diff options
Diffstat (limited to 'kernel')
61 files changed, 5545 insertions, 1606 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 82fb182f6f6..47dbcd570cd 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -8,10 +8,15 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o profile.o \ signal.o sys.o kmod.o workqueue.o pid.o \ rcupdate.o extable.o params.o posix-timers.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ - hrtimer.o + hrtimer.o rwsem.o +obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o +obj-$(CONFIG_LOCKDEP) += lockdep.o +ifeq ($(CONFIG_PROC_FS),y) +obj-$(CONFIG_LOCKDEP) += lockdep_proc.o +endif obj-$(CONFIG_FUTEX) += futex.o ifeq ($(CONFIG_COMPAT),y) obj-$(CONFIG_FUTEX) += futex_compat.o @@ -22,6 +27,7 @@ obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o obj-$(CONFIG_SMP) += cpu.o spinlock.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o +obj-$(CONFIG_PROVE_LOCKING) += spinlock.o obj-$(CONFIG_UID16) += uid16.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_KALLSYMS) += kallsyms.o diff --git a/kernel/acct.c b/kernel/acct.c index 126ca43d5d2..f18e0b8df3e 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -43,7 +43,6 @@ * a struct file opened for write. Fixed. 2/6/2000, AV. */ -#include <linux/config.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/acct.h> diff --git a/kernel/audit.c b/kernel/audit.c index 82443fb433e..d417ca1db79 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -445,7 +445,7 @@ void audit_send_reply(int pid, int seq, int type, int done, int multi, * Check for appropriate CAP_AUDIT_ capabilities on incoming audit * control messages. */ -static int audit_netlink_ok(kernel_cap_t eff_cap, u16 msg_type) +static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) { int err = 0; @@ -459,13 +459,13 @@ static int audit_netlink_ok(kernel_cap_t eff_cap, u16 msg_type) case AUDIT_DEL: case AUDIT_DEL_RULE: case AUDIT_SIGNAL_INFO: - if (!cap_raised(eff_cap, CAP_AUDIT_CONTROL)) + if (security_netlink_recv(skb, CAP_AUDIT_CONTROL)) err = -EPERM; break; case AUDIT_USER: case AUDIT_FIRST_USER_MSG...AUDIT_LAST_USER_MSG: case AUDIT_FIRST_USER_MSG2...AUDIT_LAST_USER_MSG2: - if (!cap_raised(eff_cap, CAP_AUDIT_WRITE)) + if (security_netlink_recv(skb, CAP_AUDIT_WRITE)) err = -EPERM; break; default: /* bad msg */ @@ -488,7 +488,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) char *ctx; u32 len; - err = audit_netlink_ok(NETLINK_CB(skb).eff_cap, msg_type); + err = audit_netlink_ok(skb, msg_type); if (err) return err; diff --git a/kernel/audit.h b/kernel/audit.h index 8323e4132a3..6aa33b848cf 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -81,6 +81,7 @@ struct audit_krule { u32 mask[AUDIT_BITMASK_SIZE]; u32 buflen; /* for data alloc on list rules */ u32 field_count; + char *filterkey; /* ties events to rules */ struct audit_field *fields; struct audit_field *inode_f; /* quick access to an inode field */ struct audit_watch *watch; /* associated watch */ diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 4c99d2c586e..5b4e16276ca 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -141,6 +141,7 @@ static inline void audit_free_rule(struct audit_entry *e) selinux_audit_rule_free(f->se_rule); } kfree(e->rule.fields); + kfree(e->rule.filterkey); kfree(e); } @@ -278,6 +279,29 @@ static int audit_to_watch(struct audit_krule *krule, char *path, int len, return 0; } +static __u32 *classes[AUDIT_SYSCALL_CLASSES]; + +int __init audit_register_class(int class, unsigned *list) +{ + __u32 *p = kzalloc(AUDIT_BITMASK_SIZE * sizeof(__u32), GFP_KERNEL); + if (!p) + return -ENOMEM; + while (*list != ~0U) { + unsigned n = *list++; + if (n >= AUDIT_BITMASK_SIZE * 32 - AUDIT_SYSCALL_CLASSES) { + kfree(p); + return -EINVAL; + } + p[AUDIT_WORD(n)] |= AUDIT_BIT(n); + } + if (class >= AUDIT_SYSCALL_CLASSES || classes[class]) { + kfree(p); + return -EINVAL; + } + classes[class] = p; + return 0; +} + /* Common user-space to kernel rule translation. */ static inline struct audit_entry *audit_to_entry_common(struct audit_rule *rule) { @@ -321,6 +345,22 @@ static inline struct audit_entry *audit_to_entry_common(struct audit_rule *rule) for (i = 0; i < AUDIT_BITMASK_SIZE; i++) entry->rule.mask[i] = rule->mask[i]; + for (i = 0; i < AUDIT_SYSCALL_CLASSES; i++) { + int bit = AUDIT_BITMASK_SIZE * 32 - i - 1; + __u32 *p = &entry->rule.mask[AUDIT_WORD(bit)]; + __u32 *class; + + if (!(*p & AUDIT_BIT(bit))) + continue; + *p &= ~AUDIT_BIT(bit); + class = classes[i]; + if (class) { + int j; + for (j = 0; j < AUDIT_BITMASK_SIZE; j++) + entry->rule.mask[j] |= class[j]; + } + } + return entry; exit_err: @@ -469,11 +509,16 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_ARG2: case AUDIT_ARG3: break; - case AUDIT_SE_USER: - case AUDIT_SE_ROLE: - case AUDIT_SE_TYPE: - case AUDIT_SE_SEN: - case AUDIT_SE_CLR: + case AUDIT_SUBJ_USER: + case AUDIT_SUBJ_ROLE: + case AUDIT_SUBJ_TYPE: + case AUDIT_SUBJ_SEN: + case AUDIT_SUBJ_CLR: + case AUDIT_OBJ_USER: + case AUDIT_OBJ_ROLE: + case AUDIT_OBJ_TYPE: + case AUDIT_OBJ_LEV_LOW: + case AUDIT_OBJ_LEV_HIGH: str = audit_unpack_string(&bufp, &remain, f->val); if (IS_ERR(str)) goto exit_free; @@ -511,6 +556,16 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, if (err) goto exit_free; break; + case AUDIT_FILTERKEY: + err = -EINVAL; + if (entry->rule.filterkey || f->val > AUDIT_MAX_KEY_LEN) + goto exit_free; + str = audit_unpack_string(&bufp, &remain, f->val); + if (IS_ERR(str)) + goto exit_free; + entry->rule.buflen += f->val; + entry->rule.filterkey = str; + break; default: goto exit_free; } @@ -600,11 +655,16 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) data->fields[i] = f->type; data->fieldflags[i] = f->op; switch(f->type) { - case AUDIT_SE_USER: - case AUDIT_SE_ROLE: - case AUDIT_SE_TYPE: - case AUDIT_SE_SEN: - case AUDIT_SE_CLR: + case AUDIT_SUBJ_USER: + case AUDIT_SUBJ_ROLE: + case AUDIT_SUBJ_TYPE: + case AUDIT_SUBJ_SEN: + case AUDIT_SUBJ_CLR: + case AUDIT_OBJ_USER: + case AUDIT_OBJ_ROLE: + case AUDIT_OBJ_TYPE: + case AUDIT_OBJ_LEV_LOW: + case AUDIT_OBJ_LEV_HIGH: data->buflen += data->values[i] = audit_pack_string(&bufp, f->se_str); break; @@ -612,6 +672,10 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) data->buflen += data->values[i] = audit_pack_string(&bufp, krule->watch->path); break; + case AUDIT_FILTERKEY: + data->buflen += data->values[i] = + audit_pack_string(&bufp, krule->filterkey); + break; default: data->values[i] = f->val; } @@ -639,11 +703,16 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) return 1; switch(a->fields[i].type) { - case AUDIT_SE_USER: - case AUDIT_SE_ROLE: - case AUDIT_SE_TYPE: - case AUDIT_SE_SEN: - case AUDIT_SE_CLR: + case AUDIT_SUBJ_USER: + case AUDIT_SUBJ_ROLE: + case AUDIT_SUBJ_TYPE: + case AUDIT_SUBJ_SEN: + case AUDIT_SUBJ_CLR: + case AUDIT_OBJ_USER: + case AUDIT_OBJ_ROLE: + case AUDIT_OBJ_TYPE: + case AUDIT_OBJ_LEV_LOW: + case AUDIT_OBJ_LEV_HIGH: if (strcmp(a->fields[i].se_str, b->fields[i].se_str)) return 1; break; @@ -651,6 +720,11 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) if (strcmp(a->watch->path, b->watch->path)) return 1; break; + case AUDIT_FILTERKEY: + /* both filterkeys exist based on above type compare */ + if (strcmp(a->filterkey, b->filterkey)) + return 1; + break; default: if (a->fields[i].val != b->fields[i].val) return 1; @@ -730,6 +804,7 @@ static struct audit_entry *audit_dupe_rule(struct audit_krule *old, u32 fcount = old->field_count; struct audit_entry *entry; struct audit_krule *new; + char *fk; int i, err = 0; entry = audit_init_entry(fcount); @@ -753,13 +828,25 @@ static struct audit_entry *audit_dupe_rule(struct audit_krule *old, * the originals will all be freed when the old rule is freed. */ for (i = 0; i < fcount; i++) { switch (new->fields[i].type) { - case AUDIT_SE_USER: - case AUDIT_SE_ROLE: - case AUDIT_SE_TYPE: - case AUDIT_SE_SEN: - case AUDIT_SE_CLR: + case AUDIT_SUBJ_USER: + case AUDIT_SUBJ_ROLE: + case AUDIT_SUBJ_TYPE: + case AUDIT_SUBJ_SEN: + case AUDIT_SUBJ_CLR: + case AUDIT_OBJ_USER: + case AUDIT_OBJ_ROLE: + case AUDIT_OBJ_TYPE: + case AUDIT_OBJ_LEV_LOW: + case AUDIT_OBJ_LEV_HIGH: err = audit_dupe_selinux_field(&new->fields[i], &old->fields[i]); + break; + case AUDIT_FILTERKEY: + fk = kstrdup(old->filterkey, GFP_KERNEL); + if (unlikely(!fk)) + err = -ENOMEM; + else + new->filterkey = fk; } if (err) { audit_free_rule(entry); @@ -1245,6 +1332,34 @@ static void audit_list_rules(int pid, int seq, struct sk_buff_head *q) skb_queue_tail(q, skb); } +/* Log rule additions and removals */ +static void audit_log_rule_change(uid_t loginuid, u32 sid, char *action, + struct audit_krule *rule, int res) +{ + struct audit_buffer *ab; + + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); + if (!ab) + return; + audit_log_format(ab, "auid=%u", loginuid); + if (sid) { + char *ctx = NULL; + u32 len; + if (selinux_ctxid_to_string(sid, &ctx, &len)) + audit_log_format(ab, " ssid=%u", sid); + else + audit_log_format(ab, " subj=%s", ctx); + kfree(ctx); + } + audit_log_format(ab, " %s rule key=", action); + if (rule->filterkey) + audit_log_untrustedstring(ab, rule->filterkey); + else + audit_log_format(ab, "(null)"); + audit_log_format(ab, " list=%d res=%d", rule->listnr, res); + audit_log_end(ab); +} + /** * audit_receive_filter - apply all rules to the specified message type * @type: audit message type @@ -1304,24 +1419,7 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data, err = audit_add_rule(entry, &audit_filter_list[entry->rule.listnr]); - - if (sid) { - char *ctx = NULL; - u32 len; - if (selinux_ctxid_to_string(sid, &ctx, &len)) { - /* Maybe call audit_panic? */ - audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE, - "auid=%u ssid=%u add rule to list=%d res=%d", - loginuid, sid, entry->rule.listnr, !err); - } else - audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE, - "auid=%u subj=%s add rule to list=%d res=%d", - loginuid, ctx, entry->rule.listnr, !err); - kfree(ctx); - } else - audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE, - "auid=%u add rule to list=%d res=%d", - loginuid, entry->rule.listnr, !err); + audit_log_rule_change(loginuid, sid, "add", &entry->rule, !err); if (err) audit_free_rule(entry); @@ -1337,24 +1435,8 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data, err = audit_del_rule(entry, &audit_filter_list[entry->rule.listnr]); - - if (sid) { - char *ctx = NULL; - u32 len; - if (selinux_ctxid_to_string(sid, &ctx, &len)) { - /* Maybe call audit_panic? */ - audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE, - "auid=%u ssid=%u remove rule from list=%d res=%d", - loginuid, sid, entry->rule.listnr, !err); - } else - audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE, - "auid=%u subj=%s remove rule from list=%d res=%d", - loginuid, ctx, entry->rule.listnr, !err); - kfree(ctx); - } else - audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE, - "auid=%u remove rule from list=%d res=%d", - loginuid, entry->rule.listnr, !err); + audit_log_rule_change(loginuid, sid, "remove", &entry->rule, + !err); audit_free_rule(entry); break; @@ -1514,11 +1596,16 @@ static inline int audit_rule_has_selinux(struct audit_krule *rule) for (i = 0; i < rule->field_count; i++) { struct audit_field *f = &rule->fields[i]; switch (f->type) { - case AUDIT_SE_USER: - case AUDIT_SE_ROLE: - case AUDIT_SE_TYPE: - case AUDIT_SE_SEN: - case AUDIT_SE_CLR: + case AUDIT_SUBJ_USER: + case AUDIT_SUBJ_ROLE: + case AUDIT_SUBJ_TYPE: + case AUDIT_SUBJ_SEN: + case AUDIT_SUBJ_CLR: + case AUDIT_OBJ_USER: + case AUDIT_OBJ_ROLE: + case AUDIT_OBJ_TYPE: + case AUDIT_OBJ_LEV_LOW: + case AUDIT_OBJ_LEV_HIGH: return 1; } } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index dc5e3f01efe..ae40ac8c39e 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -186,6 +186,7 @@ struct audit_context { int auditable; /* 1 if record should be written */ int name_count; struct audit_names names[AUDIT_NAMES]; + char * filterkey; /* key for rule that triggered record */ struct dentry * pwd; struct vfsmount * pwdmnt; struct audit_context *previous; /* For nested syscalls */ @@ -320,11 +321,11 @@ static int audit_filter_rules(struct task_struct *tsk, if (ctx) result = audit_comparator(ctx->loginuid, f->op, f->val); break; - case AUDIT_SE_USER: - case AUDIT_SE_ROLE: - case AUDIT_SE_TYPE: - case AUDIT_SE_SEN: - case AUDIT_SE_CLR: + case AUDIT_SUBJ_USER: + case AUDIT_SUBJ_ROLE: + case AUDIT_SUBJ_TYPE: + case AUDIT_SUBJ_SEN: + case AUDIT_SUBJ_CLR: /* NOTE: this may return negative values indicating a temporary error. We simply treat this as a match for now to avoid losing information that @@ -341,6 +342,46 @@ static int audit_filter_rules(struct task_struct *tsk, ctx); } break; + case AUDIT_OBJ_USER: + case AUDIT_OBJ_ROLE: + case AUDIT_OBJ_TYPE: + case AUDIT_OBJ_LEV_LOW: + case AUDIT_OBJ_LEV_HIGH: + /* The above note for AUDIT_SUBJ_USER...AUDIT_SUBJ_CLR + also applies here */ + if (f->se_rule) { + /* Find files that match */ + if (name) { + result = selinux_audit_rule_match( + name->osid, f->type, f->op, + f->se_rule, ctx); + } else if (ctx) { + for (j = 0; j < ctx->name_count; j++) { + if (selinux_audit_rule_match( + ctx->names[j].osid, + f->type, f->op, + f->se_rule, ctx)) { + ++result; + break; + } + } + } + /* Find ipc objects that match */ + if (ctx) { + struct audit_aux_data *aux; + for (aux = ctx->aux; aux; + aux = aux->next) { + if (aux->type == AUDIT_IPC) { + struct audit_aux_data_ipcctl *axi = (void *)aux; + if (selinux_audit_rule_match(axi->osid, f->type, f->op, f->se_rule, ctx)) { + ++result; + break; + } + } + } + } + } + break; case AUDIT_ARG0: case AUDIT_ARG1: case AUDIT_ARG2: @@ -348,11 +389,17 @@ static int audit_filter_rules(struct task_struct *tsk, if (ctx) result = audit_comparator(ctx->argv[f->type-AUDIT_ARG0], f->op, f->val); break; + case AUDIT_FILTERKEY: + /* ignore this field for filtering */ + result = 1; + break; } if (!result) return 0; } + if (rule->filterkey) + ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC); switch (rule->action) { case AUDIT_NEVER: *state = AUDIT_DISABLED; break; case AUDIT_ALWAYS: *state = AUDIT_RECORD_CONTEXT; break; @@ -627,6 +674,7 @@ static inline void audit_free_context(struct audit_context *context) } audit_free_names(context); audit_free_aux(context); + kfree(context->filterkey); kfree(context); context = previous; } while (context); @@ -735,6 +783,11 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts context->euid, context->suid, context->fsuid, context->egid, context->sgid, context->fsgid, tty); audit_log_task_info(ab, tsk); + if (context->filterkey) { + audit_log_format(ab, " key="); + audit_log_untrustedstring(ab, context->filterkey); + } else + audit_log_format(ab, " key=(null)"); audit_log_end(ab); for (aux = context->aux; aux; aux = aux->next) { @@ -1060,6 +1113,8 @@ void audit_syscall_exit(int valid, long return_code) } else { audit_free_names(context); audit_free_aux(context); + kfree(context->filterkey); + context->filterkey = NULL; tsk->audit_context = context; } } diff --git a/kernel/capability.c b/kernel/capability.c index 1a4d8a40d3f..c7685ad00a9 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -46,7 +46,7 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr) int ret = 0; pid_t pid; __u32 version; - task_t *target; + struct task_struct *target; struct __user_cap_data_struct data; if (get_user(version, &header->version)) @@ -96,7 +96,7 @@ static inline int cap_set_pg(int pgrp, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { - task_t *g, *target; + struct task_struct *g, *target; int ret = -EPERM; int found = 0; @@ -128,7 +128,7 @@ static inline int cap_set_all(kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { - task_t *g, *target; + struct task_struct *g, *target; int ret = -EPERM; int found = 0; @@ -172,7 +172,7 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) { kernel_cap_t inheritable, permitted, effective; __u32 version; - task_t *target; + struct task_struct *target; int ret; pid_t pid; diff --git a/kernel/configs.c b/kernel/configs.c index 009e1ebdcb8..f9e31974f4a 100644 --- a/kernel/configs.c +++ b/kernel/configs.c @@ -23,7 +23,6 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/proc_fs.h> diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 1535af3a912..c232dc07743 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -18,7 +18,6 @@ * distribution for more details. */ -#include <linux/config.h> #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/cpuset.h> @@ -1064,7 +1063,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf) } /* - * Frequency meter - How fast is some event occuring? + * Frequency meter - How fast is some event occurring? * * These routines manage a digitally filtered, constant time based, * event frequency meter. There are four routines: diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c index c01cead2cfd..3c2eaea66b1 100644 --- a/kernel/exec_domain.c +++ b/kernel/exec_domain.c @@ -7,7 +7,6 @@ * 2001-05-06 Complete rewrite, Christoph Hellwig (hch@infradead.org) */ -#include <linux/config.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kmod.h> diff --git a/kernel/exit.c b/kernel/exit.c index ab06b9f88f6..6664c084783 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -4,7 +4,6 @@ * Copyright (C) 1991, 1992 Linus Torvalds */ -#include <linux/config.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/interrupt.h> @@ -135,8 +134,8 @@ static void delayed_put_task_struct(struct rcu_head *rhp) void release_task(struct task_struct * p) { + struct task_struct *leader; int zap_leader; - task_t *leader; repeat: atomic_dec(&p->user->processes); write_lock_irq(&tasklist_lock); @@ -210,7 +209,7 @@ out: * * "I ask you, have you ever known what it is to be an orphan?" */ -static int will_become_orphaned_pgrp(int pgrp, task_t *ignored_task) +static int will_become_orphaned_pgrp(int pgrp, struct task_struct *ignored_task) { struct task_struct *p; int ret = 1; @@ -583,7 +582,8 @@ static void exit_mm(struct task_struct * tsk) mmput(mm); } -static inline void choose_new_parent(task_t *p, task_t *reaper) +static inline void +choose_new_parent(struct task_struct *p, struct task_struct *reaper) { /* * Make sure we're not reparenting to ourselves and that @@ -593,7 +593,8 @@ static inline void choose_new_parent(task_t *p, task_t *reaper) p->real_parent = reaper; } -static void reparent_thread(task_t *p, task_t *father, int traced) +static void +reparent_thread(struct task_struct *p, struct task_struct *father, int traced) { /* We don't want people slaying init. */ if (p->exit_signal != -1) @@ -657,8 +658,8 @@ static void reparent_thread(task_t *p, task_t *father, int traced) * group, and if no such member exists, give it to * the global child reaper process (ie "init") */ -static void forget_original_parent(struct task_struct * father, - struct list_head *to_release) +static void +forget_original_parent(struct task_struct *father, struct list_head *to_release) { struct task_struct *p, *reaper = father; struct list_head *_p, *_n; @@ -681,7 +682,7 @@ static void forget_original_parent(struct task_struct * father, */ list_for_each_safe(_p, _n, &father->children) { int ptrace; - p = list_entry(_p,struct task_struct,sibling); + p = list_entry(_p, struct task_struct, sibling); ptrace = p->ptrace; @@ -710,7 +711,7 @@ static void forget_original_parent(struct task_struct * father, list_add(&p->ptrace_list, to_release); } list_for_each_safe(_p, _n, &father->ptrace_children) { - p = list_entry(_p,struct task_struct,ptrace_list); + p = list_entry(_p, struct task_struct, ptrace_list); choose_new_parent(p, reaper); reparent_thread(p, father, 1); } @@ -830,7 +831,7 @@ static void exit_notify(struct task_struct *tsk) list_for_each_safe(_p, _n, &ptrace_dead) { list_del_init(_p); - t = list_entry(_p,struct task_struct,ptrace_list); + t = list_entry(_p, struct task_struct, ptrace_list); release_task(t); } @@ -934,10 +935,9 @@ fastcall NORET_TYPE void do_exit(long code) if (unlikely(current->pi_state_cache)) kfree(current->pi_state_cache); /* - * If DEBUG_MUTEXES is on, make sure we are holding no locks: + * Make sure we are holding no locks: */ - mutex_debug_check_no_locks_held(tsk); - rt_mutex_debug_check_no_locks_held(tsk); + debug_check_no_locks_held(tsk); if (tsk->io_context) exit_io_context(); @@ -1012,7 +1012,7 @@ asmlinkage void sys_exit_group(int error_code) do_group_exit((error_code & 0xff) << 8); } -static int eligible_child(pid_t pid, int options, task_t *p) +static int eligible_child(pid_t pid, int options, struct task_struct *p) { if (pid > 0) { if (p->pid != pid) @@ -1053,12 +1053,13 @@ static int eligible_child(pid_t pid, int options, task_t *p) return 1; } -static int wait_noreap_copyout(task_t *p, pid_t pid, uid_t uid, +static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid, int why, int status, struct siginfo __user *infop, struct rusage __user *rusagep) { int retval = rusagep ? getrusage(p, RUSAGE_BOTH, rusagep) : 0; + put_task_struct(p); if (!retval) retval = put_user(SIGCHLD, &infop->si_signo); @@ -1083,7 +1084,7 @@ static int wait_noreap_copyout(task_t *p, pid_t pid, uid_t uid, * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ -static int wait_task_zombie(task_t *p, int noreap, +static int wait_task_zombie(struct task_struct *p, int noreap, struct siginfo __user *infop, int __user *stat_addr, struct rusage __user *ru) { @@ -1245,8 +1246,8 @@ static int wait_task_zombie(task_t *p, int noreap, * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ -static int wait_task_stopped(task_t *p, int delayed_group_leader, int noreap, - struct siginfo __user *infop, +static int wait_task_stopped(struct task_struct *p, int delayed_group_leader, + int noreap, struct siginfo __user *infop, int __user *stat_addr, struct rusage __user *ru) { int retval, exit_code; @@ -1360,7 +1361,7 @@ bail_ref: * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ -static int wait_task_continued(task_t *p, int noreap, +static int wait_task_continued(struct task_struct *p, int noreap, struct siginfo __user *infop, int __user *stat_addr, struct rusage __user *ru) { @@ -1446,7 +1447,7 @@ repeat: int ret; list_for_each(_p,&tsk->children) { - p = list_entry(_p,struct task_struct,sibling); + p = list_entry(_p, struct task_struct, sibling); ret = eligible_child(pid, options, p); if (!ret) diff --git a/kernel/fork.c b/kernel/fork.c index 628198a4f28..56e4e07e45f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -11,7 +11,6 @@ * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ -#include <linux/config.