diff options
Diffstat (limited to 'kernel')
71 files changed, 2153 insertions, 999 deletions
diff --git a/kernel/audit.c b/kernel/audit.c index 121d37e700a6..4cebadb5f30d 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -718,7 +718,7 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, { int rc = 0; struct sk_buff *skb; - static unsigned int failed = 0; + unsigned int failed = 0; /* NOTE: kauditd_thread takes care of all our locking, we just use * the netlink info passed to us (e.g. sk and portid) */ @@ -735,32 +735,30 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, continue; } +retry: /* grab an extra skb reference in case of error */ skb_get(skb); rc = netlink_unicast(sk, skb, portid, 0); if (rc < 0) { - /* fatal failure for our queue flush attempt? */ + /* send failed - try a few times unless fatal error */ if (++failed >= retry_limit || rc == -ECONNREFUSED || rc == -EPERM) { - /* yes - error processing for the queue */ sk = NULL; if (err_hook) (*err_hook)(skb); - if (!skb_hook) - goto out; - /* keep processing with the skb_hook */ + if (rc == -EAGAIN) + rc = 0; + /* continue to drain the queue */ continue; } else - /* no - requeue to preserve ordering */ - skb_queue_head(queue, skb); + goto retry; } else { - /* it worked - drop the extra reference and continue */ + /* skb sent - drop the extra reference and continue */ consume_skb(skb); failed = 0; } } -out: return (rc >= 0 ? 0 : rc); } @@ -1609,7 +1607,8 @@ static int __net_init audit_net_init(struct net *net) audit_panic("cannot initialize netlink socket in namespace"); return -ENOMEM; } - aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; + /* limit the timeout in case auditd is blocked/stopped */ + aunet->sk->sk_sndtimeo = HZ / 10; return 0; } diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index cf6ca339f3cd..c1a9be6a4b9f 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -36,3 +36,7 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o obj-${CONFIG_BPF_LSM} += bpf_lsm.o endif obj-$(CONFIG_BPF_PRELOAD) += preload/ + +obj-$(CONFIG_BPF_SYSCALL) += relo_core.o +$(obj)/relo_core.o: $(srctree)/tools/lib/bpf/relo_core.c FORCE + $(call if_changed_rule,cc_o_c) diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index 277a05e9c984..b141a1346f72 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -82,6 +82,11 @@ static int bloom_map_delete_elem(struct bpf_map *map, void *value) return -EOPNOTSUPP; } +static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -EOPNOTSUPP; +} + static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) { u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; @@ -192,6 +197,7 @@ const struct bpf_map_ops bloom_filter_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = bloom_map_alloc, .map_free = bloom_map_free, + .map_get_next_key = bloom_map_get_next_key, .map_push_elem = bloom_map_push_elem, .map_peek_elem = bloom_map_peek_elem, .map_pop_elem = bloom_map_pop_elem, diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 96ceed0e0fb5..e29d9e3d853e 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -17,6 +17,7 @@ #include <linux/bpf_lsm.h> #include <linux/btf_ids.h> #include <linux/fdtable.h> +#include <linux/rcupdate_trace.h> DEFINE_BPF_STORAGE_CACHE(inode_cache); @@ -44,7 +45,8 @@ static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode, if (!bsb) return NULL; - inode_storage = rcu_dereference(bsb->storage); + inode_storage = + rcu_dereference_check(bsb->storage, bpf_rcu_lock_held()); if (!inode_storage) return NULL; @@ -172,6 +174,7 @@ BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode, { struct bpf_local_storage_data *sdata; + WARN_ON_ONCE(!bpf_rcu_lock_held()); if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) return (unsigned long)NULL; @@ -204,6 +207,7 @@ BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode, BPF_CALL_2(bpf_inode_storage_delete, struct bpf_map *, map, struct inode *, inode) { + WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!inode) return -EINVAL; diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index b2ee45064e06..b7aef5b3416d 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -714,3 +714,38 @@ const struct bpf_func_proto bpf_for_each_map_elem_proto = { .arg3_type = ARG_PTR_TO_STACK_OR_NULL, .arg4_type = ARG_ANYTHING, }; + +/* maximum number of loops */ +#define MAX_LOOPS BIT(23) + +BPF_CALL_4(bpf_loop, u32, nr_loops, void *, callback_fn, void *, callback_ctx, + u64, flags) +{ + bpf_callback_t callback = (bpf_callback_t)callback_fn; + u64 ret; + u32 i; + + if (flags) + return -EINVAL; + if (nr_loops > MAX_LOOPS) + return -E2BIG; + + for (i = 0; i < nr_loops; i++) { + ret = callback((u64)i, (u64)(long)callback_ctx, 0, 0, 0); + /* return value: 0 - continue, 1 - stop and return */ + if (ret) + return i + 1; + } + + return i; +} + +const struct bpf_func_proto bpf_loop_proto = { + .func = bpf_loop, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_PTR_TO_FUNC, + .arg3_type = ARG_PTR_TO_STACK_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index b305270b7a4b..71de2a89869c 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -11,6 +11,9 @@ #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> +#include <linux/rcupdate.h> +#include <linux/rcupdate_trace.h> +#include <linux/rcupdate_wait.h> #define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE) @@ -81,6 +84,22 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, return NULL; } +void bpf_local_storage_free_rcu(struct rcu_head *rcu) +{ + struct bpf_local_storage *local_storage; + + local_storage = container_of(rcu, struct bpf_local_storage, rcu); + kfree_rcu(local_storage, rcu); +} + +static void bpf_selem_free_rcu(struct rcu_head *rcu) +{ + struct bpf_local_storage_elem *selem; + + selem = container_of(rcu, struct bpf_local_storage_elem, rcu); + kfree_rcu(selem, rcu); +} + /* local_storage->lock must be held and selem->local_storage == local_storage. * The caller must ensure selem->smap is still valid to be * dereferenced for its smap->elem_size and smap->cache_idx. @@ -93,7 +112,7 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, bool free_local_storage; void *owner; - smap = rcu_dereference(SDATA(selem)->smap); + smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); owner = local_storage->owner; /* All uncharging on the owner must be done first. @@ -118,12 +137,12 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, * * Although the unlock will be done under * rcu_read_lock(), it is more intutivie to - * read if kfree_rcu(local_storage, rcu) is done + * read if the freeing of the storage is done * after the raw_spin_unlock_bh(&local_storage->lock). * * Hence, a "bool free_local_storage" is returned - * to the caller which then calls the kfree_rcu() - * after unlock. + * to the caller which then calls then frees the storage after + * all the RCU grace periods have expired. */ } hlist_del_init_rcu(&selem->snode); @@ -131,8 +150,7 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, SDATA(selem)) RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); - kfree_rcu(selem, rcu); - + call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_rcu); return free_local_storage; } @@ -146,7 +164,8 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem) /* selem has already been unlinked from sk */ return; - local_storage = rcu_dereference(selem->local_storage); + local_storage = rcu_dereference_check(selem->local_storage, + bpf_rcu_lock_held()); raw_spin_lock_irqsave(&local_storage->lock, flags); if (likely(selem_linked_to_storage(selem))) free_local_storage = bpf_selem_unlink_storage_nolock( @@ -154,7 +173,8 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem) raw_spin_unlock_irqrestore(&local_storage->lock, flags); if (free_local_storage) - kfree_rcu(local_storage, rcu); + call_rcu_tasks_trace(&local_storage->rcu, + bpf_local_storage_free_rcu); } void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, @@ -174,7 +194,7 @@ void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) /* selem has already be unlinked from smap */ return; - smap = rcu_dereference(SDATA(selem)->smap); + smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); b = select_bucket(smap, selem); raw_spin_lock_irqsave(&b->lock, flags); if (likely(selem_linked_to_map(selem))) @@ -213,12 +233,14 @@ bpf_local_storage_lookup(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem; /* Fast path (cache hit) */ - sdata = rcu_dereference(local_storage->cache[smap->cache_idx]); + sdata = rcu_dereference_check(local_storage->cache[smap->cache_idx], + bpf_rcu_lock_held()); if (sdata && rcu_access_pointer(sdata->smap) == smap) return sdata; /* Slow path (cache miss) */ - hlist_for_each_entry_rcu(selem, &local_storage->list, snode) + hlist_for_each_entry_rcu(selem, &local_storage->list, snode, + rcu_read_lock_trace_held()) if (rcu_access_pointer(SDATA(selem)->smap) == smap) break; @@ -306,7 +328,8 @@ int bpf_local_storage_alloc(void *owner, * bucket->list, first_selem can be freed immediately * (instead of kfree_rcu) because * bpf_local_storage_map_free() does a - * synchronize_rcu() before walking the bucket->list. + * synchronize_rcu_mult (waiting for both sleepable and + * normal programs) before walking the bucket->list. * Hence, no one is accessing selem from the * bucket->list under rcu_read_lock(). */ @@ -342,7 +365,8 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, !map_value_has_spin_lock(&smap->map))) return ERR_PTR(-EINVAL); - local_storage = rcu_dereference(*owner_storage(smap, owner)); + local_storage = rcu_dereference_check(*owner_storage(smap, owner), + bpf_rcu_lock_held()); if (!local_storage || hlist_empty(&local_storage->list)) { /* Very first elem for the owner */ err = check_flags(NULL, map_flags); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 8ecfe4752769..21069dbe9138 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -165,7 +165,7 @@ void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) break; } - if (btf_member_bitfield_size(t, member)) { + if (__btf_member_bitfield_size(t, member)) { pr_warn("bit field member %s in struct %s is not supported\n", mname, st_ops->name); break; @@ -296,7 +296,7 @@ static int check_zero_holes(const struct btf_type *t, void *data) const struct btf_type *mtype; for_each_member(i, t, member) { - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; if (moff > prev_mend && memchr_inv(data + prev_mend, 0, moff - prev_mend)) return -EINVAL; @@ -387,7 +387,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, struct bpf_prog *prog; u32 moff; - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); if (ptype == module_type) { if (*(void **)(udata + moff)) diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index ebfa8bc90892..5da7bed0f5f6 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -17,6 +17,7 @@ #include <uapi/linux/btf.h> #include <linux/btf_ids.h> #include <linux/fdtable.h> +#include <linux/rcupdate_trace.h> DEFINE_BPF_STORAGE_CACHE(task_cache); @@ -59,7 +60,8 @@ task_storage_lookup(struct task_struct *task, struct bpf_map *map, struct bpf_local_storage *task_storage; struct bpf_local_storage_map *smap; - task_storage = rcu_dereference(task->bpf_storage); + task_storage = + rcu_dereference_check(task->bpf_storage, bpf_rcu_lock_held()); if (!task_storage) return NULL; @@ -229,6 +231,7 @@ BPF_CALL_4(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *, { struct bpf_local_storage_data *sdata; + WARN_ON_ONCE(!bpf_rcu_lock_held()); if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) return (unsigned long)NULL; @@ -260,6 +263,7 @@ BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *, { int ret; + WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!task) return -EINVAL; @@ -323,7 +327,7 @@ const struct bpf_func_proto bpf_task_storage_get_proto = { .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID, - .arg2_btf_id = &btf_task_struct_ids[0], + .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; @@ -334,5 +338,5 @@ const struct bpf_func_proto bpf_task_storage_delete_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID, - .arg2_btf_id = &btf_task_struct_ids[0], + .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index dbc3ad07e21b..33bb8ae4a804 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -25,6 +25,7 @@ #include <linux/kobject.h> #include <linux/sysfs.h> #include <net/sock.h> +#include "../tools/lib/bpf/relo_core.h" /* BTF (BPF Type Format) is the meta data format which describes * the data types of BPF program/map. Hence, it basically focus @@ -282,6 +283,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", [BTF_KIND_DECL_TAG] = "DECL_TAG", + [BTF_KIND_TYPE_TAG] = "TYPE_TAG", }; const char *btf_type_str(const struct btf_type *t) @@ -418,6 +420,7 @@ static bool btf_type_is_modifier(const struct btf_type *t) case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + case BTF_KIND_TYPE_TAG: return true; } @@ -834,7 +837,7 @@ static const char *btf_show_name(struct btf_show *show) const char *ptr_suffix = &ptr_suffixes[strlen(ptr_suffixes)]; const char *name = NULL, *prefix = "", *parens = ""; const struct btf_member *m = show->state.member; - const struct btf_type *t = show->state.type; + const struct btf_type *t; const struct btf_array *array; u32 id = show->state.type_id; const char *member = NULL; @@ -1737,6 +1740,7 @@ __btf_resolve_size(const struct btf *btf, const struct btf_type *type, case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + case BTF_KIND_TYPE_TAG: id = type->type; type = btf_type_by_id(btf, type->type); break; @@ -2345,6 +2349,8 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { + const char *value; + if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; @@ -2360,7 +2366,7 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env, return -EINVAL; } - /* typedef type must have a valid name, and other ref types, + /* typedef/type_tag type must have a valid name, and other ref types, * volatile, const, restrict, should have a null name. */ if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF) { @@ -2369,6 +2375,12 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env, btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } + } else if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPE_TAG) { + value = btf_name_by_offset(env->btf, t->name_off); + if (!value || !value[0]) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } } else { if (t->name_off) { btf_verifier_log_type(env, t, "Invalid name"); @@ -2958,7 +2970,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, return -EINVAL; } - offset = btf_member_bit_offset(t, member); + offset = __btf_member_bit_offset(t, member); if (is_union && offset) { btf_verifier_log_member(env, t, member, "Invalid member bits_offset"); @@ -3083,7 +3095,7 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t if (off != -ENOENT) /* only one such field is allowed */ return -E2BIG; - off = btf_member_bit_offset(t, member); + off = __btf_member_bit_offset(t, member); if (off % 8) /* valid C code cannot generate such BTF */ return -EINVAL; @@ -3173,8 +3185,8 @@ static void __btf_struct_show(const struct btf *btf, const struct btf_type *t, btf_show_start_member(show, member); - member_offset = btf_member_bit_offset(t, member); - bitfield_size = btf_member_bitfield_size(t, member); + member_offset = __btf_member_bit_offset(t, member); + bitfield_size = __btf_member_bitfield_size(t, member); bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset); bits8_offset = BITS_PER_BYTE_MASKED(member_offset); if (bitfield_size) { @@ -4059,6 +4071,7 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_DATASEC] = &datasec_ops, [BTF_KIND_FLOAT] = &float_ops, [BTF_KIND_DECL_TAG] = &decl_tag_ops, + [BTF_KIND_TYPE_TAG] = &modifier_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, @@ -4460,8 +4473,7 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, log->len_total = log_size; /* log attributes have to be sane */ - if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 || - !log->level || !log->ubuf) { + if (!bpf_verifier_log_attr_valid(log)) { err = -EINVAL; goto errout; } @@ -4814,7 +4826,7 @@ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog) return prog->aux->attach_btf; } -static bool is_string_ptr(struct btf *btf, const struct btf_type *t) +static bool is_int_ptr(struct btf *btf, const struct btf_type *t) { /* t comes in already as a pointer */ t = btf_type_by_id(btf, t->type); @@ -4823,8 +4835,7 @@ static bool is_string_ptr(struct btf *btf, const struct btf_type *t) if (BTF_INFO_KIND(t->info) == BTF_KIND_CONST) t = btf_type_by_id(btf, t->type); - /* char, signed char, unsigned char */ - return btf_type_is_int(t) && t->size == 1; + return btf_type_is_int(t); } bool btf_ctx_access(int off, int size, enum bpf_access_type type, @@ -4929,10 +4940,12 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, /* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */ for (i = 0; i < prog->aux->ctx_arg_info_size; i++) { const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i]; + u32 type, flag; - if (ctx_arg_info->offset == off && - (ctx_arg_info->reg_type == PTR_TO_RDONLY_BUF_OR_NULL || - ctx_arg_info->reg_type == PTR_TO_RDWR_BUF_OR_NULL)) { + type = base_type(ctx_arg_info->reg_type); + flag = type_flag(ctx_arg_info->reg_type); + if (ctx_arg_info->offset == off && type == PTR_TO_BUF && + (flag & PTR_MAYBE_NULL)) { info->reg_type = ctx_arg_info->reg_type; return true; } @@ -4945,7 +4958,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, */ return true; - if (is_string_ptr(btf, t)) + if (is_int_ptr(btf, t)) return true; /* this is a pointer to another type */ @@ -5048,7 +5061,7 @@ again: if (array_elem->nelems != 0) goto error; - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; if (off < moff) goto error; @@ -5071,14 +5084,14 @@ error: for_each_member(i, t, member) { /* offset of the field in bytes */ - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; if (off + size <= moff) /* won't find anything, field is already too far */ break; - if (btf_member_bitfield_size(t, member)) { - u32 end_bit = btf_member_bit_offset(t, member) + - btf_member_bitfield_size(t, member); + if (__btf_member_bitfield_size(t, member)) { + u32 end_bit = __btf_member_bit_offset(t, member) + + __btf_member_bitfield_size(t, member); /* off <= moff instead of off == moff because clang * does not generate a BTF member for anonymous @@ -5563,12 +5576,53 @@ static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { #endif }; +/* Returns true if struct is composed of scalars, 4 levels of nesting allowed */ +static bool __btf_type_is_scalar_struct(struct bpf_verifier_log *log, + const struct btf *btf, + const struct btf_type *t, int rec) +{ + const struct btf_type *member_type; + const struct btf_member *member; + u32 i; + + if (!btf_type_is_struct(t)) + return false; + + for_each_member(i, t, member) { + const struct btf_array *array; + + member_type = btf_type_skip_modifiers(btf, member->type, NULL); + if (btf_type_is_struct(member_type)) { + if (rec >= 3) { + bpf_log(log, "max struct nesting depth exceeded\n"); + return false; + } + if (!__btf_type_is_scalar_struct(log, btf, member_type, rec + 1)) + return false; + continue; + } + if (btf_type_is_array(member_type)) { + array = btf_type_array(member_type); + if (!array->nelems) + return false; + member_type = btf_type_skip_modifiers(btf, array->type, NULL); + if (!btf_type_is_scalar(member_type)) + return false; + continue; + } + if (!btf_type_is_scalar(member_type)) + return false; + } + return true; +} + static int btf_check_func_arg_match(struct bpf_verifier_env *env, const struct btf *btf, u32 func_id, struct bpf_reg_state *regs, bool ptr_to_mem_ok) { struct bpf_verifier_log *log = &env->log; + bool is_kfunc = btf_is_kernel(btf); const char *func_name, *ref_tname; const struct btf_type *t, *ref_t; const struct btf_param *args; @@ -5621,7 +5675,20 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id); ref_tname = btf_name_by_offset(btf, ref_t->name_off); - if (btf_is_kernel(btf)) { + if (btf_get_prog_ctx_type(log, btf, t, + env->prog->type, i)) { + /* If function expects ctx type in BTF check that caller + * is passing PTR_TO_CTX. + */ + if (reg->type != PTR_TO_CTX) { + bpf_log(log, + "arg#%d expected pointer to ctx, but got %s\n", + i, btf_type_str(t)); + return -EINVAL; + } + if (check_ctx_reg(env, reg, regno)) + return -EINVAL; + } else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || reg2btf_ids[reg->type])) { const struct btf_type *reg_ref_t; const struct btf *reg_btf; const char *reg_ref_tname; @@ -5637,14 +5704,9 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, if (reg->type == PTR_TO_BTF_ID) { reg_btf = reg->btf; reg_ref_id = reg->btf_id; - } else if (reg2btf_ids[reg->type]) { + } else { reg_btf = btf_vmlinux; reg_ref_id = *reg2btf_ids[reg->type]; - } else { - bpf_log(log, "kernel function %s args#%d expected pointer to %s %s but R%d is not a pointer to btf_id\n", - func_name, i, - btf_type_str(ref_t), ref_tname, regno); - return -EINVAL; } reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, @@ -5660,23 +5722,24 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, reg_ref_tname); return -EINVAL; } - } else if (btf_get_prog_ctx_type(log, btf, t, - env->prog->type, i)) { - /* If function expects ctx type in BTF check that caller - * is passing PTR_TO_CTX. - */ - if (reg->type != PTR_TO_CTX) { - bpf_log(log, - "arg#%d expected pointer to ctx, but got %s\n", - i, btf_type_str(t)); - return -EINVAL; - } - if (check_ctx_reg(env, reg, regno)) - return -EINVAL; } else if (ptr_to_mem_ok) { const struct btf_type *resolve_ret; u32 type_size; + if (is_kfunc) { + /* Permit pointer to mem, but only when argument + * type is pointer to scalar, or struct composed + * (recursively) of scalars. + */ + if (!btf_type_is_scalar(ref_t) && + !