From b0659d8a950d424e57cc0a67afc4740ee561224e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 15 Jun 2020 14:49:26 -0700 Subject: [PATCH 01/10] 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 --- include/uapi/linux/bpf.h | 2 +- tools/include/uapi/linux/bpf.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 19684813faae..974a71342aea 100644 --- a/include/uapi/linux/bpf.h +++ b/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 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 From c34a06c56df7c513cd19f591b26fe7d814c778cc Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 15 Jun 2020 15:53:55 -0700 Subject: [PATCH 02/10] 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(+) 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); From 6903cdae9f9f08d61e49c16cbef11c293e33a615 Mon Sep 17 00:00:00 2001 From: Gaurav Singh Date: Fri, 12 Jun 2020 14:53:27 -0400 Subject: [PATCH 03/10] bpf, xdp, samples: Fix null pointer dereference in *_user code Memset on the pointer right after malloc can cause a NULL pointer deference if it failed to allocate memory. A simple fix is to replace malloc()/memset() pair with a simple call to calloc(). Fixes: 0fca931a6f21 ("samples/bpf: program demonstrating access to xdp_rxq_info") Signed-off-by: Gaurav Singh Signed-off-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Acked-by: John Fastabend --- samples/bpf/xdp_monitor_user.c | 8 ++------ samples/bpf/xdp_redirect_cpu_user.c | 7 ++----- samples/bpf/xdp_rxq_info_user.c | 13 +++---------- 3 files changed, 7 insertions(+), 21 deletions(-) diff --git a/samples/bpf/xdp_monitor_user.c b/samples/bpf/xdp_monitor_user.c index dd558cbb2309..ef53b93db573 100644 --- a/samples/bpf/xdp_monitor_user.c +++ b/samples/bpf/xdp_monitor_user.c @@ -509,11 +509,8 @@ static void *alloc_rec_per_cpu(int record_size) { unsigned int nr_cpus = bpf_num_possible_cpus(); void *array; - size_t size; - size = record_size * nr_cpus; - array = malloc(size); - memset(array, 0, size); + array = calloc(nr_cpus, record_size); if (!array) { fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus); exit(EXIT_FAIL_MEM); @@ -528,8 +525,7 @@ static struct stats_record *alloc_stats_record(void) int i; /* Alloc main stats_record structure */ - rec = malloc(sizeof(*rec)); - memset(rec, 0, sizeof(*rec)); + rec = calloc(1, sizeof(*rec)); if (!rec) { fprintf(stderr, "Mem alloc error\n"); exit(EXIT_FAIL_MEM); diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index f3468168982e..f4e755e0dd73 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -207,11 +207,8 @@ static struct datarec *alloc_record_per_cpu(void) { unsigned int nr_cpus = bpf_num_possible_cpus(); struct datarec *array; - size_t size; - size = sizeof(struct datarec) * nr_cpus; - array = malloc(size); - memset(array, 0, size); + array = calloc(nr_cpus, sizeof(struct datarec)); if (!array) { fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus); exit(EXIT_FAIL_MEM); @@ -226,11 +223,11 @@ static struct stats_record *alloc_stats_record(void) size = sizeof(*rec) + n_cpus * sizeof(struct record); rec = malloc(size); - memset(rec, 0, size); if (!rec) { fprintf(stderr, "Mem alloc error\n"); exit(EXIT_FAIL_MEM); } + memset(rec, 0, size); rec->rx_cnt.cpu = alloc_record_per_cpu(); rec->redir_err.cpu = alloc_record_per_cpu(); rec->kthread.cpu = alloc_record_per_cpu(); diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c index 4fe47502ebed..caa4e7ffcfc7 100644 --- a/samples/bpf/xdp_rxq_info_user.c +++ b/samples/bpf/xdp_rxq_info_user.c @@ -198,11 +198,8 @@ static struct datarec *alloc_record_per_cpu(void) { unsigned int nr_cpus = bpf_num_possible_cpus(); struct datarec *array; - size_t size; - size = sizeof(struct datarec) * nr_cpus; - array = malloc(size); - memset(array, 0, size); + array = calloc(nr_cpus, sizeof(struct datarec)); if (!array) { fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus); exit(EXIT_FAIL_MEM); @@ -214,11 +211,8 @@ static struct record *alloc_record_per_rxq(void) { unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; struct record *array; - size_t size; - size = sizeof(struct record) * nr_rxqs; - array = malloc(size); - memset(array, 0, size); + array = calloc(nr_rxqs, sizeof(struct record)); if (!array) { fprintf(stderr, "Mem alloc error (nr_rxqs:%u)\n", nr_rxqs); exit(EXIT_FAIL_MEM); @@ -232,8 +226,7 @@ static struct stats_record *alloc_stats_record(void) struct stats_record *rec; int i; - rec = malloc(sizeof(*rec)); - memset(rec, 0, sizeof(*rec)); + rec = calloc(1, sizeof(struct stats_record)); if (!rec) { fprintf(stderr, "Mem alloc error\n"); exit(EXIT_FAIL_MEM); From 02553b91da5deb63c8562b47529b09b734659af0 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 15 Jun 2020 22:04:30 -0700 Subject: [PATCH 04/10] bpf: bpf_probe_read_kernel_str() has to return amount of data read on success During recent refactorings, bpf_probe_read_kernel_str() started returning 0 on success, instead of amount of data successfully read. This majorly breaks applications relying on bpf_probe_read_kernel_str() and bpf_probe_read_str() and