diff options
Diffstat (limited to 'kernel')
92 files changed, 2358 insertions, 1148 deletions
diff --git a/kernel/audit.c b/kernel/audit.c index 8e09f0f55b4b..17b0d523afb3 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -102,12 +102,13 @@ struct audit_net { * This struct is RCU protected; you must either hold the RCU lock for reading * or the associated spinlock for writing. */ -static struct auditd_connection { +struct auditd_connection { struct pid *pid; u32 portid; struct net *net; struct rcu_head rcu; -} *auditd_conn = NULL; +}; +static struct auditd_connection __rcu *auditd_conn; static DEFINE_SPINLOCK(auditd_conn_lock); /* If audit_rate_limit is non-zero, limit the rate of sending audit records diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 4fb20ab179fe..9e43b72eb619 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -35,8 +35,8 @@ void cgroup_bpf_offline(struct cgroup *cgrp) */ static void cgroup_bpf_release(struct work_struct *work) { - struct cgroup *cgrp = container_of(work, struct cgroup, - bpf.release_work); + struct cgroup *p, *cgrp = container_of(work, struct cgroup, + bpf.release_work); enum bpf_cgroup_storage_type stype; struct bpf_prog_array *old_array; unsigned int type; @@ -65,6 +65,9 @@ static void cgroup_bpf_release(struct work_struct *work) mutex_unlock(&cgroup_mutex); + for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) + cgroup_bpf_put(p); + percpu_ref_exit(&cgrp->bpf.refcnt); cgroup_put(cgrp); } @@ -199,6 +202,7 @@ int cgroup_bpf_inherit(struct cgroup *cgrp) */ #define NR ARRAY_SIZE(cgrp->bpf.effective) struct bpf_prog_array *arrays[NR] = {}; + struct cgroup *p; int ret, i; ret = percpu_ref_init(&cgrp->bpf.refcnt, cgroup_bpf_release_fn, 0, @@ -206,6 +210,9 @@ int cgroup_bpf_inherit(struct cgroup *cgrp) if (ret) return ret; + for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) + cgroup_bpf_get(p); + for (i = 0; i < NR; i++) INIT_LIST_HEAD(&cgrp->bpf.progs[i]); diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index ca52b9642943..d4f335a9a899 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -44,14 +44,19 @@ struct tnum tnum_rshift(struct tnum a, u8 shift) return TNUM(a.value >> shift, a.mask >> shift); } -struct tnum tnum_arshift(struct tnum a, u8 min_shift) +struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness) { /* if a.value is negative, arithmetic shifting by minimum shift * will have larger negative offset compared to more shifting. * If a.value is nonnegative, arithmetic shifting by minimum shift * will have larger positive offset compare to more shifting. */ - return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift); + if (insn_bitness == 32) + return TNUM((u32)(((s32)a.value) >> min_shift), + (u32)(((s32)a.mask) >> min_shift)); + else + return TNUM((s64)a.value >> min_shift, + (s64)a.mask >> min_shift); } struct tnum tnum_add(struct tnum a, struct tnum b) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4983940cbdca..7d530ce8719d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -907,7 +907,8 @@ static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; -static void __mark_reg_not_init(struct bpf_reg_state *reg); +static void __mark_reg_not_init(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg); /* Mark the unknown part of a register (variable offset or scalar value) as * known to have the value @imm. @@ -945,7 +946,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env, verbose(env, "mark_reg_known_zero(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } __mark_reg_known_zero(regs + regno); @@ -1054,7 +1055,8 @@ static void __mark_reg_unbounded(struct bpf_reg_state *reg) } /* Mark a register as having a completely unknown (scalar) value. */ -static void __mark_reg_unknown(struct bpf_reg_state *reg) +static void __mark_reg_unknown(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg) { /* * Clear type, id, off, and union(map_ptr, range) and @@ -1064,6 +1066,8 @@ static void __mark_reg_unknown(struct bpf_reg_state *reg) reg->type = SCALAR_VALUE; reg->var_off = tnum_unknown; reg->frameno = 0; + reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ? + true : false; __mark_reg_unbounded(reg); } @@ -1074,19 +1078,16 @@ static void mark_reg_unknown(struct bpf_verifier_env *env, verbose(env, "mark_reg_unknown(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } - regs += regno; - __mark_reg_unknown(regs); - /* constant backtracking is enabled for root without bpf2bpf calls */ - regs->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ? - true : false; + __mark_reg_unknown(env, regs + regno); } -static void __mark_reg_not_init(struct bpf_reg_state *reg) +static void __mark_reg_not_init(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg) { - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); reg->type = NOT_INIT; } @@ -1097,10 +1098,10 @@ static void mark_reg_not_init(struct bpf_verifier_env *env, verbose(env, "mark_reg_not_init(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); } #define DEF_NOT_SUBREG (0) @@ -3234,7 +3235,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, } if (state->stack[spi].slot_type[0] == STACK_SPILL && state->stack[spi].spilled_ptr.type == SCALAR_VALUE) { - __mark_reg_unknown(&state->stack[spi].spilled_ptr); + __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) state->stack[spi].slot_type[j] = STACK_MISC; goto mark; @@ -3892,7 +3893,7 @@ static void __clear_all_pkt_pointers(struct bpf_verifier_env *env, if (!reg) continue; if (reg_is_pkt_pointer_any(reg)) - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); } } @@ -3920,7 +3921,7 @@ static void release_reg_references(struct bpf_verifier_env *env, if (!reg) continue; if (reg->ref_obj_id == ref_obj_id) - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); } } @@ -4582,7 +4583,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } @@ -4834,13 +4835,13 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } if (!src_known && opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) { - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } @@ -5048,9 +5049,16 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Upon reaching here, src_known is true and * umax_val is equal to umin_val. */ - dst_reg->smin_value >>= umin_val; - dst_reg->smax_value >>= umin_val; - dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val); + if (insn_bitness == 32) { + dst_reg->smin_value = (u32)(((s32)dst_reg->smin_value) >> umin_val); + dst_reg->smax_value = (u32)(((s32)dst_reg->smax_value) >> umin_val); + } else { + dst_reg->smin_value >>= umin_val; + dst_reg->smax_value >>= umin_val; + } + + dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, + insn_bitness); /* blow away the dst_reg umin_value/umax_value and rely on * dst_reg var_off to refine the result. @@ -6263,6 +6271,7 @@ static bool may_access_skb(enum bpf_prog_type type) static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = cur_regs(env); + static const int ctx_reg = BPF_REG_6; u8 mode = BPF_MODE(insn->code); int i, err; @@ -6296,7 +6305,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) } /* check whether implicit source operand (register R6) is readable */ - err = check_reg_arg(env, BPF_REG_6, SRC_OP); + err = check_reg_arg(env, ctx_reg, SRC_OP); if (err) return err; @@ -6315,7 +6324,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } - if (regs[BPF_REG_6].type != PTR_TO_CTX) { + if (regs[ctx_reg].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); return -EINVAL; @@ -6328,6 +6337,10 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } + err = check_ctx_reg(env, ®s[ctx_reg], ctx_reg); + if (err < 0) + return err; + /* reset caller saved regs to unreadable */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); @@ -6982,7 +6995,7 @@ static void clean_func_state(struct bpf_verifier_env *env, /* since the register is unused, clear its state * to make further comparison simpler */ - __mark_reg_not_init(&st->regs[i]); + __mark_reg_not_init(env, &st->regs[i]); } for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) { @@ -6990,7 +7003,7 @@ static void clean_func_state(struct bpf_verifier_env *env, /* liveness must not touch this stack slot anymore */ st->stack[i].spilled_ptr.live |= REG_LIVE_DONE; if (!(live & REG_LIVE_READ)) { - __mark_reg_not_init(&st->stack[i].spilled_ptr); + __mark_reg_not_init(env, &st->stack[i].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) st->stack[i].slot_type[j] = STACK_INVALID; } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 735af8f15f95..1e12e6928bca 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3055,8 +3055,6 @@ static int cgroup_apply_control_enable(struct cgroup *cgrp) for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); - WARN_ON_ONCE(css && percpu_ref_is_dying(&css->refcnt)); - if (!(cgroup_ss_mask(dsct) & (1 << ss->id))) continue; @@ -3066,6 +3064,8 @@ static int cgroup_apply_control_enable(struct cgroup *cgrp) return PTR_ERR(css); } + WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); + if (css_visible(css)) { ret = css_populate_dir(css); if (ret) @@ -3101,11 +3101,11 @@ static void cgroup_apply_control_disable(struct cgroup *cgrp) for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); - WARN_ON_ONCE(css && percpu_ref_is_dying(&css->refcnt)); - if (!css) continue; + WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); + if (css->parent && !(cgroup_ss_mask(dsct) & (1 << ss->id))) { kill_css(css); @@ -3392,7 +3392,8 @@ static ssize_t cgroup_type_write(struct kernfs_open_file *of, char *buf, if (strcmp(strstrip(buf), "threaded")) return -EINVAL; - cgrp = cgroup_kn_lock_live(of->kn, false); + /* drain dying csses before we re-apply (threaded) subtree control */ + cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENOENT; diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index b48b22d4deb6..6f87352f8219 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -33,7 +33,7 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) return; /* - * Paired with the one in cgroup_rstat_cpu_pop_upated(). Either we + * Paired with the one in cgroup_rstat_cpu_pop_updated(). Either we * see NULL updated_next or they see our updated stat. */ smp_mb(); diff --git a/kernel/cpu.c b/kernel/cpu.c index e7f79674824d..9c706af713fb 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1914,6 +1914,78 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) } EXPORT_SYMBOL(__cpuhp_remove_state); +#ifdef CONFIG_HOTPLUG_SMT +static void cpuhp_offline_cpu_device(unsigned int cpu) +{ + struct device *dev = get_cpu_device(cpu); + + dev->offline = true; + /* Tell user space about the state change */ + kobject_uevent(&dev->kobj, KOBJ_OFFLINE); +} + +static void cpuhp_online_cpu_device(unsigned int cpu) +{ + struct device *dev = get_cpu_device(cpu); + + dev->offline = false; + /* Tell user space about the state change */ + kobject_uevent(&dev->kobj, KOBJ_ONLINE); +} + +int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) +{ + int cpu, ret = 0; + + cpu_maps_update_begin(); + for_each_online_cpu(cpu) { + if (topology_is_primary_thread(cpu)) + continue; + ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); + if (ret) + break; + /* + * As this needs to hold the cpu maps lock it's impossible + * to call device_offline() because that ends up calling + * cpu_down() which takes cpu maps lock. cpu maps lock + * needs to be held as this might race against in kernel + * abusers of the hotplug machinery (thermal management). + * + * So nothing would update device:offline state. That would + * leave the sysfs entry stale and prevent onlining after + * smt control has been changed to 'off' again. This is + * called under the sysfs hotplug lock, so it is properly + * serialized against the regular offline usage. + */ + cpuhp_offline_cpu_device(cpu); + } + if (!ret) + cpu_smt_control = ctrlval; + cpu_maps_update_done(); + return ret; +} + +int cpuhp_smt_enable(void) +{ + int cpu, ret = 0; + + cpu_maps_update_begin(); + cpu_smt_control = CPU_SMT_ENABLED; + for_each_present_cpu(cpu) { + /* Skip online CPUs and CPUs on offline nodes */ + if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) + continue; + ret = _cpu_up(cpu, 0, CPUHP_ONLINE); + if (ret) + break; + /* See comment in cpuhp_smt_disable() */ + cpuhp_online_cpu_device(cpu); + } + cpu_maps_update_done(); + return ret; +} +#endif + #if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU) static ssize_t show_cpuhp_state(struct device *dev, struct device_attribute *attr, char *buf) @@ -2068,77 +2140,6 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = { #ifdef CONFIG_HOTPLUG_SMT -static void cpuhp_offline_cpu_device(unsigned int cpu) -{ - struct device *dev = get_cpu_device(cpu); - - dev->offline = true; - /* Tell user space about the state change */ - kobject_uevent(&dev->kobj, KOBJ_OFFLINE); -} - -static void cpuhp_online_cpu_device(unsigned int cpu) -{ - struct device *dev = get_cpu_device(cpu); - - dev->offline = false; - /* Tell user space about the state change */ - kobject_uevent(&dev->kobj, KOBJ_ONLINE); -} - -int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) -{ - int cpu, ret = 0; - - cpu_maps_update_begin(); - for_each_online_cpu(cpu) { - if (topology_is_primary_thread(cpu)) - continue; - ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); - if (ret) - break; - /* - * As this needs to hold the cpu maps lock it's impossible - * to call device_offline() because that ends up calling - * cpu_down() which takes cpu maps lock. cpu maps lock - * needs to be held as this might race against in kernel - * abusers of the hotplug machinery (thermal management). - * - * So nothing would update device:offline state. That would - * leave the sysfs entry stale and prevent onlining after - * smt control has been changed to 'off' again. This is - * called under the sysfs hotplug lock, so it is properly - * serialized against the regular offline usage. - */ - cpuhp_offline_cpu_device(cpu); - } - if (!ret) - cpu_smt_control = ctrlval; - cpu_maps_update_done(); - return ret; -} - -int cpuhp_smt_enable(void) -{ - int cpu, ret = 0; - - cpu_maps_update_begin(); - cpu_smt_control = CPU_SMT_ENABLED; - for_each_present_cpu(cpu) { - /* Skip online CPUs and CPUs on offline nodes */ - if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) - continue; - ret = _cpu_up(cpu, 0, CPUHP_ONLINE); - if (ret) - break; - /* See comment in cpuhp_smt_disable() */ - cpuhp_online_cpu_device(cpu); - } - cpu_maps_update_done(); - return ret; -} - - static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) diff --git a/kernel/cred.c b/kernel/cred.c index c0a4c12d38b2..809a985b1793 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -175,8 +175,8 @@ void exit_creds(struct task_struct *tsk) put_cred(cred); #ifdef CONFIG_KEYS_REQUEST_CACHE - key_put(current->cached_requested_key); - current->cached_requested_key = NULL; + key_put(tsk->cached_requested_key); + tsk->cached_requested_key = NULL; #endif } @@ -223,7 +223,7 @@ struct cred *cred_alloc_blank(void) new->magic = CRED_MAGIC; #endif - if (security_cred_alloc_blank(new, GFP_KERNEL) < 0) + if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0) goto error; return new; @@ -282,7 +282,7 @@ struct cred *prepare_creds(void) new->security = NULL; #endif - if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; validate_creds(new); return new; @@ -715,7 +715,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) #ifdef CONFIG_SECURITY new->security = NULL; #endif - if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; put_cred(old); diff --git a/kernel/events/core.c b/kernel/events/core.c index a1f8bde19b56..2173c23c25b4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -11465,8 +11465,10 @@ SYSCALL_DEFINE5(perf_event_open, } } - if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader)) + if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader)) { + err = -EINVAL; goto err_locked; + } /* * Must be under the same ctx::mutex as perf_install_in_context(), diff --git a/kernel/exit.c b/kernel/exit.c index bcbd59888e67..2833ffb0c211 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -517,10 +517,6 @@ static struct task_struct *find_child_reaper(struct task_struct *father, } write_unlock_irq(&tasklist_lock); - if (unlikely(pid_ns == &init_pid_ns)) { - panic("Attempted to kill init! exitcode=0x%08x\n", - father->signal->group_exit_code ?: father->exit_code); - } list_for_each_entry_safe(p, n, dead, ptrace_entry) { list_del_init(&p->ptrace_entry); @@ -766,6 +762,14 @@ void __noreturn do_exit(long code) acct_update_integrals(tsk); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { + /* + * If the last thread of global init has exited, panic + * immediately to get a useable coredump. + */ + if (unlikely(is_global_init(tsk))) + panic("Attempted to kill init! exitcode=0x%08x\n", + tsk->signal->group_exit_code ?: (int)code); + #ifdef CONFIG_POSIX_TIMERS hrtimer_cancel(&tsk->signal->real_timer); exit_itimers(tsk->signal); diff --git a/kernel/fork.c b/kernel/fork.c index 2508a4f238a3..ef82feb4bddc 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1832,6 +1832,7 @@ static __latent_entropy struct task_struct *copy_process( struct multiprocess_signals delayed; struct file *pidfile = NULL; u64 clone_flags = args->flags; + struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different @@ -1874,8 +1875,16 @@ static __latent_entropy struct task_struct *copy_process( */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || - (task_active_pid_ns(current) != - current->nsproxy->pid_ns_for_children)) + (task_active_pid_ns(current) != nsp->pid_ns_for_children)) + return ERR_PTR(-EINVAL); + } + + /* + * If the new process will be in a different time namespace + * do not allow it to share VM or a thread group with the forking task. + */ + if (clone_flags & (CLONE_THREAD | CLONE_VM)) { + if (nsp->time_ns != nsp->time_ns_for_children) return ERR_PTR(-EINVAL); } @@ -2578,6 +2587,16 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, #endif #ifdef __ARCH_WANT_SYS_CLONE3 + +/* + * copy_thread implementations handle CLONE_SETTLS by reading the TLS value from + * the registers containing the syscall arguments for clone. This doesn't work + * with clone3 since the TLS value is passed in clone_args instead. + */ +#ifndef CONFIG_HAVE_COPY_THREAD_TLS +#error clone3 requires copy_thread_tls support in arch +#endif + noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, size_t usize) @@ -2811,7 +2830,8 @@ static int check_unshare_flags(unsigned long unshare_flags) if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| - CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP)) + CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP| + CLONE_NEWTIME)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing diff --git a/kernel/futex.c b/kernel/futex.c index 03c518e9747e..0cf84c8664f2 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1178,6 +1178,7 @@ out_error: /** * wait_for_owner_exiting - Block until the owner has exited + * @ret: owner's current futex lock status * @exiting: Pointer to the exiting task * * Caller must hold a refcount on @exiting. diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 6c7ca2e983a5..02236b13b359 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -12,6 +12,7 @@ #include <linux/interrupt.h> #include <linux/ratelimit.h> #include <linux/irq.h> +#include <linux/sched/isolation.h> #include "internals.h" @@ -171,6 +172,20 @@ void irq_migrate_all_off_this_cpu(void) } } +static bool hk_should_isolate(struct irq_data *data, unsigned int cpu) +{ + const struct cpumask *hk_mask; + + if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) + return false; + + hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask)) + return false; + + return cpumask_test_cpu(cpu, hk_mask); +} + static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu) { struct irq_data *data = irq_desc_get_irq_data(desc); @@ -188,9 +203,11 @@ static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu) /* * If the interrupt can only be directed to a single target * CPU then it is already assigned to a CPU in the affinity - * mask. No point in trying to move it around. + * mask. No point in trying to move it around unless the + * isolation mechanism requests to move it to an upcoming + * housekeeping CPU. */ - if (!irqd_is_single_target(data)) + if (!irqd_is_single_target(data) || hk_should_isolate(data, cpu)) irq_set_affinity_locked(data, affinity, false); } diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 5b8fdd659e54..98a5f10d1900 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -891,6 +891,7 @@ __irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus, } void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus) + __releases(&desc->lock) { raw_spin_unlock_irqrestore(&desc->lock, flags); if (bus) diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index dd822fd8a7d5..7527e5ef6fe5 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -987,6 +987,23 @@ const struct irq_domain_ops irq_domain_simple_ops = { EXPORT_SYMBOL_GPL(irq_domain_simple_ops); /** + * irq_domain_translate_onecell() - Generic translate for direct one cell + * bindings + */ +int irq_domain_translate_onecell(struct irq_domain *d, + struct irq_fwspec *fwspec, + unsigned long *out_hwirq, + unsigned int *out_type) +{ + if (WARN_ON(fwspec->param_count < 1)) + return -EINVAL; + *out_hwirq = fwspec->param[0]; + *out_type = IRQ_TYPE_NONE; + return 0; +} +EXPORT_SYMBOL_GPL(irq_domain_translate_onecell); + +/** * irq_domain_translate_twocell() - Generic translate for direct two cell * bindings * @@ -1459,6 +1476,7 @@ int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg) if (rv) { /* Restore the original irq_data. */ *root_irq_data = *child_irq_data; + kfree(child_irq_data); goto error; } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 1753486b440c..818b2802d3e7 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -18,6 +18,7 @@ #include <linux/sched.h> #include <linux/sched/rt.h> #include <linux/sched/task.h> +#include <linux/sched/isolation.h> #include <uapi/linux/sched/types.h> #include <linux/task_work.h> @@ -217,7 +218,45 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, if (!chip || !chip->irq_set_affinity) return -EINVAL; - ret = chip->irq_set_affinity(data, mask, force); + /* + * If this is a managed interrupt and housekeeping is enabled on + * it check whether the requested affinity mask intersects with + * a housekeeping CPU. If so, then remove the isolated CPUs from + * the mask and just keep the housekeeping CPU(s). This prevents + * the affinity setter from routing the interrupt to an isolated + * CPU to avoid that I/O submitted from a housekeeping CPU causes + * interrupts on an isolated one. + * + * If the masks do not intersect or include online CPU(s) then + * keep the requested mask. The isolated target CPUs are only + * receiving interrupts when the I/O operation was submitted + * directly from them. + * + * If all housekeeping CPUs in the affinity mask are offline, the + * interrupt will be migrated by the CPU hotplug code once a + * housekeeping CPU which belongs to the affinity mask comes + * online. + */ + if (irqd_affinity_is_managed(data) && + housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) { + const struct cpumask *hk_mask, *prog_mask; + + static DEFINE_RAW_SPINLOCK(tmp_mask_lock); + static struct cpumask tmp_mask; + + hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + + raw_spin_lock(&tmp_mask_lock); + cpumask_and(&tmp_mask, mask, hk_mask); + if (!cpumask_intersects(&tmp_mask, cpu_online_mask)) + prog_mask = mask; + else + prog_mask = &tmp_mask; + ret = chip->irq_set_affinity(data, prog_mask, force); + raw_spin_unlock(&tmp_mask_lock); + } else { + ret = chip->irq_set_affinity(data, mask, force); + } switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: @@ -1500,8 +1539,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) * has. The type flags are unreliable as the * underlying chip implementation can override them. */ - pr_err("Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n", - irq); + pr_err("Threaded irq requested with handler=NULL and !ONESHOT for %s (irq %d)\n", + new->name, irq); ret = -EINVAL; goto out_unlock; } diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index 2ed97a7c9b2a..f865e5f4d382 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -34,6 +34,7 @@ static atomic_t irq_poll_active; * true and let the handler run. */ bool irq_wait_for_poll(struct irq_desc *desc) + __must_hold(&desc->lock) { if (WARN_ONCE(irq_poll_cpu == smp_processor_id(), "irq poll in progress on cpu %d for irq %d\n", diff --git a/kernel/kexec.c b/kernel/kexec.c index bc933c0db9bf..f977786fe498 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -159,6 +159,10 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, kimage_terminate(image); + ret = machine_kexec_post_load(image); + if (ret) + goto out; + /* Install the new kernel and uninstall the old */ image = xchg(dest_image, image); diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 15d70a90b50d..c19c0dad1ebe 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -589,6 +589,12 @@ static void kimage_free_extra_pages(struct kimage *image) kimage_free_page_list(&image->unusable_pages); } + +int __weak machine_kexec_post_load(struct kimage *image) +{ + return 0; +} + void kimage_terminate(struct kimage *image) { if (*image->entry != 0) @@ -1171,7 +1177,7 @@ int kernel_kexec(void) * CPU hotplug again; so re-enable it here. */ cpu_hotplug_enable(); - pr_emerg("Starting new kernel\n"); + pr_notice("Starting new kernel\n"); machine_shutdown(); } diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index a2df93948665..faa74d5f6941 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -441,6 +441,10 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, kimage_terminate(image); + ret = machine_kexec_post_load(image); + if (ret) + goto out; + /* * Free up any temporary buffers allocated which are not needed * after image has been loaded diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 48aaf2ac0d0d..39d30ccf8d87 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -13,6 +13,8 @@ void kimage_terminate(struct kimage *image); int kimage_is_destination_range(struct kimage *image, unsigned long start, unsigned long end); +int machine_kexec_post_load(struct kimage *image); + extern struct mutex kexec_mutex; #ifdef CONFIG_KEXEC_FILE diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 53534aa258a6..2625c241ac00 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -510,6 +510,8 @@ static void do_unoptimize_kprobes(void) arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); /* Loop free_list for disarming */ list_for_each_entry_safe(op, tmp, &freeing_list, list) { + /* Switching from detour code to origin */ + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; /* Disarm probes if marked disabled */ if (kprobe_disabled(&op->kp)) arch_disarm_kprobe(&op->kp); @@ -610,6 +612,18 @@ void wait_for_kprobe_optimizer(void) mutex_unlock(&kprobe_mutex); } +static bool optprobe_queued_unopt(struct optimized_kprobe *op) +{ + struct optimized_kprobe *_op; + + list_for_each_entry(_op, &unoptimizing_list, list) { + if (op == _op) + return true; + } + + return false; +} + /* Optimize kprobe if p is ready to be optimized */ static void optimize_kprobe(struct kprobe *p) { @@ -631,17 +645,21 @@ static void optimize_kprobe(struct kprobe *p) return; /* Check if it is already optimized. */ - if (op->kp.flags & KPROBE_FLAG_OPTIMIZED) + if (op->kp.flags & KPROBE_FLAG_OPTIMIZED) { + if (optprobe_queued_unopt(op)) { + /* This is under unoptimizing. Just dequeue the probe */ + list_del_init(&op->list); + } return; + } op->kp.flags |= KPROBE_FLAG_OPTIMIZED; - if (!list_empty(&op->list)) - /* This is under unoptimizing. Just dequeue the probe */ - list_del_init(&op->list); - else { - list_add(&op->list, &optimizing_list); - kick_kprobe_optimizer(); - } + /* On unoptimizing/optimizing_list, op must have OPTIMIZED flag */ + if (WARN_ON_ONCE(!list_empty(&op->list))) + return; + + list_add(&op->list, &optimizing_list); + kick_kprobe_optimizer(); } /* Short