diff options
Diffstat (limited to 'kernel')
90 files changed, 1900 insertions, 1077 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 583ff349e37e..dcdf383c4c82 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -91,7 +91,6 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o obj-$(CONFIG_TRACEPOINTS) += tracepoint.o obj-$(CONFIG_LATENCYTOP) += latencytop.o -obj-$(CONFIG_ELFCORE) += elfcore.o obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ obj-$(CONFIG_TRACE_CLOCK) += trace/ diff --git a/kernel/audit.c b/kernel/audit.c index b21a8910f765..2b82316b844b 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -686,7 +686,7 @@ 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) */ @@ -703,32 +703,30 @@ 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); } @@ -853,7 +851,7 @@ main_queue: return 0; } -int audit_send_list(void *_dest) +int audit_send_list_thread(void *_dest) { struct audit_netlink_list *dest = _dest; struct sk_buff *skb; @@ -897,19 +895,30 @@ out_kfree_skb: return NULL; } +static void audit_free_reply(struct audit_reply *reply) +{ + if (!reply) + return; + + if (reply->skb) + kfree_skb(reply->skb); + if (reply->net) + put_net(reply->net); + kfree(reply); +} + static int audit_send_reply_thread(void *arg) { struct audit_reply *reply = (struct audit_reply *)arg; - struct sock *sk = audit_get_sk(reply->net); mutex_lock(&audit_cmd_mutex); mutex_unlock(&audit_cmd_mutex); /* Ignore failure. It'll only happen if the sender goes away, because our timeout is set to infinite. */ - netlink_unicast(sk, reply->skb, reply->portid, 0); - put_net(reply->net); - kfree(reply); + netlink_unicast(audit_get_sk(reply->net), reply->skb, reply->portid, 0); + reply->skb = NULL; + audit_free_reply(reply); return 0; } @@ -923,35 +932,32 @@ static int audit_send_reply_thread(void *arg) * @payload: payload data * @size: payload size * - * Allocates an skb, builds the netlink message, and sends it to the port id. - * No failure notifications. + * Allocates a skb, builds the netlink message, and sends it to the port id. */ static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done, int multi, const void *payload, int size) { - struct net *net = sock_net(NETLINK_CB(request_skb).sk); - struct sk_buff *skb; struct task_struct *tsk; - struct audit_reply *reply = kmalloc(sizeof(struct audit_reply), - GFP_KERNEL); + struct audit_reply *reply; + reply = kzalloc(sizeof(*reply), GFP_KERNEL); if (!reply) return; - skb = audit_make_reply(seq, type, done, multi, payload, size); - if (!skb) - goto out; - - reply->net = get_net(net); + reply->skb = audit_make_reply(seq, type, done, multi, payload, size); + if (!reply->skb) + goto err; + reply->net = get_net(sock_net(NETLINK_CB(request_skb).sk)); reply->portid = NETLINK_CB(request_skb).portid; - reply->skb = skb; tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply"); - if (!IS_ERR(tsk)) - return; - kfree_skb(skb); -out: - kfree(reply); + if (IS_ERR(tsk)) + goto err; + + return; + +err: + audit_free_reply(reply); } /* @@ -1292,6 +1298,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: if (!audit_enabled && msg_type != AUDIT_USER_AVC) return 0; + /* exit early if there isn't at least one character to print */ + if (data_len < 2) + return -EINVAL; err = audit_filter(msg_type, AUDIT_FILTER_USER); if (err == 1) { /* match or error */ @@ -1507,7 +1516,8 @@ 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/audit.h b/kernel/audit.h index 9b110ae17ee3..1007773b0b81 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -248,7 +248,7 @@ struct audit_netlink_list { struct sk_buff_head q; }; -int audit_send_list(void *_dest); +int audit_send_list_thread(void *_dest); extern int selinux_audit_rule_update(void); diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 35f1d706bd5b..ac87820cc082 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -316,8 +316,6 @@ static void audit_update_watch(struct audit_parent *parent, if (oentry->rule.exe) audit_remove_mark(oentry->rule.exe); - audit_watch_log_rule_change(r, owatch, "updated_rules"); - call_rcu(&oentry->rcu, audit_free_rule_rcu); } diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 16cf396ea738..f26f4cb5d08d 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1137,11 +1137,8 @@ int audit_rule_change(int type, int seq, void *data, size_t datasz) */ int audit_list_rules_send(struct sk_buff *request_skb, int seq) { - u32 portid = NETLINK_CB(request_skb).portid; - struct net *net = sock_net(NETLINK_CB(request_skb).sk); struct task_struct *tsk; struct audit_netlink_list *dest; - int err = 0; /* We can't just spew out the rules here because we might fill * the available socket buffer space and deadlock waiting for @@ -1149,25 +1146,26 @@ int audit_list_rules_send(struct sk_buff *request_skb, int seq) * happen if we're actually running in the context of auditctl * trying to _send_ the stuff */ - dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL); + dest = kmalloc(sizeof(*dest), GFP_KERNEL); if (!dest) return -ENOMEM; - dest->net = get_net(net); - dest->portid = portid; + dest->net = get_net(sock_net(NETLINK_CB(request_skb).sk)); + dest->portid = NETLINK_CB(request_skb).portid; skb_queue_head_init(&dest->q); mutex_lock(&audit_filter_mutex); audit_list_rules(seq, &dest->q); mutex_unlock(&audit_filter_mutex); - tsk = kthread_run(audit_send_list, dest, "audit_send_list"); + tsk = kthread_run(audit_send_list_thread, dest, "audit_send_list"); if (IS_ERR(tsk)) { skb_queue_purge(&dest->q); + put_net(dest->net); kfree(dest); - err = PTR_ERR(tsk); + return PTR_ERR(tsk); } - return err; + return 0; } int audit_comparator(u32 left, u32 op, u32 right) diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c index e6ef4401a138..9b5eeff72fd3 100644 --- a/kernel/bpf/bpf_lru_list.c +++ b/kernel/bpf/bpf_lru_list.c @@ -505,13 +505,14 @@ struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash) static void bpf_common_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node) { + u8 node_type = READ_ONCE(node->type); unsigned long flags; - if (WARN_ON_ONCE(node->type == BPF_LRU_LIST_T_FREE) || - WARN_ON_ONCE(node->type == BPF_LRU_LOCAL_LIST_T_FREE)) + if (WARN_ON_ONCE(node_type == BPF_LRU_LIST_T_FREE) || + WARN_ON_ONCE(node_type == BPF_LRU_LOCAL_LIST_T_FREE)) return; - if (node->type == BPF_LRU_LOCAL_LIST_T_PENDING) { + if (node_type == BPF_LRU_LOCAL_LIST_T_PENDING) { struct bpf_lru_locallist *loc_l; loc_l = per_cpu_ptr(lru->common_lru.local_list, node->cpu); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index e7211b0fa27c..485e319ba742 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -295,6 +295,7 @@ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON); int bpf_jit_harden __read_mostly; int bpf_jit_kallsyms __read_mostly; long bpf_jit_limit __read_mostly; +long bpf_jit_limit_max __read_mostly; static __always_inline void bpf_get_prog_addr_region(const struct bpf_prog *prog, @@ -508,7 +509,8 @@ u64 __weak bpf_jit_alloc_exec_limit(void) static int __init bpf_jit_charge_init(void) { /* Only used as heuristic here to derive limit. */ - bpf_jit_limit = min_t(u64, round_up(bpf_jit_alloc_exec_limit() >> 2, + bpf_jit_limit_max = bpf_jit_alloc_exec_limit(); + bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 2, PAGE_SIZE), LONG_MAX); return 0; } diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 505e69854eb8..ecc58137525b 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -645,26 +645,23 @@ static void htab_elem_free_rcu(struct rcu_head *head) struct htab_elem *l = container_of(head, struct htab_elem, rcu); struct bpf_htab *htab = l->htab; - /* must increment bpf_prog_active to avoid kprobe+bpf triggering while - * we're calling kfree, otherwise deadlock is possible if kprobes - * are placed somewhere inside of slub - */ - preempt_disable(); - __this_cpu_inc(bpf_prog_active); htab_elem_free(htab, l); - __this_cpu_dec(bpf_prog_active); - preempt_enable(); } -static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l) { struct bpf_map *map = &htab->map; + void *ptr; if (map->ops->map_fd_put_ptr) { - void *ptr = fd_htab_map_get_ptr(map, l); - + ptr = fd_htab_map_get_ptr(map, l); map->ops->map_fd_put_ptr(ptr); } +} + +static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +{ + htab_put_fd_value(htab, l); if (htab_is_prealloc(htab)) { __pcpu_freelist_push(&htab->freelist, &l->fnode); @@ -725,6 +722,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, */ pl_new = this_cpu_ptr(htab->extra_elems); l_new = *pl_new; + htab_put_fd_value(htab, old_elem); *pl_new = old_elem; } else { struct pcpu_freelist_node *l; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 135be433e9a0..099dc780a92f 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -28,7 +28,8 @@ struct bpf_stack_map { static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) { - u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size; + u64 elem_size = sizeof(struct stack_map_bucket) + + (u64)smap->map.value_size; int err; smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries, @@ -71,6 +72,8 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) /* hash table size must be power of 2 */ n_buckets = roundup_pow_of_two(attr->max_entries); + if (!n_buckets) + return ERR_PTR(-E2BIG); cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); if (cost >= U32_MAX - PAGE_SIZE) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 615a2e44d2a0..08f0588fa832 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2024,32 +2024,43 @@ static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env) return &env->insn_aux_data[env->insn_idx]; } +enum { + REASON_BOUNDS = -1, + REASON_TYPE = -2, + REASON_PATHS = -3, + REASON_LIMIT = -4, + REASON_STACK = -5, +}; + static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, - u32 *ptr_limit, u8 opcode, bool off_is_neg) + u32 *alu_limit, bool mask_to_left) { - bool mask_to_left = (opcode == BPF_ADD && off_is_neg) || - (opcode == BPF_SUB && !off_is_neg); - u32 off; + u32 max = 0, ptr_limit = 0; switch (ptr_reg->type) { case PTR_TO_STACK: - off = ptr_reg->off + ptr_reg->var_off.value; - if (mask_to_left) - *ptr_limit = MAX_BPF_STACK + off; - else - *ptr_limit = -off; - return 0; + /* Offset 0 is out-of-bounds, but acceptable start for the + * left direction, see BPF_REG_FP. Also, unknown scalar + * offset where we would need to deal with min/max bounds is + * currently prohibited for unprivileged. + */ + max = MAX_BPF_STACK + mask_to_left; + ptr_limit = -(ptr_reg->var_off.value + ptr_reg->off); + break; case PTR_TO_MAP_VALUE: - if (mask_to_left) { - *ptr_limit = ptr_reg->umax_value + ptr_reg->off; - } else { - off = ptr_reg->smin_value + ptr_reg->off; - *ptr_limit = ptr_reg->map_ptr->value_size - off; - } - return 0; + max = ptr_reg->map_ptr->value_size; + ptr_limit = (mask_to_left ? + ptr_reg->smin_value : + ptr_reg->umax_value) + ptr_reg->off; + break; default: - return -EINVAL; + return REASON_TYPE; } + + if (ptr_limit >= max) + return REASON_LIMIT; + *alu_limit = ptr_limit; + return 0; } static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env, @@ -2067,7 +2078,7 @@ static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux, if (aux->alu_state && (aux->alu_state != alu_state || aux->alu_limit != alu_limit)) - return -EACCES; + return REASON_PATHS; /* Corresponding fixup done in fixup_bpf_calls(). */ aux->alu_state = alu_state; @@ -2086,19 +2097,34 @@ static int sanitize_val_alu(struct bpf_verifier_env *env, return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0); } +static bool sanitize_needed(u8 opcode) +{ + return opcode == BPF_ADD || opcode == BPF_SUB; +} + +struct bpf_sanitize_info { + struct bpf_insn_aux_data aux; + bool mask_to_left; +}; + static int sanitize_ptr_alu(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, + const struct bpf_reg_state *off_reg, struct bpf_reg_state *dst_reg, - bool off_is_neg) + struct bpf_sanitize_info *info, + const bool commit_window) { + struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : &info->aux; struct bpf_verifier_state *vstate = env->cur_state; - struct bpf_insn_aux_data *aux = cur_aux(env); + bool off_is_imm = tnum_is_const(off_reg->var_off); + bool off_is_neg = off_reg->smin_value < 0; bool ptr_is_dst_reg = ptr_reg == dst_reg; u8 opcode = BPF_OP(insn->code); u32 alu_state, alu_limit; struct bpf_reg_state tmp; bool ret; + int err; if (can_skip_alu_sanitation(env, insn)) return 0; @@ -2110,15 +2136,47 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, if (vstate->speculative) goto do_sim; - alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; - alu_state |= ptr_is_dst_reg ? - BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; + if (!commit_window) { + if (!tnum_is_const(off_reg->var_off) && + (off_reg->smin_value < 0) != (off_reg->smax_value < 0)) + return REASON_BOUNDS; - if (retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg)) - return 0; - if (update_alu_sanitation_state(aux, alu_state, alu_limit)) - return -EACCES; + info->mask_to_left = (opcode == BPF_ADD && off_is_neg) || + (opcode == BPF_SUB && !off_is_neg); + } + + err = retrieve_ptr_limit(ptr_reg, &alu_limit, info->mask_to_left); + if (err < 0) + return err; + + if (commit_window) { + /* In commit phase we narrow the masking window based on + * the observed pointer move after the simulated operation. + */ + alu_state = info->aux.alu_state; + alu_limit = abs(info->aux.alu_limit - alu_limit); + } else { + alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; + alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0; + alu_state |= ptr_is_dst_reg ? + BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; + } + + err = update_alu_sanitation_state(aux, alu_state, alu_limit); + if (err < 0) + return err; do_sim: + /* If we're in commit phase, we're done here given we already + * pushed the truncated dst_reg into the speculative verification + * stack. + * + * Also, when register is a known constant, we rewrite register-based + * operation to immediate-based, and thus do not need masking (and as + * a consequence, do not need to simulate the zero-truncation either). + */ + if (commit_window || off_is_imm) + return 0; + /* Simulate and find potential out-of-bounds access under * speculative execution from truncation as a result of * masking when off was not within expected range. If off @@ -2135,7 +2193,81 @@ do_sim: ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true); if (!ptr_is_dst_reg && ret) *dst_reg = tmp; - return !ret ? -EFAULT : 0; + return !ret ? REASON_STACK : 0; +} + +static int sanitize_err(struct bpf_verifier_env *env, + const struct bpf_insn *insn, int reason, + const struct bpf_reg_state *off_reg, + const struct bpf_reg_state *dst_reg) +{ + static const char *err = "pointer arithmetic with it prohibited for !root"; + const char *op = BPF_OP(insn->code) == BPF_ADD ? "add" : "sub"; + u32 dst = insn->dst_reg, src = insn->src_reg; + + switch (reason) { + case REASON_BOUNDS: + verbose("R%d has unknown scalar with mixed signed bounds, %s\n", + off_reg == dst_reg ? dst : src, err); + break; + case REASON_TYPE: + verbose("R%d has pointer with unsupported alu operation, %s\n", + off_reg == dst_reg ? src : dst, err); + break; + case REASON_PATHS: + verbose("R%d tried to %s from different maps, paths or scalars, %s\n", + dst, op, err); + break; + case REASON_LIMIT: + verbose("R%d tried to %s beyond pointer bounds, %s\n", + dst, op, err); + break; + case REASON_STACK: + verbose("R%d could not be pushed for speculative verification, %s\n", + dst, err); + break; + default: + verbose("verifier internal error: unknown reason (%d)\n", + reason); + break; + } + + return -EACCES; +} + +static int sanitize_check_bounds(struct bpf_verifier_env *env, + const struct bpf_insn *insn, + const struct bpf_reg_state *dst_reg) +{ + u32 dst = insn->dst_reg; + + /* For unprivileged we require that resulting offset must be in bounds + * in order to be able to sanitize access later on. + */ + if (env->allow_ptr_leaks) + return 0; + + switch (dst_reg->type) { + case PTR_TO_STACK: + if (check_stack_access(env, dst_reg, dst_reg->off + + dst_reg->var_off.value, 1)) { + verbose("R%d stack pointer arithmetic goes out of range, " + "prohibited for !root\n", dst); + return -EACCES; + } + break; + case PTR_TO_MAP_VALUE: + if (check_map_access(env, dst, dst_reg->off, 1)) { + verbose("R%d pointer arithmetic of map value goes out of range, " + "prohibited for !root\n", dst); + return -EACCES; + } + break; + default: + break; + } + + return 0; } /* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off. @@ -2154,8 +2286,9 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value; u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value, umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value; - u32 dst = insn->dst_reg, src = insn->src_reg; + struct bpf_sanitize_info info = {}; u8 opcode = BPF_OP(insn->code); + u32 dst = insn->dst_reg; int ret; dst_reg = ®s[dst]; @@ -2171,28 +2304,24 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (BPF_CLASS(insn->code) != BPF_ALU64) { /* 32-bit ALU ops on pointers produce (meaningless) scalars */ - if (!env->allow_ptr_leaks) - verbose("R%d 32-bit pointer arithmetic prohibited\n", - dst); + verbose("R%d 32-bit pointer arithmetic prohibited\n", + dst); return -EACCES; } if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) { - if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", - dst); + verbose("R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", + dst); return -EACCES; } if (ptr_reg->type == CONST_PTR_TO_MAP) { - if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", - dst); + verbose("R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", + dst); return -EACCES; } if (ptr_reg->type == PTR_TO_PACKET_END) { - if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", - dst); + verbose("R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", + dst); return -EACCES; } @@ -2206,13 +2335,15 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, !check_reg_sane_offset(env, ptr_reg, ptr_reg->type)) return -EINVAL; + if (sanitize_needed(opcode)) { + ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg, + &info, false); + if (ret < 0) + return sanitize_err(env, insn, ret, off_reg, dst_reg); + } + switch (opcode) { case BPF_ADD: - ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0); - if (ret < 0) { - verbose("R%d tried to add from different maps or paths\n", dst); - return ret; - } /* We can take a fixed offset as long as it doesn't overflow * the s32 'off' field */ @@ -2263,16 +2394,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } break; case BPF_SUB: - ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0); - if (ret < 0) { - verbose("R%d tried to sub from different maps or paths\n", dst); - return ret; - } if (dst_reg == off_reg) { /* scalar -= pointer. Creates an unknown scalar */ - if (!env->allow_ptr_leaks) - verbose("R%d tried to subtract pointer from scalar\n", - dst); + verbose("R%d tried to subtract pointer from scalar\n", + dst); return -EACCES; } /* We don't allow subtraction from FP, because (according to @@ -2280,9 +2405,8 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, * be able to deal with it. */ if (ptr_reg->type == PTR_TO_STACK) { - if (!env->allow_ptr_leaks) - verbose("R%d subtraction from stack pointer prohibited\n", - dst); + verbose("R%d subtraction from stack pointer prohibited\n", + dst); return -EACCES; } if (known && (ptr_reg->off - smin_val == @@ -2332,26 +2456,14 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, case BPF_AND: case BPF_OR: case BPF_XOR: - /* bitwise ops on pointers are troublesome, prohibit for now. - * (However, in principle we could allow some cases, e.g. - * ptr &= ~3 which would reduce min_value by 3.) - */ - if (!env->allow_ptr_leaks) - verbose("R%d bitwise operator %s on pointer prohibited\n", - dst, bpf_alu_string[opcode >> 4]); + /* bitwise ops on pointers are troublesome. */ + verbose("R%d bitwise operator %s on pointer prohibited\n", + dst, bpf_alu_string[opcode >> 4]); return -EACCES; - case PTR_TO_MAP_VALUE: - if (!env->allow_ptr_leaks && !known && (smin_val < 0) != (smax_val < 0)) { - verbose("R%d has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root\n", - off_reg == dst_reg ? dst : src); - return -EACCES; - } - /* fall-through */ default: /* other operators (e.g. MUL,LSH) produce non-pointer results */ - if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic with %s operator prohibited\n", - dst, bpf_alu_string[opcode >> 4]); + verbose("R%d pointer arithmetic with %s operator prohibited\n", + dst, bpf_alu_string[opcode >> 4]); return -EACCES; } @@ -2362,22 +2474,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, __reg_deduce_bounds(dst_reg); __reg_bound_offset(dst_reg); - /* For unprivileged we require that resulting offset must be in bounds - * in order to be able to sanitize access later on. - */ - if (!env->allow_ptr_leaks) { - if (dst_reg->type == PTR_TO_MAP_VALUE && - check_map_access(env, dst, dst_reg->off, 1)) { - verbose("R%d pointer arithmetic of map value goes out of range, " - "prohibited for !root\n", dst); - return -EACCES; - } else if (dst_reg->type == PTR_TO_STACK && - check_stack_access(env, dst_reg, dst_reg->off + - dst_reg->var_off.value, 1)) { - verbose("R%d stack pointer arithmetic goes out of range, " - "prohibited for !root\n", dst); - return -EACCES; - } + if (sanitize_check_bounds(env, insn, dst_reg) < 0) + return -EACCES; + if (sanitize_needed(opcode)) { + ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg, + &info, true); + if (ret < 0) + return sanitize_err(env, insn, ret, off_reg, dst_reg); } return 0; @@ -2398,7 +2501,6 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, s64 smin_val, smax_val; u64 umin_val, umax_val; u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; - u32 dst = insn->dst_reg; int ret; if (insn_bitness == 32) { @@ -2432,13 +2534,14 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, return 0; } + if (sanitize_needed(opcode)) { + ret = sanitize_val_alu(env, insn); + if (ret < 0) + return sanitize_err(env, insn, ret, NULL, NULL); + } + switch (opcode) { case BPF_ADD: - ret = sanitize_val_alu(env, insn); - if (ret < 0) { - verbose("R%d tried to add from different pointers or scalars\n", dst); - return ret; - } if (signed_add_overflows(dst_reg->smin_value, smin_val) || signed_add_overflows(dst_reg->smax_value, smax_val)) { dst_reg->smin_value = S64_MIN; @@ -2458,11 +2561,6 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off); break; case BPF_SUB: - ret = sanitize_val_alu(env, insn); - if (ret < 0) { - verbose("R%d tried to sub from different pointers or scalars\n", dst); - return ret; - } if (signed_sub_overflows(dst_reg->smin_value, smax_val) || signed_sub_overflows(dst_reg->smax_value, smin_val)) { /* Overflow possible, we know nothing */ @@ -2655,7 +2753,6 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_reg_state *regs = cur_regs(env), *dst_reg, *src_reg; struct bpf_reg_state *ptr_reg = NULL, off_reg = {0}; u8 opcode = BPF_OP(insn->code); - int rc; dst_reg = ®s[insn->dst_reg]; src_reg = NULL; @@ -2666,43 +2763,29 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, if (src_reg->type != SCALAR_VALUE) { if (dst_reg->type != SCALAR_VALUE) { /* Combining two pointers by any ALU op yields - * an arbitrary scalar. + * an arbitrary scalar. Disallow all math except + * pointer subtraction */ - if (!env->allow_ptr_leaks) { - verbose("R%d pointer %s pointer prohibited\n", - insn->dst_reg, - bpf_alu_string[opcode >> 4]); - return -EACCES; + if (opcode == BPF_SUB && env->allow_ptr_leaks) { + mark_reg_unknown(regs, insn->dst_reg); + return 0; } - mark_reg_unknown(regs, insn->dst_reg); - return 0; + verbose("R%d pointer %s pointer prohibited\n", + insn->dst_reg, + bpf_alu_string[opcode >> 4]); + return -EACCES; } else { /* scalar += pointer * This is legal, but we have to reverse our * src/dest handling in