diff options
Diffstat (limited to 'kernel')
77 files changed, 3318 insertions, 3585 deletions
diff --git a/kernel/audit.c b/kernel/audit.c index 95a20f3f52f1..7c2893602d06 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -182,7 +182,7 @@ struct audit_buffer { struct audit_reply { __u32 portid; - struct net *net; + struct net *net; struct sk_buff *skb; }; @@ -396,7 +396,7 @@ static void audit_printk_skb(struct sk_buff *skb) if (printk_ratelimit()) pr_notice("type=%d %s\n", nlh->nlmsg_type, data); else - audit_log_lost("printk limit exceeded\n"); + audit_log_lost("printk limit exceeded"); } audit_hold_skb(skb); @@ -412,7 +412,7 @@ static void kauditd_send_skb(struct sk_buff *skb) BUG_ON(err != -ECONNREFUSED); /* Shouldn't happen */ if (audit_pid) { pr_err("*NO* daemon at audit_pid=%d\n", audit_pid); - audit_log_lost("auditd disappeared\n"); + audit_log_lost("auditd disappeared"); audit_pid = 0; audit_sock = NULL; } @@ -607,7 +607,7 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) { int err = 0; - /* Only support the initial namespaces for now. */ + /* Only support initial user namespace for now. */ /* * We return ECONNREFUSED because it tricks userspace into thinking * that audit was not configured into the kernel. Lots of users @@ -618,8 +618,7 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) * userspace will reject all logins. This should be removed when we * support non init namespaces!! */ - if ((current_user_ns() != &init_user_ns) || - (task_active_pid_ns(current) != &init_pid_ns)) + if (current_user_ns() != &init_user_ns) return -ECONNREFUSED; switch (msg_type) { @@ -639,6 +638,11 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) case AUDIT_TTY_SET: case AUDIT_TRIM: case AUDIT_MAKE_EQUIV: + /* Only support auditd and auditctl in initial pid namespace + * for now. */ + if ((task_active_pid_ns(current) != &init_pid_ns)) + return -EPERM; + if (!capable(CAP_AUDIT_CONTROL)) err = -EPERM; break; @@ -659,6 +663,7 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type) { int rc = 0; uid_t uid = from_kuid(&init_user_ns, current_uid()); + pid_t pid = task_tgid_nr(current); if (!audit_enabled && msg_type != AUDIT_USER_AVC) { *ab = NULL; @@ -668,7 +673,7 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type) *ab = audit_log_start(NULL, GFP_KERNEL, msg_type); if (unlikely(!*ab)) return rc; - audit_log_format(*ab, "pid=%d uid=%u", task_tgid_vnr(current), uid); + audit_log_format(*ab, "pid=%d uid=%u", pid, uid); audit_log_session_info(*ab); audit_log_task_context(*ab); @@ -1097,7 +1102,7 @@ static void __net_exit audit_net_exit(struct net *net) audit_sock = NULL; } - rcu_assign_pointer(aunet->nlsk, NULL); + RCU_INIT_POINTER(aunet->nlsk, NULL); synchronize_net(); netlink_kernel_release(sock); } @@ -1829,11 +1834,11 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk) spin_unlock_irq(&tsk->sighand->siglock); audit_log_format(ab, - " ppid=%ld pid=%d auid=%u uid=%u gid=%u" + " ppid=%d pid=%d auid=%u uid=%u gid=%u" " euid=%u suid=%u fsuid=%u" " egid=%u sgid=%u fsgid=%u tty=%s ses=%u", - sys_getppid(), - tsk->pid, + task_ppid_nr(tsk), + task_pid_nr(tsk), from_kuid(&init_user_ns, audit_get_loginuid(tsk)), from_kuid(&init_user_ns, cred->uid), from_kgid(&init_user_ns, cred->gid), diff --git a/kernel/audit.h b/kernel/audit.h index 8df132214606..7bb65730c890 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -106,6 +106,11 @@ struct audit_names { bool should_free; }; +struct audit_proctitle { + int len; /* length of the cmdline field. */ + char *value; /* the cmdline field */ +}; + /* The per-task audit context. */ struct audit_context { int dummy; /* must be the first element */ @@ -202,6 +207,7 @@ struct audit_context { } execve; }; int fds[2]; + struct audit_proctitle proctitle; #if AUDIT_DEBUG int put_count; diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 92062fd6cc8c..8e9bc9c3dbb7 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -19,6 +19,8 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/audit.h> #include <linux/kthread.h> @@ -226,7 +228,7 @@ static int audit_match_signal(struct audit_entry *entry) #endif /* Common user-space to kernel rule translation. */ -static inline struct audit_entry *audit_to_entry_common(struct audit_rule *rule) +static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data *rule) { unsigned listnr; struct audit_entry *entry; @@ -249,7 +251,7 @@ static inline struct audit_entry *audit_to_entry_common(struct audit_rule *rule) ; } if (unlikely(rule->action == AUDIT_POSSIBLE)) { - printk(KERN_ERR "AUDIT_POSSIBLE is deprecated\n"); + pr_err("AUDIT_POSSIBLE is deprecated\n"); goto exit_err; } if (rule->action != AUDIT_NEVER && rule->action != AUDIT_ALWAYS) @@ -403,7 +405,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, int i; char *str; - entry = audit_to_entry_common((struct audit_rule *)data); + entry = audit_to_entry_common(data); if (IS_ERR(entry)) goto exit_nofree; @@ -431,6 +433,19 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, f->val = 0; } + if ((f->type == AUDIT_PID) || (f->type == AUDIT_PPID)) { + struct pid *pid; + rcu_read_lock(); + pid = find_vpid(f->val); + if (!pid) { + rcu_read_unlock(); + err = -ESRCH; + goto exit_free; + } + f->val = pid_nr(pid); + rcu_read_unlock(); + } + err = audit_field_valid(entry, f); if (err) goto exit_free; @@ -479,8 +494,8 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (err == -EINVAL) { - printk(KERN_WARNING "audit rule for LSM " - "\'%s\' is invalid\n", str); + pr_warn("audit rule for LSM \'%s\' is invalid\n", + str); err = 0; } if (err) { @@ -709,8 +724,8 @@ static inline int audit_dupe_lsm_field(struct audit_field *df, /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (ret == -EINVAL) { - printk(KERN_WARNING "audit rule for LSM \'%s\' is " - "invalid\n", df->lsm_str); + pr_warn("audit rule for LSM \'%s\' is invalid\n", + df->lsm_str); ret = 0; } @@ -1240,12 +1255,14 @@ static int audit_filter_user_rules(struct audit_krule *rule, int type, for (i = 0; i < rule->field_count; i++) { struct audit_field *f = &rule->fields[i]; + pid_t pid; int result = 0; u32 sid; switch (f->type) { case AUDIT_PID: - result = audit_comparator(task_pid_vnr(current), f->op, f->val); + pid = task_pid_nr(current); + result = audit_comparator(pid, f->op, f->val); break; case AUDIT_UID: result = audit_uid_comparator(current_uid(), f->op, f->uid); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 7aef2f4b6c64..f251a5e8d17a 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -42,6 +42,8 @@ * and <dustin.kirkland@us.ibm.com> for LSPP certification compliance. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/init.h> #include <asm/types.h> #include <linux/atomic.h> @@ -68,6 +70,7 @@ #include <linux/capability.h> #include <linux/fs_struct.h> #include <linux/compat.h> +#include <linux/ctype.h> #include "audit.h" @@ -79,6 +82,9 @@ /* no execve audit message should be longer than this (userspace limits) */ #define MAX_EXECVE_AUDIT_LEN 7500 +/* max length to print of cmdline/proctitle value during audit */ +#define MAX_PROCTITLE_AUDIT_LEN 128 + /* number of audit rules */ int audit_n_rules; @@ -451,15 +457,17 @@ static int audit_filter_rules(struct task_struct *tsk, struct audit_field *f = &rule->fields[i]; struct audit_names *n; int result = 0; + pid_t pid; switch (f->type) { case AUDIT_PID: - result = audit_comparator(tsk->pid, f->op, f->val); + pid = task_pid_nr(tsk); + result = audit_comparator(pid, f->op, f->val); break; case AUDIT_PPID: if (ctx) { if (!ctx->ppid) - ctx->ppid = sys_getppid(); + ctx->ppid = task_ppid_nr(tsk); result = audit_comparator(ctx->ppid, f->op, f->val); } break; @@ -805,7 +813,8 @@ void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx) rcu_read_unlock(); } -static inline struct audit_context *audit_get_context(struct task_struct *tsk, +/* Transfer the audit context pointer to the caller, clearing it in the tsk's struct */ +static inline struct audit_context *audit_take_context(struct task_struct *tsk, int return_valid, long return_code) { @@ -842,6 +851,13 @@ static inline struct audit_context *audit_get_context(struct task_struct *tsk, return context; } +static inline void audit_proctitle_free(struct audit_context *context) +{ + kfree(context->proctitle.value); + context->proctitle.value = NULL; + context->proctitle.len = 0; +} + static inline void audit_free_names(struct audit_context *context) { struct audit_names *n, *next; @@ -850,16 +866,15 @@ static inline void audit_free_names(struct audit_context *context) if (context->put_count + context->ino_count != context->name_count) { int i = 0; - printk(KERN_ERR "%s:%d(:%d): major=%d in_syscall=%d" - " name_count=%d put_count=%d" - " ino_count=%d [NOT freeing]\n", - __FILE__, __LINE__, + 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) { - printk(KERN_ERR "names[%d] = %p = %s\n", i++, - n->name, n->name->name ?: "(null)"); + pr_err("names[%d] = %p = %s\n", i++, n->name, + n->name->name ?: "(null)"); } dump_stack(); return; @@ -955,6 +970,7 @@ static inline void audit_free_context(struct audit_context *context) audit_free_aux(context); kfree(context->filterkey); kfree(context->sockaddr); + audit_proctitle_free(context); kfree(context); } @@ -1157,7 +1173,7 @@ static void audit_log_execve_info(struct audit_context *context, */ buf = kmalloc(MAX_EXECVE_AUDIT_LEN + 1, GFP_KERNEL); if (!buf) { - audit_panic("out of memory for argv string\n"); + audit_panic("out of memory for argv string"); return; } @@ -1271,6 +1287,59 @@ static void show_special(struct audit_context *context, int *call_panic) audit_log_end(ab); } +static inline int audit_proctitle_rtrim(char *proctitle, int len) +{ + char *end = proctitle + len - 1; + while (end > proctitle && !isprint(*end)) + end--; + + /* catch the case where proctitle is only 1 non-print character */ + len = end - proctitle + 1; + len -= isprint(proctitle[len-1]) == 0; + return len; +} + +static void audit_log_proctitle(struct task_struct *tsk, + struct audit_context *context) +{ + int res; + char *buf; + char *msg = "(null)"; + int len = strlen(msg); + struct audit_buffer *ab; + + ab = audit_log_start(context, GFP_KERNEL, AUDIT_PROCTITLE); + if (!ab) + return; /* audit_panic or being filtered */ + + audit_log_format(ab, "proctitle="); + + /* Not cached */ + if (!context->proctitle.value) { + buf = kmalloc(MAX_PROCTITLE_AUDIT_LEN, GFP_KERNEL); + if (!buf) + goto out; + /* Historically called this from procfs naming */ + res = get_cmdline(tsk, buf, MAX_PROCTITLE_AUDIT_LEN); + if (res == 0) { + kfree(buf); + goto out; + } + res = audit_proctitle_rtrim(buf, res); + if (res == 0) { + kfree(buf); + goto out; + } + context->proctitle.value = buf; + context->proctitle.len = res; + } + msg = context->proctitle.value; + len = context->proctitle.len; +out: + audit_log_n_untrustedstring(ab, msg, len); + audit_log_end(ab); +} + static void audit_log_exit(struct audit_context *context, struct task_struct *tsk) { int i, call_panic = 0; @@ -1388,6 +1457,8 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts audit_log_name(context, n, NULL, i++, &call_panic); } + audit_log_proctitle(tsk, context); + /* Send end of event record to help user space know we are finished */ ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE); if (ab) @@ -1406,7 +1477,7 @@ void __audit_free(struct task_struct *tsk) { struct audit_context *context; - context = audit_get_context(tsk, 0, 0); + context = audit_take_context(tsk, 0, 0); if (!context) return; @@ -1500,7 +1571,7 @@ void __audit_syscall_exit(int success, long return_code) else success = AUDITSC_FAILURE; - context = audit_get_context(tsk, success, return_code); + context = audit_take_context(tsk, success, return_code); if (!context) return; @@ -1550,7 +1621,7 @@ static inline void handle_one(const struct inode *inode) if (likely(put_tree_ref(context, chunk))) return; if (unlikely(!grow_tree_refs(context))) { - printk(KERN_WARNING "out of memory, audit has lost a tree reference\n"); + pr_warn("out of memory, audit has lost a tree reference\n"); audit_set_auditable(context); audit_put_chunk(chunk); unroll_tree_refs(context, p, count); @@ -1609,8 +1680,7 @@ retry: goto retry; } /* too bad */ - printk(KERN_WARNING - "out of memory, audit has lost a tree reference\n"); + pr_warn("out of memory, audit has lost a tree reference\n"); unroll_tree_refs(context, p, count); audit_set_auditable(context); return; @@ -1682,7 +1752,7 @@ void __audit_getname(struct filename *name) if (!context->in_syscall) { #if AUDIT_DEBUG == 2 - printk(KERN_ERR "%s:%d(:%d): ignoring getname(%p)\n", + pr_err("%s:%d(:%d): ignoring getname(%p)\n", __FILE__, __LINE__, context->serial, name); dump_stack(); #endif @@ -1721,15 +1791,15 @@ void audit_putname(struct filename *name) BUG_ON(!context); if (!name->aname || !context->in_syscall) { #if AUDIT_DEBUG == 2 - printk(KERN_ERR "%s:%d(:%d): final_putname(%p)\n", + 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) - printk(KERN_ERR "name[%d] = %p = %s\n", i++, - n->name, n->name->name ?: "(null)"); + pr_err("name[%d] = %p = %s\n", i++, n->name, + n->name->name ?: "(null)"); } #endif final_putname(name); @@ -1738,9 +1808,8 @@ void audit_putname(struct filename *name) else { ++context->put_count; if (context->put_count > context->name_count) { - printk(KERN_ERR "%s:%d(:%d): major=%d" - " in_syscall=%d putname(%p) name_count=%d" - " put_count=%d\n", + 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, @@ -1981,12 +2050,10 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid, ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN); if (!ab) return; - audit_log_format(ab, "pid=%d uid=%u" - " old-auid=%u new-auid=%u old-ses=%u new-ses=%u" - " res=%d", - current->pid, uid, - oldloginuid, loginuid, oldsessionid, sessionid, - !rc); + audit_log_format(ab, "pid=%d uid=%u", task_pid_nr(current), uid); + audit_log_task_context(ab); + audit_log_format(ab, " old-auid=%u auid=%u old-ses=%u ses=%u res=%d", + oldloginuid, loginuid, oldsessionid, sessionid, !rc); audit_log_end(ab); } @@ -2208,7 +2275,7 @@ void __audit_ptrace(struct task_struct *t) { struct audit_context *context = current->audit_context; - context->target_pid = t->pid; + context->target_pid = task_pid_nr(t); context->target_auid = audit_get_loginuid(t); context->target_uid = task_uid(t); context->target_sessionid = audit_get_sessionid(t); @@ -2233,7 +2300,7 @@ int __audit_signal_info(int sig, struct task_struct *t) if (audit_pid && t->tgid == audit_pid) { if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) { - audit_sig_pid = tsk->pid; + audit_sig_pid = task_pid_nr(tsk); if (uid_valid(tsk->loginuid)) audit_sig_uid = tsk->loginuid; else @@ -2247,7 +2314,7 @@ int __audit_signal_info(int sig, struct task_struct *t) /* optimize the common case by putting first signal recipient directly * in audit_context */ if (!ctx->target_pid) { - ctx->target_pid = t->tgid; + ctx->target_pid = task_tgid_nr(t); ctx->target_auid = audit_get_loginuid(t); ctx->target_uid = t_uid; ctx->target_sessionid = audit_get_sessionid(t); @@ -2268,7 +2335,7 @@ int __audit_signal_info(int sig, struct task_struct *t) } BUG_ON(axp->pid_count >= AUDIT_AUX_PIDS); - axp->target_pid[axp->pid_count] = t->tgid; + axp->target_pid[axp->pid_count] = task_tgid_nr(t); axp->target_auid[axp->pid_count] = audit_get_loginuid(t); axp->target_uid[axp->pid_count] = t_uid; axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t); @@ -2368,7 +2435,7 @@ static void audit_log_task(struct audit_buffer *ab) from_kgid(&init_user_ns, gid), sessionid); audit_log_task_context(ab); - audit_log_format(ab, " pid=%d comm=", current->pid); + audit_log_format(ab, " pid=%d comm=", task_pid_nr(current)); audit_log_untrustedstring(ab, current->comm); if (mm) { down_read(&mm->mmap_sem); diff --git a/kernel/capability.c b/kernel/capability.c index 34019c57888d..a8d63df0c322 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -7,6 +7,8 @@ * 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/audit.h> #include <linux/capability.h> #include <linux/mm.h> @@ -42,15 +44,10 @@ __setup("no_file_caps", file_caps_disable); static void warn_legacy_capability_use(void) { - static int warned; - if (!warned) { - char name[sizeof(current->comm)]; - - printk(KERN_INFO "warning: `%s' uses 32-bit capabilities" - " (legacy support in use)\n", - get_task_comm(name, current)); - warned = 1; - } + char name[sizeof(current->comm)]; + + pr_info_once("warning: `%s' uses 32-bit capabilities (legacy support in use)\n", + get_task_comm(name, current)); } /* @@ -71,16 +68,10 @@ static void warn_legacy_capability_use(void) static void warn_deprecated_v2(void) { - static int warned; + char name[sizeof(current->comm)]; - if (!warned) { - char name[sizeof(current->comm)]; - - printk(KERN_INFO "warning: `%s' uses deprecated v2" - " capabilities in a way that may be insecure.\n", - get_task_comm(name, current)); - warned = 1; - } + pr_info_once("warning: `%s' uses deprecated v2 capabilities in a way that may be insecure\n", + get_task_comm(name, current)); } /* @@ -380,7 +371,7 @@ bool has_capability_noaudit(struct task_struct *t, int cap) bool ns_capable(struct user_namespace *ns, int cap) { if (unlikely(!cap_valid(cap))) { - printk(KERN_CRIT "capable() called with invalid cap=%u\n", cap); + pr_crit("capable() called with invalid cap=%u\n", cap); BUG(); } diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 0c753ddd223b..9fcdaa705b6c 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -40,23 +40,20 @@ #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/sched.h> -#include <linux/backing-dev.h> #include <linux/slab.h> -#include <linux/magic.h> #include <linux/spinlock.h> +#include <linux/rwsem.h> #include <linux/string.h> #include <linux/sort.h> #include <linux/kmod.h> -#include <linux/module.h> #include <linux/delayacct.h> #include <linux/cgroupstats.h> #include <linux/hashtable.h> -#include <linux/namei.h> #include <linux/pid_namespace.h> #include <linux/idr.h> #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */ -#include <linux/flex_array.h> /* used in cgroup_attach_task */ #include <linux/kthread.h> +#include <linux/delay.h> #include <linux/atomic.h> @@ -68,43 +65,49 @@ */ #define CGROUP_PIDLIST_DESTROY_DELAY HZ +#define CGROUP_FILE_NAME_MAX (MAX_CGROUP_TYPE_NAMELEN + \ + MAX_CFTYPE_NAME + 2) + +/* + * cgroup_tree_mutex nests above cgroup_mutex and protects cftypes, file + * creation/removal and hierarchy changing operations including cgroup + * creation, removal, css association and controller rebinding. This outer + * lock is needed mainly to resolve the circular dependency between kernfs + * active ref and cgroup_mutex. cgroup_tree_mutex nests above both. + */ +static DEFINE_MUTEX(cgroup_tree_mutex); + /* * cgroup_mutex is the master lock. Any modification to cgroup or its * hierarchy must be performed while holding it. * - * cgroup_root_mutex nests inside cgroup_mutex and should be held to modify - * cgroupfs_root of any cgroup hierarchy - subsys list, flags, - * release_agent_path and so on. Modifying requires both cgroup_mutex and - * cgroup_root_mutex. Readers can acquire either of the two. This is to - * break the following locking order cycle. - * - * A. cgroup_mutex -> cred_guard_mutex -> s_type->i_mutex_key -> namespace_sem - * B. namespace_sem -> cgroup_mutex + * css_set_rwsem protects task->cgroups pointer, the list of css_set + * objects, and the chain of tasks off each css_set. * - * B happens only through cgroup_show_options() and using cgroup_root_mutex - * breaks it. + * These locks are exported if CONFIG_PROVE_RCU so that accessors in + * cgroup.h can use them for lockdep annotations. */ #ifdef CONFIG_PROVE_RCU DEFINE_MUTEX(cgroup_mutex); -EXPORT_SYMBOL_GPL(cgroup_mutex); /* only for lockdep */ +DECLARE_RWSEM(css_set_rwsem); +EXPORT_SYMBOL_GPL(cgroup_mutex); +EXPORT_SYMBOL_GPL(css_set_rwsem); #else static DEFINE_MUTEX(cgroup_mutex); +static DECLARE_RWSEM(css_set_rwsem); #endif -static DEFINE_MUTEX(cgroup_root_mutex); +/* + * Protects cgroup_subsys->release_agent_path. Modifying it also requires + * cgroup_mutex. Reading requires either cgroup_mutex or this spinlock. + */ +static DEFINE_SPINLOCK(release_agent_path_lock); -#define cgroup_assert_mutex_or_rcu_locked() \ +#define cgroup_assert_mutexes_or_rcu_locked() \ rcu_lockdep_assert(rcu_read_lock_held() || \ + lockdep_is_held(&cgroup_tree_mutex) || \ lockdep_is_held(&cgroup_mutex), \ - "cgroup_mutex or RCU read lock required"); - -#ifdef CONFIG_LOCKDEP -#define cgroup_assert_mutex_or_root_locked() \ - WARN_ON_ONCE(debug_locks && (!lockdep_is_held(&cgroup_mutex) && \ - !lockdep_is_held(&cgroup_root_mutex))) -#else -#define cgroup_assert_mutex_or_root_locked() do { } while (0) -#endif + "cgroup_[tree_]mutex or RCU read lock required"); /* * cgroup destruction makes heavy use of work items and there can be a lot @@ -120,42 +123,41 @@ static struct workqueue_struct *cgroup_destroy_wq; */ static struct workqueue_struct *cgroup_pidlist_destroy_wq; -/* - * Generate an array of cgroup subsystem pointers. At boot time, this is - * populated with the built in subsystems, and modular subsystems are - * registered after that. The mutable section of this array is protected by - * cgroup_mutex. - */ -#define SUBSYS(_x) [_x ## _subsys_id] = &_x ## _subsys, -#define IS_SUBSYS_ENABLED(option) IS_BUILTIN(option) -static struct cgroup_subsys *cgroup_subsys[CGROUP_SUBSYS_COUNT] = { +/* generate an array of cgroup subsystem pointers */ +#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys, +static struct cgroup_subsys *cgroup_subsys[] = { +#include <linux/cgroup_subsys.h> +}; +#undef SUBSYS + +/* array of cgroup subsystem names */ +#define SUBSYS(_x) [_x ## _cgrp_id] = #_x, +static const char *cgroup_subsys_name[] = { #include <linux/cgroup_subsys.h> }; +#undef SUBSYS /* - * The dummy hierarchy, reserved for the subsystems that are otherwise + * The default hierarchy, reserved for the subsystems that are otherwise * unattached - it never has more than a single cgroup, and all tasks are * part of that cgroup. */ -static struct cgroupfs_root cgroup_dummy_root; +struct cgroup_root cgrp_dfl_root; -/* dummy_top is a shorthand for the dummy hierarchy's top cgroup */ -static struct cgroup * const cgroup_dummy_top = &cgroup_dummy_root.top_cgroup; +/* + * The default hierarchy always exists but is hidden until mounted for the + * first time. This is for backward compatibility. + */ +static bool cgrp_dfl_root_visible; /* The list of hierarchy roots */ static LIST_HEAD(cgroup_roots); static int cgroup_root_count; -/* - * Hierarchy ID allocation and mapping. It follows the same exclusion - * rules as other root ops - both cgroup_mutex and cgroup_root_mutex for - * writes, either for reads. - */ +/* hierarchy ID allocation and mapping, protected by cgroup_mutex */ static DEFINE_IDR(cgroup_hierarchy_idr); -static struct cgroup_name root_cgroup_name = { .name = "/" }; - /* * Assign a monotonically increasing serial number to cgroups. It * guarantees cgroups with bigger numbers are newer than those with smaller @@ -175,11 +177,13 @@ static int need_forkexit_callback __read_mostly; static struct cftype cgroup_base_files[]; +static void cgroup_put(struct cgroup *cgrp); +static int rebind_subsystems(struct cgroup_root *dst_root, + unsigned long ss_mask); static void cgroup_destroy_css_killed(struct cgroup *cgrp); static int cgroup_destroy_locked(struct cgroup *cgrp); static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[], bool is_add); -static int cgroup_file_release(struct inode *inode, struct file *file); static void cgroup_pidlist_destroy_all(struct cgroup *cgrp); /** @@ -197,8 +201,9 @@ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { if (ss) - return rcu_dereference_check(cgrp->subsys[ss->subsys_id], - lockdep_is_held(&cgroup_mutex)); + return rcu_dereference_check(cgrp->subsys[ss->id], + lockdep_is_held(&cgroup_tree_mutex) || + lockdep_is_held(&cgroup_mutex)); else return &cgrp->dummy_css; } @@ -209,6 +214,27 @@ static inline bool cgroup_is_dead(const struct cgroup *cgrp) return test_bit(CGRP_DEAD, &cgrp->flags); } +struct cgroup_subsys_state *seq_css(struct seq_file *seq) +{ + struct kernfs_open_file *of = seq->private; + struct cgroup *cgrp = of->kn->parent->priv; + struct cftype *cft = seq_cft(seq); + + /* + * This is open and unprotected implementation of cgroup_css(). + * seq_css() is only called from a kernfs file operation which has + * an active reference on the file. Because all the subsystem + * files are drained before a css is disassociated with a cgroup, + * the matching css from the cgroup's subsys table is guaranteed to + * be and stay valid until the enclosing operation is complete. + */ + if (cft->ss) + return rcu_dereference_raw(cgrp->subsys[cft->ss->id]); + else + return &cgrp->dummy_css; +} +EXPORT_SYMBOL_GPL(seq_css); + /** * cgroup_is_descendant - test ancestry * @cgrp: the cgroup to be tested @@ -227,7 +253,6 @@ bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor) } return false; } -EXPORT_SYMBOL_GPL(cgroup_is_descendant); static int cgroup_is_releasable(const struct cgroup *cgrp) { @@ -254,54 +279,23 @@ static int notify_on_release(const struct cgroup *cgrp) for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ if (!((css) = rcu_dereference_check( \ (cgrp)->subsys[(ssid)], \ + lockdep_is_held(&cgroup_tree_mutex) || \ lockdep_is_held(&cgroup_mutex)))) { } \ else /** - * for_each_subsys - iterate all loaded cgroup subsystems + * for_each_subsys - iterate all enabled cgroup subsystems * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end - * - * Iterates through all loaded subsystems. Should be called under - * cgroup_mutex or cgroup_root_mutex. */ #define for_each_subsys(ss, ssid) \ - for (({ cgroup_assert_mutex_or_root_locked(); (ssid) = 0; }); \ - (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ - if (!((ss) = cgroup_subsys[(ssid)])) { } \ - else + for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \ + (((ss) = cgroup_subsys[ssid]) || true); (ssid)++) -/** - * for_each_builtin_subsys - iterate all built-in cgroup subsystems - * @ss: the iteration cursor - * @i: the index of @ss, CGROUP_BUILTIN_SUBSYS_COUNT after reaching the end - * - * Bulit-in subsystems are always present and iteration itself doesn't - * require any synchronization. - */ -#define for_each_builtin_subsys(ss, i) \ - for ((i) = 0; (i) < CGROUP_BUILTIN_SUBSYS_COUNT && \ - (((ss) = cgroup_subsys[i]) || true); (i)++) - -/* iterate across the active hierarchies */ -#define for_each_active_root(root) \ +/* iterate across the hierarchies */ +#define for_each_root(root) \ list_for_each_entry((root), &cgroup_roots, root_list) -static inline struct cgroup *__d_cgrp(struct dentry *dentry) -{ - return dentry->d_fsdata; -} - -static inline struct cfent *__d_cfe(struct dentry *dentry) -{ - return dentry->d_fsdata; -} - -static inline struct cftype *__d_cft(struct dentry *dentry) -{ - return __d_cfe(dentry)->type; -} - /** * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive. * @cgrp: the cgroup to be checked for liveness @@ -347,23 +341,23 @@ struct cgrp_cset_link { struct list_head cgrp_link; }; -/* The default css_set - used by init and its children prior to any +/* + * The default css_set - used by init and its children prior to any * hierarchies being mounted. It contains a pointer to the root state * for each subsystem. Also used to anchor the list of css_sets. Not * reference-counted, to improve performance when child cgroups * haven't been created. */ +static struct css_set init_css_set = { + .refcount = ATOMIC_INIT(1), + .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), + .tasks = LIST_HEAD_INIT(init_css_set.tasks), + .mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks), + .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node), + .mg_node = LIST_HEAD_INIT(init_css_set.mg_node), +}; -static struct css_set init_css_set; -static struct cgrp_cset_link init_cgrp_cset_link; - -/* - * css_set_lock protects the list of css_set objects, and the chain of - * tasks off each css_set. Nests outside task->alloc_lock due to - * css_task_iter_start(). - */ -static DEFINE_RWLOCK(css_set_lock); -static int css_set_count; +static int css_set_count = 1; /* 1 for init_css_set */ /* * hash table for cgroup groups. This improves the performance to find @@ -386,30 +380,14 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[]) return key; } -/* - * We don't maintain the lists running through each css_set to its task - * until after the first call to css_task_iter_start(). This reduces the - * fork()/exit() overhead for people who have cgroups compiled into their - * kernel but not actually in use. - */ -static int use_task_css_set_links __read_mostly; - -static void __put_css_set(struct css_set *cset, int taskexit) +static void put_css_set_locked(struct css_set *cset, bool taskexit) { struct cgrp_cset_link *link, *tmp_link; - /* - * Ensure that the refcount doesn't hit zero while any readers - * can see it. Similar to atomic_dec_and_lock(), but for an - * rwlock - */ - if (atomic_add_unless(&cset->refcount, -1, 1)) - return; - write_lock(&css_set_lock); - if (!atomic_dec_and_test(&cset->refcount)) { - write_unlock(&css_set_lock); + lockdep_assert_held(&css_set_rwsem); + + if (!atomic_dec_and_test(&cset->refcount)) return; - } /* This css_set is dead. unlink it and release cgroup refcounts */ hash_del(&cset->hlist); @@ -421,7 +399,7 @@ static void __put_css_set(struct css_set *cset, int taskexit) list_del(&link->cset_link); list_del(&link->cgrp_link); - /* @cgrp can't go away while we're holding css_set_lock */ + /* @cgrp can't go away while we're holding css_set_rwsem */ if (list_empty(&cgrp->cset_links) && notify_on_release(cgrp)) { if (taskexit) set_bit(CGRP_RELEASABLE, &cgrp->flags); @@ -431,10 +409,24 @@ static void __put_css_set(struct css_set *cset, int taskexit) kfree(link); } - write_unlock(&css_set_lock); kfree_rcu(cset, rcu_head); } +static void put_css_set(struct css_set *cset, bool taskexit) +{ + /* + * Ensure that the refcount doesn't hit zero while any readers + * can see it. Similar to atomic_dec_and_lock(), but for an + * rwlock + */ + if (atomic_add_unless(&cset->refcount, -1, 1)) + return; + + down_write(&css_set_rwsem); + put_css_set_locked(cset, taskexit); + up_write(&css_set_rwsem); +} + /* * refcounted get/put for css_set objects */ @@ -443,16 +435,6 @@ static inline void get_css_set(struct css_set *cset) atomic_inc(&cset->refcount); } -static inline void put_css_set(struct css_set *cset) -{ - __put_css_set(cset, 0); -} - -static inline void put_css_set_taskexit(struct css_set *cset) -{ - __put_css_set(cset, 1); -} - /** * compare_css_sets - helper function for find_existing_css_set(). * @cset: candidate css_set being tested @@ -535,7 +517,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset, struct cgroup *cgrp, struct cgroup_subsys_state *template[]) { - struct cgroupfs_root *root = cgrp->root; + struct cgroup_root *root = cgrp->root; struct cgroup_subsys *ss; struct css_set *cset; unsigned long key; @@ -547,7 +529,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset, * won't change, so no need for locking. */ for_each_subsys(ss, i) { - if (root->subsys_mask & (1UL << i)) { + if (root->cgrp.subsys_mask & (1UL << i)) { /* Subsystem is in this hierarchy. So we want * the subsystem state from the new * cgroup */ @@ -652,11 +634,11 @@ static struct css_set *find_css_set(struct css_set *old_cset, /* First see if we already have a cgroup group that matches * the desired set */ - read_lock(&css_set_lock); + down_read(&css_set_rwsem); cset = find_existing_css_set(old_cset, cgrp, template); if (cset) get_css_set(cset); - read_unlock(&css_set_lock); + up_read(&css_set_rwsem); if (cset) return cset; @@ -674,13 +656,16 @@ static struct css_set *find_css_set(struct css_set *old_cset, atomic_set(&cset->refcount, 1); INIT_LIST_HEAD(&cset->cgrp_links); INIT_LIST_HEAD(&cset->tasks); + INIT_LIST_HEAD(&cset->mg_tasks); + INIT_LIST_HEAD(&cset->mg_preload_node); + INIT_LIST_HEAD(&cset->mg_node); INIT_HLIST_NODE(&cset->hlist); /* Copy the set of subsystem state objects generated in * find_existing_css_set() */ memcpy(cset->subsys, template, sizeof(cset->subsys)); - write_lock(&css_set_lock); + down_write(&css_set_rwsem); /* Add reference counts and links from the new css_set. */ list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; @@ -698,31 +683,105 @@ static struct css_set *find_css_set(struct css_set *old_cset, key = css_set_hash(cset->subsys); hash_add(css_set_table, &cset->hlist, key); - write_unlock(&css_set_lock); + up_write(&css_set_rwsem); return cset; } -/* - * Return the cgroup for "task" from the given hierarchy. Must be - * called with cgroup_mutex held. - */ -static struct cgroup *task_cgroup_from_root(struct task_struct *task, - struct cgroupfs_root *root) +static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root) { - struct css_set *cset; - struct cgroup *res = NULL; + struct cgroup *root_cgrp = kf_root->kn->priv; + + return root_cgrp->root; +} + +static int cgroup_init_root_id(struct cgroup_root *root) +{ + int id; + + lockdep_assert_held(&cgroup_mutex); + + id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, 0, 0, GFP_KERNEL); + if (id < 0) + return id; + + root->hierarchy_id = id; + return 0; +} + +static void cgroup_exit_root_id(struct cgroup_root *root) +{ + lockdep_assert_held(&cgroup_mutex); + + if (root->hierarchy_id) { + idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id); + root->hierarchy_id = 0; + } +} + +static void cgroup_free_root(struct cgroup_root *root) +{ + if (root) { + /* hierarhcy ID shoulid already have been released */ + WARN_ON_ONCE(root->hierarchy_id); + + idr_destroy(&root->cgroup_idr); + kfree(root); + } +} + +static void cgroup_destroy_root(struct cgroup_root *root) +{ + struct cgroup *cgrp = &root->cgrp; + struct cgrp_cset_link *link, *tmp_link; + + mutex_lock(&cgroup_tree_mutex); + mutex_lock(&cgroup_mutex); + + BUG_ON(atomic_read(&root->nr_cgrps)); + BUG_ON(!list_empty(&cgrp->children)); + + /* Rebind all subsystems back to the default hierarchy */ + rebind_subsystems(&cgrp_dfl_root, cgrp->subsys_mask); - BUG_ON(!mutex_is_locked(&cgroup_mutex)); - read_lock(&css_set_lock); /* - * No need to lock the task - since we hold cgroup_mutex the - * task can't change groups, so the only thing that can happen - * is that it exits and its css is set back to init_css_set. + * Release all the links from cset_links to this hierarchy's + * root cgroup */ - cset = task_css_set(task); + down_write(&css_set_rwsem); + + list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) { + list_del(&link->cset_link); + list_del(&link->cgrp_link); + kfree(link); + } + up_write(&css_set_rwsem); + + if (!list_empty(&root->root_list)) { + list_del(&root->root_list); + cgroup_root_count--; + } + + cgroup_exit_root_id(root); + + mutex_unlock(&cgroup_mutex); + mutex_unlock(&cgroup_tree_mutex); + + kernfs_destroy_root(root->kf_root); + cgroup_free_root(root); +} + +/* look up cgroup associated with given css_set on the specified hierarchy */ +static struct cgroup *cset_cgroup_from_root(struct css_set *cset, + struct cgroup_root *root) +{ + struct cgroup *res = NULL; + + lockdep_assert_held(&cgroup_mutex); + lockdep_assert_held(&css_set_rwsem); + if (cset == &init_css_set) { - res = &root->top_cgroup; + res = &root->cgrp; } else { struct cgrp_cset_link *link; @@ -735,16 +794,27 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task, } } } - read_unlock(&css_set_lock); + BUG_ON(!res); return res; } /* - * There is one global cgroup mutex. We also require taking - * task_lock() when dereferencing a task's cgroup subsys pointers. - * See "The task_lock() exception", at the end of this comment. - * + * Return the cgroup for "task" from the given hierarchy. Must be + * called with cgroup_mutex and css_set_rwsem held. + */ +static struct cgroup *task_cgroup_from_root(struct task_struct *task, + struct cgroup_root *root) +{ + /* + * No need to lock the task - since we hold cgroup_mutex the + * task can't change groups, so the only thing that can happen + * is that it exits and its css is set back to init_css_set. + */ + return cset_cgroup_from_root(task_css_set(task), root); +} + +/* * A task must hold cgroup_mutex to modify cgroups. * * Any task can increment and decrement the count field without lock. @@ -770,98 +840,79 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task, * A cgroup can only be deleted if both its 'count' of using tasks * is zero, and its list of 'children' cgroups is empty. Since all * tasks in the system use _some_ cgroup, and since there is always at - * least one task in the system (init, pid == 1), therefore, top_cgroup + * least one task in the system (init, pid == 1), therefore, root cgroup * always has either children cgroups and/or using tasks. So we don't - * need a special hack to ensure that top_cgroup cannot be deleted. - * - * The task_lock() exception - * - * The need for this exception arises from the action of - * cgroup_attach_task(), which overwrites one task's cgroup pointer with - * another. It does so using cgroup_mutex, however there are - * several performance critical places that need to reference - * task->cgroup without the expense of grabbing a system global - * mutex. Therefore except as noted below, when dereferencing or, as - * in cgroup_attach_task(), modifying a task's cgroup pointer we use - * task_lock(), which acts on a spinlock (task->alloc_lock) already in - * the task_struct routinely used for such matters. + * need a special hack to ensure that root cgroup cannot be deleted. * * P.S. One more locking exception. RCU is used to guard the * update of a tasks cgroup pointer by cgroup_attach_task() */ -/* - * A couple of forward declarations required, due to cyclic reference loop: - * cgroup_mkdir -> cgroup_create -> cgroup_populate_dir -> - * cgroup_add_file -> cgroup_create_file -> cgroup_dir_inode_operations - * -> cgroup_mkdir. - */ - -static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); -static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry); static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask); -static const struct inode_operations cgroup_dir_inode_operations; +static struct kernfs_syscall_ops cgroup_kf_syscall_ops; static const struct file_operations proc_cgroupstats_operations; -static struct backing_dev_info cgroup_backing_dev_info = { - .name = "cgroup", - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, -}; - -static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb) +static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft, + char *buf) { - struct inode *inode = new_inode(sb); - - if (inode) { - inode->i_ino = get_next_ino(); - inode->i_mode = mode; - inode->i_uid = current_fsuid(); - inode->i_gid = current_fsgid(); - inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; - inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info; - } - return inode; + if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) && + !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) + snprintf(buf, CGROUP_FILE_NAME_MAX, "%s.%s", + cft->ss->name, cft->name); + else + strncpy(buf, cft->name, CGROUP_FILE_NAME_MAX); + return buf; } -static struct cgroup_name *cgroup_alloc_name(struct dentry *dentry) +/** + * cgroup_file_mode - deduce file mode of a control file + * @cft: the control file in question + * + * returns cft->mode if ->mode is not 0 + * returns S_IRUGO|S_IWUSR if it has both a read and a write handler + * returns S_IRUGO if it has only a read handler + * returns S_IWUSR if it has only a write hander + */ +static umode_t cgroup_file_mode(const struct cftype *cft) { - struct cgroup_name *name; + umode_t mode = 0; - name = kmalloc(sizeof(*name) + dentry->d_name.len + 1, GFP_KERNEL); - if (!name) - return NULL; - strcpy(name->name, dentry->d_name.name); - return name; + if (cft->mode) + return cft->mode; + + if (cft->read_u64 || cft->read_s64 || cft->seq_show) + mode |= S_IRUGO; + + if (cft->write_u64 || cft->write_s64 || cft->write_string || + cft->trigger) + mode |= S_IWUSR; + + return mode; } static void cgroup_free_fn(struct work_struct *work) { struct cgroup *cgrp = container_of(work, struct cgroup, destroy_work); - mutex_lock(&cgroup_mutex); - cgrp->root->number_of_cgroups--; - mutex_unlock(&cgroup_mutex); - - /* - * We get a ref to the parent's dentry, and put the ref when - * this cgroup is being freed, so it's guaranteed that the - * parent won't be destroyed before its children. - */ - dput(cgrp->parent->dentry); - - /* - * Drop the active superblock reference that we took when we - * created the cgroup. This will free cgrp->root, if we are - * holding the last reference to @sb. - */ - deactivate_super(cgrp->root->sb); - + atomic_dec(&cgrp->root->nr_cgrps); cgroup_pidlist_destroy_all(cgrp); - simple_xattrs_free(&cgrp->xattrs); - - kfree(rcu_dereference_raw(cgrp->name)); - kfree(cgrp); + if (cgrp->parent) { + /* + * We get a ref to the parent, and put the ref when this + * cgroup is being freed, so it's guaranteed that the + * parent won't be destroyed before its children. + */ + cgroup_put(cgrp->parent); + kernfs_put(cgrp->kn); + kfree(cgrp); + } else { + /* + * This is root cgroup's refcnt reaching zero, which + * indicates that the root should be released. + */ + cgroup_destroy_root(cgrp->root); + } } static void cgroup_free_rcu(struct rcu_head *head) @@ -872,73 +923,40 @@ static void cgroup_free_rcu(struct rcu_head *head) queue_work(cgroup_destroy_wq, &cgrp->destroy_work); } -static void cgroup_diput(struct dentry *dentry, struct inode *inode) -{ - /* is dentry a directory ? if so, kfree() associated cgroup */ - if (S_ISDIR(inode->i_mode)) { - struct cgroup *cgrp = dentry->d_fsdata; - - BUG_ON(!(cgroup_is_dead(cgrp))); - - /* - * XXX: cgrp->id is only used to look up css's. As cgroup - * and css's lifetimes will be decoupled, it should be made - * per-subsystem and moved to css->id so that lookups are - * successful until the target css is released. - */ - mutex_lock(&cgroup_mutex); - idr_remove(&cgrp->root->cgroup_idr, cgrp->id); - mutex_unlock(&cgroup_mutex); - cgrp->id = -1; - - call_rcu(&cgrp->rcu_head, cgroup_free_rcu); - } else { - struct cfent *cfe = __d_cfe(dentry); - struct cgroup *cgrp = dentry->d_parent->d_fsdata; - - WARN_ONCE(!list_empty(&cfe->node) && - cgrp != &cgrp->root->top_cgroup, - "cfe still linked for %s\n", cfe->type->name); - simple_xattrs_free(&cfe->xattrs); - kfree(cfe); - } - iput(inode); -} - -static void remove_dir(struct dentry *d) +static void cgroup_get(struct cgroup *cgrp) { - struct dentry *parent = dget(d->d_parent); - - d_delete(d); - simple_rmdir(parent->d_inode, d); - dput(parent); + WARN_ON_ONCE(cgroup_is_dead(cgrp)); + WARN_ON_ONCE(atomic_read(&cgrp->refcnt) <= 0); + atomic_inc(&cgrp->refcnt); } -static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) +static void cgroup_put(struct cgroup *cgrp) { - struct cfent *cfe; - - lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex); - lockdep_assert_held(&cgroup_mutex); + if (!atomic_dec_and_test(&cgrp->refcnt)) + return; + if (WARN_ON_ONCE(cgrp->parent && !cgroup_is_dead(cgrp))) + return; /* - * If we're doing cleanup due to failure of cgroup_create(), - * the corresponding @cfe may not exist. + * XXX: cgrp->id is only used to look up css's. As cgroup and + * css's lifetimes will be decoupled, it should be made + * per-subsystem and moved to css->id so that lookups are + * successful until the target css is released. */ - list_for_each_entry(cfe, &cgrp->files, node) { - struct dentry *d = cfe->dentry; + mutex_lock(&cgroup_mutex); + idr_remove(&cgrp->root->cgroup_idr, cgrp->id); + mutex_unlock(&cgroup_mutex); + cgrp->id = -1; - if (cft && cfe->type != cft) - continue; + call_rcu(&cgrp->rcu_head, cgroup_free_rcu); +} - dget(d); - d_delete(d); - simple_unlink(cgrp->dentry->d_inode, d); - list_del_init(&cfe->node); - dput(d); +static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) +{ + char name[CGROUP_FILE_NAME_MAX]; - break; - } + lockdep_assert_held(&cgroup_tree_mutex); + kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name)); } /** @@ -952,144 +970,106 @@ static void cgroup_clear_dir(struct cgroup *cgrp, unsigned long subsys_mask) int i; for_each_subsys(ss, i) { - struct cftype_set *set; + struct cftype *cfts; if (!test_bit(i, &subsys_mask)) continue; - list_for_each_entry(set, &ss->cftsets, node) - cgroup_addrm_files(cgrp, set->cfts, false); + list_for_each_entry(cfts, &ss->cfts, node) + cgroup_addrm_files(cgrp, cfts, false); } } -/* - * NOTE : the dentry must have been dget()'ed - */ -static void cgroup_d_remove_dir(struct dentry *dentry) -{ - struct dentry *parent; - - parent = dentry->d_parent; - spin_lock(&parent->d_lock); - spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); - list_del_init(&dentry->d_u.d_child); - spin_unlock(&dentry->d_lock); - spin_unlock(&parent->d_lock); - remove_dir(dentry); -} - -/* - * Call with cgroup_mutex held. Drops reference counts on modules, including - * any duplicate ones that parse_cgroupfs_options took. If this function - * returns an error, no reference counts are touched. - */ -static int rebind_subsystems(struct cgroupfs_root *root, - unsigned long added_mask, unsigned removed_mask) +static int rebind_subsystems(struct cgroup_root *dst_root, + unsigned long ss_mask) { - struct cgroup *cgrp = &root->top_cgroup; struct cgroup_subsys *ss; - unsigned long pinned = 0; - int i, ret; + int ssid, ret; - BUG_ON(!mutex_is_locked(&cgroup_mutex)); - BUG_ON(!mutex_is_locked(&cgroup_root_mutex)); + lockdep_assert_held(&cgroup_tree_mutex); + lockdep_assert_held(&cgroup_mutex); - /* Check that any added subsystems are currently free */ - for_each_subsys(ss, i) { - if (!