diff options
Diffstat (limited to 'kernel')
81 files changed, 1006 insertions, 860 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 616994f0a76f..1408b3353a3c 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -13,8 +13,8 @@ obj-y = fork.o exec_domain.o panic.o \ ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files -CFLAGS_REMOVE_cgroup-debug.o = -pg -CFLAGS_REMOVE_irq_work.o = -pg +CFLAGS_REMOVE_cgroup-debug.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_irq_work.o = $(CC_FLAGS_FTRACE) endif # cond_syscall is currently not LTO compatible @@ -143,7 +143,7 @@ endif kernel/system_certificates.o: $(obj)/x509_certificate_list quiet_cmd_x509certs = CERTS $@ - cmd_x509certs = cat $(X509_CERTIFICATES) /dev/null >$@ $(foreach X509,$(X509_CERTIFICATES),; echo " - Including cert $(X509)") + cmd_x509certs = cat $(X509_CERTIFICATES) /dev/null >$@ $(foreach X509,$(X509_CERTIFICATES),; $(kecho) " - Including cert $(X509)") targets += $(obj)/x509_certificate_list $(obj)/x509_certificate_list: $(X509_CERTIFICATES) $(obj)/.x509.list diff --git a/kernel/acct.c b/kernel/acct.c index 33738ef972f3..e6c10d1a4058 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -76,10 +76,11 @@ int acct_parm[3] = {4, 2, 30}; /* * External references and all of the globals. */ -static void do_acct_process(struct bsd_acct_struct *acct); struct bsd_acct_struct { struct fs_pin pin; + atomic_long_t count; + struct rcu_head rcu; struct mutex lock; int active; unsigned long needcheck; @@ -89,6 +90,8 @@ struct bsd_acct_struct { struct completion done; }; +static void do_acct_process(struct bsd_acct_struct *acct); + /* * Check the amount of free space and suspend/resume accordingly. */ @@ -124,32 +127,56 @@ out: return acct->active; } +static void acct_put(struct bsd_acct_struct *p) +{ + if (atomic_long_dec_and_test(&p->count)) + kfree_rcu(p, rcu); +} + +static inline struct bsd_acct_struct *to_acct(struct fs_pin *p) +{ + return p ? container_of(p, struct bsd_acct_struct, pin) : NULL; +} + static struct bsd_acct_struct *acct_get(struct pid_namespace *ns) { struct bsd_acct_struct *res; again: smp_rmb(); rcu_read_lock(); - res = ACCESS_ONCE(ns->bacct); + res = to_acct(ACCESS_ONCE(ns->bacct)); if (!res) { rcu_read_unlock(); return NULL; } - if (!atomic_long_inc_not_zero(&res->pin.count)) { + if (!atomic_long_inc_not_zero(&res->count)) { rcu_read_unlock(); cpu_relax(); goto again; } rcu_read_unlock(); mutex_lock(&res->lock); - if (!res->ns) { + if (res != to_acct(ACCESS_ONCE(ns->bacct))) { mutex_unlock(&res->lock); - pin_put(&res->pin); + acct_put(res); goto again; } return res; } +static void acct_pin_kill(struct fs_pin *pin) +{ + struct bsd_acct_struct *acct = to_acct(pin); + mutex_lock(&acct->lock); + do_acct_process(acct); + schedule_work(&acct->work); + wait_for_completion(&acct->done); + cmpxchg(&acct->ns->bacct, pin, NULL); + mutex_unlock(&acct->lock); + pin_remove(pin); + acct_put(acct); +} + static void close_work(struct work_struct *work) { struct bsd_acct_struct *acct = container_of(work, struct bsd_acct_struct, work); @@ -160,44 +187,13 @@ static void close_work(struct work_struct *work) complete(&acct->done); } -static void acct_kill(struct bsd_acct_struct *acct, - struct bsd_acct_struct *new) -{ - if (acct) { - struct pid_namespace *ns = acct->ns; - do_acct_process(acct); - INIT_WORK(&acct->work, close_work); - init_completion(&acct->done); - schedule_work(&acct->work); - wait_for_completion(&acct->done); - pin_remove(&acct->pin); - ns->bacct = new; - acct->ns = NULL; - atomic_long_dec(&acct->pin.count); - mutex_unlock(&acct->lock); - pin_put(&acct->pin); - } -} - -static void acct_pin_kill(struct fs_pin *pin) -{ - struct bsd_acct_struct *acct; - acct = container_of(pin, struct bsd_acct_struct, pin); - mutex_lock(&acct->lock); - if (!acct->ns) { - mutex_unlock(&acct->lock); - pin_put(pin); - acct = NULL; - } - acct_kill(acct, NULL); -} - static int acct_on(struct filename *pathname) { struct file *file; struct vfsmount *mnt, *internal; struct pid_namespace *ns = task_active_pid_ns(current); - struct bsd_acct_struct *acct, *old; + struct bsd_acct_struct *acct; + struct fs_pin *old; int err; acct = kzalloc(sizeof(struct bsd_acct_struct), GFP_KERNEL); @@ -238,21 +234,21 @@ static int acct_on(struct filename *pathname) mnt = file->f_path.mnt; file->f_path.mnt = internal; - atomic_long_set(&acct->pin.count, 1); - acct->pin.kill = acct_pin_kill; + atomic_long_set(&acct->count, 1); + init_fs_pin(&acct->pin, acct_pin_kill); acct->file = file; acct->needcheck = jiffies; acct->ns = ns; mutex_init(&acct->lock); + INIT_WORK(&acct->work, close_work); + init_completion(&acct->done); mutex_lock_nested(&acct->lock, 1); /* nobody has seen it yet */ pin_insert(&acct->pin, mnt); - old = acct_get(ns); - if (old) - acct_kill(old, acct); - else - ns->bacct = acct; + rcu_read_lock(); + old = xchg(&ns->bacct, &acct->pin); mutex_unlock(&acct->lock); + pin_kill(old); mnt_drop_write(mnt); mntput(mnt); return 0; @@ -288,7 +284,8 @@ SYSCALL_DEFINE1(acct, const char __user *, name) mutex_unlock(&acct_on_mutex); putname(tmp); } else { - acct_kill(acct_get(task_active_pid_ns(current)), NULL); + rcu_read_lock(); + pin_kill(task_active_pid_ns(current)->bacct); } return error; @@ -296,7 +293,8 @@ SYSCALL_DEFINE1(acct, const char __user *, name) void acct_exit_ns(struct pid_namespace *ns) { - acct_kill(acct_get(ns), NULL); + rcu_read_lock(); + pin_kill(ns->bacct); } /* @@ -576,7 +574,7 @@ static void slow_acct_process(struct pid_namespace *ns) if (acct) { do_acct_process(acct); mutex_unlock(&acct->lock); - pin_put(&acct->pin); + acct_put(acct); } } } diff --git a/kernel/audit.h b/kernel/audit.h index 3cdffad5a1d9..1caa0d345d90 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -24,12 +24,6 @@ #include <linux/skbuff.h> #include <uapi/linux/mqueue.h> -/* 0 = no checking - 1 = put_count checking - 2 = verbose put_count checking -*/ -#define AUDIT_DEBUG 0 - /* AUDIT_NAMES is the number of slots we reserve in the audit_context * for saving names from getname(). If we get more names we will allocate * a name dynamically and also add those to the list anchored by names_list. */ @@ -74,9 +68,8 @@ struct audit_cap_data { }; }; -/* When fs/namei.c:getname() is called, we store the pointer in name and - * we don't let putname() free it (instead we free all of the saved - * pointers at syscall exit time). +/* When fs/namei.c:getname() is called, we store the pointer in name and bump + * the refcnt in the associated filename struct. * * Further, in fs/namei.c:path_lookup() we store the inode and device. */ @@ -86,7 +79,6 @@ struct audit_names { struct filename *name; int name_len; /* number of chars to log */ bool hidden; /* don't log this record */ - bool name_put; /* call __putname()? */ unsigned long ino; dev_t dev; @@ -208,11 +200,6 @@ struct audit_context { }; int fds[2]; struct audit_proctitle proctitle; - -#if AUDIT_DEBUG - int put_count; - int ino_count; -#endif }; extern u32 audit_ever_enabled; diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 4f68a326d92e..72e1660a79a3 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -425,7 +425,6 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, goto exit_nofree; bufp = data->buf; - entry->rule.vers_ops = 2; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &entry->rule.fields[i]; @@ -758,7 +757,6 @@ struct audit_entry *audit_dupe_rule(struct audit_krule *old) return ERR_PTR(-ENOMEM); new = &entry->rule; - new->vers_ops = old->vers_ops; new->flags = old->flags; new->pflags = old->pflags; new->listnr = old->listnr; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 072566dd0caf..dc4ae70a7413 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -866,33 +866,10 @@ static inline void audit_free_names(struct audit_context *context) { struct audit_names *n, *next; -#if AUDIT_DEBUG == 2 - if (context->put_count + context->ino_count != context->name_count) { - int i = 0; - - pr_err("%s:%d(:%d): major=%d in_syscall=%d" - " name_count=%d put_count=%d ino_count=%d" - " [NOT freeing]\n", __FILE__, __LINE__, - context->serial, context->major, context->in_syscall, - context->name_count, context->put_count, - context->ino_count); - list_for_each_entry(n, &context->names_list, list) { - pr_err("names[%d] = %p = %s\n", i++, n->name, - n->name->name ?: "(null)"); - } - dump_stack(); - return; - } -#endif -#if AUDIT_DEBUG - context->put_count = 0; - context->ino_count = 0; -#endif - list_for_each_entry_safe(n, next, &context->names_list, list) { list_del(&n->list); - if (n->name && n->name_put) - final_putname(n->name); + if (n->name) + putname(n->name); if (n->should_free) kfree(n); } @@ -1711,9 +1688,6 @@ static struct audit_names *audit_alloc_name(struct audit_context *context, list_add_tail(&aname->list, &context->names_list); context->name_count++; -#if AUDIT_DEBUG - context->ino_count++; -#endif return aname; } @@ -1734,8 +1708,10 @@ __audit_reusename(const __user char *uptr) list_for_each_entry(n, &context->names_list, list) { if (!n->name) continue; - if (n->name->uptr == uptr) + if (n->name->uptr == uptr) { + n->name->refcnt++; return n->name; + } } return NULL; } @@ -1752,19 +1728,8 @@ void __audit_getname(struct filename *name) struct audit_context *context = current->audit_context; struct audit_names *n; - if (!context->in_syscall) { -#if AUDIT_DEBUG == 2 - pr_err("%s:%d(:%d): ignoring getname(%p)\n", - __FILE__, __LINE__, context->serial, name); - dump_stack(); -#endif + if (!context->in_syscall) return; - } - -#if AUDIT_DEBUG - /* The filename _must_ have a populated ->name */ - BUG_ON(!name->name); -#endif n = audit_alloc_name(context, AUDIT_TYPE_UNKNOWN); if (!n) @@ -1772,56 +1737,13 @@ void __audit_getname(struct filename *name) n->name = name; n->name_len = AUDIT_NAME_FULL; - n->name_put = true; name->aname = n; + name->refcnt++; if (!context->pwd.dentry) get_fs_pwd(current->fs, &context->pwd); } -/* audit_putname - intercept a putname request - * @name: name to intercept and delay for putname - * - * If we have stored the name from getname in the audit context, - * then we delay the putname until syscall exit. - * Called from include/linux/fs.h:putname(). - */ -void audit_putname(struct filename *name) -{ - struct audit_context *context = current->audit_context; - - BUG_ON(!context); - if (!name->aname || !context->in_syscall) { -#if AUDIT_DEBUG == 2 - pr_err("%s:%d(:%d): final_putname(%p)\n", - __FILE__, __LINE__, context->serial, name); - if (context->name_count) { - struct audit_names *n; - int i = 0; - - list_for_each_entry(n, &context->names_list, list) - pr_err("name[%d] = %p = %s\n", i++, n->name, - n->name->name ?: "(null)"); - } -#endif - final_putname(name); - } -#if AUDIT_DEBUG - else { - ++context->put_count; - if (context->put_count > context->name_count) { - pr_err("%s:%d(:%d): major=%d in_syscall=%d putname(%p)" - " name_count=%d put_count=%d\n", - __FILE__, __LINE__, - context->serial, context->major, - context->in_syscall, name->name, - context->name_count, context->put_count); - dump_stack(); - } - } -#endif -} - /** * __audit_inode - store the inode and device from a lookup * @name: name being audited @@ -1842,10 +1764,6 @@ void __audit_inode(struct filename *name, const struct dentry *dentry, if (!name) goto out_alloc; -#if AUDIT_DEBUG - /* The struct filename _must_ have a populated ->name */ - BUG_ON(!name->name); -#endif /* * If we have a pointer to an audit_names entry already, then we can * just use it directly if the type is correct. @@ -1863,7 +1781,17 @@ void __audit_inode(struct filename *name, const struct dentry *dentry, } list_for_each_entry_reverse(n, &context->names_list, list) { - if (!n->name || strcmp(n->name->name, name->name)) + if (n->ino) { + /* valid inode number, use that for the comparison */ + if (n->ino != inode->i_ino || + n->dev != inode->i_sb->s_dev) + continue; + } else if (n->name) { + /* inode number has not been set, check the name */ + if (strcmp(n->name->name, name->name)) + continue; + } else + /* no inode and no name (?!) ... this is odd ... */ continue; /* match the correct record type */ @@ -1882,44 +1810,11 @@ out_alloc: n = audit_alloc_name(context, AUDIT_TYPE_UNKNOWN); if (!n) return; - /* unfortunately, while we may have a path name to record with the - * inode, we can't always rely on the string lasting until the end of - * the syscall so we need to create our own copy, it may fail due to - * memory allocation issues, but we do our best */ if (name) { - /* we can't use getname_kernel() due to size limits */ - size_t len = strlen(name->name) + 1; - struct filename *new = __getname(); - - if (unlikely(!new)) - goto out; - - if (len <= (PATH_MAX - sizeof(*new))) { - new->name = (char *)(new) + sizeof(*new); - new->separate = false; - } else if (len <= PATH_MAX) { - /* this looks odd, but is due to final_putname() */ - struct filename *new2; - - new2 = kmalloc(sizeof(*new2), GFP_KERNEL); - if (unlikely(!new2)) { - __putname(new); - goto out; - } - new2->name = (char *)new; - new2->separate = true; - new = new2; - } else { - /* we should never get here, but let's be safe */ - __putname(new); - goto out; - } - strlcpy((char *)new->name, name->name, len); - new->uptr = NULL; - new->aname = n; - n->name = new; - n->name_put = true; + n->name = name; + name->refcnt++; } + out: if (parent) { n->name_len = n->name ? parent_len(n->name->name) : AUDIT_NAME_FULL; @@ -1970,11 +1865,16 @@ void __audit_inode_child(const struct inode *parent, /* look for a parent entry first */ list_for_each_entry(n, &context->names_list, list) { - if (!n->name || n->type != AUDIT_TYPE_PARENT) + if (!n->name || + (n->type != AUDIT_TYPE_PARENT && + n->type != AUDIT_TYPE_UNKNOWN)) continue; - if (n->ino == parent->i_ino && - !audit_compare_dname_path(dname, n->name->name, n->name_len)) { + if (n->ino == parent->i_ino && n->dev == parent->i_sb->s_dev && + !audit_compare_dname_path(dname, + n->name->name, n->name_len)) { + if (n->type == AUDIT_TYPE_UNKNOWN) + n->type = AUDIT_TYPE_PARENT; found_parent = n; break; } @@ -1983,11 +1883,8 @@ void __audit_inode_child(const struct inode *parent, /* is there a matching child entry? */ list_for_each_entry(n, &context->names_list, list) { /* can only match entries