program * -bpf_program__prev(struct bpf_program *next, struct bpf_object *obj) +bpf_program__prev(struct bpf_program *next, const struct bpf_object *obj) { struct bpf_program *prog = next; @@ -3392,7 +3394,7 @@ int bpf_program__set_priv(struct bpf_program *prog, void *priv, return 0; } -void *bpf_program__priv(struct bpf_program *prog) +void *bpf_program__priv(const struct bpf_program *prog) { return prog ? prog->priv : ERR_PTR(-EINVAL); } @@ -3402,7 +3404,7 @@ void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex) prog->prog_ifindex = ifindex; } -const char *bpf_program__title(struct bpf_program *prog, bool needs_copy) +const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy) { const char *title; @@ -3418,7 +3420,7 @@ const char *bpf_program__title(struct bpf_program *prog, bool needs_copy) return title; } -int bpf_program__fd(struct bpf_program *prog) +int bpf_program__fd(const struct bpf_program *prog) { return bpf_program__nth_fd(prog, 0); } @@ -3451,7 +3453,7 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, return 0; } -int bpf_program__nth_fd(struct bpf_program *prog, int n) +int bpf_program__nth_fd(const struct bpf_program *prog, int n) { int fd; @@ -3479,25 +3481,25 @@ void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) prog->type = type; } -static bool bpf_program__is_type(struct bpf_program *prog, +static bool bpf_program__is_type(const struct bpf_program *prog, enum bpf_prog_type type) { return prog ? (prog->type == type) : false; } -#define BPF_PROG_TYPE_FNS(NAME, TYPE) \ -int bpf_program__set_##NAME(struct bpf_program *prog) \ -{ \ - if (!prog) \ - return -EINVAL; \ - bpf_program__set_type(prog, TYPE); \ - return 0; \ -} \ - \ -bool bpf_program__is_##NAME(struct bpf_program *prog) \ -{ \ - return bpf_program__is_type(prog, TYPE); \ -} \ +#define BPF_PROG_TYPE_FNS(NAME, TYPE) \ +int bpf_program__set_##NAME(struct bpf_program *prog) \ +{ \ + if (!prog) \ + return -EINVAL; \ + bpf_program__set_type(prog, TYPE); \ + return 0; \ +} \ + \ +bool bpf_program__is_##NAME(const struct bpf_program *prog) \ +{ \ + return bpf_program__is_type(prog, TYPE); \ +} \ BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER); BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE); @@ -3692,17 +3694,17 @@ bpf_program__identify_section(struct bpf_program *prog, expected_attach_type); } -int bpf_map__fd(struct bpf_map *map) +int bpf_map__fd(const struct bpf_map *map) { return map ? map->fd : -EINVAL; } -const struct bpf_map_def *bpf_map__def(struct bpf_map *map) +const struct bpf_map_def *bpf_map__def(const struct bpf_map *map) { return map ? &map->def : ERR_PTR(-EINVAL); } -const char *bpf_map__name(struct bpf_map *map) +const char *bpf_map__name(const struct bpf_map *map) { return map ? map->name : NULL; } @@ -3733,17 +3735,17 @@ int bpf_map__set_priv(struct bpf_map *map, void *priv, return 0; } -void *bpf_map__priv(struct bpf_map *map) +void *bpf_map__priv(const struct bpf_map *map) { return map ? map->priv : ERR_PTR(-EINVAL); } -bool bpf_map__is_offload_neutral(struct bpf_map *map) +bool bpf_map__is_offload_neutral(const struct bpf_map *map) { return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; } -bool bpf_map__is_internal(struct bpf_map *map) +bool bpf_map__is_internal(const struct bpf_map *map) { return map->libbpf_type != LIBBPF_MAP_UNSPEC; } @@ -3768,7 +3770,7 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd) } static struct bpf_map * -__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i) +__bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i) { ssize_t idx; struct bpf_map *s, *e; @@ -3792,7 +3794,7 @@ __bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i) } struct bpf_map * -bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) +bpf_map__next(const struct bpf_map *prev, const struct bpf_object *obj) { if (prev == NULL) return obj->maps; @@ -3801,7 +3803,7 @@ bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) } struct bpf_map * -bpf_map__prev(struct bpf_map *next, struct bpf_object *obj) +bpf_map__prev(const struct bpf_map *next, const struct bpf_object *obj) { if (next == NULL) { if (!obj->nr_maps) @@ -3813,7 +3815,7 @@ bpf_map__prev(struct bpf_map *next, struct bpf_object *obj) } struct bpf_map * -bpf_object__find_map_by_name(struct bpf_object *obj, const char *name) +bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name) { struct bpf_map *pos; @@ -3825,7 +3827,7 @@ bpf_object__find_map_by_name(struct bpf_object *obj, const char *name) } int -bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name) +bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name) { return bpf_map__fd(bpf_object__find_map_by_name(obj, name)); } diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 2e594a0fa961..d639f47e3110 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -98,15 +98,16 @@ struct bpf_object_load_attr { LIBBPF_API int bpf_object__load(struct bpf_object *obj); LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr); LIBBPF_API int bpf_object__unload(struct bpf_object *obj); -LIBBPF_API const char *bpf_object__name(struct bpf_object *obj); -LIBBPF_API unsigned int bpf_object__kversion(struct bpf_object *obj); +LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj); +LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj); struct btf; -LIBBPF_API struct btf *bpf_object__btf(struct bpf_object *obj); +LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj); LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); LIBBPF_API struct bpf_program * -bpf_object__find_program_by_title(struct bpf_object *obj, const char *title); +bpf_object__find_program_by_title(const struct bpf_object *obj, + const char *title); LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev); #define bpf_object__for_each_safe(pos, tmp) \ @@ -118,7 +119,7 @@ LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev); typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *); LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv, bpf_object_clear_priv_t clear_priv); -LIBBPF_API void *bpf_object__priv(struct bpf_object *prog); +LIBBPF_API void *bpf_object__priv(const struct bpf_object *prog); LIBBPF_API int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, @@ -129,7 +130,7 @@ LIBBPF_API int libbpf_attach_type_by_name(const char *name, /* Accessors of bpf_program */ struct bpf_program; LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog, - struct bpf_object *obj); + const struct bpf_object *obj); #define bpf_object__for_each_program(pos, obj) \ for ((pos) = bpf_program__next(NULL, (obj)); \ @@ -137,24 +138,23 @@ LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog, (pos) = bpf_program__next((pos), (obj))) LIBBPF_API struct bpf_program *bpf_program__prev(struct bpf_program *prog, - struct bpf_object *obj); + const struct bpf_object *obj); -typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, - void *); +typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *); LIBBPF_API int bpf_program__set_priv(struct bpf_program *prog, void *priv, bpf_program_clear_priv_t clear_priv); -LIBBPF_API void *bpf_program__priv(struct bpf_program *prog); +LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex); -LIBBPF_API const char *bpf_program__title(struct bpf_program *prog, +LIBBPF_API const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy); LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_version); -LIBBPF_API int bpf_program__fd(struct bpf_program *prog); +LIBBPF_API int bpf_program__fd(const struct bpf_program *prog); LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog, const char *path, int instance); @@ -227,7 +227,7 @@ typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n, LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance, bpf_program_prep_t prep); -LIBBPF_API int