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/unistd.h> @@ -194,7 +193,10 @@ static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) down_write(&oldmm->mmap_sem); flush_cache_mm(oldmm); - down_write(&mm->mmap_sem); + /* + * Not linked in yet - no deadlock potential: + */ + down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING); mm->locked_vm = 0; mm->mmap = NULL; @@ -920,10 +922,6 @@ static inline void rt_mutex_init_task(struct task_struct *p) spin_lock_init(&p->pi_lock); plist_head_init(&p->pi_waiters, &p->pi_lock); p->pi_blocked_on = NULL; -# ifdef CONFIG_DEBUG_RT_MUTEXES - spin_lock_init(&p->held_list_lock); - INIT_LIST_HEAD(&p->held_list_head); -# endif #endif } @@ -935,13 +933,13 @@ static inline void rt_mutex_init_task(struct task_struct *p) * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ -static task_t *copy_process(unsigned long clone_flags, - unsigned long stack_start, - struct pt_regs *regs, - unsigned long stack_size, - int __user *parent_tidptr, - int __user *child_tidptr, - int pid) +static struct task_struct *copy_process(unsigned long clone_flags, + unsigned long stack_start, + struct pt_regs *regs, + unsigned long stack_size, + int __user *parent_tidptr, + int __user *child_tidptr, + int pid) { int retval; struct task_struct *p = NULL; @@ -973,6 +971,10 @@ static task_t *copy_process(unsigned long clone_flags, if (!p) goto fork_out; +#ifdef CONFIG_TRACE_IRQFLAGS + DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled); + DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); +#endif retval = -EAGAIN; if (atomic_read(&p->user->processes) >= p->signal->rlim[RLIMIT_NPROC].rlim_cur) { @@ -1047,6 +1049,26 @@ static task_t *copy_process(unsigned long clone_flags, } mpol_fix_fork_child_flag(p); #endif +#ifdef CONFIG_TRACE_IRQFLAGS + p->irq_events = 0; + p->hardirqs_enabled = 0; + p->hardirq_enable_ip = 0; + p->hardirq_enable_event = 0; + p->hardirq_disable_ip = _THIS_IP_; + p->hardirq_disable_event = 0; + p->softirqs_enabled = 1; + p->softirq_enable_ip = _THIS_IP_; + p->softirq_enable_event = 0; + p->softirq_disable_ip = 0; + p->softirq_disable_event = 0; + p->hardirq_context = 0; + p->softirq_context = 0; +#endif +#ifdef CONFIG_LOCKDEP + p->lockdep_depth = 0; /* no locks held yet */ + p->curr_chain_key = 0; + p->lockdep_recursion = 0; +#endif rt_mutex_init_task(p); @@ -1272,9 +1294,9 @@ struct pt_regs * __devinit __attribute__((weak)) idle_regs(struct pt_regs *regs) return regs; } -task_t * __devinit fork_idle(int cpu) +struct task_struct * __devinit fork_idle(int cpu) { - task_t *task; + struct task_struct *task; struct pt_regs regs; task = copy_process(CLONE_VM, 0, idle_regs(®s), 0, NULL, NULL, 0); diff --git a/kernel/futex.c b/kernel/futex.c index 6c91f938005..1dc98e4dd28 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -607,6 +607,22 @@ static int unlock_futex_pi(u32 __user *uaddr, u32 uval) } /* + * Express the locking dependencies for lockdep: + */ +static inline void +double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) +{ + if (hb1 <= hb2) { + spin_lock(&hb1->lock); + if (hb1 < hb2) + spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING); + } else { /* hb1 > hb2 */ + spin_lock(&hb2->lock); + spin_lock_nested(&hb1->lock, SINGLE_DEPTH_NESTING); + } +} + +/* * Wake up all waiters hashed on the physical page that is mapped * to this virtual address: */ @@ -630,8 +646,10 @@ static int futex_wake(u32 __user *uaddr, int nr_wake) list_for_each_entry_safe(this, next, head, list) { if (match_futex (&this->key, &key)) { - if (this->pi_state) - return -EINVAL; + if (this->pi_state) { + ret = -EINVAL; + break; + } wake_futex(this); if (++ret >= nr_wake) break; @@ -672,11 +690,7 @@ retryfull: hb2 = hash_futex(&key2); retry: - if (hb1 < hb2) - spin_lock(&hb1->lock); - spin_lock(&hb2->lock); - if (hb1 > hb2) - spin_lock(&hb1->lock); + double_lock_hb(hb1, hb2); op_ret = futex_atomic_op_inuser(op, uaddr2); if (unlikely(op_ret < 0)) { @@ -785,11 +799,7 @@ static int futex_requeue(u32 __user *uaddr1, u32 __user *uaddr2, hb1 = hash_futex(&key1); hb2 = hash_futex(&key2); - if (hb1 < hb2) - spin_lock(&hb1->lock); - spin_lock(&hb2->lock); - if (hb1 > hb2) - spin_lock(&hb1->lock); + double_lock_hb(hb1, hb2); if (likely(cmpval != NULL)) { u32 curval; @@ -1208,7 +1218,7 @@ static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock, } down_read(&curr->mm->mmap_sem); - hb = queue_lock(&q, -1, NULL); + spin_lock(q.lock_ptr); /* * Got the lock. We might not be the anticipated owner if we diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 8d3dc29ef41..d17766d40da 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -669,7 +669,7 @@ static int hrtimer_wakeup(struct hrtimer *timer) return HRTIMER_NORESTART; } -void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, task_t *task) +void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) { sl->timer.function = hrtimer_wakeup; sl->task = task; @@ -782,8 +782,10 @@ static void __devinit init_hrtimers_cpu(int cpu) struct hrtimer_base *base = per_cpu(hrtimer_bases, cpu); int i; - for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) + for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) { spin_lock_init(&base->lock); + lockdep_set_class(&base->lock, &base->lock_key); + } } #ifdef CONFIG_HOTPLUG_CPU diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index 9f77f50d814..1dab0ac3f79 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -1,5 +1,5 @@ -obj-y := handle.o manage.o spurious.o +obj-y := handle.o manage.o spurious.o resend.o chip.o obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c index 3467097ca61..533068cfb60 100644 --- a/kernel/irq/autoprobe.c +++ b/kernel/irq/autoprobe.c @@ -11,12 +11,14 @@ #include <linux/interrupt.h> #include <linux/delay.h> +#include "internals.h" + /* * Autodetection depends on the fact that any interrupt that * comes in on to an unassigned handler will get stuck with * "IRQ_WAITING" cleared and the interrupt disabled. */ -static DECLARE_MUTEX(probe_sem); +static DEFINE_MUTEX(probing_active); /** * probe_irq_on - begin an interrupt autodetect @@ -27,11 +29,11 @@ static DECLARE_MUTEX(probe_sem); */ unsigned long probe_irq_on(void) { - unsigned long val; - irq_desc_t *desc; + struct irq_desc *desc; + unsigned long mask; unsigned int i; - down(&probe_sem); + mutex_lock(&probing_active); /* * something may have generated an irq long ago and we want to * flush such a longstanding irq before considering it as spurious. @@ -40,8 +42,21 @@ unsigned long probe_irq_on(void) desc = irq_desc + i; spin_lock_irq(&desc->lock); - if (!irq_desc[i].action) - irq_desc[i].handler->startup(i); + if (!desc->action && !(desc->status & IRQ_NOPROBE)) { + /* + * An old-style architecture might still have + * the handle_bad_irq handler there: + */ + compat_irq_chip_set_default_handler(desc); + + /* + * Some chips need to know about probing in + * progress: + */ + if (desc->chip->set_type) + desc->chip->set_type(i, IRQ_TYPE_PROBE); + desc->chip->startup(i); + } spin_unlock_irq(&desc->lock); } @@ -57,9 +72,9 @@ unsigned long probe_irq_on(void) desc = irq_desc + i; spin_lock_irq(&desc->lock); - if (!desc->action) { + if (!desc->action && !(desc->status & IRQ_NOPROBE)) { desc->status |= IRQ_AUTODETECT | IRQ_WAITING; - if (desc->handler->startup(i)) + if (desc->chip->startup(i)) desc->status |= IRQ_PENDING; } spin_unlock_irq(&desc->lock); @@ -73,11 +88,11 @@ unsigned long probe_irq_on(void) /* * Now filter out any obviously spurious interrupts */ - val = 0; + mask = 0; for (i = 0; i < NR_IRQS; i++) { - irq_desc_t *desc = irq_desc + i; unsigned int status; + desc = irq_desc + i; spin_lock_irq(&desc->lock); status = desc->status; @@ -85,17 +100,16 @@ unsigned long probe_irq_on(void) /* It triggered already - consider it spurious. */ if (!(status & IRQ_WAITING)) { desc->status = status & ~IRQ_AUTODETECT; - desc->handler->shutdown(i); + desc->chip->shutdown(i); } else if (i < 32) - val |= 1 << i; + mask |= 1 << i; } spin_unlock_irq(&desc->lock); } - return val; + return mask; } - EXPORT_SYMBOL(probe_irq_on); /** @@ -117,7 +131,7 @@ unsigned int probe_irq_mask(unsigned long val) mask = 0; for (i = 0; i < NR_IRQS; i++) { - irq_desc_t *desc = irq_desc + i; + struct irq_desc *desc = irq_desc + i; unsigned int status; spin_lock_irq(&desc->lock); @@ -128,11 +142,11 @@ unsigned int probe_irq_mask(unsigned long val) mask |= 1 << i; desc->status = status & ~IRQ_AUTODETECT; - desc->handler->shutdown(i); + desc->chip->shutdown(i); } spin_unlock_irq(&desc->lock); } - up(&probe_sem); + mutex_unlock(&probing_active); return mask & val; } @@ -160,7 +174,7 @@ int probe_irq_off(unsigned long val) int i, irq_found = 0, nr_irqs = 0; for (i = 0; i < NR_IRQS; i++) { - irq_desc_t *desc = irq_desc + i; + struct irq_desc *desc = irq_desc + i; unsigned int status; spin_lock_irq(&desc->lock); @@ -173,16 +187,16 @@ int probe_irq_off(unsigned long val) nr_irqs++; } desc->status = status & ~IRQ_AUTODETECT; - desc->handler->shutdown(i); + desc->chip->shutdown(i); } spin_unlock_irq(&desc->lock); } - up(&probe_sem); + mutex_unlock(&probing_active); if (nr_irqs > 1) irq_found = -irq_found; + return irq_found; } - EXPORT_SYMBOL(probe_irq_off); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c new file mode 100644 index 00000000000..9336f2e89e4 --- /dev/null +++ b/kernel/irq/chip.c @@ -0,0 +1,537 @@ +/* + * linux/kernel/irq/chip.c + * + * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar + * Copyright (C) 2005-2006, Thomas Gleixner, Russell King + * + * This file contains the core interrupt handling code, for irq-chip + * based architectures. + * + * Detailed information is available in Documentation/DocBook/genericirq + */ + +#include <linux/irq.h> +#include <linux/module.h> +#include <linux/interrupt.h> +#include <linux/kernel_stat.h> + +#include "internals.h" + +/** + * set_irq_chip - set the irq chip for an irq + * @irq: irq number + * @chip: pointer to irq chip description structure + */ +int set_irq_chip(unsigned int irq, struct irq_chip *chip) +{ + struct irq_desc *desc; + unsigned long flags; + + if (irq >= NR_IRQS) { + printk(KERN_ERR "Trying to install chip for IRQ%d\n", irq); + WARN_ON(1); + return -EINVAL; + } + + if (!chip) + chip = &no_irq_chip; + + desc = irq_desc + irq; + spin_lock_irqsave(&desc->lock, flags); + irq_chip_set_defaults(chip); + desc->chip = chip; + /* + * For compatibility only: + */ + desc->chip = chip; + spin_unlock_irqrestore(&desc->lock, flags); + + return 0; +} +EXPORT_SYMBOL(set_irq_chip); + +/** + * set_irq_type - set the irq type for an irq + * @irq: irq number + * @type: interrupt type - see include/linux/interrupt.h + */ +int set_irq_type(unsigned int irq, unsigned int type) +{ + struct irq_desc *desc; + unsigned long flags; + int ret = -ENXIO; + + if (irq >= NR_IRQS) { + printk(KERN_ERR "Trying to set irq type for IRQ%d\n", irq); + return -ENODEV; + } + + desc = irq_desc + irq; + if (desc->chip->set_type) { + spin_lock_irqsave(&desc->lock, flags); + ret = desc->chip->set_type(irq, type); + spin_unlock_irqrestore(&desc->lock, flags); + } + return ret; +} +EXPORT_SYMBOL(set_irq_type); + +/** + * set_irq_data - set irq type data for an irq + * @irq: Interrupt number + * @data: Pointer to interrupt specific data + * + * Set the hardware irq controller data for an irq + */ +int set_irq_data(unsigned int irq, void *data) +{ + struct irq_desc *desc; + unsigned long flags; + + if (irq >= NR_IRQS) { + printk(KERN_ERR + "Trying to install controller data for IRQ%d\n", irq); + return -EINVAL; + } + + desc = irq_desc + irq; + spin_lock_irqsave(&desc->lock, flags); + desc->handler_data = data; + spin_unlock_irqrestore(&desc->lock, flags); + return 0; +} +EXPORT_SYMBOL(set_irq_data); + +/** + * set_irq_chip_data - set irq chip data for an irq + * @irq: Interrupt number + * @data: Pointer to chip specific data + * + * Set the hardware irq chip data for an irq + */ +int set_irq_chip_data(unsigned int irq, void *data) +{ + struct irq_desc *desc = irq_desc + irq; + unsigned long flags; + + if (irq >= NR_IRQS || !desc->chip) { + printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq); + return -EINVAL; + } + + spin_lock_irqsave(&desc->lock, flags); + desc->chip_data = data; + spin_unlock_irqrestore(&desc->lock, flags); + + return 0; +} +EXPORT_SYMBOL(set_irq_chip_data); + +/* + * default enable function + */ +static void default_enable(unsigned int irq) +{ + struct irq_desc *desc = irq_desc + irq; + + desc->chip->unmask(irq); + desc->status &= ~IRQ_MASKED; +} + +/* + * default disable function + */ +static void default_disable(unsigned int irq) +{ + struct irq_desc *desc = irq_desc + irq; + + if (!(desc->status & IRQ_DELAYED_DISABLE)) + irq_desc[irq].chip->mask(irq); +} + +/* + * default startup function + */ +static unsigned int default_startup(unsigned int irq) +{ + irq_desc[irq].chip->enable(irq); + + return 0; +} + +/* + * Fixup enable/disable function pointers + */ +void irq_chip_set_defaults(struct irq_chip *chip) +{ + if (!chip->enable) + chip->enable = default_enable; + if (!chip->disable) + chip->disable = default_disable; + if (!chip->startup) + chip->startup = default_startup; + if (!chip->shutdown) + chip->shutdown = chip->disable; + if (!chip->name) + chip->name = chip->typename; +} + +static inline void mask_ack_irq(struct irq_desc *desc, int irq) +{ + if (desc->chip->mask_ack) + desc->chip->mask_ack(irq); + else { + desc->chip->mask(irq); + desc->chip->ack(irq); + } +} + +/** + * handle_simple_irq - Simple and software-decoded IRQs. + * @irq: the interrupt number + * @desc: the interrupt description structure for this irq + * @regs: pointer to a register structure + * + * Simple interrupts are either sent from a demultiplexing interrupt + * handler or come from hardware, where no interrupt hardware control + * is necessary. + * + * Note: The caller is expected to handle the ack, clear, mask and + * unmask issues if necessary. + */ +void fastcall +handle_simple_irq(unsigned int irq, struct irq_desc *desc, struct pt_regs *regs) +{ + struct irqaction *action; + irqreturn_t action_ret; + const unsigned int cpu = smp_processor_id(); + + spin_lock(&desc->lock); + + if (unlikely(desc->status & IRQ_INPROGRESS)) + goto out_unlock; + desc->status &= ~(IRQ_REPLAY | IRQ_WAITING); + kstat_cpu(cpu).irqs[irq]++; + + action = desc->action; + if (unlikely(!action || (desc->status & IRQ_DISABLED))) + goto out_unlock; + + desc->status |= IRQ_INPROGRESS; + spin_unlock(&desc->lock); + + action_ret = handle_IRQ_event(irq, regs, action); + if (!noirqdebug) + note_interrupt(irq, desc, action_ret, regs); + + spin_lock(&desc->lock); + desc->status &= ~IRQ_INPROGRESS; +out_unlock: + spin_unlock(&desc->lock); +} + +/** + * handle_level_irq - Level type irq handler + * @irq: the interrupt number + * @desc: the interrupt description structure for this irq + * @regs: pointer to a register structure + * + * Level type interrupts are active as long as the hardware line has + * the active level. This may require to mask the interrupt and unmask + * it after the associated handler has acknowledged the device, so the + * interrupt line is back to inactive. + */ +void fastcall +handle_level_irq(unsigned int irq, struct irq_desc *desc, struct pt_regs *regs) +{ + unsigned int cpu = smp_processor_id(); + struct irqaction *action; + irqreturn_t action_ret; + + spin_lock(&desc->lock); + mask_ack_irq(desc, irq); + + if (unlikely(desc->status & IRQ_INPROGRESS)) + goto out; + desc->status &= ~(IRQ_REPLAY | IRQ_WAITING); + kstat_cpu(cpu).irqs[irq]++; + + /* + * If its disabled or no action available + * keep it masked and get out of here + */ + action = desc->action; + if (unlikely(!action || (desc->status & IRQ_DISABLED))) { + desc->status |= IRQ_PENDING; + goto out; + } + + desc->status |= IRQ_INPROGRESS; + desc->status &= ~IRQ_PENDING; + spin_unlock(&desc->lock); + + action_ret = handle_IRQ_event(irq, regs, action); + if (!noirqdebug) + note_interrupt(irq, desc, action_ret, regs); + + spin_lock(&desc->lock); + desc->status &= ~IRQ_INPROGRESS; +out: + if (!(desc->status & IRQ_DISABLED) && desc->chip->unmask) + desc->chip->unmask(irq); + spin_unlock(&desc->lock); +} + +/** + * handle_fasteoi_irq - irq handler for transparent controllers + * @irq: the interrupt number + * @desc: the interrupt description structure for this irq + * @regs: pointer to a register structure + * + * Only a single callback will be issued to the chip: an ->eoi() + * call when the interrupt has been serviced. This enables support + * for modern forms of interrupt handlers, which handle the flow + * details in hardware, transparently. + */ +void fastcall +handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc, + struct pt_regs *regs) +{ + unsigned int cpu = smp_processor_id(); + struct irqaction *action; + irqreturn_t action_ret; + + spin_lock(&desc->lock); + + if (unlikely(desc->status & IRQ_INPROGRESS)) + goto out; + + desc->status &= ~(IRQ_REPLAY | IRQ_WAITING); + kstat_cpu(cpu).irqs[irq]++; + + /* + * If its disabled or no action available + * keep it masked and get out of here + */ + action = desc->action; + if (unlikely(!action || (desc->status & IRQ_DISABLED))) { + desc->status |= IRQ_PENDING; + goto out; + } + + desc->status |= IRQ_INPROGRESS; + desc->status &= ~IRQ_PENDING; + spin_unlock(&desc->lock); + + action_ret = handle_IRQ_event(irq, regs, action); + if (!noirqdebug) + note_interrupt(irq, desc, action_ret, regs); + + spin_lock(&desc->lock); + desc->status &= ~IRQ_INPROGRESS; +out: + desc->chip->eoi(irq); + + spin_unlock(&desc->lock); +} + +/** + * handle_edge_irq - edge type IRQ handler + * @irq: the interrupt number + * @desc: the interrupt description structure for this irq + * @regs: pointer to a register structure + * + * Interrupt occures on the falling and/or rising edge of a hardware + * signal. The occurence is latched into the irq controller hardware + * and must be acked in order to be reenabled. After the ack another + * interrupt can happen on the same source even before the first one + * is handled by the assosiacted event handler. If this happens it + * might be necessary to disable (mask) the interrupt depending on the + * controller hardware. This requires to reenable the interrupt inside + * of the loop which handles the interrupts which have arrived while + * the handler was running. If all pending interrupts are handled, the + * loop is left. + */ +void fastcall +handle_edge_irq(unsigned int irq, struct irq_desc *desc, struct pt_regs *regs) +{ + const unsigned int cpu = smp_processor_id(); + + spin_lock(&desc->lock); + + desc->status &= ~(IRQ_REPLAY | IRQ_WAITING); + + /* + * If we're currently running this IRQ, or its disabled, + * we shouldn't process the IRQ. Mark it pending, handle + * the necessary masking and go out + */ + if (unlikely((desc->status & (IRQ_INPROGRESS | IRQ_DISABLED)) || + !desc->action)) { + desc->status |= (IRQ_PENDING | IRQ_MASKED); + mask_ack_irq(desc, irq); + goto out_unlock; + } + + kstat_cpu(cpu).irqs[irq]++; + + /* Start handling the irq */ + desc->chip->ack(irq); + + /* Mark the IRQ currently in progress.*/ + desc->status |= IRQ_INPROGRESS; + + do { + struct irqaction *action = desc->action; + irqreturn_t action_ret; + + if (unlikely(!action)) { + desc->chip->mask(irq); + goto out_unlock; + } + + /* + * When another irq arrived while we were handling + * one, we could have masked the irq. + * Renable it, if it was not disabled in meantime. + */ + if (unlikely((desc->status & + (IRQ_PENDING | IRQ_MASKED | IRQ_DISABLED)) == + (IRQ_PENDING | IRQ_MASKED))) { + desc->chip->unmask(irq); + desc->status &= ~IRQ_MASKED; + } + + desc->status &= ~IRQ_PENDING; + spin_unlock(&desc->lock); + action_ret = handle_IRQ_event(irq, regs, action); + if (!noirqdebug) + note_interrupt(irq, desc, action_ret, regs); + spin_lock(&desc->lock); + + } while ((desc->status & (IRQ_PENDING | IRQ_DISABLED)) == IRQ_PENDING); + + desc->status &= ~IRQ_INPROGRESS; +out_unlock: + spin_unlock(&desc->lock); +} + +#ifdef CONFIG_SMP +/** + * handle_percpu_IRQ - Per CPU local irq handler + * @irq: the interrupt number + * @desc: the interrupt description structure for this irq + * @regs: pointer to a register structure + * + * Per CPU interrupts on SMP machines without locking requirements + */ +void fastcall +handle_percpu_irq(unsigned int irq, struct irq_desc *desc, struct pt_regs *regs) +{ + irqreturn_t action_ret; + + kstat_this_cpu.irqs[irq]++; + + if (desc->chip->ack) + desc->chip->ack(irq); + + action_ret = handle_IRQ_event(irq, regs, desc->action); + if (!noirqdebug) + note_interrupt(irq, desc, action_ret, regs); + + if (desc->chip->eoi) + desc->chip->eoi(irq); +} + +#endif /* CONFIG_SMP */ + +void +__set_irq_handler(unsigned int irq, + void fastcall (*handle)(unsigned int, irq_desc_t *, + struct pt_regs *), + int is_chained) +{ + struct irq_desc *desc; + unsigned long flags; + + if (irq >= NR_IRQS) { + printk(KERN_ERR + "Trying to install type control for IRQ%d\n", irq); + return; + } + + desc = irq_desc + irq; + + if (!handle) + handle = handle_bad_irq; + + if (desc->chip == &no_irq_chip) { + printk(KERN_WARNING "Trying to install %sinterrupt handler " + "for IRQ%d\n", is_chained ? "chained " : " ", irq); + /* + * Some ARM implementations install a handler for really dumb + * interrupt hardware without setting an irq_chip. This worked + * with the ARM no_irq_chip but the check in setup_irq would + * prevent us to setup the interrupt at all. Switch it to + * dummy_irq_chip for easy transition. + */ + desc->chip = &dummy_irq_chip; + } + + spin_lock_irqsave(&desc->lock, flags); + + /* Uninstall? */ + if (handle == handle_bad_irq) { + if (desc->chip != &no_irq_chip) { + desc->chip->mask(irq); + desc->chip->ack(irq); + } + desc->status |= IRQ_DISABLED; + desc->depth = 1; + } + desc->handle_irq = handle; + + if (handle != handle_bad_irq && is_chained) { + desc->status &= ~IRQ_DISABLED; + desc->status |= IRQ_NOREQUEST | IRQ_NOPROBE; + desc->depth = 0; + desc->chip->unmask(irq); + } + spin_unlock_irqrestore(&desc->lock, flags); +} + +void +set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip, + void fastcall (*handle)(unsigned int, + struct irq_desc *, + struct pt_regs *)) +{ + set_irq_chip(irq, chip); + __set_irq_handler(irq, handle, 0); +} + +/* + * Get a descriptive string for the highlevel handler, for + * /proc/interrupts output: + */ +const char * +handle_irq_name(void fastcall (*handle)(unsigned int, struct irq_desc *, + struct pt_regs *)) +{ + if (handle == handle_level_irq) + return "level "; + if (handle == handle_fasteoi_irq) + return "fasteoi"; + if (handle == handle_edge_irq) + return "edge "; + if (handle == handle_simple_irq) + return "simple "; +#ifdef CONFIG_SMP + if (handle == handle_percpu_irq) + return "percpu "; +#endif + if (handle == handle_bad_irq) + return "bad "; + + return NULL; +} diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 0f653011710..fc4e906aedb 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -1,9 +1,13 @@ /* * linux/kernel/irq/handle.c * - * Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar + * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar + * Copyright (C) 2005-2006, Thomas Gleixner, Russell King * * This file contains the core interrupt handling code. + * + * Detailed information is available in Documentation/DocBook/genericirq + * */ #include <linux/irq.h> @@ -14,11 +18,22 @@ #include "internals.h" +/** + * handle_bad_irq - handle spurious and unhandled irqs + */ +void fastcall +handle_bad_irq(unsigned int irq, struct irq_desc *desc, struct pt_regs *regs) +{ + print_irq_desc(irq, desc); + kstat_this_cpu.irqs[irq]++; + ack_bad_irq(irq); +} + /* * Linux has a controller-independent interrupt architecture. * Every controller has a 'controller-template', that is used * by the main code to do the right thing. Each driver-visible - * interrupt source is transparently wired to the apropriate + * interrupt source is transparently wired to the appropriate * controller. Thus drivers need not be aware of the * interrupt-controller. * @@ -28,41 +43,68 @@ * * Controller mappings for all interrupt sources: */ -irq_desc_t irq_desc[NR_IRQS] __cacheline_aligned = { +struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned = { [0 ... NR_IRQS-1] = { .status = IRQ_DISABLED, - .handler = &no_irq_type, - .lock = SPIN_LOCK_UNLOCKED + .chip = &no_irq_chip, + .handle_irq = handle_bad_irq, + .depth = 1, + .lock = SPIN_LOCK_UNLOCKED, +#ifdef CONFIG_SMP + .affinity = CPU_MASK_ALL +#endif } }; /* - * Generic 'no controller' code + * What should we do if we get a hw irq event on an illegal vector? + * Each architecture has to answer this themself. */ -static void end_none(unsigned int irq) { } -static void enable_none(unsigned int irq) { } -static void disable_none(unsigned int irq) { } -static void shutdown_none(unsigned int irq) { } -static unsigned int startup_none(unsigned int irq) { return 0; } - -static void ack_none(unsigned int irq) +static void ack_bad(unsigned int irq) { - /* - * 'what should we do if we get a hw irq event on an illegal vector'. - * each architecture has to answer this themself. - */ + print_irq_desc(irq, irq_desc + irq); ack_bad_irq(irq); } -struct hw_interrupt_type no_irq_type = { - .typename = "none", - .startup = startup_none, - .shutdown = shutdown_none, - .enable = enable_none, - .disable = disable_none, - .ack = ack_none, - .end = end_none, - .set_affinity = NULL +/* + * NOP functions + */ +static void noop(unsigned int irq) +{ +} + +static unsigned int noop_ret(unsigned int irq) +{ + return 0; +} + +/* + * Generic no controller implementation + */ +struct irq_chip no_irq_chip = { + .name = "none", + .startup = noop_ret, + .shutdown = noop, + .enable = noop, + .disable = noop, + .ack = ack_bad, + .end = noop, +}; + +/* + * Generic dummy implementation which can be used for + * real dumb interrupt sources + */ +struct irq_chip dummy_irq_chip = { + .name = "dummy", + .startup = noop_ret, + .shutdown = noop, + .enable = noop, + .disable = noop, + .ack = noop, + .mask = noop, + .unmask = noop, + .end = noop, }; /* @@ -73,17 +115,24 @@ irqreturn_t no_action(int cpl, void *dev_id, struct pt_regs *regs) return IRQ_NONE; } -/* - * Have got an event to handle: +/** + * handle_IRQ_event - irq action chain handler + * @irq: the interrupt number + * @regs: pointer to a register structure + * @action: the interrupt action chain for this irq + * + * Handles the action chain of an irq event */ -fastcall irqreturn_t handle_IRQ_event(unsigned int irq, struct pt_regs *regs, - struct irqaction *action) +irqreturn_t handle_IRQ_event(unsigned int irq, struct pt_regs *regs, + struct irqaction *action) { irqreturn_t ret, retval = IRQ_NONE; unsigned int status = 0; - if (!(action->flags & SA_INTERRUPT)) - local_irq_enable(); + handle_dynamic_tick(action); + + if (!