that have a name */ - if (!n->name || n->type != type) - continue; - - /* if we found a parent, make sure this one is a child of it */ - if (found_parent && (n->name != found_parent->name)) + if (!n->name || + (n->type != type && n->type != AUDIT_TYPE_UNKNOWN)) continue; if (!strcmp(dname, n->name->name) || @@ -1995,6 +1892,8 @@ void __audit_inode_child(const struct inode *parent, found_parent ? found_parent->name_len : AUDIT_NAME_FULL)) { + if (n->type == AUDIT_TYPE_UNKNOWN) + n->type = type; found_child = n; break; } @@ -2019,10 +1918,10 @@ void __audit_inode_child(const struct inode *parent, if (found_parent) { found_child->name = found_parent->name; found_child->name_len = AUDIT_NAME_FULL; - /* don't call __putname() */ - found_child->name_put = false; + found_child->name->refcnt++; } } + if (inode) audit_copy_inode(found_child, dentry, inode); else @@ -2405,7 +2304,6 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm, struct audit_aux_data_bprm_fcaps *ax; struct audit_context *context = current->audit_context; struct cpu_vfs_cap_data vcaps; - struct dentry *dentry; ax = kmalloc(sizeof(*ax), GFP_KERNEL); if (!ax) @@ -2415,9 +2313,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm, ax->d.next = context->aux; context->aux = (void *)ax; - dentry = dget(bprm->file->f_path.dentry); - get_vfs_caps_from_disk(dentry, &vcaps); - dput(dentry); + get_vfs_caps_from_disk(bprm->file->f_path.dentry, &vcaps); ax->fcap.permitted = vcaps.permitted; ax->fcap.inheritable = vcaps.inheritable; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 04cfe8ace520..29a7b2cc593e 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3077,7 +3077,7 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft) #endif kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name), cgroup_file_mode(cft), 0, cft->kf_ops, cft, - NULL, false, key); + NULL, key); if (IS_ERR(kn)) return PTR_ERR(kn); @@ -4373,16 +4373,20 @@ static void css_free_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); + struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; percpu_ref_exit(&css->refcnt); - if (css->ss) { + if (ss) { /* css free path */ + int id = css->id; + if (css->parent) css_put(css->parent); - css->ss->css_free(css); + ss->css_free(css); + cgroup_idr_remove(&ss->css_idr, id); cgroup_put(cgrp); } else { /* cgroup free path */ @@ -4434,7 +4438,7 @@ static void css_release_work_fn(struct work_struct *work) if (ss) { /* css release path */ - cgroup_idr_remove(&ss->css_idr, css->id); + cgroup_idr_replace(&ss->css_idr, NULL, css->id); if (ss->css_released) ss->css_released(css); } else { diff --git a/kernel/compat.c b/kernel/compat.c index ebb3c369d03d..24f00610c575 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -276,8 +276,7 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp, * core implementation decides to return random nonsense. */ if (ret == -ERESTART_RESTARTBLOCK) { - struct restart_block *restart - = ¤t_thread_info()->restart_block; + struct restart_block *restart = ¤t->restart_block; restart->fn = compat_nanosleep_restart; restart->nanosleep.compat_rmtp = rmtp; @@ -860,7 +859,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, return -EFAULT; if (err == -ERESTART_RESTARTBLOCK) { - restart = ¤t_thread_info()->restart_block; + restart = ¤t->restart_block; restart->fn = compat_clock_nanosleep_restart; restart->nanosleep.compat_rmtp = rmtp; } diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 64b257f6bca2..1d1fe9361d29 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1707,40 +1707,27 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v) { struct cpuset *cs = css_cs(seq_css(sf)); cpuset_filetype_t type = seq_cft(sf)->private; - ssize_t count; - char *buf, *s; int ret = 0; - count = seq_get_buf(sf, &buf); - s = buf; - spin_lock_irq(&callback_lock); switch (type) { case FILE_CPULIST: - s += cpulist_scnprintf(s, count, cs->cpus_allowed); + seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_allowed)); break; case FILE_MEMLIST: - s += nodelist_scnprintf(s, count, cs->mems_allowed); + seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed)); break; case FILE_EFFECTIVE_CPULIST: - s += cpulist_scnprintf(s, count, cs->effective_cpus); + seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_cpus)); break; case FILE_EFFECTIVE_MEMLIST: - s += nodelist_scnprintf(s, count, cs->effective_mems); + seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems)); break; default: ret = -EINVAL; - goto out_unlock; } - if (s < buf + count - 1) { - *s++ = '\n'; - seq_commit(sf, s - buf); - } else { - seq_commit(sf, -1); - } -out_unlock: spin_unlock_irq(&callback_lock); return ret; } @@ -2400,7 +2387,7 @@ void cpuset_cpus_allowed_fallback(struct task_struct *tsk) */ } -void cpuset_init_current_mems_allowed(void) +void __init cpuset_init_current_mems_allowed(void) { nodes_setall(current->mems_allowed); } @@ -2610,8 +2597,6 @@ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed); } -#define CPUSET_NODELIST_LEN (256) - /** * cpuset_print_task_mems_allowed - prints task's cpuset and mems_allowed * @tsk: pointer to task_struct of some task. @@ -2621,23 +2606,16 @@ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, */ void cpuset_print_task_mems_allowed(struct task_struct *tsk) { - /* Statically allocated to prevent using excess stack. */ - static char cpuset_nodelist[CPUSET_NODELIST_LEN]; - static DEFINE_SPINLOCK(cpuset_buffer_lock); struct cgroup *cgrp; - spin_lock(&cpuset_buffer_lock); rcu_read_lock(); cgrp = task_cs(tsk)->css.cgroup; - nodelist_scnprintf(cpuset_nodelist, CPUSET_NODELIST_LEN, - tsk->mems_allowed); pr_info("%s cpuset=", tsk->comm); pr_cont_cgroup_name(cgrp); - pr_cont(" mems_allowed=%s\n", cpuset_nodelist); + pr_cont(" mems_allowed=%*pbl\n", nodemask_pr_args(&tsk->mems_allowed)); rcu_read_unlock(); - spin_unlock(&cpuset_buffer_lock); } /* @@ -2715,10 +2693,8 @@ out: /* Display task mems_allowed in /proc/<pid>/status file. */ void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { - seq_puts(m, "Mems_allowed:\t"); - seq_nodemask(m, &task->mems_allowed); - seq_puts(m, "\n"); - seq_puts(m, "Mems_allowed_list:\t"); - seq_nodemask_list(m, &task->mems_allowed); - seq_puts(m, "\n"); + seq_printf(m, "Mems_allowed:\t%*pb\n", + nodemask_pr_args(&task->mems_allowed)); + seq_printf(m, "Mems_allowed_list:\t%*pbl\n", + nodemask_pr_args(&task->mems_allowed)); } diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 07ce18ca71e0..0874e2edd275 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -604,7 +604,7 @@ return_normal: online_cpus) cpu_relax(); if (!time_left) - pr_crit("KGDB: Timed out waiting for secondary CPUs.\n"); + pr_crit("Timed out waiting for secondary CPUs.\n"); /* * At this point the primary processor is completely @@ -696,6 +696,14 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs) if (arch_kgdb_ops.enable_nmi) arch_kgdb_ops.enable_nmi(0); + /* + * Avoid entering the debugger if we were triggered due to an oops + * but panic_timeout indicates the system should automatically + * reboot on panic. We don't want to get stuck waiting for input + * on such systems, especially if its "just" an oops. + */ + if (signo != SIGTRAP && panic_timeout) + return 1; memset(ks, 0, sizeof(struct kgdb_state)); ks->cpu = raw_smp_processor_id(); @@ -828,6 +836,15 @@ static int kgdb_panic_event(struct notifier_block *self, unsigned long val, void *data) { + /* + * Avoid entering the debugger if we were triggered due to a panic + * We don't want to get stuck waiting for input from user in such case. + * panic_timeout indicates the system should automatically + * reboot on panic. + */ + if (panic_timeout) + return NOTIFY_DONE; + if (dbg_kdb_mode) kdb_printf("PANIC: %s\n", (char *)data); kgdb_breakpoint(); diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 7c70812caea5..fc1ef736253c 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -439,7 +439,7 @@ poll_again: * substituted for %d, %x or %o in the prompt. */ -char *kdb_getstr(char *buffer, size_t bufsize, char *prompt) +char *kdb_getstr(char *buffer, size_t bufsize, const char *prompt) { if (prompt && kdb_prompt_str != prompt) strncpy(kdb_prompt_str, prompt, CMD_BUFLEN); @@ -548,7 +548,7 @@ static int kdb_search_string(char *searched, char *searchfor) return 0; } -int vkdb_printf(const char *fmt, va_list ap) +int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap) { int diag; int linecount; @@ -680,6 +680,12 @@ int vkdb_printf(const char *fmt, va_list ap) size_avail = sizeof(kdb_buffer) - len; goto kdb_print_out; } + if (kdb_grepping_flag >= KDB_GREPPING_FLAG_SEARCH) + /* + * This was a interactive search (using '/' at more + * prompt) and it has completed. Clear the flag. + */ + kdb_grepping_flag = 0; /* * at this point the string is a full line and * should be printed, up to the null. @@ -691,19 +697,20 @@ kdb_printit: * Write to all consoles. */ retlen = strlen(kdb_buffer); + cp = (char *) printk_skip_level(kdb_buffer); if (!dbg_kdb_mode && kgdb_connected) { - gdbstub_msg_write(kdb_buffer, retlen); + gdbstub_msg_write(cp, retlen - (cp - kdb_buffer)); } else { if (dbg_io_ops && !dbg_io_ops->is_console) { - len = retlen; - cp = kdb_buffer; + len = retlen - (cp - kdb_buffer); + cp2 = cp; while (len--) { - dbg_io_ops->write_char(*cp); - cp++; + dbg_io_ops->write_char(*cp2); + cp2++; } } while (c) { - c->write(c, kdb_buffer, retlen); + c->write(c, cp, retlen - (cp - kdb_buffer)); touch_nmi_watchdog(); c = c->next; } @@ -711,7 +718,10 @@ kdb_printit: if (logging) { saved_loglevel = console_loglevel; console_loglevel = CONSOLE_LOGLEVEL_SILENT; - printk(KERN_INFO "%s", kdb_buffer); + if (printk_get_level(kdb_buffer) || src == KDB_MSGSRC_PRINTK) + printk("%s", kdb_buffer); + else + pr_info("%s", kdb_buffer); } if (KDB_STATE(PAGER)) { @@ -794,11 +804,23 @@ kdb_printit: kdb_nextline = linecount - 1; kdb_printf("\r"); suspend_grep = 1; /* for this recursion */ + } else if (buf1[0] == '/' && !kdb_grepping_flag) { + kdb_printf("\r"); + kdb_getstr(kdb_grep_string, KDB_GREP_STRLEN, + kdbgetenv("SEARCHPROMPT") ?: "search> "); + *strchrnul(kdb_grep_string, '\n') = '\0'; + kdb_grepping_flag += KDB_GREPPING_FLAG_SEARCH; + suspend_grep = 1; /* for this recursion */ } else if (buf1[0] && buf1[0] != '\n') { /* user hit something other than enter */ suspend_grep = 1; /* for this recursion */ - kdb_printf("\nOnly 'q' or 'Q' are processed at more " - "prompt, input ignored\n"); + if (buf1[0] != '/') + kdb_printf( + "\nOnly 'q', 'Q' or '/' are processed at " + "more prompt, input ignored\n"); + else + kdb_printf("\n'/' cannot be used during | " + "grep filtering, input ignored\n"); } else if (kdb_grepping_flag) { /* user hit enter */ suspend_grep = 1; /* for this recursion */ @@ -844,7 +866,7 @@ int kdb_printf(const char *fmt, ...) int r; va_start(ap, fmt); - r = vkdb_printf(fmt, ap); + r = vkdb_printf(KDB_MSGSRC_INTERNAL, fmt, ap); va_end(ap); return r; diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 7b40c5f07dce..4121345498e0 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -50,8 +50,7 @@ static int kdb_cmd_enabled = CONFIG_KDB_DEFAULT_ENABLE; module_param_named(cmd_enable, kdb_cmd_enabled, int, 0600); -#define GREP_LEN 256 -char kdb_grep_string[GREP_LEN]; +char kdb_grep_string[KDB_GREP_STRLEN]; int kdb_grepping_flag; EXPORT_SYMBOL(kdb_grepping_flag); int kdb_grep_leading; @@ -870,7 +869,7 @@ static void parse_grep(const char *str) len = strlen(cp); if (!len) return; - if (len >= GREP_LEN) { + if (len >= KDB_GREP_STRLEN) { kdb_printf("search string too long\n"); return; } @@ -915,13 +914,12 @@ int kdb_parse(const char *cmdstr) char *cp; char *cpp, quoted; kdbtab_t *tp; - int i, escaped, ignore_errors = 0, check_grep; + int i, escaped, ignore_errors = 0, check_grep = 0; /* * First tokenize the command string. */ cp = (char *)cmdstr; - kdb_grepping_flag = check_grep = 0; if (KDB_FLAG(CMD_INTERRUPT)) { /* Previous command was interrupted, newline must not @@ -1247,7 +1245,6 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs, kdb_printf("due to NonMaskable Interrupt @ " kdb_machreg_fmt "\n", instruction_pointer(regs)); - kdb_dumpregs(regs); break; case KDB_REASON_SSTEP: case KDB_REASON_BREAK: @@ -1281,6 +1278,9 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs, */ kdb_nextline = 1; KDB_STATE_CLEAR(SUPPRESS); + kdb_grepping_flag = 0; + /* ensure the old search does not leak into '/' commands */ + kdb_grep_string[0] = '\0'; cmdbuf = cmd_cur; *cmdbuf = '\0'; @@ -2256,7 +2256,7 @@ static int kdb_cpu(int argc, const char **argv) /* * Validate cpunum */ - if ((cpunum > NR_CPUS) || !kgdb_info[cpunum].enter_kgdb) + if ((cpunum >= CONFIG_NR_CPUS) || !kgdb_info[cpunum].enter_kgdb) return KDB_BADCPUNUM; dbg_switch_cpu = cpunum; @@ -2583,7 +2583,7 @@ static int kdb_summary(int argc, const char **argv) #define K(x) ((x) << (PAGE_SHIFT - 10)) kdb_printf("\nMemTotal: %8lu kB\nMemFree: %8lu kB\n" "Buffers: %8lu kB\n", - val.totalram, val.freeram, val.bufferram); + K(val.totalram), K(val.freeram), K(val.bufferram)); return 0; } diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index eaacd1693954..75014d7f4568 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -196,7 +196,9 @@ extern int kdb_main_loop(kdb_reason_t, kdb_reason_t, /* Miscellaneous functions and data areas */ extern int kdb_grepping_flag; +#define KDB_GREPPING_FLAG_SEARCH 0x8000 extern char kdb_grep_string[]; +#define KDB_GREP_STRLEN 256 extern int kdb_grep_leading; extern int kdb_grep_trailing; extern char *kdb_cmds[]; @@ -209,7 +211,7 @@ extern void kdb_ps1(const struct task_struct *p); extern void kdb_print_nameval(const char *name, unsigned long val); extern void kdb_send_sig_info(struct task_struct *p, struct siginfo *info); extern void kdb_meminfo_proc_show(void); -extern char *kdb_getstr(char *, size_t, char *); +extern char *kdb_getstr(char *, size_t, const char *); extern void kdb_gdb_state_pass(char *buf); /* Defines for kdb_symbol_print */ diff --git a/kernel/events/Makefile b/kernel/events/Makefile index 103f5d147b2f..2925188f50ea 100644 --- a/kernel/events/Makefile +++ b/kernel/events/Makefile @@ -1,5 +1,5 @@ ifdef CONFIG_FUNCTION_TRACER -CFLAGS_REMOVE_core.o = -pg +CFLAGS_REMOVE_core.o = $(CC_FLAGS_FTRACE) endif obj-y := core.o