diff options
author | David S. Miller <davem@davemloft.net> | 2020-02-08 15:01:03 +0100 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2020-02-08 15:01:03 +0100 |
commit | 2696e1146d3490f1af4b0080955bf1628bd8ab85 (patch) | |
tree | 54f7e295c3cff749a399f37d55b54022e5a48194 | |
parent | dfa7f709596be5ca46c070d4f8acbb344322056a (diff) | |
parent | 88d6f130e5632bbf419a2e184ec7adcbe241260b (diff) | |
download | linux-2696e1146d3490f1af4b0080955bf1628bd8ab85.tar.gz linux-2696e1146d3490f1af4b0080955bf1628bd8ab85.tar.bz2 linux-2696e1146d3490f1af4b0080955bf1628bd8ab85.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf
Daniel Borkmann says:
====================
pull-request: bpf 2020-02-07
The following pull-request contains BPF updates for your *net* tree.
We've added 15 non-merge commits during the last 10 day(s) which contain
a total of 12 files changed, 114 insertions(+), 31 deletions(-).
The main changes are:
1) Various BPF sockmap fixes related to RCU handling in the map's tear-
down code, from Jakub Sitnicki.
2) Fix macro state explosion in BPF sk_storage map when calculating its
bucket_log on allocation, from Martin KaFai Lau.
3) Fix potential BPF sockmap update race by rechecking socket's established
state under lock, from Lorenz Bauer.
4) Fix crash in bpftool on missing xlated instructions when kptr_restrict
sysctl is set, from Toke Høiland-Jørgensen.
5) Fix i40e's XSK wakeup code to return proper error in busy state and
various misc fixes in xdpsock BPF sample code, from Maciej Fijalkowski.
6) Fix the way modifiers are skipped in BTF in the verifier while walking
pointers to avoid program rejection, from Alexei Starovoitov.
7) Fix Makefile for runqslower BPF tool to i) rebuild on libbpf changes and
ii) to fix undefined reference linker errors for older gcc version due to
order of passed gcc parameters, from Yulia Kartseva and Song Liu.
8) Fix a trampoline_count BPF kselftest warning about missing braces around
initializer, from Andrii Nakryiko.
9) Fix up redundant "HAVE" prefix from large INSN limit kernel probe in
bpftool, from Michal Rostecki.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r-- | drivers/net/ethernet/intel/i40e/i40e_xsk.c | 2 | ||||
-rw-r--r-- | include/linux/bpf.h | 7 | ||||
-rw-r--r-- | kernel/bpf/bpf_struct_ops.c | 5 | ||||
-rw-r--r-- | kernel/bpf/btf.c | 10 | ||||
-rw-r--r-- | net/core/bpf_sk_storage.c | 5 | ||||
-rw-r--r-- | net/core/sock_map.c | 28 | ||||
-rw-r--r-- | samples/bpf/xdpsock_user.c | 4 | ||||
-rw-r--r-- | tools/bpf/bpftool/feature.c | 2 | ||||
-rw-r--r-- | tools/bpf/bpftool/prog.c | 2 | ||||
-rw-r--r-- | tools/bpf/runqslower/Makefile | 4 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/prog_tests/sockmap_basic.c | 74 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/prog_tests/trampoline_count.c | 2 |
12 files changed, 114 insertions, 31 deletions
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 42058fad6a3c..0b7d29192b2c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -791,7 +791,7 @@ int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) struct i40e_ring *ring; if (test_bit(__I40E_CONFIG_BUSY, pf->state)) - return -ENETDOWN; + return -EAGAIN; if (test_bit(__I40E_VSI_DOWN, vsi->state)) return -ENETDOWN; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8e9ad3943cd9..49b1a70e12c8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -728,7 +728,7 @@ struct bpf_struct_ops { #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id); -void bpf_struct_ops_init(struct btf *btf); +void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log); bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, @@ -752,7 +752,10 @@ static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) { return NULL; } -static inline void bpf_struct_ops_init(struct btf *btf) { } +static inline void bpf_struct_ops_init(struct btf *btf, + struct bpf_verifier_log *log) +{ +} static inline bool bpf_try_module_get(const void *data, struct module *owner) { return try_module_get(owner); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 8ad1c9ea26b2..042f95534f86 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -96,12 +96,11 @@ const struct bpf_prog_ops bpf_struct_ops_prog_ops = { static const struct btf_type *module_type; -void bpf_struct_ops_init(struct btf *btf) +void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) { s32 type_id, value_id, module_id; const struct btf_member *member; struct bpf_struct_ops *st_ops; - struct bpf_verifier_log log = {}; const struct btf_type *t; char