bpf_program__nth_fd(struct bpf_program *prog, int n); +LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n); /* * Adjust type of BPF program. Default is kprobe. @@ -246,14 +246,14 @@ LIBBPF_API void bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type); -LIBBPF_API bool bpf_program__is_socket_filter(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_tracepoint(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_raw_tracepoint(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_kprobe(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_sched_cls(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_sched_act(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_xdp(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_perf_event(struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog); /* * No need for __attribute__((packed)), all members of 'bpf_map_def' @@ -275,10 +275,10 @@ struct bpf_map_def { */ struct bpf_map; LIBBPF_API struct bpf_map * -bpf_object__find_map_by_name(struct bpf_object *obj, const char *name); +bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name); LIBBPF_API int -bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name); +bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name); /* * Get bpf_map through the offset of corresponding struct bpf_map_def @@ -288,7 +288,7 @@ LIBBPF_API struct bpf_map * bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset); LIBBPF_API struct bpf_map * -bpf_map__next(struct bpf_map *map, struct bpf_object *obj); +bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj); #define bpf_object__for_each_map(pos, obj) \ for ((pos) = bpf_map__next(NULL, (obj)); \ (pos) != NULL; \ @@ -296,22 +296,22 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj); #define bpf_map__for_each bpf_object__for_each_map LIBBPF_API struct bpf_map * -bpf_map__prev(struct bpf_map *map, struct bpf_object *obj); +bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj); -LIBBPF_API int bpf_map__fd(struct bpf_map *map); -LIBBPF_API const struct bpf_map_def *bpf_map__def(struct bpf_map *map); -LIBBPF_API const char *bpf_map__name(struct bpf_map *map); +LIBBPF_API int bpf_map__fd(const struct bpf_map *map); +LIBBPF_API const struct bpf_map_def *bpf_map__def(const struct bpf_map *map); +LIBBPF_API const char *bpf_map__name(const struct bpf_map *map); LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map); LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, bpf_map_clear_priv_t clear_priv); -LIBBPF_API void *bpf_map__priv(struct bpf_map *map); +LIBBPF_API void *bpf_map__priv(const struct bpf_map *map); LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); -LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map); -LIBBPF_API bool bpf_map__is_internal(struct bpf_map *map); +LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); +LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path); LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path); -- cgit v1.2.3 From fc559a70d57c6ee5443f7a750858503e94cdc941 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sat, 15 Jun 2019 12:12:18 -0700 Subject: selftests/bpf: fix tests due to const spill/fill fix tests that incorrectly assumed that the verifier cannot track constants through stack. Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann --- .../selftests/bpf/verifier/direct_packet_access.c | 3 ++- .../selftests/bpf/verifier/helper_access_var_len.c | 28 ++++++++++++---------- 2 files changed, 17 insertions(+), 14 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/verifier/direct_packet_access.c b/tools/testing/selftests/bpf/verifier/direct_packet_access.c index d5c596fdc4b9..2c5fbe7bcd27 100644 --- a/tools/testing/selftests/bpf/verifier/direct_packet_access.c +++ b/tools/testing/selftests/bpf/verifier/direct_packet_access.c @@ -511,7 +511,8 @@ offsetof(struct __sk_buff, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct __sk_buff, data_end)), - BPF_MOV64_IMM(BPF_REG_0, 0xffffffff), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, mark)), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffff), diff --git a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c index 1f39d845c64f..67ab12410050 100644 --- a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c +++ b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c @@ -29,9 +29,9 @@ { "helper access to variable memory: stack, bitwise AND, zero included", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_MOV64_IMM(BPF_REG_2, 16), BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64), @@ -46,9 +46,9 @@ { "helper access to variable memory: stack, bitwise AND + JMP, wrong max", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_MOV64_IMM(BPF_REG_2, 16), BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 65), @@ -122,9 +122,9 @@ { "helper access to variable memory: stack, JMP, bounds + offset", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_MOV64_IMM(BPF_REG_2, 16), BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 5), @@ -143,9 +143,9 @@ { "helper access to variable memory: stack, JMP, wrong max", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_MOV64_IMM(BPF_REG_2, 16), BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 65, 4), @@ -163,9 +163,9 @@ { "helper access to variable memory: stack, JMP, no max check", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_MOV64_IMM(BPF_REG_2, 16), BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), BPF_MOV64_IMM(BPF_REG_4, 0), @@ -183,9 +183,9 @@ { "helper access to variable memory: stack, JMP, no min check", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_MOV64_IMM(BPF_REG_2, 16), BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 3), @@ -201,9 +201,9 @@ { "helper access to variable memory: stack, JMP (signed), no min check", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_MOV64_IMM(BPF_REG_2, 16), BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, 64, 3), @@ -244,6 +244,7 @@ { "helper access to variable memory: map, JMP, wrong max", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), @@ -251,7 +252,7 @@ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10), BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), - BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) + 1, 4), @@ -262,7 +263,7 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_48b = { 3 }, + .fixup_map_hash_48b = { 4 }, .errstr = "invalid access to map value, value_size=48 off=0 size=49", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, @@ -296,6 +297,7 @@ { "helper access to variable memory: map adjusted, JMP, wrong max", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), @@ -304,7 +306,7 @@ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 20), - BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) - 19, 4), @@ -315,7 +317,7 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_48b = { 3 }, + .fixup_map_hash_48b = { 4 }, .errstr = "R1 min value is outside of the array range", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, @@ -337,8 +339,8 @@ { "helper access to variable memory: size > 0 not allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)", .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), BPF_MOV64_IMM(BPF_REG_1, 0), - BPF_MOV64_IMM(BPF_REG_2, 1), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64), @@ -562,6 +564,7 @@ { "helper access to variable memory: 8 bytes leak", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -572,7 +575,6 @@ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), - BPF_MOV64_IMM(BPF_REG_2, 1), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 63), -- cgit v1.2.3 From aeee380ccfc59c05a4c6e8e762fd645c6bdc773a Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sat, 15 Jun 2019 12:12:22 -0700 Subject: selftests/bpf: fix tests Fix tests that assumed no loops. Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/test_verifier.c | 11 ++++------- tools/testing/selftests/bpf/verifier/calls.c | 22 +++++++++++++--------- tools/testing/selftests/bpf/verifier/cfg.c | 11 +++++++---- 3 files changed, 24 insertions(+), 20 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index cd0248c54e25..93e1d87a343a 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -237,10 +237,10 @@ static void bpf_fill_scale1(struct bpf_test *self) insn[i++] = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, -8 * (k % 64 + 1)); } - /* every jump adds 1 step to insn_processed, so to stay exactly - * within 1m limit add MAX_TEST_INSNS - MAX_JMP_SEQ - 1 MOVs and 1 EXIT + /* is_state_visited() doesn't allocate state for pruning for every jump. + * Hence multiply jmps by 4 to accommodate that heuristic */ - while (i < MAX_TEST_INSNS - MAX_JMP_SEQ - 1) + while (i < MAX_TEST_INSNS - MAX_JMP_SEQ * 4) insn[i++] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 42); insn[i] = BPF_EXIT_INSN(); self->prog_len = i + 1; @@ -269,10 +269,7 @@ static void bpf_fill_scale2(struct bpf_test *self) insn[i++] = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, -8 * (k % (64 - 4 * FUNC_NEST) + 1)); } - /* every jump adds 1 step to insn_processed, so to stay exactly - * within 1m limit add MAX_TEST_INSNS - MAX_JMP_SEQ - 1 MOVs and 1 EXIT - */ - while (i < MAX_TEST_INSNS - MAX_JMP_SEQ - 1) + while (i < MAX_TEST_INSNS - MAX_JMP_SEQ * 4) insn[i++] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 42); insn[i] = BPF_EXIT_INSN(); self->prog_len = i + 1; diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 9093a8f64dc6..2d752c4f8d9d 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -215,9 +215,11 @@ BPF_MOV64_IMM(BPF_REG_0, 3), BPF_JMP_IMM(BPF_JA, 0, 0, -6), }, - .prog_type = BPF_PROG_TYPE_TRACEPOINT, - .errstr = "back-edge from insn", - .result = REJECT, + .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, + .errstr_unpriv = "back-edge from insn", + .result_unpriv = REJECT, + .result = ACCEPT, + .retval = 1, }, { "calls: conditional call 4", @@ -250,22 +252,24 @@ BPF_MOV64_IMM(BPF_REG_0, 3), BPF_EXIT_INSN(), }, - .prog_type = BPF_PROG_TYPE_TRACEPOINT, - .errstr = "back-edge from insn", - .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 1, }, { "calls: conditional call 6", .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -3), BPF_EXIT_INSN(), BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, mark)), BPF_EXIT_INSN(), }, - .prog_type = BPF_PROG_TYPE_TRACEPOINT, - .errstr = "back-edge from insn", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "infinite loop detected", .result = REJECT, }, { diff --git a/tools/testing/selftests/bpf/verifier/cfg.c b/tools/testing/selftests/bpf/verifier/cfg.c index 349c0862fb4c..4eb76ed739ce 100644 --- a/tools/testing/selftests/bpf/verifier/cfg.c +++ b/tools/testing/selftests/bpf/verifier/cfg.c @@ -41,7 +41,8 @@ BPF_JMP_IMM(BPF_JA, 0, 0, -1), BPF_EXIT_INSN(), }, - .errstr = "back-edge", + .errstr = "unreachable insn 1", + .errstr_unpriv = "back-edge", .result = REJECT, }, { @@ -53,18 +54,20 @@ BPF_JMP_IMM(BPF_JA, 0, 0, -4), BPF_EXIT_INSN(), }, - .errstr = "back-edge", + .errstr = "unreachable insn 4", + .errstr_unpriv = "back-edge", .result = REJECT, }, { "conditional loop", .insns = { - BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, -3), BPF_EXIT_INSN(), }, - .errstr = "back-edge", + .errstr = "infinite loop detected", + .errstr_unpriv = "back-edge", .result = REJECT, }, -- cgit v1.2.3 From 0d3679e99ae4b7868da22e3b8540fd597df501f5 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sat, 15 Jun 2019 12:12:23 -0700 Subject: selftests/bpf: add basic verifier tests for loops This set of tests is a rewrite of Edward's earlier tests: https://patchwork.ozlabs.org/patch/877221/ Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/verifier/loops1.c | 161 ++++++++++++++++++++++++++ 1 file changed, 161 insertions(+) create mode 100644 tools/testing/selftests/bpf/verifier/loops1.c (limited to 'tools') diff --git a/tools/testing/selftests/bpf/verifier/loops1.c b/tools/testing/selftests/bpf/verifier/loops1.c new file mode 100644 index 000000000000..5e980a5ab69d --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/loops1.c @@ -0,0 +1,161 @@ +{ + "bounded loop, count to 4", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .retval = 4, +}, +{ + "bounded loop, count to 20", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 20, -2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bounded loop, count from positive unknown to 4", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_0, 0, 2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .retval = 4, +}, +{ + "bounded loop, count from totally unknown to 4", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bounded loop, count to 4 with equality", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 4, -2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bounded loop, start in the middle", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(1), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "back-edge", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .retval = 4, +}, +{ + "bounded loop containing a forward jump", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -3), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .retval = 4, +}, +{ + "bounded loop that jumps out rather than in", + .insns = { + BPF_MOV64_IMM(BPF_REG_6, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + BPF_JMP_IMM(BPF_JGT, BPF_REG_6, 10000, 2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), + BPF_JMP_A(-4), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "infinite loop after a conditional jump", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 5), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, 2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_JMP_A(-2), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "program is too large", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bounded recursion", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_1, 4, 1), + BPF_EXIT_INSN(), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -5), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "back-edge", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "infinite loop in two jumps", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(0), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "loop detected", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "infinite loop: three-jump trick", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 2, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 2, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 2, -11), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "loop detected", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, -- cgit v1.2.3 From b061017f8b4d0e05d4c11486581a702fb2a975b2 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sat, 15 Jun 2019 12:12:24 -0700 Subject: selftests/bpf: add realistic loop tests Add a bunch of loop tests. Most of them are created by replacing '#pragma unroll' with '#pragma clang loop unroll(disable)' Several tests are artificially large: /* partial unroll. llvm will unroll loop ~150 times. * C loop count -> 600. * Asm loop count -> 4. * 16k insns in loop body. * Total of 5 such loops. Total program size ~82k insns. */ "./pyperf600.o", /* no unroll at all. * C loop count -> 600. * ASM loop count -> 600. * ~110 insns in loop body. * Total of 5 such loops. Total program size ~1500 insns. */ "./pyperf600_nounroll.o", /* partial unroll. 