cut to direct unoptimizing */ @@ -649,6 +667,7 @@ static void force_unoptimize_kprobe(struct optimized_kprobe *op) { lockdep_assert_cpus_held(); arch_unoptimize_kprobe(op); + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; if (kprobe_disabled(&op->kp)) arch_disarm_kprobe(&op->kp); } @@ -662,31 +681,33 @@ static void unoptimize_kprobe(struct kprobe *p, bool force) return; /* This is not an optprobe nor optimized */ op = container_of(p, struct optimized_kprobe, kp); - if (!kprobe_optimized(p)) { - /* Unoptimized or unoptimizing case */ - if (force && !list_empty(&op->list)) { - /* - * Only if this is unoptimizing kprobe and forced, - * forcibly unoptimize it. (No need to unoptimize - * unoptimized kprobe again :) - */ - list_del_init(&op->list); - force_unoptimize_kprobe(op); - } + if (!kprobe_optimized(p)) return; - } - op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; if (!list_empty(&op->list)) { - /* Dequeue from the optimization queue */ - list_del_init(&op->list); + if (optprobe_queued_unopt(op)) { + /* Queued in unoptimizing queue */ + if (force) { + /* + * Forcibly unoptimize the kprobe here, and queue it + * in the freeing list for release afterwards. + */ + force_unoptimize_kprobe(op); + list_move(&op->list, &freeing_list); + } + } else { + /* Dequeue from the optimizing queue */ + list_del_init(&op->list); + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; + } return; } + /* Optimized kprobe case */ - if (force) + if (force) { /* Forcibly update the code: this is a special case */ force_unoptimize_kprobe(op); - else { + } else { list_add(&op->list, &unoptimizing_list); kick_kprobe_optimizer(); } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 32282e7112d3..32406ef0d6a2 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -482,7 +482,7 @@ static struct lock_trace *save_trace(void) struct lock_trace *trace, *t2; struct hlist_head *hash_head; u32 hash; - unsigned int max_entries; + int max_entries; BUILD_BUG_ON_NOT_POWER_OF_2(STACK_TRACE_HASH_SIZE); BUILD_BUG_ON(LOCK_TRACE_SIZE_IN_LONGS >= MAX_STACK_TRACE_ENTRIES); @@ -490,10 +490,8 @@ static struct lock_trace *save_trace(void) trace = (struct lock_trace *)(stack_trace + nr_stack_trace_entries); max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries - LOCK_TRACE_SIZE_IN_LONGS; - trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3); - if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES - - LOCK_TRACE_SIZE_IN_LONGS - 1) { + if (max_entries <= 0) { if (!debug_locks_off_graph_unlock()) return NULL; @@ -502,6 +500,7 @@ static struct lock_trace *save_trace(void) return NULL; } + trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3); hash = jhash(trace->entries, trace->nr_entries * sizeof(trace->entries[0]), 0); diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index dadb7b7fba37..9bb6d2497b04 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -286,9 +286,9 @@ static int lockdep_stats_show(struct seq_file *m, void *v) seq_printf(m, " stack-trace entries: %11lu [max: %lu]\n", nr_stack_trace_entries, MAX_STACK_TRACE_ENTRIES); #if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) - seq_printf(m, " number of stack traces: %llu\n", + seq_printf(m, " number of stack traces: %11llu\n", lockdep_stack_trace_count()); - seq_printf(m, " number of stack hash chains: %llu\n", + seq_printf(m, " number of stack hash chains: %11llu\n", lockdep_stack_hash_count()); #endif seq_printf(m, " combined max dependencies: %11u\n", diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index 6ef600aa0f47..1f7734949ac8 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -134,20 +134,17 @@ bool osq_lock(struct optimistic_spin_queue *lock) * cmpxchg in an attempt to undo our queueing. */ - while (!READ_ONCE(node->locked)) { - /* - * If we need to reschedule bail... so we can block. - * Use vcpu_is_preempted() to avoid waiting for a preempted - * lock holder: - */ - if (need_resched() || vcpu_is_preempted(node_cpu(node->prev))) - goto unqueue; - - cpu_relax(); - } - return true; + /* + * Wait to acquire the lock or cancelation. Note that need_resched() + * will come with an IPI, which will wake smp_cond_load_relaxed() if it + * is implemented with a monitor-wait. vcpu_is_preempted() relies on + * polling, be careful. + */ + if (smp_cond_load_relaxed(&node->locked, VAL || need_resched() || + vcpu_is_preempted(node_cpu(node->prev)))) + return true; -unqueue: + /* unqueue */ /* * Step - A -- stabilize @prev * diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 2473f10c6956..b9515fcc9b29 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -31,14 +31,15 @@ /* * The basic principle of a queue-based spinlock can best be understood * by studying a classic queue-based spinlock implementation called the - * MCS lock. The paper below provides a good description for this kind - * of lock. + * MCS lock. A copy of the original MCS lock paper ("Algorithms for Scalable + * Synchronization on Shared-Memory Multiprocessors by Mellor-Crummey and + * Scott") is available at * - * http://www.cise.ufl.edu/tr/DOC/REP-1992-71.pdf + * https://bugzilla.kernel.org/show_bug.cgi?id=206115 * - * This queued spinlock implementation is based on the MCS lock, however to make - * it fit the 4 bytes we assume spinlock_t to be, and preserve its existing - * API, we must modify it somehow. + * This queued spinlock implementation is based on the MCS lock, however to + * make it fit the 4 bytes we assume spinlock_t to be, and preserve its + * existing API, we must modify it somehow. * * In particular; where the traditional MCS lock consists of a tail pointer * (8 bytes) and needs the next pointer (another 8 bytes) of its own node to diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 44e68761f432..0d9b6be9ecc8 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1226,8 +1226,8 @@ wait: * In this case, we attempt to acquire the lock again * without sleeping. */ - if ((wstate == WRITER_HANDOFF) && - (rwsem_spin_on_owner(sem, 0) == OWNER_NULL)) + if (wstate == WRITER_HANDOFF && + rwsem_spin_on_owner(sem, RWSEM_NONSPINNABLE) == OWNER_NULL) goto trylock_again; /* Block until there are no active lockers. */ diff --git a/kernel/module.c b/kernel/module.c index b56f3224b161..ac058a5ad1d1 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2031,49 +2031,6 @@ static void module_enable_nx(const struct module *mod) frob_writable_data(&mod->init_layout, set_memory_nx); } -/* Iterate through all modules and set each module's text as RW */ -void set_all_modules_text_rw(void) -{ - struct module *mod; - - if (!rodata_enabled) - return; - - mutex_lock(&module_mutex); - list_for_each_entry_rcu(mod, &modules, list) { - if (mod->state == MODULE_STATE_UNFORMED) - continue; - - frob_text(&mod->core_layout, set_memory_rw); - frob_text(&mod->init_layout, set_memory_rw); - } - mutex_unlock(&module_mutex); -} - -/* Iterate through all modules and set each module's text as RO */ -void set_all_modules_text_ro(void) -{ - struct module *mod; - - if (!rodata_enabled) - return; - - mutex_lock(&module_mutex); - list_for_each_entry_rcu(mod, &modules, list) { - /* - * Ignore going modules since it's possible that ro - * protection has already been disabled, otherwise we'll - * run into protection faults at module deallocation. - */ - if (mod->state == MODULE_STATE_UNFORMED || - mod->state == MODULE_STATE_GOING) - continue; - - frob_text(&mod->core_layout, set_memory_ro); - frob_text(&mod->init_layout, set_memory_ro); - } - mutex_unlock(&module_mutex); -} #else /* !CONFIG_STRICT_MODULE_RWX */ static void module_enable_nx(const struct module *mod) { } #endif /* CONFIG_STRICT_MODULE_RWX */ diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index c815f58e6bc0..ed9882108cd2 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -18,6 +18,7 @@ #include <linux/pid_namespace.h> #include <net/net_namespace.h> #include <linux/ipc_namespace.h> +#include <linux/time_namespace.h> #include <linux/proc_ns.h> #include <linux/file.h> #include <linux/syscalls.h> @@ -40,6 +41,10 @@ struct nsproxy init_nsproxy = { #ifdef CONFIG_CGROUPS .cgroup_ns = &init_cgroup_ns, #endif +#ifdef CONFIG_TIME_NS + .time_ns = &init_time_ns, + .time_ns_for_children = &init_time_ns, +#endif }; static inline struct nsproxy *create_nsproxy(void) @@ -106,8 +111,18 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, goto out_net; } + new_nsp->time_ns_for_children = copy_time_ns(flags, user_ns, + tsk->nsproxy->time_ns_for_children); + if (IS_ERR(new_nsp->time_ns_for_children)) { + err = PTR_ERR(new_nsp->time_ns_for_children); + goto out_time; + } + new_nsp->time_ns = get_time_ns(tsk->nsproxy->time_ns); + return new_nsp; +out_time: + put_net(new_nsp->net_ns); out_net: put_cgroup_ns(new_nsp->cgroup_ns); out_cgroup: @@ -136,15 +151,16 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) struct nsproxy *old_ns = tsk->nsproxy; struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns); struct nsproxy *new_ns; + int ret; if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | CLONE_NEWPID | CLONE_NEWNET | - CLONE_NEWCGROUP)))) { - get_nsproxy(old_ns); - return 0; - } - - if (!ns_capable(user_ns, CAP_SYS_ADMIN)) + CLONE_NEWCGROUP | CLONE_NEWTIME)))) { + if (likely(old_ns->time_ns_for_children == old_ns->time_ns)) { + get_nsproxy(old_ns); + return 0; + } + } else if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; /* @@ -162,6 +178,12 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) if (IS_ERR(new_ns)) return PTR_ERR(new_ns); + ret = timens_on_fork(new_ns, tsk); + if (ret) { + free_nsproxy(new_ns); + return ret; + } + tsk->nsproxy = new_ns; return 0; } @@ -176,6 +198,10 @@ void free_nsproxy(struct nsproxy *ns) put_ipc_ns(ns->ipc_ns); if (ns->pid_ns_for_children) put_pid_ns(ns->pid_ns_for_children); + if (ns->time_ns) + put_time_ns(ns->time_ns); + if (ns->time_ns_for_children) + put_time_ns(ns->time_ns_for_children); put_cgroup_ns(ns->cgroup_ns); put_net(ns->net_ns); kmem_cache_free(nsproxy_cachep, ns); @@ -192,7 +218,8 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags, int err = 0; if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | - CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP))) + CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP | + CLONE_NEWTIME))) return 0; user_ns = new_cred ? new_cred->user_ns : current_user_ns(); diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index d3667b4075c1..7cbfbeacd68a 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -27,7 +27,10 @@ config SUSPEND_SKIP_SYNC Skip the kernel sys_sync() before freezing user processes. Some systems prefer not to pay this cost on every invocation of suspend, or they are content with invoking sync() from - user-space before invoking suspend. Say Y if that's your case. + user-space before invoking suspend. There's a run-time switch + at '/sys/power/sync_on_suspend' to configure this behaviour. + This setting changes the default for the run-tim switch. Say Y + to change the default to disable the kernel sys_sync(). config HIBERNATE_CALLBACKS bool diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 3c0a5a8170b0..6dbeedb7354c 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -9,7 +9,7 @@ * Copyright (C) 2012 Bojan Smojver <bojan@rexursive.com> */ -#define pr_fmt(fmt) "PM: " fmt +#define pr_fmt(fmt) "PM: hibernation: " fmt #include <linux/export.h> #include <linux/suspend.h> @@ -106,7 +106,7 @@ EXPORT_SYMBOL(system_entering_hibernation); #ifdef CONFIG_PM_DEBUG static void hibernation_debug_sleep(void) { - pr_info("hibernation debug: Waiting for 5 seconds.\n"); + pr_info("debug: Waiting for 5 seconds.\n"); mdelay(5000); } @@ -277,7 +277,7 @@ static int create_image(int platform_mode) error = dpm_suspend_end(PMSG_FREEZE); if (error) { - pr_err("Some devices failed to power down, aborting hibernation\n"); + pr_err("Some devices failed to power down, aborting\n"); return error; } @@ -295,7 +295,7 @@ static int create_image(int platform_mode) error = syscore_suspend(); if (error) { - pr_err("Some system devices failed to power down, aborting hibernation\n"); + pr_err("Some system devices failed to power down, aborting\n"); goto Enable_irqs; } @@ -310,7 +310,7 @@ static int create_image(int platform_mode) restore_processor_state(); trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false); if (error) - pr_err("Error %d creating hibernation image\n", error); + pr_err("Error %d creating image\n", error); if (!in_suspend) { events_check_enabled = false; @@ -680,7 +680,7 @@ static int load_image_and_restore(void) if (!error) hibernation_restore(flags & SF_PLATFORM_MODE); - pr_err("Failed to load hibernation image, recovering.\n"); + pr_err("Failed to load image, recovering.\n"); swsusp_free(); free_basic_memory_bitmaps(); Unlock: @@ -743,7 +743,7 @@ int hibernate(void) else flags |= SF_CRC32_MODE; - pm_pr_dbg("Writing image.\n"); + pm_pr_dbg("Writing hibernation image.\n"); error = swsusp_write(flags); swsusp_free(); if (!error) { @@ -755,7 +755,7 @@ int hibernate(void) in_suspend = 0; pm_restore_gfp_mask(); } else { - pm_pr_dbg("Image restored successfully.\n"); + pm_pr_dbg("Hibernation image restored successfully.\n"); } Free_bitmaps: @@ -894,7 +894,7 @@ static int software_resume(void) goto Close_Finish; } - pm_pr_dbg("Preparing processes for restore.\n"); + pm_pr_dbg("Preparing processes for hibernation restore.\n"); error = freeze_processes(); if (error) goto Close_Finish; @@ -903,7 +903,7 @@ static int software_resume(void) Finish: __pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL); pm_restore_console(); - pr_info("resume from hibernation failed (%d)\n", error); + pr_info("resume failed (%d)\n", error); atomic_inc(&snapshot_device_available); /* For success case, the suspend path will release the lock */ Unlock: @@ -1068,7 +1068,8 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, lock_system_sleep(); swsusp_resume_device = res; unlock_system_sleep(); - pm_pr_dbg("Configured resume from disk to %u\n", swsusp_resume_device); + pm_pr_dbg("Configured hibernation resume from disk to %u\n", + swsusp_resume_device); noresume = 0; software_resume(); return n; diff --git a/kernel/power/main.c b/kernel/power/main.c index e26de7af520b..69b7a8aeca3b 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -190,6 +190,38 @@ static ssize_t mem_sleep_store(struct kobject *kobj, struct kobj_attribute *attr } power_attr(mem_sleep); + +/* + * sync_on_suspend: invoke ksys_sync_helper() before suspend. + * + * show() returns whether ksys_sync_helper() is invoked before suspend. + * store() accepts 0 or 1. 0 disables ksys_sync_helper() and 1 enables it. + */ +bool sync_on_suspend_enabled = !IS_ENABLED(CONFIG_SUSPEND_SKIP_SYNC); + +static ssize_t sync_on_suspend_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", sync_on_suspend_enabled); +} + +static ssize_t sync_on_suspend_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + unsigned long val; + + if (kstrtoul(buf, 10, &val)) + return -EINVAL; + + if (val > 1) + return -EINVAL; + + sync_on_suspend_enabled = !!val; + return n; +} + +power_attr(sync_on_suspend); #endif /* CONFIG_SUSPEND */ #ifdef CONFIG_PM_SLEEP_DEBUG @@ -855,6 +887,7 @@ static struct attribute * g[] = { &wakeup_count_attr.attr, #ifdef CONFIG_SUSPEND &mem_sleep_attr.attr, + &sync_on_suspend_attr.attr, #endif #ifdef CONFIG_PM_AUTOSLEEP &autosleep_attr.attr, diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 26b9168321e7..ddade80ad276 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -8,7 +8,7 @@ * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl> */ -#define pr_fmt(fmt) "PM: " fmt +#define pr_fmt(fmt) "PM: hibernation: " fmt #include <linux/version.h> #include <linux/module.h> @@ -1147,24 +1147,24 @@ void free_basic_memory_bitmaps(void) void clear_free_pages(void) { -#ifdef CONFIG_PAGE_POISONING_ZERO struct memory_bitmap *bm = free_pages_map; unsigned long pfn; if (WARN_ON(!(free_pages_map))) return; - memory_bm_position_reset(bm); - pfn = memory_bm_next_pfn(bm); - while (pfn != BM_END_OF_MAP) { - if (pfn_valid(pfn)) - clear_highpage(pfn_to_page(pfn)); - + if (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) || want_init_on_free()) { + memory_bm_position_reset(bm); pfn = memory_bm_next_pfn(bm); + while (pfn != BM_END_OF_MAP) { + if (pfn_valid(pfn)) + clear_highpage(pfn_to_page(pfn)); + + pfn = memory_bm_next_pfn(bm); + } + memory_bm_position_reset(bm); + pr_info("free pages cleared after restore\n"); } - memory_bm_position_reset(bm); - pr_info("free pages cleared after restore\n"); -#endif /* PAGE_POISONING_ZERO */ } /** @@ -1566,9 +1566,7 @@ static unsigned long preallocate_image_highmem(unsigned long nr_pages) */ static unsigned long __fraction(u64 x, u64 multiplier, u64 base) { - x *= multiplier; - do_div(x, base); - return (unsigned long)x; + return div64_u64(x * multiplier, base); } static unsigned long preallocate_highmem_fraction(unsigned long nr_pages, @@ -1705,16 +1703,20 @@ int hibernate_preallocate_memory(void) ktime_t start, stop; int error; - pr_info("Preallocating image memory... "); + pr_info("Preallocating image memory\n"); start = ktime_get(); error = memory_bm_create(&orig_bm, GFP_IMAGE, PG_ANY); - if (error) + if (error) { + pr_err("Cannot allocate original bitmap\n"); goto err_out; + } error = memory_bm_create(©_bm, GFP_IMAGE, PG_ANY); - if (error) + if (error) { + pr_err("Cannot allocate copy bitmap\n"); goto err_out; + } alloc_normal = 0; alloc_highmem = 0; @@ -1804,8 +1806,11 @@ int hibernate_preallocate_memory(void) alloc -= pages; pages += pages_highmem; pages_highmem = preallocate_image_highmem(alloc); - if (pages_highmem < alloc) + if (pages_highmem < alloc) { + pr_err("Image allocation is %lu pages short\n", + alloc - pages_highmem); goto err_out; + } pages += pages_highmem; /* * size is the desired number of saveable pages to leave in @@ -1836,13 +1841,12 @@ int hibernate_preallocate_memory(void) out: stop = ktime_get(); - pr_cont("done (allocated %lu pages)\n", pages); + pr_info("Allocated %lu pages for snapshot\n", pages); swsusp_show_speed(start, stop, pages, "Allocated"); return 0; err_out: - pr_cont("\n"); swsusp_free(); return -ENOMEM; } @@ -1976,7 +1980,7 @@ asmlinkage __visible int swsusp_save(void) { unsigned int nr_pages, nr_highmem; - pr_info("Creating hibernation image:\n"); + pr_info("Creating image:\n"); drain_local_pages(NULL); nr_pages = count_data_pages(); @@ -2010,7 +2014,7 @@ asmlinkage __visible int swsusp_save(void) nr_copy_pages = nr_pages; nr_meta_pages = DIV_ROUND_UP(nr_pages * sizeof(long), PAGE_SIZE); - pr_info("Hibernation image created (%d pages copied)\n", nr_pages); + pr_info("Image created (%d pages copied)\n", nr_pages); return 0; } diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index f3b7239f1892..2c47280fbfc7 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -564,7 +564,7 @@ static int enter_state(suspend_state_t state) if (state == PM_SUSPEND_TO_IDLE) s2idle_begin(); - if (!IS_ENABLED(CONFIG_SUSPEND_SKIP_SYNC)) { + if (sync_on_suspend_enabled) { trace_suspend_resume(TPS("sync_filesystems"), 0, true); ksys_sync_helper(); trace_suspend_resume(TPS("sync_filesystems"), 0, false); diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c index 60564b58de07..e1ed58adb69e 100644 --- a/kernel/power/suspend_test.c +++ b/kernel/power/suspend_test.c @@ -70,7 +70,7 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state) static char info_test[] __initdata = KERN_INFO "PM: test RTC wakeup from '%s' suspend\n"; - unsigned long now; + time64_t now; struct rtc_wkalrm alm; int status; @@ -81,10 +81,10 @@ repeat: printk(err_readtime, dev_name(&rtc->dev), status); return; } - rtc_tm_to_time(&alm.time, &now); + now = rtc_tm_to_time64(&alm.time); memset(&alm, 0, sizeof alm); - rtc_time_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time); + rtc_time64_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time); alm.enabled = true; status = rtc_set_alarm(rtc, &alm); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index cb9ddcc08119..43d6179508d6 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -264,12 +264,17 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) return ret; } -static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) +static bool ptrace_has_cap(const struct cred *cred, struct user_namespace *ns, + unsigned int mode) { + int ret; + if (mode & PTRACE_MODE_NOAUDIT) - return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE); + ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT); else - return has_ns_capability(current, ns, CAP_SYS_PTRACE); + ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NONE); + + return ret == 0; } /* Returns 0 on success, -errno on denial. */ @@ -321,7 +326,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) gid_eq(caller_gid, tcred->sgid) && gid_eq(caller_gid, tcred->gid)) goto ok; - if (ptrace_has_cap(tcred->user_ns, mode)) + if (ptrace_has_cap(cred, tcred->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM; @@ -340,7 +345,7 @@ ok: mm = task->mm; if (mm && ((get_dumpable(mm) != SUID_DUMP_USER) && - !ptrace_has_cap(mm->user_ns, mode))) + !ptrace_has_cap(cred, mm->user_ns, mode))) return -EPERM; return security_ptrace_access_check(task, mode); diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig index 7644eda17d62..1cc940fef17c 100644 --- a/kernel/rcu/Kconfig +++ b/kernel/rcu/Kconfig @@ -7,7 +7,7 @@ menu "RCU Subsystem" config TREE_RCU bool - default y if !PREEMPTION && SMP + default y if SMP help This option selects the RCU implementation that is designed for very large SMP system with hundreds or @@ -17,6 +17,7 @@ config TREE_RCU config PREEMPT_RCU bool default y if PREEMPTION + select TREE_RCU help This option selects the RCU implementation that is designed for very large SMP systems with hundreds or @@ -78,7 +79,7 @@ config TASKS_RCU user-mode execution as quiescent states. config RCU_STALL_COMMON - def_bool ( TREE_RCU || PREEMPT_RCU ) + def_bool TREE_RCU help This option enables RCU CPU stall code that is common between the TINY and TREE variants of RCU. The purpose is to allow @@ -86,13 +87,13 @@ config RCU_STALL_COMMON making these warnings mandatory for the tree variants. config RCU_NEED_SEGCBLIST - def_bool ( TREE_RCU || PREEMPT_RCU || TREE_SRCU ) + def_bool ( TREE_RCU || TREE_SRCU ) config RCU_FANOUT int "Tree-based hierarchical RCU fanout value" range 2 64 if 64BIT range 2 32 if !64BIT - depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT + depends on TREE_RCU && RCU_EXPERT default 64 if 64BIT default 32 if !64BIT help @@ -112,7 +113,7 @@ config RCU_FANOUT_LEAF int "Tree-based hierarchical RCU leaf-level fanout value" range 2 64 if 64BIT range 2 32 if !64BIT - depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT + depends on TREE_RCU && RCU_EXPERT default 16 help This option controls the leaf-level fanout of hierarchical @@ -187,7 +188,7 @@ config RCU_BOOST_DELAY config RCU_NOCB_CPU bool "Offload RCU callback processing from boot-selected CPUs" - depends on TREE_RCU || PREEMPT_RCU + depends on TREE_RCU depends on RCU_EXPERT || NO_HZ_FULL default n help @@ -200,8 +201,8 @@ config RCU_NOCB_CPU specified at boot time by the rcu_nocbs parameter. For each such CPU, a kthread ("rcuox/N") will be created to invoke callbacks, where the "N" is the CPU being offloaded, and where - the "p" for RCU-preempt (PREEMPT kernels) and "s" for RCU-sched - (!PREEMPT kernels). Nothing prevents this kthread from running + the "p" for RCU-preempt (PREEMPTION kernels) and "s" for RCU-sched + (!PREEMPTION kernels). Nothing prevents this kthread from running on the specified CPUs, but (1) the kthreads may be preempted between each callback, and (2) affinity or cgroups can be used to force the kthreads to run on whatever set of CPUs is desired. diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile index 020e8b6a644b..82d5fba48b2f 100644 --- a/kernel/rcu/Makefile +++ b/kernel/rcu/Makefile @@ -9,6 +9,5 @@ obj-$(CONFIG_TINY_SRCU) += srcutiny.