value_name[128]; const char *mname; @@ -172,7 +171,7 @@ void bpf_struct_ops_init(struct btf *btf) member->type, NULL); if (func_proto && - btf_distill_func_proto(&log, btf, + btf_distill_func_proto(log, btf, func_proto, mname, &st_ops->func_models[j])) { pr_warn("Error in parsing func ptr %s in struct %s\n", diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index b7c1660fb594..805c43b083e9 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3643,7 +3643,7 @@ struct btf *btf_parse_vmlinux(void) goto errout; } - bpf_struct_ops_init(btf); + bpf_struct_ops_init(btf, log); btf_verifier_env_free(env); refcount_set(&btf->refcnt, 1); @@ -3931,6 +3931,7 @@ again: if (btf_type_is_ptr(mtype)) { const struct btf_type *stype; + u32 id; if (msize != size || off != moff) { bpf_log(log, @@ -3939,12 +3940,9 @@ again: return -EACCES; } - stype = btf_type_by_id(btf_vmlinux, mtype->type); - /* skip modifiers */ - while (btf_type_is_modifier(stype)) - stype = btf_type_by_id(btf_vmlinux, stype->type); + stype = btf_type_skip_modifiers(btf_vmlinux, mtype->type, &id); if (btf_type_is_struct(stype)) { - *next_btf_id = mtype->type; + *next_btf_id = id; return PTR_TO_BTF_ID; } } diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 458be6b3eda9..3ab23f698221 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -643,9 +643,10 @@ static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&smap->map, attr); + nbuckets = roundup_pow_of_two(num_possible_cpus()); /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ - smap->bucket_log = max_t(u32, 1, ilog2(roundup_pow_of_two(num_possible_cpus()))); - nbuckets = 1U << smap->bucket_log; + nbuckets = max_t(u32, 2, nbuckets); + smap->bucket_log = ilog2(nbuckets); cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap); ret = bpf_map_charge_init(&smap->map.memory, cost); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 8998e356f423..085cef5857bb 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -234,7 +234,6 @@ static void sock_map_free(struct bpf_map *map) int i; synchronize_rcu(); - rcu_read_lock(); raw_spin_lock_bh(&stab->lock); for (i = 0; i < stab->map.max_entries; i++) { struct sock **psk = &stab->sks[i]; @@ -243,13 +242,15 @@ static void sock_map_free(struct bpf_map *map) sk = xchg(psk, NULL); if (sk) { lock_sock(sk); + rcu_read_lock(); sock_map_unref(sk, psk); + rcu_read_unlock(); release_sock(sk); } } raw_spin_unlock_bh(&stab->lock); - rcu_read_unlock(); + /* wait for psock readers accessing its map link */ synchronize_rcu(); bpf_map_area_free(stab->sks); @@ -416,14 +417,16 @@ static int sock_map_update_elem(struct bpf_map *map, void *key, ret = -EINVAL; goto out; } - if (!sock_map_sk_is_suitable(sk) || - sk->sk_state != TCP_ESTABLISHED) { + if (!sock_map_sk_is_suitable(sk)) { ret = -EOPNOTSUPP; goto out; } sock_map_sk_acquire(sk); - ret = sock_map_update_common(map, idx, sk, flags); + if (sk->sk_state != TCP_ESTABLISHED) + ret = -EOPNOTSUPP; + else + ret = sock_map_update_common(map, idx, sk, flags); sock_map_sk_release(sk); out: fput(sock->file); @@ -739,14 +742,16 @@ static int sock_hash_update_elem(struct bpf_map *map, void *key, ret = -EINVAL; goto out; } - if (!sock_map_sk_is_suitable(sk) || - sk->sk_state != TCP_ESTABLISHED) { + if (!sock_map_sk_is_suitable(sk)) { ret = -EOPNOTSUPP; goto out; } sock_map_sk_acquire(sk); - ret = sock_hash_update_common(map, key, sk, flags); + if (sk->sk_state != TCP_ESTABLISHED) + ret = -EOPNOTSUPP; + else + ret = sock_hash_update_common(map, key, sk, flags); sock_map_sk_release(sk); out: fput(sock->file); @@ -859,19 +864,22 @@ static void sock_hash_free(struct bpf_map *map) int i; synchronize_rcu(); - rcu_read_lock(); for (i = 0; i < htab->buckets_num; i++) { bucket = sock_hash_select_bucket(htab, i); raw_spin_lock_bh(&bucket->lock); hlist_for_each_entry_safe(elem, node, &bucket->head, node) { hlist_del_rcu(&elem->node); lock_sock(elem->sk); + rcu_read_lock(); sock_map_unref(elem->sk, elem); + rcu_read_unlock(); release_sock(elem->sk); } raw_spin_unlock_bh(&bucket->lock); } - rcu_read_unlock(); + + /* wait for psock readers accessing its map link */ + synchronize_rcu(); bpf_map_area_free(htab->buckets); kfree(htab); diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 0b5acd722306..c91e91362a0c 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -83,7 +83,6 @@ static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP; static u32 opt_umem_flags; static int opt_unaligned_chunks; static int opt_mmap_flags; -static u32 