__btf_type_is_scalar_struct(log, btf, ref_t, 0)) { + bpf_log(log, + "arg#%d pointer type %s %s must point to scalar or struct with scalar\n", + i, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + } + resolve_ret = btf_resolve_size(btf, ref_t, &type_size); if (IS_ERR(resolve_ret)) { bpf_log(log, @@ -5689,6 +5752,8 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, if (check_mem_reg(env, reg, regno, type_size)) return -EINVAL; } else { + bpf_log(log, "reg type unsupported for arg#%d %sfunction %s#%d\n", i, + is_kfunc ? "kernel " : "", func_name, func_id); return -EINVAL; } } @@ -5738,7 +5803,7 @@ int btf_check_kfunc_arg_match(struct bpf_verifier_env *env, const struct btf *btf, u32 func_id, struct bpf_reg_state *regs) { - return btf_check_func_arg_match(env, btf, func_id, regs, false); + return btf_check_func_arg_match(env, btf, func_id, regs, true); } /* Convert BTF of a function into bpf_reg_state if possible @@ -5846,7 +5911,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, return -EINVAL; } - reg->type = PTR_TO_MEM_OR_NULL; + reg->type = PTR_TO_MEM | PTR_MAYBE_NULL; reg->id = ++env->id_gen; continue; @@ -6157,6 +6222,8 @@ btf_module_read(struct file *file, struct kobject *kobj, return len; } +static void purge_cand_cache(struct btf *btf); + static int btf_module_notify(struct notifier_block *nb, unsigned long op, void *module) { @@ -6191,6 +6258,7 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op, goto out; } + purge_cand_cache(NULL); mutex_lock(&btf_module_mutex); btf_mod->module = module; btf_mod->btf = btf; @@ -6233,6 +6301,7 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op, list_del(&btf_mod->list); if (btf_mod->sysfs_attr) sysfs_remove_bin_file(btf_kobj, btf_mod->sysfs_attr); + purge_cand_cache(btf_mod->btf); btf_put(btf_mod->btf); kfree(btf_mod->sysfs_attr); kfree(btf_mod); @@ -6336,21 +6405,19 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { .func = bpf_btf_find_by_name_kind, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; -BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct) +BTF_ID_LIST_GLOBAL(btf_tracing_ids, MAX_BTF_TRACING_TYPE) +#define BTF_TRACING_TYPE(name, type) BTF_ID(struct, type) +BTF_TRACING_TYPE_xxx +#undef BTF_TRACING_TYPE /* BTF ID set registration API for modules */ -struct kfunc_btf_id_list { - struct list_head list; - struct mutex mutex; -}; - #ifdef CONFIG_DEBUG_INFO_BTF_MODULES void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, @@ -6376,8 +6443,6 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, { struct kfunc_btf_id_set *s; - if (!owner) - return false; mutex_lock(&klist->mutex); list_for_each_entry(s, &klist->list, list) { if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) { @@ -6389,8 +6454,6 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, return false; } -#endif - #define DEFINE_KFUNC_BTF_ID_LIST(name) \ struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \ __MUTEX_INITIALIZER(name.mutex) }; \ @@ -6398,3 +6461,386 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list); DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list); + +#endif + +int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, + const struct btf *targ_btf, __u32 targ_id) +{ + return -EOPNOTSUPP; +} + +static bool bpf_core_is_flavor_sep(const char *s) +{ + /* check X___Y name pattern, where X and Y are not underscores */ + return s[0] != '_' && /* X */ + s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */ + s[4] != '_'; /* Y */ +} + +size_t bpf_core_essential_name_len(const char *name) +{ + size_t n = strlen(name); + int i; + + for (i = n - 5; i >= 0; i--) { + if (bpf_core_is_flavor_sep(name + i)) + return i + 1; + } + return n; +} + +struct bpf_cand_cache { + const char *name; + u32 name_len; + u16 kind; + u16 cnt; + struct { + const struct btf *btf; + u32 id; + } cands[]; +}; + +static void bpf_free_cands(struct bpf_cand_cache *cands) +{ + if (!cands->cnt) + /* empty candidate array was allocated on stack */ + return; + kfree(cands); +} + +static void bpf_free_cands_from_cache(struct bpf_cand_cache *cands) +{ + kfree(cands->name); + kfree(cands); +} + +#define VMLINUX_CAND_CACHE_SIZE 31 +static struct bpf_cand_cache *vmlinux_cand_cache[VMLINUX_CAND_CACHE_SIZE]; + +#define MODULE_CAND_CACHE_SIZE 31 +static struct bpf_cand_cache *module_cand_cache[MODULE_CAND_CACHE_SIZE]; + +static DEFINE_MUTEX(cand_cache_mutex); + +static void __print_cand_cache(struct bpf_verifier_log *log, + struct bpf_cand_cache **cache, + int cache_size) +{ + struct bpf_cand_cache *cc; + int i, j; + + for (i = 0; i < cache_size; i++) { + cc = cache[i]; + if (!cc) + continue; + bpf_log(log, "[%d]%s(", i, cc->name); + for (j = 0; j < cc->cnt; j++) { + bpf_log(log, "%d", cc->cands[j].id); + if (j < cc->cnt - 1) + bpf_log(log, " "); + } + bpf_log(log, "), "); + } +} + +static void print_cand_cache(struct bpf_verifier_log *log) +{ + mutex_lock(&cand_cache_mutex); + bpf_log(log, "vmlinux_cand_cache:"); + __print_cand_cache(log, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE); + bpf_log(log, "\nmodule_cand_cache:"); + __print_cand_cache(log, module_cand_cache, MODULE_CAND_CACHE_SIZE); + bpf_log(log, "\n"); + mutex_unlock(&cand_cache_mutex); +} + +static u32 hash_cands(struct bpf_cand_cache *cands) +{ + return jhash(cands->name, cands->name_len, 0); +} + +static struct bpf_cand_cache *check_cand_cache(struct bpf_cand_cache *cands, + struct bpf_cand_cache **cache, + int cache_size) +{ + struct bpf_cand_cache *cc = cache[hash_cands(cands) % cache_size]; + + if (cc && cc->name_len == cands->name_len && + !strncmp(cc->name, cands->name, cands->name_len)) + return cc; + return NULL; +} + +static size_t sizeof_cands(int cnt) +{ + return offsetof(struct bpf_cand_cache, cands[cnt]); +} + +static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands, + struct bpf_cand_cache **cache, + int cache_size) +{ + struct bpf_cand_cache **cc = &cache[hash_cands(cands) % cache_size], *new_cands; + + if (*cc) { + bpf_free_cands_from_cache(*cc); + *cc = NULL; + } + new_cands = kmemdup(cands, sizeof_cands(cands->cnt), GFP_KERNEL); + if (!new_cands) { + bpf_free_cands(cands); + return ERR_PTR(-ENOMEM); + } + /* strdup the name, since it will stay in cache. + * the cands->name points to strings in prog's BTF and the prog can be unloaded. + */ + new_cands->name = kmemdup_nul(cands->name, cands->name_len, GFP_KERNEL); + bpf_free_cands(cands); + if (!new_cands->name) { + kfree(new_cands); + return ERR_PTR(-ENOMEM); + } + *cc = new_cands; + return new_cands; +} + +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES +static void __purge_cand_cache(struct btf *btf, struct bpf_cand_cache **cache, + int cache_size) +{ + struct bpf_cand_cache *cc; + int i, j; + + for (i = 0; i < cache_size; i++) { + cc = cache[i]; + if (!cc) + continue; + if (!btf) { + /* when new module is loaded purge all of module_cand_cache, + * since new module might have candidates with the name + * that matches cached cands. + */ + bpf_free_cands_from_cache(cc); + cache[i] = NULL; + continue; + } + /* when module is unloaded purge cache entries + * that match module's btf + */ + for (j = 0; j < cc->cnt; j++) + if (cc->cands[j].btf == btf) { + bpf_free_cands_from_cache(cc); + cache[i] = NULL; + break; + } + } + +} + +static void purge_cand_cache(struct btf *btf) +{ + mutex_lock(&cand_cache_mutex); + __purge_cand_cache(btf, module_cand_cache, MODULE_CAND_CACHE_SIZE); + mutex_unlock(&cand_cache_mutex); +} +#endif + +static struct bpf_cand_cache * +bpf_core_add_cands(struct bpf_cand_cache *cands, const struct btf *targ_btf, + int targ_start_id) +{ + struct bpf_cand_cache *new_cands; + const struct btf_type *t; + const char *targ_name; + size_t targ_essent_len; + int n, i; + + n = btf_nr_types(targ_btf); + for (i = targ_start_id; i < n; i++) { + t = btf_type_by_id(targ_btf, i); + if (btf_kind(t) != cands->kind) + continue; + + targ_name = btf_name_by_offset(targ_btf, t->name_off); + if (!targ_name) + continue; + + /* the resched point is before strncmp to make sure that search + * for non-existing name will have a chance to schedule(). + */ + cond_resched(); + + if (strncmp(cands->name, targ_name, cands->name_len) != 0) + continue; + + targ_essent_len = bpf_core_essential_name_len(targ_name); + if (targ_essent_len != cands->name_len) + continue; + + /* most of the time there is only one candidate for a given kind+name pair */ + new_cands = kmalloc(sizeof_cands(cands->cnt + 1), GFP_KERNEL); + if (!new_cands) { + bpf_free_cands(cands); + return ERR_PTR(-ENOMEM); + } + + memcpy(new_cands, cands, sizeof_cands(cands->cnt)); + bpf_free_cands(cands); + cands = new_cands; + cands->cands[cands->cnt].btf = targ_btf; + cands->cands[cands->cnt].id = i; + cands->cnt++; + } + return cands; +} + +static struct bpf_cand_cache * +bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id) +{ + struct bpf_cand_cache *cands, *cc, local_cand = {}; + const struct btf *local_btf = ctx->btf; + const struct btf_type *local_type; + const struct btf *main_btf; + size_t local_essent_len; + struct btf *mod_btf; + const char *name; + int id; + + main_btf = bpf_get_btf_vmlinux(); + if (IS_ERR(main_btf)) + return ERR_CAST(main_btf); + + local_type = btf_type_by_id(local_btf, local_type_id); + if (!local_type) + return ERR_PTR(-EINVAL); + + name = btf_name_by_offset(local_btf, local_type->name_off); + if (str_is_empty(name)) + return ERR_PTR(-EINVAL); + local_essent_len = bpf_core_essential_name_len(name); + + cands = &local_cand; + cands->name = name; + cands->kind = btf_kind(local_type); + cands->name_len = local_essent_len; + + cc = check_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE); + /* cands is a pointer to stack here */ + if (cc) { + if (cc->cnt) + return cc; + goto check_modules; + } + + /* Attempt to find target candidates in vmlinux BTF first */ + cands = bpf_core_add_cands(cands, main_btf, 1); + if (IS_ERR(cands)) + return ERR_CAST(cands); + + /* cands is a pointer to kmalloced memory here if cands->cnt > 0 */ + + /* populate cache even when cands->cnt == 0 */ + cc = populate_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE); + if (IS_ERR(cc)) + return ERR_CAST(cc); + + /* if vmlinux BTF has any candidate, don't go for module BTFs */ + if (cc->cnt) + return cc; + +check_modules: + /* cands is a pointer to stack here and cands->cnt == 0 */ + cc = check_cand_cache(cands, module_cand_cache, MODULE_CAND_CACHE_SIZE); + if (cc) + /* if cache has it return it even if cc->cnt == 0 */ + return cc; + + /* If candidate is not found in vmlinux's BTF then search in module's BTFs */ + spin_lock_bh(&btf_idr_lock); + idr_for_each_entry(&btf_idr, mod_btf, id) { + if (!btf_is_module(mod_btf)) + continue; + /* linear search could be slow hence unlock/lock + * the IDR to avoiding holding it for too long + */ + btf_get(mod_btf); + spin_unlock_bh(&btf_idr_lock); + cands = bpf_core_add_cands(cands, mod_btf, btf_nr_types(main_btf)); + if (IS_ERR(cands)) { + btf_put(mod_btf); + return ERR_CAST(cands); + } + spin_lock_bh(&btf_idr_lock); + btf_put(mod_btf); + } + spin_unlock_bh(&btf_idr_lock); + /* cands is a pointer to kmalloced memory here if cands->cnt > 0 + * or pointer to stack if cands->cnd == 0. + * Copy it into the cache even when cands->cnt == 0 and + * return the result. + */ + return populate_cand_cache(cands, module_cand_cache, MODULE_CAND_CACHE_SIZE); +} + +int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, + int relo_idx, void *insn) +{ + bool need_cands = relo->kind != BPF_CORE_TYPE_ID_LOCAL; + struct bpf_core_cand_list cands = {}; + struct bpf_core_spec *specs; + int err; + + /* ~4k of temp memory necessary to convert LLVM spec like "0:1:0:5" + * into arrays of btf_ids of struct fields and array indices. + */ + specs = kcalloc(3, sizeof(*specs), GFP_KERNEL); + if (!specs) + return -ENOMEM; + + if (need_cands) { + struct bpf_cand_cache *cc; + int i; + + mutex_lock(&cand_cache_mutex); + cc = bpf_core_find_cands(ctx, relo->type_id); + if (IS_ERR(cc)) { + bpf_log(ctx->log, "target candidate search failed for %d\n", + relo->type_id); + err = PTR_ERR(cc); + goto out; + } + if (cc->cnt) { + cands.cands = kcalloc(cc->cnt, sizeof(*cands.cands), GFP_KERNEL); + if (!cands.cands) { + err = -ENOMEM; + goto out; + } + } + for (i = 0; i < cc->cnt; i++) { + bpf_log(ctx->log, + "CO-RE relocating %s %s: found target candidate [%d]\n", + btf_kind_str[cc->kind], cc->name, cc->cands[i].id); + cands.cands[i].btf = cc->cands[i].btf; + cands.cands[i].id = cc->cands[i].id; + } + cands.len = cc->cnt; + /* cand_cache_mutex needs to span the cache lookup and + * copy of btf pointer into bpf_core_cand_list, + * since module can be unloaded while bpf_core_apply_relo_insn + * is working with module's btf. + */ + } + + err = bpf_core_apply_relo_insn((void *)ctx->log, insn, relo->insn_off / 8, + relo, relo_idx, ctx->btf, &cands, specs); +out: + kfree(specs); + if (need_cands) { + kfree(cands.cands); + mutex_unlock(&cand_cache_mutex); + if (ctx->log->level & BPF_LOG_LEVEL2) + print_cand_cache(ctx->log); + } + return err; +} diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 2ca643af9a54..514b4681a90a 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1789,7 +1789,7 @@ static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; @@ -1809,6 +1809,8 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sysctl_get_new_value_proto; case BPF_FUNC_sysctl_set_new_value: return &bpf_sysctl_set_new_value_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return cgroup_base_func_proto(func_id, prog); } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 2405e39d800f..de3e5bc6781f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1574,7 +1574,8 @@ select_insn: if (unlikely(index >= array->map.max_entries)) goto out; - if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT)) + + if (unlikely(tail_call_cnt >= MAX_TAIL_CALL_CNT)) goto out; tail_call_cnt++; @@ -1891,7 +1892,7 @@ static void bpf_prog_select_func(struct bpf_prog *fp) /** * bpf_prog_select_runtime - select exec runtime for BPF program - * @fp: bpf_prog populated with internal BPF program + * @fp: bpf_prog populated with BPF program * @err: pointer to error variable * * Try to JIT eBPF program, if JIT is not available, use interpreter. @@ -2300,7 +2301,6 @@ static void bpf_prog_free_deferred(struct work_struct *work) } } -/* Free internal BPF program */ void bpf_prog_free(struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 585b2b77ccc4..b3e6b9422238 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -195,7 +195,7 @@ static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu, } return; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(skb->dev, rcpu->prog, act); @@ -254,7 +254,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, } break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act); fallthrough; case XDP_DROP: xdp_return_frame(xdpf); @@ -746,15 +746,9 @@ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) list_add(&bq->flush_node, flush_list); } -int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, +int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx) { - struct xdp_frame *xdpf; - - xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) - return -EOVERFLOW; - /* Info needed when constructing SKB on remote CPU */ xdpf->dev_rx = dev_rx; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index f02d04540c0c..fe019dbdb3f0 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -348,7 +348,7 @@ static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, frames[nframes++] = xdpf; break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(NULL, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dev, xdp_prog, act); @@ -467,24 +467,19 @@ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, bq->q[bq->count++] = xdpf; } -static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, +static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { - struct xdp_frame *xdpf; int err; if (!dev->netdev_ops->ndo_xdp_xmit) return -EOPNOTSUPP; - err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); + err = xdp_ok_fwd_dev(dev, xdpf->len); if (unlikely(err)) return err; - xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) - return -EOVERFLOW; - bq_enqueue(dev, xdpf, dev_rx, xdp_prog); return 0; } @@ -507,7 +502,7 @@ static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev __skb_push(skb, skb->mac_len); break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(NULL, dst->xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dst->dev, dst->xdp_prog, act); @@ -520,27 +515,27 @@ static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev return act; } -int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, +int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { - return __xdp_enqueue(dev, xdp, dev_rx, NULL); + return __xdp_enqueue(dev, xdpf, dev_rx, NULL); } -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { struct net_device *dev = dst->dev; - return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog); + return __xdp_enqueue(dev, xdpf, dev_rx, dst->xdp_prog); } -static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_buff *xdp) +static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf) { if (!obj || !obj->dev->netdev_ops->ndo_xdp_xmit) return false; - if (xdp_ok_fwd_dev(obj->dev, xdp->data_end - xdp->data)) + if (xdp_ok_fwd_dev(obj->dev, xdpf->len)) return false; return true; @@ -586,14 +581,13 @@ static int get_upper_ifindexes(struct net_device *dev, int *indexes) return n; } -int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, +int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; - struct xdp_frame *xdpf; int num_excluded = 0; unsigned int i; int err; @@ -603,15 +597,11 @@ int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, excluded_devices[num_excluded++] = dev_rx->ifindex; } - xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) - return -EOVERFLOW; - if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); - if (!is_valid_dst(dst, xdp)) + if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) @@ -634,7 +624,7 @@ int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, head = dev_map_index_hash(dtab, i); hlist_for_each_entry_rcu(dst, head, index_hlist, lockdep_is_held(&dtab->index_lock)) { - if (!is_valid_dst(dst, xdp)) + if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1ffd469c217f..01cfdf40c838 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2,6 +2,7 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <linux/bpf.h> +#include <linux/bpf-cgroup.h> #include <linux/rcupdate.h> #include <linux/random.h> #include <linux/smp.h> @@ -530,7 +531,7 @@ const struct bpf_func_proto bpf_strtol_proto = { .func = bpf_strtol, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_LONG, @@ -558,13 +559,27 @@ const struct bpf_func_proto bpf_strtoul_proto = { .func = bpf_strtoul, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_LONG, }; #endif +BPF_CALL_3(bpf_strncmp, const char *, s1, u32, s1_sz, const char *, s2) +{ + return strncmp(s1, s2, s1_sz); +} + +const struct bpf_func_proto bpf_strncmp_proto = { + .func = bpf_strncmp, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_PTR_TO_CONST_STR, +}; + BPF_CALL_4(bpf_get_ns_current_pid_tgid, u64, dev, u64, ino, struct bpf_pidns_info *, nsdata, u32, size) { @@ -630,7 +645,7 @@ const struct bpf_func_proto bpf_event_output_data_proto = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -667,7 +682,7 @@ BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu) const struct bpf_func_proto bpf_per_cpu_ptr_proto = { .func = bpf_per_cpu_ptr, .gpl_only = false, - .ret_type = RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, + .ret_type = RET_PTR_TO_MEM_OR_BTF_ID | PTR_MAYBE_NULL | MEM_RDONLY, .arg1_type = ARG_PTR_TO_PERCPU_BTF_ID, .arg2_type = ARG_ANYTHING, }; @@ -680,7 +695,7 @@ BPF_CALL_1(bpf_this_cpu_ptr, const void *, percpu_ptr) const struct bpf_func_proto bpf_this_cpu_ptr_proto = { .func = bpf_this_cpu_ptr, .gpl_only = false, - .ret_type = RET_PTR_TO_MEM_OR_BTF_ID, + .ret_type = RET_PTR_TO_MEM_OR_BTF_ID | MEM_RDONLY, .arg1_type = ARG_PTR_TO_PERCPU_BTF_ID, }; @@ -1011,7 +1026,7 @@ const struct bpf_func_proto bpf_snprintf_proto = { .arg1_type = ARG_PTR_TO_MEM_OR_NULL, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_PTR_TO_CONST_STR, - .arg4_type = ARG_PTR_TO_MEM_OR_NULL, + .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -1364,8 +1379,6 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; - case BPF_FUNC_ktime_get_coarse_ns: - return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_ringbuf_output: return &bpf_ringbuf_output_proto; case BPF_FUNC_ringbuf_reserve: @@ -1378,6 +1391,10 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ringbuf_query_proto; case BPF_FUNC_for_each_map_elem: return &bpf_for_each_map_elem_proto; + case BPF_FUNC_loop: + return &bpf_loop_proto; + case BPF_FUNC_strncmp: + return &bpf_strncmp_proto; default: break; } diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 035e9e3a7132..23f7f9d08a62 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -163,8 +163,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *key, return 0; } - new = bpf_map_kmalloc_node(map, sizeof(struct bpf_storage_buffer) + - map->value_size, + new = bpf_map_kmalloc_node(map, struct_size(new, data, map->value_size), __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN, map->numa_node); if (!new) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 423549d2c52e..5763cc7ac4f1 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -412,7 +412,7 @@ static int trie_update_elem(struct bpf_map *map, rcu_assign_pointer(im_node->child[1], node); } - /* Finally, assign the intermediate node to the determined spot */ + /* Finally, assign the intermediate node to the determined slot */ rcu_assign_pointer(*slot, im_node); out: diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c index 6a9542af4212..b0fa190b0979 100644 --- a/kernel/bpf/map_iter.c +++ b/kernel/bpf/map_iter.c @@ -174,9 +174,9 @@ static const struct bpf_iter_reg bpf_map_elem_reg_info = { .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__bpf_map_elem, key), - PTR_TO_RDONLY_BUF_OR_NULL }, + PTR_TO_BUF | PTR_MAYBE_NULL | MEM_RDONLY }, { offsetof(struct bpf_iter__bpf_map_elem, value), - PTR_TO_RDWR_BUF_OR_NULL }, + PTR_TO_BUF | PTR_MAYBE_NULL }, }, }; diff --git a/kernel/bpf/mmap_unlock_work.h b/kernel/bpf/mmap_unlock_work.h new file mode 100644 index 000000000000..5d18d7d85bef --- /dev/null +++ b/kernel/bpf/mmap_unlock_work.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2021 Facebook + */ + +#ifndef __MMAP_UNLOCK_WORK_H__ +#define __MMAP_UNLOCK_WORK_H__ +#include <linux/irq_work.h> + +/* irq_work to run mmap_read_unlock() in irq_work */ +struct mmap_unlock_irq_work { + struct irq_work irq_work; + struct mm_struct *mm; +}; + +DECLARE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work); + +/* + * We cannot do mmap_read_unlock() when the irq is disabled, because of + * risk to deadlock with rq_lock. To look up vma when the irqs are + * disabled, we need to run mmap_read_unlock() in irq_work. We use a + * percpu variable to do the irq_work. If the irq_work is already used + * by another lookup, we fall over. + */ +static inline bool bpf_mmap_unlock_get_irq_work(struct mmap_unlock_irq_work **work_ptr) +{ + struct mmap_unlock_irq_work *work = NULL; + bool irq_work_busy = false; + + if (irqs_disabled()) { + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { + work = this_cpu_ptr(&mmap_unlock_work); + if (irq_work_is_busy(&work->irq_work)) { + /* cannot queue more up_read, fallback */ + irq_work_busy = true; + } + } else { + /* + * PREEMPT_RT does not allow to trylock mmap sem in + * interrupt disabled context. Force the fallback code. + */ + irq_work_busy = true; + } + } + + *work_ptr = work; + return irq_work_busy; +} + +static inline void bpf_mmap_unlock_mm(struct mmap_unlock_irq_work *work, struct mm_struct *mm) +{ + if (!work) { + mmap_read_unlock(mm); + } else { + work->mm = mm; + + /* The lock will be released once we're out of interrupt + * context. Tell lockdep that we've released it now so + * it doesn't complain that we forgot to release it. + */ + rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); + irq_work_queue(&work->irq_work); + } +} + +#endif /* __MMAP_UNLOCK_WORK_H__ */ diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c index 542f275bf252..868cc2c43899 100644 --- a/kernel/bpf/net_namespace.c +++ b/kernel/bpf/net_namespace.