(added_mask & (1 << i))) + for_each_subsys(ss, ssid) { + if (!(ss_mask & (1 << ssid))) continue; - /* is the subsystem mounted elsewhere? */ - if (ss->root != &cgroup_dummy_root) { - ret = -EBUSY; - goto out_put; - } + /* if @ss is on the dummy_root, we can always move it */ + if (ss->root == &cgrp_dfl_root) + continue; - /* pin the module */ - if (!try_module_get(ss->module)) { - ret = -ENOENT; - goto out_put; - } - pinned |= 1 << i; - } + /* if @ss has non-root cgroups attached to it, can't move */ + if (!list_empty(&ss->root->cgrp.children)) + return -EBUSY; - /* subsys could be missing if unloaded between parsing and here */ - if (added_mask != pinned) { - ret = -ENOENT; - goto out_put; + /* can't move between two non-dummy roots either */ + if (dst_root != &cgrp_dfl_root) + return -EBUSY; } - ret = cgroup_populate_dir(cgrp, added_mask); - if (ret) - goto out_put; + ret = cgroup_populate_dir(&dst_root->cgrp, ss_mask); + if (ret) { + if (dst_root != &cgrp_dfl_root) + return ret; + + /* + * Rebinding back to the default root is not allowed to + * fail. Using both default and non-default roots should + * be rare. Moving subsystems back and forth even more so. + * Just warn about it and continue. + */ + if (cgrp_dfl_root_visible) { + pr_warning("cgroup: failed to create files (%d) while rebinding 0x%lx to default root\n", + ret, ss_mask); + pr_warning("cgroup: you may retry by moving them to a different hierarchy and unbinding\n"); + } + } /* * Nothing can fail from this point on. Remove files for the * removed subsystems and rebind each subsystem. */ - cgroup_clear_dir(cgrp, removed_mask); - - for_each_subsys(ss, i) { - unsigned long bit = 1UL << i; - - if (bit & added_mask) { - /* We're binding this subsystem to this hierarchy */ - BUG_ON(cgroup_css(cgrp, ss)); - BUG_ON(!cgroup_css(cgroup_dummy_top, ss)); - BUG_ON(cgroup_css(cgroup_dummy_top, ss)->cgroup != cgroup_dummy_top); + mutex_unlock(&cgroup_mutex); + for_each_subsys(ss, ssid) + if (ss_mask & (1 << ssid)) + cgroup_clear_dir(&ss->root->cgrp, 1 << ssid); + mutex_lock(&cgroup_mutex); - rcu_assign_pointer(cgrp->subsys[i], - cgroup_css(cgroup_dummy_top, ss)); - cgroup_css(cgrp, ss)->cgroup = cgrp; + for_each_subsys(ss, ssid) { + struct cgroup_root *src_root; + struct cgroup_subsys_state *css; - ss->root = root; - if (ss->bind) - ss->bind(cgroup_css(cgrp, ss)); + if (!(ss_mask & (1 << ssid))) + continue; - /* refcount was already taken, and we're keeping it */ - root->subsys_mask |= bit; - } else if (bit & removed_mask) { - /* We're removing this subsystem */ - BUG_ON(cgroup_css(cgrp, ss) != cgroup_css(cgroup_dummy_top, ss)); - BUG_ON(cgroup_css(cgrp, ss)->cgroup != cgrp); + src_root = ss->root; + css = cgroup_css(&src_root->cgrp, ss); - if (ss->bind) - ss->bind(cgroup_css(cgroup_dummy_top, ss)); + WARN_ON(!css || cgroup_css(&dst_root->cgrp, ss)); - cgroup_css(cgroup_dummy_top, ss)->cgroup = cgroup_dummy_top; - RCU_INIT_POINTER(cgrp->subsys[i], NULL); + RCU_INIT_POINTER(src_root->cgrp.subsys[ssid], NULL); + rcu_assign_pointer(dst_root->cgrp.subsys[ssid], css); + ss->root = dst_root; + css->cgroup = &dst_root->cgrp; - cgroup_subsys[i]->root = &cgroup_dummy_root; + src_root->cgrp.subsys_mask &= ~(1 << ssid); + dst_root->cgrp.subsys_mask |= 1 << ssid; - /* subsystem is now free - drop reference on module */ - module_put(ss->module); - root->subsys_mask &= ~bit; - } + if (ss->bind) + ss->bind(css); } - /* - * Mark @root has finished binding subsystems. @root->subsys_mask - * now matches the bound subsystems. - */ - root->flags |= CGRP_ROOT_SUBSYS_BOUND; - + kernfs_activate(dst_root->cgrp.kn); return 0; - -out_put: - for_each_subsys(ss, i) - if (pinned & (1 << i)) - module_put(ss->module); - return ret; } -static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry) +static int cgroup_show_options(struct seq_file *seq, + struct kernfs_root *kf_root) { - struct cgroupfs_root *root = dentry->d_sb->s_fs_info; + struct cgroup_root *root = cgroup_root_from_kf(kf_root); struct cgroup_subsys *ss; int ssid; - mutex_lock(&cgroup_root_mutex); for_each_subsys(ss, ssid) - if (root->subsys_mask & (1 << ssid)) + if (root->cgrp.subsys_mask & (1 << ssid)) seq_printf(seq, ",%s", ss->name); if (root->flags & CGRP_ROOT_SANE_BEHAVIOR) seq_puts(seq, ",sane_behavior"); @@ -1097,13 +1077,16 @@ static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry) seq_puts(seq, ",noprefix"); if (root->flags & CGRP_ROOT_XATTR) seq_puts(seq, ",xattr"); + + spin_lock(&release_agent_path_lock); if (strlen(root->release_agent_path)) seq_printf(seq, ",release_agent=%s", root->release_agent_path); - if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags)) + spin_unlock(&release_agent_path_lock); + + if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags)) seq_puts(seq, ",clone_children"); if (strlen(root->name)) seq_printf(seq, ",name=%s", root->name); - mutex_unlock(&cgroup_root_mutex); return 0; } @@ -1115,9 +1098,6 @@ struct cgroup_sb_opts { char *name; /* User explicitly requested empty subsystem */ bool none; - - struct cgroupfs_root *new_root; - }; /* @@ -1137,7 +1117,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) BUG_ON(!mutex_is_locked(&cgroup_mutex)); #ifdef CONFIG_CPUSETS - mask = ~(1UL << cpuset_subsys_id); + mask = ~(1UL << cpuset_cgrp_id); #endif memset(opts, 0, sizeof(*opts)); @@ -1227,30 +1207,34 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) return -ENOENT; } - /* - * If the 'all' option was specified select all the subsystems, - * otherwise if 'none', 'name=' and a subsystem name options - * were not specified, let's default to 'all' - */ - if (all_ss || (!one_ss && !opts->none && !opts->name)) - for_each_subsys(ss, i) - if (!ss->disabled) - set_bit(i, &opts->subsys_mask); - /* Consistency checks */ if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) { pr_warning("cgroup: sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n"); - if (opts->flags & CGRP_ROOT_NOPREFIX) { - pr_err("cgroup: sane_behavior: noprefix is not allowed\n"); + if ((opts->flags & (CGRP_ROOT_NOPREFIX | CGRP_ROOT_XATTR)) || + opts->cpuset_clone_children || opts->release_agent || + opts->name) { + pr_err("cgroup: sane_behavior: noprefix, xattr, clone_children, release_agent and name are not allowed\n"); return -EINVAL; } + } else { + /* + * If the 'all' option was specified select all the + * subsystems, otherwise if 'none', 'name=' and a subsystem + * name options were not specified, let's default to 'all' + */ + if (all_ss || (!one_ss && !opts->none && !opts->name)) + for_each_subsys(ss, i) + if (!ss->disabled) + set_bit(i, &opts->subsys_mask); - if (opts->cpuset_clone_children) { - pr_err("cgroup: sane_behavior: clone_children is not allowed\n"); + /* + * We either have to specify by name or by subsystems. (So + * all empty hierarchies must have a name). + */ + if (!opts->subsys_mask && !opts->name) return -EINVAL; - } } /* @@ -1266,21 +1250,13 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) if (opts->subsys_mask && opts->none) return -EINVAL; - /* - * We either have to specify by name or by subsystems. (So all - * empty hierarchies must have a name). - */ - if (!opts->subsys_mask && !opts->name) - return -EINVAL; - return 0; } -static int cgroup_remount(struct super_block *sb, int *flags, char *data) +static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data) { int ret = 0; - struct cgroupfs_root *root = sb->s_fs_info; - struct cgroup *cgrp = &root->top_cgroup; + struct cgroup_root *root = cgroup_root_from_kf(kf_root); struct cgroup_sb_opts opts; unsigned long added_mask, removed_mask; @@ -1289,21 +1265,20 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data) return -EINVAL; } - mutex_lock(&cgrp->dentry->d_inode->i_mutex); + mutex_lock(&cgroup_tree_mutex); mutex_lock(&cgroup_mutex); - mutex_lock(&cgroup_root_mutex); /* See what subsystems are wanted */ ret = parse_cgroupfs_options(data, &opts); if (ret) goto out_unlock; - if (opts.subsys_mask != root->subsys_mask || opts.release_agent) + if (opts.subsys_mask != root->cgrp.subsys_mask || opts.release_agent) pr_warning("cgroup: option changes via remount are deprecated (pid=%d comm=%s)\n", task_tgid_nr(current), current->comm); - added_mask = opts.subsys_mask & ~root->subsys_mask; - removed_mask = root->subsys_mask & ~opts.subsys_mask; + added_mask = opts.subsys_mask & ~root->cgrp.subsys_mask; + removed_mask = root->cgrp.subsys_mask & ~opts.subsys_mask; /* Don't allow flags or name to change at remount */ if (((opts.flags ^ root->flags) & CGRP_ROOT_OPTION_MASK) || @@ -1316,422 +1291,332 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data) } /* remounting is not allowed for populated hierarchies */ - if (root->number_of_cgroups > 1) { + if (!list_empty(&root->cgrp.children)) { ret = -EBUSY; goto out_unlock; } - ret = rebind_subsystems(root, added_mask, removed_mask); + ret = rebind_subsystems(root, added_mask); if (ret) goto out_unlock; - if (opts.release_agent) + rebind_subsystems(&cgrp_dfl_root, removed_mask); + + if (opts.release_agent) { + spin_lock(&release_agent_path_lock); strcpy(root->release_agent_path, opts.release_agent); + spin_unlock(&release_agent_path_lock); + } out_unlock: kfree(opts.release_agent); kfree(opts.name); - mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); - mutex_unlock(&cgrp->dentry->d_inode->i_mutex); + mutex_unlock(&cgroup_tree_mutex); return ret; } -static const struct super_operations cgroup_ops = { - .statfs = simple_statfs, - .drop_inode = generic_delete_inode, - .show_options = cgroup_show_options, - .remount_fs = cgroup_remount, -}; +/* + * To reduce the fork() overhead for systems that are not actually using + * their cgroups capability, we don't maintain the lists running through + * each css_set to its tasks until we see the list actually used - in other + * words after the first mount. + */ +static bool use_task_css_set_links __read_mostly; + +static void cgroup_enable_task_cg_lists(void) +{ + struct task_struct *p, *g; + + down_write(&css_set_rwsem); + + if (use_task_css_set_links) + goto out_unlock; + + use_task_css_set_links = true; + + /* + * We need tasklist_lock because RCU is not safe against + * while_each_thread(). Besides, a forking task that has passed + * cgroup_post_fork() without seeing use_task_css_set_links = 1 + * is not guaranteed to have its child immediately visible in the + * tasklist if we walk through it with RCU. + */ + read_lock(&tasklist_lock); + do_each_thread(g, p) { + WARN_ON_ONCE(!list_empty(&p->cg_list) || + task_css_set(p) != &init_css_set); + + /* + * We should check if the process is exiting, otherwise + * it will race with cgroup_exit() in that the list + * entry won't be deleted though the process has exited. + * Do it while holding siglock so that we don't end up + * racing against cgroup_exit(). + */ + spin_lock_irq(&p->sighand->siglock); + if (!(p->flags & PF_EXITING)) { + struct css_set *cset = task_css_set(p); + + list_add(&p->cg_list, &cset->tasks); + get_css_set(cset); + } + spin_unlock_irq(&p->sighand->siglock); + } while_each_thread(g, p); + read_unlock(&tasklist_lock); +out_unlock: + up_write(&css_set_rwsem); +} static void init_cgroup_housekeeping(struct cgroup *cgrp) { + atomic_set(&cgrp->refcnt, 1); INIT_LIST_HEAD(&cgrp->sibling); INIT_LIST_HEAD(&cgrp->children); - INIT_LIST_HEAD(&cgrp->files); INIT_LIST_HEAD(&cgrp->cset_links); INIT_LIST_HEAD(&cgrp->release_list); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); cgrp->dummy_css.cgroup = cgrp; - simple_xattrs_init(&cgrp->xattrs); } -static void init_cgroup_root(struct cgroupfs_root *root) +static void init_cgroup_root(struct cgroup_root *root, + struct cgroup_sb_opts *opts) { - struct cgroup *cgrp = &root->top_cgroup; + struct cgroup *cgrp = &root->cgrp; INIT_LIST_HEAD(&root->root_list); - root->number_of_cgroups = 1; + atomic_set(&root->nr_cgrps, 1); cgrp->root = root; - RCU_INIT_POINTER(cgrp->name, &root_cgroup_name); init_cgroup_housekeeping(cgrp); idr_init(&root->cgroup_idr); -} - -static int cgroup_init_root_id(struct cgroupfs_root *root, int start, int end) -{ - int id; - lockdep_assert_held(&cgroup_mutex); - lockdep_assert_held(&cgroup_root_mutex); - - id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, start, end, - GFP_KERNEL); - if (id < 0) - return id; - - root->hierarchy_id = id; - return 0; -} - -static void cgroup_exit_root_id(struct cgroupfs_root *root) -{ - lockdep_assert_held(&cgroup_mutex); - lockdep_assert_held(&cgroup_root_mutex); - - if (root->hierarchy_id) { - idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id); - root->hierarchy_id = 0; - } -} - -static int cgroup_test_super(struct super_block *sb, void *data) -{ - struct cgroup_sb_opts *opts = data; - struct cgroupfs_root *root = sb->s_fs_info; - - /* If we asked for a name then it must match */ - if (opts->name && strcmp(opts->name, root->name)) - return 0; - - /* - * If we asked for subsystems (or explicitly for no - * subsystems) then they must match - */ - if ((opts->subsys_mask || opts->none) - && (opts->subsys_mask != root->subsys_mask)) - return 0; - - return 1; -} - -static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts) -{ - struct cgroupfs_root *root; - - if (!opts->subsys_mask && !opts->none) - return NULL; - - root = kzalloc(sizeof(*root), GFP_KERNEL); - if (!root) - return ERR_PTR(-ENOMEM); - - init_cgroup_root(root); - - /* - * We need to set @root->subsys_mask now so that @root can be - * matched by cgroup_test_super() before it finishes - * initialization; otherwise, competing mounts with the same - * options may try to bind the same subsystems instead of waiting - * for the first one leading to unexpected mount errors. - * SUBSYS_BOUND will be set once actual binding is complete. - */ - root->subsys_mask = opts->subsys_mask; root->flags = opts->flags; if (opts->release_agent) strcpy(root->release_agent_path, opts->release_agent); if (opts->name) strcpy(root->name, opts->name); if (opts->cpuset_clone_children) - set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags); - return root; + set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags); } -static void cgroup_free_root(struct cgroupfs_root *root) +static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask) { - if (root) { - /* hierarhcy ID shoulid already have been released */ - WARN_ON_ONCE(root->hierarchy_id); - - idr_destroy(&root->cgroup_idr); - kfree(root); - } -} + LIST_HEAD(tmp_links); + struct cgroup *root_cgrp = &root->cgrp; + struct css_set *cset; + int i, ret; -static int cgroup_set_super(struct super_block *sb, void *data) -{ - int ret; - struct cgroup_sb_opts *opts = data; + lockdep_assert_held(&cgroup_tree_mutex); + lockdep_assert_held(&cgroup_mutex); - /* If we don't have a new root, we can't set up a new sb */ - if (!opts->new_root) - return -EINVAL; + ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL); + if (ret < 0) + goto out; + root_cgrp->id = ret; - BUG_ON(!opts->subsys_mask && !opts->none); + /* + * We're accessing css_set_count without locking css_set_rwsem here, + * but that's OK - it can only be increased by someone holding + * cgroup_lock, and that's us. The worst that can happen is that we + * have some link structures left over + */ + ret = allocate_cgrp_cset_links(css_set_count, &tmp_links); + if (ret) + goto out; - ret = set_anon_super(sb, NULL); + ret = cgroup_init_root_id(root); if (ret) - return ret; + goto out; - sb->s_fs_info = opts->new_root; - opts->new_root->sb = sb; + root->kf_root = kernfs_create_root(&cgroup_kf_syscall_ops, + KERNFS_ROOT_CREATE_DEACTIVATED, + root_cgrp); + if (IS_ERR(root->kf_root)) { + ret = PTR_ERR(root->kf_root); + goto exit_root_id; + } + root_cgrp->kn = root->kf_root->kn; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; - sb->s_magic = CGROUP_SUPER_MAGIC; - sb->s_op = &cgroup_ops; + ret = cgroup_addrm_files(root_cgrp, cgroup_base_files, true); + if (ret) + goto destroy_root; - return 0; -} + ret = rebind_subsystems(root, ss_mask); + if (ret) + goto destroy_root; -static int cgroup_get_rootdir(struct super_block *sb) -{ - static const struct dentry_operations cgroup_dops = { - .d_iput = cgroup_diput, - .d_delete = always_delete_dentry, - }; + /* + * There must be no failure case after here, since rebinding takes + * care of subsystems' refcounts, which are explicitly dropped in + * the failure exit path. + */ + list_add(&root->root_list, &cgroup_roots); + cgroup_root_count++; - struct inode *inode = - cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb); + /* + * Link the root cgroup in this hierarchy into all the css_set + * objects. + */ + down_write(&css_set_rwsem); + hash_for_each(css_set_table, i, cset, hlist) + link_css_set(&tmp_links, cset, root_cgrp); + up_write(&css_set_rwsem); - if (!inode) - return -ENOMEM; + BUG_ON(!list_empty(&root_cgrp->children)); + BUG_ON(atomic_read(&root->nr_cgrps) != 1); - inode->i_fop = &simple_dir_operations; - inode->i_op = &cgroup_dir_inode_operations; - /* directories start off with i_nlink == 2 (for "." entry) */ - inc_nlink(inode); - sb->s_root = d_make_root(inode); - if (!sb->s_root) - return -ENOMEM; - /* for everything else we want ->d_op set */ - sb->s_d_op = &cgroup_dops; - return 0; + kernfs_activate(root_cgrp->kn); + ret = 0; + goto out; + +destroy_root: + kernfs_destroy_root(root->kf_root); + root->kf_root = NULL; +exit_root_id: + cgroup_exit_root_id(root); +out: + free_cgrp_cset_links(&tmp_links); + return ret; } static struct dentry *cgroup_mount(struct file_system_type *fs_type, int flags, const char *unused_dev_name, void *data) { + struct cgroup_root *root; struct cgroup_sb_opts opts; - struct cgroupfs_root *root; - int ret = 0; - struct super_block *sb; - struct cgroupfs_root *new_root; - struct list_head tmp_links; - struct inode *inode; - const struct cred *cred; + struct dentry *dentry; + int ret; + bool new_sb; - /* First find the desired set of subsystems */ + /* + * The first time anyone tries to mount a cgroup, enable the list + * linking each css_set to its tasks and fix up all existing tasks. + */ + if (!use_task_css_set_links) + cgroup_enable_task_cg_lists(); +retry: + mutex_lock(&cgroup_tree_mutex); mutex_lock(&cgroup_mutex); + + /* First find the desired set of subsystems */ ret = parse_cgroupfs_options(data, &opts); - mutex_unlock(&cgroup_mutex); if (ret) - goto out_err; - - /* - * Allocate a new cgroup root. We may not need it if we're - * reusing an existing hierarchy. - */ - new_root = cgroup_root_from_opts(&opts); - if (IS_ERR(new_root)) { - ret = PTR_ERR(new_root); - goto out_err; - } - opts.new_root = new_root; + goto out_unlock; - /* Locate an existing or new sb for this hierarchy */ - sb = sget(fs_type, cgroup_test_super, cgroup_set_super, 0, &opts); - if (IS_ERR(sb)) { - ret = PTR_ERR(sb); - cgroup_free_root(opts.new_root); - goto out_err; + /* look for a matching existing root */ + if (!opts.subsys_mask && !opts.none && !opts.name) { + cgrp_dfl_root_visible = true; + root = &cgrp_dfl_root; + cgroup_get(&root->cgrp); + ret = 0; + goto out_unlock; } - root = sb->s_fs_info; - BUG_ON(!root); - if (root == opts.new_root) { - /* We used the new root structure, so this is a new hierarchy */ - struct cgroup *root_cgrp = &root->top_cgroup; - struct cgroupfs_root *existing_root; - int i; - struct css_set *cset; - - BUG_ON(sb->s_root != NULL); + for_each_root(root) { + bool name_match = false; - ret = cgroup_get_rootdir(sb); - if (ret) - goto drop_new_super; - inode = sb->s_root->d_inode; - - mutex_lock(&inode->i_mutex); - mutex_lock(&cgroup_mutex); - mutex_lock(&cgroup_root_mutex); - - ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL); - if (ret < 0) - goto unlock_drop; - root_cgrp->id = ret; - - /* Check for name clashes with existing mounts */ - ret = -EBUSY; - if (strlen(root->name)) - for_each_active_root(existing_root) - if (!strcmp(existing_root->name, root->name)) - goto unlock_drop; - - /* - * We're accessing css_set_count without locking - * css_set_lock here, but that's OK - it can only be - * increased by someone holding cgroup_lock, and - * that's us. The worst that can happen is that we - * have some link structures left over - */ - ret = allocate_cgrp_cset_links(css_set_count, &tmp_links); - if (ret) - goto unlock_drop; - - /* ID 0 is reserved for dummy root, 1 for unified hierarchy */ - ret = cgroup_init_root_id(root, 2, 0); - if (ret) - goto unlock_drop; - - sb->s_root->d_fsdata = root_cgrp; - root_cgrp->dentry = sb->s_root; - - /* - * We're inside get_sb() and will call lookup_one_len() to - * create the root files, which doesn't work if SELinux is - * in use. The following cred dancing somehow works around - * it. See 2ce9738ba ("cgroupfs: use init_cred when - * populating new cgroupfs mount") for more details. - */ - cred = override_creds(&init_cred); - - ret = cgroup_addrm_files(root_cgrp, cgroup_base_files, true); - if (ret) - goto rm_base_files; - - ret = rebind_subsystems(root, root->subsys_mask, 0); - if (ret) - goto rm_base_files; - - revert_creds(cred); + if (root == &cgrp_dfl_root) + continue; /* - * There must be no failure case after here, since rebinding - * takes care of subsystems' refcounts, which are explicitly - * dropped in the failure exit path. + * If we asked for a name then it must match. Also, if + * name matches but sybsys_mask doesn't, we should fail. + * Remember whether name matched. */ + if (opts.name) { + if (strcmp(opts.name, root->name)) + continue; + name_match = true; + } - list_add(&root->root_list, &cgroup_roots); - cgroup_root_count++; - - /* Link the top cgroup in this hierarchy into all - * the css_set objects */ - write_lock(&css_set_lock); - hash_for_each(css_set_table, i, cset, hlist) - link_css_set(&tmp_links, cset, root_cgrp); - write_unlock(&css_set_lock); - - free_cgrp_cset_links(&tmp_links); - - BUG_ON(!list_empty(&root_cgrp->children)); - BUG_ON(root->number_of_cgroups != 1); - - mutex_unlock(&cgroup_root_mutex); - mutex_unlock(&cgroup_mutex); - mutex_unlock(&inode->i_mutex); - } else { /* - * We re-used an existing hierarchy - the new root (if - * any) is not needed + * If we asked for subsystems (or explicitly for no + * subsystems) then they must match. */ - cgroup_free_root(opts.new_root); + if ((opts.subsys_mask || opts.none) && + (opts.subsys_mask != root->cgrp.subsys_mask)) { + if (!name_match) + continue; + ret = -EBUSY; + goto out_unlock; + } if ((root->flags ^ opts.flags) & CGRP_ROOT_OPTION_MASK) { if ((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) { pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n"); ret = -EINVAL; - goto drop_new_super; + goto out_unlock; } else { pr_warning("cgroup: new mount options do not match the existing superblock, will be ignored\n"); } } - } - - kfree(opts.release_agent); - kfree(opts.name); - return dget(sb->s_root); - rm_base_files: - free_cgrp_cset_links(&tmp_links); - cgroup_addrm_files(&root->top_cgroup, cgroup_base_files, false); - revert_creds(cred); - unlock_drop: - cgroup_exit_root_id(root); - mutex_unlock(&cgroup_root_mutex); - mutex_unlock(&cgroup_mutex); - mutex_unlock(&inode->i_mutex); - drop_new_super: - deactivate_locked_super(sb); - out_err: - kfree(opts.release_agent); - kfree(opts.name); - return ERR_PTR(ret); -} - -static void cgroup_kill_sb(struct super_block *sb) -{ - struct cgroupfs_root *root = sb->s_fs_info; - struct cgroup *cgrp = &root->top_cgroup; - struct cgrp_cset_link *link, *tmp_link; - int ret; - - BUG_ON(!root); - - BUG_ON(root->number_of_cgroups != 1); - BUG_ON(!list_empty(&cgrp->children)); - - mutex_lock(&cgrp->dentry->d_inode->i_mutex); - mutex_lock(&cgroup_mutex); - mutex_lock(&cgroup_root_mutex); + /* + * A root's lifetime is governed by its root cgroup. Zero + * ref indicate that the root is being destroyed. Wait for + * destruction to complete so that the subsystems are free. + * We can use wait_queue for the wait but this path is + * super cold. Let's just sleep for a bit and retry. + */ + if (!atomic_inc_not_zero(&root->cgrp.refcnt)) { + mutex_unlock(&cgroup_mutex); + mutex_unlock(&cgroup_tree_mutex); + kfree(opts.release_agent); + kfree(opts.name); + msleep(10); + goto retry; + } - /* Rebind all subsystems back to the default hierarchy */ - if (root->flags & CGRP_ROOT_SUBSYS_BOUND) { - ret = rebind_subsystems(root, 0, root->subsys_mask); - /* Shouldn't be able to fail ... */ - BUG_ON(ret); + ret = 0; + goto out_unlock; } /* - * Release all the links from cset_links to this hierarchy's - * root cgroup + * No such thing, create a new one. name= matching without subsys + * specification is allowed for already existing hierarchies but we + * can't create new one without subsys specification. */ - write_lock(&css_set_lock); - - list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) { - list_del(&link->cset_link); - list_del(&link->cgrp_link); - kfree(link); + if (!opts.subsys_mask && !opts.none) { + ret = -EINVAL; + goto out_unlock; } - write_unlock(&css_set_lock); - if (!list_empty(&root->root_list)) { - list_del(&root->root_list); - cgroup_root_count--; + root = kzalloc(sizeof(*root), GFP_KERNEL); + if (!root) { + ret = -ENOMEM; + goto out_unlock; } - cgroup_exit_root_id(root); + init_cgroup_root(root, &opts); + + ret = cgroup_setup_root(root, opts.subsys_mask); + if (ret) + cgroup_free_root(root); - mutex_unlock(&cgroup_root_mutex); +out_unlock: mutex_unlock(&cgroup_mutex); - mutex_unlock(&cgrp->dentry->d_inode->i_mutex); + mutex_unlock(&cgroup_tree_mutex); + + kfree(opts.release_agent); + kfree(opts.name); - simple_xattrs_free(&cgrp->xattrs); + if (ret) + return ERR_PTR(ret); - kill_litter_super(sb); - cgroup_free_root(root); + dentry = kernfs_mount(fs_type, flags, root->kf_root, &new_sb); + if (IS_ERR(dentry) || !new_sb) + cgroup_put(&root->cgrp); + return dentry; +} + +static void cgroup_kill_sb(struct super_block *sb) +{ + struct kernfs_root *kf_root = kernfs_root_from_sb(sb); + struct cgroup_root *root = cgroup_root_from_kf(kf_root); + + cgroup_put(&root->cgrp); + kernfs_kill_sb(sb); } static struct file_system_type cgroup_fs_type = { @@ -1743,57 +1628,6 @@ static struct file_system_type cgroup_fs_type = { static struct kobject *cgroup_kobj; /** - * cgroup_path - generate the path of a cgroup - * @cgrp: the cgroup in question - * @buf: the buffer to write the path into - * @buflen: the length of the buffer - * - * Writes path of cgroup into buf. Returns 0 on success, -errno on error. - * - * We can't generate cgroup path using dentry->d_name, as accessing - * dentry->name must be protected by irq-unsafe dentry->d_lock or parent - * inode's i_mutex, while on the other hand cgroup_path() can be called - * with some irq-safe spinlocks held. - */ -int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen) -{ - int ret = -ENAMETOOLONG; - char *start; - - if (!cgrp->parent) { - if (strlcpy(buf, "/", buflen) >= buflen) - return -ENAMETOOLONG; - return 0; - } - - start = buf + buflen - 1; - *start = '\0'; - - rcu_read_lock(); - do { - const char *name = cgroup_name(cgrp); - int len; - - len = strlen(name); - if ((start -= len) < buf) - goto out; - memcpy(start, name, len); - - if (--start < buf) - goto out; - *start = '/'; - - cgrp = cgrp->parent; - } while (cgrp->parent); - ret = 0; - memmove(buf, start, buf + buflen - start); -out: - rcu_read_unlock(); - return ret; -} -EXPORT_SYMBOL_GPL(cgroup_path); - -/** * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy * @task: target task * @buf: the buffer to write the path into @@ -1804,49 +1638,55 @@ EXPORT_SYMBOL_GPL(cgroup_path); * function grabs cgroup_mutex and shouldn't be used inside locks used by * cgroup controller callbacks. * - * Returns 0 on success, fails with -%ENAMETOOLONG if @buflen is too short. + * Return value is the same as kernfs_path(). */ -int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) +char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) { - struct cgroupfs_root *root; + struct cgroup_root *root; struct cgroup *cgrp; - int hierarchy_id = 1, ret = 0; - - if (buflen < 2) - return -ENAMETOOLONG; + int hierarchy_id = 1; + char *path = NULL; mutex_lock(&cgroup_mutex); + down_read(&css_set_rwsem); root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id); if (root) { cgrp = task_cgroup_from_root(task, root); - ret = cgroup_path(cgrp, buf, buflen); + path = cgroup_path(cgrp, buf, buflen); } else { /* if no hierarchy exists, everyone is in "/" */ - memcpy(buf, "/", 2); + if (strlcpy(buf, "/", buflen) < buflen) + path = buf; } + up_read(&css_set_rwsem); mutex_unlock(&cgroup_mutex); - return ret; + return path; } EXPORT_SYMBOL_GPL(task_cgroup_path); -/* - * Control Group taskset - */ -struct task_and_cgroup { - struct task_struct *task; - struct cgroup *cgrp; - struct css_set *cset; -}; - +/* used to track tasks and other necessary states during migration */ struct cgroup_taskset { - struct task_and_cgroup single; - struct flex_array *tc_array; - int tc_array_len; - int idx; - struct cgroup *cur_cgrp; + /* the src and dst cset list running through cset->mg_node */ + struct list_head src_csets; + struct list_head dst_csets; + + /* + * Fields for cgroup_taskset_*() iteration. + * + * Before migration is committed, the target migration tasks are on + * ->mg_tasks of the csets on ->src_csets. After, on ->mg_tasks of + * the csets on ->dst_csets. ->csets point to either ->src_csets + * or ->dst_csets depending on whether migration is committed. + * + * ->cur_csets and ->cur_task point to the current task position + * during iteration. + */ + struct list_head *csets; + struct css_set *cur_cset; + struct task_struct *cur_task; }; /** @@ -1857,15 +1697,11 @@ struct cgroup_taskset { */ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset) { - if (tset->tc_array) { - tset->idx = 0; - return cgroup_taskset_next(tset); - } else { - tset->cur_cgrp = tset->single.cgrp; - return tset->single.task; - } + tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node); + tset->cur_task = NULL; + + return cgroup_taskset_next(tset); } -EXPORT_SYMBOL_GPL(cgroup_taskset_first); /** * cgroup_taskset_next - iterate to the next task in taskset @@ -1876,48 +1712,36 @@ EXPORT_SYMBOL_GPL(cgroup_taskset_first); */ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset) { - struct task_and_cgroup *tc; + struct css_set *cset = tset->cur_cset; + struct task_struct *task = tset->cur_task; - if (!tset->tc_array || tset->idx >= tset->tc_array_len) - return NULL; + while (&cset->mg_node != tset->csets) { + if (!task) + task = list_first_entry(&cset->mg_tasks, + struct task_struct, cg_list); + else + task = list_next_entry(task, cg_list); - tc = flex_array_get(tset->tc_array, tset->idx++); - tset->cur_cgrp = tc->cgrp; - return tc->task; -} -EXPORT_SYMBOL_GPL(cgroup_taskset_next); + if (&task->cg_list != &cset->mg_tasks) { + tset->cur_cset = cset; + tset->cur_task = task; + return task; + } -/** - * cgroup_taskset_cur_css - return the matching css for the current task - * @tset: taskset of interest - * @subsys_id: the ID of the target subsystem - * - * Return the css for the current (last returned) task of @tset for - * subsystem specified by @subsys_id. This function must be preceded by - * either cgroup_taskset_first() or cgroup_taskset_next(). - */ -struct cgroup_subsys_state *cgroup_taskset_cur_css(struct cgroup_taskset *tset, - int subsys_id) -{ - return cgroup_css(tset->cur_cgrp, cgroup_subsys[subsys_id]); -} -EXPORT_SYMBOL_GPL(cgroup_taskset_cur_css); + cset = list_next_entry(cset, mg_node); + task = NULL; + } -/** - * cgroup_taskset_size - return the number of tasks in taskset - * @tset: taskset of interest - */ -int cgroup_taskset_size(struct cgroup_taskset *tset) -{ - return tset->tc_array ? tset->tc_array_len : 1; + return NULL; } -EXPORT_SYMBOL_GPL(cgroup_taskset_size); - -/* +/** * cgroup_task_migrate - move a task from one cgroup to another. + * @old_cgrp; the cgroup @tsk is being migrated from + * @tsk: the task being migrated + * @new_cset: the new css_set @tsk is being attached to * - * Must be called with cgroup_mutex and threadgroup locked. + * Must be called with cgroup_mutex, threadgroup and css_set_rwsem locked. */ static void cgroup_task_migrate(struct cgroup *old_cgrp, struct task_struct *tsk, @@ -1925,6 +1749,9 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp, { struct css_set *old_cset; + lockdep_assert_held(&cgroup_mutex); + lockdep_assert_held(&css_set_rwsem); + /* * We are synchronized through threadgroup_lock() against PF_EXITING * setting such that we can't race against cgroup_exit() changing the @@ -1933,15 +1760,16 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp, WARN_ON_ONCE(tsk->flags & PF_EXITING); old_cset = task_css_set(tsk); - task_lock(tsk); + get_css_set(new_cset); rcu_assign_pointer(tsk->cgroups, new_cset); - task_unlock(tsk); - /* Update the css_set linked lists if we're using them */ - write_lock(&css_set_lock); - if (!list_empty(&tsk->cg_list)) - list_move(&tsk->cg_list, &new_cset->tasks); - write_unlock(&css_set_lock); + /* + * Use move_tail so that cgroup_taskset_first() still returns the + * leader after migration. This works because cgroup_migrate() + * ensures that the dst_cset of the leader is the first on the + * tset's dst_csets list. + */ + list_move_tail(&tsk->cg_list, &new_cset->mg_tasks); /* * We just gained a reference on old_cset by taking it from the @@ -1949,100 +1777,199 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp, * we're safe to drop it here; it will be freed under RCU. */ set_bit(CGRP_RELEASABLE, &old_cgrp->flags); - put_css_set(old_cset); + put_css_set_locked(old_cset, false); } /** - * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup - * @cgrp: the cgroup to attach to - * @tsk: the task or the leader of the threadgroup to be attached - * @threadgroup: attach the whole threadgroup? + * cgroup_migrate_finish - cleanup after attach + * @preloaded_csets: list of preloaded css_sets * - * Call holding cgroup_mutex and the group_rwsem of the leader. Will take - * task_lock of @tsk or each thread in the threadgroup individually in turn. + * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst(). See + * those functions for details. */ -static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk, - bool threadgroup) +static void cgroup_migrate_finish(struct list_head *preloaded_csets) { - int retval, i, group_size; - struct cgroupfs_root *root = cgrp->root; - struct cgroup_subsys_state *css, *failed_css = NULL; - /* threadgroup list cursor and array */ - struct task_struct *leader = tsk; - struct task_and_cgroup *tc; - struct flex_array *group; - struct cgroup_taskset tset = { }; + struct css_set *cset, *tmp_cset; - /* - * step 0: in order to do expensive, possibly blocking operations for - * every thread, we cannot iterate the thread group list, since it needs - * rcu or tasklist locked. instead, build an array of all threads in the - * group - group_rwsem prevents new threads from appearing, and if - * threads exit, this will just be an over-estimate. - */ - if (threadgroup) - group_size = get_nr_threads(tsk); - else - group_size = 1; - /* flex_array supports very large thread-groups better than kmalloc. */ - group = flex_array_alloc(sizeof(*tc), group_size, GFP_KERNEL); - if (!group) - return -ENOMEM; - /* pre-allocate to guarantee space while iterating in rcu read-side. */ - retval = flex_array_prealloc(group, 0, group_size, GFP_KERNEL); - if (retval) - goto out_free_group_list; + lockdep_assert_held(&cgroup_mutex); + + down_write(&css_set_rwsem); + list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) { + cset->mg_src_cgrp = NULL; + cset->mg_dst_cset = NULL; + list_del_init(&cset->mg_preload_node); + put_css_set_locked(cset, false); + } + up_write(&css_set_rwsem); +} + +/** + * cgroup_migrate_add_src - add a migration source css_set + * @src_cset: the source css_set to add + * @dst_cgrp: the destination cgroup + * @preloaded_csets: list of preloaded css_sets + * + * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp. Pin + * @src_cset and add it to @preloaded_csets, which should later be cleaned + * up by cgroup_migrate_finish(). + * + * This function may be called without holding threadgroup_lock even if the + * target is a process. Threads may be created and destroyed but as long + * as cgroup_mutex is not dropped, no new css_set can be put into play and + * the preloaded css_sets are guaranteed to cover all migrations. + */ +static void cgroup_migrate_add_src(struct css_set *src_cset, + struct cgroup *dst_cgrp, + struct list_head *preloaded_csets) +{ + struct cgroup *src_cgrp; + + lockdep_assert_held(&cgroup_mutex); + lockdep_assert_held(&css_set_rwsem); + + src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); + + /* nothing to do if this cset already belongs to the cgroup */ + if (src_cgrp == dst_cgrp) + return; + + if (!list_empty(&src_cset->mg_preload_node)) + return; + + WARN_ON(src_cset->mg_src_cgrp); + WARN_ON(!list_empty(&src_cset->mg_tasks)); + WARN_ON(!list_empty(&src_cset->mg_node)); + + src_cset->mg_src_cgrp = src_cgrp; + get_css_set(src_cset); + list_add(&src_cset->mg_preload_node, preloaded_csets); +} + +/** + * cgroup_migrate_prepare_dst - prepare destination css_sets for migration + * @dst_cgrp: the destination cgroup + * @preloaded_csets: list of preloaded source css_sets + * + * Tasks are about to be moved to @dst_cgrp and all the source css_sets + * have been preloaded to @preloaded_csets. This function looks up and + * pins all destination css_sets, links each to its source, and put them on + * @preloaded_csets. + * + * This function must be called after cgroup_migrate_add_src() has been + * called on each migration source css_set. After migration is performed + * using cgroup_migrate(), cgroup_migrate_finish() must be called on + * @preloaded_csets. + */ +static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp, + struct list_head *preloaded_csets) +{ + LIST_HEAD(csets); + struct css_set *src_cset; + + lockdep_assert_held(&cgroup_mutex); + + /* look up the dst cset for each src cset and link it to src */ + list_for_each_entry(src_cset, preloaded_csets, mg_preload_node) { + struct css_set *dst_cset; + + dst_cset = find_css_set(src_cset, dst_cgrp); + if (!dst_cset) + goto err; + + WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset); + src_cset->mg_dst_cset = dst_cset; + + if (list_empty(&dst_cset->mg_preload_node)) + list_add(&dst_cset->mg_preload_node, &csets); + else + put_css_set(dst_cset, false); + } + + list_splice(&csets, preloaded_csets); + return 0; +err: + cgroup_migrate_finish(&csets); + return -ENOMEM; +} + +/** + * cgroup_migrate - migrate a process or task to a cgroup + * @cgrp: the destination cgroup + * @leader: the leader of the process or the task to migrate + * @threadgroup: whether @leader points to the whole process or a single task + * + * Migrate a process or task denoted by @leader to @cgrp. If migrating a + * process, the caller must be holding threadgroup_lock of @leader. The + * caller is also responsible for invoking cgroup_migrate_add_src() and + * cgroup_migrate_prepare_dst() on the targets before invoking this + * function and following up with cgroup_migrate_finish(). + * + * As long as a controller's ->can_attach() doesn't fail, this function is + * guaranteed to succeed. This means that, excluding ->can_attach() + * failure, when migrating multiple targets, the success or failure can be + * decided for all targets by invoking group_migrate_prepare_dst() before + * actually starting migrating. + */ +static int cgroup_migrate(struct cgroup *cgrp, struct task_struct *leader, + bool threadgroup) +{ + struct cgroup_taskset tset = { + .src_csets = LIST_HEAD_INIT(tset.src_csets), + .dst_csets = LIST_HEAD_INIT(tset.dst_csets), + .csets = &tset.src_csets, + }; + struct cgroup_subsys_state *css, *failed_css = NULL; + struct css_set *cset, *tmp_cset; + struct task_struct *task, *tmp_task; + int i, ret; - i = 0; /* * Prevent freeing of tasks while we take a snapshot. Tasks that are * already PF_EXITING could be freed from underneath us unless we * take an rcu_read_lock. */ + down_write(&css_set_rwsem); rcu_read_lock(); + task = leader; do { - struct task_and_cgroup ent; + /* @task either already exited or can't exit until the end */ + if (task->flags & PF_EXITING) + goto next; - /* @tsk either already exited or can't exit until the end */ - if (tsk->flags & PF_EXITING) + /* leave @task alone if post_fork() hasn't linked it yet */ + if (list_empty(&task->cg_list)) goto next; - /* as per above, nr_threads may decrease, but not increase. */ - BUG_ON(i >= group_size); - ent.task = tsk; - ent.cgrp = task_cgroup_from_root(tsk, root); - /* nothing to do if this task is already in the cgroup */ - if (ent.cgrp == cgrp) + cset = task_css_set(task); + if (!cset->mg_src_cgrp) goto next; + /* - * saying GFP_ATOMIC has no effect here because we did prealloc - * earlier, but it's good form to communicate our expectations. + * cgroup_taskset_first() must always return the leader. + * Take care to avoid disturbing the ordering. */ - retval = flex_array_put(group, i, &ent, GFP_ATOMIC); - BUG_ON(retval != 0); - i++; + list_move_tail(&task->cg_list, &cset->mg_tasks); + if (list_empty(&cset->mg_node)) + list_add_tail(&cset->mg_node, &tset.src_csets); + if (list_empty(&cset->mg_dst_cset->mg_node)) + list_move_tail(&cset->mg_dst_cset->mg_node, + &tset.dst_csets); next: if (!threadgroup) break; - } while_each_thread(leader, tsk); + } while_each_thread(leader, task); rcu_read_unlock(); - /* remember the number of threads in the array for later. */ - group_size = i; - tset.tc_array = group; - tset.tc_array_len = group_size; + up_write(&css_set_rwsem); /* methods shouldn't be called if no task is actually migrating */ - retval = 0; - if (!group_size) - goto out_free_group_list; + if (list_empty(&tset.src_csets)) + return 0; - /* - * step 1: check that we can legitimately attach to the cgroup. - */ + /* check that we can legitimately attach to the cgroup */ for_each_css(css, i, cgrp) { if (css->ss->can_attach) { - retval = css->ss->can_attach(css, &tset); - if (retval) { + ret = css->ss->can_attach(css, &tset); + if (ret) { failed_css = css; goto out_cancel_attach; } @@ -2050,70 +1977,91 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk, } /* - * step 2: make