diff options
Diffstat (limited to 'kernel/bpf')
-rw-r--r-- | kernel/bpf/arraymap.c | 28 | ||||
-rw-r--r-- | kernel/bpf/bloom_filter.c | 12 | ||||
-rw-r--r-- | kernel/bpf/bpf_cgrp_storage.c | 1 | ||||
-rw-r--r-- | kernel/bpf/bpf_inode_storage.c | 1 | ||||
-rw-r--r-- | kernel/bpf/bpf_local_storage.c | 95 | ||||
-rw-r--r-- | kernel/bpf/bpf_struct_ops.c | 16 | ||||
-rw-r--r-- | kernel/bpf/bpf_task_storage.c | 1 | ||||
-rw-r--r-- | kernel/bpf/btf.c | 42 | ||||
-rw-r--r-- | kernel/bpf/cgroup.c | 53 | ||||
-rw-r--r-- | kernel/bpf/cpumap.c | 10 | ||||
-rw-r--r-- | kernel/bpf/cpumask.c | 46 | ||||
-rw-r--r-- | kernel/bpf/devmap.c | 26 | ||||
-rw-r--r-- | kernel/bpf/hashtab.c | 102 | ||||
-rw-r--r-- | kernel/bpf/helpers.c | 257 | ||||
-rw-r--r-- | kernel/bpf/local_storage.c | 7 | ||||
-rw-r--r-- | kernel/bpf/lpm_trie.c | 11 | ||||
-rw-r--r-- | kernel/bpf/offload.c | 6 | ||||
-rw-r--r-- | kernel/bpf/queue_stack_maps.c | 10 | ||||
-rw-r--r-- | kernel/bpf/reuseport_array.c | 8 | ||||
-rw-r--r-- | kernel/bpf/ringbuf.c | 20 | ||||
-rw-r--r-- | kernel/bpf/stackmap.c | 14 | ||||
-rw-r--r-- | kernel/bpf/syscall.c | 28 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 963 |
23 files changed, 1343 insertions, 414 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 484706959556..1588c793a715 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -721,6 +721,28 @@ static int bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_ return num_elems; } +static u64 array_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + bool percpu = map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; + u32 elem_size = array->elem_size; + u64 entries = map->max_entries; + u64 usage = sizeof(*array); + + if (percpu) { + usage += entries * sizeof(void *); + usage += entries * elem_size * num_possible_cpus(); + } else { + if (map->map_flags & BPF_F_MMAPABLE) { + usage = PAGE_ALIGN(usage); + usage += PAGE_ALIGN(entries * elem_size); + } else { + usage += entries * elem_size; + } + } + return usage; +} + BTF_ID_LIST_SINGLE(array_map_btf_ids, struct, bpf_array) const struct bpf_map_ops array_map_ops = { .map_meta_equal = array_map_meta_equal, @@ -742,6 +764,7 @@ const struct bpf_map_ops array_map_ops = { .map_update_batch = generic_map_update_batch, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_array_elem, + .map_mem_usage = array_map_mem_usage, .map_btf_id = &array_map_btf_ids[0], .iter_seq_info = &iter_seq_info, }; @@ -762,6 +785,7 @@ const struct bpf_map_ops percpu_array_map_ops = { .map_update_batch = generic_map_update_batch, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_array_elem, + .map_mem_usage = array_map_mem_usage, .map_btf_id = &array_map_btf_ids[0], .iter_seq_info = &iter_seq_info, }; @@ -1156,6 +1180,7 @@ const struct bpf_map_ops prog_array_map_ops = { .map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem, .map_release_uref = prog_array_map_clear, .map_seq_show_elem = prog_array_map_seq_show_elem, + .map_mem_usage = array_map_mem_usage, .map_btf_id = &array_map_btf_ids[0], }; @@ -1257,6 +1282,7 @@ const struct bpf_map_ops perf_event_array_map_ops = { .map_fd_put_ptr = perf_event_fd_array_put_ptr, .map_release = perf_event_fd_array_release, .map_check_btf = map_check_no_btf, + .map_mem_usage = array_map_mem_usage, .map_btf_id = &array_map_btf_ids[0], }; @@ -1291,6 +1317,7 @@ const struct bpf_map_ops cgroup_array_map_ops = { .map_fd_get_ptr = cgroup_fd_array_get_ptr, .map_fd_put_ptr = cgroup_fd_array_put_ptr, .map_check_btf = map_check_no_btf, + .map_mem_usage = array_map_mem_usage, .map_btf_id = &array_map_btf_ids[0], }; #endif @@ -1379,5 +1406,6 @@ const struct bpf_map_ops array_of_maps_map_ops = { .map_lookup_batch = generic_map_lookup_batch, .map_update_batch = generic_map_update_batch, .map_check_btf = map_check_no_btf, + .map_mem_usage = array_map_mem_usage, .map_btf_id = &array_map_btf_ids[0], }; diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index 48ee750849f2..6350c5d35a9b 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -193,6 +193,17 @@ static int bloom_map_check_btf(const struct bpf_map *map, return btf_type_is_void(key_type) ? 0 : -EINVAL; } +static u64 bloom_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_bloom_filter *bloom; + u64 bitset_bytes; + + bloom = container_of(map, struct bpf_bloom_filter, map); + bitset_bytes = BITS_TO_BYTES((u64)bloom->bitset_mask + 1); + bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long)); + return sizeof(*bloom) + bitset_bytes; +} + BTF_ID_LIST_SINGLE(bpf_bloom_map_btf_ids, struct, bpf_bloom_filter) const struct bpf_map_ops bloom_filter_map_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -206,5 +217,6 @@ const struct bpf_map_ops bloom_filter_map_ops = { .map_update_elem = bloom_map_update_elem, .map_delete_elem = bloom_map_delete_elem, .map_check_btf = bloom_map_check_btf, + .map_mem_usage = bloom_map_mem_usage, .map_btf_id = &bpf_bloom_map_btf_ids[0], }; diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c index 6cdf6d9ed91d..9ae07aedaf23 100644 --- a/kernel/bpf/bpf_cgrp_storage.c +++ b/kernel/bpf/bpf_cgrp_storage.c @@ -221,6 +221,7 @@ const struct bpf_map_ops cgrp_storage_map_ops = { .map_update_elem = bpf_cgrp_storage_update_elem, .map_delete_elem = bpf_cgrp_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, + .map_mem_usage = bpf_local_storage_map_mem_usage, .map_btf_id = &bpf_local_storage_map_btf_id[0], .map_owner_storage_ptr = cgroup_storage_ptr, }; diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 05f4c66c9089..43e2619c8167 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -223,6 +223,7 @@ const struct bpf_map_ops inode_storage_map_ops = { .map_update_elem = bpf_fd_inode_storage_update_elem, .map_delete_elem = bpf_fd_inode_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, + .map_mem_usage = bpf_local_storage_map_mem_usage, .map_btf_id = &bpf_local_storage_map_btf_id[0], .map_owner_storage_ptr = inode_storage_ptr, }; diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 35f4138a54dc..d3ba3f2db640 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -51,11 +51,21 @@ owner_storage(struct bpf_local_storage_map *smap, void *owner) return map->ops->map_owner_storage_ptr(owner); } +static bool selem_linked_to_storage_lockless(const struct bpf_local_storage_elem *selem) +{ + return !hlist_unhashed_lockless(&selem->snode); +} + static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->snode); } +static bool selem_linked_to_map_lockless(const struct bpf_local_storage_elem *selem) +{ + return !hlist_unhashed_lockless(&selem->map_node); +} + static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->map_node); @@ -75,6 +85,7 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, if (selem) { if (value) copy_map_value(&smap->map, SDATA(selem)->data, value); + /* No need to call check_and_init_map_value as memory is zero init */ return selem; } @@ -98,7 +109,28 @@ void bpf_local_storage_free_rcu(struct rcu_head *rcu) kfree_rcu(local_storage, rcu); } -static void bpf_selem_free_rcu(struct rcu_head *rcu) +static void bpf_selem_free_fields_rcu(struct rcu_head *rcu) +{ + struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map *smap; + + selem = container_of(rcu, struct bpf_local_storage_elem, rcu); + /* protected by the rcu_barrier*() */ + smap = rcu_dereference_protected(SDATA(selem)->smap, true); + bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); + kfree(selem); +} + +static void bpf_selem_free_fields_trace_rcu(struct rcu_head *rcu) +{ + /* Free directly if Tasks Trace RCU GP also implies RCU GP */ + if (rcu_trace_implies_rcu_gp()) + bpf_selem_free_fields_rcu(rcu); + else + call_rcu(rcu, bpf_selem_free_fields_rcu); +} + +static void bpf_selem_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage_elem *selem; @@ -119,6 +151,7 @@ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_stor { struct bpf_local_storage_map *smap; bool free_local_storage; + struct btf_record *rec; void *owner; smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); @@ -159,10 +192,26 @@ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_stor SDATA(selem)) RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); - if (use_trace_rcu) - call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_rcu); - else - kfree_rcu(selem, rcu); + /* A different RCU callback is chosen whenever we need to free + * additional fields in selem data before freeing selem. + * bpf_local_storage_map_free only executes rcu_barrier to wait for RCU + * callbacks when it has special fields, hence we can only conditionally + * dereference smap, as by this time the map might have already been + * freed without waiting for our call_rcu callback if it did not have + * any special fields. + */ + rec = smap->map.record; + if (use_trace_rcu) { + if (!IS_ERR_OR_NULL(rec)) + call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_fields_trace_rcu); + else + call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_trace_rcu); + } else { + if (!IS_ERR_OR_NULL(rec)) + call_rcu(&selem->rcu, bpf_selem_free_fields_rcu); + else + kfree_rcu(selem, rcu); + } return free_local_storage; } @@ -174,7 +223,7 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem, bool free_local_storage = false; unsigned long flags; - if (unlikely(!selem_linked_to_storage(selem))) + if (unlikely(!selem_linked_to_storage_lockless(selem))) /* selem has already been unlinked from sk */ return; @@ -208,7 +257,7 @@ void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) struct bpf_local_storage_map_bucket *b; unsigned long flags; - if (unlikely(!selem_linked_to_map(selem))) + if (unlikely(!selem_linked_to_map_lockless(selem))) /* selem has already be unlinked from smap */ return; @@ -420,7 +469,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, err = check_flags(old_sdata, map_flags); if (err) return ERR_PTR(err); - if (old_sdata && selem_linked_to_storage(SELEM(old_sdata))) { + if (old_sdata && selem_linked_to_storage_lockless(SELEM(old_sdata))) { copy_map_value_locked(&smap->map, old_sdata->data, value, false); return old_sdata; @@ -636,6 +685,16 @@ bool bpf_local_storage_unlink_nolock(struct bpf_local_storage *local_storage) return free_storage; } +u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_local_storage_map *smap = (struct bpf_local_storage_map *)map; + u64 usage = sizeof(*smap); + + /* The dynamically callocated selems are not counted currently. */ + usage += sizeof(*smap->buckets) * (1ULL << smap->bucket_log); + return usage; +} + struct bpf_map * bpf_local_storage_map_alloc(union bpf_attr *attr, struct bpf_local_storage_cache *cache) @@ -713,6 +772,26 @@ void bpf_local_storage_map_free(struct bpf_map *map, */ synchronize_rcu(); + /* Only delay freeing of smap, buckets are not needed anymore */ kvfree(smap->buckets); + + /* When local storage has special fields, callbacks for + * bpf_selem_free_fields_rcu and bpf_selem_free_fields_trace_rcu will + * keep using the map BTF record, we need to execute an RCU barrier to + * wait for them as the record will be freed right after our map_free + * callback. + */ + if (!IS_ERR_OR_NULL(smap->map.record)) { + rcu_barrier_tasks_trace(); + /* We cannot skip rcu_barrier() when rcu_trace_implies_rcu_gp() + * is true, because while call_rcu invocation is skipped in that + * case in bpf_selem_free_fields_trace_rcu (and all local + * storage maps pass use_trace_rcu = true), there can be + * call_rcu callbacks based on use_trace_rcu = false in the + * while ((selem = ...)) loop above or when owner's free path + * calls bpf_local_storage_unlink_nolock. + */ + rcu_barrier(); + } bpf_map_area_free(smap); } diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index ece9870cab68..38903fb52f98 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -641,6 +641,21 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) return map; } +static u64 bpf_struct_ops_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + const struct bpf_struct_ops *st_ops = st_map->st_ops; + const struct btf_type *vt = st_ops->value_type; + u64 usage; + + usage = sizeof(*st_map) + + vt->size - sizeof(struct bpf_struct_ops_value); + usage += vt->size; + usage += btf_type_vlen(vt) * sizeof(struct bpf_links *); + usage += PAGE_SIZE; + return usage; +} + BTF_ID_LIST_SINGLE(bpf_struct_ops_map_btf_ids, struct, bpf_struct_ops_map) const struct bpf_map_ops bpf_struct_ops_map_ops = { .map_alloc_check = bpf_struct_ops_map_alloc_check, @@ -651,6 +666,7 @@ const struct bpf_map_ops bpf_struct_ops_map_ops = { .map_delete_elem = bpf_struct_ops_map_delete_elem, .map_update_elem = bpf_struct_ops_map_update_elem, .map_seq_show_elem = bpf_struct_ops_map_seq_show_elem, + .map_mem_usage = bpf_struct_ops_map_mem_usage, .map_btf_id = &bpf_struct_ops_map_btf_ids[0], }; diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index 1e486055a523..20f942229f3c 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -335,6 +335,7 @@ const struct bpf_map_ops task_storage_map_ops = { .map_update_elem = bpf_pid_task_storage_update_elem, .map_delete_elem = bpf_pid_task_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, + .map_mem_usage = bpf_local_storage_map_mem_usage, .map_btf_id = &bpf_local_storage_map_btf_id[0], .map_owner_storage_ptr = task_storage_ptr, }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 73780748404c..1853beaed4be 