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> +#include <linux/bpf-netns.h> #include <linux/filter.h> #include <net/net_namespace.h> diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index 93a55391791a..556a769b5b80 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -152,16 +152,12 @@ static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); struct reuseport_array *array; - u64 array_size; if (!bpf_capable()) return ERR_PTR(-EPERM); - array_size = sizeof(*array); - array_size += (u64)attr->max_entries * sizeof(struct sock *); - /* allocate all map elements and zero-initialize them */ - array = bpf_map_area_alloc(array_size, numa_node); + array = bpf_map_area_alloc(struct_size(array, ptrs, attr->max_entries), numa_node); if (!array) return ERR_PTR(-ENOMEM); diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 9e0c10c6892a..638d7fd7b375 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -444,7 +444,7 @@ const struct bpf_func_proto bpf_ringbuf_output_proto = { .func = bpf_ringbuf_output, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 6e75bbee39f0..49e567209c6b 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -7,10 +7,10 @@ #include <linux/kernel.h> #include <linux/stacktrace.h> #include <linux/perf_event.h> -#include <linux/irq_work.h> #include <linux/btf_ids.h> #include <linux/buildid.h> #include "percpu_freelist.h" +#include "mmap_unlock_work.h" #define STACK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY | \ @@ -31,25 +31,6 @@ struct bpf_stack_map { struct stack_map_bucket *buckets[]; }; -/* irq_work to run up_read() for build_id lookup in nmi context */ -struct stack_map_irq_work { - struct irq_work irq_work; - struct mm_struct *mm; -}; - -static void do_up_read(struct irq_work *entry) -{ - struct stack_map_irq_work *work; - - if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT))) - return; - - work = container_of(entry, struct stack_map_irq_work, irq_work); - mmap_read_unlock_non_owner(work->mm); -} - -static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work); - static inline bool stack_map_use_build_id(struct bpf_map *map) { return (map->map_flags & BPF_F_STACK_BUILD_ID); @@ -149,35 +130,13 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, u64 *ips, u32 trace_nr, bool user) { int i; + struct mmap_unlock_irq_work *work = NULL; + bool irq_work_busy = bpf_mmap_unlock_get_irq_work(&work); struct vm_area_struct *vma; - bool irq_work_busy = false; - struct stack_map_irq_work *work = NULL; - - if (irqs_disabled()) { - if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { - work = this_cpu_ptr(&up_read_work); - if (irq_work_is_busy(&work->irq_work)) { - /* cannot queue more up_read, fallback */ - irq_work_busy = true; - } - } else { - /* - * PREEMPT_RT does not allow to trylock mmap sem in - * interrupt disabled context. Force the fallback code. - */ - irq_work_busy = true; - } - } - /* - * We cannot do up_read() when the irq is disabled, because of - * risk to deadlock with rq_lock. To do build_id lookup when the - * irqs are disabled, we need to run up_read() in irq_work. We use - * a percpu variable to do the irq_work. If the irq_work is - * already used by another lookup, we fall back to report ips. - * - * Same fallback is used for kernel stack (!user) on a stackmap - * with build_id. + /* If the irq_work is in use, fall back to report ips. Same + * fallback is used for kernel stack (!user) on a stackmap with + * build_id. */ if (!user || !current || !current->mm || irq_work_busy || !mmap_read_trylock(current->mm)) { @@ -203,19 +162,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, - vma->vm_start; id_offs[i].status = BPF_STACK_BUILD_ID_VALID; } - - if (!work) { - mmap_read_unlock(current->mm); - } else { - work->mm = current->mm; - - /* The lock will be released once we're out of interrupt - * context. Tell lockdep that we've released it now so - * it doesn't complain that we forgot to release it. - */ - rwsem_release(¤t->mm->mmap_lock.dep_map, _RET_IP_); - irq_work_queue(&work->irq_work); - } + bpf_mmap_unlock_mm(work, current->mm); } static struct perf_callchain_entry * @@ -542,7 +489,7 @@ const struct bpf_func_proto bpf_get_task_stack_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, - .arg1_btf_id = &btf_task_struct_ids[0], + .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, @@ -719,16 +666,3 @@ const struct bpf_map_ops stack_trace_map_ops = { .map_btf_name = "bpf_stack_map", .map_btf_id = &stack_trace_map_btf_id, }; - -static int __init stack_map_init(void) -{ - int cpu; - struct stack_map_irq_work *work; - - for_each_possible_cpu(cpu) { - work = per_cpu_ptr(&up_read_work, cpu); - init_irq_work(&work->irq_work, do_up_read); - } - return 0; -} -subsys_initcall(stack_map_init); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 50f96ea4452a..fa4505f9b611 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2,6 +2,7 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <linux/bpf.h> +#include <linux/bpf-cgroup.h> #include <linux/bpf_trace.h> #include <linux/bpf_lirc.h> #include <linux/bpf_verifier.h> @@ -132,6 +133,21 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } +static void bpf_map_write_active_inc(struct bpf_map *map) +{ + atomic64_inc(&map->writecnt); +} + +static void bpf_map_write_active_dec(struct bpf_map *map) +{ + atomic64_dec(&map->writecnt); +} + +bool bpf_map_write_active(const struct bpf_map *map) +{ + return atomic64_read(&map->writecnt) != 0; +} + static u32 bpf_map_value_size(const struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || @@ -601,11 +617,8 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_MAYWRITE) { - mutex_lock(&map->freeze_mutex); - map->writecnt++; - mutex_unlock(&map->freeze_mutex); - } + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_inc(map); } /* called for all unmapped memory region (including initial) */ @@ -613,11 +626,8 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_MAYWRITE) { - mutex_lock(&map->freeze_mutex); - map->writecnt--; - mutex_unlock(&map->freeze_mutex); - } + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_dec(map); } static const struct vm_operations_struct bpf_map_default_vmops = { @@ -668,7 +678,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) goto out; if (vma->vm_flags & VM_MAYWRITE) - map->writecnt++; + bpf_map_write_active_inc(map); out: mutex_unlock(&map->freeze_mutex); return err; @@ -1139,6 +1149,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; @@ -1174,6 +1185,7 @@ free_value: free_key: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1196,6 +1208,7 @@ static int map_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; @@ -1226,6 +1239,7 @@ static int map_delete_elem(union bpf_attr *attr) out: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1533,6 +1547,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; @@ -1597,6 +1612,7 @@ free_value: free_key: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1624,8 +1640,7 @@ static int map_freeze(const union bpf_attr *attr) } mutex_lock(&map->freeze_mutex); - - if (map->writecnt) { + if (bpf_map_write_active(map)) { err = -EBUSY; goto err_put; } @@ -2184,7 +2199,7 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD fd_array +#define BPF_PROG_LOAD_LAST_FIELD core_relo_rec_size static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) { @@ -4171,6 +4186,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr, union bpf_attr __user *uattr, int cmd) { + bool has_read = cmd == BPF_MAP_LOOKUP_BATCH || + cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH; + bool has_write = cmd != BPF_MAP_LOOKUP_BATCH; struct bpf_map *map; int err, ufd; struct fd f; @@ -4183,16 +4201,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr, map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if ((cmd == BPF_MAP_LOOKUP_BATCH || - cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) && - !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { + if (has_write) + bpf_map_write_active_inc(map); + if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } - - if (cmd != BPF_MAP_LOOKUP_BATCH && - !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { + if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } @@ -4205,8 +4220,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr, BPF_DO_BATCH(map->ops->map_update_batch); else BPF_DO_BATCH(map->ops->map_delete_batch); - err_put: + if (has_write) + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -4757,7 +4773,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; @@ -4804,7 +4820,7 @@ const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM, - .arg2_type = ARG_CONST_SIZE, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_LONG, }; diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index b48750bfba5a..d94696198ef8 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -8,6 +8,7 @@ #include <linux/fdtable.h> #include <linux/filter.h> #include <linux/btf_ids.h> +#include "mmap_unlock_work.h" struct bpf_iter_seq_task_common { struct pid_namespace *ns; @@ -524,10 +525,6 @@ static const struct seq_operations task_vma_seq_ops = { .show = task_vma_seq_show, }; -BTF_ID_LIST(btf_task_file_ids) -BTF_ID(struct, file) -BTF_ID(struct, vm_area_struct) - static const struct bpf_iter_seq_info task_seq_info = { .seq_ops = &task_seq_ops, .init_seq_private = init_seq_pidns, @@ -586,23 +583,88 @@ static struct bpf_iter_reg task_vma_reg_info = { .seq_info = &task_vma_seq_info, }; +BPF_CALL_5(bpf_find_vma, struct task_struct *, task, u64, start, + bpf_callback_t, callback_fn, void *, callback_ctx, u64, flags) +{ + struct mmap_unlock_irq_work *work = NULL; + struct vm_area_struct *vma; + bool irq_work_busy = false; + struct mm_struct *mm; + int ret = -ENOENT; + + if (flags) + return -EINVAL; + + if (!task) + return -ENOENT; + + mm = task->mm; + if (!mm) + return -ENOENT; + + irq_work_busy = bpf_mmap_unlock_get_irq_work(&work); + + if (irq_work_busy || !mmap_read_trylock(mm)) + return -EBUSY; + + vma = find_vma(mm, start); + + if (vma && vma->vm_start <= start && vma->vm_end > start) { + callback_fn((u64)(long)task, (u64)(long)vma, + (u64)(long)callback_ctx, 0, 0); + ret = 0; + } + bpf_mmap_unlock_mm(work, mm); + return ret; +} + +const struct bpf_func_proto bpf_find_vma_proto = { + .func = bpf_find_vma, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_FUNC, + .arg4_type = ARG_PTR_TO_STACK_OR_NULL, + .arg5_type = ARG_ANYTHING, +}; + +DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work); + +static void do_mmap_read_unlock(struct irq_work *entry) +{ + struct mmap_unlock_irq_work *work; + + if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT))) + return; + + work = container_of(entry, struct mmap_unlock_irq_work, irq_work); + mmap_read_unlock_non_owner(work->mm); +} + static int __init task_iter_init(void) { - int ret; + struct mmap_unlock_irq_work *work; + int ret, cpu; + + for_each_possible_cpu(cpu) { + work = per_cpu_ptr(&mmap_unlock_work, cpu); + init_irq_work(&work->irq_work, do_mmap_read_unlock); + } - task_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0]; + task_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK]; ret = bpf_iter_reg_target(&task_reg_info); if (ret) return ret; - task_file_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0]; - task_file_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[0]; + task_file_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK]; + task_file_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_FILE]; ret = bpf_iter_reg_target(&task_file_reg_info); if (ret) return ret; - task_vma_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0]; - task_vma_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[1]; + task_vma_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK]; + task_vma_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA]; return bpf_iter_reg_target(&task_vma_reg_info); } late_initcall(task_iter_init); diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index e98de5e73ba5..4b6974a195c1 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -27,6 +27,14 @@ static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE]; /* serializes access to trampoline_table */ static DEFINE_MUTEX(trampoline_mutex); +bool bpf_prog_has_trampoline(const struct bpf_prog *prog) +{ + enum bpf_attach_type eatype = prog->expected_attach_type; + + return eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT || + eatype == BPF_MODIFY_RETURN; +} + void *bpf_jit_alloc_exec_page(void) { void *image; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 890b3ec375a3..bfb45381fb3f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4,6 +4,7 @@ * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io */ #include <uapi/linux/btf.h> +#include <linux/bpf-cgroup.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> @@ -293,13 +294,15 @@ void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1, "verifier log line truncated - local buffer too short\n"); - n = min(log->len_total - log->len_used - 1, n); - log->kbuf[n] = '\0'; - if (log->level == BPF_LOG_KERNEL) { - pr_err("BPF:%s\n", log->kbuf); + bool newline = n > 0 && log->kbuf[n - 1] == '\n'; + + pr_err("BPF: %s%s", log->kbuf, newline ? "" : "\n"); return; } + + n = min(log->len_total - log->len_used - 1, n); + log->kbuf[n] = '\0'; if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1)) log->len_used += n; else @@ -439,18 +442,6 @@ static bool reg_type_not_null(enum bpf_reg_type type) type == PTR_TO_SOCK_COMMON; } -static bool reg_type_may_be_null(enum bpf_reg_type type) -{ - return type == PTR_TO_MAP_VALUE_OR_NULL || - type == PTR_TO_SOCKET_OR_NULL || - type == PTR_TO_SOCK_COMMON_OR_NULL || - type == PTR_TO_TCP_SOCK_OR_NULL || - type == PTR_TO_BTF_ID_OR_NULL || - type == PTR_TO_MEM_OR_NULL || - type == PTR_TO_RDONLY_BUF_OR_NULL || - type == PTR_TO_RDWR_BUF_OR_NULL; -} - static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return reg->type == PTR_TO_MAP_VALUE && @@ -459,12 +450,14 @@ static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type) { - return type == PTR_TO_SOCKET || - type == PTR_TO_SOCKET_OR_NULL || - type == PTR_TO_TCP_SOCK || - type == PTR_TO_TCP_SOCK_OR_NULL || - type == PTR_TO_MEM || - type == PTR_TO_MEM_OR_NULL; + return base_type(type) == PTR_TO_SOCKET || + base_type(type) == PTR_TO_TCP_SOCK || + base_type(type) == PTR_TO_MEM; +} + +static bool type_is_rdonly_mem(u32 type) +{ + return type & MEM_RDONLY; } static bool arg_type_may_be_refcounted(enum bpf_arg_type type) @@ -472,14 +465,9 @@ static bool arg_type_may_be_refcounted(enum bpf_arg_type type) return type == ARG_PTR_TO_SOCK_COMMON; } -static bool arg_type_may_be_null(enum bpf_arg_type type) +static bool type_may_be_null(u32 type) { - return type == ARG_PTR_TO_MAP_VALUE_OR_NULL || - type == ARG_PTR_TO_MEM_OR_NULL || - type == ARG_PTR_TO_CTX_OR_NULL || - type == ARG_PTR_TO_SOCKET_OR_NULL || - type == ARG_PTR_TO_ALLOC_MEM_OR_NULL || - type == ARG_PTR_TO_STACK_OR_NULL; + return type & PTR_MAYBE_NULL; } /* Determine whether the function releases some resources allocated by another @@ -539,39 +527,54 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn) insn->imm == BPF_CMPXCHG; } -/* string representation of 'enum bpf_reg_type' */ -static const char * const reg_type_str[] = { - [NOT_INIT] = "?", - [SCALAR_VALUE] = "inv", - [PTR_TO_CTX] = "ctx", - [CONST_PTR_TO_MAP] = "map_ptr", - [PTR_TO_MAP_VALUE] = "map_value", - [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null", - [PTR_TO_STACK] = "fp", - [PTR_TO_PACKET] = "pkt", - [PTR_TO_PACKET_META] = "pkt_meta", - [PTR_TO_PACKET_END] = "pkt_end", - [PTR_TO_FLOW_KEYS] = "flow_keys", - [PTR_TO_SOCKET] = "sock", - [PTR_TO_SOCKET_OR_NULL] = "sock_or_null", - [PTR_TO_SOCK_COMMON] = "sock_common", - [PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null", - [PTR_TO_TCP_SOCK] = "tcp_sock", - [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null", - [PTR_TO_TP_BUFFER] = "tp_buffer", - [PTR_TO_XDP_SOCK] = "xdp_sock", - [PTR_TO_BTF_ID] = "ptr_", - [PTR_TO_BTF_ID_OR_NULL] = "ptr_or_null_", - [PTR_TO_PERCPU_BTF_ID] = "percpu_ptr_", - [PTR_TO_MEM] = "mem", - [PTR_TO_MEM_OR_NULL] = "mem_or_null", - [PTR_TO_RDONLY_BUF] = "rdonly_buf", - [PTR_TO_RDONLY_BUF_OR_NULL] = "rdonly_buf_or_null", - [PTR_TO_RDWR_BUF] = "rdwr_buf", - [PTR_TO_RDWR_BUF_OR_NULL] = "rdwr_buf_or_null", - [PTR_TO_FUNC] = "func", - [PTR_TO_MAP_KEY] = "map_key", -}; +/* string representation of 'enum bpf_reg_type' + * + * Note that reg_type_str() can not appear more than once in a single verbose() + * statement. + */ +static const char *reg_type_str(struct bpf_verifier_env *env, + enum bpf_reg_type type) +{ + char postfix[16] = {0}, prefix[16] = {0}; + static const char * const str[] = { + [NOT_INIT] = "?", + [SCALAR_VALUE] = "inv", + [PTR_TO_CTX] = "ctx", + [CONST_PTR_TO_MAP] = "map_ptr", + [PTR_TO_MAP_VALUE] = "map_value", + [PTR_TO_STACK] = "fp", + [PTR_TO_PACKET] = "pkt", + [PTR_TO_PACKET_META] = "pkt_meta", + [PTR_TO_PACKET_END] = "pkt_end", + [PTR_TO_FLOW_KEYS] = "flow_keys", + [PTR_TO_SOCKET] = "sock", + [PTR_TO_SOCK_COMMON] = "sock_common", + [PTR_TO_TCP_SOCK] = "tcp_sock", + [PTR_TO_TP_BUFFER] = "tp_buffer", + [PTR_TO_XDP_SOCK] = "xdp_sock", + [PTR_TO_BTF_ID] = "ptr_", + [PTR_TO_PERCPU_BTF_ID] = "percpu_ptr_", + [PTR_TO_MEM] = "mem", + [PTR_TO_BUF] = "buf", + [PTR_TO_FUNC] = "func", + [PTR_TO_MAP_KEY] = "map_key", + }; + + if (type & PTR_MAYBE_NULL) { + if (base_type(type) == PTR_TO_BTF_ID || + base_type(type) == PTR_TO_PERCPU_BTF_ID) + strncpy(postfix, "or_null_", 16); + else + strncpy(postfix, "_or_null", 16); + } + + if (type & MEM_RDONLY) + strncpy(prefix, "rdonly_", 16); + + snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s", + prefix, str[base_type(type)], postfix); + return env->type_str_buf; +} static char slot_type_char[] = { [STACK_INVALID] = '?', @@ -606,6 +609,44 @@ 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 void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno) +{ + env->scratched_regs |= 1U << regno; +} + +static void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi) +{ + env->scratched_stack_slots |= 1UL << spi; +} + +static bool reg_scratched(const struct bpf_verifier_env *env, u32 regno) +{ + return (env->scratched_regs >> regno) & 1; +} + +static bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno) +{ + return (env->scratched_stack_slots >> regno) & 1; +} + +static bool verifier_state_scratched(const struct bpf_verifier_env *env) +{ + return env->scratched_regs || env->scratched_stack_slots; +} + +static void mark_verifier_state_clean(struct bpf_verifier_env *env) +{ + env->scratched_regs = 0U; + env->scratched_stack_slots = 0UL; +} + +/* Used for printing the entire verifier state. */ +static void mark_verifier_state_scratched(struct bpf_verifier_env *env) +{ + env->scratched_regs = ~0U; + env->scratched_stack_slots = ~0UL; +} + /* The reg state of a pointer or a bounded scalar was saved when * it was spilled to the stack. */ @@ -621,7 +662,8 @@ static void scrub_spilled_slot(u8 *stype) } static void print_verifier_state(struct bpf_verifier_env *env, - const struct bpf_func_state *state) + const struct bpf_func_state *state, + bool print_all) { const struct bpf_reg_state *reg; enum bpf_reg_type t; @@ -634,9 +676,11 @@ static void print_verifier_state(struct bpf_verifier_env *env, t = reg->type; if (t == NOT_INIT) continue; + if (!print_all && !reg_scratched(env, i)) + continue; verbose(env, " R%d", i); print_liveness(env, reg->live); - verbose(env, "=%s", reg_type_str[t]); + verbose(env, "=%s", reg_type_str(env, t)); if (t == SCALAR_VALUE && reg->precise) verbose(env, "P"); if ((t == SCALAR_VALUE || t == PTR_TO_STACK) && @@ -644,9 +688,8 @@ static void print_verifier_state(struct bpf_verifier_env *env, /* reg->off should be 0 for SCALAR_VALUE */ verbose(env, "%lld", reg->var_off.value + reg->off); } else { - if (t == PTR_TO_BTF_ID || - t == PTR_TO_BTF_ID_OR_NULL || - t == PTR_TO_PERCPU_BTF_ID) + if (base_type(t) == PTR_TO_BTF_ID || + base_type(t) == PTR_TO_PERCPU_BTF_ID) verbose(env, "%s", kernel_type_name(reg->btf, reg->btf_id)); verbose(env, "(id=%d", reg->id); if (reg_type_may_be_refcounted_or_null(t)) @@ -655,10 +698,9 @@ static void print_verifier_state(struct bpf_verifier_env *env, verbose(env, ",off=%d", reg->off); if (type_is_pkt_pointer(t)) verbose(env, ",r=%d", reg->range); - else if (t == CONST_PTR_TO_MAP || - t == PTR_TO_MAP_KEY || - t == PTR_TO_MAP_VALUE || - t == PTR_TO_MAP_VALUE_OR_NULL) + else if (base_type(t) == CONST_PTR_TO_MAP || + base_type(t) == PTR_TO_MAP_KEY || + base_type(t) == PTR_TO_MAP_VALUE) verbose(env, ",ks=%d,vs=%d", reg->map_ptr->key_size, reg->map_ptr->value_size); @@ -723,12 +765,14 @@ static void print_verifier_state(struct bpf_verifier_env *env, 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])) { reg = &state->stack[i].spilled_ptr; t = reg->type; - verbose(env, "=%s", reg_type_str[t]); + verbose(env, "=%s", reg_type_str(env, t)); if (t == SCALAR_VALUE && reg->precise) verbose(env, "P"); if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) @@ -748,6 +792,26 @@ static void print_verifier_state(struct bpf_verifier_env *env, if (state->in_async_callback_fn) verbose(env, " async_cb"); verbose(env, "\n"); + mark_verifier_state_clean(env); +} + +static inline u32 vlog_alignment(u32 pos) +{ + return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT), + BPF_LOG_MIN_ALIGNMENT) - pos - 1; +} + +static void print_insn_state(struct bpf_verifier_env *env, + const struct bpf_func_state *state) +{ + if (env->prev_log_len && env->prev_log_len == env->log.len_used) { + /* remove new line character */ + bpf_vlog_reset(&env->log, env->prev_log_len - 1); + verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_len), ' '); + } else { + verbose(env, "%d:", env->insn_idx); + } + print_verifier_state(env, state, false); } /* copy array src of length n * size bytes to dst. dst is reallocated if it's too @@ -1141,8 +1205,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env, static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) { - switch (reg->type) { - case PTR_TO_MAP_VALUE_OR_NULL: { + if (base_type(reg->type) == PTR_TO_MAP_VALUE) { const struct bpf_map *map = reg->map_ptr; if (map->inner_map_meta) { @@ -1151,7 +1214,8 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) /* transfer reg's id which is unique for every map_lookup_elem * as UID of the inner map. */ - reg->map_uid = reg->id; + if (map_value_has_timer(map->inner_map_meta)) + reg->map_uid = reg->id; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK; } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || @@ -1160,32 +1224,10 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) } else { reg->type = PTR_TO_MAP_VALUE; } - break; - } - case PTR_TO_SOCKET_OR_NULL: - reg->type = PTR_TO_SOCKET; - break; - case PTR_TO_SOCK_COMMON_OR_NULL: - reg->type = PTR_TO_SOCK_COMMON; - break; - case PTR_TO_TCP_SOCK_OR_NULL: - reg->type = PTR_TO_TCP_SOCK; - break; - case PTR_TO_BTF_ID_OR_NULL: - reg->type = PTR_TO_BTF_ID; - break; - case PTR_TO_MEM_OR_NULL: - reg->type = PTR_TO_MEM; - break; - case PTR_TO_RDONLY_BUF_OR_NULL: - reg->type = PTR_TO_RDONLY_BUF; - break; - case PTR_TO_RDWR_BUF_OR_NULL: - reg->type = PTR_TO_RDWR_BUF; - break; - default: - WARN_ONCE(1, "unknown nullable register type"); + return; } + + reg->type &= ~PTR_MAYBE_NULL; } static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg) @@ -1365,22 +1407,28 @@ static void __reg_bound_offset(struct bpf_reg_state *reg) reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off); } +static bool __reg32_bound_s64(s32 a) +{ + return a >= 0 && a <= S32_MAX; +} + static void __reg_assign_32_into_64(struct bpf_reg_state *reg) { reg->umin_value = reg->u32_min_value; reg->umax_value = reg->u32_max_value; - /* Attempt to pull 32-bit signed bounds into 64-bit bounds - * but must be positive otherwise set to worse case bounds - * and refine later from tnum. + + /* Attempt to pull 32-bit signed bounds into 64-bit bounds but must + * be positive otherwise set to worse case bounds and refine later + * from tnum. */ - if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0) - reg->smax_value = reg->s32_max_value; - else - reg->smax_value = U32_MAX; - if (reg->s32_min_value >= 0) + if (__reg32_bound_s64(reg->s32_min_value) && + __reg32_bound_s64(reg->s32_max_value)) { reg->smin_value = reg->s32_min_value; - else + reg->smax_value = reg->s32_max_value; + } else { reg->smin_value = 0; + reg->smax_value = U32_MAX; + } } static void __reg_combine_32_into_64(struct bpf_reg_state *reg) @@ -1537,6 +1585,7 @@ static void init_func_state(struct bpf_verifier_env *env, state->frameno = frameno; state->subprogno = subprogno; init_reg_state(env, state); + mark_verifier_state_scratched(env); } /* Similar to push_stack(), but for async callbacks */ @@ -2040,7 +2089,7 @@ static int mark_reg_read(struct bpf_verifier_env *env, break; if (parent->live & REG_LIVE_DONE) { verbose(env, "verifier BUG type %s var_off %lld off %d\n", - reg_type_str[parent->type], + reg_type_str(env, parent->type), parent->var_off.value, parent->off); return -EFAULT; } @@ -2224,6 +2273,8 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, return -EINVAL; } + mark_reg_scratched(env, regno); + reg = ®s[regno]; rw64 = is_reg64(env, insn, regno, reg, t); if (t == SRC_OP) { @@ -2328,7 +2379,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, if (insn->code == 0) return 0; - if (env->log.level & BPF_LOG_LEVEL) { + if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask); verbose(env, "%d: ", idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); @@ -2378,8 +2429,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, */ if (insn->src_reg != BPF_REG_FP) return 0; - if (BPF_SIZE(insn->code) != BPF_DW) - return 0; /* dreg = *(u64 *)[fp - off] was a fill from the stack. * that [fp - off] slot contains scalar that needs to be @@ -2402,8 +2451,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, /* scalars can only be spilled into stack */ if (insn->dst_reg != BPF_REG_FP) return 0; - if (BPF_SIZE(insn->code) != BPF_DW) - return 0; spi = (-insn->off - 1) / BPF_REG_SIZE; if (spi >= 