19k insn in a loop. * Total program size 20.8k insn. * ~350k processed_insns */ "./strobemeta.o", Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann --- .../selftests/bpf/prog_tests/bpf_verif_scale.c | 67 ++- tools/testing/selftests/bpf/progs/loop1.c | 28 ++ tools/testing/selftests/bpf/progs/loop2.c | 28 ++ tools/testing/selftests/bpf/progs/loop3.c | 22 + tools/testing/selftests/bpf/progs/pyperf.h | 6 +- tools/testing/selftests/bpf/progs/pyperf600.c | 9 + .../selftests/bpf/progs/pyperf600_nounroll.c | 8 + tools/testing/selftests/bpf/progs/strobemeta.c | 10 + tools/testing/selftests/bpf/progs/strobemeta.h | 528 +++++++++++++++++++++ .../selftests/bpf/progs/strobemeta_nounroll1.c | 9 + .../selftests/bpf/progs/strobemeta_nounroll2.c | 9 + tools/testing/selftests/bpf/progs/test_seg6_loop.c | 261 ++++++++++ .../selftests/bpf/progs/test_sysctl_loop1.c | 71 +++ .../selftests/bpf/progs/test_sysctl_loop2.c | 72 +++ tools/testing/selftests/bpf/progs/test_xdp_loop.c | 231 +++++++++ 15 files changed, 1347 insertions(+), 12 deletions(-) create mode 100644 tools/testing/selftests/bpf/progs/loop1.c create mode 100644 tools/testing/selftests/bpf/progs/loop2.c create mode 100644 tools/testing/selftests/bpf/progs/loop3.c create mode 100644 tools/testing/selftests/bpf/progs/pyperf600.c create mode 100644 tools/testing/selftests/bpf/progs/pyperf600_nounroll.c create mode 100644 tools/testing/selftests/bpf/progs/strobemeta.c create mode 100644 tools/testing/selftests/bpf/progs/strobemeta.h create mode 100644 tools/testing/selftests/bpf/progs/strobemeta_nounroll1.c create mode 100644 tools/testing/selftests/bpf/progs/strobemeta_nounroll2.c create mode 100644 tools/testing/selftests/bpf/progs/test_seg6_loop.c create mode 100644 tools/testing/selftests/bpf/progs/test_sysctl_loop1.c create mode 100644 tools/testing/selftests/bpf/progs/test_sysctl_loop2.c create mode 100644 tools/testing/selftests/bpf/progs/test_xdp_loop.c (limited to 'tools') diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c index c0091137074b..e1b55261526f 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c @@ -5,7 +5,7 @@ static int libbpf_debug_print(enum libbpf_print_level level, const char *format, va_list args) { if (level != LIBBPF_DEBUG) - return 0; + return vfprintf(stderr, format, args); if (!strstr(format, "verifier log")) return 0; @@ -32,24 +32,69 @@ static int check_load(const char *file, enum bpf_prog_type type) void test_bpf_verif_scale(void) { - const char *scale[] = { - "./test_verif_scale1.o", "./test_verif_scale2.o", "./test_verif_scale3.o" + const char *sched_cls[] = { + "./test_verif_scale1.o", "./test_verif_scale2.o", "./test_verif_scale3.o", }; - const char *pyperf[] = { - "./pyperf50.o", "./pyperf100.o", "./pyperf180.o" + const char *raw_tp[] = { + /* full unroll by llvm */ + "./pyperf50.o", "./pyperf100.o", "./pyperf180.o", + + /* partial unroll. llvm will unroll loop ~150 times. + * C loop count -> 600. + * Asm loop count -> 4. + * 16k insns in loop body. + * Total of 5 such loops. Total program size ~82k insns. + */ + "./pyperf600.o", + + /* no unroll at all. + * C loop count -> 600. + * ASM loop count -> 600. + * ~110 insns in loop body. + * Total of 5 such loops. Total program size ~1500 insns. + */ + "./pyperf600_nounroll.o", + + "./loop1.o", "./loop2.o", + + /* partial unroll. 19k insn in a loop. + * Total program size 20.8k insn. + * ~350k processed_insns + */ + "./strobemeta.o", + + /* no unroll, tiny loops */ + "./strobemeta_nounroll1.o", + "./strobemeta_nounroll2.o", + }; + const char *cg_sysctl[] = { + "./test_sysctl_loop1.o", "./test_sysctl_loop2.o", }; int err, i; if (verifier_stats) libbpf_set_print(libbpf_debug_print); - for (i = 0; i < ARRAY_SIZE(scale); i++) { - err = check_load(scale[i], BPF_PROG_TYPE_SCHED_CLS); - printf("test_scale:%s:%s\n", scale[i], err ? "FAIL" : "OK"); + err = check_load("./loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT); + printf("test_scale:loop3:%s\n", err ? (error_cnt--, "OK") : "FAIL"); + + for (i = 0; i < ARRAY_SIZE(sched_cls); i++) { + err = check_load(sched_cls[i], BPF_PROG_TYPE_SCHED_CLS); + printf("test_scale:%s:%s\n", sched_cls[i], err ? "FAIL" : "OK"); } - for (i = 0; i < ARRAY_SIZE(pyperf); i++) { - err = check_load(pyperf[i], BPF_PROG_TYPE_RAW_TRACEPOINT); - printf("test_scale:%s:%s\n", pyperf[i], err ? "FAIL" : "OK"); + for (i = 0; i < ARRAY_SIZE(raw_tp); i++) { + err = check_load(raw_tp[i], BPF_PROG_TYPE_RAW_TRACEPOINT); + printf("test_scale:%s:%s\n", raw_tp[i], err ? "FAIL" : "OK"); } + + for (i = 0; i < ARRAY_SIZE(cg_sysctl); i++) { + err = check_load(cg_sysctl[i], BPF_PROG_TYPE_CGROUP_SYSCTL); + printf("test_scale:%s:%s\n", cg_sysctl[i], err ? "FAIL" : "OK"); + } + err = check_load("./test_xdp_loop.o", BPF_PROG_TYPE_XDP); + printf("test_scale:test_xdp_loop:%s\n", err ? "FAIL" : "OK"); + + err = check_load("./test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL); + printf("test_scale:test_seg6_loop:%s\n", err ? "FAIL" : "OK"); } diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c new file mode 100644 index 000000000000..dea395af9ea9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop1.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include +#include +#include +#include +#include +#include +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +SEC("raw_tracepoint/kfree_skb") +int nested_loops(volatile struct pt_regs* ctx) +{ + int i, j, sum = 0, m; + + for (j = 0; j < 300; j++) + for (i = 0; i < j; i++) { + if (j & 1) + m = ctx->rax; + else + m = j; + sum += i * m; + } + + return sum; +} diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c new file mode 100644 index 000000000000..0637bd8e8bcf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop2.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include +#include +#include +#include +#include +#include +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +SEC("raw_tracepoint/consume_skb") +int while_true(volatile struct pt_regs* ctx) +{ + int i = 0; + + while (true) { + if (ctx->rax & 1) + i += 3; + else + i += 7; + if (i > 40) + break; + } + + return i; +} diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c new file mode 100644 index 000000000000..30a0f6cba080 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop3.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include +#include +#include +#include +#include +#include +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +SEC("raw_tracepoint/consume_skb") +int while_true(volatile struct pt_regs* ctx) +{ + __u64 i = 0, sum = 0; + do { + i++; + sum += ctx->rax; + } while (i < 0x100000000ULL); + return sum; +} diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h index 0cc5e4ee90bd..6b0781391be5 100644 --- a/tools/testing/selftests/bpf/progs/pyperf.h +++ b/tools/testing/selftests/bpf/progs/pyperf.h @@ -220,7 +220,11 @@ static inline __attribute__((__always_inline__)) int __on_event(struct pt_regs * int32_t* symbol_counter = bpf_map_lookup_elem(&symbolmap, &sym); if (symbol_counter == NULL) return 0; -#pragma unroll +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma clang loop unroll(full) +#endif /* Unwind python stack */ for (int i = 0; i < STACK_MAX_LEN; ++i) { if (frame_ptr && get_frame_data(frame_ptr, pidData, &frame, &sym)) { diff --git a/tools/testing/selftests/bpf/progs/pyperf600.c b/tools/testing/selftests/bpf/progs/pyperf600.c new file mode 100644 index 000000000000..cb49b89e37cd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf600.