ring_buffer.o callchain.o diff --git a/kernel/events/core.c b/kernel/events/core.c index 7f2fbb8b5069..f04daabfd1cf 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4101,7 +4101,8 @@ unlock: rcu_read_unlock(); } -void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) +void __weak arch_perf_update_userpage( + struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now) { } @@ -4151,7 +4152,7 @@ void perf_event_update_userpage(struct perf_event *event) userpg->time_running = running + atomic64_read(&event->child_total_time_running); - arch_perf_update_userpage(userpg, now); + arch_perf_update_userpage(event, userpg, now); barrier(); ++userpg->lock; @@ -4293,6 +4294,9 @@ static void perf_mmap_open(struct vm_area_struct *vma) atomic_inc(&event->mmap_count); atomic_inc(&event->rb->mmap_count); + + if (event->pmu->event_mapped) + event->pmu->event_mapped(event); } /* @@ -4312,6 +4316,9 @@ static void perf_mmap_close(struct vm_area_struct *vma) int mmap_locked = rb->mmap_locked; unsigned long size = perf_data_size(rb); + if (event->pmu->event_unmapped) + event->pmu->event_unmapped(event); + atomic_dec(&rb->mmap_count); if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) @@ -4513,6 +4520,9 @@ unlock: vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_ops = &perf_mmap_vmops; + if (event->pmu->event_mapped) + event->pmu->event_mapped(event); + return ret; } @@ -8508,6 +8518,18 @@ void __init perf_event_init(void) != 1024); } +ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, + char *page) +{ + struct perf_pmu_events_attr *pmu_attr = + container_of(attr, struct perf_pmu_events_attr, attr); + + if (pmu_attr->event_str) + return sprintf(page, "%s\n", pmu_attr->event_str); + + return 0; +} + static int __init perf_event_sysfs_init(void) { struct pmu *pmu; diff --git a/kernel/exit.c b/kernel/exit.c index 6806c55475ee..feff10bbb307 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -435,7 +435,8 @@ static void exit_mm(struct task_struct *tsk) task_unlock(tsk); mm_update_next_owner(mm); mmput(mm); - clear_thread_flag(TIF_MEMDIE); + if (test_thread_flag(TIF_MEMDIE)) + unmark_oom_victim(); } static struct task_struct *find_alive_thread(struct task_struct *p) diff --git a/kernel/fork.c b/kernel/fork.c index b379d9abddc7..cf65139615a0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -555,6 +555,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) INIT_LIST_HEAD(&mm->mmlist); mm->core_state = NULL; atomic_long_set(&mm->nr_ptes, 0); + mm_nr_pmds_init(mm); mm->map_count = 0; mm->locked_vm = 0; mm->pinned_vm = 0; @@ -603,6 +604,14 @@ static void check_mm(struct mm_struct *mm) printk(KERN_ALERT "BUG: Bad rss-counter state " "mm:%p idx:%d val:%ld\n", mm, i, x); } + + if (atomic_long_read(&mm->nr_ptes)) + pr_alert("BUG: non-zero nr_ptes on freeing mm: %ld\n", + atomic_long_read(&mm->nr_ptes)); + if (mm_nr_pmds(mm)) + pr_alert("BUG: non-zero nr_pmds on freeing mm: %ld\n", + mm_nr_pmds(mm)); + #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS VM_BUG_ON_MM(mm->pmd_huge_pte, mm); #endif diff --git a/kernel/futex.c b/kernel/futex.c index 4eeb63de7e54..2a5e3830e953 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2217,7 +2217,7 @@ retry: if (!abs_time) goto out; - restart = ¤t_thread_info()->restart_block; + restart = ¤t->restart_block; restart->fn = futex_wait_restart; restart->futex.uaddr = uaddr; restart->futex.val = val; diff --git a/kernel/gcov/Makefile b/kernel/gcov/Makefile index 52aa7e8de927..752d6486b67e 100644 --- a/kernel/gcov/Makefile +++ b/kernel/gcov/Makefile @@ -1,33 +1,7 @@ ccflags-y := -DSRCTREE='"$(srctree)"' -DOBJTREE='"$(objtree)"' -# if-lt -# Usage VAR := $(call if-lt, $(a), $(b)) -# Returns 1 if (a < b) -if-lt = $(shell [ $(1) -lt $(2) ] && echo 1) - -ifeq ($(CONFIG_GCOV_FORMAT_3_4),y) - cc-ver := 0304 -else ifeq ($(CONFIG_GCOV_FORMAT_4_7),y) - cc-ver := 0407 -else -# Use cc-version if available, otherwise set 0 -# -# scripts/Kbuild.include, which contains cc-version function, is not included -# during make clean "make -f scripts/Makefile.clean obj=kernel/gcov" -# Meaning cc-ver is empty causing if-lt test to fail with -# "/bin/sh: line 0: [: -lt: unary operator expected" error mesage. -# This has no affect on the clean phase, but the error message could be -# confusing/annoying. So this dummy workaround sets cc-ver to zero if cc-version -# is not available. We can probably move if-lt to Kbuild.include, so it's also -# not defined during clean or to include Kbuild.include in -# scripts/Makefile.clean. But the following workaround seems least invasive. - cc-ver := $(if $(call cc-version),$(call cc-version),0) -endif - -obj-$(CONFIG_GCOV_KERNEL) := base.o fs.o - -ifeq ($(call if-lt, $(cc-ver), 0407),1) - obj-$(CONFIG_GCOV_KERNEL) += gcc_3_4.o -else - obj-$(CONFIG_GCOV_KERNEL) += gcc_4_7.o -endif +obj-y := base.o fs.o +obj-$(CONFIG_GCOV_FORMAT_3_4) += gcc_3_4.o +obj-$(CONFIG_GCOV_FORMAT_4_7) += gcc_4_7.o +obj-$(CONFIG_GCOV_FORMAT_AUTODETECT) += $(call cc-ifversion, -lt, 0407, \ + gcc_3_4.o, gcc_4_7.o) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 80692373abd6..886d09e691d5 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -243,6 +243,9 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) return -EINVAL; desc->affinity_hint = m; irq_put_desc_unlock(desc, flags); + /* set the initial affinity to prevent every interrupt being on CPU0 */ + if (m) + __irq_set_affinity(irq, m, false); return 0; } EXPORT_SYMBOL_GPL(irq_set_affinity_hint); @@ -1471,8 +1474,13 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, * otherwise we'll have trouble later trying to figure out * which interrupt is which (messes up the interrupt freeing * logic etc). + * + * Also IRQF_COND_SUSPEND only makes sense for shared interrupts and + * it cannot be set along with IRQF_NO_SUSPEND. */ - if ((irqflags & IRQF_SHARED) && !dev_id) + if (((irqflags & IRQF_SHARED) && !dev_id) || + (!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) || + ((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND))) return -EINVAL; desc = irq_to_desc(irq); diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c index 3ca532592704..5204a6d1b985 100644 --- a/kernel/irq/pm.c +++ b/kernel/irq/pm.c @@ -43,9 +43,12 @@ void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) if (action->flags & IRQF_NO_SUSPEND) desc->no_suspend_depth++; + else if (action->flags & IRQF_COND_SUSPEND) + desc->cond_suspend_depth++; WARN_ON_ONCE(desc->no_suspend_depth && - desc->no_suspend_depth != desc->nr_actions); + (desc->no_suspend_depth + + desc->cond_suspend_depth) != desc->nr_actions); } /* @@ -61,6 +64,8 @@ void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) if (action->flags & IRQF_NO_SUSPEND) desc->no_suspend_depth--; + else if (action->flags & IRQF_COND_SUSPEND) + desc->cond_suspend_depth--; } static bool suspend_device_irq(struct irq_desc *desc, int irq) diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 9dc9bfd8a678..df2f4642d1e7 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -46,10 +46,9 @@ static int show_irq_affinity(int type, struct seq_file *m, void *v) mask = desc->pending_mask; #endif if (type) - seq_cpumask_list(m, mask); + seq_printf(m, "%*pbl\n", cpumask_pr_args(mask)); else - seq_cpumask(m, mask); - seq_putc(m, '\n'); + seq_printf(m, "%*pb\n", cpumask_pr_args(mask)); return 0; } @@ -67,8 +66,7 @@ static int irq_affinity_hint_proc_show(struct seq_file *m, void *v) cpumask_copy(mask, desc->affinity_hint); raw_spin_unlock_irqrestore(&desc->lock, flags); - seq_cpumask(m, mask); - seq_putc(m, '\n'); + seq_printf(m, "%*pb\n", cpumask_pr_args(mask)); free_cpumask_var(mask); return 0; @@ -186,8 +184,7 @@ static const struct file_operations irq_affinity_list_proc_fops = { static int default_affinity_show(struct seq_file *m, void *v) { - seq_cpumask(m, irq_default_affinity); - seq_putc(m, '\n'); + seq_printf(m, "%*pb\n", cpumask_pr_args(irq_default_affinity)); return 0; } diff --git a/kernel/kexec.c b/kernel/kexec.c index 9a8a01abbaed..38c25b1f2fd5 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -444,7 +444,7 @@ arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, } /* - * Free up memory used by kernel, initrd, and comand line. This is temporary + * Free up memory used by kernel, initrd, and command line. This is temporary * memory allocation which is not needed any more after these buffers have * been loaded into separate segments and have been copied elsewhere. */ @@ -856,8 +856,6 @@ static int kimage_set_destination(struct kimage *image, destination &= PAGE_MASK; result = kimage_add_entry(image, destination | IND_DESTINATION); - if (result == 0) - image->destination = destination; return result; } @@ -869,8 +867,6 @@ static int kimage_add_page(struct kimage *image, unsigned long page) page &= PAGE_MASK; result = kimage_add_entry(image, page | IND_SOURCE); - if (result == 0) - image->destination += PAGE_SIZE; return result; } @@ -1288,19 +1284,22 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, if (nr_segments > 0) { unsigned long i; - /* Loading another kernel to reboot into */ - if ((flags & KEXEC_ON_CRASH) == 0) - result = kimage_alloc_init(&image, entry, nr_segments, - segments, flags); - /* Loading another kernel to switch to if this one crashes */ - else if (flags & KEXEC_ON_CRASH) { - /* Free any current crash dump kernel before + if (flags & KEXEC_ON_CRASH) { + /* + * Loading another kernel to switch to if this one + * crashes. Free any current crash dump kernel before * we corrupt it. */ + kimage_free(xchg(&kexec_crash_image, NULL)); result = kimage_alloc_init(&image, entry, nr_segments, segments, flags); crash_map_reserved_pages(); + } else { + /* Loading another kernel to reboot into. */ + + result = kimage_alloc_init(&image, entry, nr_segments, + segments, flags); } if (result) goto out; @@ -2512,7 +2511,7 @@ static int kexec_apply_relocations(struct kimage *image) continue; /* - * Respective archicture needs to provide support for applying + * Respective architecture needs to provide support for applying * relocations of type SHT_RELA/SHT_REL. */ if (sechdrs[i].sh_type == SHT_RELA) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ee619929cf90..c90e417bb963 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -717,7 +717,7 @@ static void prepare_optimized_kprobe(struct kprobe *p) struct optimized_kprobe *op; op = container_of(p, struct optimized_kprobe, kp); - arch_prepare_optimized_kprobe(op); + arch_prepare_optimized_kprobe(op, p); } /* Allocate new optimized_kprobe and try to prepare optimized instructions */ @@ -731,7 +731,7 @@ static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) INIT_LIST_HEAD(&op->list); op->kp.addr = p->addr; - arch_prepare_optimized_kprobe(op); + arch_prepare_optimized_kprobe(op, p); return &op->kp; } @@ -869,7 +869,8 @@ static void __disarm_kprobe(struct kprobe *p, bool reopt) { struct kprobe *_p; - unoptimize_kprobe(p, false); /* Try to unoptimize */ + /* Try to unoptimize */ + unoptimize_kprobe(p, kprobes_all_disarmed); if (!kprobe_queued(p)) { arch_disarm_kprobe(p); @@ -1571,7 +1572,13 @@ static struct kprobe *__disable_kprobe(struct kprobe *p) /* Try to disarm and disable this/parent probe */ if (p == orig_p || aggr_kprobe_disabled(orig_p)) { - disarm_kprobe(orig_p, true); + /* + * If kprobes_all_disarmed is set, orig_p + * should have already been disarmed, so + * skip unneed disarming process. + */ + if (!kprobes_all_disarmed) + disarm_kprobe(orig_p, true); orig_p->flags |= KPROBE_FLAG_DISABLED; } } @@ -2320,6 +2327,12 @@ static void arm_all_kprobes(void) if (!kprobes_all_disarmed) goto already_enabled; + /* + * optimize_kprobe() called by arm_kprobe() checks + * kprobes_all_disarmed, so set kprobes_all_disarmed before + * arm_kprobe. + */ + kprobes_all_disarmed = false; /* Arming kprobes doesn't optimize kprobe itself */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; @@ -2328,7 +2341,6 @@ static void arm_all_kprobes(void) arm_kprobe(p); } - kprobes_all_disarmed = false; printk(KERN_INFO "Kprobes globally enabled\n"); already_enabled: diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 4ca8eb151975..de7a416cca2a 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -2,10 +2,10 @@ obj-y += mutex.o semaphore.o rwsem.o ifdef CONFIG_FUNCTION_TRACER -CFLAGS_REMOVE_lockdep.o = -pg -CFLAGS_REMOVE_lockdep_proc.o = -pg -CFLAGS_REMOVE_mutex-debug.o = -pg -CFLAGS_REMOVE_rtmutex-debug.o = -pg +CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_lockdep_proc.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_mutex-debug.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE) endif obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 3059bc2f022d..6357265a31ad 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1193,7 +1193,9 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, ret = __rt_mutex_slowlock(lock, state, timeout, &waiter); if (unlikely(ret)) { - remove_waiter(lock, &waiter); + __set_current_state(TASK_RUNNING); + if (rt_mutex_has_waiters(lock)) + remove_waiter(lock, &waiter); rt_mutex_handle_deadlock(ret, chwalk, &waiter); } diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index 4b082b5cac9e..db3ccb1dd614 100644 --- a/kernel/locking/spinlock.c +++ b/kernel/locking/spinlock.c @@ -363,6 +363,14 @@ void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) } EXPORT_SYMBOL(_raw_spin_lock_nested); +void __lockfunc _raw_spin_lock_bh_nested(raw_spinlock_t *lock, int subclass) +{ + __local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET); + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock); +} +EXPORT_SYMBOL(_raw_spin_lock_bh_nested); + unsigned long __lockfunc _raw_spin_lock_irqsave_nested(raw_spinlock_t *lock, int subclass) { diff --git a/kernel/module.c b/kernel/module.c index d856e96a3cce..b34813f725e9 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -56,6 +56,7 @@ #include <linux/async.h> #include <linux/percpu.h> #include <linux/kmemleak.h> +#include <linux/kasan.h> #include <linux/jump_label.h> #include <linux/pfn.h> #include <linux/bsearch.h> @@ -1225,6 +1226,12 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod, const unsigned long *crc; int err; + /* + * The module_mutex should not be a heavily contended lock; + * if we get the occasional sleep here, we'll go an extra iteration + * in the wait_event_interruptible(), which is harmless. + */ + sched_annotate_sleep(); mutex_lock(&module_mutex); sym = find_symbol(name, &owner, &crc, !