opt_xdp_bind_flags; static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; static int opt_timeout = 1000; static bool opt_need_wakeup = true; @@ -789,7 +788,8 @@ static void kick_tx(struct xsk_socket_info *xsk) int ret; ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); - if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN || errno == EBUSY) + if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN || + errno == EBUSY || errno == ENETDOWN) return; exit_with_error(errno); } diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 446ba891f1e2..941873d778d8 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -580,7 +580,7 @@ probe_large_insn_limit(const char *define_prefix, __u32 ifindex) res = bpf_probe_large_insn_limit(ifindex); print_bool_feature("have_large_insn_limit", "Large program size limit", - "HAVE_LARGE_INSN_LIMIT", + "LARGE_INSN_LIMIT", res, define_prefix); } diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index a3521deca869..b352ab041160 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -536,7 +536,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, buf = (unsigned char *)(info->jited_prog_insns); member_len = info->jited_prog_len; } else { /* DUMP_XLATED */ - if (info->xlated_prog_len == 0) { + if (info->xlated_prog_len == 0 || !info->xlated_prog_insns) { p_err("error retrieving insn dump: kernel.kptr_restrict set?"); return -1; } diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile index 0c021352beed..39edd68afa8e 100644 --- a/tools/bpf/runqslower/Makefile +++ b/tools/bpf/runqslower/Makefile @@ -41,7 +41,7 @@ clean: $(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ) $(call msg,BINARY,$@) - $(Q)$(CC) $(CFLAGS) -lelf -lz $^ -o $@ + $(Q)$(CC) $(CFLAGS) $^ -lelf -lz -o $@ $(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h \ $(OUTPUT)/runqslower.bpf.o @@ -75,7 +75,7 @@ $(OUTPUT)/vmlinux.h: $(VMLINUX_BTF_PATH) | $(OUTPUT) $(BPFTOOL) fi $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF_PATH) format c > $@ -$(BPFOBJ): | $(OUTPUT) +$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT) $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) \ OUTPUT=$(abspath $(dir $@))/ $(abspath $@) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c new file mode 100644 index 000000000000..07f5b462c2ef --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Cloudflare + +#include "test_progs.h" + +static int connected_socket_v4(void) +{ + struct sockaddr_in addr = { + .sin_family = AF_INET, + .sin_port = htons(80), + .sin_addr = { inet_addr("127.0.0.1") }, + }; + socklen_t len = sizeof(addr); + int s, repair, err; + + s = socket(AF_INET, SOCK_STREAM, 0); + if (CHECK_FAIL(s == -1)) + goto error; + + repair = TCP_REPAIR_ON; + err = setsockopt(s, SOL_TCP, TCP_REPAIR, &repair, sizeof(repair)); + if (CHECK_FAIL(err)) + goto error; + + err = connect(s, (struct sockaddr *)&addr, len); + if (CHECK_FAIL(err)) + goto error; + + repair = TCP_REPAIR_OFF_NO_WP; + err = setsockopt(s, SOL_TCP, TCP_REPAIR, &repair, sizeof(repair)); + if (CHECK_FAIL(err)) + goto error; + + return s; +error: + perror(__func__); + close(s); + return -1; +} + +/* Create a map, populate it with one socket, and free the map. */ +static void test_sockmap_create_update_free(enum bpf_map_type map_type) +{ + const int zero = 0; + int s, map, err; + + s = connected_socket_v4(); + if (CHECK_FAIL(s == -1)) + return; + + map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0); + if (CHECK_FAIL(map == -1)) { + perror("bpf_create_map"); + goto out; + } + + err = bpf_map_update_elem(map, &zero, &s, BPF_NOEXIST); + if (CHECK_FAIL(err)) { + perror("bpf_map_update"); + goto out; + } + +out: + close(map); + close(s); +} + +void test_sockmap_basic(void) +{ + if (test__start_subtest("sockmap create_update_free")) + test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKMAP); + if (test__start_subtest("sockhash create_update_free")) + test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKHASH); +} diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c index 1235f3d1cc50..1f6ccdaed1ac 100644 --- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c +++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c @@ -46,7 +46,7 @@ void test_trampoline_count(void) const char *fentry_name = "fentry/__set_task_comm"; const char *fexit_name = "fexit/__set_task_comm"; const char *object = "test_trampoline_count.o"; - struct inst inst[MAX_TRAMP_PROGS] = { 0 }; + struct inst inst[MAX_TRAMP_PROGS] = {}; int err, i = 0, duration = 0; struct bpf_object *obj; struct bpf_link *link; |