sure css_sets exist for all threads to be migrated. - * we use find_css_set, which allocates a new one if necessary. + * Now that we're guaranteed success, proceed to move all tasks to + * the new cgroup. There are no failure cases after here, so this + * is the commit point. */ - for (i = 0; i < group_size; i++) { - struct css_set *old_cset; - - tc = flex_array_get(group, i); - old_cset = task_css_set(tc->task); - tc->cset = find_css_set(old_cset, cgrp); - if (!tc->cset) { - retval = -ENOMEM; - goto out_put_css_set_refs; - } + down_write(&css_set_rwsem); + list_for_each_entry(cset, &tset.src_csets, mg_node) { + list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) + cgroup_task_migrate(cset->mg_src_cgrp, task, + cset->mg_dst_cset); } + up_write(&css_set_rwsem); /* - * step 3: now that we're guaranteed success wrt the css_sets, - * proceed to move all tasks to the new cgroup. There are no - * failure cases after here, so this is the commit point. + * Migration is committed, all target tasks are now on dst_csets. + * Nothing is sensitive to fork() after this point. Notify + * controllers that migration is complete. */ - for (i = 0; i < group_size; i++) { - tc = flex_array_get(group, i); - cgroup_task_migrate(tc->cgrp, tc->task, tc->cset); - } - /* nothing is sensitive to fork() after this point. */ + tset.csets = &tset.dst_csets; - /* - * step 4: do subsystem attach callbacks. - */ for_each_css(css, i, cgrp) if (css->ss->attach) css->ss->attach(css, &tset); - /* - * step 5: success! and cleanup - */ - retval = 0; -out_put_css_set_refs: - if (retval) { - for (i = 0; i < group_size; i++) { - tc = flex_array_get(group, i); - if (!tc->cset) - break; - put_css_set(tc->cset); - } - } + ret = 0; + goto out_release_tset; + out_cancel_attach: - if (retval) { - for_each_css(css, i, cgrp) { - if (css == failed_css) - break; - if (css->ss->cancel_attach) - css->ss->cancel_attach(css, &tset); - } + for_each_css(css, i, cgrp) { + if (css == failed_css) + break; + if (css->ss->cancel_attach) + css->ss->cancel_attach(css, &tset); } -out_free_group_list: - flex_array_free(group); - return retval; +out_release_tset: + down_write(&css_set_rwsem); + list_splice_init(&tset.dst_csets, &tset.src_csets); + list_for_each_entry_safe(cset, tmp_cset, &tset.src_csets, mg_node) { + list_splice_tail_init(&cset->mg_tasks, &cset->tasks); + list_del_init(&cset->mg_node); + } + up_write(&css_set_rwsem); + return ret; +} + +/** + * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup + * @dst_cgrp: the cgroup to attach to + * @leader: the task or the leader of the threadgroup to be attached + * @threadgroup: attach the whole threadgroup? + * + * Call holding cgroup_mutex and threadgroup_lock of @leader. + */ +static int cgroup_attach_task(struct cgroup *dst_cgrp, + struct task_struct *leader, bool threadgroup) +{ + LIST_HEAD(preloaded_csets); + struct task_struct *task; + int ret; + + /* look up all src csets */ + down_read(&css_set_rwsem); + rcu_read_lock(); + task = leader; + do { + cgroup_migrate_add_src(task_css_set(task), dst_cgrp, + &preloaded_csets); + if (!threadgroup) + break; + } while_each_thread(leader, task); + rcu_read_unlock(); + up_read(&css_set_rwsem); + + /* prepare dst csets and commit */ + ret = cgroup_migrate_prepare_dst(dst_cgrp, &preloaded_csets); + if (!ret) + ret = cgroup_migrate(dst_cgrp, leader, threadgroup); + + cgroup_migrate_finish(&preloaded_csets); + return ret; } /* * Find the task_struct of the task to attach by vpid and pass it along to the * function to attach either it or all tasks in its threadgroup. Will lock - * cgroup_mutex and threadgroup; may take task_lock of task. + * cgroup_mutex and threadgroup. */ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup) { @@ -2198,12 +2146,19 @@ out_unlock_cgroup: */ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) { - struct cgroupfs_root *root; + struct cgroup_root *root; int retval = 0; mutex_lock(&cgroup_mutex); - for_each_active_root(root) { - struct cgroup *from_cgrp = task_cgroup_from_root(from, root); + for_each_root(root) { + struct cgroup *from_cgrp; + + if (root == &cgrp_dfl_root) + continue; + + down_read(&css_set_rwsem); + from_cgrp = task_cgroup_from_root(from, root); + up_read(&css_set_rwsem); retval = cgroup_attach_task(from_cgrp, tsk, false); if (retval) @@ -2228,16 +2183,17 @@ static int cgroup_procs_write(struct cgroup_subsys_state *css, } static int cgroup_release_agent_write(struct cgroup_subsys_state *css, - struct cftype *cft, const char *buffer) + struct cftype *cft, char *buffer) { - BUILD_BUG_ON(sizeof(css->cgroup->root->release_agent_path) < PATH_MAX); - if (strlen(buffer) >= PATH_MAX) - return -EINVAL; + struct cgroup_root *root = css->cgroup->root; + + BUILD_BUG_ON(sizeof(root->release_agent_path) < PATH_MAX); if (!cgroup_lock_live_group(css->cgroup)) return -ENODEV; - mutex_lock(&cgroup_root_mutex); - strcpy(css->cgroup->root->release_agent_path, buffer); - mutex_unlock(&cgroup_root_mutex); + spin_lock(&release_agent_path_lock); + strlcpy(root->release_agent_path, buffer, + sizeof(root->release_agent_path)); + spin_unlock(&release_agent_path_lock); mutex_unlock(&cgroup_mutex); return 0; } @@ -2262,32 +2218,23 @@ static int cgroup_sane_behavior_show(struct seq_file *seq, void *v) return 0; } -/* A buffer size big enough for numbers or short strings */ -#define CGROUP_LOCAL_BUFFER_SIZE 64 - -static ssize_t cgroup_file_write(struct file *file, const char __user *userbuf, - size_t nbytes, loff_t *ppos) +static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) { - struct cfent *cfe = __d_cfe(file->f_dentry); - struct cftype *cft = __d_cft(file->f_dentry); - struct cgroup_subsys_state *css = cfe->css; - size_t max_bytes = cft->max_write_len ?: CGROUP_LOCAL_BUFFER_SIZE - 1; - char *buf; + struct cgroup *cgrp = of->kn->parent->priv; + struct cftype *cft = of->kn->priv; + struct cgroup_subsys_state *css; int ret; - if (nbytes >= max_bytes) - return -E2BIG; - - buf = kmalloc(nbytes + 1, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - if (copy_from_user(buf, userbuf, nbytes)) { - ret = -EFAULT; - goto out_free; - } - - buf[nbytes] = '\0'; + /* + * kernfs guarantees that a file isn't deleted with operations in + * flight, which means that the matching css is and stays alive and + * doesn't need to be pinned. The RCU locking is not necessary + * either. It's just for the convenience of using cgroup_css(). + */ + rcu_read_lock(); + css = cgroup_css(cgrp, cft->ss); + rcu_read_unlock(); if (cft->write_string) { ret = cft->write_string(css, cft, strstrip(buf)); @@ -2306,53 +2253,23 @@ static ssize_t cgroup_file_write(struct file *file, const char __user *userbuf, } else { ret = -EINVAL; } -out_free: - kfree(buf); + return ret ?: nbytes; } -/* - * seqfile ops/methods for returning structured data. Currently just - * supports string->u64 maps, but can be extended in future. - */ - static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos) { - struct cftype *cft = seq_cft(seq); - - if (cft->seq_start) { - return cft->seq_start(seq, ppos); - } else { - /* - * The same behavior and code as single_open(). Returns - * !NULL if pos is at the beginning; otherwise, NULL. - */ - return NULL + !*ppos; - } + return seq_cft(seq)->seq_start(seq, ppos); } static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos) { - struct cftype *cft = seq_cft(seq); - - if (cft->seq_next) { - return cft->seq_next(seq, v, ppos); - } else { - /* - * The same behavior and code as single_open(), always - * terminate after the initial read. - */ - ++*ppos; - return NULL; - } + return seq_cft(seq)->seq_next(seq, v, ppos); } static void cgroup_seqfile_stop(struct seq_file *seq, void *v) { - struct cftype *cft = seq_cft(seq); - - if (cft->seq_stop) - cft->seq_stop(seq, v); + seq_cft(seq)->seq_stop(seq, v); } static int cgroup_seqfile_show(struct seq_file *m, void *arg) @@ -2372,96 +2289,35 @@ static int cgroup_seqfile_show(struct seq_file *m, void *arg) return 0; } -static struct seq_operations cgroup_seq_operations = { - .start = cgroup_seqfile_start, - .next = cgroup_seqfile_next, - .stop = cgroup_seqfile_stop, - .show = cgroup_seqfile_show, +static struct kernfs_ops cgroup_kf_single_ops = { + .atomic_write_len = PAGE_SIZE, + .write = cgroup_file_write, + .seq_show = cgroup_seqfile_show, }; -static int cgroup_file_open(struct inode *inode, struct file *file) -{ - struct cfent *cfe = __d_cfe(file->f_dentry); - struct cftype *cft = __d_cft(file->f_dentry); - struct cgroup *cgrp = __d_cgrp(cfe->dentry->d_parent); - struct cgroup_subsys_state *css; - struct cgroup_open_file *of; - int err; - - err = generic_file_open(inode, file); - if (err) - return err; - - /* - * If the file belongs to a subsystem, pin the css. Will be - * unpinned either on open failure or release. This ensures that - * @css stays alive for all file operations. - */ - rcu_read_lock(); - css = cgroup_css(cgrp, cft->ss); - if (cft->ss && !css_tryget(css)) - css = NULL; - rcu_read_unlock(); - - if (!css) - return -ENODEV; - - /* - * @cfe->css is used by read/write/close to determine the - * associated css. @file->private_data would be a better place but - * that's already used by seqfile. Multiple accessors may use it - * simultaneously which is okay as the association never changes. - */ - WARN_ON_ONCE(cfe->css && cfe->css != css); - cfe->css = css; - - of = __seq_open_private(file, &cgroup_seq_operations, - sizeof(struct cgroup_open_file)); - if (of) { - of->cfe = cfe; - return 0; - } - - if (css->ss) - css_put(css); - return -ENOMEM; -} - -static int cgroup_file_release(struct inode *inode, struct file *file) -{ - struct cfent *cfe = __d_cfe(file->f_dentry); - struct cgroup_subsys_state *css = cfe->css; - - if (css->ss) - css_put(css); - return seq_release_private(inode, file); -} +static struct kernfs_ops cgroup_kf_ops = { + .atomic_write_len = PAGE_SIZE, + .write = cgroup_file_write, + .seq_start = cgroup_seqfile_start, + .seq_next = cgroup_seqfile_next, + .seq_stop = cgroup_seqfile_stop, + .seq_show = cgroup_seqfile_show, +}; /* * cgroup_rename - Only allow simple rename of directories in place. */ -static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry) +static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, + const char *new_name_str) { + struct cgroup *cgrp = kn->priv; int ret; - struct cgroup_name *name, *old_name; - struct cgroup *cgrp; - - /* - * It's convinient to use parent dir's i_mutex to protected - * cgrp->name. - */ - lockdep_assert_held(&old_dir->i_mutex); - if (!S_ISDIR(old_dentry->d_inode->i_mode)) + if (kernfs_type(kn) != KERNFS_DIR) return -ENOTDIR; - if (new_dentry->d_inode) - return -EEXIST; - if (old_dir != new_dir) + if (kn->parent != new_parent) return -EIO; - cgrp = __d_cgrp(old_dentry); - /* * This isn't a proper migration and its usefulness is very * limited. Disallow if sane_behavior. @@ -2469,218 +2325,61 @@ static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry, if (cgroup_sane_behavior(cgrp)) return -EPERM; - name = cgroup_alloc_name(new_dentry); - if (!name) - return -ENOMEM; - - ret = simple_rename(old_dir, old_dentry, new_dir, new_dentry); - if (ret) { - kfree(name); - return ret; - } - - old_name = rcu_dereference_protected(cgrp->name, true); - rcu_assign_pointer(cgrp->name, name); - - kfree_rcu(old_name, rcu_head); - return 0; -} - -static struct simple_xattrs *__d_xattrs(struct dentry *dentry) -{ - if (S_ISDIR(dentry->d_inode->i_mode)) - return &__d_cgrp(dentry)->xattrs; - else - return &__d_cfe(dentry)->xattrs; -} - -static inline int xattr_enabled(struct dentry *dentry) -{ - struct cgroupfs_root *root = dentry->d_sb->s_fs_info; - return root->flags & CGRP_ROOT_XATTR; -} - -static bool is_valid_xattr(const char *name) -{ - if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) || - !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) - return true; - return false; -} - -static int cgroup_setxattr(struct dentry *dentry, const char *name, - const void *val, size_t size, int flags) -{ - if (!xattr_enabled(dentry)) - return -EOPNOTSUPP; - if (!is_valid_xattr(name)) - return -EINVAL; - return simple_xattr_set(__d_xattrs(dentry), name, val, size, flags); -} - -static int cgroup_removexattr(struct dentry *dentry, const char *name) -{ - if (!xattr_enabled(dentry)) - return -EOPNOTSUPP; - if (!is_valid_xattr(name)) - return -EINVAL; - return simple_xattr_remove(__d_xattrs(dentry), name); -} - -static ssize_t cgroup_getxattr(struct dentry *dentry, const char *name, - void *buf, size_t size) -{ - if (!xattr_enabled(dentry)) - return -EOPNOTSUPP; - if (!is_valid_xattr(name)) - return -EINVAL; - return simple_xattr_get(__d_xattrs(dentry), name, buf, size); -} - -static ssize_t cgroup_listxattr(struct dentry *dentry, char *buf, size_t size) -{ - if (!xattr_enabled(dentry)) - return -EOPNOTSUPP; - return simple_xattr_list(__d_xattrs(dentry), buf, size); -} - -static const struct file_operations cgroup_file_operations = { - .read = seq_read, - .write = cgroup_file_write, - .llseek = generic_file_llseek, - .open = cgroup_file_open, - .release = cgroup_file_release, -}; - -static const struct inode_operations cgroup_file_inode_operations = { - .setxattr = cgroup_setxattr, - .getxattr = cgroup_getxattr, - .listxattr = cgroup_listxattr, - .removexattr = cgroup_removexattr, -}; - -static const struct inode_operations cgroup_dir_inode_operations = { - .lookup = simple_lookup, - .mkdir = cgroup_mkdir, - .rmdir = cgroup_rmdir, - .rename = cgroup_rename, - .setxattr = cgroup_setxattr, - .getxattr = cgroup_getxattr, - .listxattr = cgroup_listxattr, - .removexattr = cgroup_removexattr, -}; - -static int cgroup_create_file(struct dentry *dentry, umode_t mode, - struct super_block *sb) -{ - struct inode *inode; - - if (!dentry) - return -ENOENT; - if (dentry->d_inode) - return -EEXIST; + /* + * We're gonna grab cgroup_tree_mutex which nests outside kernfs + * active_ref. kernfs_rename() doesn't require active_ref + * protection. Break them before grabbing cgroup_tree_mutex. + */ + kernfs_break_active_protection(new_parent); + kernfs_break_active_protection(kn); - inode = cgroup_new_inode(mode, sb); - if (!inode) - return -ENOMEM; + mutex_lock(&cgroup_tree_mutex); + mutex_lock(&cgroup_mutex); - if (S_ISDIR(mode)) { - inode->i_op = &cgroup_dir_inode_operations; - inode->i_fop = &simple_dir_operations; + ret = kernfs_rename(kn, new_parent, new_name_str); - /* start off with i_nlink == 2 (for "." entry) */ - inc_nlink(inode); - inc_nlink(dentry->d_parent->d_inode); + mutex_unlock(&cgroup_mutex); + mutex_unlock(&cgroup_tree_mutex); - /* - * Control reaches here with cgroup_mutex held. - * @inode->i_mutex should nest outside cgroup_mutex but we - * want to populate it immediately without releasing - * cgroup_mutex. As @inode isn't visible to anyone else - * yet, trylock will always succeed without affecting - * lockdep checks. - */ - WARN_ON_ONCE(!mutex_trylock(&inode->i_mutex)); - } else if (S_ISREG(mode)) { - inode->i_size = 0; - inode->i_fop = &cgroup_file_operations; - inode->i_op = &cgroup_file_inode_operations; - } - d_instantiate(dentry, inode); - dget(dentry); /* Extra count - pin the dentry in core */ - return 0; + kernfs_unbreak_active_protection(kn); + kernfs_unbreak_active_protection(new_parent); + return ret; } -/** - * cgroup_file_mode - deduce file mode of a control file - * @cft: the control file in question - * - * returns cft->mode if ->mode is not 0 - * returns S_IRUGO|S_IWUSR if it has both a read and a write handler - * returns S_IRUGO if it has only a read handler - * returns S_IWUSR if it has only a write hander - */ -static umode_t cgroup_file_mode(const struct cftype *cft) +/* set uid and gid of cgroup dirs and files to that of the creator */ +static int cgroup_kn_set_ugid(struct kernfs_node *kn) { - umode_t mode = 0; - - if (cft->mode) - return cft->mode; - - if (cft->read_u64 || cft->read_s64 || cft->seq_show) - mode |= S_IRUGO; + struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = current_fsuid(), + .ia_gid = current_fsgid(), }; - if (cft->write_u64 || cft->write_s64 || cft->write_string || - cft->trigger) - mode |= S_IWUSR; + if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) && + gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID)) + return 0; - return mode; + return kernfs_setattr(kn, &iattr); } static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft) { - struct dentry *dir = cgrp->dentry; - struct cgroup *parent = __d_cgrp(dir); - struct dentry *dentry; - struct cfent *cfe; - int error; - umode_t mode; - char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 }; - - if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) && - !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) { - strcpy(name, cft->ss->name); - strcat(name, "."); - } - strcat(name, cft->name); - - BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex)); - - cfe = kzalloc(sizeof(*cfe), GFP_KERNEL); - if (!cfe) - return -ENOMEM; - - dentry = lookup_one_len(name, dir, strlen(name)); - if (IS_ERR(dentry)) { - error = PTR_ERR(dentry); - goto out; - } + char name[CGROUP_FILE_NAME_MAX]; + struct kernfs_node *kn; + struct lock_class_key *key = NULL; + int ret; - cfe->type = (void *)cft; - cfe->dentry = dentry; - dentry->d_fsdata = cfe; - simple_xattrs_init(&cfe->xattrs); +#ifdef CONFIG_DEBUG_LOCK_ALLOC + key = &cft->lockdep_key; +#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); + if (IS_ERR(kn)) + return PTR_ERR(kn); - mode = cgroup_file_mode(cft); - error = cgroup_create_file(dentry, mode | S_IFREG, cgrp->root->sb); - if (!error) { - list_add_tail(&cfe->node, &parent->files); - cfe = NULL; - } - dput(dentry); -out: - kfree(cfe); - return error; + ret = cgroup_kn_set_ugid(kn); + if (ret) + kernfs_remove(kn); + return ret; } /** @@ -2700,11 +2399,12 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[], struct cftype *cft; int ret; - lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex); - lockdep_assert_held(&cgroup_mutex); + lockdep_assert_held(&cgroup_tree_mutex); for (cft = cfts; cft->name[0] != '\0'; cft++) { /* does cft->flags tell us to skip this file on @cgrp? */ + if ((cft->flags & CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp)) + continue; if ((cft->flags & CFTYPE_INSANE) && cgroup_sane_behavior(cgrp)) continue; if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent) @@ -2726,44 +2426,19 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[], return 0; } -static void cgroup_cfts_prepare(void) - __acquires(&cgroup_mutex) -{ - /* - * Thanks to the entanglement with vfs inode locking, we can't walk - * the existing cgroups under cgroup_mutex and create files. - * Instead, we use css_for_each_descendant_pre() and drop RCU read - * lock before calling cgroup_addrm_files(). - */ - mutex_lock(&cgroup_mutex); -} - -static int cgroup_cfts_commit(struct cftype *cfts, bool is_add) - __releases(&cgroup_mutex) +static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add) { LIST_HEAD(pending); struct cgroup_subsys *ss = cfts[0].ss; - struct cgroup *root = &ss->root->top_cgroup; - struct super_block *sb = ss->root->sb; - struct dentry *prev = NULL; - struct inode *inode; + struct cgroup *root = &ss->root->cgrp; struct cgroup_subsys_state *css; - u64 update_before; int ret = 0; - /* %NULL @cfts indicates abort and don't bother if @ss isn't attached */ - if (!cfts || ss->root == &cgroup_dummy_root || - !atomic_inc_not_zero(&sb->s_active)) { - mutex_unlock(&cgroup_mutex); - return 0; - } + lockdep_assert_held(&cgroup_tree_mutex); - /* - * All cgroups which are created after we drop cgroup_mutex will - * have the updated set of files, so we only need to update the - * cgroups created before the current @cgroup_serial_nr_next. - */ - update_before = cgroup_serial_nr_next; + /* don't bother if @ss isn't attached */ + if (ss->root == &cgrp_dfl_root) + return 0; /* add/rm files for all cgroups created before */ css_for_each_descendant_pre(css, cgroup_css(root, ss)) { @@ -2772,62 +2447,75 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add) if (cgroup_is_dead(cgrp)) continue; - inode = cgrp->dentry->d_inode; - dget(cgrp->dentry); - dput(prev); - prev = cgrp->dentry; - - mutex_unlock(&cgroup_mutex); - mutex_lock(&inode->i_mutex); - mutex_lock(&cgroup_mutex); - if (cgrp->serial_nr < update_before && !cgroup_is_dead(cgrp)) - ret = cgroup_addrm_files(cgrp, cfts, is_add); - mutex_unlock(&inode->i_mutex); + ret = cgroup_addrm_files(cgrp, cfts, is_add); if (ret) break; } - mutex_unlock(&cgroup_mutex); - dput(prev); - deactivate_super(sb); + + if (is_add && !ret) + kernfs_activate(root->kn); return ret; } -/** - * cgroup_add_cftypes - add an array of cftypes to a subsystem - * @ss: target cgroup subsystem - * @cfts: zero-length name terminated array of cftypes - * - * Register @cfts to @ss. Files described by @cfts are created for all - * existing cgroups to which @ss is attached and all future cgroups will - * have them too. This function can be called anytime whether @ss is - * attached or not. - * - * Returns 0 on successful registration, -errno on failure. Note that this - * function currently returns 0 as long as @cfts registration is successful - * even if some file creation attempts on existing cgroups fail. - */ -int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) +static void cgroup_exit_cftypes(struct cftype *cfts) { - struct cftype_set *set; struct cftype *cft; - int ret; - set = kzalloc(sizeof(*set), GFP_KERNEL); - if (!set) - return -ENOMEM; + for (cft = cfts; cft->name[0] != '\0'; cft++) { + /* free copy for custom atomic_write_len, see init_cftypes() */ + if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) + kfree(cft->kf_ops); + cft->kf_ops = NULL; + cft->ss = NULL; + } +} + +static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) +{ + struct cftype *cft; + + for (cft = cfts; cft->name[0] != '\0'; cft++) { + struct kernfs_ops *kf_ops; - for (cft = cfts; cft->name[0] != '\0'; cft++) + WARN_ON(cft->ss || cft->kf_ops); + + if (cft->seq_start) + kf_ops = &cgroup_kf_ops; + else + kf_ops = &cgroup_kf_single_ops; + + /* + * Ugh... if @cft wants a custom max_write_len, we need to + * make a copy of kf_ops to set its atomic_write_len. + */ + if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) { + kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL); + if (!kf_ops) { + cgroup_exit_cftypes(cfts); + return -ENOMEM; + } + kf_ops->atomic_write_len = cft->max_write_len; + } + + cft->kf_ops = kf_ops; cft->ss = ss; + } - cgroup_cfts_prepare(); - set->cfts = cfts; - list_add_tail(&set->node, &ss->cftsets); - ret = cgroup_cfts_commit(cfts, true); - if (ret) - cgroup_rm_cftypes(cfts); - return ret; + return 0; +} + +static int cgroup_rm_cftypes_locked(struct cftype *cfts) +{ + lockdep_assert_held(&cgroup_tree_mutex); + + if (!cfts || !cfts[0].ss) + return -ENOENT; + + list_del(&cfts->node); + cgroup_apply_cftypes(cfts, false); + cgroup_exit_cftypes(cfts); + return 0; } -EXPORT_SYMBOL_GPL(cgroup_add_cftypes); /** * cgroup_rm_cftypes - remove an array of cftypes from a subsystem @@ -2842,24 +2530,48 @@ EXPORT_SYMBOL_GPL(cgroup_add_cftypes); */ int cgroup_rm_cftypes(struct cftype *cfts) { - struct cftype_set *set; + int ret; - if (!cfts || !cfts[0].ss) - return -ENOENT; + mutex_lock(&cgroup_tree_mutex); + ret = cgroup_rm_cftypes_locked(cfts); + mutex_unlock(&cgroup_tree_mutex); + return ret; +} - cgroup_cfts_prepare(); +/** + * cgroup_add_cftypes - add an array of cftypes to a subsystem + * @ss: target cgroup subsystem + * @cfts: zero-length name terminated array of cftypes + * + * Register @cfts to @ss. Files described by @cfts are created for all + * existing cgroups to which @ss is attached and all future cgroups will + * have them too. This function can be called anytime whether @ss is + * attached or not. + * + * Returns 0 on successful registration, -errno on failure. Note that this + * function currently returns 0 as long as @cfts registration is successful + * even if some file creation attempts on existing cgroups fail. + */ +int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) +{ + int ret; - list_for_each_entry(set, &cfts[0].ss->cftsets, node) { - if (set->cfts == cfts) { - list_del(&set->node); - kfree(set); - cgroup_cfts_commit(cfts, false); - return 0; - } - } + if (!cfts || cfts[0].name[0] == '\0') + return 0; - cgroup_cfts_commit(NULL, false); - return -ENOENT; + ret = cgroup_init_cftypes(ss, cfts); + if (ret) + return ret; + + mutex_lock(&cgroup_tree_mutex); + + list_add_tail(&cfts->node, &ss->cfts); + ret = cgroup_apply_cftypes(cfts, true); + if (ret) + cgroup_rm_cftypes_locked(cfts); + + mutex_unlock(&cgroup_tree_mutex); + return ret; } /** @@ -2868,57 +2580,18 @@ int cgroup_rm_cftypes(struct cftype *cfts) * * Return the number of tasks in the cgroup. */ -int cgroup_task_count(const struct cgroup *cgrp) +static int cgroup_task_count(const struct cgroup *cgrp) { int count = 0; struct cgrp_cset_link *link; - read_lock(&css_set_lock); + down_read(&css_set_rwsem); list_for_each_entry(link, &cgrp->cset_links, cset_link) count += atomic_read(&link->cset->refcount); - read_unlock(&css_set_lock); + up_read(&css_set_rwsem); return count; } -/* - * To reduce the fork() overhead for systems that are not actually using - * their cgroups capability, we don't maintain the lists running through - * each css_set to its tasks until we see the list actually used - in other - * words after the first call to css_task_iter_start(). - */ -static void cgroup_enable_task_cg_lists(void) -{ - struct task_struct *p, *g; - write_lock(&css_set_lock); - use_task_css_set_links = 1; - /* - * We need tasklist_lock because RCU is not safe against - * while_each_thread(). Besides, a forking task that has passed - * cgroup_post_fork() without seeing use_task_css_set_links = 1 - * is not guaranteed to have its child immediately visible in the - * tasklist if we walk through it with RCU. - */ - read_lock(&tasklist_lock); - do_each_thread(g, p) { - task_lock(p); - /* - * We should check if the process is exiting, otherwise - * it will race with cgroup_exit() in that the list - * entry won't be deleted though the process has exited. - * Do it while holding siglock so that we don't end up - * racing against cgroup_exit(). - */ - spin_lock_irq(&p->sighand->siglock); - if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list)) - list_add(&p->cg_list, &task_css_set(p)->tasks); - spin_unlock_irq(&p->sighand->siglock); - - task_unlock(p); - } while_each_thread(g, p); - read_unlock(&tasklist_lock); - write_unlock(&css_set_lock); -} - /** * css_next_child - find the next child of a given css * @pos_css: the current position (%NULL to initiate traversal) @@ -2937,7 +2610,7 @@ css_next_child(struct cgroup_subsys_state *pos_css, struct cgroup *cgrp = parent_css->cgroup; struct cgroup *next; - cgroup_assert_mutex_or_rcu_locked(); + cgroup_assert_mutexes_or_rcu_locked(); /* * @pos could already have been removed. Once a cgroup is removed, @@ -2973,7 +2646,6 @@ css_next_child(struct cgroup_subsys_state *pos_css, return cgroup_css(next, parent_css->ss); } -EXPORT_SYMBOL_GPL(css_next_child); /** * css_next_descendant_pre - find the next descendant for pre-order walk @@ -2995,7 +2667,7 @@ css_next_descendant_pre(struct cgroup_subsys_state *pos, { struct cgroup_subsys_state *next; - cgroup_assert_mutex_or_rcu_locked(); + cgroup_assert_mutexes_or_rcu_locked(); /* if first iteration, visit @root */ if (!pos) @@ -3016,7 +2688,6 @@ css_next_descendant_pre(struct cgroup_subsys_state *pos, return NULL; } -EXPORT_SYMBOL_GPL(css_next_descendant_pre); /** * css_rightmost_descendant - return the rightmost descendant of a css @@ -3036,7 +2707,7 @@ css_rightmost_descendant(struct cgroup_subsys_state *pos) { struct cgroup_subsys_state *last, *tmp; - cgroup_assert_mutex_or_rcu_locked(); + cgroup_assert_mutexes_or_rcu_locked(); do { last = pos; @@ -3048,7 +2719,6 @@ css_rightmost_descendant(struct cgroup_subsys_state *pos) return last; } -EXPORT_SYMBOL_GPL(css_rightmost_descendant); static struct cgroup_subsys_state * css_leftmost_descendant(struct cgroup_subsys_state *pos) @@ -3084,7 +2754,7 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, { struct cgroup_subsys_state *next; - cgroup_assert_mutex_or_rcu_locked(); + cgroup_assert_mutexes_or_rcu_locked(); /* if first iteration, visit leftmost descendant which may be @root */ if (!pos) @@ -3102,7 +2772,6 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, /* no sibling left, visit parent */ return css_parent(pos); } -EXPORT_SYMBOL_GPL(css_next_descendant_post); /** * css_advance_task_iter - advance a task itererator to the next css_set @@ -3125,9 +2794,14 @@ static void css_advance_task_iter(struct css_task_iter *it) } link = list_entry(l, struct cgrp_cset_link, cset_link); cset = link->cset; - } while (list_empty(&cset->tasks)); + } while (list_empty(&cset->tasks) && list_empty(&cset->mg_tasks)); + it->cset_link = l; - it->task = cset->tasks.next; + + if (!list_empty(&cset->tasks)) + it->task = cset->tasks.next; + else + it->task = cset->mg_tasks.next; } /** @@ -3146,17 +2820,12 @@ static void css_advance_task_iter(struct css_task_iter *it) */ void css_task_iter_start(struct cgroup_subsys_state *css, struct css_task_iter *it) - __acquires(css_set_lock) + __acquires(css_set_rwsem) { - /* - * The first time anyone tries to iterate across a css, we need to - * enable the list linking each css_set to its tasks, and fix up - * all existing tasks. - */ - if (!use_task_css_set_links) - cgroup_enable_task_cg_lists(); + /* no one should try to iterate before mounting cgroups */ + WARN_ON_ONCE(!use_task_css_set_links); - read_lock(&css_set_lock); + down_read(&css_set_rwsem); it->origin_css = css; it->cset_link = &css->cgroup->cset_links; @@ -3176,24 +2845,29 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) { struct task_struct *res; struct list_head *l = it->task; - struct cgrp_cset_link *link; + struct cgrp_cset_link *link = list_entry(it->cset_link, + struct cgrp_cset_link, cset_link); /* If the iterator cg is NULL, we have no tasks */ if (!it->cset_link) return NULL; res = list_entry(l, struct task_struct, cg_list); - /* Advance iterator to find next entry */ + + /* + * Advance iterator to find next entry. cset->tasks is consumed + * first and then ->mg_tasks. After ->mg_tasks, we move onto the + * next cset. + */ l = l->next; - link = list_entry(it->cset_link, struct cgrp_cset_link, cset_link); - if (l == &link->cset->tasks) { - /* - * We reached the end of this task list - move on to the - * next cgrp_cset_link. - */ + + if (l == &link->cset->tasks) + l = link->cset->mg_tasks.next; + + if (l == &link->cset->mg_tasks) css_advance_task_iter(it); - } else { + else it->task = l; - } + return res; } @@ -3204,191 +2878,62 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) * Finish task iteration started by css_task_iter_start(). */ void css_task_iter_end(struct css_task_iter *it) - __releases(css_set_lock) -{ - read_unlock(&css_set_lock); -} - -static inline int started_after_time(struct task_struct *t1, - struct timespec *time, - struct task_struct *t2) -{ - int start_diff = timespec_compare(&t1->start_time, time); - if (start_diff > 0) { - return 1; - } else if (start_diff < 0) { - return 0; - } else { - /* - * Arbitrarily, if two processes started at the same - * time, we'll say that the lower pointer value - * started first. Note that t2 may have exited by now - * so this may not be a valid pointer any longer, but - * that's fine - it still serves to distinguish - * between two tasks started (effectively) simultaneously. - */ - return t1 > t2; - } -} - -/* - * This function is a callback from heap_insert() and is used to order - * the heap. - * In this case we order the heap in descending task start time. - */ -static inline int started_after(void *p1, void *p2) + __releases(css_set_rwsem) { - struct task_struct *t1 = p1; - struct task_struct *t2 = p2; - return started_after_time(t1, &t2->start_time, t2); + up_read(&css_set_rwsem); } /** - * css_scan_tasks - iterate though all the tasks in a css - * @css: the css to iterate tasks of - * @test: optional test callback - * @process: process callback - * @data: data passed to @test and @process - * @heap: optional pre-allocated heap used for task iteration - * - * Iterate through all the tasks in @css, calling @test for each, and if it - * returns %true, call @process for it also. - * - * @test may be NULL, meaning always true (select all tasks), which - * effectively duplicates css_task_iter_{start,next,end}() but does not - * lock css_set_lock for the call to @process. - * - * It is guaranteed that @process will act on every task that is a member - * of @css for the duration of this call. This function may or may not - * call @process for tasks that exit or move to a different css during the - * call, or are forked or move into the css during the call. - * - * Note that @test may be called with locks held, and may in some - * situations be called multiple times for the same task, so it should be - * cheap. + * cgroup_trasnsfer_tasks - move tasks from one cgroup to another + * @to: cgroup to which the tasks will be moved + * @from: cgroup in which the tasks currently reside * - * If @heap is non-NULL, a heap has been pre-allocated and will be used for - * heap operations (and its "gt" member will be overwritten), else a - * temporary heap will be used (allocation of which may cause this function - * to fail). + * Locking rules between cgroup_post_fork() and the migration path + * guarantee that, if a task is forking while being migrated, the new child + * is guaranteed to be either visible in the source cgroup after the + * parent's migration is complete or put into the target cgroup. No task + * can slip out of migration through forking. */ -int css_scan_tasks(struct cgroup_subsys_state *css, - bool (*test)(struct task_struct *, void *), - void (*process)(struct task_struct *, void *), - void *data, struct ptr_heap *heap) +int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) { - int retval, i; + LIST_HEAD(preloaded_csets); + struct cgrp_cset_link *link; struct css_task_iter it; - struct task_struct *p, *dropped; - /* Never dereference latest_task, since it's not refcounted */ - struct task_struct *latest_task = NULL; - struct ptr_heap tmp_heap; - struct timespec latest_time = { 0, 0 }; - - if (heap) { - /* The caller supplied our heap and pre-allocated its memory */ - heap->gt = &started_after; - } else { - /* We need to allocate our own heap memory */ - heap = &tmp_heap; - retval = heap_init(heap, PAGE_SIZE, GFP_KERNEL, &started_after); - if (retval) - /* cannot allocate the heap */ - return retval; - } + struct task_struct *task; + int ret; - again: - /* - * Scan tasks in the css, using the @test callback to determine - * which are of interest, and invoking @process callback on the - * ones which need an update. Since we don't want to hold any - * locks during the task updates, gather tasks to be processed in a - * heap structure. The heap is sorted by descending task start - * time. If the statically-sized heap fills up, we overflow tasks - * that started later, and in future iterations only consider tasks - * that started after the latest task in the previous pass. This - * guarantees forward progress and that we don't miss any tasks. - */ - heap->size = 0; - css_task_iter_start(css, &it); - while ((p = css_task_iter_next(&it))) { - /* - * Only affect tasks that qualify per the caller's callback, - * if he provided one - */ - if (test && !test(p, data)) - continue; - /* - * Only process tasks that started after the last task - * we processed - */ - if (!started_after_time(p, &latest_time, latest_task)) - continue; - dropped = heap_insert(heap, p); - if (dropped == NULL) { - /* - * The new task was inserted; the heap wasn't - * previously full - */ - get_task_struct(p); - } else if (dropped != p) { - /* - * The new task was inserted, and pushed out a - * different task - */ - get_task_struct(p); - put_task_struct(dropped); - } - /* - * Else the new task was newer than anything already in - * the heap and wasn't inserted - */ - } - css_task_iter_end(&it); + mutex_lock(&cgroup_mutex); - if (heap->size) { - for (i = 0; i < heap->size; i++) { - struct task_struct *q = heap->ptrs[i]; - if (i == 0) { - latest_time = q->start_time; - latest_task = q; - } - /* Process the task per the caller's callback */ - process(q, data); - put_task_struct(q); - } - /* - * If we had to process any tasks at all, scan again - * in case some of them were in the middle of forking - * children that didn't get processed. - * Not the most efficient way to do it, but it avoids - * having to take callback_mutex in the fork path - */ - goto again; - } - if (heap == &tmp_heap) - heap_free(&tmp_heap); - return 0; -} + /* all tasks in @from are being moved, all csets are source */ + down_read(&css_set_rwsem); + list_for_each_entry(link, &from->cset_links, cset_link) + cgroup_migrate_add_src(link->cset, to, &preloaded_csets); + up_read(&css_set_rwsem); -static void cgroup_transfer_one_task(struct task_struct *task, void *data) -{ - struct cgroup *new_cgroup = data; + ret = cgroup_migrate_prepare_dst(to, &preloaded_csets); + if (ret) + goto out_err; - mutex_lock(&cgroup_mutex); - cgroup_attach_task(new_cgroup, task, false); + /* + * Migrate tasks one-by-one until @form is empty. This fails iff + * ->can_attach() fails. + */ + do { + css_task_iter_start(&from->dummy_css, &it); + task = css_task_iter_next(&it); + if (task) + get_task_struct(task); + css_task_iter_end(&it); + + if (task) { + ret = cgroup_migrate(to, task, false); + put_task_struct(task); + } + } while (task && !ret); +out_err: + cgroup_migrate_finish(&preloaded_csets); mutex_unlock(&cgroup_mutex); -} - -/** - * cgroup_trasnsfer_tasks - move tasks from one cgroup to another - * @to: cgroup to which the tasks will be moved - * @from: cgroup in which the tasks currently reside - */ -int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) -{ - return css_scan_tasks(&from->dummy_css, NULL, cgroup_transfer_one_task, - to, NULL); + return ret; } /* @@ -3687,21 +3232,31 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, */ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { - int ret = -EINVAL; + struct kernfs_node *kn = kernfs_node_from_dentry(dentry); struct cgroup *cgrp; struct css_task_iter it; struct task_struct *tsk; + /* it should be kernfs_node belonging to cgroupfs and is a directory */ + if (dentry->d_sb->s_type != &cgroup_fs_type || !kn || + kernfs_type(kn) != KERNFS_DIR) + return -EINVAL; + + mutex_lock(&cgroup_mutex); + /* - * Validate dentry by checking the superblock operations, - * and make sure it's a directory. + * We aren't being called from kernfs and there's no guarantee on + * @kn->priv's validity. For this and css_tryget_from_dir(), + * @kn->priv is RCU safe. Let's do the RCU dancing. */ - if (dentry->d_sb->s_op != &cgroup_ops || - !S_ISDIR(dentry->d_inode->i_mode)) - goto err; - - ret = 0; - cgrp = dentry->d_fsdata; + rcu_read_lock(); + cgrp = rcu_dereference(kn->priv); + if (!cgrp || cgroup_is_dead(cgrp)) { + rcu_read_unlock(); + mutex_unlock(&cgroup_mutex); + return -ENOENT; + } + rcu_read_unlock(); css_task_iter_start(&cgrp->dummy_css, &it); while ((tsk = css_task_iter_next(&it))) { @@ -3726,8 +3281,8 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) } css_task_iter_end(&it); -err: - return ret; + mutex_unlock(&cgroup_mutex); + return 0; } @@ -3745,7 +3300,7 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) * after a seek to the start). Use a binary-search to find the * next pid to display, if any */ - struct cgroup_open_file *of = s->private; + struct kernfs_open_file *of = s->private; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_pidlist *l; enum cgroup_filetype type = seq_cft(s)->private; @@ -3800,7 +3355,7 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) static void cgroup_pidlist_stop(struct seq_file *s, void *v) { - struct cgroup_open_file *of = s->private; + struct kernfs_open_file *of = s->private; struct cgroup_pidlist *l = of->priv; if (l) @@ -3811,7 +3366,7 @@ static void cgroup_pidlist_stop(struct seq_file *s, void *v) static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) { - struct cgroup_open_file *of = s->private; + struct kernfs_open_file *of = s->private; struct cgroup_pidlist *l = of->priv; pid_t *p = v; pid_t *end = l->list + l->length; @@ -3861,23 +3416,6 @@ static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css, return 0; } -/* - * When dput() is called asynchronously, if umount has been done and - * then deactivate_super() in cgroup_free_fn() kills the superblock, - * there's a small window that vfs will see the root dentry with non-zero - * refcnt and trigger BUG(). - * - * That's why we hold a reference before dput() and drop it right after. - */ -static void cgroup_dput(struct cgroup *cgrp) -{ - struct super_block *sb = cgrp->root->sb; - - atomic_inc(&sb->s_active); - dput(cgrp->dentry); - deactivate_super(sb); -} - static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css, struct cftype *cft) { @@ -3944,7 +3482,7 @@ static struct cftype cgroup_base_files[] = { .flags = CFTYPE_INSANE | CFTYPE_ONLY_ON_ROOT, .seq_show = cgroup_release_agent_show, .write_string = cgroup_release_agent_write, - .max_write_len = PATH_MAX, + .max_write_len = PATH_MAX - 1, }, { } /* terminate */ }; @@ -3963,13 +3501,13 @@ static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask) /* process cftsets of each subsystem */ for_each_subsys(ss, i) { - struct cftype_set *set; + struct cftype *cfts; if (!test_bit(i, &subsys_mask)) continue; - list_for_each_entry(set, &ss->cftsets, node) { - ret = cgroup_addrm_files(cgrp, set->cfts, true); + list_for_each_entry(cfts, &ss->cfts, node) { + ret = cgroup_addrm_files(cgrp, cfts, true); if (ret < 0) goto err; } @@ -4012,7 +3550,7 @@ static void css_free_work_fn(struct work_struct *work) css_put(css->parent); css->ss->css_free(css); - cgroup_dput(cgrp); + cgroup_put(cgrp); } static void css_free_rcu_fn(struct rcu_head *rcu_head) @@ -4020,10 +3558,6 @@ static void css_free_rcu_fn(struct rcu_head *rcu_head) struct cgroup_subsys_state *css = container_of(rcu_head, struct cgroup_subsys_state, rcu_head); - /* - * css holds an extra ref to @cgrp->dentry which is put on the last - * css_put(). dput() requires process context which we don't have. - */ INIT_WORK(&css->destroy_work, css_free_work_fn); queue_work(cgroup_destroy_wq, &css->destroy_work); } @@ -4033,7 +3567,7 @@ static void css_release(struct percpu_ref *ref) struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); - rcu_assign_pointer(css->cgroup->subsys[css->ss->subsys_id], NULL); + RCU_INIT_POINTER(css->cgroup->subsys[css->ss->id], NULL); call_rcu(&css->rcu_head, css_free_rcu_fn); } @@ -4058,6 +3592,7 @@ static int online_css(struct cgroup_subsys_state *css) struct cgroup_subsys *ss = css->ss; int ret = 0; + lockdep_assert_held(&cgroup_tree_mutex); lockdep_assert_held(&cgroup_mutex); if (ss->css_online) @@ -4065,7 +3600,7 @@ static int online_css(struct cgroup_subsys_state *css) if (!ret) { css->flags |= CSS_ONLINE; css->cgroup->nr_css++; - rcu_assign_pointer(css->cgroup->subsys[ss->subsys_id], css); + rcu_assign_pointer(css->cgroup->subsys[ss->id], css); } return ret; } @@ -4075,6 +3610,7 @@ static void offline_css(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; + lockdep_assert_held(&cgroup_tree_mutex); lockdep_assert_held(&cgroup_mutex); if (!