diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/core.c | 7 | ||||
-rw-r--r-- | kernel/bpf/hashtab.c | 4 | ||||
-rw-r--r-- | kernel/bpf/helpers.c | 30 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 9 | ||||
-rw-r--r-- | kernel/cfi.c | 8 | ||||
-rw-r--r-- | kernel/cred.c | 12 | ||||
-rw-r--r-- | kernel/fork.c | 8 | ||||
-rw-r--r-- | kernel/irq/chip.c | 5 | ||||
-rw-r--r-- | kernel/irq/msi.c | 13 | ||||
-rw-r--r-- | kernel/irq/timings.c | 5 | ||||
-rw-r--r-- | kernel/locking/rtmutex.c | 2 | ||||
-rw-r--r-- | kernel/sched/core.c | 143 | ||||
-rw-r--r-- | kernel/sched/sched.h | 5 | ||||
-rw-r--r-- | kernel/seccomp.c | 2 | ||||
-rw-r--r-- | kernel/trace/Kconfig | 5 | ||||
-rw-r--r-- | kernel/trace/bpf_trace.c | 13 | ||||
-rw-r--r-- | kernel/trace/trace.c | 18 | ||||
-rw-r--r-- | kernel/trace/trace.h | 32 | ||||
-rw-r--r-- | kernel/trace/trace_events_hist.c | 2 | ||||
-rw-r--r-- | kernel/trace/trace_osnoise.c | 56 | ||||
-rw-r--r-- | kernel/ucount.c | 19 |
21 files changed, 284 insertions, 114 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index b1a5fc04492b..0a28a8095d3e 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1362,11 +1362,13 @@ u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) } /** - * __bpf_prog_run - run eBPF program on a given context + * ___bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers * @insn: is the array of eBPF instructions * * Decode and execute eBPF instructions. + * + * Return: whatever value is in %BPF_R0 at program exit */ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) { @@ -1878,6 +1880,9 @@ static void bpf_prog_select_func(struct bpf_prog *fp) * * Try to JIT eBPF program, if JIT is not available, use interpreter. * The BPF program will be executed via BPF_PROG_RUN() macro. + * + * Return: the &fp argument along with &err set to 0 for success or + * a negative errno code on failure */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 72c58cc516a3..9c011f3a2687 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1565,8 +1565,8 @@ alloc: /* We cannot do copy_from_user or copy_to_user inside * the rcu_read_lock. Allocate enough space here. */ - keys = kvmalloc(key_size * bucket_size, GFP_USER | __GFP_NOWARN); - values = kvmalloc(value_size * bucket_size, GFP_USER | __GFP_NOWARN); + keys = kvmalloc_array(key_size, bucket_size, GFP_USER | __GFP_NOWARN); + values = kvmalloc_array(value_size, bucket_size, GFP_USER | __GFP_NOWARN); if (!keys || !values) { ret = -ENOMEM; goto after_loop; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 62cf00383910..55f83ea09dae 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -353,9 +353,15 @@ const struct bpf_func_proto bpf_jiffies64_proto = { #ifdef CONFIG_CGROUPS BPF_CALL_0(bpf_get_current_cgroup_id) { - struct cgroup *cgrp = task_dfl_cgroup(current); + struct cgroup *cgrp; + u64 cgrp_id; - return cgroup_id(cgrp); + rcu_read_lock(); + cgrp = task_dfl_cgroup(current); + cgrp_id = cgroup_id(cgrp); + rcu_read_unlock(); + + return cgrp_id; } const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { @@ -366,13 +372,17 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { BPF_CALL_1(bpf_get_current_ancestor_cgroup_id, int, ancestor_level) { - struct cgroup *cgrp = task_dfl_cgroup(current); + struct cgroup *cgrp; struct cgroup *ancestor; + u64 cgrp_id; + rcu_read_lock(); + cgrp = task_dfl_cgroup(current); ancestor = cgroup_ancestor(cgrp, ancestor_level); - if (!ancestor) - return 0; - return cgroup_id(ancestor); + cgrp_id = ancestor ? cgroup_id(ancestor) : 0; + rcu_read_unlock(); + + return cgrp_id; } const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto = { @@ -397,8 +407,8 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) void *ptr; int i; - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) + for (i = BPF_CGROUP_STORAGE_NEST_MAX - 1; i >= 0; i--) { + if (likely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) continue; storage = this_cpu_read(bpf_cgroup_storage_info[i].storage[stype]); @@ -1070,12 +1080,12 @@ bpf_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_str_proto; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f9bda5476ea5..49f07e2bf23b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5150,8 +5150,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_RINGBUF: if (func_id != BPF_FUNC_ringbuf_output && func_id != BPF_FUNC_ringbuf_reserve && - func_id != BPF_FUNC_ringbuf_submit && - func_id != BPF_FUNC_ringbuf_discard && func_id != BPF_FUNC_ringbuf_query) goto error; break; @@ -5260,6 +5258,12 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) goto error; break; + case BPF_FUNC_ringbuf_output: + case BPF_FUNC_ringbuf_reserve: + case BPF_FUNC_ringbuf_query: + if (map->map_type != BPF_MAP_TYPE_RINGBUF) + goto error; + break; case BPF_FUNC_get_stackid: if (map->map_type != BPF_MAP_TYPE_STACK_TRACE) goto error; @@ -11663,6 +11667,7 @@ static void sanitize_dead_code(struct bpf_verifier_env *env) if (aux_data[i].seen) continue; memcpy(insn + i, &trap, sizeof(trap)); + aux_data[i].zext_dst = false; } } diff --git a/kernel/cfi.c b/kernel/cfi.c index e17a56639766..9594cfd1cf2c 100644 --- a/kernel/cfi.c +++ b/kernel/cfi.c @@ -248,9 +248,9 @@ static inline cfi_check_fn find_shadow_check_fn(unsigned long ptr) { cfi_check_fn fn; - rcu_read_lock_sched(); + rcu_read_lock_sched_notrace(); fn = ptr_to_check_fn(rcu_dereference_sched(cfi_shadow), ptr); - rcu_read_unlock_sched(); + rcu_read_unlock_sched_notrace(); return fn; } @@ -269,11 +269,11 @@ static inline cfi_check_fn find_module_check_fn(unsigned long ptr) cfi_check_fn fn = NULL; struct module *mod; - rcu_read_lock_sched(); + rcu_read_lock_sched_notrace(); mod = __module_address(ptr); if (mod) fn = mod->cfi_check; - rcu_read_unlock_sched(); + rcu_read_unlock_sched_notrace(); return fn; } diff --git a/kernel/cred.c b/kernel/cred.c index e6fd2b3fc31f..f784e08c2fbd 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -286,13 +286,13 @@ struct cred *prepare_creds(void) new->security = NULL; #endif - if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) - goto error; - new->ucounts = get_ucounts(new->ucounts); if (!new->ucounts) goto error; + if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) + goto error; + validate_creds(new); return new; @@ -753,13 +753,13 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) #ifdef CONFIG_SECURITY new->security = NULL; #endif - if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) - goto error; - new->ucounts = get_ucounts(new->ucounts); if (!new->ucounts) goto error; + if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) + goto error; + put_cred(old); validate_creds(new); return new; diff --git a/kernel/fork.c b/kernel/fork.c index bc94b2cc5995..44f4c2d83763 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -828,10 +828,10 @@ void __init fork_init(void) for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; - set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, task_rlimit(&init_task, RLIMIT_NPROC)); - set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, task_rlimit(&init_task, RLIMIT_MSGQUEUE)); - set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, task_rlimit(&init_task, RLIMIT_SIGPENDING)); - set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, task_rlimit(&init_task, RLIMIT_MEMLOCK)); + set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY); + set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY); + set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY); + set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY); #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 7f04c7d8296e..a98bcfc4be7b 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -265,8 +265,11 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force) } else { switch (__irq_startup_managed(desc, aff, force)) { case IRQ_STARTUP_NORMAL: + if (d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP) + irq_setup_affinity(desc); ret = __irq_startup(desc); - irq_setup_affinity(desc); + if (!