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#define STACK_MAX_LEN 600 +/* clang will not unroll the loop 600 times. + * Instead it will unroll it to the amount it deemed + * appropriate, but the loop will still execute 600 times. + * Total program size is around 90k insns + */ +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c b/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c new file mode 100644 index 000000000000..6beff7502f4d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#define STACK_MAX_LEN 600 +#define NO_UNROLL +/* clang will not unroll at all. + * Total program size is around 2k insns + */ +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/strobemeta.c b/tools/testing/selftests/bpf/progs/strobemeta.c new file mode 100644 index 000000000000..d3df3d86f092 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook + +#define STROBE_MAX_INTS 2 +#define STROBE_MAX_STRS 25 +#define STROBE_MAX_MAPS 100 +#define STROBE_MAX_MAP_ENTRIES 20 +/* full unroll by llvm #undef NO_UNROLL */ +#include "strobemeta.h" + diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h new file mode 100644 index 000000000000..1ff73f60a3e4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta.h @@ -0,0 +1,528 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include +#include +#include +#include +#include +#include +#include +#include "bpf_helpers.h" + +typedef uint32_t pid_t; +struct task_struct {}; + +#define TASK_COMM_LEN 16 +#define PERF_MAX_STACK_DEPTH 127 + +#define STROBE_TYPE_INVALID 0 +#define STROBE_TYPE_INT 1 +#define STROBE_TYPE_STR 2 +#define STROBE_TYPE_MAP 3 + +#define STACK_TABLE_EPOCH_SHIFT 20 +#define STROBE_MAX_STR_LEN 1 +#define STROBE_MAX_CFGS 32 +#define STROBE_MAX_PAYLOAD \ + (STROBE_MAX_STRS * STROBE_MAX_STR_LEN + \ + STROBE_MAX_MAPS * (1 + STROBE_MAX_MAP_ENTRIES * 2) * STROBE_MAX_STR_LEN) + +struct strobe_value_header { + /* + * meaning depends on type: + * 1. int: 0, if value not set, 1 otherwise + * 2. str: 1 always, whether value is set or not is determined by ptr + * 3. map: 1 always, pointer points to additional struct with number + * of entries (up to STROBE_MAX_MAP_ENTRIES) + */ + uint16_t len; + /* + * _reserved might be used for some future fields/flags, but we always + * want to keep strobe_value_header to be 8 bytes, so BPF can read 16 + * bytes in one go and get both header and value + */ + uint8_t _reserved[6]; +}; + +/* + * strobe_value_generic is used from BPF probe only, but needs to be a union + * of strobe_value_int/strobe_value_str/strobe_value_map + */ +struct strobe_value_generic { + struct strobe_value_header header; + union { + int64_t val; + void *ptr; + }; +}; + +struct strobe_value_int { + struct strobe_value_header header; + int64_t value; +}; + +struct strobe_value_str { + struct strobe_value_header header; + const char* value; +}; + +struct strobe_value_map { + struct strobe_value_header header; + const struct strobe_map_raw* value; +}; + +struct strobe_map_entry { + const char* key; + const char* val; +}; + +/* + * Map of C-string key/value pairs with fixed maximum capacity. Each map has + * corresponding int64 ID, which application can use (or ignore) in whatever + * way appropriate. Map is "write-only", there is no way to get data out of + * map. Map is intended to be used to provide metadata for profilers and is + * not to be used for internal in-app communication. All methods are + * thread-safe. + */ +struct strobe_map_raw { + /* + * general purpose unique ID that's up to application to decide + * whether and how to use; for request metadata use case id is unique + * request ID that's used to match metadata with stack traces on + * Strobelight backend side + */ + int64_t id; + /* number of used entries in map */ + int64_t cnt; + /* + * having volatile doesn't change anything on BPF side, but clang + * emits warnings for passing `volatile const char *` into + * bpf_probe_read_str that expects just `const char *` + */ + const char* tag; + /* + * key/value entries, each consisting of 2 pointers to key and value + * C strings + */ + struct strobe_map_entry entries[STROBE_MAX_MAP_ENTRIES]; +}; + +/* Following values define supported values of TLS mode */ +#define TLS_NOT_SET -1 +#define TLS_LOCAL_EXEC 0 +#define TLS_IMM_EXEC 1 +#define TLS_GENERAL_DYN 2 + +/* + * structure that universally represents TLS location (both for static + * executables and shared libraries) + */ +struct strobe_value_loc { + /* + * tls_mode defines what TLS mode was used for particular metavariable: + * - -1 (TLS_NOT_SET) - no metavariable; + * - 0 (TLS_LOCAL_EXEC) - Local Executable mode; + * - 1 (TLS_IMM_EXEC) - Immediate Executable mode; + * - 2 (TLS_GENERAL_DYN) - General Dynamic mode; + * Local Dynamic mode is not yet supported, because never seen in + * practice. Mode defines how offset field is interpreted. See + * calc_location() in below for details. + */ + int64_t tls_mode; + /* + * TLS_LOCAL_EXEC: offset from thread pointer (fs:0 for x86-64, + * tpidr_el0 for aarch64). + * TLS_IMM_EXEC: absolute address of GOT entry containing offset + * from thread pointer; + * TLS_GENERAL_DYN: absolute addres of double GOT entry + * containing tls_index_t struct; + */ + int64_t offset; +}; + +struct strobemeta_cfg { + int64_t req_meta_idx; + struct strobe_value_loc int_locs[STROBE_MAX_INTS]; + struct strobe_value_loc str_locs[STROBE_MAX_STRS]; + struct strobe_value_loc map_locs[STROBE_MAX_MAPS]; +}; + +struct strobe_map_descr { + uint64_t id; + int16_t tag_len; + /* + * cnt <0 - map value isn't set; + * 0 - map has id set, but no key/value entries + */ + int16_t cnt; + /* + * both key_lens[i] and val_lens[i] should be >0 for present key/value + * entry + */ + uint16_t key_lens[STROBE_MAX_MAP_ENTRIES]; + uint16_t val_lens[STROBE_MAX_MAP_ENTRIES]; +}; + +struct strobemeta_payload { + /* req_id has valid request ID, if req_meta_valid == 1 */ + int64_t req_id; + uint8_t req_meta_valid; + /* + * mask has Nth bit set to 1, if Nth metavar was present and + * successfully read + */ + uint64_t int_vals_set_mask; + int64_t int_vals[STROBE_MAX_INTS]; + /* len is >0 for present values */ + uint16_t str_lens[STROBE_MAX_STRS]; + /* if map_descrs[i].cnt == -1, metavar is not present/set */ + struct strobe_map_descr map_descrs[STROBE_MAX_MAPS]; + /* + * payload has compactly packed values of str and map variables in the + * form: strval1\0strval2\0map1key1\0map1val1\0map2key1\0map2val1\0 + * (and so on); str_lens[i], key_lens[i] and val_lens[i] determines + * value length + */ + char payload[STROBE_MAX_PAYLOAD]; +}; + +struct strobelight_bpf_sample { + uint64_t ktime; + char comm[TASK_COMM_LEN]; + pid_t pid; + int user_stack_id; + int kernel_stack_id; + int has_meta; + struct strobemeta_payload metadata; + /* + * makes it possible to pass ( + 1) as data size to + * perf_submit() to avoid perf_submit's paranoia about passing zero as + * size, as it deduces that might be + * **theoretically** zero + */ + char dummy_safeguard; +}; + +struct bpf_map_def SEC("maps") samples = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 32, +}; + +struct bpf_map_def SEC("maps") stacks_0 = { + .type = BPF_MAP_TYPE_STACK_TRACE, + .key_size = sizeof(uint32_t), + .value_size = sizeof(uint64_t) * PERF_MAX_STACK_DEPTH, + .max_entries = 16, +}; + +struct bpf_map_def SEC("maps") stacks_1 = { + .type = BPF_MAP_TYPE_STACK_TRACE, + .key_size = sizeof(uint32_t), + .value_size = sizeof(uint64_t) * PERF_MAX_STACK_DEPTH, + .max_entries = 16, +}; + +struct bpf_map_def SEC("maps") sample_heap = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(uint32_t), + .value_size = sizeof(struct strobelight_bpf_sample), + .max_entries = 1, +}; + +struct bpf_map_def SEC("maps") strobemeta_cfgs = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(pid_t), + .value_size = sizeof(struct strobemeta_cfg), + .max_entries = STROBE_MAX_CFGS, +}; + +/* Type for the dtv. */ +/* https://github.com/lattera/glibc/blob/master/nptl/sysdeps/x86_64/tls.h#L34 */ +typedef union dtv { + size_t counter; + struct { + void* val; + bool is_static; + } pointer; +} dtv_t; + +/* Partial definition for tcbhead_t */ +/* https://github.com/bminor/glibc/blob/master/sysdeps/x86_64/nptl/tls.h#L42 */ +struct tcbhead { + void* tcb; + dtv_t* dtv; +}; + +/* + * TLS module/offset information for shared library case. + * For x86-64, this is mapped onto two entries in GOT. + * For aarch64, this is pointed to by second GOT entry. + */ +struct tls_index { + uint64_t module; + uint64_t offset; +}; + +static inline __attribute__((always_inline)) +void *calc_location(struct strobe_value_loc *loc, void *tls_base) +{ + /* + * tls_mode value is: + * - -1 (TLS_NOT_SET), if no metavar is present; + * - 0 (TLS_LOCAL_EXEC), if metavar uses Local Executable mode of TLS + * (offset from fs:0 for x86-64 or tpidr_el0 for aarch64); + * - 1 (TLS_IMM_EXEC), if metavar uses Immediate Executable mode of TLS; + * - 2 (TLS_GENERAL_DYN), if metavar uses General Dynamic mode of TLS; + * This schema allows to use something like: + * (tls_mode + 1) * (tls_base + offset) + * to get NULL for "no metavar" location, or correct pointer for local + * executable mode without doing extra ifs. + */ + if (loc->tls_mode <= TLS_LOCAL_EXEC) { + /* static executable is simple, we just have offset from + * tls_base */ + void *addr = tls_base + loc->offset; + /* multiply by (tls_mode + 1) to get NULL, if we have no + * metavar in this slot */ + return (void *)((loc->tls_mode + 1) * (int64_t)addr); + } + /* + * Other modes are more complicated, we need to jump through few hoops. + * + * For immediate executable mode (currently supported only for aarch64): + * - loc->offset is pointing to a GOT entry containing fixed offset + * relative to tls_base; + * + * For general dynamic mode: + * - loc->offset is pointing to a beginning of double GOT entries; + * - (for aarch64 only) second entry points to tls_index_t struct; + * - (for x86-64 only) two GOT entries are already tls_index_t; + * - tls_index_t->module is used to find start of TLS section in + * which variable resides; + * - tls_index_t->offset provides offset within that TLS section, + * pointing to value of variable. + */ + struct tls_index tls_index; + dtv_t *dtv; + void *tls_ptr; + + bpf_probe_read(&tls_index, sizeof(struct tls_index), + (void *)loc->offset); + /* valid module index is always positive */ + if (tls_index.module > 0) { + /* dtv = ((struct tcbhead *)tls_base)->dtv[tls_index.module] */ + bpf_probe_read(&dtv, sizeof(dtv), + &((struct tcbhead *)tls_base)->dtv); + dtv += tls_index.module; + } else { + dtv = NULL; + } + bpf_probe_read(&tls_ptr, sizeof(void *), dtv); + /* if pointer has (void *)-1 value, then TLS wasn't initialized yet */ + return tls_ptr && tls_ptr != (void *)-1 + ? tls_ptr + tls_index.offset + : NULL; +} + +static inline __attribute__((always_inline)) +void read_int_var(struct strobemeta_cfg *cfg, size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload *data) +{ + void *location = calc_location(&cfg->int_locs[idx], tls_base); + if (!location) + return; + + bpf_probe_read(value, sizeof(struct strobe_value_generic), location); + data->int_vals[idx] = value->val; + if (value->header.len) + data->int_vals_set_mask |= (1 << idx); +} + +static inline __attribute__((always_inline)) +uint64_t read_str_var(struct strobemeta_cfg* cfg, size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload *data, void *payload) +{ + void *location; + uint32_t len; + + data->str_lens[idx] = 0; + location = calc_location(&cfg->str_locs[idx], tls_base); + if (!location) + return 0; + + bpf_probe_read(value, sizeof(struct strobe_value_generic), location); + len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, value->ptr); + /* + * if bpf_probe_read_str returns error (<0), due to casting to + * unsinged int, it will become big number, so next check is + * sufficient to check for errors AND prove to BPF verifier, that + * bpf_probe_read_str won't return anything bigger than + * STROBE_MAX_STR_LEN + */ + if (len > STROBE_MAX_STR_LEN) + return 0; + + data->str_lens[idx] = len; + return len; +} + +static inline __attribute__((always_inline)) +void *read_map_var(struct strobemeta_cfg *cfg, size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload* data, void *payload) +{ + struct strobe_map_descr* descr = &data->map_descrs[idx]; + struct strobe_map_raw map; + void *location; + uint32_t len; + int i; + + descr->tag_len = 0; /* presume no tag is set */ + descr->cnt = -1; /* presume no value is set */ + + location = calc_location(&cfg->map_locs[idx], tls_base); + if (!location) + return payload; + + bpf_probe_read(value, sizeof(struct strobe_value_generic), location); + if (bpf_probe_read(&map, sizeof(struct strobe_map_raw), value->ptr)) + return payload; + + descr->id = map.id; + descr->cnt = map.cnt; + if (cfg->req_meta_idx == idx) { + data->req_id = map.id; + data->req_meta_valid = 1; + } + + len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, map.tag); + if (len <= STROBE_MAX_STR_LEN) { + descr->tag_len = len; + payload += len; + } + +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif + for (int i = 0; i < STROBE_MAX_MAP_ENTRIES && i < map.cnt; ++i) { + descr->key_lens[i] = 0; + len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, + map.entries[i].key); + if (len <= STROBE_MAX_STR_LEN) { + descr->key_lens[i] = len; + payload += len; + } + descr->val_lens[i] = 0; + len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, + map.entries[i].val); + if (len <= STROBE_MAX_STR_LEN) { + descr->val_lens[i] = len; + payload += len; + } + } + + return payload; +} + +/* + * read_strobe_meta returns NULL, if no metadata was read; otherwise returns + * pointer to *right after* payload ends + */ +static inline __attribute__((always_inline)) +void *read_strobe_meta(struct task_struct* task, + struct strobemeta_payload* data) { + pid_t pid = bpf_get_current_pid_tgid() >> 32; + struct strobe_value_generic value = {0}; + struct strobemeta_cfg *cfg; + void *tls_base, *payload; + + cfg = bpf_map_lookup_elem(&strobemeta_cfgs, &pid); + if (!cfg) + return NULL; + + data->int_vals_set_mask = 0; + data->req_meta_valid = 0; + payload = data->payload; + /* + * we don't have struct task_struct definition, it should be: + * tls_base = (void *)task->thread.fsbase; + */ + tls_base = (void *)task; + +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif + for (int i = 0; i < STROBE_MAX_INTS; ++i) { + read_int_var(cfg, i, tls_base, &value, data); + } +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif + for (int i = 0; i < STROBE_MAX_STRS; ++i) { + payload += read_str_var(cfg, i, tls_base, &value, data, payload); + } +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif + for (int i = 0; i < STROBE_MAX_MAPS; ++i) { + payload = read_map_var(cfg, i, tls_base, &value, data, payload); + } + /* + * return pointer right after end of payload, so it's possible to + * calculate exact amount of useful data that needs to be sent + */ + return payload; +} + +SEC("raw_tracepoint/kfree_skb") +int on_event(struct pt_regs *ctx) { + pid_t pid = bpf_get_current_pid_tgid() >> 32; + struct strobelight_bpf_sample* sample; + struct task_struct *task; + uint32_t zero = 0; + uint64_t ktime_ns; + void *sample_end; + + sample = bpf_map_lookup_elem(&sample_heap, &zero); + if (!sample) + return 0; /* this will never happen */ + + sample->pid = pid; + bpf_get_current_comm(&sample->comm, TASK_COMM_LEN); + ktime_ns = bpf_ktime_get_ns(); + sample->ktime = ktime_ns; + + task = (struct task_struct *)bpf_get_current_task(); + sample_end = read_strobe_meta(task, &sample->metadata); + sample->has_meta = sample_end != NULL; + sample_end = sample_end ? : &sample->metadata; + + if ((ktime_ns >> STACK_TABLE_EPOCH_SHIFT) & 1) { + sample->kernel_stack_id = bpf_get_stackid(ctx, &stacks_1, 0); + sample->user_stack_id = bpf_get_stackid(ctx, &stacks_1, BPF_F_USER_STACK); + } else { + sample->kernel_stack_id = bpf_get_stackid(ctx, &stacks_0, 0); + sample->user_stack_id = bpf_get_stackid(ctx, &stacks_0, BPF_F_USER_STACK); + } + + uint64_t sample_size = sample_end - (void *)sample; + /* should always be true */ + if (sample_size < sizeof(struct strobelight_bpf_sample)) + bpf_perf_event_output(ctx, &samples, 0, sample, 1 + sample_size); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/strobemeta_nounroll1.c b/tools/testing/selftests/bpf/progs/strobemeta_nounroll1.c new file mode 100644 index 000000000000..f0a1669e11d6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta_nounroll1.