64) { verbose(env, "BUG spi %d\n", spi); @@ -2586,7 +2633,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, DECLARE_BITMAP(mask, 64); u32 history = st->jmp_history_cnt; - if (env->log.level & BPF_LOG_LEVEL) + if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx); for (i = last_idx;;) { if (skip_first) { @@ -2673,11 +2720,11 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, new_marks = true; reg->precise = true; } - if (env->log.level & BPF_LOG_LEVEL) { - print_verifier_state(env, func); - verbose(env, "parent %s regs=%x stack=%llx marks\n", + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "parent %s regs=%x stack=%llx marks:", new_marks ? "didn't have" : "already had", reg_mask, stack_mask); + print_verifier_state(env, func, true); } if (!reg_mask && !stack_mask) @@ -2703,9 +2750,8 @@ static int mark_chain_precision_stack(struct bpf_verifier_env *env, int spi) static bool is_spillable_regtype(enum bpf_reg_type type) { - switch (type) { + switch (base_type(type)) { case PTR_TO_MAP_VALUE: - case PTR_TO_MAP_VALUE_OR_NULL: case PTR_TO_STACK: case PTR_TO_CTX: case PTR_TO_PACKET: @@ -2714,21 +2760,13 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_FLOW_KEYS: case CONST_PTR_TO_MAP: case PTR_TO_SOCKET: - case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: - case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: - case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: - case PTR_TO_BTF_ID_OR_NULL: - case PTR_TO_RDONLY_BUF: - case PTR_TO_RDONLY_BUF_OR_NULL: - case PTR_TO_RDWR_BUF: - case PTR_TO_RDWR_BUF_OR_NULL: + case PTR_TO_BUF: case PTR_TO_PERCPU_BTF_ID: case PTR_TO_MEM: - case PTR_TO_MEM_OR_NULL: case PTR_TO_FUNC: case PTR_TO_MAP_KEY: return true; @@ -2833,6 +2871,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, env->insn_aux_data[insn_idx].sanitize_stack_spill = true; } + mark_stack_slot_scratched(env, spi); if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && !register_is_null(reg) && env->bpf_capable) { if (dst_reg != BPF_REG_FP) { @@ -2954,6 +2993,7 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env, slot = -i - 1; spi = slot / BPF_REG_SIZE; stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE]; + mark_stack_slot_scratched(env, spi); if (!env->allow_ptr_leaks && *stype != NOT_INIT @@ -3370,11 +3410,8 @@ static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno, /* We may have adjusted the register pointing to memory region, so we * need to try adding each of min_value and max_value to off * to make sure our theoretical access will be safe. - */ - if (env->log.level & BPF_LOG_LEVEL) - print_verifier_state(env, state); - - /* The minimum value is only important with signed + * + * The minimum value is only important with signed * comparisons where we can't assume the floor of a * value is 0. If we are using signed variables for our * index'es we need to make sure that whatever we use @@ -3569,7 +3606,7 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, */ *reg_type = info.reg_type; - if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL) { + if (base_type(*reg_type) == PTR_TO_BTF_ID) { *btf = info.btf; *btf_id = info.btf_id; } else { @@ -3637,7 +3674,7 @@ static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, } verbose(env, "R%d invalid %s access off=%d size=%d\n", - regno, reg_type_str[reg->type], off, size); + regno, reg_type_str(env, reg->type), off, size); return -EACCES; } @@ -4055,7 +4092,22 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) static bool bpf_map_is_rdonly(const struct bpf_map *map) { - return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen; + /* A map is considered read-only if the following condition are true: + * + * 1) BPF program side cannot change any of the map content. The + * BPF_F_RDONLY_PROG flag is throughout the lifetime of a map + * and was set at map creation time. + * 2) The map value(s) have been initialized from user space by a + * loader and then "frozen", such that no new map update/delete + * operations from syscall side are possible for the rest of + * the map's lifetime from that point onwards. + * 3) Any parallel/pending map update/delete operations from syscall + * side have been completed. Only after that point, it's safe to + * assume that map value(s) are immutable. + */ + return (map->map_flags & BPF_F_RDONLY_PROG) && + READ_ONCE(map->frozen) && + !bpf_map_write_active(map); } static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) @@ -4349,15 +4401,30 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn mark_reg_unknown(env, regs, value_regno); } } - } else if (reg->type == PTR_TO_MEM) { + } else if (base_type(reg->type) == PTR_TO_MEM) { + bool rdonly_mem = type_is_rdonly_mem(reg->type); + + if (type_may_be_null(reg->type)) { + verbose(env, "R%d invalid mem access '%s'\n", regno, + reg_type_str(env, reg->type)); + return -EACCES; + } + + if (t == BPF_WRITE && rdonly_mem) { + verbose(env, "R%d cannot write into %s\n", + regno, reg_type_str(env, reg->type)); + return -EACCES; + } + if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into mem\n", value_regno); return -EACCES; } + err = check_mem_region_access(env, regno, off, size, reg->mem_size, false); - if (!err && t == BPF_READ && value_regno >= 0) + if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem)) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_CTX) { enum bpf_reg_type reg_type = SCALAR_VALUE; @@ -4387,7 +4454,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else { mark_reg_known_zero(env, regs, value_regno); - if (reg_type_may_be_null(reg_type)) + if (type_may_be_null(reg_type)) regs[value_regno].id = ++env->id_gen; /* A load of ctx field could have different * actual load size with the one encoded in the @@ -4395,8 +4462,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn * a sub-register. */ regs[value_regno].subreg_def = DEF_NOT_SUBREG; - if (reg_type == PTR_TO_BTF_ID || - reg_type == PTR_TO_BTF_ID_OR_NULL) { + if (base_type(reg_type) == PTR_TO_BTF_ID) { regs[value_regno].btf = btf; regs[value_regno].btf_id = btf_id; } @@ -4449,7 +4515,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else if (type_is_sk_pointer(reg->type)) { if (t == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", - regno, reg_type_str[reg->type]); + regno, reg_type_str(env, reg->type)); return -EACCES; } err = check_sock_access(env, insn_idx, regno, off, size, t); @@ -4465,26 +4531,32 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else if (reg->type == CONST_PTR_TO_MAP) { err = check_ptr_to_map_access(env, regs, regno, off, size, t, value_regno); - } else if (reg->type == PTR_TO_RDONLY_BUF) { - if (t == BPF_WRITE) { - verbose(env, "R%d cannot write into %s\n", - regno, reg_type_str[reg->type]); - return -EACCES; + } else if (base_type(reg->type) == PTR_TO_BUF) { + bool rdonly_mem = type_is_rdonly_mem(reg->type); + const char *buf_info; + u32 *max_access; + + if (rdonly_mem) { + if (t == BPF_WRITE) { + verbose(env, "R%d cannot write into %s\n", + regno, reg_type_str(env, reg->type)); + return -EACCES; + } + buf_info = "rdonly"; + max_access = &env->prog->aux->max_rdonly_access; + } else { + buf_info = "rdwr"; + max_access = &env->prog->aux->max_rdwr_access; } + err = check_buffer_access(env, reg, regno, off, size, false, - "rdonly", - &env->prog->aux->max_rdonly_access); - if (!err && value_regno >= 0) - mark_reg_unknown(env, regs, value_regno); - } else if (reg->type == PTR_TO_RDWR_BUF) { - err = check_buffer_access(env, reg, regno, off, size, false, - "rdwr", - &env->prog->aux->max_rdwr_access); - if (!err && t == BPF_READ && value_regno >= 0) + buf_info, max_access); + + if (!err && value_regno >= 0 && (rdonly_mem || t == BPF_READ)) mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, - reg_type_str[reg->type]); + reg_type_str(env, reg->type)); return -EACCES; } @@ -4535,9 +4607,16 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i if (insn->imm == BPF_CMPXCHG) { /* Check comparison of R0 with memory location */ - err = check_reg_arg(env, BPF_REG_0, SRC_OP); + const u32 aux_reg = BPF_REG_0; + + err = check_reg_arg(env, aux_reg, SRC_OP); if (err) return err; + + if (is_pointer_value(env, aux_reg)) { + verbose(env, "R%d leaks addr into mem\n", aux_reg); + return -EACCES; + } } if (is_pointer_value(env, insn->src_reg)) { @@ -4551,7 +4630,7 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i is_sk_reg(env, insn->dst_reg)) { verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n", insn->dst_reg, - reg_type_str[reg_state(env, insn->dst_reg)->type]); + reg_type_str(env, reg_state(env, insn->dst_reg)->type)); return -EACCES; } @@ -4572,13 +4651,19 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i load_reg = -1; } - /* check whether we can read the memory */ + /* Check whether we can read the memory, with second call for fetch + * case to simulate the register fill. + */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_READ, load_reg, true); + BPF_SIZE(insn->code), BPF_READ, -1, true); + if (!err && load_reg >= 0) + err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_READ, load_reg, + true); if (err) return err; - /* check whether we can write into the same memory */ + /* Check whether we can write into the same memory. */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1, true); if (err) @@ -4728,8 +4813,10 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + const char *buf_info; + u32 *max_access; - switch (reg->type) { + switch (base_type(reg->type)) { case PTR_TO_PACKET: case PTR_TO_PACKET_META: return check_packet_access(env, regno, reg->off, access_size, @@ -4748,18 +4835,20 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_mem_region_access(env, regno, reg->off, access_size, reg->mem_size, zero_size_allowed); - case PTR_TO_RDONLY_BUF: - if (meta && meta->raw_mode) - return -EACCES; - return check_buffer_access(env, reg, regno, reg->off, - access_size, zero_size_allowed, - "rdonly", - &env->prog->aux->max_rdonly_access); - case PTR_TO_RDWR_BUF: + case PTR_TO_BUF: + if (type_is_rdonly_mem(reg->type)) { + if (meta && meta->raw_mode) + return -EACCES; + + buf_info = "rdonly"; + max_access = &env->prog->aux->max_rdonly_access; + } else { + buf_info = "rdwr"; + max_access = &env->prog->aux->max_rdwr_access; + } return check_buffer_access(env, reg, regno, reg->off, access_size, zero_size_allowed, - "rdwr", - &env->prog->aux->max_rdwr_access); + buf_info, max_access); case PTR_TO_STACK: return check_stack_range_initialized( env, @@ -4771,9 +4860,9 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, register_is_null(reg)) return 0; - verbose(env, "R%d type=%s expected=%s\n", regno, - reg_type_str[reg->type], - reg_type_str[PTR_TO_STACK]); + verbose(env, "R%d type=%s ", regno, + reg_type_str(env, reg->type)); + verbose(env, "expected=%s\n", reg_type_str(env, PTR_TO_STACK)); return -EACCES; } } @@ -4784,7 +4873,7 @@ int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, if (register_is_null(reg)) return 0; - if (reg_type_may_be_null(reg->type)) { + if (type_may_be_null(reg->type)) { /* Assuming that the register contains a value check if the memory * access is safe. Temporarily save and restore the register's state as * the conversion shouldn't be visible to a caller. @@ -4932,9 +5021,8 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno, static bool arg_type_is_mem_ptr(enum bpf_arg_type type) { - return type == ARG_PTR_TO_MEM || - type == ARG_PTR_TO_MEM_OR_NULL || - type == ARG_PTR_TO_UNINIT_MEM; + return base_type(type) == ARG_PTR_TO_MEM || + base_type(type) == ARG_PTR_TO_UNINIT_MEM; } static bool arg_type_is_mem_size(enum bpf_arg_type type) @@ -5039,8 +5127,7 @@ static const struct bpf_reg_types mem_types = { PTR_TO_MAP_KEY, PTR_TO_MAP_VALUE, PTR_TO_MEM, - PTR_TO_RDONLY_BUF, - PTR_TO_RDWR_BUF, + PTR_TO_BUF, }, }; @@ -5071,31 +5158,26 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_MAP_KEY] = &map_key_value_types, [ARG_PTR_TO_MAP_VALUE] = &map_key_value_types, [ARG_PTR_TO_UNINIT_MAP_VALUE] = &map_key_value_types, - [ARG_PTR_TO_MAP_VALUE_OR_NULL] = &map_key_value_types, [ARG_CONST_SIZE] = &scalar_types, [ARG_CONST_SIZE_OR_ZERO] = &scalar_types, [ARG_CONST_ALLOC_SIZE_OR_ZERO] = &scalar_types, [ARG_CONST_MAP_PTR] = &const_map_ptr_types, [ARG_PTR_TO_CTX] = &context_types, - [ARG_PTR_TO_CTX_OR_NULL] = &context_types, [ARG_PTR_TO_SOCK_COMMON] = &sock_types, #ifdef CONFIG_NET [ARG_PTR_TO_BTF_ID_SOCK_COMMON] = &btf_id_sock_common_types, #endif [ARG_PTR_TO_SOCKET] = &fullsock_types, - [ARG_PTR_TO_SOCKET_OR_NULL] = &fullsock_types, [ARG_PTR_TO_BTF_ID] = &btf_ptr_types, [ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types, [ARG_PTR_TO_MEM] = &mem_types, - [ARG_PTR_TO_MEM_OR_NULL] = &mem_types, [ARG_PTR_TO_UNINIT_MEM] = &mem_types, [ARG_PTR_TO_ALLOC_MEM] = &alloc_mem_types, - [ARG_PTR_TO_ALLOC_MEM_OR_NULL] = &alloc_mem_types, [ARG_PTR_TO_INT] = &int_ptr_types, [ARG_PTR_TO_LONG] = &int_ptr_types, [ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types, [ARG_PTR_TO_FUNC] = &func_ptr_types, - [ARG_PTR_TO_STACK_OR_NULL] = &stack_ptr_types, + [ARG_PTR_TO_STACK] = &stack_ptr_types, [ARG_PTR_TO_CONST_STR] = &const_str_ptr_types, [ARG_PTR_TO_TIMER] = &timer_types, }; @@ -5109,12 +5191,27 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, const struct bpf_reg_types *compatible; int i, j; - compatible = compatible_reg_types[arg_type]; + compatible = compatible_reg_types[base_type(arg_type)]; if (!compatible) { verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type); return -EFAULT; } + /* ARG_PTR_TO_MEM + RDONLY is compatible with PTR_TO_MEM and PTR_TO_MEM + RDONLY, + * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM and NOT with PTR_TO_MEM + RDONLY + * + * Same for MAYBE_NULL: + * + * ARG_PTR_TO_MEM + MAYBE_NULL is compatible with PTR_TO_MEM and PTR_TO_MEM + MAYBE_NULL, + * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM but NOT with PTR_TO_MEM + MAYBE_NULL + * + * Therefore we fold these flags depending on the arg_type before comparison. + */ + if (arg_type & MEM_RDONLY) + type &= ~MEM_RDONLY; + if (arg_type & PTR_MAYBE_NULL) + type &= ~PTR_MAYBE_NULL; + for (i = 0; i < ARRAY_SIZE(compatible->types); i++) { expected = compatible->types[i]; if (expected == NOT_INIT) @@ -5124,14 +5221,14 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, goto found; } - verbose(env, "R%d type=%s expected=", regno, reg_type_str[type]); + verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, reg->type)); for (j = 0; j + 1 < i; j++) - verbose(env, "%s, ", reg_type_str[compatible->types[j]]); - verbose(env, "%s\n", reg_type_str[compatible->types[j]]); + verbose(env, "%s, ", reg_type_str(env, compatible->types[j])); + verbose(env, "%s\n", reg_type_str(env, compatible->types[j])); return -EACCES; found: - if (type == PTR_TO_BTF_ID) { + if (reg->type == PTR_TO_BTF_ID) { if (!arg_btf_id) { if (!compatible->btf_id) { verbose(env, "verifier internal error: missing arg compatible BTF ID\n"); @@ -5190,15 +5287,14 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, return -EACCES; } - if (arg_type == ARG_PTR_TO_MAP_VALUE || - arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE || - arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) { + if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE || + base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) { err = resolve_map_arg_type(env, meta, &arg_type); if (err) return err; } - if (register_is_null(reg) && arg_type_may_be_null(arg_type)) + if (register_is_null(reg) && type_may_be_null(arg_type)) /* A NULL register has a SCALAR_VALUE type, so skip * type checking. */ @@ -5267,10 +5363,11 @@ skip_type_check: err = check_helper_mem_access(env, regno, meta->map_ptr->key_size, false, NULL); - } else if (arg_type == ARG_PTR_TO_MAP_VALUE || - (arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL && - !register_is_null(reg)) || - arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { + } else if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE || + base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) { + if (type_may_be_null(arg_type) && register_is_null(reg)) + return 0; + /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity */ @@ -5934,6 +6031,7 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn } if (insn->code == (BPF_JMP | BPF_CALL) && + insn->src_reg == 0 && insn->imm == BPF_FUNC_timer_set_callback) { struct bpf_verifier_state *async_cb; @@ -5992,9 +6090,9 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "caller:\n"); - print_verifier_state(env, caller); + print_verifier_state(env, caller, true); verbose(env, "callee:\n"); - print_verifier_state(env, callee); + print_verifier_state(env, callee, true); } return 0; } @@ -6085,6 +6183,27 @@ static int set_map_elem_callback_state(struct bpf_verifier_env *env, return 0; } +static int set_loop_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + /* bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, + * u64 flags); + * callback_fn(u32 index, void *callback_ctx); + */ + callee->regs[BPF_REG_1].type = SCALAR_VALUE; + callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; + + /* unused */ + __mark_reg_not_init(env, &callee->regs[BPF_REG_3]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); + + callee->in_callback_fn = true; + return 0; +} + static int set_timer_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, @@ -6114,6 +6233,33 @@ static int set_timer_callback_state(struct bpf_verifier_env *env, return 0; } +static int set_find_vma_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + /* bpf_find_vma(struct task_struct *task, u64 addr, + * void *callback_fn, void *callback_ctx, u64 flags) + * (callback_fn)(struct task_struct *task, + * struct vm_area_struct *vma, void *callback_ctx); + */ + callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1]; + + callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID; + __mark_reg_known_zero(&callee->regs[BPF_REG_2]); + callee->regs[BPF_REG_2].btf = btf_vmlinux; + callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA], + + /* pointer to stack or null */ + callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4]; + + /* unused */ + __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); + callee->in_callback_fn = true; + return 0; +} + static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; @@ -6161,9 +6307,9 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) *insn_idx = callee->callsite + 1; if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "returning from callee:\n"); - print_verifier_state(env, callee); + print_verifier_state(env, callee, true); verbose(env, "to caller at %d:\n", *insn_idx); - print_verifier_state(env, caller); + print_verifier_state(env, caller, true); } /* clear everything in the callee */ free_func_state(callee); @@ -6329,13 +6475,11 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env, static int check_get_func_ip(struct bpf_verifier_env *env) { - enum bpf_attach_type eatype = env->prog->expected_attach_type; enum bpf_prog_type type = resolve_prog_type(env->prog); int func_id = BPF_FUNC_get_func_ip; if (type == BPF_PROG_TYPE_TRACING) { - if (eatype != BPF_TRACE_FENTRY && eatype != BPF_TRACE_FEXIT && - eatype != BPF_MODIFY_RETURN) { + if (!bpf_prog_has_trampoline(env->prog)) { verbose(env, "func %s#%d supported only for fentry/fexit/fmod_ret programs\n", func_id_name(func_id), func_id); return -ENOTSUPP; @@ -6354,6 +6498,8 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn int *insn_idx_p) { const struct bpf_func_proto *fn = NULL; + enum bpf_return_type ret_type; + enum bpf_type_flag ret_flag; struct bpf_reg_state *regs; struct bpf_call_arg_meta meta; int insn_idx = *insn_idx_p; @@ -6431,13 +6577,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return err; } - if (func_id == BPF_FUNC_tail_call) { - err = check_reference_leak(env); - if (err) { - verbose(env, "tail_call would lead to reference leak\n"); - return err; - } - } else if (is_release_function(func_id)) { + if (is_release_function(func_id)) { err = release_reference(env, meta.ref_obj_id); if (err) { verbose(env, "func %s#%d reference has not been acquired before\n", @@ -6448,35 +6588,47 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs = cur_regs(env); - /* check that flags argument in get_local_storage(map, flags) is 0, - * this is required because get_local_storage() can't return an error. - */ - if (func_id == BPF_FUNC_get_local_storage && - !register_is_null(®s[BPF_REG_2])) { - verbose(env, "get_local_storage() doesn't support non-zero flags\n"); - return -EINVAL; - } - - if (func_id == BPF_FUNC_for_each_map_elem) { + switch (func_id) { + case BPF_FUNC_tail_call: + err = check_reference_leak(env); + if (err) { + verbose(env, "tail_call would lead to reference leak\n"); + return err; + } + break; + case BPF_FUNC_get_local_storage: + /* check that flags argument in get_local_storage(map, flags) is 0, + * this is required because get_local_storage() can't return an error. + */ + if (!register_is_null(®s[BPF_REG_2])) { + verbose(env, "get_local_storage() doesn't support non-zero flags\n"); + return -EINVAL; + } + break; + case BPF_FUNC_for_each_map_elem: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_map_elem_callback_state); - if (err < 0) - return -EINVAL; - } - - if (func_id == BPF_FUNC_timer_set_callback) { + break; + case BPF_FUNC_timer_set_callback: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_timer_callback_state); - if (err < 0) - return -EINVAL; - } - - if (func_id == BPF_FUNC_snprintf) { + break; + case BPF_FUNC_find_vma: + err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, + set_find_vma_callback_state); + break; + case BPF_FUNC_snprintf: err = check_bpf_snprintf_call(env, regs); - if (err < 0) - return err; + break; + case BPF_FUNC_loop: + err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, + set_loop_callback_state); + break; } + if (err) + return err; + /* reset caller saved regs */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); @@ -6487,13 +6639,14 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; /* update return register (already marked as written above) */ - if (fn->ret_type == RET_INTEGER) { + ret_type = fn->ret_type; + ret_flag = type_flag(fn->ret_type); + if (ret_type == RET_INTEGER) { /* sets type to SCALAR_VALUE */ mark_reg_unknown(env, regs, BPF_REG_0); - } else if (fn->ret_type == RET_VOID) { + } else if (ret_type == RET_VOID) { regs[BPF_REG_0].type = NOT_INIT; - } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL || - fn->ret_type == RET_PTR_TO_MAP_VALUE) { + } else if (base_type(ret_type) == RET_PTR_TO_MAP_VALUE) { /* There is no offset yet applied, variable or fixed */ mark_reg_known_zero(env, regs, BPF_REG_0); /* remember map_ptr, so that check_map_access() @@ -6507,28 +6660,25 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn } regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].map_uid = meta.map_uid; - if (fn->ret_type == RET_PTR_TO_MAP_VALUE) { - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; - if (map_value_has_spin_lock(meta.map_ptr)) - regs[BPF_REG_0].id = ++env->id_gen; - } else { - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; + regs[BPF_REG_0].type = PTR_TO_MAP_VALUE | ret_flag; + if (!type_may_be_null(ret_type) && + map_value_has_spin_lock(meta.map_ptr)) { + regs[BPF_REG_0].id = ++env->id_gen; } - } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) { + } else if (base_type(ret_type) == RET_PTR_TO_SOCKET) { mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL; - } else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) { + regs[BPF_REG_0].type = PTR_TO_SOCKET | ret_flag; + } else if (base_type(ret_type) == RET_PTR_TO_SOCK_COMMON) { mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL; - } else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) { + regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON | ret_flag; + } else if (base_type(ret_type) == RET_PTR_TO_TCP_SOCK) { mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL; - } else if (fn->ret_type == RET_PTR_TO_ALLOC_MEM_OR_NULL) { + regs[BPF_REG_0].type = PTR_TO_TCP_SOCK | ret_flag; + } else if (base_type(ret_type) == RET_PTR_TO_ALLOC_MEM) { mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL; + regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; regs[BPF_REG_0].mem_size = meta.mem_size; - } else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL || - fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID) { + } else if (base_type(ret_type) == RET_PTR_TO_MEM_OR_BTF_ID) { const struct btf_type *t; mark_reg_known_zero(env, regs, BPF_REG_0); @@ -6546,29 +6696,30 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn tname, PTR_ERR(ret)); return -EINVAL; } - regs[BPF_REG_0].type = - fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ? - PTR_TO_MEM : PTR_TO_MEM_OR_NULL; + regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; regs[BPF_REG_0].mem_size = tsize; } else { - regs[BPF_REG_0].type = - fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ? - PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL; + /* MEM_RDONLY may be carried from ret_flag, but it + * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise + * it will confuse the check of PTR_TO_BTF_ID in + * check_mem_access(). + */ + ret_flag &= ~MEM_RDONLY; + + regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; regs[BPF_REG_0].btf = meta.ret_btf; regs[BPF_REG_0].btf_id = meta.ret_btf_id; } - } else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL || - fn->ret_type == RET_PTR_TO_BTF_ID) { + } else if (base_type(ret_type) == RET_PTR_TO_BTF_ID) { int ret_btf_id; mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = fn->ret_type == RET_PTR_TO_BTF_ID ? - PTR_TO_BTF_ID : - PTR_TO_BTF_ID_OR_NULL; + regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; ret_btf_id = *fn->ret_btf_id; if (ret_btf_id == 0) { - verbose(env, "invalid return type %d of func %s#%d\n", - fn->ret_type, func_id_name(func_id), func_id); + verbose(env, "invalid return type %u of func %s#%d\n", + base_type(ret_type), func_id_name(func_id), + func_id); return -EINVAL; } /* current BPF helper definitions are only coming from @@ -6577,12 +6728,12 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs[BPF_REG_0].btf = btf_vmlinux; regs[BPF_REG_0].btf_id = ret_btf_id; } else { - verbose(env, "unknown return type %d of func %s#%d\n", - fn->ret_type, func_id_name(func_id), func_id); + verbose(env, "unknown return type %u of func %s#%d\n", + base_type(ret_type), func_id_name(func_id), func_id); return -EINVAL; } - if (reg_type_may_be_null(regs[BPF_REG_0].type)) + if (type_may_be_null(regs[BPF_REG_0].type)) regs[BPF_REG_0].id = ++env->id_gen; if (is_ptr_cast_function(func_id)) { @@ -6791,25 +6942,25 @@ static bool check_reg_sane_offset(struct bpf_verifier_env *env, if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) { verbose(env, "math between %s pointer and %lld is not allowed\n", - reg_type_str[type], val); + reg_type_str(env, type), val); return false; } if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) { verbose(env, "%s pointer offset %d is not allowed\n", - reg_type_str[type], reg->off); + reg_type_str(env, type), reg->off); return false; } if (smin == S64_MIN) { verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n", - reg_type_str[type]); + reg_type_str(env, type)); return false; } if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) { verbose(env, "value %lld makes %s pointer be out of bounds\n", - smin, reg_type_str[type]); + smin, reg_type_str(env, type)); return false; } @@ -7186,11 +7337,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; } - switch (ptr_reg->type) { - case PTR_TO_MAP_VALUE_OR_NULL: + if (ptr_reg->type & PTR_MAYBE_NULL) { verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n", - dst, reg_type_str[ptr_reg->type]); + dst, reg_type_str(env, ptr_reg->type)); return -EACCES; + } + + switch (base_type(ptr_reg->type)) { case CONST_PTR_TO_MAP: /* smin_val represents the known value */ if (known && smin_val == 0 && opcode == BPF_ADD) @@ -7198,14 +7351,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, fallthrough; case PTR_TO_PACKET_END: case PTR_TO_SOCKET: - case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: - case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: - case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: verbose(env, "R%d pointer arithmetic on %s prohibited\n", - dst, reg_type_str[ptr_reg->type]); + dst, reg_type_str(env, ptr_reg->type)); return -EACCES; default: break; @@ -8178,12 +8328,12 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, /* Got here implies adding two SCALAR_VALUEs */ if (WARN_ON_ONCE(ptr_reg)) { - print_verifier_state(env, state); + print_verifier_state(env, state, true); verbose(env, "verifier internal error: unexpected ptr_reg\n"); return -EINVAL; } if (WARN_ON(!src_reg)) { - print_verifier_state(env, state); + print_verifier_state(env, state, true); verbose(env, "verifier internal error: no src_reg\n"); return -EINVAL; } @@ -8292,6 +8442,10 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->dst_reg); } zext_32_to_64(dst_reg); + + __update_reg_bounds(dst_reg); + __reg_deduce_bounds(dst_reg); + __reg_bound_offset(dst_reg); } } else { /* case: R = imm @@ -8406,7 +8560,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, new_range = dst_reg->off; if (range_right_open) - new_range--; + new_range++; /* Examples for register markings: * @@ -8924,17 +9078,17 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, struct bpf_reg_state *reg, u32 id, bool is_null) { - if (reg_type_may_be_null(reg->type) && reg->id == id && + if (type_may_be_null(reg->type) && reg->id == id && !WARN_ON_ONCE(!reg->id)) { - /* Old offset (both fixed and variable parts) should - * have been known-zero, because we don't allow pointer - * arithmetic on pointers that might be NULL. - */ if (WARN_ON_ONCE(reg->smin_value || reg->smax_value || !tnum_equals_const(reg->var_off, 0) || reg->off)) { - __mark_reg_known_zero(reg); - reg->off = 0; + /* Old offset (both fixed and variable parts) should + * have been known-zero, because we don't allow pointer + * arithmetic on pointers that might be NULL. If we + * see this happening, don't convert the register. + */ + return; } if (is_null) { reg->type = SCALAR_VALUE; @@ -9302,7 +9456,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, */ if (!is_jmp32 && BPF_SRC(insn->code) == BPF_K && insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) && - reg_type_may_be_null(dst_reg->type)) { + type_may_be_null(dst_reg->type)) { /* Mark all identical registers in each branch as either * safe or unknown depending R == 0 or R != 0 conditional. */ @@ -9318,7 +9472,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return -EACCES; } if (env->log.level & BPF_LOG_LEVEL) - print_verifier_state(env, this_branch->frame[this_branch->curframe]); + print_insn_state(env, this_branch->frame[this_branch->curframe]); return 0; } @@ -9357,7 +9511,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) mark_reg_known_zero(env, regs, insn->dst_reg); dst_reg->type = aux->btf_var.reg_type; - switch (dst_reg->type) { + switch (base_type(dst_reg->type)) { case PTR_TO_MEM: dst_reg->mem_size = aux->btf_var.mem_size; break; @@ -9556,7 +9710,7 @@ static int check_return_code(struct bpf_verifier_env *env) /* enforce return zero from async callbacks like timer */ if (reg->type != SCALAR_VALUE) { verbose(env, "In async callback the register R0 is not a known value (%s)\n", - reg_type_str[reg->type]); + reg_type_str(env, reg->type)); return -EINVAL; } @@ -9570,7 +9724,7 @@ static int check_return_code(struct bpf_verifier_env *env) if (is_subprog) { if (reg->type != SCALAR_VALUE) { verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n", - reg_type_str[reg->type]); + reg_type_str(env, reg->type)); return -EINVAL; } return 0; @@ -9634,7 +9788,7 @@ static int check_return_code(struct bpf_verifier_env *env) if (reg->type != SCALAR_VALUE) { verbose(env, "At program exit the register R0 is not a known value (%s)\n", - reg_type_str[reg->type]); + reg_type_str(env, reg->type)); return -EINVAL; } @@ -10217,6 +10371,78 @@ err_free: return err; } +#define MIN_CORE_RELO_SIZE sizeof(struct bpf_core_relo) +#define MAX_CORE_RELO_SIZE MAX_FUNCINFO_REC_SIZE + +static int check_core_relo(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) +{ + u32 i, nr_core_relo, ncopy, expected_size, rec_size; + struct bpf_core_relo core_relo = {}; + struct bpf_prog *prog = env->prog; + const struct btf *btf = prog->aux->btf; + struct bpf_core_ctx ctx = { + .log = &env->log, + .btf = btf, + }; + bpfptr_t u_core_relo; + int err; + + nr_core_relo = attr->core_relo_cnt; + if (!nr_core_relo) + return 0; + if (nr_core_relo > INT_MAX / sizeof(struct bpf_core_relo)) + return -EINVAL; + + rec_size = attr->core_relo_rec_size; + if (rec_size < MIN_CORE_RELO_SIZE || + rec_size > MAX_CORE_RELO_SIZE || + rec_size % sizeof(u32)) + return -EINVAL; + + u_core_relo = make_bpfptr(attr->core_relos, uattr.is_kernel); + expected_size = sizeof(struct bpf_core_relo); + ncopy = min_t(u32, expected_size, rec_size); + + /* Unlike func_info and line_info, copy and apply each CO-RE + * relocation record one at a time. + */ + for (i = 0; i < nr_core_relo; i++) { + /* future proofing when sizeof(bpf_core_relo) changes */ + err = bpf_check_uarg_tail_zero(u_core_relo, expected_size, rec_size); + if (err) { + if (err == -E2BIG) { + verbose(env, "nonzero tailing record in core_relo"); + if (copy_to_bpfptr_offset(uattr, + offsetof(union bpf_attr, core_relo_rec_size), + &expected_size, sizeof(expected_size))) + err = -EFAULT; + } + break; + } + + if (copy_from_bpfptr(&core_relo, u_core_relo, ncopy)) { + err = -EFAULT; + break; + } + + if (core_relo.insn_off % 8 || core_relo.insn_off / 8 >= prog->len) { + verbose(env, "Invalid core_relo[%u].insn_off:%u prog->len:%u\n", + i, core_relo.insn_off, prog->len); + err = -EINVAL; + break; + } + + err = bpf_core_apply(&ctx, &core_relo, i, + &prog->insnsi[core_relo.insn_off / 8]); + if (err) + break; + bpfptr_add(&u_core_relo, rec_size); + } + return err; +} + static int check_btf_info(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) @@ -10247,6 +10473,10 @@ static int check_btf_info(struct bpf_verifier_env *env, if (err) return err; + err = check_core_relo(env, attr, uattr); + if (err) + return err; + return 0; } @@ -10415,7 +10645,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, return true; if (rcur->type == NOT_INIT) return false; - switch (rold->type) { + switch (base_type(rold->type)) { case SCALAR_VALUE: if (env->explore_alu_limits) return false; @@ -10437,6 +10667,22 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, } case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: + /* a PTR_TO_MAP_VALUE could be safe to use as a + * PTR_TO_MAP_VALUE_OR_NULL into the same map. + * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL- + * checked, doing so could have affected others with the same + * id, and we can't check for that because we lost the id when + * we converted to a PTR_TO_MAP_VALUE. + */ + if (type_may_be_null(rold->type)) { + if (!type_may_be_null(rcur->type)) + return false; + if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id))) + return false; + /* Check our ids match any regs they're supposed to */ + return check_ids(rold->id, rcur->id, idmap); + } + /* If the new min/max/var_off satisfy the old ones and * everything else matches, we are OK. * 'id' is not compared, since it's only used for maps with @@ -10448,20 +10694,6 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); - case PTR_TO_MAP_VALUE_OR_NULL: - /* a PTR_TO_MAP_VALUE could be safe to use as a - * PTR_TO_MAP_VALUE_OR_NULL into the same map. - * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL- - * checked, doing so could have affected others with the same - * id, and we can't check for that because we lost the id when - * we converted to a PTR_TO_MAP_VALUE. - */ - if (rcur->type != PTR_TO_MAP_VALUE_OR_NULL) - return false; - if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id))) - return false; - /* Check our ids match any regs they're supposed to */ - return check_ids(rold->id, rcur->id, idmap); case PTR_TO_PACKET_META: case PTR_TO_PACKET: if (rcur->type != rold->type) @@ -10490,11 +10722,8 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, case PTR_TO_PACKET_END: case PTR_TO_FLOW_KEYS: case PTR_TO_SOCKET: - case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: - case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: - case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: /* Only valid matches are exact, which memcmp() above * would have accepted @@ -11020,17 +11249,13 @@ next: /* Return true if it's OK to have the same insn return a different type. */ static bool reg_type_mismatch_ok(enum bpf_reg_type type) { - switch (type) { + switch (base_type(type)) { case PTR_TO_CTX: case PTR_TO_SOCKET: - case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: - case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: - case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: - case PTR_TO_BTF_ID_OR_NULL: return false; default: return true; @@ -11110,16 +11335,12 @@ static int do_check(struct bpf_verifier_env *env) if (need_resched()) cond_resched(); - if (env->log.level & BPF_LOG_LEVEL2 || - (env->log.level & BPF_LOG_LEVEL && do_print_state)) { - if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "%d:", env->insn_idx); - else - verbose(env, "\nfrom %d to %d%s:", - env->prev_insn_idx, env->insn_idx, - env->cur_state->speculative ? - " (speculative execution)" : ""); - print_verifier_state(env, state->frame[state->curframe]); + if (env->log.level & BPF_LOG_LEVEL2 && do_print_state) { + verbose(env, "\nfrom %d to %d%s:", + env->prev_insn_idx, env->insn_idx, + env->cur_state->speculative ? + " (speculative execution)" : ""); + print_verifier_state(env, state->frame[state->curframe], true); do_print_state = false; } @@ -11130,9 +11351,15 @@ static int do_check(struct bpf_verifier_env *env) .private_data = env, }; + if (verifier_state_scratched(env)) + print_insn_state(env, state->frame[state->curframe]); + verbose_linfo(env, env->insn_idx, "; "); + env->prev_log_len = env->log.len_used; verbose(env, "%d: ", env->insn_idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); + env->prev_insn_print_len = env->log.len_used - env->prev_log_len; + env->prev_log_len = env->log.len_used; } if (bpf_prog_is_dev_bound(env->prog->aux)) { @@ -11254,7 +11481,7 @@ static int do_check(struct bpf_verifier_env *env) 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[reg_state(env, insn->dst_reg)->type]); + reg_type_str(env, reg_state(env, insn->dst_reg)->type)); return -EACCES; } @@ -11341,6 +11568,7 @@ static int do_check(struct bpf_verifier_env *env) if (err) return err; process_bpf_exit: + mark_verifier_state_scratched(env); update_branch_counts(env, env->cur_state); err = pop_stack(env, &prev_insn_idx, &env->insn_idx, pop_log); @@ -11506,7 +11734,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, err = -EINVAL; goto err_put; } - aux->btf_var.reg_type = PTR_TO_MEM; + aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY; aux->btf_var.mem_size = tsize; } else { aux->btf_var.reg_type = PTR_TO_BTF_ID; @@ -11631,6 +11859,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } } + if (map_value_has_timer(map)) { + if (is_tracing_prog_type(prog_type)) { + verbose(env, "tracing progs cannot use bpf_timer yet\n"); + return -EINVAL; + } + } + if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); @@ -11659,6 +11894,9 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } break; case BPF_MAP_TYPE_RINGBUF: + case BPF_MAP_TYPE_INODE_STORAGE: + case BPF_MAP_TYPE_SK_STORAGE: + case BPF_MAP_TYPE_TASK_STORAGE: break; default: verbose(env, @@ -12842,6 +13080,7 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, static int do_misc_fixups(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; + enum bpf_attach_type eatype = prog->expected_attach_type; bool expect_blinding = bpf_jit_blinding_enabled(prog); enum bpf_prog_type prog_type = resolve_prog_type(prog); struct bpf_insn *insn = prog->insnsi; @@ -13212,11 +13451,79 @@ patch_map_ops_generic: continue; } + /* Implement bpf_get_func_arg inline. */ + if (prog_type == BPF_PROG_TYPE_TRACING && + insn->imm == BPF_FUNC_get_func_arg) { + /* Load nr_args from ctx - 8 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + insn_buf[1] = BPF_JMP32_REG(BPF_JGE, BPF_REG_2, BPF_REG_0, 6); + insn_buf[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 3); + insn_buf[3] = BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1); + insn_buf[4] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0); + insn_buf[5] = BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0); + insn_buf[6] = BPF_MOV64_IMM(BPF_REG_0, 0); + insn_buf[7] = BPF_JMP_A(1); + insn_buf[8] = BPF_MOV64_IMM(BPF_REG_0, -EINVAL); + cnt = 9; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + + /* Implement bpf_get_func_ret inline. */ + if (prog_type == BPF_PROG_TYPE_TRACING && + insn->imm == BPF_FUNC_get_func_ret) { + if (eatype == BPF_TRACE_FEXIT || + eatype == BPF_MODIFY_RETURN) { + /* Load nr_args from ctx - 8 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + insn_buf[1] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3); + insn_buf[2] = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1); + insn_buf[3] = BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0); + insn_buf[4] = BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_3, 0); + insn_buf[5] = BPF_MOV64_IMM(BPF_REG_0, 0); + cnt = 6; + } else { + insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, -EOPNOTSUPP); + cnt = 1; + } + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + + /* Implement get_func_arg_cnt inline. */ + if (prog_type == BPF_PROG_TYPE_TRACING && + insn->imm == BPF_FUNC_get_func_arg_cnt) { + /* Load nr_args from ctx - 8 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1); + if (!new_prog) + return -ENOMEM; + + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + /* Implement bpf_get_func_ip inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_ip) { - /* Load IP address from ctx - 8 */ - insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + /* Load IP address from ctx - 16 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -16); new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1); if (!new_prog) @@ -13330,7 +13637,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) mark_reg_known_zero(env, regs, i); else if (regs[i].type == SCALAR_VALUE) mark_reg_unknown(env, regs, i); - else if (regs[i].type == PTR_TO_MEM_OR_NULL) { + else if (base_type(regs[i].type) == PTR_TO_MEM) { const u32 mem_size = regs[i].mem_size; mark_reg_known_zero(env, regs, i); @@ -13918,13 +14225,15 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) log->ubuf = (char __user *) (unsigned long) attr->log_buf; log->len_total = attr->log_size; - ret = -EINVAL; /* log attributes have to be sane */ - if (log->len_total < 128 || log->len_total > UINT_MAX >> 2 || - !log->level || !log->ubuf || log->level & ~BPF_LOG_MASK) + if (!bpf_verifier_log_attr_valid(log)) { + ret = -EINVAL; goto err_unlock; + } } + mark_verifier_state_clean(env); + if (IS_ERR(btf_vmlinux)) { /* Either gcc or pahole or kernel are broken. */ verbose(env, "in-kernel BTF is malformed\n"); diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index bfbeabc17a9d..6e36e854b512 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -65,6 +65,25 @@ static inline struct cgroup_fs_context *cgroup_fc2context(struct fs_context *fc) return container_of(kfc, struct cgroup_fs_context, kfc); } +struct cgroup_pidlist; + +struct cgroup_file_ctx { + struct cgroup_namespace *ns; + + struct { + void *trigger; + } psi; + + struct { + bool started; + struct css_task_iter iter; + } procs; + + struct { + struct cgroup_pidlist *pidlist; + } procs1; +}; + /* * A cgroup can be associated with multiple css_sets as different tasks may * belong to different cgroups on different hierarchies. In the other diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 81c9e0685948..41e0837a5a0b 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -394,6 +394,7 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) * next pid to display, if any */ struct kernfs_open_file *of = s->private; + struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_pidlist *l; enum cgroup_filetype type = seq_cft(s)->private; @@ -403,25 +404,24 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) mutex_lock(&cgrp->pidlist_mutex); /* - * !NULL @of->priv indicates that this isn't the first start() - * after open. If the matching pidlist is around, we can use that. - * Look for it. Note that @of->priv can't be used directly. It - * could already have been destroyed. + * !NULL @ctx->procs1.pidlist indicates that this isn't the first + * start() after open. If the matching pidlist is around, we can use + * that. Look for it. Note that @ctx->procs1.pidlist can't be used + * directly. It could already have been destroyed. */ - if (of->priv) - of->priv = cgroup_pidlist_find(cgrp, type); + if (ctx->procs1.pidlist) + ctx->procs1.pidlist = cgroup_pidlist_find(cgrp, type); /* * Either this is the first start() after open or the matching * pidlist has been destroyed inbetween. Create a new one. */ - if (!of->priv) { - ret = pidlist_array_load(cgrp, type, - (struct cgroup_pidlist **)&of->priv); + if (!ctx->procs1.pidlist) { + ret = pidlist_array_load(cgrp, type, &ctx->procs1.pidlist); if (ret) return ERR_PTR(ret); } - l = of->priv; + l = ctx->procs1.pidlist; if (pid) { int end = l->length; @@ -449,7 +449,8 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) static void cgroup_pidlist_stop(struct seq_file *s, void *v) { struct kernfs_open_file *of = s->private; - struct cgroup_pidlist *l = of->priv; + struct cgroup_file_ctx *ctx = of->priv; + struct cgroup_pidlist *l = ctx->procs1.pidlist; if (l) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, @@ -460,7 +461,8 @@ static void cgroup_pidlist_stop(struct seq_file *s, void *v) static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; - struct cgroup_pidlist *l = of->priv; + struct cgroup_file_ctx *ctx = of->priv; + struct cgroup_pidlist *l = ctx->procs1.pidlist; pid_t *p = v; pid_t *end = l->list + l->length; /* @@ -504,10 +506,11 @@ static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of, goto out_unlock; /* - * Even if we're attaching all tasks in the thread group, we only - * need to check permissions on one of them. + * Even if we're attaching all tasks in the thread group, we only need + * to check permissions on one of them. Check permissions using the + * credentials from file open to protect against inherited fd attacks. */ - cred = current_cred(); + cred = of->file->f_cred; tcred = get_task_cred(task); if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && !uid_eq(cred->euid, tcred->uid) && diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 919194de39c8..b31e1465868a 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -30,6 +30,7 @@ #include "cgroup-internal.h" +#include <linux/bpf-cgroup.h> #include <linux/cred.h> #include <linux/errno.h> #include <linux/init_task.h> @@ -2650,11 +2651,11 @@ void cgroup_migrate_add_src(struct css_set *src_cset, if (src_cset->dead) return; - src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); - if (!list_empty(&src_cset->mg_preload_node)) return; + src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); + WARN_ON(src_cset->mg_src_cgrp); WARN_ON(src_cset->mg_dst_cgrp); WARN_ON(!list_empty(&src_cset->mg_tasks)); @@ -3630,6 +3631,7 @@ static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, enum psi_res res) { + struct cgroup_file_ctx *ctx = of->priv; struct psi_trigger *new; struct cgroup *cgrp; struct psi_group *psi; @@ -3648,7 +3650,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, return PTR_ERR(new); } - psi_trigger_replace(&of->priv, new); + psi_trigger_replace(&ctx->psi.trigger, new); cgroup_put(cgrp); @@ -3679,12 +3681,16 @@ static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, poll_table *pt) { - return psi_trigger_poll(&of->priv, of->file, pt); + struct cgroup_file_ctx *ctx = of->priv; + + return psi_trigger_poll(&ctx->psi.trigger, of->file, pt); } static void cgroup_pressure_release(struct kernfs_open_file *of) { - psi_trigger_replace(&of->priv, NULL); + struct cgroup_file_ctx *ctx = of->priv; + + psi_trigger_replace(&ctx->psi.trigger, NULL); } bool cgroup_psi_enabled(void) @@ -3811,24 +3817,43 @@ static ssize_t cgroup_kill_write(struct kernfs_open_file *of, char *buf, static int cgroup_file_open(struct kernfs_open_file *of) { struct cftype *cft = of_cft(of); + struct cgroup_file_ctx *ctx; + int ret; - if (cft->open) - return cft->open(of); - return 0; + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->ns = current->nsproxy->cgroup_ns; + get_cgroup_ns(ctx->ns); + of->priv = ctx; + + if (!cft->open) + return 0; + + ret = cft->open(of); + if (ret) { + put_cgroup_ns(ctx->ns); + kfree(ctx); + } + return ret; } static void cgroup_file_release(struct kernfs_open_file *of) { struct cftype *cft = of_cft(of); + struct cgroup_file_ctx *ctx = of->priv; if (cft->release) cft->release(of); + put_cgroup_ns(ctx->ns); + kfree(ctx); } static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; + struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = of->kn->parent->priv; struct cftype *cft = of_cft(of); struct cgroup_subsys_state *css; @@ -3845,7 +3870,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, */ if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) && !