(css->flags & CSS_ONLINE)) @@ -4085,7 +3621,7 @@ static void offline_css(struct cgroup_subsys_state *css) css->flags &= ~CSS_ONLINE; css->cgroup->nr_css--; - RCU_INIT_POINTER(css->cgroup->subsys[ss->subsys_id], css); + RCU_INIT_POINTER(css->cgroup->subsys[ss->id], css); } /** @@ -4103,7 +3639,6 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss) struct cgroup_subsys_state *css; int err; - lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex); lockdep_assert_held(&cgroup_mutex); css = ss->css_alloc(cgroup_css(parent, ss)); @@ -4116,7 +3651,7 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss) init_css(css, ss, cgrp); - err = cgroup_populate_dir(cgrp, 1 << ss->subsys_id); + err = cgroup_populate_dir(cgrp, 1 << ss->id); if (err) goto err_free_percpu_ref; @@ -4124,9 +3659,11 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss) if (err) goto err_clear_dir; - dget(cgrp->dentry); + cgroup_get(cgrp); css_get(css->parent); + cgrp->subsys_mask |= 1 << ss->id; + if (ss->broken_hierarchy && !ss->warned_broken_hierarchy && parent->parent) { pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n", @@ -4139,7 +3676,7 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss) return 0; err_clear_dir: - cgroup_clear_dir(css->cgroup, 1 << css->ss->subsys_id); + cgroup_clear_dir(css->cgroup, 1 << css->ss->id); err_free_percpu_ref: percpu_ref_cancel_init(&css->refcnt); err_free_css: @@ -4147,35 +3684,34 @@ err_free_css: return err; } -/* +/** * cgroup_create - create a cgroup * @parent: cgroup that will be parent of the new cgroup - * @dentry: dentry of the new cgroup - * @mode: mode to set on new inode - * - * Must be called with the mutex on the parent inode held + * @name: name of the new cgroup + * @mode: mode to set on new cgroup */ -static long cgroup_create(struct cgroup *parent, struct dentry *dentry, - umode_t mode) +static long cgroup_create(struct cgroup *parent, const char *name, + umode_t mode) { struct cgroup *cgrp; - struct cgroup_name *name; - struct cgroupfs_root *root = parent->root; + struct cgroup_root *root = parent->root; int ssid, err; struct cgroup_subsys *ss; - struct super_block *sb = root->sb; + struct kernfs_node *kn; + + /* + * XXX: The default hierarchy isn't fully implemented yet. Block + * !root cgroup creation on it for now. + */ + if (root == &cgrp_dfl_root) + return -EINVAL; /* allocate the cgroup and its ID, 0 is reserved for the root */ cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL); if (!cgrp) return -ENOMEM; - name = cgroup_alloc_name(dentry); - if (!name) { - err = -ENOMEM; - goto err_free_cgrp; - } - rcu_assign_pointer(cgrp->name, name); + mutex_lock(&cgroup_tree_mutex); /* * Only live parents can have children. Note that the liveliness @@ -4186,7 +3722,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, */ if (!cgroup_lock_live_group(parent)) { err = -ENODEV; - goto err_free_name; + goto err_unlock_tree; } /* @@ -4199,18 +3735,8 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, goto err_unlock; } - /* Grab a reference on the superblock so the hierarchy doesn't - * get deleted on unmount if there are child cgroups. This - * can be done outside cgroup_mutex, since the sb can't - * disappear while someone has an open control file on the - * fs */ - atomic_inc(&sb->s_active); - init_cgroup_housekeeping(cgrp); - dentry->d_fsdata = cgrp; - cgrp->dentry = dentry; - cgrp->parent = parent; cgrp->dummy_css.parent = &parent->dummy_css; cgrp->root = parent->root; @@ -4221,24 +3747,26 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags)) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags); + /* create the directory */ + kn = kernfs_create_dir(parent->kn, name, mode, cgrp); + if (IS_ERR(kn)) { + err = PTR_ERR(kn); + goto err_free_id; + } + cgrp->kn = kn; + /* - * Create directory. cgroup_create_file() returns with the new - * directory locked on success so that it can be populated without - * dropping cgroup_mutex. + * This extra ref will be put in cgroup_free_fn() and guarantees + * that @cgrp->kn is always accessible. */ - err = cgroup_create_file(dentry, S_IFDIR | mode, sb); - if (err < 0) - goto err_free_id; - lockdep_assert_held(&dentry->d_inode->i_mutex); + kernfs_get(kn); cgrp->serial_nr = cgroup_serial_nr_next++; /* allocation complete, commit to creation */ list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children); - root->number_of_cgroups++; - - /* hold a ref to the parent's dentry */ - dget(parent->dentry); + atomic_inc(&root->nr_cgrps); + cgroup_get(parent); /* * @cgrp is now fully operational. If something fails after this @@ -4246,49 +3774,66 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, */ idr_replace(&root->cgroup_idr, cgrp, cgrp->id); + err = cgroup_kn_set_ugid(kn); + if (err) + goto err_destroy; + err = cgroup_addrm_files(cgrp, cgroup_base_files, true); if (err) goto err_destroy; /* let's create and online css's */ for_each_subsys(ss, ssid) { - if (root->subsys_mask & (1 << ssid)) { + if (root->cgrp.subsys_mask & (1 << ssid)) { err = create_css(cgrp, ss); if (err) goto err_destroy; } } + kernfs_activate(kn); + mutex_unlock(&cgroup_mutex); - mutex_unlock(&cgrp->dentry->d_inode->i_mutex); + mutex_unlock(&cgroup_tree_mutex); return 0; err_free_id: idr_remove(&root->cgroup_idr, cgrp->id); - /* Release the reference count that we took on the superblock */ - deactivate_super(sb); err_unlock: mutex_unlock(&cgroup_mutex); -err_free_name: - kfree(rcu_dereference_raw(cgrp->name)); -err_free_cgrp: +err_unlock_tree: + mutex_unlock(&cgroup_tree_mutex); kfree(cgrp); return err; err_destroy: cgroup_destroy_locked(cgrp); mutex_unlock(&cgroup_mutex); - mutex_unlock(&dentry->d_inode->i_mutex); + mutex_unlock(&cgroup_tree_mutex); return err; } -static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, + umode_t mode) { - struct cgroup *c_parent = dentry->d_parent->d_fsdata; + struct cgroup *parent = parent_kn->priv; + int ret; + + /* + * cgroup_create() grabs cgroup_tree_mutex which nests outside + * kernfs active_ref and cgroup_create() already synchronizes + * properly against removal through cgroup_lock_live_group(). + * Break it before calling cgroup_create(). + */ + cgroup_get(parent); + kernfs_break_active_protection(parent_kn); + + ret = cgroup_create(parent, name, mode); - /* the vfs holds inode->i_mutex already */ - return cgroup_create(c_parent, dentry, mode | S_IFDIR); + kernfs_unbreak_active_protection(parent_kn); + cgroup_put(parent); + return ret; } /* @@ -4301,6 +3846,7 @@ static void css_killed_work_fn(struct work_struct *work) container_of(work, struct cgroup_subsys_state, destroy_work); struct cgroup *cgrp = css->cgroup; + mutex_lock(&cgroup_tree_mutex); mutex_lock(&cgroup_mutex); /* @@ -4318,6 +3864,7 @@ static void css_killed_work_fn(struct work_struct *work) cgroup_destroy_css_killed(cgrp); mutex_unlock(&cgroup_mutex); + mutex_unlock(&cgroup_tree_mutex); /* * Put the css refs from kill_css(). Each css holds an extra @@ -4339,18 +3886,15 @@ static void css_killed_ref_fn(struct percpu_ref *ref) queue_work(cgroup_destroy_wq, &css->destroy_work); } -/** - * kill_css - destroy a css - * @css: css to destroy - * - * This function initiates destruction of @css by removing cgroup interface - * files and putting its base reference. ->css_offline() will be invoked - * asynchronously once css_tryget() is guaranteed to fail and when the - * reference count reaches zero, @css will be released. - */ -static void kill_css(struct cgroup_subsys_state *css) +static void __kill_css(struct cgroup_subsys_state *css) { - cgroup_clear_dir(css->cgroup, 1 << css->ss->subsys_id); + lockdep_assert_held(&cgroup_tree_mutex); + + /* + * This must happen before css is disassociated with its cgroup. + * See seq_css() for details. + */ + cgroup_clear_dir(css->cgroup, 1 << css->ss->id); /* * Killing would put the base ref, but we need to keep it alive @@ -4372,6 +3916,28 @@ static void kill_css(struct cgroup_subsys_state *css) } /** + * kill_css - destroy a css + * @css: css to destroy + * + * This function initiates destruction of @css by removing cgroup interface + * files and putting its base reference. ->css_offline() will be invoked + * asynchronously once css_tryget() is guaranteed to fail and when the + * reference count reaches zero, @css will be released. + */ +static void kill_css(struct cgroup_subsys_state *css) +{ + struct cgroup *cgrp = css->cgroup; + + lockdep_assert_held(&cgroup_tree_mutex); + + /* if already killed, noop */ + if (cgrp->subsys_mask & (1 << css->ss->id)) { + cgrp->subsys_mask &= ~(1 << css->ss->id); + __kill_css(css); + } +} + +/** * cgroup_destroy_locked - the first stage of cgroup destruction * @cgrp: cgroup to be destroyed * @@ -4398,22 +3964,21 @@ static void kill_css(struct cgroup_subsys_state *css) static int cgroup_destroy_locked(struct cgroup *cgrp) __releases(&cgroup_mutex) __acquires(&cgroup_mutex) { - struct dentry *d = cgrp->dentry; - struct cgroup_subsys_state *css; struct cgroup *child; + struct cgroup_subsys_state *css; bool empty; int ssid; - lockdep_assert_held(&d->d_inode->i_mutex); + lockdep_assert_held(&cgroup_tree_mutex); lockdep_assert_held(&cgroup_mutex); /* - * css_set_lock synchronizes access to ->cset_links and prevents - * @cgrp from being removed while __put_css_set() is in progress. + * css_set_rwsem synchronizes access to ->cset_links and prevents + * @cgrp from being removed while put_css_set() is in progress. */ - read_lock(&css_set_lock); + down_read(&css_set_rwsem); empty = list_empty(&cgrp->cset_links); - read_unlock(&css_set_lock); + up_read(&css_set_rwsem); if (!empty) return -EBUSY; @@ -4434,14 +3999,6 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) return -EBUSY; /* - * Initiate massacre of all css's. cgroup_destroy_css_killed() - * will be invoked to perform the rest of destruction once the - * percpu refs of all css's are confirmed to be killed. - */ - for_each_css(css, ssid, cgrp) - kill_css(css); - - /* * Mark @cgrp dead. This prevents further task migration and child * creation by disabling cgroup_lock_live_group(). Note that * CGRP_DEAD assertion is depended upon by css_next_child() to @@ -4450,6 +4007,17 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) */ set_bit(CGRP_DEAD, &cgrp->flags); + /* + * Initiate massacre of all css's. cgroup_destroy_css_killed() + * will be invoked to perform the rest of destruction once the + * percpu refs of all css's are confirmed to be killed. This + * involves removing the subsystem's files, drop cgroup_mutex. + */ + mutex_unlock(&cgroup_mutex); + for_each_css(css, ssid, cgrp) + kill_css(css); + mutex_lock(&cgroup_mutex); + /* CGRP_DEAD is set, remove from ->release_list for the last time */ raw_spin_lock(&release_list_lock); if (!list_empty(&cgrp->release_list)) @@ -4465,14 +4033,20 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) if (!cgrp->nr_css) cgroup_destroy_css_killed(cgrp); + /* remove @cgrp directory along with the base files */ + mutex_unlock(&cgroup_mutex); + /* - * Clear the base files and remove @cgrp directory. The removal - * puts the base ref but we aren't quite done with @cgrp yet, so - * hold onto it. + * There are two control paths which try to determine cgroup from + * dentry without going through kernfs - cgroupstats_build() and + * css_tryget_from_dir(). Those are supported by RCU protecting + * clearing of cgrp->kn->priv backpointer, which should happen + * after all files under it have been removed. */ - cgroup_addrm_files(cgrp, cgroup_base_files, false); - dget(d); - cgroup_d_remove_dir(d); + kernfs_remove(cgrp->kn); /* @cgrp has an extra ref on its kn */ + RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL); + + mutex_lock(&cgroup_mutex); return 0; }; @@ -4489,72 +4063,82 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) static void cgroup_destroy_css_killed(struct cgroup *cgrp) { struct cgroup *parent = cgrp->parent; - struct dentry *d = cgrp->dentry; + lockdep_assert_held(&cgroup_tree_mutex); lockdep_assert_held(&cgroup_mutex); /* delete this cgroup from parent->children */ list_del_rcu(&cgrp->sibling); - dput(d); + cgroup_put(cgrp); set_bit(CGRP_RELEASABLE, &parent->flags); check_for_release(parent); } -static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) +static int cgroup_rmdir(struct kernfs_node *kn) { - int ret; - - mutex_lock(&cgroup_mutex); - ret = cgroup_destroy_locked(dentry->d_fsdata); - mutex_unlock(&cgroup_mutex); + struct cgroup *cgrp = kn->priv; + int ret = 0; - return ret; -} + /* + * This is self-destruction but @kn can't be removed while this + * callback is in progress. Let's break active protection. Once + * the protection is broken, @cgrp can be destroyed at any point. + * Pin it so that it stays accessible. + */ + cgroup_get(cgrp); + kernfs_break_active_protection(kn); -static void __init_or_module cgroup_init_cftsets(struct cgroup_subsys *ss) -{ - INIT_LIST_HEAD(&ss->cftsets); + mutex_lock(&cgroup_tree_mutex); + mutex_lock(&cgroup_mutex); /* - * base_cftset is embedded in subsys itself, no need to worry about - * deregistration. + * @cgrp might already have been destroyed while we're trying to + * grab the mutexes. */ - if (ss->base_cftypes) { - struct cftype *cft; + if (!cgroup_is_dead(cgrp)) + ret = cgroup_destroy_locked(cgrp); - for (cft = ss->base_cftypes; cft->name[0] != '\0'; cft++) - cft->ss = ss; + mutex_unlock(&cgroup_mutex); + mutex_unlock(&cgroup_tree_mutex); - ss->base_cftset.cfts = ss->base_cftypes; - list_add_tail(&ss->base_cftset.node, &ss->cftsets); - } + kernfs_unbreak_active_protection(kn); + cgroup_put(cgrp); + return ret; } +static struct kernfs_syscall_ops cgroup_kf_syscall_ops = { + .remount_fs = cgroup_remount, + .show_options = cgroup_show_options, + .mkdir = cgroup_mkdir, + .rmdir = cgroup_rmdir, + .rename = cgroup_rename, +}; + static void __init cgroup_init_subsys(struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name); + mutex_lock(&cgroup_tree_mutex); mutex_lock(&cgroup_mutex); - /* init base cftset */ - cgroup_init_cftsets(ss); + INIT_LIST_HEAD(&ss->cfts); - /* Create the top cgroup state for this subsystem */ - ss->root = &cgroup_dummy_root; - css = ss->css_alloc(cgroup_css(cgroup_dummy_top, ss)); + /* Create the root cgroup state for this subsystem */ + ss->root = &cgrp_dfl_root; + css = ss->css_alloc(cgroup_css(&cgrp_dfl_root.cgrp, ss)); /* We don't handle early failures gracefully */ BUG_ON(IS_ERR(css)); - init_css(css, ss, cgroup_dummy_top); + init_css(css, ss, &cgrp_dfl_root.cgrp); /* Update the init_css_set to contain a subsys * pointer to this state - since the subsystem is * newly registered, all tasks and hence the - * init_css_set is in the subsystem's top cgroup. */ - init_css_set.subsys[ss->subsys_id] = css; + * init_css_set is in the subsystem's root cgroup. */ + init_css_set.subsys[ss->id] = css; need_forkexit_callback |= ss->fork || ss->exit; @@ -4565,185 +4149,11 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss) BUG_ON(online_css(css)); - mutex_unlock(&cgroup_mutex); - - /* this function shouldn't be used with modular subsystems, since they - * need to register a subsys_id, among other things */ - BUG_ON(ss->module); -} - -/** - * cgroup_load_subsys: load and register a modular subsystem at runtime - * @ss: the subsystem to load - * - * This function should be called in a modular subsystem's initcall. If the - * subsystem is built as a module, it will be assigned a new subsys_id and set - * up for use. If the subsystem is built-in anyway, work is delegated to the - * simpler cgroup_init_subsys. - */ -int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) -{ - struct cgroup_subsys_state *css; - int i, ret; - struct hlist_node *tmp; - struct css_set *cset; - unsigned long key; - - /* check name and function validity */ - if (ss->name == NULL || strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN || - ss->css_alloc == NULL || ss->css_free == NULL) - return -EINVAL; - - /* - * we don't support callbacks in modular subsystems. this check is - * before the ss->module check for consistency; a subsystem that could - * be a module should still have no callbacks even if the user isn't - * compiling it as one. - */ - if (ss->fork || ss->exit) - return -EINVAL; - - /* - * an optionally modular subsystem is built-in: we want to do nothing, - * since cgroup_init_subsys will have already taken care of it. - */ - if (ss->module == NULL) { - /* a sanity check */ - BUG_ON(cgroup_subsys[ss->subsys_id] != ss); - return 0; - } - - /* init base cftset */ - cgroup_init_cftsets(ss); - - mutex_lock(&cgroup_mutex); - mutex_lock(&cgroup_root_mutex); - cgroup_subsys[ss->subsys_id] = ss; - - /* - * no ss->css_alloc seems to need anything important in the ss - * struct, so this can happen first (i.e. before the dummy root - * attachment). - */ - css = ss->css_alloc(cgroup_css(cgroup_dummy_top, ss)); - if (IS_ERR(css)) { - /* failure case - need to deassign the cgroup_subsys[] slot. */ - cgroup_subsys[ss->subsys_id] = NULL; - mutex_unlock(&cgroup_root_mutex); - mutex_unlock(&cgroup_mutex); - return PTR_ERR(css); - } - - ss->root = &cgroup_dummy_root; - - /* our new subsystem will be attached to the dummy hierarchy. */ - init_css(css, ss, cgroup_dummy_top); - - /* - * Now we need to entangle the css into the existing css_sets. unlike - * in cgroup_init_subsys, there are now multiple css_sets, so each one - * will need a new pointer to it; done by iterating the css_set_table. - * furthermore, modifying the existing css_sets will corrupt the hash - * table state, so each changed css_set will need its hash recomputed. - * this is all done under the css_set_lock. - */ - write_lock(&css_set_lock); - hash_for_each_safe(css_set_table, i, tmp, cset, hlist) { - /* skip entries that we already rehashed */ - if (cset->subsys[ss->subsys_id]) - continue; - /* remove existing entry */ - hash_del(&cset->hlist); - /* set new value */ - cset->subsys[ss->subsys_id] = css; - /* recompute hash and restore entry */ - key = css_set_hash(cset->subsys); - hash_add(css_set_table, &cset->hlist, key); - } - write_unlock(&css_set_lock); - - ret = online_css(css); - if (ret) { - ss->css_free(css); - goto err_unload; - } - - /* success! */ - mutex_unlock(&cgroup_root_mutex); - mutex_unlock(&cgroup_mutex); - return 0; - -err_unload: - mutex_unlock(&cgroup_root_mutex); - mutex_unlock(&cgroup_mutex); - /* @ss can't be mounted here as try_module_get() would fail */ - cgroup_unload_subsys(ss); - return ret; -} -EXPORT_SYMBOL_GPL(cgroup_load_subsys); - -/** - * cgroup_unload_subsys: unload a modular subsystem - * @ss: the subsystem to unload - * - * This function should be called in a modular subsystem's exitcall. When this - * function is invoked, the refcount on the subsystem's module will be 0, so - * the subsystem will not be attached to any hierarchy. - */ -void cgroup_unload_subsys(struct cgroup_subsys *ss) -{ - struct cgrp_cset_link *link; - struct cgroup_subsys_state *css; - - BUG_ON(ss->module == NULL); - - /* - * we shouldn't be called if the subsystem is in use, and the use of - * try_module_get() in rebind_subsystems() should ensure that it - * doesn't start being used while we're killing it off. - */ - BUG_ON(ss->root != &cgroup_dummy_root); - - mutex_lock(&cgroup_mutex); - mutex_lock(&cgroup_root_mutex); - - css = cgroup_css(cgroup_dummy_top, ss); - if (css) - offline_css(css); + cgrp_dfl_root.cgrp.subsys_mask |= 1 << ss->id; - /* deassign the subsys_id */ - cgroup_subsys[ss->subsys_id] = NULL; - - /* - * disentangle the css from all css_sets attached to the dummy - * top. as in loading, we need to pay our respects to the hashtable - * gods. - */ - write_lock(&css_set_lock); - list_for_each_entry(link, &cgroup_dummy_top->cset_links, cset_link) { - struct css_set *cset = link->cset; - unsigned long key; - - hash_del(&cset->hlist); - cset->subsys[ss->subsys_id] = NULL; - key = css_set_hash(cset->subsys); - hash_add(css_set_table, &cset->hlist, key); - } - write_unlock(&css_set_lock); - - /* - * remove subsystem's css from the cgroup_dummy_top and free it - - * need to free before marking as null because ss->css_free needs - * the cgrp->subsys pointer to find their state. - */ - if (css) - ss->css_free(css); - RCU_INIT_POINTER(cgroup_dummy_top->subsys[ss->subsys_id], NULL); - - mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); + mutex_unlock(&cgroup_tree_mutex); } -EXPORT_SYMBOL_GPL(cgroup_unload_subsys); /** * cgroup_init_early - cgroup initialization at system boot @@ -4753,34 +4163,24 @@ EXPORT_SYMBOL_GPL(cgroup_unload_subsys); */ int __init cgroup_init_early(void) { + static struct cgroup_sb_opts __initdata opts = + { .flags = CGRP_ROOT_SANE_BEHAVIOR }; struct cgroup_subsys *ss; int i; - atomic_set(&init_css_set.refcount, 1); - INIT_LIST_HEAD(&init_css_set.cgrp_links); - INIT_LIST_HEAD(&init_css_set.tasks); - INIT_HLIST_NODE(&init_css_set.hlist); - css_set_count = 1; - init_cgroup_root(&cgroup_dummy_root); - cgroup_root_count = 1; + init_cgroup_root(&cgrp_dfl_root, &opts); RCU_INIT_POINTER(init_task.cgroups, &init_css_set); - init_cgrp_cset_link.cset = &init_css_set; - init_cgrp_cset_link.cgrp = cgroup_dummy_top; - list_add(&init_cgrp_cset_link.cset_link, &cgroup_dummy_top->cset_links); - list_add(&init_cgrp_cset_link.cgrp_link, &init_css_set.cgrp_links); - - /* at bootup time, we don't worry about modular subsystems */ - for_each_builtin_subsys(ss, i) { - BUG_ON(!ss->name); - BUG_ON(strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN); - BUG_ON(!ss->css_alloc); - BUG_ON(!ss->css_free); - if (ss->subsys_id != i) { - printk(KERN_ERR "cgroup: Subsys %s id == %d\n", - ss->name, ss->subsys_id); - BUG(); - } + for_each_subsys(ss, i) { + WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id, + "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p name:id=%d:%s\n", + i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free, + ss->id, ss->name); + WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN, + "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]); + + ss->id = i; + ss->name = cgroup_subsys_name[i]; if (ss->early_init) cgroup_init_subsys(ss); @@ -4798,53 +4198,46 @@ int __init cgroup_init(void) { struct cgroup_subsys *ss; unsigned long key; - int i, err; + int ssid, err; - err = bdi_init(&cgroup_backing_dev_info); - if (err) - return err; + BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files)); - for_each_builtin_subsys(ss, i) { - if (!ss->early_init) - cgroup_init_subsys(ss); - } - - /* allocate id for the dummy hierarchy */ + mutex_lock(&cgroup_tree_mutex); mutex_lock(&cgroup_mutex); - mutex_lock(&cgroup_root_mutex); /* Add init_css_set to the hash table */ key = css_set_hash(init_css_set.subsys); hash_add(css_set_table, &init_css_set.hlist, key); - BUG_ON(cgroup_init_root_id(&cgroup_dummy_root, 0, 1)); + BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0)); - err = idr_alloc(&cgroup_dummy_root.cgroup_idr, cgroup_dummy_top, - 0, 1, GFP_KERNEL); - BUG_ON(err < 0); - - mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); + mutex_unlock(&cgroup_tree_mutex); - cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj); - if (!cgroup_kobj) { - err = -ENOMEM; - goto out; + for_each_subsys(ss, ssid) { + if (!ss->early_init) + cgroup_init_subsys(ss); + + /* + * cftype registration needs kmalloc and can't be done + * during early_init. Register base cftypes separately. + */ + if (ss->base_cftypes) + WARN_ON(cgroup_add_cftypes(ss, ss->base_cftypes)); } + cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj); + if (!cgroup_kobj) + return -ENOMEM; + err = register_filesystem(&cgroup_fs_type); if (err < 0) { kobject_put(cgroup_kobj); - goto out; + return err; } proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations); - -out: - if (err) - bdi_destroy(&cgroup_backing_dev_info); - - return err; + return 0; } static int __init cgroup_wq_init(void) @@ -4876,12 +4269,6 @@ core_initcall(cgroup_wq_init); * proc_cgroup_show() * - Print task's cgroup paths into seq_file, one line for each hierarchy * - Used for /proc/<pid>/cgroup. - * - No need to task_lock(tsk) on this tsk->cgroup reference, as it - * doesn't really matter if tsk->cgroup changes after we read it, - * and we take cgroup_mutex, keeping cgroup_attach_task() from changing it - * anyway. No need to check that tsk->cgroup != NULL, thanks to - * the_top_cgroup_hack in cgroup_exit(), which sets an exiting tasks - * cgroup to top_cgroup. */ /* TODO: Use a proper seq_file iterator */ @@ -4889,12 +4276,12 @@ int proc_cgroup_show(struct seq_file *m, void *v) { struct pid *pid; struct task_struct *tsk; - char *buf; + char *buf, *path; int retval; - struct cgroupfs_root *root; + struct cgroup_root *root; retval = -ENOMEM; - buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) goto out; @@ -4907,29 +4294,36 @@ int proc_cgroup_show(struct seq_file *m, void *v) retval = 0; mutex_lock(&cgroup_mutex); + down_read(&css_set_rwsem); - for_each_active_root(root) { + for_each_root(root) { struct cgroup_subsys *ss; struct cgroup *cgrp; int ssid, count = 0; + if (root == &cgrp_dfl_root && !cgrp_dfl_root_visible) + continue; + seq_printf(m, "%d:", root->hierarchy_id); for_each_subsys(ss, ssid) - if (root->subsys_mask & (1 << ssid)) + if (root->cgrp.subsys_mask & (1 << ssid)) seq_printf(m, "%s%s", count++ ? "," : "", ss->name); if (strlen(root->name)) seq_printf(m, "%sname=%s", count ? "," : "", root->name); seq_putc(m, ':'); cgrp = task_cgroup_from_root(tsk, root); - retval = cgroup_path(cgrp, buf, PAGE_SIZE); - if (retval < 0) + path = cgroup_path(cgrp, buf, PATH_MAX); + if (!path) { + retval = -ENAMETOOLONG; goto out_unlock; - seq_puts(m, buf); + } + seq_puts(m, path); seq_putc(m, '\n'); } out_unlock: + up_read(&css_set_rwsem); mutex_unlock(&cgroup_mutex); put_task_struct(tsk); out_free: @@ -4955,7 +4349,7 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v) for_each_subsys(ss, i) seq_printf(m, "%s\t%d\t%d\t%d\n", ss->name, ss->root->hierarchy_id, - ss->root->number_of_cgroups, !ss->disabled); + atomic_read(&ss->root->nr_cgrps), !ss->disabled); mutex_unlock(&cgroup_mutex); return 0; @@ -4974,27 +4368,16 @@ static const struct file_operations proc_cgroupstats_operations = { }; /** - * cgroup_fork - attach newly forked task to its parents cgroup. + * cgroup_fork - initialize cgroup related fields during copy_process() * @child: pointer to task_struct of forking parent process. * - * Description: A task inherits its parent's cgroup at fork(). - * - * A pointer to the shared css_set was automatically copied in - * fork.c by dup_task_struct(). However, we ignore that copy, since - * it was not made under the protection of RCU or cgroup_mutex, so - * might no longer be a valid cgroup pointer. cgroup_attach_task() might - * have already changed current->cgroups, allowing the previously - * referenced cgroup group to be removed and freed. - * - * At the point that cgroup_fork() is called, 'current' is the parent - * task, and the passed argument 'child' points to the child task. + * A task is associated with the init_css_set until cgroup_post_fork() + * attaches it to the parent's css_set. Empty cg_list indicates that + * @child isn't holding reference to its css_set. */ void cgroup_fork(struct task_struct *child) { - task_lock(current); - get_css_set(task_css_set(current)); - child->cgroups = current->cgroups; - task_unlock(current); + RCU_INIT_POINTER(child->cgroups, &init_css_set); INIT_LIST_HEAD(&child->cg_list); } @@ -5014,23 +4397,37 @@ void cgroup_post_fork(struct task_struct *child) int i; /* - * use_task_css_set_links is set to 1 before we walk the tasklist - * under the tasklist_lock and we read it here after we added the child - * to the tasklist under the tasklist_lock as well. If the child wasn't - * yet in the tasklist when we walked through it from - * cgroup_enable_task_cg_lists(), then use_task_css_set_links value - * should be visible now due to the paired locking and barriers implied - * by LOCK/UNLOCK: it is written before the tasklist_lock unlock - * in cgroup_enable_task_cg_lists() and read here after the tasklist_lock - * lock on fork. + * This may race against cgroup_enable_task_cg_links(). As that + * function sets use_task_css_set_links before grabbing + * tasklist_lock and we just went through tasklist_lock to add + * @child, it's guaranteed that either we see the set + * use_task_css_set_links or cgroup_enable_task_cg_lists() sees + * @child during its iteration. + * + * If we won the race, @child is associated with %current's + * css_set. Grabbing css_set_rwsem guarantees both that the + * association is stable, and, on completion of the parent's + * migration, @child is visible in the source of migration or + * already in the destination cgroup. This guarantee is necessary + * when implementing operations which need to migrate all tasks of + * a cgroup to another. + * + * Note that if we lose to cgroup_enable_task_cg_links(), @child + * will remain in init_css_set. This is safe because all tasks are + * in the init_css_set before cg_links is enabled and there's no + * operation which transfers all tasks out of init_css_set. */ if (use_task_css_set_links) { - write_lock(&css_set_lock); - task_lock(child); - if (list_empty(&child->cg_list)) - list_add(&child->cg_list, &task_css_set(child)->tasks); - task_unlock(child); - write_unlock(&css_set_lock); + struct css_set *cset; + + down_write(&css_set_rwsem); + cset = task_css_set(current); + if (list_empty(&child->cg_list)) { + rcu_assign_pointer(child->cgroups, cset); + list_add(&child->cg_list, &cset->tasks); + get_css_set(cset); + } + up_write(&css_set_rwsem); } /* @@ -5039,15 +4436,7 @@ void cgroup_post_fork(struct task_struct *child) * and addition to css_set. */ if (need_forkexit_callback) { - /* - * fork/exit callbacks are supported only for builtin - * subsystems, and the builtin section of the subsys - * array is immutable, so we don't need to lock the - * subsys array here. On the other hand, modular section - * of the array can be freed at module unload, so we - * can't touch that. - */ - for_each_builtin_subsys(ss, i) + for_each_subsys(ss, i) if (ss->fork) ss->fork(child); } @@ -5056,7 +4445,6 @@ void cgroup_post_fork(struct task_struct *child) /** * cgroup_exit - detach cgroup from exiting task * @tsk: pointer to task_struct of exiting process - * @run_callback: run exit callbacks? * * Description: Detach cgroup from @tsk and release it. * @@ -5066,57 +4454,38 @@ void cgroup_post_fork(struct task_struct *child) * use notify_on_release cgroups where very high task exit scaling * is required on large systems. * - * the_top_cgroup_hack: - * - * Set the exiting tasks cgroup to the root cgroup (top_cgroup). - * - * We call cgroup_exit() while the task is still competent to - * handle notify_on_release(), then leave the task attached to the - * root cgroup in each hierarchy for the remainder of its exit. - * - * To do this properly, we would increment the reference count on - * top_cgroup, and near the very end of the kernel/exit.c do_exit() - * code we would add a second cgroup function call, to drop that - * reference. This would just create an unnecessary hot spot on - * the top_cgroup reference count, to no avail. - * - * Normally, holding a reference to a cgroup without bumping its - * count is unsafe. The cgroup could go away, or someone could - * attach us to a different cgroup, decrementing the count on - * the first cgroup that we never incremented. But in this case, - * top_cgroup isn't going away, and either task has PF_EXITING set, - * which wards off any cgroup_attach_task() attempts, or task is a failed - * fork, never visible to cgroup_attach_task. + * We set the exiting tasks cgroup to the root cgroup (top_cgroup). We + * call cgroup_exit() while the task is still competent to handle + * notify_on_release(), then leave the task attached to the root cgroup in + * each hierarchy for the remainder of its exit. No need to bother with + * init_css_set refcnting. init_css_set never goes away and we can't race + * with migration path - PF_EXITING is visible to migration path. */ -void cgroup_exit(struct task_struct *tsk, int run_callbacks) +void cgroup_exit(struct task_struct *tsk) { struct cgroup_subsys *ss; struct css_set *cset; + bool put_cset = false; int i; /* - * Unlink from the css_set task list if necessary. - * Optimistically check cg_list before taking - * css_set_lock + * Unlink from @tsk from its css_set. As migration path can't race + * with us, we can check cg_list without grabbing css_set_rwsem. */ if (!list_empty(&tsk->cg_list)) { - write_lock(&css_set_lock); - if (!list_empty(&tsk->cg_list)) - list_del_init(&tsk->cg_list); - write_unlock(&css_set_lock); + down_write(&css_set_rwsem); + list_del_init(&tsk->cg_list); + up_write(&css_set_rwsem); + put_cset = true; } /* Reassign the task to the init_css_set. */ - task_lock(tsk); cset = task_css_set(tsk); RCU_INIT_POINTER(tsk->cgroups, &init_css_set); - if (run_callbacks && need_forkexit_callback) { - /* - * fork/exit callbacks are supported only for builtin - * subsystems, see cgroup_post_fork() for details. - */ - for_each_builtin_subsys(ss, i) { + if (need_forkexit_callback) { + /* see cgroup_post_fork() for details */ + for_each_subsys(ss, i) { if (ss->exit) { struct cgroup_subsys_state *old_css = cset->subsys[i]; struct cgroup_subsys_state *css = task_css(tsk, i); @@ -5125,9 +4494,9 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks) } } } - task_unlock(tsk); - put_css_set_taskexit(cset); + if (put_cset) + put_css_set(cset, true); } static void check_for_release(struct cgroup *cgrp) @@ -5184,16 +4553,17 @@ static void cgroup_release_agent(struct work_struct *work) while (!list_empty(&release_list)) { char *argv[3], *envp[3]; int i; - char *pathbuf = NULL, *agentbuf = NULL; + char *pathbuf = NULL, *agentbuf = NULL, *path; struct cgroup *cgrp = list_entry(release_list.next, struct cgroup, release_list); list_del_init(&cgrp->release_list); raw_spin_unlock(&release_list_lock); - pathbuf = kmalloc(PAGE_SIZE, GFP_KERNEL); + pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); if (!pathbuf) goto continue_free; - if (cgroup_path(cgrp, pathbuf, PAGE_SIZE) < 0) + path = cgroup_path(cgrp, pathbuf, PATH_MAX); + if (!path) goto continue_free; agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL); if (!agentbuf) @@ -5201,7 +4571,7 @@ static void cgroup_release_agent(struct work_struct *work) i = 0; argv[i++] = agentbuf; - argv[i++] = pathbuf; + argv[i++] = path; argv[i] = NULL; i = 0; @@ -5235,11 +4605,7 @@ static int __init cgroup_disable(char *str) if (!*token) continue; - /* - * cgroup_disable, being at boot time, can't know about - * module subsystems, so we don't worry about them. - */ - for_each_builtin_subsys(ss, i) { + for_each_subsys(ss, i) { if (!strcmp(token, ss->name)) { ss->disabled = 1; printk(KERN_INFO "Disabling %s control group" @@ -5253,28 +4619,42 @@ static int __init cgroup_disable(char *str) __setup("cgroup_disable=", cgroup_disable); /** - * css_from_dir - get corresponding css from the dentry of a cgroup dir + * css_tryget_from_dir - get corresponding css from the dentry of a cgroup dir * @dentry: directory dentry of interest * @ss: subsystem of interest * - * Must be called under cgroup_mutex or RCU read lock. The caller is - * responsible for pinning the returned css if it needs to be accessed - * outside the critical section. + * If @dentry is a directory for a cgroup which has @ss enabled on it, try + * to get the corresponding css and return it. If such css doesn't exist + * or can't be pinned, an ERR_PTR value is returned. */ -struct cgroup_subsys_state *css_from_dir(struct dentry *dentry, - struct cgroup_subsys *ss) +struct cgroup_subsys_state *css_tryget_from_dir(struct dentry *dentry, + struct cgroup_subsys *ss) { + struct kernfs_node *kn = kernfs_node_from_dentry(dentry); + struct cgroup_subsys_state *css = NULL; struct cgroup *cgrp; - cgroup_assert_mutex_or_rcu_locked(); - /* is @dentry a cgroup dir? */ - if (!dentry->d_inode || - dentry->d_inode->i_op != &cgroup_dir_inode_operations) + if (dentry->d_sb->s_type != &cgroup_fs_type || !kn || + kernfs_type(kn) != KERNFS_DIR) return ERR_PTR(-EBADF); - cgrp = __d_cgrp(dentry); - return cgroup_css(cgrp, ss) ?: ERR_PTR(-ENOENT); + rcu_read_lock(); + + /* + * This path doesn't originate from kernfs and @kn could already + * have been or be removed at any point. @kn->priv is RCU + * protected for this access. See destroy_locked() for details. + */ + cgrp = rcu_dereference(kn->priv); + if (cgrp) + css = cgroup_css(cgrp, ss); + + if (!css || !css_tryget(css)) + css = ERR_PTR(-ENOENT); + + rcu_read_unlock(); + return css; } /** @@ -5289,7 +4669,7 @@ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss) { struct cgroup *cgrp; - cgroup_assert_mutex_or_rcu_locked(); + cgroup_assert_mutexes_or_rcu_locked(); cgrp = idr_find(&ss->root->cgroup_idr, id); if (cgrp) @@ -5341,23 +4721,25 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v) { struct cgrp_cset_link *link; struct css_set *cset; + char *name_buf; - read_lock(&css_set_lock); + name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL); + if (!name_buf) + return -ENOMEM; + + down_read(&css_set_rwsem); rcu_read_lock(); cset = rcu_dereference(current->cgroups); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; - const char *name; - if (c->dentry) - name = c->dentry->d_name.name; - else - name = "?"; + cgroup_name(c, name_buf, NAME_MAX + 1); seq_printf(seq, "Root %d group %s\n", - c->root->hierarchy_id, name); + c->root->hierarchy_id, name_buf); } rcu_read_unlock(); - read_unlock(&css_set_lock); + up_read(&css_set_rwsem); + kfree(name_buf); return 0; } @@ -5367,23 +4749,30 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v) struct cgroup_subsys_state *css = seq_css(seq); struct cgrp_cset_link *link; - read_lock(&css_set_lock); + down_read(&css_set_rwsem); list_for_each_entry(link, &css->cgroup->cset_links, cset_link) { struct css_set *cset = link->cset; struct task_struct *task; int count = 0; + seq_printf(seq, "css_set %p\n", cset); + list_for_each_entry(task, &cset->tasks, cg_list) { - if (count++ > MAX_TASKS_SHOWN_PER_CSS) { - seq_puts(seq, " ...\n"); - break; - } else { - seq_printf(seq, " task %d\n", - task_pid_vnr(task)); - } + if (count++ > MAX_TASKS_SHOWN_PER_CSS) + goto overflow; + seq_printf(seq, " task %d\n", task_pid_vnr(task)); + } + + list_for_each_entry(task, &cset->mg_tasks, cg_list) { + if (count++ > MAX_TASKS_SHOWN_PER_CSS) + goto overflow; + seq_printf(seq, " task %d\n", task_pid_vnr(task)); } + continue; + overflow: + seq_puts(seq, " ...\n"); } - read_unlock(&css_set_lock); + up_read(&css_set_rwsem); return 0; } @@ -5426,11 +4815,9 @@ static struct cftype debug_files[] = { { } /* terminate */ }; -struct cgroup_subsys debug_subsys = { - .name = "debug", +struct cgroup_subsys debug_cgrp_subsys = { .css_alloc = debug_css_alloc, .css_free = debug_css_free, - .subsys_id = debug_subsys_id, .base_cftypes = debug_files, }; #endif /* CONFIG_CGROUP_DEBUG */ diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 6c3154e477f6..2bc4a2256444 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -52,7 +52,7 @@ static inline struct freezer *css_freezer(struct cgroup_subsys_state *css) static inline struct freezer *task_freezer(struct task_struct *task) { - return css_freezer(task_css(task, freezer_subsys_id)); + return css_freezer(task_css(task, freezer_cgrp_id)); } static struct freezer *parent_freezer(struct freezer *freezer) @@ -84,8 +84,6 @@ static const char *freezer_state_strs(unsigned int state) return "THAWED"; }; -struct cgroup_subsys freezer_subsys; - static struct cgroup_subsys_state * freezer_css_alloc(struct cgroup_subsys_state *parent_css) { @@ -189,7 +187,7 @@ static void freezer_attach(struct cgroup_subsys_state *new_css, * current state before executing the following - !frozen tasks may * be visible in a FROZEN cgroup and frozen tasks in a THAWED one. */ - cgroup_taskset_for_each(task, new_css, tset) { + cgroup_taskset_for_each(task, tset) { if (!