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o obj-$(CONFIG_TREE_RCU) += tree.o -obj-$(CONFIG_PREEMPT_RCU) += tree.o obj-$(CONFIG_TINY_RCU) += tiny.o obj-$(CONFIG_RCU_NEED_SEGCBLIST) += rcu_segcblist.o diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index ab504fbc76ca..05f936ed167a 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -198,33 +198,6 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head) } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ -void kfree(const void *); - -/* - * Reclaim the specified callback, either by invoking it (non-lazy case) - * or freeing it directly (lazy case). Return true if lazy, false otherwise. - */ -static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head) -{ - rcu_callback_t f; - unsigned long offset = (unsigned long)head->func; - - rcu_lock_acquire(&rcu_callback_map); - if (__is_kfree_rcu_offset(offset)) { - trace_rcu_invoke_kfree_callback(rn, head, offset); - kfree((void *)head - offset); - rcu_lock_release(&rcu_callback_map); - return true; - } else { - trace_rcu_invoke_callback(rn, head); - f = head->func; - WRITE_ONCE(head->func, (rcu_callback_t)0L); - f(head); - rcu_lock_release(&rcu_callback_map); - return false; - } -} - #ifdef CONFIG_RCU_STALL_COMMON extern int rcu_cpu_stall_ftrace_dump; @@ -281,7 +254,7 @@ void rcu_test_sync_prims(void); */ extern void resched_cpu(int cpu); -#if defined(SRCU) || !defined(TINY_RCU) +#if defined(CONFIG_SRCU) || !defined(CONFIG_TINY_RCU) #include <linux/rcu_node_tree.h> @@ -418,7 +391,7 @@ do { \ #define raw_lockdep_assert_held_rcu_node(p) \ lockdep_assert_held(&ACCESS_PRIVATE(p, lock)) -#endif /* #if defined(SRCU) || !defined(TINY_RCU) */ +#endif /* #if defined(CONFIG_SRCU) || !defined(CONFIG_TINY_RCU) */ #ifdef CONFIG_SRCU void srcu_init(void); @@ -454,7 +427,7 @@ enum rcutorture_type { INVALID_RCU_FLAVOR }; -#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) +#if defined(CONFIG_TREE_RCU) void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, unsigned long *gp_seq); void do_trace_rcu_torture_read(const char *rcutorturename, diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c index cbc87b804db9..5f4fd3b8777c 100644 --- a/kernel/rcu/rcu_segcblist.c +++ b/kernel/rcu/rcu_segcblist.c @@ -20,14 +20,10 @@ void rcu_cblist_init(struct rcu_cblist *rclp) rclp->head = NULL; rclp->tail = &rclp->head; rclp->len = 0; - rclp->len_lazy = 0; } /* * Enqueue an rcu_head structure onto the specified callback list. - * This function assumes that the callback is non-lazy because it - * is intended for use by no-CBs CPUs, which do not distinguish - * between lazy and non-lazy RCU callbacks. */ void rcu_cblist_enqueue(struct rcu_cblist *rclp, struct rcu_head *rhp) { @@ -54,7 +50,6 @@ void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp, else drclp->tail = &drclp->head; drclp->len = srclp->len; - drclp->len_lazy = srclp->len_lazy; if (!rhp) { rcu_cblist_init(srclp); } else { @@ -62,16 +57,12 @@ void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp, srclp->head = rhp; srclp->tail = &rhp->next; WRITE_ONCE(srclp->len, 1); - srclp->len_lazy = 0; } } /* * Dequeue the oldest rcu_head structure from the specified callback - * list. This function assumes that the callback is non-lazy, but - * the caller can later invoke rcu_cblist_dequeued_lazy() if it - * finds otherwise (and if it cares about laziness). This allows - * different users to have different ways of determining laziness. + * list. */ struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp) { @@ -161,7 +152,6 @@ void rcu_segcblist_init(struct rcu_segcblist *rsclp) for (i = 0; i < RCU_CBLIST_NSEGS; i++) rsclp->tails[i] = &rsclp->head; rcu_segcblist_set_len(rsclp, 0); - rsclp->len_lazy = 0; rsclp->enabled = 1; } @@ -173,7 +163,6 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp) { WARN_ON_ONCE(!rcu_segcblist_empty(rsclp)); WARN_ON_ONCE(rcu_segcblist_n_cbs(rsclp)); - WARN_ON_ONCE(rcu_segcblist_n_lazy_cbs(rsclp)); rsclp->enabled = 0; } @@ -253,11 +242,9 @@ bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, unsigned long *lp) * absolutely not OK for it to ever miss posting a callback. */ void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp, - struct rcu_head *rhp, bool lazy) + struct rcu_head *rhp) { rcu_segcblist_inc_len(rsclp); - if (lazy) - rsclp->len_lazy++; smp_mb(); /* Ensure counts are updated before callback is enqueued. */ rhp->next = NULL; WRITE_ONCE(*rsclp->tails[RCU_NEXT_TAIL], rhp); @@ -275,15 +262,13 @@ void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp, * period. You have been warned. */ bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp, - struct rcu_head *rhp, bool lazy) + struct rcu_head *rhp) { int i; if (rcu_segcblist_n_cbs(rsclp) == 0) return false; rcu_segcblist_inc_len(rsclp); - if (lazy) - rsclp->len_lazy++; smp_mb(); /* Ensure counts are updated before callback is entrained. */ rhp->next = NULL; for (i = RCU_NEXT_TAIL; i > RCU_DONE_TAIL; i--) @@ -307,8 +292,6 @@ bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp, void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp, struct rcu_cblist *rclp) { - rclp->len_lazy += rsclp->len_lazy; - rsclp->len_lazy = 0; rclp->len = rcu_segcblist_xchg_len(rsclp, 0); } @@ -361,9 +344,7 @@ void rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp, void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp, struct rcu_cblist *rclp) { - rsclp->len_lazy += rclp->len_lazy; rcu_segcblist_add_len(rsclp, rclp->len); - rclp->len_lazy = 0; rclp->len = 0; } diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h index 815c2fdd3fcc..5c293afc07b8 100644 --- a/kernel/rcu/rcu_segcblist.h +++ b/kernel/rcu/rcu_segcblist.h @@ -15,15 +15,6 @@ static inline long rcu_cblist_n_cbs(struct rcu_cblist *rclp) return READ_ONCE(rclp->len); } -/* - * Account for the fact that a previously dequeued callback turned out - * to be marked as lazy. - */ -static inline void rcu_cblist_dequeued_lazy(struct rcu_cblist *rclp) -{ - rclp->len_lazy--; -} - void rcu_cblist_init(struct rcu_cblist *rclp); void rcu_cblist_enqueue(struct rcu_cblist *rclp, struct rcu_head *rhp); void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp, @@ -59,18 +50,6 @@ static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp) #endif } -/* Return number of lazy callbacks in segmented callback list. */ -static inline long rcu_segcblist_n_lazy_cbs(struct rcu_segcblist *rsclp) -{ - return rsclp->len_lazy; -} - -/* Return number of lazy callbacks in segmented callback list. */ -static inline long rcu_segcblist_n_nonlazy_cbs(struct rcu_segcblist *rsclp) -{ - return rcu_segcblist_n_cbs(rsclp) - rsclp->len_lazy; -} - /* * Is the specified rcu_segcblist enabled, for example, not corresponding * to an offline CPU? @@ -106,9 +85,9 @@ struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp); struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp); bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, unsigned long *lp); void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp, - struct rcu_head *rhp, bool lazy); + struct rcu_head *rhp); bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp, - struct rcu_head *rhp, bool lazy); + struct rcu_head *rhp); void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp, struct rcu_cblist *rclp); void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp, diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index 5f884d560384..da94b89cd531 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -86,6 +86,7 @@ torture_param(bool, shutdown, RCUPERF_SHUTDOWN, "Shutdown at end of performance tests."); torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable"); +torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() perf test?"); static char *perf_type = "rcu"; module_param(perf_type, charp, 0444); @@ -105,8 +106,8 @@ static atomic_t n_rcu_perf_writer_finished; static wait_queue_head_t shutdown_wq; static u64 t_rcu_perf_writer_started; static u64 t_rcu_perf_writer_finished; -static unsigned long b_rcu_perf_writer_started; -static unsigned long b_rcu_perf_writer_finished; +static unsigned long b_rcu_gp_test_started; +static unsigned long b_rcu_gp_test_finished; static DEFINE_PER_CPU(atomic_t, n_async_inflight); #define MAX_MEAS 10000 @@ -378,10 +379,10 @@ rcu_perf_writer(void *arg) if (atomic_inc_return(&n_rcu_perf_writer_started) >= nrealwriters) { t_rcu_perf_writer_started = t; if (gp_exp) { - b_rcu_perf_writer_started = + b_rcu_gp_test_started = cur_ops->exp_completed() / 2; } else { - b_rcu_perf_writer_started = cur_ops->get_gp_seq(); + b_rcu_gp_test_started = cur_ops->get_gp_seq(); } } @@ -429,10 +430,10 @@ retry: PERFOUT_STRING("Test complete"); t_rcu_perf_writer_finished = t; if (gp_exp) { - b_rcu_perf_writer_finished = + b_rcu_gp_test_finished = cur_ops->exp_completed() / 2; } else { - b_rcu_perf_writer_finished = + b_rcu_gp_test_finished = cur_ops->get_gp_seq(); } if (shutdown) { @@ -515,8 +516,8 @@ rcu_perf_cleanup(void) t_rcu_perf_writer_finished - t_rcu_perf_writer_started, ngps, - rcuperf_seq_diff(b_rcu_perf_writer_finished, - b_rcu_perf_writer_started)); + rcuperf_seq_diff(b_rcu_gp_test_finished, + b_rcu_gp_test_started)); for (i = 0; i < nrealwriters; i++) { if (!writer_durations) break; @@ -584,6 +585,159 @@ rcu_perf_shutdown(void *arg) return -EINVAL; } +/* + * kfree_rcu() performance tests: Start a kfree_rcu() loop on all CPUs for number + * of iterations and measure total time and number of GP for all iterations to complete. + */ + +torture_param(int, kfree_nthreads, -1, "Number of threads running loops of kfree_rcu()."); +torture_param(int, kfree_alloc_num, 8000, "Number of allocations and frees done in an iteration."); +torture_param(int, kfree_loops, 10, "Number of loops doing kfree_alloc_num allocations and frees."); + +static struct task_struct **kfree_reader_tasks; +static int kfree_nrealthreads; +static atomic_t n_kfree_perf_thread_started; +static atomic_t n_kfree_perf_thread_ended; + +struct kfree_obj { + char kfree_obj[8]; + struct rcu_head rh; +}; + +static int +kfree_perf_thread(void *arg) +{ + int i, loop = 0; + long me = (long)arg; + struct kfree_obj *alloc_ptr; + u64 start_time, end_time; + + VERBOSE_PERFOUT_STRING("kfree_perf_thread task started"); + set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids)); + set_user_nice(current, MAX_NICE); + + start_time = ktime_get_mono_fast_ns(); + + if (atomic_inc_return(&n_kfree_perf_thread_started) >= kfree_nrealthreads) { + if (gp_exp) + b_rcu_gp_test_started = cur_ops->exp_completed() / 2; + else + b_rcu_gp_test_started = cur_ops->get_gp_seq(); + } + + do { + for (i = 0; i < kfree_alloc_num; i++) { + alloc_ptr = kmalloc(sizeof(struct kfree_obj), GFP_KERNEL); + if (!alloc_ptr) + return -ENOMEM; + + kfree_rcu(alloc_ptr, rh); + } + + cond_resched(); + } while (!torture_must_stop() && ++loop < kfree_loops); + + if (atomic_inc_return(&n_kfree_perf_thread_ended) >= kfree_nrealthreads) { + end_time = ktime_get_mono_fast_ns(); + + if (gp_exp) + b_rcu_gp_test_finished = cur_ops->exp_completed() / 2; + else + b_rcu_gp_test_finished = cur_ops->get_gp_seq(); + + pr_alert("Total time taken by all kfree'ers: %llu ns, loops: %d, batches: %ld\n", + (unsigned long long)(end_time - start_time), kfree_loops, + rcuperf_seq_diff(b_rcu_gp_test_finished, b_rcu_gp_test_started)); + if (shutdown) { + smp_mb(); /* Assign before wake. */ + wake_up(&shutdown_wq); + } + } + + torture_kthread_stopping("kfree_perf_thread"); + return 0; +} + +static void +kfree_perf_cleanup(void) +{ + int i; + + if (torture_cleanup_begin()) + return; + + if (kfree_reader_tasks) { + for (i = 0; i < kfree_nrealthreads; i++) + torture_stop_kthread(kfree_perf_thread, + kfree_reader_tasks[i]); + kfree(kfree_reader_tasks); + } + + torture_cleanup_end(); +} + +/* + * shutdown kthread. Just waits to be awakened, then shuts down system. + */ +static int +kfree_perf_shutdown(void *arg) +{ + do { + wait_event(shutdown_wq, + atomic_read(&n_kfree_perf_thread_ended) >= + kfree_nrealthreads); + } while (atomic_read(&n_kfree_perf_thread_ended) < kfree_nrealthreads); + + smp_mb(); /* Wake before output. */ + + kfree_perf_cleanup(); + kernel_power_off(); + return -EINVAL; +} + +static int __init +kfree_perf_init(void) +{ + long i; + int firsterr = 0; + + kfree_nrealthreads = compute_real(kfree_nthreads); + /* Start up the kthreads. */ + if (shutdown) { + init_waitqueue_head(&shutdown_wq); + firsterr = torture_create_kthread(kfree_perf_shutdown, NULL, + shutdown_task); + if (firsterr) + goto unwind; + schedule_timeout_uninterruptible(1); + } + + kfree_reader_tasks = kcalloc(kfree_nrealthreads, sizeof(kfree_reader_tasks[0]), + GFP_KERNEL); + if (kfree_reader_tasks == NULL) { + firsterr = -ENOMEM; + goto unwind; + } + + for (i = 0; i < kfree_nrealthreads; i++) { + firsterr = torture_create_kthread(kfree_perf_thread, (void *)i, + kfree_reader_tasks[i]); + if (firsterr) + goto unwind; + } + + while (atomic_read(&n_kfree_perf_thread_started) < kfree_nrealthreads) + schedule_timeout_uninterruptible(1); + + torture_init_end(); + return 0; + +unwind: + torture_init_end(); + kfree_perf_cleanup(); + return firsterr; +} + static int __init rcu_perf_init(void) { @@ -616,6 +770,9 @@ rcu_perf_init(void) if (cur_ops->init) cur_ops->init(); + if (kfree_rcu_test) + return kfree_perf_init(); + nrealwriters = compute_real(nwriters); nrealreaders = compute_real(nreaders); atomic_set(&n_rcu_perf_reader_started, 0); diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index dee043feb71f..1aeecc165b21 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -1661,43 +1661,52 @@ static void rcu_torture_fwd_prog_cb(struct rcu_head *rhp) struct rcu_fwd_cb { struct rcu_head rh; struct rcu_fwd_cb *rfc_next; + struct rcu_fwd *rfc_rfp; int rfc_gps; }; -static DEFINE_SPINLOCK(rcu_fwd_lock); -static struct rcu_fwd_cb *rcu_fwd_cb_head; -static struct rcu_fwd_cb **rcu_fwd_cb_tail = &rcu_fwd_cb_head; -static long n_launders_cb; -static unsigned long rcu_fwd_startat; -static bool rcu_fwd_emergency_stop; + #define MAX_FWD_CB_JIFFIES (8 * HZ) /* Maximum CB test duration. */ #define MIN_FWD_CB_LAUNDERS 3 /* This many CB invocations to count. */ #define MIN_FWD_CBS_LAUNDERED 100 /* Number of counted CBs. */ #define FWD_CBS_HIST_DIV 10 /* Histogram buckets/second. */ +#define N_LAUNDERS_HIST (2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV)) + struct rcu_launder_hist { long n_launders; unsigned long launder_gp_seq; }; -#define N_LAUNDERS_HIST (2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV)) -static struct rcu_launder_hist n_launders_hist[N_LAUNDERS_HIST]; -static unsigned long rcu_launder_gp_seq_start; -static void rcu_torture_fwd_cb_hist(void) +struct rcu_fwd { + spinlock_t rcu_fwd_lock; + struct rcu_fwd_cb *rcu_fwd_cb_head; + struct rcu_fwd_cb **rcu_fwd_cb_tail; + long n_launders_cb; + unsigned long rcu_fwd_startat; + struct rcu_launder_hist n_launders_hist[N_LAUNDERS_HIST]; + unsigned long rcu_launder_gp_seq_start; +}; + +struct rcu_fwd *rcu_fwds; +bool rcu_fwd_emergency_stop; + +static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp) { unsigned long gps; unsigned long gps_old; int i; int j; - for (i = ARRAY_SIZE(n_launders_hist) - 1; i > 0; i--) - if (n_launders_hist[i].n_launders > 0) + for (i = ARRAY_SIZE(rfp->n_launders_hist) - 1; i > 0; i--) + if (rfp->n_launders_hist[i].n_launders > 0) break; pr_alert("%s: Callback-invocation histogram (duration %lu jiffies):", - __func__, jiffies - rcu_fwd_startat); - gps_old = rcu_launder_gp_seq_start; + __func__, jiffies - rfp->rcu_fwd_startat); + gps_old = rfp->rcu_launder_gp_seq_start; for (j = 0; j <= i; j++) { - gps = n_launders_hist[j].launder_gp_seq; + gps = rfp->n_launders_hist[j].launder_gp_seq; pr_cont(" %ds/%d: %ld:%ld", - j + 1, FWD_CBS_HIST_DIV, n_launders_hist[j].n_launders, + j + 1, FWD_CBS_HIST_DIV, + rfp->n_launders_hist[j].n_launders, rcutorture_seq_diff(gps, gps_old)); gps_old = gps; } @@ -1711,26 +1720,27 @@ static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp) int i; struct rcu_fwd_cb *rfcp = container_of(rhp, struct rcu_fwd_cb, rh); struct rcu_fwd_cb **rfcpp; + struct rcu_fwd *rfp = rfcp->rfc_rfp; rfcp->rfc_next = NULL; rfcp->rfc_gps++; - spin_lock_irqsave(&rcu_fwd_lock, flags); - rfcpp = rcu_fwd_cb_tail; - rcu_fwd_cb_tail = &rfcp->rfc_next; + spin_lock_irqsave(&rfp->rcu_fwd_lock, flags); + rfcpp = rfp->rcu_fwd_cb_tail; + rfp->rcu_fwd_cb_tail = &rfcp->rfc_next; WRITE_ONCE(*rfcpp, rfcp); - WRITE_ONCE(n_launders_cb, n_launders_cb + 1); - i = ((jiffies - rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV)); - if (i >= ARRAY_SIZE(n_launders_hist)) - i = ARRAY_SIZE(n_launders_hist) - 1; - n_launders_hist[i].n_launders++; - n_launders_hist[i].launder_gp_seq = cur_ops->get_gp_seq(); - spin_unlock_irqrestore(&rcu_fwd_lock, flags); + WRITE_ONCE(rfp->n_launders_cb, rfp->n_launders_cb + 1); + i = ((jiffies - rfp->rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV)); + if (i >= ARRAY_SIZE(rfp->n_launders_hist)) + i = ARRAY_SIZE(rfp->n_launders_hist) - 1; + rfp->n_launders_hist[i].n_launders++; + rfp->n_launders_hist[i].launder_gp_seq = cur_ops->get_gp_seq(); + spin_unlock_irqrestore(&rfp->rcu_fwd_lock, flags); } // Give the scheduler a chance, even on nohz_full CPUs. static void rcu_torture_fwd_prog_cond_resched(unsigned long iter) { - if (IS_ENABLED(CONFIG_PREEMPT) && IS_ENABLED(CONFIG_NO_HZ_FULL)) { + if (IS_ENABLED(CONFIG_PREEMPTION) && IS_ENABLED(CONFIG_NO_HZ_FULL)) { // Real call_rcu() floods hit userspace, so emulate that. if (need_resched() || (iter & 0xfff)) schedule(); @@ -1744,23 +1754,23 @@ static void rcu_torture_fwd_prog_cond_resched(unsigned long iter) * Free all callbacks on the rcu_fwd_cb_head list, either because the * test is over or because we hit an OOM event. */ -static unsigned long rcu_torture_fwd_prog_cbfree(void) +static unsigned long rcu_torture_fwd_prog_cbfree(struct rcu_fwd *rfp) { unsigned long flags; unsigned long freed = 0; struct rcu_fwd_cb *rfcp; for (;;) { - spin_lock_irqsave(&rcu_fwd_lock, flags); - rfcp = rcu_fwd_cb_head; + spin_lock_irqsave(&rfp->rcu_fwd_lock, flags); + rfcp = rfp->rcu_fwd_cb_head; if (!rfcp) { - spin_unlock_irqrestore(&rcu_fwd_lock, flags); + spin_unlock_irqrestore(&rfp->rcu_fwd_lock, flags); break; } - rcu_fwd_cb_head = rfcp->rfc_next; - if (!rcu_fwd_cb_head) - rcu_fwd_cb_tail = &rcu_fwd_cb_head; - spin_unlock_irqrestore(&rcu_fwd_lock, flags); + rfp->rcu_fwd_cb_head = rfcp->rfc_next; + if (!rfp->rcu_fwd_cb_head) + rfp->rcu_fwd_cb_tail = &rfp->rcu_fwd_cb_head; + spin_unlock_irqrestore(&rfp->rcu_fwd_lock, flags); kfree(rfcp); freed++; rcu_torture_fwd_prog_cond_resched(freed); @@ -1774,7 +1784,8 @@ static unsigned long rcu_torture_fwd_prog_cbfree(void) } /* Carry out need_resched()/cond_resched() forward-progress testing. */ -static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries) +static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp, + int *tested, int *tested_tries) { unsigned long cver; unsigned long dur; @@ -1804,8 +1815,8 @@ static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries) sd = cur_ops->stall_dur() + 1; sd4 = (sd + fwd_progress_div - 1) / fwd_progress_div; dur = sd4 + torture_random(&trs) % (sd - sd4); - WRITE_ONCE(rcu_fwd_startat, jiffies); - stopat = rcu_fwd_startat + dur; + WRITE_ONCE(rfp->rcu_fwd_startat, jiffies); + stopat = rfp->rcu_fwd_startat + dur; while (time_before(jiffies, stopat) && !shutdown_time_arrived() && !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) { @@ -1840,7 +1851,7 @@ static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries) } /* Carry out call_rcu() forward-progress testing. */ -static void rcu_torture_fwd_prog_cr(void) +static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp) { unsigned long cver; unsigned long flags; @@ -1864,23 +1875,23 @@ static void rcu_torture_fwd_prog_cr(void) /* Loop continuously posting RCU callbacks. */ WRITE_ONCE(rcu_fwd_cb_nodelay, true); cur_ops->sync(); /* Later readers see above write. */ - WRITE_ONCE(rcu_fwd_startat, jiffies); - stopat = rcu_fwd_startat + MAX_FWD_CB_JIFFIES; + WRITE_ONCE(rfp->rcu_fwd_startat, jiffies); + stopat = rfp->rcu_fwd_startat + MAX_FWD_CB_JIFFIES; n_launders = 0; - n_launders_cb = 0; + rfp->n_launders_cb = 0; // Hoist initialization for multi-kthread n_launders_sa = 0; n_max_cbs = 0; n_max_gps = 0; - for (i = 0; i < ARRAY_SIZE(n_launders_hist); i++) - n_launders_hist[i].n_launders = 0; + for (i = 0; i < ARRAY_SIZE(rfp->n_launders_hist); i++) + rfp->n_launders_hist[i].n_launders = 0; cver = READ_ONCE(rcu_torture_current_version); gps = cur_ops->get_gp_seq(); - rcu_launder_gp_seq_start = gps; + rfp->rcu_launder_gp_seq_start = gps; tick_dep_set_task(current, TICK_DEP_BIT_RCU); while (time_before(jiffies, stopat) && !shutdown_time_arrived() && !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) { - rfcp = READ_ONCE(rcu_fwd_cb_head); + rfcp = READ_ONCE(rfp->rcu_fwd_cb_head); rfcpn = NULL; if (rfcp) rfcpn = READ_ONCE(rfcp->rfc_next); @@ -1888,7 +1899,7 @@ static void rcu_torture_fwd_prog_cr(void) if (rfcp->rfc_gps >= MIN_FWD_CB_LAUNDERS && ++n_max_gps >= MIN_FWD_CBS_LAUNDERED) break; - rcu_fwd_cb_head = rfcpn; + rfp->rcu_fwd_cb_head = rfcpn; n_launders++; n_launders_sa++; } else { @@ -1900,6 +1911,7 @@ static void rcu_torture_fwd_prog_cr(void) n_max_cbs++; n_launders_sa = 0; rfcp->rfc_gps = 0; + rfcp->rfc_rfp = rfp; } cur_ops->call(&rfcp->rh, rcu_torture_fwd_cb_cr); rcu_torture_fwd_prog_cond_resched(n_launders + n_max_cbs); @@ -1910,22 +1922,22 @@ static void rcu_torture_fwd_prog_cr(void) } } stoppedat = jiffies; - n_launders_cb_snap = READ_ONCE(n_launders_cb); + n_launders_cb_snap = READ_ONCE(rfp->n_launders_cb); cver = READ_ONCE(rcu_torture_current_version) - cver; gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps); cur_ops->cb_barrier(); /* Wait for callbacks to be invoked. */ - (void)rcu_torture_fwd_prog_cbfree(); + (void)rcu_torture_fwd_prog_cbfree(rfp); if (!torture_must_stop() && !READ_ONCE(rcu_fwd_emergency_stop) && !shutdown_time_arrived()) { WARN_ON(n_max_gps < MIN_FWD_CBS_LAUNDERED); pr_alert("%s Duration %lu barrier: %lu pending %ld n_launders: %ld n_launders_sa: %ld n_max_gps: %ld n_max_cbs: %ld cver %ld gps %ld\n", __func__, - stoppedat - rcu_fwd_startat, jiffies - stoppedat, + stoppedat - rfp->rcu_fwd_startat, jiffies - stoppedat, n_launders + n_max_cbs - n_launders_cb_snap, n_launders, n_launders_sa, n_max_gps, n_max_cbs, cver, gps); - rcu_torture_fwd_cb_hist(); + rcu_torture_fwd_cb_hist(rfp); } schedule_timeout_uninterruptible(HZ); /* Let CBs drain. */ tick_dep_clear_task(current, TICK_DEP_BIT_RCU); @@ -1940,20 +1952,22 @@ static void rcu_torture_fwd_prog_cr(void) static int rcutorture_oom_notify(struct notifier_block *self, unsigned long notused, void *nfreed) { + struct rcu_fwd *rfp = rcu_fwds; + WARN(1, "%s invoked upon OOM during forward-progress testing.\n", __func__); - rcu_torture_fwd_cb_hist(); - rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat)) / 2); + rcu_torture_fwd_cb_hist(rfp); + rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rfp->rcu_fwd_startat)) / 2); WRITE_ONCE(rcu_fwd_emergency_stop, true); smp_mb(); /* Emergency stop before free and wait to avoid hangs. */ pr_info("%s: Freed %lu RCU callbacks.\n", - __func__, rcu_torture_fwd_prog_cbfree()); + __func__, rcu_torture_fwd_prog_cbfree(rfp)); rcu_barrier(); pr_info("%s: Freed %lu RCU callbacks.\n", - __func__, rcu_torture_fwd_prog_cbfree()); + __func__, rcu_torture_fwd_prog_cbfree(rfp)); rcu_barrier(); pr_info("%s: Freed %lu RCU callbacks.\n", - __func__, rcu_torture_fwd_prog_cbfree()); + __func__, rcu_torture_fwd_prog_cbfree(rfp)); smp_mb(); /* Frees before return to avoid redoing OOM. */ (*(unsigned long *)nfreed)++; /* Forward progress CBs freed! */ pr_info("%s returning after OOM processing.\n", __func__); @@ -1967,6 +1981,7 @@ static struct notifier_block rcutorture_oom_nb = { /* Carry out grace-period forward-progress testing. */ static int rcu_torture_fwd_prog(void *args) { + struct rcu_fwd *rfp = args; int tested = 0; int tested_tries = 0; @@ -1978,8 +1993,8 @@ static int rcu_torture_fwd_prog(void *args) schedule_timeout_interruptible(fwd_progress_holdoff * HZ); WRITE_ONCE(rcu_fwd_emergency_stop, false); register_oom_notifier(&rcutorture_oom_nb); - rcu_torture_fwd_prog_nr(&tested, &tested_tries); - rcu_torture_fwd_prog_cr(); + rcu_torture_fwd_prog_nr(rfp, &tested, &tested_tries); + rcu_torture_fwd_prog_cr(rfp); unregister_oom_notifier(&rcutorture_oom_nb); /* Avoid slow periods, better to test when busy. */ @@ -1995,6 +2010,8 @@ static int rcu_torture_fwd_prog(void *args) /* If forward-progress checking is requested and feasible, spawn the thread. */ static int __init rcu_torture_fwd_prog_init(void) { + struct rcu_fwd *rfp; + if (!fwd_progress) return 0; /* Not requested, so don't do it. */ if (!cur_ops->stall_dur || cur_ops->stall_dur() <= 0 || @@ -2013,8 +2030,12 @@ static int __init rcu_torture_fwd_prog_init(void) fwd_progress_holdoff = 1; if (fwd_progress_div <= 0) fwd_progress_div = 4; - return torture_create_kthread(rcu_torture_fwd_prog, - NULL, fwd_prog_task); + rfp = kzalloc(sizeof(*rfp), GFP_KERNEL); + if (!rfp) + return -ENOMEM; + spin_lock_init(&rfp->rcu_fwd_lock); + rfp->rcu_fwd_cb_tail = &rfp->rcu_fwd_cb_head; + return torture_create_kthread(rcu_torture_fwd_prog, rfp, fwd_prog_task); } /* Callback function for RCU barrier testing. */ diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index 44d6606b8325..6208c1dae5c9 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -103,7 +103,7 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock); /* * Workqueue handler to drive one grace period and invoke any callbacks - * that become ready as a result. Single-CPU and !PREEMPT operation + * that become ready as a result. Single-CPU and !PREEMPTION operation * means that we get away with murder on synchronization. ;-) */ void srcu_drive_gp(struct work_struct *wp) diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 5dffade2d7cd..657e6a7d1c03 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -530,7 +530,7 @@ static void srcu_gp_end(struct srcu_struct *ssp) idx = rcu_seq_state(ssp->srcu_gp_seq); WARN_ON_ONCE(idx != SRCU_STATE_SCAN2); cbdelay = srcu_get_delay(ssp); - ssp->srcu_last_gp_end = ktime_get_mono_fast_ns(); + WRITE_ONCE(ssp->srcu_last_gp_end, ktime_get_mono_fast_ns()); rcu_seq_end(&ssp->srcu_gp_seq); gpseq = rcu_seq_current(&ssp->srcu_gp_seq); if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, gpseq)) @@ -762,6 +762,7 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp) unsigned long flags; struct srcu_data *sdp; unsigned long t; + unsigned long tlast; /* If the local srcu_data structure has callbacks, not idle. */ local_irq_save(flags); @@ -780,9 +781,9 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp) /* First, see if enough time has passed since the last GP. */ t = ktime_get_mono_fast_ns(); + tlast = READ_ONCE(ssp->srcu_last_gp_end); if (exp_holdoff == 0 || - time_in_range_open(t, ssp->srcu_last_gp_end, - ssp->srcu_last_gp_end + exp_holdoff)) + time_in_range_open(t, tlast, tlast + exp_holdoff)) return false; /* Too soon after last GP. */ /* Next, check for probable idleness. */ @@ -853,7 +854,7 @@ static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp, local_irq_save(flags); sdp = this_cpu_ptr(ssp->sda); spin_lock_rcu_node(sdp); - rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false); + rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&ssp->srcu_gp_seq)); s = rcu_seq_snap(&ssp->srcu_gp_seq); @@ -1052,7 +1053,7 @@ void srcu_barrier(struct srcu_struct *ssp) sdp->srcu_barrier_head.func = srcu_barrier_cb; debug_rcu_head_queue(&sdp->srcu_barrier_head); if (!rcu_segcblist_entrain(&sdp->srcu_cblist, - &sdp->srcu_barrier_head, 0)) { + &sdp->srcu_barrier_head)) { debug_rcu_head_unqueue(&sdp->srcu_barrier_head); atomic_dec(&ssp->srcu_barrier_cpu_cnt); } diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index 477b4eb44af5..dd572ce7c747 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -22,6 +22,7 @@ #include <linux/time.h> #include <linux/cpu.h> #include <linux/prefetch.h> +#include <linux/slab.h> #include "rcu.h" @@ -73,6 +74,31 @@ void rcu_sched_clock_irq(int user) } } +/* + * Reclaim the specified callback, either by invoking it for non-kfree cases or + * freeing it directly (for kfree). Return true if kfreeing, false otherwise. + */ +static inline bool rcu_reclaim_tiny(struct rcu_head *head) +{ + rcu_callback_t f; + unsigned long offset = (unsigned long)head->func; + + rcu_lock_acquire(&rcu_callback_map); + if (__is_kfree_rcu_offset(offset)) { + trace_rcu_invoke_kfree_callback("", head, offset); + kfree((void *)head - offset); + rcu_lock_release(&rcu_callback_map); + return true; + } + + trace_rcu_invoke_callback("", head); + f = head->func; + WRITE_ONCE(head->func, (rcu_callback_t)0L); + f(head); + rcu_lock_release(&rcu_callback_map); + return false; +} + /* Invoke the RCU callbacks whose grace period has elapsed. */ static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) { @@ -100,7 +126,7 @@ static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused prefetch(next); debug_rcu_head_unqueue(list); local_bh_disable(); - __rcu_reclaim("", list); + rcu_reclaim_tiny(list); local_bh_enable(); list = next; } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1694a6b57ad8..d91c9156fab2 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -43,7 +43,6 @@ #include <uapi/linux/sched/types.h> #include <linux/prefetch.h> #include <linux/delay.h> -#include <linux/stop_machine.h> #include <linux/random.h> #include <linux/trace_events.h> #include <linux/suspend.h> @@ -55,6 +54,7 @@ #include <linux/oom.h> #include <linux/smpboot.h> #include <linux/jiffies.h> +#include <linux/slab.h> #include <linux/sched/isolation.h> #include <linux/sched/clock.h> #include "../time/tick-internal.h" @@ -84,7 +84,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = { .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE, .