(action->flags & IRQF_DISABLED)) + local_irq_enable_in_hardirq(); do { ret = action->handler(irq, action->dev_id, regs); @@ -93,22 +142,29 @@ fastcall irqreturn_t handle_IRQ_event(unsigned int irq, struct pt_regs *regs, action = action->next; } while (action); - if (status & SA_SAMPLE_RANDOM) + if (status & IRQF_SAMPLE_RANDOM) add_interrupt_randomness(irq); local_irq_disable(); return retval; } -/* - * do_IRQ handles all normal device IRQ's (the special +/** + * __do_IRQ - original all in one highlevel IRQ handler + * @irq: the interrupt number + * @regs: pointer to a register structure + * + * __do_IRQ handles all normal device IRQ's (the special * SMP cross-CPU interrupts have their own specific * handlers). + * + * This is the original x86 implementation which is used for every + * interrupt type. */ fastcall unsigned int __do_IRQ(unsigned int irq, struct pt_regs *regs) { - irq_desc_t *desc = irq_desc + irq; - struct irqaction * action; + struct irq_desc *desc = irq_desc + irq; + struct irqaction *action; unsigned int status; kstat_this_cpu.irqs[irq]++; @@ -118,16 +174,16 @@ fastcall unsigned int __do_IRQ(unsigned int irq, struct pt_regs *regs) /* * No locking required for CPU-local interrupts: */ - if (desc->handler->ack) - desc->handler->ack(irq); + if (desc->chip->ack) + desc->chip->ack(irq); action_ret = handle_IRQ_event(irq, regs, desc->action); - desc->handler->end(irq); + desc->chip->end(irq); return 1; } spin_lock(&desc->lock); - if (desc->handler->ack) - desc->handler->ack(irq); + if (desc->chip->ack) + desc->chip->ack(irq); /* * REPLAY is when Linux resends an IRQ that was dropped earlier * WAITING is used by probe to mark irqs that are being tested @@ -187,9 +243,25 @@ out: * The ->end() handler has to deal with interrupts which got * disabled while the handler was running. */ - desc->handler->end(irq); + desc->chip->end(irq); spin_unlock(&desc->lock); return 1; } +#ifdef CONFIG_TRACE_IRQFLAGS + +/* + * lockdep: we want to handle all irq_desc locks as a single lock-class: + */ +static struct lock_class_key irq_desc_lock_class; + +void early_init_irq_lock_class(void) +{ + int i; + + for (i = 0; i < NR_IRQS; i++) + lockdep_set_class(&irq_desc[i].lock, &irq_desc_lock_class); +} + +#endif diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 46feba63026..08a849a2244 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -4,6 +4,12 @@ extern int noirqdebug; +/* Set default functions for irq_chip structures: */ +extern void irq_chip_set_defaults(struct irq_chip *chip); + +/* Set default handler: */ +extern void compat_irq_chip_set_default_handler(struct irq_desc *desc); + #ifdef CONFIG_PROC_FS extern void register_irq_proc(unsigned int irq); extern void register_handler_proc(unsigned int irq, struct irqaction *action); @@ -16,3 +22,43 @@ static inline void unregister_handler_proc(unsigned int irq, struct irqaction *action) { } #endif +/* + * Debugging printout: + */ + +#include <linux/kallsyms.h> + +#define P(f) if (desc->status & f) printk("%14s set\n", #f) + +static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc) +{ + printk("irq %d, desc: %p, depth: %d, count: %d, unhandled: %d\n", + irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled); + printk("->handle_irq(): %p, ", desc->handle_irq); + print_symbol("%s\n", (unsigned long)desc->handle_irq); + printk("->chip(): %p, ", desc->chip); + print_symbol("%s\n", (unsigned long)desc->chip); + printk("->action(): %p\n", desc->action); + if (desc->action) { + printk("->action->handler(): %p, ", desc->action->handler); + print_symbol("%s\n", (unsigned long)desc->action->handler); + } + + P(IRQ_INPROGRESS); + P(IRQ_DISABLED); + P(IRQ_PENDING); + P(IRQ_REPLAY); + P(IRQ_AUTODETECT); + P(IRQ_WAITING); + P(IRQ_LEVEL); + P(IRQ_MASKED); +#ifdef CONFIG_IRQ_PER_CPU + P(IRQ_PER_CPU); +#endif + P(IRQ_NOPROBE); + P(IRQ_NOREQUEST); + P(IRQ_NOAUTOEN); +} + +#undef P + diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 1279e349953..4e461438e48 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1,12 +1,12 @@ /* * linux/kernel/irq/manage.c * - * Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar + * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar + * Copyright (C) 2005-2006 Thomas Gleixner * * This file contains driver APIs to the irq subsystem. */ -#include <linux/config.h> #include <linux/irq.h> #include <linux/module.h> #include <linux/random.h> @@ -16,12 +16,6 @@ #ifdef CONFIG_SMP -cpumask_t irq_affinity[NR_IRQS] = { [0 ... NR_IRQS-1] = CPU_MASK_ALL }; - -#if defined (CONFIG_GENERIC_PENDING_IRQ) || defined (CONFIG_IRQBALANCE) -cpumask_t __cacheline_aligned pending_irq_cpumask[NR_IRQS]; -#endif - /** * synchronize_irq - wait for pending IRQ handlers (on other CPUs) * @irq: interrupt number to wait for @@ -42,7 +36,6 @@ void synchronize_irq(unsigned int irq) while (desc->status & IRQ_INPROGRESS) cpu_relax(); } - EXPORT_SYMBOL(synchronize_irq); #endif @@ -60,7 +53,7 @@ EXPORT_SYMBOL(synchronize_irq); */ void disable_irq_nosync(unsigned int irq) { - irq_desc_t *desc = irq_desc + irq; + struct irq_desc *desc = irq_desc + irq; unsigned long flags; if (irq >= NR_IRQS) @@ -69,11 +62,10 @@ void disable_irq_nosync(unsigned int irq) spin_lock_irqsave(&desc->lock, flags); if (!desc->depth++) { desc->status |= IRQ_DISABLED; - desc->handler->disable(irq); + desc->chip->disable(irq); } spin_unlock_irqrestore(&desc->lock, flags); } - EXPORT_SYMBOL(disable_irq_nosync); /** @@ -90,7 +82,7 @@ EXPORT_SYMBOL(disable_irq_nosync); */ void disable_irq(unsigned int irq) { - irq_desc_t *desc = irq_desc + irq; + struct irq_desc *desc = irq_desc + irq; if (irq >= NR_IRQS) return; @@ -99,7 +91,6 @@ void disable_irq(unsigned int irq) if (desc->action) synchronize_irq(irq); } - EXPORT_SYMBOL(disable_irq); /** @@ -114,7 +105,7 @@ EXPORT_SYMBOL(disable_irq); */ void enable_irq(unsigned int irq) { - irq_desc_t *desc = irq_desc + irq; + struct irq_desc *desc = irq_desc + irq; unsigned long flags; if (irq >= NR_IRQS) @@ -123,17 +114,15 @@ void enable_irq(unsigned int irq) spin_lock_irqsave(&desc->lock, flags); switch (desc->depth) { case 0: + printk(KERN_WARNING "Unbalanced enable for IRQ %d\n", irq); WARN_ON(1); break; case 1: { unsigned int status = desc->status & ~IRQ_DISABLED; - desc->status = status; - if ((status & (IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) { - desc->status = status | IRQ_REPLAY; - hw_resend_irq(desc->handler,irq); - } - desc->handler->enable(irq); + /* Prevent probing on this irq: */ + desc->status = status | IRQ_NOPROBE; + check_irq_resend(desc, irq); /* fall-through */ } default: @@ -141,9 +130,29 @@ void enable_irq(unsigned int irq) } spin_unlock_irqrestore(&desc->lock, flags); } - EXPORT_SYMBOL(enable_irq); +/** + * set_irq_wake - control irq power management wakeup + * @irq: interrupt to control + * @on: enable/disable power management wakeup + * + * Enable/disable power management wakeup mode + */ +int set_irq_wake(unsigned int irq, unsigned int on) +{ + struct irq_desc *desc = irq_desc + irq; + unsigned long flags; + int ret = -ENXIO; + + spin_lock_irqsave(&desc->lock, flags); + if (desc->chip->set_wake) + ret = desc->chip->set_wake(irq, on); + spin_unlock_irqrestore(&desc->lock, flags); + return ret; +} +EXPORT_SYMBOL(set_irq_wake); + /* * Internal function that tells the architecture code whether a * particular irq has been exclusively allocated or is available @@ -153,22 +162,33 @@ int can_request_irq(unsigned int irq, unsigned long irqflags) { struct irqaction *action; - if (irq >= NR_IRQS) + if (irq >= NR_IRQS || irq_desc[irq].status & IRQ_NOREQUEST) return 0; action = irq_desc[irq].action; if (action) - if (irqflags & action->flags & SA_SHIRQ) + if (irqflags & action->flags & IRQF_SHARED) action = NULL; return !action; } +void compat_irq_chip_set_default_handler(struct irq_desc *desc) +{ + /* + * If the architecture still has not overriden + * the flow handler then zap the default. This + * should catch incorrect flow-type setting. + */ + if (desc->handle_irq == &handle_bad_irq) + desc->handle_irq = NULL; +} + /* * Internal function to register an irqaction - typically used to * allocate special interrupts that are part of the architecture. */ -int setup_irq(unsigned int irq, struct irqaction * new) +int setup_irq(unsigned int irq, struct irqaction *new) { struct irq_desc *desc = irq_desc + irq; struct irqaction *old, **p; @@ -178,14 +198,14 @@ int setup_irq(unsigned int irq, struct irqaction * new) if (irq >= NR_IRQS) return -EINVAL; - if (desc->handler == &no_irq_type) + if (desc->chip == &no_irq_chip) return -ENOSYS; /* * Some drivers like serial.c use request_irq() heavily, * so we have to be careful not to interfere with a * running system. */ - if (new->flags & SA_SAMPLE_RANDOM) { + if (new->flags & IRQF_SAMPLE_RANDOM) { /* * This function might sleep, we want to call it first, * outside of the atomic block. @@ -200,16 +220,24 @@ int setup_irq(unsigned int irq, struct irqaction * new) /* * The following block of code has to be executed atomically */ - spin_lock_irqsave(&desc->lock,flags); + spin_lock_irqsave(&desc->lock, flags); p = &desc->action; - if ((old = *p) != NULL) { - /* Can't share interrupts unless both agree to */ - if (!(old->flags & new->flags & SA_SHIRQ)) + old = *p; + if (old) { + /* + * Can't share interrupts unless both agree to and are + * the same type (level, edge, polarity). So both flag + * fields must have IRQF_SHARED set and the bits which + * set the trigger type must match. + */ + if (!((old->flags & new->flags) & IRQF_SHARED) || + ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK)) goto mismatch; -#if defined(ARCH_HAS_IRQ_PER_CPU) && defined(SA_PERCPU_IRQ) +#if defined(CONFIG_IRQ_PER_CPU) /* All handlers must agree on per-cpuness */ - if ((old->flags & IRQ_PER_CPU) != (new->flags & IRQ_PER_CPU)) + if ((old->flags & IRQF_PERCPU) != + (new->flags & IRQF_PERCPU)) goto mismatch; #endif @@ -222,20 +250,45 @@ int setup_irq(unsigned int irq, struct irqaction * new) } *p = new; -#if defined(ARCH_HAS_IRQ_PER_CPU) && defined(SA_PERCPU_IRQ) - if (new->flags & SA_PERCPU_IRQ) +#if defined(CONFIG_IRQ_PER_CPU) + if (new->flags & IRQF_PERCPU) desc->status |= IRQ_PER_CPU; #endif if (!shared) { - desc->depth = 0; - desc->status &= ~(IRQ_DISABLED | IRQ_AUTODETECT | - IRQ_WAITING | IRQ_INPROGRESS); - if (desc->handler->startup) - desc->handler->startup(irq); - else - desc->handler->enable(irq); + irq_chip_set_defaults(desc->chip); + + /* Setup the type (level, edge polarity) if configured: */ + if (new->flags & IRQF_TRIGGER_MASK) { + if (desc->chip && desc->chip->set_type) + desc->chip->set_type(irq, + new->flags & IRQF_TRIGGER_MASK); + else + /* + * IRQF_TRIGGER_* but the PIC does not support + * multiple flow-types? + */ + printk(KERN_WARNING "No IRQF_TRIGGER set_type " + "function for IRQ %d (%s)\n", irq, + desc->chip ? desc->chip->name : + "unknown"); + } else + compat_irq_chip_set_default_handler(desc); + + desc->status &= ~(IRQ_AUTODETECT | IRQ_WAITING | + IRQ_INPROGRESS); + + if (!(desc->status & IRQ_NOAUTOEN)) { + desc->depth = 0; + desc->status &= ~IRQ_DISABLED; + if (desc->chip->startup) + desc->chip->startup(irq); + else + desc->chip->enable(irq); + } else + /* Undo nested disables: */ + desc->depth = 1; } - spin_unlock_irqrestore(&desc->lock,flags); + spin_unlock_irqrestore(&desc->lock, flags); new->irq = irq; register_irq_proc(irq); @@ -246,8 +299,8 @@ int setup_irq(unsigned int irq, struct irqaction * new) mismatch: spin_unlock_irqrestore(&desc->lock, flags); - if (!(new->flags & SA_PROBEIRQ)) { - printk(KERN_ERR "%s: irq handler mismatch\n", __FUNCTION__); + if (!(new->flags & IRQF_PROBE_SHARED)) { + printk(KERN_ERR "IRQ handler type mismatch for IRQ %d\n", irq); dump_stack(); } return -EBUSY; @@ -278,10 +331,10 @@ void free_irq(unsigned int irq, void *dev_id) return; desc = irq_desc + irq; - spin_lock_irqsave(&desc->lock,flags); + spin_lock_irqsave(&desc->lock, flags); p = &desc->action; for (;;) { - struct irqaction * action = *p; + struct irqaction *action = *p; if (action) { struct irqaction **pp = p; @@ -295,18 +348,18 @@ void free_irq(unsigned int irq, void *dev_id) /* Currently used only by UML, might disappear one day.*/ #ifdef CONFIG_IRQ_RELEASE_METHOD - if (desc->handler->release) - desc->handler->release(irq, dev_id); + if (desc->chip->release) + desc->chip->release(irq, dev_id); #endif if (!desc->action) { desc->status |= IRQ_DISABLED; - if (desc->handler->shutdown) - desc->handler->shutdown(irq); + if (desc->chip->shutdown) + desc->chip->shutdown(irq); else - desc->handler->disable(irq); + desc->chip->disable(irq); } - spin_unlock_irqrestore(&desc->lock,flags); + spin_unlock_irqrestore(&desc->lock, flags); unregister_handler_proc(irq, action); /* Make sure it's not being used on another CPU */ @@ -314,12 +367,11 @@ void free_irq(unsigned int irq, void *dev_id) kfree(action); return; } - printk(KERN_ERR "Trying to free free IRQ%d\n",irq); - spin_unlock_irqrestore(&desc->lock,flags); + printk(KERN_ERR "Trying to free already-free IRQ %d\n", irq); + spin_unlock_irqrestore(&desc->lock, flags); return; } } - EXPORT_SYMBOL(free_irq); /** @@ -346,28 +398,36 @@ EXPORT_SYMBOL(free_irq); * * Flags: * - * SA_SHIRQ Interrupt is shared - * SA_INTERRUPT Disable local interrupts while processing - * SA_SAMPLE_RANDOM The interrupt can be used for entropy + * IRQF_SHARED Interrupt is shared + * IRQF_DISABLED Disable local interrupts while processing + * IRQF_SAMPLE_RANDOM The interrupt can be used for entropy * */ int request_irq(unsigned int irq, irqreturn_t (*handler)(int, void *, struct pt_regs *), - unsigned long irqflags, const char * devname, void *dev_id) + unsigned long irqflags, const char *devname, void *dev_id) { - struct irqaction * action; + struct irqaction *action; int retval; +#ifdef CONFIG_LOCKDEP + /* + * Lockdep wants atomic interrupt handlers: + */ + irqflags |= SA_INTERRUPT; +#endif /* * Sanity-check: shared interrupts must pass in a real dev-ID, * otherwise we'll have trouble later trying to figure out * which interrupt is which (messes up the interrupt freeing * logic etc). */ - if ((irqflags & SA_SHIRQ) && !dev_id) + if ((irqflags & IRQF_SHARED) && !dev_id) return -EINVAL; if (irq >= NR_IRQS) return -EINVAL; + if (irq_desc[irq].status & IRQ_NOREQUEST) + return -EINVAL; if (!handler) return -EINVAL; @@ -390,6 +450,5 @@ int request_irq(unsigned int irq, return retval; } - EXPORT_SYMBOL(request_irq); diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index a12d00eb5e7..a57ebe9fa6f 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -3,19 +3,19 @@ void set_pending_irq(unsigned int irq, cpumask_t mask) { - irq_desc_t *desc = irq_desc + irq; + struct irq_desc *desc = irq_desc + irq; unsigned long flags; spin_lock_irqsave(&desc->lock, flags); desc->move_irq = 1; - pending_irq_cpumask[irq] = mask; + irq_desc[irq].pending_mask = mask; spin_unlock_irqrestore(&desc->lock, flags); } void move_native_irq(int irq) { + struct irq_desc *desc = irq_desc + irq; cpumask_t tmp; - irq_desc_t *desc = irq_descp(irq); if (likely(!desc->move_irq)) return; @@ -30,15 +30,15 @@ void move_native_irq(int irq) desc->move_irq = 0; - if (unlikely(cpus_empty(pending_irq_cpumask[irq]))) + if (unlikely(cpus_empty(irq_desc[irq].pending_mask))) return; - if (!desc->handler->set_affinity) + if (!desc->chip->set_affinity) return; assert_spin_locked(&desc->lock); - cpus_and(tmp, pending_irq_cpumask[irq], cpu_online_map); + cpus_and(tmp, irq_desc[irq].pending_mask, cpu_online_map); /* * If there was a valid mask to work with, please @@ -51,12 +51,12 @@ void move_native_irq(int irq) */ if (likely(!cpus_empty(tmp))) { if (likely(!(desc->status & IRQ_DISABLED))) - desc->handler->disable(irq); + desc->chip->disable(irq); - desc->handler->set_affinity(irq,tmp); + desc->chip->set_affinity(irq,tmp); if (likely(!(desc->status & IRQ_DISABLED))) - desc->handler->enable(irq); + desc->chip->enable(irq); } - cpus_clear(pending_irq_cpumask[irq]); + cpus_clear(irq_desc[irq].pending_mask); } diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index afacd6f585f..607c7809ad0 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -12,15 +12,10 @@ #include "internals.h" -static struct proc_dir_entry *root_irq_dir, *irq_dir[NR_IRQS]; +static struct proc_dir_entry *root_irq_dir; #ifdef CONFIG_SMP -/* - * The /proc/irq/<irq>/smp_affinity values: - */ -static struct proc_dir_entry *smp_affinity_entry[NR_IRQS]; - #ifdef CONFIG_GENERIC_PENDING_IRQ void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val) { @@ -36,15 +31,15 @@ void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val) void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val) { set_balance_irq_affinity(irq, mask_val); - irq_affinity[irq] = mask_val; - irq_desc[irq].handler->set_affinity(irq, mask_val); + irq_desc[irq].affinity = mask_val; + irq_desc[irq].chip->set_affinity(irq, mask_val); } #endif static int irq_affinity_read_proc(char *page, char **start, off_t off, int count, int *eof, void *data) { - int len = cpumask_scnprintf(page, count, irq_affinity[(long)data]); + int len = cpumask_scnprintf(page, count, irq_desc[(long)data].affinity); if (count - len < 2) return -EINVAL; @@ -59,7 +54,7 @@ static int irq_affinity_write_proc(struct file *file, const char __user *buffer, unsigned int irq = (int)(long)data, full_count = count, err; cpumask_t new_value, tmp; - if (!irq_desc[irq].handler->set_affinity || no_irq_affinity) + if (!irq_desc[irq].chip->set_affinity || no_irq_affinity) return -EIO; err = cpumask_parse(buffer, count, new_value); @@ -102,7 +97,7 @@ void register_handler_proc(unsigned int irq, struct irqaction *action) { char name [MAX_NAMELEN]; - if (!irq_dir[irq] || action->dir || !action->name || + if (!irq_desc[irq].dir || action->dir || !action->name || !name_unique(irq, action)) return; @@ -110,7 +105,7 @@ void register_handler_proc(unsigned int irq, struct irqaction *action) snprintf(name, MAX_NAMELEN, "%s", action->name); /* create /proc/irq/1234/handler/ */ - action->dir = proc_mkdir(name, irq_dir[irq]); + action->dir = proc_mkdir(name, irq_desc[irq].dir); } #undef MAX_NAMELEN @@ -122,22 +117,22 @@ void register_irq_proc(unsigned int irq) char name [MAX_NAMELEN]; if (!root_irq_dir || - (irq_desc[irq].handler == &no_irq_type) || - irq_dir[irq]) + (irq_desc[irq].chip == &no_irq_chip) || + irq_desc[irq].dir) return; memset(name, 0, MAX_NAMELEN); sprintf(name, "%d", irq); /* create /proc/irq/1234 */ - irq_dir[irq] = proc_mkdir(name, root_irq_dir); + irq_desc[irq].dir = proc_mkdir(name, root_irq_dir); #ifdef CONFIG_SMP { struct proc_dir_entry *entry; /* create /proc/irq/<irq>/smp_affinity */ - entry = create_proc_entry("smp_affinity", 0600, irq_dir[irq]); + entry = create_proc_entry("smp_affinity", 0600, irq_desc[irq].dir); if (entry) { entry->nlink = 1; @@ -145,7 +140,6 @@ void register_irq_proc(unsigned int irq) entry->read_proc = irq_affinity_read_proc; entry->write_proc = irq_affinity_write_proc; } - smp_affinity_entry[irq] = entry; } #endif } @@ -155,7 +149,7 @@ void register_irq_proc(unsigned int irq) void unregister_handler_proc(unsigned int irq, struct irqaction *action) { if (action->dir) - remove_proc_entry(action->dir->name, irq_dir[irq]); + remove_proc_entry(action->dir->name, irq_desc[irq].dir); } void init_irq_proc(void) diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c new file mode 100644 index 00000000000..872f91ba2ce --- /dev/null +++ b/kernel/irq/resend.c @@ -0,0 +1,78 @@ +/* + * linux/kernel/irq/resend.c + * + * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar + * Copyright (C) 2005-2006, Thomas Gleixner + * + * This file contains the IRQ-resend code + * + * If the interrupt is waiting to be processed, we try to re-run it. + * We can't directly run it from here since the caller might be in an + * interrupt-protected region. Not all irq controller chips can + * retrigger interrupts at the hardware level, so in those cases + * we allow the resending of IRQs via a tasklet. + */ + +#include <linux/irq.h> +#include <linux/module.h> +#include <linux/random.h> +#include <linux/interrupt.h> + +#include "internals.h" + +#ifdef CONFIG_HARDIRQS_SW_RESEND + +/* Bitmap to handle software resend of interrupts: */ +static DECLARE_BITMAP(irqs_resend, NR_IRQS); + +/* + * Run software resends of IRQ's + */ +static void resend_irqs(unsigned long arg) +{ + struct irq_desc *desc; + int irq; + + while (!bitmap_empty(irqs_resend, NR_IRQS)) { + irq = find_first_bit(irqs_resend, NR_IRQS); + clear_bit(irq, irqs_resend); + desc = irq_desc + irq; + local_irq_disable(); + desc->handle_irq(irq, desc, NULL); + local_irq_enable(); + } +} + +/* Tasklet to handle resend: */ +static DECLARE_TASKLET(resend_tasklet, resend_irqs, 0); + +#endif + +/* + * IRQ resend + * + * Is called with interrupts disabled and desc->lock held. + */ +void check_irq_resend(struct irq_desc *desc, unsigned int irq) +{ + unsigned int status = desc->status; + + /* + * Make sure the interrupt is enabled, before resending it: + */ + desc->chip->enable(irq); + + if ((status & (IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) { + desc->status &= ~IRQ_PENDING; + desc->status = status | IRQ_REPLAY; + + if (!desc->chip || !desc->chip->retrigger || + !desc->chip->retrigger(irq)) { +#ifdef CONFIG_HARDIRQS_SW_RESEND + /* Set it pending and activate the softirq: */ + set_bit(irq, irqs_resend); + tasklet_schedule(&resend_tasklet); +#endif + } + } +} diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index b2fb3c18d06..417e98092cf 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -16,39 +16,39 @@ static int irqfixup __read_mostly; /* * Recovery handler for misrouted interrupts. */ - static int misrouted_irq(int irq, struct pt_regs *regs) { int i; - irq_desc_t *desc; int ok = 0; int work = 0; /* Did we do work for a real IRQ */ - for(i = 1; i < NR_IRQS; i++) { + for (i = 1; i < NR_IRQS; i++) { + struct irq_desc *desc = irq_desc + i; struct irqaction *action; if (i == irq) /* Already tried */ continue; - desc = &irq_desc[i]; + spin_lock(&desc->lock); - action = desc->action; /* Already running on another processor */ if (desc->status & IRQ_INPROGRESS) { /* * Already running: If it is shared get the other * CPU to go looking for our mystery interrupt too */ - if (desc->action && (desc->action->flags & SA_SHIRQ)) + if (desc->action && (desc->action->flags & IRQF_SHARED)) desc->status |= IRQ_PENDING; spin_unlock(&desc->lock); continue; } /* Honour the normal IRQ locking */ desc->status |= IRQ_INPROGRESS; + action = desc->action; spin_unlock(&desc->lock); + while (action) { /* Only shared IRQ handlers are safe to call */ - if (action->flags & SA_SHIRQ) { + if (action->flags & IRQF_SHARED) { if (action->handler(i, action->dev_id, regs) == IRQ_HANDLED) ok = 1; @@ -62,9 +62,8 @@ static int misrouted_irq(int irq, struct pt_regs *regs) /* * While we were looking for a fixup someone queued a real - * IRQ clashing with our walk + * IRQ clashing with our walk: */ - while ((desc->status & IRQ_PENDING) && action) { /* * Perform real IRQ processing for the IRQ we deferred @@ -80,8 +79,8 @@ static int misrouted_irq(int irq, struct pt_regs *regs) * If we did actual work for the real IRQ line we must let the * IRQ controller clean up too */ - if(work) - desc->handler->end(i); + if (work && desc->chip && desc->chip->end) + desc->chip->end(i); spin_unlock(&desc->lock); } /* So the caller can adjust the irq error counts */ @@ -100,7 +99,8 @@ static int misrouted_irq(int irq, struct pt_regs *regs) */ static void -__report_bad_irq(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret) +__report_bad_irq(unsigned int irq, struct irq_desc *desc, + irqreturn_t action_ret) { struct irqaction *action; @@ -113,6 +113,7 @@ __report_bad_irq(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret) } dump_stack(); printk(KERN_ERR "handlers:\n"); + action = desc->action; while (action) { printk(KERN_ERR "[<%p>]", action->handler); @@ -123,7 +124,8 @@ __report_bad_irq(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret) } } -static void report_bad_irq(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret) +static void +report_bad_irq(unsigned int irq, struct irq_desc *desc, irqreturn_t action_ret) { static int count = 100; @@ -133,8 +135,8 @@ static void report_bad_irq(unsigned int irq, irq_desc_t *desc, irqreturn_t actio } } -void note_interrupt(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret, - struct pt_regs *regs) +void note_interrupt(unsigned int irq, struct irq_desc *desc, + irqreturn_t action_ret, struct pt_regs *regs) { if (unlikely(action_ret != IRQ_HANDLED)) { desc->irqs_unhandled++; @@ -166,7 +168,8 @@ void note_interrupt(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret, */ printk(KERN_EMERG "Disabling IRQ #%d\n", irq); desc->status |= IRQ_DISABLED; - desc->handler->disable(irq); + desc->depth = 1; + desc->chip->disable(irq); } desc->irqs_unhandled = 0; } @@ -177,6 +180,7 @@ int __init noirqdebug_setup(char *str) { noirqdebug = 1; printk(KERN_INFO "IRQ lockup detection disabled\n"); + return 1; } @@ -187,6 +191,7 @@ static int __init irqfixup_setup(char *str) irqfixup = 1; printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n"); printk(KERN_WARNING "This may impact system performance.\n"); + return 1; } diff --git a/kernel/kexec.c b/kernel/kexec.c index 58f0f382597..50087ecf337 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1042,7 +1042,6 @@ asmlinkage long compat_sys_kexec_load(unsigned long entry, void crash_kexec(struct pt_regs *regs) { - struct kimage *image; int locked; @@ -1056,12 +1055,11 @@ void crash_kexec(struct pt_regs *regs) */ locked = xchg(&kexec_lock, 1); if (!locked) { - image = xchg(&kexec_crash_image, NULL); - if (image) { + if (kexec_crash_image) { struct pt_regs fixed_regs; crash_setup_regs(&fixed_regs, regs); machine_crash_shutdown(&fixed_regs); - machine_kexec(image); + machine_kexec(kexec_crash_image); } xchg(&kexec_lock, 0); } diff --git a/kernel/kmod.c b/kernel/kmod.c index 20a997c73c3..1d32defa38a 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -20,7 +20,6 @@ */ #define __KERNEL_SYSCALLS__ -#include <linux/config.