(d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP)) + irq_setup_affinity(desc); break; case IRQ_STARTUP_MANAGED: irq_do_set_affinity(d, aff, false); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index c41965e348b5..85df3ca03efe 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -476,11 +476,6 @@ skip_activate: return 0; cleanup: - for_each_msi_vector(desc, i, dev) { - irq_data = irq_domain_get_irq_data(domain, i); - if (irqd_is_activated(irq_data)) - irq_domain_deactivate_irq(irq_data); - } msi_domain_free_irqs(domain, dev); return ret; } @@ -505,7 +500,15 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) { + struct irq_data *irq_data; struct msi_desc *desc; + int i; + + for_each_msi_vector(desc, i, dev) { + irq_data = irq_domain_get_irq_data(domain, i); + if (irqd_is_activated(irq_data)) + irq_domain_deactivate_irq(irq_data); + } for_each_msi_entry(desc, dev) { /* diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c index d309d6fbf5bd..4d2a702d7aa9 100644 --- a/kernel/irq/timings.c +++ b/kernel/irq/timings.c @@ -453,6 +453,11 @@ static __always_inline void __irq_timings_store(int irq, struct irqt_stat *irqs, */ index = irq_timings_interval_index(interval); + if (index > PREDICTION_BUFFER_SIZE - 1) { + irqs->count = 0; + return; + } + /* * Store the index as an element of the pattern in another * circular array. diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index b5d9bb5202c6..ad0db322ed3b 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -343,7 +343,7 @@ static __always_inline bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter, enum rtmutex_chainwalk chwalk) { - if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEX)) + if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES)) return waiter != NULL; return chwalk == RT_MUTEX_FULL_CHAINWALK; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 20ffcc044134..f3b27c6c5153 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -237,9 +237,30 @@ static DEFINE_MUTEX(sched_core_mutex); static atomic_t sched_core_count; static struct cpumask sched_core_mask; +static void sched_core_lock(int cpu, unsigned long *flags) +{ + const struct cpumask *smt_mask = cpu_smt_mask(cpu); + int t, i = 0; + + local_irq_save(*flags); + for_each_cpu(t, smt_mask) + raw_spin_lock_nested(&cpu_rq(t)->__lock, i++); +} + +static void sched_core_unlock(int cpu, unsigned long *flags) +{ + const struct cpumask *smt_mask = cpu_smt_mask(cpu); + int t; + + for_each_cpu(t, smt_mask) + raw_spin_unlock(&cpu_rq(t)->__lock); + local_irq_restore(*flags); +} + static void __sched_core_flip(bool enabled) { - int cpu, t, i; + unsigned long flags; + int cpu, t; cpus_read_lock(); @@ -250,19 +271,12 @@ static void __sched_core_flip(bool enabled) for_each_cpu(cpu, &sched_core_mask) { const struct cpumask *smt_mask = cpu_smt_mask(cpu); - i = 0; - local_irq_disable(); - for_each_cpu(t, smt_mask) { - /* supports up to SMT8 */ - raw_spin_lock_nested(&cpu_rq(t)->__lock, i++); - } + sched_core_lock(cpu, &flags); for_each_cpu(t, smt_mask) cpu_rq(t)->core_enabled = enabled; - for_each_cpu(t, smt_mask) - raw_spin_unlock(&cpu_rq(t)->__lock); - local_irq_enable(); + sched_core_unlock(cpu, &flags); cpumask_andnot(&sched_core_mask, &sched_core_mask, smt_mask); } @@ -5736,35 +5750,109 @@ void queue_core_balance(struct rq *rq) queue_balance_callback(rq, &per_cpu(core_balance_head, rq->cpu), sched_core_balance); } -static inline void sched_core_cpu_starting(unsigned int cpu) +static void sched_core_cpu_starting(unsigned int cpu) { const struct cpumask *smt_mask = cpu_smt_mask(cpu); - struct rq *rq, *core_rq = NULL; - int i; + struct rq *rq = cpu_rq(cpu), *core_rq = NULL; + unsigned long flags; + int t; - core_rq = cpu_rq(cpu)->core; + sched_core_lock(cpu, &flags); - if (!core_rq) { - for_each_cpu(i, smt_mask) { - rq = cpu_rq(i); - if (rq->core && rq->core == rq) - core_rq = rq; + WARN_ON_ONCE(rq->core != rq); + + /* if we're the first, we'll be our own leader */ + if (cpumask_weight(smt_mask) == 1) + goto unlock; + + /* find the leader */ + for_each_cpu(t, smt_mask) { + if (t == cpu) + continue; + rq = cpu_rq(t); + if (rq->core == rq) { + core_rq = rq; + break; } + } - if (!core_rq) - core_rq = cpu_rq(cpu); + if (WARN_ON_ONCE(!core_rq)) /* whoopsie */ + goto unlock; - for_each_cpu(i, smt_mask) { - rq = cpu_rq(i); + /* install and validate core_rq */ + for_each_cpu(t, smt_mask) { + rq = cpu_rq(t); - WARN_ON_ONCE(rq->core && rq->core != core_rq); + if (t == cpu) rq->core = core_rq; - } + + WARN_ON_ONCE(rq->core != core_rq); } + +unlock: + sched_core_unlock(cpu, &flags); } + +static void sched_core_cpu_deactivate(unsigned int cpu) +{ + const struct cpumask *smt_mask = cpu_smt_mask(cpu); + struct rq *rq = cpu_rq(cpu), *core_rq = NULL; + unsigned long flags; + int t; + + sched_core_lock(cpu, &flags); + + /* if we're the last man standing, nothing to do */ + if (cpumask_weight(smt_mask) == 1) { + WARN_ON_ONCE(rq->core != rq); + goto unlock; + } + + /* if we're not the leader, nothing to do */ + if (rq->core != rq) + goto unlock; + + /* find a new leader */ + for_each_cpu(t, smt_mask) { + if (t == cpu) + continue; + core_rq = cpu_rq(t); + break; + } + + if (WARN_ON_ONCE(!core_rq)) /* impossible */ + goto unlock; + + /* copy the shared state to the new leader */ + core_rq->core_task_seq = rq->core_task_seq; + core_rq->core_pick_seq = rq->core_pick_seq; + core_rq->core_cookie = rq->core_cookie; + core_rq->core_forceidle = rq->core_forceidle; + core_rq->core_forceidle_seq = rq->core_forceidle_seq; + + /* install new leader */ + for_each_cpu(t, smt_mask) { + rq = cpu_rq(t); + rq->core = core_rq; + } + +unlock: + sched_core_unlock(cpu, &flags); +} + +static inline void sched_core_cpu_dying(unsigned int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (rq->core != rq) + rq->core = rq; +} + #else /* !CONFIG_SCHED_CORE */ static inline void sched_core_cpu_starting(unsigned int cpu) {} +static inline void sched_core_cpu_deactivate(unsigned int cpu) {} +static inline void sched_core_cpu_dying(unsigned int cpu) {} static struct task_struct * pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) @@ -8707,6 +8795,8 @@ int sched_cpu_deactivate(unsigned int cpu) */ if (cpumask_weight(cpu_smt_mask(cpu)) == 2) static_branch_dec_cpuslocked(&sched_smt_present); + + sched_core_cpu_deactivate(cpu); #endif if (!sched_smp_initialized) @@ -8811,6 +8901,7 @@ int sched_cpu_dying(unsigned int cpu) calc_load_migrate(rq); update_max_interval(); hrtick_clear(rq); + sched_core_cpu_dying(cpu); return 0; } #endif @@ -9022,7 +9113,7 @@ void __init sched_init(void) atomic_set(&rq->nr_iowait, 0); #ifdef CONFIG_SCHED_CORE - rq->core = NULL; + rq->core = rq; rq->core_pick = NULL; rq->core_enabled = 0; rq->core_tree = RB_ROOT; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 14a41a243f7b..ddefb0419d7a 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1093,7 +1093,7 @@ struct rq { unsigned int core_sched_seq; struct rb_root core_tree; - /* shared state */ + /* shared state -- careful with sched_core_cpu_deactivate() */ unsigned int core_task_seq; unsigned int core_pick_seq; unsigned long core_cookie; @@ -2255,6 +2255,9 @@ static inline struct task_struct *get_push_task(struct rq *rq) if (p->nr_cpus_allowed == 1) return NULL; + if (p->migration_disabled) + return NULL; + rq->push_busy = true; return get_task_struct(p); } diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 057e17f3215d..6469eca8078c 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -602,7 +602,7 @@ static inline void seccomp_sync_threads(unsigned long flags) smp_store_release(&thread->seccomp.filter, caller->seccomp.filter); atomic_set(&thread->seccomp.filter_count, - atomic_read(&thread->seccomp.filter_count)); + atomic_read(&caller->seccomp.filter_count)); /* * Don't let an unprivileged task work around diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index d567b1717c4c..3ee23f4d437f 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -219,6 +219,11 @@ config DYNAMIC_FTRACE_WITH_DIRECT_CALLS depends on DYNAMIC_FTRACE_WITH_REGS depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +config DYNAMIC_FTRACE_WITH_ARGS + def_bool y + depends on DYNAMIC_FTRACE + depends on HAVE_DYNAMIC_FTRACE_WITH_ARGS + config