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR), }; -struct rcu_state rcu_state = { +static struct rcu_state rcu_state = { .level = { &rcu_state.node[0] }, .gp_state = RCU_GP_IDLE, .gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, @@ -188,7 +188,7 @@ EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio); * held, but the bit corresponding to the current CPU will be stable * in most contexts. */ -unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) +static unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) { return READ_ONCE(rnp->qsmaskinitnext); } @@ -294,7 +294,7 @@ static void rcu_dynticks_eqs_online(void) * * No ordering, as we are sampling CPU-local information. */ -bool rcu_dynticks_curr_cpu_in_eqs(void) +static bool rcu_dynticks_curr_cpu_in_eqs(void) { struct rcu_data *rdp = this_cpu_ptr(&rcu_data); @@ -305,7 +305,7 @@ bool rcu_dynticks_curr_cpu_in_eqs(void) * Snapshot the ->dynticks counter with full ordering so as to allow * stable comparison of this counter with past and future snapshots. */ -int rcu_dynticks_snap(struct rcu_data *rdp) +static int rcu_dynticks_snap(struct rcu_data *rdp) { int snap = atomic_add_return(0, &rdp->dynticks); @@ -529,16 +529,6 @@ static struct rcu_node *rcu_get_root(void) } /* - * Convert a ->gp_state value to a character string. - */ -static const char *gp_state_getname(short gs) -{ - if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names)) - return "???"; - return gp_state_names[gs]; -} - -/* * Send along grace-period-related data for rcutorture diagnostics. */ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, @@ -577,7 +567,7 @@ static void rcu_eqs_enter(bool user) } lockdep_assert_irqs_disabled(); - trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, rdp->dynticks); + trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks)); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); rdp = this_cpu_ptr(&rcu_data); do_nocb_deferred_wakeup(rdp); @@ -650,14 +640,15 @@ static __always_inline void rcu_nmi_exit_common(bool irq) * leave it in non-RCU-idle state. */ if (rdp->dynticks_nmi_nesting != 1) { - trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2, rdp->dynticks); + trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2, + atomic_read(&rdp->dynticks)); WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */ rdp->dynticks_nmi_nesting - 2); return; } /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */ - trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, rdp->dynticks); + trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks)); WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */ if (irq) @@ -744,7 +735,7 @@ static void rcu_eqs_exit(bool user) rcu_dynticks_task_exit(); rcu_dynticks_eqs_exit(); rcu_cleanup_after_idle(); - trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, rdp->dynticks); + trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks)); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); WRITE_ONCE(rdp->dynticks_nesting, 1); WARN_ON_ONCE(rdp->dynticks_nmi_nesting); @@ -800,8 +791,8 @@ void rcu_user_exit(void) */ static __always_inline void rcu_nmi_enter_common(bool irq) { - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); long incby = 2; + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); /* Complain about underflow. */ WARN_ON_ONCE(rdp->dynticks_nmi_nesting < 0); @@ -828,12 +819,17 @@ static __always_inline void rcu_nmi_enter_common(bool irq) } else if (tick_nohz_full_cpu(rdp->cpu) && rdp->dynticks_nmi_nesting == DYNTICK_IRQ_NONIDLE && READ_ONCE(rdp->rcu_urgent_qs) && !rdp->rcu_forced_tick) { - rdp->rcu_forced_tick = true; - tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU); + raw_spin_lock_rcu_node(rdp->mynode); + // Recheck under lock. + if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) { + rdp->rcu_forced_tick = true; + tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU); + } + raw_spin_unlock_rcu_node(rdp->mynode); } trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="), rdp->dynticks_nmi_nesting, - rdp->dynticks_nmi_nesting + incby, rdp->dynticks); + rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks)); WRITE_ONCE(rdp->dynticks_nmi_nesting, /* Prevent store tearing. */ rdp->dynticks_nmi_nesting + incby); barrier(); @@ -898,6 +894,7 @@ void rcu_irq_enter_irqson(void) */ static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp) { + raw_lockdep_assert_held_rcu_node(rdp->mynode); WRITE_ONCE(rdp->rcu_urgent_qs, false); WRITE_ONCE(rdp->rcu_need_heavy_qs, false); if (tick_nohz_full_cpu(rdp->cpu) && rdp->rcu_forced_tick) { @@ -1934,7 +1931,7 @@ rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) struct rcu_node *rnp_p; raw_lockdep_assert_held_rcu_node(rnp); - if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPTION)) || + if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_RCU)) || WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) || rnp->qsmask != 0) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -2146,7 +2143,6 @@ static void rcu_do_batch(struct rcu_data *rdp) /* If no callbacks are ready, just return. */ if (!rcu_segcblist_ready_cbs(&rdp->cblist)) { trace_rcu_batch_start(rcu_state.name, - rcu_segcblist_n_lazy_cbs(&rdp->cblist), rcu_segcblist_n_cbs(&rdp->cblist), 0); trace_rcu_batch_end(rcu_state.name, 0, !rcu_segcblist_empty(&rdp->cblist), @@ -2168,7 +2164,6 @@ static void rcu_do_batch(struct rcu_data *rdp) if (unlikely(bl > 100)) tlimit = local_clock() + rcu_resched_ns; trace_rcu_batch_start(rcu_state.name, - rcu_segcblist_n_lazy_cbs(&rdp->cblist), rcu_segcblist_n_cbs(&rdp->cblist), bl); rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl); if (offloaded) @@ -2179,9 +2174,19 @@ static void rcu_do_batch(struct rcu_data *rdp) tick_dep_set_task(current, TICK_DEP_BIT_RCU); rhp = rcu_cblist_dequeue(&rcl); for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) { + rcu_callback_t f; + debug_rcu_head_unqueue(rhp); - if (__rcu_reclaim(rcu_state.name, rhp)) - rcu_cblist_dequeued_lazy(&rcl); + + rcu_lock_acquire(&rcu_callback_map); + trace_rcu_invoke_callback(rcu_state.name, rhp); + + f = rhp->func; + WRITE_ONCE(rhp->func, (rcu_callback_t)0L); + f(rhp); + + rcu_lock_release(&rcu_callback_map); + /* * Stop only if limit reached and CPU has something to do. * Note: The rcl structure counts down from zero. @@ -2294,7 +2299,7 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp)) mask = 0; raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->qsmask == 0) { - if (!IS_ENABLED(CONFIG_PREEMPTION) || + if (!IS_ENABLED(CONFIG_PREEMPT_RCU) || rcu_preempt_blocked_readers_cgp(rnp)) { /* * No point in scanning bits because they @@ -2308,14 +2313,11 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp)) raw_spin_unlock_irqrestore_rcu_node(rnp, flags); continue; } - for_each_leaf_node_possible_cpu(rnp, cpu) { - unsigned long bit = leaf_node_cpu_bit(rnp, cpu); - if ((rnp->qsmask & bit) != 0) { - rdp = per_cpu_ptr(&rcu_data, cpu); - if (f(rdp)) { - mask |= bit; - rcu_disable_urgency_upon_qs(rdp); - } + for_each_leaf_node_cpu_mask(rnp, cpu, rnp->qsmask) { + rdp = per_cpu_ptr(&rcu_data, cpu); + if (f(rdp)) { + mask |= rdp->grpmask; + rcu_disable_urgency_upon_qs(rdp); } } if (mask != 0) { @@ -2474,8 +2476,8 @@ static void rcu_cpu_kthread(unsigned int cpu) char work, *workp = this_cpu_ptr(&rcu_data.rcu_cpu_has_work); int spincnt; + trace_rcu_utilization(TPS("Start CPU kthread@rcu_run")); for (spincnt = 0; spincnt < 10; spincnt++) { - trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); local_bh_disable(); *statusp = RCU_KTHREAD_RUNNING; local_irq_disable(); @@ -2583,7 +2585,7 @@ static void rcu_leak_callback(struct rcu_head *rhp) * is expected to specify a CPU. */ static void -__call_rcu(struct rcu_head *head, rcu_callback_t func, bool lazy) +__call_rcu(struct rcu_head *head, rcu_callback_t func) { unsigned long flags; struct rcu_data *rdp; @@ -2618,18 +2620,17 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, bool lazy) if (rcu_segcblist_empty(&rdp->cblist)) rcu_segcblist_init(&rdp->cblist); } + if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags)) return; // Enqueued onto ->nocb_bypass, so just leave. /* If we get here, rcu_nocb_try_bypass() acquired ->nocb_lock. */ - rcu_segcblist_enqueue(&rdp->cblist, head, lazy); + rcu_segcblist_enqueue(&rdp->cblist, head); if (__is_kfree_rcu_offset((unsigned long)func)) trace_rcu_kfree_callback(rcu_state.name, head, (unsigned long)func, - rcu_segcblist_n_lazy_cbs(&rdp->cblist), rcu_segcblist_n_cbs(&rdp->cblist)); else trace_rcu_callback(rcu_state.name, head, - rcu_segcblist_n_lazy_cbs(&rdp->cblist), rcu_segcblist_n_cbs(&rdp->cblist)); /* Go handle any RCU core processing required. */ @@ -2679,28 +2680,230 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, bool lazy) */ void call_rcu(struct rcu_head *head, rcu_callback_t func) { - __call_rcu(head, func, 0); + __call_rcu(head, func); } EXPORT_SYMBOL_GPL(call_rcu); + +/* Maximum number of jiffies to wait before draining a batch. */ +#define KFREE_DRAIN_JIFFIES (HZ / 50) +#define KFREE_N_BATCHES 2 + +/** + * struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests + * @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period + * @head_free: List of kfree_rcu() objects waiting for a grace period + * @krcp: Pointer to @kfree_rcu_cpu structure + */ + +struct kfree_rcu_cpu_work { + struct rcu_work rcu_work; + struct rcu_head *head_free; + struct kfree_rcu_cpu *krcp; +}; + +/** + * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period + * @head: List of kfree_rcu() objects not yet waiting for a grace period + * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period + * @lock: Synchronize access to this structure + * @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES + * @monitor_todo: Tracks whether a @monitor_work delayed work is pending + * @initialized: The @lock and @rcu_work fields have been initialized + * + * This is a per-CPU structure. The reason that it is not included in + * the rcu_data structure is to permit this code to be extracted from + * the RCU files. Such extraction could allow further optimization of + * the interactions with the slab allocators. + */ +struct kfree_rcu_cpu { + struct rcu_head *head; + struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES]; + spinlock_t lock; + struct delayed_work monitor_work; + bool monitor_todo; + bool initialized; +}; + +static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc); + +/* + * This function is invoked in workqueue context after a grace period. + * It frees all the objects queued on ->head_free. + */ +static void kfree_rcu_work(struct work_struct *work) +{ + unsigned long flags; + struct rcu_head *head, *next; + struct kfree_rcu_cpu *krcp; + struct kfree_rcu_cpu_work *krwp; + + krwp = container_of(to_rcu_work(work), + struct kfree_rcu_cpu_work, rcu_work); + krcp = krwp->krcp; + spin_lock_irqsave(&krcp->lock, flags); + head = krwp->head_free; + krwp->head_free = NULL; + spin_unlock_irqrestore(&krcp->lock, flags); + + // List "head" is now private, so traverse locklessly. + for (; head; head = next) { + unsigned long offset = (unsigned long)head->func; + + next = head->next; + // Potentially optimize with kfree_bulk in future. + debug_rcu_head_unqueue(head); + rcu_lock_acquire(&rcu_callback_map); + trace_rcu_invoke_kfree_callback(rcu_state.name, head, offset); + + if (!WARN_ON_ONCE(!__is_kfree_rcu_offset(offset))) { + /* Could be optimized with kfree_bulk() in future. */ + kfree((void *)head - offset); + } + + rcu_lock_release(&rcu_callback_map); + cond_resched_tasks_rcu_qs(); + } +} + /* - * Queue an RCU callback for lazy invocation after a grace period. - * This will likely be later named something like "call_rcu_lazy()", - * but this change will require some way of tagging the lazy RCU - * callbacks in the list of pending callbacks. Until then, this - * function may only be called from __kfree_rcu(). + * Schedule the kfree batch RCU work to run in workqueue context after a GP. + * + * This function is invoked by kfree_rcu_monitor() when the KFREE_DRAIN_JIFFIES + * timeout has been reached. + */ +static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp) +{ + int i; + struct kfree_rcu_cpu_work *krwp = NULL; + + lockdep_assert_held(&krcp->lock); + for (i = 0; i < KFREE_N_BATCHES; i++) + if (!krcp->krw_arr[i].head_free) { + krwp = &(krcp->krw_arr[i]); + break; + } + + // If a previous RCU batch is in progress, we cannot immediately + // queue another one, so return false to tell caller to retry. + if (!krwp) + return false; + + krwp->head_free = krcp->head; + krcp->head = NULL; + INIT_RCU_WORK(&krwp->rcu_work, kfree_rcu_work); + queue_rcu_work(system_wq, &krwp->rcu_work); + return true; +} + +static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp, + unsigned long flags) +{ + // Attempt to start a new batch. + krcp->monitor_todo = false; + if (queue_kfree_rcu_work(krcp)) { + // Success! Our job is done here. + spin_unlock_irqrestore(&krcp->lock, flags); + return; + } + + // Previous RCU batch still in progress, try again later. + krcp->monitor_todo = true; + schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES); + spin_unlock_irqrestore(&krcp->lock, flags); +} + +/* + * This function is invoked after the KFREE_DRAIN_JIFFIES timeout. + * It invokes kfree_rcu_drain_unlock() to attempt to start another batch. + */ +static void kfree_rcu_monitor(struct work_struct *work) +{ + unsigned long flags; + struct kfree_rcu_cpu *krcp = container_of(work, struct kfree_rcu_cpu, + monitor_work.work); + + spin_lock_irqsave(&krcp->lock, flags); + if (krcp->monitor_todo) + kfree_rcu_drain_unlock(krcp, flags); + else + spin_unlock_irqrestore(&krcp->lock, flags); +} + +/* + * Queue a request for lazy invocation of kfree() after a grace period. + * + * Each kfree_call_rcu() request is added to a batch. The batch will be drained + * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch + * will be kfree'd in workqueue context. This allows us to: + * + * 1. Batch requests together to reduce the number of grace periods during + * heavy kfree_rcu() load. + * + * 2. It makes it possible to use kfree_bulk() on a large number of + * kfree_rcu() requests thus reducing cache misses and the per-object + * overhead of kfree(). */ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) { - __call_rcu(head, func, 1); + unsigned long flags; + struct kfree_rcu_cpu *krcp; + + local_irq_save(flags); // For safely calling this_cpu_ptr(). + krcp = this_cpu_ptr(&krc); + if (krcp->initialized) + spin_lock(&krcp->lock); + + // Queue the object but don't yet schedule the batch. + if (debug_rcu_head_queue(head)) { + // Probable double kfree_rcu(), just leak. + WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n", + __func__, head); + goto unlock_return; + } + head->func = func; + head->next = krcp->head; + krcp->head = head; + + // Set timer to drain after KFREE_DRAIN_JIFFIES. + if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING && + !krcp->monitor_todo) { + krcp->monitor_todo = true; + schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES); + } + +unlock_return: + if (krcp->initialized) + spin_unlock(&krcp->lock); + local_irq_restore(flags); } EXPORT_SYMBOL_GPL(kfree_call_rcu); +void __init kfree_rcu_scheduler_running(void) +{ + int cpu; + unsigned long flags; + + for_each_online_cpu(cpu) { + struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); + + spin_lock_irqsave(&krcp->lock, flags); + if (!krcp->head || krcp->monitor_todo) { + spin_unlock_irqrestore(&krcp->lock, flags); + continue; + } + krcp->monitor_todo = true; + schedule_delayed_work_on(cpu, &krcp->monitor_work, + KFREE_DRAIN_JIFFIES); + spin_unlock_irqrestore(&krcp->lock, flags); + } +} + /* * During early boot, any blocking grace-period wait automatically - * implies a grace period. Later on, this is never the case for PREEMPT. + * implies a grace period. Later on, this is never the case for PREEMPTION. * - * Howevr, because a context switch is a grace period for !PREEMPT, any + * Howevr, because a context switch is a grace period for !PREEMPTION, any * blocking grace-period wait automatically implies a grace period if * there is only one CPU online at any point time during execution of * either synchronize_rcu() or synchronize_rcu_expedited(). It is OK to @@ -2896,7 +3099,7 @@ static void rcu_barrier_func(void *unused) debug_rcu_head_queue(&rdp->barrier_head); rcu_nocb_lock(rdp); WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies)); - if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head, 0)) { + if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head)) { atomic_inc(&rcu_state.barrier_cpu_count); } else { debug_rcu_head_unqueue(&rdp->barrier_head); @@ -3557,12 +3760,29 @@ static void __init rcu_dump_rcu_node_tree(void) struct workqueue_struct *rcu_gp_wq; struct workqueue_struct *rcu_par_gp_wq; +static void __init kfree_rcu_batch_init(void) +{ + int cpu; + int i; + + for_each_possible_cpu(cpu) { + struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); + + spin_lock_init(&krcp->lock); + for (i = 0; i < KFREE_N_BATCHES; i++) + krcp->krw_arr[i].krcp = krcp; + INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor); + krcp->initialized = true; + } +} + void __init rcu_init(void) { int cpu; rcu_early_boot_tests(); + kfree_rcu_batch_init(); rcu_bootup_announce(); rcu_init_geometry(); rcu_init_one(); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 055c31781d3a..0c87e4c161c2 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -16,7 +16,6 @@ #include <linux/cpumask.h> #include <linux/seqlock.h> #include <linux/swait.h> -#include <linux/stop_machine.h> #include <linux/rcu_node_tree.h> #include "rcu_segcblist.h" @@ -182,8 +181,8 @@ struct rcu_data { bool rcu_need_heavy_qs; /* GP old, so heavy quiescent state! */ bool rcu_urgent_qs; /* GP old need light quiescent state. */ bool rcu_forced_tick; /* Forced tick to provide QS. */ + bool rcu_forced_tick_exp; /* ... provide QS to expedited GP. */ #ifdef CONFIG_RCU_FAST_NO_HZ - bool all_lazy; /* All CPU's CBs lazy at idle start? */ unsigned long last_accelerate; /* Last jiffy CBs were accelerated. */ unsigned long last_advance_all; /* Last jiffy CBs were all advanced. */ int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */ @@ -368,18 +367,6 @@ struct rcu_state { #define RCU_GP_CLEANUP 7 /* Grace-period cleanup started. */ #define RCU_GP_CLEANED 8 /* Grace-period cleanup complete. */ -static const char * const gp_state_names[] = { - "RCU_GP_IDLE", - "RCU_GP_WAIT_GPS", - "RCU_GP_DONE_GPS", - "RCU_GP_ONOFF", - "RCU_GP_INIT", - "RCU_GP_WAIT_FQS", - "RCU_GP_DOING_FQS", - "RCU_GP_CLEANUP", - "RCU_GP_CLEANED", -}; - /* * In order to export the rcu_state name to the tracing tools, it * needs to be added in the __tracepoint_string section. @@ -403,8 +390,6 @@ static const char *tp_rcu_varname __used __tracepoint_string = rcu_name; #define RCU_NAME rcu_name #endif /* #else #ifdef CONFIG_TRACING */ -int rcu_dynticks_snap(struct rcu_data *rdp); - /* Forward declarations for tree_plugin.h */ static void rcu_bootup_announce(void); static void rcu_qs(void); @@ -415,7 +400,6 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp); static int rcu_print_task_exp_stall(struct rcu_node *rnp); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); static void rcu_flavor_sched_clock_irq(int user); -void call_rcu(struct rcu_head *head, rcu_callback_t func); static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index d632cd019597..6935a9e2b094 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -21,7 +21,7 @@ static void rcu_exp_gp_seq_start(void) } /* - * Return then value that expedited-grace-period counter will have + * Return the value that the expedited-grace-period counter will have * at the end of the current grace period. */ static __maybe_unused unsigned long rcu_exp_gp_seq_endval(void) @@ -39,7 +39,9 @@ static void rcu_exp_gp_seq_end(void) } /* - * Take a snapshot of the expedited-grace-period counter. + * Take a snapshot of the expedited-grace-period counter, which is the + * earliest value that will indicate that a full grace period has + * elapsed since the current time. */ static unsigned long rcu_exp_gp_seq_snap(void) { @@ -134,7 +136,7 @@ static void __maybe_unused sync_exp_reset_tree(void) rcu_for_each_node_breadth_first(rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); WARN_ON_ONCE(rnp->expmask); - rnp->expmask = rnp->expmaskinit; + WRITE_ONCE(rnp->expmask, rnp->expmaskinit); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } } @@ -143,31 +145,26 @@ static void __maybe_unused sync_exp_reset_tree(void) * Return non-zero if there is no RCU expedited grace period in progress * for the specified rcu_node structure, in other words, if all CPUs and * tasks covered by the specified rcu_node structure have done their bit - * for the current expedited grace period. Works only for preemptible - * RCU -- other RCU implementation use other means. - * - * Caller must hold the specificed rcu_node structure's ->lock + * for the current expedited grace period. */ -static bool sync_rcu_preempt_exp_done(struct rcu_node *rnp) +static bool sync_rcu_exp_done(struct rcu_node *rnp) { raw_lockdep_assert_held_rcu_node(rnp); - return rnp->exp_tasks == NULL && READ_ONCE(rnp->expmask) == 0; } /* - * Like sync_rcu_preempt_exp_done(), but this function assumes the caller - * doesn't hold the rcu_node's ->lock, and will acquire and release the lock - * itself + * Like sync_rcu_exp_done(), but where the caller does not hold the + * rcu_node's ->lock. */ -static bool sync_rcu_preempt_exp_done_unlocked(struct rcu_node *rnp) +static bool sync_rcu_exp_done_unlocked(struct rcu_node *rnp) { unsigned long flags; bool ret; raw_spin_lock_irqsave_rcu_node(rnp, flags); - ret = sync_rcu_preempt_exp_done(rnp); + ret = sync_rcu_exp_done(rnp); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return ret; @@ -181,8 +178,6 @@ static bool sync_rcu_preempt_exp_done_unlocked(struct rcu_node *rnp) * which the task was queued or to one of that rcu_node structure's ancestors, * recursively up the tree. (Calm down, calm down, we do the recursion * iteratively!) - * - * Caller must hold the specified rcu_node structure's ->lock. */ static void __rcu_report_exp_rnp(struct rcu_node *rnp, bool wake, unsigned long flags) @@ -190,8 +185,9 @@ static void __rcu_report_exp_rnp(struct rcu_node *rnp, { unsigned long mask; + raw_lockdep_assert_held_rcu_node(rnp); for (;;) { - if (!sync_rcu_preempt_exp_done(rnp)) { + if (!sync_rcu_exp_done(rnp)) { if (!rnp->expmask) rcu_initiate_boost(rnp, flags); else @@ -211,7 +207,7 @@ static void __rcu_report_exp_rnp(struct rcu_node *rnp, rnp = rnp->parent; raw_spin_lock_rcu_node(rnp); /* irqs already disabled */ WARN_ON_ONCE(!(rnp->expmask & mask)); - rnp->expmask &= ~mask; + WRITE_ONCE(rnp->expmask, rnp->expmask & ~mask); } } @@ -234,14 +230,23 @@ static void __maybe_unused rcu_report_exp_rnp(struct rcu_node *rnp, bool wake) static void rcu_report_exp_cpu_mult(struct rcu_node *rnp, unsigned long mask, bool wake) { + int cpu; unsigned long flags; + struct rcu_data *rdp; raw_spin_lock_irqsave_rcu_node(rnp, flags); if (!(rnp->expmask & mask)) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } - rnp->expmask &= ~mask; + WRITE_ONCE(rnp->expmask, rnp->expmask & ~mask); + for_each_leaf_node_cpu_mask(rnp, cpu, mask) { + rdp = per_cpu_ptr(&rcu_data, cpu); + if (!IS_ENABLED(CONFIG_NO_HZ_FULL) || !rdp->rcu_forced_tick_exp) + continue; + rdp->rcu_forced_tick_exp = false; + tick_dep_clear_cpu(cpu, TICK_DEP_BIT_RCU_EXP); + } __rcu_report_exp_rnp(rnp, wake, flags); /* Releases rnp->lock. */ } @@ -345,8 +350,8 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) /* Each pass checks a CPU for identity, offline, and idle. */ mask_ofl_test = 0; for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) { - unsigned long mask = leaf_node_cpu_bit(rnp, cpu); struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + unsigned long mask = rdp->grpmask; int snap; if (raw_smp_processor_id() == cpu || @@ -372,12 +377,10 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) raw_spin_unlock_irqrestore_rcu_node(rnp, flags); /* IPI the remaining CPUs for expedited quiescent state. */ - for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) { - unsigned long mask = leaf_node_cpu_bit(rnp, cpu); + for_each_leaf_node_cpu_mask(rnp, cpu, mask_ofl_ipi) { struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + unsigned long mask = rdp->grpmask; - if (!(mask_ofl_ipi & mask)) - continue; retry_ipi: if (rcu_dynticks_in_eqs_since(rdp, rdp->exp_dynticks_snap)) { mask_ofl_test |= mask; @@ -389,10 +392,10 @@ retry_ipi: } ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0); put_cpu(); - if (!ret) { - mask_ofl_ipi &= ~mask; + /* The CPU will report the QS in response to the IPI. */ + if (!ret) continue; - } + /* Failed, raced with CPU hotplug operation. */ raw_spin_lock_irqsave_rcu_node(rnp, flags); if ((rnp->qsmaskinitnext & mask) && @@ -403,13 +406,12 @@ retry_ipi: schedule_timeout_uninterruptible(1); goto retry_ipi; } - /* CPU really is offline, so we can ignore it. */ - if (!(rnp->expmask & mask)) - mask_ofl_ipi &= ~mask; + /* CPU really is offline, so we must report its QS. */ + if (rnp->expmask & mask) + mask_ofl_test |= mask; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } /* Report quiescent states for those that went offline. */ - mask_ofl_test |= mask_ofl_ipi; if (mask_ofl_test) rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false); } @@ -456,29 +458,62 @@ static void sync_rcu_exp_select_cpus(void) flush_work(&rnp->rew.rew_work); } -static void synchronize_sched_expedited_wait(void) +/* + * Wait for the expedited grace period to elapse, within time limit. + * If the time limit is exceeded without the grace period elapsing, + * return false, otherwise return true. + */ +static bool synchronize_rcu_expedited_wait_once(long tlimit) +{ + int t; + struct rcu_node *rnp_root = rcu_get_root(); + + t = swait_event_timeout_exclusive(rcu_state.expedited_wq, + sync_rcu_exp_done_unlocked(rnp_root), + tlimit); + // Workqueues should not be signaled. + if (t > 0 || sync_rcu_exp_done_unlocked(rnp_root)) + return true; + WARN_ON(t < 0); /* workqueues should not be signaled. */ + return false; +} + +/* + * Wait for the expedited grace period to elapse, issuing any needed + * RCU CPU stall warnings along the way. + */ +static void synchronize_rcu_expedited_wait(void) { int cpu; unsigned long jiffies_stall; unsigned long jiffies_start; unsigned long mask; int ndetected; + struct rcu_data *rdp; struct rcu_node *rnp; struct rcu_node *rnp_root = rcu_get_root(); - int ret; trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("startwait")); jiffies_stall = rcu_jiffies_till_stall_check(); jiffies_start = jiffies; + if (IS_ENABLED(CONFIG_NO_HZ_FULL)) { + if (synchronize_rcu_expedited_wait_once(1)) + return; + rcu_for_each_leaf_node(rnp) { + for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) { + rdp = per_cpu_ptr(&rcu_data, cpu); + if (rdp->rcu_forced_tick_exp) + continue; + rdp->rcu_forced_tick_exp = true; + tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP); + } + } + WARN_ON_ONCE(1); + } for (;;) { - ret = swait_event_timeout_exclusive( - rcu_state.expedited_wq, - sync_rcu_preempt_exp_done_unlocked(rnp_root), - jiffies_stall); - if (ret > 0 || sync_rcu_preempt_exp_done_unlocked(rnp_root)) + if (synchronize_rcu_expedited_wait_once(jiffies_stall)) return; - WARN_ON(ret < 0); /* workqueues should not be signaled. */ if (rcu_cpu_stall_suppress) continue; panic_on_rcu_stall(); @@ -491,7 +526,7 @@ static void synchronize_sched_expedited_wait(void) struct rcu_data *rdp; mask = leaf_node_cpu_bit(rnp, cpu); - if (!(rnp->expmask & mask)) + if (!(READ_ONCE(rnp->expmask) & mask)) continue; ndetected++; rdp = per_cpu_ptr(&rcu_data, cpu); @@ -503,17 +538,18 @@ static void synchronize_sched_expedited_wait(void) } pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n", jiffies - jiffies_start, rcu_state.expedited_sequence, - rnp_root->expmask, ".T"[!!rnp_root->exp_tasks]); + READ_ONCE(rnp_root->expmask), + ".T"[!!rnp_root->exp_tasks]); if (ndetected) { pr_err("blocking rcu_node structures:"); rcu_for_each_node_breadth_first(rnp) { if (rnp == rnp_root) continue; /* printed unconditionally */ - if (sync_rcu_preempt_exp_done_unlocked(rnp)) + if (sync_rcu_exp_done_unlocked(rnp)) continue; pr_cont(" l=%u:%d-%d:%#lx/%c", rnp->level, rnp->grplo, rnp->grphi, - rnp->expmask, + READ_ONCE(rnp->expmask), ".T"[!!rnp->exp_tasks]); } pr_cont("\n"); @@ -521,7 +557,7 @@ static void synchronize_sched_expedited_wait(void) rcu_for_each_leaf_node(rnp) { for_each_leaf_node_possible_cpu(rnp, cpu) { mask = leaf_node_cpu_bit(rnp, cpu); - if (!(rnp->expmask & mask)) + if (!