(freezer->state & CGROUP_FREEZING)) { __thaw_task(task); } else { @@ -216,6 +214,16 @@ static void freezer_attach(struct cgroup_subsys_state *new_css, } } +/** + * freezer_fork - cgroup post fork callback + * @task: a task which has just been forked + * + * @task has just been created and should conform to the current state of + * the cgroup_freezer it belongs to. This function may race against + * freezer_attach(). Losing to freezer_attach() means that we don't have + * to do anything as freezer_attach() will put @task into the appropriate + * state. + */ static void freezer_fork(struct task_struct *task) { struct freezer *freezer; @@ -224,14 +232,26 @@ static void freezer_fork(struct task_struct *task) freezer = task_freezer(task); /* - * The root cgroup is non-freezable, so we can skip the - * following check. + * The root cgroup is non-freezable, so we can skip locking the + * freezer. This is safe regardless of race with task migration. + * If we didn't race or won, skipping is obviously the right thing + * to do. If we lost and root is the new cgroup, noop is still the + * right thing to do. */ if (!parent_freezer(freezer)) goto out; + /* + * Grab @freezer->lock and freeze @task after verifying @task still + * belongs to @freezer and it's freezing. The former is for the + * case where we have raced against task migration and lost and + * @task is already in a different cgroup which may not be frozen. + * This isn't strictly necessary as freeze_task() is allowed to be + * called spuriously but let's do it anyway for, if nothing else, + * documentation. + */ spin_lock_irq(&freezer->lock); - if (freezer->state & CGROUP_FREEZING) + if (freezer == task_freezer(task) && (freezer->state & CGROUP_FREEZING)) freeze_task(task); spin_unlock_irq(&freezer->lock); out: @@ -422,7 +442,7 @@ static void freezer_change_state(struct freezer *freezer, bool freeze) } static int freezer_write(struct cgroup_subsys_state *css, struct cftype *cft, - const char *buffer) + char *buffer) { bool freeze; @@ -473,13 +493,11 @@ static struct cftype files[] = { { } /* terminate */ }; -struct cgroup_subsys freezer_subsys = { - .name = "freezer", +struct cgroup_subsys freezer_cgrp_subsys = { .css_alloc = freezer_css_alloc, .css_online = freezer_css_online, .css_offline = freezer_css_offline, .css_free = freezer_css_free, - .subsys_id = freezer_subsys_id, .attach = freezer_attach, .fork = freezer_fork, .base_cftypes = files, diff --git a/kernel/cpu.c b/kernel/cpu.c index deff2e693766..a9e710eef0e2 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -19,6 +19,7 @@ #include <linux/mutex.h> #include <linux/gfp.h> #include <linux/suspend.h> +#include <linux/lockdep.h> #include "smpboot.h" @@ -27,18 +28,23 @@ static DEFINE_MUTEX(cpu_add_remove_lock); /* - * The following two API's must be used when attempting - * to serialize the updates to cpu_online_mask, cpu_present_mask. + * The following two APIs (cpu_maps_update_begin/done) must be used when + * attempting to serialize the updates to cpu_online_mask & cpu_present_mask. + * The APIs cpu_notifier_register_begin/done() must be used to protect CPU + * hotplug callback (un)registration performed using __register_cpu_notifier() + * or __unregister_cpu_notifier(). */ void cpu_maps_update_begin(void) { mutex_lock(&cpu_add_remove_lock); } +EXPORT_SYMBOL(cpu_notifier_register_begin); void cpu_maps_update_done(void) { mutex_unlock(&cpu_add_remove_lock); } +EXPORT_SYMBOL(cpu_notifier_register_done); static RAW_NOTIFIER_HEAD(cpu_chain); @@ -57,17 +63,30 @@ static struct { * an ongoing cpu hotplug operation. */ int refcount; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif } cpu_hotplug = { .active_writer = NULL, .lock = __MUTEX_INITIALIZER(cpu_hotplug.lock), .refcount = 0, +#ifdef CONFIG_DEBUG_LOCK_ALLOC + .dep_map = {.name = "cpu_hotplug.lock" }, +#endif }; +/* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */ +#define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map) +#define cpuhp_lock_acquire() lock_map_acquire(&cpu_hotplug.dep_map) +#define cpuhp_lock_release() lock_map_release(&cpu_hotplug.dep_map) + void get_online_cpus(void) { might_sleep(); if (cpu_hotplug.active_writer == current) return; + cpuhp_lock_acquire_read(); mutex_lock(&cpu_hotplug.lock); cpu_hotplug.refcount++; mutex_unlock(&cpu_hotplug.lock); @@ -87,6 +106,7 @@ void put_online_cpus(void) if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer)) wake_up_process(cpu_hotplug.active_writer); mutex_unlock(&cpu_hotplug.lock); + cpuhp_lock_release(); } EXPORT_SYMBOL_GPL(put_online_cpus); @@ -117,6 +137,7 @@ void cpu_hotplug_begin(void) { cpu_hotplug.active_writer = current; + cpuhp_lock_acquire(); for (;;) { mutex_lock(&cpu_hotplug.lock); if (likely(!cpu_hotplug.refcount)) @@ -131,6 +152,7 @@ void cpu_hotplug_done(void) { cpu_hotplug.active_writer = NULL; mutex_unlock(&cpu_hotplug.lock); + cpuhp_lock_release(); } /* @@ -166,6 +188,11 @@ int __ref register_cpu_notifier(struct notifier_block *nb) return ret; } +int __ref __register_cpu_notifier(struct notifier_block *nb) +{ + return raw_notifier_chain_register(&cpu_chain, nb); +} + static int __cpu_notify(unsigned long val, void *v, int nr_to_call, int *nr_calls) { @@ -189,6 +216,7 @@ static void cpu_notify_nofail(unsigned long val, void *v) BUG_ON(cpu_notify(val, v)); } EXPORT_SYMBOL(register_cpu_notifier); +EXPORT_SYMBOL(__register_cpu_notifier); void __ref unregister_cpu_notifier(struct notifier_block *nb) { @@ -198,6 +226,12 @@ void __ref unregister_cpu_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_cpu_notifier); +void __ref __unregister_cpu_notifier(struct notifier_block *nb) +{ + raw_notifier_chain_unregister(&cpu_chain, nb); +} +EXPORT_SYMBOL(__unregister_cpu_notifier); + /** * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU * @cpu: a CPU id diff --git a/kernel/cpuset.c b/kernel/cpuset.c index e6b1b66afe52..3d54c418bd06 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -119,7 +119,7 @@ static inline struct cpuset *css_cs(struct cgroup_subsys_state *css) /* Retrieve the cpuset for a task */ static inline struct cpuset *task_cs(struct task_struct *task) { - return css_cs(task_css(task, cpuset_subsys_id)); + return css_cs(task_css(task, cpuset_cgrp_id)); } static inline struct cpuset *parent_cs(struct cpuset *cs) @@ -467,7 +467,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial) * be changed to have empty cpus_allowed or mems_allowed. */ ret = -ENOSPC; - if ((cgroup_task_count(cur->css.cgroup) || cur->attach_in_progress)) { + if ((cgroup_has_tasks(cur->css.cgroup) || cur->attach_in_progress)) { if (!cpumask_empty(cur->cpus_allowed) && cpumask_empty(trial->cpus_allowed)) goto out; @@ -829,55 +829,36 @@ static struct cpuset *effective_nodemask_cpuset(struct cpuset *cs) } /** - * cpuset_change_cpumask - make a task's cpus_allowed the same as its cpuset's - * @tsk: task to test - * @data: cpuset to @tsk belongs to - * - * Called by css_scan_tasks() for each task in a cgroup whose cpus_allowed - * mask needs to be changed. - * - * We don't need to re-check for the cgroup/cpuset membership, since we're - * holding cpuset_mutex at this point. - */ -static void cpuset_change_cpumask(struct task_struct *tsk, void *data) -{ - struct cpuset *cs = data; - struct cpuset *cpus_cs = effective_cpumask_cpuset(cs); - - set_cpus_allowed_ptr(tsk, cpus_cs->cpus_allowed); -} - -/** * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset. * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed - * @heap: if NULL, defer allocating heap memory to css_scan_tasks() - * - * Called with cpuset_mutex held * - * The css_scan_tasks() function will scan all the tasks in a cgroup, - * calling callback functions for each. - * - * No return value. It's guaranteed that css_scan_tasks() always returns 0 - * if @heap != NULL. + * Iterate through each task of @cs updating its cpus_allowed to the + * effective cpuset's. As this function is called with cpuset_mutex held, + * cpuset membership stays stable. */ -static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap) +static void update_tasks_cpumask(struct cpuset *cs) { - css_scan_tasks(&cs->css, NULL, cpuset_change_cpumask, cs, heap); + struct cpuset *cpus_cs = effective_cpumask_cpuset(cs); + struct css_task_iter it; + struct task_struct *task; + + css_task_iter_start(&cs->css, &it); + while ((task = css_task_iter_next(&it))) + set_cpus_allowed_ptr(task, cpus_cs->cpus_allowed); + css_task_iter_end(&it); } /* * update_tasks_cpumask_hier - Update the cpumasks of tasks in the hierarchy. * @root_cs: the root cpuset of the hierarchy * @update_root: update root cpuset or not? - * @heap: the heap used by css_scan_tasks() * * This will update cpumasks of tasks in @root_cs and all other empty cpusets * which take on cpumask of @root_cs. * * Called with cpuset_mutex held */ -static void update_tasks_cpumask_hier(struct cpuset *root_cs, - bool update_root, struct ptr_heap *heap) +static void update_tasks_cpumask_hier(struct cpuset *root_cs, bool update_root) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; @@ -898,7 +879,7 @@ static void update_tasks_cpumask_hier(struct cpuset *root_cs, continue; rcu_read_unlock(); - update_tasks_cpumask(cp, heap); + update_tasks_cpumask(cp); rcu_read_lock(); css_put(&cp->css); @@ -914,7 +895,6 @@ static void update_tasks_cpumask_hier(struct cpuset *root_cs, static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { - struct ptr_heap heap; int retval; int is_load_balanced; @@ -947,19 +927,13 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, if (retval < 0) return retval; - retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL); - if (retval) - return retval; - is_load_balanced = is_sched_load_balance(trialcs); mutex_lock(&callback_mutex); cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); mutex_unlock(&callback_mutex); - update_tasks_cpumask_hier(cs, true, &heap); - - heap_free(&heap); + update_tasks_cpumask_hier(cs, true); if (is_load_balanced) rebuild_sched_domains_locked(); @@ -1022,7 +996,7 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, task_lock(tsk); /* * Determine if a loop is necessary if another thread is doing - * get_mems_allowed(). If at least one node remains unchanged and + * read_mems_allowed_begin(). If at least one node remains unchanged and * tsk does not have a mempolicy, then an empty nodemask will not be * possible when mems_allowed is larger than a word. */ @@ -1048,53 +1022,22 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, task_unlock(tsk); } -struct cpuset_change_nodemask_arg { - struct cpuset *cs; - nodemask_t *newmems; -}; - -/* - * Update task's mems_allowed and rebind its mempolicy and vmas' mempolicy - * of it to cpuset's new mems_allowed, and migrate pages to new nodes if - * memory_migrate flag is set. Called with cpuset_mutex held. - */ -static void cpuset_change_nodemask(struct task_struct *p, void *data) -{ - struct cpuset_change_nodemask_arg *arg = data; - struct cpuset *cs = arg->cs; - struct mm_struct *mm; - int migrate; - - cpuset_change_task_nodemask(p, arg->newmems); - - mm = get_task_mm(p); - if (!mm) - return; - - migrate = is_memory_migrate(cs); - - mpol_rebind_mm(mm, &cs->mems_allowed); - if (migrate) - cpuset_migrate_mm(mm, &cs->old_mems_allowed, arg->newmems); - mmput(mm); -} - static void *cpuset_being_rebound; /** * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset. * @cs: the cpuset in which each task's mems_allowed mask needs to be changed - * @heap: if NULL, defer allocating heap memory to css_scan_tasks() * - * Called with cpuset_mutex held. No return value. It's guaranteed that - * css_scan_tasks() always returns 0 if @heap != NULL. + * Iterate through each task of @cs updating its mems_allowed to the + * effective cpuset's. As this function is called with cpuset_mutex held, + * cpuset membership stays stable. */ -static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap) +static void update_tasks_nodemask(struct cpuset *cs) { static nodemask_t newmems; /* protected by cpuset_mutex */ struct cpuset *mems_cs = effective_nodemask_cpuset(cs); - struct cpuset_change_nodemask_arg arg = { .cs = cs, - .newmems = &newmems }; + struct css_task_iter it; + struct task_struct *task; cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ @@ -1110,7 +1053,25 @@ static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap) * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. */ - css_scan_tasks(&cs->css, NULL, cpuset_change_nodemask, &arg, heap); + css_task_iter_start(&cs->css, &it); + while ((task = css_task_iter_next(&it))) { + struct mm_struct *mm; + bool migrate; + + cpuset_change_task_nodemask(task, &newmems); + + mm = get_task_mm(task); + if (!mm) + continue; + + migrate = is_memory_migrate(cs); + + mpol_rebind_mm(mm, &cs->mems_allowed); + if (migrate) + cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); + mmput(mm); + } + css_task_iter_end(&it); /* * All the tasks' nodemasks have been updated, update @@ -1126,15 +1087,13 @@ static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap) * update_tasks_nodemask_hier - Update the nodemasks of tasks in the hierarchy. * @cs: the root cpuset of the hierarchy * @update_root: update the root cpuset or not? - * @heap: the heap used by css_scan_tasks() * * This will update nodemasks of tasks in @root_cs and all other empty cpusets * which take on nodemask of @root_cs. * * Called with cpuset_mutex held */ -static void update_tasks_nodemask_hier(struct cpuset *root_cs, - bool update_root, struct ptr_heap *heap) +static void update_tasks_nodemask_hier(struct cpuset *root_cs, bool update_root) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; @@ -1155,7 +1114,7 @@ static void update_tasks_nodemask_hier(struct cpuset *root_cs, continue; rcu_read_unlock(); - update_tasks_nodemask(cp, heap); + update_tasks_nodemask(cp); rcu_read_lock(); css_put(&cp->css); @@ -1180,7 +1139,6 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; - struct ptr_heap heap; /* * top_cpuset.mems_allowed tracks node_stats[N_MEMORY]; @@ -1219,17 +1177,11 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, if (retval < 0) goto done; - retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL); - if (retval < 0) - goto done; - mutex_lock(&callback_mutex); cs->mems_allowed = trialcs->mems_allowed; mutex_unlock(&callback_mutex); - update_tasks_nodemask_hier(cs, true, &heap); - - heap_free(&heap); + update_tasks_nodemask_hier(cs, true); done: return retval; } @@ -1257,38 +1209,22 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) } /** - * cpuset_change_flag - make a task's spread flags the same as its cpuset's - * @tsk: task to be updated - * @data: cpuset to @tsk belongs to - * - * Called by css_scan_tasks() for each task in a cgroup. - * - * We don't need to re-check for the cgroup/cpuset membership, since we're - * holding cpuset_mutex at this point. - */ -static void cpuset_change_flag(struct task_struct *tsk, void *data) -{ - struct cpuset *cs = data; - - cpuset_update_task_spread_flag(cs, tsk); -} - -/** * update_tasks_flags - update the spread flags of tasks in the cpuset. * @cs: the cpuset in which each task's spread flags needs to be changed - * @heap: if NULL, defer allocating heap memory to css_scan_tasks() - * - * Called with cpuset_mutex held * - * The css_scan_tasks() function will scan all the tasks in a cgroup, - * calling callback functions for each. - * - * No return value. It's guaranteed that css_scan_tasks() always returns 0 - * if @heap != NULL. + * Iterate through each task of @cs updating its spread flags. As this + * function is called with cpuset_mutex held, cpuset membership stays + * stable. */ -static void update_tasks_flags(struct cpuset *cs, struct ptr_heap *heap) +static void update_tasks_flags(struct cpuset *cs) { - css_scan_tasks(&cs->css, NULL, cpuset_change_flag, cs, heap); + struct css_task_iter it; + struct task_struct *task; + + css_task_iter_start(&cs->css, &it); + while ((task = css_task_iter_next(&it))) + cpuset_update_task_spread_flag(cs, task); + css_task_iter_end(&it); } /* @@ -1306,7 +1242,6 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, struct cpuset *trialcs; int balance_flag_changed; int spread_flag_changed; - struct ptr_heap heap; int err; trialcs = alloc_trial_cpuset(cs); @@ -1322,10 +1257,6 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, if (err < 0) goto out; - err = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL); - if (err < 0) - goto out; - balance_flag_changed = (is_sched_load_balance(cs) != is_sched_load_balance(trialcs)); @@ -1340,8 +1271,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, rebuild_sched_domains_locked(); if (spread_flag_changed) - update_tasks_flags(cs, &heap); - heap_free(&heap); + update_tasks_flags(cs); out: free_trial_cpuset(trialcs); return err; @@ -1445,6 +1375,8 @@ static int fmeter_getrate(struct fmeter *fmp) return val; } +static struct cpuset *cpuset_attach_old_cs; + /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) @@ -1453,6 +1385,9 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css, struct task_struct *task; int ret; + /* used later by cpuset_attach() */ + cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset)); + mutex_lock(&cpuset_mutex); /* @@ -1464,7 +1399,7 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css, (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; - cgroup_taskset_for_each(task, css, tset) { + cgroup_taskset_for_each(task, tset) { /* * Kthreads which disallow setaffinity shouldn't be moved * to a new cpuset; we don't want to change their cpu @@ -1516,10 +1451,8 @@ static void cpuset_attach(struct cgroup_subsys_state *css, struct mm_struct *mm; struct task_struct *task; struct task_struct *leader = cgroup_taskset_first(tset); - struct cgroup_subsys_state *oldcss = cgroup_taskset_cur_css(tset, - cpuset_subsys_id); struct cpuset *cs = css_cs(css); - struct cpuset *oldcs = css_cs(oldcss); + struct cpuset *oldcs = cpuset_attach_old_cs; struct cpuset *cpus_cs = effective_cpumask_cpuset(cs); struct cpuset *mems_cs = effective_nodemask_cpuset(cs); @@ -1533,7 +1466,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css, guarantee_online_mems(mems_cs, &cpuset_attach_nodemask_to); - cgroup_taskset_for_each(task, css, tset) { + cgroup_taskset_for_each(task, tset) { /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here @@ -1673,7 +1606,7 @@ out_unlock: * Common handling for a write to a "cpus" or "mems" file. */ static int cpuset_write_resmask(struct cgroup_subsys_state *css, - struct cftype *cft, const char *buf) + struct cftype *cft, char *buf) { struct cpuset *cs = css_cs(css); struct cpuset *trialcs; @@ -2020,8 +1953,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css) kfree(cs); } -struct cgroup_subsys cpuset_subsys = { - .name = "cpuset", +struct cgroup_subsys cpuset_cgrp_subsys = { .css_alloc = cpuset_css_alloc, .css_online = cpuset_css_online, .css_offline = cpuset_css_offline, @@ -2029,7 +1961,6 @@ struct cgroup_subsys cpuset_subsys = { .can_attach = cpuset_can_attach, .cancel_attach = cpuset_cancel_attach, .attach = cpuset_attach, - .subsys_id = cpuset_subsys_id, .base_cftypes = files, .early_init = 1, }; @@ -2086,10 +2017,9 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) parent = parent_cs(parent); if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) { - rcu_read_lock(); - printk(KERN_ERR "cpuset: failed to transfer tasks out of empty cpuset %s\n", - cgroup_name(cs->css.cgroup)); - rcu_read_unlock(); + printk(KERN_ERR "cpuset: failed to transfer tasks out of empty cpuset "); + pr_cont_cgroup_name(cs->css.cgroup); + pr_cont("\n"); } } @@ -2137,7 +2067,7 @@ retry: */ if ((sane && cpumask_empty(cs->cpus_allowed)) || (!cpumask_empty(&off_cpus) && !cpumask_empty(cs->cpus_allowed))) - update_tasks_cpumask(cs, NULL); + update_tasks_cpumask(cs); mutex_lock(&callback_mutex); nodes_andnot(cs->mems_allowed, cs->mems_allowed, off_mems); @@ -2151,7 +2081,7 @@ retry: */ if ((sane && nodes_empty(cs->mems_allowed)) || (!nodes_empty(off_mems) && !nodes_empty(cs->mems_allowed))) - update_tasks_nodemask(cs, NULL); + update_tasks_nodemask(cs); is_empty = cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed); @@ -2213,7 +2143,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) mutex_lock(&callback_mutex); top_cpuset.mems_allowed = new_mems; mutex_unlock(&callback_mutex); - update_tasks_nodemask(&top_cpuset, NULL); + update_tasks_nodemask(&top_cpuset); } mutex_unlock(&cpuset_mutex); @@ -2305,10 +2235,10 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) struct cpuset *cpus_cs; mutex_lock(&callback_mutex); - task_lock(tsk); + rcu_read_lock(); cpus_cs = effective_cpumask_cpuset(task_cs(tsk)); guarantee_online_cpus(cpus_cs, pmask); - task_unlock(tsk); + rcu_read_unlock(); mutex_unlock(&callback_mutex); } @@ -2361,10 +2291,10 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) nodemask_t mask; mutex_lock(&callback_mutex); - task_lock(tsk); + rcu_read_lock(); mems_cs = effective_nodemask_cpuset(task_cs(tsk)); guarantee_online_mems(mems_cs, &mask); - task_unlock(tsk); + rcu_read_unlock(); mutex_unlock(&callback_mutex); return mask; @@ -2480,10 +2410,10 @@ int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask) /* Not hardwall and node outside mems_allowed: scan up cpusets */ mutex_lock(&callback_mutex); - task_lock(current); + rcu_read_lock(); cs = nearest_hardwall_ancestor(task_cs(current)); allowed = node_isset(node, cs->mems_allowed); - task_unlock(current); + rcu_read_unlock(); mutex_unlock(&callback_mutex); return allowed; @@ -2609,27 +2539,27 @@ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, * @task: pointer to task_struct of some task. * * Description: Prints @task's name, cpuset name, and cached copy of its - * mems_allowed to the kernel log. Must hold task_lock(task) to allow - * dereferencing task_cs(task). + * mems_allowed to the kernel log. */ 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; - struct cgroup *cgrp = task_cs(tsk)->css.cgroup; - - rcu_read_lock(); spin_lock(&cpuset_buffer_lock); + rcu_read_lock(); + cgrp = task_cs(tsk)->css.cgroup; nodelist_scnprintf(cpuset_nodelist, CPUSET_NODELIST_LEN, tsk->mems_allowed); - printk(KERN_INFO "%s cpuset=%s mems_allowed=%s\n", - tsk->comm, cgroup_name(cgrp), cpuset_nodelist); + printk(KERN_INFO "%s cpuset=", tsk->comm); + pr_cont_cgroup_name(cgrp); + pr_cont(" mems_allowed=%s\n", cpuset_nodelist); - spin_unlock(&cpuset_buffer_lock); rcu_read_unlock(); + spin_unlock(&cpuset_buffer_lock); } /* @@ -2660,9 +2590,9 @@ int cpuset_memory_pressure_enabled __read_mostly; void __cpuset_memory_pressure_bump(void) { - task_lock(current); + rcu_read_lock(); fmeter_markevent(&task_cs(current)->fmeter); - task_unlock(current); + rcu_read_unlock(); } #ifdef CONFIG_PROC_PID_CPUSET @@ -2679,12 +2609,12 @@ int proc_cpuset_show(struct seq_file *m, void *unused_v) { struct pid *pid; struct task_struct *tsk; - char *buf; + char *buf, *p; struct cgroup_subsys_state *css; int retval; retval = -ENOMEM; - buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) goto out; @@ -2694,14 +2624,16 @@ int proc_cpuset_show(struct seq_file *m, void *unused_v) if (!tsk) goto out_free; + retval = -ENAMETOOLONG; rcu_read_lock(); - css = task_css(tsk, cpuset_subsys_id); - retval = cgroup_path(css->cgroup, buf, PAGE_SIZE); + css = task_css(tsk, cpuset_cgrp_id); + p = cgroup_path(css->cgroup, buf, PATH_MAX); rcu_read_unlock(); - if (retval < 0) + if (!p) goto out_put_task; - seq_puts(m, buf); + seq_puts(m, p); seq_putc(m, '\n'); + retval = 0; out_put_task: put_task_struct(tsk); out_free: diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 99982a70ddad..2956c8da1605 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -49,6 +49,7 @@ #include <linux/pid.h> #include <linux/smp.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/rcupdate.h> #include <asm/cacheflush.h> @@ -224,10 +225,17 @@ static void kgdb_flush_swbreak_addr(unsigned long addr) if (!CACHE_FLUSH_IS_SAFE) return; - if (current->mm && current->mm->mmap_cache) { - flush_cache_range(current->mm->mmap_cache, - addr, addr + BREAK_INSTR_SIZE); + if (current->mm) { + int i; + + for (i = 0; i < VMACACHE_SIZE; i++) { + if (!current->vmacache[i]) + continue; + flush_cache_range(current->vmacache[i], + addr, addr + BREAK_INSTR_SIZE); + } } + /* Force flush instruction cache if it was outside the mm */ flush_icache_range(addr, addr + BREAK_INSTR_SIZE); } diff --git a/kernel/events/core.c b/kernel/events/core.c index 661951ab8ae7..f83a71a3e46d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -361,7 +361,7 @@ struct perf_cgroup { static inline struct perf_cgroup * perf_cgroup_from_task(struct task_struct *task) { - return container_of(task_css(task, perf_subsys_id), + return container_of(task_css(task, perf_event_cgrp_id), struct perf_cgroup, css); } @@ -389,11 +389,6 @@ perf_cgroup_match(struct perf_event *event) event->cgrp->css.cgroup); } -static inline bool perf_tryget_cgroup(struct perf_event *event) -{ - return css_tryget(&event->cgrp->css); -} - static inline void perf_put_cgroup(struct perf_event *event) { css_put(&event->cgrp->css); @@ -612,9 +607,7 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event, if (!f.file) return -EBADF; - rcu_read_lock(); - - css = css_from_dir(f.file->f_dentry, &perf_subsys); + css = css_tryget_from_dir(f.file->f_dentry, &perf_event_cgrp_subsys); if (IS_ERR(css)) { ret = PTR_ERR(css); goto out; @@ -623,13 +616,6 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event, cgrp = container_of(css, struct perf_cgroup, css); event->cgrp = cgrp; - /* must be done before we fput() the file */ - if (!perf_tryget_cgroup(event)) { - event->cgrp = NULL; - ret = -ENOENT; - goto out; - } - /* * all events in a group must monitor * the same cgroup because a task belongs @@ -640,7 +626,6 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event, ret = -EINVAL; } out: - rcu_read_unlock(); fdput(f); return ret; } @@ -8053,7 +8038,7 @@ static void perf_cgroup_attach(struct cgroup_subsys_state *css, { struct task_struct *task; - cgroup_taskset_for_each(task, css, tset) + cgroup_taskset_for_each(task, tset) task_function_call(task, __perf_cgroup_move, task); } @@ -8072,9 +8057,7 @@ static void perf_cgroup_exit(struct cgroup_subsys_state *css, task_function_call(task, __perf_cgroup_move, task); } -struct cgroup_subsys perf_subsys = { - .name = "perf_event", - .subsys_id = perf_subsys_id, +struct cgroup_subsys perf_event_cgrp_subsys = { .css_alloc = perf_cgroup_css_alloc, .css_free = perf_cgroup_css_free, .exit = perf_cgroup_exit, diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 307d87c0991a..04709b66369d 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1804,6 +1804,11 @@ static bool handle_trampoline(struct pt_regs *regs) return true; } +bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs) +{ + return false; +} + /* * Run handler and ask thread to singlestep. * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. @@ -1858,7 +1863,11 @@ static void handle_swbp(struct pt_regs *regs) if (!get_utask()) goto out; + if (arch_uprobe_ignore(&uprobe->arch, regs)) + goto out; + handler_chain(uprobe, regs); + if (can_skip_sstep(uprobe, regs)) goto out; diff --git a/kernel/exit.c b/kernel/exit.c index 1e77fc645317..6ed6a1d552b5 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -570,7 +570,7 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p, if (same_thread_group(p->real_parent, father)) return; - /* We don't want people slaying init. */ + /* We don't want people slaying init. */ p->exit_signal = SIGCHLD; /* If it has exited notify the new parent about this child's death. */ @@ -784,9 +784,10 @@ void do_exit(long code) exit_shm(tsk); exit_files(tsk); exit_fs(tsk); + if (group_dead) + disassociate_ctty(1); exit_task_namespaces(tsk); exit_task_work(tsk); - check_stack_usage(); exit_thread(); /* @@ -797,21 +798,17 @@ void do_exit(long code) */ perf_event_exit_task(tsk); - cgroup_exit(tsk, 1); - - if (group_dead) - disassociate_ctty(1); + cgroup_exit(tsk); module_put(task_thread_info(tsk)->exec_domain->module); - proc_exit_connector(tsk); - /* * FIXME: do that only when needed, using sched_exit tracepoint */ flush_ptrace_hw_breakpoint(tsk); exit_notify(tsk, group_dead); + proc_exit_connector(tsk); #ifdef CONFIG_NUMA task_lock(tsk); mpol_put(tsk->mempolicy); @@ -844,6 +841,7 @@ void do_exit(long code) validate_creds_for_do_exit(tsk); + check_stack_usage(); preempt_disable(); if (tsk->nr_dirtied) __this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied); @@ -1038,17 +1036,13 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) return wait_noreap_copyout(wo, p, pid, uid, why, status); } + traced = ptrace_reparented(p); /* - * Try to move the task's state to DEAD - * only one thread is allowed to do this: + * Move the task's state to DEAD/TRACE, only one thread can do this. */ - state = xchg(&p->exit_state, EXIT_DEAD); - if (state != EXIT_ZOMBIE) { - BUG_ON(state != EXIT_DEAD); + state = traced && thread_group_leader(p) ? EXIT_TRACE : EXIT_DEAD; + if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE) return 0; - } - - traced = ptrace_reparented(p); /* * It can be ptraced but not reparented, check * thread_group_leader() to filter out sub-threads. @@ -1109,7 +1103,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) /* * Now we are sure this task is interesting, and no other - * thread can reap it because we set its state to EXIT_DEAD. + * thread can reap it because we its state == DEAD/TRACE. */ read_unlock(&tasklist_lock); @@ -1146,22 +1140,19 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) if (!retval) retval = pid; - if (traced) { + if (state == EXIT_TRACE) { write_lock_irq(&tasklist_lock); /* We dropped tasklist, ptracer could die and untrace */ ptrace_unlink(p); - /* - * If this is not a sub-thread, notify the parent. - * If parent wants a zombie, don't release it now. - */ - if (thread_group_leader(p) && - !do_notify_parent(p, p->exit_signal)) { - p->exit_state = EXIT_ZOMBIE; - p = NULL; - } + + /* If parent wants a zombie, don't release it now */ + state = EXIT_ZOMBIE; + if (do_notify_parent(p, p->exit_signal)) + state = EXIT_DEAD; + p->exit_state = state; write_unlock_irq(&tasklist_lock); } - if (p != NULL) + if (state == EXIT_DEAD) release_task(p); return retval; @@ -1338,7 +1329,12 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) static int wait_consider_task(struct wait_opts *wo, int ptrace, struct task_struct *p) { - int ret = eligible_child(wo, p); + int ret; + + if (unlikely(p->exit_state == EXIT_DEAD)) + return 0; + + ret = eligible_child(wo, p); if (!ret) return ret; @@ -1356,33 +1352,44 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace, return 0; } - /* dead body doesn't have much to contribute */ - if (unlikely(p->exit_state == EXIT_DEAD)) { + if (unlikely(p->exit_state == EXIT_TRACE)) { /* - * But do not ignore this task until the tracer does - * wait_task_zombie()->do_notify_parent(). + * ptrace == 0 means we are the natural parent. In this case + * we should clear notask_error, debugger will notify us. */ - if (likely(!ptrace) && unlikely(ptrace_reparented(p))) + if (likely(!ptrace)) wo->notask_error = 0; return 0; } - /* slay zombie? */ - if (p->exit_state == EXIT_ZOMBIE) { + if (likely(!ptrace) && unlikely(p->ptrace)) { /* - * A zombie ptracee is only visible to its ptracer. - * Notification and reaping will be cascaded to the real - * parent when the ptracer detaches. + * If it is traced by its real parent's group, just pretend + * the caller is ptrace_do_wait() and reap this child if it + * is zombie. + * + * This also hides group stop state from real parent; otherwise + * a single stop can be reported twice as group and ptrace stop. + * If a ptracer wants to distinguish these two events for its + * own children it should create a separate process which takes + * the role of real parent. */ - if (likely(!ptrace) && unlikely(p->ptrace)) { - /* it will become visible, clear notask_error */ - wo->notask_error = 0; - return 0; - } + if (!ptrace_reparented(p)) + ptrace = 1; + } + /* slay zombie? */ + if (p->exit_state == EXIT_ZOMBIE) { /* we don't reap group leaders with subthreads */ - if (!delay_group_leader(p)) - return wait_task_zombie(wo, p); + if (!delay_group_leader(p)) { + /* + * A zombie ptracee is only visible to its ptracer. + * Notification and reaping will be cascaded to the + * real parent when the ptracer detaches. + */ + if (unlikely(ptrace) || likely(!p->ptrace)) + return wait_task_zombie(wo, p); + } /* * Allow access to stopped/continued state via zombie by @@ -1408,19 +1415,6 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace, wo->notask_error = 0; } else { /* - * If @p is ptraced by a task in its real parent's group, - * hide group stop/continued state when looking at @p as - * the real parent; otherwise, a single stop can be - * reported twice as group and ptrace stops. - * - * If a ptracer wants to distinguish the two events for its - * own children, it should create a separate process which - * takes the role of real parent. - */ - if (likely(!ptrace) && p->ptrace && !ptrace_reparented(p)) - return 0; - - /* * @p is alive and it's gonna stop, continue or exit, so * there always is something to wait for. */ diff --git a/kernel/fork.c b/kernel/fork.c index 332688e5e7b4..54a8d26f612f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -28,6 +28,8 @@ #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/fs.h> +#include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> @@ -71,6 +73,7 @@ #include <linux/signalfd.h> #include <linux/uprobes.h> #include <linux/aio.h> +#include <linux/compiler.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -284,7 +287,7 @@ void __init fork_init(unsigned long mempages) init_task.signal->rlim[RLIMIT_NPROC]; } -int __attribute__((weak)) arch_dup_task_struct(struct task_struct *dst, +int __weak arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; @@ -364,7 +367,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) mm->locked_vm = 0; mm->mmap = NULL; - mm->mmap_cache = NULL; + mm->vmacache_seqnum = 0; mm->map_count = 0; cpumask_clear(mm_cpumask(mm)); mm->mm_rb = RB_ROOT; @@ -530,8 +533,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) atomic_set(&mm->mm_count, 1); init_rwsem(&mm->mmap_sem); INIT_LIST_HEAD(&mm->mmlist); - mm->flags = (current->mm) ? - (current->mm->flags & MMF_INIT_MASK) : default_dump_filter; mm->core_state = NULL; atomic_long_set(&mm->nr_ptes, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); @@ -540,8 +541,15 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) mm_init_owner(mm, p); clear_tlb_flush_pending(mm); - if (likely(!mm_alloc_pgd(mm))) { + if (current->mm) { + mm->flags = current->mm->flags & MMF_INIT_MASK; + mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; + } else { + mm->flags = default_dump_filter; mm->def_flags = 0; + } + + if (likely(!mm_alloc_pgd(mm))) { mmu_notifier_mm_init(mm); return mm; } @@ -877,6 +885,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) if (!oldmm) return 0; + /* initialize the new vmacache entries */ + vmacache_flush(tsk); + if (clone_flags & CLONE_VM) { atomic_inc(&oldmm->mm_users); mm = oldmm; @@ -1070,15 +1081,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) return 0; } -static void copy_flags(unsigned long clone_flags, struct task_struct *p) -{ - unsigned long new_flags = p->flags; - - new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER); - new_flags |= PF_FORKNOEXEC; - p->flags = new_flags; -} - SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) { current->clear_child_tid = tidptr; @@ -1228,7 +1230,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ - copy_flags(clone_flags, p); + p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER); + p->flags |= PF_FORKNOEXEC; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); rcu_copy_process(p); @@ -1272,9 +1275,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; - goto bad_fork_cleanup_cgroup; + goto bad_fork_cleanup_threadgroup_lock; } - mpol_fix_fork_child_flag(p); #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; @@ -1525,11 +1527,10 @@ bad_fork_cleanup_policy: perf_event_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); -bad_fork_cleanup_cgroup: +bad_fork_cleanup_threadgroup_lock: #endif if (clone_flags & CLONE_THREAD) threadgroup_change_end(current); - cgroup_exit(p, 0); delayacct_tsk_free(p); module_put(task_thread_info(p)->exec_domain->module); bad_fork_cleanup_count: diff --git a/kernel/futex.c b/kernel/futex.c index 67dacaf93e56..5f589279e462 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -70,7 +70,10 @@ #include "locking/rtmutex_common.h" /* - * Basic futex operation and ordering guarantees: + * READ this before attempting to hack on futexes! + * + * Basic futex operation and ordering guarantees + * ============================================= * * The waiter reads the futex value in user space and calls * futex_wait(). This function computes the hash bucket and acquires @@ -119,7 +122,7 @@ * sys_futex(WAIT, futex, val); * futex_wait(futex, val); * - * waiters++; + * waiters++; (a) * mb(); (A) <-- paired with -. * | * lock(hash_bucket(futex)); | @@ -135,14 +138,14 @@ * unlock(hash_bucket(futex)); * schedule(); if (waiters) * lock(hash_bucket(futex)); - * wake_waiters(futex); - * unlock(hash_bucket(futex)); + * else wake_waiters(futex); + * waiters--; (b) unlock(hash_bucket(futex)); * - * Where (A) orders the waiters increment and the futex value read -- this - * is guaranteed by the head counter in the hb spinlock; and where (B) - * orders the write to futex and the waiters read -- this is done by the - * barriers in get_futex_key_refs(), through either ihold or atomic_inc, - * depending on the futex type. + * Where (A) orders the waiters increment and the futex value read through + * atomic operations (see hb_waiters_inc) and where (B) orders the write + * to futex and the waiters read -- this is done by the barriers in + * get_futex_key_refs(), through either ihold or atomic_inc, depending on the + * futex type. * * This yields the following case (where X:=waiters, Y:=futex): * @@ -155,6 +158,17 @@ * Which guarantees that x==0 && y==0 is impossible; which translates back into * the guarantee that we cannot both miss the futex variable change and the * enqueue. + * + * Note that a new waiter is accounted for in (a) even when it is possible that + * the wait call can return error, in which case we backtrack from it in (b). + * Refer to the comment in queue_lock(). + * + * Similarly, in order to account for waiters being requeued on another + * address we always increment the waiters for the destination bucket before + * acquiring the lock. It then decrements them again after releasing it - + * the code that actually moves the futex(es) between hash buckets (requeue_futex) + * will do the additional required waiter count housekeeping. This is done for + * double_lock_hb() and double_unlock_hb(), respectively. */ #ifndef CONFIG_HAVE_FUTEX_CMPXCHG @@ -1452,6 +1466,7 @@ retry: hb2 = hash_futex(&key2); retry_private: + hb_waiters_inc(hb2); double_lock_hb(hb1, hb2); if (likely(cmpval != NULL)) { @@ -1461,6 +1476,7 @@ retry_private: if (unlikely(ret)) { double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); ret = get_user(curval, uaddr1); if (ret) @@ -1510,6 +1526,7 @@ retry_private: break; case -EFAULT: double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); put_futex_key(&key2); put_futex_key(&key1); ret = fault_in_user_writeable(uaddr2); @@ -1519,6 +1536,7 @@ retry_private: case -EAGAIN: /* The owner was exiting, try again. */ double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); put_futex_key(&key2); put_futex_key(&key1); cond_resched(); @@ -1594,6 +1612,7 @@ retry_private: out_unlock: double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); /* * drop_futex_key_refs() must be called outside the spinlocks. During diff --git a/kernel/groups.c b/kernel/groups.c index 90cf1c38c8ea..451698f86cfa 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -157,17 +157,13 @@ int groups_search(const struct group_info *group_info, kgid_t grp) * set_groups - Change a group subscription in a set of credentials * @new: The newly prepared set of credentials to alter * @group_info: The group list to install - * - * Validate a group subscription and, if valid, insert it into a set - * of credentials. */ -int set_groups(struct cred *new, struct group_info *group_info) +void set_groups(struct cred *new, struct group_info *group_info) { put_group_info(new->group_info); groups_sort(group_info); get_group_info(group_info); new->group_info = group_info; - return 0; } EXPORT_SYMBOL(set_groups); @@ -182,18 +178,12 @@ EXPORT_SYMBOL(set_groups); int set_current_groups(struct group_info *group_info) { struct cred *new; - int ret; new = prepare_creds(); if (!new) return -ENOMEM; - ret = set_groups(new, group_info); - if (ret < 0) { - abort_creds(new); - return ret; - } - + set_groups(new, group_info); return commit_creds(new); } diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 0b9c169d577f..06bb1417b063 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -246,5 +246,4 @@ static int __init hung_task_init(void) return 0; } - -module_init(hung_task_init); +subsys_initcall(hung_task_init); diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 3127ad52cdb2..cb0cf37dac3a 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -23,6 +23,7 @@ #include <linux/mm.h> #include <linux/ctype.h> #include <linux/slab.h> +#include <linux/compiler.h> #include <asm/sections.h> @@ -36,8 +37,8 @@ * These will be re-linked against their real values * during the second link stage. */ -extern const unsigned long kallsyms_addresses[] __attribute__((weak)); -extern const u8 kallsyms_names[] __attribute__((weak)); +extern const unsigned long kallsyms_addresses[] __weak; +extern const u8 kallsyms_names[] __weak; /* * Tell the compiler that the count isn't in the small data section if the arch @@ -46,10 +47,10 @@ extern const u8 kallsyms_names[] __attribute__((weak)); extern const unsigned long kallsyms_num_syms __attribute__((weak, section(".rodata"))); -extern const u8 kallsyms_token_table[] __attribute__((weak)); -extern const u16 kallsyms_token_index[] __attribute__((weak)); +extern const u8 kallsyms_token_table[] __weak; +extern const u16 kallsyms_token_index[] __weak; -extern const unsigned long kallsyms_markers[] __attribute__((weak)); +extern const unsigned long kallsyms_markers[] __weak; static inline int is_kernel_inittext(unsigned long addr) { diff --git a/kernel/kexec.c b/kernel/kexec.c index 45601cf41bee..c8380ad203bc 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -32,6 +32,7 @@ #include <linux/vmalloc.h> #include <linux/swap.h> #include <linux/syscore_ops.h> +#include <linux/compiler.h> #include <asm/page.h> #include <asm/uaccess.h> @@ -1235,7 +1236,7 @@ static int __init crash_notes_memory_init(void) } return 0; } -module_init(crash_notes_memory_init) +subsys_initcall(crash_notes_memory_init); /* @@ -1551,10 +1552,10 @@ void vmcoreinfo_append_str(const char *fmt, ...) * provide an empty default implementation here -- architecture * code may override this */ -void __attribute__ ((weak)) arch_crash_save_vmcoreinfo(void) +void __weak arch_crash_save_vmcoreinfo(void) {} -unsigned long __attribute__ ((weak)) paddr_vmcoreinfo_note(void) +unsigned long __weak paddr_vmcoreinfo_note(void) { return __pa((unsigned long)(char *)&vmcoreinfo_note); } @@ -1629,7 +1630,7 @@ static int __init crash_save_vmcoreinfo_init(void) return 0; } -module_init(crash_save_vmcoreinfo_init) +subsys_initcall(crash_save_vmcoreinfo_init); /* * Move into place and start executing a preloaded standalone diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index e660964086e2..2495a9b14ac8 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -18,6 +18,7 @@ #include <linux/stat.h> #include <linux/sched.h> #include <linux/capability.h> +#include <linux/compiler.h> #include <linux/rcupdate.h> /* rcu_expedited */ @@ -162,8 +163,8 @@ KERNEL_ATTR_RW(rcu_expedited); /* * Make /sys/kernel/notes give the raw contents of our kernel .notes section. */ -extern const void __start_notes __attribute__((weak)); -extern const void __stop_notes __attribute__((weak)); +extern const void __start_notes __weak; +extern const void __stop_notes __weak; #define notes_size (&__stop_notes - &__start_notes) static ssize_t notes_read(struct file *filp, struct kobject *kobj, diff --git a/kernel/kthread.c b/kernel/kthread.c index b5ae3ee860a9..9a130ec06f7a 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -217,7 +217,7 @@ int tsk_fork_get_node(struct task_struct *tsk) if (tsk == kthreadd_task) return tsk->pref_node_fork; #endif - return numa_node_id(); + return NUMA_NO_NODE; } static void create_kthread(struct kthread_create_info *create) @@ -369,7 +369,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), { struct task_struct *p; - p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt, + p = kthread_create_on_node(threadfn, data, cpu_to_mem(cpu), namefmt, cpu); if (IS_ERR(p)) return p; diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 306a76b51e0f..b8bdcd4785b7 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -1,5 +1,5 @@ -obj-y += mutex.o semaphore.o rwsem.o lglock.o mcs_spinlock.o +obj-y += mutex.o semaphore.o rwsem.o mcs_spinlock.o ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_lockdep.o = -pg @@ -14,6 +14,7 @@ ifeq ($(CONFIG_PROC_FS),y) obj-$(CONFIG_LOCKDEP) += lockdep_proc.o endif obj-$(CONFIG_SMP) += spinlock.o +obj-$(CONFIG_SMP) += lglock.o obj-$(CONFIG_PROVE_LOCKING) += spinlock.o obj-$(CONFIG_RT_MUTEXES) += rtmutex.o obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c index e1191c996c59..5cf6731b98e9 100644 --- a/kernel/locking/mutex-debug.c +++ b/kernel/locking/mutex-debug.c @@ -71,18 +71,17 @@ void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, void debug_mutex_unlock(struct mutex *lock) { - if (unlikely(!debug_locks)) - return; + if (likely(debug_locks)) { + DEBUG_LOCKS_WARN_ON(lock->magic != lock); - DEBUG_LOCKS_WARN_ON(lock->magic != lock); + if (!lock->owner) + DEBUG_LOCKS_WARN_ON(!lock->owner); + else + DEBUG_LOCKS_WARN_ON(lock->owner != current); - if (!lock->owner) - DEBUG_LOCKS_WARN_ON(!lock->owner); - else - DEBUG_LOCKS_WARN_ON(lock->owner != current); - - DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); - mutex_clear_owner(lock); + DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); + mutex_clear_owner(lock); + } /* * __mutex_slowpath_needs_to_unlock() is explicitly 0 for debug diff --git a/kernel/module.c b/kernel/module.c index 8dc7f5e80dd8..11869408f79b 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -640,7 +640,7 @@ static int module_unload_init(struct module *mod) INIT_LIST_HEAD(&mod->target_list); /* Hold reference count during initialization. */ - __this_cpu_write(mod->refptr->incs, 1); + raw_cpu_write(mod->refptr->incs, 1); return 0; } @@ -1013,6 +1013,8 @@ static size_t module_flags_taint(struct module *mod, char *buf) buf[l++] = 'F'; if (mod->taints & (1 << TAINT_CRAP)) buf[l++] = 'C'; + if (mod->taints & (1 << TAINT_UNSIGNED_MODULE)) + buf[l++] = 'E'; /* * TAINT_FORCED_RMMOD: could be added. * TAINT_CPU_OUT_OF_SPEC, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't @@ -3218,7 +3220,7 @@ static int load_module(struct load_info *info, const char __user *uargs, pr_notice_once("%s: module verification failed: signature " "and/or required key missing - tainting " "kernel\n", mod->name); - add_taint_module(mod, TAINT_FORCED_MODULE, LOCKDEP_STILL_OK); + add_taint_module(mod, TAINT_UNSIGNED_MODULE, LOCKDEP_STILL_OK); } #endif @@ -3813,12 +3815,12 @@ void print_modules(void) list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; - printk(" %s%s", mod->name, module_flags(mod, buf)); + pr_cont(" %s%s", mod->name, module_flags(mod, buf)); } preempt_enable(); if (last_unloaded_module[0]) - printk(" [last unloaded: %s]", last_unloaded_module); - printk("\n"); + pr_cont(" [last unloaded: %s]", last_unloaded_module); + pr_cont("\n"); } #ifdef CONFIG_MODVERSIONS diff --git a/kernel/panic.c b/kernel/panic.c index cca8a913ae7c..d02fa9fef46a 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -100,7 +100,7 @@ void panic(const char *fmt, ...) va_start(args, fmt); vsnprintf(buf, sizeof(buf), fmt, args); va_end(args); - printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf); + pr_emerg("Kernel panic - not syncing: %s\n", buf); #ifdef CONFIG_DEBUG_BUGVERBOSE /* * Avoid nested stack-dumping if a panic occurs during oops processing @@ -141,7 +141,7 @@ void panic(const char *fmt, ...) * Delay timeout seconds before rebooting the machine. * We can't use the "normal" timers since we just panicked. */ - printk(KERN_EMERG "Rebooting in %d seconds..", panic_timeout); + pr_emerg("Rebooting in %d seconds..", panic_timeout); for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) { touch_nmi_watchdog(); @@ -165,7 +165,7 @@ void panic(const char *fmt, ...) extern int stop_a_enabled; /* Make sure the user can actually press Stop-A (L1-A) */ stop_a_enabled = 1; - printk(KERN_EMERG "Press Stop-A (L1-A) to return to the boot prom\n"); + pr_emerg("Press Stop-A (L1-A) to return to the boot prom\n"); } #endif #if defined(CONFIG_S390) @@ -176,6 +176,7 @@ void panic(const char *fmt, ...) disabled_wait(caller); } #endif + pr_emerg("---[ end Kernel panic - not syncing: %s\n", buf); local_irq_enable(); for (i = 0; ; i += PANIC_TIMER_STEP) { touch_softlockup_watchdog(); @@ -210,6 +211,7 @@ static const struct tnt tnts[] = { { TAINT_CRAP, 'C', ' ' }, { TAINT_FIRMWARE_WORKAROUND, 'I', ' ' }, { TAINT_OOT_MODULE, 'O', ' ' }, + { TAINT_UNSIGNED_MODULE, 'E', ' ' }, }; /** @@ -228,6 +230,7 @@ static const struct tnt tnts[] = { * 'C' - modules from drivers/staging are loaded. * 'I' - Working around severe firmware bug. * 'O' - Out-of-tree module has been loaded. + * 'E' - Unsigned module has been loaded. * * The string is overwritten by the next call to print_tainted(). */ @@ -274,8 +277,7 @@ unsigned long get_taint(void) void add_taint(unsigned flag, enum lockdep_ok lockdep_ok) { if (lockdep_ok == LOCKDEP_NOW_UNRELIABLE && __debug_locks_off()) - printk(KERN_WARNING - "Disabling lock debugging due to kernel taint\n"); + pr_warn("Disabling lock debugging due to kernel taint\n"); set_bit(flag, &tainted_mask); } @@ -380,8 +382,7 @@ late_initcall(init_oops_id); void print_oops_end_marker(void) { init_oops_id(); - printk(KERN_WARNING "---[ end trace %016llx ]---\n", - (unsigned long long)oops_id); + pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id); } /* diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 06c62de9c711..db95d8eb761b 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -318,7 +318,9 @@ static void *pidns_get(struct task_struct *task) struct pid_namespace *ns; rcu_read_lock(); - ns = get_pid_ns(task_active_pid_ns(task)); + ns = task_active_pid_ns(task); + if (ns) + get_pid_ns(ns); rcu_read_unlock(); return ns; diff --git a/kernel/power/power.h b/kernel/power/power.h index 1ca753106557..15f37ea08719 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -2,6 +2,7 @@ #include <linux/suspend_ioctls.h> #include <linux/utsname.h> #include <linux/freezer.h> +#include <linux/compiler.h> struct swsusp_info { struct new_utsname uts; @@ -11,7 +12,7 @@ struct swsusp_info { unsigned long image_pages; unsigned long pages; unsigned long size; -} __attribute__((aligned(PAGE_SIZE))); +} __aligned(PAGE_SIZE); #ifdef CONFIG_HIBERNATION /* kernel/power/snapshot.c */ diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 149e745eaa52..18fb7a2fb14b 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -27,6 +27,7 @@ #include <linux/highmem.