FUNCTION_PROFILER bool "Kernel function profiler" depends on FUNCTION_TRACER diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index b4916ef388ad..fdd14072fc3b 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -990,28 +990,29 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_numa_node_id_proto; case BPF_FUNC_perf_event_read: return &bpf_perf_event_read_proto; - case BPF_FUNC_probe_write_user: - return bpf_get_probe_write_proto(); case BPF_FUNC_current_task_under_cgroup: return &bpf_current_task_under_cgroup_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; + case BPF_FUNC_probe_write_user: + return security_locked_down(LOCKDOWN_BPF_WRITE_USER) < 0 ? + NULL : bpf_get_probe_write_proto(); case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_str_proto; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE case BPF_FUNC_probe_read: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_compat_proto; case BPF_FUNC_probe_read_str: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_compat_str_proto; #endif #ifdef CONFIG_CGROUPS diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 33899a71fdc1..a1adb29ef5c1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2897,14 +2897,26 @@ int tracepoint_printk_sysctl(struct ctl_table *table, int write, void trace_event_buffer_commit(struct trace_event_buffer *fbuffer) { + enum event_trigger_type tt = ETT_NONE; + struct trace_event_file *file = fbuffer->trace_file; + + if (__event_trigger_test_discard(file, fbuffer->buffer, fbuffer->event, + fbuffer->entry, &tt)) + goto discard; + if (static_key_false(&tracepoint_printk_key.key)) output_printk(fbuffer); if (static_branch_unlikely(&trace_event_exports_enabled)) ftrace_exports(fbuffer->event, TRACE_EXPORT_EVENT); - event_trigger_unlock_commit_regs(fbuffer->trace_file, fbuffer->buffer, - fbuffer->event, fbuffer->entry, - fbuffer->trace_ctx, fbuffer->regs); + + trace_buffer_unlock_commit_regs(file->tr, fbuffer->buffer, + fbuffer->event, fbuffer->trace_ctx, fbuffer->regs); + +discard: + if (tt) + event_triggers_post_call(file, tt); + } EXPORT_SYMBOL_GPL(trace_event_buffer_commit); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index a180abf76d4e..4a0e693000c6 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1389,38 +1389,6 @@ event_trigger_unlock_commit(struct trace_event_file *file, event_triggers_post_call(file, tt); } -/** - * event_trigger_unlock_commit_regs - handle triggers and finish event commit - * @file: The file pointer associated with the event - * @buffer: The ring buffer that the event is being written to - * @event: The event meta data in the ring buffer - * @entry: The event itself - * @trace_ctx: The tracing context flags. - * - * This is a helper function to handle triggers that require data - * from the event itself. It also tests the event against filters and - * if the event is soft disabled and should be discarded. - * - * Same as event_trigger_unlock_commit() but calls - * trace_buffer_unlock_commit_regs() instead of trace_buffer_unlock_commit(). - */ -static inline void -event_trigger_unlock_commit_regs(struct trace_event_file *file, - struct trace_buffer *buffer, - struct ring_buffer_event *event, - void *entry, unsigned int trace_ctx, - struct pt_regs *regs) -{ - enum event_trigger_type tt = ETT_NONE; - - if (!__event_trigger_test_discard(file, buffer, event, entry, &tt)) - trace_buffer_unlock_commit_regs(file->tr, buffer, event, - trace_ctx, regs); - - if (tt) - event_triggers_post_call(file, tt); -} - #define FILTER_PRED_INVALID ((unsigned short)-1) #define FILTER_PRED_IS_RIGHT (1 << 15) #define FILTER_PRED_FOLD (1 << 15) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 949ef09dc537..a48aa2a2875b 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3430,6 +3430,8 @@ trace_action_create_field_var(struct hist_trigger_data *hist_data, event = data->match_data.event; } + if (!event) + goto free; /* * At this point, we're looking at a field on another * event. Because we can't modify a hist trigger on diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index a7e3c24dee13..b61eefe5ccf5 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -253,6 +253,7 @@ static struct osnoise_data { */ static bool osnoise_busy; +#ifdef CONFIG_PREEMPT_RT /* * Print the osnoise header info. */ @@ -261,6 +262,35 @@ static void print_osnoise_headers(struct seq_file *s) if (osnoise_data.tainted) seq_puts(s, "# osnoise is tainted!