(cft->flags & CFTYPE_NS_DELEGATABLE) && - ns != &init_cgroup_ns && ns->root_cset->dfl_cgrp == cgrp) + ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp) return -EPERM; if (cft->write) @@ -4751,21 +4776,21 @@ void css_task_iter_end(struct css_task_iter *it) static void cgroup_procs_release(struct kernfs_open_file *of) { - if (of->priv) { - css_task_iter_end(of->priv); - kfree(of->priv); - } + struct cgroup_file_ctx *ctx = of->priv; + + if (ctx->procs.started) + css_task_iter_end(&ctx->procs.iter); } static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; - struct css_task_iter *it = of->priv; + struct cgroup_file_ctx *ctx = of->priv; if (pos) (*pos)++; - return css_task_iter_next(it); + return css_task_iter_next(&ctx->procs.iter); } static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, @@ -4773,21 +4798,18 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, { struct kernfs_open_file *of = s->private; struct cgroup *cgrp = seq_css(s)->cgroup; - struct css_task_iter *it = of->priv; + struct cgroup_file_ctx *ctx = of->priv; + struct css_task_iter *it = &ctx->procs.iter; /* * When a seq_file is seeked, it's always traversed sequentially * from position 0, so we can simply keep iterating on !0 *pos. */ - if (!it) { + if (!ctx->procs.started) { if (WARN_ON_ONCE((*pos))) return ERR_PTR(-EINVAL); - - it = kzalloc(sizeof(*it), GFP_KERNEL); - if (!it) - return ERR_PTR(-ENOMEM); - of->priv = it; css_task_iter_start(&cgrp->self, iter_flags, it); + ctx->procs.started = true; } else if (!(*pos)) { css_task_iter_end(it); css_task_iter_start(&cgrp->self, iter_flags, it); @@ -4838,9 +4860,9 @@ static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb) static int cgroup_procs_write_permission(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, - struct super_block *sb) + struct super_block *sb, + struct cgroup_namespace *ns) { - struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; struct cgroup *com_cgrp = src_cgrp; int ret; @@ -4869,11 +4891,12 @@ static int cgroup_procs_write_permission(struct cgroup *src_cgrp, static int cgroup_attach_permissions(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, - struct super_block *sb, bool threadgroup) + struct super_block *sb, bool threadgroup, + struct cgroup_namespace *ns) { int ret = 0; - ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb); + ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb, ns); if (ret) return ret; @@ -4890,8 +4913,10 @@ static int cgroup_attach_permissions(struct cgroup *src_cgrp, static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, bool threadgroup) { + struct cgroup_file_ctx *ctx = of->priv; struct cgroup *src_cgrp, *dst_cgrp; struct task_struct *task; + const struct cred *saved_cred; ssize_t ret; bool locked; @@ -4909,9 +4934,16 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); spin_unlock_irq(&css_set_lock); - /* process and thread migrations follow same delegation rule */ + /* + * Process and thread migrations follow same delegation rule. Check + * permissions using the credentials from file open to protect against + * inherited fd attacks. + */ + saved_cred = override_creds(of->file->f_cred); ret = cgroup_attach_permissions(src_cgrp, dst_cgrp, - of->file->f_path.dentry->d_sb, threadgroup); + of->file->f_path.dentry->d_sb, + threadgroup, ctx->ns); + revert_creds(saved_cred); if (ret) goto out_finish; @@ -5711,7 +5743,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) /* Create the root cgroup state for this subsystem */ ss->root = &cgrp_dfl_root; - css = ss->css_alloc(cgroup_css(&cgrp_dfl_root.cgrp, ss)); + css = ss->css_alloc(NULL); /* We don't handle early failures gracefully */ BUG_ON(IS_ERR(css)); init_and_link_css(css, ss, &cgrp_dfl_root.cgrp); @@ -6130,7 +6162,8 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) goto err; ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb, - !(kargs->flags & CLONE_THREAD)); + !(kargs->flags & CLONE_THREAD), + current->nsproxy->cgroup_ns); if (ret) goto err; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index d0e163a02099..dc653ab26e50 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -616,19 +616,11 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial) struct cpuset *c, *par; int ret; - rcu_read_lock(); - - /* Each of our child cpusets must be a subset of us */ - ret = -EBUSY; - cpuset_for_each_child(c, css, cur) - if (!is_cpuset_subset(c, trial)) - goto out; - - /* Remaining checks don't apply to root cpuset */ - ret = 0; + /* The checks don't apply to root cpuset */ if (cur == &top_cpuset) - goto out; + return 0; + rcu_read_lock(); par = parent_cs(cur); /* On legacy hierarchy, we must be a subset of our parent cpuset. */ @@ -3536,7 +3528,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) bool __cpuset_node_allowed(int node, gfp_t gfp_mask) { struct cpuset *cs; /* current cpuset ancestors */ - int allowed; /* is allocation in zone z allowed? */ + bool allowed; /* is allocation in zone z allowed? */ unsigned long flags; if (in_interrupt()) diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 1486768f2318..9d331ba44870 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -35,7 +35,7 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) * instead of NULL, we can tell whether @cgrp is on the list by * testing the next pointer for NULL. */ - if (cgroup_rstat_cpu(cgrp, cpu)->updated_next) + if (data_race(cgroup_rstat_cpu(cgrp, cpu)->updated_next)) return; raw_spin_lock_irqsave(cpu_lock, flags); @@ -88,6 +88,7 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, struct cgroup *root, int cpu) { struct cgroup_rstat_cpu *rstatc; + struct cgroup *parent; if (pos == root) return NULL; @@ -96,10 +97,14 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, * We're gonna walk down to the first leaf and visit/remove it. We * can pick whatever unvisited node as the starting point. */ - if (!pos) + if (!pos) { pos = root; - else + /* return NULL if this subtree is not on-list */ + if (!cgroup_rstat_cpu(pos, cpu)->updated_next) + return NULL; + } else { pos = cgroup_parent(pos); + } /* walk down to the first leaf */ while (true) { @@ -115,33 +120,25 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, * However, due to the way we traverse, @pos will be the first * child in most cases. The only exception is @root. */ - if (rstatc->updated_next) { - struct cgroup *parent = cgroup_parent(pos); - - if (parent) { - struct cgroup_rstat_cpu *prstatc; - struct cgroup **nextp; - - prstatc = cgroup_rstat_cpu(parent, cpu); - nextp = &prstatc->updated_children; - while (true) { - struct cgroup_rstat_cpu *nrstatc; - - nrstatc = cgroup_rstat_cpu(*nextp, cpu); - if (*nextp == pos) - break; - WARN_ON_ONCE(*nextp == parent); - nextp = &nrstatc->updated_next; - } - *nextp = rstatc->updated_next; - } + parent = cgroup_parent(pos); + if (parent) { + struct cgroup_rstat_cpu *prstatc; + struct cgroup **nextp; - rstatc->updated_next = NULL; - return pos; + prstatc = cgroup_rstat_cpu(parent, cpu); + nextp = &prstatc->updated_children; + while (*nextp != pos) { + struct cgroup_rstat_cpu *nrstatc; + + nrstatc = cgroup_rstat_cpu(*nextp, cpu); + WARN_ON_ONCE(*nextp == parent); + nextp = &nrstatc->updated_next; + } + *nextp = rstatc->updated_next; } - /* only happens for @root */ - return NULL; + rstatc->updated_next = NULL; + return pos; } /* see cgroup_rstat_flush() */ diff --git a/kernel/cpu.c b/kernel/cpu.c index 192e43a87407..407a2568f35e 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -31,6 +31,7 @@ #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> +#include <linux/scs.h> #include <linux/percpu-rwsem.h> #include <linux/cpuset.h> @@ -588,6 +589,12 @@ static int bringup_cpu(unsigned int cpu) int ret; /* + * Reset stale stack state from the last time this CPU was online. + */ + scs_task_reset(idle); + kasan_unpoison_task_stack(idle); + + /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. * Prevent irq alloc/free across the bringup. diff --git a/kernel/crash_core.c b/kernel/crash_core.c index eb53f5ec62c9..256cf6db573c 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -6,6 +6,7 @@ #include <linux/buildid.h> #include <linux/crash_core.h> +#include <linux/init.h> #include <linux/utsname.h> #include <linux/vmalloc.h> @@ -295,6 +296,16 @@ int __init parse_crashkernel_low(char *cmdline, "crashkernel=", suffix_tbl[SUFFIX_LOW]); } +/* + * Add a dummy early_param handler to mark crashkernel= as a known command line + * parameter and suppress incorrect warnings in init/main.c. + */ +static int __init parse_crashkernel_dummy(char *arg) +{ + return 0; +} +early_param("crashkernel", parse_crashkernel_dummy); + Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len) { diff --git a/kernel/entry/common.c b/kernel/entry/common.c index d5a61d565ad5..bad713684c2e 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -187,7 +187,7 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, /* Check if any of the above work has queued a deferred wakeup */ tick_nohz_user_enter_prepare(); - ti_work = READ_ONCE(current_thread_info()->flags); + ti_work = read_thread_flags(); } /* Return the latest work state for arch_exit_to_user_mode() */ @@ -196,7 +196,7 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, static void exit_to_user_mode_prepare(struct pt_regs *regs) { - unsigned long ti_work = READ_ONCE(current_thread_info()->flags); + unsigned long ti_work = read_thread_flags(); lockdep_assert_irqs_disabled(); diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c index 49972ee99aff..96d476e06c77 100644 --- a/kernel/entry/kvm.c +++ b/kernel/entry/kvm.c @@ -26,7 +26,7 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) if (ret) return ret; - ti_work = READ_ONCE(current_thread_info()->flags); + ti_work = read_thread_flags(); } while (ti_work & XFER_TO_GUEST_MODE_WORK || need_resched()); return 0; } @@ -43,7 +43,7 @@ int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu) * disabled in the inner loop before going into guest mode. No need * to disable interrupts here. */ - ti_work = READ_ONCE(current_thread_info()->flags); + ti_work = read_thread_flags(); if (!(ti_work & XFER_TO_GUEST_MODE_WORK)) return 0; diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c index 4508201847d2..0b6379adff6b 100644 --- a/kernel/entry/syscall_user_dispatch.c +++ b/kernel/entry/syscall_user_dispatch.c @@ -48,7 +48,7 @@ bool syscall_user_dispatch(struct pt_regs *regs) * the selector is loaded by userspace. */ if (unlikely(__get_user(state, sd->selector))) { - force_fatal_sig(SIGSEGV); + force_exit_sig(SIGSEGV); return true; } @@ -56,7 +56,7 @@ bool syscall_user_dispatch(struct pt_regs *regs) return false; if (state != SYSCALL_DISPATCH_FILTER_BLOCK) { - force_fatal_sig(SIGSYS); + force_exit_sig(SIGSYS); return true; } } diff --git a/kernel/events/core.c b/kernel/events/core.c index 523106a506ee..1362b9b770d8 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1808,6 +1808,8 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) list_add_rcu(&event->event_entry, &ctx->event_list); ctx->nr_events++; + if (event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT) + ctx->nr_user++; if (event->attr.inherit_stat) ctx->nr_stat++; @@ -1999,6 +2001,8 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) event->attach_state &= ~PERF_ATTACH_CONTEXT; ctx->nr_events--; + if (event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT) + ctx->nr_user--; if (event->attr.inherit_stat) ctx->nr_stat--; @@ -9759,6 +9763,9 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, continue; if (event->attr.config != entry->type) continue; + /* Cannot deliver synchronous signal to other task. */ + if (event->attr.sigtrap) + continue; if (perf_tp_event_match(event, &data, regs)) perf_swevent_event(event, count, &data, regs); } diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index f895265d7548..c09324663088 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -575,8 +575,6 @@ EXPORT_SYMBOL_GPL(handle_simple_irq); */ void handle_untracked_irq(struct irq_desc *desc) { - unsigned int flags = 0; - raw_spin_lock(&desc->lock); if (!irq_may_run(desc)) @@ -593,7 +591,7 @@ void handle_untracked_irq(struct irq_desc *desc) irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS); raw_spin_unlock(&desc->lock); - __handle_irq_event_percpu(desc, &flags); + __handle_irq_event_percpu(desc); raw_spin_lock(&desc->lock); irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS); diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 27182003b879..9489f93b3db3 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -136,7 +136,7 @@ void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action) wake_up_process(action->thread); } -irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags) +irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc) { irqreturn_t retval = IRQ_NONE; unsigned int irq = desc->irq_data.irq; @@ -174,10 +174,6 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags } __irq_wake_thread(desc, action); - - fallthrough; /* to add to randomness */ - case IRQ_HANDLED: - *flags |= action->flags; break; default: @@ -193,11 +189,10 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) { irqreturn_t retval; - unsigned int flags = 0; - retval = __handle_irq_event_percpu(desc, &flags); + retval = __handle_irq_event_percpu(desc); - add_interrupt_randomness(desc->irq_data.irq, flags); + add_interrupt_randomness(desc->irq_data.irq); if (!irq_settings_no_debug(desc)) note_interrupt(desc, retval); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 54363527feea..99cbdf55a8bd 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -103,7 +103,7 @@ extern int __irq_get_irqchip_state(struct irq_data *data, extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr); -irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags); +irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc); irqreturn_t handle_irq_event_percpu(struct irq_desc *desc); irqreturn_t handle_irq_event(struct irq_desc *desc); diff --git a/kernel/kcsan/Makefile b/kernel/kcsan/Makefile index c2bb07f5bcc7..e893b0e1d62a 100644 --- a/kernel/kcsan/Makefile +++ b/kernel/kcsan/Makefile @@ -8,6 +8,7 @@ CFLAGS_REMOVE_debugfs.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_report.o = $(CC_FLAGS_FTRACE) CFLAGS_core.o := $(call cc-option,-fno-conserve-stack) \ + $(call cc-option,-mno-outline-atomics) \ -fno-stack-protector -DDISABLE_BRANCH_PROFILING obj-y := core.o debugfs.o report.o diff --git a/kernel/kprobes.c b/kernel/kprobes.c index e9db0c810554..21eccc961bba 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2086,6 +2086,9 @@ int register_kretprobe(struct kretprobe *rp) } } + if (rp->data_size > KRETPROBE_MAX_DATA_SIZE) + return -E2BIG; + rp->kp.pre_handler = pre_handler_kretprobe; rp->kp.post_handler = NULL; diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 0c6a48dfcecb..1f25a4d7de27 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1380,7 +1380,7 @@ static bool rtmutex_spin_on_owner(struct rt_mutex_base *lock, * - the VCPU on which owner runs is preempted */ if (!owner->on_cpu || need_resched() || - rt_mutex_waiter_is_top_waiter(lock, waiter) || + !rt_mutex_waiter_is_top_waiter(lock, waiter) || vcpu_is_preempted(task_cpu(owner))) { res = false; break; diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index c51387a43265..04a74d040a6d 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -105,9 +105,9 @@ * atomic_long_cmpxchg() will be used to obtain writer lock. * * There are three places where the lock handoff bit may be set or cleared. - * 1) rwsem_mark_wake() for readers. - * 2) rwsem_try_write_lock() for writers. - * 3) Error path of rwsem_down_write_slowpath(). + * 1) rwsem_mark_wake() for readers -- set, clear + * 2) rwsem_try_write_lock() for writers -- set, clear + * 3) rwsem_del_waiter() -- clear * * For all the above cases, wait_lock will be held. A writer must also * be the first one in the wait_list to be eligible for setting the handoff @@ -334,6 +334,9 @@ struct rwsem_waiter { struct task_struct *task; enum rwsem_waiter_type type; unsigned long timeout; + + /* Writer only, not initialized in reader */ + bool handoff_set; }; #define rwsem_first_waiter(sem) \ list_first_entry(&sem->wait_list, struct rwsem_waiter, list) @@ -344,12 +347,6 @@ enum rwsem_wake_type { RWSEM_WAKE_READ_OWNED /* Waker thread holds the read lock */ }; -enum writer_wait_state { - WRITER_NOT_FIRST, /* Writer is not first in wait list */ - WRITER_FIRST, /* Writer is first in wait list */ - WRITER_HANDOFF /* Writer is first & handoff needed */ -}; - /* * The typical HZ value is either 250 or 1000. So set the minimum waiting * time to at least 4ms or 1 jiffy (if it is higher than 4ms) in the wait @@ -365,6 +362,31 @@ enum writer_wait_state { */ #define MAX_READERS_WAKEUP 0x100 +static inline void +rwsem_add_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter) +{ + lockdep_assert_held(&sem->wait_lock); + list_add_tail(&waiter->list, &sem->wait_list); + /* caller will set RWSEM_FLAG_WAITERS */ +} + +/* + * Remove a waiter from the wait_list and clear flags. + * + * Both rwsem_mark_wake() and rwsem_try_write_lock() contain a full 'copy' of + * this function. Modify with care. + */ +static inline void +rwsem_del_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter) +{ + lockdep_assert_held(&sem->wait_lock); + list_del(&waiter->list); + if (likely(!list_empty(&sem->wait_list))) + return; + + atomic_long_andnot(RWSEM_FLAG_HANDOFF | RWSEM_FLAG_WAITERS, &sem->count); +} + /* * handle the lock release when processes blocked on it that can now run * - if we come here from up_xxxx(), then the RWSEM_FLAG_WAITERS bit must @@ -376,6 +398,8 @@ enum writer_wait_state { * preferably when the wait_lock is released * - woken process blocks are discarded from the list after having task zeroed * - writers are only marked woken if downgrading is false + * + * Implies rwsem_del_waiter() for all woken readers. */ static void rwsem_mark_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type, @@ -490,18 +514,25 @@ static void rwsem_mark_wake(struct rw_semaphore *sem, adjustment = woken * RWSEM_READER_BIAS - adjustment; lockevent_cond_inc(rwsem_wake_reader, woken); + + oldcount = atomic_long_read(&sem->count); if (list_empty(&sem->wait_list)) { - /* hit end of list above */ + /* + * Combined with list_move_tail() above, this implies + * rwsem_del_waiter(). + */ adjustment -= RWSEM_FLAG_WAITERS; + if (oldcount & RWSEM_FLAG_HANDOFF) + adjustment -= RWSEM_FLAG_HANDOFF; + } else if (woken) { + /* + * When we've woken a reader, we no longer need to force + * writers to give up the lock and we can clear HANDOFF. + */ + if (oldcount & RWSEM_FLAG_HANDOFF) + adjustment -= RWSEM_FLAG_HANDOFF; } - /* - * When we've woken a reader, we no longer need to force writers - * to give up the lock and we can clear HANDOFF. - */ - if (woken && (atomic_long_read(&sem->count) & RWSEM_FLAG_HANDOFF)) - adjustment -= RWSEM_FLAG_HANDOFF; - if (adjustment) atomic_long_add(adjustment, &sem->count); @@ -532,12 +563,12 @@ static void rwsem_mark_wake(struct rw_semaphore *sem, * race conditions between checking the rwsem wait list and setting the * sem->count accordingly. * - * If wstate is WRITER_HANDOFF, it will make sure that either the handoff - * bit is set or the lock is acquired with handoff bit cleared. + * Implies rwsem_del_waiter() on success. */ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, - enum writer_wait_state wstate) + struct rwsem_waiter *waiter) { + bool first = rwsem_first_waiter(sem) == waiter; long count, new; lockdep_assert_held(&sem->wait_lock); @@ -546,13 +577,19 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, do { bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF); - if (has_handoff && wstate == WRITER_NOT_FIRST) - return false; + if (has_handoff) { + if (!first) + return false; + + /* First waiter inherits a previously set handoff bit */ + waiter->handoff_set = true; + } new = count; if (count & RWSEM_LOCK_MASK) { - if (has_handoff || (wstate != WRITER_HANDOFF)) + if (has_handoff || (!rt_task(waiter->task) && + !time_after(jiffies, waiter->timeout))) return false; new |= RWSEM_FLAG_HANDOFF; @@ -569,9 +606,17 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, * We have either acquired the lock with handoff bit cleared or * set the handoff bit. */ - if (new & RWSEM_FLAG_HANDOFF) + if (new & RWSEM_FLAG_HANDOFF) { + waiter->handoff_set = true; + lockevent_inc(rwsem_wlock_handoff); return false; + } + /* + * Have rwsem_try_write_lock() fully imply rwsem_del_waiter() on + * success. + */ + list_del(&waiter->list); rwsem_set_owner(sem); return true; } @@ -956,7 +1001,7 @@ queue: } adjustment += RWSEM_FLAG_WAITERS; } - list_add_tail(&waiter.list, &sem->wait_list); + rwsem_add_waiter(sem, &waiter); /* we're now waiting on the lock, but no longer actively locking */ count = atomic_long_add_return(adjustment, &sem->count); @@ -1002,11 +1047,7 @@ queue: return sem; out_nolock: - list_del(&waiter.list); - if (list_empty(&sem->wait_list)) { - atomic_long_andnot(RWSEM_FLAG_WAITERS|RWSEM_FLAG_HANDOFF, - &sem->count); - } + rwsem_del_waiter(sem, &waiter); raw_spin_unlock_irq(&sem->wait_lock); __set_current_state(TASK_RUNNING); lockevent_inc(rwsem_rlock_fail); @@ -1020,9 +1061,7 @@ static struct rw_semaphore * rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) { long count; - enum writer_wait_state wstate; struct rwsem_waiter waiter; - struct rw_semaphore *ret = sem; DEFINE_WAKE_Q(wake_q); /* do optimistic spinning and steal lock if possible */ @@ -1038,16 +1077,13 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) waiter.task = current; waiter.type = RWSEM_WAITING_FOR_WRITE; waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT; + waiter.handoff_set = false; raw_spin_lock_irq(&sem->wait_lock); - - /* account for this before adding a new element to the list */ - wstate = list_empty(&sem->wait_list) ? WRITER_FIRST : WRITER_NOT_FIRST; - - list_add_tail(&waiter.list, &sem->wait_list); + rwsem_add_waiter(sem, &waiter); /* we're now waiting on the lock */ - if (wstate == WRITER_NOT_FIRST) { + if (rwsem_first_waiter(sem) != &waiter) { count = atomic_long_read(&sem->count); /* @@ -1083,13 +1119,16 @@ wait: /* wait until we successfully acquire the lock */ set_current_state(state); for (;;) { - if (rwsem_try_write_lock(sem, wstate)) { + if (rwsem_try_write_lock(sem, &waiter)) { /* rwsem_try_write_lock() implies ACQUIRE on success */ break; } raw_spin_unlock_irq(&sem->wait_lock); + if (signal_pending_state(state, current)) + goto out_nolock; + /* * After setting the handoff bit and failing to acquire * the lock, attempt to spin on owner to accelerate lock @@ -1098,7 +1137,7 @@ wait: * In this case, we attempt to acquire the lock again * without sleeping. */ - if (wstate == WRITER_HANDOFF) { + if (waiter.handoff_set) { enum owner_state owner_state; preempt_disable(); @@ -1109,66 +1148,26 @@ wait: goto trylock_again; } - /* Block until there are no active lockers. */ - for (;;) { - if (signal_pending_state(state, current)) - goto out_nolock; - - schedule(); - lockevent_inc(rwsem_sleep_writer); - set_current_state(state); - /* - * If HANDOFF bit is set, unconditionally do - * a trylock. - */ - if (wstate == WRITER_HANDOFF) - break; - - if ((wstate == WRITER_NOT_FIRST) && - (rwsem_first_waiter(sem) == &waiter)) - wstate = WRITER_FIRST; - - count = atomic_long_read(&sem->count); - if (!