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -207,6 +207,11 @@ enum btf_kfunc_hook { BTF_KFUNC_HOOK_TRACING, BTF_KFUNC_HOOK_SYSCALL, BTF_KFUNC_HOOK_FMODRET, + BTF_KFUNC_HOOK_CGROUP_SKB, + BTF_KFUNC_HOOK_SCHED_ACT, + BTF_KFUNC_HOOK_SK_SKB, + BTF_KFUNC_HOOK_SOCKET_FILTER, + BTF_KFUNC_HOOK_LWT, BTF_KFUNC_HOOK_MAX, }; @@ -3283,9 +3288,9 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, /* Reject extra tags */ if (btf_type_is_type_tag(btf_type_by_id(btf, t->type))) return -EINVAL; - if (!strcmp("kptr", __btf_name_by_offset(btf, t->name_off))) + if (!strcmp("kptr_untrusted", __btf_name_by_offset(btf, t->name_off))) type = BPF_KPTR_UNREF; - else if (!strcmp("kptr_ref", __btf_name_by_offset(btf, t->name_off))) + else if (!strcmp("kptr", __btf_name_by_offset(btf, t->name_off))) type = BPF_KPTR_REF; else return -EINVAL; @@ -5684,6 +5689,10 @@ again: * int socket_filter_bpf_prog(struct __sk_buff *skb) * { // no fields of skb are ever used } */ + if (strcmp(ctx_tname, "__sk_buff") == 0 && strcmp(tname, "sk_buff") == 0) + return ctx_type; + if (strcmp(ctx_tname, "xdp_md") == 0 && strcmp(tname, "xdp_buff") == 0) + return ctx_type; if (strcmp(ctx_tname, tname)) { /* bpf_user_pt_regs_t is a typedef, so resolve it to * underlying struct and check name again @@ -6155,6 +6164,7 @@ static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf, const char *tname, *mname, *tag_value; u32 vlen, elem_id, mid; + *flag = 0; again: tname = __btf_name_by_offset(btf, t->name_off); if (!btf_type_is_struct(t)) { @@ -6321,6 +6331,15 @@ error: * of this field or inside of this struct */ if (btf_type_is_struct(mtype)) { + if (BTF_INFO_KIND(mtype->info) == BTF_KIND_UNION && + btf_type_vlen(mtype) != 1) + /* + * walking unions yields untrusted pointers + * with exception of __bpf_md_ptr and other + * unions with a single member + */ + *flag |= PTR_UNTRUSTED; + /* our field must be inside that union or struct */ t = mtype; @@ -6365,7 +6384,7 @@ error: stype = btf_type_skip_modifiers(btf, mtype->type, &id); if (btf_type_is_struct(stype)) { *next_btf_id = id; - *flag = tmp_flag; + *flag |= tmp_flag; return WALK_PTR; } } @@ -7705,6 +7724,19 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type) return BTF_KFUNC_HOOK_TRACING; case BPF_PROG_TYPE_SYSCALL: return BTF_KFUNC_HOOK_SYSCALL; + case BPF_PROG_TYPE_CGROUP_SKB: + return BTF_KFUNC_HOOK_CGROUP_SKB; + case BPF_PROG_TYPE_SCHED_ACT: + return BTF_KFUNC_HOOK_SCHED_ACT; + case BPF_PROG_TYPE_SK_SKB: + return BTF_KFUNC_HOOK_SK_SKB; + case BPF_PROG_TYPE_SOCKET_FILTER: + return BTF_KFUNC_HOOK_SOCKET_FILTER; + case BPF_PROG_TYPE_LWT_OUT: + case BPF_PROG_TYPE_LWT_IN: + case BPF_PROG_TYPE_LWT_XMIT: + case BPF_PROG_TYPE_LWT_SEG6LOCAL: + return BTF_KFUNC_HOOK_LWT; default: return BTF_KFUNC_HOOK_MAX; } @@ -8336,7 +8368,7 @@ out: bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off) + int off, const char *suffix) { struct btf *btf = reg->btf; const struct btf_type *walk_type, *safe_type; @@ -8353,7 +8385,7 @@ bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, tname = btf_name_by_offset(btf, walk_type->name_off); - ret = snprintf(safe_tname, sizeof(safe_tname), "%s__safe_fields", tname); + ret = snprintf(safe_tname, sizeof(safe_tname), "%s%s", tname, suffix); if (ret < 0) return false; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index bf2fdb33fb31..53edb8ad2471 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -2223,10 +2223,12 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos), treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, ppos)); - *insn++ = BPF_STX_MEM( - BPF_SIZEOF(u32), treg, si->src_reg, + *insn++ = BPF_RAW_INSN( + BPF_CLASS(si->code) | BPF_MEM | BPF_SIZEOF(u32), + treg, si->src_reg, bpf_ctx_narrow_access_offset( - 0, sizeof(u32), sizeof(loff_t))); + 0, sizeof(u32), sizeof(loff_t)), + si->imm); *insn++ = BPF_LDX_MEM( BPF_DW, treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, tmp_reg)); @@ -2376,10 +2378,17 @@ static bool cg_sockopt_is_valid_access(int off, int size, return true; } -#define CG_SOCKOPT_ACCESS_FIELD(T, F) \ - T(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F), \ - si->dst_reg, si->src_reg, \ - offsetof(struct bpf_sockopt_kern, F)) +#define CG_SOCKOPT_READ_FIELD(F) \ + BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F), \ + si->dst_reg, si->src_reg, \ + offsetof(struct bpf_sockopt_kern, F)) + +#define CG_SOCKOPT_WRITE_FIELD(F) \ + BPF_RAW_INSN((BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F) | \ + BPF_MEM | BPF_CLASS(si->code)), \ + si->dst_reg, si->src_reg, \ + offsetof(struct bpf_sockopt_kern, F), \ + si->imm) static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, @@ -2391,25 +2400,25 @@ static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type, switch (si->off) { case offsetof(struct bpf_sockopt, sk): - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, sk); + *insn++ = CG_SOCKOPT_READ_FIELD(sk); break; case offsetof(struct bpf_sockopt, level): if (type == BPF_WRITE) - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, level); + *insn++ = CG_SOCKOPT_WRITE_FIELD(level); else - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, level); + *insn++ = CG_SOCKOPT_READ_FIELD(level); break; case offsetof(struct bpf_sockopt, optname): if (type == BPF_WRITE) - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optname); + *insn++ = CG_SOCKOPT_WRITE_FIELD(optname); else - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optname); + *insn++ = CG_SOCKOPT_READ_FIELD(optname); break; case offsetof(struct bpf_sockopt, optlen): if (type == BPF_WRITE) - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optlen); + *insn++ = CG_SOCKOPT_WRITE_FIELD(optlen); else - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optlen); + *insn++ = CG_SOCKOPT_READ_FIELD(optlen); break; case offsetof(struct bpf_sockopt, retval): BUILD_BUG_ON(offsetof(struct bpf_cg_run_ctx, run_ctx) != 0); @@ -2429,9 +2438,11 @@ static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx), treg, treg, offsetof(struct task_struct, bpf_ctx)); - *insn++ = BPF_STX_MEM(BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval), - treg, si->src_reg, - offsetof(struct bpf_cg_run_ctx, retval)); + *insn++ = BPF_RAW_INSN(BPF_CLASS(si->code) | BPF_MEM | + BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval), + treg, si->src_reg, + offsetof(struct bpf_cg_run_ctx, retval), + si->imm); *insn++ = BPF_LDX_MEM(BPF_DW, treg, si->dst_reg, offsetof(struct bpf_sockopt_kern, tmp_reg)); } else { @@ -2447,10 +2458,10 @@ static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type, } break; case offsetof(struct bpf_sockopt, optval): - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval); + *insn++ = CG_SOCKOPT_READ_FIELD(optval); break; case offsetof(struct bpf_sockopt, optval_end): - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval_end); + *insn++ = CG_SOCKOPT_READ_FIELD(optval_end); break; } @@ -2529,10 +2540,6 @@ cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_current_pid_tgid_proto; case BPF_FUNC_get_current_comm: return &bpf_get_current_comm_proto; - case BPF_FUNC_get_current_cgroup_id: - return &bpf_get_current_cgroup_id_proto; - case BPF_FUNC_get_current_ancestor_cgroup_id: - return &bpf_get_current_ancestor_cgroup_id_proto; #ifdef CONFIG_CGROUP_NET_CLASSID case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_curr_proto; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index d2110c1f6fa6..871809e71b4e 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -673,6 +673,15 @@ static int cpu_map_redirect(struct bpf_map *map, u64 index, u64 flags) __cpu_map_lookup_elem); } +static u64 cpu_map_mem_usage(const struct bpf_map *map) +{ + u64 usage = sizeof(struct bpf_cpu_map); + + /* Currently the dynamically allocated elements are not counted */ + usage += (u64)map->max_entries * sizeof(struct bpf_cpu_map_entry *); + return usage; +} + BTF_ID_LIST_SINGLE(cpu_map_btf_ids, struct, bpf_cpu_map) const struct bpf_map_ops cpu_map_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -683,6 +692,7 @@ const struct bpf_map_ops cpu_map_ops = { .map_lookup_elem = cpu_map_lookup_elem, .map_get_next_key = cpu_map_get_next_key, .map_check_btf = map_check_no_btf, + .map_mem_usage = cpu_map_mem_usage, .map_btf_id = &cpu_map_btf_ids[0], .map_redirect = cpu_map_redirect, }; diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c index 52b981512a35..b6587ec40f1b 100644 --- a/kernel/bpf/cpumask.c +++ b/kernel/bpf/cpumask.c @@ -55,7 +55,7 @@ __bpf_kfunc struct bpf_cpumask *bpf_cpumask_create(void) /* cpumask must be the first element so struct bpf_cpumask be cast to struct cpumask. */ BUILD_BUG_ON(offsetof(struct bpf_cpumask, cpumask) != 0); - cpumask = bpf_mem_alloc(&bpf_cpumask_ma, sizeof(*cpumask)); + cpumask = bpf_mem_cache_alloc(&bpf_cpumask_ma); if (!cpumask) return NULL; @@ -123,7 +123,7 @@ __bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask) if (refcount_dec_and_test(&cpumask->usage)) { migrate_disable(); - bpf_mem_free(&bpf_cpumask_ma, cpumask); + bpf_mem_cache_free(&bpf_cpumask_ma, cpumask); migrate_enable(); } } @@ -427,26 +427,26 @@ BTF_ID_FLAGS(func, bpf_cpumask_create, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_cpumask_release, KF_RELEASE | KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_cpumask_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_cpumask_kptr_get, KF_ACQUIRE | KF_KPTR_GET | KF_RET_NULL) -BTF_ID_FLAGS(func, bpf_cpumask_first, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_first_zero, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_set_cpu, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_clear_cpu, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_test_cpu, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_test_and_set_cpu, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_test_and_clear_cpu, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_setall, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_clear, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_and, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_or, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_xor, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_equal, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_intersects, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_subset, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_empty, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_full, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_copy, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_any, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_any_and, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_first, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_first_zero, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_set_cpu, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_clear_cpu, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_test_cpu, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_test_and_set_cpu, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_test_and_clear_cpu, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_setall, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_clear, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_and, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_or, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_xor, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_equal, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_intersects, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_subset, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_empty, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_full, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_copy, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_any, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_any_and, KF_RCU) BTF_SET8_END(cpumask_kfunc_btf_ids) static const struct btf_kfunc_id_set cpumask_kfunc_set = { @@ -468,7 +468,7 @@ static int __init cpumask_kfunc_init(void) }, }; - ret = bpf_mem_alloc_init(&bpf_cpumask_ma, 0, false); + ret = bpf_mem_alloc_init(&bpf_cpumask_ma, sizeof(struct bpf_cpumask), false); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &cpumask_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &cpumask_kfunc_set); return ret ?: register_btf_id_dtor_kfuncs(cpumask_dtors, diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 2675fefc6cb6..19b036a228f7 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -819,8 +819,10 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key) return -EINVAL; old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL)); - if (old_dev) + if (old_dev) { call_rcu(&old_dev->rcu, __dev_map_entry_free); + atomic_dec((atomic_t *)&dtab->items); + } return 0; } @@ -931,6 +933,8 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map, old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev))); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); + else + atomic_inc((atomic_t *)&dtab->items); return 0; } @@ -1016,6 +1020,20 @@ static int dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) __dev_map_hash_lookup_elem); } +static u64 dev_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + u64 usage = sizeof(struct bpf_dtab); + + if (map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) + usage += (u64)dtab->n_buckets * sizeof(struct hlist_head); + else + usage += (u64)map->max_entries * sizeof(struct bpf_dtab_netdev *); + usage += atomic_read((atomic_t *)&dtab->items) * + (u64)sizeof(struct bpf_dtab_netdev); + return usage; +} + BTF_ID_LIST_SINGLE(dev_map_btf_ids, struct, bpf_dtab) const struct bpf_map_ops dev_map_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -1026,6 +1044,7 @@ const struct bpf_map_ops dev_map_ops = { .map_update_elem = dev_map_update_elem, .map_delete_elem = dev_map_delete_elem, .map_check_btf = map_check_no_btf, + .map_mem_usage = dev_map_mem_usage, .