(READ_ONCE(rnp->expmask) & mask)) continue; dump_cpu_task(cpu); } @@ -540,15 +576,14 @@ static void rcu_exp_wait_wake(unsigned long s) { struct rcu_node *rnp; - synchronize_sched_expedited_wait(); - rcu_exp_gp_seq_end(); - trace_rcu_exp_grace_period(rcu_state.name, s, TPS("end")); + synchronize_rcu_expedited_wait(); - /* - * Switch over to wakeup mode, allowing the next GP, but -only- the - * next GP, to proceed. - */ + // Switch over to wakeup mode, allowing the next GP to proceed. + // End the previous grace period only after acquiring the mutex + // to ensure that only one GP runs concurrently with wakeups. mutex_lock(&rcu_state.exp_wake_mutex); + rcu_exp_gp_seq_end(); + trace_rcu_exp_grace_period(rcu_state.name, s, TPS("end")); rcu_for_each_node_breadth_first(rnp) { if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s)) { @@ -559,7 +594,7 @@ static void rcu_exp_wait_wake(unsigned long s) spin_unlock(&rnp->exp_lock); } smp_mb(); /* All above changes before wakeup. */ - wake_up_all(&rnp->exp_wq[rcu_seq_ctr(rcu_state.expedited_sequence) & 0x3]); + wake_up_all(&rnp->exp_wq[rcu_seq_ctr(s) & 0x3]); } trace_rcu_exp_grace_period(rcu_state.name, s, TPS("endwake")); mutex_unlock(&rcu_state.exp_wake_mutex); @@ -610,7 +645,7 @@ static void rcu_exp_handler(void *unused) * critical section. If also enabled or idle, immediately * report the quiescent state, otherwise defer. */ - if (!t->rcu_read_lock_nesting) { + if (!rcu_preempt_depth()) { if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) || rcu_dynticks_curr_cpu_in_eqs()) { rcu_report_exp_rdp(rdp); @@ -634,7 +669,7 @@ static void rcu_exp_handler(void *unused) * can have caused this quiescent state to already have been * reported, so we really do need to check ->expmask. */ - if (t->rcu_read_lock_nesting > 0) { + if (rcu_preempt_depth() > 0) { raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->expmask & rdp->grpmask) { rdp->exp_deferred_qs = true; @@ -670,7 +705,7 @@ static void rcu_exp_handler(void *unused) } } -/* PREEMPT=y, so no PREEMPT=n expedited grace period to clean up after. */ +/* PREEMPTION=y, so no PREEMPTION=n expedited grace period to clean up after. */ static void sync_sched_exp_online_cleanup(int cpu) { } @@ -785,7 +820,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) * implementations, it is still unfriendly to real-time workloads, so is * thus not recommended for any sort of common-case code. In fact, if * you are using synchronize_rcu_expedited() in a loop, please restructure - * your code to batch your updates, and then Use a single synchronize_rcu() + * your code to batch your updates, and then use a single synchronize_rcu() * instead. * * This has the same semantics as (but is more brutal than) synchronize_rcu(). diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index fa08d55f7040..c6ea81cd4189 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -220,7 +220,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) * blocked tasks. */ if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) { - rnp->gp_tasks = &t->rcu_node_entry; + WRITE_ONCE(rnp->gp_tasks, &t->rcu_node_entry); WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq); } if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) @@ -290,8 +290,8 @@ void rcu_note_context_switch(bool preempt) trace_rcu_utilization(TPS("Start context switch")); lockdep_assert_irqs_disabled(); - WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0); - if (t->rcu_read_lock_nesting > 0 && + WARN_ON_ONCE(!preempt && rcu_preempt_depth() > 0); + if (rcu_preempt_depth() > 0 && !t->rcu_read_unlock_special.b.blocked) { /* Possibly blocking in an RCU read-side critical section. */ @@ -340,7 +340,7 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch); */ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) { - return rnp->gp_tasks != NULL; + return READ_ONCE(rnp->gp_tasks) != NULL; } /* Bias and limit values for ->rcu_read_lock_nesting. */ @@ -348,6 +348,21 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) #define RCU_NEST_NMAX (-INT_MAX / 2) #define RCU_NEST_PMAX (INT_MAX / 2) +static void rcu_preempt_read_enter(void) +{ + current->rcu_read_lock_nesting++; +} + +static void rcu_preempt_read_exit(void) +{ + current->rcu_read_lock_nesting--; +} + +static void rcu_preempt_depth_set(int val) +{ + current->rcu_read_lock_nesting = val; +} + /* * Preemptible RCU implementation for rcu_read_lock(). * Just increment ->rcu_read_lock_nesting, shared state will be updated @@ -355,9 +370,9 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) */ void __rcu_read_lock(void) { - current->rcu_read_lock_nesting++; + rcu_preempt_read_enter(); if (IS_ENABLED(CONFIG_PROVE_LOCKING)) - WARN_ON_ONCE(current->rcu_read_lock_nesting > RCU_NEST_PMAX); + WARN_ON_ONCE(rcu_preempt_depth() > RCU_NEST_PMAX); barrier(); /* critical section after entry code. */ } EXPORT_SYMBOL_GPL(__rcu_read_lock); @@ -373,19 +388,19 @@ void __rcu_read_unlock(void) { struct task_struct *t = current; - if (t->rcu_read_lock_nesting != 1) { - --t->rcu_read_lock_nesting; + if (rcu_preempt_depth() != 1) { + rcu_preempt_read_exit(); } else { barrier(); /* critical section before exit code. */ - t->rcu_read_lock_nesting = -RCU_NEST_BIAS; + rcu_preempt_depth_set(-RCU_NEST_BIAS); barrier(); /* assign before ->rcu_read_unlock_special load */ if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s))) rcu_read_unlock_special(t); barrier(); /* ->rcu_read_unlock_special load before assign */ - t->rcu_read_lock_nesting = 0; + rcu_preempt_depth_set(0); } if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { - int rrln = t->rcu_read_lock_nesting; + int rrln = rcu_preempt_depth(); WARN_ON_ONCE(rrln < 0 && rrln > RCU_NEST_NMAX); } @@ -444,15 +459,9 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) local_irq_restore(flags); return; } - t->rcu_read_unlock_special.b.deferred_qs = false; - if (special.b.need_qs) { + t->rcu_read_unlock_special.s = 0; + if (special.b.need_qs) rcu_qs(); - t->rcu_read_unlock_special.b.need_qs = false; - if (!t->rcu_read_unlock_special.s && !rdp->exp_deferred_qs) { - local_irq_restore(flags); - return; - } - } /* * Respond to a request by an expedited grace period for a @@ -460,17 +469,11 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) * tasks are handled when removing the task from the * blocked-tasks list below. */ - if (rdp->exp_deferred_qs) { + if (rdp->exp_deferred_qs) rcu_report_exp_rdp(rdp); - if (!t->rcu_read_unlock_special.s) { - local_irq_restore(flags); - return; - } - } /* Clean up if blocked during RCU read-side critical section. */ if (special.b.blocked) { - t->rcu_read_unlock_special.b.blocked = false; /* * Remove this task from the list it blocked on. The task @@ -485,7 +488,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq && (!empty_norm || rnp->qsmask)); - empty_exp = sync_rcu_preempt_exp_done(rnp); + empty_exp = sync_rcu_exp_done(rnp); smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ np = rcu_next_node_entry(t, rnp); list_del_init(&t->rcu_node_entry); @@ -493,7 +496,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) trace_rcu_unlock_preempted_task(TPS("rcu_preempt"), rnp->gp_seq, t->pid); if (&t->rcu_node_entry == rnp->gp_tasks) - rnp->gp_tasks = np; + WRITE_ONCE(rnp->gp_tasks, np); if (&t->rcu_node_entry == rnp->exp_tasks) rnp->exp_tasks = np; if (IS_ENABLED(CONFIG_RCU_BOOST)) { @@ -509,7 +512,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) * Note that rcu_report_unblock_qs_rnp() releases rnp->lock, * so we must take a snapshot of the expedited state. */ - empty_exp_now = sync_rcu_preempt_exp_done(rnp); + empty_exp_now = sync_rcu_exp_done(rnp); if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) { trace_rcu_quiescent_state_report(TPS("preempt_rcu"), rnp->gp_seq, @@ -551,7 +554,7 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t) { return (__this_cpu_read(rcu_data.exp_deferred_qs) || READ_ONCE(t->rcu_read_unlock_special.s)) && - t->rcu_read_lock_nesting <= 0; + rcu_preempt_depth() <= 0; } /* @@ -564,16 +567,16 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t) static void rcu_preempt_deferred_qs(struct task_struct *t) { unsigned long flags; - bool couldrecurse = t->rcu_read_lock_nesting >= 0; + bool couldrecurse = rcu_preempt_depth() >= 0; if (!rcu_preempt_need_deferred_qs(t)) return; if (couldrecurse) - t->rcu_read_lock_nesting -= RCU_NEST_BIAS; + rcu_preempt_depth_set(rcu_preempt_depth() - RCU_NEST_BIAS); local_irq_save(flags); rcu_preempt_deferred_qs_irqrestore(t, flags); if (couldrecurse) - t->rcu_read_lock_nesting += RCU_NEST_BIAS; + rcu_preempt_depth_set(rcu_preempt_depth() + RCU_NEST_BIAS); } /* @@ -610,9 +613,8 @@ static void rcu_read_unlock_special(struct task_struct *t) struct rcu_data *rdp = this_cpu_ptr(&rcu_data); struct rcu_node *rnp = rdp->mynode; - t->rcu_read_unlock_special.b.exp_hint = false; exp = (t->rcu_blocked_node && t->rcu_blocked_node->exp_tasks) || - (rdp->grpmask & rnp->expmask) || + (rdp->grpmask & READ_ONCE(rnp->expmask)) || tick_nohz_full_cpu(rdp->cpu); // Need to defer quiescent state until everything is enabled. if (irqs_were_disabled && use_softirq && @@ -640,7 +642,6 @@ static void rcu_read_unlock_special(struct task_struct *t) local_irq_restore(flags); return; } - WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, false); rcu_preempt_deferred_qs_irqrestore(t, flags); } @@ -648,8 +649,7 @@ static void rcu_read_unlock_special(struct task_struct *t) * Check that the list of blocked tasks for the newly completed grace * period is in fact empty. It is a serious bug to complete a grace * period that still has RCU readers blocked! This function must be - * invoked -before- updating this rnp's ->gp_seq, and the rnp's ->lock - * must be held by the caller. + * invoked -before- updating this rnp's ->gp_seq. * * Also, if there are blocked tasks on the list, they automatically * block the newly created grace period, so set up ->gp_tasks accordingly. @@ -659,11 +659,12 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) struct task_struct *t; RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n"); + raw_lockdep_assert_held_rcu_node(rnp); if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp))) dump_blkd_tasks(rnp, 10); if (rcu_preempt_has_tasks(rnp) && (rnp->qsmaskinit || rnp->wait_blkd_tasks)) { - rnp->gp_tasks = rnp->blkd_tasks.next; + WRITE_ONCE(rnp->gp_tasks, rnp->blkd_tasks.next); t = container_of(rnp->gp_tasks, struct task_struct, rcu_node_entry); trace_rcu_unlock_preempted_task(TPS("rcu_preempt-GPS"), @@ -686,7 +687,7 @@ static void rcu_flavor_sched_clock_irq(int user) if (user || rcu_is_cpu_rrupt_from_idle()) { rcu_note_voluntary_context_switch(current); } - if (t->rcu_read_lock_nesting > 0 || + if (rcu_preempt_depth() > 0 || (preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK))) { /* No QS, force context switch if deferred. */ if (rcu_preempt_need_deferred_qs(t)) { @@ -696,13 +697,13 @@ static void rcu_flavor_sched_clock_irq(int user) } else if (rcu_preempt_need_deferred_qs(t)) { rcu_preempt_deferred_qs(t); /* Report deferred QS. */ return; - } else if (!t->rcu_read_lock_nesting) { + } else if (!rcu_preempt_depth()) { rcu_qs(); /* Report immediate QS. */ return; } /* If GP is oldish, ask for help from rcu_read_unlock_special(). */ - if (t->rcu_read_lock_nesting > 0 && + if (rcu_preempt_depth() > 0 && __this_cpu_read(rcu_data.core_needs_qs) && __this_cpu_read(rcu_data.cpu_no_qs.b.norm) && !t->rcu_read_unlock_special.b.need_qs && @@ -723,11 +724,11 @@ void exit_rcu(void) struct task_struct *t = current; if (unlikely(!list_empty(¤t->rcu_node_entry))) { - t->rcu_read_lock_nesting = 1; + rcu_preempt_depth_set(1); barrier(); WRITE_ONCE(t->rcu_read_unlock_special.b.blocked, true); - } else if (unlikely(t->rcu_read_lock_nesting)) { - t->rcu_read_lock_nesting = 1; + } else if (unlikely(rcu_preempt_depth())) { + rcu_preempt_depth_set(1); } else { return; } @@ -757,7 +758,8 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n", __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext); pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n", - __func__, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks); + __func__, READ_ONCE(rnp->gp_tasks), rnp->boost_tasks, + rnp->exp_tasks); pr_info("%s: ->blkd_tasks", __func__); i = 0; list_for_each(lhp, &rnp->blkd_tasks) { @@ -788,7 +790,7 @@ static void __init rcu_bootup_announce(void) } /* - * Note a quiescent state for PREEMPT=n. Because we do not need to know + * Note a quiescent state for PREEMPTION=n. Because we do not need to know * how many quiescent states passed, just if there was at least one since * the start of the grace period, this just sets a flag. The caller must * have disabled preemption. @@ -838,7 +840,7 @@ void rcu_all_qs(void) EXPORT_SYMBOL_GPL(rcu_all_qs); /* - * Note a PREEMPT=n context switch. The caller must have disabled interrupts. + * Note a PREEMPTION=n context switch. The caller must have disabled interrupts. */ void rcu_note_context_switch(bool preempt) { @@ -1262,10 +1264,9 @@ static void rcu_prepare_for_idle(void) /* * This code is invoked when a CPU goes idle, at which point we want * to have the CPU do everything required for RCU so that it can enter - * the energy-efficient dyntick-idle mode. This is handled by a - * state machine implemented by rcu_prepare_for_idle() below. + * the energy-efficient dyntick-idle mode. * - * The following three proprocessor symbols control this state machine: + * The following preprocessor symbol controls this: * * RCU_IDLE_GP_DELAY gives the number of jiffies that a CPU is permitted * to sleep in dyntick-idle mode with RCU callbacks pending. This @@ -1274,21 +1275,15 @@ static void rcu_prepare_for_idle(void) * number, be warned: Setting RCU_IDLE_GP_DELAY too high can hang your * system. And if you are -that- concerned about energy efficiency, * just power the system down and be done with it! - * RCU_IDLE_LAZY_GP_DELAY gives the number of jiffies that a CPU is - * permitted to sleep in dyntick-idle mode with only lazy RCU - * callbacks pending. Setting this too high can OOM your system. * - * The values below work well in practice. If future workloads require + * The value below works well in practice. If future workloads require * adjustment, they can be converted into kernel config parameters, though * making the state machine smarter might be a better option. */ #define RCU_IDLE_GP_DELAY 4 /* Roughly one grace period. */ -#define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */ static int rcu_idle_gp_delay = RCU_IDLE_GP_DELAY; module_param(rcu_idle_gp_delay, int, 0644); -static int rcu_idle_lazy_gp_delay = RCU_IDLE_LAZY_GP_DELAY; -module_param(rcu_idle_lazy_gp_delay, int, 0644); /* * Try to advance callbacks on the current CPU, but only if it has been @@ -1327,8 +1322,7 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void) /* * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready * to invoke. If the CPU has callbacks, try to advance them. Tell the - * caller to set the timeout based on whether or not there are non-lazy - * callbacks. + * caller about what to set the timeout. * * The caller must have disabled interrupts. */ @@ -1354,25 +1348,18 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt) } rdp->last_accelerate = jiffies; - /* Request timer delay depending on laziness, and round. */ - rdp->all_lazy = !rcu_segcblist_n_nonlazy_cbs(&rdp->cblist); - if (rdp->all_lazy) { - dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies; - } else { - dj = round_up(rcu_idle_gp_delay + jiffies, - rcu_idle_gp_delay) - jiffies; - } + /* Request timer and round. */ + dj = round_up(rcu_idle_gp_delay + jiffies, rcu_idle_gp_delay) - jiffies; + *nextevt = basemono + dj * TICK_NSEC; return 0; } /* - * Prepare a CPU for idle from an RCU perspective. The first major task - * is to sense whether nohz mode has been enabled or disabled via sysfs. - * The second major task is to check to see if a non-lazy callback has - * arrived at a CPU that previously had only lazy callbacks. The third - * major task is to accelerate (that is, assign grace-period numbers to) - * any recently arrived callbacks. + * Prepare a CPU for idle from an RCU perspective. The first major task is to + * sense whether nohz mode has been enabled or disabled via sysfs. The second + * major task is to accelerate (that is, assign grace-period numbers to) any + * recently arrived callbacks. * * The caller must have disabled interrupts. */ @@ -1399,17 +1386,6 @@ static void rcu_prepare_for_idle(void) return; /* - * If a non-lazy callback arrived at a CPU having only lazy - * callbacks, invoke RCU core for the side-effect of recalculating - * idle duration on re-entry to idle. - */ - if (rdp->all_lazy && rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)) { - rdp->all_lazy = false; - invoke_rcu_core(); - return; - } - - /* * If we have not yet accelerated this jiffy, accelerate all * callbacks on this CPU. */ @@ -2321,6 +2297,8 @@ static void __init rcu_organize_nocb_kthreads(void) { int cpu; bool firsttime = true; + bool gotnocbs = false; + bool gotnocbscbs = true; int ls = rcu_nocb_gp_stride; int nl = 0; /* Next GP kthread. */ struct rcu_data *rdp; @@ -2343,21 +2321,31 @@ static void __init rcu_organize_nocb_kthreads(void) rdp = per_cpu_ptr(&rcu_data, cpu); if (rdp->cpu >= nl) { /* New GP kthread, set up for CBs & next GP. */ + gotnocbs = true; nl = DIV_ROUND_UP(rdp->cpu + 1, ls) * ls; rdp->nocb_gp_rdp = rdp; rdp_gp = rdp; - if (!firsttime && dump_tree) - pr_cont("\n"); - firsttime = false; - pr_alert("%s: No-CB GP kthread CPU %d:", __func__, cpu); + if (dump_tree) { + if (!firsttime) + pr_cont("%s\n", gotnocbscbs + ? "" : " (self only)"); + gotnocbscbs = false; + firsttime = false; + pr_alert("%s: No-CB GP kthread CPU %d:", + __func__, cpu); + } } else { /* Another CB kthread, link to previous GP kthread. */ + gotnocbscbs = true; rdp->nocb_gp_rdp = rdp_gp; rdp_prev->nocb_next_cb_rdp = rdp; - pr_alert(" %d", cpu); + if (dump_tree) + pr_cont(" %d", cpu); } rdp_prev = rdp; } + if (gotnocbs && dump_tree) + pr_cont("%s\n", gotnocbscbs ? "" : " (self only)"); } /* diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index c0b8c458d8a6..55f9b84790d3 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -163,7 +163,7 @@ static void rcu_iw_handler(struct irq_work *iwp) // // Printing RCU CPU stall warnings -#ifdef CONFIG_PREEMPTION +#ifdef CONFIG_PREEMPT_RCU /* * Dump detailed information for all tasks blocking the current RCU @@ -215,7 +215,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp) return ndetected; } -#else /* #ifdef CONFIG_PREEMPTION */ +#else /* #ifdef CONFIG_PREEMPT_RCU */ /* * Because preemptible RCU does not exist, we never have to check for @@ -233,7 +233,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp) { return 0; } -#endif /* #else #ifdef CONFIG_PREEMPTION */ +#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* * Dump stacks of all tasks running on stalled CPUs. First try using @@ -263,11 +263,9 @@ static void print_cpu_stall_fast_no_hz(char *cp, int cpu) { struct rcu_data *rdp = &per_cpu(rcu_data, cpu); - sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c", + sprintf(cp, "last_accelerate: %04lx/%04lx dyntick_enabled: %d", rdp->last_accelerate & 0xffff, jiffies & 0xffff, - ".l"[rdp->all_lazy], - ".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)], - ".D"[!!rdp->tick_nohz_enabled_snap]); + !!rdp->tick_nohz_enabled_snap); } #else /* #ifdef CONFIG_RCU_FAST_NO_HZ */ @@ -279,6 +277,28 @@ static void print_cpu_stall_fast_no_hz(char *cp, int cpu) #endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */ +static const char * const gp_state_names[] = { + [RCU_GP_IDLE] = "RCU_GP_IDLE", + [RCU_GP_WAIT_GPS] = "RCU_GP_WAIT_GPS", + [RCU_GP_DONE_GPS] = "RCU_GP_DONE_GPS", + [RCU_GP_ONOFF] = "RCU_GP_ONOFF", + [RCU_GP_INIT] = "RCU_GP_INIT", + [RCU_GP_WAIT_FQS] = "RCU_GP_WAIT_FQS", + [RCU_GP_DOING_FQS] = "RCU_GP_DOING_FQS", + [RCU_GP_CLEANUP] = "RCU_GP_CLEANUP", + [RCU_GP_CLEANED] = "RCU_GP_CLEANED", +}; + +/* + * Convert a ->gp_state value to a character string. + */ +static const char *gp_state_getname(short gs) +{ + if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names)) + return "???"; + return gp_state_names[gs]; +} + /* * Print out diagnostic information for the specified stalled CPU. * diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 1861103662db..6c4b862f57d6 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -40,6 +40,7 @@ #include <linux/rcupdate_wait.h> #include <linux/sched/isolation.h> #include <linux/kprobes.h> +#include <linux/slab.h> #define CREATE_TRACE_POINTS @@ -51,9 +52,7 @@ #define MODULE_PARAM_PREFIX "rcupdate." #ifndef CONFIG_TINY_RCU -extern int rcu_expedited; /* from sysctl */ module_param(rcu_expedited, int, 0); -extern int rcu_normal; /* from sysctl */ module_param(rcu_normal, int, 0); static int rcu_normal_after_boot; module_param(rcu_normal_after_boot, int, 0); @@ -218,6 +217,7 @@ static int __init rcu_set_runtime_mode(void) { rcu_test_sync_prims(); rcu_scheduler_active = RCU_SCHEDULER_RUNNING; + kfree_rcu_scheduler_running(); rcu_test_sync_prims(); return 0; } @@ -435,7 +435,7 @@ struct debug_obj_descr rcuhead_debug_descr = { EXPORT_SYMBOL_GPL(rcuhead_debug_descr); #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */ -#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE) +#if defined(CONFIG_TREE_RCU) || defined(CONFIG_RCU_TRACE) void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp, unsigned long secs, unsigned long c_old, unsigned long c) @@ -853,14 +853,22 @@ static void test_callback(struct rcu_head *r) DEFINE_STATIC_SRCU(early_srcu); +struct early_boot_kfree_rcu { + struct rcu_head rh; +}; + static void early_boot_test_call_rcu(void) { static struct rcu_head head; static struct rcu_head shead; + struct early_boot_kfree_rcu *rhp; call_rcu(&head, test_callback); if (IS_ENABLED(CONFIG_SRCU)) call_srcu(&early_srcu, &shead, test_callback); + rhp = kmalloc(sizeof(*rhp), GFP_KERNEL); + if (!WARN_ON_ONCE(!rhp)) + kfree_rcu(rhp, rh); } void rcu_early_boot_tests(void) diff --git a/kernel/rseq.c b/kernel/rseq.c index 27c48eb7de40..a4f86a9d6937 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -310,6 +310,8 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int ret; if (flags & RSEQ_FLAG_UNREGISTER) { + if (flags & ~RSEQ_FLAG_UNREGISTER) + return -EINVAL; /* Unregister rseq for current thread. */ if (current->rseq != rseq || !current->rseq) return -EINVAL; diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 9fcb2a695a41..008d6ac2342b 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -163,6 +163,12 @@ static int __init housekeeping_isolcpus_setup(char *str) continue; } + if (!strncmp(str, "managed_irq,", 12)) { + str += 12; + flags |= HK_FLAG_MANAGED_IRQ; + continue; + } + pr_warn("isolcpus: Error, unknown flag\n"); return 0; } diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 12d2227e5786..b6ea3dcb57bf 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -1026,6 +1026,13 @@ static long seccomp_notify_recv(struct seccomp_filter *filter, struct seccomp_notif unotif; ssize_t ret; + /* Verify that we're not given garbage to keep struct extensible. */ + ret = check_zeroed_user(buf, sizeof(unotif)); + if (ret < 0) + return ret; + if (!ret) + return -EINVAL; + memset(&unotif, 0, sizeof(unotif)); ret = down_interruptible(&filter->notif->request); diff --git a/kernel/smp.c b/kernel/smp.c index 7dbcb402c2fc..3b7bedc97af3 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -395,22 +395,9 @@ call: } EXPORT_SYMBOL_GPL(smp_call_function_any); -/** - * smp_call_function_many(): Run a function on a set of other CPUs. - * @mask: The set of cpus to run on (only runs on online subset). - * @func: The function to run. This must be fast and non-blocking. - * @info: An arbitrary pointer to pass to the function. - * @wait: If true, wait (atomically) until function has completed - * on other CPUs. - * - * If @wait is true, then returns once @func has returned. - * - * You must not call this function with disabled interrupts or from a - * hardware interrupt handler or from a bottom half handler. Preemption - * must be disabled when calling this function. - */ -void smp_call_function_many(const struct cpumask *mask, - smp_call_func_t func, void *info, bool wait) +static void smp_call_function_many_cond(const struct cpumask *mask, + smp_call_func_t func, void *info, + bool wait, smp_cond_func_t cond_func) { struct call_function_data *cfd; int cpu, next_cpu, this_cpu = smp_processor_id(); @@ -448,7 +435,8 @@ void smp_call_function_many(const struct cpumask *mask, /* Fastpath: do that cpu by itself. */ if (next_cpu >= nr_cpu_ids) { - smp_call_function_single(cpu, func, info, wait); + if (!cond_func || (cond_func && cond_func(cpu, info))) + smp_call_function_single(cpu, func, info, wait); return; } @@ -465,6 +453,9 @@ void smp_call_function_many(const struct cpumask *mask, for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu); + if (cond_func && !cond_func(cpu, info)) + continue; + csd_lock(csd); if (wait) csd->flags |= CSD_FLAG_SYNCHRONOUS; @@ -486,6 +477,26 @@ void smp_call_function_many(const struct cpumask *mask, } } } + +/** + * smp_call_function_many(): Run a function on a set of other CPUs. + * @mask: The set of cpus to run on (only runs on online subset). + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @wait: If true, wait (atomically) until function has completed + * on other CPUs. + * + * If @wait is true, then returns once @func has returned. + * + * You must not call this function with disabled interrupts or from a + * hardware interrupt handler or from a bottom half handler. Preemption + * must be disabled when calling this function. + */ +void smp_call_function_many(const struct cpumask *mask, + smp_call_func_t func, void *info, bool wait) +{ + smp_call_function_many_cond(mask, func, info, wait, NULL); +} EXPORT_SYMBOL(smp_call_function_many); /** @@ -668,11 +679,6 @@ EXPORT_SYMBOL(on_each_cpu_mask); * @info: An arbitrary pointer to pass to both functions. * @wait: If true, wait (atomically) until function has * completed on other CPUs. - * @gfp_flags: GFP flags to use when allocating the cpumask - * used internally by the function. - * - * The function might sleep if the GFP flags indicates a non - * atomic allocation is allowed. * * Preemption is disabled to protect against CPUs going offline but not online. * CPUs going online during the call will not be seen or sent an IPI. @@ -680,46 +686,27 @@ EXPORT_SYMBOL(on_each_cpu_mask); * You must not call this function with disabled interrupts or * from a hardware interrupt handler or from a bottom half handler. */ -void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info), - smp_call_func_t func, void *info, bool wait, - gfp_t gfp_flags, const struct cpumask *mask) +void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, + void *info, bool wait, const struct cpumask *mask) { - cpumask_var_t cpus; - int cpu, ret; - - might_sleep_if(gfpflags_allow_blocking(gfp_flags)); - - if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) { - preempt_disable(); - for_each_cpu(cpu, mask) - if (cond_func(cpu, info)) - __cpumask_set_cpu(cpu, cpus); - on_each_cpu_mask(cpus, func, info, wait); - preempt_enable(); - free_cpumask_var(cpus); - } else { - /* - * No free cpumask, bother. No matter, we'll - * just have to IPI them one by one. - */ - preempt_disable(); - for_each_cpu(cpu, mask) - if (cond_func(cpu, info)) { - ret = smp_call_function_single(cpu, func, - info, wait); - WARN_ON_ONCE(ret); - } - preempt_enable(); + int cpu = get_cpu(); + + smp_call_function_many_cond(mask, func, info, wait, cond_func); + if (cpumask_test_cpu(cpu, mask) && cond_func(cpu, info)) { + unsigned long flags; + + local_irq_save(flags); + func(info); + local_irq_restore(flags); } + put_cpu(); } EXPORT_SYMBOL(on_each_cpu_cond_mask); -void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), - smp_call_func_t func, void *info, bool wait, - gfp_t gfp_flags) +void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func, + void *info, bool wait) { - on_each_cpu_cond_mask(cond_func, func, info, wait, gfp_flags, - cpu_online_mask); + on_each_cpu_cond_mask(cond_func, func, info, wait, cpu_online_mask); } EXPORT_SYMBOL(on_each_cpu_cond); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 70665934d53e..d396aaaf19a3 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1268,7 +1268,7 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_do_static_key, }, #endif -#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) +#if defined(CONFIG_TREE_RCU) { .procname = "panic_on_rcu_stall", .data = &sysctl_panic_on_rcu_stall, diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 13a0f2e6ebc2..e2ac0e37c4ae 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -554,25 +554,33 @@ static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; - struct taskstats *stats; + struct taskstats *stats_new, *stats; - if (sig->stats || thread_group_empty(tsk)) - goto ret; + /* Pairs with smp_store_release() below. */ + stats = smp_load_acquire(&sig->stats); + if (stats || thread_group_empty(tsk)) + return stats; /* No problem if kmem_cache_zalloc() fails */ - stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); + stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); spin_lock_irq(&tsk->sighand->siglock); - if (!sig->stats) { - sig->stats = stats; - stats = NULL; + stats = sig->stats; + if (!stats) { + /* + * Pairs with smp_store_release() above and order the + * kmem_cache_zalloc(). + */ + smp_store_release(&sig->stats, stats_new); + stats = stats_new; + stats_new = NULL; } spin_unlock_irq(&tsk->sighand->siglock); - if (stats) - kmem_cache_free(taskstats_cache, stats); -ret: - return sig->stats; + if (stats_new) + kmem_cache_free(taskstats_cache, stats_new); + + return