their results. Fix this by returning actual number of bytes read. Fixes: 8d92db5c04d1 ("bpf: rework the compat kernel probe handling") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Reviewed-by: Christoph Hellwig Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200616050432.1902042-1-andriin@fb.com --- kernel/trace/bpf_trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index e729c9e587a0..a3ac7de98baa 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -241,7 +241,7 @@ bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr) if (unlikely(ret < 0)) goto fail; - return 0; + return ret; fail: memset(dst, 0, size); return ret; From 1c7fb20d6b0acd452cb93d447051eac7724edfa7 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Tue, 16 Jun 2020 13:33:03 +0200 Subject: [PATCH 05/10] 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(-) 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]); From 3ff2351651a2ecb73ec9d29119793bde190b2850 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 16 Jun 2020 18:35:18 +0800 Subject: [PATCH 06/10] xdp: Handle frame_sz in xdp_convert_zc_to_xdp_frame() In commit 34cc0b338a61 we only handled the frame_sz in convert_to_xdp_frame(). This patch will also handle frame_sz in xdp_convert_zc_to_xdp_frame(). Fixes: 34cc0b338a61 ("xdp: Xdp_frame add member frame_sz and handle in convert_to_xdp_frame") Signed-off-by: Hangbin Liu Signed-off-by: Alexei Starovoitov Acked-by: Jesper Dangaard Brouer Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200616103518.2963410-1-liuhangbin@gmail.com --- net/core/xdp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/core/xdp.c b/net/core/xdp.c index 90f44f382115..3c45f99e26d5 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -462,6 +462,7 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) xdpf->len = totsize - metasize; xdpf->headroom = 0; xdpf->metasize = metasize; + xdpf->frame_sz = PAGE_SIZE; xdpf->mem.type = MEM_TYPE_PAGE_ORDER0; xsk_buff_free(xdp); From 99c51064fb06146b3d494b745c947e438a10aaa7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Tue, 16 Jun 2020 16:28:29 +0200 Subject: [PATCH 07/10] devmap: Use bpf_map_area_alloc() for allocating hash buckets MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Syzkaller discovered that creating a hash of type devmap_hash with a large number of entries can hit the memory allocator limit for allocating contiguous memory regions. There's really no reason to use kmalloc_array() directly in the devmap code, so just switch it to the existing bpf_map_area_alloc() function that is used elsewhere. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-by: Xiumei Mu Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200616142829.114173-1-toke@redhat.com --- kernel/bpf/devmap.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 0cbb72cdaf63..5fdbc776a760 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -86,12 +86,13 @@ static DEFINE_PER_CPU(struct list_head, dev_flush_list); static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); -static struct hlist_head *dev_map_create_hash(unsigned int entries) +static struct hlist_head *dev_map_create_hash(unsigned int entries, + int numa_node) { int i; struct hlist_head *hash; - hash = kmalloc_array(entries, sizeof(*hash), GFP_KERNEL); + hash = bpf_map_area_alloc(entries * sizeof(*hash), numa_node); if (hash != NULL) for (i = 0; i < entries; i++) INIT_HLIST_HEAD(&hash[i]); @@ -145,7 +146,8 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) return -EINVAL; if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { - dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets); + dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, + dtab->map.numa_node); if (!dtab->dev_index_head) goto free_charge; @@ -232,7 +234,7 @@ static void dev_map_free(struct bpf_map *map) } } - kfree(dtab->dev_index_head); + bpf_map_area_free(dtab->dev_index_head); } else { for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev; From d8fe449a9c51a37d844ab607e14e2f5c657d3cf2 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 16 Jun 2020 18:04:14 -0700 Subject: [PATCH 08/10] bpf: Don't return EINVAL from {get,set}sockopt when optlen > PAGE_SIZE Attaching to these hooks can break iptables because its optval is usually quite big, or at least bigger than the current PAGE_SIZE limit. David also mentioned some SCTP options can be big (around 256k). For such optvals we expose only the first PAGE_SIZE bytes to the BPF program. BPF program has two options: 1. Set ctx->optlen to 0 to indicate that the BPF's optval should be ignored and the kernel should use original userspace value. 