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/compiler.h> #include <asm/uaccess.h> #include <asm/mmu_context.h> @@ -155,7 +156,7 @@ static inline void free_image_page(void *addr, int clear_nosave_free) struct linked_page { struct linked_page *next; char data[LINKED_PAGE_DATA_SIZE]; -} __attribute__((packed)); +} __packed; static inline void free_list_of_pages(struct linked_page *list, int clear_page_nosave) diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 90b3d9366d1a..c3ad9cafe930 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -26,6 +26,7 @@ #include <linux/syscore_ops.h> #include <linux/ftrace.h> #include <trace/events/power.h> +#include <linux/compiler.h> #include "power.h" @@ -156,13 +157,13 @@ static int suspend_prepare(suspend_state_t state) } /* default implementation */ -void __attribute__ ((weak)) arch_suspend_disable_irqs(void) +void __weak arch_suspend_disable_irqs(void) { local_irq_disable(); } /* default implementation */ -void __attribute__ ((weak)) arch_suspend_enable_irqs(void) +void __weak arch_suspend_enable_irqs(void) { local_irq_enable(); } diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 7c33ed200410..8c9a4819f798 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -101,7 +101,7 @@ struct swsusp_header { unsigned int flags; /* Flags to pass to the "boot" kernel */ char orig_sig[10]; char sig[10]; -} __attribute__((packed)); +} __packed; static struct swsusp_header *swsusp_header; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 4dae9cbe9259..a45b50962295 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -319,7 +319,7 @@ static void log_store(int facility, int level, else free = log_first_idx - log_next_idx; - if (free > size + sizeof(struct printk_log)) + if (free >= size + sizeof(struct printk_log)) break; /* drop old messages until we have enough contiuous space */ @@ -327,7 +327,7 @@ static void log_store(int facility, int level, log_first_seq++; } - if (log_next_idx + size + sizeof(struct printk_log) >= log_buf_len) { + if (log_next_idx + size + sizeof(struct printk_log) > log_buf_len) { /* * This message + an additional empty header does not fit * at the end of the buffer. Add an empty header with len == 0 @@ -351,7 +351,7 @@ static void log_store(int facility, int level, else msg->ts_nsec = local_clock(); memset(log_dict(msg) + dict_len, 0, pad_len); - msg->len = sizeof(struct printk_log) + text_len + dict_len + pad_len; + msg->len = size; /* insert message */ log_next_idx += msg->len; @@ -1560,9 +1560,12 @@ asmlinkage int vprintk_emit(int facility, int level, level = kern_level - '0'; case 'd': /* KERN_DEFAULT */ lflags |= LOG_PREFIX; - case 'c': /* KERN_CONT */ - break; } + /* + * No need to check length here because vscnprintf + * put '\0' at the end of the string. Only valid and + * newly printed level is detected. + */ text_len -= end_of_header - text; text = (char *)end_of_header; } @@ -1880,6 +1883,7 @@ void suspend_console(void) console_lock(); console_suspended = 1; up(&console_sem); + mutex_release(&console_lock_dep_map, 1, _RET_IP_); } void resume_console(void) @@ -1887,6 +1891,7 @@ void resume_console(void) if (!console_suspend_enabled) return; down(&console_sem); + mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_); console_suspended = 0; console_unlock(); } diff --git a/kernel/profile.c b/kernel/profile.c index ebdd9c1a86b4..cb980f0c731b 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -591,18 +591,28 @@ out_cleanup: int __ref create_proc_profile(void) /* false positive from hotcpu_notifier */ { struct proc_dir_entry *entry; + int err = 0; if (!prof_on) return 0; - if (create_hash_tables()) - return -ENOMEM; + + cpu_notifier_register_begin(); + + if (create_hash_tables()) { + err = -ENOMEM; + goto out; + } + entry = proc_create("profile", S_IWUSR | S_IRUGO, NULL, &proc_profile_operations); if (!entry) - return 0; + goto out; proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t)); - hotcpu_notifier(profile_cpu_callback, 0); - return 0; + __hotcpu_notifier(profile_cpu_callback, 0); + +out: + cpu_notifier_register_done(); + return err; } -module_init(create_proc_profile); +subsys_initcall(create_proc_profile); #endif /* CONFIG_PROC_FS */ diff --git a/kernel/relay.c b/kernel/relay.c index 5001c9887db1..5a56d3c8dc03 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -227,7 +227,7 @@ static void relay_destroy_buf(struct rchan_buf *buf) * relay_remove_buf - remove a channel buffer * @kref: target kernel reference that contains the relay buffer * - * Removes the file from the fileystem, which also frees the + * Removes the file from the filesystem, which also frees the * rchan_buf_struct and the channel buffer. Should only be called from * kref_put(). */ @@ -1195,8 +1195,6 @@ static void relay_pipe_buf_release(struct pipe_inode_info *pipe, static const struct pipe_buf_operations relay_pipe_buf_ops = { .can_merge = 0, - .map = generic_pipe_buf_map, - .unmap = generic_pipe_buf_unmap, .confirm = generic_pipe_buf_confirm, .release = relay_pipe_buf_release, .steal = generic_pipe_buf_steal, @@ -1253,7 +1251,7 @@ static ssize_t subbuf_splice_actor(struct file *in, subbuf_pages = rbuf->chan->alloc_size >> PAGE_SHIFT; pidx = (read_start / PAGE_SIZE) % subbuf_pages; poff = read_start & ~PAGE_MASK; - nr_pages = min_t(unsigned int, subbuf_pages, pipe->buffers); + nr_pages = min_t(unsigned int, subbuf_pages, spd.nr_pages_max); for (total_len = 0; spd.nr_pages < nr_pages; spd.nr_pages++) { unsigned int this_len, this_end, private; diff --git a/kernel/res_counter.c b/kernel/res_counter.c index 4aa8a305aede..51dbac6a3633 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -22,8 +22,18 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent) counter->parent = parent; } -int res_counter_charge_locked(struct res_counter *counter, unsigned long val, - bool force) +static u64 res_counter_uncharge_locked(struct res_counter *counter, + unsigned long val) +{ + if (WARN_ON(counter->usage < val)) + val = counter->usage; + + counter->usage -= val; + return counter->usage; +} + +static int res_counter_charge_locked(struct res_counter *counter, + unsigned long val, bool force) { int ret = 0; @@ -86,15 +96,6 @@ int res_counter_charge_nofail(struct res_counter *counter, unsigned long val, return __res_counter_charge(counter, val, limit_fail_at, true); } -u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) -{ - if (WARN_ON(counter->usage < val)) - val = counter->usage; - - counter->usage -= val; - return counter->usage; -} - u64 res_counter_uncharge_until(struct res_counter *counter, struct res_counter *top, unsigned long val) diff --git a/kernel/resource.c b/kernel/resource.c index 673061c06da1..8957d686e29b 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -511,7 +511,7 @@ static int find_resource(struct resource *root, struct resource *new, * @newsize: new size of the resource descriptor * @constraint: the size and alignment constraints to be met. */ -int reallocate_resource(struct resource *root, struct resource *old, +static int reallocate_resource(struct resource *root, struct resource *old, resource_size_t newsize, struct resource_constraint *constraint) { diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index b30a2924ef14..3ef6451e972e 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -60,13 +60,14 @@ #include <linux/sched.h> #include <linux/static_key.h> #include <linux/workqueue.h> +#include <linux/compiler.h> /* * Scheduler clock - returns current time in nanosec units. * This is default implementation. * Architectures and sub-architectures can override this. */ -unsigned long long __attribute__((weak)) sched_clock(void) +unsigned long long __weak sched_clock(void) { return (unsigned long long)(jiffies - INITIAL_JIFFIES) * (NSEC_PER_SEC / HZ); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9cae286824bb..13584f1cccfc 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -73,6 +73,7 @@ #include <linux/init_task.h> #include <linux/binfmts.h> #include <linux/context_tracking.h> +#include <linux/compiler.h> #include <asm/switch_to.h> #include <asm/tlb.h> @@ -2591,8 +2592,14 @@ pick_next_task(struct rq *rq, struct task_struct *prev) if (likely(prev->sched_class == class && rq->nr_running == rq->cfs.h_nr_running)) { p = fair_sched_class.pick_next_task(rq, prev); - if (likely(p && p != RETRY_TASK)) - return p; + if (unlikely(p == RETRY_TASK)) + goto again; + + /* assumes fair_sched_class->next == idle_sched_class */ + if (unlikely(!p)) + p = idle_sched_class.pick_next_task(rq, prev); + + return p; } again: @@ -2845,52 +2852,6 @@ int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, } EXPORT_SYMBOL(default_wake_function); -static long __sched -sleep_on_common(wait_queue_head_t *q, int state, long timeout) -{ - unsigned long flags; - wait_queue_t wait; - - init_waitqueue_entry(&wait, current); - - __set_current_state(state); - - spin_lock_irqsave(&q->lock, flags); - __add_wait_queue(q, &wait); - spin_unlock(&q->lock); - timeout = schedule_timeout(timeout); - spin_lock_irq(&q->lock); - __remove_wait_queue(q, &wait); - spin_unlock_irqrestore(&q->lock, flags); - - return timeout; -} - -void __sched interruptible_sleep_on(wait_queue_head_t *q) -{ - sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); -} -EXPORT_SYMBOL(interruptible_sleep_on); - -long __sched -interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout) -{ - return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout); -} -EXPORT_SYMBOL(interruptible_sleep_on_timeout); - -void __sched sleep_on(wait_queue_head_t *q) -{ - sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); -} -EXPORT_SYMBOL(sleep_on); - -long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout) -{ - return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout); -} -EXPORT_SYMBOL(sleep_on_timeout); - #ifdef CONFIG_RT_MUTEXES /* @@ -3169,6 +3130,7 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr) dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime); dl_se->dl_throttled = 0; dl_se->dl_new = 1; + dl_se->dl_yielded = 0; } static void __setscheduler_params(struct task_struct *p, @@ -3684,6 +3646,7 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) * sys_sched_setattr - same as above, but with extended sched_attr * @pid: the pid in question. * @uattr: structure containing the extended parameters. + * @flags: for future extension. */ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, unsigned int, flags) @@ -3828,6 +3791,7 @@ err_size: * @pid: the pid in question. * @uattr: structure containing the extended parameters. * @size: sizeof(attr) for fwd/bwd comp. + * @flags: for future extension. */ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, unsigned int, size, unsigned int, flags) @@ -6062,6 +6026,8 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu) , .last_balance = jiffies, .balance_interval = sd_weight, + .max_newidle_lb_cost = 0, + .next_decay_max_lb_cost = jiffies, }; SD_INIT_NAME(sd, NUMA); sd->private = &tl->data; @@ -6498,7 +6464,7 @@ static cpumask_var_t fallback_doms; * cpu core maps. It is supposed to return 1 if the topology changed * or 0 if it stayed the same. */ -int __attribute__((weak)) arch_update_cpu_topology(void) +int __weak arch_update_cpu_topology(void) { return 0; } @@ -7230,7 +7196,7 @@ void sched_move_task(struct task_struct *tsk) if (unlikely(running)) tsk->sched_class->put_prev_task(rq, tsk); - tg = container_of(task_css_check(tsk, cpu_cgroup_subsys_id, + tg = container_of(task_css_check(tsk, cpu_cgrp_id, lockdep_is_held(&tsk->sighand->siglock)), struct task_group, css); tg = autogroup_task_group(tsk, tg); @@ -7657,7 +7623,7 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, { struct task_struct *task; - cgroup_taskset_for_each(task, css, tset) { + cgroup_taskset_for_each(task, tset) { #ifdef CONFIG_RT_GROUP_SCHED if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; @@ -7675,7 +7641,7 @@ static void cpu_cgroup_attach(struct cgroup_subsys_state *css, { struct task_struct *task; - cgroup_taskset_for_each(task, css, tset) + cgroup_taskset_for_each(task, tset) sched_move_task(task); } @@ -8014,8 +7980,7 @@ static struct cftype cpu_files[] = { { } /* terminate */ }; -struct cgroup_subsys cpu_cgroup_subsys = { - .name = "cpu", +struct cgroup_subsys cpu_cgrp_subsys = { .css_alloc = cpu_cgroup_css_alloc, .css_free = cpu_cgroup_css_free, .css_online = cpu_cgroup_css_online, @@ -8023,7 +7988,6 @@ struct cgroup_subsys cpu_cgroup_subsys = { .can_attach = cpu_cgroup_can_attach, .attach = cpu_cgroup_attach, .exit = cpu_cgroup_exit, - .subsys_id = cpu_cgroup_subsys_id, .base_cftypes = cpu_files, .early_init = 1, }; diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 622e0818f905..c143ee380e3a 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -41,7 +41,7 @@ static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css) /* return cpu accounting group to which this task belongs */ static inline struct cpuacct *task_ca(struct task_struct *tsk) { - return css_ca(task_css(tsk, cpuacct_subsys_id)); + return css_ca(task_css(tsk, cpuacct_cgrp_id)); } static inline struct cpuacct *parent_ca(struct cpuacct *ca) @@ -275,11 +275,9 @@ void cpuacct_account_field(struct task_struct *p, int index, u64 val) rcu_read_unlock(); } -struct cgroup_subsys cpuacct_subsys = { - .name = "cpuacct", +struct cgroup_subsys cpuacct_cgrp_subsys = { .css_alloc = cpuacct_css_alloc, .css_free = cpuacct_css_free, - .subsys_id = cpuacct_subsys_id, .base_cftypes = files, .early_init = 1, }; diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index 5b9bb42b2d47..ab001b5d5048 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -210,7 +210,5 @@ int cpudl_init(struct cpudl *cp) */ void cpudl_cleanup(struct cpudl *cp) { - /* - * nothing to do for the moment - */ + free_cpumask_var(cp->free_cpus); } diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index 8b836b376d91..3031bac8aa3e 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -70,8 +70,7 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, int idx = 0; int task_pri = convert_prio(p->prio); - if (task_pri >= MAX_RT_PRIO) - return 0; + BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES); for (idx = 0; idx < task_pri; idx++) { struct cpupri_vec *vec = &cp->pri_to_cpu[idx]; diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index a95097cb4591..72fdf06ef865 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -332,50 +332,50 @@ out: * softirq as those do not count in task exec_runtime any more. */ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, - struct rq *rq) + struct rq *rq, int ticks) { - cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + cputime_t scaled = cputime_to_scaled(cputime_one_jiffy); + u64 cputime = (__force u64) cputime_one_jiffy; u64 *cpustat = kcpustat_this_cpu->cpustat; if (steal_account_process_tick()) return; + cputime *= ticks; + scaled *= ticks; + if (irqtime_account_hi_update()) { - cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy; + cpustat[CPUTIME_IRQ] += cputime; } else if (irqtime_account_si_update()) { - cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy; + cpustat[CPUTIME_SOFTIRQ] += cputime; } else if (this_cpu_ksoftirqd() == p) { /* * ksoftirqd time do not get accounted in cpu_softirq_time. * So, we have to handle it separately here. * Also, p->stime needs to be updated for ksoftirqd. */ - __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, - CPUTIME_SOFTIRQ); + __account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ); } else if (user_tick) { - account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); + account_user_time(p, cputime, scaled); } else if (p == rq->idle) { - account_idle_time(cputime_one_jiffy); + account_idle_time(cputime); } else if (p->flags & PF_VCPU) { /* System time or guest time */ - account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled); + account_guest_time(p, cputime, scaled); } else { - __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, - CPUTIME_SYSTEM); + __account_system_time(p, cputime, scaled, CPUTIME_SYSTEM); } } static void irqtime_account_idle_ticks(int ticks) { - int i; struct rq *rq = this_rq(); - for (i = 0; i < ticks; i++) - irqtime_account_process_tick(current, 0, rq); + irqtime_account_process_tick(current, 0, rq, ticks); } #else /* CONFIG_IRQ_TIME_ACCOUNTING */ static inline void irqtime_account_idle_ticks(int ticks) {} static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick, - struct rq *rq) {} + struct rq *rq, int nr_ticks) {} #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ /* @@ -464,7 +464,7 @@ void account_process_tick(struct task_struct *p, int user_tick) return; if (sched_clock_irqtime) { - irqtime_account_process_tick(p, user_tick, rq); + irqtime_account_process_tick(p, user_tick, rq, 1); return; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index b08095786cb8..800e99b99075 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -528,6 +528,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) sched_clock_tick(); update_rq_clock(rq); dl_se->dl_throttled = 0; + dl_se->dl_yielded = 0; if (p->on_rq) { enqueue_task_dl(rq, p, ENQUEUE_REPLENISH); if (task_has_dl_policy(rq->curr)) @@ -893,10 +894,10 @@ static void yield_task_dl(struct rq *rq) * We make the task go to sleep until its current deadline by * forcing its runtime to zero. This way, update_curr_dl() stops * it and the bandwidth timer will wake it up and will give it - * new scheduling parameters (thanks to dl_new=1). + * new scheduling parameters (thanks to dl_yielded=1). */ if (p->dl.runtime > 0) { - rq->curr->dl.dl_new = 1; + rq->curr->dl.dl_yielded = 1; p->dl.runtime = 0; } update_curr_dl(rq); diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index f3344c31632a..695f9773bb60 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -111,8 +111,7 @@ static char *task_group_path(struct task_group *tg) if (autogroup_path(tg, group_path, PATH_MAX)) return group_path; - cgroup_path(tg->css.cgroup, group_path, PATH_MAX); - return group_path; + return cgroup_path(tg->css.cgroup, group_path, PATH_MAX); } #endif diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 43232b8bacde..5d859ec975c2 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6658,6 +6658,7 @@ static int idle_balance(struct rq *this_rq) int this_cpu = this_rq->cpu; idle_enter_fair(this_rq); + /* * We must set idle_stamp _before_ calling idle_balance(), such that we * measure the duration of idle_balance() as idle time. @@ -6710,14 +6711,16 @@ static int idle_balance(struct rq *this_rq) raw_spin_lock(&this_rq->lock); + if (curr_cost > this_rq->max_idle_balance_cost) + this_rq->max_idle_balance_cost = curr_cost; + /* - * While browsing the domains, we released the rq lock. - * A task could have be enqueued in the meantime + * While browsing the domains, we released the rq lock, a task could + * have been enqueued in the meantime. Since we're not going idle, + * pretend we pulled a task. */ - if (this_rq->cfs.h_nr_running && !pulled_task) { + if (this_rq->cfs.h_nr_running && !pulled_task) pulled_task = 1; - goto out; - } if (pulled_task || time_after(jiffies, this_rq->next_balance)) { /* @@ -6727,9 +6730,6 @@ static int idle_balance(struct rq *this_rq) this_rq->next_balance = next_balance; } - if (curr_cost > this_rq->max_idle_balance_cost) - this_rq->max_idle_balance_cost = curr_cost; - out: /* Is there a task of a high priority class? */ if (this_rq->nr_running != this_rq->cfs.h_nr_running) diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index b7976a127178..8f4390a079c7 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -63,6 +63,136 @@ void __weak arch_cpu_idle(void) local_irq_enable(); } +/** + * cpuidle_idle_call - the main idle function + * + * NOTE: no locks or semaphores should be used here + * return non-zero on failure + */ +static int cpuidle_idle_call(void) +{ + struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); + int next_state, entered_state, ret; + bool broadcast; + + /* + * Check if the idle task must be rescheduled. If it is the + * case, exit the function after re-enabling the local irq and + * set again the polling flag + */ + if (current_clr_polling_and_test()) { + local_irq_enable(); + __current_set_polling(); + return 0; + } + + /* + * During the idle period, stop measuring the disabled irqs + * critical sections latencies + */ + stop_critical_timings(); + + /* + * Tell the RCU framework we are entering an idle section, + * so no more rcu read side critical sections and one more + * step to the grace period + */ + rcu_idle_enter(); + + /* + * Check if the cpuidle framework is ready, otherwise fallback + * to the default arch specific idle method + */ + ret = cpuidle_enabled(drv, dev); + + if (!ret) { + /* + * Ask the governor to choose an idle state it thinks + * it is convenient to go to. There is *always* a + * convenient idle state + */ + next_state = cpuidle_select(drv, dev); + + /* + * The idle task must be scheduled, it is pointless to + * go to idle, just update no idle residency and get + * out of this function + */ + if (current_clr_polling_and_test()) { + dev->last_residency = 0; + entered_state = next_state; + local_irq_enable(); + } else { + broadcast = !!(drv->states[next_state].flags & + CPUIDLE_FLAG_TIMER_STOP); + + if (broadcast) + /* + * Tell the time framework to switch + * to a broadcast timer because our + * local timer will be shutdown. If a + * local timer is used from another + * cpu as a broadcast timer, this call + * may fail if it is not available + */ + ret = clockevents_notify( + CLOCK_EVT_NOTIFY_BROADCAST_ENTER, + &dev->cpu); + + if (!ret) { + trace_cpu_idle_rcuidle(next_state, dev->cpu); + + /* + * Enter the idle state previously + * returned by the governor + * decision. This function will block + * until an interrupt occurs and will + * take care of re-enabling the local + * interrupts + */ + entered_state = cpuidle_enter(drv, dev, + next_state); + + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, + dev->cpu); + + if (broadcast) + clockevents_notify( + CLOCK_EVT_NOTIFY_BROADCAST_EXIT, + &dev->cpu); + + /* + * Give the governor an opportunity to reflect on the + * outcome + */ + cpuidle_reflect(dev, entered_state); + } + } + } + + /* + * We can't use the cpuidle framework, let's use the default + * idle routine + */ + if (ret) + arch_cpu_idle(); + + __current_set_polling(); + + /* + * It is up to the idle functions to enable back the local + * interrupt + */ + if (WARN_ON_ONCE(irqs_disabled())) + local_irq_enable(); + + rcu_idle_exit(); + start_critical_timings(); + + return 0; +} + /* * Generic idle loop implementation */ @@ -90,23 +220,11 @@ static void cpu_idle_loop(void) * know that the IPI is going to arrive right * away */ - if (cpu_idle_force_poll || tick_check_broadcast_expired()) { + if (cpu_idle_force_poll || tick_check_broadcast_expired()) cpu_idle_poll(); - } else { - if (!current_clr_polling_and_test()) { - stop_critical_timings(); - rcu_idle_enter(); - if (cpuidle_idle_call()) - arch_cpu_idle(); - if (WARN_ON_ONCE(irqs_disabled())) - local_irq_enable(); - rcu_idle_exit(); - start_critical_timings(); - } else { - local_irq_enable(); - } - __current_set_polling(); - } + else + cpuidle_idle_call(); + arch_cpu_idle_exit(); } diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index da98af347e8b..a476bea17fbc 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -142,4 +142,4 @@ static int __init proc_schedstat_init(void) proc_create("schedstat", 0, NULL, &proc_schedstat_operations); return 0; } -module_init(proc_schedstat_init); +subsys_initcall(proc_schedstat_init); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index b7a10048a32c..b35c21503a36 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -55,60 +55,32 @@ struct seccomp_filter { atomic_t usage; struct seccomp_filter *prev; unsigned short len; /* Instruction count */ - struct sock_filter insns[]; + struct sock_filter_int insnsi[]; }; /* Limit any path through the tree to 256KB worth of instructions. */ #define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter)) -/** - * get_u32 - returns a u32 offset into data - * @data: a unsigned 64 bit value - * @index: 0 or 1 to return the first or second 32-bits - * - * This inline exists to hide the length of unsigned long. If a 32-bit - * unsigned long is passed in, it will be extended and the top 32-bits will be - * 0. If it is a 64-bit unsigned long, then whatever data is resident will be - * properly returned. - * +/* * Endianness is explicitly ignored and left for BPF program authors to manage * as per the specific architecture. */ -static inline u32 get_u32(u64 data, int index) -{ - return ((u32 *)&data)[index]; -} - -/* Helper for bpf_load below. */ -#define BPF_DATA(_name) offsetof(struct seccomp_data, _name) -/** - * bpf_load: checks and returns a pointer to the requested offset - * @off: offset into struct seccomp_data to load from - * - * Returns the requested 32-bits of data. - * seccomp_check_filter() should assure that @off is 32-bit aligned - * and not out of bounds. Failure to do so is a BUG. - */ -u32 seccomp_bpf_load(int off) +static void populate_seccomp_data(struct seccomp_data *sd) { - struct pt_regs *regs = task_pt_regs(current); - if (off == BPF_DATA(nr)) - return syscall_get_nr(current, regs); - if (off == BPF_DATA(arch)) - return syscall_get_arch(current, regs); - if (off >= BPF_DATA(args[0]) && off < BPF_DATA(args[6])) { - unsigned long value; - int arg = (off - BPF_DATA(args[0])) / sizeof(u64); - int index = !!(off % sizeof(u64)); - syscall_get_arguments(current, regs, arg, 1, &value); - return get_u32(value, index); - } - if (off == BPF_DATA(instruction_pointer)) - return get_u32(KSTK_EIP(current), 0); - if (off == BPF_DATA(instruction_pointer) + sizeof(u32)) - return get_u32(KSTK_EIP(current), 1); - /* seccomp_check_filter should make this impossible. */ - BUG(); + struct task_struct *task = current; + struct pt_regs *regs = task_pt_regs(task); + unsigned long args[6]; + + sd->nr = syscall_get_nr(task, regs); + sd->arch = syscall_get_arch(); + syscall_get_arguments(task, regs, 0, 6, args); + sd->args[0] = args[0]; + sd->args[1] = args[1]; + sd->args[2] = args[2]; + sd->args[3] = args[3]; + sd->args[4] = args[4]; + sd->args[5] = args[5]; + sd->instruction_pointer = KSTK_EIP(task); } /** @@ -133,17 +105,17 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) switch (code) { case BPF_S_LD_W_ABS: - ftest->code = BPF_S_ANC_SECCOMP_LD_W; + ftest->code = BPF_LDX | BPF_W | BPF_ABS; /* 32-bit aligned and not out of bounds. */ if (k >= sizeof(struct seccomp_data) || k & 3) return -EINVAL; continue; case BPF_S_LD_W_LEN: - ftest->code = BPF_S_LD_IMM; + ftest->code = BPF_LD | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; case BPF_S_LDX_W_LEN: - ftest->code = BPF_S_LDX_IMM; + ftest->code = BPF_LDX | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; /* Explicitly include allowed calls. */ @@ -185,6 +157,7 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) case BPF_S_JMP_JGT_X: case BPF_S_JMP_JSET_K: case BPF_S_JMP_JSET_X: + sk_decode_filter(ftest, ftest); continue; default: return -EINVAL; @@ -202,18 +175,21 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) static u32 seccomp_run_filters(int syscall) { struct seccomp_filter *f; + struct seccomp_data sd; u32 ret = SECCOMP_RET_ALLOW; /* Ensure unexpected behavior doesn't result in failing open. */ if (WARN_ON(current->seccomp.filter == NULL)) return SECCOMP_RET_KILL; + populate_seccomp_data(&sd); + /* * All filters in the list are evaluated and the lowest BPF return * value always takes priority (ignoring the DATA). */ for (f = current->seccomp.filter; f; f = f->prev) { - u32 cur_ret = sk_run_filter(NULL, f->insns); + u32 cur_ret = sk_run_filter_int_seccomp(&sd, f->insnsi); if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION)) ret = cur_ret; } @@ -231,6 +207,8 @@ static long seccomp_attach_filter(struct sock_fprog *fprog) struct seccomp_filter *filter; unsigned long fp_size = fprog->len * sizeof(struct sock_filter); unsigned long total_insns = fprog->len; + struct sock_filter *fp; + int new_len; long ret; if (fprog->len == 0 || fprog->len > BPF_MAXINSNS) @@ -252,28 +230,45 @@ static long seccomp_attach_filter(struct sock_fprog *fprog) CAP_SYS_ADMIN) != 0) return -EACCES; - /* Allocate a new seccomp_filter */ - filter = kzalloc(sizeof(struct seccomp_filter) + fp_size, - GFP_KERNEL|__GFP_NOWARN); - if (!filter) + fp = kzalloc(fp_size, GFP_KERNEL|__GFP_NOWARN); + if (!fp) return -ENOMEM; - atomic_set(&filter->usage, 1); - filter->len = fprog->len; /* Copy the instructions from fprog. */ ret = -EFAULT; - if (copy_from_user(filter->insns, fprog->filter, fp_size)) - goto fail; + if (copy_from_user(fp, fprog->filter, fp_size)) + goto free_prog; /* Check and rewrite the fprog via the skb checker */ - ret = sk_chk_filter(filter->insns, filter->len); + ret = sk_chk_filter(fp, fprog->len); if (ret) - goto fail; + goto free_prog; /* Check and rewrite the fprog for seccomp use */ - ret = seccomp_check_filter(filter->insns, filter->len); + ret = seccomp_check_filter(fp, fprog->len); + if (ret) + goto free_prog; + + /* Convert 'sock_filter' insns to 'sock_filter_int' insns */ + ret = sk_convert_filter(fp, fprog->len, NULL, &new_len); if (ret) - goto fail; + goto free_prog; + + /* Allocate a new seccomp_filter */ + ret = -ENOMEM; + filter = kzalloc(sizeof(struct seccomp_filter) + + sizeof(struct sock_filter_int) * new_len, + GFP_KERNEL|__GFP_NOWARN); + if (!filter) + goto free_prog; + + ret = sk_convert_filter(fp, fprog->len, filter->insnsi, &new_len); + if (ret) + goto free_filter; + kfree(fp); + + atomic_set(&filter->usage, 1); + filter->len = new_len; /* * If there is an existing filter, make it the prev and don't drop its @@ -282,8 +277,11 @@ static long seccomp_attach_filter(struct sock_fprog *fprog) filter->prev = current->seccomp.filter; current->seccomp.filter = filter; return 0; -fail: + +free_filter: kfree(filter); +free_prog: + kfree(fp); return ret; } @@ -293,7 +291,7 @@ fail: * * Returns 0 on success and non-zero otherwise. */ -long seccomp_attach_user_filter(char __user *user_filter) +static long seccomp_attach_user_filter(char __user *user_filter) { struct sock_fprog fprog; long ret = -EFAULT; @@ -351,7 +349,7 @@ static void seccomp_send_sigsys(int syscall, int reason) info.si_code = SYS_SECCOMP; info.si_call_addr = (void __user *)KSTK_EIP(current); info.si_errno = reason; - info.si_arch = syscall_get_arch(current, task_pt_regs(current)); + info.si_arch = syscall_get_arch(); info.si_syscall = syscall; force_sig_info(SIGSYS, &info, current); } diff --git a/kernel/signal.c b/kernel/signal.c index 52f881db1ca0..6ea13c09ae56 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -33,6 +33,8 @@ #include <linux/uprobes.h> #include <linux/compat.h> #include <linux/cn_proc.h> +#include <linux/compiler.h> + #define CREATE_TRACE_POINTS #include <trace/events/signal.h> @@ -2382,7 +2384,7 @@ relock: * @regs: user register state * @stepping: nonzero if debugger single-step or block-step in use * - * This function should be called when a signal has succesfully been + * This function should be called when a signal has successfully been * delivered. It updates the blocked signals accordingly (@ka->sa.sa_mask * is always blocked, and the signal itself is blocked unless %SA_NODEFER * is set in @ka->sa.sa_flags. Tracing is notified. @@ -3618,7 +3620,7 @@ SYSCALL_DEFINE3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask) } #endif -__attribute__((weak)) const char *arch_vma_name(struct vm_area_struct *vma) +__weak const char *arch_vma_name(struct vm_area_struct *vma) { return NULL; } diff --git a/kernel/sys.c b/kernel/sys.c index adaeab6f7a87..fba0f29401ea 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1996,6 +1996,21 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, if (arg2 || arg3 || arg4 || arg5) return -EINVAL; return current->no_new_privs ? 1 : 0; + case PR_GET_THP_DISABLE: + if (arg2 || arg3 || arg4 || arg5) + return -EINVAL; + error = !!(me->mm->def_flags & VM_NOHUGEPAGE); + break; + case PR_SET_THP_DISABLE: + if (arg3 || arg4 || arg5) + return -EINVAL; + down_write(&me->mm->mmap_sem); + if (arg2) + me->mm->def_flags |= VM_NOHUGEPAGE; + else + me->mm->def_flags &= ~VM_NOHUGEPAGE; + up_write(&me->mm->mmap_sem); + break; default: error = -EINVAL; break; diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 7078052284fd..bc8d1b74a6b9 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -146,11 +146,13 @@ cond_syscall(sys_io_destroy); cond_syscall(sys_io_submit); cond_syscall(sys_io_cancel); cond_syscall(sys_io_getevents); +cond_syscall(sys_sysfs); cond_syscall(sys_syslog); cond_syscall(sys_process_vm_readv); cond_syscall(sys_process_vm_writev); cond_syscall(compat_sys_process_vm_readv); cond_syscall(compat_sys_process_vm_writev); +cond_syscall(sys_uselib); /* arch-specific weak syscall entries */ cond_syscall(sys_pciconfig_read); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 09d2e2413605..74f5b580fe34 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -123,7 +123,7 @@ static int __maybe_unused neg_one = -1; static int zero; static int __maybe_unused one = 1; static int __maybe_unused two = 2; -static int __maybe_unused three = 3; +static int __maybe_unused four = 4; static unsigned long one_ul = 1; static int one_hundred = 100; #ifdef CONFIG_PRINTK @@ -141,6 +141,11 @@ static int min_percpu_pagelist_fract = 8; static int ngroups_max = NGROUPS_MAX; static const int cap_last_cap = CAP_LAST_CAP; +/*this is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs */ +#ifdef CONFIG_DETECT_HUNG_TASK +static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); +#endif + #ifdef CONFIG_INOTIFY_USER #include <linux/inotify.h> #endif @@ -985,6 +990,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_dohung_task_timeout_secs, + .extra2 = &hung_task_timeout_max, }, { .procname = "hung_task_warnings", @@ -1264,7 +1270,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = drop_caches_sysctl_handler, .extra1 = &one, - .extra2 = &three, + .extra2 = &four, }, #ifdef CONFIG_COMPACTION { diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 015661279b68..0a0608edeb26 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -276,7 +276,7 @@ static bool tick_check_preferred(struct clock_event_device *curdev, bool tick_check_replacement(struct clock_event_device *curdev, struct clock_event_device *newdev) { - if (tick_check_percpu(curdev, newdev, smp_processor_id())) + if (!tick_check_percpu(curdev, newdev, smp_processor_id())) return false; return tick_check_preferred(curdev, newdev); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 9f8af69c67ec..6558b7ac112d 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -84,6 +84,9 @@ static void tick_do_update_jiffies64(ktime_t now) /* Keep the tick_next_period variable up to date */ tick_next_period = ktime_add(last_jiffies_update, tick_period); + } else { + write_sequnlock(&jiffies_lock); + return; } write_sequnlock(&jiffies_lock); update_wall_time(); @@ -967,7 +970,7 @@ static void tick_nohz_switch_to_nohz(void) struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); ktime_t next; - if (!tick_nohz_active) + if (!tick_nohz_enabled) return; local_irq_disable(); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 5b40279ecd71..f7df8ea21707 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -22,6 +22,7 @@ #include <linux/tick.h> #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> +#include <linux/compiler.h> #include "tick-internal.h" #include "ntp_internal.h" @@ -760,7 +761,7 @@ u64 timekeeping_max_deferment(void) * * XXX - Do be sure to remove it once all arches implement it. */ -void __attribute__((weak)) read_persistent_clock(struct timespec *ts) +void __weak read_persistent_clock(struct timespec *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; @@ -775,7 +776,7 @@ void __attribute__((weak)) read_persistent_clock(struct timespec *ts) * * XXX - Do be sure to remove it once all arches implement it. */ -void __attribute__((weak)) read_boot_clock(struct timespec *ts) +void __weak read_boot_clock(struct timespec *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 015f85aaca08..8639819f6cef 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -424,6 +424,7 @@ config UPROBE_EVENT bool "Enable uprobes-based dynamic events" depends on ARCH_SUPPORTS_UPROBES depends on MMU + depends on PERF_EVENTS select UPROBES select PROBE_EVENTS select TRACING diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 4f3a3c03eadb..c1bd4ada2a04 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1429,7 +1429,8 @@ static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter) return print_one_line(iter, true); } -static int blk_tracer_set_flag(u32 old_flags, u32 bit, int set) +static int +blk_tracer_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { /* don't output context-info for blk_classic output */ if (bit == TRACE_BLK_OPT_CLASSIC) { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index cd7f76d1eb86..1fd4b9479210 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -237,14 +237,13 @@ static int control_ops_alloc(struct ftrace_ops *ops) return 0; } -static void control_ops_free(struct ftrace_ops *ops) -{ - free_percpu(ops->disabled); -} - static void update_global_ops(void) { - ftrace_func_t func; + ftrace_func_t func = ftrace_global_list_func; + void *private = NULL; + + /* The list has its own recursion protection. */ + global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE; /* * If there's only one function registered, then call that @@ -254,23 +253,17 @@ static void update_global_ops(void) if (ftrace_global_list == &ftrace_list_end || ftrace_global_list->next == &ftrace_list_end) { func = ftrace_global_list->func; + private = ftrace_global_list->private; /* * As we are calling the function directly. * If it does not have recursion protection, * the function_trace_op needs to be updated * accordingly. */ - if (ftrace_global_list->flags & FTRACE_OPS_FL_RECURSION_SAFE) - global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE; - else + if (!(ftrace_global_list->flags & FTRACE_OPS_FL_RECURSION_SAFE)) global_ops.flags &= ~FTRACE_OPS_FL_RECURSION_SAFE; - } else { - func = ftrace_global_list_func; - /* The list has its own recursion protection. */ - global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE; } - /* If we filter on pids, update to use the pid function */ if (!list_empty(&ftrace_pids)) { set_ftrace_pid_function(func); @@ -278,6 +271,7 @@ static void update_global_ops(void) } global_ops.func = func; + global_ops.private = private; } static void ftrace_sync(struct work_struct *work) @@ -437,6 +431,9 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list, static int __register_ftrace_function(struct ftrace_ops *ops) { + if (ops->flags & FTRACE_OPS_FL_DELETED) + return -EINVAL; + if (FTRACE_WARN_ON(ops == &global_ops)) return -EINVAL; @@ -1172,8 +1169,6 @@ struct ftrace_page { int size; }; -static struct ftrace_page *ftrace_new_pgs; - #define ENTRY_SIZE sizeof(struct dyn_ftrace) #define ENTRIES_PER_PAGE (PAGE_SIZE / ENTRY_SIZE) @@ -1560,7 +1555,7 @@ unsigned long ftrace_location(unsigned long ip) * the function tracer. It checks the ftrace internal tables to * determine if the address belongs or not. */ -int ftrace_text_reserved(void *start, void *end) +int ftrace_text_reserved(const void *start, const void *end) { unsigned long ret; @@ -1994,6 +1989,7 @@ int __weak ftrace_arch_code_modify_post_process(void) void ftrace_modify_all_code(int command) { int update = command & FTRACE_UPDATE_TRACE_FUNC; + int err = 0; /* * If the ftrace_caller calls a ftrace_ops func directly, @@ -2005,8 +2001,11 @@ void ftrace_modify_all_code(int command) * to make sure the ops are having the right functions * traced. */ - if (update) - ftrace_update_ftrace_func(ftrace_ops_list_func); + if (update) { + err = ftrace_update_ftrace_func(ftrace_ops_list_func); + if (FTRACE_WARN_ON(err)) + return; + } if (command & FTRACE_UPDATE_CALLS) ftrace_replace_code(1); @@ -2019,13 +2018,16 @@ void ftrace_modify_all_code(int command) /* If irqs are disabled, we are in stop machine */ if (!irqs_disabled()) smp_call_function(ftrace_sync_ipi, NULL, 1); - ftrace_update_ftrace_func(ftrace_trace_function); + err = ftrace_update_ftrace_func(ftrace_trace_function); + if (FTRACE_WARN_ON(err)) + return; } if (command & FTRACE_START_FUNC_RET) - ftrace_enable_ftrace_graph_caller(); + err = ftrace_enable_ftrace_graph_caller(); else if (command & FTRACE_STOP_FUNC_RET) - ftrace_disable_ftrace_graph_caller(); + err = ftrace_disable_ftrace_graph_caller(); + FTRACE_WARN_ON(err); } static int __ftrace_modify_code(void *data) @@ -2093,6 +2095,11 @@ static ftrace_func_t saved_ftrace_func; static int ftrace_start_up; static int global_start_up; +static void control_ops_free(struct ftrace_ops *ops) +{ + free_percpu(ops->disabled); +} + static void ftrace_startup_enable(int command) { if (saved_ftrace_func != ftrace_trace_function) { @@ -2244,7 +2251,6 @@ static void ftrace_shutdown_sysctl(void) } static cycle_t ftrace_update_time; -static unsigned long ftrace_update_cnt; unsigned long ftrace_update_tot_cnt; static inline int ops_traces_mod(struct ftrace_ops *ops) @@ -2300,11 +2306,12 @@ static int referenced_filters(struct dyn_ftrace *rec) return cnt; } -static int ftrace_update_code(struct module *mod) +static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) { struct ftrace_page *pg; struct dyn_ftrace *p; cycle_t start, stop; + unsigned long update_cnt = 0; unsigned long ref = 0; bool test = false; int i; @@ -2330,9 +2337,8 @@ static int ftrace_update_code(struct module *mod) } start = ftrace_now(raw_smp_processor_id()); - ftrace_update_cnt = 0; - for (pg = ftrace_new_pgs; pg; pg = pg->next) { + for (pg = new_pgs; pg; pg = pg->next) { for (i = 0; i < pg->index; i++) { int cnt = ref; @@ -2353,7 +2359,7 @@ static int ftrace_update_code(struct module *mod) if (!ftrace_code_disable(mod, p)) break; - ftrace_update_cnt++; + update_cnt++; /* * If the tracing is enabled, go ahead and enable the record. @@ -2372,11 +2378,9 @@ static int ftrace_update_code(struct module *mod) } } - ftrace_new_pgs = NULL; - stop = ftrace_now(raw_smp_processor_id()); ftrace_update_time = stop - start; - ftrace_update_tot_cnt += ftrace_update_cnt; + ftrace_update_tot_cnt += update_cnt; return 0; } @@ -2468,22 +2472,6 @@ ftrace_allocate_pages(unsigned long num_to_init) return NULL; } -static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) -{ - int cnt; - - if (!num_to_init) { - pr_info("ftrace: No functions to be traced?