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true); @@ -1807,6 +1814,7 @@ static void unset_module_init_ro_nx(struct module *mod) { } void __weak module_memfree(void *module_region) { vfree(module_region); + kasan_module_free(module_region); } void __weak module_arch_cleanup(struct module *mod) @@ -2978,6 +2986,12 @@ static bool finished_loading(const char *name) struct module *mod; bool ret; + /* + * The module_mutex should not be a heavily contended lock; + * if we get the occasional sleep here, we'll go an extra iteration + * in the wait_event_interruptible(), which is harmless. + */ + sched_annotate_sleep(); mutex_lock(&module_mutex); mod = find_module_all(name, strlen(name), true); ret = !mod || mod->state == MODULE_STATE_LIVE @@ -3011,8 +3025,13 @@ static void do_free_init(struct rcu_head *head) kfree(m); } -/* This is where the real work happens */ -static int do_init_module(struct module *mod) +/* + * This is where the real work happens. + * + * Keep it uninlined to provide a reliable breakpoint target, e.g. for the gdb + * helper command 'lx-symbols'. + */ +static noinline int do_init_module(struct module *mod) { int ret = 0; struct mod_initfree *freeinit; @@ -3120,32 +3139,6 @@ static int may_init_module(void) } /* - * Can't use wait_event_interruptible() because our condition - * 'finished_loading()' contains a blocking primitive itself (mutex_lock). - */ -static int wait_finished_loading(struct module *mod) -{ - DEFINE_WAIT_FUNC(wait, woken_wake_function); - int ret = 0; - - add_wait_queue(&module_wq, &wait); - for (;;) { - if (finished_loading(mod->name)) - break; - - if (signal_pending(current)) { - ret = -ERESTARTSYS; - break; - } - - wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); - } - remove_wait_queue(&module_wq, &wait); - - return ret; -} - -/* * We try to place it in the list now to make sure it's unique before * we dedicate too many resources. In particular, temporary percpu * memory exhaustion. @@ -3165,8 +3158,8 @@ again: || old->state == MODULE_STATE_UNFORMED) { /* Wait in case it fails to load. */ mutex_unlock(&module_mutex); - - err = wait_finished_loading(mod); + err = wait_event_interruptible(module_wq, + finished_loading(mod->name)); if (err) goto out_unlocked; goto again; @@ -3265,7 +3258,7 @@ static int load_module(struct load_info *info, const char __user *uargs, mod->sig_ok = info->sig_ok; if (!mod->sig_ok) { pr_notice_once("%s: module verification failed: signature " - "and/or required key missing - tainting " + "and/or required key missing - tainting " "kernel\n", mod->name); add_taint_module(mod, TAINT_UNSIGNED_MODULE, LOCKDEP_STILL_OK); } @@ -3356,6 +3349,9 @@ static int load_module(struct load_info *info, const char __user *uargs, module_bug_cleanup(mod); mutex_unlock(&module_mutex); + /* Free lock-classes: */ + lockdep_free_key_range(mod->module_core, mod->core_size); + /* we can't deallocate the module until we clear memory protection */ unset_module_init_ro_nx(mod); unset_module_core_ro_nx(mod); diff --git a/kernel/padata.c b/kernel/padata.c index 161402f0b517..b38bea9c466a 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -917,15 +917,10 @@ static ssize_t show_cpumask(struct padata_instance *pinst, else cpumask = pinst->cpumask.pcpu; - len = bitmap_scnprintf(buf, PAGE_SIZE, cpumask_bits(cpumask), - nr_cpu_ids); - if (PAGE_SIZE - len < 2) - len = -EINVAL; - else - len += sprintf(buf + len, "\n"); - + len = snprintf(buf, PAGE_SIZE, "%*pb\n", + nr_cpu_ids, cpumask_bits(cpumask)); mutex_unlock(&pinst->lock); - return len; + return len < PAGE_SIZE ? len : -EINVAL; } static ssize_t store_cpumask(struct padata_instance *pinst, diff --git a/kernel/power/process.c b/kernel/power/process.c index 5a6ec8678b9a..564f786df470 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -84,8 +84,8 @@ static int try_to_freeze_tasks(bool user_only) elapsed_msecs = elapsed_msecs64; if (todo) { - printk("\n"); - printk(KERN_ERR "Freezing of tasks %s after %d.%03d seconds " + pr_cont("\n"); + pr_err("Freezing of tasks %s after %d.%03d seconds " "(%d tasks refusing to freeze, wq_busy=%d):\n", wakeup ? "aborted" : "failed", elapsed_msecs / 1000, elapsed_msecs % 1000, @@ -101,37 +101,13 @@ static int try_to_freeze_tasks(bool user_only) read_unlock(&tasklist_lock); } } else { - printk("(elapsed %d.%03d seconds) ", elapsed_msecs / 1000, + pr_cont("(elapsed %d.%03d seconds) ", elapsed_msecs / 1000, elapsed_msecs % 1000); } return todo ? -EBUSY : 0; } -static bool __check_frozen_processes(void) -{ - struct task_struct *g, *p; - - for_each_process_thread(g, p) - if (p != current && !freezer_should_skip(p) && !frozen(p)) - return false; - - return true; -} - -/* - * Returns true if all freezable tasks (except for current) are frozen already - */ -static bool check_frozen_processes(void) -{ - bool ret; - - read_lock(&tasklist_lock); - ret = __check_frozen_processes(); - read_unlock(&tasklist_lock); - return ret; -} - /** * freeze_processes - Signal user space processes to enter the refrigerator. * The current thread will not be frozen. The same process that calls @@ -142,7 +118,6 @@ static bool check_frozen_processes(void) int freeze_processes(void) { int error; - int oom_kills_saved; error = __usermodehelper_disable(UMH_FREEZING); if (error) @@ -155,31 +130,24 @@ int freeze_processes(void) atomic_inc(&system_freezing_cnt); pm_wakeup_clear(); - printk("Freezing user space processes ... "); + pr_info("Freezing user space processes ... "); pm_freezing = true; - oom_kills_saved = oom_kills_count(); error = try_to_freeze_tasks(true); if (!error) { __usermodehelper_set_disable_depth(UMH_DISABLED); - oom_killer_disable(); - - /* - * There might have been an OOM kill while we were - * freezing tasks and the killed task might be still - * on the way out so we have to double check for race. - */ - if (oom_kills_count() != oom_kills_saved && - !check_frozen_processes()) { - __usermodehelper_set_disable_depth(UMH_ENABLED); - printk("OOM in progress."); - error = -EBUSY; - } else { - printk("done."); - } + pr_cont("done."); } - printk("\n"); + pr_cont("\n"); BUG_ON(in_atomic()); + /* + * Now that the whole userspace is frozen we need to disbale + * the OOM killer to disallow any further interference with + * killable tasks. + */ + if (!error && !oom_killer_disable()) + error = -EBUSY; + if (error) thaw_processes(); return error; @@ -197,13 +165,14 @@ int freeze_kernel_threads(void) { int error; - printk("Freezing remaining freezable tasks ... "); + pr_info("Freezing remaining freezable tasks ... "); + pm_nosig_freezing = true; error = try_to_freeze_tasks(false); if (!error) - printk("done."); + pr_cont("done."); - printk("\n"); + pr_cont("\n"); BUG_ON(in_atomic()); if (error) @@ -224,7 +193,7 @@ void thaw_processes(void) oom_killer_enable(); - printk("Restarting tasks ... "); + pr_info("Restarting tasks ... "); __usermodehelper_set_disable_depth(UMH_FREEZING); thaw_workqueues(); @@ -243,7 +212,7 @@ void thaw_processes(void) usermodehelper_enable(); schedule(); - printk("done.\n"); + pr_cont("done.\n"); trace_suspend_resume(TPS("thaw_processes"), 0, false); } @@ -252,7 +221,7 @@ void thaw_kernel_threads(void) struct task_struct *g, *p; pm_nosig_freezing = false; - printk("Restarting kernel threads ... "); + pr_info("Restarting kernel threads ... "); thaw_workqueues(); @@ -264,5 +233,5 @@ void thaw_kernel_threads(void) read_unlock(&tasklist_lock); schedule(); - printk("done.\n"); + pr_cont("done.\n"); } diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index c347e3ce3a55..b7d6b3a721b1 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -37,7 +37,9 @@ const char *pm_states[PM_SUSPEND_MAX]; static const struct platform_suspend_ops *suspend_ops; static const struct platform_freeze_ops *freeze_ops; static DECLARE_WAIT_QUEUE_HEAD(suspend_freeze_wait_head); -static bool suspend_freeze_wake; + +enum freeze_state __read_mostly suspend_freeze_state; +static DEFINE_SPINLOCK(suspend_freeze_lock); void freeze_set_ops(const struct platform_freeze_ops *ops) { @@ -48,22 +50,49 @@ void freeze_set_ops(const struct platform_freeze_ops *ops) static void freeze_begin(void) { - suspend_freeze_wake = false; + suspend_freeze_state = FREEZE_STATE_NONE; } static void freeze_enter(void) { - cpuidle_use_deepest_state(true); + spin_lock_irq(&suspend_freeze_lock); + if (pm_wakeup_pending()) + goto out; + + suspend_freeze_state = FREEZE_STATE_ENTER; + spin_unlock_irq(&suspend_freeze_lock); + + get_online_cpus(); cpuidle_resume(); - wait_event(suspend_freeze_wait_head, suspend_freeze_wake); + + /* Push all the CPUs into the idle loop. */ + wake_up_all_idle_cpus(); + pr_debug("PM: suspend-to-idle\n"); + /* Make the current CPU wait so it can enter the idle loop too. */ + wait_event(suspend_freeze_wait_head, + suspend_freeze_state == FREEZE_STATE_WAKE); + pr_debug("PM: resume from suspend-to-idle\n"); + cpuidle_pause(); - cpuidle_use_deepest_state(false); + put_online_cpus(); + + spin_lock_irq(&suspend_freeze_lock); + + out: + suspend_freeze_state = FREEZE_STATE_NONE; + spin_unlock_irq(&suspend_freeze_lock); } void freeze_wake(void) { - suspend_freeze_wake = true; - wake_up(&suspend_freeze_wait_head); + unsigned long flags; + + spin_lock_irqsave(&suspend_freeze_lock, flags); + if (suspend_freeze_state > FREEZE_STATE_NONE) { + suspend_freeze_state = FREEZE_STATE_WAKE; + wake_up(&suspend_freeze_wait_head); + } + spin_unlock_irqrestore(&suspend_freeze_lock, flags); } EXPORT_SYMBOL_GPL(freeze_wake); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 02d6b6d28796..01cfd69c54c6 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -935,8 +935,8 @@ static int __init ignore_loglevel_setup(char *str) early_param("ignore_loglevel", ignore_loglevel_setup); module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR); -MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting, to" - "print all kernel messages to the console."); +MODULE_PARM_DESC(ignore_loglevel, + "ignore loglevel setting (prints all kernel messages to the console)"); #ifdef CONFIG_BOOT_PRINTK_DELAY @@ -1419,16 +1419,16 @@ static void call_console_drivers(int level, const char *text, size_t len) } /* - * Zap console related locks when oopsing. Only zap at most once - * every 10 seconds, to leave time for slow consoles to print a - * full oops. + * Zap console related locks when oopsing. + * To leave time for slow consoles to print a full oops, + * only zap at most once every 30 seconds. */ static void zap_locks(void) { static unsigned long oops_timestamp; if (time_after_eq(jiffies, oops_timestamp) && - !time_after(jiffies, oops_timestamp + 30 * HZ)) + !time_after(jiffies, oops_timestamp + 30 * HZ)) return; oops_timestamp = jiffies; @@ -1811,7 +1811,7 @@ int vprintk_default(const char *fmt, va_list args) #ifdef CONFIG_KGDB_KDB if (unlikely(kdb_trap_printk)) { - r = vkdb_printf(fmt, args); + r = vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); return r; } #endif diff --git a/kernel/profile.c b/kernel/profile.c index 54bf5ba26420..a7bcd28d6e9f 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -422,8 +422,7 @@ void profile_tick(int type) static int prof_cpu_mask_proc_show(struct seq_file *m, void *v) { - seq_cpumask(m, prof_cpu_mask); - seq_putc(m, '\n'); + seq_printf(m, "%*pb\n", cpumask_pr_args(prof_cpu_mask)); return 0; } diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 1eb9d90c3af9..227fec36b12a 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -1077,7 +1077,6 @@ int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, } #if defined CONFIG_COMPAT -#include <linux/compat.h> int compat_ptrace_request(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 2e850a51bb8f..0a571e9a0f1d 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -49,7 +49,6 @@ DEFINE_PER_CPU(char, rcu_cpu_has_work); static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */ static bool have_rcu_nocb_mask; /* Was rcu_nocb_mask allocated? */ static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ -static char __initdata nocb_buf[NR_CPUS * 5]; #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ /* @@ -327,6 +326,7 @@ void rcu_read_unlock_special(struct task_struct *t) special = t->rcu_read_unlock_special; if (special.b.need_qs) { rcu_preempt_qs(); + t->rcu_read_unlock_special.b.need_qs = false; if (!t->rcu_read_unlock_special.s) { local_irq_restore(flags); return; @@ -2386,8 +2386,8 @@ void __init rcu_init_nohz(void) cpumask_and(rcu_nocb_mask, cpu_possible_mask, rcu_nocb_mask); } - cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask); - pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf); + pr_info("\tOffload RCU callbacks from CPUs: %*pbl.\n", + cpumask_pr_args(rcu_nocb_mask)); if (rcu_nocb_poll) pr_info("\tPoll for callbacks from no-CBs CPUs.