2. Set ctx->optlen to something that's smaller than the PAGE_SIZE. v5: * use ctx->optlen == 0 with trimmed buffer (Alexei Starovoitov) * update the docs accordingly v4: * use temporary buffer to avoid optval == optval_end == NULL; this removes the corner case in the verifier that might assume non-zero PTR_TO_PACKET/PTR_TO_PACKET_END. v3: * don't increase the limit, bypass the argument v2: * proper comments formatting (Jakub Kicinski) Fixes: 0d01da6afc54 ("bpf: implement getsockopt and setsockopt hooks") Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Cc: David Laight Link: https://lore.kernel.org/bpf/20200617010416.93086-1-sdf@google.com --- kernel/bpf/cgroup.c | 53 ++++++++++++++++++++++++++++----------------- 1 file changed, 33 insertions(+), 20 deletions(-) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 4d76f16524cc..ac53102e244a 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1276,16 +1276,23 @@ static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp, static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen) { - if (unlikely(max_optlen > PAGE_SIZE) || max_optlen < 0) + if (unlikely(max_optlen < 0)) return -EINVAL; + if (unlikely(max_optlen > PAGE_SIZE)) { + /* We don't expose optvals that are greater than PAGE_SIZE + * to the BPF program. + */ + max_optlen = PAGE_SIZE; + } + ctx->optval = kzalloc(max_optlen, GFP_USER); if (!ctx->optval) return -ENOMEM; ctx->optval_end = ctx->optval + max_optlen; - return 0; + return max_optlen; } static void sockopt_free_buf(struct bpf_sockopt_kern *ctx) @@ -1319,13 +1326,13 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, */ max_optlen = max_t(int, 16, *optlen); - ret = sockopt_alloc_buf(&ctx, max_optlen); - if (ret) - return ret; + max_optlen = sockopt_alloc_buf(&ctx, max_optlen); + if (max_optlen < 0) + return max_optlen; ctx.optlen = *optlen; - if (copy_from_user(ctx.optval, optval, *optlen) != 0) { + if (copy_from_user(ctx.optval, optval, min(*optlen, max_optlen)) != 0) { ret = -EFAULT; goto out; } @@ -1353,8 +1360,14 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, /* export any potential modifications */ *level = ctx.level; *optname = ctx.optname; - *optlen = ctx.optlen; - *kernel_optval = ctx.optval; + + /* optlen == 0 from BPF indicates that we should + * use original userspace data. + */ + if (ctx.optlen != 0) { + *optlen = ctx.optlen; + *kernel_optval = ctx.optval; + } } out: @@ -1385,12 +1398,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT)) return retval; - ret = sockopt_alloc_buf(&ctx, max_optlen); - if (ret) - return ret; - ctx.optlen = max_optlen; + max_optlen = sockopt_alloc_buf(&ctx, max_optlen); + if (max_optlen < 0) + return max_optlen; + if (!retval) { /* If kernel getsockopt finished successfully, * copy whatever was returned to the user back @@ -1404,10 +1417,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; } - if (ctx.optlen > max_optlen) - ctx.optlen = max_optlen; - - if (copy_from_user(ctx.optval, optval, ctx.optlen) != 0) { + if (copy_from_user(ctx.optval, optval, + min(ctx.optlen, max_optlen)) != 0) { ret = -EFAULT; goto out; } @@ -1436,10 +1447,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; } - if (copy_to_user(optval, ctx.optval, ctx.optlen) || - put_user(ctx.optlen, optlen)) { - ret = -EFAULT; - goto out; + if (ctx.optlen != 0) { + if (copy_to_user(optval, ctx.optval, ctx.optlen) || + put_user(ctx.optlen, optlen)) { + ret = -EFAULT; + goto out; + } } ret = ctx.retval; From a0cb12b03132befbdb29d835ca330c18792e8134 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 16 Jun 2020 18:04:15 -0700 Subject: [PATCH 09/10] 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 --- .../selftests/bpf/prog_tests/sockopt_sk.c | 46 +++++++++++++--- .../testing/selftests/bpf/progs/sockopt_sk.c | 54 ++++++++++++++++++- 2 files changed, 91 insertions(+), 9 deletions(-) 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 */ From 8030e250d882db174cbcd88273570ffb36a13080 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 16 Jun 2020 18:04:16 -0700 Subject: [PATCH 10/10] bpf: Document optval > PAGE_SIZE behavior for sockopt hooks Extend existing doc with more details about requiring ctx->optlen = 0 for handling optval > PAGE_SIZE. Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200617010416.93086-3-sdf@google.com --- Documentation/bpf/prog_cgroup_sockopt.rst | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/Documentation/bpf/prog_cgroup_sockopt.rst b/Documentation/bpf/prog_cgroup_sockopt.rst index c47d974629ae..172f957204bf 100644 --- a/Documentation/bpf/prog_cgroup_sockopt.rst +++ b/Documentation/bpf/prog_cgroup_sockopt.rst @@ -86,6 +86,20 @@ then the next program in the chain (A) will see those changes, *not* the original input ``setsockopt`` arguments. The potentially modified values will be then passed down to the kernel. +Large optval +============ +When the ``optval`` is greater than the ``PAGE_SIZE``, the BPF program +can access only the first ``PAGE_SIZE`` of that data. So it has to options: + +* Set ``optlen`` to zero, which indicates that the kernel should + use the original buffer from the userspace. Any modifications + done by the BPF program to the ``optval`` are ignored. +* Set ``optlen`` to the value less than ``PAGE_SIZE``, which + indicates that the kernel should use BPF's trimmed ``optval``. + +When the BPF program returns with the ``optlen`` greater than +``PAGE_SIZE``, the userspace will receive ``EFAULT`` errno. + Example =======