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/syscalls.h> @@ -234,7 +233,7 @@ static void __call_usermodehelper(void *data) int call_usermodehelper_keys(char *path, char **argv, char **envp, struct key *session_keyring, int wait) { - DECLARE_COMPLETION(done); + DECLARE_COMPLETION_ONSTACK(done); struct subprocess_info sub_info = { .complete = &done, .path = path, diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 9e28478a17a..e0ffe4ab091 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -8,7 +8,6 @@ * */ -#include <linux/config.h> #include <linux/kobject.h> #include <linux/string.h> #include <linux/sysfs.h> diff --git a/kernel/lockdep.c b/kernel/lockdep.c new file mode 100644 index 00000000000..f32ca78c198 --- /dev/null +++ b/kernel/lockdep.c @@ -0,0 +1,2702 @@ +/* + * kernel/lockdep.c + * + * Runtime locking correctness validator + * + * Started by Ingo Molnar: + * + * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * + * this code maps all the lock dependencies as they occur in a live kernel + * and will warn about the following classes of locking bugs: + * + * - lock inversion scenarios + * - circular lock dependencies + * - hardirq/softirq safe/unsafe locking bugs + * + * Bugs are reported even if the current locking scenario does not cause + * any deadlock at this point. + * + * I.e. if anytime in the past two locks were taken in a different order, + * even if it happened for another task, even if those were different + * locks (but of the same class as this lock), this code will detect it. + * + * Thanks to Arjan van de Ven for coming up with the initial idea of + * mapping lock dependencies runtime. + */ +#include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/spinlock.h> +#include <linux/kallsyms.h> +#include <linux/interrupt.h> +#include <linux/stacktrace.h> +#include <linux/debug_locks.h> +#include <linux/irqflags.h> + +#include <asm/sections.h> + +#include "lockdep_internals.h" + +/* + * hash_lock: protects the lockdep hashes and class/list/hash allocators. + * + * This is one of the rare exceptions where it's justified + * to use a raw spinlock - we really dont want the spinlock + * code to recurse back into the lockdep code. + */ +static raw_spinlock_t hash_lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; + +static int lockdep_initialized; + +unsigned long nr_list_entries; +static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES]; + +/* + * Allocate a lockdep entry. (assumes hash_lock held, returns + * with NULL on failure) + */ +static struct lock_list *alloc_list_entry(void) +{ + if (nr_list_entries >= MAX_LOCKDEP_ENTRIES) { + __raw_spin_unlock(&hash_lock); + debug_locks_off(); + printk("BUG: MAX_LOCKDEP_ENTRIES too low!\n"); + printk("turning off the locking correctness validator.\n"); + return NULL; + } + return list_entries + nr_list_entries++; +} + +/* + * All data structures here are protected by the global debug_lock. + * + * Mutex key structs only get allocated, once during bootup, and never + * get freed - this significantly simplifies the debugging code. + */ +unsigned long nr_lock_classes; +static struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; + +/* + * We keep a global list of all lock classes. The list only grows, + * never shrinks. The list is only accessed with the lockdep + * spinlock lock held. + */ +LIST_HEAD(all_lock_classes); + +/* + * The lockdep classes are in a hash-table as well, for fast lookup: + */ +#define CLASSHASH_BITS (MAX_LOCKDEP_KEYS_BITS - 1) +#define CLASSHASH_SIZE (1UL << CLASSHASH_BITS) +#define CLASSHASH_MASK (CLASSHASH_SIZE - 1) +#define __classhashfn(key) ((((unsigned long)key >> CLASSHASH_BITS) + (unsigned long)key) & CLASSHASH_MASK) +#define classhashentry(key) (classhash_table + __classhashfn((key))) + +static struct list_head classhash_table[CLASSHASH_SIZE]; + +unsigned long nr_lock_chains; +static struct lock_chain lock_chains[MAX_LOCKDEP_CHAINS]; + +/* + * We put the lock dependency chains into a hash-table as well, to cache + * their existence: + */ +#define CHAINHASH_BITS (MAX_LOCKDEP_CHAINS_BITS-1) +#define CHAINHASH_SIZE (1UL << CHAINHASH_BITS) +#define CHAINHASH_MASK (CHAINHASH_SIZE - 1) +#define __chainhashfn(chain) \ + (((chain >> CHAINHASH_BITS) + chain) & CHAINHASH_MASK) +#define chainhashentry(chain) (chainhash_table + __chainhashfn((chain))) + +static struct list_head chainhash_table[CHAINHASH_SIZE]; + +/* + * The hash key of the lock dependency chains is a hash itself too: + * it's a hash of all locks taken up to that lock, including that lock. + * It's a 64-bit hash, because it's important for the keys to be + * unique. + */ +#define iterate_chain_key(key1, key2) \ + (((key1) << MAX_LOCKDEP_KEYS_BITS/2) ^ \ + ((key1) >> (64-MAX_LOCKDEP_KEYS_BITS/2)) ^ \ + (key2)) + +void lockdep_off(void) +{ + current->lockdep_recursion++; +} + +EXPORT_SYMBOL(lockdep_off); + +void lockdep_on(void) +{ + current->lockdep_recursion--; +} + +EXPORT_SYMBOL(lockdep_on); + +int lockdep_internal(void) +{ + return current->lockdep_recursion != 0; +} + +EXPORT_SYMBOL(lockdep_internal); + +/* + * Debugging switches: + */ + +#define VERBOSE 0 +#ifdef VERBOSE +# define VERY_VERBOSE 0 +#endif + +#if VERBOSE +# define HARDIRQ_VERBOSE 1 +# define SOFTIRQ_VERBOSE 1 +#else +# define HARDIRQ_VERBOSE 0 +# define SOFTIRQ_VERBOSE 0 +#endif + +#if VERBOSE || HARDIRQ_VERBOSE || SOFTIRQ_VERBOSE +/* + * Quick filtering for interesting events: + */ +static int class_filter(struct lock_class *class) +{ + if (class->name_version == 1 && + !strcmp(class->name, "&rl->lock")) + return 1; + if (class->name_version == 1 && + !strcmp(class->name, "&ni->mrec_lock")) + return 1; + if (class->name_version == 1 && + !strcmp(class->name, "mft_ni_runlist_lock")) + return 1; + if (class->name_version == 1 && + !strcmp(class->name, "mft_ni_mrec_lock")) + return 1; + if (class->name_version == 1 && + !strcmp(class->name, "&vol->lcnbmp_lock")) + return 1; + return 0; +} +#endif + +static int verbose(struct lock_class *class) +{ +#if VERBOSE + return class_filter(class); +#endif + return 0; +} + +#ifdef CONFIG_TRACE_IRQFLAGS + +static int hardirq_verbose(struct lock_class *class) +{ +#if HARDIRQ_VERBOSE + return class_filter(class); +#endif + return 0; +} + +static int softirq_verbose(struct lock_class *class) +{ +#if SOFTIRQ_VERBOSE + return class_filter(class); +#endif + return 0; +} + +#endif + +/* + * Stack-trace: tightly packed array of stack backtrace + * addresses. Protected by the hash_lock. + */ +unsigned long nr_stack_trace_entries; +static unsigned long stack_trace[MAX_STACK_TRACE_ENTRIES]; + +static int save_trace(struct stack_trace *trace) +{ + trace->nr_entries = 0; + trace->max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries; + trace->entries = stack_trace + nr_stack_trace_entries; + + save_stack_trace(trace, NULL, 0, 3); + + trace->max_entries = trace->nr_entries; + + nr_stack_trace_entries += trace->nr_entries; + if (DEBUG_LOCKS_WARN_ON(nr_stack_trace_entries > MAX_STACK_TRACE_ENTRIES)) + return 0; + + if (nr_stack_trace_entries == MAX_STACK_TRACE_ENTRIES) { + __raw_spin_unlock(&hash_lock); + if (debug_locks_off()) { + printk("BUG: MAX_STACK_TRACE_ENTRIES too low!\n"); + printk("turning off the locking correctness validator.\n"); + dump_stack(); + } + return 0; + } + + return 1; +} + +unsigned int nr_hardirq_chains; +unsigned int nr_softirq_chains; +unsigned int nr_process_chains; +unsigned int max_lockdep_depth; +unsigned int max_recursion_depth; + +#ifdef CONFIG_DEBUG_LOCKDEP +/* + * We cannot printk in early bootup code. Not even early_printk() + * might work. So we mark any initialization errors and printk + * about it later on, in lockdep_info(). + */ +static int lockdep_init_error; + +/* + * Various lockdep statistics: + */ +atomic_t chain_lookup_hits; +atomic_t chain_lookup_misses; +atomic_t hardirqs_on_events; +atomic_t hardirqs_off_events; +atomic_t redundant_hardirqs_on; +atomic_t redundant_hardirqs_off; +atomic_t softirqs_on_events; +atomic_t softirqs_off_events; +atomic_t redundant_softirqs_on; +atomic_t redundant_softirqs_off; +atomic_t nr_unused_locks; +atomic_t nr_cyclic_checks; +atomic_t nr_cyclic_check_recursions; +atomic_t nr_find_usage_forwards_checks; +atomic_t nr_find_usage_forwards_recursions; +atomic_t nr_find_usage_backwards_checks; +atomic_t nr_find_usage_backwards_recursions; +# define debug_atomic_inc(ptr) atomic_inc(ptr) +# define debug_atomic_dec(ptr) atomic_dec(ptr) +# define debug_atomic_read(ptr) atomic_read(ptr) +#else +# define debug_atomic_inc(ptr) do { } while (0) +# define debug_atomic_dec(ptr) do { } while (0) +# define debug_atomic_read(ptr) 0 +#endif + +/* + * Locking printouts: + */ + +static const char *usage_str[] = +{ + [LOCK_USED] = "initial-use ", + [LOCK_USED_IN_HARDIRQ] = "in-hardirq-W", + [LOCK_USED_IN_SOFTIRQ] = "in-softirq-W", + [LOCK_ENABLED_SOFTIRQS] = "softirq-on-W", + [LOCK_ENABLED_HARDIRQS] = "hardirq-on-W", + [LOCK_USED_IN_HARDIRQ_READ] = "in-hardirq-R", + [LOCK_USED_IN_SOFTIRQ_READ] = "in-softirq-R", + [LOCK_ENABLED_SOFTIRQS_READ] = "softirq-on-R", + [LOCK_ENABLED_HARDIRQS_READ] = "hardirq-on-R", +}; + +const char * __get_key_name(struct lockdep_subclass_key *key, char *str) +{ + unsigned long offs, size; + char *modname; + + return kallsyms_lookup((unsigned long)key, &size, &offs, &modname, str); +} + +void +get_usage_chars(struct lock_class *class, char *c1, char *c2, char *c3, char *c4) +{ + *c1 = '.', *c2 = '.', *c3 = '.', *c4 = '.'; + + if (class->usage_mask & LOCKF_USED_IN_HARDIRQ) + *c1 = '+'; + else + if (class->usage_mask & LOCKF_ENABLED_HARDIRQS) + *c1 = '-'; + + if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ) + *c2 = '+'; + else + if (class->usage_mask & LOCKF_ENABLED_SOFTIRQS) + *c2 = '-'; + + if (class->usage_mask & LOCKF_ENABLED_HARDIRQS_READ) + *c3 = '-'; + if (class->usage_mask & LOCKF_USED_IN_HARDIRQ_READ) { + *c3 = '+'; + if (class->usage_mask & LOCKF_ENABLED_HARDIRQS_READ) + *c3 = '?'; + } + + if (class->usage_mask & LOCKF_ENABLED_SOFTIRQS_READ) + *c4 = '-'; + if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ_READ) { + *c4 = '+'; + if (class->usage_mask & LOCKF_ENABLED_SOFTIRQS_READ) + *c4 = '?'; + } +} + +static void print_lock_name(struct lock_class *class) +{ + char str[128], c1, c2, c3, c4; + const char *name; + + get_usage_chars(class, &c1, &c2, &c3, &c4); + + name = class->name; + if (!name) { + name = __get_key_name(class->key, str); + printk(" (%s", name); + } else { + printk(" (%s", name); + if (class->name_version > 1) + printk("#%d", class->name_version); + if (class->subclass) + printk("/%d", class->subclass); + } + printk("){%c%c%c%c}", c1, c2, c3, c4); +} + +static void print_lockdep_cache(struct lockdep_map *lock) +{ + const char *name; + char str[128]; + + name = lock->name; + if (!name) + name = __get_key_name(lock->key->subkeys, str); + + printk("%s", name); +} + +static void print_lock(struct held_lock *hlock) +{ + print_lock_name(hlock->class); + printk(", at: "); + print_ip_sym(hlock->acquire_ip); +} + +static void lockdep_print_held_locks(struct task_struct *curr) +{ + int i, depth = curr->lockdep_depth; + + if (!depth) { + printk("no locks held by %s/%d.\n", curr->comm, curr->pid); + return; + } + printk("%d lock%s held by %s/%d:\n", + depth, depth > 1 ? "s" : "", curr->comm, curr->pid); + + for (i = 0; i < depth; i++) { + printk(" #%d: ", i); + print_lock(curr->held_locks + i); + } +} +/* + * Helper to print a nice hierarchy of lock dependencies: + */ +static void print_spaces(int nr) +{ + int i; + + for (i = 0; i < nr; i++) + printk(" "); +} + +static void print_lock_class_header(struct lock_class *class, int depth) +{ + int bit; + + print_spaces(depth); + printk("->"); + print_lock_name(class); + printk(" ops: %lu", class->ops); + printk(" {\n"); + + for (bit = 0; bit < LOCK_USAGE_STATES; bit++) { + if (class->usage_mask & (1 << bit)) { + int len = depth; + + print_spaces(depth); + len += printk(" %s", usage_str[bit]); + len += printk(" at:\n"); + print_stack_trace(class->usage_traces + bit, len); + } + } + print_spaces(depth); + printk(" }\n"); + + print_spaces(depth); + printk(" ... key at: "); + print_ip_sym((unsigned long)class->key); +} + +/* + * printk all lock dependencies starting at <entry>: + */ +static void print_lock_dependencies(struct lock_class *class, int depth) +{ + struct lock_list *entry; + + if (DEBUG_LOCKS_WARN_ON(depth >= 20)) + return; + + print_lock_class_header(class, depth); + + list_for_each_entry(entry, &class->locks_after, entry) { + DEBUG_LOCKS_WARN_ON(!entry->class); + print_lock_dependencies(entry->class, depth + 1); + + print_spaces(depth); + printk(" ... acquired at:\n"); + print_stack_trace(&entry->trace, 2); + printk("\n"); + } +} + +/* + * Add a new dependency to the head of the list: + */ +static int add_lock_to_list(struct lock_class *class, struct lock_class *this, + struct list_head *head, unsigned long ip) +{ + struct lock_list *entry; + /* + * Lock not present yet - get a new dependency struct and + * add it to the list: + */ + entry = alloc_list_entry(); + if (!entry) + return 0; + + entry->class = this; + save_trace(&entry->trace); + + /* + * Since we never remove from the dependency list, the list can + * be walked lockless by other CPUs, it's only allocation + * that must be protected by the spinlock. But this also means + * we must make new entries visible only once writes to the + * entry become visible - hence the RCU op: + */ + list_add_tail_rcu(&entry->entry, head); + + return 1; +} + +/* + * Recursive, forwards-direction lock-dependency checking, used for + * both noncyclic checking and for hardirq-unsafe/softirq-unsafe + * checking. + * + * (to keep the stackframe of the recursive functions small we + * use these global variables, and we also mark various helper + * functions as noinline.) + */ +static struct held_lock *check_source, *check_target; + +/* + * Print a dependency chain entry (this is only done when a deadlock + * has been detected): + */ +static noinline int +print_circular_bug_entry(struct lock_list *target, unsigned int depth) +{ + if (debug_locks_silent) + return 0; + printk("\n-> #%u", depth); + print_lock_name(target->class); + printk(":\n"); + print_stack_trace(&target->trace, 6); + + return 0; +} + +/* + * When a circular dependency is detected, print the + * header first: + */ +static noinline int +print_circular_bug_header(struct lock_list *entry, unsigned int depth) +{ + struct task_struct *curr = current; + + __raw_spin_unlock(&hash_lock); + debug_locks_off(); + if (debug_locks_silent) + return 0; + + printk("\n=======================================================\n"); + printk( "[ INFO: possible circular locking dependency detected ]\n"); + printk( "-------------------------------------------------------\n"); + printk("%s/%d is trying to acquire lock:\n", + curr->comm, curr->pid); + print_lock(check_source); + printk("\nbut task is already holding lock:\n"); + print_lock(check_target); + printk("\nwhich lock already depends on the new lock.\n\n"); + printk("\nthe existing dependency chain (in reverse order) is:\n"); + + print_circular_bug_entry(entry, depth); + + return 0; +} + +static noinline int print_circular_bug_tail(void) +{ + struct task_struct *curr = current; + struct lock_list this; + + if (debug_locks_silent) + return 0; + + this.class = check_source->class; + save_trace(&this.trace); + print_circular_bug_entry(&this, 0); + + printk("\nother info that might help us debug this:\n\n"); + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +static int noinline print_infinite_recursion_bug(void) +{ + __raw_spin_unlock(&hash_lock); + DEBUG_LOCKS_WARN_ON(1); + + return 0; +} + +/* + * Prove that the dependency graph starting at <entry> can not + * lead to <target>. Print an error and return 0 if it does. + */ +static noinline int +check_noncircular(struct lock_class *source, unsigned int depth) +{ + struct lock_list *entry; + + debug_atomic_inc(&nr_cyclic_check_recursions); + if (depth > max_recursion_depth) + max_recursion_depth = depth; + if (depth >= 20) + return print_infinite_recursion_bug(); + /* + * Check this lock's dependency list: + */ + list_for_each_entry(entry, &source->locks_after, entry) { + if (entry->class == check_target->class) + return print_circular_bug_header(entry, depth+1); + debug_atomic_inc(&nr_cyclic_checks); + if (!check_noncircular(entry->class, depth+1)) + return print_circular_bug_entry(entry, depth+1); + } + return 1; +} + +static int very_verbose(struct lock_class *class) +{ +#if VERY_VERBOSE + return class_filter(class); +#endif + return 0; +} +#ifdef CONFIG_TRACE_IRQFLAGS + +/* + * Forwards and backwards subgraph searching, for the purposes of + * proving that two subgraphs can be connected by a new dependency + * without creating any illegal irq-safe -> irq-unsafe lock dependency. + */ +static enum lock_usage_bit find_usage_bit; +static struct lock_class *forwards_match, *backwards_match; + +/* + * Find a node in the forwards-direction dependency sub-graph starting + * at <source> that matches <find_usage_bit>. + * + * Return 2 if such a node exists in the subgraph, and put that node + * into <forwards_match>. + * + * Return 1 otherwise and keep <forwards_match> unchanged. + * Return 0 on error. + */ +static noinline int +find_usage_forwards(struct lock_class *source, unsigned int depth) +{ + struct lock_list *entry; + int ret; + + if (depth > max_recursion_depth) + max_recursion_depth = depth; + if (depth >= 20) + return print_infinite_recursion_bug(); + + debug_atomic_inc(&nr_find_usage_forwards_checks); + if (source->usage_mask & (1 << find_usage_bit)) { + forwards_match = source; + return 2; + } + + /* + * Check this lock's dependency list: + */ + list_for_each_entry(entry, &source->locks_after, entry) { + debug_atomic_inc(&nr_find_usage_forwards_recursions); + ret = find_usage_forwards(entry->class, depth+1); + if (ret == 2 || ret == 0) + return ret; + } + return 1; +} + +/* + * Find a node in the backwards-direction dependency sub-graph starting + * at <source> that matches <find_usage_bit>. + * + * Return 2 if such a node exists in the subgraph, and put that node + * into <backwards_match>. + * + * Return 1 otherwise and keep <backwards_match> unchanged. + * Return 0 on error. + */ +static noinline int +find_usage_backwards(struct lock_class *source, unsigned int depth) +{ + struct lock_list *entry; + int ret; + + if (depth > max_recursion_depth) + max_recursion_depth = depth; + if (depth >= 20) + return print_infinite_recursion_bug(); + + debug_atomic_inc(&nr_find_usage_backwards_checks); + if (source->usage_mask & (1 << find_usage_bit)) { + backwards_match = source; + return 2; + } + + /* + * Check this lock's dependency list: + */ + list_for_each_entry(entry, &source->locks_before, entry) { + debug_atomic_inc(&nr_find_usage_backwards_recursions); + ret = find_usage_backwards(entry->class, depth+1); + if (ret == 2 || ret == 0) + return ret; + } + return 1; +} + +static int +print_bad_irq_dependency(struct task_struct *curr, + struct held_lock *prev, + struct held_lock *next, + enum lock_usage_bit bit1, + enum lock_usage_bit bit2, + const char *irqclass) +{ + __raw_spin_unlock(&hash_lock); + debug_locks_off(); + if (debug_locks_silent) + return 0; + + printk("\n======================================================\n"); + printk( "[ INFO: %s-safe -> %s-unsafe lock order detected ]\n", + irqclass, irqclass); + printk( "------------------------------------------------------\n"); + printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n", + curr->comm, curr->pid, + curr->hardirq_context, hardirq_count() >> HARDIRQ_SHIFT, + curr->softirq_context, softirq_count() >> SOFTIRQ_SHIFT, + curr->hardirqs_enabled, + curr->softirqs_enabled); + print_lock(next); + + printk("\nand this task is already holding:\n"); + print_lock(prev); + printk("which would create a new lock dependency:\n"); + print_lock_name(prev->class); + printk(" ->"); + print_lock_name(next->class); + printk("\n"); + + printk("\nbut this new dependency connects a %s-irq-safe lock:\n", + irqclass); + print_lock_name(backwards_match); + printk("\n... which became %s-irq-safe at:\n", irqclass); + + print_stack_trace(backwards_match->usage_traces + bit1, 1); + + printk("\nto a %s-irq-unsafe lock:\n", irqclass); + print_lock_name(forwards_match); + printk("\n... which became %s-irq-unsafe at:\n", irqclass); + printk("..."); + + print_stack_trace(forwards_match->usage_traces + bit2, 1); + + printk("\nother info that might help us debug this:\n\n"); + lockdep_print_held_locks(curr); + + printk("\nthe %s-irq-safe lock's dependencies:\n", irqclass); + print_lock_dependencies(backwards_match, 0); + + printk("\nthe %s-irq-unsafe lock's dependencies:\n", irqclass); + print_lock_dependencies(forwards_match, 0); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +static int +check_usage(struct task_struct *curr, struct held_lock *prev, + struct held_lock *next, enum lock_usage_bit bit_backwards, + enum lock_usage_bit bit_forwards, const char *irqclass) +{ + int ret; + + find_usage_bit = bit_backwards; + /* fills in <backwards_match> */ + ret = find_usage_backwards(prev->class, 0); + if (!ret || ret == 1) + return ret; + + find_usage_bit = bit_forwards; + ret = find_usage_forwards(next->class, 0); + if (!ret || ret == 1) + return ret; + /* ret == 2 */ + return print_bad_irq_dependency(curr, prev, next, + bit_backwards, bit_forwards, irqclass); +} + +#endif + +static int +print_deadlock_bug(struct task_struct *curr, struct held_lock *prev, + struct held_lock *next) +{ + debug_locks_off(); + __raw_spin_unlock(&hash_lock); + if (debug_locks_silent) + return 0; + + printk("\n=============================================\n"); + printk( "[ INFO: possible recursive locking detected ]\n"); + printk( "---------------------------------------------\n"); + printk("%s/%d is trying to acquire lock:\n", + curr->comm, curr->pid); + print_lock(next); + printk("\nbut task is already holding lock:\n"); + print_lock(prev); + + printk("\nother info that might help us debug this:\n"); + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +/* + * Check whether we are holding such a class already. + * + * (Note that this has to be done separately, because the graph cannot + * detect such classes of deadlocks.) + * + * Returns: 0 on deadlock detected, 1 on OK, 2 on recursive read + */ +static int +check_deadlock(struct task_struct *curr, struct held_lock *next, + struct lockdep_map *next_instance, int read) +{ + struct held_lock *prev; + int i; + + for (i = 0; i < curr->lockdep_depth; i++) { + prev = curr->held_locks + i; + if (prev->class != next->class) + continue; + /* + * Allow read-after-read recursion of the same + * lock class (i.e. read_lock(lock)+read_lock(lock)): + */ + if ((read == 2) && prev->read) + return 2; + return print_deadlock_bug(curr, prev, next); + } + return 1; +} + +/* + * There was a chain-cache miss, and we are about to add a new dependency + * to a previous lock. We recursively validate the following rules: + * + * - would the adding of the <prev> -> <next> dependency create a + * circular dependency in the graph? [== circular deadlock] + * + * - does the new prev->next dependency connect any hardirq-safe lock + * (in the full backwards-subgraph starting at <prev>) with any + * hardirq-unsafe lock (in the full forwards-subgraph starting at + * <next>)? [== illegal lock inversion with hardirq contexts] + * + * - does the new prev->next dependency connect any softirq-safe lock + * (in the full backwards-subgraph starting at <prev>) with any + * softirq-unsafe lock (in the full forwards-subgraph starting at + * <next>)? [== illegal lock inversion with softirq contexts] + * + * any of these scenarios could lead to a deadlock. + * + * Then if all the validations pass, we add the forwards and backwards + * dependency. + */ +static int +check_prev_add(struct task_struct *curr, struct held_lock *prev, + struct held_lock *next) +{ + struct lock_list *entry; + int ret; + + /* + * Prove that the new <prev> -> <next> dependency would not + * create a circular dependency in the graph. (We do this by + * forward-recursing into the graph starting at <next>, and + * checking whether we can reach <prev>.) + * + * We are using global variables to control the recursion, to + * keep the stackframe size of the recursive functions low: + */ + check_source = next; + check_target = prev; + if (!