From b0659d8a950d424e57cc0a67afc4740ee561224e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 15 Jun 2020 14:49:26 -0700 Subject: bpf: Fix definition of bpf_ringbuf_output() helper in UAPI comments Fix definition of bpf_ringbuf_output() in UAPI header comments, which is used to generate libbpf's bpf_helper_defs.h header. Return value is a number (error code), not a pointer. Fixes: 457f44363a88 ("bpf: Implement BPF ring buffer and verifier support for it") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200615214926.3638836-1-andriin@fb.com --- tools/include/uapi/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 19684813faae..974a71342aea 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3168,7 +3168,7 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * void *bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) + * int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) * Description * Copy *size* bytes from *data* into a ring buffer *ringbuf*. * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of -- cgit v1.2.3 From c34a06c56df7c513cd19f591b26fe7d814c778cc Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 15 Jun 2020 15:53:55 -0700 Subject: tools/bpftool: Add ringbuf map to a list of known map types Add symbolic name "ringbuf" to map to BPF_MAP_TYPE_RINGBUF. Without this, users will see "type 27" instead of "ringbuf" in `map show` output. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200615225355.366256-1-andriin@fb.com --- tools/bpf/bpftool/map.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index c5fac8068ba1..99109a6afe17 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -49,6 +49,7 @@ const char * const map_type_name[] = { [BPF_MAP_TYPE_STACK] = "stack", [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", [BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops", + [BPF_MAP_TYPE_RINGBUF] = "ringbuf", }; const size_t map_type_name_size = ARRAY_SIZE(map_type_name); -- cgit v1.2.3 From 1c7fb20d6b0acd452cb93d447051eac7724edfa7 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Tue, 16 Jun 2020 13:33:03 +0200 Subject: tools, bpftool: Add ringbuf map type to map command docs Commit c34a06c56df7 ("tools/bpftool: Add ringbuf map to a list of known map types") added the symbolic "ringbuf" name. Document it in the bpftool map command docs and usage as well. Signed-off-by: Tobias Klauser Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200616113303.8123-1-tklauser@distanz.ch --- tools/bpf/bpftool/Documentation/bpftool-map.rst | 2 +- tools/bpf/bpftool/map.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 31101643e57c..70c78faa47ab 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -49,7 +49,7 @@ MAP COMMANDS | | **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps** | | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** | | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** -| | **queue** | **stack** | **sk_storage** | **struct_ops** } +| | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** } DESCRIPTION =========== diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 99109a6afe17..1d3b60651078 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -1591,7 +1591,7 @@ static int do_help(int argc, char **argv) " lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n" " devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n" - " queue | stack | sk_storage | struct_ops }\n" + " queue | stack | sk_storage | struct_ops | ringbuf }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2]); -- cgit v1.2.3 From a0cb12b03132befbdb29d835ca330c18792e8134 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 16 Jun 2020 18:04:15 -0700 Subject: selftests/bpf: Make sure optvals > PAGE_SIZE are bypassed We are relying on the fact, that we can pass > sizeof(int) optvals to the SOL_IP+IP_FREEBIND option (the kernel will take first 4 bytes). In the BPF program we check that we can only touch PAGE_SIZE bytes, but the real optlen is PAGE_SIZE * 2. In both cases, we override it to some predefined value and trim the optlen. Also, let's modify exiting IP_TOS usecase to test optlen=0 case where BPF program just bypasses the data as is. Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200617010416.93086-2-sdf@google.com --- .../testing/selftests/bpf/prog_tests/sockopt_sk.c | 46 +++++++++++++++--- tools/testing/selftests/bpf/progs/sockopt_sk.c | 54 +++++++++++++++++++++- 2 files changed, 91 insertions(+), 9 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 2061a6beac0f..5f54c6aec7f0 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -13,6 +13,7 @@ static int getsetsockopt(void) char cc[16]; /* TCP_CA_NAME_MAX */ } buf = {}; socklen_t optlen; + char *big_buf = NULL; fd = socket(AF_INET, SOCK_STREAM, 0); if (fd < 0) { @@ -22,24 +23,31 @@ static int getsetsockopt(void) /* IP_TOS - BPF bypass */ - buf.u8[0] = 0x08; - err = setsockopt(fd, SOL_IP, IP_TOS, &buf, 1); + optlen = getpagesize() * 2; + big_buf = calloc(1, optlen); + if (!big_buf) { + log_err("Couldn't allocate two pages"); + goto err; + } + + *(int *)big_buf = 0x08; + err = setsockopt(fd, SOL_IP, IP_TOS, big_buf, optlen); if (err) { log_err("Failed to call setsockopt(IP_TOS)"); goto err; } - buf.u8[0] = 0x00; + memset(big_buf, 0, optlen); optlen = 1; - err = getsockopt(fd, SOL_IP, IP_TOS, &buf, &optlen); + err = getsockopt(fd, SOL_IP, IP_TOS, big_buf, &optlen); if (err) { log_err("Failed to call getsockopt(IP_TOS)"); goto err; } - if (buf.u8[0] != 0x08) { - log_err("Unexpected getsockopt(IP_TOS) buf[0] 0x%02x != 0x08", - buf.u8[0]); + if (*(int *)big_buf != 0x08) { + log_err("Unexpected getsockopt(IP_TOS) optval 0x%x != 0x08", + *(int *)big_buf); goto err; } @@ -78,6 +86,28 @@ static int getsetsockopt(void) goto err; } + /* IP_FREEBIND - BPF can't access optval past PAGE_SIZE */ + + optlen = getpagesize() * 2; + memset(big_buf, 0, optlen); + + err = setsockopt(fd, SOL_IP, IP_FREEBIND, big_buf, optlen); + if (err != 0) { + log_err("Failed to call setsockopt, ret=%d", err); + goto err; + } + + err = getsockopt(fd, SOL_IP, IP_FREEBIND, big_buf, &optlen); + if (err != 0) { + log_err("Failed to call getsockopt, ret=%d", err); + goto err; + } + + if (optlen != 1 || *(__u8 *)big_buf != 0x55) { + log_err("Unexpected IP_FREEBIND getsockopt, optlen=%d, optval=0x%x", + optlen, *(__u8 *)big_buf); + } + /* SO_SNDBUF is overwritten */ buf.u32 = 0x01010101; @@ -124,9 +154,11 @@ static int getsetsockopt(void) goto err; } + free(big_buf); close(fd); return 0; err: + free(big_buf); close(fd); return -1; } diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index d5a5eeb5fb52..712df7b49cb1 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -8,6 +8,10 @@ char _license[] SEC("license") = "GPL"; __u32 _version SEC("version") = 1; +#ifndef PAGE_SIZE +#define PAGE_SIZE 4096 +#endif + #define SOL_CUSTOM 0xdeadbeef struct sockopt_sk { @@ -28,12 +32,14 @@ int _getsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; struct sockopt_sk *storage; - if (ctx->level == SOL_IP && ctx->optname == IP_TOS) + if (ctx->level == SOL_IP && ctx->optname == IP_TOS) { /* Not interested in SOL_IP:IP_TOS; * let next BPF program in the cgroup chain or kernel * handle it. */ + ctx->optlen = 0; /* bypass optval>PAGE_SIZE */ return 1; + } if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) { /* Not interested in SOL_SOCKET:SO_SNDBUF; @@ -51,6 +57,26 @@ int _getsockopt(struct bpf_sockopt *ctx) return 1; } + if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + ctx->retval = 0; /* Reset system call return value to zero */ + + /* Always export 0x55 */ + optval[0] = 0x55; + ctx->optlen = 1; + + /* Userspace buffer is PAGE_SIZE * 2, but BPF + * program can only see the first PAGE_SIZE + * bytes of data. + */ + if (optval_end - optval != PAGE_SIZE) + return 0; /* EPERM, unexpected data size */ + + return 1; + } + if (ctx->level != SOL_CUSTOM) return 0; /* EPERM, deny everything except custom level */ @@ -81,12 +107,14 @@ int _setsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; struct sockopt_sk *storage; - if (ctx->level == SOL_IP && ctx->optname == IP_TOS) + if (ctx->level == SOL_IP && ctx->optname == IP_TOS) { /* Not interested in SOL_IP:IP_TOS; * let next BPF program in the cgroup chain or kernel * handle it. */ + ctx->optlen = 0; /* bypass optval>PAGE_SIZE */ return 1; + } if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) { /* Overwrite SO_SNDBUF value */ @@ -112,6 +140,28 @@ int _setsockopt(struct bpf_sockopt *ctx) return 1; } + if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { + /* Original optlen is larger than PAGE_SIZE. */ + if (ctx->optlen != PAGE_SIZE * 2) + return 0; /* EPERM, unexpected data size */ + + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + /* Make sure we can trim the buffer. */ + optval[0] = 0; + ctx->optlen = 1; + + /* Usepace buffer is PAGE_SIZE * 2, but BPF + * program can only see the first PAGE_SIZE + * bytes of data. + */ + if (optval_end - optval != PAGE_SIZE) + return 0; /* EPERM, unexpected data size */ + + return 1; + } + if (ctx->level != SOL_CUSTOM) return 0; /* EPERM, deny everything except custom level */ -- cgit v1.2.3