computing the range */ - rc = adjust_ptr_min_max_vals(env, insn, - src_reg, dst_reg); - if (rc == -EACCES && env->allow_ptr_leaks) { - /* scalar += unknown scalar */ - __mark_reg_unknown(&off_reg); - return adjust_scalar_min_max_vals( - env, insn, - dst_reg, off_reg); - } - return rc; + return adjust_ptr_min_max_vals(env, insn, + src_reg, dst_reg); } } else if (ptr_reg) { /* pointer += scalar */ - rc = adjust_ptr_min_max_vals(env, insn, - dst_reg, src_reg); - if (rc == -EACCES && env->allow_ptr_leaks) { - /* unknown scalar += scalar */ - __mark_reg_unknown(dst_reg); - return adjust_scalar_min_max_vals( - env, insn, dst_reg, *src_reg); - } - return rc; + return adjust_ptr_min_max_vals(env, insn, + dst_reg, src_reg); } } else { /* Pretend the src is a reg with a known value, since we only @@ -2711,17 +2794,9 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, off_reg.type = SCALAR_VALUE; __mark_reg_known(&off_reg, insn->imm); src_reg = &off_reg; - if (ptr_reg) { /* pointer += K */ - rc = adjust_ptr_min_max_vals(env, insn, - ptr_reg, src_reg); - if (rc == -EACCES && env->allow_ptr_leaks) { - /* unknown scalar += K */ - __mark_reg_unknown(dst_reg); - return adjust_scalar_min_max_vals( - env, insn, dst_reg, off_reg); - } - return rc; - } + if (ptr_reg) /* pointer += K */ + return adjust_ptr_min_max_vals(env, insn, + ptr_reg, src_reg); } /* Got here implies adding two SCALAR_VALUEs */ @@ -2914,7 +2989,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, new_range = dst_reg->off; if (range_right_open) - new_range--; + new_range++; /* Examples for register markings: * @@ -4787,7 +4862,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) const u8 code_sub = BPF_ALU64 | BPF_SUB | BPF_X; struct bpf_insn insn_buf[16]; struct bpf_insn *patch = &insn_buf[0]; - bool issrc, isneg; + bool issrc, isneg, isimm; u32 off_reg; aux = &env->insn_aux_data[i + delta]; @@ -4798,28 +4873,29 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) isneg = aux->alu_state & BPF_ALU_NEG_VALUE; issrc = (aux->alu_state & BPF_ALU_SANITIZE) == BPF_ALU_SANITIZE_SRC; + isimm = aux->alu_state & BPF_ALU_IMMEDIATE; off_reg = issrc ? insn->src_reg : insn->dst_reg; - if (isneg) - *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); - *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit - 1); - *patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg); - *patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg); - *patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0); - *patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63); - if (issrc) { - *patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX, - off_reg); - insn->src_reg = BPF_REG_AX; + if (isimm) { + *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit); } else { - *patch++ = BPF_ALU64_REG(BPF_AND, off_reg, - BPF_REG_AX); + if (isneg) + *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); + *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit); + *patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg); + *patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg); + *patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0); + *patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63); + *patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX, off_reg); } + if (!issrc) + *patch++ = BPF_MOV64_REG(insn->dst_reg, insn->src_reg); + insn->src_reg = BPF_REG_AX; if (isneg) insn->code = insn->code == code_add ? code_sub : code_add; *patch++ = *insn; - if (issrc && isneg) + if (issrc && isneg && !isimm) *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); cnt = patch - insn_buf; diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 545f29c5268d..5602bd81caa9 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -861,6 +861,10 @@ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent struct cgroup *cgrp = kn->priv; int ret; + /* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ + if (strchr(new_name_str, '\n')) + return -EINVAL; + if (kernfs_type(kn) != KERNFS_DIR) return -ENOTDIR; if (kn->parent != new_parent) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 2b3f2ea6a8a3..d5044ca33bd0 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1599,6 +1599,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; int ssid, i, ret; + u16 dfl_disable_ss_mask = 0; lockdep_assert_held(&cgroup_mutex); @@ -1615,8 +1616,28 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) /* can't move between two non-dummy roots either */ if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root) return -EBUSY; + + /* + * Collect ssid's that need to be disabled from default + * hierarchy. + */ + if (ss->root == &cgrp_dfl_root) + dfl_disable_ss_mask |= 1 << ssid; + } while_each_subsys_mask(); + if (dfl_disable_ss_mask) { + struct cgroup *scgrp = &cgrp_dfl_root.cgrp; + + /* + * Controllers from default hierarchy that need to be rebound + * are all disabled together in one go. + */ + cgrp_dfl_root.subsys_mask &= ~dfl_disable_ss_mask; + WARN_ON(cgroup_apply_control(scgrp)); + cgroup_finalize_control(scgrp, 0); + } + do_each_subsys_mask(ss, ssid, ss_mask) { struct cgroup_root *src_root = ss->root; struct cgroup *scgrp = &src_root->cgrp; @@ -1625,10 +1646,12 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) WARN_ON(!css || cgroup_css(dcgrp, ss)); - /* disable from the source */ - src_root->subsys_mask &= ~(1 << ssid); - WARN_ON(cgroup_apply_control(scgrp)); - cgroup_finalize_control(scgrp, 0); + if (src_root != &cgrp_dfl_root) { + /* disable from the source */ + src_root->subsys_mask &= ~(1 << ssid); + WARN_ON(cgroup_apply_control(scgrp)); + cgroup_finalize_control(scgrp, 0); + } /* rebind */ RCU_INIT_POINTER(scgrp->subsys[ssid], NULL); @@ -5219,8 +5242,6 @@ int __init cgroup_init_early(void) return 0; } -static u16 cgroup_disable_mask __initdata; - /** * cgroup_init - cgroup initialization * @@ -5278,12 +5299,8 @@ int __init cgroup_init(void) * disabled flag and cftype registration needs kmalloc, * both of which aren't available during early_init. */ - if (cgroup_disable_mask & (1 << ssid)) { - static_branch_disable(cgroup_subsys_enabled_key[ssid]); - printk(KERN_INFO "Disabling %s control group subsystem\n", - ss->name); + if (!cgroup_ssid_enabled(ssid)) continue; - } if (cgroup1_ssid_disabled(ssid)) printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n", @@ -5642,7 +5659,10 @@ static int __init cgroup_disable(char *str) if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; - cgroup_disable_mask |= 1 << i; + + static_branch_disable(cgroup_subsys_enabled_key[i]); + pr_info("Disabling %s control group subsystem\n", + ss->name); } } return 1; @@ -5798,17 +5818,8 @@ void cgroup_sk_alloc_disable(void) void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { - if (cgroup_sk_alloc_disabled) - return; - - /* Socket clone path */ - if (skcd->val) { - /* - * We might be cloning a socket which is left in an empty - * cgroup and the cgroup might have already been rmdir'd. - * Don't use cgroup_get_live(). - */ - cgroup_get(sock_cgroup_ptr(skcd)); + if (cgroup_sk_alloc_disabled) { + skcd->no_refcnt = 1; return; } @@ -5832,8 +5843,26 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd) rcu_read_unlock(); } +void cgroup_sk_clone(struct sock_cgroup_data *skcd) +{ + /* Socket clone path */ + if (skcd->val) { + if (skcd->no_refcnt) + return; + /* + * We might be cloning a socket which is left in an empty + * cgroup and the cgroup might have already been rmdir'd. + * Don't use cgroup_get_live(). + */ + cgroup_get(sock_cgroup_ptr(skcd)); + } +} + void cgroup_sk_free(struct sock_cgroup_data *skcd) { + if (skcd->no_refcnt) + return; + cgroup_put(sock_cgroup_ptr(skcd)); } diff --git a/kernel/compat.c b/kernel/compat.c index 7e83733d4c95..45ae3ace49c2 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -437,10 +437,9 @@ long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG); nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size); - if (!access_ok(VERIFY_READ, umask, bitmap_size / 8)) + if (!user_access_begin(VERIFY_READ, umask, bitmap_size / 8)) return -EFAULT; - user_access_begin(); while (nr_compat_longs > 1) { compat_ulong_t l1, l2; unsafe_get_user(l1, umask++, Efault); @@ -467,10 +466,9 @@ long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG); nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size); - if (!access_ok(VERIFY_WRITE, umask, bitmap_size / 8)) + if (!user_access_begin(VERIFY_WRITE, umask, bitmap_size / 8)) return -EFAULT; - user_access_begin(); while (nr_compat_longs > 1) { unsigned long m = *mask++; unsafe_put_user((compat_ulong_t)m, umask++, Efault); diff --git a/kernel/cpu.c b/kernel/cpu.c index 96c0a868232e..f3b231cb6b65 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -30,6 +30,7 @@ #include <linux/relay.h> #include <linux/slab.h> #include <linux/percpu-rwsem.h> +#include <linux/cpuset.h> #include <trace/events/power.h> #define CREATE_TRACE_POINTS @@ -771,7 +772,57 @@ void __init cpuhp_threads_init(void) kthread_unpark(this_cpu_read(cpuhp_state.thread)); } +/* + * + * Serialize hotplug trainwrecks outside of the cpu_hotplug_lock + * protected region. + * + * The operation is still serialized against concurrent CPU hotplug via + * cpu_add_remove_lock, i.e. CPU map protection. But it is _not_ + * serialized against other hotplug related activity like adding or + * removing of state callbacks and state instances, which invoke either the + * startup or the teardown callback of the affected state. + * + * This is required for subsystems which are unfixable vs. CPU hotplug and + * evade lock inversion problems by scheduling work which has to be + * completed _before_ cpu_up()/_cpu_down() returns. + * + * Don't even think about adding anything to this for any new code or even + * drivers. It's only purpose is to keep existing lock order trainwrecks + * working. + * + * For cpu_down() there might be valid reasons to finish cleanups which are + * not required to be done under cpu_hotplug_lock, but that's a different + * story and would be not invoked via this. + */ +static void cpu_up_down_serialize_trainwrecks(bool tasks_frozen) +{ + /* + * cpusets delegate hotplug operations to a worker to "solve" the + * lock order problems. Wait for the worker, but only if tasks are + * _not_ frozen (suspend, hibernate) as that would wait forever. + * + * The wait is required because otherwise the hotplug operation + * returns with inconsistent state, which could even be observed in + * user space when a new CPU is brought up. The CPU plug uevent + * would be delivered and user space reacting on it would fail to + * move tasks to the newly plugged CPU up to the point where the + * work has finished because up to that point the newly plugged CPU + * is not assignable in cpusets/cgroups. On unplug that's not + * necessarily a visible issue, but it is still inconsistent state, + * which is the real problem which needs to be "fixed". This can't + * prevent the transient state between scheduling the work and + * returning from waiting for it. + */ + if (!tasks_frozen) + cpuset_wait_for_hotplug(); +} + #ifdef CONFIG_HOTPLUG_CPU +#ifndef arch_clear_mm_cpumask_cpu +#define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm)) +#endif + /** * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU * @cpu: a CPU id @@ -807,7 +858,7 @@ void clear_tasks_mm_cpumask(int cpu) t = find_lock_task_mm(p); if (!t) continue; - cpumask_clear_cpu(cpu, mm_cpumask(t->mm)); + arch_clear_mm_cpumask_cpu(cpu, t->mm); task_unlock(t); } rcu_read_unlock(); @@ -1006,6 +1057,7 @@ out: */ lockup_detector_cleanup(); arch_smt_update(); + cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } @@ -1141,6 +1193,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) out: cpus_write_unlock(); arch_smt_update(); + cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } @@ -2089,10 +2142,8 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) */ cpuhp_offline_cpu_device(cpu); } - if (!ret) { + if (!ret) cpu_smt_control = ctrlval; - arch_smt_update(); - } cpu_maps_update_done(); return ret; } @@ -2103,7 +2154,6 @@ int cpuhp_smt_enable(void) cpu_maps_update_begin(); cpu_smt_control = CPU_SMT_ENABLED; - arch_smt_update(); for_each_present_cpu(cpu) { /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c index 67b02e138a47..2ed6351e2a7e 100644 --- a/kernel/cpu_pm.c +++ b/kernel/cpu_pm.c @@ -89,7 +89,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier); */ int cpu_pm_enter(void) { - int nr_calls; + int nr_calls = 0; int ret = 0; ret = cpu_pm_notify(CPU_PM_ENTER, -1, &nr_calls); @@ -140,7 +140,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_exit); */ int cpu_cluster_pm_enter(void) { - int nr_calls; + int nr_calls = 0; int ret = 0; ret = cpu_pm_notify(CPU_CLUSTER_PM_ENTER, -1, &nr_calls); diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 94aa9ae0007a..4cf5697e72b1 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -95,14 +95,6 @@ int dbg_switch_cpu; /* Use kdb or gdbserver mode */ int dbg_kdb_mode = 1; -static int __init opt_kgdb_con(char *str) -{ - kgdb_use_con = 1; - return 0; -} - -early_param("kgdbcon", opt_kgdb_con); - module_param(kgdb_use_con, int, 0644); module_param(kgdbreboot, int, 0644); @@ -444,6 +436,7 @@ static int kgdb_reenter_check(struct kgdb_state *ks) if (exception_level > 1) { dump_stack(); + kgdb_io_module_registered = false; panic("Recursive entry to debugger"); } @@ -488,6 +481,7 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs, arch_kgdb_ops.disable_hw_break(regs); acquirelock: + rcu_read_lock(); /* * Interrupts will be restored by the 'trap return' code, except when * single stepping. @@ -544,6 +538,7 @@ return_normal: atomic_dec(&slaves_in_kgdb); dbg_touch_watchdogs(); local_irq_restore(flags); + rcu_read_unlock(); return 0; } cpu_relax(); @@ -562,6 +557,7 @@ return_normal: raw_spin_unlock(&dbg_master_lock); dbg_touch_watchdogs(); local_irq_restore(flags); + rcu_read_unlock(); goto acquirelock; } @@ -681,6 +677,7 @@ kgdb_restore: raw_spin_unlock(&dbg_master_lock); dbg_touch_watchdogs(); local_irq_restore(flags); + rcu_read_unlock(); return kgdb_info[cpu].ret_state; } @@ -811,6 +808,20 @@ static struct console kgdbcons = { .index = -1, }; +static int __init opt_kgdb_con(char *str) +{ + kgdb_use_con = 1; + + if (kgdb_io_module_registered && !kgdb_con_registered) { + register_console(&kgdbcons); + kgdb_con_registered = 1; + } + + return 0; +} + +early_param("kgdbcon", opt_kgdb_con); + #ifdef CONFIG_MAGIC_SYSRQ static void sysrq_handle_dbg(int key) { diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 6a4b41484afe..b45576ca3b0d 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -679,12 +679,16 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap) size_avail = sizeof(kdb_buffer) - len; goto kdb_print_out; } - if (kdb_grepping_flag >= KDB_GREPPING_FLAG_SEARCH) + if (kdb_grepping_flag >= KDB_GREPPING_FLAG_SEARCH) { /* * This was a interactive search (using '/' at more - * prompt) and it has completed. Clear the flag. + * prompt) and it has completed. Replace the \0 with + * its original value to ensure multi-line strings + * are handled properly, and return to normal mode. */ + *cphold = replaced_byte; kdb_grepping_flag = 0; + } /* * at this point the string is a full line and * should be printed, up to the null. diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index f2158e463a0f..598744ffe526 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -233,7 +233,7 @@ extern struct task_struct *kdb_curr_task(int); #define kdb_do_each_thread(g, p) do_each_thread(g, p) #define kdb_while_each_thread(g, p) while_each_thread(g, p) -#define GFP_KDB (in_interrupt() ? GFP_ATOMIC : GFP_KERNEL) +#define GFP_KDB (in_dbg_master() ? GFP_ATOMIC : GFP_KERNEL) extern void *debug_kmalloc(size_t size, gfp_t flags); extern void debug_kfree(void *); diff --git a/kernel/elfcore.c b/kernel/elfcore.c deleted file mode 100644 index 57fb4dcff434..000000000000 --- a/kernel/elfcore.c +++ /dev/null @@ -1,26 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/elf.h> -#include <linux/fs.h> -#include <linux/mm.h> -#include <linux/binfmts.h> -#include <linux/elfcore.h> - -Elf_Half __weak elf_core_extra_phdrs(void) -{ - return 0; -} - -int __weak elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) -{ - return 1; -} - -int __weak elf_core_write_extra_data(struct coredump_params *cprm) -{ - return 1; -} - -size_t __weak elf_core_extra_data_size(void) -{ - return 0; -} diff --git a/kernel/events/core.c b/kernel/events/core.c index 845c8a1a9d30..0736508d595b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -94,11 +94,11 @@ static void remote_function(void *data) * @info: the function call argument * * Calls the function @func when the task is currently running. This might - * be on the current CPU, which just calls the function directly + * be on the current CPU, which just calls the function directly. This will + * retry due to any failures in smp_call_function_single(), such as if the + * task_cpu() goes offline concurrently. * - * returns: @func return value, or - * -ESRCH - when the process isn't running - * -EAGAIN - when the process moved away + * returns @func return value or -ESRCH or -ENXIO when the process isn't running */ static int task_function_call(struct task_struct *p, remote_function_f func, void *info) @@ -111,11 +111,17 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info) }; int ret; - do { - ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1); + for (;;) { + ret = smp_call_function_single(task_cpu(p), remote_function, + &data, 1); if (!ret) ret = data.ret; - } while (ret == -EAGAIN); + + if (ret != -EAGAIN) + break; + + cond_resched(); + } return ret; } @@ -3912,7 +3918,9 @@ find_get_context(struct pmu *pmu, struct task_struct *task, cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); ctx = &cpuctx->ctx; get_ctx(ctx); + raw_spin_lock_irqsave(&ctx->lock, flags); ++ctx->pin_count; + raw_spin_unlock_irqrestore(&ctx->lock, flags); return ctx; } @@ -5201,11 +5209,11 @@ static void perf_pmu_output_stop(struct perf_event *event); static void perf_mmap_close(struct vm_area_struct *vma) { struct perf_event *event = vma->vm_file->private_data; - struct ring_buffer *rb = ring_buffer_get(event); struct user_struct *mmap_user = rb->mmap_user; int mmap_locked = rb->mmap_locked; unsigned long size = perf_data_size(rb); + bool detach_rest = false; if (event->pmu->event_unmapped) event->pmu->event_unmapped(event, vma->vm_mm); @@ -5236,7 +5244,8 @@ static void perf_mmap_close(struct vm_area_struct *vma) mutex_unlock(&event->mmap_mutex); } - atomic_dec(&rb->mmap_count); + if (atomic_dec_and_test(&rb->mmap_count)) + detach_rest = true; if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) goto out_put; @@ -5245,7 +5254,7 @@ static void perf_mmap_close(struct vm_area_struct *vma) mutex_unlock(&event->mmap_mutex); /* If there's still other mmap()s of this buffer, we're done. */ - if (atomic_read(&rb->mmap_count)) + if (!detach_rest) goto out_put; /* @@ -6101,7 +6110,6 @@ void perf_output_sample(struct perf_output_handle *handle, static u64 perf_virt_to_phys(u64 virt) { u64 phys_addr = 0; - struct page *p = NULL; if (!virt) return 0; @@ -6119,12 +6127,16 @@ static u64 perf_virt_to_phys(u64 virt) * Try IRQ-safe __get_user_pages_fast first. * If failed, leave phys_addr as 0. */ - if ((current->mm != NULL) && - (__get_user_pages_fast(virt, 1, 0, &p) == 1)) - phys_addr = page_to_phys(p) + virt % PAGE_SIZE; + if (current->mm != NULL) { + struct page *p; - if (p) - put_page(p); + pagefault_disable(); + if (__get_user_pages_fast(virt, 1, 0, &p) == 1) { + phys_addr = page_to_phys(p) + virt % PAGE_SIZE; + put_page(p); + } + pagefault_enable(); + } } return phys_addr; @@ -6441,7 +6453,7 @@ static void perf_event_addr_filters_exec(struct perf_event *event, void *data) raw_spin_lock_irqsave(&ifh->lock, flags); list_for_each_entry(filter, &ifh->list, entry) { - if (filter->inode) { + if (filter->path.dentry) { event->addr_filters_offs[count] = 0; restart++; } @@ -6607,10 +6619,17 @@ static void perf_event_task_output(struct perf_event *event, goto out; task_event->event_id.pid = perf_event_pid(event, task); - task_event->event_id.ppid = perf_event_pid(event, current); - task_event->event_id.tid = perf_event_tid(event, task); - task_event->event_id.ptid = perf_event_tid(event, current); + + if (task_event->event_id.header.type == PERF_RECORD_EXIT) { + task_event->event_id.ppid = perf_event_pid(event, + task->real_parent); + task_event->event_id.ptid = perf_event_pid(event, + task->real_parent); + } else { /* PERF_RECORD_FORK */ + task_event->event_id.ppid = perf_event_pid(event, current); + task_event->event_id.ptid = perf_event_tid(event, current); + } task_event->event_id.time = perf_event_clock(event); @@ -7108,7 +7127,11 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter, struct file *file, unsigned long offset, unsigned long size) { - if (filter->inode != file_inode(file)) + /* d_inode(NULL) won't be equal to any mapped user-space file */ + if (!filter->path.dentry) + return false; + + if (d_inode(filter->path.dentry) != file_inode(file)) return false; if (filter->offset > offset + size) @@ -8329,8 +8352,7 @@ static void free_filters_list(struct list_head *filters) struct perf_addr_filter *filter, *iter; list_for_each_entry_safe(filter, iter, filters, entry) { - if (filter->inode) - iput(filter->inode); + path_put(&filter->path); list_del(&filter->entry); kfree(filter); } @@ -8413,7 +8435,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event) if (!ifh->nr_file_filters) return; - mm = get_task_mm(event->ctx->task); + mm = get_task_mm(task); if (!mm) goto restart; @@ -8427,7 +8449,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event) * Adjust base offset if the filter is associated to a binary * that needs to be mapped: */ - if (filter->inode) + if (filter->path.dentry) event->addr_filters_offs[count] = perf_addr_filter_apply(filter, mm); @@ -8500,7 +8522,6 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, { struct perf_addr_filter *filter = NULL; char *start, *orig, *filename = NULL; - struct path path; substring_t args[MAX_OPT_ARGS]; int state = IF_STATE_ACTION, token; unsigned int kernel = 0; @@ -8563,6 +8584,7 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, if (token == IF_SRC_FILE || token == IF_SRC_FILEADDR) { int fpos = filter->range ? 