(count & RWSEM_LOCK_MASK)) - break; - - /* - * The setting of the handoff bit is deferred - * until rwsem_try_write_lock() is called. - */ - if ((wstate == WRITER_FIRST) && (rt_task(current) || - time_after(jiffies, waiter.timeout))) { - wstate = WRITER_HANDOFF; - lockevent_inc(rwsem_wlock_handoff); - break; - } - } + schedule(); + lockevent_inc(rwsem_sleep_writer); + set_current_state(state); trylock_again: raw_spin_lock_irq(&sem->wait_lock); } __set_current_state(TASK_RUNNING); - list_del(&waiter.list); raw_spin_unlock_irq(&sem->wait_lock); lockevent_inc(rwsem_wlock); - - return ret; + return sem; out_nolock: __set_current_state(TASK_RUNNING); raw_spin_lock_irq(&sem->wait_lock); - list_del(&waiter.list); - - if (unlikely(wstate == WRITER_HANDOFF)) - atomic_long_add(-RWSEM_FLAG_HANDOFF, &sem->count); - - if (list_empty(&sem->wait_list)) - atomic_long_andnot(RWSEM_FLAG_WAITERS, &sem->count); - else + rwsem_del_waiter(sem, &waiter); + if (!list_empty(&sem->wait_list)) rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q); raw_spin_unlock_irq(&sem->wait_lock); wake_up_q(&wake_q); lockevent_inc(rwsem_wlock_fail); - return ERR_PTR(-EINTR); } @@ -1249,17 +1248,14 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem); - /* - * Optimize for the case when the rwsem is not locked at all. - */ - tmp = RWSEM_UNLOCKED_VALUE; - do { + tmp = atomic_long_read(&sem->count); + while (!(tmp & RWSEM_READ_FAILED_MASK)) { if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp, - tmp + RWSEM_READER_BIAS)) { + tmp + RWSEM_READER_BIAS)) { rwsem_set_reader_owned(sem); return 1; } - } while (!(tmp & RWSEM_READ_FAILED_MASK)); + } return 0; } diff --git a/kernel/notifier.c b/kernel/notifier.c index b8251dc0bc0f..ba005ebf4730 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -20,12 +20,13 @@ BLOCKING_NOTIFIER_HEAD(reboot_notifier_list); */ static int notifier_chain_register(struct notifier_block **nl, - struct notifier_block *n) + struct notifier_block *n) { while ((*nl) != NULL) { if (unlikely((*nl) == n)) { - WARN(1, "double register detected"); - return 0; + WARN(1, "notifier callback %ps already registered", + n->notifier_call); + return -EEXIST; } if (n->priority > (*nl)->priority) break; @@ -134,7 +135,7 @@ static int notifier_call_chain_robust(struct notifier_block **nl, * * Adds a notifier to an atomic notifier chain. * - * Currently always returns zero. + * Returns 0 on success, %-EEXIST on error. */ int atomic_notifier_chain_register(struct atomic_notifier_head *nh, struct notifier_block *n) @@ -216,7 +217,7 @@ NOKPROBE_SYMBOL(atomic_notifier_call_chain); * Adds a notifier to a blocking notifier chain. * Must be called in process context. * - * Currently always returns zero. + * Returns 0 on success, %-EEXIST on error. */ int blocking_notifier_chain_register(struct blocking_notifier_head *nh, struct notifier_block *n) @@ -335,7 +336,7 @@ EXPORT_SYMBOL_GPL(blocking_notifier_call_chain); * Adds a notifier to a raw notifier chain. * All locking must be provided by the caller. * - * Currently always returns zero. + * Returns 0 on success, %-EEXIST on error. */ int raw_notifier_chain_register(struct raw_notifier_head *nh, struct notifier_block *n) @@ -406,7 +407,7 @@ EXPORT_SYMBOL_GPL(raw_notifier_call_chain); * Adds a notifier to an SRCU notifier chain. * Must be called in process context. * - * Currently always returns zero. + * Returns 0 on success, %-EEXIST on error. */ int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *n) diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 9ed9b744876c..e6af502c2fd7 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -693,7 +693,7 @@ static int load_image_and_restore(void) goto Unlock; error = swsusp_read(&flags); - swsusp_close(FMODE_READ); + swsusp_close(FMODE_READ | FMODE_EXCL); if (!error) error = hibernation_restore(flags & SF_PLATFORM_MODE); @@ -983,7 +983,7 @@ static int software_resume(void) /* The snapshot device should not be opened while we're running */ if (!hibernate_acquire()) { error = -EBUSY; - swsusp_close(FMODE_READ); + swsusp_close(FMODE_READ | FMODE_EXCL); goto Unlock; } @@ -1018,7 +1018,7 @@ static int software_resume(void) pm_pr_dbg("Hibernation image not present or could not be loaded.\n"); return error; Close_Finish: - swsusp_close(FMODE_READ); + swsusp_close(FMODE_READ | FMODE_EXCL); goto Finish; } diff --git a/kernel/power/power.h b/kernel/power/power.h index 326f8d032eb5..b4f433943209 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -170,6 +170,7 @@ extern int swsusp_swap_in_use(void); #define SF_PLATFORM_MODE 1 #define SF_NOCOMPRESS_MODE 2 #define SF_CRC32_MODE 4 +#define SF_HW_SIG 8 /* kernel/power/hibernate.c */ extern int swsusp_check(void); diff --git a/kernel/power/swap.c b/kernel/power/swap.c index ff326c2cb77b..ad10359030a4 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -36,6 +36,8 @@ #define HIBERNATE_SIG "S1SUSPEND" +u32 swsusp_hardware_signature; + /* * When reading an {un,}compressed image, we may restore pages in place, * in which case some architectures need these pages cleaning before they @@ -104,7 +106,8 @@ struct swap_map_handle { struct swsusp_header { char reserved[PAGE_SIZE - 20 - sizeof(sector_t) - sizeof(int) - - sizeof(u32)]; + sizeof(u32) - sizeof(u32)]; + u32 hw_sig; u32 crc32; sector_t image; unsigned int flags; /* Flags to pass to the "boot" kernel */ @@ -312,7 +315,6 @@ static int hib_wait_io(struct hib_bio_batch *hb) /* * Saving part */ - static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags) { int error; @@ -324,6 +326,10 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags) memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10); memcpy(swsusp_header->sig, HIBERNATE_SIG, 10); swsusp_header->image = handle->first_sector; + if (swsusp_hardware_signature) { + swsusp_header->hw_sig = swsusp_hardware_signature; + flags |= SF_HW_SIG; + } swsusp_header->flags = flags; if (flags & SF_CRC32_MODE) swsusp_header->crc32 = handle->crc32; @@ -1537,6 +1543,12 @@ int swsusp_check(void) } else { error = -EINVAL; } + if (!error && swsusp_header->flags & SF_HW_SIG && + swsusp_header->hw_sig != swsusp_hardware_signature) { + pr_info("Suspend image hardware signature mismatch (%08x now %08x); aborting resume.\n", + swsusp_header->hw_sig, swsusp_hardware_signature); + error = -EINVAL; + } put: if (error) diff --git a/kernel/power/user.c b/kernel/power/user.c index 740723bb3885..ad241b4ff64c 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -177,7 +177,7 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf, if (res <= 0) goto unlock; } else { - res = PAGE_SIZE - pg_offp; + res = PAGE_SIZE; } if (!data_of(data->handle)) { diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 013bfd6dcc34..155229f0cf0f 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -280,7 +280,6 @@ static struct console *exclusive_console; static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES]; static int preferred_console = -1; -static bool has_preferred_console; int console_set_on_cmdline; EXPORT_SYMBOL(console_set_on_cmdline); @@ -2861,7 +2860,8 @@ early_param("keep_bootcon", keep_bootcon_setup); * Care need to be taken with consoles that are statically * enabled such as netconsole */ -static int try_enable_new_console(struct console *newcon, bool user_specified) +static int try_enable_preferred_console(struct console *newcon, + bool user_specified) { struct console_cmdline *c; int i, err; @@ -2891,10 +2891,8 @@ static int try_enable_new_console(struct console *newcon, bool user_specified) return err; } newcon->flags |= CON_ENABLED; - if (i == preferred_console) { + if (i == preferred_console) newcon->flags |= CON_CONSDEV; - has_preferred_console = true; - } return 0; } @@ -2909,6 +2907,21 @@ static int try_enable_new_console(struct console *newcon, bool user_specified) return -ENOENT; } +/* Try to enable the console unconditionally */ +static void try_enable_default_console(struct console *newcon) +{ + if (newcon->index < 0) + newcon->index = 0; + + if (newcon->setup && newcon->setup(newcon, NULL) != 0) + return; + + newcon->flags |= CON_ENABLED; + + if (newcon->device) + newcon->flags |= CON_CONSDEV; +} + /* * The console driver calls this routine during kernel initialization * to register the console printing procedure with printk() and to @@ -2930,59 +2943,56 @@ static int try_enable_new_console(struct console *newcon, bool user_specified) */ void register_console(struct console *newcon) { - struct console *bcon = NULL; + struct console *con; + bool bootcon_enabled = false; + bool realcon_enabled = false; int err; - for_each_console(bcon) { - if (WARN(bcon == newcon, "console '%s%d' already registered\n", - bcon->name, bcon->index)) + for_each_console(con) { + if (WARN(con == newcon, "console '%s%d' already registered\n", + con->name, con->index)) return; } - /* - * before we register a new CON_BOOT console, make sure we don't - * already have a valid console - */ - if (newcon->flags & CON_BOOT) { - for_each_console(bcon) { - if (!(bcon->flags & CON_BOOT)) { - pr_info("Too late to register bootconsole %s%d\n", - newcon->name, newcon->index); - return; - } - } + for_each_console(con) { + if (con->flags & CON_BOOT) + bootcon_enabled = true; + else + realcon_enabled = true; } - if (console_drivers && console_drivers->flags & CON_BOOT) - bcon = console_drivers; - - if (!has_preferred_console || bcon || !console_drivers) - has_preferred_console = preferred_console >= 0; + /* Do not register boot consoles when there already is a real one. */ + if (newcon->flags & CON_BOOT && realcon_enabled) { + pr_info("Too late to register bootconsole %s%d\n", + newcon->name, newcon->index); + return; + } /* - * See if we want to use this console driver. If we - * didn't select a console we take the first one - * that registers here. + * See if we want to enable this console driver by default. + * + * Nope when a console is preferred by the command line, device + * tree, or SPCR. + * + * The first real console with tty binding (driver) wins. More + * consoles might get enabled before the right one is found. + * + * Note that a console with tty binding will have CON_CONSDEV + * flag set and will be first in the list. */ - if (!has_preferred_console) { - if (newcon->index < 0) - newcon->index = 0; - if (newcon->setup == NULL || - newcon->setup(newcon, NULL) == 0) { - newcon->flags |= CON_ENABLED; - if (newcon->device) { - newcon->flags |= CON_CONSDEV; - has_preferred_console = true; - } + if (preferred_console < 0) { + if (!console_drivers || !console_drivers->device || + console_drivers->flags & CON_BOOT) { + try_enable_default_console(newcon); } } /* See if this console matches one we selected on the command line */ - err = try_enable_new_console(newcon, true); + err = try_enable_preferred_console(newcon, true); /* If not, try to match against the platform default(s) */ if (err == -ENOENT) - err = try_enable_new_console(newcon, false); + err = try_enable_preferred_console(newcon, false); /* printk() messages are not printed to the Braille console. */ if (err || newcon->flags & CON_BRL) @@ -2994,8 +3004,10 @@ void register_console(struct console *newcon) * the real console are the same physical device, it's annoying to * see the beginning boot messages twice */ - if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) + if (bootcon_enabled && + ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) { newcon->flags &= ~CON_PRINTBUFFER; + } /* * Put this console in the list - keep the @@ -3051,15 +3063,15 @@ void register_console(struct console *newcon) pr_info("%sconsole [%s%d] enabled\n", (newcon->flags & CON_BOOT) ? "boot" : "" , newcon->name, newcon->index); - if (bcon && + if (bootcon_enabled && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) && !keep_bootcon) { /* We need to iterate through all boot consoles, to make * sure we print everything out, before we unregister them. */ - for_each_console(bcon) - if (bcon->flags & CON_BOOT) - unregister_console(bcon); + for_each_console(con) + if (con->flags & CON_BOOT) + unregister_console(con); } } EXPORT_SYMBOL(register_console); @@ -3253,6 +3265,11 @@ void defer_console_output(void) preempt_enable(); } +void printk_trigger_flush(void) +{ + defer_console_output(); +} + int vprintk_deferred(const char *fmt, va_list args) { int r; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3c9b0fda64ac..bb5e7fd25354 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1918,7 +1918,7 @@ static void __init init_uclamp_rq(struct rq *rq) }; } - rq->uclamp_flags = 0; + rq->uclamp_flags = UCLAMP_FLAG_IDLE; } static void __init init_uclamp(void) @@ -6617,11 +6617,11 @@ static int __init setup_preempt_mode(char *str) int mode = sched_dynamic_mode(str); if (mode < 0) { pr_warn("Dynamic Preempt: unsupported mode: %s\n", str); - return 1; + return 0; } sched_dynamic_update(mode); - return 0; + return 1; } __setup("preempt=", setup_preempt_mode); @@ -8520,7 +8520,7 @@ void sched_show_task(struct task_struct *p) rcu_read_unlock(); pr_cont(" stack:%5lu pid:%5d ppid:%6d flags:0x%08lx\n", free, task_pid_nr(p), ppid, - (unsigned long)task_thread_info(p)->flags); + read_task_thread_flags(p)); print_worker_info(KERN_INFO, p); print_stop_info(KERN_INFO, p); @@ -8619,9 +8619,6 @@ void __init init_idle(struct task_struct *idle, int cpu) idle->flags |= PF_IDLE | PF_KTHREAD | PF_NO_SETAFFINITY; kthread_set_per_cpu(idle, cpu); - scs_task_reset(idle); - kasan_unpoison_task_stack(idle); - #ifdef CONFIG_SMP /* * It's possible that init_idle() gets called multiple times on a task, @@ -8777,7 +8774,6 @@ void idle_task_exit(void) finish_arch_post_lock_switch(); } - scs_task_reset(current); /* finish_cpu(), as ran on the BP, will clean up the active_mm state */ } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 872e481d5098..9392aea1804e 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -615,7 +615,8 @@ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) .sum_exec_runtime = p->se.sum_exec_runtime, }; - task_cputime(p, &cputime.utime, &cputime.stime); + if (task_cputime(p, &cputime.utime, &cputime.stime)) + cputime.sum_exec_runtime = task_sched_runtime(p); cputime_adjust(&cputime, &p->prev_cputime, ut, st); } EXPORT_SYMBOL_GPL(task_cputime_adjusted); @@ -828,19 +829,21 @@ u64 task_gtime(struct task_struct *t) * add up the pending nohz execution time since the last * cputime snapshot. */ -void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) +bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime) { struct vtime *vtime = &t->vtime; unsigned int seq; u64 delta; + int ret; if (!vtime_accounting_enabled()) { *utime = t->utime; *stime = t->stime; - return; + return false; } do { + ret = false; seq = read_seqcount_begin(&vtime->seqcount); *utime = t->utime; @@ -850,6 +853,7 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) if (vtime->state < VTIME_SYS) continue; + ret = true; delta = vtime_delta(vtime); /* @@ -861,6 +865,8 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) else *utime += vtime->utime + delta; } while (read_seqcount_retry(&vtime->seqcount, seq)); + + return ret; } static int vtime_state_fetch(struct vtime *vtime, int cpu) diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 76577d1642a5..eca38107b32f 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -238,6 +238,13 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode) } EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ +void __wake_up_pollfree(struct wait_queue_head *wq_head) +{ + __wake_up(wq_head, TASK_NORMAL, 0, poll_to_key(EPOLLHUP | POLLFREE)); + /* POLLFREE must have cleared the queue. */ + WARN_ON_ONCE(waitqueue_active(wq_head)); +} + /* * Note: we use "set_current_state()" _after_ the wait-queue add, * because we need a memory barrier there on SMP, so that any diff --git a/kernel/signal.c b/kernel/signal.c index 7c4b7ae714d4..dfcee3888b00 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1298,6 +1298,12 @@ int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p return ret; } +enum sig_handler { + HANDLER_CURRENT, /* If reachable use the current handler */ + HANDLER_SIG_DFL, /* Always use SIG_DFL handler semantics */ + HANDLER_EXIT, /* Only visible as the process exit code */ +}; + /* * Force a signal that the process can't ignore: if necessary * we unblock the signal and change any SIG_IGN to SIG_DFL. @@ -1310,7 +1316,8 @@ int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p * that is why we also clear SIGNAL_UNKILLABLE. */ static int -force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool sigdfl) +force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, + enum sig_handler handler) { unsigned long int flags; int ret, blocked, ignored; @@ -1321,9 +1328,10 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool action = &t->sighand->action[sig-1]; ignored = action->sa.sa_handler == SIG_IGN; blocked = sigismember(&t->blocked, sig); - if (blocked || ignored || sigdfl) { + if (blocked || ignored || (handler != HANDLER_CURRENT)) { action->sa.sa_handler = SIG_DFL; - action->sa.sa_flags |= SA_IMMUTABLE; + if (handler == HANDLER_EXIT) + action->sa.sa_flags |= SA_IMMUTABLE; if (blocked) { sigdelset(&t->blocked, sig); recalc_sigpending_and_wake(t); @@ -1343,7 +1351,7 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool int force_sig_info(struct kernel_siginfo *info) { - return force_sig_info_to_task(info, current, false); + return force_sig_info_to_task(info, current, HANDLER_CURRENT); } /* @@ -1660,7 +1668,20 @@ void force_fatal_sig(int sig) info.si_code = SI_KERNEL; info.si_pid = 0; info.si_uid = 0; - force_sig_info_to_task(&info, current, true); + force_sig_info_to_task(&info, current, HANDLER_SIG_DFL); +} + +void force_exit_sig(int sig) +{ + struct kernel_siginfo info; + + clear_siginfo(&info); + info.si_signo = sig; + info.si_errno = 0; + info.si_code = SI_KERNEL; + info.si_pid = 0; + info.si_uid = 0; + force_sig_info_to_task(&info, current, HANDLER_EXIT); } /* @@ -1693,7 +1714,7 @@ int force_sig_fault_to_task(int sig, int code, void __user *addr info.si_flags = flags; info.si_isr = isr; #endif - return force_sig_info_to_task(&info, t, false); + return force_sig_info_to_task(&info, t, HANDLER_CURRENT); } int force_sig_fault(int sig, int code, void __user *addr @@ -1813,7 +1834,8 @@ int force_sig_seccomp(int syscall, int reason, bool force_coredump) info.si_errno = reason; info.si_arch = syscall_get_arch(current); info.si_syscall = syscall; - return force_sig_info_to_task(&info, current, force_coredump); + return force_sig_info_to_task(&info, current, + force_coredump ? HANDLER_EXIT : HANDLER_CURRENT); } /* For the crazy architectures that include trap information in @@ -4163,6 +4185,15 @@ do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp, ss_mode != 0)) return -EINVAL; + /* + * Return before taking any locks if no actual + * sigaltstack changes were requested. + */ + if (t->sas_ss_sp == (unsigned long)ss_sp && + t->sas_ss_size == ss_size && + t->sas_ss_flags == ss_flags) + return 0; + sigaltstack_lock(); if (ss_mode == SS_DISABLE) { ss_size = 0; diff --git a/kernel/softirq.c b/kernel/softirq.c index 322b65d45676..41f470929e99 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -595,7 +595,8 @@ void irq_enter_rcu(void) { __irq_enter_raw(); - if (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET)) + if (tick_nohz_full_cpu(smp_processor_id()) || + (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET))) tick_irq_enter(); account_hardirq_enter(current); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 083be6af29d7..d7ed1dffa426 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -33,6 +33,7 @@ #include <linux/security.h> #include <linux/ctype.h> #include <linux/kmemleak.h> +#include <linux/filter.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 6bffe5af8cb1..17a283ce2b20 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -1375,6 +1375,13 @@ static inline void tick_nohz_irq_enter(void) now = ktime_get(); if (ts->idle_active) tick_nohz_stop_idle(ts, now); + /* + * If all CPUs are idle. We may need to update a stale jiffies value. + * Note nohz_full is a special case: a timekeeper is guaranteed to stay + * alive but it might be busy looping with interrupts disabled in some + * rare case (typically stop machine). So we must make sure we have a + * last resort. + */ if (ts->tick_stopped) tick_nohz_update_jiffies(now); } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index b348749a9fc6..dcdcb85121e4 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1306,8 +1306,7 @@ int do_settimeofday64(const struct timespec64 *ts) timekeeping_forward_now(tk); xt = tk_xtime(tk); - ts_delta.tv_sec = ts->tv_sec - xt.tv_sec; - ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec; + ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { ret = -EINVAL; diff --git a/kernel/time/timer.c b/kernel/time/timer.c index e3d2c23c413d..85f1021ad459 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -2054,26 +2054,28 @@ unsigned long msleep_interruptible(unsigned int msecs) EXPORT_SYMBOL(msleep_interruptible); /** - * usleep_range - Sleep for an approximate time - * @min: Minimum time in usecs to sleep - * @max: Maximum time in usecs to sleep + * usleep_range_state - Sleep for an approximate time in a given state + * @min: Minimum time in usecs to sleep + * @max: Maximum time in usecs to sleep + * @state: State of the current task that will be while sleeping * * In non-atomic context where the exact wakeup time is flexible, use - * usleep_range() instead of udelay(). The sleep improves responsiveness + * usleep_range_state() instead of udelay(). The sleep improves responsiveness * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces * power usage by allowing hrtimers to take advantage of an already- * scheduled interrupt instead of scheduling a new one just for this sleep. */ -void __sched usleep_range(unsigned long min, unsigned long max) +void __sched usleep_range_state(unsigned long min, unsigned long max, + unsigned int state) { ktime_t exp = ktime_add_us(ktime_get(), min); u64 delta = (u64)(max - min) * NSEC_PER_USEC; for (;;) { - __set_current_state(TASK_UNINTERRUPTIBLE); + __set_current_state(state); /* Do not return before the requested sleep time has elapsed */ if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS)) break; } } -EXPORT_SYMBOL(usleep_range); +EXPORT_SYMBOL(usleep_range_state); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7396488793ff..21aa30644219 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -345,7 +345,7 @@ static const struct bpf_func_proto bpf_probe_write_user_proto = { .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; @@ -394,7 +394,7 @@ static const struct bpf_func_proto bpf_trace_printk_proto = { .func = bpf_trace_printk, .gpl_only = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, }; @@ -450,9 +450,9 @@ static const struct bpf_func_proto bpf_trace_vprintk_proto = { .func = bpf_trace_vprintk, .gpl_only = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, - .arg3_type = ARG_PTR_TO_MEM_OR_NULL, + .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -492,9 +492,9 @@ static const struct bpf_func_proto bpf_seq_printf_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, - .arg4_type = ARG_PTR_TO_MEM_OR_NULL, + .