\n"); + seq_puts(s, "# _-------=> irqs-off\n"); + seq_puts(s, "# / _------=> need-resched\n"); + seq_puts(s, "# | / _-----=> need-resched-lazy\n"); + seq_puts(s, "# || / _----=> hardirq/softirq\n"); + seq_puts(s, "# ||| / _---=> preempt-depth\n"); + seq_puts(s, "# |||| / _--=> preempt-lazy-depth\n"); + seq_puts(s, "# ||||| / _-=> migrate-disable\n"); + + seq_puts(s, "# |||||| / "); + seq_puts(s, " MAX\n"); + + seq_puts(s, "# ||||| / "); + seq_puts(s, " SINGLE Interference counters:\n"); + + seq_puts(s, "# ||||||| RUNTIME "); + seq_puts(s, " NOISE %% OF CPU NOISE +-----------------------------+\n"); + + seq_puts(s, "# TASK-PID CPU# ||||||| TIMESTAMP IN US "); + seq_puts(s, " IN US AVAILABLE IN US HW NMI IRQ SIRQ THREAD\n"); + + seq_puts(s, "# | | | ||||||| | | "); + seq_puts(s, " | | | | | | | |\n"); +} +#else /* CONFIG_PREEMPT_RT */ +static void print_osnoise_headers(struct seq_file *s) +{ + if (osnoise_data.tainted) + seq_puts(s, "# osnoise is tainted!\n"); + seq_puts(s, "# _-----=> irqs-off\n"); seq_puts(s, "# / _----=> need-resched\n"); seq_puts(s, "# | / _---=> hardirq/softirq\n"); @@ -279,6 +309,7 @@ static void print_osnoise_headers(struct seq_file *s) seq_puts(s, "# | | | |||| | | "); seq_puts(s, " | | | | | | | |\n"); } +#endif /* CONFIG_PREEMPT_RT */ /* * osnoise_taint - report an osnoise error. @@ -323,6 +354,24 @@ static void trace_osnoise_sample(struct osnoise_sample *sample) /* * Print the timerlat header info. */ +#ifdef CONFIG_PREEMPT_RT +static void print_timerlat_headers(struct seq_file *s) +{ + seq_puts(s, "# _-------=> irqs-off\n"); + seq_puts(s, "# / _------=> need-resched\n"); + seq_puts(s, "# | / _-----=> need-resched-lazy\n"); + seq_puts(s, "# || / _----=> hardirq/softirq\n"); + seq_puts(s, "# ||| / _---=> preempt-depth\n"); + seq_puts(s, "# |||| / _--=> preempt-lazy-depth\n"); + seq_puts(s, "# ||||| / _-=> migrate-disable\n"); + seq_puts(s, "# |||||| /\n"); + seq_puts(s, "# ||||||| ACTIVATION\n"); + seq_puts(s, "# TASK-PID CPU# ||||||| TIMESTAMP ID "); + seq_puts(s, " CONTEXT LATENCY\n"); + seq_puts(s, "# | | | ||||||| | | "); + seq_puts(s, " | |\n"); +} +#else /* CONFIG_PREEMPT_RT */ static void print_timerlat_headers(struct seq_file *s) { seq_puts(s, "# _-----=> irqs-off\n"); @@ -336,6 +385,7 @@ static void print_timerlat_headers(struct seq_file *s) seq_puts(s, "# | | | |||| | | "); seq_puts(s, " | |\n"); } +#endif /* CONFIG_PREEMPT_RT */ /* * Record an timerlat_sample into the tracer buffer. @@ -1025,9 +1075,13 @@ diff_osn_sample_stats(struct osnoise_variables *osn_var, struct osnoise_sample * /* * osnoise_stop_tracing - Stop tracing and the tracer. */ -static void osnoise_stop_tracing(void) +static __always_inline void osnoise_stop_tracing(void) { struct trace_array *tr = osnoise_trace; + + trace_array_printk_buf(tr->array_buffer.buffer, _THIS_IP_, + "stop tracing hit on cpu %d\n", smp_processor_id()); + tracer_tracing_off(tr); } diff --git a/kernel/ucount.c b/kernel/ucount.c index 77be3bbe3cc4..bb51849e6375 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -58,14 +58,17 @@ static struct ctl_table_root set_root = { .permissions = set_permissions, }; -#define UCOUNT_ENTRY(name) \ - { \ - .procname = name, \ - .maxlen = sizeof(int), \ - .mode = 0644, \ - .proc_handler = proc_dointvec_minmax, \ - .extra1 = SYSCTL_ZERO, \ - .extra2 = SYSCTL_INT_MAX, \ +static long ue_zero = 0; +static long ue_int_max = INT_MAX; + +#define UCOUNT_ENTRY(name) \ + { \ + .procname = name, \ + .maxlen = sizeof(long), \ + .mode = 0644, \ + .proc_handler = proc_doulongvec_minmax, \ + .extra1 = &ue_zero, \ + .extra2 = &ue_int_max, \ } static struct ctl_table user_table[] = { UCOUNT_ENTRY("max_user_namespaces"), |