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_map_redirect, }; @@ -1039,6 +1058,7 @@ const struct bpf_map_ops dev_map_hash_ops = { .map_update_elem = dev_map_hash_update_elem, .map_delete_elem = dev_map_hash_delete_elem, .map_check_btf = map_check_no_btf, + .map_mem_usage = dev_map_mem_usage, .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_hash_map_redirect, }; @@ -1109,9 +1129,11 @@ static int dev_map_notification(struct notifier_block *notifier, if (!dev || netdev != dev->dev) continue; odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL)); - if (dev == odev) + if (dev == odev) { call_rcu(&dev->rcu, __dev_map_entry_free); + atomic_dec((atomic_t *)&dtab->items); + } } } rcu_read_unlock(); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 5dfcb5ad0d06..0df4b0c10f59 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -249,7 +249,18 @@ static void htab_free_prealloced_fields(struct bpf_htab *htab) struct htab_elem *elem; elem = get_htab_elem(htab, i); - bpf_obj_free_fields(htab->map.record, elem->key + round_up(htab->map.key_size, 8)); + if (htab_is_percpu(htab)) { + void __percpu *pptr = htab_elem_get_ptr(elem, htab->map.key_size); + int cpu; + + for_each_possible_cpu(cpu) { + bpf_obj_free_fields(htab->map.record, per_cpu_ptr(pptr, cpu)); + cond_resched(); + } + } else { + bpf_obj_free_fields(htab->map.record, elem->key + round_up(htab->map.key_size, 8)); + cond_resched(); + } cond_resched(); } } @@ -759,9 +770,17 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map, static void check_and_free_fields(struct bpf_htab *htab, struct htab_elem *elem) { - void *map_value = elem->key + round_up(htab->map.key_size, 8); + if (htab_is_percpu(htab)) { + void __percpu *pptr = htab_elem_get_ptr(elem, htab->map.key_size); + int cpu; + + for_each_possible_cpu(cpu) + bpf_obj_free_fields(htab->map.record, per_cpu_ptr(pptr, cpu)); + } else { + void *map_value = elem->key + round_up(htab->map.key_size, 8); - bpf_obj_free_fields(htab->map.record, map_value); + bpf_obj_free_fields(htab->map.record, map_value); + } } /* It is called from the bpf_lru_list when the LRU needs to delete @@ -858,9 +877,9 @@ find_first_elem: static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l) { + check_and_free_fields(htab, l); if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) bpf_mem_cache_free(&htab->pcpu_ma, l->ptr_to_pptr); - check_and_free_fields(htab, l); bpf_mem_cache_free(&htab->ma, l); } @@ -918,14 +937,13 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, { if (!onallcpus) { /* copy true value_size bytes */ - memcpy(this_cpu_ptr(pptr), value, htab->map.value_size); + copy_map_value(&htab->map, this_cpu_ptr(pptr), value); } else { u32 size = round_up(htab->map.value_size, 8); int off = 0, cpu; for_each_possible_cpu(cpu) { - bpf_long_memcpy(per_cpu_ptr(pptr, cpu), - value + off, size); + copy_map_value_long(&htab->map, per_cpu_ptr(pptr, cpu), value + off); off += size; } } @@ -940,16 +958,14 @@ static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr, * (onallcpus=false always when coming from bpf prog). */ if (!onallcpus) { - u32 size = round_up(htab->map.value_size, 8); int current_cpu = raw_smp_processor_id(); int cpu; for_each_possible_cpu(cpu) { if (cpu == current_cpu) - bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value, - size); - else - memset(per_cpu_ptr(pptr, cpu), 0, size); + copy_map_value_long(&htab->map, per_cpu_ptr(pptr, cpu), value); + else /* Since elem is preallocated, we cannot touch special fields */ + zero_map_value(&htab->map, per_cpu_ptr(pptr, cpu)); } } else { pcpu_copy_value(htab, pptr, value, onallcpus); @@ -1575,9 +1591,8 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, pptr = htab_elem_get_ptr(l, key_size); for_each_possible_cpu(cpu) { - bpf_long_memcpy(value + off, - per_cpu_ptr(pptr, cpu), - roundup_value_size); + copy_map_value_long(&htab->map, value + off, per_cpu_ptr(pptr, cpu)); + check_and_init_map_value(&htab->map, value + off); off += roundup_value_size; } } else { @@ -1772,8 +1787,8 @@ again_nocopy: pptr = htab_elem_get_ptr(l, map->key_size); for_each_possible_cpu(cpu) { - bpf_long_memcpy(dst_val + off, - per_cpu_ptr(pptr, cpu), size); + copy_map_value_long(&htab->map, dst_val + off, per_cpu_ptr(pptr, cpu)); + check_and_init_map_value(&htab->map, dst_val + off); off += size; } } else { @@ -2046,9 +2061,9 @@ static int __bpf_hash_map_seq_show(struct seq_file *seq, struct htab_elem *elem) roundup_value_size = round_up(map->value_size, 8); pptr = htab_elem_get_ptr(elem, map->key_size); for_each_possible_cpu(cpu) { - bpf_long_memcpy(info->percpu_value_buf + off, - per_cpu_ptr(pptr, cpu), - roundup_value_size); + copy_map_value_long(map, info->percpu_value_buf + off, + per_cpu_ptr(pptr, cpu)); + check_and_init_map_value(map, info->percpu_value_buf + off); off += roundup_value_size; } ctx.value = info->percpu_value_buf; @@ -2175,6 +2190,44 @@ out: return num_elems; } +static u64 htab_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + u32 value_size = round_up(htab->map.value_size, 8); + bool prealloc = htab_is_prealloc(htab); + bool percpu = htab_is_percpu(htab); + bool lru = htab_is_lru(htab); + u64 num_entries; + u64 usage = sizeof(struct bpf_htab); + + usage += sizeof(struct bucket) * htab->n_buckets; + usage += sizeof(int) * num_possible_cpus() * HASHTAB_MAP_LOCK_COUNT; + if (prealloc) { + num_entries = map->max_entries; + if (htab_has_extra_elems(htab)) + num_entries += num_possible_cpus(); + + usage += htab->elem_size * num_entries; + + if (percpu) + usage += value_size * num_possible_cpus() * num_entries; + else if (!lru) + usage += sizeof(struct htab_elem *) * num_possible_cpus(); + } else { +#define LLIST_NODE_SZ sizeof(struct llist_node) + + num_entries = htab->use_percpu_counter ? + percpu_counter_sum(&htab->pcount) : + atomic_read(&htab->count); + usage += (htab->elem_size + LLIST_NODE_SZ) * num_entries; + if (percpu) { + usage += (LLIST_NODE_SZ + sizeof(void *)) * num_entries; + usage += value_size * num_possible_cpus() * num_entries; + } + } + return usage; +} + BTF_ID_LIST_SINGLE(htab_map_btf_ids, struct, bpf_htab) const struct bpf_map_ops htab_map_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -2191,6 +2244,7 @@ const struct bpf_map_ops htab_map_ops = { .map_seq_show_elem = htab_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab), .map_btf_id = &htab_map_btf_ids[0], .iter_seq_info = &iter_seq_info, @@ -2212,6 +2266,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_seq_show_elem = htab_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab_lru), .map_btf_id = &htab_map_btf_ids[0], .iter_seq_info = &iter_seq_info, @@ -2292,8 +2347,8 @@ int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value) */ pptr = htab_elem_get_ptr(l, map->key_size); for_each_possible_cpu(cpu) { - bpf_long_memcpy(value + off, - per_cpu_ptr(pptr, cpu), size); + copy_map_value_long(map, value + off, per_cpu_ptr(pptr, cpu)); + check_and_init_map_value(map, value + off); off += size; } ret = 0; @@ -2363,6 +2418,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { .map_seq_show_elem = htab_percpu_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab_percpu), .map_btf_id = &htab_map_btf_ids[0], .iter_seq_info = &iter_seq_info, @@ -2382,6 +2438,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_seq_show_elem = htab_percpu_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab_lru_percpu), .map_btf_id = &htab_map_btf_ids[0], .iter_seq_info = &iter_seq_info, @@ -2519,6 +2576,7 @@ const struct bpf_map_ops htab_of_maps_map_ops = { .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, .map_gen_lookup = htab_of_map_gen_lookup, .map_check_btf = map_check_no_btf, + .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab), .map_btf_id = &htab_map_btf_ids[0], }; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 5b278a38ae58..637ac4e92e75 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1264,10 +1264,11 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla { struct bpf_hrtimer *t; int ret = 0; + enum hrtimer_mode mode; if (in_nmi()) return -EOPNOTSUPP; - if (flags) + if (flags > BPF_F_TIMER_ABS) return -EINVAL; __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; @@ -1275,7 +1276,13 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla ret = -EINVAL; goto out; } - hrtimer_start(&t->timer, ns_to_ktime(nsecs), HRTIMER_MODE_REL_SOFT); + + if (flags & BPF_F_TIMER_ABS) + mode = HRTIMER_MODE_ABS_SOFT; + else + mode = HRTIMER_MODE_REL_SOFT; + + hrtimer_start(&t->timer, ns_to_ktime(nsecs), mode); out: __bpf_spin_unlock_irqrestore(&timer->lock); return ret; @@ -1420,11 +1427,21 @@ static bool bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr) return ptr->size & DYNPTR_RDONLY_BIT; } +void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr) +{ + ptr->size |= DYNPTR_RDONLY_BIT; +} + static void bpf_dynptr_set_type(struct bpf_dynptr_kern *ptr, enum bpf_dynptr_type type) { ptr->size |= type << DYNPTR_TYPE_SHIFT; } +static enum bpf_dynptr_type bpf_dynptr_get_type(const struct bpf_dynptr_kern *ptr) +{ + return (ptr->size & ~(DYNPTR_RDONLY_BIT)) >> DYNPTR_TYPE_SHIFT; +} + u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr) { return ptr->size & DYNPTR_SIZE_MASK; @@ -1497,6 +1514,7 @@ static const struct bpf_func_proto bpf_dynptr_from_mem_proto = { BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src, u32, offset, u64, flags) { + enum bpf_dynptr_type type; int err; if (!src->data || flags) @@ -1506,13 +1524,25 @@ BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern if (err) return err; - /* Source and destination may possibly overlap, hence use memmove to - * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr - * pointing to overlapping PTR_TO_MAP_VALUE regions. - */ - memmove(dst, src->data + src->offset + offset, len); + type = bpf_dynptr_get_type(src); - return 0; + switch (type) { + case BPF_DYNPTR_TYPE_LOCAL: + case BPF_DYNPTR_TYPE_RINGBUF: + /* Source and destination may possibly overlap, hence use memmove to + * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr + * pointing to overlapping PTR_TO_MAP_VALUE regions. + */ + memmove(dst, src->data + src->offset + offset, len); + return 0; + case BPF_DYNPTR_TYPE_SKB: + return __bpf_skb_load_bytes(src->data, src->offset + offset, dst, len); + case BPF_DYNPTR_TYPE_XDP: + return __bpf_xdp_load_bytes(src->data, src->offset + offset, dst, len); + default: + WARN_ONCE(true, "bpf_dynptr_read: unknown dynptr type %d\n", type); + return -EFAULT; + } } static const struct bpf_func_proto bpf_dynptr_read_proto = { @@ -1529,22 +1559,40 @@ static const struct bpf_func_proto bpf_dynptr_read_proto = { BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, void *, src, u32, len, u64, flags) { + enum bpf_dynptr_type type; int err; - if (!dst->data || flags || bpf_dynptr_is_rdonly(dst)) + if (!dst->data || bpf_dynptr_is_rdonly(dst)) return -EINVAL; err = bpf_dynptr_check_off_len(dst, offset, len); if (err) return err; - /* Source and destination may possibly overlap, hence use memmove to - * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr - * pointing to overlapping PTR_TO_MAP_VALUE regions. - */ - memmove(dst->data + dst->offset + offset, src, len); + type = bpf_dynptr_get_type(dst); - return 0; + switch (type) { + case BPF_DYNPTR_TYPE_LOCAL: + case BPF_DYNPTR_TYPE_RINGBUF: + if (flags) + return -EINVAL; + /* Source and destination may possibly overlap, hence use memmove to + * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr + * pointing to overlapping PTR_TO_MAP_VALUE regions. + */ + memmove(dst->data + dst->offset + offset, src, len); + return 0; + case BPF_DYNPTR_TYPE_SKB: + return __bpf_skb_store_bytes(dst->data, dst->offset + offset, src, len, + flags); + case BPF_DYNPTR_TYPE_XDP: + if (flags) + return -EINVAL; + return __bpf_xdp_store_bytes(dst->data, dst->offset + offset, src, len); + default: + WARN_ONCE(true, "bpf_dynptr_write: unknown dynptr type %d\n", type); + return -EFAULT; + } } static const struct bpf_func_proto bpf_dynptr_write_proto = { @@ -1560,6 +1608,7 @@ static const struct bpf_func_proto bpf_dynptr_write_proto = { BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u32, len) { + enum bpf_dynptr_type type; int err; if (!ptr->data) @@ -1572,7 +1621,20 @@ BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u3 if (bpf_dynptr_is_rdonly(ptr)) return 0; - return (unsigned long)(ptr->data + ptr->offset + offset); + type = bpf_dynptr_get_type(ptr); + + switch (type) { + case BPF_DYNPTR_TYPE_LOCAL: + case BPF_DYNPTR_TYPE_RINGBUF: + return (unsigned long)(ptr->data + ptr->offset + offset); + case BPF_DYNPTR_TYPE_SKB: + case BPF_DYNPTR_TYPE_XDP: + /* skb and xdp dynptrs should use bpf_dynptr_slice / bpf_dynptr_slice_rdwr */ + return 0; + default: + WARN_ONCE(true, "bpf_dynptr_data: unknown dynptr type %d\n", type); + return 0; + } } static const struct bpf_func_proto bpf_dynptr_data_proto = { @@ -1693,6 +1755,10 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_cgrp_storage_get_proto; case BPF_FUNC_cgrp_storage_delete: return &bpf_cgrp_storage_delete_proto; + case BPF_FUNC_get_current_cgroup_id: + return &bpf_get_current_cgroup_id_proto; + case BPF_FUNC_get_current_ancestor_cgroup_id: + return &bpf_get_current_ancestor_cgroup_id_proto; #endif default: break; @@ -2097,10 +2163,28 @@ __bpf_kfunc struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) if (level > cgrp->level || level < 0) return NULL; + /* cgrp's refcnt could be 0 here, but ancestors can still be accessed */ ancestor = cgrp->ancestors[level]; - cgroup_get(ancestor); + if (!cgroup_tryget(ancestor)) + return NULL; return ancestor; } + +/** + * bpf_cgroup_from_id - Find a cgroup from its ID. A cgroup returned by this + * kfunc which is not subsequently stored in a map, must be released by calling + * bpf_cgroup_release(). + * @cgid: cgroup id. + */ +__bpf_kfunc struct cgroup *bpf_cgroup_from_id(u64 cgid) +{ + struct cgroup *cgrp; + + cgrp = cgroup_get_from_id(cgid); + if (IS_ERR(cgrp)) + return NULL; + return cgrp; +} #endif /* CONFIG_CGROUPS */ /** @@ -2122,6 +2206,140 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid) return p; } +/** + * bpf_dynptr_slice() - Obtain a read-only pointer to the dynptr data. + * @ptr: The dynptr whose data slice to retrieve + * @offset: Offset into the dynptr + * @buffer: User-provided buffer to copy contents into + * @buffer__szk: Size (in bytes) of the buffer. This is the length of the + * requested slice. This must be a constant. + * + * For non-skb and non-xdp type dynptrs, there is no difference between + * bpf_dynptr_slice and bpf_dynptr_data. + * + * If the intention is to write to the data slice, please use + * bpf_dynptr_slice_rdwr. + * + * The user must check that the returned pointer is not null before using it. + * + * Please note that in the case of skb and xdp dynptrs, bpf_dynptr_slice + * does not change the underlying packet data pointers, so a call to + * bpf_dynptr_slice will not invalidate any ctx->data/data_end pointers in + * the bpf program. + * + * Return: NULL if the call failed (eg invalid dynptr), pointer to a read-only + * data slice (can be either direct pointer to the data or a pointer to the user + * provided buffer, with its contents containing the data, if unable to obtain + * direct pointer) + */ +__bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset, + void *buffer, u32 buffer__szk) +{ + enum bpf_dynptr_type type; + u32 len = buffer__szk; + int err; + + if (!ptr->data) + return NULL; + + err = bpf_dynptr_check_off_len(ptr, offset, len); + if (err) + return NULL; + + type = bpf_dynptr_get_type(ptr); + + switch (type) { + case BPF_DYNPTR_TYPE_LOCAL: + case BPF_DYNPTR_TYPE_RINGBUF: + return ptr->data + ptr->offset + offset; + case BPF_DYNPTR_TYPE_SKB: + return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer); + case BPF_DYNPTR_TYPE_XDP: + { + void *xdp_ptr = bpf_xdp_pointer(ptr->data, ptr->offset + offset, len); + if (xdp_ptr) + return xdp_ptr; + + bpf_xdp_copy_buf(ptr->data, ptr->offset + offset, buffer, len, false); + return buffer; + } + default: + WARN_ONCE(true, "unknown dynptr type %d\n", type); + return NULL; + } +} + +/** + * bpf_dynptr_slice_rdwr() - Obtain a writable pointer to the dynptr data. + * @ptr: The dynptr whose data slice to retrieve + * @offset: Offset into the dynptr + * @buffer: User-provided buffer to copy contents into + * @buffer__szk: Size (in bytes) of the buffer. This is the length of the + * requested slice. This must be a constant. + * + * For non-skb and non-xdp type dynptrs, there is no difference between + * bpf_dynptr_slice and bpf_dynptr_data. + * + * The returned pointer is writable and may point to either directly the dynptr + * data at the requested offset or to the buffer if unable to obtain a direct + * data pointer to (example: the requested slice is to the paged area of an skb + * packet). In the case where the returned pointer is to the buffer, the user + * is responsible for persisting writes through calling bpf_dynptr_write(). This + * usually looks something like this pattern: + * + * struct eth_hdr *eth = bpf_dynptr_slice_rdwr(&dynptr, 0, buffer, sizeof(buffer)); + * if (!eth) + * return TC_ACT_SHOT; + * + * // mutate eth header // + * + * if (eth == buffer) + * bpf_dynptr_write(&ptr, 0, buffer, sizeof(buffer), 0); + * + * Please note that, as in the example above, the user must check that the + * returned pointer is not null before using it. + * + * Please also note that in the case of skb and xdp dynptrs, bpf_dynptr_slice_rdwr + * does not change the underlying packet data pointers, so a call to + * bpf_dynptr_slice_rdwr will not invalidate any ctx->data/data_end pointers in + * the bpf program. + * + * Return: NULL if the call failed (eg invalid dynptr), pointer to a + * data slice (can be either direct pointer to the data or a pointer to the user + * provided buffer, with its contents containing the data, if unable to obtain + * direct pointer) + */ +__bpf_kfunc void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr_kern *ptr, u32 offset, + void *buffer, u32 buffer__szk) +{ + if (!ptr->data || bpf_dynptr_is_rdonly(ptr)) + return NULL; + + /* bpf_dynptr_slice_rdwr is the same logic as bpf_dynptr_slice. + * + * For skb-type dynptrs, it is safe to write into the returned pointer + * if the bpf program allows skb data writes. There are two possiblities + * that may occur when calling bpf_dynptr_slice_rdwr: + * + * 1) The requested slice is in the head of the skb. In this case, the + * returned pointer is directly to skb data, and if the skb is cloned, the + * verifier will have uncloned it (see bpf_unclone_prologue()) already. + * The pointer can be directly written into. + * + * 2) Some portion of the requested slice is in the paged buffer area. + * In this case, the requested data will be copied out into the buffer + * and the returned pointer will be a pointer to the buffer. The skb + * will not be pulled. To persist the write, the user will need to call + * bpf_dynptr_write(), which will pull the skb and commit the write. + * + * Similarly for xdp programs, if the requested slice is not across xdp + * fragments, then a direct pointer will be returned, otherwise the data + * will be copied out into the buffer and the user will need to call + * bpf_dynptr_write() to commit changes. + */ + return bpf_dynptr_slice(ptr, offset, buffer, buffer__szk); +} + __bpf_kfunc void *bpf_cast_to_kern_ctx(void *obj) { return obj; @@ -2166,7 +2384,8 @@ BTF_ID_FLAGS(func, bpf_rbtree_first, KF_RET_NULL) BTF_ID_FLAGS(func, bpf_cgroup_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_cgroup_kptr_get, KF_ACQUIRE | KF_KPTR_GET | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_cgroup_release, KF_RELEASE) -BTF_ID_FLAGS(func, bpf_cgroup_ancestor, KF_ACQUIRE | KF_TRUSTED_ARGS | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_cgroup_ancestor, KF_ACQUIRE | KF_RCU | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_cgroup_from_id, KF_ACQUIRE | KF_RET_NULL) #endif BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL) BTF_SET8_END(generic_btf_ids) @@ -2190,6 +2409,8 @@ BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx) BTF_ID_FLAGS(func, bpf_rdonly_cast) BTF_ID_FLAGS(func, bpf_rcu_read_lock) BTF_ID_FLAGS(func, bpf_rcu_read_unlock) +BTF_ID_FLAGS(func, bpf_dynptr_slice, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_dynptr_slice_rdwr, KF_RET_NULL) BTF_SET8_END(common_btf_ids) static const struct btf_kfunc_id_set common_kfunc_set = { diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index e90d9f63edc5..a993560f200a 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -446,6 +446,12 @@ static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } +static u64 cgroup_storage_map_usage(const struct bpf_map *map) +{ + /* Currently the dynamically allocated elements are not counted. */ + return sizeof(struct bpf_cgroup_storage_map); +} + BTF_ID_LIST_SINGLE(cgroup_storage_map_btf_ids, struct, bpf_cgroup_storage_map) const struct bpf_map_ops cgroup_storage_map_ops = { @@ -457,6 +463,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = { .map_delete_elem = cgroup_storage_delete_elem, .map_check_btf = cgroup_storage_check_btf, .map_seq_show_elem = cgroup_storage_seq_show_elem, + .map_mem_usage = cgroup_storage_map_usage, .map_btf_id = &cgroup_storage_map_btf_ids[0], }; diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index d833496e9e42..dc23f2ac9cde 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -720,6 +720,16 @@ static int trie_check_btf(const struct bpf_map *map, -EINVAL : 0; } +static u64 trie_mem_usage(const struct bpf_map *map) +{ + struct lpm_trie *trie = container_of(map, struct lpm_trie, map); + u64 elem_size; + + elem_size = sizeof(struct lpm_trie_node) + trie->data_size + + trie->map.value_size; + return elem_size * READ_ONCE(trie->n_entries); +} + BTF_ID_LIST_SINGLE(trie_map_btf_ids, struct, lpm_trie) const struct bpf_map_ops trie_map_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -733,5 +743,6 @@ const struct bpf_map_ops trie_map_ops = { .map_update_batch = generic_map_update_batch, .map_delete_batch = generic_map_delete_batch, .map_check_btf = trie_check_btf, + .map_mem_usage = trie_mem_usage, .map_btf_id = &trie_map_btf_ids[0], }; diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 0c85e06f7ea7..d9c9f45e3529 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -563,6 +563,12 @@ void bpf_map_offload_map_free(struct bpf_map *map) bpf_map_area_free(offmap); } +u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map) +{ + /* The memory dynamically allocated in netdev dev_ops is not counted */ + return sizeof(struct bpf_offloaded_map); +} + int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value) { struct bpf_offloaded_map *offmap = map_to_offmap(map); diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 8a5e060de63b..63ecbbcb349d 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -246,6 +246,14 @@ static int queue_stack_map_get_next_key(struct bpf_map *map, void *key, return -EINVAL; } +static u64 queue_stack_map_mem_usage(const struct bpf_map *map) +{ + u64 usage = sizeof(struct bpf_queue_stack); + + usage += ((u64)map->max_entries + 1) * map->value_size; + return usage; +} + BTF_ID_LIST_SINGLE(queue_map_btf_ids, struct, bpf_queue_stack) const struct bpf_map_ops queue_map_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -259,6 +267,7 @@ const struct bpf_map_ops queue_map_ops = { .map_pop_elem = queue_map_pop_elem, .map_peek_elem = queue_map_peek_elem, .map_get_next_key = queue_stack_map_get_next_key, + .map_mem_usage = queue_stack_map_mem_usage, .map_btf_id = &queue_map_btf_ids[0], }; @@ -274,5 +283,6 @@ const struct bpf_map_ops stack_map_ops = { .map_pop_elem = stack_map_pop_elem, .map_peek_elem = stack_map_peek_elem, .map_get_next_key = queue_stack_map_get_next_key, + .map_mem_usage = queue_stack_map_mem_usage, .map_btf_id = &queue_map_btf_ids[0], }; diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index 82c61612f382..71cb72f5b733 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -335,6 +335,13 @@ static int reuseport_array_get_next_key(struct bpf_map *map, void *key, return 0; } +static u64 reuseport_array_mem_usage(const struct bpf_map *map) +{ + struct reuseport_array *array; + + return struct_size(array, ptrs, map->max_entries); +} + BTF_ID_LIST_SINGLE(reuseport_array_map_btf_ids, struct, reuseport_array) const struct bpf_map_ops reuseport_array_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -344,5 +351,6 @@ const struct bpf_map_ops reuseport_array_ops = { .map_lookup_elem = reuseport_array_lookup_elem, .map_get_next_key = reuseport_array_get_next_key, .map_delete_elem = reuseport_array_delete_elem, + .map_mem_usage = reuseport_array_mem_usage, .map_btf_id = &reuseport_array_map_btf_ids[0], }; diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 8732e0aadf36..0d2a45ff83f1 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -19,6 +19,7 @@ (offsetof(struct bpf_ringbuf, consumer_pos) >> PAGE_SHIFT) /* consumer page and producer page */ #define RINGBUF_POS_PAGES 2 +#define RINGBUF_NR_META_PAGES (RINGBUF_PGOFF + RINGBUF_POS_PAGES) #define RINGBUF_MAX_RECORD_SZ (UINT_MAX/4) @@ -96,7 +97,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) { const gfp_t flags = GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL | __GFP_NOWARN | __GFP_ZERO; - int nr_meta_pages = RINGBUF_PGOFF + RINGBUF_POS_PAGES; + int nr_meta_pages = RINGBUF_NR_META_PAGES; int nr_data_pages = data_sz >> PAGE_SHIFT; int nr_pages = nr_meta_pages + nr_data_pages; struct page **pages, *page; @@ -336,6 +337,21 @@ static __poll_t ringbuf_map_poll_user(struct bpf_map *map, struct file *filp, return 0; } +static u64 ringbuf_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_ringbuf *rb; + int nr_data_pages; + int nr_meta_pages; + u64 usage = sizeof(struct bpf_ringbuf_map); + + rb = container_of(map, struct bpf_ringbuf_map, map)->rb; + usage += (u64)rb->nr_pages << PAGE_SHIFT; + nr_meta_pages = RINGBUF_NR_META_PAGES; + nr_data_pages = map->max_entries >> PAGE_SHIFT; + usage += (nr_meta_pages + 2 * nr_data_pages) * sizeof(struct page *); + return usage; +} + BTF_ID_LIST_SINGLE(ringbuf_map_btf_ids, struct, bpf_ringbuf_map) const struct bpf_map_ops ringbuf_map_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -347,6 +363,7 @@ const struct bpf_map_ops ringbuf_map_ops = { .map_update_elem = ringbuf_map_update_elem, .map_delete_elem = ringbuf_map_delete_elem, .map_get_next_key = ringbuf_map_get_next_key, + .map_mem_usage = ringbuf_map_mem_usage, .map_btf_id = &ringbuf_map_btf_ids[0], }; @@ -361,6 +378,7 @@ const struct bpf_map_ops user_ringbuf_map_ops = { .map_update_elem = ringbuf_map_update_elem, .map_delete_elem = ringbuf_map_delete_elem, .map_get_next_key = ringbuf_map_get_next_key, + .map_mem_usage = ringbuf_map_mem_usage, .map_btf_id = &user_ringbuf_map_btf_ids[0], }; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index aecea7451b61..0f1d8dced933 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -654,6 +654,19 @@ static void stack_map_free(struct bpf_map *map) put_callchain_buffers(); } +static u64 stack_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + u64 value_size = map->value_size; + u64 n_buckets = smap->n_buckets; + u64 enties = map->max_entries; + u64 usage = sizeof(*smap); + + usage += n_buckets * sizeof(struct stack_map_bucket *); + usage += enties * (sizeof(struct stack_map_bucket) + value_size); + return usage; +} + BTF_ID_LIST_SINGLE(stack_trace_map_btf_ids, struct, bpf_stack_map) const struct bpf_map_ops stack_trace_map_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -664,5 +677,6 @@ const struct bpf_map_ops stack_trace_map_ops = { .map_update_elem = stack_map_update_elem, .map_delete_elem = stack_map_delete_elem, .map_check_btf = map_check_no_btf, + .map_mem_usage = stack_map_mem_usage, .map_btf_id = &stack_trace_map_btf_ids[0], }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index adc83cb82f37..f406dfa13792 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -105,6 +105,7 @@ const struct bpf_map_ops bpf_map_offload_ops = { .map_alloc = bpf_map_offload_map_alloc, .map_free = bpf_map_offload_map_free, .map_check_btf = map_check_no_btf, + .map_mem_usage = bpf_map_offload_map_mem_usage, }; static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) @@ -128,6 +129,8 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) } if (attr->map_ifindex) ops = &bpf_map_offload_ops; + if (!ops->map_mem_usage) + return ERR_PTR(-EINVAL); map = ops->map_alloc(attr); if (IS_ERR(map)) return map; @@ -771,17 +774,10 @@ static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) } #ifdef CONFIG_PROC_FS -/* Provides an approximation of the map's memory footprint. - * Used only to provide a backward compatibility and display - * a reasonable "memlock" info. - */ -static unsigned long bpf_map_memory_footprint(const struct bpf_map *map) +/* Show the memory usage of a bpf map */ +static u64 bpf_map_memory_usage(const struct bpf_map *map) { - unsigned long size; - - size = round_up(map->key_size + bpf_map_value_size(map), 8); - - return round_up(map->max_entries * size, PAGE_SIZE); + return map->ops->map_mem_usage(map); } static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) @@ -803,7 +799,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "max_entries:\t%u\n" "map_flags:\t%#x\n" "map_extra:\t%#llx\n" - "memlock:\t%lu\n" + "memlock:\t%llu\n" "map_id:\t%u\n" "frozen:\t%u\n", map->map_type, @@ -812,7 +808,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->max_entries, map->map_flags, (unsigned long long)map->map_extra, - bpf_map_memory_footprint(map), + bpf_map_memory_usage(map), map->id, READ_ONCE(map->frozen)); if (type) { @@ -1059,9 +1055,15 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, case BPF_KPTR_UNREF: case BPF_KPTR_REF: if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && + map->map_type != BPF_MAP_TYPE_LRU_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && - map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY) { + map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY && + map->map_type != BPF_MAP_TYPE_SK_STORAGE && + map->map_type != BPF_MAP_TYPE_INODE_STORAGE && + map->map_type != BPF_MAP_TYPE_TASK_STORAGE && + map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) { ret = -EOPNOTSUPP; goto free_map_tab; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d517d13878cf..b2116ca78d9a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -268,7 +268,41 @@ struct bpf_call_arg_meta { u32 ret_btf_id; u32 subprogno; struct btf_field *kptr_field; - u8 uninit_dynptr_regno; +}; + +struct bpf_kfunc_call_arg_meta { + /* In parameters */ + struct btf *btf; + u32 func_id; + u32 kfunc_flags; + const struct btf_type *func_proto; + const char *func_name; + /* Out parameters */ + u32 ref_obj_id; + u8 release_regno; + bool r0_rdonly; + u32 ret_btf_id; + u64 r0_size; + u32 subprogno; + struct { + u64 value; + bool found; + } arg_constant; + struct { + struct btf *btf; + u32 btf_id; + } arg_obj_drop; + struct { + struct btf_field *field; + } arg_list_head; + struct { + struct btf_field *field; + } arg_rbtree_root; + struct { + enum bpf_dynptr_type type; + u32 id; + } initialized_dynptr; + u64 mem_size; }; struct btf *btf_vmlinux; @@ -453,7 +487,8 @@ static bool reg_type_not_null(enum bpf_reg_type type) type == PTR_TO_TCP_SOCK || type == PTR_TO_MAP_VALUE || type == PTR_TO_MAP_KEY || - type == PTR_TO_SOCK_COMMON; + type == PTR_TO_SOCK_COMMON || + type == PTR_TO_MEM; } static bool type_is_ptr_alloc_obj(u32 type) @@ -675,37 +710,62 @@ static bool is_spi_bounds_valid(struct bpf_func_state *state, int spi, int nr_sl return spi - nr_slots + 1 >= 0 && spi < allocated_slots; } -static int dynptr_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +static int stack_slot_obj_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + const char *obj_kind, int nr_slots) { int off, spi; if (!tnum_is_const(reg->var_off)) { - verbose(env, "dynptr has to be at a constant offset\n"); + verbose(env, "%s has to be at a constant offset\n", obj_kind); return -EINVAL; } off = reg->off + reg->var_off.value; if (off % BPF_REG_SIZE) { - verbose(env, "cannot pass in dynptr at an offset=%d\n", off); + verbose(env, "cannot pass in %s at an offset=%d\n", obj_kind, off); return -EINVAL; } spi = __get_spi(off); - if (spi < 1) { - verbose(env, "cannot pass in dynptr at an offset=%d\n", off); + if (spi + 1 < nr_slots) { + verbose(env, "cannot pass in %s at an offset=%d\n", obj_kind, off); return -EINVAL; } - if (!is_spi_bounds_valid(func(env, reg), spi, BPF_DYNPTR_NR_SLOTS)) + if (!is_spi_bounds_valid(func(env, reg), spi, nr_slots)) return -ERANGE; return spi; } +static int dynptr_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + return stack_slot_obj_get_spi(env, reg, "dynptr", BPF_DYNPTR_NR_SLOTS); +} + static const char *kernel_type_name(const struct btf* btf, u32 id) { return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); } +static const char *dynptr_type_str(enum bpf_dynptr_type type) +{ + switch (type) { + case BPF_DYNPTR_TYPE_LOCAL: + return "local"; + case BPF_DYNPTR_TYPE_RINGBUF: + return "ringbuf"; + case BPF_DYNPTR_TYPE_SKB: + return "skb"; + case BPF_DYNPTR_TYPE_XDP: + return "xdp"; + case BPF_DYNPTR_TYPE_INVALID: + return "<invalid>"; + default: + WARN_ONCE(1, "unknown dynptr type %d\n", type); + return "<unknown>"; + } +} + static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno) { env->scratched_regs |= 1U << regno; @@ -751,11 +811,31 @@ static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type) return BPF_DYNPTR_TYPE_LOCAL; case DYNPTR_TYPE_RINGBUF: return BPF_DYNPTR_TYPE_RINGBUF; + case DYNPTR_TYPE_SKB: + return BPF_DYNPTR_TYPE_SKB; + case DYNPTR_TYPE_XDP: + return BPF_DYNPTR_TYPE_XDP; default: return BPF_DYNPTR_TYPE_INVALID; } } +static enum bpf_type_flag get_dynptr_type_flag(enum bpf_dynptr_type type) +{ + switch (type) { + case BPF_DYNPTR_TYPE_LOCAL: + return DYNPTR_TYPE_LOCAL; + case BPF_DYNPTR_TYPE_RINGBUF: + return DYNPTR_TYPE_RINGBUF; + case BPF_DYNPTR_TYPE_SKB: + return DYNPTR_TYPE_SKB; + case BPF_DYNPTR_TYPE_XDP: + return DYNPTR_TYPE_XDP; + default: + return 0; + } +} + static bool dynptr_type_refcounted(enum bpf_dynptr_type type) { return type == BPF_DYNPTR_TYPE_RINGBUF; @@ -895,6 +975,14 @@ static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_re static void __mark_reg_unknown(const struct bpf_verifier_env *env, struct bpf_reg_state *reg); +static void mark_reg_invalid(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + if (!env->allow_ptr_leaks) + __mark_reg_not_init(env, reg); + else + __mark_reg_unknown(env, reg); +} + static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env, struct bpf_func_state *state, int spi) { @@ -934,12 +1022,8 @@ static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env, /* Dynptr slices are only PTR_TO_MEM_OR_NULL and PTR_TO_MEM */ if (dreg->type != (PTR_TO_MEM | PTR_MAYBE_NULL) && dreg->type != PTR_TO_MEM) continue; - if (dreg->dynptr_id == dynptr_id) { - if (!env->allow_ptr_leaks) - __mark_reg_not_init(env, dreg); - else - __mark_reg_unknown(env, dreg); - } + if (dreg->dynptr_id == dynptr_id) + mark_reg_invalid(env, dreg); })); /* Do not release reference state, we are destroying dynptr on stack, @@ -955,39 +1039,49 @@ static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env, return 0; } -static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - int spi) +static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { + int spi; + if (reg->type == CONST_PTR_TO_DYNPTR) return false; - /* For -ERANGE (i.e. spi not falling into allocated stack slots), we - * will do check_mem_access to check and update stack bounds later, so - * return true for that case. + spi = dynptr_get_spi(env, reg); + + /* -ERANGE (i.e. spi not falling into allocated stack slots) isn't an + * error because this just means the stack state hasn't been updated yet. + * We will do check_mem_access to check and update stack bounds later. */ - if (spi < 0) - return spi == -ERANGE; - /* We allow overwriting existing unreferenced STACK_DYNPTR slots, see - * mark_stack_slots_dynptr which calls destroy_if_dynptr_stack_slot to - * ensure dynptr objects at the slots we are touching are completely - * destructed before we reinitialize them for a new one. For referenced - * ones, destroy_if_dynptr_stack_slot returns an error early instead of - * delaying it until the end where the user will get "Unreleased + if (spi < 0 && spi != -ERANGE) + return false; + + /* We don't need to check if the stack slots are marked by previous + * dynptr initializations because we allow overwriting existing unreferenced + * STACK_DYNPTR slots, see mark_stack_slots_dynptr which calls + * destroy_if_dynptr_stack_slot to ensure dynptr objects at the slots we are + * touching are completely destructed before we reinitialize them for a new + * one. For referenced ones, destroy_if_dynptr_stack_slot returns an error early + * instead of delaying it until the end where the user will get "Unreleased * reference" error. */ return true; } -static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - int spi) +static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); - int i; + int i, spi; - /* This already represents first slot of initialized bpf_dynptr */ + /* This already represents first slot of initialized bpf_dynptr. + * + * CONST_PTR_TO_DYNPTR already has fixed and var_off as 0 due to + * check_func_arg_reg_off's logic, so we don't need to check its + * offset and alignment. + */ if (reg->type == CONST_PTR_TO_DYNPTR) return true; + spi = dynptr_get_spi(env, reg); if (spi < 0) return false; if (!state->stack[spi].spilled_ptr.dynptr.first_slot) @@ -1143,26 +1237,49 @@ static void print_verifier_state(struct bpf_verifier_env *env, for (j = 0; j < BPF_REG_SIZE; j++) { if (state->stack[i].slot_type[j] != STACK_INVALID) valid = true; - types_buf[j] = slot_type_char[ - state->stack[i].slot_type[j]]; + types_buf[j] = slot_type_char[state->stack[i].slot_type[j]]; } types_buf[BPF_REG_SIZE] = 0; if (!valid) continue; if (!print_all && !stack_slot_scratched(env, i)) continue; - verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); - print_liveness(env, state->stack[i].spilled_ptr.live); - if (is_spilled_reg(&state->stack[i])) { + switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) { + case STACK_SPILL: reg = &state->stack[i].spilled_ptr; t = reg->type; + + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, reg->live); verbose(env, "=%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t)); if (t == SCALAR_VALUE && reg->precise) verbose(env, "P"); if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) verbose(env, "%lld", reg->var_off.value + reg->off); - } else { + break; + case STACK_DYNPTR: + i += BPF_DYNPTR_NR_SLOTS - 1; + reg = &state->stack[i].spilled_ptr; + + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, reg->live); + verbose(env, "=dynptr_%s", dynptr_type_str(reg->dynptr.type)); + if (reg->ref_obj_id) + verbose(env, "(ref_id=%d)", reg->ref_obj_id); + break; + case STACK_MISC: + case STACK_ZERO: + default: + reg = &state->stack[i].spilled_ptr; + + for (j = 0; j < BPF_REG_SIZE; j++) + types_buf[j] = slot_type_char[state->stack[i].slot_type[j]]; + types_buf[BPF_REG_SIZE] = 0; + + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, reg->live); verbose(env, "=%s", types_buf); + break; } } if (state->acquired_refs && state->refs[0].id) { @@ -1664,6 +1781,12 @@ static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg) reg->type == PTR_TO_PACKET_END; } +static bool reg_is_dynptr_slice_pkt(const struct bpf_reg_state *reg) +{ + return base_type(reg->type) == PTR_TO_MEM && + (reg->type & DYNPTR_TYPE_SKB || reg->type & DYNPTR_TYPE_XDP); +} + /* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */ static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg, enum bpf_reg_type which) @@ -2475,8 +2598,8 @@ static int check_subprogs(struct bpf_verifier_env *env) u8 code = insn[i].code; if (code == (BPF_JMP | BPF_CALL) && - insn[i].imm == BPF_FUNC_tail_call && - insn[i].src_reg != BPF_PSEUDO_CALL) + insn[i].src_reg == 0 && + insn[i].imm == BPF_FUNC_tail_call) subprog[cur_subprog].has_tail_call = true; if (BPF_CLASS(code) == BPF_LD && (BPF_MODE(code) == BPF_ABS || BPF_MODE(code) == BPF_IND)) @@ -4179,7 +4302,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno) { const char *targ_name = kernel_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id); - int perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED; + int perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED | MEM_RCU; const char *reg_name = ""; /* Only unreferenced case accepts untrusted pointers */ @@ -4246,6 +4369,34 @@ bad_type: return -EINVAL; } +/* The non-sleepable programs and sleepable programs with explicit bpf_rcu_read_lock() + * can dereference RCU protected pointers and result is PTR_TRUSTED. + */ +static bool in_rcu_cs(struct bpf_verifier_env *env) +{ + return env->cur_state->active_rcu_lock || !env->prog->aux->sleepable; +} + +/* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */ +BTF_SET_START(rcu_protected_types) +BTF_ID(struct, prog_test_ref_kfunc) +BTF_ID(struct, cgroup) +BTF_SET_END(rcu_protected_types) + +static bool rcu_protected_object(const struct btf *btf, u32 btf_id) +{ + if (!btf_is_kernel(btf)) + return false; + return btf_id_set_contains(&rcu_protected_types, btf_id); +} + +static bool rcu_safe_kptr(const struct btf_field *field) +{ + const struct btf_field_kptr *kptr = &field->kptr; + + return field->type == BPF_KPTR_REF && rcu_protected_object(kptr->btf, kptr->btf_id); +} + static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, int value_regno, int insn_idx, struct btf_field *kptr_field) @@ -4280,7 +4431,10 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, * value from map as PTR_TO_BTF_ID, with the correct type. */ mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, kptr_field->kptr.btf, - kptr_field->kptr.btf_id, PTR_MAYBE_NULL | PTR_UNTRUSTED); + kptr_field->kptr.btf_id, + rcu_safe_kptr(kptr_field) && in_rcu_cs(env) ? + PTR_MAYBE_NULL | MEM_RCU : + PTR_MAYBE_NULL | PTR_UNTRUSTED); /* For mark_ptr_or_null_reg */ val_reg->id = ++env->id_gen; } else if (class == BPF_STX) { @@ -5003,23 +5157,76 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) return 0; } -#define BTF_TYPE_SAFE_NESTED(__type) __PASTE(__type, __safe_fields) +#define BTF_TYPE_SAFE_RCU(__type) __PASTE(__type, __safe_rcu) +#define BTF_TYPE_SAFE_TRUSTED(__type) __PASTE(__type, __safe_trusted) + +/* + * Allow list few fields as RCU trusted or full trusted. + * This logic doesn't allow mix tagging and will be removed once GCC supports + * btf_type_tag. + */ -BTF_TYPE_SAFE_NESTED(struct task_struct) { +/* RCU trusted: these fields are trusted in RCU CS and never NULL */ +BTF_TYPE_SAFE_RCU(struct task_struct) { const cpumask_t *cpus_ptr; + struct css_set __rcu *cgroups; + struct task_struct __rcu *real_parent; + struct task_struct *group_leader; }; -static bool nested_ptr_is_trusted(struct bpf_verifier_env *env, - struct bpf_reg_state *reg, - int off) +BTF_TYPE_SAFE_RCU(struct css_set) { + struct cgroup *dfl_cgrp; +}; + +/* full trusted: these fields are trusted even outside of RCU CS and never NULL */ +BTF_TYPE_SAFE_TRUSTED(struct bpf_iter_meta) { + __bpf_md_ptr(struct seq_file *, seq); +}; + +BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task) { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct task_struct *, task); +}; + +BTF_TYPE_SAFE_TRUSTED(struct linux_binprm) { + struct file *file; +}; + +BTF_TYPE_SAFE_TRUSTED(struct file) { + struct inode *f_inode; +}; + +BTF_TYPE_SAFE_TRUSTED(struct dentry) { + /* no negative dentry-s in places where bpf can see it */ + struct inode *d_inode; +}; + +BTF_TYPE_SAFE_TRUSTED(struct socket) { + struct sock *sk; +}; + +static bool type_is_rcu(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + int off) { - /* If its parent is not trusted, it can't regain its trusted status. */ - if (!is_trusted_reg(reg)) - return false; + BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct task_struct)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct css_set)); - BTF_TYPE_EMIT(BTF_TYPE_SAFE_NESTED(struct task_struct)); + return btf_nested_type_is_trusted(&env->log, reg, off, "__safe_rcu"); +} - return btf_nested_type_is_trusted(&env->log, reg, off); +static bool type_is_trusted(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + int off) +{ + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter_meta)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct linux_binprm)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct file)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct dentry)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct socket)); + + return btf_nested_type_is_trusted(&env->log, reg, off, "__safe_trusted"); } static int check_ptr_to_btf_access(struct bpf_verifier_env *env, @@ -5105,41 +5312,56 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, if (ret < 0) return ret; - /* If this is an untrusted pointer, all pointers formed by walking it - * also inherit the untrusted flag. - */ - if (type_flag(reg->type) & PTR_UNTRUSTED) - flag |= PTR_UNTRUSTED; - - /* By default any pointer obtained from walking a trusted pointer is no - * longer trusted, unless the field being accessed has explicitly been - * marked as inheriting its parent's state of trust. - * - * An RCU-protected pointer can also be deemed trusted if we are in an - * RCU read region. This case is handled below. - */ - if (nested_ptr_is_trusted(env, reg, off)) - flag |= PTR_TRUSTED; - else - flag &= ~PTR_TRUSTED; + if (ret != PTR_TO_BTF_ID) { + /* just mark; */ - if (flag & MEM_RCU) { - /* Mark value register as MEM_RCU only if it is protected by - * bpf_rcu_read_lock() and the ptr reg is rcu or trusted. MEM_RCU - * itself can already indicate trustedness inside the rcu - * read lock region. Also mark rcu pointer as PTR_MAYBE_NULL since - * it could be null in some cases. + } else if (type_flag(reg->type) & PTR_UNTRUSTED) { + /* If this is an untrusted pointer, all pointers formed by walking it + * also inherit the untrusted flag. */ - if (!env->cur_state->active_rcu_lock || - !(is_trusted_reg(reg) || is_rcu_reg(reg))) - flag &= ~MEM_RCU; - else - flag |= PTR_MAYBE_NULL; - } else if (reg->type & MEM_RCU) { - /* ptr (reg) is marked as MEM_RCU, but the struct field is not tagged - * with __rcu. Mark the flag as PTR_UNTRUSTED conservatively. + flag = PTR_UNTRUSTED; + + } else if (is_trusted_reg(reg) || is_rcu_reg(reg)) { + /* By default any pointer obtained from walking a trusted pointer is no + * longer trusted, unless the field being accessed has explicitly been + * marked as inheriting its parent's state of trust (either full or RCU). + * For example: + * 'cgroups' pointer is untrusted if task->cgroups dereference + * happened in a sleepable program outside of bpf_rcu_read_lock() + * section. In a non-sleepable program it's trusted while in RCU CS (aka MEM_RCU). + * Note bpf_rcu_read_unlock() converts MEM_RCU pointers to PTR_UNTRUSTED. + * + * A regular RCU-protected pointer with __rcu tag can also be deemed + * trusted if we are in an RCU CS. Such pointer can be NULL. */ - flag |= PTR_UNTRUSTED; + if (type_is_trusted(env, reg, off)) { + flag |= PTR_TRUSTED; + } else if (in_rcu_cs(env) && !type_may_be_null(reg->type)) { + if (type_is_rcu(env, reg, off)) { + /* ignore __rcu tag and mark it MEM_RCU */ + flag |= MEM_RCU; + } else if (flag & MEM_RCU) { + /* __rcu tagged pointers can be NULL */ + flag |= PTR_MAYBE_NULL; + } else if (flag & (MEM_PERCPU | MEM_USER)) { + /* keep as-is */ + } else { + /* walking unknown pointers yields untrusted pointer */ + flag = PTR_UNTRUSTED; + } + } else { + /* + * If not in RCU CS or MEM_RCU pointer can be NULL then + * aggressively mark as untrusted otherwise such + * pointers will be plain PTR_TO_BTF_ID without flags + * and will be allowed to be passed into helpers for + * compat reasons. + */ + flag = PTR_UNTRUSTED; + } + } else { + /* Old compat. Deprecated */ + flag &= ~PTR_TRUSTED; } if (atype == BPF_READ && value_regno >= 0) @@ -6211,11 +6433,11 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno, * Helpers which do not mutate the bpf_dynptr set MEM_RDONLY in their argument * type, and declare it as 'const struct bpf_dynptr *' in their prototype. */ -int process_dynptr_func(struct bpf_verifier_env *env, int regno, - enum bpf_arg_type arg_type, struct bpf_call_arg_meta *meta) +static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn_idx, + enum bpf_arg_type arg_type) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; - int spi = 0; + int err; /* MEM_UNINIT and MEM_RDONLY are exclusive, when applied to an * ARG_PTR_TO_DYNPTR (or ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_*): @@ -6224,15 +6446,6 @@ int process_dynptr_func(struct bpf_verifier_env *env, int regno, verbose(env, "verifier internal error: misconfigured dynptr helper type flags\n"); return -EFAULT; } - /* CONST_PTR_TO_DYNPTR already has fixed and var_off as 0 due to - * check_func_arg_reg_off's logic. We only need to check offset - * and its alignment for PTR_TO_STACK. - */ - if (reg->type == PTR_TO_STACK) { - spi = dynptr_get_spi(env, reg); - if (spi < 0 && spi != -ERANGE) - return spi; - } /* MEM_UNINIT - Points to memory that is an appropriate candidate for * constructing a mutable bpf_dynptr object. @@ -6250,30 +6463,30 @@ int process_dynptr_func(struct bpf_verifier_env *env, int regno, * to. */ if (arg_type & MEM_UNINIT) { - if (!is_dynptr_reg_valid_uninit(env, reg, spi)) { + int i; + + if (!is_dynptr_reg_valid_uninit(env, reg)) { verbose(env, "Dynptr has to be an uninitialized dynptr\n"); return -EINVAL; } - /* We only support one dynptr being uninitialized at the moment, - * which is sufficient for the helper functions we have right now. - */ - if (meta->uninit_dynptr_regno) { - verbose(env, "verifier internal error: multiple uninitialized dynptr args\n"); - return -EFAULT; + /* we write BPF_DW bits (8 bytes) at a time */ + for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) { + err = check_mem_access(env, insn_idx, regno, + i, BPF_DW, BPF_WRITE, -1, false); + if (err) + return err; } - meta->uninit_dynptr_regno = regno; + err = mark_stack_slots_dynptr(env, reg, arg_type, insn_idx); } else /* MEM_RDONLY and None case from above */ { - int err; - /* For the reg->type == PTR_TO_STACK case, bpf_dynptr is never const */ if (reg->type == CONST_PTR_TO_DYNPTR && !(arg_type & MEM_RDONLY)) { verbose(env, "cannot pass pointer to const bpf_dynptr, the helper mutates it\n"); return -EINVAL; } - if (!is_dynptr_reg_valid_init(env, reg, spi)) { + if (!is_dynptr_reg_valid_init(env, reg)) { verbose(env, "Expected an initialized dynptr as arg #%d\n", regno); @@ -6282,30 +6495,15 @@ int process_dynptr_func(struct bpf_verifier_env *env, int regno, /* Fold modifiers (in this case, MEM_RDONLY) when checking expected type */ if (!is_dynptr_type_expected(env, reg, arg_type & ~MEM_RDONLY)) { - const char *err_extra = ""; - - switch (arg_type & DYNPTR_TYPE_FLAG_MASK) { - case DYNPTR_TYPE_LOCAL: - err_extra = "local"; - break; - case DYNPTR_TYPE_RINGBUF: - err_extra = "ringbuf"; - break; - default: - err_extra = "<unknown>"; - break; - } verbose(env, "Expected a dynptr of type %s as arg #%d\n", - err_extra, regno); + dynptr_type_str(arg_to_dynptr_type(arg_type)), regno); return -EINVAL; } err = mark_dynptr_read(env, reg); - if (err) - return err; } - return 0; + return err; } static bool arg_type_is_mem_size(enum bpf_arg_type type) @@ -6527,7 +6725,14 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, return -EACCES; found: - if (reg->type == PTR_TO_BTF_ID || reg->type & PTR_TRUSTED) { + if (base_type(reg->type) != PTR_TO_BTF_ID) + return 0; + + switch ((int)reg->type) { + case PTR_TO_BTF_ID: + case PTR_TO_BTF_ID | PTR_TRUSTED: + case PTR_TO_BTF_ID | MEM_RCU: + { /* For bpf_sk_release, it needs to match against first member * 'struct sock_common', hence make an exception for it. This * allows bpf_sk_release to work for multiple socket types. @@ -6563,13 +6768,23 @@ found: return -EACCES; } } - } else if (type_is_alloc(reg->type)) { + break; + } + case PTR_TO_BTF_ID | MEM_ALLOC: if (meta->func_id != BPF_FUNC_spin_lock && meta->func_id != BPF_FUNC_spin_unlock) { verbose(env, "verifier internal error: unimplemented handling of MEM_ALLOC\n"); return -EFAULT; } + /* Handled by helper specific checks */ + break; + case PTR_TO_BTF_ID | MEM_PERCPU: + case PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED: + /* Handled by helper specific checks */ + break; + default: + verbose(env, "verifier internal error: invalid PTR_TO_BTF_ID register