\n"); - return -1; - } - - cnt = num_to_init / ENTRIES_PER_PAGE; - pr_info("ftrace: allocating %ld entries in %d pages\n", - num_to_init, cnt + 1); - - return 0; -} - #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */ struct ftrace_iterator { @@ -2871,7 +2859,9 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, static int ftrace_filter_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(&global_ops, + struct ftrace_ops *ops = inode->i_private; + + return ftrace_regex_open(ops, FTRACE_ITER_FILTER | FTRACE_ITER_DO_HASH, inode, file); } @@ -2879,7 +2869,9 @@ ftrace_filter_open(struct inode *inode, struct file *file) static int ftrace_notrace_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(&global_ops, FTRACE_ITER_NOTRACE, + struct ftrace_ops *ops = inode->i_private; + + return ftrace_regex_open(ops, FTRACE_ITER_NOTRACE, inode, file); } @@ -4109,6 +4101,36 @@ static const struct file_operations ftrace_graph_notrace_fops = { }; #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ +void ftrace_create_filter_files(struct ftrace_ops *ops, + struct dentry *parent) +{ + + trace_create_file("set_ftrace_filter", 0644, parent, + ops, &ftrace_filter_fops); + + trace_create_file("set_ftrace_notrace", 0644, parent, + ops, &ftrace_notrace_fops); +} + +/* + * The name "destroy_filter_files" is really a misnomer. Although + * in the future, it may actualy delete the files, but this is + * really intended to make sure the ops passed in are disabled + * and that when this function returns, the caller is free to + * free the ops. + * + * The "destroy" name is only to match the "create" name that this + * should be paired with. + */ +void ftrace_destroy_filter_files(struct ftrace_ops *ops) +{ + mutex_lock(&ftrace_lock); + if (ops->flags & FTRACE_OPS_FL_ENABLED) + ftrace_shutdown(ops, 0); + ops->flags |= FTRACE_OPS_FL_DELETED; + mutex_unlock(&ftrace_lock); +} + static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { @@ -4118,11 +4140,7 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer) trace_create_file("enabled_functions", 0444, d_tracer, NULL, &ftrace_enabled_fops); - trace_create_file("set_ftrace_filter", 0644, d_tracer, - NULL, &ftrace_filter_fops); - - trace_create_file("set_ftrace_notrace", 0644, d_tracer, - NULL, &ftrace_notrace_fops); + ftrace_create_filter_files(&global_ops, d_tracer); #ifdef CONFIG_FUNCTION_GRAPH_TRACER trace_create_file("set_graph_function", 0444, d_tracer, @@ -4238,9 +4256,6 @@ static int ftrace_process_locs(struct module *mod, /* Assign the last page to ftrace_pages */ ftrace_pages = pg; - /* These new locations need to be initialized */ - ftrace_new_pgs = start_pg; - /* * We only need to disable interrupts on start up * because we are modifying code that an interrupt @@ -4251,7 +4266,7 @@ static int ftrace_process_locs(struct module *mod, */ if (!mod) local_irq_save(flags); - ftrace_update_code(mod); + ftrace_update_code(mod, start_pg); if (!mod) local_irq_restore(flags); ret = 0; @@ -4360,30 +4375,27 @@ struct notifier_block ftrace_module_exit_nb = { .priority = INT_MIN, /* Run after anything that can remove kprobes */ }; -extern unsigned long __start_mcount_loc[]; -extern unsigned long __stop_mcount_loc[]; - void __init ftrace_init(void) { - unsigned long count, addr, flags; + extern unsigned long __start_mcount_loc[]; + extern unsigned long __stop_mcount_loc[]; + unsigned long count, flags; int ret; - /* Keep the ftrace pointer to the stub */ - addr = (unsigned long)ftrace_stub; - local_irq_save(flags); - ftrace_dyn_arch_init(&addr); + ret = ftrace_dyn_arch_init(); local_irq_restore(flags); - - /* ftrace_dyn_arch_init places the return code in addr */ - if (addr) + if (ret) goto failed; count = __stop_mcount_loc - __start_mcount_loc; - - ret = ftrace_dyn_table_alloc(count); - if (ret) + if (!count) { + pr_info("ftrace: No functions to be traced?\n"); goto failed; + } + + pr_info("ftrace: allocating %ld entries in %ld pages\n", + count, count / ENTRIES_PER_PAGE + 1); last_ftrace_enabled = ftrace_enabled = 1; @@ -4431,7 +4443,13 @@ static inline void ftrace_startup_enable(int command) { } (ops)->flags |= FTRACE_OPS_FL_ENABLED; \ ___ret; \ }) -# define ftrace_shutdown(ops, command) __unregister_ftrace_function(ops) +# define ftrace_shutdown(ops, command) \ + ({ \ + int ___ret = __unregister_ftrace_function(ops); \ + if (!___ret) \ + (ops)->flags &= ~FTRACE_OPS_FL_ENABLED; \ + ___ret; \ + }) # define ftrace_startup_sysctl() do { } while (0) # define ftrace_shutdown_sysctl() do { } while (0) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index fc4da2d97f9b..c634868c2921 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1301,7 +1301,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, * In that off case, we need to allocate for all possible cpus. */ #ifdef CONFIG_HOTPLUG_CPU - get_online_cpus(); + cpu_notifier_register_begin(); cpumask_copy(buffer->cpumask, cpu_online_mask); #else cpumask_copy(buffer->cpumask, cpu_possible_mask); @@ -1324,10 +1324,10 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, #ifdef CONFIG_HOTPLUG_CPU buffer->cpu_notify.notifier_call = rb_cpu_notify; buffer->cpu_notify.priority = 0; - register_cpu_notifier(&buffer->cpu_notify); + __register_cpu_notifier(&buffer->cpu_notify); + cpu_notifier_register_done(); #endif - put_online_cpus(); mutex_init(&buffer->mutex); return buffer; @@ -1341,7 +1341,9 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, fail_free_cpumask: free_cpumask_var(buffer->cpumask); - put_online_cpus(); +#ifdef CONFIG_HOTPLUG_CPU + cpu_notifier_register_done(); +#endif fail_free_buffer: kfree(buffer); @@ -1358,16 +1360,17 @@ ring_buffer_free(struct ring_buffer *buffer) { int cpu; - get_online_cpus(); - #ifdef CONFIG_HOTPLUG_CPU - unregister_cpu_notifier(&buffer->cpu_notify); + cpu_notifier_register_begin(); + __unregister_cpu_notifier(&buffer->cpu_notify); #endif for_each_buffer_cpu(buffer, cpu) rb_free_cpu_buffer(buffer->buffers[cpu]); - put_online_cpus(); +#ifdef CONFIG_HOTPLUG_CPU + cpu_notifier_register_done(); +#endif kfree(buffer->buffers); free_cpumask_var(buffer->cpumask); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 24c1f2382557..737b0efa1a62 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -73,7 +73,8 @@ static struct tracer_flags dummy_tracer_flags = { .opts = dummy_tracer_opt }; -static int dummy_set_flag(u32 old_flags, u32 bit, int set) +static int +dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { return 0; } @@ -118,7 +119,7 @@ enum ftrace_dump_mode ftrace_dump_on_oops; /* When set, tracing will stop when a WARN*() is hit */ int __disable_trace_on_warning; -static int tracing_set_tracer(const char *buf); +static int tracing_set_tracer(struct trace_array *tr, const char *buf); #define MAX_TRACER_SIZE 100 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; @@ -180,6 +181,17 @@ static int __init set_trace_boot_options(char *str) } __setup("trace_options=", set_trace_boot_options); +static char trace_boot_clock_buf[MAX_TRACER_SIZE] __initdata; +static char *trace_boot_clock __initdata; + +static int __init set_trace_boot_clock(char *str) +{ + strlcpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE); + trace_boot_clock = trace_boot_clock_buf; + return 0; +} +__setup("trace_clock=", set_trace_boot_clock); + unsigned long long ns2usecs(cycle_t nsec) { @@ -1230,7 +1242,7 @@ int register_tracer(struct tracer *type) printk(KERN_INFO "Starting tracer '%s'\n", type->name); /* Do we want this tracer to start on bootup? */ - tracing_set_tracer(type->name); + tracing_set_tracer(&global_trace, type->name); default_bootup_tracer = NULL; /* disable other selftests, since this will break it. */ tracing_selftest_disabled = true; @@ -3137,27 +3149,52 @@ static int tracing_open(struct inode *inode, struct file *file) return ret; } +/* + * Some tracers are not suitable for instance buffers. + * A tracer is always available for the global array (toplevel) + * or if it explicitly states that it is. + */ +static bool +trace_ok_for_array(struct tracer *t, struct trace_array *tr) +{ + return (tr->flags & TRACE_ARRAY_FL_GLOBAL) || t->allow_instances; +} + +/* Find the next tracer that this trace array may use */ +static struct tracer * +get_tracer_for_array(struct trace_array *tr, struct tracer *t) +{ + while (t && !trace_ok_for_array(t, tr)) + t = t->next; + + return t; +} + static void * t_next(struct seq_file *m, void *v, loff_t *pos) { + struct trace_array *tr = m->private; struct tracer *t = v; (*pos)++; if (t) - t = t->next; + t = get_tracer_for_array(tr, t->next); return t; } static void *t_start(struct seq_file *m, loff_t *pos) { + struct trace_array *tr = m->private; struct tracer *t; loff_t l = 0; mutex_lock(&trace_types_lock); - for (t = trace_types; t && l < *pos; t = t_next(m, t, &l)) - ; + + t = get_tracer_for_array(tr, trace_types); + for (; t && l < *pos; t = t_next(m, t, &l)) + ; return t; } @@ -3192,10 +3229,21 @@ static const struct seq_operations show_traces_seq_ops = { static int show_traces_open(struct inode *inode, struct file *file) { + struct trace_array *tr = inode->i_private; + struct seq_file *m; + int ret; + if (tracing_disabled) return -ENODEV; - return seq_open(file, &show_traces_seq_ops); + ret = seq_open(file, &show_traces_seq_ops); + if (ret) + return ret; + + m = file->private_data; + m->private = tr; + + return 0; } static ssize_t @@ -3355,13 +3403,14 @@ static int tracing_trace_options_show(struct seq_file *m, void *v) return 0; } -static int __set_tracer_option(struct tracer *trace, +static int __set_tracer_option(struct trace_array *tr, struct tracer_flags *tracer_flags, struct tracer_opt *opts, int neg) { + struct tracer *trace = tr->current_trace; int ret; - ret = trace->set_flag(tracer_flags->val, opts->bit, !neg); + ret = trace->set_flag(tr, tracer_flags->val, opts->bit, !neg); if (ret) return ret; @@ -3373,8 +3422,9 @@ static int __set_tracer_option(struct tracer *trace, } /* Try to assign a tracer specific option */ -static int set_tracer_option(struct tracer *trace, char *cmp, int neg) +static int set_tracer_option(struct trace_array *tr, char *cmp, int neg) { + struct tracer *trace = tr->current_trace; struct tracer_flags *tracer_flags = trace->flags; struct tracer_opt *opts = NULL; int i; @@ -3383,8 +3433,7 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg) opts = &tracer_flags->opts[i]; if (strcmp(cmp, opts->name) == 0) - return __set_tracer_option(trace, trace->flags, - opts, neg); + return __set_tracer_option(tr, trace->flags, opts, neg); } return -EINVAL; @@ -3407,7 +3456,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) /* Give the tracer a chance to approve the change */ if (tr->current_trace->flag_changed) - if (tr->current_trace->flag_changed(tr->current_trace, mask, !!enabled)) + if (tr->current_trace->flag_changed(tr, mask, !!enabled)) return -EINVAL; if (enabled) @@ -3456,7 +3505,7 @@ static int trace_set_options(struct trace_array *tr, char *option) /* If no option could be set, test the specific tracer options */ if (!trace_options[i]) - ret = set_tracer_option(tr->current_trace, cmp, neg); + ret = set_tracer_option(tr, cmp, neg); mutex_unlock(&trace_types_lock); @@ -3562,6 +3611,8 @@ static const char readme_msg[] = #ifdef CONFIG_TRACER_SNAPSHOT "\t\t snapshot\n" #endif + "\t\t dump\n" + "\t\t cpudump\n" "\t example: echo do_fault:traceoff > set_ftrace_filter\n" "\t echo do_trap:traceoff:3 > set_ftrace_filter\n" "\t The first one will disable tracing every time do_fault is hit\n" @@ -3885,10 +3936,26 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer); static void destroy_trace_option_files(struct trace_option_dentry *topts); -static int tracing_set_tracer(const char *buf) +/* + * Used to clear out the tracer before deletion of an instance. + * Must have trace_types_lock held. + */ +static void tracing_set_nop(struct trace_array *tr) +{ + if (tr->current_trace == &nop_trace) + return; + + tr->current_trace->enabled--; + + if (tr->current_trace->reset) + tr->current_trace->reset(tr); + + tr->current_trace = &nop_trace; +} + +static int tracing_set_tracer(struct trace_array *tr, const char *buf) { static struct trace_option_dentry *topts; - struct trace_array *tr = &global_trace; struct tracer *t; #ifdef CONFIG_TRACER_MAX_TRACE bool had_max_tr; @@ -3916,9 +3983,15 @@ static int tracing_set_tracer(const char *buf) if (t == tr->current_trace) goto out; + /* Some tracers are only allowed for the top level buffer */ + if (!trace_ok_for_array(t, tr)) { + ret = -EINVAL; + goto out; + } + trace_branch_disable(); - tr->current_trace->enabled = false; + tr->current_trace->enabled--; if (tr->current_trace->reset) tr->current_trace->reset(tr); @@ -3941,9 +4014,11 @@ static int tracing_set_tracer(const char *buf) free_snapshot(tr); } #endif - destroy_trace_option_files(topts); - - topts = create_trace_option_files(tr, t); + /* Currently, only the top instance has options */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) { + destroy_trace_option_files(topts); + topts = create_trace_option_files(tr, t); + } #ifdef CONFIG_TRACER_MAX_TRACE if (t->use_max_tr && !had_max_tr) { @@ -3960,7 +4035,7 @@ static int tracing_set_tracer(const char *buf) } tr->current_trace = t; - tr->current_trace->enabled = true; + tr->current_trace->enabled++; trace_branch_enable(tr); out: mutex_unlock(&trace_types_lock); @@ -3972,6 +4047,7 @@ static ssize_t tracing_set_trace_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { + struct trace_array *tr = filp->private_data; char buf[MAX_TRACER_SIZE+1]; int i; size_t ret; @@ -3991,7 +4067,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, for (i = cnt - 1; i > 0 && isspace(buf[i]); i--) buf[i] = 0; - err = tracing_set_tracer(buf); + err = tracing_set_tracer(tr, buf); if (err) return err; @@ -4316,8 +4392,6 @@ static void tracing_spd_release_pipe(struct splice_pipe_desc *spd, static const struct pipe_buf_operations tracing_pipe_buf_ops = { .can_merge = 0, - .map = generic_pipe_buf_map, - .unmap = generic_pipe_buf_unmap, .confirm = generic_pipe_buf_confirm, .release = generic_pipe_buf_release, .steal = generic_pipe_buf_steal, @@ -4412,7 +4486,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, trace_access_lock(iter->cpu_file); /* Fill as many pages as possible. */ - for (i = 0, rem = len; i < pipe->buffers && rem; i++) { + for (i = 0, rem = len; i < spd.nr_pages_max && rem; i++) { spd.pages[i] = alloc_page(GFP_KERNEL); if (!spd.pages[i]) break; @@ -4699,25 +4773,10 @@ static int tracing_clock_show(struct seq_file *m, void *v) return 0; } -static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *fpos) +static int tracing_set_clock(struct trace_array *tr, const char *clockstr) { - struct seq_file *m = filp->private_data; - struct trace_array *tr = m->private; - char buf[64]; - const char *clockstr; int i; - if (cnt >= sizeof(buf)) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - - clockstr = strstrip(buf); - for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) { if (strcmp(trace_clocks[i].name, clockstr) == 0) break; @@ -4745,6 +4804,32 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, mutex_unlock(&trace_types_lock); + return 0; +} + +static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *fpos) +{ + struct seq_file *m = filp->private_data; + struct trace_array *tr = m->private; + char buf[64]; + const char *clockstr; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + clockstr = strstrip(buf); + + ret = tracing_set_clock(tr, clockstr); + if (ret) + return ret; + *fpos += cnt; return cnt; @@ -5194,8 +5279,6 @@ static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, /* Pipe buffer operations for a buffer. */ static const struct pipe_buf_operations buffer_pipe_buf_ops = { .can_merge = 0, - .map = generic_pipe_buf_map, - .unmap = generic_pipe_buf_unmap, .confirm = generic_pipe_buf_confirm, .release = buffer_pipe_buf_release, .steal = generic_pipe_buf_steal, @@ -5271,7 +5354,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, trace_access_lock(iter->cpu_file); entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file); - for (i = 0; i < pipe->buffers && len && entries; i++, len -= PAGE_SIZE) { + for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= PAGE_SIZE) { struct page *page; int r; @@ -5705,7 +5788,7 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, if (!!(topt->flags->val & topt->opt->bit) != val) { mutex_lock(&trace_types_lock); - ret = __set_tracer_option(topt->tr->current_trace, topt->flags, + ret = __set_tracer_option(topt->tr, topt->flags, topt->opt, !val); mutex_unlock(&trace_types_lock); if (ret) @@ -6112,7 +6195,9 @@ static int instance_delete(const char *name) list_del(&tr->list); + tracing_set_nop(tr); event_trace_del_tracer(tr); + ftrace_destroy_function_files(tr); debugfs_remove_recursive(tr->dir); free_percpu(tr->trace_buffer.data); ring_buffer_free(tr->trace_buffer.buffer); @@ -6207,6 +6292,12 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) { int cpu; + trace_create_file("available_tracers", 0444, d_tracer, + tr, &show_traces_fops); + + trace_create_file("current_tracer", 0644, d_tracer, + tr, &set_tracer_fops); + trace_create_file("tracing_cpumask", 0644, d_tracer, tr, &tracing_cpumask_fops); @@ -6237,6 +6328,9 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) trace_create_file("tracing_on", 0644, d_tracer, tr, &rb_simple_fops); + if (ftrace_create_function_files(tr, d_tracer)) + WARN(1, "Could not allocate function filter files"); + #ifdef CONFIG_TRACER_SNAPSHOT trace_create_file("snapshot", 0644, d_tracer, tr, &snapshot_fops); @@ -6259,12 +6353,6 @@ static __init int tracer_init_debugfs(void) init_tracer_debugfs(&global_trace, d_tracer); - trace_create_file("available_tracers", 0444, d_tracer, - &global_trace, &show_traces_fops); - - trace_create_file("current_tracer", 0644, d_tracer, - &global_trace, &set_tracer_fops); - #ifdef CONFIG_TRACER_MAX_TRACE trace_create_file("tracing_max_latency", 0644, d_tracer, &tracing_max_latency, &tracing_max_lat_fops); @@ -6527,6 +6615,13 @@ __init static int tracer_alloc_buffers(void) trace_init_cmdlines(); + if (trace_boot_clock) { + ret = tracing_set_clock(&global_trace, trace_boot_clock); + if (ret < 0) + pr_warning("Trace clock %s not defined, going back to default\n", + trace_boot_clock); + } + /* * register_tracer() might reference current_trace, so it * needs to be set before we register anything. This is diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 02b592f2d4b7..2e29d7ba5a52 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -13,6 +13,7 @@ #include <linux/hw_breakpoint.h> #include <linux/trace_seq.h> #include <linux/ftrace_event.h> +#include <linux/compiler.h> #ifdef CONFIG_FTRACE_SYSCALLS #include <asm/unistd.h> /* For NR_SYSCALLS */ @@ -210,6 +211,11 @@ struct trace_array { struct list_head events; cpumask_var_t tracing_cpumask; /* only trace on set CPUs */ int ref; +#ifdef CONFIG_FUNCTION_TRACER + struct ftrace_ops *ops; + /* function tracing enabled */ + int function_enabled; +#endif }; enum { @@ -355,14 +361,16 @@ struct tracer { void (*print_header)(struct seq_file *m); enum print_line_t (*print_line)(struct trace_iterator *iter); /* If you handled the flag setting, return 0 */ - int (*set_flag)(u32 old_flags, u32 bit, int set); + int (*set_flag)(struct trace_array *tr, + u32 old_flags, u32 bit, int set); /* Return 0 if OK with change, else return non-zero */ - int (*flag_changed)(struct tracer *tracer, + int (*flag_changed)(struct trace_array *tr, u32 mask, int set); struct tracer *next; struct tracer_flags *flags; + int enabled; bool print_max; - bool enabled; + bool allow_instances; #ifdef CONFIG_TRACER_MAX_TRACE bool use_max_tr; #endif @@ -812,13 +820,36 @@ static inline int ftrace_trace_task(struct task_struct *task) return test_tsk_trace_trace(task); } extern int ftrace_is_dead(void); +int ftrace_create_function_files(struct trace_array *tr, + struct dentry *parent); +void ftrace_destroy_function_files(struct trace_array *tr); #else static inline int ftrace_trace_task(struct task_struct *task) { return 1; } static inline int ftrace_is_dead(void) { return 0; } -#endif +static inline int +ftrace_create_function_files(struct trace_array *tr, + struct dentry *parent) +{ + return 0; +} +static inline void ftrace_destroy_function_files(struct trace_array *tr) { } +#endif /* CONFIG_FUNCTION_TRACER */ + +#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE) +void ftrace_create_filter_files(struct ftrace_ops *ops, + struct dentry *parent); +void ftrace_destroy_filter_files(struct ftrace_ops *ops); +#else +/* + * The ops parameter passed in is usually undefined. + * This must be a macro. + */ +#define ftrace_create_filter_files(ops, parent) do { } while (0) +#define ftrace_destroy_filter_files(ops) do { } while (0) +#endif /* CONFIG_FUNCTION_TRACER && CONFIG_DYNAMIC_FTRACE */ int ftrace_event_is_function(struct ftrace_event_call *call); @@ -1249,7 +1280,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled); #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ extern struct ftrace_event_call \ - __attribute__((__aligned__(4))) event_##call; + __aligned(4) event_##call; #undef FTRACE_ENTRY_DUP #define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \ FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 7b16d40bd64d..3ddfd8f62c05 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -188,29 +188,60 @@ int trace_event_raw_init(struct ftrace_event_call *call) } EXPORT_SYMBOL_GPL(trace_event_raw_init); +void *ftrace_event_buffer_reserve(struct ftrace_event_buffer *fbuffer, + struct ftrace_event_file *ftrace_file, + unsigned long len) +{ + struct ftrace_event_call *event_call = ftrace_file->event_call; + + local_save_flags(fbuffer->flags); + fbuffer->pc = preempt_count(); + fbuffer->ftrace_file = ftrace_file; + + fbuffer->event = + trace_event_buffer_lock_reserve(&fbuffer->buffer, ftrace_file, + event_call->event.type, len, + fbuffer->flags, fbuffer->pc); + if (!fbuffer->event) + return NULL; + + fbuffer->entry = ring_buffer_event_data(fbuffer->event); + return fbuffer->entry; +} +EXPORT_SYMBOL_GPL(ftrace_event_buffer_reserve); + +void ftrace_event_buffer_commit(struct ftrace_event_buffer *fbuffer) +{ + event_trigger_unlock_commit(fbuffer->ftrace_file, fbuffer->buffer, + fbuffer->event, fbuffer->entry, + fbuffer->flags, fbuffer->pc); +} +EXPORT_SYMBOL_GPL(ftrace_event_buffer_commit); + int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type, void *data) { struct ftrace_event_file *file = data; + WARN_ON(!(call->flags & TRACE_EVENT_FL_TRACEPOINT)); switch (type) { case TRACE_REG_REGISTER: - return tracepoint_probe_register(call->name, + return tracepoint_probe_register(call->tp, call->class->probe, file); case TRACE_REG_UNREGISTER: - tracepoint_probe_unregister(call->name, + tracepoint_probe_unregister(call->tp, call->class->probe, file); return 0; #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: - return tracepoint_probe_register(call->name, + return tracepoint_probe_register(call->tp, call->class->perf_probe, call); case TRACE_REG_PERF_UNREGISTER: - tracepoint_probe_unregister(call->name, + tracepoint_probe_unregister(call->tp, call->class->perf_probe, call); return 0; @@ -322,7 +353,7 @@ static int __ftrace_event_enable_disable(struct ftrace_event_file *file, if (ret) { tracing_stop_cmdline_record(); pr_info("event trace: Could not enable event " - "%s\n", call->name); + "%s\n", ftrace_event_name(call)); break; } set_bit(FTRACE_EVENT_FL_ENABLED_BIT, &file->flags); @@ -451,27 +482,29 @@ __ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match, { struct ftrace_event_file *file; struct ftrace_event_call *call; + const char *name; int ret = -EINVAL; list_for_each_entry(file, &tr->events, list) { call = file->event_call; + name = ftrace_event_name(call); - if (!call->name || !call->class || !call->class->reg) + if (!name || !call->class || !call->class->reg) continue; if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) continue; if (match && - strcmp(match, call->name) != 0 && + strcmp(match, name) != 0 && strcmp(match, call->class->system) != 0) continue; if (sub && strcmp(sub, call->class->system) != 0) continue; - if (event && strcmp(event, call->name) != 0) + if (event && strcmp(event, name) != 0) continue; ftrace_event_enable_disable(file, set); @@ -669,7 +702,7 @@ static int t_show(struct seq_file *m, void *v) if (strcmp(call->class->system, TRACE_SYSTEM) != 0) seq_printf(m, "%s:", call->class->system); - seq_printf(m, "%s\n", call->name); + seq_printf(m, "%s\n", ftrace_event_name(call)); return 0; } @@ -762,7 +795,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, mutex_lock(&event_mutex); list_for_each_entry(file, &tr->events, list) { call = file->event_call; - if (!call->name || !call->class || !call->class->reg) + if (!ftrace_event_name(call) || !call->class || !call->class->reg) continue; if (system && strcmp(call->class->system, system->name) != 0) @@ -877,7 +910,7 @@ static int f_show(struct seq_file *m, void *v) switch ((unsigned long)v) { case FORMAT_HEADER: - seq_printf(m, "name: %s\n", call->name); + seq_printf(m, "name: %s\n", ftrace_event_name(call)); seq_printf(m, "ID: %d\n", call->event.type); seq_printf(m, "format:\n"); return 0; @@ -1497,6 +1530,7 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file) struct trace_array *tr = file->tr; struct list_head *head; struct dentry *d_events; + const char *name; int ret; /* @@ -1510,10 +1544,11 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file) } else d_events = parent; - file->dir = debugfs_create_dir(call->name, d_events); + name = ftrace_event_name(call); + file->dir = debugfs_create_dir(name, d_events); if (!file->dir) { pr_warning("Could not create debugfs '%s' directory\n", - call->name); + name); return -1; } @@ -1537,7 +1572,7 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file) ret = call->class->define_fields(call); if (ret < 0) { pr_warning("Could not initialize trace point" - " events/%s\n", call->name); + " events/%s\n", name); return -1; } } @@ -1601,15 +1636,17 @@ static void event_remove(struct ftrace_event_call *call) static int event_init(struct ftrace_event_call *call) { int ret = 0; + const char *name; - if (WARN_ON(!call->name)) + name = ftrace_event_name(call); + if (WARN_ON(!name)) return -EINVAL; if (call->class->raw_init) { ret = call->class->raw_init(call); if (ret < 0 && ret != -ENOSYS) pr_warn("Could not initialize trace events/%s\n", - call->name); + name); } return ret; @@ -1855,7 +1892,7 @@ __trace_add_event_dirs(struct trace_array *tr) ret = __trace_add_new_event(call, tr); if (ret < 0) pr_warning("Could not create directory for event %s\n", - call->name); + ftrace_event_name(call)); } } @@ -1864,18 +1901,20 @@ find_event_file(struct trace_array *tr, const char *system, const char *event) { struct ftrace_event_file *file; struct ftrace_event_call *call; + const char *name; list_for_each_entry(file, &tr->events, list) { call = file->event_call; + name = ftrace_event_name(call); - if (!call->name || !call->class || !call->class->reg) + if (!name || !call->class || !call->class->reg) continue; if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) continue; - if (strcmp(event, call->name) == 0 && + if (strcmp(event, name) == 0 && strcmp(system, call->class->system) == 0) return file; } @@ -1943,7 +1982,7 @@ event_enable_print(struct seq_file *m, unsigned long ip, seq_printf(m, "%s:%s:%s", data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR, data->file->event_call->class->system, - data->file->event_call->name); + ftrace_event_name(data->file->event_call)); if (data->count == -1) seq_printf(m, ":unlimited\n"); @@ -2163,7 +2202,7 @@ __trace_early_add_event_dirs(struct trace_array *tr) ret = event_create_dir(tr->event_dir, file); if (ret < 0) pr_warning("Could not create directory for event %s\n", - file->event_call->name); + ftrace_event_name(file->event_call)); } } @@ -2187,7 +2226,7 @@ __trace_early_add_events(struct trace_array *tr) ret = __trace_early_add_new_event(call, tr); if (ret < 0) pr_warning("Could not create early event %s\n", - call->name); + ftrace_event_name(call)); } } @@ -2519,7 +2558,7 @@ static __init void event_trace_self_tests(void) continue; #endif - pr_info("Testing event %s: ", call->name); + pr_info("Testing event %s: ", ftrace_event_name(call)); /* * If an event is already enabled, someone is using diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 8efbb69b04f0..925f537f07d1 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -1095,7 +1095,7 @@ event_enable_trigger_print(struct seq_file *m, struct event_trigger_ops *ops, seq_printf(m, "%s:%s:%s", enable_data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR, enable_data->file->event_call->class->system, - enable_data->file->event_call->name); + ftrace_event_name(enable_data->file->event_call)); if (data->count == -1) seq_puts(m, ":unlimited"); diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index ee0a5098ac43..d4ddde28a81a 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -173,9 +173,11 @@ struct ftrace_event_class __refdata event_class_ftrace_##call = { \ }; \ \ struct ftrace_event_call __used event_##call = { \ - .name = #call, \ - .event.type = etype, \ .class = &event_class_ftrace_##call, \ + { \ + .name = #call, \ + }, \ + .event.type = etype, \ .print_fmt = print, \ .flags = TRACE_EVENT_FL_IGNORE_ENABLE | TRACE_EVENT_FL_USE_CALL_FILTER, \ }; \ diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 38fe1483c508..ffd56351b521 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -13,32 +13,110 @@ #include <linux/debugfs.h> #include <linux/uaccess.h> #include <linux/ftrace.h> +#include <linux/slab.h> #include <linux/fs.h> #include "trace.h" -/* function tracing enabled */ -static int ftrace_function_enabled; +static void tracing_start_function_trace(struct trace_array *tr); +static void tracing_stop_function_trace(struct trace_array *tr); +static void +function_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs); +static void +function_stack_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs); +static struct ftrace_ops trace_ops; +static struct ftrace_ops trace_stack_ops; +static struct tracer_flags func_flags; + +/* Our option */ +enum { + TRACE_FUNC_OPT_STACK = 0x1, +}; + +static int allocate_ftrace_ops(struct trace_array *tr) +{ + struct ftrace_ops *ops; + + ops = kzalloc(sizeof(*ops), GFP_KERNEL); + if (!ops) + return -ENOMEM; + + /* Currently only the non stack verision is supported */ + ops->func = function_trace_call; + ops->flags = FTRACE_OPS_FL_RECURSION_SAFE; -static struct trace_array *func_trace; + tr->ops = ops; + ops->private = tr; + return 0; +} + + +int ftrace_create_function_files(struct trace_array *tr, + struct dentry *parent) +{ + int ret; + + /* + * The top level array uses the "global_ops", and the files are + * created on boot up. + */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + return 0; -static void tracing_start_function_trace(void); -static void tracing_stop_function_trace(void); + ret = allocate_ftrace_ops(tr); + if (ret) + return ret; + + ftrace_create_filter_files(tr->ops, parent); + + return 0; +} + +void ftrace_destroy_function_files(struct trace_array *tr) +{ + ftrace_destroy_filter_files(tr->ops); + kfree(tr->ops); + tr->ops = NULL; +} static int function_trace_init(struct trace_array *tr) { - func_trace = tr; + struct ftrace_ops *ops; + + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) { + /* There's only one global tr */ + if (!trace_ops.private) { + trace_ops.private = tr; + trace_stack_ops.private = tr; + } + + if (func_flags.val & TRACE_FUNC_OPT_STACK) + ops = &trace_stack_ops; + else + ops = &trace_ops; + tr->ops = ops; + } else if (!tr->ops) { + /* + * Instance trace_arrays get their ops allocated + * at instance creation. Unless it failed + * the allocation. + */ + return -ENOMEM; + } + tr->trace_buffer.cpu = get_cpu(); put_cpu(); tracing_start_cmdline_record(); - tracing_start_function_trace(); + tracing_start_function_trace(tr); return 0; } static void function_trace_reset(struct trace_array *tr) { - tracing_stop_function_trace(); + tracing_stop_function_trace(tr); tracing_stop_cmdline_record(); } @@ -47,25 +125,18 @@ static void function_trace_start(struct trace_array *tr) tracing_reset_online_cpus(&tr->trace_buffer); } -/* Our option */ -enum { - TRACE_FUNC_OPT_STACK = 0x1, -}; - -static struct tracer_flags func_flags; - static void function_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) { - struct trace_array *tr = func_trace; + struct trace_array *tr = op->private; struct trace_array_cpu *data; unsigned long flags; int bit; int cpu; int pc; - if (unlikely(!ftrace_function_enabled)) + if (unlikely(!tr->function_enabled)) return; pc = preempt_count(); @@ -91,14 +162,14 @@ static void function_stack_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) { - struct trace_array *tr = func_trace; + struct trace_array *tr = op->private; struct trace_array_cpu *data; unsigned long flags; long disabled; int cpu; int pc; - if (unlikely(!ftrace_function_enabled)) + if (unlikely(!tr->function_enabled)) return; /* @@ -128,7 +199,6 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip, local_irq_restore(flags); } - static struct ftrace_ops trace_ops __read_mostly = { .func = function_trace_call, @@ -153,29 +223,21 @@ static struct tracer_flags func_flags = { .opts = func_opts }; -static void tracing_start_function_trace(void) +static void tracing_start_function_trace(struct trace_array *tr) { - ftrace_function_enabled = 0; - - if (func_flags.val & TRACE_FUNC_OPT_STACK) - register_ftrace_function(&trace_stack_ops); - else - register_ftrace_function(&trace_ops); - - ftrace_function_enabled = 1; + tr->function_enabled = 0; + register_ftrace_function(tr->ops); + tr->function_enabled = 1; } -static void tracing_stop_function_trace(void) +static void tracing_stop_function_trace(struct trace_array *tr) { - ftrace_function_enabled = 0; - - if (func_flags.val & TRACE_FUNC_OPT_STACK) - unregister_ftrace_function(&trace_stack_ops); - else - unregister_ftrace_function(&trace_ops); + tr->function_enabled = 0; + unregister_ftrace_function(tr->ops); } -static int func_set_flag(u32 old_flags, u32 bit, int set) +static int +func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { switch (bit) { case TRACE_FUNC_OPT_STACK: @@ -183,12 +245,14 @@ static int func_set_flag(u32 old_flags, u32 bit, int set) if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK)) break; + unregister_ftrace_function(tr->ops); + if (set) { - unregister_ftrace_function(&trace_ops); - register_ftrace_function(&trace_stack_ops); + tr->ops = &trace_stack_ops; + register_ftrace_function(tr->ops); } else { - unregister_ftrace_function(&trace_stack_ops); - register_ftrace_function(&trace_ops); + tr->ops = &trace_ops; + register_ftrace_function(tr->ops); } break; @@ -208,6 +272,7 @@ static struct tracer function_trace __tracer_data = .wait_pipe = poll_wait_pipe, .flags = &func_flags, .set_flag = func_set_flag, + .allow_instances = true, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_function, #endif diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 0b99120d395c..deff11200261 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -1476,7 +1476,8 @@ void graph_trace_close(struct trace_iterator *iter) } } -static int func_graph_set_flag(u32 old_flags, u32 bit, int set) +static int +func_graph_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { if (bit == TRACE_GRAPH_PRINT_IRQS) ftrace_graph_skip_irqs = !set; diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 887ef88b0bc7..8ff02cbb892f 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -160,7 +160,8 @@ static struct ftrace_ops trace_ops __read_mostly = #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER -static int irqsoff_set_flag(u32 old_flags, u32 bit, int set) +static int +irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { int cpu; @@ -266,7 +267,8 @@ __trace_function(struct trace_array *tr, #else #define __trace_function trace_function -static int irqsoff_set_flag(u32 old_flags, u32 bit, int set) +static int +irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { return -EINVAL; } @@ -570,8 +572,10 @@ static void irqsoff_function_set(int set) unregister_irqsoff_function(is_graph()); } -static int irqsoff_flag_changed(struct tracer *tracer, u32 mask, int set) +static int irqsoff_flag_changed(struct trace_array *tr, u32 mask, int set) { + struct tracer *tracer = tr->current_trace; + if (mask & TRACE_ITER_FUNCTION) irqsoff_function_set(set); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index bdbae450c13e..903ae28962be 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -35,11 +35,6 @@ struct trace_kprobe { struct trace_probe tp; }; -struct event_file_link { - struct ftrace_event_file *file; - struct list_head list; -}; - #define SIZEOF_TRACE_KPROBE(n) \ (offsetof(struct trace_kprobe, tp.args) + \ (sizeof(struct probe_arg) * (n))) @@ -346,7 +341,7 @@ static struct trace_kprobe *find_trace_kprobe(const char *event, struct trace_kprobe *tk; list_for_each_entry(tk, &probe_list, list) - if (strcmp(tk->tp.call.name, event) == 0 && + if (strcmp(ftrace_event_name(&tk->tp.call), event) == 0 && strcmp(tk->tp.call.class->system, group) == 0) return tk; return NULL; @@ -387,18 +382,6 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct ftrace_event_file *file) return ret; } -static struct event_file_link * -find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file) -{ - struct event_file_link *link; - - list_for_each_entry(link, &tp->files, list) - if (link->file == file) - return link; - - return NULL; -} - /* * Disable trace_probe * if the file is NULL, disable "perf" handler, or disable "trace" handler. @@ -533,7 +516,8 @@ static int register_trace_kprobe(struct trace_kprobe *tk) mutex_lock(&probe_lock); /* Delete old (same name) event if exist */ - old_tk = find_trace_kprobe(tk->tp.call.name, tk->tp.call.class->system); + old_tk = find_trace_kprobe(ftrace_event_name(&tk->tp.call), + tk->tp.call.class->system); if (old_tk) { ret = unregister_trace_kprobe(old_tk); if (ret < 0) @@ -581,7 +565,8 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, if (ret) pr_warning("Failed to re-register probe %s on" "%s: %d\n", - tk->tp.call.name, mod->name, ret); + ftrace_event_name(&tk->tp.call), + mod->name, ret); } } mutex_unlock(&probe_lock); @@ -835,7 +820,8 @@ static int probes_seq_show(struct seq_file *m, void *v) int i; seq_printf(m, "%c", trace_kprobe_is_return(tk) ? 'r' : 'p'); - seq_printf(m, ":%s/%s", tk->tp.call.class->system, tk->tp.call.name); + seq_printf(m, ":%s/%s", tk->tp.call.class->system, + ftrace_event_name(&tk->tp.call)); if (!tk->symbol) seq_printf(m, " 0x%p", tk->rp.kp.addr); @@ -893,7 +879,8 @@ static int probes_profile_seq_show(struct seq_file *m, void *v) { struct trace_kprobe *tk = v; - seq_printf(m, " %-44s %15lu %15lu\n", tk->tp.call.name, tk->nhit, + seq_printf(m, " %-44s %15lu %15lu\n", + ftrace_event_name(&tk->tp.call), tk->nhit, tk->rp.kp.nmissed); return 0; @@ -1028,7 +1015,7 @@ print_kprobe_event(struct trace_iterator *iter, int flags, field = (struct kprobe_trace_entry_head *)iter->ent; tp = container_of(event, struct trace_probe, call.event); - if (!trace_seq_printf(s, "%s: (", tp->call.name)) + if (!trace_seq_printf(s, "%s: (", ftrace_event_name(&tp->call))) goto partial; if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET)) @@ -1064,7 +1051,7 @@ print_kretprobe_event(struct trace_iterator *iter, int flags, field = (struct kretprobe_trace_entry_head *)iter->ent; tp = container_of(event, struct trace_probe, call.event); - if (!trace_seq_printf(s, "%s: (", tp->call.name)) + if (!trace_seq_printf(s, "%s: (", ftrace_event_name(&tp->call))) goto partial; if (!seq_print_ip_sym(s, field->ret_ip, flags | TRACE_ITER_SYM_OFFSET)) @@ -1303,7 +1290,8 @@ static int register_kprobe_event(struct trace_kprobe *tk) call->data = tk; ret = trace_add_event_call(call); if (ret) { - pr_info("Failed to register kprobe event: %s\n", call->name); + pr_info("Failed to register kprobe event: %s\n", + ftrace_event_name(call)); kfree(call->print_fmt); unregister_ftrace_event(&call->event); } diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c index 394f94417e2f..69a5cc94c01a 100644 --- a/kernel/trace/trace_nop.c +++ b/kernel/trace/trace_nop.c @@ -62,7 +62,7 @@ static void nop_trace_reset(struct trace_array *tr) * If you don't implement it, then the flag setting will be * automatically accepted. */ -static int nop_set_flag(u32 old_flags, u32 bit, int set) +static int nop_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { /* * Note that you don't need to update nop_flags.val yourself. @@ -96,6 +96,7 @@ struct tracer nop_trace __read_mostly = .selftest = trace_selftest_startup_nop, #endif .flags = &nop_flags, - .set_flag = nop_set_flag + .set_flag = nop_set_flag, + .allow_instances = true, }; diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index ed32284fbe32..a436de18aa99 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -431,7 +431,7 @@ int ftrace_raw_output_prep(struct trace_iterator *iter, } trace_seq_init(p); - ret = trace_seq_printf(s, "%s: ", event->name); + ret = trace_seq_printf(s, "%s: ", ftrace_event_name(event)); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -439,6 +439,37 @@ int ftrace_raw_output_prep(struct trace_iterator *iter, } EXPORT_SYMBOL(ftrace_raw_output_prep); +static int ftrace_output_raw(struct trace_iterator *iter, char *name, + char *fmt, va_list ap) +{ + struct trace_seq *s = &iter->seq; + int ret; + + ret = trace_seq_printf(s, "%s: ", name); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + ret = trace_seq_vprintf(s, fmt, ap); + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +int ftrace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...) +{ + va_list ap; + int ret; + + va_start(ap, fmt); + ret = ftrace_output_raw(iter, name, fmt, ap); + va_end(ap); + + return ret; +} +EXPORT_SYMBOL_GPL(ftrace_output_call); + #ifdef CONFIG_KRETPROBES static inline const char *kretprobed(const char *name) { diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index b73574a5f429..fb1ab5dfbd42 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -288,6 +288,11 @@ struct trace_probe { struct probe_arg args[]; }; +struct event_file_link { + struct ftrace_event_file *file; + struct list_head list; +}; + static inline bool trace_probe_is_enabled(struct trace_probe *tp) { return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE)); @@ -316,6 +321,18 @@ static inline int is_good_name(const char *name) return 1; } +static inline struct event_file_link * +find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file) +{ + struct event_file_link *link; + + list_for_each_entry(link, &tp->files, list) + if (link->file == file) + return link; + + return NULL; +} + extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size, struct probe_arg *parg, bool is_return, bool is_kprobe); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 6e32635e5e57..e14da5e97a69 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -179,8 +179,10 @@ static void wakeup_function_set(int set) unregister_wakeup_function(is_graph()); } -static int wakeup_flag_changed(struct tracer *tracer, u32 mask, int set) +static int wakeup_flag_changed(struct trace_array *tr, u32 mask, int set) { + struct tracer *tracer = tr->current_trace; + if (mask & TRACE_ITER_FUNCTION) wakeup_function_set(set); @@ -209,7 +211,8 @@ static void stop_func_tracer(int graph) } #ifdef CONFIG_FUNCTION_GRAPH_TRACER -static int wakeup_set_flag(u32 old_flags, u32 bit, int set) +static int +wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { if (!