\n"); diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index ab32b7b0db5c..46be87024875 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -1,5 +1,5 @@ ifdef CONFIG_FUNCTION_TRACER -CFLAGS_REMOVE_clock.o = -pg +CFLAGS_REMOVE_clock.o = $(CC_FLAGS_FTRACE) endif ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c index 8a2e230fb86a..eae160dd669d 100644 --- a/kernel/sched/auto_group.c +++ b/kernel/sched/auto_group.c @@ -87,8 +87,7 @@ static inline struct autogroup *autogroup_create(void) * so we don't have to move tasks around upon policy change, * or flail around trying to allocate bandwidth on the fly. * A bandwidth exception in __sched_setscheduler() allows - * the policy change to proceed. Thereafter, task_group() - * returns &root_task_group, so zero bandwidth is required. + * the policy change to proceed. */ free_rt_sched_group(tg); tg->rt_se = root_task_group.rt_se; @@ -115,9 +114,6 @@ bool task_wants_autogroup(struct task_struct *p, struct task_group *tg) if (tg != &root_task_group) return false; - if (p->sched_class != &fair_sched_class) - return false; - /* * We can only assume the task group can't go away on us if * autogroup_move_group() can see us on ->thread_group list. diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index c27e4f8f4879..c0a205101c23 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -420,3 +420,16 @@ u64 local_clock(void) EXPORT_SYMBOL_GPL(cpu_clock); EXPORT_SYMBOL_GPL(local_clock); + +/* + * Running clock - returns the time that has elapsed while a guest has been + * running. + * On a guest this value should be local_clock minus the time the guest was + * suspended by the hypervisor (for any reason). + * On bare metal this function should return the same as local_clock. + * Architectures and sub-architectures can override this. + */ +u64 __weak running_clock(void) +{ + return local_clock(); +} diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index 7052d3fd4e7b..8d0f35debf35 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -274,7 +274,7 @@ bool try_wait_for_completion(struct completion *x) * first without taking the lock so we can * return early in the blocking case. */ - if (!ACCESS_ONCE(x->done)) + if (!READ_ONCE(x->done)) return 0; spin_lock_irqsave(&x->wait.lock, flags); @@ -297,6 +297,21 @@ EXPORT_SYMBOL(try_wait_for_completion); */ bool completion_done(struct completion *x) { - return !!ACCESS_ONCE(x->done); + if (!READ_ONCE(x->done)) + return false; + + /* + * If ->done, we need to wait for complete() to release ->wait.lock + * otherwise we can end up freeing the completion before complete() + * is done referencing it. + * + * The RMB pairs with complete()'s RELEASE of ->wait.lock and orders + * the loads of ->done and ->wait.lock such that we cannot observe + * the lock before complete() acquires it while observing the ->done + * after it's acquired the lock. + */ + smp_rmb(); + spin_unlock_wait(&x->wait.lock); + return true; } EXPORT_SYMBOL(completion_done); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1f37fe7f77a4..f0f831e8a345 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -307,66 +307,6 @@ __read_mostly int scheduler_running; int sysctl_sched_rt_runtime = 950000; /* - * __task_rq_lock - lock the rq @p resides on. - */ -static inline struct rq *__task_rq_lock(struct task_struct *p) - __acquires(rq->lock) -{ - struct rq *rq; - - lockdep_assert_held(&p->pi_lock); - - for (;;) { - rq = task_rq(p); - raw_spin_lock(&rq->lock); - if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) - return rq; - raw_spin_unlock(&rq->lock); - - while (unlikely(task_on_rq_migrating(p))) - cpu_relax(); - } -} - -/* - * task_rq_lock - lock p->pi_lock and lock the rq @p resides on. - */ -static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) - __acquires(p->pi_lock) - __acquires(rq->lock) -{ - struct rq *rq; - - for (;;) { - raw_spin_lock_irqsave(&p->pi_lock, *flags); - rq = task_rq(p); - raw_spin_lock(&rq->lock); - if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) - return rq; - raw_spin_unlock(&rq->lock); - raw_spin_unlock_irqrestore(&p->pi_lock, *flags); - - while (unlikely(task_on_rq_migrating(p))) - cpu_relax(); - } -} - -static void __task_rq_unlock(struct rq *rq) - __releases(rq->lock) -{ - raw_spin_unlock(&rq->lock); -} - -static inline void -task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags) - __releases(rq->lock) - __releases(p->pi_lock) -{ - raw_spin_unlock(&rq->lock); - raw_spin_unlock_irqrestore(&p->pi_lock, *flags); -} - -/* * this_rq_lock - lock this runqueue and disable interrupts. */ static struct rq *this_rq_lock(void) @@ -2899,7 +2839,7 @@ void __sched schedule_preempt_disabled(void) preempt_disable(); } -static void preempt_schedule_common(void) +static void __sched notrace preempt_schedule_common(void) { do { __preempt_count_add(PREEMPT_ACTIVE); @@ -4418,36 +4358,29 @@ EXPORT_SYMBOL_GPL(yield_to); * This task is about to go to sleep on IO. Increment rq->nr_iowait so * that process accounting knows that this is a task in IO wait state. */ -void __sched io_schedule(void) -{ - struct rq *rq = raw_rq(); - - delayacct_blkio_start(); - atomic_inc(&rq->nr_iowait); - blk_flush_plug(current); - current->in_iowait = 1; - schedule(); - current->in_iowait = 0; - atomic_dec(&rq->nr_iowait); - delayacct_blkio_end(); -} -EXPORT_SYMBOL(io_schedule); - long __sched io_schedule_timeout(long timeout) { - struct rq *rq = raw_rq(); + int old_iowait = current->in_iowait; + struct rq *rq; long ret; + current->in_iowait = 1; + if (old_iowait) + blk_schedule_flush_plug(current); + else + blk_flush_plug(current); + delayacct_blkio_start(); + rq = raw_rq(); atomic_inc(&rq->nr_iowait); - blk_flush_plug(current); - current->in_iowait = 1; ret = schedule_timeout(timeout); - current->in_iowait = 0; + current->in_iowait = old_iowait; atomic_dec(&rq->nr_iowait); delayacct_blkio_end(); + return ret; } +EXPORT_SYMBOL(io_schedule_timeout); /** * sys_sched_get_priority_max - return maximum RT priority. @@ -5462,9 +5395,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, struct cpumask *groupmask) { struct sched_group *group = sd->groups; - char str[256]; - cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd)); cpumask_clear(groupmask); printk(KERN_DEBUG "%*s domain %d: ", level, "", level); @@ -5477,7 +5408,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, return -1; } - printk(KERN_CONT "span %s level %s\n", str, sd->name); + printk(KERN_CONT "span %*pbl level %s\n", + cpumask_pr_args(sched_domain_span(sd)), sd->name); if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { printk(KERN_ERR "ERROR: domain->span does not contain " @@ -5522,9 +5454,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, cpumask_or(groupmask, groupmask, sched_group_cpus(group)); - cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); - - printk(KERN_CONT " %s", str); + printk(KERN_CONT " %*pbl", + cpumask_pr_args(sched_group_cpus(group))); if (group->sgc->capacity != SCHED_CAPACITY_SCALE) { printk(KERN_CONT " (cpu_capacity = %d)", group->sgc->capacity); @@ -7644,6 +7575,12 @@ static inline int tg_has_rt_tasks(struct task_group *tg) { struct task_struct *g, *p; + /* + * Autogroups do not have RT tasks; see autogroup_create(). + */ + if (task_group_is_autogroup(tg)) + return 0; + for_each_process_thread(g, p) { if (rt_task(p) && task_group(p) == tg) return 1; @@ -7736,6 +7673,17 @@ static int tg_set_rt_bandwidth(struct task_group *tg, { int i, err = 0; + /* + * Disallowing the root group RT runtime is BAD, it would disallow the + * kernel creating (and or operating) RT threads. + */ + if (tg == &root_task_group && rt_runtime == 0) + return -EINVAL; + + /* No period doesn't make any sense. */ + if (rt_period == 0) + return -EINVAL; + mutex_lock(&rt_constraints_mutex); read_lock(&tasklist_lock); err = __rt_schedulable(tg, rt_period, rt_runtime); @@ -7792,9 +7740,6 @@ static int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) rt_period = (u64)rt_period_us * NSEC_PER_USEC; rt_runtime = tg->rt_bandwidth.rt_runtime; - if (rt_period == 0) - return -EINVAL; - return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index a027799ae130..3fa8fa6d9403 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -511,16 +511,10 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) struct sched_dl_entity, dl_timer); struct task_struct *p = dl_task_of(dl_se); + unsigned long flags; struct rq *rq; -again: - rq = task_rq(p); - raw_spin_lock(&rq->lock); - if (rq != task_rq(p)) { - /* Task was moved, retrying. */ - raw_spin_unlock(&rq->lock); - goto again; - } + rq = task_rq_lock(current, &flags); /* * We need to take care of several possible races here: @@ -541,6 +535,26 @@ again: sched_clock_tick(); update_rq_clock(rq); + + /* + * If the throttle happened during sched-out; like: + * + * schedule() + * deactivate_task() + * dequeue_task_dl() + * update_curr_dl() + * start_dl_timer() + * __dequeue_task_dl() + * prev->on_rq = 0; + * + * We can be both throttled and !queued. Replenish the counter + * but do not enqueue -- wait for our wakeup to do that. + */ + if (!task_on_rq_queued(p)) { + replenish_dl_entity(dl_se, dl_se); + goto unlock; + } + enqueue_task_dl(rq, p, ENQUEUE_REPLENISH); if (dl_task(rq->curr)) check_preempt_curr_dl(rq, p, 0); @@ -555,7 +569,7 @@ again: push_dl_task(rq); #endif unlock: - raw_spin_unlock(&rq->lock); + task_rq_unlock(rq, current, &flags); return HRTIMER_NORESTART; } @@ -898,6 +912,7 @@ static void yield_task_dl(struct rq *rq) rq->curr->dl.dl_yielded = 1; p->dl.runtime = 0; } + update_rq_clock(rq); update_curr_dl(rq); } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index aaf1c1d5cf5d..80014a178342 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -7,6 +7,7 @@ #include <linux/tick.h> #include <linux/mm.h> #include <linux/stackprotector.h> +#include <linux/suspend.h> #include <asm/tlb.h> @@ -81,6 +82,7 @@ static void cpuidle_idle_call(void) struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); int next_state, entered_state; unsigned int broadcast; + bool reflect; /* * Check if the idle task must be rescheduled. If it is the @@ -104,25 +106,37 @@ static void cpuidle_idle_call(void) */ rcu_idle_enter(); + if (cpuidle_not_available(drv, dev)) + goto use_default; + /* - * Ask the cpuidle framework to choose a convenient idle state. - * Fall back to the default arch idle method on errors. + * Suspend-to-idle ("freeze") is a system state in which all user space + * has been frozen, all I/O devices have been suspended and the only + * activity happens here and in iterrupts (if any). In that case bypass + * the cpuidle governor and go stratight for the deepest idle state + * available. Possibly also suspend the local tick and the entire + * timekeeping to prevent timer interrupts from kicking us out of idle + * until a proper wakeup interrupt happens. */ - next_state = cpuidle_select(drv, dev); - if (next_state < 0) { -use_default: - /* - * We can't use the cpuidle framework, let's use the default - * idle routine. - */ - if (current_clr_polling_and_test()) + if (idle_should_freeze()) { + entered_state = cpuidle_enter_freeze(drv, dev); + if (entered_state >= 0) { local_irq_enable(); - else - arch_cpu_idle(); + goto exit_idle; + } - goto exit_idle; + reflect = false; + next_state = cpuidle_find_deepest_state(drv, dev); + } else { + reflect = true; + /* + * Ask the cpuidle framework to choose a convenient idle state. + */ + next_state = cpuidle_select(drv, dev); } - + /* Fall back to the default arch idle method on errors. */ + if (next_state < 0) + goto use_default; /* * The idle task must be scheduled, it is pointless to @@ -167,7 +181,8 @@ use_default: /* * Give the governor an opportunity to reflect on the outcome */ - cpuidle_reflect(dev, entered_state); + if (reflect) + cpuidle_reflect(dev, entered_state); exit_idle: __current_set_polling(); @@ -180,6 +195,19 @@ exit_idle: rcu_idle_exit(); start_critical_timings(); + return; + +use_default: + /* + * We can't use the cpuidle framework, let's use the default + * idle routine. + */ + if (current_clr_polling_and_test()) + local_irq_enable(); + else + arch_cpu_idle(); + + goto exit_idle; } /* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 0870db23d79c..dc0f435a2779 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1380,6 +1380,82 @@ static inline void sched_avg_update(struct rq *rq) { } extern void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period); +/* + * __task_rq_lock - lock the rq @p resides on. + */ +static inline struct rq *__task_rq_lock(struct task_struct *p) + __acquires(rq->lock) +{ + struct rq *rq; + + lockdep_assert_held(&p->pi_lock); + + for (;;) { + rq = task_rq(p); + raw_spin_lock(&rq->lock); + if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) + return rq; + raw_spin_unlock(&rq->lock); + + while (unlikely(task_on_rq_migrating(p))) + cpu_relax(); + } +} + +/* + * task_rq_lock - lock p->pi_lock and lock the rq @p resides on. + */ +static inline struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) + __acquires(p->pi_lock) + __acquires(rq->lock) +{ + struct rq *rq; + + for (;;) { + raw_spin_lock_irqsave(&p->pi_lock, *flags); + rq = task_rq(p); + raw_spin_lock(&rq->lock); + /* + * move_queued_task() task_rq_lock() + * + * ACQUIRE (rq->lock) + * [S] ->on_rq = MIGRATING [L] rq = task_rq() + * WMB (__set_task_cpu()) ACQUIRE (rq->lock); + * [S] ->cpu = new_cpu [L] task_rq() + * [L] ->on_rq + * RELEASE (rq->lock) + * + * If we observe the old cpu in task_rq_lock, the acquire of + * the old rq->lock will fully serialize against the stores. + * + * If we observe the new cpu in task_rq_lock, the acquire will + * pair with the WMB to ensure we must then also see migrating. + */ + if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) + return rq; + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, *flags); + + while (unlikely(task_on_rq_migrating(p))) + cpu_relax(); + } +} + +static inline void __task_rq_unlock(struct rq *rq) + __releases(rq->lock) +{ + raw_spin_unlock(&rq->lock); +} + +static inline void +task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags) + __releases(rq->lock) + __releases(p->pi_lock) +{ + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, *flags); +} + #ifdef CONFIG_SMP #ifdef CONFIG_PREEMPT diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index a476bea17fbc..87e2c9f0c33e 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -15,11 +15,6 @@ static int show_schedstat(struct seq_file *seq, void *v) { int cpu; - int mask_len = DIV_ROUND_UP(NR_CPUS, 32) * 9; - char *mask_str = kmalloc(mask_len, GFP_KERNEL); - - if (mask_str == NULL) - return -ENOMEM; if (v == (void *)1) { seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION); @@ -50,9 +45,8 @@ static int show_schedstat(struct seq_file *seq, void *v) for_each_domain(cpu, sd) { enum cpu_idle_type itype; - cpumask_scnprintf(mask_str, mask_len, - sched_domain_span(sd)); - seq_printf(seq, "domain%d %s", dcount++, mask_str); + seq_printf(seq, "domain%d %*pb", dcount++, + cpumask_pr_args(sched_domain_span(sd))); for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES; itype++) { seq_printf(seq, " %u %u %u %u %u %u %u %u", @@ -76,7 +70,6 @@ static int show_schedstat(struct seq_file *seq, void *v) rcu_read_unlock(); #endif } - kfree(mask_str); return 0; } diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 4ef9687ac115..4f44028943e6 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -629,7 +629,9 @@ static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd) switch (action) { case SECCOMP_RET_ERRNO: - /* Set the low-order 16-bits as a errno. */ + /* Set low-order bits as an errno, capped at MAX_ERRNO. */ + if (data > MAX_ERRNO) + data = MAX_ERRNO; syscall_set_return_value(current, task_pt_regs(current), -data, 0); goto skip; diff --git a/kernel/signal.c b/kernel/signal.c index 16a305295256..a390499943e4 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2501,7 +2501,7 @@ EXPORT_SYMBOL(unblock_all_signals); */ SYSCALL_DEFINE0(restart_syscall) { - struct restart_block *restart = ¤t_thread_info()->restart_block; + struct restart_block *restart = ¤t->restart_block; return restart->fn(restart); } @@ -3550,7 +3550,7 @@ SYSCALL_DEFINE2(signal, int, sig, __sighandler_t, handler) SYSCALL_DEFINE0(pause) { while (!signal_pending(current)) { - current->state = TASK_INTERRUPTIBLE; + __set_current_state(TASK_INTERRUPTIBLE); schedule(); } return -ERESTARTNOHAND; @@ -3563,7 +3563,7 @@ int sigsuspend(sigset_t *set) current->saved_sigmask = current->blocked; set_current_blocked(set); - current->state = TASK_INTERRUPTIBLE; + __set_current_state(TASK_INTERRUPTIBLE); schedule(); set_restore_sigmask(); return -ERESTARTNOHAND; diff --git a/kernel/sys.c b/kernel/sys.c index ea9c88109894..a03d9cd23ed7 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -97,6 +97,12 @@ #ifndef MPX_DISABLE_MANAGEMENT # define MPX_DISABLE_MANAGEMENT(a) (-EINVAL) #endif +#ifndef GET_FP_MODE +# define GET_FP_MODE(a) (-EINVAL) +#endif +#ifndef SET_FP_MODE +# define SET_FP_MODE(a,b) (-EINVAL) +#endif /* * this is where the system-wide overflow UID and GID are defined, for @@ -1102,6 +1108,7 @@ DECLARE_RWSEM(uts_sem); /* * Work around broken programs that cannot handle "Linux 3.0". * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40 + * And we map 4.x to 2.6.60+x, so 4.0 would be 2.6.60. */ static int override_release(char __user *release, size_t len) { @@ -1121,7 +1128,7 @@ static int override_release(char __user *release, size_t len) break; rest++; } - v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 40; + v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 60; copy = clamp_t(size_t, len, 1, sizeof(buf)); copy = scnprintf(buf, copy, "2.6.%u%s", v, rest); ret = copy_to_user(release, buf, copy + 1); @@ -2219,6 +2226,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, return -EINVAL; error = MPX_DISABLE_MANAGEMENT(me); break; + case PR_SET_FP_MODE: + error = SET_FP_MODE(me, arg2); + break; + case PR_GET_FP_MODE: + error = GET_FP_MODE(me); + break; default: error = -EINVAL; break; diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 670fff88a961..21f82c29c914 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -111,13 +111,8 @@ static int send_reply(struct sk_buff *skb, struct genl_info *info) { struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); void *reply = genlmsg_data(genlhdr); - int rc; - rc = genlmsg_end(skb, reply); - if (rc < 0) { - nlmsg_free(skb); - return rc; - } + genlmsg_end(skb, reply); return genlmsg_reply(skb, info); } @@ -134,11 +129,7 @@ static void send_cpu_listeners(struct sk_buff *skb, void *reply = genlmsg_data(genlhdr); int rc, delcount = 0; - rc = genlmsg_end(skb, reply); - if (rc < 0) { - nlmsg_free(skb); - return; - } + genlmsg_end(skb, reply); rc = 0; down_read(&listeners->sem); diff --git a/kernel/time/Makefile b/kernel/time/Makefile index f622cf28628a..c09c07817d7a 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -1,6 +1,6 @@ obj-y += time.o timer.o hrtimer.o itimer.o posix-timers.o posix-cpu-timers.o obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o -obj-y += timeconv.o posix-clock.o alarmtimer.o +obj-y += timeconv.o timecounter.o posix-clock.o alarmtimer.o obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index a7077d3ae52f..1b001ed1edb9 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -788,7 +788,7 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, goto out; } - restart = ¤t_thread_info()->restart_block; + restart = ¤t->restart_block; restart->fn = alarm_timer_nsleep_restart; restart->nanosleep.clockid = type; restart->nanosleep.expires = exp.tv64; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index b79f39bda7e1..4892352f0e49 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -34,82 +34,6 @@ #include "tick-internal.h" #include "timekeeping_internal.h" -void timecounter_init(struct timecounter *tc, - const struct cyclecounter *cc, - u64 start_tstamp) -{ - tc->cc = cc; - tc->cycle_last = cc->read(cc); - tc->nsec = start_tstamp; -} -EXPORT_SYMBOL_GPL(timecounter_init); - -/** - * timecounter_read_delta - get nanoseconds since last call of this function - * @tc: Pointer to time counter - * - * When the underlying cycle counter runs over, this will be handled - * correctly as long as it does not run over more than once between - * calls. - * - * The first call to this function for a new time counter initializes - * the time tracking and returns an undefined result. - */ -static u64 timecounter_read_delta(struct timecounter *tc) -{ - cycle_t cycle_now, cycle_delta; - u64 ns_offset; - - /* read cycle counter: */ - cycle_now = tc->cc->read(tc->cc); - - /* calculate the delta since the last timecounter_read_delta(): */ - cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask; - - /* convert to nanoseconds: */ - ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta); - - /* update time stamp of timecounter_read_delta() call: */ - tc->cycle_last = cycle_now; - - return ns_offset; -} - -u64 timecounter_read(struct timecounter *tc) -{ - u64 nsec; - - /* increment time by nanoseconds since last call */ - nsec = timecounter_read_delta(tc); - nsec += tc->nsec; - tc->nsec = nsec; - - return nsec; -} -EXPORT_SYMBOL_GPL(timecounter_read); - -u64 timecounter_cyc2time(struct timecounter *tc, - cycle_t cycle_tstamp) -{ - u64 cycle_delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask; - u64 nsec; - - /* - * Instead of always treating cycle_tstamp as more recent - * than tc->cycle_last, detect when it is too far in the - * future and treat it as old time stamp instead. - */ - if (cycle_delta > tc->cc->mask / 2) { - cycle_delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask; - nsec = tc->nsec - cyclecounter_cyc2ns(tc->cc, cycle_delta); - } else { - nsec = cyclecounter_cyc2ns(tc->cc, cycle_delta) + tc->nsec; - } - - return nsec; -} -EXPORT_SYMBOL_GPL(timecounter_cyc2time); - /** * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks * @mult: pointer to mult variable diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 3f5e183c3d97..bee0c1f78091 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1583,7 +1583,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, goto out; } - restart = ¤t_thread_info()->restart_block; + restart = ¤t->restart_block; restart->fn = hrtimer_nanosleep_restart; restart->nanosleep.clockid = t.timer.base->clockid; restart->nanosleep.rmtp = rmtp; diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 4b585e0fdd22..0f60b08a4f07 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -633,10 +633,14 @@ int ntp_validate_timex(struct timex *txc) if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME))) return -EPERM; - if (txc->modes & ADJ_FREQUENCY) { - if (LONG_MIN / PPM_SCALE > txc->freq) + /* + * Check for potential multiplication overflows that can + * only happen on 64-bit systems: + */ + if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { + if (LLONG_MIN / PPM_SCALE > txc->freq) return -EINVAL; - if (LONG_MAX / PPM_SCALE < txc->freq) + if (LLONG_MAX / PPM_SCALE < txc->freq) return -EINVAL; } diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index a16b67859e2a..0075da74abf0 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -1334,8 +1334,7 @@ static long posix_cpu_nsleep_restart(struct restart_block *restart_block); static int posix_cpu_nsleep(const clockid_t which_clock, int flags, struct timespec *rqtp, struct timespec __user *rmtp) { - struct restart_block *restart_block = - ¤t_thread_info()->restart_block; + struct restart_block *restart_block = ¤t->restart_block; struct itimerspec it; int error; diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 7efeedf53ebd..f7c515595b42 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -394,6 +394,56 @@ void tick_resume(void) } } +static DEFINE_RAW_SPINLOCK(tick_freeze_lock); +static unsigned int tick_freeze_depth; + +/** + * tick_freeze - Suspend the local tick and (possibly) timekeeping. + * + * Check if this is the last online CPU executing the function and if so, + * suspend timekeeping. Otherwise suspend the local tick. + * + * Call with interrupts disabled. Must be balanced with %tick_unfreeze(). + * Interrupts must not be enabled before the subsequent %tick_unfreeze(). + */ +void tick_freeze(void) +{ + raw_spin_lock(&tick_freeze_lock); + + tick_freeze_depth++; + if (tick_freeze_depth == num_online_cpus()) { + timekeeping_suspend(); + } else { + tick_suspend(); + tick_suspend_broadcast(); + } + + raw_spin_unlock(&tick_freeze_lock); +} + +/** + * tick_unfreeze - Resume the local tick and (possibly) timekeeping. + * + * Check if this is the first CPU executing the function and if so, resume + * timekeeping. Otherwise resume the local tick. + * + * Call with interrupts disabled. Must be balanced with %tick_freeze(). + * Interrupts must not be enabled after the preceding %tick_freeze(). + */ +void tick_unfreeze(void) +{ + raw_spin_lock(&tick_freeze_lock); + + if (tick_freeze_depth == num_online_cpus()) + timekeeping_resume(); + else + tick_resume(); + + tick_freeze_depth--; + + raw_spin_unlock(&tick_freeze_lock); +} + /** * tick_init - initialize the tick control */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 1363d58f07e9..a4c4edac4528 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -326,13 +326,6 @@ static int tick_nohz_cpu_down_callback(struct notifier_block *nfb, return NOTIFY_OK; } -/* - * Worst case string length in chunks of CPU range seems 2 steps - * separations: 0,2,4,6,... - * This is NR_CPUS + sizeof('\0') - */ -static char __initdata nohz_full_buf[NR_CPUS + 1]; - static int tick_nohz_init_all(void) { int err = -1; @@ -393,8 +386,8 @@ void __init tick_nohz_init(void) context_tracking_cpu_set(cpu); cpu_notifier(tick_nohz_cpu_down_callback, 0); - cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), tick_nohz_full_mask); - pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf); + pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n", + cpumask_pr_args(tick_nohz_full_mask)); } #endif diff --git a/kernel/time/timecounter.c b/kernel/time/timecounter.c new file mode 100644 index 000000000000..4687b3104bae --- /dev/null +++ b/kernel/time/timecounter.c @@ -0,0 +1,112 @@ +/* + * linux/kernel/time/timecounter.c + * + * based on code that migrated away from + * linux/kernel/time/clocksource.c + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/export.h> +#include <linux/timecounter.h> + +void timecounter_init(struct timecounter *tc, + const struct cyclecounter *cc, + u64 start_tstamp) +{ + tc->cc = cc; + tc->cycle_last = cc->read(cc); + tc->nsec = start_tstamp; + tc->mask = (1ULL << cc->shift) - 1; + tc->frac = 0; +} +EXPORT_SYMBOL_GPL(timecounter_init); + +/** + * timecounter_read_delta - get nanoseconds since last call of this function + * @tc: Pointer to time counter + * + * When the underlying cycle counter runs over, this will be handled + * correctly as long as it does not run over more than once between + * calls. + * + * The first call to this function for a new time counter initializes + * the time tracking and returns an undefined result. + */ +static u64 timecounter_read_delta(struct timecounter *tc) +{ + cycle_t cycle_now, cycle_delta; + u64 ns_offset; + + /* read cycle counter: */ + cycle_now = tc->cc->read(tc->cc); + + /* calculate the delta since the last timecounter_read_delta(): */ + cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask; + + /* convert to nanoseconds: */ + ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta, + tc->mask, &tc->frac); + + /* update time stamp of timecounter_read_delta() call: */ + tc->cycle_last = cycle_now; + + return ns_offset; +} + +u64 timecounter_read(struct timecounter *tc) +{ + u64 nsec; + + /* increment time by nanoseconds since last call */ + nsec = timecounter_read_delta(tc); + nsec += tc->nsec; + tc->nsec = nsec; + + return nsec; +} +EXPORT_SYMBOL_GPL(timecounter_read); + +/* + * This is like cyclecounter_cyc2ns(), but it is used for computing a + * time previous to the time stored in the cycle counter. + */ +static u64 cc_cyc2ns_backwards(const struct cyclecounter *cc, + cycle_t cycles, u64 mask, u64 frac) +{ + u64 ns = (u64) cycles; + + ns = ((ns * cc->mult) - frac) >> cc->shift; + + return ns; +} + +u64 timecounter_cyc2time(struct timecounter *tc, + cycle_t cycle_tstamp) +{ + u64 delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask; + u64 nsec = tc->nsec, frac = tc->frac; + + /* + * Instead of always treating cycle_tstamp as more recent + * than tc->cycle_last, detect when it is too far in the + * future and treat it as old time stamp instead. + */ + if (delta > tc->cc->mask / 2) { + delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask; + nsec -= cc_cyc2ns_backwards(tc->cc, delta, tc->mask, frac); + } else { + nsec += cyclecounter_cyc2ns(tc->cc, delta, tc->mask, &frac); + } + + return nsec; +} +EXPORT_SYMBOL_GPL(timecounter_cyc2time); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index b124af259800..91db94136c10 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -230,9 +230,7 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. - * @tk: The timekeeper from which we take the update - * @tkf: The fast timekeeper to update - * @tbase: The time base for the fast timekeeper (mono/raw) + * @tkr: Timekeeping readout base from which we take the update * * We want to use this from any context including NMI and tracing / * instrumenting the timekeeping code itself. @@ -244,11 +242,11 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) * smp_wmb(); <- Ensure that the last base[1] update is visible * tkf->seq++; * smp_wmb(); <- Ensure that the seqcount update is visible - * update(tkf->base[0], tk); + * update(tkf->base[0], tkr); * smp_wmb(); <- Ensure that the base[0] update is visible * tkf->seq++; * smp_wmb(); <- Ensure that the seqcount update is visible - * update(tkf->base[1], tk); + * update(tkf->base[1], tkr); * * The reader side does: * @@ -269,7 +267,7 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ -static void update_fast_timekeeper(struct timekeeper *tk) +static void update_fast_timekeeper(struct tk_read_base *tkr) { struct tk_read_base *base = tk_fast_mono.base; @@ -277,7 +275,7 @@ static void update_fast_timekeeper(struct timekeeper *tk) raw_write_seqcount_latch(&tk_fast_mono.seq); /* Update base[0] */ - memcpy(base, &tk->tkr, sizeof(*base)); + memcpy(base, tkr, sizeof(*base)); /* Force readers back to base[0] */ raw_write_seqcount_latch(&tk_fast_mono.seq); @@ -334,6 +332,35 @@ u64 notrace ktime_get_mono_fast_ns(void) } EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); +/* Suspend-time cycles value for halted fast timekeeper. */ +static cycle_t cycles_at_suspend; + +static cycle_t dummy_clock_read(struct clocksource *cs) +{ + return cycles_at_suspend; +} + +/** + * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. + * @tk: Timekeeper to snapshot. + * + * It generally is unsafe to access the clocksource after timekeeping has been + * suspended, so take a snapshot of the readout base of @tk and use it as the + * fast timekeeper's readout base while suspended. It will return the same + * number of cycles every time until timekeeping is resumed at which time the + * proper readout base for the fast timekeeper will be restored automatically. + */ +static void halt_fast_timekeeper(struct timekeeper *tk) +{ + static struct tk_read_base tkr_dummy; + struct tk_read_base *tkr = &tk->tkr; + + memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); + cycles_at_suspend = tkr->read(tkr->clock); + tkr_dummy.read = dummy_clock_read; + update_fast_timekeeper(&tkr_dummy); +} + #ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD static inline void update_vsyscall(struct timekeeper *tk) @@ -462,7 +489,7 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) memcpy(&shadow_timekeeper, &tk_core.timekeeper, sizeof(tk_core.timekeeper)); - update_fast_timekeeper(tk); + update_fast_timekeeper(&tk->tkr); } /** @@ -1170,7 +1197,7 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta) * xtime/wall_to_monotonic/jiffies/etc are * still managed by arch specific suspend/resume code. */ -static void timekeeping_resume(void) +void timekeeping_resume(void) { struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock = tk->tkr.clock; @@ -1251,7 +1278,7 @@ static void timekeeping_resume(void) hrtimers_resume(); } -static int timekeeping_suspend(void) +int timekeeping_suspend(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; @@ -1296,6 +1323,7 @@ static int timekeeping_suspend(void) } timekeeping_update(tk, TK_MIRROR); + halt_fast_timekeeper(tk); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index adc1fc98bde3..1d91416055d5 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -16,5 +16,7 @@ extern int timekeeping_inject_offset(struct timespec *ts); extern s32 timekeeping_get_tai_offset(void); extern void timekeeping_set_tai_offset(s32 tai_offset); extern void timekeeping_clocktai(struct timespec *ts); +extern int timekeeping_suspend(void); +extern void timekeeping_resume(void); #endif diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 979ccde26720..98f26588255e 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -3,11 +3,11 @@ ifdef CONFIG_FUNCTION_TRACER ORIG_CFLAGS := $(KBUILD_CFLAGS) -KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS)) +KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS)) ifdef CONFIG_FTRACE_SELFTEST # selftest needs instrumentation -CFLAGS_trace_selftest_dynamic.o = -pg +CFLAGS_trace_selftest_dynamic.o = $(CC_FLAGS_FTRACE) obj-y += trace_selftest_dynamic.o endif endif diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 224e768bdc73..45e5cb143d17 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5456,7 +5456,7 @@ static __init int ftrace_init_debugfs(void) struct dentry *d_tracer; d_tracer = tracing_init_dentry(); - if (!d_tracer) + if (IS_ERR(d_tracer)) return 0; ftrace_init_dyn_debugfs(d_tracer); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 7a4104cb95cb..5040d44fe5a3 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -9,7 +9,6 @@ #include <linux/trace_seq.h> #include <linux/spinlock.h> #include <linux/irq_work.h> -#include <linux/debugfs.h> #include <linux/uaccess.h> #include <linux/hardirq.h> #include <linux/kthread.h> /* for self test */ @@ -23,7 +22,6 @@ #include <linux/hash.h> #include <linux/list.h> #include <linux/cpu.h> -#include <linux/fs.h> #include <asm/local.h> @@ -447,7 +445,10 @@ int ring_buffer_print_page_header(struct trace_seq *s) struct rb_irq_work { struct irq_work work; wait_queue_head_t waiters; + wait_queue_head_t full_waiters; bool waiters_pending; + bool full_waiters_pending; + bool wakeup_full; }; /* @@ -529,6 +530,10 @@ static void rb_wake_up_waiters(struct irq_work *work) struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work); wake_up_all(&rbwork->waiters); + if (rbwork->wakeup_full) { + rbwork->wakeup_full = false; + wake_up_all(&rbwork->full_waiters); + } } /** @@ -553,9 +558,11 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full) * data in any cpu buffer, or a specific buffer, put the * caller on the appropriate wait queue. */ - if (cpu == RING_BUFFER_ALL_CPUS) + if (cpu == RING_BUFFER_ALL_CPUS) { work = &buffer->irq_work; - else { + /* Full only makes sense on per cpu reads */ + full = false; + } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) return -ENODEV; cpu_buffer = buffer->buffers[cpu]; @@ -564,7 +571,10 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full) while (true) { - prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE); + if (full) + prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE); + else + prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE); /* * The events can happen in critical sections where @@ -586,7 +596,10 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full) * that is necessary is that the wake up happens after * a task has been queued. It's OK for spurious wake ups. */ - work->waiters_pending = true; + if (full) + work->full_waiters_pending = true; + else + work->waiters_pending = true; if (signal_pending(current)) { ret = -EINTR; @@ -615,7 +628,10 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full) schedule(); } - finish_wait(&work->waiters, &wait); + if (full) + finish_wait(&work->full_waiters, &wait); + else + finish_wait(&work->waiters, &wait); return ret; } @@ -1230,6 +1246,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu) init_completion(&cpu_buffer->update_done); init_irq_work(&cpu_buffer->irq_work.work, rb_wake_up_waiters); init_waitqueue_head(&cpu_buffer->irq_work.waiters); + init_waitqueue_head(&cpu_buffer->irq_work.full_waiters); bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu)); @@ -2801,6 +2818,8 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer, static __always_inline void rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) { + bool pagebusy; + if (buffer->irq_work.waiters_pending) { buffer->irq_work.waiters_pending = false; /* irq_work_queue() supplies it's own memory barriers */ @@ -2812,6 +2831,15 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) /* irq_work_queue() supplies it's own memory barriers */ irq_work_queue(&cpu_buffer->irq_work.work); } + + pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; + + if (!pagebusy && cpu_buffer->irq_work.full_waiters_pending) { + cpu_buffer->irq_work.wakeup_full = true; + cpu_buffer->irq_work.full_waiters_pending = false; + /* irq_work_queue() supplies it's own memory barriers */ + irq_work_queue(&cpu_buffer->irq_work.work); + } } /** diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index 3f9e328c30b5..13d945c0d03f 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -7,7 +7,7 @@ #include <linux/completion.h> #include <linux/kthread.h> #include <linux/module.h> -#include <linux/time.h> +#include <linux/ktime.h> #include <asm/local.h> struct rb_page { @@ -17,7 +17,7 @@ struct rb_page { }; /* run time and sleep time in seconds */ -#define RUN_TIME 10 +#define RUN_TIME 10ULL #define SLEEP_TIME 10 /* number of events for writer to wake up the reader */ @@ -212,8 +212,7 @@ static void ring_buffer_consumer(void) static void ring_buffer_producer(void) { - struct timeval start_tv; - struct timeval end_tv; + ktime_t start_time, end_time, timeout; unsigned long long time; unsigned long long entries; unsigned long long overruns; @@ -227,7 +226,8 @@ static void ring_buffer_producer(void) * make the system stall) */ trace_printk("Starting ring buffer hammer\n"); - do_gettimeofday(&start_tv); + start_time = ktime_get(); + timeout = ktime_add_ns(start_time, RUN_TIME * NSEC_PER_SEC); do { struct ring_buffer_event *event; int *entry; @@ -244,7 +244,7 @@ static void ring_buffer_producer(void) ring_buffer_unlock_commit(buffer, event); } } - do_gettimeofday(&end_tv); + end_time = ktime_get(); cnt++; if (consumer && !(cnt % wakeup_interval)) @@ -264,7 +264,7 @@ static void ring_buffer_producer(void) cond_resched(); #endif - } while (end_tv.tv_sec < (start_tv.tv_sec + RUN_TIME) && !kill_test); + } while (ktime_before(end_time, timeout) && !kill_test); trace_printk("End ring buffer hammer\n"); if (consumer) { @@ -280,9 +280,7 @@ static void ring_buffer_producer(void) wait_for_completion(&read_done); } - time = end_tv.tv_sec - start_tv.tv_sec; - time *= USEC_PER_SEC; - time += (long long)((long)end_tv.tv_usec - (long)start_tv.tv_usec); + time = ktime_us_delta(end_time, start_time); entries = ring_buffer_entries(buffer); overruns = ring_buffer_overruns(buffer); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4a9079b9f082..62c6506d663f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2036,7 +2036,8 @@ void trace_printk_init_buffers(void) /* trace_printk() is for debug use only. Don't use it in production. */ - pr_warning("\n**********************************************************\n"); + pr_warning("\n"); + pr_warning("**********************************************************\n"); pr_warning("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warning("** **\n"); pr_warning("** trace_printk() being used. Allocating extra memory. **\n"); @@ -3352,12 +3353,12 @@ tracing_cpumask_read(struct file *filp, char __user *ubuf, mutex_lock(&tracing_cpumask_update_lock); - len = cpumask_scnprintf(mask_str, count, tr->tracing_cpumask); - if (count - len < 2) { + len = snprintf(mask_str, count, "%*pb\n", + cpumask_pr_args(tr->tracing_cpumask)); + if (len >= count) { count = -EINVAL; goto out_err; } - len += sprintf(mask_str + len, "\n"); count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1); out_err: @@ -4140,6 +4141,12 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf) goto out; } + /* If trace pipe files are being read, we can't change the tracer */ + if (tr->current_trace->ref) { + ret = -EBUSY; + goto out; + } + trace_branch_disable(); tr->current_trace->enabled--; @@ -4326,17 +4333,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) } trace_seq_init(&iter->seq); - - /* - * We make a copy of the current tracer to avoid concurrent - * changes on it while we are reading. - */ - iter->trace = kmalloc(sizeof(*iter->trace), GFP_KERNEL); - if (!iter->trace) { - ret = -ENOMEM; - goto fail; - } - *iter->trace = *tr->current_trace; + iter->trace = tr->current_trace; if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) { ret = -ENOMEM; @@ -4363,6 +4360,8 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) iter->trace->pipe_open(iter); nonseekable_open(inode, filp); + + tr->current_trace->ref++; out: mutex_unlock(&trace_types_lock); return ret; @@ -4382,6 +4381,8 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) mutex_lock(&trace_types_lock); + tr->current_trace->ref--; + if (iter->trace->pipe_close) iter->trace->pipe_close(iter); @@ -4389,7 +4390,6 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) free_cpumask_var(iter->started); mutex_destroy(&iter->mutex); - kfree(iter->trace); kfree(iter); trace_array_put(tr); @@ -4422,7 +4422,7 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table) return trace_poll(iter, filp, poll_table); } -/* Must be called with trace_types_lock mutex held. */ +/* Must be called with iter->mutex held. */ static int tracing_wait_pipe(struct file *filp) { struct trace_iterator *iter = filp->private_data; @@ -4467,7 +4467,6 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_iterator *iter = filp->private_data; - struct trace_array *tr = iter->tr; ssize_t sret; /* return any leftover data */ @@ -4477,12 +4476,6 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, trace_seq_init(&iter->seq); - /* copy the tracer to avoid using a global lock all around */ - mutex_lock(&trace_types_lock); - if (unlikely(iter->trace->name != tr->current_trace->name)) - *iter->trace = *tr->current_trace; - mutex_unlock(&trace_types_lock); - /* * Avoid more than one consumer on a single file descriptor * This is just a matter of traces coherency, the ring buffer itself @@ -4642,7 +4635,6 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, .ops = &tracing_pipe_buf_ops, .spd_release = tracing_spd_release_pipe, }; - struct trace_array *tr = iter->tr; ssize_t ret; size_t rem; unsigned int i; @@ -4650,12 +4642,6 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, if (splice_grow_spd(pipe, &spd)) return -ENOMEM; - /* copy the tracer to avoid using a global lock all around */ - mutex_lock(&trace_types_lock); - if (unlikely(iter->trace->name != tr->current_trace->name)) - *iter->trace = *tr->current_trace; - mutex_unlock(&trace_types_lock); - mutex_lock(&iter->mutex); if (iter->trace->splice_read) { @@ -4942,7 +4928,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, *fpos += written; out_unlock: - for (i = 0; i < nr_pages; i++){ + for (i = nr_pages - 1; i >= 0; i--) { kunmap_atomic(map_page[i]); put_page(pages[i]); } @@ -5331,6 +5317,8 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) filp->private_data = info; + tr->current_trace->ref++; + mutex_unlock(&trace_types_lock); ret = nonseekable_open(inode, filp); @@ -5361,21 +5349,16 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, if (!count) return 0; - mutex_lock(&trace_types_lock); - #ifdef CONFIG_TRACER_MAX_TRACE - if (iter->snapshot && iter->tr->current_trace->use_max_tr) { - size = -EBUSY; - goto out_unlock; - } + if (iter->snapshot && iter->tr->current_trace->use_max_tr) + return -EBUSY; #endif if (!info->spare) info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer, iter->cpu_file); - size = -ENOMEM; if (!info->spare) - goto out_unlock; + return -ENOMEM; /* Do we have previous read data to read? */ if (info->read < PAGE_SIZE) @@ -5391,21 +5374,16 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, if (ret < 0) { if (trace_empty(iter)) { - if ((filp->f_flags & O_NONBLOCK)) { - size = -EAGAIN; - goto out_unlock; - } - mutex_unlock(&trace_types_lock); + if ((filp->f_flags & O_NONBLOCK)) + return -EAGAIN; + ret = wait_on_pipe(iter, false); - mutex_lock(&trace_types_lock); - if (ret) { - size = ret; - goto out_unlock; - } + if (ret) + return ret; + goto again; } - size = 0; - goto out_unlock; + return 0; } info->read = 0; @@ -5415,18 +5393,14 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, size = count; ret = copy_to_user(ubuf, info->spare + info->read, size); - if (ret == size) { - size = -EFAULT; - goto out_unlock; - } + if (ret == size) + return -EFAULT; + size -= ret; *ppos += size; info->read += size; - out_unlock: - mutex_unlock(&trace_types_lock); - return size; } @@ -5437,6 +5411,8 @@ static int tracing_buffers_release(struct inode *inode, struct file *file) mutex_lock(&trace_types_lock); + iter->tr->current_trace->ref--; + __trace_array_put(iter->tr); if (info->spare) @@ -5522,30 +5498,20 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, int entries, size, i; ssize_t ret = 0; - mutex_lock(&trace_types_lock); - #ifdef CONFIG_TRACER_MAX_TRACE - if (iter->snapshot && iter->tr->current_trace->use_max_tr) { - ret = -EBUSY; - goto out; - } + if (iter->snapshot && iter->tr->current_trace->use_max_tr) + return -EBUSY; #endif - if (splice_grow_spd(pipe, &spd)) { - ret = -ENOMEM; - goto out; - } + if (splice_grow_spd(pipe, &spd)) + return -ENOMEM; - if (*ppos & (PAGE_SIZE - 1)) { - ret = -EINVAL; - goto out; - } + if (*ppos & (PAGE_SIZE - 1)) + return -EINVAL; if (len & (PAGE_SIZE - 1)) { - if (len < PAGE_SIZE) { - ret = -EINVAL; - goto out; - } + if (len < PAGE_SIZE) + return -EINVAL; len &= PAGE_MASK; } @@ -5606,25 +5572,20 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, /* did we read anything? */ if (!spd.nr_pages) { if (ret) - goto out; + return ret; + + if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) + return -EAGAIN; - if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) { - ret = -EAGAIN; - goto out; - } - mutex_unlock(&trace_types_lock); ret = wait_on_pipe(iter, true); - mutex_lock(&trace_types_lock); if (ret) - goto out; + return ret; goto again; } ret = splice_to_pipe(pipe, &spd); splice_shrink_spd(&spd); -out: - mutex_unlock(&trace_types_lock); return ret; } @@ -5854,28 +5815,11 @@ static __init int register_snapshot_cmd(void) static inline __init int register_snapshot_cmd(void) { return 0; } #endif /* defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) */ -struct dentry *tracing_init_dentry_tr(struct trace_array *tr) +static struct dentry *tracing_get_dentry(struct trace_array *tr) { - if (tr->dir) - return tr->dir; - - if (!debugfs_initialized()) - return NULL; - - if (tr->flags & TRACE_ARRAY_FL_GLOBAL) - tr->dir = debugfs_create_dir("tracing", NULL); - - if (!tr->dir) - pr_warn_once("Could not create debugfs directory 'tracing'\n"); - return tr->dir; } -struct dentry *tracing_init_dentry(void) -{ - return tracing_init_dentry_tr(&global_trace); -} - static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu) { struct dentry *d_tracer; @@ -5883,8 +5827,8 @@ static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu) if (tr->percpu_dir) return tr->percpu_dir; - d_tracer = tracing_init_dentry_tr(tr); - if (!d_tracer) + d_tracer = tracing_get_dentry(tr); + if (IS_ERR(d_tracer)) return NULL; tr->percpu_dir = debugfs_create_dir("per_cpu", d_tracer); @@ -6086,8 +6030,8 @@ static struct dentry *trace_options_init_dentry(struct trace_array *tr) if (tr->options) return tr->options; - d_tracer = tracing_init_dentry_tr(tr); - if (!d_tracer) + d_tracer = tracing_get_dentry(tr); + if (IS_ERR(d_tracer)) return NULL; tr->options = debugfs_create_dir("options", d_tracer); @@ -6416,7 +6360,7 @@ static int instance_delete(const char *name) goto out_unlock; ret = -EBUSY; - if (tr->ref) + if (tr->ref || (tr->current_trace && tr->current_trace->ref)) goto out_unlock; list_del(&tr->list); @@ -6571,6 +6515,33 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) } +/** + * tracing_init_dentry - initialize top level trace array + * + * This is called when creating files or directories in the tracing + * directory. It is called via fs_initcall() by any of the boot up code + * and expects to return the dentry of the top level tracing directory. + */ +struct dentry *tracing_init_dentry(void) +{ + struct trace_array *tr = &global_trace; + + if (tr->dir) + return tr->dir; + + if (WARN_ON(!debugfs_initialized())) + return ERR_PTR(-ENODEV); + + tr->dir = debugfs_create_dir("tracing", NULL); + + if (!tr->dir) { + pr_warn_once("Could not create debugfs directory 'tracing'\n"); + return ERR_PTR(-ENOMEM); + } + + return tr->dir; +} + static __init int tracer_init_debugfs(void) { struct dentry *d_tracer; @@ -6578,7 +6549,7 @@ static __init int tracer_init_debugfs(void) trace_access_lock_init(); d_tracer = tracing_init_dentry(); - if (!d_tracer) + if (IS_ERR(d_tracer)) return 0; init_tracer_debugfs(&global_trace, d_tracer); @@ -6811,7 +6782,6 @@ __init static int tracer_alloc_buffers(void) int ring_buf_size; int ret = -ENOMEM; - if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL)) goto out; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 8de48bac1ce2..dd8205a35760 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -388,6 +388,7 @@ struct tracer { struct tracer *next; struct tracer_flags *flags; int enabled; + int ref; bool print_max; bool allow_instances; #ifdef CONFIG_TRACER_MAX_TRACE @@ -541,7 +542,6 @@ struct dentry *trace_create_file(const char *name, void *data, const struct file_operations *fops); -struct dentry *tracing_init_dentry_tr(struct trace_array *tr); struct dentry *tracing_init_dentry(void); struct ring_buffer_event; diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 7d6e2afde669..57cbf1efdd44 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -7,7 +7,6 @@ #include <linux/seq_file.h> #include <linux/spinlock.h> #include <linux/irqflags.h> -#include <linux/debugfs.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/ftrace.h> diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index b03a0ea77b99..db54dda10ccc 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2531,7 +2531,7 @@ static __init int event_trace_init(void) return -ENODEV; d_tracer = tracing_init_dentry(); - if (!d_tracer) + if (IS_ERR(d_tracer)) return 0; entry = debugfs_create_file("available_events", 0444, d_tracer, diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index d4ddde28a81a..12e2b99be862 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -6,12 +6,10 @@ #include <linux/stringify.h> #include <linux/kallsyms.h> #include <linux/seq_file.h> -#include <linux/debugfs.h> #include <linux/uaccess.h> #include <linux/ftrace.h> #include <linux/module.h> #include <linux/init.h> -#include <linux/fs.h> #include "trace_output.h" diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index ba476009e5de..2d25ad1526bb 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -1437,7 +1437,7 @@ static __init int init_graph_debugfs(void) struct dentry *d_tracer; d_tracer = tracing_init_dentry(); - if (!d_tracer) + if (IS_ERR(d_tracer)) return 0; trace_create_file("max_graph_depth", 0644, d_tracer, diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 9bb104f748d0..8523ea345f2b 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -10,11 +10,9 @@ * Copyright (C) 2004 Nadia Yvette Chambers */ #include <linux/kallsyms.h> -#include <linux/debugfs.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/ftrace.h> -#include <linux/fs.h> #include "trace.h" diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 296079ae6583..d73f565b4e06 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1320,7 +1320,7 @@ static __init int init_kprobe_trace(void) return -EINVAL; d_tracer = tracing_init_dentry(); - if (!d_tracer) + if (IS_ERR(d_tracer)) return 0; entry = debugfs_create_file("kprobe_events", 0644, d_tracer, diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c index fcf0a9e48916..8bb2071474dd 100644 --- a/kernel/trace/trace_nop.c +++ b/kernel/trace/trace_nop.c @@ -6,8 +6,6 @@ */ #include <linux/module.h> -#include <linux/fs.h> -#include <linux/debugfs.h> #include <linux/ftrace.h> #include "trace.h" diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index b77b9a697619..692bf7184c8c 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -177,6 +177,50 @@ ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len) } EXPORT_SYMBOL(ftrace_print_hex_seq); +const char * +ftrace_print_array_seq(struct trace_seq *p, const void *buf, int buf_len, + size_t el_size) +{ + const char *ret = trace_seq_buffer_ptr(p); + const char *prefix = ""; + void *ptr = (void *)buf; + + trace_seq_putc(p, '{'); + + while (ptr < buf + buf_len) { + switch (el_size) { + case 1: + trace_seq_printf(p, "%s0x%x", prefix, + *(u8 *)ptr); + break; + case 2: + trace_seq_printf(p, "%s0x%x", prefix, + *(u16 *)ptr); + break; + case 4: + trace_seq_printf(p, "%s0x%x", prefix, + *(u32 *)ptr); + break; + case 8: + trace_seq_printf(p, "%s0x%llx", prefix, + *(u64 *)ptr); + break; + default: + trace_seq_printf(p, "BAD SIZE:%zu 0x%x", el_size, + *(u8 *)ptr); + el_size = 1; + } + prefix = ","; + ptr += el_size; + } + + trace_seq_putc(p, '}'); + trace_seq_putc(p, 0); + + return ret; +} +EXPORT_SYMBOL(ftrace_print_array_seq); + int ftrace_raw_output_prep(struct trace_iterator *iter, struct trace_event *trace_event) { diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index c4e70b6bd7fa..36c1455b7567 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -5,7 +5,6 @@ * */ #include <linux/seq_file.h> -#include <linux/debugfs.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/ftrace.h> @@ -15,7 +14,6 @@ #include <linux/ctype.h> #include <linux/list.h> #include <linux/slab.h> -#include <linux/fs.h> #include "trace.h" @@ -349,7 +347,7 @@ static __init int init_trace_printk_function_export(void) struct dentry *d_tracer; d_tracer = tracing_init_dentry(); - if (!d_tracer) + if (IS_ERR(d_tracer)) return 0; trace_create_file("printk_formats", 0444, d_tracer, diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 2e293beb186e..419ca37e72c9 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -5,8 +5,6 @@ * */ #include <linux/module.h> -#include <linux/fs.h> -#include <linux/debugfs.h> #include <linux/kallsyms.h> #include <linux/uaccess.h> #include <linux/ftrace.h> diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 8fb84b362816..d6e1003724e9 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -10,8 +10,6 @@ * Copyright (C) 2004 Nadia Yvette Chambers */ #include <linux/module.h> -#include <linux/fs.h> -#include <linux/debugfs.h> #include <linux/kallsyms.h> #include <linux/uaccess.h> #include <linux/ftrace.h> diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c index f8b45d8792f9..e694c9f9efa4 100644 --- a/kernel/trace/trace_seq.c +++ b/kernel/trace/trace_seq.c @@ -120,7 +120,7 @@ void trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp, __trace_seq_init(s); - seq_buf_bitmask(&s->seq, maskp, nmaskbits); + seq_buf_printf(&s->seq, "%*pb", nmaskbits, maskp); if (unlikely(seq_buf_has_overflowed(&s->seq))) { s->seq.len = save_len; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 16eddb308c33..c3e4fcfddd45 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -7,12 +7,10 @@ #include <linux/seq_file.h> #include <linux/spinlock.h> #include <linux/uaccess.h> -#include <linux/debugfs.h> #include <linux/ftrace.h> #include <linux/module.h> #include <linux/sysctl.h> #include <linux/init.h> -#include <linux/fs.h> #include <asm/setup.h> @@ -462,7 +460,7 @@ static __init int stack_trace_init(void) struct dentry *d_tracer; d_tracer = tracing_init_dentry(); - if (!d_tracer) + if (IS_ERR(d_tracer)) return 0; trace_create_file("stack_max_size", 0644, d_tracer, diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index 7af67360b330..75e19e86c954 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -276,7 +276,7 @@ static int tracing_stat_init(void) struct dentry *d_tracing; d_tracing = tracing_init_dentry(); - if (!d_tracing) + if (IS_ERR(d_tracing)) return 0; stat_dir = debugfs_create_dir("trace_stat", d_tracing); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index b11441321e7a..7dc1c8abecd6 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1321,7 +1321,7 @@ static __init int init_uprobe_trace(void) struct dentry *d_tracer; d_tracer = tracing_init_dentry(); - if (!d_tracer) + if (IS_ERR(d_tracer)) return 0; trace_create_file("uprobe_events", 0644, d_tracer, diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 70bf11815f84..3174bf8e3538 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -154,7 +154,7 @@ static int get_softlockup_thresh(void) */ static unsigned long get_timestamp(void) { - return local_clock() >> 30LL; /* 2^30 ~= 10^9 */ + return running_clock() >> 30LL; /* 2^30 ~= 10^9 */ } static void set_sample_period(void) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index beeeac9e0e3e..f28849394791 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3083,10 +3083,9 @@ static ssize_t wq_cpumask_show(struct device *dev, int written; mutex_lock(&wq->mutex); - written = cpumask_scnprintf(buf, PAGE_SIZE, wq->unbound_attrs->cpumask); + written = scnprintf(buf, PAGE_SIZE, "%*pb\n", + cpumask_pr_args(wq->unbound_attrs->cpumask)); mutex_unlock(&wq->mutex); - - written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); return written; } |