(check_noncircular(next->class, 0))) + return print_circular_bug_tail(); + +#ifdef CONFIG_TRACE_IRQFLAGS + /* + * Prove that the new dependency does not connect a hardirq-safe + * lock with a hardirq-unsafe lock - to achieve this we search + * the backwards-subgraph starting at <prev>, and the + * forwards-subgraph starting at <next>: + */ + if (!check_usage(curr, prev, next, LOCK_USED_IN_HARDIRQ, + LOCK_ENABLED_HARDIRQS, "hard")) + return 0; + + /* + * Prove that the new dependency does not connect a hardirq-safe-read + * lock with a hardirq-unsafe lock - to achieve this we search + * the backwards-subgraph starting at <prev>, and the + * forwards-subgraph starting at <next>: + */ + if (!check_usage(curr, prev, next, LOCK_USED_IN_HARDIRQ_READ, + LOCK_ENABLED_HARDIRQS, "hard-read")) + return 0; + + /* + * Prove that the new dependency does not connect a softirq-safe + * lock with a softirq-unsafe lock - to achieve this we search + * the backwards-subgraph starting at <prev>, and the + * forwards-subgraph starting at <next>: + */ + if (!check_usage(curr, prev, next, LOCK_USED_IN_SOFTIRQ, + LOCK_ENABLED_SOFTIRQS, "soft")) + return 0; + /* + * Prove that the new dependency does not connect a softirq-safe-read + * lock with a softirq-unsafe lock - to achieve this we search + * the backwards-subgraph starting at <prev>, and the + * forwards-subgraph starting at <next>: + */ + if (!check_usage(curr, prev, next, LOCK_USED_IN_SOFTIRQ_READ, + LOCK_ENABLED_SOFTIRQS, "soft")) + return 0; +#endif + /* + * For recursive read-locks we do all the dependency checks, + * but we dont store read-triggered dependencies (only + * write-triggered dependencies). This ensures that only the + * write-side dependencies matter, and that if for example a + * write-lock never takes any other locks, then the reads are + * equivalent to a NOP. + */ + if (next->read == 2 || prev->read == 2) + return 1; + /* + * Is the <prev> -> <next> dependency already present? + * + * (this may occur even though this is a new chain: consider + * e.g. the L1 -> L2 -> L3 -> L4 and the L5 -> L1 -> L2 -> L3 + * chains - the second one will be new, but L1 already has + * L2 added to its dependency list, due to the first chain.) + */ + list_for_each_entry(entry, &prev->class->locks_after, entry) { + if (entry->class == next->class) + return 2; + } + + /* + * Ok, all validations passed, add the new lock + * to the previous lock's dependency list: + */ + ret = add_lock_to_list(prev->class, next->class, + &prev->class->locks_after, next->acquire_ip); + if (!ret) + return 0; + /* + * Return value of 2 signals 'dependency already added', + * in that case we dont have to add the backlink either. + */ + if (ret == 2) + return 2; + ret = add_lock_to_list(next->class, prev->class, + &next->class->locks_before, next->acquire_ip); + + /* + * Debugging printouts: + */ + if (verbose(prev->class) || verbose(next->class)) { + __raw_spin_unlock(&hash_lock); + printk("\n new dependency: "); + print_lock_name(prev->class); + printk(" => "); + print_lock_name(next->class); + printk("\n"); + dump_stack(); + __raw_spin_lock(&hash_lock); + } + return 1; +} + +/* + * Add the dependency to all directly-previous locks that are 'relevant'. + * The ones that are relevant are (in increasing distance from curr): + * all consecutive trylock entries and the final non-trylock entry - or + * the end of this context's lock-chain - whichever comes first. + */ +static int +check_prevs_add(struct task_struct *curr, struct held_lock *next) +{ + int depth = curr->lockdep_depth; + struct held_lock *hlock; + + /* + * Debugging checks. + * + * Depth must not be zero for a non-head lock: + */ + if (!depth) + goto out_bug; + /* + * At least two relevant locks must exist for this + * to be a head: + */ + if (curr->held_locks[depth].irq_context != + curr->held_locks[depth-1].irq_context) + goto out_bug; + + for (;;) { + hlock = curr->held_locks + depth-1; + /* + * Only non-recursive-read entries get new dependencies + * added: + */ + if (hlock->read != 2) { + check_prev_add(curr, hlock, next); + /* + * Stop after the first non-trylock entry, + * as non-trylock entries have added their + * own direct dependencies already, so this + * lock is connected to them indirectly: + */ + if (!hlock->trylock) + break; + } + depth--; + /* + * End of lock-stack? + */ + if (!depth) + break; + /* + * Stop the search if we cross into another context: + */ + if (curr->held_locks[depth].irq_context != + curr->held_locks[depth-1].irq_context) + break; + } + return 1; +out_bug: + __raw_spin_unlock(&hash_lock); + DEBUG_LOCKS_WARN_ON(1); + + return 0; +} + + +/* + * Is this the address of a static object: + */ +static int static_obj(void *obj) +{ + unsigned long start = (unsigned long) &_stext, + end = (unsigned long) &_end, + addr = (unsigned long) obj; +#ifdef CONFIG_SMP + int i; +#endif + + /* + * static variable? + */ + if ((addr >= start) && (addr < end)) + return 1; + +#ifdef CONFIG_SMP + /* + * percpu var? + */ + for_each_possible_cpu(i) { + start = (unsigned long) &__per_cpu_start + per_cpu_offset(i); + end = (unsigned long) &__per_cpu_end + per_cpu_offset(i); + + if ((addr >= start) && (addr < end)) + return 1; + } +#endif + + /* + * module var? + */ + return is_module_address(addr); +} + +/* + * To make lock name printouts unique, we calculate a unique + * class->name_version generation counter: + */ +static int count_matching_names(struct lock_class *new_class) +{ + struct lock_class *class; + int count = 0; + + if (!new_class->name) + return 0; + + list_for_each_entry(class, &all_lock_classes, lock_entry) { + if (new_class->key - new_class->subclass == class->key) + return class->name_version; + if (class->name && !strcmp(class->name, new_class->name)) + count = max(count, class->name_version); + } + + return count + 1; +} + +extern void __error_too_big_MAX_LOCKDEP_SUBCLASSES(void); + +/* + * Register a lock's class in the hash-table, if the class is not present + * yet. Otherwise we look it up. We cache the result in the lock object + * itself, so actual lookup of the hash should be once per lock object. + */ +static inline struct lock_class * +register_lock_class(struct lockdep_map *lock, unsigned int subclass) +{ + struct lockdep_subclass_key *key; + struct list_head *hash_head; + struct lock_class *class; + +#ifdef CONFIG_DEBUG_LOCKDEP + /* + * If the architecture calls into lockdep before initializing + * the hashes then we'll warn about it later. (we cannot printk + * right now) + */ + if (unlikely(!lockdep_initialized)) { + lockdep_init(); + lockdep_init_error = 1; + } +#endif + + /* + * Static locks do not have their class-keys yet - for them the key + * is the lock object itself: + */ + if (unlikely(!lock->key)) + lock->key = (void *)lock; + + /* + * NOTE: the class-key must be unique. For dynamic locks, a static + * lock_class_key variable is passed in through the mutex_init() + * (or spin_lock_init()) call - which acts as the key. For static + * locks we use the lock object itself as the key. + */ + if (sizeof(struct lock_class_key) > sizeof(struct lock_class)) + __error_too_big_MAX_LOCKDEP_SUBCLASSES(); + + key = lock->key->subkeys + subclass; + + hash_head = classhashentry(key); + + /* + * We can walk the hash lockfree, because the hash only + * grows, and we are careful when adding entries to the end: + */ + list_for_each_entry(class, hash_head, hash_entry) + if (class->key == key) + goto out_set; + + /* + * Debug-check: all keys must be persistent! + */ + if (!static_obj(lock->key)) { + debug_locks_off(); + printk("INFO: trying to register non-static key.\n"); + printk("the code is fine but needs lockdep annotation.\n"); + printk("turning off the locking correctness validator.\n"); + dump_stack(); + + return NULL; + } + + __raw_spin_lock(&hash_lock); + /* + * We have to do the hash-walk again, to avoid races + * with another CPU: + */ + list_for_each_entry(class, hash_head, hash_entry) + if (class->key == key) + goto out_unlock_set; + /* + * Allocate a new key from the static array, and add it to + * the hash: + */ + if (nr_lock_classes >= MAX_LOCKDEP_KEYS) { + __raw_spin_unlock(&hash_lock); + debug_locks_off(); + printk("BUG: MAX_LOCKDEP_KEYS too low!\n"); + printk("turning off the locking correctness validator.\n"); + return NULL; + } + class = lock_classes + nr_lock_classes++; + debug_atomic_inc(&nr_unused_locks); + class->key = key; + class->name = lock->name; + class->subclass = subclass; + INIT_LIST_HEAD(&class->lock_entry); + INIT_LIST_HEAD(&class->locks_before); + INIT_LIST_HEAD(&class->locks_after); + class->name_version = count_matching_names(class); + /* + * We use RCU's safe list-add method to make + * parallel walking of the hash-list safe: + */ + list_add_tail_rcu(&class->hash_entry, hash_head); + + if (verbose(class)) { + __raw_spin_unlock(&hash_lock); + printk("\nnew class %p: %s", class->key, class->name); + if (class->name_version > 1) + printk("#%d", class->name_version); + printk("\n"); + dump_stack(); + __raw_spin_lock(&hash_lock); + } +out_unlock_set: + __raw_spin_unlock(&hash_lock); + +out_set: + lock->class[subclass] = class; + + DEBUG_LOCKS_WARN_ON(class->subclass != subclass); + + return class; +} + +/* + * Look up a dependency chain. If the key is not present yet then + * add it and return 0 - in this case the new dependency chain is + * validated. If the key is already hashed, return 1. + */ +static inline int lookup_chain_cache(u64 chain_key) +{ + struct list_head *hash_head = chainhashentry(chain_key); + struct lock_chain *chain; + + DEBUG_LOCKS_WARN_ON(!irqs_disabled()); + /* + * We can walk it lock-free, because entries only get added + * to the hash: + */ + list_for_each_entry(chain, hash_head, entry) { + if (chain->chain_key == chain_key) { +cache_hit: + debug_atomic_inc(&chain_lookup_hits); + /* + * In the debugging case, force redundant checking + * by returning 1: + */ +#ifdef CONFIG_DEBUG_LOCKDEP + __raw_spin_lock(&hash_lock); + return 1; +#endif + return 0; + } + } + /* + * Allocate a new chain entry from the static array, and add + * it to the hash: + */ + __raw_spin_lock(&hash_lock); + /* + * We have to walk the chain again locked - to avoid duplicates: + */ + list_for_each_entry(chain, hash_head, entry) { + if (chain->chain_key == chain_key) { + __raw_spin_unlock(&hash_lock); + goto cache_hit; + } + } + if (unlikely(nr_lock_chains >= MAX_LOCKDEP_CHAINS)) { + __raw_spin_unlock(&hash_lock); + debug_locks_off(); + printk("BUG: MAX_LOCKDEP_CHAINS too low!\n"); + printk("turning off the locking correctness validator.\n"); + return 0; + } + chain = lock_chains + nr_lock_chains++; + chain->chain_key = chain_key; + list_add_tail_rcu(&chain->entry, hash_head); + debug_atomic_inc(&chain_lookup_misses); +#ifdef CONFIG_TRACE_IRQFLAGS + if (current->hardirq_context) + nr_hardirq_chains++; + else { + if (current->softirq_context) + nr_softirq_chains++; + else + nr_process_chains++; + } +#else + nr_process_chains++; +#endif + + return 1; +} + +/* + * We are building curr_chain_key incrementally, so double-check + * it from scratch, to make sure that it's done correctly: + */ +static void check_chain_key(struct task_struct *curr) +{ +#ifdef CONFIG_DEBUG_LOCKDEP + struct held_lock *hlock, *prev_hlock = NULL; + unsigned int i, id; + u64 chain_key = 0; + + for (i = 0; i < curr->lockdep_depth; i++) { + hlock = curr->held_locks + i; + if (chain_key != hlock->prev_chain_key) { + debug_locks_off(); + printk("hm#1, depth: %u [%u], %016Lx != %016Lx\n", + curr->lockdep_depth, i, + (unsigned long long)chain_key, + (unsigned long long)hlock->prev_chain_key); + WARN_ON(1); + return; + } + id = hlock->class - lock_classes; + DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS); + if (prev_hlock && (prev_hlock->irq_context != + hlock->irq_context)) + chain_key = 0; + chain_key = iterate_chain_key(chain_key, id); + prev_hlock = hlock; + } + if (chain_key != curr->curr_chain_key) { + debug_locks_off(); + printk("hm#2, depth: %u [%u], %016Lx != %016Lx\n", + curr->lockdep_depth, i, + (unsigned long long)chain_key, + (unsigned long long)curr->curr_chain_key); + WARN_ON(1); + } +#endif +} + +#ifdef CONFIG_TRACE_IRQFLAGS + +/* + * print irq inversion bug: + */ +static int +print_irq_inversion_bug(struct task_struct *curr, struct lock_class *other, + struct held_lock *this, int forwards, + const char *irqclass) +{ + __raw_spin_unlock(&hash_lock); + debug_locks_off(); + if (debug_locks_silent) + return 0; + + printk("\n=========================================================\n"); + printk( "[ INFO: possible irq lock inversion dependency detected ]\n"); + printk( "---------------------------------------------------------\n"); + printk("%s/%d just changed the state of lock:\n", + curr->comm, curr->pid); + print_lock(this); + if (forwards) + printk("but this lock took another, %s-irq-unsafe lock in the past:\n", irqclass); + else + printk("but this lock was taken by another, %s-irq-safe lock in the past:\n", irqclass); + print_lock_name(other); + printk("\n\nand interrupts could create inverse lock ordering between them.\n\n"); + + printk("\nother info that might help us debug this:\n"); + lockdep_print_held_locks(curr); + + printk("\nthe first lock's dependencies:\n"); + print_lock_dependencies(this->class, 0); + + printk("\nthe second lock's dependencies:\n"); + print_lock_dependencies(other, 0); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +/* + * Prove that in the forwards-direction subgraph starting at <this> + * there is no lock matching <mask>: + */ +static int +check_usage_forwards(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit bit, const char *irqclass) +{ + int ret; + + find_usage_bit = bit; + /* fills in <forwards_match> */ + ret = find_usage_forwards(this->class, 0); + if (!ret || ret == 1) + return ret; + + return print_irq_inversion_bug(curr, forwards_match, this, 1, irqclass); +} + +/* + * Prove that in the backwards-direction subgraph starting at <this> + * there is no lock matching <mask>: + */ +static int +check_usage_backwards(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit bit, const char *irqclass) +{ + int ret; + + find_usage_bit = bit; + /* fills in <backwards_match> */ + ret = find_usage_backwards(this->class, 0); + if (!ret || ret == 1) + return ret; + + return print_irq_inversion_bug(curr, backwards_match, this, 0, irqclass); +} + +static inline void print_irqtrace_events(struct task_struct *curr) +{ + printk("irq event stamp: %u\n", curr->irq_events); + printk("hardirqs last enabled at (%u): ", curr->hardirq_enable_event); + print_ip_sym(curr->hardirq_enable_ip); + printk("hardirqs last disabled at (%u): ", curr->hardirq_disable_event); + print_ip_sym(curr->hardirq_disable_ip); + printk("softirqs last enabled at (%u): ", curr->softirq_enable_event); + print_ip_sym(curr->softirq_enable_ip); + printk("softirqs last disabled at (%u): ", curr->softirq_disable_event); + print_ip_sym(curr->softirq_disable_ip); +} + +#else +static inline void print_irqtrace_events(struct task_struct *curr) +{ +} +#endif + +static int +print_usage_bug(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit prev_bit, enum lock_usage_bit new_bit) +{ + __raw_spin_unlock(&hash_lock); + debug_locks_off(); + if (debug_locks_silent) + return 0; + + printk("\n=================================\n"); + printk( "[ INFO: inconsistent lock state ]\n"); + printk( "---------------------------------\n"); + + printk("inconsistent {%s} -> {%s} usage.\n", + usage_str[prev_bit], usage_str[new_bit]); + + printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] takes:\n", + curr->comm, curr->pid, + trace_hardirq_context(curr), hardirq_count() >> HARDIRQ_SHIFT, + trace_softirq_context(curr), softirq_count() >> SOFTIRQ_SHIFT, + trace_hardirqs_enabled(curr), + trace_softirqs_enabled(curr)); + print_lock(this); + + printk("{%s} state was registered at:\n", usage_str[prev_bit]); + print_stack_trace(this->class->usage_traces + prev_bit, 1); + + print_irqtrace_events(curr); + printk("\nother info that might help us debug this:\n"); + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +/* + * Print out an error if an invalid bit is set: + */ +static inline int +valid_state(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit new_bit, enum lock_usage_bit bad_bit) +{ + if (unlikely(this->class->usage_mask & (1 << bad_bit))) + return print_usage_bug(curr, this, bad_bit, new_bit); + return 1; +} + +#define STRICT_READ_CHECKS 1 + +/* + * Mark a lock with a usage bit, and validate the state transition: + */ +static int mark_lock(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit new_bit, unsigned long ip) +{ + unsigned int new_mask = 1 << new_bit, ret = 1; + + /* + * If already set then do not dirty the cacheline, + * nor do any checks: + */ + if (likely(this->class->usage_mask & new_mask)) + return 1; + + __raw_spin_lock(&hash_lock); + /* + * Make sure we didnt race: + */ + if (unlikely(this->class->usage_mask & new_mask)) { + __raw_spin_unlock(&hash_lock); + return 1; + } + + this->class->usage_mask |= new_mask; + +#ifdef CONFIG_TRACE_IRQFLAGS + if (new_bit == LOCK_ENABLED_HARDIRQS || + new_bit == LOCK_ENABLED_HARDIRQS_READ) + ip = curr->hardirq_enable_ip; + else if (new_bit == LOCK_ENABLED_SOFTIRQS || + new_bit == LOCK_ENABLED_SOFTIRQS_READ) + ip = curr->softirq_enable_ip; +#endif + if (!save_trace(this->class->usage_traces + new_bit)) + return 0; + + switch (new_bit) { +#ifdef CONFIG_TRACE_IRQFLAGS + case LOCK_USED_IN_HARDIRQ: + if (!valid_state(curr, this, new_bit, LOCK_ENABLED_HARDIRQS)) + return 0; + if (!valid_state(curr, this, new_bit, + LOCK_ENABLED_HARDIRQS_READ)) + return 0; + /* + * just marked it hardirq-safe, check that this lock + * took no hardirq-unsafe lock in the past: + */ + if (!check_usage_forwards(curr, this, + LOCK_ENABLED_HARDIRQS, "hard")) + return 0; +#if STRICT_READ_CHECKS + /* + * just marked it hardirq-safe, check that this lock + * took no hardirq-unsafe-read lock in the past: + */ + if (!check_usage_forwards(curr, this, + LOCK_ENABLED_HARDIRQS_READ, "hard-read")) + return 0; +#endif + if (hardirq_verbose(this->class)) + ret = 2; + break; + case LOCK_USED_IN_SOFTIRQ: + if (!valid_state(curr, this, new_bit, LOCK_ENABLED_SOFTIRQS)) + return 0; + if (!valid_state(curr, this, new_bit, + LOCK_ENABLED_SOFTIRQS_READ)) + return 0; + /* + * just marked it softirq-safe, check that this lock + * took no softirq-unsafe lock in the past: + */ + if (!check_usage_forwards(curr, this, + LOCK_ENABLED_SOFTIRQS, "soft")) + return 0; +#if STRICT_READ_CHECKS + /* + * just marked it softirq-safe, check that this lock + * took no softirq-unsafe-read lock in the past: + */ + if (!check_usage_forwards(curr, this, + LOCK_ENABLED_SOFTIRQS_READ, "soft-read")) + return 0; +#endif + if (softirq_verbose(this->class)) + ret = 2; + break; + case LOCK_USED_IN_HARDIRQ_READ: + if (!valid_state(curr, this, new_bit, LOCK_ENABLED_HARDIRQS)) + return 0; + /* + * just marked it hardirq-read-safe, check that this lock + * took no hardirq-unsafe lock in the past: + */ + if (!check_usage_forwards(curr, this, + LOCK_ENABLED_HARDIRQS, "hard")) + return 0; + if (hardirq_verbose(this->class)) + ret = 2; + break; + case LOCK_USED_IN_SOFTIRQ_READ: + if (!valid_state(curr, this, new_bit, LOCK_ENABLED_SOFTIRQS)) + return 0; + /* + * just marked it softirq-read-safe, check that this lock + * took no softirq-unsafe lock in the past: + */ + if (!check_usage_forwards(curr, this, + LOCK_ENABLED_SOFTIRQS, "soft")) + return 0; + if (softirq_verbose(this->class)) + ret = 2; + break; + case LOCK_ENABLED_HARDIRQS: + if (!valid_state(curr, this, new_bit, LOCK_USED_IN_HARDIRQ)) + return 0; + if (!valid_state(curr, this, new_bit, + LOCK_USED_IN_HARDIRQ_READ)) + return 0; + /* + * just marked it hardirq-unsafe, check that no hardirq-safe + * lock in the system ever took it in the past: + */ + if (!check_usage_backwards(curr, this, + LOCK_USED_IN_HARDIRQ, "hard")) + return 0; +#if STRICT_READ_CHECKS + /* + * just marked it hardirq-unsafe, check that no + * hardirq-safe-read lock in the system ever took + * it in the past: + */ + if (!check_usage_backwards(curr, this, + LOCK_USED_IN_HARDIRQ_READ, "hard-read")) + return 0; +#endif + if (hardirq_verbose(this->class)) + ret = 2; + break; + case LOCK_ENABLED_SOFTIRQS: + if (!valid_state(curr, this, new_bit, LOCK_USED_IN_SOFTIRQ)) + return 0; + if (!valid_state(curr, this, new_bit, + LOCK_USED_IN_SOFTIRQ_READ)) + return 0; + /* + * just marked it softirq-unsafe, check that no softirq-safe + * lock in the system ever took it in the past: + */ + if (!check_usage_backwards(curr, this, + LOCK_USED_IN_SOFTIRQ, "soft")) + return 0; +#if STRICT_READ_CHECKS + /* + * just marked it softirq-unsafe, check that no + * softirq-safe-read lock in the system ever took + * it in the past: + */ + if (!check_usage_backwards(curr, this, + LOCK_USED_IN_SOFTIRQ_READ, "soft-read")) + return 0; +#endif + if (softirq_verbose(this->class)) + ret = 2; + break; + case LOCK_ENABLED_HARDIRQS_READ: + if (!valid_state(curr, this, new_bit, LOCK_USED_IN_HARDIRQ)) + return 0; +#if STRICT_READ_CHECKS + /* + * just marked it hardirq-read-unsafe, check that no + * hardirq-safe lock in the system ever took it in the past: + */ + if (!check_usage_backwards(curr, this, + LOCK_USED_IN_HARDIRQ, "hard")) + return 0; +#endif + if (hardirq_verbose(this->class)) + ret = 2; + break; + case LOCK_ENABLED_SOFTIRQS_READ: + if (!valid_state(curr, this, new_bit, LOCK_USED_IN_SOFTIRQ)) + return 0; +#if STRICT_READ_CHECKS + /* + * just marked it softirq-read-unsafe, check that no + * softirq-safe lock in the system ever took it in the past: + */ + if (!check_usage_backwards(curr, this, + LOCK_USED_IN_SOFTIRQ, "soft")) + return 0; +#endif + if (softirq_verbose(this->class)) + ret = 2; + break; +#endif + case LOCK_USED: + /* + * Add it to the global list of classes: + */ + list_add_tail_rcu(&this->class->lock_entry, &all_lock_classes); + debug_atomic_dec(&nr_unused_locks); + break; + default: + debug_locks_off(); + WARN_ON(1); + return 0; + } + + __raw_spin_unlock(&hash_lock); + + /* + * We must printk outside of the hash_lock: + */ + if (ret == 2) { + printk("\nmarked lock as {%s}:\n", usage_str[new_bit]); + print_lock(this); + print_irqtrace_events(curr); + dump_stack(); + } + + return ret; +} + +#ifdef CONFIG_TRACE_IRQFLAGS +/* + * Mark all held locks with a usage bit: + */ +static int +mark_held_locks(struct task_struct *curr, int hardirq, unsigned long ip) +{ + enum lock_usage_bit usage_bit; + struct held_lock *hlock; + int i; + + for (i = 0; i < curr->lockdep_depth; i++) { + hlock = curr->held_locks + i; + + if (hardirq) { + if (hlock->read) + usage_bit = LOCK_ENABLED_HARDIRQS_READ; + else + usage_bit = LOCK_ENABLED_HARDIRQS; + } else { + if (hlock->read) + usage_bit = LOCK_ENABLED_SOFTIRQS_READ; + else + usage_bit = LOCK_ENABLED_SOFTIRQS; + } + if (!mark_lock(curr, hlock, usage_bit, ip)) + return 0; + } + + return 1; +} + +/* + * Debugging helper: via this flag we know that we are in + * 'early bootup code', and will warn about any invalid irqs-on event: + */ +static int early_boot_irqs_enabled; + +void early_boot_irqs_off(void) +{ + early_boot_irqs_enabled = 0; +} + +void early_boot_irqs_on(void) +{ + early_boot_irqs_enabled = 1; +} + +/* + * Hardirqs will be enabled: + */ +void trace_hardirqs_on(void) +{ + struct task_struct *curr = current; + unsigned long ip; + + if (unlikely(!debug_locks || current->lockdep_recursion)) + return; + + if (DEBUG_LOCKS_WARN_ON(unlikely(!early_boot_irqs_enabled))) + return; + + if (unlikely(curr->hardirqs_enabled)) { + debug_atomic_inc(&redundant_hardirqs_on); + return; + } + /* we'll do an OFF -> ON transition: */ + curr->hardirqs_enabled = 1; + ip = (unsigned long) __builtin_return_address(0); + + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return; + if (DEBUG_LOCKS_WARN_ON(current->hardirq_context)) + return; + /* + * We are going to turn hardirqs on, so set the + * usage bit for all held locks: + */ + if (!mark_held_locks(curr, 1, ip)) + return; + /* + * If we have softirqs enabled, then set the usage + * bit for all held locks. (disabled hardirqs prevented + * this bit from being set before) + */ + if (curr->softirqs_enabled) + if (!mark_held_locks(curr, 0, ip)) + return; + + curr->hardirq_enable_ip = ip; + curr->hardirq_enable_event = ++curr->irq_events; + debug_atomic_inc(&hardirqs_on_events); +} + +EXPORT_SYMBOL(trace_hardirqs_on); + +/* + * Hardirqs were disabled: + */ +void trace_hardirqs_off(void) +{ + struct task_struct *curr = current; + + if (unlikely(!debug_locks || current->lockdep_recursion)) + return; + + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return; + + if (curr->hardirqs_enabled) { + /* + * We have done an ON -> OFF transition: + */ + curr->hardirqs_enabled = 0; + curr->hardirq_disable_ip = _RET_IP_; + curr->hardirq_disable_event = ++curr->irq_events; + debug_atomic_inc(&hardirqs_off_events); + } else + debug_atomic_inc(&redundant_hardirqs_off); +} + +EXPORT_SYMBOL(trace_hardirqs_off); + +/* + * Softirqs will be enabled: + */ +void trace_softirqs_on(unsigned long ip) +{ + struct task_struct *curr = current; + + if (unlikely(!debug_locks)) + return; + + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return; + + if (curr->softirqs_enabled) { + debug_atomic_inc(&redundant_softirqs_on); + return; + } + + /* + * We'll do an OFF -> ON transition: + */ + curr->softirqs_enabled = 1; + curr->softirq_enable_ip = ip; + curr->softirq_enable_event = ++curr->irq_events; + debug_atomic_inc(&softirqs_on_events); + /* + * We are going to turn softirqs on, so set the + * usage bit for all held locks, if hardirqs are + * enabled too: + */ + if (curr->hardirqs_enabled) + mark_held_locks(curr, 0, ip); +} + +/* + * Softirqs were disabled: + */ +void trace_softirqs_off(unsigned long ip) +{ + struct task_struct *curr = current; + + if (unlikely(!debug_locks)) + return; + + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return; + + if (curr->softirqs_enabled) { + /* + * We have done an ON -> OFF transition: + */ + curr->softirqs_enabled = 0; + curr->softirq_disable_ip = ip; + curr->softirq_disable_event = ++curr->irq_events; + debug_atomic_inc(&softirqs_off_events); + DEBUG_LOCKS_WARN_ON(!softirq_count()); + } else + debug_atomic_inc(&redundant_softirqs_off); +} + +#endif + +/* + * Initialize a lock instance's lock-class mapping info: + */ +void lockdep_init_map(struct lockdep_map *lock, const char *name, + struct lock_class_key *key) +{ + if (unlikely(!debug_locks)) + return; + + if (DEBUG_LOCKS_WARN_ON(!key)) + return; + if (DEBUG_LOCKS_WARN_ON(!name)) + return; + /* + * Sanity check, the lock-class key must be persistent: + */ + if (!static_obj(key)) { + printk("BUG: key %p not in .data!