diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/audit_fsnotify.c | 1 | ||||
-rw-r--r-- | kernel/auditsc.c | 4 | ||||
-rw-r--r-- | kernel/bpf/cgroup.c | 4 | ||||
-rw-r--r-- | kernel/bpf/core.c | 2 | ||||
-rw-r--r-- | kernel/bpf/syscall.c | 2 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 13 | ||||
-rw-r--r-- | kernel/cgroup/cgroup-v1.c | 2 | ||||
-rw-r--r-- | kernel/cgroup/cgroup.c | 80 | ||||
-rw-r--r-- | kernel/cgroup/cpuset.c | 3 | ||||
-rw-r--r-- | kernel/crash_core.c | 1 | ||||
-rw-r--r-- | kernel/kprobes.c | 9 | ||||
-rw-r--r-- | kernel/module/main.c | 2 | ||||
-rw-r--r-- | kernel/sched/psi.c | 10 | ||||
-rw-r--r-- | kernel/sched/wait_bit.c | 2 | ||||
-rw-r--r-- | kernel/sys_ni.c | 1 | ||||
-rw-r--r-- | kernel/trace/ftrace.c | 79 |
16 files changed, 119 insertions, 96 deletions
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c index 6432a37ac1c9..c565fbf66ac8 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -102,6 +102,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, 0); if (ret < 0) { + audit_mark->path = NULL; fsnotify_put_mark(&audit_mark->mark); audit_mark = ERR_PTR(ret); } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index dd8d9ab747c3..79a5da1bc5bb 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1940,6 +1940,7 @@ void __audit_uring_exit(int success, long code) goto out; } + audit_return_fixup(ctx, success, code); if (ctx->context == AUDIT_CTX_SYSCALL) { /* * NOTE: See the note in __audit_uring_entry() about the case @@ -1981,7 +1982,6 @@ void __audit_uring_exit(int success, long code) audit_filter_inodes(current, ctx); if (ctx->current_state != AUDIT_STATE_RECORD) goto out; - audit_return_fixup(ctx, success, code); audit_log_exit(); out: @@ -2065,13 +2065,13 @@ void __audit_syscall_exit(int success, long return_code) if (!list_empty(&context->killed_trees)) audit_kill_trees(context); + audit_return_fixup(context, success, return_code); /* run through both filters to ensure we set the filterkey properly */ audit_filter_syscall(current, context); audit_filter_inodes(current, context); if (context->current_state < AUDIT_STATE_RECORD) goto out; - audit_return_fixup(context, success, return_code); audit_log_exit(); out: diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 59b7eb60d5b4..4a400cd63731 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -921,8 +921,10 @@ static void purge_effective_progs(struct cgroup *cgrp, struct bpf_prog *prog, pos++; } } + + /* no link or prog match, skip the cgroup of this layer */ + continue; found: - BUG_ON(!cg); progs = rcu_dereference_protected( desc->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index c1e10d088dbb..3d9eb3ae334c 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -971,7 +971,7 @@ pure_initcall(bpf_jit_charge_init); int bpf_jit_charge_modmem(u32 size) { - if (atomic_long_add_return(size, &bpf_jit_current) > bpf_jit_limit) { + if (atomic_long_add_return(size, &bpf_jit_current) > READ_ONCE(bpf_jit_limit)) { if (!bpf_capable()) { atomic_long_sub(size, &bpf_jit_current); return -EPERM; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a4d40d98428a..27760627370d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5197,7 +5197,7 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sys_bpf: - return &bpf_sys_bpf_proto; + return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto; case BPF_FUNC_btf_find_by_name_kind: return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 096fdac70165..3eadb14e090b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6066,6 +6066,9 @@ skip_type_check: return -EACCES; } meta->mem_size = reg->var_off.value; + err = mark_chain_precision(env, regno); + if (err) + return err; break; case ARG_PTR_TO_INT: case ARG_PTR_TO_LONG: @@ -7030,8 +7033,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; struct bpf_reg_state *regs = cur_regs(env), *reg; struct bpf_map *map = meta->map_ptr; - struct tnum range; - u64 val; + u64 val, max; int err; if (func_id != BPF_FUNC_tail_call) @@ -7041,10 +7043,11 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return -EINVAL; } - range = tnum_range(0, map->max_entries - 1); reg = ®s[BPF_REG_3]; + val = reg->var_off.value; + max = map->max_entries; - if (!register_is_const(reg) || !tnum_in(range, reg->var_off)) { + if (!