2 : 1; + kfree(filename); filename = match_strdup(&args[fpos]); if (!filename) { ret = -ENOMEM; @@ -8601,22 +8623,18 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, */ ret = -EOPNOTSUPP; if (!event->ctx->task) - goto fail_free_name; + goto fail; /* look up the path and grab its inode */ - ret = kern_path(filename, LOOKUP_FOLLOW, &path); + ret = kern_path(filename, LOOKUP_FOLLOW, + &filter->path); if (ret) - goto fail_free_name; - - filter->inode = igrab(d_inode(path.dentry)); - path_put(&path); - kfree(filename); - filename = NULL; + goto fail; ret = -EINVAL; - if (!filter->inode || - !S_ISREG(filter->inode->i_mode)) - /* free_filters_list() will iput() */ + if (!filter->path.dentry || + !S_ISREG(d_inode(filter->path.dentry) + ->i_mode)) goto fail; event->addr_filters.nr_file_filters++; @@ -8631,13 +8649,13 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, if (state != IF_STATE_ACTION) goto fail; + kfree(filename); kfree(orig); return 0; -fail_free_name: - kfree(filename); fail: + kfree(filename); free_filters_list(filters); kfree(orig); diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 09b1537ae06c..41317d04eeae 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -213,7 +213,7 @@ static inline int get_recursion_context(int *recursion) rctx = 3; else if (in_irq()) rctx = 2; - else if (in_softirq()) + else if (in_serving_softirq()) rctx = 1; else rctx = 0; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index c74fc9826250..f08ba79ee5d1 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -612,10 +612,6 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file, if (ret) goto out; - /* uprobe_write_opcode() assumes we don't cross page boundary */ - BUG_ON((uprobe->offset & ~PAGE_MASK) + - UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); - smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */ set_bit(UPROBE_COPY_INSN, &uprobe->flags); @@ -894,6 +890,13 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer * if (offset > i_size_read(inode)) return -EINVAL; + /* + * This ensures that copy_from_page() and copy_to_page() + * can't cross page boundary. + */ + if (!IS_ALIGNED(offset, UPROBE_SWBP_INSN_SIZE)) + return -EINVAL; + retry: uprobe = alloc_uprobe(inode, offset); if (!uprobe) @@ -1704,6 +1707,9 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr) uprobe_opcode_t opcode; int result; + if (WARN_ON_ONCE(!IS_ALIGNED(vaddr, UPROBE_SWBP_INSN_SIZE))) + return -EINVAL; + pagefault_disable(); result = __get_user(opcode, (uprobe_opcode_t __user *)vaddr); pagefault_enable(); @@ -1887,7 +1893,7 @@ static void handle_swbp(struct pt_regs *regs) if (!uprobe) { if (is_swbp > 0) { /* No matching uprobe; signal SIGTRAP. */ - send_sig(SIGTRAP, current, 0); + force_sig(SIGTRAP, current); } else { /* * Either we raced with uprobe_unregister() or we can't diff --git a/kernel/exit.c b/kernel/exit.c index d1baf9c96c3e..9e70577b818a 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -516,7 +516,10 @@ static void exit_mm(void) up_read(&mm->mmap_sem); self.task = current; - self.next = xchg(&core_state->dumper.next, &self); + if (self.task->flags & PF_SIGNALED) + self.next = xchg(&core_state->dumper.next, &self); + else + self.task = NULL; /* * Implies mb(), the result of xchg() must be visible * to core_state->dumper. @@ -770,8 +773,12 @@ void __noreturn do_exit(long code) struct task_struct *tsk = current; int group_dead; - profile_task_exit(tsk); - kcov_task_exit(tsk); + /* + * We can get here from a kernel oops, sometimes with preemption off. + * Start by checking for critical errors. + * Then fix up important state like USER_DS and preemption. + * Then do everything else. + */ WARN_ON(blk_needs_flush_plug(tsk)); @@ -789,6 +796,16 @@ void __noreturn do_exit(long code) */ set_fs(USER_DS); + if (unlikely(in_atomic())) { + pr_info("note: %s[%d] exited with preempt_count %d\n", + current->comm, task_pid_nr(current), + preempt_count()); + preempt_count_set(PREEMPT_ENABLED); + } + + profile_task_exit(tsk); + kcov_task_exit(tsk); + ptrace_event(PTRACE_EVENT_EXIT, code); validate_creds_for_do_exit(tsk); @@ -806,13 +823,6 @@ void __noreturn do_exit(long code) exit_signals(tsk); /* sets PF_EXITING */ - if (unlikely(in_atomic())) { - pr_info("note: %s[%d] exited with preempt_count %d\n", - current->comm, task_pid_nr(current), - preempt_count()); - preempt_count_set(PREEMPT_ENABLED); - } - /* sync mm's RSS info before statistics gathering */ if (tsk->mm) sync_mm_rss(tsk->mm); @@ -1597,10 +1607,9 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, if (!infop) return err; - if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop))) + if (!user_access_begin(VERIFY_WRITE, infop, sizeof(*infop))) return -EFAULT; - user_access_begin(); unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(info.cause, &infop->si_code, Efault); @@ -1725,10 +1734,9 @@ COMPAT_SYSCALL_DEFINE5(waitid, if (!infop) return err; - if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop))) + if (!user_access_begin(VERIFY_WRITE, infop, sizeof(*infop))) return -EFAULT; - user_access_begin(); unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(info.cause, &infop->si_code, Efault); diff --git a/kernel/fork.c b/kernel/fork.c index dc9ce1b3060b..28cdcf4b6888 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -837,6 +837,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); + hugetlb_count_init(mm); if (current->mm) { mm->flags = current->mm->flags & MMF_INIT_MASK; @@ -1544,6 +1545,25 @@ static __always_inline void delayed_free_task(struct task_struct *tsk) free_task(tsk); } +static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk) +{ + /* Skip if kernel thread */ + if (!tsk->mm) + return; + + /* Skip if spawning a thread or using vfork */ + if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM) + return; + + /* We need to synchronize with __set_oom_adj */ + mutex_lock(&oom_adj_mutex); + set_bit(MMF_MULTIPROCESS, &tsk->mm->flags); + /* Update the values in case they were changed after copy_signal */ + tsk->signal->oom_score_adj = current->signal->oom_score_adj; + tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min; + mutex_unlock(&oom_adj_mutex); +} + /* * This creates a new process as a copy of the old one, * but does not actually start it yet. @@ -1814,14 +1834,9 @@ static __latent_entropy struct task_struct *copy_process( /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { - p->exit_signal = -1; p->group_leader = current->group_leader; p->tgid = current->tgid; } else { - if (clone_flags & CLONE_PARENT) - p->exit_signal = current->group_leader->exit_signal; - else - p->exit_signal = (clone_flags & CSIGNAL); p->group_leader = p; p->tgid = p->pid; } @@ -1866,9 +1881,14 @@ static __latent_entropy struct task_struct *copy_process( if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; p->parent_exec_id = current->parent_exec_id; + if (clone_flags & CLONE_THREAD) + p->exit_signal = -1; + else + p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; + p->exit_signal = (clone_flags & CSIGNAL); } klp_copy_process(p); @@ -1952,6 +1972,8 @@ static __latent_entropy struct task_struct *copy_process( trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); + copy_oom_score_adj(clone_flags, p); + return p; bad_fork_cancel_cgroup: diff --git a/kernel/futex.c b/kernel/futex.c index 2921ebaa1467..e282c083df59 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -719,7 +719,7 @@ again: key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.i_seq = get_inode_sequence_number(inode); - key->shared.pgoff = basepage_index(tail); + key->shared.pgoff = page_to_pgoff(tail); rcu_read_unlock(); } @@ -839,6 +839,29 @@ static struct futex_pi_state *alloc_pi_state(void) return pi_state; } +static void pi_state_update_owner(struct futex_pi_state *pi_state, + struct task_struct *new_owner) +{ + struct task_struct *old_owner = pi_state->owner; + + lockdep_assert_held(&pi_state->pi_mutex.wait_lock); + + if (old_owner) { + raw_spin_lock(&old_owner->pi_lock); + WARN_ON(list_empty(&pi_state->list)); + list_del_init(&pi_state->list); + raw_spin_unlock(&old_owner->pi_lock); + } + + if (new_owner) { + raw_spin_lock(&new_owner->pi_lock); + WARN_ON(!list_empty(&pi_state->list)); + list_add(&pi_state->list, &new_owner->pi_state_list); + pi_state->owner = new_owner; + raw_spin_unlock(&new_owner->pi_lock); + } +} + static void get_pi_state(struct futex_pi_state *pi_state) { WARN_ON_ONCE(!atomic_inc_not_zero(&pi_state->refcount)); @@ -861,17 +884,12 @@ static void put_pi_state(struct futex_pi_state *pi_state) * and has cleaned up the pi_state already */ if (pi_state->owner) { - struct task_struct *owner; + unsigned long flags; - raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); - owner = pi_state->owner; - if (owner) { - raw_spin_lock(&owner->pi_lock); - list_del_init(&pi_state->list); - raw_spin_unlock(&owner->pi_lock); - } - rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner); - raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_lock_irqsave(&pi_state->pi_mutex.wait_lock, flags); + pi_state_update_owner(pi_state, NULL); + rt_mutex_proxy_unlock(&pi_state->pi_mutex); + raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags); } if (current->pi_state_cache) { @@ -1034,7 +1052,8 @@ static inline void exit_pi_state_list(struct task_struct *curr) { } * FUTEX_OWNER_DIED bit. See [4] * * [10] There is no transient state which leaves owner and user space - * TID out of sync. + * TID out of sync. Except one error case where the kernel is denied + * write access to the user address, see fixup_pi_state_owner(). * * * Serialization and lifetime rules: @@ -1595,8 +1614,10 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_ */ newval = FUTEX_WAITERS | task_pid_vnr(new_owner); - if (unlikely(should_fail_futex(true))) + if (unlikely(should_fail_futex(true))) { ret = -EFAULT; + goto out_unlock; + } ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval); if (!ret && (curval != uval)) { @@ -1612,26 +1633,15 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_ ret = -EINVAL; } - if (ret) - goto out_unlock; - - /* - * This is a point of no return; once we modify the uval there is no - * going back and subsequent operations must not fail. - */ - - raw_spin_lock(&pi_state->owner->pi_lock); - WARN_ON(list_empty(&pi_state->list)); - list_del_init(&pi_state->list); - raw_spin_unlock(&pi_state->owner->pi_lock); - - raw_spin_lock(&new_owner->pi_lock); - WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &new_owner->pi_state_list); - pi_state->owner = new_owner; - raw_spin_unlock(&new_owner->pi_lock); - - postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); + if (!ret) { + /* + * This is a point of no return; once we modified the uval + * there is no going back and subsequent operations must + * not fail. + */ + pi_state_update_owner(pi_state, new_owner); + postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); + } out_unlock: raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); @@ -1722,8 +1732,8 @@ static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr) { unsigned int op = (encoded_op & 0x70000000) >> 28; unsigned int cmp = (encoded_op & 0x0f000000) >> 24; - int oparg = sign_extend32((encoded_op & 0x00fff000) >> 12, 12); - int cmparg = sign_extend32(encoded_op & 0x00000fff, 12); + int oparg = sign_extend32((encoded_op & 0x00fff000) >> 12, 11); + int cmparg = sign_extend32(encoded_op & 0x00000fff, 11); int oldval, ret; if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) { @@ -2454,18 +2464,13 @@ static void unqueue_me_pi(struct futex_q *q) spin_unlock(q->lock_ptr); } -static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, - struct task_struct *argowner) +static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, + struct task_struct *argowner) { + u32 uval, uninitialized_var(curval), newval, newtid; struct futex_pi_state *pi_state = q->pi_state; - u32 uval, uninitialized_var(curval), newval; struct task_struct *oldowner, *newowner; - u32 newtid; - int ret, err = 0; - - lockdep_assert_held(q->lock_ptr); - - raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + int err = 0; oldowner = pi_state->owner; @@ -2499,21 +2504,31 @@ retry: * We raced against a concurrent self; things are * already fixed up. Nothing to do. */ - ret = 0; - goto out_unlock; + return 0; } if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) { - /* We got the lock after all, nothing to fix. */ - ret = 0; - goto out_unlock; + /* We got the lock. pi_state is correct. Tell caller. */ + return 1; } /* - * Since we just failed the trylock; there must be an owner. + * The trylock just failed, so either there is an owner or + * there is a higher priority waiter than this one. */ newowner = rt_mutex_owner(&pi_state->pi_mutex); - BUG_ON(!newowner); + /* + * If the higher priority waiter has not yet taken over the + * rtmutex then newowner is NULL. We can't return here with + * that state because it's inconsistent vs. the user space + * state. So drop the locks and try again. It's a valid + * situation and not any different from the other retry + * conditions. + */ + if (unlikely(!newowner)) { + err = -EAGAIN; + goto handle_err; + } } else { WARN_ON_ONCE(argowner != current); if (oldowner == current) { @@ -2521,8 +2536,7 @@ retry: * We raced against a concurrent self; things are * already fixed up. Nothing to do. */ - ret = 0; - goto out_unlock; + return 1; } newowner = argowner; } @@ -2552,22 +2566,9 @@ retry: * We fixed up user space. Now we need to fix the pi_state * itself. */ - if (pi_state->owner != NULL) { - raw_spin_lock(&pi_state->owner->pi_lock); - WARN_ON(list_empty(&pi_state->list)); - list_del_init(&pi_state->list); - raw_spin_unlock(&pi_state->owner->pi_lock); - } + pi_state_update_owner(pi_state, newowner); - pi_state->owner = newowner; - - raw_spin_lock(&newowner->pi_lock); - WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &newowner->pi_state_list); - raw_spin_unlock(&newowner->pi_lock); - raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); - - return 0; + return argowner == current; /* * In order to reschedule or handle a page fault, we need to drop the @@ -2588,17 +2589,16 @@ handle_err: switch (err) { case -EFAULT: - ret = fault_in_user_writeable(uaddr); + err = fault_in_user_writeable(uaddr); break; case -EAGAIN: cond_resched(); - ret = 0; + err = 0; break; default: WARN_ON_ONCE(1); - ret = err; break; } @@ -2608,17 +2608,44 @@ handle_err: /* * Check if someone else fixed it for us: */ - if (pi_state->owner != oldowner) { - ret = 0; - goto out_unlock; - } + if (pi_state->owner != oldowner) + return argowner == current; - if (ret) - goto out_unlock; + /* Retry if err was -EAGAIN or the fault in succeeded */ + if (!err) + goto retry; - goto retry; + /* + * fault_in_user_writeable() failed so user state is immutable. At + * best we can make the kernel state consistent but user state will + * be most likely hosed and any subsequent unlock operation will be + * rejected due to PI futex rule [10]. + * + * Ensure that the rtmutex owner is also the pi_state owner despite + * the user space value claiming something different. There is no + * point in unlocking the rtmutex if current is the owner as it + * would need to wait until the next waiter has taken the rtmutex + * to guarantee consistent state. Keep it simple. Userspace asked + * for this wreckaged state. + * + * The rtmutex has an owner - either current or some other + * task. See the EAGAIN loop above. + */ + pi_state_update_owner(pi_state, rt_mutex_owner(&pi_state->pi_mutex)); -out_unlock: + return err; +} + +static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, + struct task_struct *argowner) +{ + struct futex_pi_state *pi_state = q->pi_state; + int ret; + + lockdep_assert_held(q->lock_ptr); + + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + ret = __fixup_pi_state_owner(uaddr, q, argowner); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); return ret; } @@ -2642,8 +2669,6 @@ static long futex_wait_restart(struct restart_block *restart); */ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) { - int ret = 0; - if (locked) { /* * Got the lock. We might not be the anticipated owner if we @@ -2654,8 +2679,8 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) * stable state, anything else needs more attention. */ if (q->pi_state->owner != current) - ret = fixup_pi_state_owner(uaddr, q, current); - goto out; + return fixup_pi_state_owner(uaddr, q, current); + return 1; } /* @@ -2666,24 +2691,17 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) * Another speculative read; pi_state->owner == current is unstable * but needs our attention. */ - if (q->pi_state->owner == current) { - ret = fixup_pi_state_owner(uaddr, q, NULL); - goto out; - } + if (q->pi_state->owner == current) + return fixup_pi_state_owner(uaddr, q, NULL); /* * Paranoia check. If we did not take the lock, then we should not be - * the owner of the rt_mutex. + * the owner of the rt_mutex. Warn and establish consistent state. */ - if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) { - printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p " - "pi-state %p\n", ret, - q->pi_state->pi_mutex.owner, - q->pi_state->owner); - } + if (WARN_ON_ONCE(rt_mutex_owner(&q->pi_state->pi_mutex) == current)) + return fixup_pi_state_owner(uaddr, q, current); -out: - return ret ? ret : locked; + return 0; } /** @@ -2857,14 +2875,13 @@ retry: goto out; restart = ¤t->restart_block; - restart->fn = futex_wait_restart; restart->futex.uaddr = uaddr; restart->futex.val = val; restart->futex.time = *abs_time; restart->futex.bitset = bitset; restart->futex.flags = flags | FLAGS_HAS_TIMEOUT; - ret = -ERESTART_RESTARTBLOCK; + ret = set_restart_fn(restart, futex_wait_restart); out: if (to) { @@ -2904,7 +2921,6 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock) { struct hrtimer_sleeper timeout, *to = NULL; - struct futex_pi_state *pi_state = NULL; struct task_struct *exiting = NULL; struct rt_mutex_waiter rt_waiter; struct futex_hash_bucket *hb; @@ -3047,23 +3063,9 @@ no_block: if (res) ret = (res < 0) ? res : 0; - /* - * If fixup_owner() faulted and was unable to handle the fault, unlock - * it and return the fault to userspace. - */ - if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current)) { - pi_state = q.pi_state; - get_pi_state(pi_state); - } - /* Unqueue and drop the lock */ unqueue_me_pi(&q); - if (pi_state) { - rt_mutex_futex_unlock(&pi_state->pi_mutex); - put_pi_state(pi_state); - } - goto out_put_key; out_unlock_put_key: @@ -3329,7 +3331,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32 __user *uaddr2) { struct hrtimer_sleeper timeout, *to = NULL; - struct futex_pi_state *pi_state = NULL; struct rt_mutex_waiter rt_waiter; struct futex_hash_bucket *hb; union futex_key key2 = FUTEX_KEY_INIT; @@ -3414,16 +3415,17 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (q.pi_state && (q.pi_state->owner != current)) { spin_lock(q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); - if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) { - pi_state = q.pi_state; - get_pi_state(pi_state); - } /* * Drop the reference to the pi state which * the requeue_pi() code acquired for us. */ put_pi_state(q.pi_state); spin_unlock(q.lock_ptr); + /* + * Adjust the return value. It's either -EFAULT or + * success (1) but the caller expects 0 for success. + */ + ret = ret < 0 ? ret : 0; } } else { struct rt_mutex *pi_mutex; @@ -3454,25 +3456,10 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (res) ret = (res < 0) ? res : 0; - /* - * If fixup_pi_state_owner() faulted and was unable to handle - * the fault, unlock the rt_mutex and return the fault to - * userspace. - */ - if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) { - pi_state = q.pi_state; - get_pi_state(pi_state); - } - /* Unqueue and drop the lock. */ unqueue_me_pi(&q); } - if (pi_state) { - rt_mutex_futex_unlock(&pi_state->pi_mutex); - put_pi_state(pi_state); - } - if (ret == -EINTR) { /* * We've already been requeued, but cannot restart by calling @@ -3898,8 +3885,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, if (op & FUTEX_CLOCK_REALTIME) { flags |= FLAGS_CLOCKRT; - if (cmd != FUTEX_WAIT && cmd != FUTEX_WAIT_BITSET && \ - cmd != FUTEX_WAIT_REQUEUE_PI) + if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI) return -ENOSYS; } diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c index 6e40ff6be083..291e0797125b 100644 --- a/kernel/gcov/fs.c +++ b/kernel/gcov/fs.c @@ -109,9 +109,9 @@ static void *gcov_seq_next(struct seq_file *seq, void *data, loff_t *pos) { struct gcov_iterator *iter = data; + (*pos)++; if (gcov_iter_next(iter)) return NULL; - (*pos)++; return iter; } diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index ca5e5c0ef853..5b9e76117ded 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -19,7 +19,9 @@ #include <linux/vmalloc.h> #include "gcov.h" -#if (__GNUC__ >= 7) +#if (__GNUC__ >= 10) +#define GCOV_COUNTERS 8 +#elif (__GNUC__ >= 7) #define GCOV_COUNTERS 9 #elif (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1) #define GCOV_COUNTERS 10 diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index a117adf7084b..779d858da2b3 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -80,6 +80,7 @@ config IRQ_FASTEOI_HIERARCHY_HANDLERS # Generic IRQ IPI support config GENERIC_IRQ_IPI bool + select IRQ_DOMAIN_HIERARCHY # Generic MSI interrupt support config GENERIC_MSI_IRQ diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index b269ae16b10c..cafea68749e0 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1364,14 +1364,26 @@ static void irq_domain_free_irqs_hierarchy(struct irq_domain *domain, unsigned int irq_base, unsigned int nr_irqs) { - if (domain->ops->free) - domain->ops->free(domain, irq_base, nr_irqs); + unsigned int i; + + if (!domain->ops->free) + return; + + for (i = 0; i < nr_irqs; i++) { + if (irq_domain_get_irq_data(domain, irq_base + i)) + domain->ops->free(domain, irq_base + i, 1); + } } int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain, unsigned int irq_base, unsigned int nr_irqs, void *arg) { + if (!domain->ops->alloc) { + pr_debug("domain->ops->alloc() is NULL\n"); + return -ENOSYS; + } + return domain->ops->alloc(domain, irq_base, nr_irqs, arg); } @@ -1409,11 +1421,6 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, return -EINVAL; } - if (!domain->ops->alloc) { - pr_debug("domain->ops->alloc() is NULL\n"); - return -ENOSYS; - } - if (realloc && irq_base >= 0) { virq = irq_base; } else { diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 5277949e82e0..914b43f2255b 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -168,9 +168,9 @@ void irq_set_thread_affinity(struct irq_desc *desc) set_bit(IRQTF_AFFINITY, &action->thread_flags); } +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK static void irq_validate_effective_affinity(struct irq_data *data) { -#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK const struct cpumask *m = irq_data_get_effective_affinity_mask(data); struct irq_chip *chip = irq_data_get_irq_chip(data); @@ -178,9 +178,19 @@ static void irq_validate_effective_affinity(struct irq_data *data) return; pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n", chip->name, data->irq); -#endif } +static inline void irq_init_effective_affinity(struct irq_data *data, + const struct cpumask *mask) +{ + cpumask_copy(irq_data_get_effective_affinity_mask(data), mask); +} +#else +static inline void irq_validate_effective_affinity(struct irq_data *data) { } +static inline void irq_init_effective_affinity(struct irq_data *data, + const struct cpumask *mask) { } +#endif + int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -205,6 +215,30 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, return ret; } +static bool irq_set_affinity_deactivated(struct irq_data *data, + const struct cpumask *mask, bool force) +{ + struct irq_desc *desc = irq_data_to_desc(data); + + /* + * Handle irq chips which can handle affinity only in activated + * state correctly + * + * If the interrupt is not yet activated, just store the affinity + * mask and do not call the chip driver at all. On activation the + * driver has to make sure anyway that the interrupt is in a + * useable state so startup works. + */ + if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) || + irqd_is_activated(data) || !irqd_affinity_on_activate(data)) + return false; + + cpumask_copy(desc->irq_common_data.affinity, mask); + irq_init_effective_affinity(data, mask); + irqd_set(data, IRQD_AFFINITY_SET); + return true; +} + int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -215,6 +249,9 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, if (!chip || !chip->irq_set_affinity) return -EINVAL; + if (irq_set_affinity_deactivated(data, mask, force)) + return 0; + if (irq_can_move_pcntxt(data)) { ret = irq_do_set_affinity(data, mask, force); } else { @@ -879,11 +916,15 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) irqreturn_t ret; local_bh_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) + local_irq_disable(); ret = action->thread_fn(action->irq, action->dev_id); if (ret == IRQ_HANDLED) atomic_inc(&desc->threads_handled); irq_finalize_oneshot(desc, action); + if (!IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) + local_irq_enable(); local_bh_enable(); return ret; } diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index 86ae0eb80b53..8b8cecd18cce 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -38,17 +38,18 @@ bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear) void irq_move_masked_irq(struct irq_data *idata) { struct irq_desc *desc = irq_data_to_desc(idata); - struct irq_chip *chip = desc->irq_data.chip; + struct irq_data *data = &desc->irq_data; + struct irq_chip *chip = data->chip; - if (likely(!irqd_is_setaffinity_pending(&desc->irq_data))) + if (likely(!irqd_is_setaffinity_pending(data))) return; - irqd_clr_move_pending(&desc->irq_data); + irqd_clr_move_pending(data); /* * Paranoia: cpu-local interrupts shouldn't be calling in here anyway. */ - if (irqd_is_per_cpu(&desc->irq_data)) { + if (irqd_is_per_cpu(data)) { WARN_ON(1); return; } @@ -73,9 +74,20 @@ void irq_move_masked_irq(struct irq_data *idata) * For correct operation this depends on the caller * masking the irqs. */ - if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) - irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false); - + if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) { + int ret; + + ret = irq_do_set_affinity(data, desc->pending_mask, false); + /* + * If the there is a cleanup pending in the underlying + * vector management, reschedule the move for the next + * interrupt. Leave desc->pending_mask intact. + */ + if (ret == -EBUSY) { + irqd_set_move_pending(data); + return; + } + } cpumask_clear(desc->pending_mask); } diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 9f48f4412297..9d979b2954ef 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -95,6 +95,11 @@ void kimage_file_post_load_cleanup(struct kimage *image) vfree(pi->sechdrs); pi->sechdrs = NULL; +#ifdef CONFIG_IMA_KEXEC + vfree(image->ima_buffer); + image->ima_buffer = NULL; +#endif /* CONFIG_IMA_KEXEC */ + /* See if architecture has anything to cleanup post load */ arch_kimage_file_post_load_cleanup(image); @@ -549,8 +554,10 @@ static int kexec_calculate_store_digests(struct kimage *image) sha_region_sz = KEXEC_SEGMENT_MAX * sizeof(struct kexec_sha_region); sha_regions = vzalloc(sha_region_sz); - if (!sha_regions) + if (!sha_regions) { + ret = -ENOMEM; goto out_free_desc; + } desc->tfm = tfm; desc->flags = 0; diff --git a/kernel/kmod.c b/kernel/kmod.c index bc6addd9152b..a2de58de6ab6 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -120,7 +120,7 @@ out: * invoke it. * * If module auto-loading support is disabled then this function - * becomes a no-operation. + * simply returns -ENOENT. */ int __request_module(bool wait, const char *fmt, ...) { @@ -137,7 +137,7 @@ int __request_module(bool wait, const char *fmt, ...) WARN_ON_ONCE(wait && current_is_async()); if (!modprobe_path[0]) - return 0; + return -ENOENT; va_start(args, fmt); ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 66f1818d4762..4f918dd28fb7 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -599,11 +599,12 @@ static void kprobe_optimizer(struct work_struct *work) mutex_unlock(&module_mutex); mutex_unlock(&text_mutex); cpus_read_unlock(); - mutex_unlock(&kprobe_mutex); /* Step 5: Kick optimizer again if needed */ if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) kick_kprobe_optimizer(); + + mutex_unlock(&kprobe_mutex); } /* Wait for completing optimization and unoptimization */ @@ -1217,6 +1218,26 @@ __releases(hlist_lock) } NOKPROBE_SYMBOL(kretprobe_table_unlock); +struct kprobe kprobe_busy = { + .addr = (void *) get_kprobe, +}; + +void kprobe_busy_begin(void) +{ + struct kprobe_ctlblk *kcb; + + preempt_disable(); + __this_cpu_write(current_kprobe, &kprobe_busy); + kcb = get_kprobe_ctlblk(); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; +} + +void kprobe_busy_end(void) +{ + __this_cpu_write(current_kprobe, NULL); + preempt_enable(); +} + /* * This function is called from finish_task_switch when task tk becomes dead, * so that we can recycle any function-return probe instances associated @@ -1234,6 +1255,8 @@ void kprobe_flush_task(struct task_struct *tk) /* Early boot. kretprobe_table_locks not yet initialized. */ return; + kprobe_busy_begin(); + INIT_HLIST_HEAD(&empty_rp); hash = hash_ptr(tk, KPROBE_HASH_BITS); head = &kretprobe_inst_table[hash]; @@ -1247,6 +1270,8 @@ void kprobe_flush_task(struct task_struct *tk) hlist_del(&ri->hlist); kfree(ri); } + + kprobe_busy_end(); } NOKPROBE_SYMBOL(kprobe_flush_task); @@ -1964,6 +1989,10 @@ int register_kretprobe(struct kretprobe *rp) if (!kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset)) return -EINVAL; + /* If only rp->kp.addr is specified, check reregistering kprobes */ + if (rp->kp.addr && check_kprobe_rereg(&rp->kp)) + return -EINVAL; + if (kretprobe_blacklist_size) { addr = kprobe_addr(&rp->kp); if (IS_ERR(addr)) @@ -1975,6 +2004,9 @@ 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; rp->kp.fault_handler = NULL; @@ -2092,6 +2124,9 @@ static void kill_kprobe(struct kprobe *p) { struct kprobe *kp; + if (WARN_ON_ONCE(kprobe_gone(p))) + return; + p->flags |= KPROBE_FLAG_GONE; if (kprobe_aggrprobe(p)) { /* @@ -2109,6 +2144,14 @@ static void kill_kprobe(struct kprobe *p) * the original probed function (which will be freed soon) any more. */ arch_remove_kprobe(p); + + /* + * The module is going away. We should disarm the kprobe which + * is using ftrace, because ftrace framework is still available at + * MODULE_STATE_GOING notification. + */ + if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed) + disarm_kprobe_ftrace(p); } /* Disable one kprobe */ @@ -2227,7 +2270,10 @@ static int kprobes_module_callback(struct notifier_block *nb, mutex_lock(&kprobe_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; - hlist_for_each_entry_rcu(p, head, hlist) + hlist_for_each_entry_rcu(p, head, hlist) { + if (kprobe_gone(p)) + continue; + if (within_module_init((unsigned long)p->addr, mod) || (checkcore && within_module_core((unsigned long)p->addr, mod))) { @@ -2244,6 +2290,7 @@ static int kprobes_module_callback(struct notifier_block *nb, */ kill_kprobe(p); } + } } mutex_unlock(&kprobe_mutex); return NOTIFY_DONE; diff --git a/kernel/kthread.c b/kernel/kthread.c index 4e6d85b63201..7dd2c8a797d7 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -433,11 +433,36 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), return p; kthread_bind(p, cpu); /* CPU hotplug need to bind once again when unparking the thread. */ - set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags); to_kthread(p)->cpu = cpu; return p; } +void kthread_set_per_cpu(struct task_struct *k, int cpu) +{ + struct kthread *kthread = to_kthread(k); + if (!kthread) + return; + + WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY)); + + if (cpu < 0) { + clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags); + return; + } + + kthread->cpu = cpu; + set_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} + +bool kthread_is_per_cpu(struct task_struct *k) +{ + struct kthread *kthread = to_kthread(k); + if (!kthread) + return false; + + return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} + /** * kthread_unpark - unpark a thread created by kthread_create(). * @k: thread created by kthread_create(). @@ -831,7 +856,8 @@ void kthread_delayed_work_timer_fn(unsigned long __data) /* Move the work from worker->delayed_work_list. */ WARN_ON_ONCE(list_empty(&work->node)); list_del_init(&work->node); - kthread_insert_work(worker, work, &worker->work_list); + if (!work->canceling) + kthread_insert_work(worker, work, &worker->work_list); spin_unlock(&worker->lock); } @@ -953,8 +979,38 @@ void kthread_flush_work(struct kthread_work *work) EXPORT_SYMBOL_GPL(kthread_flush_work); /* - * This function removes the work from the worker queue. Also it makes sure - * that it won't get queued later via the delayed work's timer. + * Make sure that the timer is neither set nor running and could + * not manipulate the work list_head any longer. + * + * The function is called under worker->lock. The lock is temporary + * released but the timer can't be set again in the meantime. + */ +static void kthread_cancel_delayed_work_timer(struct kthread_work *work, + unsigned long *flags) +{ + struct kthread_delayed_work *dwork = + container_of(work, struct kthread_delayed_work, work); + struct kthread_worker *worker = work->worker; + + /* + * del_timer_sync() must be called to make sure that the timer + * callback is not running. The lock must be temporary released + * to avoid a deadlock with the callback. In the meantime, + * any queuing is blocked by setting the canceling counter. + */ + work->canceling++; + spin_unlock_irqrestore(&worker->lock, *flags); + del_timer_sync(&dwork->timer); + spin_lock_irqsave(&worker->lock, *flags); + work->canceling--; +} + +/* + * This function removes the work from the worker queue. + * + * It is called under worker->lock. The caller must make sure that + * the timer used by delayed work is not running, e.g. by calling + * kthread_cancel_delayed_work_timer(). * * The work might still be in use when this function finishes. See the * current_work proceed by the worker. @@ -962,28 +1018,8 @@ EXPORT_SYMBOL_GPL(kthread_flush_work); * Return: %true if @work was pending and successfully canceled, * %false if @work was not pending */ -static bool __kthread_cancel_work(struct kthread_work *work, bool is_dwork, - unsigned long *flags) +static bool __kthread_cancel_work(struct kthread_work *work) { - /* Try to cancel the timer if exists. */ - if (is_dwork) { - struct kthread_delayed_work *dwork = - container_of(work, struct kthread_delayed_work, work); - struct kthread_worker *worker = work->worker; - - /* - * del_timer_sync() must be called to make sure that the timer - * callback is not running. The lock must be temporary released - * to avoid a deadlock with the callback. In the meantime, - * any queuing is blocked by setting the canceling counter. - */ - work->canceling++; - spin_unlock_irqrestore(&worker->lock, *flags); - del_timer_sync(&dwork->timer); - spin_lock_irqsave(&worker->lock, *flags); - work->canceling--; - } - /* * Try to remove the work from a worker list. It might either * be from worker->work_list or from worker->delayed_work_list. @@ -1036,11 +1072,23 @@ bool kthread_mod_delayed_work(struct kthread_worker *worker, /* Work must not be used with >1 worker, see kthread_queue_work() */ WARN_ON_ONCE(work->worker != worker); - /* Do not fight with another command that is canceling this work. */ + /* + * Temporary cancel the work but do not fight with another command + * that is canceling the work as well. + * + * It is a bit tricky because of possible races with another + * mod_delayed_work() and cancel_delayed_work() callers. + * + * The timer must be canceled first because worker->lock is released + * when doing so. But the work can be removed from the queue (list) + * only when it can be queued again so that the return value can + * be used for reference counting. + */ + kthread_cancel_delayed_work_timer(work, &flags); if (work->canceling) goto out; + ret = __kthread_cancel_work(work); - ret = __kthread_cancel_work(work, true, &flags); fast_queue: __kthread_queue_delayed_work(worker, dwork, delay); out: @@ -1062,7 +1110,10 @@ static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork) /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); - ret = __kthread_cancel_work(work, is_dwork, &flags); + if (is_dwork) + kthread_cancel_delayed_work_timer(work, &flags); + + ret = __kthread_cancel_work(work); if (worker->current_work != work) goto out_fast; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 90a3469a7a88..ac0725b1ada7 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -713,7 +713,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return NULL; - hlist_for_each_entry_rcu(class, hash_head, hash_entry) { + hlist_for_each_entry_rcu_notrace(class, hash_head, hash_entry) { if (class->key == key) { /* * Huh! same key, different name? Did someone trample @@ -1297,9 +1297,11 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class) this.class = class; raw_local_irq_save(flags); + current->lockdep_recursion = 1; arch_spin_lock(&lockdep_lock); ret = __lockdep_count_forward_deps(&this); arch_spin_unlock(&lockdep_lock); + current->lockdep_recursion = 0; raw_local_irq_restore(flags); return ret; @@ -1324,9 +1326,11 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class) this.class = class; raw_local_irq_save(flags); + current->lockdep_recursion = 1; arch_spin_lock(&lockdep_lock); ret = __lockdep_count_backward_deps(&this); arch_spin_unlock(&lockdep_lock); + current->lockdep_recursion = 0; raw_local_irq_restore(flags); return ret; diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index 8b2ef15e3552..06c02cd0ff57 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -430,7 +430,7 @@ static void seq_lock_time(struct seq_file *m, struct lock_time *lt) seq_time(m, lt->min); seq_time(m, lt->max); seq_time(m, lt->total); - seq_time(m, lt->nr ? div_s64(lt->total, lt->nr) : 0); + seq_time(m, lt->nr ? div64_u64(lt->total, lt->nr) : 0); } static void seq_stats(struct seq_file *m, struct lock_stat_data *data) diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 6dca260eeccf..032868be3259 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -723,10 +723,10 @@ static void __torture_print_stats(char *page, if (statp[i].n_lock_fail) fail = true; sum += statp[i].n_lock_acquired; - if (max < statp[i].n_lock_fail) - max = statp[i].n_lock_fail; - if (min > statp[i].n_lock_fail) - min = statp[i].n_lock_fail; + if (max < statp[i].n_lock_acquired) + max = statp[i].n_lock_acquired; + if (min > statp[i].n_lock_acquired) + min = statp[i].n_lock_acquired; } page += sprintf(page, "%s: Total: %lld Max/Min: %ld/%ld %s Fail: %d %s\n", diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 71c554a9e17f..ed1d8959e714 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1719,8 +1719,7 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock, * possible because it belongs to the pi_state which is about to be freed * and it is not longer visible to other tasks. */ -void rt_mutex_proxy_unlock(struct rt_mutex *lock, - struct task_struct *proxy_owner) +void rt_mutex_proxy_unlock(struct rt_mutex *lock) { debug_rt_mutex_proxy_unlock(lock); rt_mutex_set_owner(lock, NULL); diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index 68686b3ec3c1..4d27cb0d9d8a 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -132,8 +132,7 @@ enum rtmutex_chainwalk { extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner); -extern void rt_mutex_proxy_unlock(struct rt_mutex *lock, - struct task_struct *proxy_owner); +extern void rt_mutex_proxy_unlock(struct rt_mutex *lock); extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, diff --git a/kernel/module.c b/kernel/module.c index 2806c9b6577c..e96209667263 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -430,7 +430,7 @@ static bool each_symbol_in_section(const struct symsearch *arr, } /* Returns true as soon as fn returns true, otherwise false. */ -bool each_symbol_section(bool (*fn)(const struct symsearch *arr, +static bool each_symbol_section(bool (*fn)(const struct symsearch *arr, struct module *owner, void *data), void *data) @@ -491,7 +491,6 @@ bool each_symbol_section(bool (*fn)(const struct symsearch *arr, } return false; } -EXPORT_SYMBOL_GPL(each_symbol_section); struct find_symbol_arg { /* Input */ @@ -503,6 +502,7 @@ struct find_symbol_arg { struct module *owner; const s32 *crc; const struct kernel_symbol *sym; + enum mod_license license; }; static bool check_symbol(const struct symsearch *syms, @@ -512,9 +512,9 @@ static bool check_symbol(const struct symsearch *syms, struct find_symbol_arg *fsa = data; if (!fsa->gplok) { - if (syms->licence == GPL_ONLY) + if (syms->license == GPL_ONLY) return false; - if (syms->licence == WILL_BE_GPL_ONLY && fsa->warn) { + if (syms->license == WILL_BE_GPL_ONLY && fsa->warn) { pr_warn("Symbol %s is being used by a non-GPL module, " "which will not be allowed in the future\n", fsa->name); @@ -536,6 +536,7 @@ static bool check_symbol(const struct symsearch *syms, fsa->owner = owner; fsa->crc = symversion(syms->crcs, symnum); fsa->sym = &syms->start[symnum]; + fsa->license = syms->license; return true; } @@ -565,9 +566,10 @@ static bool find_symbol_in_section(const struct symsearch *syms, /* Find a symbol and return it, along with, (optional) crc and * (optional) module which owns it. Needs preempt disabled or module_mutex. */ -const struct kernel_symbol *find_symbol(const char *name, +static const struct kernel_symbol *find_symbol(const char *name, struct module **owner, const s32 **crc, + enum mod_license *license, bool gplok, bool warn) { @@ -582,13 +584,14 @@ const struct kernel_symbol *find_symbol(const char *name, *owner = fsa.owner; if (crc) *crc = fsa.crc; + if (license) + *license = fsa.license; return fsa.sym; } pr_debug("Failed to find symbol %s\n", name); return NULL; } -EXPORT_SYMBOL_GPL(find_symbol); /* * Search for module by name: must hold module_mutex (or preempt disabled @@ -850,7 +853,7 @@ static int add_module_usage(struct module *a, struct module *b) } /* Module a uses b: caller needs module_mutex() */ -int ref_module(struct module *a, struct module *b) +static int ref_module(struct module *a, struct module *b) { int err; @@ -869,7 +872,6 @@ int ref_module(struct module *a, struct module *b) } return 0; } -EXPORT_SYMBOL_GPL(ref_module); /* Clear the unload stuff of the module. */ static void module_unload_free(struct module *mod) @@ -1058,7 +1060,7 @@ void __symbol_put(const char *symbol) struct module *owner; preempt_disable(); - if (!find_symbol(symbol, &owner, NULL, true, false)) + if (!find_symbol(symbol, &owner, NULL, NULL, true, false)) BUG(); module_put(owner); preempt_enable(); @@ -1150,11 +1152,10 @@ static inline void module_unload_free(struct module *mod) { } -int ref_module(struct module *a, struct module *b) +static int ref_module(struct module *a, struct module *b) { return strong_try_module_get(b); } -EXPORT_SYMBOL_GPL(ref_module); static inline int module_unload_init(struct module *mod) { @@ -1338,7 +1339,7 @@ static inline int check_modstruct_version(const struct load_info *info, */ preempt_disable(); if (!find_symbol(VMLINUX_SYMBOL_STR(module_layout), NULL, - &crc, true, false)) { + &crc, NULL, true, false)) { preempt_enable(); BUG(); } @@ -1379,6 +1380,25 @@ static inline int same_magic(const char *amagic, const char *bmagic, } #endif /* CONFIG_MODVERSIONS */ +static bool inherit_taint(struct module *mod, struct module *owner) +{ + if (!owner || !test_bit(TAINT_PROPRIETARY_MODULE, &owner->taints)) + return true; + + if (mod->using_gplonly_symbols) { + pr_err("%s: module using GPL-only symbols uses symbols from proprietary module %s.\n", + mod->name, owner->name); + return false; + } + + if (!test_bit(TAINT_PROPRIETARY_MODULE, &mod->taints)) { + pr_warn("%s: module uses symbols from proprietary module %s, inheriting taint.\n", + mod->name, owner->name); + set_bit(TAINT_PROPRIETARY_MODULE, &mod->taints); + } + return true; +} + /* Resolve a symbol for this module. I.e. if we find one, record usage. */ static const struct kernel_symbol *resolve_symbol(struct module *mod, const struct load_info *info, @@ -1388,6 +1408,7 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod, struct module *owner; const struct kernel_symbol *sym; const s32 *crc; + enum mod_license license; int err; /* @@ -1397,11 +1418,19 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod, */ sched_annotate_sleep(); mutex_lock(&module_mutex); - sym = find_symbol(name, &owner, &crc, + sym = find_symbol(name, &owner, &crc, &license, !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true); if (!sym) goto unlock; + if (license == GPL_ONLY) + mod->using_gplonly_symbols = true; + + if (!inherit_taint(mod, owner)) { + sym = NULL; + goto getname; + } + if (!check_version(info, name, mod, crc)) { sym = ERR_PTR(-EINVAL); goto getname; @@ -1789,7 +1818,6 @@ static int mod_sysfs_init(struct module *mod) if (err) mod_kobject_put(mod); - /* delay uevent until full sysfs population */ out: return err; } @@ -1826,7 +1854,6 @@ static int mod_sysfs_setup(struct module *mod, add_sect_attrs(mod, info); add_notes_attrs(mod, info); - kobject_uevent(&mod->mkobj.kobj, KOBJ_ADD); return 0; out_unreg_modinfo_attrs: @@ -2203,7 +2230,7 @@ void *__symbol_get(const char *symbol) const struct kernel_symbol *sym; preempt_disable(); - sym = find_symbol(symbol, &owner, NULL, true, true); + sym = find_symbol(symbol, &owner, NULL, NULL, true, true); if (sym && strong_try_module_get(owner)) sym = NULL; preempt_enable(); @@ -2238,7 +2265,7 @@ static int verify_export_symbols(struct module *mod) for (i = 0; i < ARRAY_SIZE(arr); i++) { for (s = arr[i].sym; s < arr[i].sym + arr[i].num; s++) { - if (find_symbol(s->name, &owner, NULL, true, false)) { + if (find_symbol(s->name, &owner, NULL, NULL, true, false)) { pr_err("%s: exports duplicate symbol %s" " (owned by %s)\n", mod->name, s->name, module_name(owner)); @@ -2249,6 +2276,21 @@ static int verify_export_symbols(struct module *mod) return 0; } +static bool ignore_undef_symbol(Elf_Half emachine, const char *name) +{ + /* + * On x86, PIC code and Clang non-PIC code may have call foo@PLT. GNU as + * before 2.37 produces an unreferenced _GLOBAL_OFFSET_TABLE_ on x86-64. + * i386 has a similar problem but may not deserve a fix. + * + * If we ever have to ignore many symbols, consider refactoring the code to + * only warn if referenced by a relocation. + */ + if (emachine == EM_386 || emachine == EM_X86_64) + return !strcmp(name, "_GLOBAL_OFFSET_TABLE_"); + return false; +} + /* Change all symbols so that st_value encodes the pointer directly. */ static int simplify_symbols(struct module *mod, const struct load_info *info) { @@ -2294,8 +2336,10 @@ static int simplify_symbols(struct module *mod, const struct load_info *info) break; } - /* Ok if weak. */ - if (!ksym && ELF_ST_BIND(sym[i].st_info) == STB_WEAK) + /* Ok if weak or ignored. */ + if (!ksym && + (ELF_ST_BIND(sym[i].st_info) == STB_WEAK || + ignore_undef_symbol(info->hdr->e_machine, name))) break; pr_warn("%s: Unknown symbol %s (err %li)\n", @@ -3481,6 +3525,9 @@ static noinline int do_init_module(struct module *mod) blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_LIVE, mod); + /* Delay uevent until module has finished its init routine */ + kobject_uevent(&mod->mkobj.kobj, KOBJ_ADD); + /* * We need to finish all async code before the module init sequence * is done. This has potential to deadlock. For example, a newly @@ -3801,6 +3848,7 @@ static int load_module(struct load_info *info, const char __user *uargs, MODULE_STATE_GOING, mod); klp_module_going(mod); bug_cleanup: + mod->state = MODULE_STATE_GOING; /* module_bug_cleanup needs module_mutex protection */ mutex_lock(&module_mutex); module_bug_cleanup(mod); @@ -4309,7 +4357,6 @@ struct module *__module_address(unsigned long addr) } return mod; } -EXPORT_SYMBOL_GPL(__module_address); /* * is_module_text_address - is this address inside module code? @@ -4348,7 +4395,6 @@ struct module *__module_text_address(unsigned long addr) } return mod; } -EXPORT_SYMBOL_GPL(__module_text_address); /* Don't grab lock, we're oopsing. */ void print_modules(void) diff --git a/kernel/padata.c b/kernel/padata.c index a71620d2b8ba..f56ec63f60ba 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -133,6 +133,7 @@ int padata_do_parallel(struct padata_instance *pinst, padata->cb_cpu = cb_cpu; target_cpu = padata_cpu_hash(pd); + padata->cpu = target_cpu; queue = per_cpu_ptr(pd->pqueue, target_cpu); spin_lock(&queue->parallel.lock); @@ -165,23 +166,12 @@ EXPORT_SYMBOL(padata_do_parallel); */ static struct padata_priv *padata_get_next(struct parallel_data *pd) { - int cpu, num_cpus; - unsigned int next_nr, next_index; struct padata_parallel_queue *next_queue; struct padata_priv *padata; struct padata_list *reorder; + int cpu = pd->cpu; - num_cpus = cpumask_weight(pd->cpumask.pcpu); - - /* - * Calculate the percpu reorder queue and the sequence - * number of the next object. - */ - next_nr = pd->processed; - next_index = next_nr % num_cpus; - cpu = padata_index_to_cpu(pd, next_index); next_queue = per_cpu_ptr(pd->pqueue, cpu); - reorder = &next_queue->reorder; spin_lock(&reorder->lock); @@ -192,7 +182,8 @@ static struct padata_priv *padata_get_next(struct parallel_data *pd) list_del_init(&padata->list); atomic_dec(&pd->reorder_objects); - pd->processed++; + pd->cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu, -1, + false); spin_unlock(&reorder->lock); goto out; @@ -215,6 +206,7 @@ static void padata_reorder(struct parallel_data *pd) struct padata_priv *padata; struct padata_serial_queue *squeue; struct padata_instance *pinst = pd->pinst; + struct padata_parallel_queue *next_queue; /* * We need to ensure that only one cpu can work on dequeueing of @@ -246,7 +238,6 @@ static void padata_reorder(struct parallel_data *pd) * so exit immediately. */ if (PTR_ERR(padata) == -ENODATA) { - del_timer(&pd->timer); spin_unlock_bh(&pd->lock); return; } @@ -265,28 +256,27 @@ static void padata_reorder(struct parallel_data *pd) /* * The next object that needs serialization might have arrived to - * the reorder queues in the meantime, we will be called again - * from the timer function if no one else cares for it. + * the reorder queues in the meantime. * - * Ensure reorder_objects is read after pd->lock is dropped so we see - * an increment from another task in padata_do_serial. Pairs with + * Ensure reorder queue is read after pd->lock is dropped so we see + * new objects from another task in padata_do_serial. Pairs with * smp_mb__after_atomic in padata_do_serial. */ smp_mb(); - if (atomic_read(&pd->reorder_objects) - && !