\n", key); + DEBUG_LOCKS_WARN_ON(1); + return; + } + lock->name = name; + lock->key = key; + memset(lock->class, 0, sizeof(lock->class[0])*MAX_LOCKDEP_SUBCLASSES); +} + +EXPORT_SYMBOL_GPL(lockdep_init_map); + +/* + * This gets called for every mutex_lock*()/spin_lock*() operation. + * We maintain the dependency maps and validate the locking attempt: + */ +static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, + int trylock, int read, int check, int hardirqs_off, + unsigned long ip) +{ + struct task_struct *curr = current; + struct held_lock *hlock; + struct lock_class *class; + unsigned int depth, id; + int chain_head = 0; + u64 chain_key; + + if (unlikely(!debug_locks)) + return 0; + + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return 0; + + if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) { + debug_locks_off(); + printk("BUG: MAX_LOCKDEP_SUBCLASSES too low!\n"); + printk("turning off the locking correctness validator.\n"); + return 0; + } + + class = lock->class[subclass]; + /* not cached yet? */ + if (unlikely(!class)) { + class = register_lock_class(lock, subclass); + if (!class) + return 0; + } + debug_atomic_inc((atomic_t *)&class->ops); + if (very_verbose(class)) { + printk("\nacquire class [%p] %s", class->key, class->name); + if (class->name_version > 1) + printk("#%d", class->name_version); + printk("\n"); + dump_stack(); + } + + /* + * Add the lock to the list of currently held locks. + * (we dont increase the depth just yet, up until the + * dependency checks are done) + */ + depth = curr->lockdep_depth; + if (DEBUG_LOCKS_WARN_ON(depth >= MAX_LOCK_DEPTH)) + return 0; + + hlock = curr->held_locks + depth; + + hlock->class = class; + hlock->acquire_ip = ip; + hlock->instance = lock; + hlock->trylock = trylock; + hlock->read = read; + hlock->check = check; + hlock->hardirqs_off = hardirqs_off; + + if (check != 2) + goto out_calc_hash; +#ifdef CONFIG_TRACE_IRQFLAGS + /* + * If non-trylock use in a hardirq or softirq context, then + * mark the lock as used in these contexts: + */ + if (!trylock) { + if (read) { + if (curr->hardirq_context) + if (!mark_lock(curr, hlock, + LOCK_USED_IN_HARDIRQ_READ, ip)) + return 0; + if (curr->softirq_context) + if (!mark_lock(curr, hlock, + LOCK_USED_IN_SOFTIRQ_READ, ip)) + return 0; + } else { + if (curr->hardirq_context) + if (!mark_lock(curr, hlock, LOCK_USED_IN_HARDIRQ, ip)) + return 0; + if (curr->softirq_context) + if (!mark_lock(curr, hlock, LOCK_USED_IN_SOFTIRQ, ip)) + return 0; + } + } + if (!hardirqs_off) { + if (read) { + if (!mark_lock(curr, hlock, + LOCK_ENABLED_HARDIRQS_READ, ip)) + return 0; + if (curr->softirqs_enabled) + if (!mark_lock(curr, hlock, + LOCK_ENABLED_SOFTIRQS_READ, ip)) + return 0; + } else { + if (!mark_lock(curr, hlock, + LOCK_ENABLED_HARDIRQS, ip)) + return 0; + if (curr->softirqs_enabled) + if (!mark_lock(curr, hlock, + LOCK_ENABLED_SOFTIRQS, ip)) + return 0; + } + } +#endif + /* mark it as used: */ + if (!mark_lock(curr, hlock, LOCK_USED, ip)) + return 0; +out_calc_hash: + /* + * Calculate the chain hash: it's the combined has of all the + * lock keys along the dependency chain. We save the hash value + * at every step so that we can get the current hash easily + * after unlock. The chain hash is then used to cache dependency + * results. + * + * The 'key ID' is what is the most compact key value to drive + * the hash, not class->key. + */ + id = class - lock_classes; + if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) + return 0; + + chain_key = curr->curr_chain_key; + if (!depth) { + if (DEBUG_LOCKS_WARN_ON(chain_key != 0)) + return 0; + chain_head = 1; + } + + hlock->prev_chain_key = chain_key; + +#ifdef CONFIG_TRACE_IRQFLAGS + /* + * Keep track of points where we cross into an interrupt context: + */ + hlock->irq_context = 2*(curr->hardirq_context ? 1 : 0) + + curr->softirq_context; + if (depth) { + struct held_lock *prev_hlock; + + prev_hlock = curr->held_locks + depth-1; + /* + * If we cross into another context, reset the + * hash key (this also prevents the checking and the + * adding of the dependency to 'prev'): + */ + if (prev_hlock->irq_context != hlock->irq_context) { + chain_key = 0; + chain_head = 1; + } + } +#endif + chain_key = iterate_chain_key(chain_key, id); + curr->curr_chain_key = chain_key; + + /* + * Trylock needs to maintain the stack of held locks, but it + * does not add new dependencies, because trylock can be done + * in any order. + * + * We look up the chain_key and do the O(N^2) check and update of + * the dependencies only if this is a new dependency chain. + * (If lookup_chain_cache() returns with 1 it acquires + * hash_lock for us) + */ + if (!trylock && (check == 2) && lookup_chain_cache(chain_key)) { + /* + * Check whether last held lock: + * + * - is irq-safe, if this lock is irq-unsafe + * - is softirq-safe, if this lock is hardirq-unsafe + * + * And check whether the new lock's dependency graph + * could lead back to the previous lock. + * + * any of these scenarios could lead to a deadlock. If + * All validations + */ + int ret = check_deadlock(curr, hlock, lock, read); + + if (!ret) + return 0; + /* + * Mark recursive read, as we jump over it when + * building dependencies (just like we jump over + * trylock entries): + */ + if (ret == 2) + hlock->read = 2; + /* + * Add dependency only if this lock is not the head + * of the chain, and if it's not a secondary read-lock: + */ + if (!chain_head && ret != 2) + if (!check_prevs_add(curr, hlock)) + return 0; + __raw_spin_unlock(&hash_lock); + } + curr->lockdep_depth++; + check_chain_key(curr); + if (unlikely(curr->lockdep_depth >= MAX_LOCK_DEPTH)) { + debug_locks_off(); + printk("BUG: MAX_LOCK_DEPTH too low!\n"); + printk("turning off the locking correctness validator.\n"); + return 0; + } + if (unlikely(curr->lockdep_depth > max_lockdep_depth)) + max_lockdep_depth = curr->lockdep_depth; + + return 1; +} + +static int +print_unlock_inbalance_bug(struct task_struct *curr, struct lockdep_map *lock, + unsigned long ip) +{ + if (!debug_locks_off()) + return 0; + if (debug_locks_silent) + return 0; + + printk("\n=====================================\n"); + printk( "[ BUG: bad unlock balance detected! ]\n"); + printk( "-------------------------------------\n"); + printk("%s/%d is trying to release lock (", + curr->comm, curr->pid); + print_lockdep_cache(lock); + printk(") at:\n"); + print_ip_sym(ip); + printk("but there are no more locks to release!\n"); + printk("\nother info that might help us debug this:\n"); + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +/* + * Common debugging checks for both nested and non-nested unlock: + */ +static int check_unlock(struct task_struct *curr, struct lockdep_map *lock, + unsigned long ip) +{ + if (unlikely(!debug_locks)) + return 0; + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return 0; + + if (curr->lockdep_depth <= 0) + return print_unlock_inbalance_bug(curr, lock, ip); + + return 1; +} + +/* + * Remove the lock to the list of currently held locks in a + * potentially non-nested (out of order) manner. This is a + * relatively rare operation, as all the unlock APIs default + * to nested mode (which uses lock_release()): + */ +static int +lock_release_non_nested(struct task_struct *curr, + struct lockdep_map *lock, unsigned long ip) +{ + struct held_lock *hlock, *prev_hlock; + unsigned int depth; + int i; + + /* + * Check whether the lock exists in the current stack + * of held locks: + */ + depth = curr->lockdep_depth; + if (DEBUG_LOCKS_WARN_ON(!depth)) + return 0; + + prev_hlock = NULL; + for (i = depth-1; i >= 0; i--) { + hlock = curr->held_locks + i; + /* + * We must not cross into another context: + */ + if (prev_hlock && prev_hlock->irq_context != hlock->irq_context) + break; + if (hlock->instance == lock) + goto found_it; + prev_hlock = hlock; + } + return print_unlock_inbalance_bug(curr, lock, ip); + +found_it: + /* + * We have the right lock to unlock, 'hlock' points to it. + * Now we remove it from the stack, and add back the other + * entries (if any), recalculating the hash along the way: + */ + curr->lockdep_depth = i; + curr->curr_chain_key = hlock->prev_chain_key; + + for (i++; i < depth; i++) { + hlock = curr->held_locks + i; + if (!__lock_acquire(hlock->instance, + hlock->class->subclass, hlock->trylock, + hlock->read, hlock->check, hlock->hardirqs_off, + hlock->acquire_ip)) + return 0; + } + + if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth - 1)) + return 0; + return 1; +} + +/* + * Remove the lock to the list of currently held locks - this gets + * called on mutex_unlock()/spin_unlock*() (or on a failed + * mutex_lock_interruptible()). This is done for unlocks that nest + * perfectly. (i.e. the current top of the lock-stack is unlocked) + */ +static int lock_release_nested(struct task_struct *curr, + struct lockdep_map *lock, unsigned long ip) +{ + struct held_lock *hlock; + unsigned int depth; + + /* + * Pop off the top of the lock stack: + */ + depth = curr->lockdep_depth - 1; + hlock = curr->held_locks + depth; + + /* + * Is the unlock non-nested: + */ + if (hlock->instance != lock) + return lock_release_non_nested(curr, lock, ip); + curr->lockdep_depth--; + + if (DEBUG_LOCKS_WARN_ON(!depth && (hlock->prev_chain_key != 0))) + return 0; + + curr->curr_chain_key = hlock->prev_chain_key; + +#ifdef CONFIG_DEBUG_LOCKDEP + hlock->prev_chain_key = 0; + hlock->class = NULL; + hlock->acquire_ip = 0; + hlock->irq_context = 0; +#endif + return 1; +} + +/* + * Remove the lock to the list of currently held locks - this gets + * called on mutex_unlock()/spin_unlock*() (or on a failed + * mutex_lock_interruptible()). This is done for unlocks that nest + * perfectly. (i.e. the current top of the lock-stack is unlocked) + */ +static void +__lock_release(struct lockdep_map *lock, int nested, unsigned long ip) +{ + struct task_struct *curr = current; + + if (!check_unlock(curr, lock, ip)) + return; + + if (nested) { + if (!lock_release_nested(curr, lock, ip)) + return; + } else { + if (!lock_release_non_nested(curr, lock, ip)) + return; + } + + check_chain_key(curr); +} + +/* + * Check whether we follow the irq-flags state precisely: + */ +static void check_flags(unsigned long flags) +{ +#if defined(CONFIG_DEBUG_LOCKDEP) && defined(CONFIG_TRACE_IRQFLAGS) + if (!debug_locks) + return; + + if (irqs_disabled_flags(flags)) + DEBUG_LOCKS_WARN_ON(current->hardirqs_enabled); + else + DEBUG_LOCKS_WARN_ON(!current->hardirqs_enabled); + + /* + * We dont accurately track softirq state in e.g. + * hardirq contexts (such as on 4KSTACKS), so only + * check if not in hardirq contexts: + */ + if (!hardirq_count()) { + if (softirq_count()) + DEBUG_LOCKS_WARN_ON(current->softirqs_enabled); + else + DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); + } + + if (!debug_locks) + print_irqtrace_events(current); +#endif +} + +/* + * We are not always called with irqs disabled - do that here, + * and also avoid lockdep recursion: + */ +void lock_acquire(struct lockdep_map *lock, unsigned int subclass, + int trylock, int read, int check, unsigned long ip) +{ + unsigned long flags; + + if (unlikely(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + check_flags(flags); + + current->lockdep_recursion = 1; + __lock_acquire(lock, subclass, trylock, read, check, + irqs_disabled_flags(flags), ip); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); +} + +EXPORT_SYMBOL_GPL(lock_acquire); + +void lock_release(struct lockdep_map *lock, int nested, unsigned long ip) +{ + unsigned long flags; + + if (unlikely(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + check_flags(flags); + current->lockdep_recursion = 1; + __lock_release(lock, nested, ip); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); +} + +EXPORT_SYMBOL_GPL(lock_release); + +/* + * Used by the testsuite, sanitize the validator state + * after a simulated failure: + */ + +void lockdep_reset(void) +{ + unsigned long flags; + + raw_local_irq_save(flags); + current->curr_chain_key = 0; + current->lockdep_depth = 0; + current->lockdep_recursion = 0; + memset(current->held_locks, 0, MAX_LOCK_DEPTH*sizeof(struct held_lock)); + nr_hardirq_chains = 0; + nr_softirq_chains = 0; + nr_process_chains = 0; + debug_locks = 1; + raw_local_irq_restore(flags); +} + +static void zap_class(struct lock_class *class) +{ + int i; + + /* + * Remove all dependencies this lock is + * involved in: + */ + for (i = 0; i < nr_list_entries; i++) { + if (list_entries[i].class == class) + list_del_rcu(&list_entries[i].entry); + } + /* + * Unhash the class and remove it from the all_lock_classes list: + */ + list_del_rcu(&class->hash_entry); + list_del_rcu(&class->lock_entry); + +} + +static inline int within(void *addr, void *start, unsigned long size) +{ + return addr >= start && addr < start + size; +} + +void lockdep_free_key_range(void *start, unsigned long size) +{ + struct lock_class *class, *next; + struct list_head *head; + unsigned long flags; + int i; + + raw_local_irq_save(flags); + __raw_spin_lock(&hash_lock); + + /* + * Unhash all classes that were created by this module: + */ + for (i = 0; i < CLASSHASH_SIZE; i++) { + head = classhash_table + i; + if (list_empty(head)) + continue; + list_for_each_entry_safe(class, next, head, hash_entry) + if (within(class->key, start, size)) + zap_class(class); + } + + __raw_spin_unlock(&hash_lock); + raw_local_irq_restore(flags); +} + +void lockdep_reset_lock(struct lockdep_map *lock) +{ + struct lock_class *class, *next, *entry; + struct list_head *head; + unsigned long flags; + int i, j; + + raw_local_irq_save(flags); + __raw_spin_lock(&hash_lock); + + /* + * Remove all classes this lock has: + */ + for (i = 0; i < CLASSHASH_SIZE; i++) { + head = classhash_table + i; + if (list_empty(head)) + continue; + list_for_each_entry_safe(class, next, head, hash_entry) { + for (j = 0; j < MAX_LOCKDEP_SUBCLASSES; j++) { + entry = lock->class[j]; + if (class == entry) { + zap_class(class); + lock->class[j] = NULL; + break; + } + } + } + } + + /* + * Debug check: in the end all mapped classes should + * be gone. + */ + for (j = 0; j < MAX_LOCKDEP_SUBCLASSES; j++) { + entry = lock->class[j]; + if (!entry) + continue; + __raw_spin_unlock(&hash_lock); + DEBUG_LOCKS_WARN_ON(1); + raw_local_irq_restore(flags); + return; + } + + __raw_spin_unlock(&hash_lock); + raw_local_irq_restore(flags); +} + +void __init lockdep_init(void) +{ + int i; + + /* + * Some architectures have their own start_kernel() + * code which calls lockdep_init(), while we also + * call lockdep_init() from the start_kernel() itself, + * and we want to initialize the hashes only once: + */ + if (lockdep_initialized) + return; + + for (i = 0; i < CLASSHASH_SIZE; i++) + INIT_LIST_HEAD(classhash_table + i); + + for (i = 0; i < CHAINHASH_SIZE; i++) + INIT_LIST_HEAD(chainhash_table + i); + + lockdep_initialized = 1; +} + +void __init lockdep_info(void) +{ + printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n"); + + printk("... MAX_LOCKDEP_SUBCLASSES: %lu\n", MAX_LOCKDEP_SUBCLASSES); + printk("... MAX_LOCK_DEPTH: %lu\n", MAX_LOCK_DEPTH); + printk("... MAX_LOCKDEP_KEYS: %lu\n", MAX_LOCKDEP_KEYS); + printk("... CLASSHASH_SIZE: %lu\n", CLASSHASH_SIZE); + printk("... MAX_LOCKDEP_ENTRIES: %lu\n", MAX_LOCKDEP_ENTRIES); + printk("... MAX_LOCKDEP_CHAINS: %lu\n", MAX_LOCKDEP_CHAINS); + printk("... CHAINHASH_SIZE: %lu\n", CHAINHASH_SIZE); + + printk(" memory used by lock dependency info: %lu kB\n", + (sizeof(struct lock_class) * MAX_LOCKDEP_KEYS + + sizeof(struct list_head) * CLASSHASH_SIZE + + sizeof(struct lock_list) * MAX_LOCKDEP_ENTRIES + + sizeof(struct lock_chain) * MAX_LOCKDEP_CHAINS + + sizeof(struct list_head) * CHAINHASH_SIZE) / 1024); + + printk(" per task-struct memory footprint: %lu bytes\n", + sizeof(struct held_lock) * MAX_LOCK_DEPTH); + +#ifdef CONFIG_DEBUG_LOCKDEP + if (lockdep_init_error) + printk("WARNING: lockdep init error! Arch code didnt call lockdep_init() early enough?\n"); +#endif +} + +static inline int in_range(const void *start, const void *addr, const void *end) +{ + return addr >= start && addr <= end; +} + +static void +print_freed_lock_bug(struct task_struct *curr, const void *mem_from, + const void *mem_to) +{ + if (!debug_locks_off()) + return; + if (debug_locks_silent) + return; + + printk("\n=========================\n"); + printk( "[ BUG: held lock freed! ]\n"); + printk( "-------------------------\n"); + printk("%s/%d is freeing memory %p-%p, with a lock still held there!\n", + curr->comm, curr->pid, mem_from, mem_to-1); + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); +} + +/* + * Called when kernel memory is freed (or unmapped), or if a lock + * is destroyed or reinitialized - this code checks whether there is + * any held lock in the memory range of <from> to <to>: + */ +void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len) +{ + const void *mem_to = mem_from + mem_len, *lock_from, *lock_to; + struct task_struct *curr = current; + struct held_lock *hlock; + unsigned long flags; + int i; + + if (unlikely(!debug_locks)) + return; + + local_irq_save(flags); + for (i = 0; i < curr->lockdep_depth; i++) { + hlock = curr->held_locks + i; + + lock_from = (void *)hlock->instance; + lock_to = (void *)(hlock->instance + 1); + + if (!in_range(mem_from, lock_from, mem_to) && + !in_range(mem_from, lock_to, mem_to)) + continue; + + print_freed_lock_bug(curr, mem_from, mem_to); + break; + } + local_irq_restore(flags); +} + +static void print_held_locks_bug(struct task_struct *curr) +{ + if (!debug_locks_off()) + return; + if (debug_locks_silent) + return; + + printk("\n=====================================\n"); + printk( "[ BUG: lock held at task exit time! ]\n"); + printk( "-------------------------------------\n"); + printk("%s/%d is exiting with locks still held!\n", + curr->comm, curr->pid); + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); +} + +void debug_check_no_locks_held(struct task_struct *task) +{ + if (unlikely(task->lockdep_depth > 0)) + print_held_locks_bug(task); +} + +void debug_show_all_locks(void) +{ + struct task_struct *g, *p; + int count = 10; + int unlock = 1; + + printk("\nShowing all locks held in the system:\n"); + + /* + * Here we try to get the tasklist_lock as hard as possible, + * if not successful after 2 seconds we ignore it (but keep + * trying). This is to enable a debug printout even if a + * tasklist_lock-holding task deadlocks or crashes. + */ +retry: + if (!read_trylock(&tasklist_lock)) { + if (count == 10) + printk("hm, tasklist_lock locked, retrying... "); + if (count) { + count--; + printk(" #%d", 10-count); + mdelay(200); + goto retry; + } + printk(" ignoring it.\n"); + unlock = 0; + } + if (count != 10) + printk(" locked it.\n"); + + do_each_thread(g, p) { + if (p->lockdep_depth) + lockdep_print_held_locks(p); + if (!unlock) + if (read_trylock(&tasklist_lock)) + unlock = 1; + } while_each_thread(g, p); + + printk("\n"); + printk("=============================================\n\n"); + + if (unlock) + read_unlock(&tasklist_lock); +} + +EXPORT_SYMBOL_GPL(debug_show_all_locks); + +void debug_show_held_locks(struct task_struct *task) +{ + lockdep_print_held_locks(task); +} + +EXPORT_SYMBOL_GPL(debug_show_held_locks); + diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h new file mode 100644 index 00000000000..0d355f24fe0 --- /dev/null +++ b/kernel/lockdep_internals.h @@ -0,0 +1,78 @@ +/* + * kernel/lockdep_internals.h + * + * Runtime locking correctness validator + * + * lockdep subsystem internal functions and variables. + */ + +/* + * MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies + * we track. + * + * We use the per-lock dependency maps in two ways: we grow it by adding + * every to-be-taken lock to all currently held lock's own dependency + * table (if it's not there yet), and we check it for lock order + * conflicts and deadlocks. + */ +#define MAX_LOCKDEP_ENTRIES 8192UL + +#define MAX_LOCKDEP_KEYS_BITS 11 +#define MAX_LOCKDEP_KEYS (1UL << MAX_LOCKDEP_KEYS_BITS) + +#define MAX_LOCKDEP_CHAINS_BITS 13 +#define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) + +/* + * Stack-trace: tightly packed array of stack backtrace + * addresses. Protected by the hash_lock. + */ +#define MAX_STACK_TRACE_ENTRIES 131072UL + +extern struct list_head all_lock_classes; + +extern void +get_usage_chars(struct lock_class *class, char *c1, char *c2, char *c3, char *c4); + +extern const char * __get_key_name(struct lockdep_subclass_key *key, char *str); + +extern unsigned long nr_lock_classes; +extern unsigned long nr_list_entries; +extern unsigned long nr_lock_chains; +extern unsigned long nr_stack_trace_entries; + +extern unsigned int nr_hardirq_chains; +extern unsigned int nr_softirq_chains; +extern unsigned int nr_process_chains; +extern unsigned int max_lockdep_depth; +extern unsigned int max_recursion_depth; + +#ifdef CONFIG_DEBUG_LOCKDEP +/* + * Various lockdep statistics: + */ +extern atomic_t chain_lookup_hits; +extern atomic_t chain_lookup_misses; +extern atomic_t hardirqs_on_events; +extern atomic_t hardirqs_off_events; +extern atomic_t redundant_hardirqs_on; +extern atomic_t redundant_hardirqs_off; +extern atomic_t softirqs_on_events; +extern atomic_t softirqs_off_events; +extern atomic_t redundant_softirqs_on; +extern atomic_t redundant_softirqs_off; +extern atomic_t nr_unused_locks; +extern atomic_t nr_cyclic_checks; +extern atomic_t nr_cyclic_check_recursions; +extern atomic_t nr_find_usage_forwards_checks; +extern atomic_t nr_find_usage_forwards_recursions; +extern atomic_t nr_find_usage_backwards_checks; +extern atomic_t nr_find_usage_backwards_recursions; +# define debug_atomic_inc(ptr) atomic_inc(ptr) +# define debug_atomic_dec(ptr) atomic_dec(ptr) +# define debug_atomic_read(ptr) atomic_read(ptr) +#else +# define debug_atomic_inc(ptr) do { } while (0) +# define debug_atomic_dec(ptr) do { } while (0) +# define debug_atomic_read(ptr) 0 +#endif diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c new file mode 100644 index 00000000000..f6e72eaab3f --- /dev/null +++ b/kernel/lockdep_proc.c @@ -0,0 +1,345 @@ +/* + * kernel/lockdep_proc.c + * + * Runtime locking correctness validator + * + * Started by Ingo Molnar: + * + * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * + * Code for /proc/lockdep and /proc/lockdep_stats: + * + */ +#include <linux/sched.