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -509,7 +509,7 @@ static const struct bpf_func_proto bpf_seq_write_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -533,7 +533,7 @@ static const struct bpf_func_proto bpf_seq_printf_btf_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; @@ -694,7 +694,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -764,7 +764,7 @@ const struct bpf_func_proto bpf_get_current_task_btf_proto = { .func = bpf_get_current_task_btf, .gpl_only = true, .ret_type = RET_PTR_TO_BTF_ID, - .ret_btf_id = &btf_task_struct_ids[0], + .ret_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; BPF_CALL_1(bpf_task_pt_regs, struct task_struct *, task) @@ -779,7 +779,7 @@ const struct bpf_func_proto bpf_task_pt_regs_proto = { .func = bpf_task_pt_regs, .gpl_only = true, .arg1_type = ARG_PTR_TO_BTF_ID, - .arg1_btf_id = &btf_task_struct_ids[0], + .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .ret_type = RET_PTR_TO_BTF_ID, .ret_btf_id = &bpf_task_pt_regs_ids[0], }; @@ -1004,7 +1004,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE, - .arg3_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; @@ -1012,7 +1012,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = { BPF_CALL_1(bpf_get_func_ip_tracing, void *, ctx) { /* This helper call is inlined by verifier. */ - return ((u64 *)ctx)[-1]; + return ((u64 *)ctx)[-2]; } static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = { @@ -1091,6 +1091,53 @@ static const struct bpf_func_proto bpf_get_branch_snapshot_proto = { .arg2_type = ARG_CONST_SIZE_OR_ZERO, }; +BPF_CALL_3(get_func_arg, void *, ctx, u32, n, u64 *, value) +{ + /* This helper call is inlined by verifier. */ + u64 nr_args = ((u64 *)ctx)[-1]; + + if ((u64) n >= nr_args) + return -EINVAL; + *value = ((u64 *)ctx)[n]; + return 0; +} + +static const struct bpf_func_proto bpf_get_func_arg_proto = { + .func = get_func_arg, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_LONG, +}; + +BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value) +{ + /* This helper call is inlined by verifier. */ + u64 nr_args = ((u64 *)ctx)[-1]; + + *value = ((u64 *)ctx)[nr_args]; + return 0; +} + +static const struct bpf_func_proto bpf_get_func_ret_proto = { + .func = get_func_ret, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_LONG, +}; + +BPF_CALL_1(get_func_arg_cnt, void *, ctx) +{ + /* This helper call is inlined by verifier. */ + return ((u64 *)ctx)[-1]; +} + +static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = { + .func = get_func_arg_cnt, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + static const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1111,8 +1158,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; - case BPF_FUNC_ktime_get_coarse_ns: - return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: @@ -1208,6 +1253,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_func_ip_proto_tracing; case BPF_FUNC_get_branch_snapshot: return &bpf_get_branch_snapshot_proto; + case BPF_FUNC_find_vma: + return &bpf_find_vma_proto; case BPF_FUNC_trace_vprintk: return bpf_get_trace_vprintk_proto(); default: @@ -1287,7 +1334,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_tp = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -1402,9 +1449,6 @@ static const struct bpf_func_proto bpf_perf_prog_read_value_proto = { BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx, void *, buf, u32, size, u64, flags) { -#ifndef CONFIG_X86 - return -ENOENT; -#else static const u32 br_entry_size = sizeof(struct perf_branch_entry); struct perf_branch_stack *br_stack = ctx->data->br_stack; u32 to_copy; @@ -1413,7 +1457,7 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx, return -EINVAL; if (unlikely(!br_stack)) - return -EINVAL; + return -ENOENT; if (flags & BPF_F_GET_BRANCH_RECORDS_SIZE) return br_stack->nr * br_entry_size; @@ -1425,7 +1469,6 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx, memcpy(buf, br_stack->entries, to_copy); return to_copy; -#endif } static const struct bpf_func_proto bpf_read_branch_records_proto = { @@ -1513,7 +1556,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -1567,7 +1610,7 @@ static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = { .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; @@ -1633,6 +1676,12 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) NULL; case BPF_FUNC_d_path: return &bpf_d_path_proto; + case BPF_FUNC_get_func_arg: + return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_proto : NULL; + case BPF_FUNC_get_func_ret: + return bpf_prog_has_trampoline(prog) ? &bpf_get_func_ret_proto : NULL; + case BPF_FUNC_get_func_arg_cnt: + return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_cnt_proto : NULL; default: fn = raw_tp_prog_func_proto(func_id, prog); if (!fn && prog->expected_attach_type == BPF_TRACE_ITER) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 30bc880c3849..be5f6b32a012 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5217,6 +5217,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr) { struct ftrace_direct_func *direct; struct ftrace_func_entry *entry; + struct ftrace_hash *hash; int ret = -ENODEV; mutex_lock(&direct_mutex); @@ -5225,7 +5226,8 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr) if (!entry) goto out_unlock; - if (direct_functions->count == 1) + hash = direct_ops.func_hash->filter_hash; + if (hash->count == 1) unregister_ftrace_function(&direct_ops); ret = ftrace_set_filter_ip(&direct_ops, ip, 1, 0); @@ -5540,6 +5542,10 @@ int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) err = unregister_ftrace_function(ops); remove_direct_functions_hash(hash, addr); mutex_unlock(&direct_mutex); + + /* cleanup for possible another register call */ + ops->func = NULL; + ops->trampoline = 0; return err; } EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f9139dc1262c..78ea542ce3bc 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3207,7 +3207,7 @@ struct trace_buffer_struct { char buffer[4][TRACE_BUF_SIZE]; }; -static struct trace_buffer_struct *trace_percpu_buffer; +static struct trace_buffer_struct __percpu *trace_percpu_buffer; /* * This allows for lockless recording. If we're nested too deeply, then @@ -3217,7 +3217,7 @@ static char *get_trace_buf(void) { struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer); - if (!buffer || buffer->nesting >= 4) + if (!trace_percpu_buffer || buffer->nesting >= 4) return NULL; buffer->nesting++; @@ -3236,7 +3236,7 @@ static void put_trace_buf(void) static int alloc_percpu_trace_buffer(void) { - struct trace_buffer_struct *buffers; + struct trace_buffer_struct __percpu *buffers; if (trace_percpu_buffer) return 0; @@ -3812,6 +3812,18 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, iter->fmt[i] = '\0'; trace_seq_vprintf(&iter->seq, iter->fmt, ap); + /* + * If iter->seq is full, the above call no longer guarantees + * that ap is in sync with fmt processing, and further calls + * to va_arg() can return wrong positional arguments. + * + * Ensure that ap is no longer used in this case. + */ + if (iter->seq.full) { + p = ""; + break; + } + if (star) len = va_arg(ap, int); @@ -6706,9 +6718,7 @@ waitagain: cnt = PAGE_SIZE - 1; /* reset all but tr, trace, and overruns */ - memset(&iter->seq, 0, - sizeof(struct trace_iterator) - - offsetof(struct trace_iterator, seq)); + memset_startat(iter, 0, seq); cpumask_clear(iter->started); trace_seq_init(&iter->seq); iter->pos = -1; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 6b60ab9475ed..38715aa6cfdf 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1366,14 +1366,26 @@ __event_trigger_test_discard(struct trace_event_file *file, if (eflags & EVENT_FILE_FL_TRIGGER_COND) *tt = event_triggers_call(file, buffer, entry, event); - if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) || - (unlikely(file->flags & EVENT_FILE_FL_FILTERED) && - !filter_match_preds(file->filter, entry))) { - __trace_event_discard_commit(buffer, event); - return true; - } + if (likely(!(file->flags & (EVENT_FILE_FL_SOFT_DISABLED | + EVENT_FILE_FL_FILTERED | + EVENT_FILE_FL_PID_FILTER)))) + return false; + + if (file->flags & EVENT_FILE_FL_SOFT_DISABLED) + goto discard; + + if (file->flags & EVENT_FILE_FL_FILTERED && + !filter_match_preds(file->filter, entry)) + goto discard; + + if ((file->flags & EVENT_FILE_FL_PID_FILTER) && + trace_event_ignore_this_pid(file)) + goto discard; return false; + discard: + __trace_event_discard_commit(buffer, event); + return true; } /** diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 4021b9a79f93..92be9cb1d7d4 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2678,12 +2678,24 @@ static struct trace_event_file * trace_create_new_event(struct trace_event_call *call, struct trace_array *tr) { + struct trace_pid_list *no_pid_list; + struct trace_pid_list *pid_list; struct trace_event_file *file; + unsigned int first; file = kmem_cache_alloc(file_cachep, GFP_TRACE); if (!file) return NULL; + pid_list = rcu_dereference_protected(tr->filtered_pids, + lockdep_is_held(&event_mutex)); + no_pid_list = rcu_dereference_protected(tr->filtered_no_pids, + lockdep_is_held(&event_mutex)); + + if (!trace_pid_list_first(pid_list, &first) || + !trace_pid_list_first(no_pid_list, &first)) + file->flags |= EVENT_FILE_FL_PID_FILTER; + file->event_call = call; file->tr = tr; atomic_set(&file->sm_ref, 0); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 8a10046c775f..319f9c8ca7e7 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2576,28 +2576,27 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, /* Split the expression string at the root operator */ if (!sep) - goto free; + return ERR_PTR(-EINVAL); + *sep = '\0'; operand1_str = str; str = sep+1; /* Binary operator requires both operands */ if (*operand1_str == '\0' || *str == '\0') - goto free; + return ERR_PTR(-EINVAL); operand_flags = 0; /* LHS of string is an expression e.g. a+b in a+b+c */ operand1 = parse_expr(hist_data, file, operand1_str, operand_flags, NULL, n_subexprs); - if (IS_ERR(operand1)) { - ret = PTR_ERR(operand1); - operand1 = NULL; - goto free; - } + if (IS_ERR(operand1)) + return ERR_CAST(operand1); + if (operand1->flags & HIST_FIELD_FL_STRING) { hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(operand1_str)); ret = -EINVAL; - goto free; + goto free_op1; } /* RHS of string is another expression e.g. c in a+b+c */ @@ -2605,13 +2604,12 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, operand2 = parse_expr(hist_data, file, str, operand_flags, NULL, n_subexprs); if (IS_ERR(operand2)) { ret = PTR_ERR(operand2); - operand2 = NULL; - goto free; + goto free_op1; } if (operand2->flags & HIST_FIELD_FL_STRING) { hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str)); ret = -EINVAL; - goto free; + goto free_operands; } switch (field_op) { @@ -2629,12 +2627,12 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, break; default: ret = -EINVAL; - goto free; + goto free_operands; } ret = check_expr_operands(file->tr, operand1, operand2, &var1, &var2); if (ret) - goto free; + goto free_operands; operand_flags = var1 ? var1->flags : operand1->flags; operand2_flags = var2 ? var2->flags : operand2->flags; @@ -2653,12 +2651,13 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, expr = create_hist_field(hist_data, NULL, flags, var_name); if (!expr) { ret = -ENOMEM; - goto free; + goto free_operands; } operand1->read_once = true; operand2->read_once = true; + /* The operands are now owned and free'd by 'expr' */ expr->operands[0] = operand1; expr->operands[1] = operand2; @@ -2669,7 +2668,7 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, if (!divisor) { hist_err(file->tr, HIST_ERR_DIVISION_BY_ZERO, errpos(str)); ret = -EDOM; - goto free; + goto free_expr; } /* @@ -2709,18 +2708,22 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, expr->type = kstrdup_const(operand1->type, GFP_KERNEL); if (!expr->type) { ret = -ENOMEM; - goto free; + goto free_expr; } expr->name = expr_str(expr, 0); } return expr; -free: - destroy_hist_field(operand1, 0); + +free_operands: destroy_hist_field(operand2, 0); - destroy_hist_field(expr, 0); +free_op1: + destroy_hist_field(operand1, 0); + return ERR_PTR(ret); +free_expr: + destroy_hist_field(expr, 0); return ERR_PTR(ret); } @@ -3026,8 +3029,10 @@ static inline void __update_field_vars(struct tracing_map_elt *elt, if (val->flags & HIST_FIELD_FL_STRING) { char *str = elt_data->field_var_str[j++]; char *val_str = (char *)(uintptr_t)var_val; + unsigned int size; - strscpy(str, val_str, val->size); + size = min(val->size, STR_VAR_LEN_MAX); + strscpy(str, val_str, size); var_val = (u64)(uintptr_t)str; } tracing_map_set_var(elt, var_idx, var_val); @@ -3752,7 +3757,7 @@ static int check_synth_field(struct synth_event *event, if (strcmp(field->type, hist_field->type) != 0) { if (field->size != hist_field->size || - field->is_signed != hist_field->is_signed) + (!field->is_string && field->is_signed != hist_field->is_signed)) return -EINVAL; } @@ -4914,6 +4919,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, if (hist_field->flags & HIST_FIELD_FL_STRING) { unsigned int str_start, var_str_idx, idx; char *str, *val_str; + unsigned int size; str_start = hist_data->n_field_var_str + hist_data->n_save_var_str; @@ -4922,7 +4928,9 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, str = elt_data->field_var_str[idx]; val_str = (char *)(uintptr_t)hist_val; - strscpy(str, val_str, hist_field->size); + + size = min(hist_field->size, STR_VAR_LEN_MAX); + strscpy(str, val_str, size); hist_val = (u64)(uintptr_t)str; } diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 22db3ce95e74..ca9c13b2ecf4 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -1237,9 +1237,8 @@ static int __create_synth_event(const char *name, const char *raw_fields) argv + consumed, &consumed, &field_version); if (IS_ERR(field)) { - argv_free(argv); ret = PTR_ERR(field); - goto err; + goto err_free_arg; } /* @@ -1262,18 +1261,19 @@ static int __create_synth_event(const char *name, const char *raw_fields) if (cmd_version > 1 && n_fields_this_loop >= 1) { synth_err(SYNTH_ERR_INVALID_CMD, errpos(field_str)); ret = -EINVAL; - goto err; + goto err_free_arg; } fields[n_fields++] = field; if (n_fields == SYNTH_FIELDS_MAX) { synth_err(SYNTH_ERR_TOO_MANY_FIELDS, 0); ret = -EINVAL; - goto err; + goto err_free_arg; } n_fields_this_loop++; } + argv_free(argv); if (consumed < argc) { synth_err(SYNTH_ERR_INVALID_CMD, 0); @@ -1281,7 +1281,6 @@ static int __create_synth_event(const char *name, const char *raw_fields) goto err; } - argv_free(argv); } if (n_fields == 0) { @@ -1307,6 +1306,8 @@ static int __create_synth_event(const char *name, const char *raw_fields) kfree(saved_fields); return ret; + err_free_arg: + argv_free(argv); err: for (i = 0; i < n_fields; i++) free_synth_field(fields[i]); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 33272a7b6912..4e1257f50aa3 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -7,6 +7,7 @@ */ #define pr_fmt(fmt) "trace_kprobe: " fmt +#include <linux/bpf-cgroup.h> #include <linux/security.h> #include <linux/module.h> #include <linux/uaccess.h> diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 0a5c0db3137e..4f35514a48f3 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -7,6 +7,7 @@ */ #define pr_fmt(fmt) "trace_uprobe: " fmt +#include <linux/bpf-cgroup.h> #include <linux/security.h> #include <linux/ctype.h> #include <linux/module.h> @@ -1313,6 +1314,7 @@ static int uprobe_perf_open(struct trace_event_call *call, return 0; list_for_each_entry(pos, trace_probe_probe_list(tp), list) { + tu = container_of(pos, struct trace_uprobe, tp); err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); if (err) { uprobe_perf_close(call, event); diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 39bb56d2dcbe..9628b5571846 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -15,6 +15,7 @@ #include <linux/jhash.h> #include <linux/slab.h> #include <linux/sort.h> +#include <linux/kmemleak.h> #include "tracing_map.h" #include "trace.h" @@ -307,6 +308,7 @@ static void tracing_map_array_free(struct tracing_map_array *a) for (i = 0; i < a->n_pages; i++) { if (!a->pages[i]) break; + kmemleak_free(a->pages[i]); free_page((unsigned long)a->pages[i]); } @@ -342,6 +344,7 @@ static struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts, a->pages[i] = (void *)get_zeroed_page(GFP_KERNEL); if (!a->pages[i]) goto free; + kmemleak_alloc(a->pages[i], PAGE_SIZE, 1, GFP_KERNEL); } out: return a; diff --git a/kernel/ucount.c b/kernel/ucount.c index 4f5613dac227..7b32c356ebc5 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -264,15 +264,16 @@ void dec_ucount(struct ucounts *ucounts, enum ucount_type type) long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v) { struct ucounts *iter; + long max = LONG_MAX; long ret = 0; for (iter = ucounts; iter; iter = iter->ns->ucounts) { - long max = READ_ONCE(iter->ns->ucount_max[type]); long new = atomic_long_add_return(v, &iter->ucount[type]); if (new < 0 || new > max) ret = LONG_MAX; else if (iter == ucounts) ret = new; + max = READ_ONCE(iter->ns->ucount_max[type]); } return ret; } @@ -312,15 +313,16 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type) { /* Caller must hold a reference to ucounts */ struct ucounts *iter; + long max = LONG_MAX; long dec, ret = 0; for (iter = ucounts; iter; iter = iter->ns->ucounts) { - long max = READ_ONCE(iter->ns->ucount_max[type]); long new = atomic_long_add_return(1, &iter->ucount[type]); if (new < 0 || new > max) goto unwind; if (iter == ucounts) ret = new; + max = READ_ONCE(iter->ns->ucount_max[type]); /* * Grab an extra ucount reference for the caller when * the rlimit count was previously 0. @@ -339,15 +341,16 @@ unwind: return 0; } -bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max) +bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long rlimit) { struct ucounts *iter; - if (get_ucounts_value(ucounts, type) > max) - return true; + long max = rlimit; + if (rlimit > LONG_MAX) + max = LONG_MAX; for (iter = ucounts; iter; iter = iter->ns->ucounts) { - max = READ_ONCE(iter->ns->ucount_max[type]); if (get_ucounts_value(iter, type) > max) return true; + max = READ_ONCE(iter->ns->ucount_max[type]); } return false; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 613917bbc4e7..33f1106b4f99 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -154,6 +154,9 @@ struct worker_pool { unsigned long watchdog_ts; /* L: watchdog timestamp */ + /* The current concurrency level. */ + atomic_t nr_running; + struct list_head worklist; /* L: list of pending works */ int nr_workers; /* L: total number of workers */ @@ -178,18 +181,11 @@ struct worker_pool { int refcnt; /* PL: refcnt for unbound pools */ /* - * The current concurrency level. As it's likely to be accessed - * from other CPUs during try_to_wake_up(), put it in a separate - * cacheline. - */ - atomic_t nr_running ____cacheline_aligned_in_smp; - - /* * Destruction of pool is RCU protected to allow dereferences * from get_work_pool(). */ struct rcu_head rcu; -} ____cacheline_aligned_in_smp; +}; /* * The per-pool workqueue. While queued, the lower WORK_STRUCT_FLAG_BITS @@ -868,8 +864,17 @@ void wq_worker_running(struct task_struct *task) if (!worker->sleeping) return; + + /* + * If preempted by unbind_workers() between the WORKER_NOT_RUNNING check + * and the nr_running increment below, we may ruin the nr_running reset + * and leave with an unexpected pool->nr_running == 1 on the newly unbound + * pool. Protect against such race. + */ + preempt_disable(); if (!(worker->flags & WORKER_NOT_RUNNING)) atomic_inc(&worker->pool->nr_running); + preempt_enable(); worker->sleeping = 0; } @@ -878,8 +883,7 @@ void wq_worker_running(struct task_struct *task) * @task: task going to sleep * * This function is called from schedule() when a busy worker is - * going to sleep. Preemption needs to be disabled to protect ->sleeping - * assignment. + * going to sleep. */ void wq_worker_sleeping(struct task_struct *task) { @@ -904,6 +908,16 @@ void wq_worker_sleeping(struct task_struct *task) raw_spin_lock_irq(&pool->lock); /* + * Recheck in case unbind_workers() preempted us. We don't + * want to decrement nr_running after the worker is unbound + * and nr_running has been reset. + */ + if (worker->flags & WORKER_NOT_RUNNING) { + raw_spin_unlock_irq(&pool->lock); + return; + } + + /* * The counterpart of the following dec_and_test, implied mb, * worklist not empty test sequence is in insert_work(). * Please read comment there. @@ -1531,7 +1545,8 @@ out: * @work: work to queue * * We queue the work to a specific CPU, the caller must ensure it - * can't go away. + * can't go away. Callers that fail to ensure that the specified + * CPU cannot go away will execute on a randomly chosen CPU. * * Return: %false if @work was already on a queue, %true otherwise. */ @@ -1811,14 +1826,8 @@ static void worker_enter_idle(struct worker *worker) if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); - /* - * Sanity check nr_running. Because unbind_workers() releases - * pool->lock between setting %WORKER_UNBOUND and zapping - * nr_running, the warning may trigger spuriously. Check iff - * unbind is not in progress. - */ - WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && - pool->nr_workers == pool->nr_idle && + /* Sanity check nr_running. */ + WARN_ON_ONCE(pool->nr_workers == pool->nr_idle && atomic_read(&pool->nr_running)); } @@ -4979,38 +4988,22 @@ static void unbind_workers(int cpu) /* * We've blocked all attach/detach operations. Make all workers * unbound and set DISASSOCIATED. Before this, all workers - * except for the ones which are still executing works from - * before the last CPU down must be on the cpu. After - * this, they may become diasporas. + * must be on the cpu. After this, they may become diasporas. + * And the preemption disabled section in their sched callbacks + * are guaranteed to see WORKER_UNBOUND since the code here + * is on the same cpu. */ for_each_pool_worker(worker, pool) worker->flags |= WORKER_UNBOUND; pool->flags |= POOL_DISASSOCIATED; - raw_spin_unlock_irq(&pool->lock); - - for_each_pool_worker(worker, pool) { - kthread_set_per_cpu(worker->task, -1); - WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); - } - - mutex_unlock(&wq_pool_attach_mutex); - /* - * Call schedule() so that we cross rq->lock and thus can - * guarantee sched callbacks see the %WORKER_UNBOUND flag. - * This is necessary as scheduler callbacks may be invoked - * from other cpus. - */ - schedule(); - - /* - * Sched callbacks are disabled now. Zap nr_running. - * After this, nr_running stays zero and need_more_worker() - * and keep_working() are always true as long as the - * worklist is not empty. This pool now behaves as an - * unbound (in terms of concurrency management) pool which + * The handling of nr_running in sched callbacks are disabled + * now. Zap nr_running. After this, nr_running stays zero and + * need_more_worker() and keep_working() are always true as + * long as the worklist is not empty. This pool now behaves as + * an unbound (in terms of concurrency management) pool which * are served by workers tied to the pool. */ atomic_set(&pool->nr_running, 0); @@ -5020,9 +5013,16 @@ static void unbind_workers(int cpu) * worker blocking could lead to lengthy stalls. Kick off * unbound chain execution of currently pending work items. */ - raw_spin_lock_irq(&pool->lock); wake_up_worker(pool); + raw_spin_unlock_irq(&pool->lock); + + for_each_pool_worker(worker, pool) { + kthread_set_per_cpu(worker->task, -1); + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); + } + + mutex_unlock(&wq_pool_attach_mutex); } } @@ -5059,17 +5059,6 @@ static void rebind_workers(struct worker_pool *pool) unsigned int worker_flags = worker->flags; /* - * A bound idle worker should actually be on the runqueue - * of the associated CPU for local wake-ups targeting it to - * work. Kick all idle workers so that they migrate to the - * associated CPU. Doing this in the same loop as - * replacing UNBOUND with REBOUND is safe as no worker will - * be bound before @pool->lock is released. - */ - if (worker_flags & WORKER_IDLE) - wake_up_process(worker->task); - - /* * We want to clear UNBOUND but can't directly call * worker_clr_flags() or adjust nr_running. Atomically * replace UNBOUND with another NOT_RUNNING flag REBOUND. |