(register_is_const(reg) && val < max)) { bpf_map_key_store(aux, BPF_MAP_KEY_POISON); return 0; } @@ -7052,8 +7055,6 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, err = mark_chain_precision(env, BPF_REG_3); if (err) return err; - - val = reg->var_off.value; if (bpf_map_key_unseen(aux)) bpf_map_key_store(aux, val); else if (!bpf_map_key_poisoned(aux) && diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 2ade21b54dc4..ff6a8099eb2a 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -59,6 +59,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) int retval = 0; mutex_lock(&cgroup_mutex); + cpus_read_lock(); percpu_down_write(&cgroup_threadgroup_rwsem); for_each_root(root) { struct cgroup *from_cgrp; @@ -72,6 +73,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) break; } percpu_up_write(&cgroup_threadgroup_rwsem); + cpus_read_unlock(); mutex_unlock(&cgroup_mutex); return retval; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 217469a1ea29..718a70c01c04 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1820,6 +1820,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) if (ss->css_rstat_flush) { list_del_rcu(&css->rstat_css_node); + synchronize_rcu(); list_add_rcu(&css->rstat_css_node, &dcgrp->rstat_css_list); } @@ -2370,6 +2371,47 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) EXPORT_SYMBOL_GPL(task_cgroup_path); /** + * cgroup_attach_lock - Lock for ->attach() + * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem + * + * cgroup migration sometimes needs to stabilize threadgroups against forks and + * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach() + * implementations (e.g. cpuset), also need to disable CPU hotplug. + * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can + * lead to deadlocks. + * + * Bringing up a CPU may involve creating and destroying tasks which requires + * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside + * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while + * write-locking threadgroup_rwsem, the locking order is reversed and we end up + * waiting for an on-going CPU hotplug operation which in turn is waiting for + * the threadgroup_rwsem to be released to create new tasks. For more details: + * + * http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu + * + * Resolve the situation by always acquiring cpus_read_lock() before optionally + * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that + * CPU hotplug is disabled on entry. + */ +static void cgroup_attach_lock(bool lock_threadgroup) +{ + cpus_read_lock(); + if (lock_threadgroup) + percpu_down_write(&cgroup_threadgroup_rwsem); +} + +/** + * cgroup_attach_unlock - Undo cgroup_attach_lock() + * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem + */ +static void cgroup_attach_unlock(bool lock_threadgroup) +{ + if (lock_threadgroup) + percpu_up_write(&cgroup_threadgroup_rwsem); + cpus_read_unlock(); +} + +/** * cgroup_migrate_add_task - add a migration target task to a migration context * @task: target task * @mgctx: target migration context @@ -2841,8 +2883,7 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, } struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, - bool *locked) - __acquires(&cgroup_threadgroup_rwsem) + bool *threadgroup_locked) { struct task_struct *tsk; pid_t pid; @@ -2859,12 +2900,8 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, * Therefore, we can skip the global lock. */ lockdep_assert_held(&cgroup_mutex); - if (pid || threadgroup) { - percpu_down_write(&cgroup_threadgroup_rwsem); - *locked = true; - } else { - *locked = false; - } + *threadgroup_locked = pid || threadgroup; + cgroup_attach_lock(*threadgroup_locked); rcu_read_lock(); if (pid) { @@ -2895,17 +2932,14 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, goto out_unlock_rcu; out_unlock_threadgroup: - if (*locked) { - percpu_up_write(&cgroup_threadgroup_rwsem); - *locked = false; - } + cgroup_attach_unlock(*threadgroup_locked); + *threadgroup_locked = false; out_unlock_rcu: rcu_read_unlock(); return tsk; } -void cgroup_procs_write_finish(struct task_struct *task, bool locked) - __releases(&cgroup_threadgroup_rwsem) +void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked) { struct cgroup_subsys *ss; int ssid; @@ -2913,8 +2947,8 @@ void cgroup_procs_write_finish(struct task_struct *task, bool locked) /* release reference from cgroup_procs_write_start() */ put_task_struct(task); - if (locked) - percpu_up_write(&cgroup_threadgroup_rwsem); + cgroup_attach_unlock(threadgroup_locked); + for_each_subsys(ss, ssid) if (ss->post_attach) ss->post_attach(); @@ -3000,8 +3034,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) * write-locking can be skipped safely. */ has_tasks = !list_empty(&mgctx.preloaded_src_csets); - if (has_tasks) - percpu_down_write(&cgroup_threadgroup_rwsem); + cgroup_attach_lock(has_tasks); /* NULL dst indicates self on default hierarchy */ ret = cgroup_migrate_prepare_dst(&mgctx); @@ -3022,8 +3055,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) ret = cgroup_migrate_execute(&mgctx); out_finish: cgroup_migrate_finish(&mgctx); - if (has_tasks) - percpu_up_write(&cgroup_threadgroup_rwsem); + cgroup_attach_unlock(has_tasks); return ret; } @@ -3698,7 +3730,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, } psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; - new = psi_trigger_create(psi, buf, nbytes, res); + new = psi_trigger_create(psi, buf, res); if (IS_ERR(new)) { cgroup_put(cgrp); return PTR_ERR(new); @@ -4991,13 +5023,13 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, struct task_struct *task; const struct cred *saved_cred; ssize_t ret; - bool locked; + bool threadgroup_locked; dst_cgrp = cgroup_kn_lock_live(of->kn, false); if (!dst_cgrp) return -ENODEV; - task = cgroup_procs_write_start(buf, threadgroup, &locked); + task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock; @@ -5023,7 +5055,7 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, ret = cgroup_attach_task(dst_cgrp, task, threadgroup); out_finish: - cgroup_procs_write_finish(task, locked); + cgroup_procs_write_finish(task, threadgroup_locked); out_unlock: cgroup_kn_unlock(of->kn); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 58aadfda9b8b..1f3a55297f39 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2289,7 +2289,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) cgroup_taskset_first(tset, &css); cs = css_cs(css); - cpus_read_lock(); + lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ percpu_down_write(&cpuset_rwsem); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); @@ -2343,7 +2343,6 @@ static void cpuset_attach(struct cgroup_taskset *tset) wake_up(&cpuset_attach_wq); percpu_up_write(&cpuset_rwsem); - cpus_read_unlock(); } /* The various types of files and directories in a cpuset file system */ diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 07b26df453a9..a0eb4d5cf557 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -494,6 +494,7 @@ static int __init crash_save_vmcoreinfo_init(void) #ifdef CONFIG_KALLSYMS VMCOREINFO_SYMBOL(kallsyms_names); + VMCOREINFO_SYMBOL(kallsyms_num_syms); VMCOREINFO_SYMBOL(kallsyms_token_table); VMCOREINFO_SYMBOL(kallsyms_token_index); #ifdef CONFIG_KALLSYMS_BASE_RELATIVE diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 80697e5e03e4..08350e35aba2 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1707,11 +1707,12 @@ static struct kprobe *__disable_kprobe(struct kprobe *p) /* Try to disarm and disable this/parent probe */ if (p == orig_p || aggr_kprobe_disabled(orig_p)) { /* - * If 'kprobes_all_disarmed' is set, 'orig_p' - * should have already been disarmed, so - * skip unneed disarming process. + * Don't be lazy here. Even if 'kprobes_all_disarmed' + * is false, 'orig_p' might not have been armed yet. + * Note arm_all_kprobes() __tries__ to arm all kprobes + * on the best effort basis. */ - if (!kprobes_all_disarmed) { + if (!kprobes_all_disarmed && !kprobe_disabled(orig_p)) { ret = disarm_kprobe(orig_p, true); if (ret) { p->flags &= ~KPROBE_FLAG_DISABLED; diff --git a/kernel/module/main.c b/kernel/module/main.c index 6a477c622544..a4e4d84b6f4e 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2099,7 +2099,7 @@ static int find_module_sections(struct module *mod, struct load_info *info) sizeof(*mod->static_call_sites), &mod->num_static_call_sites); #endif -#ifdef CONFIG_KUNIT +#if IS_ENABLED(CONFIG_KUNIT) mod->kunit_suites = section_objs(info, ".kunit_test_suites", sizeof(*mod->kunit_suites), &mod->num_kunit_suites); diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index ec66b40bdd40..ecb4b4ff4ce0 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -190,12 +190,8 @@ static void group_init(struct psi_group *group) /* Init trigger-related members */ mutex_init(&group->trigger_lock); INIT_LIST_HEAD(&group->triggers); - memset(group->nr_triggers, 0, sizeof(group->nr_triggers)); - group->poll_states = 0; group->poll_min_period = U32_MAX; - memset(group->polling_total, 0, sizeof(group->polling_total)); group->polling_next_update = ULLONG_MAX; - group->polling_until = 0; init_waitqueue_head(&group->poll_wait); timer_setup(&group->poll_timer, poll_timer_fn, 0); rcu_assign_pointer(group->poll_task, NULL); @@ -957,7 +953,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup) if (static_branch_likely(&psi_disabled)) return 0; - cgroup->psi = kmalloc(sizeof(struct psi_group), GFP_KERNEL); + cgroup->psi = kzalloc(sizeof(struct psi_group), GFP_KERNEL); if (!cgroup->psi) return -ENOMEM; @@ -1091,7 +1087,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) } struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, size_t nbytes, enum psi_res res) + char *buf, enum psi_res res) { struct psi_trigger *t; enum psi_states state; @@ -1320,7 +1316,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, return -EBUSY; } - new = psi_trigger_create(&psi_system, buf, nbytes, res); + new = psi_trigger_create(&psi_system, buf, res); if (IS_ERR(new)) { mutex_unlock(&seq->lock); return PTR_ERR(new); diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c index d4788f810b55..0b1cd985dc27 100644 --- a/kernel/sched/wait_bit.c +++ b/kernel/sched/wait_bit.c @@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_ prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode); if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) ret = (*action)(&wbq_entry->key, mode); - } while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret); + } while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret); finish_wait(wq_head, &wbq_entry->wq_entry); diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index a492f159624f..860b2dcf3ac4 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -277,6 +277,7 @@ COND_SYSCALL(landlock_restrict_self); /* mm/fadvise.c */ COND_SYSCALL(fadvise64_64); +COND_SYSCALL_COMPAT(fadvise64_64); /* mm/, CONFIG_MMU only */ COND_SYSCALL(swapon); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 126c769d36c3..439e2ab6905e 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1861,8 +1861,6 @@ static void ftrace_hash_rec_enable_modify(struct ftrace_ops *ops, ftrace_hash_rec_update_modify(ops, filter_hash, 1); } -static bool ops_references_ip(struct ftrace_ops *ops, unsigned long ip); - /* * Try to update IPMODIFY flag on each ftrace_rec. Return 0 if it is OK * or no-needed to update, -EBUSY if it detects a conflict of the flag @@ -3118,49 +3116,6 @@ static inline int ops_traces_mod(struct ftrace_ops *ops) ftrace_hash_empty(ops->func_hash->notrace_hash); } -/* - * Check if the current ops references the given ip. - * - * If the ops traces all functions, then it was already accounted for. - * If the ops does not trace the current record function, skip it. - * If the ops ignores the function via notrace filter, skip it. - */ -static bool -ops_references_ip(struct ftrace_ops *ops, unsigned long ip) -{ - /* If ops isn't enabled, ignore it */ - if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) - return false; - - /* If ops traces all then it includes this function */ - if (ops_traces_mod(ops)) - return true; - - /* The function must be in the filter */ - if (!ftrace_hash_empty(ops->func_hash->filter_hash) && - !__ftrace_lookup_ip(ops->func_hash->filter_hash, ip)) - return false; - - /* If in notrace hash, we ignore it too */ - if (ftrace_lookup_ip(ops->func_hash->notrace_hash, ip)) - return false; - - return true; -} - -/* - * Check if the current ops references the record. - * - * If the ops traces all functions, then it was already accounted for. - * If the ops does not trace the current record function, skip it. - * If the ops ignores the function via notrace filter, skip it. - */ -static bool -ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec) -{ - return ops_references_ip(ops, rec->ip); -} - static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) { bool init_nop = ftrace_need_init_nop(); @@ -6822,6 +6777,38 @@ static int ftrace_get_trampoline_kallsym(unsigned int symnum, return -ERANGE; } +#if defined(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS) || defined(CONFIG_MODULES) +/* + * Check if the current ops references the given ip. + * + * If the ops traces all functions, then it was already accounted for. + * If the ops does not trace the current record function, skip it. + * If the ops ignores the function via notrace filter, skip it. + */ +static bool +ops_references_ip(struct ftrace_ops *ops, unsigned long ip) +{ + /* If ops isn't enabled, ignore it */ + if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) + return false; + + /* If ops traces all then it includes this function */ + if (ops_traces_mod(ops)) + return true; + + /* The function must be in the filter */ + if (!ftrace_hash_empty(ops->func_hash->filter_hash) && + !__ftrace_lookup_ip(ops->func_hash->filter_hash, ip)) + return false; + + /* If in notrace hash, we ignore it too */ + if (ftrace_lookup_ip(ops->func_hash->notrace_hash, ip)) + return false; + + return true; +} +#endif + #ifdef CONFIG_MODULES #define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next) @@ -6834,7 +6821,7 @@ 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)) { + if (ops_references_ip(ops, rec->ip)) { if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_DIRECT)) continue; if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_IPMODIFY)) |