for type match\n"); + return -EFAULT; } - return 0; } @@ -6656,7 +6871,6 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, case PTR_TO_BTF_ID | MEM_ALLOC: case PTR_TO_BTF_ID | PTR_TRUSTED: case PTR_TO_BTF_ID | MEM_RCU: - case PTR_TO_BTF_ID | MEM_ALLOC | PTR_TRUSTED: case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF: /* When referenced PTR_TO_BTF_ID is passed to release function, * its fixed offset must be 0. In the other cases, fixed offset @@ -6671,6 +6885,28 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, } } +static struct bpf_reg_state *get_dynptr_arg_reg(struct bpf_verifier_env *env, + const struct bpf_func_proto *fn, + struct bpf_reg_state *regs) +{ + struct bpf_reg_state *state = NULL; + int i; + + for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) + if (arg_type_is_dynptr(fn->arg_type[i])) { + if (state) { + verbose(env, "verifier internal error: multiple dynptr args\n"); + return NULL; + } + state = ®s[BPF_REG_1 + i]; + } + + if (!state) + verbose(env, "verifier internal error: no dynptr arg found\n"); + + return state; +} + static int dynptr_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); @@ -6697,9 +6933,28 @@ static int dynptr_ref_obj_id(struct bpf_verifier_env *env, struct bpf_reg_state return state->stack[spi].spilled_ptr.ref_obj_id; } +static enum bpf_dynptr_type dynptr_get_type(struct bpf_verifier_env *env, + struct bpf_reg_state *reg) +{ + struct bpf_func_state *state = func(env, reg); + int spi; + + if (reg->type == CONST_PTR_TO_DYNPTR) + return reg->dynptr.type; + + spi = __get_spi(reg->off); + if (spi < 0) { + verbose(env, "verifier internal error: invalid spi when querying dynptr type\n"); + return BPF_DYNPTR_TYPE_INVALID; + } + + return state->stack[spi].spilled_ptr.dynptr.type; +} + static int check_func_arg(struct bpf_verifier_env *env, u32 arg, struct bpf_call_arg_meta *meta, - const struct bpf_func_proto *fn) + const struct bpf_func_proto *fn, + int insn_idx) { u32 regno = BPF_REG_1 + arg; struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; @@ -6912,7 +7167,7 @@ skip_type_check: err = check_mem_size_reg(env, reg, regno, true, meta); break; case ARG_PTR_TO_DYNPTR: - err = process_dynptr_func(env, regno, arg_type, meta); + err = process_dynptr_func(env, regno, insn_idx, arg_type); if (err) return err; break; @@ -7131,22 +7386,26 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, break; case BPF_MAP_TYPE_SK_STORAGE: if (func_id != BPF_FUNC_sk_storage_get && - func_id != BPF_FUNC_sk_storage_delete) + func_id != BPF_FUNC_sk_storage_delete && + func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_INODE_STORAGE: if (func_id != BPF_FUNC_inode_storage_get && - func_id != BPF_FUNC_inode_storage_delete) + func_id != BPF_FUNC_inode_storage_delete && + func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_TASK_STORAGE: if (func_id != BPF_FUNC_task_storage_get && - func_id != BPF_FUNC_task_storage_delete) + func_id != BPF_FUNC_task_storage_delete && + func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_CGRP_STORAGE: if (func_id != BPF_FUNC_cgrp_storage_get && - func_id != BPF_FUNC_cgrp_storage_delete) + func_id != BPF_FUNC_cgrp_storage_delete && + func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_BLOOM_FILTER: @@ -7360,6 +7619,9 @@ static int check_func_proto(const struct bpf_func_proto *fn, int func_id) /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] * are now invalid, so turn them into unknown SCALAR_VALUE. + * + * This also applies to dynptr slices belonging to skb and xdp dynptrs, + * since these slices point to packet data. */ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { @@ -7367,8 +7629,8 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) struct bpf_reg_state *reg; bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ - if (reg_is_pkt_pointer_any(reg)) - __mark_reg_unknown(env, reg); + if (reg_is_pkt_pointer_any(reg) || reg_is_dynptr_slice_pkt(reg)) + mark_reg_invalid(env, reg); })); } @@ -7413,12 +7675,8 @@ static int release_reference(struct bpf_verifier_env *env, return err; bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ - if (reg->ref_obj_id == ref_obj_id) { - if (!env->allow_ptr_leaks) - __mark_reg_not_init(env, reg); - else - __mark_reg_unknown(env, reg); - } + if (reg->ref_obj_id == ref_obj_id) + mark_reg_invalid(env, reg); })); return 0; @@ -7431,7 +7689,7 @@ static void invalidate_non_owning_refs(struct bpf_verifier_env *env) bpf_for_each_reg_in_vstate(env->cur_state, unused, reg, ({ if (type_is_non_owning_ref(reg->type)) - __mark_reg_unknown(env, reg); + mark_reg_invalid(env, reg); })); } @@ -8202,7 +8460,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn meta.func_id = func_id; /* check args */ for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { - err = check_func_arg(env, i, &meta, fn); + err = check_func_arg(env, i, &meta, fn, insn_idx); if (err) return err; } @@ -8227,30 +8485,6 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs = cur_regs(env); - /* This can only be set for PTR_TO_STACK, as CONST_PTR_TO_DYNPTR cannot - * be reinitialized by any dynptr helper. Hence, mark_stack_slots_dynptr - * is safe to do directly. - */ - if (meta.uninit_dynptr_regno) { - if (regs[meta.uninit_dynptr_regno].type == CONST_PTR_TO_DYNPTR) { - verbose(env, "verifier internal error: CONST_PTR_TO_DYNPTR cannot be initialized\n"); - return -EFAULT; - } - /* we write BPF_DW bits (8 bytes) at a time */ - for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) { - err = check_mem_access(env, insn_idx, meta.uninit_dynptr_regno, - i, BPF_DW, BPF_WRITE, -1, false); - if (err) - return err; - } - - err = mark_stack_slots_dynptr(env, ®s[meta.uninit_dynptr_regno], - fn->arg_type[meta.uninit_dynptr_regno - BPF_REG_1], - insn_idx); - if (err) - return err; - } - if (meta.release_regno) { err = -EINVAL; /* This can only be set for PTR_TO_STACK, as CONST_PTR_TO_DYNPTR cannot @@ -8335,43 +8569,62 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn } break; case BPF_FUNC_dynptr_data: - for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { - if (arg_type_is_dynptr(fn->arg_type[i])) { - struct bpf_reg_state *reg = ®s[BPF_REG_1 + i]; - int id, ref_obj_id; + { + struct bpf_reg_state *reg; + int id, ref_obj_id; - if (meta.dynptr_id) { - verbose(env, "verifier internal error: meta.dynptr_id already set\n"); - return -EFAULT; - } + reg = get_dynptr_arg_reg(env, fn, regs); + if (!reg) + return -EFAULT; - if (meta.ref_obj_id) { - verbose(env, "verifier internal error: meta.ref_obj_id already set\n"); - return -EFAULT; - } - id = dynptr_id(env, reg); - if (id < 0) { - verbose(env, "verifier internal error: failed to obtain dynptr id\n"); - return id; - } + if (meta.dynptr_id) { + verbose(env, "verifier internal error: meta.dynptr_id already set\n"); + return -EFAULT; + } + if (meta.ref_obj_id) { + verbose(env, "verifier internal error: meta.ref_obj_id already set\n"); + return -EFAULT; + } - ref_obj_id = dynptr_ref_obj_id(env, reg); - if (ref_obj_id < 0) { - verbose(env, "verifier internal error: failed to obtain dynptr ref_obj_id\n"); - return ref_obj_id; - } + id = dynptr_id(env, reg); + if (id < 0) { + verbose(env, "verifier internal error: failed to obtain dynptr id\n"); + return id; + } - meta.dynptr_id = id; - meta.ref_obj_id = ref_obj_id; - break; - } + ref_obj_id = dynptr_ref_obj_id(env, reg); + if (ref_obj_id < 0) { + verbose(env, "verifier internal error: failed to obtain dynptr ref_obj_id\n"); + return ref_obj_id; } - if (i == MAX_BPF_FUNC_REG_ARGS) { - verbose(env, "verifier internal error: no dynptr in bpf_dynptr_data()\n"); + + meta.dynptr_id = id; + meta.ref_obj_id = ref_obj_id; + + break; + } + case BPF_FUNC_dynptr_write: + { + enum bpf_dynptr_type dynptr_type; + struct bpf_reg_state *reg; + + reg = get_dynptr_arg_reg(env, fn, regs); + if (!reg) return -EFAULT; - } + + dynptr_type = dynptr_get_type(env, reg); + if (dynptr_type == BPF_DYNPTR_TYPE_INVALID) + return -EFAULT; + + if (dynptr_type == BPF_DYNPTR_TYPE_SKB) + /* this will trigger clear_all_pkt_pointers(), which will + * invalidate all dynptr slices associated with the skb + */ + changes_data = true; + break; + } case BPF_FUNC_user_ringbuf_drain: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_user_ringbuf_callback_state); @@ -8600,36 +8853,6 @@ static void mark_btf_func_reg_size(struct bpf_verifier_env *env, u32 regno, } } -struct bpf_kfunc_call_arg_meta { - /* In parameters */ - struct btf *btf; - u32 func_id; - u32 kfunc_flags; - const struct btf_type *func_proto; - const char *func_name; - /* Out parameters */ - u32 ref_obj_id; - u8 release_regno; - bool r0_rdonly; - u32 ret_btf_id; - u64 r0_size; - u32 subprogno; - struct { - u64 value; - bool found; - } arg_constant; - struct { - struct btf *btf; - u32 btf_id; - } arg_obj_drop; - struct { - struct btf_field *field; - } arg_list_head; - struct { - struct btf_field *field; - } arg_rbtree_root; -}; - static bool is_kfunc_acquire(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_ACQUIRE; @@ -8701,6 +8924,19 @@ static bool is_kfunc_arg_mem_size(const struct btf *btf, return __kfunc_param_match_suffix(btf, arg, "__sz"); } +static bool is_kfunc_arg_const_mem_size(const struct btf *btf, + const struct btf_param *arg, + const struct bpf_reg_state *reg) +{ + const struct btf_type *t; + + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) + return false; + + return __kfunc_param_match_suffix(btf, arg, "__szk"); +} + static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg) { return __kfunc_param_match_suffix(btf, arg, "__k"); @@ -8716,6 +8952,11 @@ static bool is_kfunc_arg_alloc_obj(const struct btf *btf, const struct btf_param return __kfunc_param_match_suffix(btf, arg, "__alloc"); } +static bool is_kfunc_arg_uninit(const struct btf *btf, const struct btf_param *arg) +{ + return __kfunc_param_match_suffix(btf, arg, "__uninit"); +} + static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, const struct btf_param *arg, const char *name) @@ -8882,6 +9123,10 @@ enum special_kfunc_type { KF_bpf_rbtree_remove, KF_bpf_rbtree_add, KF_bpf_rbtree_first, + KF_bpf_dynptr_from_skb, + KF_bpf_dynptr_from_xdp, + KF_bpf_dynptr_slice, + KF_bpf_dynptr_slice_rdwr, }; BTF_SET_START(special_kfunc_set) @@ -8896,6 +9141,10 @@ BTF_ID(func, bpf_rdonly_cast) BTF_ID(func, bpf_rbtree_remove) BTF_ID(func, bpf_rbtree_add) BTF_ID(func, bpf_rbtree_first) +BTF_ID(func, bpf_dynptr_from_skb) +BTF_ID(func, bpf_dynptr_from_xdp) +BTF_ID(func, bpf_dynptr_slice) +BTF_ID(func, bpf_dynptr_slice_rdwr) BTF_SET_END(special_kfunc_set) BTF_ID_LIST(special_kfunc_list) @@ -8912,6 +9161,10 @@ BTF_ID(func, bpf_rcu_read_unlock) BTF_ID(func, bpf_rbtree_remove) BTF_ID(func, bpf_rbtree_add) BTF_ID(func, bpf_rbtree_first) +BTF_ID(func, bpf_dynptr_from_skb) +BTF_ID(func, bpf_dynptr_from_xdp) +BTF_ID(func, bpf_dynptr_slice) +BTF_ID(func, bpf_dynptr_slice_rdwr) static bool is_kfunc_bpf_rcu_read_lock(struct bpf_kfunc_call_arg_meta *meta) { @@ -8991,7 +9244,10 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, if (is_kfunc_arg_callback(env, meta->btf, &args[argno])) return KF_ARG_PTR_TO_CALLBACK; - if (argno + 1 < nargs && is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1])) + + if (argno + 1 < nargs && + (is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1]) || + is_kfunc_arg_const_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1]))) arg_mem_size = true; /* This is the catch all argument type of register types supported by @@ -9211,7 +9467,6 @@ static int check_reg_allocation_locked(struct bpf_verifier_env *env, struct bpf_ ptr = reg->map_ptr; break; case PTR_TO_BTF_ID | MEM_ALLOC: - case PTR_TO_BTF_ID | MEM_ALLOC | PTR_TRUSTED: ptr = reg->btf; break; default: @@ -9460,7 +9715,8 @@ static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env, &meta->arg_rbtree_root.field); } -static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta) +static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, + int insn_idx) { const char *func_name = meta->func_name, *ref_tname; const struct btf *btf = meta->btf; @@ -9543,7 +9799,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return -EINVAL; } - if (is_kfunc_trusted_args(meta) && + if ((is_kfunc_trusted_args(meta) || is_kfunc_rcu(meta)) && (register_is_null(reg) || type_may_be_null(reg->type))) { verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i); return -EACCES; @@ -9651,16 +9907,43 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return ret; break; case KF_ARG_PTR_TO_DYNPTR: + { + enum bpf_arg_type dynptr_arg_type = ARG_PTR_TO_DYNPTR; + if (reg->type != PTR_TO_STACK && reg->type != CONST_PTR_TO_DYNPTR) { verbose(env, "arg#%d expected pointer to stack or dynptr_ptr\n", i); return -EINVAL; } - ret = process_dynptr_func(env, regno, ARG_PTR_TO_DYNPTR | MEM_RDONLY, NULL); + if (reg->type == CONST_PTR_TO_DYNPTR) + dynptr_arg_type |= MEM_RDONLY; + + if (is_kfunc_arg_uninit(btf, &args[i])) + dynptr_arg_type |= MEM_UNINIT; + + if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) + dynptr_arg_type |= DYNPTR_TYPE_SKB; + else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_xdp]) + dynptr_arg_type |= DYNPTR_TYPE_XDP; + + ret = process_dynptr_func(env, regno, insn_idx, dynptr_arg_type); if (ret < 0) return ret; + + if (!