stats; } /* Send pid data out on exit */ diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 1867044800bb..c8f00168afe8 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -19,3 +19,4 @@ obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o tick-sched.o obj-$(CONFIG_HAVE_GENERIC_VDSO) += vsyscall.o obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o obj-$(CONFIG_TEST_UDELAY) += test_udelay.o +obj-$(CONFIG_TIME_NS) += namespace.o diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 451f9d05ccfe..2ffb466af77e 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -26,6 +26,7 @@ #include <linux/freezer.h> #include <linux/compat.h> #include <linux/module.h> +#include <linux/time_namespace.h> #include "posix-timers.h" @@ -36,13 +37,15 @@ * struct alarm_base - Alarm timer bases * @lock: Lock for syncrhonized access to the base * @timerqueue: Timerqueue head managing the list of events - * @gettime: Function to read the time correlating to the base + * @get_ktime: Function to read the time correlating to the base + * @get_timespec: Function to read the namespace time correlating to the base * @base_clockid: clockid for the base */ static struct alarm_base { spinlock_t lock; struct timerqueue_head timerqueue; - ktime_t (*gettime)(void); + ktime_t (*get_ktime)(void); + void (*get_timespec)(struct timespec64 *tp); clockid_t base_clockid; } alarm_bases[ALARM_NUMTYPE]; @@ -55,8 +58,6 @@ static DEFINE_SPINLOCK(freezer_delta_lock); #endif #ifdef CONFIG_RTC_CLASS -static struct wakeup_source *ws; - /* rtc timer and device for setting alarm wakeups at suspend */ static struct rtc_timer rtctimer; static struct rtc_device *rtcdev; @@ -66,8 +67,6 @@ static DEFINE_SPINLOCK(rtcdev_lock); * alarmtimer_get_rtcdev - Return selected rtcdevice * * This function returns the rtc device to use for wakealarms. - * If one has not already been chosen, it checks to see if a - * functional rtc device is available. */ struct rtc_device *alarmtimer_get_rtcdev(void) { @@ -87,7 +86,8 @@ static int alarmtimer_rtc_add_device(struct device *dev, { unsigned long flags; struct rtc_device *rtc = to_rtc_device(dev); - struct wakeup_source *__ws; + struct platform_device *pdev; + int ret = 0; if (rtcdev) return -EBUSY; @@ -97,26 +97,31 @@ static int alarmtimer_rtc_add_device(struct device *dev, if (!device_may_wakeup(rtc->dev.parent)) return -1; - __ws = wakeup_source_register(dev, "alarmtimer"); + pdev = platform_device_register_data(dev, "alarmtimer", + PLATFORM_DEVID_AUTO, NULL, 0); + if (!IS_ERR(pdev)) + device_init_wakeup(&pdev->dev, true); spin_lock_irqsave(&rtcdev_lock, flags); - if (!rtcdev) { + if (!IS_ERR(pdev) && !rtcdev) { if (!try_module_get(rtc->owner)) { - spin_unlock_irqrestore(&rtcdev_lock, flags); - return -1; + ret = -1; + goto unlock; } rtcdev = rtc; /* hold a reference so it doesn't go away */ get_device(dev); - ws = __ws; - __ws = NULL; + pdev = NULL; + } else { + ret = -1; } +unlock: spin_unlock_irqrestore(&rtcdev_lock, flags); - wakeup_source_unregister(__ws); + platform_device_unregister(pdev); - return 0; + return ret; } static inline void alarmtimer_rtc_timer_init(void) @@ -138,11 +143,6 @@ static void alarmtimer_rtc_interface_remove(void) class_interface_unregister(&alarmtimer_rtc_interface); } #else -struct rtc_device *alarmtimer_get_rtcdev(void) -{ - return NULL; -} -#define rtcdev (NULL) static inline int alarmtimer_rtc_interface_setup(void) { return 0; } static inline void alarmtimer_rtc_interface_remove(void) { } static inline void alarmtimer_rtc_timer_init(void) { } @@ -207,7 +207,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) spin_unlock_irqrestore(&base->lock, flags); if (alarm->function) - restart = alarm->function(alarm, base->gettime()); + restart = alarm->function(alarm, base->get_ktime()); spin_lock_irqsave(&base->lock, flags); if (restart != ALARMTIMER_NORESTART) { @@ -217,7 +217,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) } spin_unlock_irqrestore(&base->lock, flags); - trace_alarmtimer_fired(alarm, base->gettime()); + trace_alarmtimer_fired(alarm, base->get_ktime()); return ret; } @@ -225,7 +225,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) ktime_t alarm_expires_remaining(const struct alarm *alarm) { struct alarm_base *base = &alarm_bases[alarm->type]; - return ktime_sub(alarm->node.expires, base->gettime()); + return ktime_sub(alarm->node.expires, base->get_ktime()); } EXPORT_SYMBOL_GPL(alarm_expires_remaining); @@ -270,7 +270,7 @@ static int alarmtimer_suspend(struct device *dev) spin_unlock_irqrestore(&base->lock, flags); if (!next) continue; - delta = ktime_sub(next->expires, base->gettime()); + delta = ktime_sub(next->expires, base->get_ktime()); if (!min || (delta < min)) { expires = next->expires; min = delta; @@ -281,7 +281,7 @@ static int alarmtimer_suspend(struct device *dev) return 0; if (ktime_to_ns(min) < 2 * NSEC_PER_SEC) { - __pm_wakeup_event(ws, 2 * MSEC_PER_SEC); + pm_wakeup_event(dev, 2 * MSEC_PER_SEC); return -EBUSY; } @@ -296,7 +296,7 @@ static int alarmtimer_suspend(struct device *dev) /* Set alarm, if in the past reject suspend briefly to handle */ ret = rtc_timer_start(rtc, &rtctimer, now, 0); if (ret < 0) - __pm_wakeup_event(ws, MSEC_PER_SEC); + pm_wakeup_event(dev, MSEC_PER_SEC); return ret; } @@ -364,7 +364,7 @@ void alarm_start(struct alarm *alarm, ktime_t start) hrtimer_start(&alarm->timer, alarm->node.expires, HRTIMER_MODE_ABS); spin_unlock_irqrestore(&base->lock, flags); - trace_alarmtimer_start(alarm, base->gettime()); + trace_alarmtimer_start(alarm, base->get_ktime()); } EXPORT_SYMBOL_GPL(alarm_start); @@ -377,7 +377,7 @@ void alarm_start_relative(struct alarm *alarm, ktime_t start) { struct alarm_base *base = &alarm_bases[alarm->type]; - start = ktime_add_safe(start, base->gettime()); + start = ktime_add_safe(start, base->get_ktime()); alarm_start(alarm, start); } EXPORT_SYMBOL_GPL(alarm_start_relative); @@ -414,7 +414,7 @@ int alarm_try_to_cancel(struct alarm *alarm) alarmtimer_dequeue(base, alarm); spin_unlock_irqrestore(&base->lock, flags); - trace_alarmtimer_cancel(alarm, base->gettime()); + trace_alarmtimer_cancel(alarm, base->get_ktime()); return ret; } EXPORT_SYMBOL_GPL(alarm_try_to_cancel); @@ -474,7 +474,7 @@ u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) { struct alarm_base *base = &alarm_bases[alarm->type]; - return alarm_forward(alarm, base->gettime(), interval); + return alarm_forward(alarm, base->get_ktime(), interval); } EXPORT_SYMBOL_GPL(alarm_forward_now); @@ -500,7 +500,7 @@ static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type) return; } - delta = ktime_sub(absexp, base->gettime()); + delta = ktime_sub(absexp, base->get_ktime()); spin_lock_irqsave(&freezer_delta_lock, flags); if (!freezer_delta || (delta < freezer_delta)) { @@ -632,7 +632,7 @@ static void alarm_timer_arm(struct k_itimer *timr, ktime_t expires, struct alarm_base *base = &alarm_bases[alarm->type]; if (!absolute) - expires = ktime_add_safe(expires, base->gettime()); + expires = ktime_add_safe(expires, base->get_ktime()); if (sigev_none) alarm->node.expires = expires; else @@ -657,24 +657,41 @@ static int alarm_clock_getres(const clockid_t which_clock, struct timespec64 *tp } /** - * alarm_clock_get - posix clock_get interface + * alarm_clock_get_timespec - posix clock_get_timespec interface * @which_clock: clockid * @tp: timespec to fill. * - * Provides the underlying alarm base time. + * Provides the underlying alarm base time in a tasks time namespace. */ -static int alarm_clock_get(clockid_t which_clock, struct timespec64 *tp) +static int alarm_clock_get_timespec(clockid_t which_clock, struct timespec64 *tp) { struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)]; if (!alarmtimer_get_rtcdev()) return -EINVAL; - *tp = ktime_to_timespec64(base->gettime()); + base->get_timespec(tp); + return 0; } /** + * alarm_clock_get_ktime - posix clock_get_ktime interface + * @which_clock: clockid + * + * Provides the underlying alarm base time in the root namespace. + */ +static ktime_t alarm_clock_get_ktime(clockid_t which_clock) +{ + struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)]; + + if (!alarmtimer_get_rtcdev()) + return -EINVAL; + + return base->get_ktime(); +} + +/** * alarm_timer_create - posix timer_create interface * @new_timer: k_itimer pointer to manage * @@ -747,7 +764,7 @@ static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp, struct timespec64 rmt; ktime_t rem; - rem = ktime_sub(absexp, alarm_bases[type].gettime()); + rem = ktime_sub(absexp, alarm_bases[type].get_ktime()); if (rem <= 0) return 0; @@ -816,9 +833,11 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, exp = timespec64_to_ktime(*tsreq); /* Convert (if necessary) to absolute time */ if (flags != TIMER_ABSTIME) { - ktime_t now = alarm_bases[type].gettime(); + ktime_t now = alarm_bases[type].get_ktime(); exp = ktime_add_safe(now, exp); + } else { + exp = timens_ktime_to_host(which_clock, exp); } ret = alarmtimer_do_nsleep(&alarm, exp, type); @@ -837,7 +856,8 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, const struct k_clock alarm_clock = { .clock_getres = alarm_clock_getres, - .clock_get = alarm_clock_get, + .clock_get_ktime = alarm_clock_get_ktime, + .clock_get_timespec = alarm_clock_get_timespec, .timer_create = alarm_timer_create, .timer_set = common_timer_set, .timer_del = common_timer_del, @@ -866,6 +886,12 @@ static struct platform_driver alarmtimer_driver = { } }; +static void get_boottime_timespec(struct timespec64 *tp) +{ + ktime_get_boottime_ts64(tp); + timens_add_boottime(tp); +} + /** * alarmtimer_init - Initialize alarm timer code * @@ -874,17 +900,18 @@ static struct platform_driver alarmtimer_driver = { */ static int __init alarmtimer_init(void) { - struct platform_device *pdev; - int error = 0; + int error; int i; alarmtimer_rtc_timer_init(); /* Initialize alarm bases */ alarm_bases[ALARM_REALTIME].base_clockid = CLOCK_REALTIME; - alarm_bases[ALARM_REALTIME].gettime = &ktime_get_real; + alarm_bases[ALARM_REALTIME].get_ktime = &ktime_get_real; + alarm_bases[ALARM_REALTIME].get_timespec = ktime_get_real_ts64, alarm_bases[ALARM_BOOTTIME].base_clockid = CLOCK_BOOTTIME; - alarm_bases[ALARM_BOOTTIME].gettime = &ktime_get_boottime; + alarm_bases[ALARM_BOOTTIME].get_ktime = &ktime_get_boottime; + alarm_bases[ALARM_BOOTTIME].get_timespec = get_boottime_timespec; for (i = 0; i < ALARM_NUMTYPE; i++) { timerqueue_init_head(&alarm_bases[i].timerqueue); spin_lock_init(&alarm_bases[i].lock); @@ -898,15 +925,7 @@ static int __init alarmtimer_init(void) if (error) goto out_if; - pdev = platform_device_register_simple("alarmtimer", -1, NULL, 0); - if (IS_ERR(pdev)) { - error = PTR_ERR(pdev); - goto out_drv; - } return 0; - -out_drv: - platform_driver_unregister(&alarmtimer_driver); out_if: alarmtimer_rtc_interface_remove(); return error; diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 8de90ea31280..3a609e7344f3 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1477,7 +1477,7 @@ EXPORT_SYMBOL_GPL(hrtimer_active); static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, struct hrtimer_clock_base *base, struct hrtimer *timer, ktime_t *now, - unsigned long flags) + unsigned long flags) __must_hold(&cpu_base->lock) { enum hrtimer_restart (*fn)(struct hrtimer *); int restart; @@ -1910,8 +1910,8 @@ static long __sched hrtimer_nanosleep_restart(struct restart_block *restart) return ret; } -long hrtimer_nanosleep(const struct timespec64 *rqtp, - const enum hrtimer_mode mode, const clockid_t clockid) +long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, + const clockid_t clockid) { struct restart_block *restart; struct hrtimer_sleeper t; @@ -1923,7 +1923,7 @@ long hrtimer_nanosleep(const struct timespec64 *rqtp, slack = 0; hrtimer_init_sleeper_on_stack(&t, clockid, mode); - hrtimer_set_expires_range_ns(&t.timer, timespec64_to_ktime(*rqtp), slack); + hrtimer_set_expires_range_ns(&t.timer, rqtp, slack); ret = do_nanosleep(&t, mode); if (ret != -ERESTART_RESTARTBLOCK) goto out; @@ -1958,7 +1958,8 @@ SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; - return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC); + return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, + CLOCK_MONOTONIC); } #endif @@ -1978,7 +1979,8 @@ SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp, current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; - return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC); + return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, + CLOCK_MONOTONIC); } #endif diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c new file mode 100644 index 000000000000..12858507d75a --- /dev/null +++ b/kernel/time/namespace.c @@ -0,0 +1,468 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Author: Andrei Vagin <avagin@openvz.org> + * Author: Dmitry Safonov <dima@arista.com> + */ + +#include <linux/time_namespace.h> +#include <linux/user_namespace.h> +#include <linux/sched/signal.h> +#include <linux/sched/task.h> +#include <linux/seq_file.h> +#include <linux/proc_ns.h> +#include <linux/export.h> +#include <linux/time.h> +#include <linux/slab.h> +#include <linux/cred.h> +#include <linux/err.h> +#include <linux/mm.h> + +#include <vdso/datapage.h> + +ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim, + struct timens_offsets *ns_offsets) +{ + ktime_t offset; + + switch (clockid) { + case CLOCK_MONOTONIC: + offset = timespec64_to_ktime(ns_offsets->monotonic); + break; + case CLOCK_BOOTTIME: + case CLOCK_BOOTTIME_ALARM: + offset = timespec64_to_ktime(ns_offsets->boottime); + break; + default: + return tim; + } + + /* + * Check that @tim value is in [offset, KTIME_MAX + offset] + * and subtract offset. + */ + if (tim < offset) { + /* + * User can specify @tim *absolute* value - if it's lesser than + * the time namespace's offset - it's already expired. + */ + tim = 0; + } else { + tim = ktime_sub(tim, offset); + if (unlikely(tim > KTIME_MAX)) + tim = KTIME_MAX; + } + + return tim; +} + +static struct ucounts *inc_time_namespaces(struct user_namespace *ns) +{ + return inc_ucount(ns, current_euid(), UCOUNT_TIME_NAMESPACES); +} + +static void dec_time_namespaces(struct ucounts *ucounts) +{ + dec_ucount(ucounts, UCOUNT_TIME_NAMESPACES); +} + +/** + * clone_time_ns - Clone a time namespace + * @user_ns: User namespace which owns a new namespace. + * @old_ns: Namespace to clone + * + * Clone @old_ns and set the clone refcount to 1 + * + * Return: The new namespace or ERR_PTR. + */ +static struct time_namespace *clone_time_ns(struct user_namespace *user_ns, + struct time_namespace *old_ns) +{ + struct time_namespace *ns; + struct ucounts *ucounts; + int err; + + err = -ENOSPC; + ucounts = inc_time_namespaces(user_ns); + if (!ucounts) + goto fail; + + err = -ENOMEM; + ns = kmalloc(sizeof(*ns), GFP_KERNEL); + if (!ns) + goto fail_dec; + + kref_init(&ns->kref); + + ns->vvar_page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!ns->vvar_page) + goto fail_free; + + err = ns_alloc_inum(&ns->ns); + if (err) + goto fail_free_page; + + ns->ucounts = ucounts; + ns->ns.ops = &timens_operations; + ns->user_ns = get_user_ns(user_ns); + ns->offsets = old_ns->offsets; + ns->frozen_offsets = false; + return ns; + +fail_free_page: + __free_page(ns->vvar_page); +fail_free: + kfree(ns); +fail_dec: + dec_time_namespaces(ucounts); +fail: + return ERR_PTR(err); +} + +/** + * copy_time_ns - Create timens_for_children from @old_ns + * @flags: Cloning flags + * @user_ns: User namespace which owns a new namespace. + * @old_ns: Namespace to clone + * + * If CLONE_NEWTIME specified in @flags, creates a new timens_for_children; + * adds a refcounter to @old_ns otherwise. + * + * Return: timens_for_children namespace or ERR_PTR. + */ +struct time_namespace *copy_time_ns(unsigned long flags, + struct user_namespace *user_ns, struct time_namespace *old_ns) +{ + if (!(flags & CLONE_NEWTIME)) + return get_time_ns(old_ns); + + return clone_time_ns(user_ns, old_ns); +} + +static struct timens_offset offset_from_ts(struct timespec64 off) +{ + struct timens_offset ret; + + ret.sec = off.tv_sec; + ret.nsec = off.tv_nsec; + + return ret; +} + +/* + * A time namespace VVAR page has the same layout as the VVAR page which + * contains the system wide VDSO data. + * + * For a normal task the VVAR pages are installed in the normal ordering: + * VVAR + * PVCLOCK + * HVCLOCK + * TIMENS <- Not really required + * + * Now for a timens task the pages are installed in the following order: + * TIMENS + * PVCLOCK + * HVCLOCK + * VVAR + * + * The check for vdso_data->clock_mode is in the unlikely path of + * the seq begin magic. So for the non-timens case most of the time + * 'seq' is even, so the branch is not taken. + * + * If 'seq' is odd, i.e. a concurrent update is in progress, the extra check + * for vdso_data->clock_mode is a non-issue. The task is spin waiting for the + * update to finish and for 'seq' to become even anyway. + * + * Timens page has vdso_data->clock_mode set to VCLOCK_TIMENS which enforces + * the time namespace handling path. + */ +static void timens_setup_vdso_data(struct vdso_data *vdata, + struct time_namespace *ns) +{ + struct timens_offset *offset = vdata->offset; + struct timens_offset monotonic = offset_from_ts(ns->offsets.monotonic); + struct timens_offset boottime = offset_from_ts(ns->offsets.boottime); + + vdata->seq = 1; + vdata->clock_mode = VCLOCK_TIMENS; + offset[CLOCK_MONOTONIC] = monotonic; + offset[CLOCK_MONOTONIC_RAW] = monotonic; + offset[CLOCK_MONOTONIC_COARSE] = monotonic; + offset[CLOCK_BOOTTIME] = boottime; + offset[CLOCK_BOOTTIME_ALARM] = boottime; +} + +/* + * Protects possibly multiple offsets writers racing each other + * and tasks entering the namespace. + */ +static DEFINE_MUTEX(offset_lock); + +static void timens_set_vvar_page(struct task_struct *task, + struct time_namespace *ns) +{ + struct vdso_data *vdata; + unsigned int i; + + if (ns == &init_time_ns) + return; + + /* Fast-path, taken by every task in namespace except the first. */ + if (likely(ns->frozen_offsets)) + return; + + mutex_lock(&offset_lock); + /* Nothing to-do: vvar_page has been already initialized. */ + if (ns->frozen_offsets) + goto out; + + ns->frozen_offsets = true; + vdata = arch_get_vdso_data(page_address(ns->vvar_page)); + + for (i = 0; i < CS_BASES; i++) + timens_setup_vdso_data(&vdata[i], ns); + +out: + mutex_unlock(&offset_lock); +} + +void free_time_ns(struct kref *kref) +{ + struct time_namespace *ns; + + ns = container_of(kref, struct time_namespace, kref); + dec_time_namespaces(ns->ucounts); + put_user_ns(ns->user_ns); + ns_free_inum(&ns->ns); + __free_page(ns->vvar_page); + kfree(ns); +} + +static struct time_namespace *to_time_ns(struct ns_common *ns) +{ + return container_of(ns, struct time_namespace, ns); +} + +static struct ns_common *timens_get(struct task_struct *task) +{ + struct time_namespace *ns = NULL; + struct nsproxy *nsproxy; + + task_lock(task); + nsproxy = task->nsproxy; + if (nsproxy) { + ns = nsproxy->time_ns; + get_time_ns(ns); + } + task_unlock(task); + + return ns ? &ns->ns : NULL; +} + +static struct ns_common *timens_for_children_get(struct task_struct *task) +{ + struct time_namespace *ns = NULL; + struct nsproxy *nsproxy; + + task_lock(task); + nsproxy = task->nsproxy; + if (nsproxy) { + ns = nsproxy->time_ns_for_children; + get_time_ns(ns); + } + task_unlock(task); + + return ns ? &ns->ns : NULL; +} + +static void timens_put(struct ns_common *ns) +{ + put_time_ns(to_time_ns(ns)); +} + +static int timens_install(struct nsproxy *nsproxy, struct ns_common *new) +{ + struct time_namespace *ns = to_time_ns(new); + int err; + + if (!current_is_single_threaded()) + return -EUSERS; + + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || + !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) + return -EPERM; + + timens_set_vvar_page(current, ns); + + err = vdso_join_timens(current, ns); + if (err) + return err; + + get_time_ns(ns); + put_time_ns(nsproxy->time_ns); + nsproxy->time_ns = ns; + + get_time_ns(ns); + put_time_ns(nsproxy->time_ns_for_children); + nsproxy->time_ns_for_children = ns; + return 0; +} + +int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk) +{ + struct ns_common *nsc = &nsproxy->time_ns_for_children->ns; + struct time_namespace *ns = to_time_ns(nsc); + int err; + + /* create_new_namespaces() already incremented the ref counter */ + if (nsproxy->time_ns == nsproxy->time_ns_for_children) + return 0; + + timens_set_vvar_page(tsk, ns); + + err = vdso_join_timens(tsk, ns); + if (err) + return err; + + get_time_ns(ns); + put_time_ns(nsproxy->time_ns); + nsproxy->time_ns = ns; + + return 0; +} + +static struct user_namespace *timens_owner(struct ns_common *ns) +{ + return to_time_ns(ns)->user_ns; +} + +static void show_offset(struct seq_file *m, int clockid, struct timespec64 *ts) +{ + seq_printf(m, "%d %lld %ld\n", clockid, ts->tv_sec, ts->tv_nsec); +} + +void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m) +{ + struct ns_common *ns; + struct time_namespace *time_ns; + + ns = timens_for_children_get(p); + if (!ns) + return; + time_ns = to_time_ns(ns); + + show_offset(m, CLOCK_MONOTONIC, &time_ns->offsets.monotonic); + show_offset(m, CLOCK_BOOTTIME, &time_ns->offsets.boottime); + put_time_ns(time_ns); +} + +int proc_timens_set_offset(struct file *file, struct task_struct *p, + struct proc_timens_offset *offsets, int noffsets) +{ + struct ns_common *ns; + struct time_namespace *time_ns; + struct timespec64 tp; + int i, err; + + ns = timens_for_children_get(p); + if (!ns) + return -ESRCH; + time_ns = to_time_ns(ns); + + if (!file_ns_capable(file, time_ns->user_ns, CAP_SYS_TIME)) { + put_time_ns(time_ns); + return -EPERM; + } + + for (i = 0; i < noffsets; i++) { + struct proc_timens_offset *off = &offsets[i]; + + switch (off->clockid) { + case CLOCK_MONOTONIC: + ktime_get_ts64(&tp); + break; + case CLOCK_BOOTTIME: + ktime_get_boottime_ts64(&tp); + break; + default: + err = -EINVAL; + goto out; + } + + err = -ERANGE; + + if (off->val.tv_sec > KTIME_SEC_MAX || + off->val.tv_sec < -KTIME_SEC_MAX) + goto out; + + tp = timespec64_add(tp, off->val); + /* + * KTIME_SEC_MAX is divided by 2 to be sure that KTIME_MAX is + * still unreachable. + */ + if (tp.tv_sec < 0 || tp.tv_sec > KTIME_SEC_MAX / 2) + goto out; + } + + mutex_lock(&offset_lock); + if (time_ns->frozen_offsets) { + err = -EACCES; + goto out_unlock; + } + + err = 0; + /* Don't report errors after this line */ + for (i = 0; i < noffsets; i++) { + struct proc_timens_offset *off = &offsets[i]; + struct timespec64 *offset = NULL; + + switch (off->clockid) { + case CLOCK_MONOTONIC: + offset = &time_ns->offsets.monotonic; + break; + case CLOCK_BOOTTIME: + offset = &time_ns->offsets.boottime; + break; + } + + *offset = off->val; + } + +out_unlock: + mutex_unlock(&offset_lock); +out: + put_time_ns(time_ns); + + return err; +} + +const struct proc_ns_operations timens_operations = { + .name = "time", + .type = CLONE_NEWTIME, + .get = timens_get, + .put = timens_put, + .install = timens_install, + .owner = timens_owner, +}; + +const struct proc_ns_operations timens_for_children_operations = { + .name = "time_for_children", + .type = CLONE_NEWTIME, + .get = timens_for_children_get, + .put = timens_put, + .install = timens_install, + .owner = timens_owner, +}; + +struct time_namespace init_time_ns = { + .kref = KREF_INIT(3), + .user_ns = &init_user_ns, + .ns.inum = PROC_TIME_INIT_INO, + .ns.ops = &timens_operations, + .frozen_offsets = true, +}; + +static int __init time_ns_init(void) +{ + return 0; +} +subsys_initcall(time_ns_init); diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index ec960bb939fd..77c0c2370b6d 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -14,8 +14,6 @@ #include "posix-timers.h" -static void delete_clock(struct kref *kref); - /* * Returns NULL if the posix_clock instance attached to 'fp' is old and stale. */ @@ -125,7 +123,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp) err = 0; if (!err) { - kref_get(&clk->kref); + get_device(clk->dev); fp->private_data = clk; } out: @@ -141,7 +139,7 @@ static int posix_clock_release(struct inode *inode, struct file *fp) if (clk->ops.release) err = clk->ops.release(clk); - kref_put(&clk->kref, delete_clock); + put_device(clk->dev); fp->private_data = NULL; @@ -161,38 +159,35 @@ static const struct file_operations posix_clock_file_operations = { #endif }; -int posix_clock_register(struct posix_clock *clk, dev_t devid) +int posix_clock_register(struct posix_clock *clk, struct device *dev) { int err; - kref_init(&clk->kref); init_rwsem(&clk->rwsem); cdev_init(&clk->cdev, &posix_clock_file_operations); + err = cdev_device_add(&clk->cdev, dev); + if (err) { + pr_err("%s unable to add device %d:%d\n", + dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt)); + return err; + } clk->cdev.owner = clk->ops.owner; - err = cdev_add(&clk->cdev, devid, 1); + clk->dev = dev; - return err; + return 0; } EXPORT_SYMBOL_GPL(posix_clock_register); -static void delete_clock(struct kref *kref) -{ - struct posix_clock *clk = container_of(kref, struct posix_clock, kref); - - if (clk->release) - clk->release(clk); -} - void posix_clock_unregister(struct posix_clock *clk) { - cdev_del(&clk->cdev); + cdev_device_del(&clk->cdev, clk->dev); down_write(&clk->rwsem); clk->zombie = true; up_write(&clk->rwsem); - kref_put(&clk->kref, delete_clock); + put_device(clk->dev); } EXPORT_SYMBOL_GPL(posix_clock_unregister); @@ -315,8 +310,8 @@ out: } const struct k_clock clock_posix_dynamic = { - .clock_getres = pc_clock_getres, - .clock_set = pc_clock_settime, - .clock_get = pc_clock_gettime, - .clock_adj = pc_clock_adjtime, + .clock_getres = pc_clock_getres, + .clock_set = pc_clock_settime, + .clock_get_timespec = pc_clock_gettime, + .clock_adj = pc_clock_adjtime, }; diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 42d512fcfda2..8ff6da77a01f 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -1391,26 +1391,26 @@ static int thread_cpu_timer_create(struct k_itimer *timer) } const struct k_clock clock_posix_cpu = { - .clock_getres = posix_cpu_clock_getres, - .clock_set = posix_cpu_clock_set, - .clock_get = posix_cpu_clock_get, - .timer_create = posix_cpu_timer_create, - .nsleep = posix_cpu_nsleep, - .timer_set = posix_cpu_timer_set, - .timer_del = posix_cpu_timer_del, - .timer_get = posix_cpu_timer_get, - .timer_rearm = posix_cpu_timer_rearm, + .clock_getres = posix_cpu_clock_getres, + .clock_set = posix_cpu_clock_set, + .clock_get_timespec = posix_cpu_clock_get, + .timer_create = posix_cpu_timer_create, + .nsleep = posix_cpu_nsleep, + .timer_set = posix_cpu_timer_set, + .timer_del = posix_cpu_timer_del, + .timer_get = posix_cpu_timer_get, + .timer_rearm = posix_cpu_timer_rearm, }; const struct k_clock clock_process = { - .clock_getres = process_cpu_clock_getres, - .clock_get = process_cpu_clock_get, - .timer_create = process_cpu_timer_create, - .nsleep = process_cpu_nsleep, + .clock_getres = process_cpu_clock_getres, + .clock_get_timespec = process_cpu_clock_get, + .timer_create = process_cpu_timer_create, + .nsleep = process_cpu_nsleep, }; const struct k_clock clock_thread = { - .clock_getres = thread_cpu_clock_getres, - .clock_get = thread_cpu_clock_get, - .timer_create = thread_cpu_timer_create, + .clock_getres = thread_cpu_clock_getres, + .clock_get_timespec = thread_cpu_clock_get, + .timer_create = thread_cpu_timer_create, }; diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index 67df65f887ac..fcb3b21d8bdc 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -14,6 +14,7 @@ #include <linux/ktime.h> #include <linux/timekeeping.h> #include <linux/posix-timers.h> +#include <linux/time_namespace.h> #include <linux/compat.h> #ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER @@ -77,9 +78,11 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp) break; case CLOCK_MONOTONIC: ktime_get_ts64(tp); + timens_add_monotonic(tp); break; case CLOCK_BOOTTIME: ktime_get_boottime_ts64(tp); + timens_add_boottime(tp); break; default: return -EINVAL; @@ -126,6 +129,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, struct __kernel_timespec __user *, rmtp) { struct timespec64 t; + ktime_t texp; switch (which_clock) { case CLOCK_REALTIME: @@ -144,13 +148,19 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, rmtp = NULL; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; - return hrtimer_nanosleep(&t, flags & TIMER_ABSTIME ? + texp = timespec64_to_ktime(t); + if (flags & TIMER_ABSTIME) + texp = timens_ktime_to_host(which_clock, texp); + return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL, which_clock); } #ifdef CONFIG_COMPAT COMPAT_SYS_NI(timer_create); +#endif + +#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA) COMPAT_SYS_NI(getitimer); COMPAT_SYS_NI(setitimer); #endif @@ -212,6 +222,7 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, struct old_timespec32 __user *, rmtp) { struct timespec64 t; + ktime_t texp; switch (which_clock) { case CLOCK_REALTIME: @@ -230,7 +241,10 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, rmtp = NULL; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; - return hrtimer_nanosleep(&t, flags & TIMER_ABSTIME ? + texp = timespec64_to_ktime(t); + if (flags & TIMER_ABSTIME) + texp = timens_ktime_to_host(which_clock, texp); + return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL, which_clock); } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 0ec5b7a1d769..ff0eb30de346 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -30,6 +30,7 @@ #include <linux/hashtable.h> #include <linux/compat.h> #include <linux/nospec.h> +#include <linux/time_namespace.h> #include "timekeeping.h" #include "posix-timers.h" @@ -165,12 +166,17 @@ static inline void unlock_timer(struct k_itimer *timr, unsigned long flags) } /* Get clock_realtime */ -static int posix_clock_realtime_get(clockid_t which_clock, struct timespec64 *tp) +static int posix_get_realtime_timespec(clockid_t which_clock, struct timespec64 *tp) { ktime_get_real_ts64(tp); return 0; } +static ktime_t posix_get_realtime_ktime(clockid_t which_clock) +{ + return ktime_get_real(); +} + /* Set clock_realtime */ static int posix_clock_realtime_set(const clockid_t which_clock, const struct timespec64 *tp) @@ -187,18 +193,25 @@ static int posix_clock_realtime_adj(const clockid_t which_clock, /* * Get monotonic time for posix timers */ -static int posix_ktime_get_ts(clockid_t which_clock, struct timespec64 *tp) +static int posix_get_monotonic_timespec(clockid_t which_clock, struct timespec64 *tp) { ktime_get_ts64(tp); + timens_add_monotonic(tp); return 0; } +static ktime_t posix_get_monotonic_ktime(clockid_t which_clock) +{ + return ktime_get(); +} + /* * Get monotonic-raw time for posix timers */ static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp) { ktime_get_raw_ts64(tp); + timens_add_monotonic(tp); return 0; } @@ -213,6 +226,7 @@ static int posix_get_monotonic_coarse(clockid_t which_clock, struct timespec64 *tp) { ktime_get_coarse_ts64(tp); + timens_add_monotonic(tp); return 0; } @@ -222,18 +236,29 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 * return 0; } -static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp) +static int posix_get_boottime_timespec(const clockid_t which_clock, struct timespec64 *tp) { ktime_get_boottime_ts64(tp); + timens_add_boottime(tp); return 0; } -static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp) +static ktime_t posix_get_boottime_ktime(const clockid_t which_clock) +{ + return ktime_get_boottime(); +} + +static int posix_get_tai_timespec(clockid_t which_clock, struct timespec64 *tp) { ktime_get_clocktai_ts64(tp); return 0; } +static ktime_t posix_get_tai_ktime(clockid_t which_clock) +{ + return ktime_get_clocktai(); +} + static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec64 *tp) { tp->tv_sec = 0; @@ -645,7 +670,6 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) { const struct k_clock *kc = timr->kclock; ktime_t now, remaining, iv; - struct timespec64 ts64; bool sig_none; sig_none = timr->it_sigev_notify == SIGEV_NONE; @@ -663,12 +687,7 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) return; } - /* - * The timespec64 based conversion is suboptimal, but it's not - * worth to implement yet another callback. - */ - kc->clock_get(timr->it_clock, &ts64); - now = timespec64_to_ktime(ts64); + now = kc->clock_get_ktime(timr->it_clock); /* * When a requeue is pending or this is a SIGEV_NONE timer move the @@ -781,7 +800,7 @@ static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires, * Posix magic: Relative CLOCK_REALTIME timers are not affected by * clock modifications, so they become CLOCK_MONOTONIC based under the * hood. See hrtimer_init(). Update timr->kclock, so the generic - * functions which use timr->kclock->clock_get() work. + * functions which use timr->kclock->clock_get_*() work. * * Note: it_clock stays unmodified, because the next timer_set() might * use ABSTIME, so it needs to switch back. @@ -866,6 +885,8 @@ int common_timer_set(struct k_itimer *timr, int flags, timr->it_interval = timespec64_to_ktime(new_setting->it_interval); expires = timespec64_to_ktime(new_setting->it_value); + if (flags & TIMER_ABSTIME) + expires = timens_ktime_to_host(timr->it_clock, expires); sigev_none = timr->it_sigev_notify == SIGEV_NONE; kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none); @@ -1067,7 +1088,7 @@ SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock, if (!kc) return -EINVAL; - error = kc->clock_get(which_clock, &kernel_tp); + error = kc->clock_get_timespec(which_clock, &kernel_tp); if (!error && put_timespec64(&kernel_tp, tp)) error = -EFAULT; @@ -1149,7 +1170,7 @@ SYSCALL_DEFINE2(clock_gettime32, clockid_t, which_clock, if (!kc) return -EINVAL; - err = kc->clock_get(which_clock, &ts); + err = kc->clock_get_timespec(which_clock, &ts); if (!err && put_old_timespec32(&ts, tp)) err = -EFAULT; @@ -1200,7 +1221,22 @@ SYSCALL_DEFINE2(clock_getres_time32, clockid_t, which_clock, static int common_nsleep(const clockid_t which_clock, int flags, const struct timespec64 *rqtp) { - return hrtimer_nanosleep(rqtp, flags & TIMER_ABSTIME ? + ktime_t texp = timespec64_to_ktime(*rqtp); + + return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ? + HRTIMER_MODE_ABS : HRTIMER_MODE_REL, + which_clock); +} + +static int common_nsleep_timens(const clockid_t which_clock, int flags, + const struct timespec64 *rqtp) +{ + ktime_t texp = timespec64_to_ktime(*rqtp); + + if (flags & TIMER_ABSTIME) + texp = timens_ktime_to_host(which_clock, texp); + + return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL, which_clock); } @@ -1261,7 +1297,8 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, static const struct k_clock clock_realtime = { .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_clock_realtime_get, + .clock_get_timespec = posix_get_realtime_timespec, + .clock_get_ktime = posix_get_realtime_ktime, .clock_set = posix_clock_realtime_set, .clock_adj = posix_clock_realtime_adj, .nsleep = common_nsleep, @@ -1279,8 +1316,9 @@ static const struct k_clock clock_realtime = { static const struct k_clock clock_monotonic = { .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_ktime_get_ts, - .nsleep = common_nsleep, + .clock_get_timespec = posix_get_monotonic_timespec, + .clock_get_ktime = posix_get_monotonic_ktime, + .nsleep = common_nsleep_timens, .timer_create = common_timer_create, .timer_set = common_timer_set, .timer_get = common_timer_get, @@ -1295,22 +1333,23 @@ static const struct k_clock clock_monotonic = { static const struct k_clock clock_monotonic_raw = { .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_get_monotonic_raw, + .clock_get_timespec = posix_get_monotonic_raw, }; static const struct k_clock clock_realtime_coarse = { .clock_getres = posix_get_coarse_res, - .clock_get = posix_get_realtime_coarse, + .clock_get_timespec = posix_get_realtime_coarse, }; static const struct k_clock clock_monotonic_coarse = { .clock_getres = posix_get_coarse_res, - .clock_get = posix_get_monotonic_coarse, + .clock_get_timespec = posix_get_monotonic_coarse, }; static const struct k_clock clock_tai = { .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_get_tai, + .clock_get_ktime = posix_get_tai_ktime, + .clock_get_timespec = posix_get_tai_timespec, .nsleep = common_nsleep, .timer_create = common_timer_create, .timer_set = common_timer_set, @@ -1326,8 +1365,9 @@ static const struct k_clock clock_tai = { static const struct k_clock clock_boottime = { .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_get_boottime, - .nsleep = common_nsleep, + .clock_get_ktime = posix_get_boottime_ktime, + .clock_get_timespec = posix_get_boottime_timespec, + .nsleep = common_nsleep_timens, .timer_create = common_timer_create, .timer_set = common_timer_set, .timer_get = common_timer_get, diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index 897c29e162b9..f32a2ebba9b8 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -6,8 +6,11 @@ struct k_clock { struct timespec64 *tp); int (*clock_set)(const clockid_t which_clock, const struct timespec64 *tp); - int (*clock_get)(const clockid_t which_clock, - struct timespec64 *tp); + /* Returns the clock value in the current time namespace. */ + int (*clock_get_timespec)(const clockid_t which_clock, + struct timespec64 *tp); + /* Returns the clock value in the root time namespace. */ + ktime_t (*clock_get_ktime)(const clockid_t which_clock); int (*clock_adj)(const clockid_t which_clock, struct __kernel_timex *tx); int (*timer_create)(struct k_itimer *timer); int (*nsleep)(const clockid_t which_clock, int flags, diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index dbd69052eaa6..e4332e3e2d56 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -169,14 +169,15 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) { u64 res, wrap, new_mask, new_epoch, cyc, ns; u32 new_mult, new_shift; - unsigned long r; + unsigned long r, flags; char r_unit; struct clock_read_data rd; if (cd.rate > rate) return; - WARN_ON(!irqs_disabled()); + /* Cannot register a sched_clock with interrupts on */ + local_irq_save(flags); /* Calculate the mult/shift to convert counter ticks to ns. */ clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600); @@ -233,6 +234,8 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) if (irqtime > 0 || (irqtime == -1 && rate >= 1000000)) enable_sched_clock_irqtime(); + local_irq_restore(flags); + pr_debug("Registered %pS as sched_clock source\n", read); } diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 59225b484e4e..7e5d3524e924 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -11,6 +11,7 @@ #include <linux/err.h> #include <linux/hrtimer.h> #include <linux/interrupt.h> +#include <linux/nmi.h> #include <linux/percpu.h> #include <linux/profile.h> #include <linux/sched.h> @@ -558,6 +559,7 @@ void tick_unfreeze(void) trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), false); } else { + touch_softlockup_watchdog(); tick_resume_local(); } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 8b192e67aabc..a792d21cac64 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -58,8 +58,9 @@ static void tick_do_update_jiffies64(ktime_t now) /* * Do a quick check without holding jiffies_lock: + * The READ_ONCE() pairs with two updates done later in this function. */ - delta = ktime_sub(now, last_jiffies_update); + delta = ktime_sub(now, READ_ONCE(last_jiffies_update)); if (delta < tick_period) return; @@ -70,8 +71,9 @@ static void tick_do_update_jiffies64(ktime_t now) if (delta >= tick_period) { delta = ktime_sub(delta, tick_period); - last_jiffies_update = ktime_add(last_jiffies_update, - tick_period); + /* Pairs with the lockless read in this function. */ + WRITE_ONCE(last_jiffies_update, + ktime_add(last_jiffies_update, tick_period)); /* Slow path for long timeouts */ if (unlikely(delta >= tick_period)) { @@ -79,8 +81,10 @@ static void tick_do_update_jiffies64(ktime_t now) ticks = ktime_divns(delta, incr); - last_jiffies_update = ktime_add_ns(last_jiffies_update, - incr * ticks); + /* Pairs with the lockless read in this function. */ + WRITE_ONCE(last_jiffies_update, + ktime_add_ns(last_jiffies_update, + incr * ticks)); } do_timer(++ticks); diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c index 5ee0f7709410..9577c89179cd 100644 --- a/kernel/time/vsyscall.c +++ b/kernel/time/vsyscall.c @@ -28,11 +28,6 @@ static inline void update_vdso_data(struct vdso_data *vdata, vdata[CS_RAW].mult = tk->tkr_raw.mult; vdata[CS_RAW].shift = tk->tkr_raw.shift; - /* CLOCK_REALTIME */ - vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME]; - vdso_ts->sec = tk->xtime_sec; - vdso_ts->nsec = tk->tkr_mono.xtime_nsec; - /* CLOCK_MONOTONIC */ vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC]; vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; @@ -70,12 +65,6 @@ static inline void update_vdso_data(struct vdso_data *vdata, vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_TAI]; vdso_ts->sec = tk->xtime_sec + (s64)tk->tai_offset; vdso_ts->nsec = tk->tkr_mono.xtime_nsec; - - /* - * Read without the seqlock held by clock_getres(). - * Note: No need to have a second copy. - */ - WRITE_ONCE(vdata[CS_HRES_COARSE].hrtimer_res, hrtimer_resolution); } void update_vsyscall(struct timekeeper *tk) @@ -84,20 +73,17 @@ void update_vsyscall(struct timekeeper *tk) struct vdso_timestamp *vdso_ts; u64 nsec; - if (__arch_update_vdso_data()) { - /* - * Some architectures might want to skip the update of the - * data page. - */ - return; - } - /* copy vsyscall data */ vdso_write_begin(vdata); vdata[CS_HRES_COARSE].clock_mode = __arch_get_clock_mode(tk); vdata[CS_RAW].clock_mode = __arch_get_clock_mode(tk); + /* CLOCK_REALTIME also required for time() */ + vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME]; + vdso_ts->sec = tk->xtime_sec; + vdso_ts->nsec = tk->tkr_mono.xtime_nsec; + /* CLOCK_REALTIME_COARSE */ vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE]; vdso_ts->sec = tk->xtime_sec; @@ -110,7 +96,18 @@ void update_vsyscall(struct timekeeper *tk) nsec = nsec + tk->wall_to_monotonic.tv_nsec; vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec); - update_vdso_data(vdata, tk); + /* + * Read without the seqlock held by clock_getres(). + * Note: No need to have a second copy. + */ + WRITE_ONCE(vdata[CS_HRES_COARSE].hrtimer_res, hrtimer_resolution); + + /* + * Architectures can opt out of updating the high resolution part + * of the VDSO. + */ + if (__arch_update_vdso_data()) + update_vdso_data(vdata, tk); __arch_update_vsyscall(vdata, tk); diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index a2659735db73..1af321dec0f1 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -96,6 +96,20 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, return 0; } +/* + * Not all archs define MCOUNT_INSN_SIZE which is used to look for direct + * functions. But those archs currently don't support direct functions + * anyway, and ftrace_find_rec_direct() is just a stub for them. + * Define MCOUNT_INSN_SIZE to keep those archs compiling. + */ +#ifndef MCOUNT_INSN_SIZE +/* Make sure this only works without direct calls */ +# ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +# error MCOUNT_INSN_SIZE not defined with direct calls enabled +# endif +# define MCOUNT_INSN_SIZE 0 +#endif + int function_graph_enter(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp) { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ac99a3500076..9bf1f2cd515e 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -526,8 +526,7 @@ static int function_stat_show(struct seq_file *m, void *v) } #ifdef CONFIG_FUNCTION_GRAPH_TRACER - avg = rec->time; - do_div(avg, rec->counter); + avg = div64_ul(rec->time, rec->counter); if (tracing_thresh && (avg < tracing_thresh)) goto out; #endif @@ -553,7 +552,8 @@ static int function_stat_show(struct seq_file *m, void *v) * Divide only 1000 for ns^2 -> us^2 conversion. * trace_print_graph_duration will divide 1000 again. */ - do_div(stddev, rec->counter * (rec->counter - 1) * 1000); + stddev = div64_ul(stddev, + rec->counter * (rec->counter - 1) * 1000); } trace_seq_init(&s); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ddb7e7f5fe8d..5b6ee4aadc26 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9420,6 +9420,11 @@ __init static int tracing_set_default_clock(void) { /* sched_clock_stable() is determined in late_initcall */ if (!trace_boot_clock && !sched_clock_stable()) { + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warn("Can not set tracing clock due to lockdown\n"); + return -EPERM; + } + printk(KERN_WARNING "Unstable clock detected, switching default tracing clock to \"global\"\n" "If you want to keep using the local clock, then add:\n" diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 63bf60f79398..a98dce1b3334 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -52,6 +52,9 @@ enum trace_type { #undef __field #define __field(type, item) type item; +#undef __field_fn +#define __field_fn(type, item) type item; + #undef __field_struct #define __field_struct(type, item) __field(type, item) @@ -71,26 +74,22 @@ enum trace_type { #define F_STRUCT(args...) args #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ struct struct_name { \ struct trace_entry ent; \ tstruct \ } #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter) +#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk) #undef FTRACE_ENTRY_REG -#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \ - filter, regfn) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) #undef FTRACE_ENTRY_PACKED -#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print, \ - filter) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) __packed +#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) __packed #include "trace_entries.h" @@ -1917,17 +1916,15 @@ extern void tracing_log_err(struct trace_array *tr, #define internal_trace_puts(str) __trace_puts(_THIS_IP_, str, strlen(str)) #undef FTRACE_ENTRY -#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ +#define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \ extern struct trace_event_call \ __aligned(4) event_##call; #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \ - FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print)) #undef FTRACE_ENTRY_PACKED -#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print, filter) \ - FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print)) #include "trace_entries.h" diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index fc8e97328e54..3e9d81608284 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -61,15 +61,13 @@ FTRACE_ENTRY_REG(function, ftrace_entry, TRACE_FN, F_STRUCT( - __field( unsigned long, ip ) - __field( unsigned long, parent_ip ) + __field_fn( unsigned long, ip ) + __field_fn( unsigned long, parent_ip ) ), F_printk(" %ps <-- %ps", (void *)__entry->ip, (void *)__entry->parent_ip), - FILTER_TRACE_FN, - perf_ftrace_event_register ); @@ -84,9 +82,7 @@ FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry, __field_desc( int, graph_ent, depth ) ), - F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth), - - FILTER_OTHER + F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth) ); /* Function return entry */ @@ -97,18 +93,16 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry, F_STRUCT( __field_struct( struct ftrace_graph_ret, ret ) __field_desc( unsigned long, ret, func ) + __field_desc( unsigned long, ret, overrun ) __field_desc( unsigned long long, ret, calltime) __field_desc( unsigned long long, ret, rettime ) - __field_desc( unsigned long, ret, overrun ) __field_desc( int, ret, depth ) ), F_printk("<-- %ps (%d) (start: %llx end: %llx) over: %d", (void *)__entry->func, __entry->depth, __entry->calltime, __entry->rettime, - __entry->depth), - - FILTER_OTHER + __entry->depth) ); /* @@ -137,9 +131,7 @@ FTRACE_ENTRY(context_switch, ctx_switch_entry, F_printk("%u:%u:%u ==> %u:%u:%u [%03u]", __entry->prev_pid, __entry->prev_prio, __entry->prev_state, __entry->next_pid, __entry->next_prio, __entry->next_state, - __entry->next_cpu), - - FILTER_OTHER + __entry->next_cpu) ); /* @@ -157,9 +149,7 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry, F_printk("%u:%u:%u ==+ %u:%u:%u [%03u]", __entry->prev_pid, __entry->prev_prio, __entry->prev_state, __entry->next_pid, __entry->next_prio, __entry->next_state, - __entry->next_cpu), - - FILTER_OTHER + __entry->next_cpu) ); /* @@ -183,9 +173,7 @@ FTRACE_ENTRY(kernel_stack, stack_entry, (void *)__entry->caller[0], (void *)__entry->caller[1], (void *)__entry->caller[2], (void *)__entry->caller[3], (void *)__entry->caller[4], (void *)__entry->caller[5], - (void *)__entry->caller[6], (void *)__entry->caller[7]), - - FILTER_OTHER + (void *)__entry->caller[6], (void *)__entry->caller[7]) ); FTRACE_ENTRY(user_stack, userstack_entry, @@ -203,9 +191,7 @@ FTRACE_ENTRY(user_stack, userstack_entry, (void *)__entry->caller[0], (void *)__entry->caller[1], (void *)__entry->caller[2], (void *)__entry->caller[3], (void *)__entry->caller[4], (void *)__entry->caller[5], - (void *)__entry->caller[6], (void *)__entry->caller[7]), - - FILTER_OTHER + (void *)__entry->caller[6], (void *)__entry->caller[7]) ); /* @@ -222,9 +208,7 @@ FTRACE_ENTRY(bprint, bprint_entry, ), F_printk("%ps: %s", - (void *)__entry->ip, __entry->fmt), - - FILTER_OTHER + (void *)__entry->ip, __entry->fmt) ); FTRACE_ENTRY_REG(print, print_entry, @@ -239,8 +223,6 @@ FTRACE_ENTRY_REG(print, print_entry, F_printk("%ps: %s", (void *)__entry->ip, __entry->buf), - FILTER_OTHER, - ftrace_event_register ); @@ -254,9 +236,7 @@ FTRACE_ENTRY(raw_data, raw_data_entry, ), F_printk("id:%04x %08x", - __entry->id, (int)__entry->buf[0]), - - FILTER_OTHER + __entry->id, (int)__entry->buf[0]) ); FTRACE_ENTRY(bputs, bputs_entry, @@ -269,9 +249,7 @@ FTRACE_ENTRY(bputs, bputs_entry, ), F_printk("%ps: %s", - (void *)__entry->ip, __entry->str), - - FILTER_OTHER + (void *)__entry->ip, __entry->str) ); FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw, @@ -283,16 +261,14 @@ FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw, __field_desc( resource_size_t, rw, phys ) __field_desc( unsigned long, rw, value ) __field_desc( unsigned long, rw, pc ) - __field_desc( int, rw, map_id ) + __field_desc( int, rw, map_id ) __field_desc( unsigned char, rw, opcode ) __field_desc( unsigned char, rw, width ) ), F_printk("%lx %lx %lx %d %x %x", (unsigned long)__entry->phys, __entry->value, __entry->pc, - __entry->map_id, __entry->opcode, __entry->width), - - FILTER_OTHER + __entry->map_id, __entry->opcode, __entry->width) ); FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, @@ -304,15 +280,13 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, __field_desc( resource_size_t, map, phys ) __field_desc( unsigned long, map, virt ) __field_desc( unsigned long, map, len ) - __field_desc( int, map, map_id ) + __field_desc( int, map, map_id ) __field_desc( unsigned char, map, opcode ) ), F_printk("%lx %lx %lx %d %x", (unsigned long)__entry->phys, __entry->virt, __entry->len, - __entry->map_id, __entry->opcode), - - FILTER_OTHER + __entry->map_id, __entry->opcode) ); @@ -334,9 +308,7 @@ FTRACE_ENTRY(branch, trace_branch, F_printk("%u:%s:%s (%u)%s", __entry->line, __entry->func, __entry->file, __entry->correct, - __entry->constant ? " CONSTANT" : ""), - - FILTER_OTHER + __entry->constant ? " CONSTANT" : "") ); @@ -362,7 +334,5 @@ FTRACE_ENTRY(hwlat, hwlat_entry, __entry->duration, __entry->outer_duration, __entry->nmi_total_ts, - __entry->nmi_count), - - FILTER_OTHER + __entry->nmi_count) ); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index a5b614cc3887..c8622a44d300 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -24,6 +24,7 @@ #include <linux/delay.h> #include <trace/events/sched.h> +#include <trace/syscall.h> #include <asm/setup.h> @@ -2017,7 +2018,24 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) */ head = trace_get_fields(call); if (list_empty(head)) { - ret = call->class->define_fields(call); + struct trace_event_fields *field = call->class->fields_array; + unsigned int offset = sizeof(struct trace_entry); + + for (; field->type; field++) { + if (field->type == TRACE_FUNCTION_TYPE) { + ret = field->define_fields(call); + break; + } + + offset = ALIGN(offset, field->align); + ret = trace_define_field(call, field->type, field->name, + offset, field->size, + field->is_signed, field->filter_type); + if (ret) + break; + + offset += field->size; + } if (ret < 0) { pr_warn("Could not initialize trace point events/%s\n", name); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index f62de5f43e79..f2896d13001b 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -116,6 +116,7 @@ struct hist_field { struct ftrace_event_field *field; unsigned long flags; hist_field_fn_t fn; + unsigned int ref; unsigned int size; unsigned int offset; unsigned int is_signed; @@ -1154,6 +1155,12 @@ static struct synth_event *find_synth_event(const char *name) return NULL; } +static struct trace_event_fields synth_event_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = synth_event_define_fields }, + {} +}; + static int register_synth_event(struct synth_event *event) { struct trace_event_call *call = &event->call; @@ -1175,7 +1182,7 @@ static int register_synth_event(struct synth_event *event) INIT_LIST_HEAD(&call->class->fields); call->event.funcs = &synth_event_funcs; - call->class->define_fields = synth_event_define_fields; + call->class->fields_array = synth_event_fields_array; ret = register_trace_event(&call->event); if (!ret) { @@ -1766,11 +1773,13 @@ static struct hist_field *find_var(struct hist_trigger_data *hist_data, struct event_trigger_data *test; struct hist_field *hist_field; + lockdep_assert_held(&event_mutex); + hist_field = find_var_field(hist_data, var_name); if (hist_field) return hist_field; - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { test_data = test->private_data; hist_field = find_var_field(test_data, var_name); @@ -1820,7 +1829,9 @@ static struct hist_field *find_file_var(struct trace_event_file *file, struct event_trigger_data *test; struct hist_field *hist_field; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { test_data = test->private_data; hist_field = find_var_field(test_data, var_name); @@ -2423,8 +2434,16 @@ static int contains_operator(char *str) return field_op; } +static void get_hist_field(struct hist_field *hist_field) +{ + hist_field->ref++; +} + static void __destroy_hist_field(struct hist_field *hist_field) { + if (--hist_field->ref > 1) + return; + kfree(hist_field->var.name); kfree(hist_field->name); kfree(hist_field->type); @@ -2466,6 +2485,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, if (!hist_field) return NULL; + hist_field->ref = 1; + hist_field->hist_data = hist_data; if (flags & HIST_FIELD_FL_EXPR || flags & HIST_FIELD_FL_ALIAS) @@ -2661,6 +2682,17 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data, { unsigned long flags = HIST_FIELD_FL_VAR_REF; struct hist_field *ref_field; + int i; + + /* Check if the variable already exists */ + for (i = 0; i < hist_data->n_var_refs; i++) { + ref_field = hist_data->var_refs[i]; + if (ref_field->var.idx == var_field->var.idx && + ref_field->var.hist_data == var_field->hist_data) { + get_hist_field(ref_field); + return ref_field; + } + } ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL); if (ref_field) { @@ -3115,7 +3147,9 @@ static char *find_trigger_filter(struct hist_trigger_data *hist_data, { struct event_trigger_data *test; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (test->private_data == hist_data) return test->filter_str; @@ -3166,9 +3200,11 @@ find_compatible_hist(struct hist_trigger_data *target_hist_data, struct event_trigger_data *test; unsigned int n_keys; + lockdep_assert_held(&event_mutex); + n_keys = target_hist_data->n_fields - target_hist_data->n_vals; - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { hist_data = test->private_data; @@ -5528,7 +5564,7 @@ static int hist_show(struct seq_file *m, void *v) goto out_unlock; } - list_for_each_entry_rcu(data, &event_file->triggers, list) { + list_for_each_entry(data, &event_file->triggers, list) { if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) hist_trigger_show(m, data, n++); } @@ -5921,7 +5957,9 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops, if (hist_data->attrs->name && !named_data) goto new; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (!hist_trigger_match(data, test, named_data, false)) continue; @@ -6005,10 +6043,12 @@ static bool have_hist_trigger_match(struct event_trigger_data *data, struct event_trigger_data *test, *named_data = NULL; bool match = false; + lockdep_assert_held(&event_mutex); + if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (hist_trigger_match(data, test, named_data, false)) { match = true; @@ -6026,10 +6066,12 @@ static bool hist_trigger_check_refs(struct event_trigger_data *data, struct hist_trigger_data *hist_data = data->private_data; struct event_trigger_data *test, *named_data = NULL; + lockdep_assert_held(&event_mutex); + if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (!hist_trigger_match(data, test, named_data, false)) continue; @@ -6051,10 +6093,12 @@ static void hist_unregister_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *test, *named_data = NULL; bool unregistered = false; + lockdep_assert_held(&event_mutex); + if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (!hist_trigger_match(data, test, named_data, false)) continue; @@ -6080,7 +6124,9 @@ static bool hist_file_check_refs(struct trace_event_file *file) struct hist_trigger_data *hist_data; struct event_trigger_data *test; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { hist_data = test->private_data; if (check_var_refs(hist_data)) @@ -6323,7 +6369,8 @@ hist_enable_trigger(struct event_trigger_data *data, void *rec, struct enable_trigger_data *enable_data = data->private_data; struct event_trigger_data *test; - list_for_each_entry_rcu(test, &enable_data->file->triggers, list) { + list_for_each_entry_rcu(test, &enable_data->file->triggers, list, + lockdep_is_held(&event_mutex)) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (enable_data->enable) test->paused = false; diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c index d45079ee62f8..22bcf7c51d1e 100644 --- a/kernel/trace/trace_events_inject.c +++ b/kernel/trace/trace_events_inject.c @@ -195,7 +195,7 @@ static int parse_entry(char *str, struct trace_event_call *call, void **pentry) unsigned long irq_flags; void *entry = NULL; int entry_size; - u64 val; + u64 val = 0; int len; entry = trace_alloc_entry(call, &entry_size); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 2cd53ca21b51..40106fff06a4 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -501,7 +501,9 @@ void update_cond_flag(struct trace_event_file *file) struct event_trigger_data *data; bool set_cond = false; - list_for_each_entry_rcu(data, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(data, &file->triggers, list) { if (data->filter || event_command_post_trigger(data->cmd_ops) || event_command_needs_rec(data->cmd_ops)) { set_cond = true; @@ -536,7 +538,9 @@ static int register_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *test; int ret = 0; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == data->cmd_ops->trigger_type) { ret = -EEXIST; goto out; @@ -581,7 +585,9 @@ static void unregister_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *data; bool unregistered = false; - list_for_each_entry_rcu(data, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(data, &file->triggers, list) { if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) { unregistered = true; list_del_rcu(&data->list); @@ -1497,7 +1503,9 @@ int event_enable_register_trigger(char *glob, struct event_trigger_data *test; int ret = 0; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { test_enable_data = test->private_data; if (test_enable_data && (test->cmd_ops->trigger_type == @@ -1537,7 +1545,9 @@ void event_enable_unregister_trigger(char *glob, struct event_trigger_data *data; bool unregistered = false; - list_for_each_entry_rcu(data, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(data, &file->triggers, list) { enable_data = data->private_data; if (enable_data && (data->cmd_ops->trigger_type == diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 2e6d2e9741cc..77ce5a3b6773 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -29,10 +29,8 @@ static int ftrace_event_register(struct trace_event_call *call, * function and thus become accesible via perf. */ #undef FTRACE_ENTRY_REG -#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \ - filter, regfn) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) /* not needed for this file */ #undef __field_struct @@ -41,6 +39,9 @@ static int ftrace_event_register(struct trace_event_call *call, #undef __field #define __field(type, item) type item; +#undef __field_fn +#define __field_fn(type, item) type item; + #undef __field_desc #define __field_desc(type, container, item) type item; @@ -60,7 +61,7 @@ static int ftrace_event_register(struct trace_event_call *call, #define F_printk(fmt, args...) fmt, args #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ struct ____ftrace_##name { \ tstruct \ }; \ @@ -73,76 +74,46 @@ static void __always_unused ____ftrace_check_##name(void) \ } #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print, filter) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) #include "trace_entries.h" +#undef __field_ext +#define __field_ext(_type, _item, _filter_type) { \ + .type = #_type, .name = #_item, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + is_signed_type(_type), .filter_type = _filter_type }, + #undef __field -#define __field(type, item) \ - ret = trace_define_field(event_call, #type, #item, \ - offsetof(typeof(field), item), \ - sizeof(field.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; +#define __field(_type, _item) __field_ext(_type, _item, FILTER_OTHER) + +#undef __field_fn +#define __field_fn(_type, _item) __field_ext(_type, _item, FILTER_TRACE_FN) #undef __field_desc -#define __field_desc(type, container, item) \ - ret = trace_define_field(event_call, #type, #item, \ - offsetof(typeof(field), \ - container.item), \ - sizeof(field.container.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; +#define __field_desc(_type, _container, _item) __field_ext(_type, _item, FILTER_OTHER) #undef __array -#define __array(type, item, len) \ - do { \ - char *type_str = #type"["__stringify(len)"]"; \ - BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ - ret = trace_define_field(event_call, type_str, #item, \ - offsetof(typeof(field), item), \ - sizeof(field.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; \ - } while (0); +#define __array(_type, _item, _len) { \ + .type = #_type"["__stringify(_len)"]", .name = #_item, \ + .size = sizeof(_type[_len]), .align = __alignof__(_type), \ + is_signed_type(_type), .filter_type = FILTER_OTHER }, #undef __array_desc -#define __array_desc(type, container, item, len) \ - BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ - ret = trace_define_field(event_call, #type "[" #len "]", #item, \ - offsetof(typeof(field), \ - container.item), \ - sizeof(field.container.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; +#define __array_desc(_type, _container, _item, _len) __array(_type, _item, _len) #undef __dynamic_array -#define __dynamic_array(type, item) \ - ret = trace_define_field(event_call, #type "[]", #item, \ - offsetof(typeof(field), item), \ - 0, is_signed_type(type), filter_type);\ - if (ret) \ - return ret; +#define __dynamic_array(_type, _item) { \ + .type = #_type "[]", .name = #_item, \ + .size = 0, .align = __alignof__(_type), \ + is_signed_type(_type), .filter_type = FILTER_OTHER }, #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ -static int __init \ -ftrace_define_fields_##name(struct trace_event_call *event_call) \ -{ \ - struct struct_name field; \ - int ret; \ - int filter_type = filter; \ - \ - tstruct; \ - \ - return ret; \ -} +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ +static struct trace_event_fields ftrace_event_fields_##name[] = { \ + tstruct \ + {} }; #include "trace_entries.h" @@ -152,6 +123,9 @@ ftrace_define_fields_##name(struct trace_event_call *event_call) \ #undef __field #define __field(type, item) +#undef __field_fn +#define __field_fn(type, item) + #undef __field_desc #define __field_desc(type, container, item) @@ -168,12 +142,10 @@ ftrace_define_fields_##name(struct trace_event_call *event_call) \ #define F_printk(fmt, args...) __stringify(fmt) ", " __stringify(args) #undef FTRACE_ENTRY_REG -#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\ - regfn) \ - \ +#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, regfn) \ static struct trace_event_class __refdata event_class_ftrace_##call = { \ .system = __stringify(TRACE_SYSTEM), \ - .define_fields = ftrace_define_fields_##call, \ + .fields_array = ftrace_event_fields_##call, \ .fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\ .reg = regfn, \ }; \ @@ -191,9 +163,9 @@ static struct trace_event_call __used \ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call; #undef FTRACE_ENTRY -#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print, filter) \ +#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \ FTRACE_ENTRY_REG(call, struct_name, etype, \ - PARAMS(tstruct), PARAMS(print), filter, NULL) + PARAMS(tstruct), PARAMS(print), NULL) bool ftrace_event_is_function(struct trace_event_call *call) { diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 7f890262c8a3..aa515d578c5b 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -290,7 +290,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, INIT_HLIST_NODE(&tk->rp.kp.hlist); INIT_LIST_HEAD(&tk->rp.kp.list); - ret = trace_probe_init(&tk->tp, event, group); + ret = trace_probe_init(&tk->tp, event, group, false); if (ret < 0) goto error; @@ -1555,16 +1555,28 @@ static struct trace_event_functions kprobe_funcs = { .trace = print_kprobe_event }; +static struct trace_event_fields kretprobe_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = kretprobe_event_define_fields }, + {} +}; + +static struct trace_event_fields kprobe_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = kprobe_event_define_fields }, + {} +}; + static inline void init_trace_event_call(struct trace_kprobe *tk) { struct trace_event_call *call = trace_probe_event_call(&tk->tp); if (trace_kprobe_is_return(tk)) { call->event.funcs = &kretprobe_funcs; - call->class->define_fields = kretprobe_event_define_fields; + call->class->fields_array = kretprobe_fields_array; } else { call->event.funcs = &kprobe_funcs; - call->class->define_fields = kprobe_event_define_fields; + call->class->fields_array = kprobe_fields_array; } call->flags = TRACE_EVENT_FL_KPROBE; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 905b10af5d5c..9ae87be422f2 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -984,15 +984,19 @@ void trace_probe_cleanup(struct trace_probe *tp) } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group) + const char *group, bool alloc_filter) { struct trace_event_call *call; + size_t size = sizeof(struct trace_probe_event); int ret = 0; if (!event || !group) return -EINVAL; - tp->event = kzalloc(sizeof(struct trace_probe_event), GFP_KERNEL); + if (alloc_filter) + size += sizeof(struct trace_uprobe_filter); + + tp->event = kzalloc(size, GFP_KERNEL); if (!tp->event) return -ENOMEM; diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 4ee703728aec..a0ff9e200ef6 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -223,6 +223,12 @@ struct probe_arg { const struct fetch_type *type; /* Type of this argument */ }; +struct trace_uprobe_filter { + rwlock_t rwlock; + int nr_systemwide; + struct list_head perf_events; +}; + /* Event call and class holder */ struct trace_probe_event { unsigned int flags; /* For TP_FLAG_* */ @@ -230,6 +236,7 @@ struct trace_probe_event { struct trace_event_call call; struct list_head files; struct list_head probes; + struct trace_uprobe_filter filter[0]; }; struct trace_probe { @@ -322,7 +329,7 @@ static inline bool trace_probe_has_single_file(struct trace_probe *tp) } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group); + const char *group, bool alloc_filter); void trace_probe_cleanup(struct trace_probe *tp); int trace_probe_append(struct trace_probe *tp, struct trace_probe *to); void trace_probe_unlink(struct trace_probe *tp); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 5e43b9664eca..617e297f46dc 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -630,7 +630,7 @@ static void start_wakeup_tracer(struct trace_array *tr) if (ret) { pr_info("wakeup trace: Couldn't activate tracepoint" " probe to kernel_sched_migrate_task\n"); - return; + goto fail_deprobe_sched_switch; } wakeup_reset(tr); @@ -648,6 +648,8 @@ static void start_wakeup_tracer(struct trace_array *tr) printk(KERN_ERR "failed to start wakeup tracer\n"); return; +fail_deprobe_sched_switch: + unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL); fail_deprobe_wake_new: unregister_trace_sched_wakeup_new(probe_wakeup, NULL); fail_deprobe: diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c index 344e4c1aa09c..87de6edafd14 100644 --- a/kernel/trace/trace_seq.c +++ b/kernel/trace/trace_seq.c @@ -381,7 +381,7 @@ int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii) { - unsigned int save_len = s->seq.len; + unsigned int save_len = s->seq.len; if (s->full) return 0; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 4df9a209f7ca..c557f42a9397 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -283,6 +283,11 @@ static void check_stack(unsigned long ip, unsigned long *stack) local_irq_restore(flags); } +/* Some archs may not define MCOUNT_INSN_SIZE */ +#ifndef MCOUNT_INSN_SIZE +# define MCOUNT_INSN_SIZE 0 +#endif + static void stack_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 16fa218556fa..2978c29d87d4 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -203,11 +203,10 @@ print_syscall_exit(struct trace_iterator *iter, int flags, extern char *__bad_type_size(void); -#define SYSCALL_FIELD(type, field, name) \ - sizeof(type) != sizeof(trace.field) ? \ - __bad_type_size() : \ - #type, #name, offsetof(typeof(trace), field), \ - sizeof(trace.field), is_signed_type(type) +#define SYSCALL_FIELD(_type, _name) { \ + .type = #_type, .name = #_name, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER } static int __init __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len) @@ -274,42 +273,23 @@ static int __init syscall_enter_define_fields(struct trace_event_call *call) { struct syscall_trace_enter trace; struct syscall_metadata *meta = call->data; - int ret; - int i; int offset = offsetof(typeof(trace), args); - - ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr), - FILTER_OTHER); - if (ret) - return ret; + int ret = 0; + int i; for (i = 0; i < meta->nb_args; i++) { ret = trace_define_field(call, meta->types[i], meta->args[i], offset, sizeof(unsigned long), 0, FILTER_OTHER); + if (ret) + break; offset += sizeof(unsigned long); } return ret; } -static int __init syscall_exit_define_fields(struct trace_event_call *call) -{ - struct syscall_trace_exit trace; - int ret; - - ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr), - FILTER_OTHER); - if (ret) - return ret; - - ret = trace_define_field(call, SYSCALL_FIELD(long, ret, ret), - FILTER_OTHER); - - return ret; -} - static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) { struct trace_array *tr = data; @@ -507,6 +487,13 @@ static int __init init_syscall_trace(struct trace_event_call *call) return id; } +static struct trace_event_fields __refdata syscall_enter_fields_array[] = { + SYSCALL_FIELD(int, __syscall_nr), + { .type = TRACE_FUNCTION_TYPE, + .define_fields = syscall_enter_define_fields }, + {} +}; + struct trace_event_functions enter_syscall_print_funcs = { .trace = print_syscall_enter, }; @@ -518,7 +505,7 @@ struct trace_event_functions exit_syscall_print_funcs = { struct trace_event_class __refdata event_class_syscall_enter = { .system = "syscalls", .reg = syscall_enter_register, - .define_fields = syscall_enter_define_fields, + .fields_array = syscall_enter_fields_array, .get_fields = syscall_get_enter_fields, .raw_init = init_syscall_trace, }; @@ -526,7 +513,11 @@ struct trace_event_class __refdata event_class_syscall_enter = { struct trace_event_class __refdata event_class_syscall_exit = { .system = "syscalls", .reg = syscall_exit_register, - .define_fields = syscall_exit_define_fields, + .fields_array = (struct trace_event_fields[]){ + SYSCALL_FIELD(int, __syscall_nr), + SYSCALL_FIELD(long, ret), + {} + }, .fields = LIST_HEAD_INIT(event_class_syscall_exit.fields), .raw_init = init_syscall_trace, }; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 352073d36585..7885ebd23d0c 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -34,12 +34,6 @@ struct uprobe_trace_entry_head { #define DATAOF_TRACE_ENTRY(entry, is_return) \ ((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return)) -struct trace_uprobe_filter { - rwlock_t rwlock; - int nr_systemwide; - struct list_head perf_events; -}; - static int trace_uprobe_create(int argc, const char **argv); static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev); static int trace_uprobe_release(struct dyn_event *ev); @@ -60,7 +54,6 @@ static struct dyn_event_operations trace_uprobe_ops = { */ struct trace_uprobe { struct dyn_event devent; - struct trace_uprobe_filter filter; struct uprobe_consumer consumer; struct path path; struct inode *inode; @@ -351,7 +344,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) if (!tu) return ERR_PTR(-ENOMEM); - ret = trace_probe_init(&tu->tp, event, group); + ret = trace_probe_init(&tu->tp, event, group, true); if (ret < 0) goto error; @@ -359,7 +352,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) tu->consumer.handler = uprobe_dispatcher; if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher; - init_trace_uprobe_filter(&tu->filter); + init_trace_uprobe_filter(tu->tp.event->filter); return tu; error: @@ -1067,13 +1060,14 @@ static void __probe_event_disable(struct trace_probe *tp) struct trace_probe *pos; struct trace_uprobe *tu; + tu = container_of(tp, struct trace_uprobe, tp); + WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); if (!tu->inode) continue; - WARN_ON(!uprobe_filter_is_empty(&tu->filter)); - uprobe_unregister(tu->inode, tu->offset, &tu->consumer); tu->inode = NULL; } @@ -1108,7 +1102,7 @@ static int probe_event_enable(struct trace_event_call *call, } tu = container_of(tp, struct trace_uprobe, tp); - WARN_ON(!uprobe_filter_is_empty(&tu->filter)); + WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); if (enabled) return 0; @@ -1205,39 +1199,39 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) } static inline bool -uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event) +trace_uprobe_filter_event(struct trace_uprobe_filter *filter, + struct perf_event *event) { - return __uprobe_perf_filter(&tu->filter, event->hw.target->mm); + return __uprobe_perf_filter(filter, event->hw.target->mm); } -static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) +static bool trace_uprobe_filter_remove(struct trace_uprobe_filter *filter, + struct perf_event *event) { bool done; - write_lock(&tu->filter.rwlock); + write_lock(&filter->rwlock); if (event->hw.target) { list_del(&event->hw.tp_list); - done = tu->filter.nr_systemwide || + done = filter->nr_systemwide || (event->hw.target->flags & PF_EXITING) || - uprobe_filter_event(tu, event); + trace_uprobe_filter_event(filter, event); } else { - tu->filter.nr_systemwide--; - done = tu->filter.nr_systemwide; + filter->nr_systemwide--; + done = filter->nr_systemwide; } - write_unlock(&tu->filter.rwlock); + write_unlock(&filter->rwlock); - if (!done) - return uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); - - return 0; + return done; } -static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) +/* This returns true if the filter always covers target mm */ +static bool trace_uprobe_filter_add(struct trace_uprobe_filter *filter, + struct perf_event *event) { bool done; - int err; - write_lock(&tu->filter.rwlock); + write_lock(&filter->rwlock); if (event->hw.target) { /* * event->parent != NULL means copy_process(), we can avoid @@ -1247,28 +1241,21 @@ static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) * attr.enable_on_exec means that exec/mmap will install the * breakpoints we need. */ - done = tu->filter.nr_systemwide || + done = filter->nr_systemwide || event->parent || event->attr.enable_on_exec || - uprobe_filter_event(tu, event); - list_add(&event->hw.tp_list, &tu->filter.perf_events); + trace_uprobe_filter_event(filter, event); + list_add(&event->hw.tp_list, &filter->perf_events); } else { - done = tu->filter.nr_systemwide; - tu->filter.nr_systemwide++; + done = filter->nr_systemwide; + filter->nr_systemwide++; } - write_unlock(&tu->filter.rwlock); + write_unlock(&filter->rwlock); - err = 0; - if (!done) { - err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); - if (err) - uprobe_perf_close(tu, event); - } - return err; + return done; } -static int uprobe_perf_multi_call(struct trace_event_call *call, - struct perf_event *event, - int (*op)(struct trace_uprobe *tu, struct perf_event *event)) +static int uprobe_perf_close(struct trace_event_call *call, + struct perf_event *event) { struct trace_probe *pos, *tp; struct trace_uprobe *tu; @@ -1278,25 +1265,59 @@ static int uprobe_perf_multi_call(struct trace_event_call *call, if (WARN_ON_ONCE(!tp)) return -ENODEV; + tu = container_of(tp, struct trace_uprobe, tp); + if (trace_uprobe_filter_remove(tu->tp.event->filter, event)) + return 0; + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); - ret = op(tu, event); + ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); if (ret) break; } return ret; } + +static int uprobe_perf_open(struct trace_event_call *call, + struct perf_event *event) +{ + struct trace_probe *pos, *tp; + struct trace_uprobe *tu; + int err = 0; + + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return -ENODEV; + + tu = container_of(tp, struct trace_uprobe, tp); + if (trace_uprobe_filter_add(tu->tp.event->filter, event)) + return 0; + + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { + err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); + if (err) { + uprobe_perf_close(call, event); + break; + } + } + + return err; +} + static bool uprobe_perf_filter(struct uprobe_consumer *uc, enum uprobe_filter_ctx ctx, struct mm_struct *mm) { + struct trace_uprobe_filter *filter; struct trace_uprobe *tu; int ret; tu = container_of(uc, struct trace_uprobe, consumer); - read_lock(&tu->filter.rwlock); - ret = __uprobe_perf_filter(&tu->filter, mm); - read_unlock(&tu->filter.rwlock); + filter = tu->tp.event->filter; + + read_lock(&filter->rwlock); + ret = __uprobe_perf_filter(filter, mm); + read_unlock(&filter->rwlock); return ret; } @@ -1419,10 +1440,10 @@ trace_uprobe_register(struct trace_event_call *event, enum trace_reg type, return 0; case TRACE_REG_PERF_OPEN: - return uprobe_perf_multi_call(event, data, uprobe_perf_open); + return uprobe_perf_open(event, data); case TRACE_REG_PERF_CLOSE: - return uprobe_perf_multi_call(event, data, uprobe_perf_close); + return uprobe_perf_close(event, data); #endif default: @@ -1507,12 +1528,17 @@ static struct trace_event_functions uprobe_funcs = { .trace = print_uprobe_event }; +static struct trace_event_fields uprobe_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = uprobe_event_define_fields }, + {} +}; + static inline void init_trace_event_call(struct trace_uprobe *tu) { struct trace_event_call *call = trace_probe_event_call(&tu->tp); - call->event.funcs = &uprobe_funcs; - call->class->define_fields = uprobe_event_define_fields; + call->class->fields_array = uprobe_fields_array; call->flags = TRACE_EVENT_FL_UPROBE | TRACE_EVENT_FL_CAP_ANY; call->class->reg = trace_uprobe_register; diff --git a/kernel/up.c b/kernel/up.c index 862b460ab97a..53144d056252 100644 --- a/kernel/up.c +++ b/kernel/up.c @@ -68,9 +68,8 @@ EXPORT_SYMBOL(on_each_cpu_mask); * Preemption is disabled here to make sure the cond_func is called under the * same condtions in UP and SMP. */ -void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info), - smp_call_func_t func, void *info, bool wait, - gfp_t gfp_flags, const struct cpumask *mask) +void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, + void *info, bool wait, const struct cpumask *mask) { unsigned long flags; @@ -84,11 +83,10 @@ void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info), } EXPORT_SYMBOL(on_each_cpu_cond_mask); -void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), - smp_call_func_t func, void *info, bool wait, - gfp_t gfp_flags) +void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func, + void *info, bool wait) { - on_each_cpu_cond_mask(cond_func, func, info, wait, gfp_flags, NULL); + on_each_cpu_cond_mask(cond_func, func, info, wait, NULL); } EXPORT_SYMBOL(on_each_cpu_cond); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 0621301ae8cf..b6b1f54a7837 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -161,6 +161,8 @@ static void lockup_detector_update_enable(void) #ifdef CONFIG_SOFTLOCKUP_DETECTOR +#define SOFTLOCKUP_RESET ULONG_MAX + /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; @@ -173,7 +175,6 @@ static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static DEFINE_PER_CPU(bool, soft_watchdog_warn); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts); -static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static unsigned long soft_lockup_nmi_warn; @@ -273,7 +274,7 @@ notrace void touch_softlockup_watchdog_sched(void) * Preemption can be enabled. It doesn't matter which CPU's timestamp * gets zeroed here, so use the raw_ operation. */ - raw_cpu_write(watchdog_touch_ts, 0); + raw_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET); } notrace void touch_softlockup_watchdog(void) @@ -297,14 +298,14 @@ void touch_all_softlockup_watchdogs(void) * the softlockup check. */ for_each_cpu(cpu, &watchdog_allowed_mask) - per_cpu(watchdog_touch_ts, cpu) = 0; + per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET; wq_watchdog_touch(-1); } void touch_softlockup_watchdog_sync(void) { __this_cpu_write(softlockup_touch_sync, true); - __this_cpu_write(watchdog_touch_ts, 0); + __this_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET); } static int is_softlockup(unsigned long touch_ts) @@ -380,7 +381,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) /* .. and repeat */ hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); - if (touch_ts == 0) { + if (touch_ts == SOFTLOCKUP_RESET) { if (unlikely(__this_cpu_read(softlockup_touch_sync))) { /* * If the time stamp was touched atomically @@ -413,22 +414,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) return HRTIMER_RESTART; /* only warn once */ - if (__this_cpu_read(soft_watchdog_warn) == true) { - /* - * When multiple processes are causing softlockups the - * softlockup detector only warns on the first one - * because the code relies on a full quiet cycle to - * re-arm. The second process prevents the quiet cycle - * and never gets reported. Use task pointers to detect - * this. - */ - if (__this_cpu_read(softlockup_task_ptr_saved) != - current) { - __this_cpu_write(soft_watchdog_warn, false); - __touch_watchdog(); - } + if (__this_cpu_read(soft_watchdog_warn) == true) return HRTIMER_RESTART; - } if (softlockup_all_cpu_backtrace) { /* Prevent multiple soft-lockup reports if one cpu is already @@ -444,7 +431,6 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); - __this_cpu_write(softlockup_task_ptr_saved, current); print_modules(); print_irqtrace_events(current); if (regs) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 4114412649b8..301db4406bc3 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2266,7 +2266,7 @@ __acquires(&pool->lock) * While we must be careful to not use "work" after this, the trace * point will only record its address. */ - trace_workqueue_execute_end(work); + trace_workqueue_execute_end(work, worker->current_func); lock_map_release(&lockdep_map); lock_map_release(&pwq->wq->lockdep_map); |