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/kallsyms.h> +#include <linux/debug_locks.h> + +#include "lockdep_internals.h" + +static void *l_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct lock_class *class = v; + + (*pos)++; + + if (class->lock_entry.next != &all_lock_classes) + class = list_entry(class->lock_entry.next, struct lock_class, + lock_entry); + else + class = NULL; + m->private = class; + + return class; +} + +static void *l_start(struct seq_file *m, loff_t *pos) +{ + struct lock_class *class = m->private; + + if (&class->lock_entry == all_lock_classes.next) + seq_printf(m, "all lock classes:\n"); + + return class; +} + +static void l_stop(struct seq_file *m, void *v) +{ +} + +static unsigned long count_forward_deps(struct lock_class *class) +{ + struct lock_list *entry; + unsigned long ret = 1; + + /* + * Recurse this class's dependency list: + */ + list_for_each_entry(entry, &class->locks_after, entry) + ret += count_forward_deps(entry->class); + + return ret; +} + +static unsigned long count_backward_deps(struct lock_class *class) +{ + struct lock_list *entry; + unsigned long ret = 1; + + /* + * Recurse this class's dependency list: + */ + list_for_each_entry(entry, &class->locks_before, entry) + ret += count_backward_deps(entry->class); + + return ret; +} + +static int l_show(struct seq_file *m, void *v) +{ + unsigned long nr_forward_deps, nr_backward_deps; + struct lock_class *class = m->private; + char str[128], c1, c2, c3, c4; + const char *name; + + seq_printf(m, "%p", class->key); +#ifdef CONFIG_DEBUG_LOCKDEP + seq_printf(m, " OPS:%8ld", class->ops); +#endif + nr_forward_deps = count_forward_deps(class); + seq_printf(m, " FD:%5ld", nr_forward_deps); + + nr_backward_deps = count_backward_deps(class); + seq_printf(m, " BD:%5ld", nr_backward_deps); + + get_usage_chars(class, &c1, &c2, &c3, &c4); + seq_printf(m, " %c%c%c%c", c1, c2, c3, c4); + + name = class->name; + if (!name) { + name = __get_key_name(class->key, str); + seq_printf(m, ": %s", name); + } else{ + seq_printf(m, ": %s", name); + if (class->name_version > 1) + seq_printf(m, "#%d", class->name_version); + if (class->subclass) + seq_printf(m, "/%d", class->subclass); + } + seq_puts(m, "\n"); + + return 0; +} + +static struct seq_operations lockdep_ops = { + .start = l_start, + .next = l_next, + .stop = l_stop, + .show = l_show, +}; + +static int lockdep_open(struct inode *inode, struct file *file) +{ + int res = seq_open(file, &lockdep_ops); + if (!res) { + struct seq_file *m = file->private_data; + + if (!list_empty(&all_lock_classes)) + m->private = list_entry(all_lock_classes.next, + struct lock_class, lock_entry); + else + m->private = NULL; + } + return res; +} + +static struct file_operations proc_lockdep_operations = { + .open = lockdep_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static void lockdep_stats_debug_show(struct seq_file *m) +{ +#ifdef CONFIG_DEBUG_LOCKDEP + unsigned int hi1 = debug_atomic_read(&hardirqs_on_events), + hi2 = debug_atomic_read(&hardirqs_off_events), + hr1 = debug_atomic_read(&redundant_hardirqs_on), + hr2 = debug_atomic_read(&redundant_hardirqs_off), + si1 = debug_atomic_read(&softirqs_on_events), + si2 = debug_atomic_read(&softirqs_off_events), + sr1 = debug_atomic_read(&redundant_softirqs_on), + sr2 = debug_atomic_read(&redundant_softirqs_off); + + seq_printf(m, " chain lookup misses: %11u\n", + debug_atomic_read(&chain_lookup_misses)); + seq_printf(m, " chain lookup hits: %11u\n", + debug_atomic_read(&chain_lookup_hits)); + seq_printf(m, " cyclic checks: %11u\n", + debug_atomic_read(&nr_cyclic_checks)); + seq_printf(m, " cyclic-check recursions: %11u\n", + debug_atomic_read(&nr_cyclic_check_recursions)); + seq_printf(m, " find-mask forwards checks: %11u\n", + debug_atomic_read(&nr_find_usage_forwards_checks)); + seq_printf(m, " find-mask forwards recursions: %11u\n", + debug_atomic_read(&nr_find_usage_forwards_recursions)); + seq_printf(m, " find-mask backwards checks: %11u\n", + debug_atomic_read(&nr_find_usage_backwards_checks)); + seq_printf(m, " find-mask backwards recursions:%11u\n", + debug_atomic_read(&nr_find_usage_backwards_recursions)); + + seq_printf(m, " hardirq on events: %11u\n", hi1); + seq_printf(m, " hardirq off events: %11u\n", hi2); + seq_printf(m, " redundant hardirq ons: %11u\n", hr1); + seq_printf(m, " redundant hardirq offs: %11u\n", hr2); + seq_printf(m, " softirq on events: %11u\n", si1); + seq_printf(m, " softirq off events: %11u\n", si2); + seq_printf(m, " redundant softirq ons: %11u\n", sr1); + seq_printf(m, " redundant softirq offs: %11u\n", sr2); +#endif +} + +static int lockdep_stats_show(struct seq_file *m, void *v) +{ + struct lock_class *class; + unsigned long nr_unused = 0, nr_uncategorized = 0, + nr_irq_safe = 0, nr_irq_unsafe = 0, + nr_softirq_safe = 0, nr_softirq_unsafe = 0, + nr_hardirq_safe = 0, nr_hardirq_unsafe = 0, + nr_irq_read_safe = 0, nr_irq_read_unsafe = 0, + nr_softirq_read_safe = 0, nr_softirq_read_unsafe = 0, + nr_hardirq_read_safe = 0, nr_hardirq_read_unsafe = 0, + sum_forward_deps = 0, factor = 0; + + list_for_each_entry(class, &all_lock_classes, lock_entry) { + + if (class->usage_mask == 0) + nr_unused++; + if (class->usage_mask == LOCKF_USED) + nr_uncategorized++; + if (class->usage_mask & LOCKF_USED_IN_IRQ) + nr_irq_safe++; + if (class->usage_mask & LOCKF_ENABLED_IRQS) + nr_irq_unsafe++; + if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ) + nr_softirq_safe++; + if (class->usage_mask & LOCKF_ENABLED_SOFTIRQS) + nr_softirq_unsafe++; + if (class->usage_mask & LOCKF_USED_IN_HARDIRQ) + nr_hardirq_safe++; + if (class->usage_mask & LOCKF_ENABLED_HARDIRQS) + nr_hardirq_unsafe++; + if (class->usage_mask & LOCKF_USED_IN_IRQ_READ) + nr_irq_read_safe++; + if (class->usage_mask & LOCKF_ENABLED_IRQS_READ) + nr_irq_read_unsafe++; + if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ_READ) + nr_softirq_read_safe++; + if (class->usage_mask & LOCKF_ENABLED_SOFTIRQS_READ) + nr_softirq_read_unsafe++; + if (class->usage_mask & LOCKF_USED_IN_HARDIRQ_READ) + nr_hardirq_read_safe++; + if (class->usage_mask & LOCKF_ENABLED_HARDIRQS_READ) + nr_hardirq_read_unsafe++; + + sum_forward_deps += count_forward_deps(class); + } +#ifdef CONFIG_LOCKDEP_DEBUG + DEBUG_LOCKS_WARN_ON(debug_atomic_read(&nr_unused_locks) != nr_unused); +#endif + seq_printf(m, " lock-classes: %11lu [max: %lu]\n", + nr_lock_classes, MAX_LOCKDEP_KEYS); + seq_printf(m, " direct dependencies: %11lu [max: %lu]\n", + nr_list_entries, MAX_LOCKDEP_ENTRIES); + seq_printf(m, " indirect dependencies: %11lu\n", + sum_forward_deps); + + /* + * Total number of dependencies: + * + * All irq-safe locks may nest inside irq-unsafe locks, + * plus all the other known dependencies: + */ + seq_printf(m, " all direct dependencies: %11lu\n", + nr_irq_unsafe * nr_irq_safe + + nr_hardirq_unsafe * nr_hardirq_safe + + nr_list_entries); + + /* + * Estimated factor between direct and indirect + * dependencies: + */ + if (nr_list_entries) + factor = sum_forward_deps / nr_list_entries; + + seq_printf(m, " dependency chains: %11lu [max: %lu]\n", + nr_lock_chains, MAX_LOCKDEP_CHAINS); + +#ifdef CONFIG_TRACE_IRQFLAGS + seq_printf(m, " in-hardirq chains: %11u\n", + nr_hardirq_chains); + seq_printf(m, " in-softirq chains: %11u\n", + nr_softirq_chains); +#endif + seq_printf(m, " in-process chains: %11u\n", + nr_process_chains); + seq_printf(m, " stack-trace entries: %11lu [max: %lu]\n", + nr_stack_trace_entries, MAX_STACK_TRACE_ENTRIES); + seq_printf(m, " combined max dependencies: %11u\n", + (nr_hardirq_chains + 1) * + (nr_softirq_chains + 1) * + (nr_process_chains + 1) + ); + seq_printf(m, " hardirq-safe locks: %11lu\n", + nr_hardirq_safe); + seq_printf(m, " hardirq-unsafe locks: %11lu\n", + nr_hardirq_unsafe); + seq_printf(m, " softirq-safe locks: %11lu\n", + nr_softirq_safe); + seq_printf(m, " softirq-unsafe locks: %11lu\n", + nr_softirq_unsafe); + seq_printf(m, " irq-safe locks: %11lu\n", + nr_irq_safe); + seq_printf(m, " irq-unsafe locks: %11lu\n", + nr_irq_unsafe); + + seq_printf(m, " hardirq-read-safe locks: %11lu\n", + nr_hardirq_read_safe); + seq_printf(m, " hardirq-read-unsafe locks: %11lu\n", + nr_hardirq_read_unsafe); + seq_printf(m, " softirq-read-safe locks: %11lu\n", + nr_softirq_read_safe); + seq_printf(m, " softirq-read-unsafe locks: %11lu\n", + nr_softirq_read_unsafe); + seq_printf(m, " irq-read-safe locks: %11lu\n", + nr_irq_read_safe); + seq_printf(m, " irq-read-unsafe locks: %11lu\n", + nr_irq_read_unsafe); + + seq_printf(m, " uncategorized locks: %11lu\n", + nr_uncategorized); + seq_printf(m, " unused locks: %11lu\n", + nr_unused); + seq_printf(m, " max locking depth: %11u\n", + max_lockdep_depth); + seq_printf(m, " max recursion depth: %11u\n", + max_recursion_depth); + lockdep_stats_debug_show(m); + seq_printf(m, " debug_locks: %11u\n", + debug_locks); + + return 0; +} + +static int lockdep_stats_open(struct inode *inode, struct file *file) +{ + return single_open(file, lockdep_stats_show, NULL); +} + +static struct file_operations proc_lockdep_stats_operations = { + .open = lockdep_stats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init lockdep_proc_init(void) +{ + struct proc_dir_entry *entry; + + entry = create_proc_entry("lockdep", S_IRUSR, NULL); + if (entry) + entry->proc_fops = &proc_lockdep_operations; + + entry = create_proc_entry("lockdep_stats", S_IRUSR, NULL); + if (entry) + entry->proc_fops = &proc_lockdep_stats_operations; + + return 0; +} + +__initcall(lockdep_proc_init); + diff --git a/kernel/module.c b/kernel/module.c index 10e5b872adf..35e1b1f859d 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1,4 +1,4 @@ -/* Rewritten by Rusty Russell, on the backs of many others... +/* Copyright (C) 2002 Richard Henderson Copyright (C) 2001 Rusty Russell, 2002 Rusty Russell IBM. @@ -16,7 +16,6 @@ along with this program; if not, write to the Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#include <linux/config.h> #include <linux/module.h> #include <linux/moduleloader.h> #include <linux/init.h> @@ -122,9 +121,17 @@ extern const struct kernel_symbol __start___ksymtab_gpl[]; extern const struct kernel_symbol __stop___ksymtab_gpl[]; extern const struct kernel_symbol __start___ksymtab_gpl_future[]; extern const struct kernel_symbol __stop___ksymtab_gpl_future[]; +extern const struct kernel_symbol __start___ksymtab_unused[]; +extern const struct kernel_symbol __stop___ksymtab_unused[]; +extern const struct kernel_symbol __start___ksymtab_unused_gpl[]; +extern const struct kernel_symbol __stop___ksymtab_unused_gpl[]; +extern const struct kernel_symbol __start___ksymtab_gpl_future[]; +extern const struct kernel_symbol __stop___ksymtab_gpl_future[]; extern const unsigned long __start___kcrctab[]; extern const unsigned long __start___kcrctab_gpl[]; extern const unsigned long __start___kcrctab_gpl_future[]; +extern const unsigned long __start___kcrctab_unused[]; +extern const unsigned long __start___kcrctab_unused_gpl[]; #ifndef CONFIG_MODVERSIONS #define symversion(base, idx) NULL @@ -144,6 +151,17 @@ static const struct kernel_symbol *lookup_symbol(const char *name, return NULL; } +static void printk_unused_warning(const char *name) +{ + printk(KERN_WARNING "Symbol %s is marked as UNUSED, " + "however this module is using it.\n", name); + printk(KERN_WARNING "This symbol will go away in the future.\n"); + printk(KERN_WARNING "Please evalute if this is the right api to use, " + "and if it really is, submit a report the linux kernel " + "mailinglist together with submitting your code for " + "inclusion.\n"); +} + /* Find a symbol, return value, crc and module which owns it */ static unsigned long __find_symbol(const char *name, struct module **owner, @@ -186,6 +204,25 @@ static unsigned long __find_symbol(const char *name, return ks->value; } + ks = lookup_symbol(name, __start___ksymtab_unused, + __stop___ksymtab_unused); + if (ks) { + printk_unused_warning(name); + *crc = symversion(__start___kcrctab_unused, + (ks - __start___ksymtab_unused)); + return ks->value; + } + + if (gplok) + ks = lookup_symbol(name, __start___ksymtab_unused_gpl, + __stop___ksymtab_unused_gpl); + if (ks) { + printk_unused_warning(name); + *crc = symversion(__start___kcrctab_unused_gpl, + (ks - __start___ksymtab_unused_gpl)); + return ks->value; + } + /* Now try modules. */ list_for_each_entry(mod, &modules, list) { *owner = mod; @@ -204,6 +241,23 @@ static unsigned long __find_symbol(const char *name, return ks->value; } } + ks = lookup_symbol(name, mod->unused_syms, mod->unused_syms + mod->num_unused_syms); + if (ks) { + printk_unused_warning(name); + *crc = symversion(mod->unused_crcs, (ks - mod->unused_syms)); + return ks->value; + } + + if (gplok) { + ks = lookup_symbol(name, mod->unused_gpl_syms, + mod->unused_gpl_syms + mod->num_unused_gpl_syms); + if (ks) { + printk_unused_warning(name); + *crc = symversion(mod->unused_gpl_crcs, + (ks - mod->unused_gpl_syms)); + return ks->value; + } + } ks = lookup_symbol(name, mod->gpl_future_syms, (mod->gpl_future_syms + mod->num_gpl_future_syms)); @@ -1067,6 +1121,9 @@ static void free_module(struct module *mod) if (mod->percpu) percpu_modfree(mod->percpu); + /* Free lock-classes: */ + lockdep_free_key_range(mod->module_core, mod->core_size); + /* Finally, free the core (containing the module structure) */ module_free(mod, mod->module_core); } @@ -1403,10 +1460,27 @@ static struct module *load_module(void __user *umod, Elf_Ehdr *hdr; Elf_Shdr *sechdrs; char *secstrings, *args, *modmagic, *strtab = NULL; - unsigned int i, symindex = 0, strindex = 0, setupindex, exindex, - exportindex, modindex, obsparmindex, infoindex, gplindex, - crcindex, gplcrcindex, versindex, pcpuindex, gplfutureindex, - gplfuturecrcindex, unwindex = 0; + unsigned int i; + unsigned int symindex = 0; + unsigned int strindex = 0; + unsigned int setupindex; + unsigned int exindex; + unsigned int exportindex; + unsigned int modindex; + unsigned int obsparmindex; + unsigned int infoindex; + unsigned int gplindex; + unsigned int crcindex; + unsigned int gplcrcindex; + unsigned int versindex; + unsigned int pcpuindex; + unsigned int gplfutureindex; + unsigned int gplfuturecrcindex; + unsigned int unwindex = 0; + unsigned int unusedindex; + unsigned int unusedcrcindex; + unsigned int unusedgplindex; + unsigned int unusedgplcrcindex; struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ @@ -1487,9 +1561,13 @@ static struct module *load_module(void __user *umod, exportindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab"); gplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl"); gplfutureindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl_future"); + unusedindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused"); + unusedgplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused_gpl"); crcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab"); gplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl"); gplfuturecrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl_future"); + unusedcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused"); + unusedgplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused_gpl"); setupindex = find_sec(hdr, sechdrs, secstrings, "__param"); exindex = find_sec(hdr, sechdrs, secstrings, "__ex_table"); obsparmindex = find_sec(hdr, sechdrs, secstrings, "__obsparm"); @@ -1638,14 +1716,27 @@ static struct module *load_module(void __user *umod, mod->gpl_crcs = (void *)sechdrs[gplcrcindex].sh_addr; mod->num_gpl_future_syms = sechdrs[gplfutureindex].sh_size / sizeof(*mod->gpl_future_syms); + mod->num_unused_syms = sechdrs[unusedindex].sh_size / + sizeof(*mod->unused_syms); + mod->num_unused_gpl_syms = sechdrs[unusedgplindex].sh_size / + sizeof(*mod->unused_gpl_syms); mod->gpl_future_syms = (void *)sechdrs[gplfutureindex].sh_addr; if (gplfuturecrcindex) mod->gpl_future_crcs = (void *)sechdrs[gplfuturecrcindex].sh_addr; + mod->unused_syms = (void *)sechdrs[unusedindex].sh_addr; + if (unusedcrcindex) + mod->unused_crcs = (void *)sechdrs[unusedcrcindex].sh_addr; + mod->unused_gpl_syms = (void *)sechdrs[unusedgplindex].sh_addr; + if (unusedgplcrcindex) + mod->unused_crcs = (void *)sechdrs[unusedgplcrcindex].sh_addr; + #ifdef CONFIG_MODVERSIONS if ((mod->num_syms && !crcindex) || (mod->num_gpl_syms && !gplcrcindex) || - (mod->num_gpl_future_syms && !gplfuturecrcindex)) { + (mod->num_gpl_future_syms && !gplfuturecrcindex) || + (mod->num_unused_syms && !unusedcrcindex) || + (mod->num_unused_gpl_syms && !unusedgplcrcindex)) { printk(KERN_WARNING "%s: No versions for exported symbols." " Tainting kernel.\n", mod->name); add_taint(TAINT_FORCED_MODULE); @@ -2071,6 +2162,29 @@ const struct exception_table_entry *search_module_extables(unsigned long addr) return e; } +/* + * Is this a valid module address? + */ +int is_module_address(unsigned long addr) +{ + unsigned long flags; + struct module *mod; + + spin_lock_irqsave(&modlist_lock, flags); + + list_for_each_entry(mod, &modules, list) { + if (within(addr, mod->module_core, mod->core_size)) { + spin_unlock_irqrestore(&modlist_lock, flags); + return 1; + } + } + + spin_unlock_irqrestore(&modlist_lock, flags); + + return 0; +} + + /* Is this a valid kernel address? We don't grab the lock: we are oopsing. */ struct module *__module_text_address(unsigned long addr) { diff --git a/kernel/mutex-debug.c b/kernel/mutex-debug.c index e38e4bac97c..e3203c654dd 100644 --- a/kernel/mutex-debug.c +++ b/kernel/mutex-debug.c @@ -20,367 +20,19 @@ #include <linux/spinlock.h> #include <linux/kallsyms.h> #include <linux/interrupt.h> +#include <linux/debug_locks.h> #include "mutex-debug.h" /* - * We need a global lock when we walk through the multi-process - * lock tree. Only used in the deadlock-debugging case. - */ -DEFINE_SPINLOCK(debug_mutex_lock); - -/* - * All locks held by all tasks, in a single global list: - */ -LIST_HEAD(debug_mutex_held_locks); - -/* - * In the debug case we carry the caller's instruction pointer into - * other functions, but we dont want the function argument overhead - * in the nondebug case - hence these macros: - */ -#define __IP_DECL__ , unsigned long ip -#define __IP__ , ip -#define __RET_IP__ , (unsigned long)__builtin_return_address(0) - -/* - * "mutex debugging enabled" flag. We turn it off when we detect - * the first problem because we dont want to recurse back - * into the tracing code when doing error printk or - * executing a BUG(): - */ -int debug_mutex_on = 1; - -static void printk_task(struct task_struct *p) -{ - if (p) - printk("%16s:%5d [%p, %3d]", p->comm, p->pid, p, p->prio); - else - printk("<none>"); -} - -static void printk_ti(struct thread_info *ti) -{ - if (ti) - printk_task(ti->task); - else - printk("<none>"); -} - -static void printk_task_short(struct task_struct *p) -{ - if (p) - printk("%s/%d [%p, %3d]", p->comm, p->pid, p, p->prio); - else - printk("<none>"); -} - -static void printk_lock(struct mutex *lock, int print_owner) -{ - printk(" [%p] {%s}\n", lock, lock->name); - - if (print_owner && lock->owner) { - printk(".. held by: "); - printk_ti(lock->owner); - printk("\n"); - } - if (lock->owner) { - printk("... acquired at: "); - print_symbol("%s\n", lock->acquire_ip); - } -} - -/* - * printk locks held by a task: - */ -static void show_task_locks(struct task_struct *p) -{ - switch (p->state) { - case TASK_RUNNING: printk("R"); break; - case TASK_INTERRUPTIBLE: printk("S"); break; - case TASK_UNINTERRUPTIBLE: printk("D"); break; - case TASK_STOPPED: printk("T"); break; - case EXIT_ZOMBIE: printk("Z"); break; - case EXIT_DEAD: printk("X"); break; - default: printk("?"); break; - } - printk_task(p); - if (p->blocked_on) { - struct mutex *lock = p->blocked_on->lock; - - printk(" blocked on mutex:"); - printk_lock(lock, 1); - } else - printk(" (not blocked on mutex)\n"); -} - -/* - * printk all locks held in the system (if filter == NULL), - * or all locks belonging to a single task (if filter != NULL): - */ -void show_held_locks(struct task_struct *filter) -{ - struct list_head *curr, *cursor = NULL; - struct mutex *lock; - struct thread_info *t; - unsigned long flags; - int count = 0; - - if (filter) { - printk("------------------------------\n"); - printk("| showing all locks held by: | ("); - printk_task_short(filter); - printk("):\n"); - printk("------------------------------\n"); - } else { - printk("---------------------------\n"); - printk("| showing all locks held: |\n"); - printk("---------------------------\n"); - } - - /* - * Play safe and acquire the global trace lock. We - * cannot printk with that lock held so we iterate - * very carefully: - */ -next: - debug_spin_lock_save(&debug_mutex_lock, flags); - list_for_each(curr, &debug_mutex_held_locks) { - if (cursor && curr != cursor) - continue; - lock = list_entry(curr, struct mutex, held_list); - t = lock->owner; - if (filter && (t != filter->thread_info)) - continue; - count++; - cursor = curr->next; - debug_spin_unlock_restore(&debug_mutex_lock, flags); - - printk("\n#%03d: ", count); - printk_lock(lock, filter ? 0 : 1); - goto next; - } - debug_spin_unlock_restore(&debug_mutex_lock, flags); - printk("\n"); -} - -void mutex_debug_show_all_locks(void) -{ - struct task_struct *g, *p; - int count = 10; - int unlock = 1; - - printk("\nShowing all blocking locks in the system:\n"); - - /* - * Here we try to get the tasklist_lock as hard as possible, - * if not successful after 2 seconds we ignore it (but keep - * trying). This is to enable a debug printout even if a - * tasklist_lock-holding task deadlocks or crashes. - */ -retry: - if (!read_trylock(&tasklist_lock)) { - if (count == 10) - printk("hm, tasklist_lock locked, retrying... "); - if (count) { - count--; - printk(" #%d", 10-count); - mdelay(200); - goto retry; - } - printk(" ignoring it.\n"); - unlock = 0; - } - if (count != 10) - printk(" locked it.\n"); - - do_each_thread(g, p) { - show_task_locks(p); - if (!unlock) - if (read_trylock(&tasklist_lock)) - unlock = 1; - } while_each_thread(g, p); - - printk("\n"); - show_held_locks(NULL); - printk("=============================================\n\n"); - - if (unlock) - read_unlock(&tasklist_lock); -} - -static void report_deadlock(struct task_struct *task, struct mutex *lock, - struct mutex *lockblk, unsigned long ip) -{ - printk("\n%s/%d is trying to acquire this lock:\n", - current->comm, current->pid); - printk_lock(lock, 1); - printk("... trying at: "); - print_symbol("%s\n", ip); - show_held_locks(current); - - if (lockblk) { - printk("but %s/%d is deadlocking current task %s/%d!\n\n", - task->comm, task->pid, current->comm, current->pid); - printk("\n%s/%d is blocked on this lock:\n", - task->comm, task->pid); - printk_lock(lockblk, 1); - - show_held_locks(task); - - printk("\n%s/%d's [blocked] stackdump:\n\n", - task->comm, task->pid); - show_stack(task, NULL); - } - - printk("\n%s/%d's [current] stackdump:\n\n", - current->comm, current->pid); - dump_stack(); - mutex_debug_show_all_locks(); - printk("[ turning off deadlock detection. Please report this. ]\n\n"); - local_irq_disable(); -} - -/* - * Recursively check for mutex deadlocks: - */ -static int check_deadlock(struct mutex *lock, int depth, - struct thread_info *ti, unsigned long ip) -{ - struct mutex *lockblk; - struct task_struct *task; - - if (!debug_mutex_on) - return 0; - - ti = lock->owner; - if (!ti) - return 0; - - task = ti->task; - lockblk = NULL; - if (task->blocked_on) - lockblk = task->blocked_on->lock; - - /* Self-deadlock: */ - if (current == task) { - DEBUG_OFF(); - if (depth) - return 1; - printk("\n==========================================\n"); - printk( "[ BUG: lock recursion deadlock detected! |\n"); - printk( "------------------------------------------\n"); - report_deadlock(task, lock, NULL, ip); - return 0; - } - - /* Ugh, something corrupted the lock data structure? */ - if (depth > 20) { - DEBUG_OFF(); - printk("\n===========================================\n"); - printk( "[ BUG: infinite lock dependency detected!? |\n"); - printk( "-------------------------------------------\n"); - report_deadlock(task, lock, lockblk, ip); - return 0; - } - - /* Recursively check for dependencies: */ - if (lockblk && check_deadlock(lockblk, depth+1, ti, ip)) { - printk("\n============================================\n"); - printk( "[ BUG: circular locking deadlock detected! ]\n"); - printk( "--------------------------------------------\n"); - report_deadlock(task, lock, lockblk, ip); - return 0; - } - return 0; -} - -/* - * Called when a task exits, this function checks whether the - * task is holding any locks, and reports the first one if so: - */ -void mutex_debug_check_no_locks_held(struct task_struct *task) -{ - struct list_head *curr, *next; - struct thread_info *t; - unsigned long flags; - struct mutex *lock; - - if (!debug_mutex_on) - return; - - debug_spin_lock_save(&debug_mutex_lock, flags); - list_for_each_safe(curr, next, &debug_mutex_held_locks) { - lock = list_entry(curr, struct mutex, held_list); - t = lock->owner; - if (t != task->thread_info) - continue; - list_del_init(curr); - DEBUG_OFF(); - debug_spin_unlock_restore(&debug_mutex_lock, flags); - - printk("BUG: %s/%d, lock held at task exit time!\n", - task->comm, task->pid); - printk_lock(lock, 1); - if (lock->owner != task->thread_info) - printk("exiting task is not even the owner??\n"); - return; - } - debug_spin_unlock_restore(&debug_mutex_lock, flags); -} - -/* - * Called when kernel memory is freed (or unmapped), or if a mutex - * is destroyed or reinitialized - this code checks whether there is - * any held lock in the memory range of <from> to <to>: - */ -void mutex_debug_check_no_locks_freed(const void *from, unsigned long len) -{ - struct list_head *curr, *next; - const void *to = from + len; - unsigned long flags; - struct mutex *lock; - void *lock_addr; - - if (!debug_mutex_on) - return; - - debug_spin_lock_save(&debug_mutex_lock, flags); - list_for_each_safe(curr, next, &debug_mutex_held_locks) { - lock = list_entry(curr, struct mutex, held_list); - lock_addr = lock; - if (lock_addr < from || lock_addr >= to) - continue; - list_del_init(curr); - DEBUG_OFF(); - debug_spin_unlock_restore(&debug_mutex_lock, flags); - - printk("BUG: %s/%d, active lock [%p(%p-%p)] freed!\n", - current->comm, current->pid, lock, from, to); - dump_stack(); - printk_lock(lock, 1); - if (lock->owner != current_thread_info()) - printk("freeing task is not even the owner??