(dynptr_arg_type & MEM_UNINIT)) { + int id = dynptr_id(env, reg); + + if (id < 0) { + verbose(env, "verifier internal error: failed to obtain dynptr id\n"); + return id; + } + meta->initialized_dynptr.id = id; + meta->initialized_dynptr.type = dynptr_get_type(env, reg); + } + break; + } case KF_ARG_PTR_TO_LIST_HEAD: if (reg->type != PTR_TO_MAP_VALUE && reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { @@ -9754,14 +10037,33 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return ret; break; case KF_ARG_PTR_TO_MEM_SIZE: - ret = check_kfunc_mem_size_reg(env, ®s[regno + 1], regno + 1); + { + struct bpf_reg_state *size_reg = ®s[regno + 1]; + const struct btf_param *size_arg = &args[i + 1]; + + ret = check_kfunc_mem_size_reg(env, size_reg, regno + 1); if (ret < 0) { verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1); return ret; } - /* Skip next '__sz' argument */ + + if (is_kfunc_arg_const_mem_size(meta->btf, size_arg, size_reg)) { + if (meta->arg_constant.found) { + verbose(env, "verifier internal error: only one constant argument permitted\n"); + return -EFAULT; + } + if (!tnum_is_const(size_reg->var_off)) { + verbose(env, "R%d must be a known constant\n", regno + 1); + return -EINVAL; + } + meta->arg_constant.found = true; + meta->arg_constant.value = size_reg->var_off.value; + } + + /* Skip next '__sz' or '__szk' argument */ i++; break; + } case KF_ARG_PTR_TO_CALLBACK: meta->subprogno = reg->subprogno; break; @@ -9833,10 +10135,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, rcu_lock = is_kfunc_bpf_rcu_read_lock(&meta); rcu_unlock = is_kfunc_bpf_rcu_read_unlock(&meta); - if ((rcu_lock || rcu_unlock) && !env->rcu_tag_supported) { - verbose(env, "no vmlinux btf rcu tag support for kfunc %s\n", func_name); - return -EACCES; - } if (env->cur_state->active_rcu_lock) { struct bpf_func_state *state; @@ -9865,7 +10163,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } /* Check the arguments */ - err = check_kfunc_args(env, &meta); + err = check_kfunc_args(env, &meta, insn_idx); if (err < 0) return err; /* In case of release function, we get register number of refcounted @@ -9996,6 +10294,42 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_UNTRUSTED; regs[BPF_REG_0].btf = desc_btf; regs[BPF_REG_0].btf_id = meta.arg_constant.value; + } else if (meta.func_id == special_kfunc_list[KF_bpf_dynptr_slice] || + meta.func_id == special_kfunc_list[KF_bpf_dynptr_slice_rdwr]) { + enum bpf_type_flag type_flag = get_dynptr_type_flag(meta.initialized_dynptr.type); + + mark_reg_known_zero(env, regs, BPF_REG_0); + + if (!meta.arg_constant.found) { + verbose(env, "verifier internal error: bpf_dynptr_slice(_rdwr) no constant size\n"); + return -EFAULT; + } + + regs[BPF_REG_0].mem_size = meta.arg_constant.value; + + /* PTR_MAYBE_NULL will be added when is_kfunc_ret_null is checked */ + regs[BPF_REG_0].type = PTR_TO_MEM | type_flag; + + if (meta.func_id == special_kfunc_list[KF_bpf_dynptr_slice]) { + regs[BPF_REG_0].type |= MEM_RDONLY; + } else { + /* this will set env->seen_direct_write to true */ + if (!may_access_direct_pkt_data(env, NULL, BPF_WRITE)) { + verbose(env, "the prog does not allow writes to packet data\n"); + return -EINVAL; + } + } + + if (!meta.initialized_dynptr.id) { + verbose(env, "verifier internal error: no dynptr id\n"); + return -EFAULT; + } + regs[BPF_REG_0].dynptr_id = meta.initialized_dynptr.id; + + /* we don't need to set BPF_REG_0's ref obj id + * because packet slices are not refcounted (see + * dynptr_type_refcounted) + */ } else { verbose(env, "kernel function %s unhandled dynamic return type\n", meta.func_name); @@ -10003,6 +10337,14 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } } else if (!__btf_type_is_struct(ptr_type)) { if (!meta.r0_size) { + __u32 sz; + + if (!IS_ERR(btf_resolve_size(desc_btf, ptr_type, &sz))) { + meta.r0_size = sz; + meta.r0_rdonly = true; + } + } + if (!meta.r0_size) { ptr_type_name = btf_name_by_offset(desc_btf, ptr_type->name_off); verbose(env, @@ -13157,44 +13499,43 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns, */ static int visit_insn(int t, struct bpf_verifier_env *env) { - struct bpf_insn *insns = env->prog->insnsi; + struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t]; int ret; - if (bpf_pseudo_func(insns + t)) + if (bpf_pseudo_func(insn)) return visit_func_call_insn(t, insns, env, true); /* All non-branch instructions have a single fall-through edge. */ - if (BPF_CLASS(insns[t].code) != BPF_JMP && - BPF_CLASS(insns[t].code) != BPF_JMP32) + if (BPF_CLASS(insn->code) != BPF_JMP && + BPF_CLASS(insn->code) != BPF_JMP32) return push_insn(t, t + 1, FALLTHROUGH, env, false); - switch (BPF_OP(insns[t].code)) { + switch (BPF_OP(insn->code)) { case BPF_EXIT: return DONE_EXPLORING; case BPF_CALL: - if (insns[t].imm == BPF_FUNC_timer_set_callback) + if (insn->src_reg == 0 && insn->imm == BPF_FUNC_timer_set_callback) /* Mark this call insn as a prune point to trigger * is_state_visited() check before call itself is * processed by __check_func_call(). Otherwise new * async state will be pushed for further exploration. */ mark_prune_point(env, t); - return visit_func_call_insn(t, insns, env, - insns[t].src_reg == BPF_PSEUDO_CALL); + return visit_func_call_insn(t, insns, env, insn->src_reg == BPF_PSEUDO_CALL); case BPF_JA: - if (BPF_SRC(insns[t].code) != BPF_K) + if (BPF_SRC(insn->code) != BPF_K) return -EINVAL; /* unconditional jump with single edge */ - ret = push_insn(t, t + insns[t].off + 1, FALLTHROUGH, env, + ret = push_insn(t, t + insn->off + 1, FALLTHROUGH, env, true); if (ret) return ret; - mark_prune_point(env, t + insns[t].off + 1); - mark_jmp_point(env, t + insns[t].off + 1); + mark_prune_point(env, t + insn->off + 1); + mark_jmp_point(env, t + insn->off + 1); return ret; @@ -13206,7 +13547,7 @@ static int visit_insn(int t, struct bpf_verifier_env *env) if (ret) return ret; - return push_insn(t, t + insns[t].off + 1, BRANCH, env, true); + return push_insn(t, t + insn->off + 1, BRANCH, env, true); } } @@ -13882,13 +14223,17 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, tnum_in(rold->var_off, rcur->var_off); case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: + case PTR_TO_MEM: + case PTR_TO_BUF: + case PTR_TO_TP_BUFFER: /* If the new min/max/var_off satisfy the old ones and * everything else matches, we are OK. */ return memcmp(rold, rcur, offsetof(struct bpf_reg_state, var_off)) == 0 && range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off) && - check_ids(rold->id, rcur->id, idmap); + check_ids(rold->id, rcur->id, idmap) && + check_ids(rold->ref_obj_id, rcur->ref_obj_id, idmap); case PTR_TO_PACKET_META: case PTR_TO_PACKET: /* We must have at least as much range as the old ptr @@ -14320,7 +14665,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * This threshold shouldn't be too high either, since states * at the end of the loop are likely to be useful in pruning. */ - if (env->jmps_processed - env->prev_jmps_processed < 20 && + if (!env->test_state_freq && + env->jmps_processed - env->prev_jmps_processed < 20 && env->insn_processed - env->prev_insn_processed < 100) add_new_state = false; goto miss; @@ -14509,6 +14855,44 @@ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev) !reg_type_mismatch_ok(prev)); } +static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type type, + bool allow_trust_missmatch) +{ + enum bpf_reg_type *prev_type = &env->insn_aux_data[env->insn_idx].ptr_type; + + if (*prev_type == NOT_INIT) { + /* Saw a valid insn + * dst_reg = *(u32 *)(src_reg + off) + * save type to validate intersecting paths + */ + *prev_type = type; + } else if (reg_type_mismatch(type, *prev_type)) { + /* Abuser program is trying to use the same insn + * dst_reg = *(u32*) (src_reg + off) + * with different pointer types: + * src_reg == ctx in one branch and + * src_reg == stack|map in some other branch. + * Reject it. + */ + if (allow_trust_missmatch && + base_type(type) == PTR_TO_BTF_ID && + base_type(*prev_type) == PTR_TO_BTF_ID) { + /* + * Have to support a use case when one path through + * the program yields TRUSTED pointer while another + * is UNTRUSTED. Fallback to UNTRUSTED to generate + * BPF_PROBE_MEM. + */ + *prev_type = PTR_TO_BTF_ID | PTR_UNTRUSTED; + } else { + verbose(env, "same insn cannot be used with different pointers\n"); + return -EINVAL; + } + } + + return 0; +} + static int do_check(struct bpf_verifier_env *env) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); @@ -14618,7 +15002,7 @@ static int do_check(struct bpf_verifier_env *env) return err; } else if (class == BPF_LDX) { - enum bpf_reg_type *prev_src_type, src_reg_type; + enum bpf_reg_type src_reg_type; /* check for reserved fields is already done */ @@ -14642,29 +15026,11 @@ static int do_check(struct bpf_verifier_env *env) if (err) return err; - prev_src_type = &env->insn_aux_data[env->insn_idx].ptr_type; - - if (*prev_src_type == NOT_INIT) { - /* saw a valid insn - * dst_reg = *(u32 *)(src_reg + off) - * save type to validate intersecting paths - */ - *prev_src_type = src_reg_type; - - } else if (reg_type_mismatch(src_reg_type, *prev_src_type)) { - /* ABuser program is trying to use the same insn - * dst_reg = *(u32*) (src_reg + off) - * with different pointer types: - * src_reg == ctx in one branch and - * src_reg == stack|map in some other branch. - * Reject it. - */ - verbose(env, "same insn cannot be used with different pointers\n"); - return -EINVAL; - } - + err = save_aux_ptr_type(env, src_reg_type, true); + if (err) + return err; } else if (class == BPF_STX) { - enum bpf_reg_type *prev_dst_type, dst_reg_type; + enum bpf_reg_type dst_reg_type; if (BPF_MODE(insn->code) == BPF_ATOMIC) { err = check_atomic(env, env->insn_idx, insn); @@ -14697,16 +15063,12 @@ static int do_check(struct bpf_verifier_env *env) if (err) return err; - prev_dst_type = &env->insn_aux_data[env->insn_idx].ptr_type; - - if (*prev_dst_type == NOT_INIT) { - *prev_dst_type = dst_reg_type; - } else if (reg_type_mismatch(dst_reg_type, *prev_dst_type)) { - verbose(env, "same insn cannot be used with different pointers\n"); - return -EINVAL; - } - + err = save_aux_ptr_type(env, dst_reg_type, false); + if (err) + return err; } else if (class == BPF_ST) { + enum bpf_reg_type dst_reg_type; + if (BPF_MODE(insn->code) != BPF_MEM || insn->src_reg != BPF_REG_0) { verbose(env, "BPF_ST uses reserved fields\n"); @@ -14717,12 +15079,7 @@ static int do_check(struct bpf_verifier_env *env) if (err) return err; - if (is_ctx_reg(env, insn->dst_reg)) { - verbose(env, "BPF_ST stores into R%d %s is not allowed\n", - insn->dst_reg, - reg_type_str(env, reg_state(env, insn->dst_reg)->type)); - return -EACCES; - } + dst_reg_type = regs[insn->dst_reg].type; /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, env->insn_idx, insn->dst_reg, @@ -14731,6 +15088,9 @@ static int do_check(struct bpf_verifier_env *env) if (err) return err; + err = save_aux_ptr_type(env, dst_reg_type, false); + if (err) + return err; } else if (class == BPF_JMP || class == BPF_JMP32) { u8 opcode = BPF_OP(insn->code); @@ -14765,6 +15125,8 @@ static int do_check(struct bpf_verifier_env *env) err = check_helper_call(env, insn, &env->insn_idx); if (err) return err; + + mark_reg_scratched(env, BPF_REG_0); } else if (opcode == BPF_JA) { if (BPF_SRC(insn->code) != BPF_K || insn->imm != 0 || @@ -15839,14 +16201,12 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) for (i = 0; i < insn_cnt; i++, insn++) { bpf_convert_ctx_access_t convert_ctx_access; - bool ctx_access; if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) || insn->code == (BPF_LDX | BPF_MEM | BPF_H) || insn->code == (BPF_LDX | BPF_MEM | BPF_W) || insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) { type = BPF_READ; - ctx_access = true; } else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) || insn->code == (BPF_STX | BPF_MEM | BPF_H) || insn->code == (BPF_STX | BPF_MEM | BPF_W) || @@ -15856,7 +16216,6 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) insn->code == (BPF_ST | BPF_MEM | BPF_W) || insn->code == (BPF_ST | BPF_MEM | BPF_DW)) { type = BPF_WRITE; - ctx_access = BPF_CLASS(insn->code) == BPF_STX; } else { continue; } @@ -15879,9 +16238,6 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) continue; } - if (!ctx_access) - continue; - switch ((int)env->insn_aux_data[i + delta].ptr_type) { case PTR_TO_CTX: if (!ops->convert_ctx_access) @@ -16330,6 +16686,17 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, desc->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) { insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1); *cnt = 1; + } else if (desc->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) { + bool seen_direct_write = env->seen_direct_write; + bool is_rdonly = !may_access_direct_pkt_data(env, NULL, BPF_WRITE); + + if (is_rdonly) + insn->imm = BPF_CALL_IMM(bpf_dynptr_from_skb_rdonly); + + /* restore env->seen_direct_write to its original value, since + * may_access_direct_pkt_data mutates it + */ + env->seen_direct_write = seen_direct_write; } return 0; } @@ -17721,8 +18088,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) env->bypass_spec_v1 = bpf_bypass_spec_v1(); env->bypass_spec_v4 = bpf_bypass_spec_v4(); env->bpf_capable = bpf_capable(); - env->rcu_tag_supported = btf_vmlinux && - btf_find_by_name_kind(btf_vmlinux, "rcu", BTF_KIND_TYPE_TAG) > 0; if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; |