(pinst->flags & PADATA_RESET)) - mod_timer(&pd->timer, jiffies + HZ); - else - del_timer(&pd->timer); - return; + next_queue = per_cpu_ptr(pd->pqueue, pd->cpu); + if (!list_empty(&next_queue->reorder.list)) + queue_work(pinst->wq, &pd->reorder_work); } -static void padata_reorder_timer(unsigned long arg) +static void invoke_padata_reorder(struct work_struct *work) { - struct parallel_data *pd = (struct parallel_data *)arg; + struct parallel_data *pd; + local_bh_disable(); + pd = container_of(work, struct parallel_data, reorder_work); padata_reorder(pd); + local_bh_enable(); } static void padata_serial_worker(struct work_struct *serial_work) @@ -333,29 +323,22 @@ static void padata_serial_worker(struct work_struct *serial_work) */ void padata_do_serial(struct padata_priv *padata) { - int cpu; - struct padata_parallel_queue *pqueue; - struct parallel_data *pd; - - pd = padata->pd; - - cpu = get_cpu(); - pqueue = per_cpu_ptr(pd->pqueue, cpu); + struct parallel_data *pd = padata->pd; + struct padata_parallel_queue *pqueue = per_cpu_ptr(pd->pqueue, + padata->cpu); spin_lock(&pqueue->reorder.lock); - atomic_inc(&pd->reorder_objects); list_add_tail(&padata->list, &pqueue->reorder.list); + atomic_inc(&pd->reorder_objects); spin_unlock(&pqueue->reorder.lock); /* - * Ensure the atomic_inc of reorder_objects above is ordered correctly + * Ensure the addition to the reorder list is ordered correctly * with the trylock of pd->lock in padata_reorder. Pairs with smp_mb * in padata_reorder. */ smp_mb__after_atomic(); - put_cpu(); - padata_reorder(pd); } EXPORT_SYMBOL(padata_do_serial); @@ -404,9 +387,14 @@ static void padata_init_pqueues(struct parallel_data *pd) struct padata_parallel_queue *pqueue; cpu_index = 0; - for_each_cpu(cpu, pd->cpumask.pcpu) { + for_each_possible_cpu(cpu) { pqueue = per_cpu_ptr(pd->pqueue, cpu); - pqueue->pd = pd; + + if (!cpumask_test_cpu(cpu, pd->cpumask.pcpu)) { + pqueue->cpu_index = -1; + continue; + } + pqueue->cpu_index = cpu_index; cpu_index++; @@ -440,12 +428,13 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst, padata_init_pqueues(pd); padata_init_squeues(pd); - setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd); atomic_set(&pd->seq_nr, -1); atomic_set(&pd->reorder_objects, 0); atomic_set(&pd->refcnt, 1); pd->pinst = pinst; spin_lock_init(&pd->lock); + pd->cpu = cpumask_first(pd->cpumask.pcpu); + INIT_WORK(&pd->reorder_work, invoke_padata_reorder); return pd; diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 22091c88b3bb..93ed69037ae9 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -55,7 +55,7 @@ static struct kmem_cache *create_pid_cachep(int nr_ids) snprintf(pcache->name, sizeof(pcache->name), "pid_%d", nr_ids); cachep = kmem_cache_create(pcache->name, sizeof(struct pid) + (nr_ids - 1) * sizeof(struct upid), - 0, SLAB_HWCACHE_ALIGN, NULL); + 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (cachep == NULL) goto err_cachep; diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 2d6d14ad7b4f..e68b1c20ad3d 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -668,7 +668,7 @@ 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) hibernation_restore(flags & SF_PLATFORM_MODE); @@ -833,17 +833,6 @@ static int software_resume(void) /* Check if the device is there */ swsusp_resume_device = name_to_dev_t(resume_file); - - /* - * name_to_dev_t is ineffective to verify parition if resume_file is in - * integer format. (e.g. major:minor) - */ - if (isdigit(resume_file[0]) && resume_wait) { - int partno; - while (!get_gendisk(swsusp_resume_device, &partno)) - msleep(10); - } - if (!swsusp_resume_device) { /* * Some device discovery might still be in progress; we need @@ -876,7 +865,7 @@ static int software_resume(void) /* The snapshot device should not be opened while we're running */ if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { error = -EBUSY; - swsusp_close(FMODE_READ); + swsusp_close(FMODE_READ | FMODE_EXCL); goto Unlock; } @@ -892,6 +881,13 @@ static int software_resume(void) error = freeze_processes(); if (error) goto Close_Finish; + + error = freeze_kernel_threads(); + if (error) { + thaw_processes(); + goto Close_Finish; + } + error = load_image_and_restore(); thaw_processes(); Finish: @@ -905,7 +901,7 @@ 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/swap.c b/kernel/power/swap.c index d7cdc426ee38..8b37085a6690 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -292,7 +292,7 @@ static int hib_submit_io(int op, int op_flags, pgoff_t page_off, void *addr, return error; } -static blk_status_t hib_wait_io(struct hib_bio_batch *hb) +static int hib_wait_io(struct hib_bio_batch *hb) { wait_event(hb->wait, atomic_read(&hb->count) == 0); return blk_status_to_errno(hb->error); @@ -1526,9 +1526,10 @@ end: int swsusp_check(void) { int error; + void *holder; hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device, - FMODE_READ, NULL); + FMODE_READ | FMODE_EXCL, &holder); if (!IS_ERR(hib_resume_bdev)) { set_blocksize(hib_resume_bdev, PAGE_SIZE); clear_page(swsusp_header); @@ -1550,7 +1551,7 @@ int swsusp_check(void) put: if (error) - blkdev_put(hib_resume_bdev, FMODE_READ); + blkdev_put(hib_resume_bdev, FMODE_READ | FMODE_EXCL); else pr_debug("PM: Image signature found, resuming\n"); } else { diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 4e50beb162c0..31b5e7919d62 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2092,6 +2092,16 @@ static int __init console_setup(char *str) char *s, *options, *brl_options = NULL; int idx; + /* + * console="" or console=null have been suggested as a way to + * disable console output. Use ttynull that has been created + * for exacly this purpose. + */ + if (str[0] == 0 || strcmp(str, "null") == 0) { + __add_preferred_console("ttynull", 0, NULL, NULL); + return 1; + } + if (_braille_console_setup(&str, &brl_options)) return 1; diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index 64f8046586b6..477f19e645d1 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -56,6 +56,8 @@ struct printk_safe_seq_buf { static DEFINE_PER_CPU(struct printk_safe_seq_buf, safe_print_seq); static DEFINE_PER_CPU(int, printk_context); +static DEFINE_RAW_SPINLOCK(safe_read_lock); + #ifdef CONFIG_PRINTK_NMI static DEFINE_PER_CPU(struct printk_safe_seq_buf, nmi_print_seq); #endif @@ -194,8 +196,6 @@ static void report_message_lost(struct printk_safe_seq_buf *s) */ static void __printk_safe_flush(struct irq_work *work) { - static raw_spinlock_t read_lock = - __RAW_SPIN_LOCK_INITIALIZER(read_lock); struct printk_safe_seq_buf *s = container_of(work, struct printk_safe_seq_buf, work); unsigned long flags; @@ -209,7 +209,7 @@ static void __printk_safe_flush(struct irq_work *work) * different CPUs. This is especially important when printing * a backtrace. */ - raw_spin_lock_irqsave(&read_lock, flags); + raw_spin_lock_irqsave(&safe_read_lock, flags); i = 0; more: @@ -246,7 +246,7 @@ more: out: report_message_lost(s); - raw_spin_unlock_irqrestore(&read_lock, flags); + raw_spin_unlock_irqrestore(&safe_read_lock, flags); } /** @@ -292,6 +292,14 @@ void printk_safe_flush_on_panic(void) raw_spin_lock_init(&logbuf_lock); } + if (raw_spin_is_locked(&safe_read_lock)) { + if (num_online_cpus() > 1) + return; + + debug_locks_off(); + raw_spin_lock_init(&safe_read_lock); + } + printk_safe_flush(); } diff --git a/kernel/profile.c b/kernel/profile.c index 9aa2a4445b0d..efa58f63dc1b 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -40,7 +40,8 @@ struct profile_hit { #define NR_PROFILE_GRP (NR_PROFILE_HIT/PROFILE_GRPSZ) static atomic_t *prof_buffer; -static unsigned long prof_len, prof_shift; +static unsigned long prof_len; +static unsigned short int prof_shift; int prof_on __read_mostly; EXPORT_SYMBOL_GPL(prof_on); @@ -66,8 +67,8 @@ int profile_setup(char *str) if (str[strlen(sleepstr)] == ',') str += strlen(sleepstr) + 1; if (get_option(&str, &par)) - prof_shift = par; - pr_info("kernel sleep profiling enabled (shift: %ld)\n", + prof_shift = clamp(par, 0, BITS_PER_LONG - 1); + pr_info("kernel sleep profiling enabled (shift: %u)\n", prof_shift); #else pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n"); @@ -77,21 +78,21 @@ int profile_setup(char *str) if (str[strlen(schedstr)] == ',') str += strlen(schedstr) + 1; if (get_option(&str, &par)) - prof_shift = par; - pr_info("kernel schedule profiling enabled (shift: %ld)\n", + prof_shift = clamp(par, 0, BITS_PER_LONG - 1); + pr_info("kernel schedule profiling enabled (shift: %u)\n", prof_shift); } else if (!strncmp(str, kvmstr, strlen(kvmstr))) { prof_on = KVM_PROFILING; if (str[strlen(kvmstr)] == ',') str += strlen(kvmstr) + 1; if (get_option(&str, &par)) - prof_shift = par; - pr_info("kernel KVM profiling enabled (shift: %ld)\n", + prof_shift = clamp(par, 0, BITS_PER_LONG - 1); + pr_info("kernel KVM profiling enabled (shift: %u)\n", prof_shift); } else if (get_option(&str, &par)) { - prof_shift = par; + prof_shift = clamp(par, 0, BITS_PER_LONG - 1); prof_on = CPU_PROFILING; - pr_info("kernel profiling enabled (shift: %ld)\n", + pr_info("kernel profiling enabled (shift: %u)\n", prof_shift); } return 1; @@ -467,7 +468,7 @@ read_profile(struct file *file, char __user *buf, size_t count, loff_t *ppos) unsigned long p = *ppos; ssize_t read; char *pnt; - unsigned int sample_step = 1 << prof_shift; + unsigned long sample_step = 1UL << prof_shift; profile_flip_buffers(); if (p >= (prof_len+1)*sizeof(unsigned int)) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 43a283041296..b28f3c66c6fe 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -163,6 +163,21 @@ void __ptrace_unlink(struct task_struct *child) spin_unlock(&child->sighand->siglock); } +static bool looks_like_a_spurious_pid(struct task_struct *task) +{ + if (task->exit_code != ((PTRACE_EVENT_EXEC << 8) | SIGTRAP)) + return false; + + if (task_pid_vnr(task) == task->ptrace_message) + return false; + /* + * The tracee changed its pid but the PTRACE_EVENT_EXEC event + * was not wait()'ed, most probably debugger targets the old + * leader which was destroyed in de_thread(). + */ + return true; +} + /* Ensure that nothing can wake it up, even SIGKILL */ static bool ptrace_freeze_traced(struct task_struct *task) { @@ -173,7 +188,8 @@ static bool ptrace_freeze_traced(struct task_struct *task) return ret; spin_lock_irq(&task->sighand->siglock); - if (task_is_traced(task) && !__fatal_signal_pending(task)) { + if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && + !__fatal_signal_pending(task)) { task->state = __TASK_TRACED; ret = true; } diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 46d61b597731..f90d10c1c3c8 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -534,7 +534,7 @@ static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s) spin_unlock(&rnp->exp_lock); } smp_mb(); /* All above changes before wakeup. */ - wake_up_all(&rnp->exp_wq[rcu_seq_ctr(rsp->expedited_sequence) & 0x3]); + wake_up_all(&rnp->exp_wq[rcu_seq_ctr(s) & 0x3]); } trace_rcu_exp_grace_period(rsp->name, s, TPS("endwake")); mutex_unlock(&rsp->exp_wake_mutex); diff --git a/kernel/reboot.c b/kernel/reboot.c index bd30a973fe94..2946ed1d99d4 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -512,22 +512,22 @@ static int __init reboot_setup(char *str) break; case 's': - { - int rc; - - if (isdigit(*(str+1))) { - rc = kstrtoint(str+1, 0, &reboot_cpu); - if (rc) - return rc; - } else if (str[1] == 'm' && str[2] == 'p' && - isdigit(*(str+3))) { - rc = kstrtoint(str+3, 0, &reboot_cpu); - if (rc) - return rc; - } else + if (isdigit(*(str+1))) + reboot_cpu = simple_strtoul(str+1, NULL, 0); + else if (str[1] == 'm' && str[2] == 'p' && + isdigit(*(str+3))) + reboot_cpu = simple_strtoul(str+3, NULL, 0); + else reboot_mode = REBOOT_SOFT; + if (reboot_cpu >= num_possible_cpus()) { + pr_err("Ignoring the CPU number in reboot= option. " + "CPU %d exceeds possible cpu number %d\n", + reboot_cpu, num_possible_cpus()); + reboot_cpu = 0; + break; + } break; - } + case 'g': reboot_mode = REBOOT_GPIO; break; diff --git a/kernel/relay.c b/kernel/relay.c index 61d37e6da22d..53c2a1a4b057 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -196,6 +196,7 @@ free_buf: static void relay_destroy_channel(struct kref *kref) { struct rchan *chan = container_of(kref, struct rchan, kref); + free_percpu(chan->buf); kfree(chan); } @@ -580,6 +581,11 @@ struct rchan *relay_open(const char *base_filename, return NULL; chan->buf = alloc_percpu(struct rchan_buf *); + if (!chan->buf) { + kfree(chan); + return NULL; + } + chan->version = RELAYFS_CHANNEL_VERSION; chan->n_subbufs = n_subbufs; chan->subbuf_size = subbuf_size; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 97a27726ea21..544a1cb66d90 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1852,6 +1852,9 @@ out: bool cpus_share_cache(int this_cpu, int that_cpu) { + if (this_cpu == that_cpu) + return true; + return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu); } #endif /* CONFIG_SMP */ @@ -3731,7 +3734,8 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) */ if (dl_prio(prio)) { if (!dl_prio(p->normal_prio) || - (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) { + (pi_task && dl_prio(pi_task->prio) && + dl_entity_preempt(&pi_task->dl, &p->dl))) { p->dl.dl_boosted = 1; queue_flag |= ENQUEUE_REPLENISH; } else @@ -4825,12 +4829,8 @@ SYSCALL_DEFINE0(sched_yield) schedstat_inc(rq->yld_count); current->sched_class->yield_task(rq); - /* - * Since we are going to call schedule() anyway, there's - * no need to preempt or enable interrupts: - */ preempt_disable(); - rq_unlock(rq, &rf); + rq_unlock_irq(rq, &rf); sched_preempt_enable_no_resched(); schedule(); diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index f8c45d30ec6d..90a998638bdd 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -441,9 +441,17 @@ static struct attribute *sugov_attributes[] = { NULL }; +static void sugov_tunables_free(struct kobject *kobj) +{ + struct gov_attr_set *attr_set = container_of(kobj, struct gov_attr_set, kobj); + + kfree(to_sugov_tunables(attr_set)); +} + static struct kobj_type sugov_tunables_ktype = { .default_attrs = sugov_attributes, .sysfs_ops = &governor_sysfs_ops, + .release = &sugov_tunables_free, }; /********************** cpufreq governor interface *********************/ @@ -534,12 +542,10 @@ static struct sugov_tunables *sugov_tunables_alloc(struct sugov_policy *sg_polic return tunables; } -static void sugov_tunables_free(struct sugov_tunables *tunables) +static void sugov_clear_global_tunables(void) { if (!have_governor_per_policy()) global_tunables = NULL; - - kfree(tunables); } static int sugov_init(struct cpufreq_policy *policy) @@ -602,7 +608,7 @@ out: fail: kobject_put(&tunables->attr_set.kobj); policy->governor_data = NULL; - sugov_tunables_free(tunables); + sugov_clear_global_tunables(); stop_kthread: sugov_kthread_stop(sg_policy); @@ -629,7 +635,7 @@ static void sugov_exit(struct cpufreq_policy *policy) count = gov_attr_set_put(&tunables->attr_set, &sg_policy->tunables_hook); policy->governor_data = NULL; if (!count) - sugov_tunables_free(tunables); + sugov_clear_global_tunables(); mutex_unlock(&global_tunables_lock); diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 22770168bff8..06a6bcd6cfa6 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2345,7 +2345,7 @@ int sched_dl_global_validate(void) u64 period = global_rt_period(); u64 new_bw = to_ratio(period, runtime); struct dl_bw *dl_b; - int cpu, ret = 0; + int cpu, cpus, ret = 0; unsigned long flags; /* @@ -2360,9 +2360,10 @@ int sched_dl_global_validate(void) for_each_possible_cpu(cpu) { rcu_read_lock_sched(); dl_b = dl_bw_of(cpu); + cpus = dl_bw_cpus(cpu); raw_spin_lock_irqsave(&dl_b->lock, flags); - if (new_bw < dl_b->total_bw) + if (new_bw * cpus < dl_b->total_bw) ret = -EBUSY; raw_spin_unlock_irqrestore(&dl_b->lock, flags); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 0b4e997fea1a..3ff60230710c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2643,7 +2643,7 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr) /* * We don't care about NUMA placement if we don't have memory. */ - if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work) + if ((curr->flags & (PF_EXITING | PF_KTHREAD)) || work->next != work) return; /* @@ -4464,7 +4464,7 @@ static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC; static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire) { struct hrtimer *refresh_timer = &cfs_b->period_timer; - u64 remaining; + s64 remaining; /* if the call-back is running a quota refresh is already occurring */ if (hrtimer_callback_running(refresh_timer)) @@ -4472,7 +4472,7 @@ static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire) /* is a quota refresh about to occur? */ remaining = ktime_to_ns(hrtimer_expires_remaining(refresh_timer)); - if (remaining < min_expire) + if (remaining < (s64)min_expire) return 1; return 0; @@ -5779,6 +5779,7 @@ static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd */ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target) { + struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask); struct sched_domain *this_sd; u64 avg_cost, avg_idle; u64 time, cost; @@ -5809,11 +5810,11 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t time = local_clock(); - for_each_cpu_wrap(cpu, sched_domain_span(sd), target) { + cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed); + + for_each_cpu_wrap(cpu, cpus, target) { if (!--nr) return -1; - if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) - continue; if (idle_cpu(cpu)) break; } @@ -6871,7 +6872,15 @@ static int detach_tasks(struct lb_env *env) if (!can_migrate_task(p, env)) goto next; - load = task_h_load(p); + /* + * Depending of the number of CPUs and tasks and the + * cgroup hierarchy, task_h_load() can return a null + * value. Make sure that env->imbalance decreases + * otherwise detach_tasks() will stop only after + * detaching up to loop_max tasks. + */ + load = max_t(unsigned long, task_h_load(p), 1); + if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed) goto next; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 268f560ec998..e5cfec6bc891 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -89,7 +89,13 @@ static inline void cpu_load_update_active(struct rq *this_rq) { } #ifdef CONFIG_64BIT # define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT + SCHED_FIXEDPOINT_SHIFT) # define scale_load(w) ((w) << SCHED_FIXEDPOINT_SHIFT) -# define scale_load_down(w) ((w) >> SCHED_FIXEDPOINT_SHIFT) +# define scale_load_down(w) \ +({ \ + unsigned long __w = (w); \ + if (__w) \ + __w = max(2UL, __w >> SCHED_FIXEDPOINT_SHIFT); \ + __w; \ +}) #else # define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT) # define scale_load(w) (w) @@ -185,30 +191,6 @@ struct rt_bandwidth { void __dl_clear_params(struct task_struct *p); -/* - * To keep the bandwidth of -deadline tasks and groups under control - * we need some place where: - * - store the maximum -deadline bandwidth of the system (the group); - * - cache the fraction of that bandwidth that is currently allocated. - * - * This is all done in the data structure below. It is similar to the - * one used for RT-throttling (rt_bandwidth), with the main difference - * that, since here we are only interested in admission control, we - * do not decrease any runtime while the group "executes", neither we - * need a timer to replenish it. - * - * With respect to SMP, the bandwidth is given on a per-CPU basis, - * meaning that: - * - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU; - * - dl_total_bw array contains, in the i-eth element, the currently - * allocated bandwidth on the i-eth CPU. - * Moreover, groups consume bandwidth on each CPU, while tasks only - * consume bandwidth on the CPU they're running on. - * Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw - * that will be shown the next time the proc or cgroup controls will - * be red. It on its turn can be changed by writing on its own - * control. - */ struct dl_bandwidth { raw_spinlock_t dl_runtime_lock; u64 dl_runtime; @@ -220,6 +202,24 @@ static inline int dl_bandwidth_enabled(void) return sysctl_sched_rt_runtime >= 0; } +/* + * To keep the bandwidth of -deadline tasks under control + * we need some place where: + * - store the maximum -deadline bandwidth of each cpu; + * - cache the fraction of bandwidth that is currently allocated in + * each root domain; + * + * This is all done in the data structure below. It is similar to the + * one used for RT-throttling (rt_bandwidth), with the main difference + * that, since here we are only interested in admission control, we + * do not decrease any runtime while the group "executes", neither we + * need a timer to replenish it. + * + * With respect to SMP, bandwidth is given on a per root domain basis, + * meaning that: + * - bw (< 100%) is the deadline bandwidth of each CPU; + * - total_bw is the currently allocated bandwidth in each root domain; + */ struct dl_bw { raw_spinlock_t lock; u64 bw, total_bw; diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 867d173dab48..152ffe0c2433 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1117,7 +1117,7 @@ sd_init(struct sched_domain_topology_level *tl, sd_flags = (*tl->sd_flags)(); if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS, "wrong sd_flags in topology description\n")) - sd_flags &= ~TOPOLOGY_SD_FLAGS; + sd_flags &= TOPOLOGY_SD_FLAGS; *sd = (struct sched_domain){ .min_interval = sd_weight, diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index e29608464382..174585abc9b5 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -11,6 +11,7 @@ #include <linux/wait.h> #include <linux/hash.h> #include <linux/kthread.h> +#include <linux/poll.h> void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *key) { @@ -213,6 +214,13 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr_e } 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, (void *)(POLLHUP | 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/seccomp.c b/kernel/seccomp.c index 075e344a87c3..4270ff81184d 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -775,6 +775,8 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, const bool recheck_after_trace) { BUG(); + + return -1; } #endif diff --git a/kernel/signal.c b/kernel/signal.c index c066168f8854..3619ab24644f 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1675,7 +1675,7 @@ bool do_notify_parent(struct task_struct *tsk, int sig) * This is only possible if parent == real_parent. * Check if it has changed security domain. */ - if (tsk->parent_exec_id != tsk->parent->self_exec_id) + if (tsk->parent_exec_id != READ_ONCE(tsk->parent->self_exec_id)) sig = SIGCHLD; } @@ -1839,16 +1839,6 @@ static inline int may_ptrace_stop(void) } /* - * Return non-zero if there is a SIGKILL that should be waking us up. - * Called with the siglock held. - */ -static int sigkill_pending(struct task_struct *tsk) -{ - return sigismember(&tsk->pending.signal, SIGKILL) || - sigismember(&tsk->signal->shared_pending.signal, SIGKILL); -} - -/* * This must be called with current->sighand->siglock held. * * This should be the path for all ptrace stops. @@ -1873,17 +1863,16 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) * calling arch_ptrace_stop, so we must release it now. * To preserve proper semantics, we must do this before * any signal bookkeeping like checking group_stop_count. - * Meanwhile, a SIGKILL could come in before we retake the - * siglock. That must prevent us from sleeping in TASK_TRACED. - * So after regaining the lock, we must check for SIGKILL. */ spin_unlock_irq(¤t->sighand->siglock); arch_ptrace_stop(exit_code, info); spin_lock_irq(¤t->sighand->siglock); - if (sigkill_pending(current)) - return; } + /* + * schedule() will not sleep if there is a pending signal that + * can awaken the task. + */ set_special_state(TASK_TRACED); /* diff --git a/kernel/smp.c b/kernel/smp.c index c94dd85c8d41..f9d95d59b7ed 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -103,12 +103,12 @@ void __init call_function_init(void) * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ -static __always_inline void csd_lock_wait(call_single_data_t *csd) +static __always_inline void csd_lock_wait(struct __call_single_data *csd) { smp_cond_load_acquire(&csd->flags, !