diff options
| -rw-r--r-- | include/linux/bpf_mem_alloc.h | 3 | ||||
| -rw-r--r-- | kernel/bpf/helpers.c | 54 | ||||
| -rw-r--r-- | kernel/bpf/lpm_trie.c | 2 | ||||
| -rw-r--r-- | kernel/bpf/memalloc.c | 14 | ||||
| -rw-r--r-- | kernel/bpf/verifier.c | 23 | ||||
| -rw-r--r-- | net/bpf/test_run.c | 1 | ||||
| -rw-r--r-- | net/core/sock_map.c | 4 | ||||
| -rw-r--r-- | net/ipv4/tcp_bpf.c | 7 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c | 109 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/progs/verifier_bits_iter.c | 61 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c | 55 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/progs/verifier_search_pruning.c | 23 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/veristat.cfg | 1 |
13 files changed, 269 insertions, 88 deletions
diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index aaf004d94322..e45162ef59bb 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -33,6 +33,9 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size); void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); +/* Check the allocation size for kmalloc equivalent allocator */ +int bpf_mem_alloc_check_size(bool percpu, size_t size); + /* kmalloc/kfree equivalent: */ void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size); void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index ca3f0a2e5ed5..3d45ebe8afb4 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2851,21 +2851,47 @@ struct bpf_iter_bits { __u64 __opaque[2]; } __aligned(8); +#define BITS_ITER_NR_WORDS_MAX 511 + struct bpf_iter_bits_kern { union { - unsigned long *bits; - unsigned long bits_copy; + __u64 *bits; + __u64 bits_copy; }; - u32 nr_bits; + int nr_bits; int bit; } __aligned(8); +/* On 64-bit hosts, unsigned long and u64 have the same size, so passing + * a u64 pointer and an unsigned long pointer to find_next_bit() will + * return the same result, as both point to the same 8-byte area. + * + * For 32-bit little-endian hosts, using a u64 pointer or unsigned long + * pointer also makes no difference. This is because the first iterated + * unsigned long is composed of bits 0-31 of the u64 and the second unsigned + * long is composed of bits 32-63 of the u64. + * + * However, for 32-bit big-endian hosts, this is not the case. The first + * iterated unsigned long will be bits 32-63 of the u64, so swap these two + * ulong values within the u64. + */ +static void swap_ulong_in_u64(u64 *bits, unsigned int nr) +{ +#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN) + unsigned int i; + + for (i = 0; i < nr; i++) + bits[i] = (bits[i] >> 32) | ((u64)(u32)bits[i] << 32); +#endif +} + /** * bpf_iter_bits_new() - Initialize a new bits iterator for a given memory area * @it: The new bpf_iter_bits to be created * @unsafe_ptr__ign: A pointer pointing to a memory area to be iterated over * @nr_words: The size of the specified memory area, measured in 8-byte units. - * Due to the limitation of memalloc, it can't be greater than 512. + * The maximum value of @nr_words is @BITS_ITER_NR_WORDS_MAX. This limit may be + * further reduced by the BPF memory allocator implementation. * * This function initializes a new bpf_iter_bits structure for iterating over * a memory area which is specified by the @unsafe_ptr__ign and @nr_words. It @@ -2892,6 +2918,8 @@ bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w if (!unsafe_ptr__ign || !nr_words) return -EINVAL; + if (nr_words > BITS_ITER_NR_WORDS_MAX) + return -E2BIG; /* Optimization for u64 mask */ if (nr_bits == 64) { @@ -2899,10 +2927,15 @@ bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w if (err) return -EFAULT; + swap_ulong_in_u64(&kit->bits_copy, nr_words); + kit->nr_bits = nr_bits; return 0; } + if (bpf_mem_alloc_check_size(false, nr_bytes)) + return -E2BIG; + /* Fallback to memalloc */ kit->bits = bpf_mem_alloc(&bpf_global_ma, nr_bytes); if (!kit->bits) @@ -2914,6 +2947,8 @@ bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w return err; } + swap_ulong_in_u64(kit->bits, nr_words); + kit->nr_bits = nr_bits; return 0; } @@ -2930,17 +2965,16 @@ bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w __bpf_kfunc int *bpf_iter_bits_next(struct bpf_iter_bits *it) { struct bpf_iter_bits_kern *kit = (void *)it; - u32 nr_bits = kit->nr_bits; - const unsigned long *bits; - int bit; + int bit = kit->bit, nr_bits = kit->nr_bits; + const void *bits; - if (nr_bits == 0) + if (!nr_bits || bit >= nr_bits) return NULL; bits = nr_bits == 64 ? &kit->bits_copy : kit->bits; - bit = find_next_bit(bits, nr_bits, kit->bit + 1); + bit = find_next_bit(bits, nr_bits, bit + 1); if (bit >= nr_bits) { - kit->nr_bits = 0; + kit->bit = bit; return NULL; } diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 0218a5132ab5..9b60eda0f727 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -655,7 +655,7 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) if (!key || key->prefixlen > trie->max_prefixlen) goto find_leftmost; - node_stack = kmalloc_array(trie->max_prefixlen, + node_stack = kmalloc_array(trie->max_prefixlen + 1, sizeof(struct lpm_trie_node *), GFP_ATOMIC | __GFP_NOWARN); if (!node_stack) diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index b3858a76e0b3..146f5b57cfb1 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -35,6 +35,8 @@ */ #define LLIST_NODE_SZ sizeof(struct llist_node) +#define BPF_MEM_ALLOC_SIZE_MAX 4096 + /* similar to kmalloc, but sizeof == 8 bucket is gone */ static u8 size_index[24] __ro_after_init = { 3, /* 8 */ @@ -65,7 +67,7 @@ static u8 size_index[24] __ro_after_init = { static int bpf_mem_cache_idx(size_t size) { - if (!size || size > 4096) + if (!size || size > BPF_MEM_ALLOC_SIZE_MAX) return -1; if (size <= 192) @@ -1005,3 +1007,13 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags) return !ret ? NULL : ret + LLIST_NODE_SZ; } + +int bpf_mem_alloc_check_size(bool percpu, size_t size) +{ + /* The size of percpu allocation doesn't have LLIST_NODE_SZ overhead */ + if ((percpu && size > BPF_MEM_ALLOC_SIZE_MAX) || + (!percpu && size > BPF_MEM_ALLOC_SIZE_MAX - LLIST_NODE_SZ)) + return -E2BIG; + + return 0; +} diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 587a6c76e564..bb99bada7e2e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6804,20 +6804,10 @@ static int check_stack_slot_within_bounds(struct bpf_verifier_env *env, struct bpf_func_state *state, enum bpf_access_type t) { - struct bpf_insn_aux_data *aux = &env->insn_aux_data[env->insn_idx]; - int min_valid_off, max_bpf_stack; - - /* If accessing instruction is a spill/fill from bpf_fastcall pattern, - * add room for all caller saved registers below MAX_BPF_STACK. - * In case if bpf_fastcall rewrite won't happen maximal stack depth - * would be checked by check_max_stack_depth_subprog(). - */ - max_bpf_stack = MAX_BPF_STACK; - if (aux->fastcall_pattern) - max_bpf_stack += CALLER_SAVED_REGS * BPF_REG_SIZE; + int min_valid_off; if (t == BPF_WRITE || env->allow_uninit_stack) - min_valid_off = -max_bpf_stack; + min_valid_off = -MAX_BPF_STACK; else min_valid_off = -state->allocated_stack; @@ -17886,9 +17876,11 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) struct bpf_verifier_state_list *sl, **pprev; struct bpf_verifier_state *cur = env->cur_state, *new, *loop_entry; int i, j, n, err, states_cnt = 0; - bool force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx); - bool add_new_state = force_new_state; - bool force_exact; + bool force_new_state, add_new_state, force_exact; + + force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx) || + /* Avoid accumulating infinitely long jmp history */ + cur->jmp_history_cnt > 40; /* bpf progs typically have pruning point every 4 instructions * http://vger.kernel.org/bpfconf2019.html#session-1 @@ -17898,6 +17890,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * In tests that amounts to up to 50% reduction into total verifier * memory consumption and 20% verifier time speedup. */ + add_new_state = force_new_state; if (env->jmps_processed - env->prev_jmps_processed >= 2 && env->insn_processed - env->prev_insn_processed >= 8) add_new_state = true; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 6d7a442ceb89..501ec4249fed 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -246,6 +246,7 @@ static void reset_ctx(struct xdp_page_head *head) head->ctx.data_meta = head->orig_ctx.data_meta; head->ctx.data_end = head->orig_ctx.data_end; xdp_update_frame_from_buff(&head->ctx, head->frame); + head->frame->mem = head->orig_ctx.rxq->mem; } static int xdp_recv_frames(struct xdp_frame **frames, int nframes, diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 07d6aa4e39ef..78347d7d25ef 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1760,6 +1760,10 @@ static int sock_map_link_update_prog(struct bpf_link *link, ret = -EINVAL; goto out; } + if (!sockmap_link->map) { + ret = -ENOLINK; + goto out; + } ret = sock_map_prog_link_lookup(sockmap_link->map, &pprog, &plink, sockmap_link->attach_type); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index e7658c5d6b79..370993c03d31 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -221,11 +221,11 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, int flags, int *addr_len) { - struct tcp_sock *tcp = tcp_sk(sk); int peek = flags & MSG_PEEK; - u32 seq = tcp->copied_seq; struct sk_psock *psock; + struct tcp_sock *tcp; int copied = 0; + u32 seq; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); @@ -238,7 +238,8 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, return tcp_recvmsg(sk, msg, len, flags, addr_len); lock_sock(sk); - + tcp = tcp_sk(sk); + seq = tcp->copied_seq; /* We may have received data on the sk_receive_queue pre-accept and * then we can not use read_skb in this context because we haven't * assigned a sk_socket yet so have no link to the ops. The work-around diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c new file mode 100644 index 000000000000..0ba015686492 --- /dev/null +++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <linux/bpf.h> +#include <stdio.h> +#include <stdbool.h> +#include <unistd.h> +#include <errno.h> +#include <stdlib.h> +#include <string.h> +#include <pthread.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include <test_maps.h> + +struct test_lpm_key { + __u32 prefix; + __u32 data; +}; + +struct get_next_key_ctx { + struct test_lpm_key key; + bool start; + bool stop; + int map_fd; + int loop; +}; + +static void *get_next_key_fn(void *arg) +{ + struct get_next_key_ctx *ctx = arg; + struct test_lpm_key next_key; + int i = 0; + + while (!ctx->start) + usleep(1); + + while (!ctx->stop && i++ < ctx->loop) + bpf_map_get_next_key(ctx->map_fd, &ctx->key, &next_key); + + return NULL; +} + +static void abort_get_next_key(struct get_next_key_ctx *ctx, pthread_t *tids, + unsigned int nr) +{ + unsigned int i; + + ctx->stop = true; + ctx->start = true; + for (i = 0; i < nr; i++) + pthread_join(tids[i], NULL); +} + +/* This test aims to prevent regression of future. As long as the kernel does + * not panic, it is considered as success. + */ +void test_lpm_trie_map_get_next_key(void) +{ +#define MAX_NR_THREADS 8 + LIBBPF_OPTS(bpf_map_create_opts, create_opts, + .map_flags = BPF_F_NO_PREALLOC); + struct test_lpm_key key = {}; + __u32 val = 0; + int map_fd; + const __u32 max_prefixlen = 8 * (sizeof(key) - sizeof(key.prefix)); + const __u32 max_entries = max_prefixlen + 1; + unsigned int i, nr = MAX_NR_THREADS, loop = 65536; + pthread_t tids[MAX_NR_THREADS]; + struct get_next_key_ctx ctx; + int err; + + map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, "lpm_trie_map", + sizeof(struct test_lpm_key), sizeof(__u32), + max_entries, &create_opts); + CHECK(map_fd == -1, "bpf_map_create()", "error:%s\n", + strerror(errno)); + + for (i = 0; i <= max_prefixlen; i++) { + key.prefix = i; + err = bpf_map_update_elem(map_fd, &key, &val, BPF_ANY); + CHECK(err, "bpf_map_update_elem()", "error:%s\n", + strerror(errno)); + } + + ctx.start = false; + ctx.stop = false; + ctx.map_fd = map_fd; + ctx.loop = loop; + memcpy(&ctx.key, &key, sizeof(key)); + + for (i = 0; i < nr; i++) { + err = pthread_create(&tids[i], NULL, get_next_key_fn, &ctx); + if (err) { + abort_get_next_key(&ctx, tids, i); + CHECK(err, "pthread_create", "error %d\n", err); + } + } + + ctx.start = true; + for (i = 0; i < nr; i++) + pthread_join(tids[i], NULL); + + printf("%s:PASS\n", __func__); + + close(map_fd); +} diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c index f4da4d508ddb..156cc278e2fc 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c +++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c @@ -15,6 +15,8 @@ int bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, int *bpf_iter_bits_next(struct bpf_iter_bits *it) __ksym __weak; void bpf_iter_bits_destroy(struct bpf_iter_bits *it) __ksym __weak; +u64 bits_array[511] = {}; + SEC("iter.s/cgroup") __description("bits iter without destroy") __failure __msg("Unreleased reference") @@ -110,16 +112,16 @@ int bit_index(void) } SEC("syscall") -__description("bits nomem") +__description("bits too big") __success __retval(0) -int bits_nomem(void) +int bits_too_big(void) { u64 data[4]; int nr = 0; int *bit; __builtin_memset(&data, 0xff, sizeof(data)); - bpf_for_each(bits, bit, &data[0], 513) /* Be greater than 512 */ + bpf_for_each(bits, bit, &data[0], 