(bit & TRACE_DISPLAY_GRAPH)) @@ -311,7 +314,8 @@ __trace_function(struct trace_array *tr, #else #define __trace_function trace_function -static int wakeup_set_flag(u32 old_flags, u32 bit, int set) +static int +wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { return -EINVAL; } diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index e6be585cf06a..21b320e5d163 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -13,6 +13,7 @@ #include <linux/sysctl.h> #include <linux/init.h> #include <linux/fs.h> +#include <linux/magic.h> #include <asm/setup.h> @@ -144,6 +145,8 @@ check_stack(unsigned long ip, unsigned long *stack) i++; } + BUG_ON(current != &init_task && + *(end_of_stack(current)) != STACK_END_MAGIC); out: arch_spin_unlock(&max_stack_lock); local_irq_restore(flags); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 79e52d93860b..c082a7441345 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -260,6 +260,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) goto error; INIT_LIST_HEAD(&tu->list); + INIT_LIST_HEAD(&tu->tp.files); tu->consumer.handler = uprobe_dispatcher; if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher; @@ -293,7 +294,7 @@ static struct trace_uprobe *find_probe_event(const char *event, const char *grou struct trace_uprobe *tu; list_for_each_entry(tu, &uprobe_list, list) - if (strcmp(tu->tp.call.name, event) == 0 && + if (strcmp(ftrace_event_name(&tu->tp.call), event) == 0 && strcmp(tu->tp.call.class->system, group) == 0) return tu; @@ -323,7 +324,8 @@ static int register_trace_uprobe(struct trace_uprobe *tu) mutex_lock(&uprobe_lock); /* register as an event */ - old_tu = find_probe_event(tu->tp.call.name, tu->tp.call.class->system); + old_tu = find_probe_event(ftrace_event_name(&tu->tp.call), + tu->tp.call.class->system); if (old_tu) { /* delete old event */ ret = unregister_trace_uprobe(old_tu); @@ -598,7 +600,8 @@ static int probes_seq_show(struct seq_file *m, void *v) char c = is_ret_probe(tu) ? 'r' : 'p'; int i; - seq_printf(m, "%c:%s/%s", c, tu->tp.call.class->system, tu->tp.call.name); + seq_printf(m, "%c:%s/%s", c, tu->tp.call.class->system, + ftrace_event_name(&tu->tp.call)); seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset); for (i = 0; i < tu->tp.nr_args; i++) @@ -648,7 +651,8 @@ static int probes_profile_seq_show(struct seq_file *m, void *v) { struct trace_uprobe *tu = v; - seq_printf(m, " %s %-44s %15lu\n", tu->filename, tu->tp.call.name, tu->nhit); + seq_printf(m, " %s %-44s %15lu\n", tu->filename, + ftrace_event_name(&tu->tp.call), tu->nhit); return 0; } @@ -728,9 +732,15 @@ static int uprobe_buffer_enable(void) static void uprobe_buffer_disable(void) { + int cpu; + BUG_ON(!mutex_is_locked(&event_mutex)); if (--uprobe_buffer_refcnt == 0) { + for_each_possible_cpu(cpu) + free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, + cpu)->buf); + free_percpu(uprobe_cpu_buffer); uprobe_cpu_buffer = NULL; } @@ -758,31 +768,32 @@ static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb) mutex_unlock(&ucb->mutex); } -static void uprobe_trace_print(struct trace_uprobe *tu, - unsigned long func, struct pt_regs *regs) +static void __uprobe_trace_func(struct trace_uprobe *tu, + unsigned long func, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize, + struct ftrace_event_file *ftrace_file) { struct uprobe_trace_entry_head *entry; struct ring_buffer_event *event; struct ring_buffer *buffer; - struct uprobe_cpu_buffer *ucb; void *data; - int size, dsize, esize; + int size, esize; struct ftrace_event_call *call = &tu->tp.call; - dsize = __get_data_size(&tu->tp, regs); - esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + WARN_ON(call != ftrace_file->event_call); - if (WARN_ON_ONCE(!uprobe_cpu_buffer || tu->tp.size + dsize > PAGE_SIZE)) + if (WARN_ON_ONCE(tu->tp.size + dsize > PAGE_SIZE)) return; - ucb = uprobe_buffer_get(); - store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize); + if (ftrace_trigger_soft_disabled(ftrace_file)) + return; + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); size = esize + tu->tp.size + dsize; - event = trace_current_buffer_lock_reserve(&buffer, call->event.type, - size, 0, 0); + event = trace_event_buffer_lock_reserve(&buffer, ftrace_file, + call->event.type, size, 0, 0); if (!event) - goto out; + return; entry = ring_buffer_event_data(event); if (is_ret_probe(tu)) { @@ -796,25 +807,36 @@ static void uprobe_trace_print(struct trace_uprobe *tu, memcpy(data, ucb->buf, tu->tp.size + dsize); - if (!call_filter_check_discard(call, entry, buffer, event)) - trace_buffer_unlock_commit(buffer, event, 0, 0); - -out: - uprobe_buffer_put(ucb); + event_trigger_unlock_commit(ftrace_file, buffer, event, entry, 0, 0); } /* uprobe handler */ -static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) +static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) { - if (!is_ret_probe(tu)) - uprobe_trace_print(tu, 0, regs); + struct event_file_link *link; + + if (is_ret_probe(tu)) + return 0; + + rcu_read_lock(); + list_for_each_entry_rcu(link, &tu->tp.files, list) + __uprobe_trace_func(tu, 0, regs, ucb, dsize, link->file); + rcu_read_unlock(); + return 0; } static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, - struct pt_regs *regs) + struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) { - uprobe_trace_print(tu, func, regs); + struct event_file_link *link; + + rcu_read_lock(); + list_for_each_entry_rcu(link, &tu->tp.files, list) + __uprobe_trace_func(tu, func, regs, ucb, dsize, link->file); + rcu_read_unlock(); } /* Event entry printers */ @@ -831,12 +853,14 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e tu = container_of(event, struct trace_uprobe, tp.call.event); if (is_ret_probe(tu)) { - if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", tu->tp.call.name, + if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", + ftrace_event_name(&tu->tp.call), entry->vaddr[1], entry->vaddr[0])) goto partial; data = DATAOF_TRACE_ENTRY(entry, true); } else { - if (!trace_seq_printf(s, "%s: (0x%lx)", tu->tp.call.name, + if (!trace_seq_printf(s, "%s: (0x%lx)", + ftrace_event_name(&tu->tp.call), entry->vaddr[0])) goto partial; data = DATAOF_TRACE_ENTRY(entry, false); @@ -861,12 +885,24 @@ typedef bool (*filter_func_t)(struct uprobe_consumer *self, struct mm_struct *mm); static int -probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter) +probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file, + filter_func_t filter) { - int ret = 0; + bool enabled = trace_probe_is_enabled(&tu->tp); + struct event_file_link *link = NULL; + int ret; + + if (file) { + link = kmalloc(sizeof(*link), GFP_KERNEL); + if (!link) + return -ENOMEM; - if (trace_probe_is_enabled(&tu->tp)) - return -EINTR; + link->file = file; + list_add_tail_rcu(&link->list, &tu->tp.files); + + tu->tp.flags |= TP_FLAG_TRACE; + } else + tu->tp.flags |= TP_FLAG_PROFILE; ret = uprobe_buffer_enable(); if (ret < 0) @@ -874,24 +910,49 @@ probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter) WARN_ON(!uprobe_filter_is_empty(&tu->filter)); - tu->tp.flags |= flag; + if (enabled) + return 0; + tu->consumer.filter = filter; ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); - if (ret) - tu->tp.flags &= ~flag; + if (ret) { + if (file) { + list_del(&link->list); + kfree(link); + tu->tp.flags &= ~TP_FLAG_TRACE; + } else + tu->tp.flags &= ~TP_FLAG_PROFILE; + } return ret; } -static void probe_event_disable(struct trace_uprobe *tu, int flag) +static void +probe_event_disable(struct trace_uprobe *tu, struct ftrace_event_file *file) { if (!trace_probe_is_enabled(&tu->tp)) return; + if (file) { + struct event_file_link *link; + + link = find_event_file_link(&tu->tp, file); + if (!link) + return; + + list_del_rcu(&link->list); + /* synchronize with u{,ret}probe_trace_func */ + synchronize_sched(); + kfree(link); + + if (!list_empty(&tu->tp.files)) + return; + } + WARN_ON(!uprobe_filter_is_empty(&tu->filter)); uprobe_unregister(tu->inode, tu->offset, &tu->consumer); - tu->tp.flags &= ~flag; + tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE; uprobe_buffer_disable(); } @@ -1014,31 +1075,24 @@ static bool uprobe_perf_filter(struct uprobe_consumer *uc, return ret; } -static void uprobe_perf_print(struct trace_uprobe *tu, - unsigned long func, struct pt_regs *regs) +static void __uprobe_perf_func(struct trace_uprobe *tu, + unsigned long func, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) { struct ftrace_event_call *call = &tu->tp.call; struct uprobe_trace_entry_head *entry; struct hlist_head *head; - struct uprobe_cpu_buffer *ucb; void *data; - int size, dsize, esize; + int size, esize; int rctx; - dsize = __get_data_size(&tu->tp, regs); esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - if (WARN_ON_ONCE(!uprobe_cpu_buffer)) - return; - size = esize + tu->tp.size + dsize; size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) return; - ucb = uprobe_buffer_get(); - store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize); - preempt_disable(); head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) @@ -1068,46 +1122,49 @@ static void uprobe_perf_print(struct trace_uprobe *tu, perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); out: preempt_enable(); - uprobe_buffer_put(ucb); } /* uprobe profile handler */ -static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) +static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) { if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) return UPROBE_HANDLER_REMOVE; if (!is_ret_probe(tu)) - uprobe_perf_print(tu, 0, regs); + __uprobe_perf_func(tu, 0, regs, ucb, dsize); return 0; } static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, - struct pt_regs *regs) + struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) { - uprobe_perf_print(tu, func, regs); + __uprobe_perf_func(tu, func, regs, ucb, dsize); } #endif /* CONFIG_PERF_EVENTS */ -static -int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, void *data) +static int +trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, + void *data) { struct trace_uprobe *tu = event->data; + struct ftrace_event_file *file = data; switch (type) { case TRACE_REG_REGISTER: - return probe_event_enable(tu, TP_FLAG_TRACE, NULL); + return probe_event_enable(tu, file, NULL); case TRACE_REG_UNREGISTER: - probe_event_disable(tu, TP_FLAG_TRACE); + probe_event_disable(tu, file); return 0; #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: - return probe_event_enable(tu, TP_FLAG_PROFILE, uprobe_perf_filter); + return probe_event_enable(tu, NULL, uprobe_perf_filter); case TRACE_REG_PERF_UNREGISTER: - probe_event_disable(tu, TP_FLAG_PROFILE); + probe_event_disable(tu, NULL); return 0; case TRACE_REG_PERF_OPEN: @@ -1127,8 +1184,11 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) { struct trace_uprobe *tu; struct uprobe_dispatch_data udd; + struct uprobe_cpu_buffer *ucb; + int dsize, esize; int ret = 0; + tu = container_of(con, struct trace_uprobe, consumer); tu->nhit++; @@ -1137,13 +1197,29 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) current->utask->vaddr = (unsigned long) &udd; +#ifdef CONFIG_PERF_EVENTS + if ((tu->tp.flags & TP_FLAG_TRACE) == 0 && + !uprobe_perf_filter(&tu->consumer, 0, current->mm)) + return UPROBE_HANDLER_REMOVE; +#endif + + if (WARN_ON_ONCE(!uprobe_cpu_buffer)) + return 0; + + dsize = __get_data_size(&tu->tp, regs); + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + + ucb = uprobe_buffer_get(); + store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize); + if (tu->tp.flags & TP_FLAG_TRACE) - ret |= uprobe_trace_func(tu, regs); + ret |= uprobe_trace_func(tu, regs, ucb, dsize); #ifdef CONFIG_PERF_EVENTS if (tu->tp.flags & TP_FLAG_PROFILE) - ret |= uprobe_perf_func(tu, regs); + ret |= uprobe_perf_func(tu, regs, ucb, dsize); #endif + uprobe_buffer_put(ucb); return ret; } @@ -1152,6 +1228,8 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con, { struct trace_uprobe *tu; struct uprobe_dispatch_data udd; + struct uprobe_cpu_buffer *ucb; + int dsize, esize; tu = container_of(con, struct trace_uprobe, consumer); @@ -1160,13 +1238,23 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con, current->utask->vaddr = (unsigned long) &udd; + if (WARN_ON_ONCE(!uprobe_cpu_buffer)) + return 0; + + dsize = __get_data_size(&tu->tp, regs); + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + + ucb = uprobe_buffer_get(); + store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize); + if (tu->tp.flags & TP_FLAG_TRACE) - uretprobe_trace_func(tu, func, regs); + uretprobe_trace_func(tu, func, regs, ucb, dsize); #ifdef CONFIG_PERF_EVENTS if (tu->tp.flags & TP_FLAG_PROFILE) - uretprobe_perf_func(tu, func, regs); + uretprobe_perf_func(tu, func, regs, ucb, dsize); #endif + uprobe_buffer_put(ucb); return 0; } @@ -1198,7 +1286,8 @@ static int register_uprobe_event(struct trace_uprobe *tu) ret = trace_add_event_call(call); if (ret) { - pr_info("Failed to register uprobe event: %s\n", call->name); + pr_info("Failed to register uprobe event: %s\n", + ftrace_event_name(call)); kfree(call->print_fmt); unregister_ftrace_event(&call->event); } diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 031cc5655a51..ac5b23cf7212 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2008 Mathieu Desnoyers + * Copyright (C) 2008-2014 Mathieu Desnoyers * * 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 @@ -33,43 +33,29 @@ extern struct tracepoint * const __stop___tracepoints_ptrs[]; /* Set to 1 to enable tracepoint debug output */ static const int tracepoint_debug; +#ifdef CONFIG_MODULES /* - * Tracepoints mutex protects the builtin and module tracepoints and the hash - * table, as well as the local module list. + * Tracepoint module list mutex protects the local module list. */ -static DEFINE_MUTEX(tracepoints_mutex); +static DEFINE_MUTEX(tracepoint_module_list_mutex); -#ifdef CONFIG_MODULES -/* Local list of struct module */ +/* Local list of struct tp_module */ static LIST_HEAD(tracepoint_module_list); #endif /* CONFIG_MODULES */ /* - * Tracepoint hash table, containing the active tracepoints. - * Protected by tracepoints_mutex. + * tracepoints_mutex protects the builtin and module tracepoints. + * tracepoints_mutex nests inside tracepoint_module_list_mutex. */ -#define TRACEPOINT_HASH_BITS 6 -#define TRACEPOINT_TABLE_SIZE (1 << TRACEPOINT_HASH_BITS) -static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE]; +static DEFINE_MUTEX(tracepoints_mutex); /* * Note about RCU : * It is used to delay the free of multiple probes array until a quiescent * state is reached. - * Tracepoint entries modifications are protected by the tracepoints_mutex. */ -struct tracepoint_entry { - struct hlist_node hlist; - struct tracepoint_func *funcs; - int refcount; /* Number of times armed. 0 if disarmed. */ - char name[0]; -}; - struct tp_probes { - union { - struct rcu_head rcu; - struct list_head list; - } u; + struct rcu_head rcu; struct tracepoint_func probes[0]; }; @@ -82,7 +68,7 @@ static inline void *allocate_probes(int count) static void rcu_free_old_probes(struct rcu_head *head) { - kfree(container_of(head, struct tp_probes, u.rcu)); + kfree(container_of(head, struct tp_probes, rcu)); } static inline void release_probes(struct tracepoint_func *old) @@ -90,38 +76,37 @@ static inline void release_probes(struct tracepoint_func *old) if (old) { struct tp_probes *tp_probes = container_of(old, struct tp_probes, probes[0]); - call_rcu_sched(&tp_probes->u.rcu, rcu_free_old_probes); + call_rcu_sched(&tp_probes->rcu, rcu_free_old_probes); } } -static void debug_print_probes(struct tracepoint_entry *entry) +static void debug_print_probes(struct tracepoint_func *funcs) { int i; - if (!tracepoint_debug || !entry->funcs) + if (!tracepoint_debug || !funcs) return; - for (i = 0; entry->funcs[i].func; i++) - printk(KERN_DEBUG "Probe %d : %p\n", i, entry->funcs[i].func); + for (i = 0; funcs[i].func; i++) + printk(KERN_DEBUG "Probe %d : %p\n", i, funcs[i].func); } -static struct tracepoint_func * -tracepoint_entry_add_probe(struct tracepoint_entry *entry, - void *probe, void *data) +static struct tracepoint_func *func_add(struct tracepoint_func **funcs, + struct tracepoint_func *tp_func) { int nr_probes = 0; struct tracepoint_func *old, *new; - if (WARN_ON(!probe)) + if (WARN_ON(!tp_func->func)) return ERR_PTR(-EINVAL); - debug_print_probes(entry); - old = entry->funcs; + debug_print_probes(*funcs); + old = *funcs; if (old) { /* (N -> N+1), (N != 0, 1) probes */ for (nr_probes = 0; old[nr_probes].func; nr_probes++) - if (old[nr_probes].func == probe && - old[nr_probes].data == data) + if (old[nr_probes].func == tp_func->func && + old[nr_probes].data == tp_func->data) return ERR_PTR(-EEXIST); } /* + 2 : one for new probe, one for NULL func */ @@ -130,33 +115,30 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, return ERR_PTR(-ENOMEM); if (old) memcpy(new, old, nr_probes * sizeof(struct tracepoint_func)); - new[nr_probes].func = probe; - new[nr_probes].data = data; + new[nr_probes] = *tp_func; new[nr_probes + 1].func = NULL; - entry->refcount = nr_probes + 1; - entry->funcs = new; - debug_print_probes(entry); + *funcs = new; + debug_print_probes(*funcs); return old; } -static void * -tracepoint_entry_remove_probe(struct tracepoint_entry *entry, - void *probe, void *data) +static void *func_remove(struct tracepoint_func **funcs, + struct tracepoint_func *tp_func) { int nr_probes = 0, nr_del = 0, i; struct tracepoint_func *old, *new; - old = entry->funcs; + old = *funcs; if (!old) return ERR_PTR(-ENOENT); - debug_print_probes(entry); + debug_print_probes(*funcs); /* (N -> M), (N > 1, M >= 0) probes */ - if (probe) { + if (tp_func->func) { for (nr_probes = 0; old[nr_probes].func; nr_probes++) { - if (old[nr_probes].func == probe && - old[nr_probes].data == data) + if (old[nr_probes].func == tp_func->func && + old[nr_probes].data == tp_func->data) nr_del++; } } @@ -167,9 +149,8 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, */ if (nr_probes - nr_del == 0) { /* N -> 0, (N > 1) */ - entry->funcs = NULL; - entry->refcount = 0; - debug_print_probes(entry); + *funcs = NULL; + debug_print_probes(*funcs); return old; } else { int j = 0; @@ -179,90 +160,35 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, if (new == NULL) return ERR_PTR(-ENOMEM); for (i = 0; old[i].func; i++) - if (old[i].func != probe || old[i].data != data) + if (old[i].func != tp_func->func + || old[i].data != tp_func->data) new[j++] = old[i]; new[nr_probes - nr_del].func = NULL; - entry->refcount = nr_probes - nr_del; - entry->funcs = new; + *funcs = new; } - debug_print_probes(entry); + debug_print_probes(*funcs); return old; } /* - * Get tracepoint if the tracepoint is present in the tracepoint hash table. - * Must be called with tracepoints_mutex held. - * Returns NULL if not present. + * Add the probe function to a tracepoint. */ -static struct tracepoint_entry *get_tracepoint(const char *name) +static int tracepoint_add_func(struct tracepoint *tp, + struct tracepoint_func *func) { - struct hlist_head *head; - struct tracepoint_entry *e; - u32 hash = jhash(name, strlen(name), 0); - - head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)]; - hlist_for_each_entry(e, head, hlist) { - if (!strcmp(name, e->name)) - return e; - } - return NULL; -} + struct tracepoint_func *old, *tp_funcs; -/* - * Add the tracepoint to the tracepoint hash table. Must be called with - * tracepoints_mutex held. - */ -static struct tracepoint_entry *add_tracepoint(const char *name) -{ - struct hlist_head *head; - struct tracepoint_entry *e; - size_t name_len = strlen(name) + 1; - u32 hash = jhash(name, name_len-1, 0); - - head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)]; - hlist_for_each_entry(e, head, hlist) { - if (!strcmp(name, e->name)) { - printk(KERN_NOTICE - "tracepoint %s busy\n", name); - return ERR_PTR(-EEXIST); /* Already there */ - } - } - /* - * Using kmalloc here to allocate a variable length element. Could - * cause some memory fragmentation if overused. - */ - e = kmalloc(sizeof(struct tracepoint_entry) + name_len, GFP_KERNEL); - if (!e) - return ERR_PTR(-ENOMEM); - memcpy(&e->name[0], name, name_len); - e->funcs = NULL; - e->refcount = 0; - hlist_add_head(&e->hlist, head); - return e; -} - -/* - * Remove the tracepoint from the tracepoint hash table. Must be called with - * mutex_lock held. - */ -static inline void remove_tracepoint(struct tracepoint_entry *e) -{ - hlist_del(&e->hlist); - kfree(e); -} - -/* - * Sets the probe callback corresponding to one tracepoint. - */ -static void set_tracepoint(struct tracepoint_entry **entry, - struct tracepoint *elem, int active) -{ - WARN_ON(strcmp((*entry)->name, elem->name) != 0); + if (tp->regfunc && !static_key_enabled(&tp->key)) + tp->regfunc(); - if (elem->regfunc && !static_key_enabled(&elem->key) && active) - elem->regfunc(); - else if (elem->unregfunc && static_key_enabled(&elem->key) && !active) - elem->unregfunc(); + tp_funcs = rcu_dereference_protected(tp->funcs, + lockdep_is_held(&tracepoints_mutex)); + old = func_add(&tp_funcs, func); + if (IS_ERR(old)) { + WARN_ON_ONCE(1); + return PTR_ERR(old); + } + release_probes(old); /* * rcu_assign_pointer has a smp_wmb() which makes sure that the new @@ -271,426 +197,215 @@ static void set_tracepoint(struct tracepoint_entry **entry, * include/linux/tracepoints.h. A matching smp_read_barrier_depends() * is used. */ - rcu_assign_pointer(elem->funcs, (*entry)->funcs); - if (active && !static_key_enabled(&elem->key)) - static_key_slow_inc(&elem->key); - else if (!active && static_key_enabled(&elem->key)) - static_key_slow_dec(&elem->key); + rcu_assign_pointer(tp->funcs, tp_funcs); + if (!static_key_enabled(&tp->key)) + static_key_slow_inc(&tp->key); + return 0; } /* - * Disable a tracepoint and its probe callback. + * Remove a probe function from a tracepoint. * Note: only waiting an RCU period after setting elem->call to the empty * function insures that the original callback is not used anymore. This insured * by preempt_disable around the call site. */ -static void disable_tracepoint(struct tracepoint *elem) +static int tracepoint_remove_func(struct tracepoint *tp, + struct tracepoint_func *func) { - if (elem->unregfunc && static_key_enabled(&elem->key)) - elem->unregfunc(); + struct tracepoint_func *old, *tp_funcs; - if (static_key_enabled(&elem->key)) - static_key_slow_dec(&elem->key); - rcu_assign_pointer(elem->funcs, NULL); -} - -/** - * tracepoint_update_probe_range - Update a probe range - * @begin: beginning of the range - * @end: end of the range - * - * Updates the probe callback corresponding to a range of tracepoints. - * Called with tracepoints_mutex held. - */ -static void tracepoint_update_probe_range(struct tracepoint * const *begin, - struct tracepoint * const *end) -{ - struct tracepoint * const *iter; - struct tracepoint_entry *mark_entry; - - if (!begin) - return; - - for (iter = begin; iter < end; iter++) { - mark_entry = get_tracepoint((*iter)->name); - if (mark_entry) { - set_tracepoint(&mark_entry, *iter, - !!mark_entry->refcount); - } else { - disable_tracepoint(*iter); - } + tp_funcs = rcu_dereference_protected(tp->funcs, + lockdep_is_held(&tracepoints_mutex)); + old = func_remove(&tp_funcs, func); + if (IS_ERR(old)) { + WARN_ON_ONCE(1); + return PTR_ERR(old); } -} - -#ifdef CONFIG_MODULES -void module_update_tracepoints(void) -{ - struct tp_module *tp_mod; - - list_for_each_entry(tp_mod, &tracepoint_module_list, list) - tracepoint_update_probe_range(tp_mod->tracepoints_ptrs, - tp_mod->tracepoints_ptrs + tp_mod->num_tracepoints); -} -#else /* CONFIG_MODULES */ -void module_update_tracepoints(void) -{ -} -#endif /* CONFIG_MODULES */ - + release_probes(old); -/* - * Update probes, removing the faulty probes. - * Called with tracepoints_mutex held. - */ -static void tracepoint_update_probes(void) -{ - /* Core kernel tracepoints */ - tracepoint_update_probe_range(__start___tracepoints_ptrs, - __stop___tracepoints_ptrs); - /* tracepoints in modules. */ - module_update_tracepoints(); -} + if (!tp_funcs) { + /* Removed last function */ + if (tp->unregfunc && static_key_enabled(&tp->key)) + tp->unregfunc(); -static struct tracepoint_func * -tracepoint_add_probe(const char *name, void *probe, void *data) -{ - struct tracepoint_entry *entry; - struct tracepoint_func *old; - - entry = get_tracepoint(name); - if (!entry) { - entry = add_tracepoint(name); - if (IS_ERR(entry)) - return (struct tracepoint_func *)entry; + if (static_key_enabled(&tp->key)) + static_key_slow_dec(&tp->key); } - old = tracepoint_entry_add_probe(entry, probe, data); - if (IS_ERR(old) && !entry->refcount) - remove_tracepoint(entry); - return old; + rcu_assign_pointer(tp->funcs, tp_funcs); + return 0; } /** * tracepoint_probe_register - Connect a probe to a tracepoint - * @name: tracepoint name + * @tp: tracepoint * @probe: probe handler * * Returns 0 if ok, error value on error. - * The probe address must at least be aligned on the architecture pointer size. + * Note: if @tp is within a module, the caller is responsible for + * unregistering the probe before the module is gone. This can be + * performed either with a tracepoint module going notifier, or from + * within module exit functions. */ -int tracepoint_probe_register(const char *name, void *probe, void *data) +int tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data) { - struct tracepoint_func *old; + struct tracepoint_func tp_func; + int ret; mutex_lock(&tracepoints_mutex); - old = tracepoint_add_probe(name, probe, data); - if (IS_ERR(old)) { - mutex_unlock(&tracepoints_mutex); - return PTR_ERR(old); - } - tracepoint_update_probes(); /* may update entry */ + tp_func.func = probe; + tp_func.data = data; + ret = tracepoint_add_func(tp, &tp_func); mutex_unlock(&tracepoints_mutex); - release_probes(old); - return 0; + return ret; } EXPORT_SYMBOL_GPL(tracepoint_probe_register); -static struct tracepoint_func * -tracepoint_remove_probe(const char *name, void *probe, void *data) -{ - struct tracepoint_entry *entry; - struct tracepoint_func *old; - - entry = get_tracepoint(name); - if (!entry) - return ERR_PTR(-ENOENT); - old = tracepoint_entry_remove_probe(entry, probe, data); - if (IS_ERR(old)) - return old; - if (!entry->refcount) - remove_tracepoint(entry); - return old; -} - /** * tracepoint_probe_unregister - Disconnect a probe from a tracepoint - * @name: tracepoint name + * @tp: tracepoint * @probe: probe function pointer * - * We do not need to call a synchronize_sched to make sure the probes have - * finished running before doing a module unload, because the module unload - * itself uses stop_machine(), which insures that every preempt disabled section - * have finished. + * Returns 0 if ok, error value on error. */ -int tracepoint_probe_unregister(const char *name, void *probe, void *data) +int tracepoint_probe_unregister(struct tracepoint *tp, void *probe, void *data) { - struct tracepoint_func *old; + struct tracepoint_func tp_func; + int ret; mutex_lock(&tracepoints_mutex); - old = tracepoint_remove_probe(name, probe, data); - if (IS_ERR(old)) { - mutex_unlock(&tracepoints_mutex); - return PTR_ERR(old); - } - tracepoint_update_probes(); /* may update entry */ + tp_func.func = probe; + tp_func.data = data; + ret = tracepoint_remove_func(tp, &tp_func); mutex_unlock(&tracepoints_mutex); - release_probes(old); - return 0; + return ret; } EXPORT_SYMBOL_GPL(tracepoint_probe_unregister); -static LIST_HEAD(old_probes); -static int need_update; - -static void tracepoint_add_old_probes(void *old) +#ifdef CONFIG_MODULES +bool trace_module_has_bad_taint(struct module *mod) { - need_update = 1; - if (old) { - struct tp_probes *tp_probes = container_of(old, - struct tp_probes, probes[0]); - list_add(&tp_probes->u.list, &old_probes); - } + return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP) | + (1 << TAINT_UNSIGNED_MODULE)); } -/** - * tracepoint_probe_register_noupdate - register a probe but not connect - * @name: tracepoint name - * @probe: probe handler - * - * caller must call tracepoint_probe_update_all() - */ -int tracepoint_probe_register_noupdate(const char *name, void *probe, - void *data) -{ - struct tracepoint_func *old; - - mutex_lock(&tracepoints_mutex); - old = tracepoint_add_probe(name, probe, data); - if (IS_ERR(old)) { - mutex_unlock(&tracepoints_mutex); - return PTR_ERR(old); - } - tracepoint_add_old_probes(old); - mutex_unlock(&tracepoints_mutex); - return 0; -} -EXPORT_SYMBOL_GPL(tracepoint_probe_register_noupdate); +static BLOCKING_NOTIFIER_HEAD(tracepoint_notify_list); /** - * tracepoint_probe_unregister_noupdate - remove a probe but not disconnect - * @name: tracepoint name - * @probe: probe function pointer + * register_tracepoint_notifier - register tracepoint coming/going notifier + * @nb: notifier block * - * caller must call tracepoint_probe_update_all() + * Notifiers registered with this function are called on module + * coming/going with the tracepoint_module_list_mutex held. + * The notifier block callback should expect a "struct tp_module" data + * pointer. */ -int tracepoint_probe_unregister_noupdate(const char *name, void *probe, - void *data) +int register_tracepoint_module_notifier(struct notifier_block *nb) { - struct tracepoint_func *old; - - mutex_lock(&tracepoints_mutex); - old = tracepoint_remove_probe(name, probe, data); - if (IS_ERR(old)) { - mutex_unlock(&tracepoints_mutex); - return PTR_ERR(old); - } - tracepoint_add_old_probes(old); - mutex_unlock(&tracepoints_mutex); - return 0; -} -EXPORT_SYMBOL_GPL(tracepoint_probe_unregister_noupdate); - -/** - * tracepoint_probe_update_all - update tracepoints - */ -void tracepoint_probe_update_all(void) -{ - LIST_HEAD(release_probes); - struct tp_probes *pos, *next; + struct tp_module *tp_mod; + int ret; - mutex_lock(&tracepoints_mutex); - if (!need_update) { - mutex_unlock(&tracepoints_mutex); - return; - } - if (!list_empty(&old_probes)) - list_replace_init(&old_probes, &release_probes); - need_update = 0; - tracepoint_update_probes(); - mutex_unlock(&tracepoints_mutex); - list_for_each_entry_safe(pos, next, &release_probes, u.list) { - list_del(&pos->u.list); - call_rcu_sched(&pos->u.rcu, rcu_free_old_probes); - } + mutex_lock(&tracepoint_module_list_mutex); + ret = blocking_notifier_chain_register(&tracepoint_notify_list, nb); + if (ret) + goto end; + list_for_each_entry(tp_mod, &tracepoint_module_list, list) + (void) nb->notifier_call(nb, MODULE_STATE_COMING, tp_mod); +end: + mutex_unlock(&tracepoint_module_list_mutex); + return ret; } -EXPORT_SYMBOL_GPL(tracepoint_probe_update_all); +EXPORT_SYMBOL_GPL(register_tracepoint_module_notifier); /** - * tracepoint_get_iter_range - Get a next tracepoint iterator given a range. - * @tracepoint: current tracepoints (in), next tracepoint (out) - * @begin: beginning of the range - * @end: end of the range + * unregister_tracepoint_notifier - unregister tracepoint coming/going notifier + * @nb: notifier block * - * Returns whether a next tracepoint has been found (1) or not (0). - * Will return the first tracepoint in the range if the input tracepoint is - * NULL. + * The notifier block callback should expect a "struct tp_module" data + * pointer. */ -static int tracepoint_get_iter_range(struct tracepoint * const **tracepoint, - struct tracepoint * const *begin, struct tracepoint * const *end) +int unregister_tracepoint_module_notifier(struct notifier_block *nb) { - if (!*tracepoint && begin != end) { - *tracepoint = begin; - return 1; - } - if (*tracepoint >= begin && *tracepoint < end) - return 1; - return 0; -} + struct tp_module *tp_mod; + int ret; -#ifdef CONFIG_MODULES -static void tracepoint_get_iter(struct tracepoint_iter *iter) -{ - int found = 0; - struct tp_module *iter_mod; - - /* Core kernel tracepoints */ - if (!iter->module) { - found = tracepoint_get_iter_range(&iter->tracepoint, - __start___tracepoints_ptrs, - __stop___tracepoints_ptrs); - if (found) - goto end; - } - /* Tracepoints in modules */ - mutex_lock(&tracepoints_mutex); - list_for_each_entry(iter_mod, &tracepoint_module_list, list) { - /* - * Sorted module list - */ - if (iter_mod < iter->module) - continue; - else if (iter_mod > iter->module) - iter->tracepoint = NULL; - found = tracepoint_get_iter_range(&iter->tracepoint, - iter_mod->tracepoints_ptrs, - iter_mod->tracepoints_ptrs - + iter_mod->num_tracepoints); - if (found) { - iter->module = iter_mod; - break; - } - } - mutex_unlock(&tracepoints_mutex); + mutex_lock(&tracepoint_module_list_mutex); + ret = blocking_notifier_chain_unregister(&tracepoint_notify_list, nb); + if (ret) + goto end; + list_for_each_entry(tp_mod, &tracepoint_module_list, list) + (void) nb->notifier_call(nb, MODULE_STATE_GOING, tp_mod); end: - if (!found) - tracepoint_iter_reset(iter); -} -#else /* CONFIG_MODULES */ -static void tracepoint_get_iter(struct tracepoint_iter *iter) -{ - int found = 0; - - /* Core kernel tracepoints */ - found = tracepoint_get_iter_range(&iter->tracepoint, - __start___tracepoints_ptrs, - __stop___tracepoints_ptrs); - if (!found) - tracepoint_iter_reset(iter); -} -#endif /* CONFIG_MODULES */ - -void tracepoint_iter_start(struct tracepoint_iter *iter) -{ - tracepoint_get_iter(iter); -} -EXPORT_SYMBOL_GPL(tracepoint_iter_start); - -void tracepoint_iter_next(struct tracepoint_iter *iter) -{ - iter->tracepoint++; - /* - * iter->tracepoint may be invalid because we blindly incremented it. - * Make sure it is valid by marshalling on the tracepoints, getting the - * tracepoints from following modules if necessary. - */ - tracepoint_get_iter(iter); -} -EXPORT_SYMBOL_GPL(tracepoint_iter_next); + mutex_unlock(&tracepoint_module_list_mutex); + return ret; -void tracepoint_iter_stop(struct tracepoint_iter *iter) -{ } -EXPORT_SYMBOL_GPL(tracepoint_iter_stop); +EXPORT_SYMBOL_GPL(unregister_tracepoint_module_notifier); -void tracepoint_iter_reset(struct tracepoint_iter *iter) +/* + * Ensure the tracer unregistered the module's probes before the module + * teardown is performed. Prevents leaks of probe and data pointers. + */ +static void tp_module_going_check_quiescent(struct tracepoint * const *begin, + struct tracepoint * const *end) { -#ifdef CONFIG_MODULES - iter->module = NULL; -#endif /* CONFIG_MODULES */ - iter->tracepoint = NULL; -} -EXPORT_SYMBOL_GPL(tracepoint_iter_reset); + struct tracepoint * const *iter; -#ifdef CONFIG_MODULES -bool trace_module_has_bad_taint(struct module *mod) -{ - return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)); + if (!begin) + return; + for (iter = begin; iter < end; iter++) + WARN_ON_ONCE((*iter)->funcs); } static int tracepoint_module_coming(struct module *mod) { - struct tp_module *tp_mod, *iter; + struct tp_module *tp_mod; int ret = 0; + if (!mod->num_tracepoints) + return 0; + /* * We skip modules that taint the kernel, especially those with different * module headers (for forced load), to make sure we don't cause a crash. - * Staging and out-of-tree GPL modules are fine. + * Staging, out-of-tree, and unsigned GPL modules are fine. */ if (trace_module_has_bad_taint(mod)) return 0; - mutex_lock(&tracepoints_mutex); + mutex_lock(&tracepoint_module_list_mutex); tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL); if (!tp_mod) { ret = -ENOMEM; goto end; } - tp_mod->num_tracepoints = mod->num_tracepoints; - tp_mod->tracepoints_ptrs = mod->tracepoints_ptrs; - - /* - * tracepoint_module_list is kept sorted by struct module pointer - * address for iteration on tracepoints from a seq_file that can release - * the mutex between calls. - */ - list_for_each_entry_reverse(iter, &tracepoint_module_list, list) { - BUG_ON(iter == tp_mod); /* Should never be in the list twice */ - if (iter < tp_mod) { - /* We belong to the location right after iter. */ - list_add(&tp_mod->list, &iter->list); - goto module_added; - } - } - /* We belong to the beginning of the list */ - list_add(&tp_mod->list, &tracepoint_module_list); -module_added: - tracepoint_update_probe_range(mod->tracepoints_ptrs, - mod->tracepoints_ptrs + mod->num_tracepoints); + tp_mod->mod = mod; + list_add_tail(&tp_mod->list, &tracepoint_module_list); + blocking_notifier_call_chain(&tracepoint_notify_list, + MODULE_STATE_COMING, tp_mod); end: - mutex_unlock(&tracepoints_mutex); + mutex_unlock(&tracepoint_module_list_mutex); return ret; } -static int tracepoint_module_going(struct module *mod) +static void tracepoint_module_going(struct module *mod) { - struct tp_module *pos; + struct tp_module *tp_mod; - mutex_lock(&tracepoints_mutex); - tracepoint_update_probe_range(mod->tracepoints_ptrs, - mod->tracepoints_ptrs + mod->num_tracepoints); - list_for_each_entry(pos, &tracepoint_module_list, list) { - if (pos->tracepoints_ptrs == mod->tracepoints_ptrs) { - list_del(&pos->list); - kfree(pos); + if (!mod->num_tracepoints) + return; + + mutex_lock(&tracepoint_module_list_mutex); + list_for_each_entry(tp_mod, &tracepoint_module_list, list) { + if (tp_mod->mod == mod) { + blocking_notifier_call_chain(&tracepoint_notify_list, + MODULE_STATE_GOING, tp_mod); + list_del(&tp_mod->list); + kfree(tp_mod); + /* + * Called the going notifier before checking for + * quiescence. + */ + tp_module_going_check_quiescent(mod->tracepoints_ptrs, + mod->tracepoints_ptrs + mod->num_tracepoints); break; } } @@ -700,12 +415,11 @@ static int tracepoint_module_going(struct module *mod) * flag on "going", in case a module taints the kernel only after being * loaded. */ - mutex_unlock(&tracepoints_mutex); - return 0; + mutex_unlock(&tracepoint_module_list_mutex); } -int tracepoint_module_notify(struct notifier_block *self, - unsigned long val, void *data) +static int tracepoint_module_notify(struct notifier_block *self, + unsigned long val, void *data) { struct module *mod = data; int ret = 0; @@ -717,24 +431,58 @@ int tracepoint_module_notify(struct notifier_block *self, case MODULE_STATE_LIVE: break; case MODULE_STATE_GOING: - ret = tracepoint_module_going(mod); + tracepoint_module_going(mod); + break; + case MODULE_STATE_UNFORMED: break; } return ret; } -struct notifier_block tracepoint_module_nb = { +static struct notifier_block tracepoint_module_nb = { .notifier_call = tracepoint_module_notify, .priority = 0, }; -static int init_tracepoints(void) +static __init int init_tracepoints(void) { - return register_module_notifier(&tracepoint_module_nb); + int ret; + + ret = register_module_notifier(&tracepoint_module_nb); + if (ret) + pr_warning("Failed to register tracepoint module enter notifier\n"); + + return ret; } __initcall(init_tracepoints); #endif /* CONFIG_MODULES */ +static void for_each_tracepoint_range(struct tracepoint * const *begin, + struct tracepoint * const *end, + void (*fct)(struct tracepoint *tp, void *priv), + void *priv) +{ + struct tracepoint * const *iter; + + if (!begin) + return; + for (iter = begin; iter < end; iter++) + fct(*iter, priv); +} + +/** + * for_each_kernel_tracepoint - iteration on all kernel tracepoints + * @fct: callback + * @priv: private data + */ +void for_each_kernel_tracepoint(void (*fct)(struct tracepoint *tp, void *priv), + void *priv) +{ + for_each_tracepoint_range(__start___tracepoints_ptrs, + __stop___tracepoints_ptrs, fct, priv); +} +EXPORT_SYMBOL_GPL(for_each_kernel_tracepoint); + #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS /* NB: reg/unreg are called while guarded with the tracepoints_mutex */ diff --git a/kernel/user.c b/kernel/user.c index c006131beb77..294fc6a94168 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -222,5 +222,4 @@ static int __init uid_cache_init(void) return 0; } - -module_init(uid_cache_init); +subsys_initcall(uid_cache_init); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index dd06439b9c84..bf71b4b2d632 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -152,7 +152,7 @@ static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count) /* Find the matching extent */ extents = map->nr_extents; - smp_read_barrier_depends(); + smp_rmb(); for (idx = 0; idx < extents; idx++) { first = map->extent[idx].first; last = first + map->extent[idx].count - 1; @@ -176,7 +176,7 @@ static u32 map_id_down(struct uid_gid_map *map, u32 id) /* Find the matching extent */ extents = map->nr_extents; - smp_read_barrier_depends(); + smp_rmb(); for (idx = 0; idx < extents; idx++) { first = map->extent[idx].first; last = first + map->extent[idx].count - 1; @@ -199,7 +199,7 @@ static u32 map_id_up(struct uid_gid_map *map, u32 id) /* Find the matching extent */ extents = map->nr_extents; - smp_read_barrier_depends(); + smp_rmb(); for (idx = 0; idx < extents; idx++) { first = map->extent[idx].lower_first; last = first + map->extent[idx].count - 1; @@ -615,9 +615,8 @@ static ssize_t map_write(struct file *file, const char __user *buf, * were written before the count of the extents. * * To achieve this smp_wmb() is used on guarantee the write - * order and smp_read_barrier_depends() is guaranteed that we - * don't have crazy architectures returning stale data. - * + * order and smp_rmb() is guaranteed that we don't have crazy + * architectures returning stale data. */ mutex_lock(&id_map_mutex); @@ -902,4 +901,4 @@ static __init int user_namespaces_init(void) user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC); return 0; } -module_init(user_namespaces_init); +subsys_initcall(user_namespaces_init); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 01c6f979486f..516203e665fc 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -138,7 +138,11 @@ static void __touch_watchdog(void) void touch_softlockup_watchdog(void) { - __this_cpu_write(watchdog_touch_ts, 0); + /* + * Preemption can be enabled. It doesn't matter which CPU's timestamp + * gets zeroed here, so use the raw_ operation. + */ + raw_cpu_write(watchdog_touch_ts, 0); } EXPORT_SYMBOL(touch_softlockup_watchdog); @@ -158,14 +162,14 @@ void touch_all_softlockup_watchdogs(void) #ifdef CONFIG_HARDLOCKUP_DETECTOR void touch_nmi_watchdog(void) { - if (watchdog_user_enabled) { - unsigned cpu; - - for_each_present_cpu(cpu) { - if (per_cpu(watchdog_nmi_touch, cpu) != true) - per_cpu(watchdog_nmi_touch, cpu) = true; - } - } + /* + * Using __raw here because some code paths have + * preemption enabled. If preemption is enabled + * then interrupts should be enabled too, in which + * case we shouldn't have to worry about the watchdog + * going off. + */ + __raw_get_cpu_var(watchdog_nmi_touch) = true; touch_softlockup_watchdog(); } EXPORT_SYMBOL(touch_nmi_watchdog); |