(VAL & CSD_FLAG_LOCK)); } -static __always_inline void csd_lock(call_single_data_t *csd) +static __always_inline void csd_lock(struct __call_single_data *csd) { csd_lock_wait(csd); csd->flags |= CSD_FLAG_LOCK; @@ -121,7 +121,7 @@ static __always_inline void csd_lock(call_single_data_t *csd) smp_wmb(); } -static __always_inline void csd_unlock(call_single_data_t *csd) +static __always_inline void csd_unlock(struct __call_single_data *csd) { WARN_ON(!(csd->flags & CSD_FLAG_LOCK)); @@ -138,7 +138,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); * for execution on the given CPU. data must already have * ->func, ->info, and ->flags set. */ -static int generic_exec_single(int cpu, call_single_data_t *csd, +static int generic_exec_single(int cpu, struct __call_single_data *csd, smp_call_func_t func, void *info) { if (cpu == smp_processor_id()) { @@ -323,7 +323,7 @@ EXPORT_SYMBOL(smp_call_function_single); * NOTE: Be careful, there is unfortunately no current debugging facility to * validate the correctness of this serialization. */ -int smp_call_function_single_async(int cpu, call_single_data_t *csd) +int smp_call_function_single_async(int cpu, struct __call_single_data *csd) { int err = 0; diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 5043e7433f4b..eeb7f8e9cce3 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -187,6 +187,7 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu) kfree(td); return PTR_ERR(tsk); } + kthread_set_per_cpu(tsk, cpu); /* * Park the thread so that it could start right on the CPU * when it is available. diff --git a/kernel/sys.c b/kernel/sys.c index ab96b9882347..65701dd2707e 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1217,11 +1217,13 @@ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) { - struct oldold_utsname tmp = {}; + struct oldold_utsname tmp; if (!name) return -EFAULT; + memset(&tmp, 0, sizeof(tmp)); + down_read(&uts_sem); memcpy(&tmp.sysname, &utsname()->sysname, __OLD_UTS_LEN); memcpy(&tmp.nodename, &utsname()->nodename, __OLD_UTS_LEN); @@ -1872,13 +1874,6 @@ static int validate_prctl_map(struct prctl_mm_map *prctl_map) error = -EINVAL; /* - * @brk should be after @end_data in traditional maps. - */ - if (prctl_map->start_brk <= prctl_map->end_data || - prctl_map->brk <= prctl_map->end_data) - goto out; - - /* * Neither we should allow to override limits if they set. */ if (check_data_rlimit(rlimit(RLIMIT_DATA), prctl_map->brk, diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 9eece67f29f3..6a2ba39889bd 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -822,9 +822,9 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, if (flags == TIMER_ABSTIME) return -ERESTARTNOHAND; - restart->fn = alarm_timer_nsleep_restart; restart->nanosleep.clockid = type; restart->nanosleep.expires = exp; + set_restart_fn(restart, alarm_timer_nsleep_restart); return ret; } diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index ecce9122343b..94dd37e8890d 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1545,9 +1545,9 @@ long hrtimer_nanosleep(const struct timespec64 *rqtp, } restart = ¤t->restart_block; - restart->fn = hrtimer_nanosleep_restart; restart->nanosleep.clockid = t.timer.base->clockid; restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); + set_restart_fn(restart, hrtimer_nanosleep_restart); out: destroy_hrtimer_on_stack(&t.timer); return ret; diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index f26acef5d7b4..7f718565507b 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -153,10 +153,6 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, u64 oval, nval, ointerval, ninterval; struct cpu_itimer *it = &tsk->signal->it[clock_id]; - /* - * Use the to_ktime conversion because that clamps the maximum - * value to KTIME_MAX and avoid multiplication overflows. - */ nval = ktime_to_ns(timeval_to_ktime(value->it_value)); ninterval = ktime_to_ns(timeval_to_ktime(value->it_interval)); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 6e8c230ca877..fb5a57ffb98c 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -1348,8 +1348,8 @@ static int posix_cpu_nsleep(const clockid_t which_clock, int flags, if (flags & TIMER_ABSTIME) return -ERESTARTNOHAND; - restart_block->fn = posix_cpu_nsleep_restart; restart_block->nanosleep.clockid = which_clock; + set_restart_fn(restart_block, posix_cpu_nsleep_restart); } return error; } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index d7e478a430e9..f46694850b44 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -1172,8 +1172,8 @@ COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock, err = kc->clock_adj(which_clock, &ktx); - if (err >= 0) - err = compat_put_timex(utp, &ktx); + if (err >= 0 && compat_put_timex(utp, &ktx)) + return -EFAULT; return err; } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 1ce7c404d0b0..602b476627dd 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -988,9 +988,8 @@ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; - rem *= mult; - do_div(rem, div); + rem = div64_u64(rem * mult, div); *base = tmp + rem; return 0; } @@ -1236,8 +1235,7 @@ 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 9f8e8892e5b0..99f885d2904a 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -44,6 +44,7 @@ #include <linux/sched/debug.h> #include <linux/slab.h> #include <linux/compat.h> +#include <linux/random.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -502,8 +503,8 @@ static int calc_wheel_index(unsigned long expires, unsigned long clk) * Force expire obscene large timeouts to expire at the * capacity limit of the wheel. */ - if (expires >= WHEEL_TIMEOUT_CUTOFF) - expires = WHEEL_TIMEOUT_MAX; + if (delta >= WHEEL_TIMEOUT_CUTOFF) + expires = clk + WHEEL_TIMEOUT_MAX; idx = calc_index(expires, LVL_DEPTH - 1); } diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 71a8ee6e60dc..0b22bf622397 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -15,6 +15,9 @@ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA * */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/blktrace_api.h> @@ -348,11 +351,12 @@ static void put_probe_ref(void) static void blk_trace_cleanup(struct blk_trace *bt) { + synchronize_rcu(); blk_trace_free(bt); put_probe_ref(); } -int blk_trace_remove(struct request_queue *q) +static int __blk_trace_remove(struct request_queue *q) { struct blk_trace *bt; @@ -365,6 +369,17 @@ int blk_trace_remove(struct request_queue *q) return 0; } + +int blk_trace_remove(struct request_queue *q) +{ + int ret; + + mutex_lock(&q->blk_trace_mutex); + ret = __blk_trace_remove(q); + mutex_unlock(&q->blk_trace_mutex); + + return ret; +} EXPORT_SYMBOL_GPL(blk_trace_remove); static ssize_t blk_dropped_read(struct file *filp, char __user *buffer, @@ -483,6 +498,9 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (!buts->buf_size || !buts->buf_nr) return -EINVAL; + if (!blk_debugfs_root) + return -ENOENT; + strncpy(buts->name, name, BLKTRACE_BDEV_SIZE); buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0'; @@ -492,6 +510,16 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, */ strreplace(buts->name, '/', '_'); + /* + * bdev can be NULL, as with scsi-generic, this is a helpful as + * we can be. + */ + if (q->blk_trace) { + pr_warn("Concurrent blktraces are not allowed on %s\n", + buts->name); + return -EBUSY; + } + bt = kzalloc(sizeof(*bt), GFP_KERNEL); if (!bt) return -ENOMEM; @@ -505,17 +533,34 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (!bt->msg_data) goto err; - ret = -ENOENT; - - if (!blk_debugfs_root) - goto err; - - dir = debugfs_lookup(buts->name, blk_debugfs_root); - if (!dir) +#ifdef CONFIG_BLK_DEBUG_FS + /* + * When tracing whole make_request drivers (multiqueue) block devices, + * reuse the existing debugfs directory created by the block layer on + * init. For request-based block devices, all partitions block devices, + * and scsi-generic block devices we create a temporary new debugfs + * directory that will be removed once the trace ends. + */ + if (q->mq_ops && bdev && bdev == bdev->bd_contains) + dir = q->debugfs_dir; + else +#endif bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root); if (!dir) goto err; + /* + * As blktrace relies on debugfs for its interface the debugfs directory + * is required, contrary to the usual mantra of not checking for debugfs + * files or directories. + */ + if (IS_ERR_OR_NULL(dir)) { + pr_warn("debugfs_dir not present for %s so skipping\n", + buts->name); + ret = -ENOENT; + goto err; + } + bt->dev = dev; atomic_set(&bt->dropped, 0); INIT_LIST_HEAD(&bt->running_list); @@ -558,16 +603,13 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, ret = 0; err: - if (dir && !bt->dir) - dput(dir); if (ret) blk_trace_free(bt); return ret; } -int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, - struct block_device *bdev, - char __user *arg) +static int __blk_trace_setup(struct request_queue *q, char *name, dev_t dev, + struct block_device *bdev, char __user *arg) { struct blk_user_trace_setup buts; int ret; @@ -581,11 +623,24 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, return ret; if (copy_to_user(arg, &buts, sizeof(buts))) { - blk_trace_remove(q); + __blk_trace_remove(q); return -EFAULT; } return 0; } + +int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, + struct block_device *bdev, + char __user *arg) +{ + int ret; + + mutex_lock(&q->blk_trace_mutex); + ret = __blk_trace_setup(q, name, dev, bdev, arg); + mutex_unlock(&q->blk_trace_mutex); + + return ret; +} EXPORT_SYMBOL_GPL(blk_trace_setup); #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) @@ -614,7 +669,7 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name, return ret; if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) { - blk_trace_remove(q); + __blk_trace_remove(q); return -EFAULT; } @@ -622,11 +677,13 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name, } #endif -int blk_trace_startstop(struct request_queue *q, int start) +static int __blk_trace_startstop(struct request_queue *q, int start) { int ret; - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (bt == NULL) return -EINVAL; @@ -661,6 +718,17 @@ int blk_trace_startstop(struct request_queue *q, int start) return ret; } + +int blk_trace_startstop(struct request_queue *q, int start) +{ + int ret; + + mutex_lock(&q->blk_trace_mutex); + ret = __blk_trace_startstop(q, start); + mutex_unlock(&q->blk_trace_mutex); + + return ret; +} EXPORT_SYMBOL_GPL(blk_trace_startstop); /* @@ -691,7 +759,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) switch (cmd) { case BLKTRACESETUP: bdevname(bdev, b); - ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); + ret = __blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); break; #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) case BLKTRACESETUP32: @@ -702,10 +770,10 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) case BLKTRACESTART: start = 1; case BLKTRACESTOP: - ret = blk_trace_startstop(q, start); + ret = __blk_trace_startstop(q, start); break; case BLKTRACETEARDOWN: - ret = blk_trace_remove(q); + ret = __blk_trace_remove(q); break; default: ret = -ENOTTY; @@ -723,18 +791,24 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) **/ void blk_trace_shutdown(struct request_queue *q) { - if (q->blk_trace) { - blk_trace_startstop(q, 0); - blk_trace_remove(q); + mutex_lock(&q->blk_trace_mutex); + if (rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex))) { + __blk_trace_startstop(q, 0); + __blk_trace_remove(q); } + + mutex_unlock(&q->blk_trace_mutex); } #ifdef CONFIG_BLK_CGROUP static union kernfs_node_id * blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + /* We don't use the 'bt' value here except as an optimization... */ + bt = rcu_dereference_protected(q->blk_trace, 1); if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return NULL; @@ -779,10 +853,14 @@ static void blk_add_trace_rq(struct request *rq, int error, unsigned int nr_bytes, u32 what, union kernfs_node_id *cgid) { - struct blk_trace *bt = rq->q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(rq->q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } if (blk_rq_is_passthrough(rq)) what |= BLK_TC_ACT(BLK_TC_PC); @@ -791,6 +869,7 @@ static void blk_add_trace_rq(struct request *rq, int error, __blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq), rq->cmd_flags, what, error, 0, NULL, cgid); + rcu_read_unlock(); } static void blk_add_trace_rq_insert(void *ignore, @@ -836,13 +915,18 @@ static void blk_add_trace_rq_complete(void *ignore, struct request *rq, static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, u32 what, int error, union kernfs_node_id *cgid) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, what, error, 0, NULL, cgid); + rcu_read_unlock(); } static void blk_add_trace_bio_bounce(void *ignore, @@ -893,11 +977,14 @@ static void blk_add_trace_getrq(void *ignore, blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0, blk_trace_bio_get_cgid(q, bio)); else { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0, NULL, NULL); + rcu_read_unlock(); } } @@ -910,27 +997,35 @@ static void blk_add_trace_sleeprq(void *ignore, blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0, blk_trace_bio_get_cgid(q, bio)); else { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ, 0, 0, NULL, NULL); + rcu_read_unlock(); } } static void blk_add_trace_plug(void *ignore, struct request_queue *q) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, NULL); + rcu_read_unlock(); } static void blk_add_trace_unplug(void *ignore, struct request_queue *q, unsigned int depth, bool explicit) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(depth); u32 what; @@ -942,22 +1037,28 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q, __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, NULL); } + rcu_read_unlock(); } static void blk_add_trace_split(void *ignore, struct request_queue *q, struct bio *bio, unsigned int pdu) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(pdu); __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, - BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu), - &rpdu, blk_trace_bio_get_cgid(q, bio)); + BLK_TA_SPLIT, + blk_status_to_errno(bio->bi_status), + sizeof(rpdu), &rpdu, + blk_trace_bio_get_cgid(q, bio)); } + rcu_read_unlock(); } /** @@ -977,19 +1078,25 @@ static void blk_add_trace_bio_remap(void *ignore, struct request_queue *q, struct bio *bio, dev_t dev, sector_t from) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; struct blk_io_trace_remap r; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(bio_dev(bio)); r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, - bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status, + bio_op(bio), bio->bi_opf, BLK_TA_REMAP, + blk_status_to_errno(bio->bi_status), sizeof(r), &r, blk_trace_bio_get_cgid(q, bio)); + rcu_read_unlock(); } /** @@ -1010,11 +1117,15 @@ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev, sector_t from) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; struct blk_io_trace_remap r; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(disk_devt(rq->rq_disk)); @@ -1023,6 +1134,7 @@ static void blk_add_trace_rq_remap(void *ignore, __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rq_data_dir(rq), 0, BLK_TA_REMAP, 0, sizeof(r), &r, blk_trace_request_get_cgid(q, rq)); + rcu_read_unlock(); } /** @@ -1040,14 +1152,19 @@ void blk_add_driver_data(struct request_queue *q, struct request *rq, void *data, size_t len) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } __blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0, BLK_TA_DRV_DATA, 0, len, data, blk_trace_request_get_cgid(q, rq)); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blk_add_driver_data); @@ -1199,21 +1316,10 @@ static inline __u16 t_error(const struct trace_entry *ent) static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg) { - const __u64 *val = pdu_start(ent, has_cg); + const __be64 *val = pdu_start(ent, has_cg); return be64_to_cpu(*val); } -static void get_pdu_remap(const struct trace_entry *ent, - struct blk_io_trace_remap *r, bool has_cg) -{ - const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg); - __u64 sector_from = __r->sector_from; - - r->device_from = be32_to_cpu(__r->device_from); - r->device_to = be32_to_cpu(__r->device_to); - r->sector_from = be64_to_cpu(sector_from); -} - typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act, bool has_cg); @@ -1339,13 +1445,13 @@ static void blk_log_with_error(struct trace_seq *s, static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { - struct blk_io_trace_remap r = { .device_from = 0, }; + const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg); - get_pdu_remap(ent, &r, has_cg); trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n", t_sector(ent), t_sec(ent), - MAJOR(r.device_from), MINOR(r.device_from), - (unsigned long long)r.sector_from); + MAJOR(be32_to_cpu(__r->device_from)), + MINOR(be32_to_cpu(__r->device_from)), + be64_to_cpu(__r->sector_from)); } static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) @@ -1573,7 +1679,16 @@ static int blk_trace_remove_queue(struct request_queue *q) if (bt == NULL) return -EINVAL; + if (bt->trace_state == Blktrace_running) { + bt->trace_state = Blktrace_stopped; + spin_lock_irq(&running_trace_lock); + list_del_init(&bt->running_list); + spin_unlock_irq(&running_trace_lock); + relay_flush(bt->rchan); + } + put_probe_ref(); + synchronize_rcu(); blk_trace_free(bt); return 0; } @@ -1735,6 +1850,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, struct hd_struct *p = dev_to_part(dev); struct request_queue *q; struct block_device *bdev; + struct blk_trace *bt; ssize_t ret = -ENXIO; bdev = bdget(part_devt(p)); @@ -1747,21 +1863,23 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, mutex_lock(&q->blk_trace_mutex); + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (attr == &dev_attr_enable) { - ret = sprintf(buf, "%u\n", !!q->blk_trace); + ret = sprintf(buf, "%u\n", !!bt); goto out_unlock_bdev; } - if (q->blk_trace == NULL) + if (bt == NULL) ret = sprintf(buf, "disabled\n"); else if (attr == &dev_attr_act_mask) - ret = blk_trace_mask2str(buf, q->blk_trace->act_mask); + ret = blk_trace_mask2str(buf, bt->act_mask); else if (attr == &dev_attr_pid) - ret = sprintf(buf, "%u\n", q->blk_trace->pid); + ret = sprintf(buf, "%u\n", bt->pid); else if (attr == &dev_attr_start_lba) - ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba); + ret = sprintf(buf, "%llu\n", bt->start_lba); else if (attr == &dev_attr_end_lba) - ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); + ret = sprintf(buf, "%llu\n", bt->end_lba); out_unlock_bdev: mutex_unlock(&q->blk_trace_mutex); @@ -1778,6 +1896,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, struct block_device *bdev; struct request_queue *q; struct hd_struct *p; + struct blk_trace *bt; u64 value; ssize_t ret = -EINVAL; @@ -1808,8 +1927,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, mutex_lock(&q->blk_trace_mutex); + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (attr == &dev_attr_enable) { - if (!!value == !!q->blk_trace) { + if (!!value == !!bt) { ret = 0; goto out_unlock_bdev; } @@ -1821,18 +1942,21 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, } ret = 0; - if (q->blk_trace == NULL) + if (bt == NULL) { ret = blk_trace_setup_queue(q, bdev); + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); + } if (ret == 0) { if (attr == &dev_attr_act_mask) - q->blk_trace->act_mask = value; + bt->act_mask = value; else if (attr == &dev_attr_pid) - q->blk_trace->pid = value; + bt->pid = value; else if (attr == &dev_attr_start_lba) - q->blk_trace->start_lba = value; + bt->start_lba = value; else if (attr == &dev_attr_end_lba) - q->blk_trace->end_lba = value; + bt->end_lba = value; } out_unlock_bdev: diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 8a8d92a8045b..7d734b4144fd 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1715,6 +1715,8 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec) static struct ftrace_ops * ftrace_find_tramp_ops_any(struct dyn_ftrace *rec); static struct ftrace_ops * +ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_exclude); +static struct ftrace_ops * ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops); static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, @@ -1852,7 +1854,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, * to it. */ if (ftrace_rec_count(rec) == 1 && - ftrace_find_tramp_ops_any(rec)) + ftrace_find_tramp_ops_any_other(rec, ops)) rec->flags |= FTRACE_FL_TRAMP; else rec->flags &= ~FTRACE_FL_TRAMP; @@ -2040,12 +2042,18 @@ static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops, static void print_ip_ins(const char *fmt, const unsigned char *p) { + char ins[MCOUNT_INSN_SIZE]; int i; + if (probe_kernel_read(ins, p, MCOUNT_INSN_SIZE)) { + printk(KERN_CONT "%s[FAULT] %px\n", fmt, p); + return; + } + printk(KERN_CONT "%s", fmt); for (i = 0; i < MCOUNT_INSN_SIZE; i++) - printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]); + printk(KERN_CONT "%s%02x", i ? ":" : "", ins[i]); } enum ftrace_bug_type ftrace_bug_type; @@ -2281,6 +2289,24 @@ ftrace_find_tramp_ops_any(struct dyn_ftrace *rec) } static struct ftrace_ops * +ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_exclude) +{ + struct ftrace_ops *op; + unsigned long ip = rec->ip; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + + if (op == op_exclude || !op->trampoline) + continue; + + if (hash_contains_ip(ip, op->func_hash)) + return op; + } while_for_each_ftrace_op(op); + + return NULL; +} + +static struct ftrace_ops * ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *op) { @@ -5076,8 +5102,11 @@ int ftrace_regex_release(struct inode *inode, struct file *file) parser = &iter->parser; if (trace_parser_loaded(parser)) { + int enable = !