512) /* Be greater than 511 */ nr++; return nr; } @@ -151,3 +153,56 @@ int zero_words(void) nr++; return nr; } + +SEC("syscall") +__description("huge words") +__success __retval(0) +int huge_words(void) +{ + u64 data[8] = {0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1}; + int nr = 0; + int *bit; + + bpf_for_each(bits, bit, &data[0], 67108865) + nr++; + return nr; +} + +SEC("syscall") +__description("max words") +__success __retval(4) +int max_words(void) +{ + volatile int nr = 0; + int *bit; + + bits_array[0] = (1ULL << 63) | 1U; + bits_array[510] = (1ULL << 33) | (1ULL << 32); + + bpf_for_each(bits, bit, bits_array, 511) { + if (nr == 0 && *bit != 0) + break; + if (nr == 2 && *bit != 32672) + break; + nr++; + } + return nr; +} + +SEC("syscall") +__description("bad words") +__success __retval(0) +int bad_words(void) +{ + void *bad_addr = (void *)(3UL << 30); + int nr = 0; + int *bit; + + bpf_for_each(bits, bit, bad_addr, 1) + nr++; + + bpf_for_each(bits, bit, bad_addr, 4) + nr++; + + return nr; +} diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c index 9da97d2efcd9..5094c288cfd7 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c +++ b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c @@ -790,61 +790,6 @@ __naked static void cumulative_stack_depth_subprog(void) :: __imm(bpf_get_smp_processor_id) : __clobber_all); } -SEC("raw_tp") -__arch_x86_64 -__log_level(4) -__msg("stack depth 512") -__xlated("0: r1 = 42") -__xlated("1: *(u64 *)(r10 -512) = r1") -__xlated("2: w0 = ") -__xlated("3: r0 = &(void __percpu *)(r0)") -__xlated("4: r0 = *(u32 *)(r0 +0)") -__xlated("5: exit") -__success -__naked int bpf_fastcall_max_stack_ok(void) -{ - asm volatile( - "r1 = 42;" - "*(u64 *)(r10 - %[max_bpf_stack]) = r1;" - "*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;" - "call %[bpf_get_smp_processor_id];" - "r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);" - "exit;" - : - : __imm_const(max_bpf_stack, MAX_BPF_STACK), - __imm_const(max_bpf_stack_8, MAX_BPF_STACK + 8), - __imm(bpf_get_smp_processor_id) - : __clobber_all - ); -} - -SEC("raw_tp") -__arch_x86_64 -__log_level(4) -__msg("stack depth 520") -__failure -__naked int bpf_fastcall_max_stack_fail(void) -{ - asm volatile( - "r1 = 42;" - "*(u64 *)(r10 - %[max_bpf_stack]) = r1;" - "*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;" - "call %[bpf_get_smp_processor_id];" - "r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);" - /* call to prandom blocks bpf_fastcall rewrite */ - "*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;" - "call %[bpf_get_prandom_u32];" - "r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);" - "exit;" - : - : __imm_const(max_bpf_stack, MAX_BPF_STACK), - __imm_const(max_bpf_stack_8, MAX_BPF_STACK + 8), - __imm(bpf_get_smp_processor_id), - __imm(bpf_get_prandom_u32) - : __clobber_all - ); -} - SEC("cgroup/getsockname_unix") __xlated("0: r2 = 1") /* bpf_cast_to_kern_ctx is replaced by a single assignment */ diff --git a/tools/testing/selftests/bpf/progs/verifier_search_pruning.c b/tools/testing/selftests/bpf/progs/verifier_search_pruning.c index 5a14498d352f..f40e57251e94 100644 --- a/tools/testing/selftests/bpf/progs/verifier_search_pruning.c +++ b/tools/testing/selftests/bpf/progs/verifier_search_pruning.c @@ -2,6 +2,7 @@ /* Converted from tools/testing/selftests/bpf/verifier/search_pruning.c */ #include <linux/bpf.h> +#include <../../../include/linux/filter.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" @@ -336,4 +337,26 @@ l0_%=: r1 = 42; \ : __clobber_all); } +/* Without checkpoint forcibly inserted at the back-edge a loop this + * test would take a very long time to verify. + */ +SEC("kprobe") +__failure __log_level(4) +__msg("BPF program is too large.") +__naked void short_loop1(void) +{ + asm volatile ( + " r7 = *(u16 *)(r1 +0);" + "1: r7 += 0x1ab064b9;" + " .8byte %[jset];" /* same as 'if r7 & 0x702000 goto 1b;' */ + " r7 &= 0x1ee60e;" + " r7 += r1;" + " if r7 s> 0x37d2 goto +0;" + " r0 = 0;" + " exit;" + : + : __imm_insn(jset, BPF_JMP_IMM(BPF_JSET, BPF_REG_7, 0x702000, -2)) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/veristat.cfg b/tools/testing/selftests/bpf/veristat.cfg index 1a385061618d..e661ffdcaadf 100644 --- a/tools/testing/selftests/bpf/veristat.cfg +++ b/tools/testing/selftests/bpf/veristat.cfg @@ -15,3 +15,4 @@ test_usdt* test_verif_scale* test_xdp_noinline* xdp_synproxy* +verifier_search_pruning* |