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook + +#define STROBE_MAX_INTS 2 +#define STROBE_MAX_STRS 25 +#define STROBE_MAX_MAPS 13 +#define STROBE_MAX_MAP_ENTRIES 20 +#define NO_UNROLL +#include "strobemeta.h" diff --git a/tools/testing/selftests/bpf/progs/strobemeta_nounroll2.c b/tools/testing/selftests/bpf/progs/strobemeta_nounroll2.c new file mode 100644 index 000000000000..4291a7d642e7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta_nounroll2.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook + +#define STROBE_MAX_INTS 2 +#define STROBE_MAX_STRS 25 +#define STROBE_MAX_MAPS 30 +#define STROBE_MAX_MAP_ENTRIES 20 +#define NO_UNROLL +#include "strobemeta.h" diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c new file mode 100644 index 000000000000..463964d79f73 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c @@ -0,0 +1,261 @@ +#include +#include +#include +#include +#include +#include "bpf_helpers.h" +#include "bpf_endian.h" + +/* Packet parsing state machine helpers. */ +#define cursor_advance(_cursor, _len) \ + ({ void *_tmp = _cursor; _cursor += _len; _tmp; }) + +#define SR6_FLAG_ALERT (1 << 4) + +#define htonll(x) ((bpf_htonl(1)) == 1 ? (x) : ((uint64_t)bpf_htonl((x) & \ + 0xFFFFFFFF) << 32) | bpf_htonl((x) >> 32)) +#define ntohll(x) ((bpf_ntohl(1)) == 1 ? (x) : ((uint64_t)bpf_ntohl((x) & \ + 0xFFFFFFFF) << 32) | bpf_ntohl((x) >> 32)) +#define BPF_PACKET_HEADER __attribute__((packed)) + +struct ip6_t { + unsigned int ver:4; + unsigned int priority:8; + unsigned int flow_label:20; + unsigned short payload_len; + unsigned char next_header; + unsigned char hop_limit; + unsigned long long src_hi; + unsigned long long src_lo; + unsigned long long dst_hi; + unsigned long long dst_lo; +} BPF_PACKET_HEADER; + +struct ip6_addr_t { + unsigned long long hi; + unsigned long long lo; +} BPF_PACKET_HEADER; + +struct ip6_srh_t { + unsigned char nexthdr; + unsigned char hdrlen; + unsigned char type; + unsigned char segments_left; + unsigned char first_segment; + unsigned char flags; + unsigned short tag; + + struct ip6_addr_t segments[0]; +} BPF_PACKET_HEADER; + +struct sr6_tlv_t { + unsigned char type; + unsigned char len; + unsigned char value[0]; +} BPF_PACKET_HEADER; + +static __attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff *skb) +{ + void *cursor, *data_end; + struct ip6_srh_t *srh; + struct ip6_t *ip; + uint8_t *ipver; + + data_end = (void *)(long)skb->data_end; + cursor = (void *)(long)skb->data; + ipver = (uint8_t *)cursor; + + if ((void *)ipver + sizeof(*ipver) > data_end) + return NULL; + + if ((*ipver >> 4) != 6) + return NULL; + + ip = cursor_advance(cursor, sizeof(*ip)); + if ((void *)ip + sizeof(*ip) > data_end) + return NULL; + + if (ip->next_header != 43) + return NULL; + + srh = cursor_advance(cursor, sizeof(*srh)); + if ((void *)srh + sizeof(*srh) > data_end) + return NULL; + + if (srh->type != 4) + return NULL; + + return srh; +} + +static __attribute__((always_inline)) +int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad, + uint32_t old_pad, uint32_t pad_off) +{ + int err; + + if (new_pad != old_pad) { + err = bpf_lwt_seg6_adjust_srh(skb, pad_off, + (int) new_pad - (int) old_pad); + if (err) + return err; + } + + if (new_pad > 0) { + char pad_tlv_buf[16] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0}; + struct sr6_tlv_t *pad_tlv = (struct sr6_tlv_t *) pad_tlv_buf; + + pad_tlv->type = SR6_TLV_PADDING; + pad_tlv->len = new_pad - 2; + + err = bpf_lwt_seg6_store_bytes(skb, pad_off, + (void *)pad_tlv_buf, new_pad); + if (err) + return err; + } + + return 0; +} + +static __attribute__((always_inline)) +int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh, + uint32_t *tlv_off, uint32_t *pad_size, + uint32_t *pad_off) +{ + uint32_t srh_off, cur_off; + int offset_valid = 0; + int err; + + srh_off = (char *)srh - (char *)(long)skb->data; + // cur_off = end of segments, start of possible TLVs + cur_off = srh_off + sizeof(*srh) + + sizeof(struct ip6_addr_t) * (srh->first_segment + 1); + + *pad_off = 0; + + // we can only go as far as ~10 TLVs due to the BPF max stack size + #pragma clang loop unroll(disable) + for (int i = 0; i < 100; i++) { + struct sr6_tlv_t tlv; + + if (cur_off == *tlv_off) + offset_valid = 1; + + if (cur_off >= srh_off + ((srh->hdrlen + 1) << 3)) + break; + + err = bpf_skb_load_bytes(skb, cur_off, &tlv, sizeof(tlv)); + if (err) + return err; + + if (tlv.type == SR6_TLV_PADDING) { + *pad_size = tlv.len + sizeof(tlv); + *pad_off = cur_off; + + if (*tlv_off == srh_off) { + *tlv_off = cur_off; + offset_valid = 1; + } + break; + + } else if (tlv.type == SR6_TLV_HMAC) { + break; + } + + cur_off += sizeof(tlv) + tlv.len; + } // we reached the padding or HMAC TLVs, or the end of the SRH + + if (*pad_off == 0) + *pad_off = cur_off; + + if (*tlv_off == -1) + *tlv_off = cur_off; + else if (!offset_valid) + return -EINVAL; + + return 0; +} + +static __attribute__((always_inline)) +int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off, + struct sr6_tlv_t *itlv, uint8_t tlv_size) +{ + uint32_t srh_off = (char *)srh - (char *)(long)skb->data; + uint8_t len_remaining, new_pad; + uint32_t pad_off = 0; + uint32_t pad_size = 0; + uint32_t partial_srh_len; + int err; + + if (tlv_off != -1) + tlv_off += srh_off; + + if (itlv->type == SR6_TLV_PADDING || itlv->type == SR6_TLV_HMAC) + return -EINVAL; + + err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off); + if (err) + return err; + + err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, sizeof(*itlv) + itlv->len); + if (err) + return err; + + err = bpf_lwt_seg6_store_bytes(skb, tlv_off, (void *)itlv, tlv_size); + if (err) + return err; + + // the following can't be moved inside update_tlv_pad because the + // bpf verifier has some issues with it + pad_off += sizeof(*itlv) + itlv->len; + partial_srh_len = pad_off - srh_off; + len_remaining = partial_srh_len % 8; + new_pad = 8 - len_remaining; + + if (new_pad == 1) // cannot pad for 1 byte only + new_pad = 9; + else if (new_pad == 8) + new_pad = 0; + + return update_tlv_pad(skb, new_pad, pad_size, pad_off); +} + +// Add an Egress TLV fc00::4, add the flag A, +// and apply End.X action to fc42::1 +SEC("lwt_seg6local") +int __add_egr_x(struct __sk_buff *skb) +{ + unsigned long long hi = 0xfc42000000000000; + unsigned long long lo = 0x1; + struct ip6_srh_t *srh = get_srh(skb); + uint8_t new_flags = SR6_FLAG_ALERT; + struct ip6_addr_t addr; + int err, offset; + + if (srh == NULL) + return BPF_DROP; + + uint8_t tlv[20] = {2, 18, 0, 0, 0xfd, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x4}; + + err = add_tlv(skb, srh, (srh->hdrlen+1) << 3, + (struct sr6_tlv_t *)&tlv, 20); + if (err) + return BPF_DROP; + + offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags); + err = bpf_lwt_seg6_store_bytes(skb, offset, + (void *)&new_flags, sizeof(new_flags)); + if (err) + return BPF_DROP; + + addr.lo = htonll(lo); + addr.hi = htonll(hi); + err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_X, + (void *)&addr, sizeof(addr)); + if (err) + return BPF_DROP; + return BPF_REDIRECT; +} +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c new file mode 100644 index 000000000000..608a06871572 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include +#include + +#include +#include + +#include "bpf_helpers.h" + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +/* tcp_mem sysctl has only 3 ints, but this test is doing TCP_MEM_LOOPS */ +#define TCP_MEM_LOOPS 28 /* because 30 doesn't fit into 512 bytes of stack */ +#define MAX_ULONG_STR_LEN 7 +#define MAX_VALUE_STR_LEN (TCP_MEM_LOOPS * MAX_ULONG_STR_LEN) + +static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx) +{ + volatile char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string"; + unsigned char i; + char name[64]; + int ret; + + memset(name, 0, sizeof(name)); + ret = bpf_sysctl_get_name(ctx, name, sizeof(name), 0); + if (ret < 0 || ret != sizeof(tcp_mem_name) - 1) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < sizeof(tcp_mem_name); ++i) + if (name[i] != tcp_mem_name[i]) + return 0; + + return 1; +} + +SEC("cgroup/sysctl") +int sysctl_tcp_mem(struct bpf_sysctl *ctx) +{ + unsigned long tcp_mem[TCP_MEM_LOOPS] = {}; + char value[MAX_VALUE_STR_LEN]; + unsigned char i, off = 0; + int ret; + + if (ctx->write) + return 0; + + if (!is_tcp_mem(ctx)) + return 0; + + ret = bpf_sysctl_get_current_value(ctx, value, MAX_VALUE_STR_LEN); + if (ret < 0 || ret >= MAX_VALUE_STR_LEN) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) { + ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0, + tcp_mem + i); + if (ret <= 0 || ret > MAX_ULONG_STR_LEN) + return 0; + off += ret & MAX_ULONG_STR_LEN; + } + + return tcp_mem[0] < tcp_mem[1] && tcp_mem[1] < tcp_mem[2]; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c new file mode 100644 index 000000000000..cb201cbe11e7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include +#include + +#include +#include + +#include "bpf_helpers.h" + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +/* tcp_mem sysctl has only 3 ints, but this test is doing TCP_MEM_LOOPS */ +#define TCP_MEM_LOOPS 20 /* because 30 doesn't fit into 512 bytes of stack */ +#define MAX_ULONG_STR_LEN 7 +#define MAX_VALUE_STR_LEN (TCP_MEM_LOOPS * MAX_ULONG_STR_LEN) + +static __attribute__((noinline)) int is_tcp_mem(struct bpf_sysctl *ctx) +{ + volatile char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string_to_stress_byte_loop"; + unsigned char i; + char name[64]; + int ret; + + memset(name, 0, sizeof(name)); + ret = bpf_sysctl_get_name(ctx, name, sizeof(name), 0); + if (ret < 0 || ret != sizeof(tcp_mem_name) - 1) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < sizeof(tcp_mem_name); ++i) + if (name[i] != tcp_mem_name[i]) + return 0; + + return 1; +} + + +SEC("cgroup/sysctl") +int sysctl_tcp_mem(struct bpf_sysctl *ctx) +{ + unsigned long tcp_mem[TCP_MEM_LOOPS] = {}; + char value[MAX_VALUE_STR_LEN]; + unsigned char i, off = 0; + int ret; + + if (ctx->write) + return 0; + + if (!is_tcp_mem(ctx)) + return 0; + + ret = bpf_sysctl_get_current_value(ctx, value, MAX_VALUE_STR_LEN); + if (ret < 0 || ret >= MAX_VALUE_STR_LEN) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) { + ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0, + tcp_mem + i); + if (ret <= 0 || ret > MAX_ULONG_STR_LEN) + return 0; + off += ret & MAX_ULONG_STR_LEN; + } + + return tcp_mem[0] < tcp_mem[1] && tcp_mem[1] < tcp_mem[2]; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c new file mode 100644 index 000000000000..7fa4677df22e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c @@ -0,0 +1,231 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "bpf_helpers.h" +#include "bpf_endian.h" +#include "test_iptunnel_common.h" + +int _version SEC("version") = 1; + +struct bpf_map_def SEC("maps") rxcnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u64), + .max_entries = 256, +}; + +struct bpf_map_def SEC("maps") vip2tnl = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(struct vip), + .value_size = sizeof(struct iptnl_info), + .max_entries = MAX_IPTNL_ENTRIES, +}; + +static __always_inline void count_tx(__u32 protocol) +{ + __u64 *rxcnt_count; + + rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol); + if (rxcnt_count) + *rxcnt_count += 1; +} + +static __always_inline int get_dport(void *trans_data, void *data_end, + __u8 protocol) +{ + struct tcphdr *th; + struct udphdr *uh; + + switch (protocol) { + case IPPROTO_TCP: + th = (struct tcphdr *)trans_data; + if (th + 1 > data_end) + return -1; + return th->dest; + case IPPROTO_UDP: + uh = (struct udphdr *)trans_data; + if (uh + 1 > data_end) + return -1; + return uh->dest; + default: + return 0; + } +} + +static __always_inline void set_ethhdr(struct ethhdr *new_eth, + const struct ethhdr *old_eth, + const struct iptnl_info *tnl, + __be16 h_proto) +{ + memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source)); + memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest)); + new_eth->h_proto = h_proto; +} + +static __always_inline int handle_ipv4(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct iphdr *iph = data + sizeof(struct ethhdr); + __u16 *next_iph; + __u16 payload_len; + struct vip vip = {}; + int dport; + __u32 csum = 0; + int i; + + if (iph + 1 > data_end) + return XDP_DROP; + + dport = get_dport(iph + 1, data_end, iph->protocol); + if (dport == -1) + return XDP_DROP; + + vip.protocol = iph->protocol; + vip.family = AF_INET; + vip.daddr.v4 = iph->daddr; + vip.dport = dport; + payload_len = bpf_ntohs(iph->tot_len); + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v4-in-v4 */ + if (!tnl || tnl->family != AF_INET) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + iph = data + sizeof(*new_eth); + old_eth = data + sizeof(*iph); + + if (new_eth + 1 > data_end || + old_eth + 1 > data_end || + iph + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IP)); + + iph->version = 4; + iph->ihl = sizeof(*iph) >> 2; + iph->frag_off = 0; + iph->protocol = IPPROTO_IPIP; + iph->check = 0; + iph->tos = 0; + iph->tot_len = bpf_htons(payload_len + sizeof(*iph)); + iph->daddr = tnl->daddr.v4; + iph->saddr = tnl->saddr.v4; + iph->ttl = 8; + + next_iph = (__u16 *)iph; +#pragma clang loop unroll(disable) + for (i = 0; i < sizeof(*iph) >> 1; i++) + csum += *next_iph++; + + iph->check = ~((csum & 0xffff) + (csum >> 16)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +static __always_inline int handle_ipv6(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct ipv6hdr *ip6h = data + sizeof(struct ethhdr); + __u16 payload_len; + struct vip vip = {}; + int dport; + + if (ip6h + 1 > data_end) + return XDP_DROP; + + dport = get_dport(ip6h + 1, data_end, ip6h->nexthdr); + if (dport == -1) + return XDP_DROP; + + vip.protocol = ip6h->nexthdr; + vip.family = AF_INET6; + memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr)); + vip.dport = dport; + payload_len = ip6h->payload_len; + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v6-in-v6 */ + if (!tnl || tnl->family != AF_INET6) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + ip6h = data + sizeof(*new_eth); + old_eth = data + sizeof(*ip6h); + + if (new_eth + 1 > data_end || old_eth + 1 > data_end || + ip6h + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IPV6)); + + ip6h->version = 6; + ip6h->priority = 0; + memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl)); + ip6h->payload_len = bpf_htons(bpf_ntohs(payload_len) + sizeof(*ip6h)); + ip6h->nexthdr = IPPROTO_IPV6; + ip6h->hop_limit = 8; + memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6)); + memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +SEC("xdp_tx_iptunnel") +int _xdp_tx_iptunnel(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eth = data; + __u16 h_proto; + + if (eth + 1 > data_end) + return XDP_DROP; + + h_proto = eth->h_proto; + + if (h_proto == bpf_htons(ETH_P_IP)) + return handle_ipv4(xdp); + else if (h_proto == bpf_htons(ETH_P_IPV6)) + + return handle_ipv6(xdp); + else + return XDP_DROP; +} + +char _license[] SEC("license") = "GPL"; -- cgit v1.2.3