(iter->flags & FTRACE_ITER_NOTRACE); + parser->buffer[parser->idx] = 0; - ftrace_match_records(iter->hash, parser->buffer, parser->idx); + ftrace_process_regex(iter, parser->buffer, + parser->idx, enable); } trace_parser_put(parser); @@ -5721,8 +5750,11 @@ static int referenced_filters(struct dyn_ftrace *rec) int cnt = 0; for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) { - if (ops_references_rec(ops, rec)) - cnt++; + if (ops_references_rec(ops, rec)) { + cnt++; + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) + rec->flags |= FTRACE_FL_REGS; + } } return cnt; @@ -5871,8 +5903,8 @@ void ftrace_module_enable(struct module *mod) if (ftrace_start_up) cnt += referenced_filters(rec); - /* This clears FTRACE_FL_DISABLED */ - rec->flags = cnt; + rec->flags &= ~FTRACE_FL_DISABLED; + rec->flags += cnt; if (ftrace_start_up && cnt) { int failed = __ftrace_replace_code(rec, 1); @@ -6081,7 +6113,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op; int bit; - bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX); + bit = trace_test_and_set_recursion(TRACE_LIST_START); if (bit < 0) return; @@ -6156,17 +6188,15 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip, { int bit; - if ((op->flags & FTRACE_OPS_FL_RCU) && !rcu_is_watching()) - return; - - bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX); + bit = trace_test_and_set_recursion(TRACE_LIST_START); if (bit < 0) return; preempt_disable_notrace(); - if (!(op->flags & FTRACE_OPS_FL_PER_CPU) || - !ftrace_function_local_disabled(op)) { + if ((!(op->flags & FTRACE_OPS_FL_RCU) || rcu_is_watching()) && + (!(op->flags & FTRACE_OPS_FL_PER_CPU) || + !ftrace_function_local_disabled(op))) { op->func(ip, parent_ip, op, regs); } @@ -6239,12 +6269,12 @@ void ftrace_pid_follow_fork(struct trace_array *tr, bool enable) if (enable) { register_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork, tr); - register_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit, + register_trace_sched_process_free(ftrace_pid_follow_sched_process_exit, tr); } else { unregister_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork, tr); - unregister_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit, + unregister_trace_sched_process_free(ftrace_pid_follow_sched_process_exit, tr); } } @@ -6645,7 +6675,6 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) } if (t->ret_stack == NULL) { - atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); t->curr_ret_stack = -1; /* Make sure the tasks see the -1 first: */ @@ -6857,7 +6886,6 @@ static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack); static void graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) { - atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); t->ftrace_timestamp = 0; /* make curr_ret_stack visible before we add the ret_stack */ diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 8123a8b53c54..359f44cee08a 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -416,14 +416,16 @@ struct rb_event_info { /* * Used for which event context the event is in. - * NMI = 0 - * IRQ = 1 - * SOFTIRQ = 2 - * NORMAL = 3 + * TRANSITION = 0 + * NMI = 1 + * IRQ = 2 + * SOFTIRQ = 3 + * NORMAL = 4 * * See trace_recursive_lock() comment below for more details. */ enum { + RB_CTX_TRANSITION, RB_CTX_NMI, RB_CTX_IRQ, RB_CTX_SOFTIRQ, @@ -1625,18 +1627,18 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, { struct ring_buffer_per_cpu *cpu_buffer; unsigned long nr_pages; - int cpu, err = 0; + int cpu, err; /* * Always succeed at resizing a non-existent buffer: */ if (!buffer) - return size; + return 0; /* Make sure the requested buffer exists */ if (cpu_id != RING_BUFFER_ALL_CPUS && !cpumask_test_cpu(cpu_id, buffer->cpumask)) - return size; + return 0; nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); @@ -1776,7 +1778,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, } mutex_unlock(&buffer->mutex); - return size; + return 0; out_err: for_each_buffer_cpu(buffer, cpu) { @@ -2553,10 +2555,10 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) * a bit of overhead in something as critical as function tracing, * we use a bitmask trick. * - * bit 0 = NMI context - * bit 1 = IRQ context - * bit 2 = SoftIRQ context - * bit 3 = normal context. + * bit 1 = NMI context + * bit 2 = IRQ context + * bit 3 = SoftIRQ context + * bit 4 = normal context. * * This works because this is the order of contexts that can * preempt other contexts. A SoftIRQ never preempts an IRQ @@ -2579,6 +2581,30 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) * The least significant bit can be cleared this way, and it * just so happens that it is the same bit corresponding to * the current context. + * + * Now the TRANSITION bit breaks the above slightly. The TRANSITION bit + * is set when a recursion is detected at the current context, and if + * the TRANSITION bit is already set, it will fail the recursion. + * This is needed because there's a lag between the changing of + * interrupt context and updating the preempt count. In this case, + * a false positive will be found. To handle this, one extra recursion + * is allowed, and this is done by the TRANSITION bit. If the TRANSITION + * bit is already set, then it is considered a recursion and the function + * ends. Otherwise, the TRANSITION bit is set, and that bit is returned. + * + * On the trace_recursive_unlock(), the TRANSITION bit will be the first + * to be cleared. Even if it wasn't the context that set it. That is, + * if an interrupt comes in while NORMAL bit is set and the ring buffer + * is called before preempt_count() is updated, since the check will + * be on the NORMAL bit, the TRANSITION bit will then be set. If an + * NMI then comes in, it will set the NMI bit, but when the NMI code + * does the trace_recursive_unlock() it will clear the TRANSTION bit + * and leave the NMI bit set. But this is fine, because the interrupt + * code that set the TRANSITION bit will then clear the NMI bit when it + * calls trace_recursive_unlock(). If another NMI comes in, it will + * set the TRANSITION bit and continue. + * + * Note: The TRANSITION bit only handles a single transition between context. */ static __always_inline int @@ -2597,8 +2623,16 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) } else bit = RB_CTX_NORMAL; - if (unlikely(val & (1 << bit))) - return 1; + if (unlikely(val & (1 << bit))) { + /* + * It is possible that this was called by transitioning + * between interrupt context, and preempt_count() has not + * been updated yet. In this case, use the TRANSITION bit. + */ + bit = RB_CTX_TRANSITION; + if (val & (1 << bit)) + return 1; + } val |= (1 << bit); cpu_buffer->current_context = val; @@ -3020,10 +3054,30 @@ static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) if (unlikely(!head)) return true; - return reader->read == rb_page_commit(reader) && - (commit == reader || - (commit == head && - head->read == rb_page_commit(commit))); + /* Reader should exhaust content in reader page */ + if (reader->read != rb_page_commit(reader)) + return false; + + /* + * If writers are committing on the reader page, knowing all + * committed content has been read, the ring buffer is empty. + */ + if (commit == reader) + return true; + + /* + * If writers are committing on a page other than reader page + * and head page, there should always be content to read. + */ + if (commit != head) + return false; + + /* + * Writers are committing on the head page, we just need + * to care about there're committed data, and the reader will + * swap reader page with head page when it is to read data. + */ + return rb_page_commit(commit) == 0; } /** @@ -4228,6 +4282,8 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) if (!cpumask_test_cpu(cpu, buffer->cpumask)) return; + /* prevent another thread from changing buffer sizes */ + mutex_lock(&buffer->mutex); atomic_inc(&buffer->resize_disabled); atomic_inc(&cpu_buffer->record_disabled); @@ -4251,6 +4307,8 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) atomic_dec(&cpu_buffer->record_disabled); atomic_dec(&buffer->resize_disabled); + + mutex_unlock(&buffer->mutex); } EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 207d7c35214f..fd8e1ec39c27 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1723,8 +1723,15 @@ void tracing_reset_all_online_cpus(void) } } +/* + * The tgid_map array maps from pid to tgid; i.e. the value stored at index i + * is the tgid last observed corresponding to pid=i. + */ static int *tgid_map; +/* The maximum valid index into tgid_map. */ +static size_t tgid_map_max; + #define SAVED_CMDLINES_DEFAULT 128 #define NO_CMDLINE_MAP UINT_MAX static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED; @@ -1737,9 +1744,6 @@ struct saved_cmdlines_buffer { }; static struct saved_cmdlines_buffer *savedcmd; -/* temporary disable recording */ -static atomic_t trace_record_taskinfo_disabled __read_mostly; - static inline char *get_saved_cmdlines(int idx) { return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN]; @@ -1928,14 +1932,13 @@ static void tracing_stop_tr(struct trace_array *tr) static int trace_save_cmdline(struct task_struct *tsk) { - unsigned pid, idx; + unsigned tpid, idx; /* treat recording of idle task as a success */ if (!tsk->pid) return 1; - if (unlikely(tsk->pid > PID_MAX_DEFAULT)) - return 0; + tpid = tsk->pid & (PID_MAX_DEFAULT - 1); /* * It's not the end of the world if we don't get @@ -1946,26 +1949,15 @@ static int trace_save_cmdline(struct task_struct *tsk) if (!arch_spin_trylock(&trace_cmdline_lock)) return 0; - idx = savedcmd->map_pid_to_cmdline[tsk->pid]; + idx = savedcmd->map_pid_to_cmdline[tpid]; if (idx == NO_CMDLINE_MAP) { idx = (savedcmd->cmdline_idx + 1) % savedcmd->cmdline_num; - /* - * Check whether the cmdline buffer at idx has a pid - * mapped. We are going to overwrite that entry so we - * need to clear the map_pid_to_cmdline. Otherwise we - * would read the new comm for the old pid. - */ - pid = savedcmd->map_cmdline_to_pid[idx]; - if (pid != NO_CMDLINE_MAP) - savedcmd->map_pid_to_cmdline[pid] = NO_CMDLINE_MAP; - - savedcmd->map_cmdline_to_pid[idx] = tsk->pid; - savedcmd->map_pid_to_cmdline[tsk->pid] = idx; - + savedcmd->map_pid_to_cmdline[tpid] = idx; savedcmd->cmdline_idx = idx; } + savedcmd->map_cmdline_to_pid[idx] = tsk->pid; set_cmdline(idx, tsk->comm); arch_spin_unlock(&trace_cmdline_lock); @@ -1976,6 +1968,7 @@ static int trace_save_cmdline(struct task_struct *tsk) static void __trace_find_cmdline(int pid, char comm[]) { unsigned map; + int tpid; if (!pid) { strcpy(comm, "<idle>"); @@ -1987,16 +1980,16 @@ static void __trace_find_cmdline(int pid, char comm[]) return; } - if (pid > PID_MAX_DEFAULT) { - strcpy(comm, "<...>"); - return; + tpid = pid & (PID_MAX_DEFAULT - 1); + map = savedcmd->map_pid_to_cmdline[tpid]; + if (map != NO_CMDLINE_MAP) { + tpid = savedcmd->map_cmdline_to_pid[map]; + if (tpid == pid) { + strlcpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN); + return; + } } - - map = savedcmd->map_pid_to_cmdline[pid]; - if (map != NO_CMDLINE_MAP) - strlcpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN); - else - strcpy(comm, "<...>"); + strcpy(comm, "<...>"); } void trace_find_cmdline(int pid, char comm[]) @@ -2010,24 +2003,41 @@ void trace_find_cmdline(int pid, char comm[]) preempt_enable(); } +static int *trace_find_tgid_ptr(int pid) +{ + /* + * Pairs with the smp_store_release in set_tracer_flag() to ensure that + * if we observe a non-NULL tgid_map then we also observe the correct + * tgid_map_max. + */ + int *map = smp_load_acquire(&tgid_map); + + if (unlikely(!map || pid > tgid_map_max)) + return NULL; + + return &map[pid]; +} + int trace_find_tgid(int pid) { - if (unlikely(!tgid_map || !pid || pid > PID_MAX_DEFAULT)) - return 0; + int *ptr = trace_find_tgid_ptr(pid); - return tgid_map[pid]; + return ptr ? *ptr : 0; } static int trace_save_tgid(struct task_struct *tsk) { + int *ptr; + /* treat recording of idle task as a success */ if (!tsk->pid) return 1; - if (unlikely(!tgid_map || tsk->pid > PID_MAX_DEFAULT)) + ptr = trace_find_tgid_ptr(tsk->pid); + if (!ptr) return 0; - tgid_map[tsk->pid] = tsk->tgid; + *ptr = tsk->tgid; return 1; } @@ -2035,8 +2045,6 @@ static bool tracing_record_taskinfo_skip(int flags) { if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID)))) return true; - if (atomic_read(&trace_record_taskinfo_disabled) || !tracing_is_on()) - return true; if (!__this_cpu_read(trace_taskinfo_save)) return true; return false; @@ -2285,7 +2293,7 @@ trace_event_buffer_lock_reserve(struct ring_buffer **current_rb, (entry = this_cpu_read(trace_buffered_event))) { /* Try to use the per cpu buffer first */ val = this_cpu_inc_return(trace_buffered_event_cnt); - if (val == 1) { + if ((len < (PAGE_SIZE - sizeof(*entry) - sizeof(entry->array[0]))) && val == 1) { trace_event_setup(entry, type, flags, pc); entry->array[0] = len; return entry; @@ -2404,7 +2412,7 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr, * two. They are that meaningful. */ ftrace_trace_stack(tr, buffer, flags, regs ? 0 : 4, pc, regs); - ftrace_trace_userstack(buffer, flags, pc); + ftrace_trace_userstack(tr, buffer, flags, pc); } /* @@ -2631,7 +2639,8 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, size *= sizeof(unsigned long); event = __trace_buffer_lock_reserve(buffer, TRACE_STACK, - sizeof(*entry) + size, flags, pc); + (sizeof(*entry) - sizeof(entry->caller)) + size, + flags, pc); if (!event) goto out; entry = ring_buffer_event_data(event); @@ -2734,14 +2743,15 @@ void trace_dump_stack(int skip) static DEFINE_PER_CPU(int, user_stack_count); void -ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) +ftrace_trace_userstack(struct trace_array *tr, + struct ring_buffer *buffer, unsigned long flags, int pc) { struct trace_event_call *call = &event_user_stack; struct ring_buffer_event *event; struct userstack_entry *entry; struct stack_trace trace; - if (!(global_trace.trace_flags & TRACE_ITER_USERSTACKTRACE)) + if (!(tr->trace_flags & TRACE_ITER_USERSTACKTRACE)) return; /* @@ -2800,7 +2810,7 @@ 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; /* * Thise allows for lockless recording. If we're nested too deeply, then @@ -2810,14 +2820,14 @@ 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++; /* Interrupts must see nesting incremented before we use the buffer */ barrier(); - return &buffer->buffer[buffer->nesting][0]; + return &buffer->buffer[buffer->nesting - 1][0]; } static void put_trace_buf(void) @@ -2829,7 +2839,7 @@ static void put_trace_buf(void) static int alloc_percpu_trace_buffer(void) { - struct trace_buffer_struct *buffers; + struct trace_buffer_struct __percpu *buffers; buffers = alloc_percpu(struct trace_buffer_struct); if (WARN(!buffers, "Could not allocate percpu trace_printk buffer")) @@ -3035,6 +3045,9 @@ int trace_array_printk(struct trace_array *tr, if (!(global_trace.trace_flags & TRACE_ITER_PRINTK)) return 0; + if (!tr) + return -ENOENT; + va_start(ap, fmt); ret = trace_array_vprintk(tr, ip, fmt, ap); va_end(ap); @@ -3265,9 +3278,6 @@ static void *s_start(struct seq_file *m, loff_t *pos) return ERR_PTR(-EBUSY); #endif - if (!iter->snapshot) - atomic_inc(&trace_record_taskinfo_disabled); - if (*pos != iter->pos) { iter->ent = NULL; iter->cpu = 0; @@ -3310,9 +3320,6 @@ static void s_stop(struct seq_file *m, void *p) return; #endif - if (!iter->snapshot) - atomic_dec(&trace_record_taskinfo_disabled); - trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); } @@ -4370,6 +4377,8 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) { + int *map; + if ((mask == TRACE_ITER_RECORD_TGID) || (mask == TRACE_ITER_RECORD_CMD)) lockdep_assert_held(&event_mutex); @@ -4392,9 +4401,19 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) trace_event_enable_cmd_record(enabled); if (mask == TRACE_ITER_RECORD_TGID) { - if (!tgid_map) - tgid_map = kzalloc((PID_MAX_DEFAULT + 1) * sizeof(*tgid_map), - GFP_KERNEL); + if (!tgid_map) { + tgid_map_max = pid_max; + map = kzalloc((tgid_map_max + 1) * sizeof(*tgid_map), + GFP_KERNEL); + + /* + * Pairs with smp_load_acquire() in + * trace_find_tgid_ptr() to ensure that if it observes + * the tgid_map we just allocated then it also observes + * the corresponding tgid_map_max value. + */ + smp_store_release(&tgid_map, map); + } if (!tgid_map) { tr->trace_flags &= ~TRACE_ITER_RECORD_TGID; return -ENOMEM; @@ -4767,37 +4786,16 @@ static const struct file_operations tracing_readme_fops = { static void *saved_tgids_next(struct seq_file *m, void *v, loff_t *pos) { - int *ptr = v; - - if (*pos || m->count) - ptr++; - - (*pos)++; - - for (; ptr <= &tgid_map[PID_MAX_DEFAULT]; ptr++) { - if (trace_find_tgid(*ptr)) - return ptr; - } + int pid = ++(*pos); - return NULL; + return trace_find_tgid_ptr(pid); } static void *saved_tgids_start(struct seq_file *m, loff_t *pos) { - void *v; - loff_t l = 0; - - if (!tgid_map) - return NULL; + int pid = *pos; - v = &tgid_map[0]; - while (l <= *pos) { - v = saved_tgids_next(m, v, &l); - if (!v) - return NULL; - } - - return v; + return trace_find_tgid_ptr(pid); } static void saved_tgids_stop(struct seq_file *m, void *v) @@ -4806,9 +4804,14 @@ static void saved_tgids_stop(struct seq_file *m, void *v) static int saved_tgids_show(struct seq_file *m, void *v) { - int pid = (int *)v - tgid_map; + int *entry = (int *)v; + int pid = entry - tgid_map; + int tgid = *entry; - seq_printf(m, "%d %d\n", pid, trace_find_tgid(pid)); + if (tgid == 0) + return SEQ_SKIP; + + seq_printf(m, "%d %d\n", pid, tgid); return 0; } @@ -7666,6 +7669,19 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) */ allocate_snapshot = false; #endif + + /* + * Because of some magic with the way alloc_percpu() works on + * x86_64, we need to synchronize the pgd of all the tables, + * otherwise the trace events that happen in x86_64 page fault + * handlers can't cope with accessing the chance that a + * alloc_percpu()'d memory might be touched in the page fault trace + * event. Oh, and we need to audit all other alloc_percpu() and vmalloc() + * calls in tracing, because something might get triggered within a + * page fault trace event! + */ + vmalloc_sync_mappings(); + return 0; } @@ -7720,6 +7736,7 @@ static int instance_mkdir(const char *name) struct trace_array *tr; int ret; + mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = -EEXIST; @@ -7775,6 +7792,7 @@ static int instance_mkdir(const char *name) list_add(&tr->list, &ftrace_trace_arrays); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); return 0; @@ -7786,6 +7804,7 @@ static int instance_mkdir(const char *name) out_unlock: mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); return ret; @@ -7798,6 +7817,7 @@ static int instance_rmdir(const char *name) int ret; int i; + mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = -ENODEV; @@ -7843,6 +7863,7 @@ static int instance_rmdir(const char *name) out_unlock: mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); return ret; } @@ -8325,7 +8346,7 @@ __init static int tracer_alloc_buffers(void) goto out_free_buffer_mask; /* Only allocate trace_printk buffers if a trace_printk exists */ - if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt) + if (&__stop___trace_bprintk_fmt != &__start___trace_bprintk_fmt) /* Must be called before global_trace.buffer is allocated */ trace_printk_init_buffers(); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index c4c61ebb8d05..365bc02230a9 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -459,23 +459,8 @@ struct tracer { * When function tracing occurs, the following steps are made: * If arch does not support a ftrace feature: * call internal function (uses INTERNAL bits) which calls... - * If callback is registered to the "global" list, the list - * function is called and recursion checks the GLOBAL bits. - * then this function calls... * The function callback, which can use the FTRACE bits to * check for recursion. - * - * Now if the arch does not suppport a feature, and it calls - * the global list function which calls the ftrace callback - * all three of these steps will do a recursion protection. - * There's no reason to do one if the previous caller already - * did. The recursion that we are protecting against will - * go through the same steps again. - * - * To prevent the multiple recursion checks, if a recursion - * bit is set that is higher than the MAX bit of the current - * check, then we know that the check was made by the previous - * caller, and we can skip the current check. */ enum { TRACE_BUFFER_BIT, @@ -488,12 +473,14 @@ enum { TRACE_FTRACE_NMI_BIT, TRACE_FTRACE_IRQ_BIT, TRACE_FTRACE_SIRQ_BIT, + TRACE_FTRACE_TRANSITION_BIT, - /* INTERNAL_BITs must be greater than FTRACE_BITs */ + /* Internal use recursion bits */ TRACE_INTERNAL_BIT, TRACE_INTERNAL_NMI_BIT, TRACE_INTERNAL_IRQ_BIT, TRACE_INTERNAL_SIRQ_BIT, + TRACE_INTERNAL_TRANSITION_BIT, TRACE_BRANCH_BIT, /* @@ -545,12 +532,18 @@ enum { #define TRACE_CONTEXT_BITS 4 #define TRACE_FTRACE_START TRACE_FTRACE_BIT -#define TRACE_FTRACE_MAX ((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1) #define TRACE_LIST_START TRACE_INTERNAL_BIT -#define TRACE_LIST_MAX ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1) -#define TRACE_CONTEXT_MASK TRACE_LIST_MAX +#define TRACE_CONTEXT_MASK ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1) + +enum { + TRACE_CTX_NMI, + TRACE_CTX_IRQ, + TRACE_CTX_SOFTIRQ, + TRACE_CTX_NORMAL, + TRACE_CTX_TRANSITION, +}; static __always_inline int trace_get_context_bit(void) { @@ -558,30 +551,36 @@ static __always_inline int trace_get_context_bit(void) if (in_interrupt()) { if (in_nmi()) - bit = 0; + bit = TRACE_CTX_NMI; else if (in_irq()) - bit = 1; + bit = TRACE_CTX_IRQ; else - bit = 2; + bit = TRACE_CTX_SOFTIRQ; } else - bit = 3; + bit = TRACE_CTX_NORMAL; return bit; } -static __always_inline int trace_test_and_set_recursion(int start, int max) +static __always_inline int trace_test_and_set_recursion(int start) { unsigned int val = current->trace_recursion; int bit; - /* A previous recursion check was made */ - if ((val & TRACE_CONTEXT_MASK) > max) - return 0; - bit = trace_get_context_bit() + start; - if (unlikely(val & (1 << bit))) - return -1; + if (unlikely(val & (1 << bit))) { + /* + * It could be that preempt_count has not been updated during + * a switch between contexts. Allow for a single recursion. + */ + bit = start + TRACE_CTX_TRANSITION; + if (trace_recursion_test(bit)) + return -1; + trace_recursion_set(bit); + barrier(); + return bit; + } val |= 1 << bit; current->trace_recursion = val; @@ -594,9 +593,6 @@ static __always_inline void trace_clear_recursion(int bit) { unsigned int val = current->trace_recursion; - if (!bit) - return; - bit = 1 << bit; val &= ~bit; @@ -719,13 +715,15 @@ void update_max_tr_single(struct trace_array *tr, #endif /* CONFIG_TRACER_MAX_TRACE */ #ifdef CONFIG_STACKTRACE -void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, +void ftrace_trace_userstack(struct trace_array *tr, + struct ring_buffer *buffer, unsigned long flags, int pc); void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc); #else -static inline void ftrace_trace_userstack(struct ring_buffer *buffer, +static inline void ftrace_trace_userstack(struct trace_array *tr, + struct ring_buffer *buffer, unsigned long flags, int pc) { } @@ -1365,14 +1363,26 @@ __event_trigger_test_discard(struct trace_event_file *file, if (eflags & EVENT_FILE_FL_TRIGGER_COND) *tt = event_triggers_call(file, entry); - 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_clock.c b/kernel/trace/trace_clock.c index 5fdc779f411d..b3b02d2c2926 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -94,33 +94,49 @@ u64 notrace trace_clock_global(void) { unsigned long flags; int this_cpu; - u64 now; + u64 now, prev_time; local_irq_save(flags); this_cpu = raw_smp_processor_id(); - now = sched_clock_cpu(this_cpu); + /* - * If in an NMI context then dont risk lockups and return the - * cpu_clock() time: + * The global clock "guarantees" that the events are ordered + * between CPUs. But if two events on two different CPUS call + * trace_clock_global at roughly the same time, it really does + * not matter which one gets the earlier time. Just make sure + * that the same CPU will always show a monotonic clock. + * + * Use a read memory barrier to get the latest written + * time that was recorded. */ - if (unlikely(in_nmi())) - goto out; + smp_rmb(); + prev_time = READ_ONCE(trace_clock_struct.prev_time); + now = sched_clock_cpu(this_cpu); - arch_spin_lock(&trace_clock_struct.lock); + /* Make sure that now is always greater than or equal to prev_time */ + if ((s64)(now - prev_time) < 0) + now = prev_time; /* - * TODO: if this happens often then maybe we should reset - * my_scd->clock to prev_time+1, to make sure - * we start ticking with the local clock from now on? + * If in an NMI context then dont risk lockups and simply return + * the current time. */ - if ((s64)(now - trace_clock_struct.prev_time) < 0) - now = trace_clock_struct.prev_time + 1; + if (unlikely(in_nmi())) + goto out; - trace_clock_struct.prev_time = now; + /* Tracing can cause strange recursion, always use a try lock */ + if (arch_spin_trylock(&trace_clock_struct.lock)) { + /* Reread prev_time in case it was already updated */ + prev_time = READ_ONCE(trace_clock_struct.prev_time); + if ((s64)(now - prev_time) < 0) + now = prev_time; - arch_spin_unlock(&trace_clock_struct.lock); + trace_clock_struct.prev_time = now; + /* The unlock acts as the wmb for the above rmb */ + arch_spin_unlock(&trace_clock_struct.lock); + } out: local_irq_restore(flags); diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index e3a658bac10f..ff91acff7294 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -179,7 +179,7 @@ FTRACE_ENTRY(kernel_stack, stack_entry, F_STRUCT( __field( int, size ) - __dynamic_array(unsigned long, caller ) + __array( unsigned long, caller, FTRACE_STACK_ENTRIES ) ), F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 2b0a01b2be2d..1285ef6e2d14 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -533,12 +533,12 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable) if (enable) { register_trace_prio_sched_process_fork(event_filter_pid_sched_process_fork, tr, INT_MIN); - register_trace_prio_sched_process_exit(event_filter_pid_sched_process_exit, + register_trace_prio_sched_process_free(event_filter_pid_sched_process_exit, tr, INT_MAX); } else { unregister_trace_sched_process_fork(event_filter_pid_sched_process_fork, tr); - unregister_trace_sched_process_exit(event_filter_pid_sched_process_exit, + unregister_trace_sched_process_free(event_filter_pid_sched_process_exit, tr); } } @@ -799,6 +799,8 @@ static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) char *event = NULL, *sub = NULL, *match; int ret; + if (!tr) + return -ENOENT; /* * The buf format can be <subsystem>:<event-name> * *:<event-name> means any event by that name. @@ -1112,7 +1114,8 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, mutex_lock(&event_mutex); list_for_each_entry(file, &tr->events, list) { call = file->event_call; - if (!trace_event_name(call) || !call->class || !call->class->reg) + if ((call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) || + !trace_event_name(call) || !call->class || !call->class->reg) continue; if (system && strcmp(call->class->system, system->name) != 0) @@ -1403,8 +1406,8 @@ static int subsystem_open(struct inode *inode, struct file *filp) return -ENODEV; /* Make sure the system still exists */ - mutex_lock(&trace_types_lock); mutex_lock(&event_mutex); + mutex_lock(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { list_for_each_entry(dir, &tr->systems, list) { if (dir == inode->i_private) { @@ -1418,8 +1421,8 @@ static int subsystem_open(struct inode *inode, struct file *filp) } } exit_loop: - mutex_unlock(&event_mutex); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); if (!system) return -ENODEV; @@ -2251,12 +2254,19 @@ static struct trace_event_file * trace_create_new_event(struct trace_event_call *call, struct trace_array *tr) { + struct trace_pid_list *pid_list; struct trace_event_file *file; 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)); + + if (pid_list) + file->flags |= EVENT_FILE_FL_PID_FILTER; + file->event_call = call; file->tr = tr; atomic_set(&file->sm_ref, 0); @@ -2305,15 +2315,15 @@ static void __add_event_to_tracers(struct trace_event_call *call); int trace_add_event_call(struct trace_event_call *call) { int ret; - mutex_lock(&trace_types_lock); mutex_lock(&event_mutex); + mutex_lock(&trace_types_lock); ret = __register_event(call, NULL); if (ret >= 0) __add_event_to_tracers(call); - mutex_unlock(&event_mutex); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); return ret; } @@ -2367,13 +2377,13 @@ int trace_remove_event_call(struct trace_event_call *call) { int ret; - mutex_lock(&trace_types_lock); mutex_lock(&event_mutex); + mutex_lock(&trace_types_lock); down_write(&trace_event_sem); ret = probe_remove_event_call(call); up_write(&trace_event_sem); - mutex_unlock(&event_mutex); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); return ret; } @@ -2435,8 +2445,8 @@ static int trace_module_notify(struct notifier_block *self, { struct module *mod = data; - mutex_lock(&trace_types_lock); mutex_lock(&event_mutex); + mutex_lock(&trace_types_lock); switch (val) { case MODULE_STATE_COMING: trace_module_add_events(mod); @@ -2445,8 +2455,8 @@ static int trace_module_notify(struct notifier_block *self, trace_module_remove_events(mod); break; } - mutex_unlock(&event_mutex); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); return 0; } @@ -2961,24 +2971,24 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) * creates the event hierachry in the @parent/events directory. * * Returns 0 on success. + * + * Must be called with event_mutex held. */ int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr) { int ret; - mutex_lock(&event_mutex); + lockdep_assert_held(&event_mutex); ret = create_event_toplevel_files(parent, tr); if (ret) - goto out_unlock; + goto out; down_write(&trace_event_sem); __trace_add_event_dirs(tr); up_write(&trace_event_sem); - out_unlock: - mutex_unlock(&event_mutex); - + out: return ret; } @@ -3007,9 +3017,10 @@ early_event_add_tracer(struct dentry *parent, struct trace_array *tr) return ret; } +/* Must be called with event_mutex held */ int event_trace_del_tracer(struct trace_array *tr) { - mutex_lock(&event_mutex); + lockdep_assert_held(&event_mutex); /* Disable any event triggers and associated soft-disabled events */ clear_event_triggers(tr); @@ -3030,8 +3041,6 @@ int event_trace_del_tracer(struct trace_array *tr) tr->event_dir = NULL; - mutex_unlock(&event_mutex); - return 0; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index e8c9eba9b1e7..df94c32a44f3 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -375,7 +375,9 @@ static struct hist_field *create_hist_field(struct ftrace_event_field *field, if (WARN_ON_ONCE(!field)) goto out; - if (is_string_field(field)) { + /* Pointers to strings are just pointers and dangerous to dereference */ + if (is_string_field(field) && + (field->filter_type != FILTER_PTR_STRING)) { flags |= HIST_FIELD_FL_STRING; if (field->filter_type == FILTER_STATIC_STRING) @@ -864,8 +866,6 @@ static inline void add_to_key(char *compound_key, void *key, field = key_field->field; if (field->filter_type == FILTER_DYN_STRING) size = *(u32 *)(rec + field->offset) >> 16; - else if (field->filter_type == FILTER_PTR_STRING) - size = strlen(key); else if (field->filter_type == FILTER_STATIC_STRING) size = field->size; diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 31e91efe243e..13f501337308 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -223,11 +223,17 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file) static int trigger_process_regex(struct trace_event_file *file, char *buff) { - char *command, *next = buff; + char *command, *next; struct event_command *p; int ret = -EINVAL; + next = buff = skip_spaces(buff); command = strsep(&next, ": \t"); + if (next) { + next = skip_spaces(next); + if (!*next) + next = NULL; + } command = (command[0] != '!') ? command : command + 1; mutex_lock(&trigger_cmd_mutex); @@ -630,8 +636,14 @@ event_trigger_callback(struct event_command *cmd_ops, int ret; /* separate the trigger from the filter (t:n [if filter]) */ - if (param && isdigit(param[0])) + if (param && isdigit(param[0])) { trigger = strsep(¶m, " \t"); + if (param) { + param = skip_spaces(param); + if (!*param) + param = NULL; + } + } trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger); @@ -1075,14 +1087,10 @@ register_snapshot_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *data, struct trace_event_file *file) { - int ret = register_trigger(glob, ops, data, file); - - if (ret > 0 && tracing_alloc_snapshot_instance(file->tr) != 0) { - unregister_trigger(glob, ops, data, file); - ret = 0; - } + if (tracing_alloc_snapshot_instance(file->tr) != 0) + return 0; - return ret; + return register_trigger(glob, ops, data, file); } static int @@ -1346,6 +1354,11 @@ int event_enable_trigger_func(struct event_command *cmd_ops, trigger = strsep(¶m, " \t"); if (!trigger) return -EINVAL; + if (param) { + param = skip_spaces(param); + if (!*param) + param = NULL; + } system = strsep(&trigger, ":"); if (!trigger) diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 27f7ad12c4b1..7a5d3d422215 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -138,7 +138,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, pc = preempt_count(); preempt_disable_notrace(); - bit = trace_test_and_set_recursion(TRACE_FTRACE_START, TRACE_FTRACE_MAX); + bit = trace_test_and_set_recursion(TRACE_FTRACE_START); if (bit < 0) goto out; diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index bff6c033d70e..64a98a5bb641 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -272,6 +272,7 @@ static bool disable_migrate; static void move_to_next_cpu(void) { struct cpumask *current_mask = &save_cpumask; + struct trace_array *tr = hwlat_trace; int next_cpu; if (disable_migrate) @@ -285,7 +286,7 @@ static void move_to_next_cpu(void) goto disable; get_online_cpus(); - cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask); + cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask); next_cpu = cpumask_next(smp_processor_id(), current_mask); put_online_cpus(); @@ -359,7 +360,7 @@ static int start_kthread(struct trace_array *tr) /* Just pick the first CPU on first iteration */ current_mask = &save_cpumask; get_online_cpus(); - cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask); + cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask); put_online_cpus(); next_cpu = cpumask_first(current_mask); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index ea20274a105a..d66aed6e9c75 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -877,6 +877,8 @@ static int probes_seq_show(struct seq_file *m, void *v) int i; seq_putc(m, trace_kprobe_is_return(tk) ? 'r' : 'p'); + if (trace_kprobe_is_return(tk) && tk->rp.maxactive) + seq_printf(m, "%d", tk->rp.maxactive); seq_printf(m, ":%s/%s", tk->tp.call.class->system, trace_event_name(&tk->tp.call)); diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index cd70eb5df38e..8ae065783017 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -492,8 +492,13 @@ trace_selftest_function_recursion(void) unregister_ftrace_function(&test_rec_probe); ret = -1; - if (trace_selftest_recursion_cnt != 1) { - pr_cont("*callback not called once (%d)* ", + /* + * Recursion allows for transitions between context, + * and may call the callback twice. + */ + if (trace_selftest_recursion_cnt != 1 && + trace_selftest_recursion_cnt != 2) { + pr_cont("*callback not called once (or twice) (%d)* ", trace_selftest_recursion_cnt); goto out; } diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 35b2ba07f3c6..572c0854d631 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -24,6 +24,7 @@ #include <linux/jhash.h> #include <linux/slab.h> #include <linux/sort.h> +#include <linux/kmemleak.h> #include "tracing_map.h" #include "trace.h" @@ -227,6 +228,7 @@ 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]); } @@ -262,6 +264,7 @@ 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; @@ -703,29 +706,35 @@ int tracing_map_init(struct tracing_map *map) return err; } -static int cmp_entries_dup(const struct tracing_map_sort_entry **a, - const struct tracing_map_sort_entry **b) +static int cmp_entries_dup(const void *A, const void *B) { + const struct tracing_map_sort_entry *a, *b; int ret = 0; - if (memcmp((*a)->key, (*b)->key, (*a)->elt->map->key_size)) + a = *(const struct tracing_map_sort_entry **)A; + b = *(const struct tracing_map_sort_entry **)B; + + if (memcmp(a->key, b->key, a->elt->map->key_size)) ret = 1; return ret; } -static int cmp_entries_sum(const struct tracing_map_sort_entry **a, - const struct tracing_map_sort_entry **b) +static int cmp_entries_sum(const void *A, const void *B) { const struct tracing_map_elt *elt_a, *elt_b; + const struct tracing_map_sort_entry *a, *b; struct tracing_map_sort_key *sort_key; struct tracing_map_field *field; tracing_map_cmp_fn_t cmp_fn; void *val_a, *val_b; int ret = 0; - elt_a = (*a)->elt; - elt_b = (*b)->elt; + a = *(const struct tracing_map_sort_entry **)A; + b = *(const struct tracing_map_sort_entry **)B; + + elt_a = a->elt; + elt_b = b->elt; sort_key = &elt_a->map->sort_key; @@ -742,18 +751,21 @@ static int cmp_entries_sum(const struct tracing_map_sort_entry **a, return ret; } -static int cmp_entries_key(const struct tracing_map_sort_entry **a, - const struct tracing_map_sort_entry **b) +static int cmp_entries_key(const void *A, const void *B) { const struct tracing_map_elt *elt_a, *elt_b; + const struct tracing_map_sort_entry *a, *b; struct tracing_map_sort_key *sort_key; struct tracing_map_field *field; tracing_map_cmp_fn_t cmp_fn; void *val_a, *val_b; int ret = 0; - elt_a = (*a)->elt; - elt_b = (*b)->elt; + a = *(const struct tracing_map_sort_entry **)A; + b = *(const struct tracing_map_sort_entry **)B; + + elt_a = a->elt; + elt_b = b->elt; sort_key = &elt_a->map->sort_key; @@ -926,10 +938,8 @@ static void sort_secondary(struct tracing_map *map, struct tracing_map_sort_key *primary_key, struct tracing_map_sort_key *secondary_key) { - int (*primary_fn)(const struct tracing_map_sort_entry **, - const struct tracing_map_sort_entry **); - int (*secondary_fn)(const struct tracing_map_sort_entry **, - const struct tracing_map_sort_entry **); + int (*primary_fn)(const void *, const void *); + int (*secondary_fn)(const void *, const void *); unsigned i, start = 0, n_sub = 1; if (is_key(map, primary_key->field_idx)) @@ -998,8 +1008,7 @@ int tracing_map_sort_entries(struct tracing_map *map, unsigned int n_sort_keys, struct tracing_map_sort_entry ***sort_entries) { - int (*cmp_entries_fn)(const struct tracing_map_sort_entry **, - const struct tracing_map_sort_entry **); + int (*cmp_entries_fn)(const void *, const void *); struct tracing_map_sort_entry *sort_entry, **entries; int i, n_entries, ret; diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index a170d83043a5..b65b2e7fd850 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -60,6 +60,12 @@ struct tp_probes { struct tracepoint_func probes[0]; }; +/* Called in removal of a func but failed to allocate a new tp_funcs */ +static void tp_stub_func(void) +{ + return; +} + static inline void *allocate_probes(int count) { struct tp_probes *p = kmalloc(count * sizeof(struct tracepoint_func) @@ -98,6 +104,7 @@ func_add(struct tracepoint_func **funcs, struct tracepoint_func *tp_func, { struct tracepoint_func *old, *new; int nr_probes = 0; + int stub_funcs = 0; int pos = -1; if (WARN_ON(!tp_func->func)) @@ -114,14 +121,34 @@ func_add(struct tracepoint_func **funcs, struct tracepoint_func *tp_func, if (old[nr_probes].func == tp_func->func && old[nr_probes].data == tp_func->data) return ERR_PTR(-EEXIST); + if (old[nr_probes].func == tp_stub_func) + stub_funcs++; } } - /* + 2 : one for new probe, one for NULL func */ - new = allocate_probes(nr_probes + 2); + /* + 2 : one for new probe, one for NULL func - stub functions */ + new = allocate_probes(nr_probes + 2 - stub_funcs); if (new == NULL) return ERR_PTR(-ENOMEM); if (old) { - if (pos < 0) { + if (stub_funcs) { + /* Need to copy one at a time to remove stubs */ + int probes = 0; + + pos = -1; + for (nr_probes = 0; old[nr_probes].func; nr_probes++) { + if (old[nr_probes].func == tp_stub_func) + continue; + if (pos < 0 && old[nr_probes].prio < prio) + pos = probes++; + new[probes++] = old[nr_probes]; + } + nr_probes = probes; + if (pos < 0) + pos = probes; + else + nr_probes--; /* Account for insertion */ + + } else if (pos < 0) { pos = nr_probes; memcpy(new, old, nr_probes * sizeof(struct tracepoint_func)); } else { @@ -155,8 +182,9 @@ static void *func_remove(struct tracepoint_func **funcs, /* (N -> M), (N > 1, M >= 0) probes */ if (tp_func->func) { for (nr_probes = 0; old[nr_probes].func; nr_probes++) { - if (old[nr_probes].func == tp_func->func && - old[nr_probes].data == tp_func->data) + if ((old[nr_probes].func == tp_func->func && + old[nr_probes].data == tp_func->data) || + old[nr_probes].func == tp_stub_func) nr_del++; } } @@ -175,14 +203,32 @@ static void *func_remove(struct tracepoint_func **funcs, /* N -> M, (N > 1, M > 0) */ /* + 1 for NULL */ new = allocate_probes(nr_probes - nr_del + 1); - if (new == NULL) - return ERR_PTR(-ENOMEM); - for (i = 0; old[i].func; i++) - if (old[i].func != tp_func->func - || old[i].data != tp_func->data) - new[j++] = old[i]; - new[nr_probes - nr_del].func = NULL; - *funcs = new; + if (new) { + for (i = 0; old[i].func; i++) + if ((old[i].func != tp_func->func + || old[i].data != tp_func->data) + && old[i].func != tp_stub_func) + new[j++] = old[i]; + new[nr_probes - nr_del].func = NULL; + *funcs = new; + } else { + /* + * Failed to allocate, replace the old function + * with calls to tp_stub_func. + */ + for (i = 0; old[i].func; i++) + if (old[i].func == tp_func->func && + old[i].data == tp_func->data) { + old[i].func = tp_stub_func; + /* Set the prio to the next event. */ + if (old[i + 1].func) + old[i].prio = + old[i + 1].prio; + else + old[i].prio = -1; + } + *funcs = old; + } } debug_print_probes(*funcs); return old; @@ -239,10 +285,12 @@ static int tracepoint_remove_func(struct tracepoint *tp, tp_funcs = rcu_dereference_protected(tp->funcs, lockdep_is_held(&tracepoints_mutex)); old = func_remove(&tp_funcs, func); - if (IS_ERR(old)) { - WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM); + if (WARN_ON_ONCE(IS_ERR(old))) return PTR_ERR(old); - } + + if (tp_funcs == old) + /* Failed allocating new tp_funcs, replaced func with stub */ + return 0; if (!tp_funcs) { /* Removed last function */ diff --git a/kernel/umh.c b/kernel/umh.c index 6ff9905250ff..9c41f05f969b 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -13,6 +13,7 @@ #include <linux/cred.h> #include <linux/file.h> #include <linux/fdtable.h> +#include <linux/fs_struct.h> #include <linux/workqueue.h> #include <linux/security.h> #include <linux/mount.h> @@ -71,6 +72,14 @@ static int call_usermodehelper_exec_async(void *data) spin_unlock_irq(¤t->sighand->siglock); /* + * Initial kernel threads share ther FS with init, in order to + * get the init root directory. But we've now created a new + * thread that is going to execve a user process and has its own + * 'struct fs_struct'. Reset umask to the default. + */ + current->fs->umask = 0022; + + /* * Our parent (unbound workqueue) runs with elevated scheduling * priority. Avoid propagating that into the userspace child. */ @@ -404,6 +413,11 @@ EXPORT_SYMBOL(call_usermodehelper_setup); * Runs a user-space application. The application is started * asynchronously if wait is not set, and runs as a child of system workqueues. * (ie. it runs with full root capabilities and optimized affinity). + * + * Note: successful return value does not guarantee the helper was called at + * all. You can't rely on sub_info->{init,cleanup} being called even for + * UMH_WAIT_* wait modes as STATIC_USERMODEHELPER_PATH="" turns all helpers + * into a successful no-op. */ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) { diff --git a/kernel/up.c b/kernel/up.c index 42c46bf3e0a5..2080f75e0e65 100644 --- a/kernel/up.c +++ b/kernel/up.c @@ -23,7 +23,7 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, } EXPORT_SYMBOL(smp_call_function_single); -int smp_call_function_single_async(int cpu, call_single_data_t *csd) +int smp_call_function_single_async(int cpu, struct __call_single_data *csd) { unsigned long flags; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 18fae55713b0..cf5d8fd7472e 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -49,6 +49,7 @@ #include <linux/moduleparam.h> #include <linux/uaccess.h> #include <linux/nmi.h> +#include <linux/kvm_para.h> #include "workqueue_internal.h" @@ -1379,7 +1380,6 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, */ WARN_ON_ONCE(!irqs_disabled()); - debug_work_activate(work); /* if draining, only works from the same workqueue are allowed */ if (unlikely(wq->flags & __WQ_DRAINING) && @@ -1462,6 +1462,7 @@ retry: worklist = &pwq->delayed_works; } + debug_work_activate(work); insert_work(pwq, work, worklist, work_flags); spin_unlock(&pwq->pool->lock); @@ -3440,15 +3441,21 @@ static void pwq_unbound_release_workfn(struct work_struct *work) unbound_release_work); struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; - bool is_last; + bool is_last = false; - if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) - return; + /* + * when @pwq is not linked, it doesn't hold any reference to the + * @wq, and @wq is invalid to access. + */ + if (!list_empty(&pwq->pwqs_node)) { + if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) + return; - mutex_lock(&wq->mutex); - list_del_rcu(&pwq->pwqs_node); - is_last = list_empty(&wq->pwqs); - mutex_unlock(&wq->mutex); + mutex_lock(&wq->mutex); + list_del_rcu(&pwq->pwqs_node); + is_last = list_empty(&wq->pwqs); + mutex_unlock(&wq->mutex); + } mutex_lock(&wq_pool_mutex); put_unbound_pool(pool); @@ -3494,17 +3501,24 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq) * is updated and visible. */ if (!freezable || !workqueue_freezing) { + bool kick = false; + pwq->max_active = wq->saved_max_active; while (!list_empty(&pwq->delayed_works) && - pwq->nr_active < pwq->max_active) + pwq->nr_active < pwq->max_active) { pwq_activate_first_delayed(pwq); + kick = true; + } /* * Need to kick a worker after thawed or an unbound wq's - * max_active is bumped. It's a slow path. Do it always. + * max_active is bumped. In realtime scenarios, always kicking a + * worker will cause interference on the isolated cpu cores, so + * let's kick iff work items were activated. */ - wake_up_worker(pwq->pool); + if (kick) + wake_up_worker(pwq->pool); } else { pwq->max_active = 0; } @@ -5458,6 +5472,7 @@ static void wq_watchdog_timer_fn(unsigned long data) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; bool lockup_detected = false; + unsigned long now = jiffies; struct worker_pool *pool; int pi; @@ -5472,6 +5487,12 @@ static void wq_watchdog_timer_fn(unsigned long data) if (list_empty(&pool->worklist)) continue; + /* + * If a virtual machine is stopped by the host it can look to + * the watchdog like a stall. + */ + kvm_check_and_clear_guest_paused(); + /* get the latest of pool and touched timestamps */ pool_ts = READ_ONCE(pool->watchdog_ts); touched = READ_ONCE(wq_watchdog_touched); @@ -5490,12 +5511,12 @@ static void wq_watchdog_timer_fn(unsigned long data) } /* did we stall? */ - if (time_after(jiffies, ts + thresh)) { + if (time_after(now, ts + thresh)) { lockup_detected = true; pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", - jiffies_to_msecs(jiffies - pool_ts) / 1000); + jiffies_to_msecs(now - pool_ts) / 1000); } } |