\n"); - return; - } - debug_spin_unlock_restore(&debug_mutex_lock, flags); -} - -/* * Must be called with lock->wait_lock held. */ -void debug_mutex_set_owner(struct mutex *lock, - struct thread_info *new_owner __IP_DECL__) +void debug_mutex_set_owner(struct mutex *lock, struct thread_info *new_owner) { lock->owner = new_owner; - DEBUG_WARN_ON(!list_empty(&lock->held_list)); - if (debug_mutex_on) { - list_add_tail(&lock->held_list, &debug_mutex_held_locks); - lock->acquire_ip = ip; - } } -void debug_mutex_init_waiter(struct mutex_waiter *waiter) +void debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter) { memset(waiter, MUTEX_DEBUG_INIT, sizeof(*waiter)); waiter->magic = waiter; @@ -389,23 +41,23 @@ void debug_mutex_init_waiter(struct mutex_waiter *waiter) void debug_mutex_wake_waiter(struct mutex *lock, struct mutex_waiter *waiter) { - SMP_DEBUG_WARN_ON(!spin_is_locked(&lock->wait_lock)); - DEBUG_WARN_ON(list_empty(&lock->wait_list)); - DEBUG_WARN_ON(waiter->magic != waiter); - DEBUG_WARN_ON(list_empty(&waiter->list)); + SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock)); + DEBUG_LOCKS_WARN_ON(list_empty(&lock->wait_list)); + DEBUG_LOCKS_WARN_ON(waiter->magic != waiter); + DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list)); } void debug_mutex_free_waiter(struct mutex_waiter *waiter) { - DEBUG_WARN_ON(!list_empty(&waiter->list)); + DEBUG_LOCKS_WARN_ON(!list_empty(&waiter->list)); memset(waiter, MUTEX_DEBUG_FREE, sizeof(*waiter)); } void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, - struct thread_info *ti __IP_DECL__) + struct thread_info *ti) { - SMP_DEBUG_WARN_ON(!spin_is_locked(&lock->wait_lock)); - check_deadlock(lock, 0, ti, ip); + SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock)); + /* Mark the current thread as blocked on the lock: */ ti->task->blocked_on = waiter; waiter->lock = lock; @@ -414,9 +66,9 @@ void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, struct thread_info *ti) { - DEBUG_WARN_ON(list_empty(&waiter->list)); - DEBUG_WARN_ON(waiter->task != ti->task); - DEBUG_WARN_ON(ti->task->blocked_on != waiter); + DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list)); + DEBUG_LOCKS_WARN_ON(waiter->task != ti->task); + DEBUG_LOCKS_WARN_ON(ti->task->blocked_on != waiter); ti->task->blocked_on = NULL; list_del_init(&waiter->list); @@ -425,24 +77,23 @@ void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, void debug_mutex_unlock(struct mutex *lock) { - DEBUG_WARN_ON(lock->magic != lock); - DEBUG_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); - DEBUG_WARN_ON(lock->owner != current_thread_info()); - if (debug_mutex_on) { - DEBUG_WARN_ON(list_empty(&lock->held_list)); - list_del_init(&lock->held_list); - } + DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info()); + DEBUG_LOCKS_WARN_ON(lock->magic != lock); + DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); + DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info()); } -void debug_mutex_init(struct mutex *lock, const char *name) +void debug_mutex_init(struct mutex *lock, const char *name, + struct lock_class_key *key) { +#ifdef CONFIG_DEBUG_LOCK_ALLOC /* * Make sure we are not reinitializing a held lock: */ - mutex_debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key); +#endif lock->owner = NULL; - INIT_LIST_HEAD(&lock->held_list); - lock->name = name; lock->magic = lock; } @@ -456,7 +107,7 @@ void debug_mutex_init(struct mutex *lock, const char *name) */ void fastcall mutex_destroy(struct mutex *lock) { - DEBUG_WARN_ON(mutex_is_locked(lock)); + DEBUG_LOCKS_WARN_ON(mutex_is_locked(lock)); lock->magic = NULL; } diff --git a/kernel/mutex-debug.h b/kernel/mutex-debug.h index a5196c36a5f..babfbdfc534 100644 --- a/kernel/mutex-debug.h +++ b/kernel/mutex-debug.h @@ -10,110 +10,44 @@ * More details are in kernel/mutex-debug.c. */ -extern spinlock_t debug_mutex_lock; -extern struct list_head debug_mutex_held_locks; -extern int debug_mutex_on; - -/* - * In the debug case we carry the caller's instruction pointer into - * other functions, but we dont want the function argument overhead - * in the nondebug case - hence these macros: - */ -#define __IP_DECL__ , unsigned long ip -#define __IP__ , ip -#define __RET_IP__ , (unsigned long)__builtin_return_address(0) - /* * This must be called with lock->wait_lock held. */ -extern void debug_mutex_set_owner(struct mutex *lock, - struct thread_info *new_owner __IP_DECL__); +extern void +debug_mutex_set_owner(struct mutex *lock, struct thread_info *new_owner); static inline void debug_mutex_clear_owner(struct mutex *lock) { lock->owner = NULL; } -extern void debug_mutex_init_waiter(struct mutex_waiter *waiter); +extern void debug_mutex_lock_common(struct mutex *lock, + struct mutex_waiter *waiter); extern void debug_mutex_wake_waiter(struct mutex *lock, struct mutex_waiter *waiter); extern void debug_mutex_free_waiter(struct mutex_waiter *waiter); extern void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, - struct thread_info *ti __IP_DECL__); + struct thread_info *ti); extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, struct thread_info *ti); extern void debug_mutex_unlock(struct mutex *lock); -extern void debug_mutex_init(struct mutex *lock, const char *name); - -#define debug_spin_lock_save(lock, flags) \ - do { \ - local_irq_save(flags); \ - if (debug_mutex_on) \ - spin_lock(lock); \ - } while (0) - -#define debug_spin_unlock_restore(lock, flags) \ - do { \ - if (debug_mutex_on) \ - spin_unlock(lock); \ - local_irq_restore(flags); \ - preempt_check_resched(); \ - } while (0) +extern void debug_mutex_init(struct mutex *lock, const char *name, + struct lock_class_key *key); #define spin_lock_mutex(lock, flags) \ do { \ struct mutex *l = container_of(lock, struct mutex, wait_lock); \ \ - DEBUG_WARN_ON(in_interrupt()); \ - debug_spin_lock_save(&debug_mutex_lock, flags); \ - spin_lock(lock); \ - DEBUG_WARN_ON(l->magic != l); \ + DEBUG_LOCKS_WARN_ON(in_interrupt()); \ + local_irq_save(flags); \ + __raw_spin_lock(&(lock)->raw_lock); \ + DEBUG_LOCKS_WARN_ON(l->magic != l); \ } while (0) #define spin_unlock_mutex(lock, flags) \ do { \ - spin_unlock(lock); \ - debug_spin_unlock_restore(&debug_mutex_lock, flags); \ + __raw_spin_unlock(&(lock)->raw_lock); \ + local_irq_restore(flags); \ + preempt_check_resched(); \ } while (0) - -#define DEBUG_OFF() \ -do { \ - if (debug_mutex_on) { \ - debug_mutex_on = 0; \ - console_verbose(); \ - if (spin_is_locked(&debug_mutex_lock)) \ - spin_unlock(&debug_mutex_lock); \ - } \ -} while (0) - -#define DEBUG_BUG() \ -do { \ - if (debug_mutex_on) { \ - DEBUG_OFF(); \ - BUG(); \ - } \ -} while (0) - -#define DEBUG_WARN_ON(c) \ -do { \ - if (unlikely(c && debug_mutex_on)) { \ - DEBUG_OFF(); \ - WARN_ON(1); \ - } \ -} while (0) - -# define DEBUG_BUG_ON(c) \ -do { \ - if (unlikely(c)) \ - DEBUG_BUG(); \ -} while (0) - -#ifdef CONFIG_SMP -# define SMP_DEBUG_WARN_ON(c) DEBUG_WARN_ON(c) -# define SMP_DEBUG_BUG_ON(c) DEBUG_BUG_ON(c) -#else -# define SMP_DEBUG_WARN_ON(c) do { } while (0) -# define SMP_DEBUG_BUG_ON(c) do { } while (0) -#endif - diff --git a/kernel/mutex.c b/kernel/mutex.c index 7043db21bbc..8c71cf72a49 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/spinlock.h> #include <linux/interrupt.h> +#include <linux/debug_locks.h> /* * In the DEBUG case we are using the "NULL fastpath" for mutexes, @@ -38,13 +39,14 @@ * * It is not allowed to initialize an already locked mutex. */ -void fastcall __mutex_init(struct mutex *lock, const char *name) +void +__mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) { atomic_set(&lock->count, 1); spin_lock_init(&lock->wait_lock); INIT_LIST_HEAD(&lock->wait_list); - debug_mutex_init(lock, name); + debug_mutex_init(lock, name, key); } EXPORT_SYMBOL(__mutex_init); @@ -56,7 +58,7 @@ EXPORT_SYMBOL(__mutex_init); * branch is predicted by the CPU as default-untaken. */ static void fastcall noinline __sched -__mutex_lock_slowpath(atomic_t *lock_count __IP_DECL__); +__mutex_lock_slowpath(atomic_t *lock_count); /*** * mutex_lock - acquire the mutex @@ -79,7 +81,7 @@ __mutex_lock_slowpath(atomic_t *lock_count __IP_DECL__); * * This function is similar to (but not equivalent to) down(). */ -void fastcall __sched mutex_lock(struct mutex *lock) +void inline fastcall __sched mutex_lock(struct mutex *lock) { might_sleep(); /* @@ -92,7 +94,7 @@ void fastcall __sched mutex_lock(struct mutex *lock) EXPORT_SYMBOL(mutex_lock); static void fastcall noinline __sched -__mutex_unlock_slowpath(atomic_t *lock_count __IP_DECL__); +__mutex_unlock_slowpath(atomic_t *lock_count); /*** * mutex_unlock - release the mutex @@ -120,18 +122,18 @@ EXPORT_SYMBOL(mutex_unlock); * Lock a mutex (possibly interruptible), slowpath: */ static inline int __sched -__mutex_lock_common(struct mutex *lock, long state __IP_DECL__) +__mutex_lock_common(struct mutex *lock, long state, unsigned int subclass) { struct task_struct *task = current; struct mutex_waiter waiter; unsigned int old_val; unsigned long flags; - debug_mutex_init_waiter(&waiter); - spin_lock_mutex(&lock->wait_lock, flags); - debug_mutex_add_waiter(lock, &waiter, task->thread_info, ip); + debug_mutex_lock_common(lock, &waiter); + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + debug_mutex_add_waiter(lock, &waiter, task->thread_info); /* add waiting tasks to the end of the waitqueue (FIFO): */ list_add_tail(&waiter.list, &lock->wait_list); @@ -158,6 +160,7 @@ __mutex_lock_common(struct mutex *lock, long state __IP_DECL__) if (unlikely(state == TASK_INTERRUPTIBLE && signal_pending(task))) { mutex_remove_waiter(lock, &waiter, task->thread_info); + mutex_release(&lock->dep_map, 1, _RET_IP_); spin_unlock_mutex(&lock->wait_lock, flags); debug_mutex_free_waiter(&waiter); @@ -173,7 +176,7 @@ __mutex_lock_common(struct mutex *lock, long state __IP_DECL__) /* got the lock - rejoice! */ mutex_remove_waiter(lock, &waiter, task->thread_info); - debug_mutex_set_owner(lock, task->thread_info __IP__); + debug_mutex_set_owner(lock, task->thread_info); /* set it to 0 if there are no waiters left: */ if (likely(list_empty(&lock->wait_list))) @@ -183,32 +186,40 @@ __mutex_lock_common(struct mutex *lock, long state __IP_DECL__) debug_mutex_free_waiter(&waiter); - DEBUG_WARN_ON(list_empty(&lock->held_list)); - DEBUG_WARN_ON(lock->owner != task->thread_info); - return 0; } static void fastcall noinline __sched -__mutex_lock_slowpath(atomic_t *lock_count __IP_DECL__) +__mutex_lock_slowpath(atomic_t *lock_count) { struct mutex *lock = container_of(lock_count, struct mutex, count); - __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE __IP__); + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0); +} + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __sched +mutex_lock_nested(struct mutex *lock, unsigned int subclass) +{ + might_sleep(); + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass); } +EXPORT_SYMBOL_GPL(mutex_lock_nested); +#endif + /* * Release the lock, slowpath: */ -static fastcall noinline void -__mutex_unlock_slowpath(atomic_t *lock_count __IP_DECL__) +static fastcall inline void +__mutex_unlock_common_slowpath(atomic_t *lock_count, int nested) { struct mutex *lock = container_of(lock_count, struct mutex, count); unsigned long flags; - DEBUG_WARN_ON(lock->owner != current_thread_info()); - spin_lock_mutex(&lock->wait_lock, flags); + mutex_release(&lock->dep_map, nested, _RET_IP_); + debug_mutex_unlock(lock); /* * some architectures leave the lock unlocked in the fastpath failure @@ -218,8 +229,6 @@ __mutex_unlock_slowpath(atomic_t *lock_count __IP_DECL__) if (__mutex_slowpath_needs_to_unlock()) atomic_set(&lock->count, 1); - debug_mutex_unlock(lock); - if (!list_empty(&lock->wait_list)) { /* get the first entry from the wait-list: */ struct mutex_waiter *waiter = @@ -237,11 +246,20 @@ __mutex_unlock_slowpath(atomic_t *lock_count __IP_DECL__) } /* + * Release the lock, slowpath: + */ +static fastcall noinline void +__mutex_unlock_slowpath(atomic_t *lock_count) +{ + __mutex_unlock_common_slowpath(lock_count, 1); +} + +/* * Here come the less common (and hence less performance-critical) APIs: * mutex_lock_interruptible() and mutex_trylock(). */ static int fastcall noinline __sched -__mutex_lock_interruptible_slowpath(atomic_t *lock_count __IP_DECL__); +__mutex_lock_interruptible_slowpath(atomic_t *lock_count); /*** * mutex_lock_interruptible - acquire the mutex, interruptable @@ -264,11 +282,11 @@ int fastcall __sched mutex_lock_interruptible(struct mutex *lock) EXPORT_SYMBOL(mutex_lock_interruptible); static int fastcall noinline __sched -__mutex_lock_interruptible_slowpath(atomic_t *lock_count __IP_DECL__) +__mutex_lock_interruptible_slowpath(atomic_t *lock_count) { struct mutex *lock = container_of(lock_count, struct mutex, count); - return __mutex_lock_common(lock, TASK_INTERRUPTIBLE __IP__); + return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0); } /* @@ -284,8 +302,10 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count) spin_lock_mutex(&lock->wait_lock, flags); prev = atomic_xchg(&lock->count, -1); - if (likely(prev == 1)) - debug_mutex_set_owner(lock, current_thread_info() __RET_IP__); + if (likely(prev == 1)) { + debug_mutex_set_owner(lock, current_thread_info()); + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } /* Set it back to 0 if there are no waiters: */ if (likely(list_empty(&lock->wait_list))) atomic_set(&lock->count, 0); @@ -309,7 +329,7 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count) * This function must not be used in interrupt context. The * mutex must be released by the same task that acquired it. */ -int fastcall mutex_trylock(struct mutex *lock) +int fastcall __sched mutex_trylock(struct mutex *lock) { return __mutex_fastpath_trylock(&lock->count, __mutex_trylock_slowpath); diff --git a/kernel/mutex.h b/kernel/mutex.h index 06918994725..a075dafbb29 100644 --- a/kernel/mutex.h +++ b/kernel/mutex.h @@ -16,22 +16,15 @@ #define mutex_remove_waiter(lock, waiter, ti) \ __list_del((waiter)->list.prev, (waiter)->list.next) -#define DEBUG_WARN_ON(c) do { } while (0) #define debug_mutex_set_owner(lock, new_owner) do { } while (0) #define debug_mutex_clear_owner(lock) do { } while (0) -#define debug_mutex_init_waiter(waiter) do { } while (0) #define debug_mutex_wake_waiter(lock, waiter) do { } while (0) #define debug_mutex_free_waiter(waiter) do { } while (0) -#define debug_mutex_add_waiter(lock, waiter, ti, ip) do { } while (0) +#define debug_mutex_add_waiter(lock, waiter, ti) do { } while (0) #define debug_mutex_unlock(lock) do { } while (0) -#define debug_mutex_init(lock, name) do { } while (0) - -/* - * Return-address parameters/declarations. They are very useful for - * debugging, but add overhead in the !DEBUG case - so we go the - * trouble of using this not too elegant but zero-cost solution: - */ -#define __IP_DECL__ -#define __IP__ -#define __RET_IP__ +#define debug_mutex_init(lock, name, key) do { } while (0) +static inline void +debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter) +{ +} diff --git a/kernel/panic.c b/kernel/panic.c index cc2a4c9c36a..ab13f0f668b 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -8,7 +8,6 @@ * This function is used through-out the kernel (including mm and fs) * to indicate a major problem. */ -#include <linux/config.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/delay.h> diff --git a/kernel/params.c b/kernel/params.c index af43ecdc8d9..91aea7aa532 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -15,7 +15,6 @@ along with this program; if not, write to the Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#include <linux/config.h> #include <linux/moduleparam.h> #include <linux/kernel.h> #include <linux/string.h> diff --git a/kernel/pid.c b/kernel/pid.c index eeb836b65ca..93e212f2067 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -218,7 +218,7 @@ struct pid * fastcall find_pid(int nr) return NULL; } -int fastcall attach_pid(task_t *task, enum pid_type type, int nr) +int fastcall attach_pid(struct task_struct *task, enum pid_type type, int nr) { struct pid_link *link; struct pid *pid; @@ -233,7 +233,7 @@ int fastcall attach_pid(task_t *task, enum pid_type type, int nr) return 0; } -void fastcall detach_pid(task_t *task, enum pid_type type) +void fastcall detach_pid(struct task_struct *task, enum pid_type type) { struct pid_link *link; struct pid *pid; @@ -267,7 +267,7 @@ struct task_struct * fastcall pid_task(struct pid *pid, enum pid_type type) /* * Must be called under rcu_read_lock() or with tasklist_lock read-held. */ -task_t *find_task_by_pid_type(int type, int nr) +struct task_struct *find_task_by_pid_type(int type, int nr) { return pid_task(find_pid(nr), type); } diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 857b4fa0912..ae44a70aae8 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -100,18 +100,6 @@ config PM_STD_PARTITION suspended image to. It will simply pick the first available swap device. -config SWSUSP_ENCRYPT - bool "Encrypt suspend image" - depends on SOFTWARE_SUSPEND && CRYPTO=y && (CRYPTO_AES=y || CRYPTO_AES_586=y || CRYPTO_AES_X86_64=y) - default "" - ---help--- - To prevent data gathering from swap after resume you can encrypt - the suspend image with a temporary key that is deleted on - resume. - - Note that the temporary key is stored unencrypted on disk while the - system is suspended. - config SUSPEND_SMP bool depends on HOTPLUG_CPU && X86 && PM diff --git a/kernel/printk.c b/kernel/printk.c index 95b7fe17f12..bdba5d80496 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -26,7 +26,6 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/interrupt.h> /* For in_interrupt() */ -#include <linux/config.h> #include <linux/delay.h> #include <linux/smp.h> #include <linux/security.h> @@ -519,7 +518,9 @@ asmlinkage int vprintk(const char *fmt, va_list args) zap_locks(); /* This stops the holder of console_sem just where we want him */ - spin_lock_irqsave(&logbuf_lock, flags); + local_irq_save(flags); + lockdep_off(); + spin_lock(&logbuf_lock); printk_cpu = smp_processor_id(); /* Emit the output into the temporary buffer */ @@ -589,7 +590,7 @@ asmlinkage int vprintk(const char *fmt, va_list args) */ console_locked = 1; printk_cpu = UINT_MAX; - spin_unlock_irqrestore(&logbuf_lock, flags); + spin_unlock(&logbuf_lock); /* * Console drivers may assume that per-cpu resources have @@ -605,6 +606,8 @@ asmlinkage int vprintk(const char *fmt, va_list args) console_locked = 0; up(&console_sem); } + lockdep_on(); + local_irq_restore(flags); } else { /* * Someone else owns the drivers. We drop the spinlock, which @@ -612,7 +615,9 @@ asmlinkage int vprintk(const char *fmt, va_list args) * console drivers with the output which we just produced. */ printk_cpu = UINT_MAX; - spin_unlock_irqrestore(&logbuf_lock, flags); + spin_unlock(&logbuf_lock); + lockdep_on(); + local_irq_restore(flags); } preempt_enable(); @@ -810,8 +815,15 @@ void release_console_sem(void) console_may_schedule = 0; up(&console_sem); spin_unlock_irqrestore(&logbuf_lock, flags); - if (wake_klogd && !oops_in_progress && waitqueue_active(&log_wait)) - wake_up_interruptible(&log_wait); + if (wake_klogd && !oops_in_progress && waitqueue_active(&log_wait)) { + /* + * If we printk from within the lock dependency code, + * from within the scheduler code, then do not lock + * up due to self-recursion: + */ + if (!lockdep_internal()) + wake_up_interruptible(&log_wait); + } } EXPORT_SYMBOL(release_console_sem); diff --git a/kernel/profile.c b/kernel/profile.c index 5a730fdb1a2..d5bd75e7501 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -13,7 +13,6 @@ * to resolve timer interrupt livelocks, William Irwin, Oracle, 2004 */ -#include <linux/config.h> #include <linux/module.h> #include <linux/profile.h> #include <linux/bootmem.h> diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 335c5b932e1..9a111f70145 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -28,7 +28,7 @@ * * Must be called with the tasklist lock write-held. */ -void __ptrace_link(task_t *child, task_t *new_parent) +void __ptrace_link(struct task_struct *child, struct task_struct *new_parent) { BUG_ON(!list_empty(&child->ptrace_list)); if (child->parent == new_parent) @@ -46,7 +46,7 @@ void __ptrace_link(task_t *child, task_t *new_parent) * TASK_TRACED, resume it now. * Requires that irqs be disabled. */ -void ptrace_untrace(task_t *child) +void ptrace_untrace(struct task_struct *child) { spin_lock(&child->sighand->siglock); if (child->state == TASK_TRACED) { @@ -65,7 +65,7 @@ void ptrace_untrace(task_t *child) * * Must be called with the tasklist lock write-held. */ -void __ptrace_unlink(task_t *child) +void __ptrace_unlink(struct task_struct *child) { BUG_ON(!child->ptrace); diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index f464f5ae3f1..759805c9859 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -53,13 +53,13 @@ static struct rcu_ctrlblk rcu_ctrlblk = { .cur = -300, .completed = -300, - .lock = SPIN_LOCK_UNLOCKED, + .lock = __SPIN_LOCK_UNLOCKED(&rcu_ctrlblk.lock), .cpumask = CPU_MASK_NONE, }; static struct rcu_ctrlblk rcu_bh_ctrlblk = { .cur = -300, .completed = -300, - .lock = SPIN_LOCK_UNLOCKED, + .lock = __SPIN_LOCK_UNLOCKED(&rcu_bh_ctrlblk.lock), .cpumask = CPU_MASK_NONE, }; diff --git a/kernel/resource.c b/kernel/resource.c index 2404f9b0bc4..129cf046e56 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -7,7 +7,6 @@ * Arbitrary resource management. */ -#include <linux/config.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/errno.h> @@ -23,20 +22,18 @@ struct resource ioport_resource = { .name = "PCI IO", - .start = 0x0000, + .start = 0, .end = IO_SPACE_LIMIT, .flags = IORESOURCE_IO, }; - EXPORT_SYMBOL(ioport_resource); struct resource iomem_resource = { .name = "PCI mem", - .start = 0UL, - .end = ~0UL, + .start = 0, + .end = -1, .flags = IORESOURCE_MEM, }; - EXPORT_SYMBOL(iomem_resource); static DEFINE_RWLOCK(resource_lock); @@ -83,10 +80,10 @@ static int r_show(struct seq_file *m, void *v) for (depth = 0, p = r; depth < MAX_IORES_LEVEL; depth++, p = p->parent) if (p->parent == root) break; - seq_printf(m, "%*s%0*lx-%0*lx : %s\n", + seq_printf(m, "%*s%0*llx-%0*llx : %s\n", depth * 2, "", - width, r->start, - width, r->end, + width, (unsigned long long) r->start, + width, (unsigned long long) r->end, r->name ? r->name : "<BAD>"); return 0; } @@ -151,8 +148,8 @@ __initcall(ioresources_init); /* Return the conflict entry if you can't request it */ static struct resource * __request_resource(struct resource *root, struct resource *new) { - unsigned long start = new->start; - unsigned long end = new->end; + resource_size_t start = new->start; + resource_size_t end = new->end; struct resource *tmp, **p; if (end < start) @@ -274,11 +271,10 @@ int find_next_system_ram(struct resource *res) * Find empty slot in the resource tree given range and alignment. */ static int find_resource(struct resource *root, struct resource *new, - unsigned long size, - unsigned long min, unsigned long max, - unsigned long align, + resource_size_t size, resource_size_t min, + resource_size_t max, resource_size_t align, void (*alignf)(void *, struct resource *, - unsigned long, unsigned long), + resource_size_t, resource_size_t), void *alignf_data) { struct resource *this = root->child; @@ -320,11 +316,10 @@ static int find_resource(struct resource *root, struct resource *new, * Allocate empty slot in the resource tree given range and alignment. */ int allocate_resource(struct resource *root, struct resource *new, - unsigned long size, - unsigned long min, unsigned long max, - unsigned long align, + resource_size_t size, resource_size_t min, + resource_size_t max, resource_size_t align, void (*alignf)(void *, struct resource *, - unsigned long, unsigned long), + resource_size_t, resource_size_t), void *alignf_data) { int err; @@ -416,10 +411,10 @@ EXPORT_SYMBOL(insert_resource); * arguments. Returns -EBUSY if it can't fit. Existing children of * the resource are assumed to be immutable. */ -int adjust_resource(struct resource *res, unsigned long start, unsigned long size) +int adjust_resource(struct resource *res, resource_size_t start, resource_size_t size) { struct resource *tmp, *parent = res->parent; - unsigned long end = start + size - 1; + resource_size_t end = start + size - 1; int result = -EBUSY; write_lock(&resource_lock); @@ -466,7 +461,9 @@ EXPORT_SYMBOL(adjust_resource); * * Release-region releases a matching busy region. */ -struct resource * __request_region(struct resource *parent, unsigned long start, unsigned long n, const char *name) +struct resource * __request_region(struct resource *parent, + resource_size_t start, resource_size_t n, + const char *name) { struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL); @@ -502,7 +499,8 @@ struct resource * __request_region(struct resource *parent, unsigned long start, EXPORT_SYMBOL(__request_region); -int __check_region(struct resource *parent, unsigned long start, unsigned long n) +int __check_region(struct resource *parent, resource_size_t start, + resource_size_t n) { struct resource * res; @@ -517,10 +515,11 @@ int __check_region(struct resource *parent, unsigned long start, unsigned long n EXPORT_SYMBOL(__check_region); -void __release_region(struct resource *parent, unsigned long start, unsigned long n) +void __release_region(struct resource *parent, resource_size_t start, + resource_size_t n) { struct resource **p; - unsigned long end; + resource_size_t end; p = &parent->child; end = start + n - 1; @@ -549,7 +548,9 @@ void __release_region(struct resource *parent, unsigned long start, unsigned lon write_unlock(&resource_lock); - printk(KERN_WARNING "Trying to free nonexistent resource <%08lx-%08lx>\n", start, end); + printk(KERN_WARNING "Trying to free nonexistent resource " + "<%016llx-%016llx>\n", (unsigned long long)start, + (unsigned long long)end); } EXPORT_SYMBOL(__release_region); diff --git a/kernel/rtmutex-debug.c b/kernel/rtmutex-debug.c index 4aa8a2c9f45..0c1faa950af 100644 --- a/kernel/rtmutex-debug.c +++ b/kernel/rtmutex-debug.c @@ -26,6 +26,7 @@ #include <linux/interrupt.h> #include <linux/plist.h> #include <linux/fs.h> +#include <linux/debug_locks.h> #include "rtmutex_common.h" @@ -45,8 +46,6 @@ do { \ console_verbose(); \ if (spin_is_locked(¤t->pi_lock)) \ spin_unlock(¤t->pi_lock); \ - if (spin_is_locked(¤t->held_list_lock)) \ - spin_unlock(¤t->held_list_lock); \ } \ } while (0) @@ -97,7 +96,7 @@ void deadlock_trace_off(void) rt_trace_on = 0; } -static void printk_task(task_t *p) +static void printk_task(struct task_struct *p) { if (p) printk("%16s:%5d [%p, %3d]", p->comm, p->pid, p, p->prio); @@ -105,14 +104,6 @@ static void printk_task(task_t *p) printk("<none>"); } -static void printk_task_short(task_t *p) -{ - if (p) - printk("%s/%d [%p, %3d]", p->comm, p->pid, p, p->prio); - else - printk("<none>"); -} - static void printk_lock(struct rt_mutex *lock, int print_owner) { if (lock->name) @@ -128,222 +119,6 @@ static void printk_lock(struct rt_mutex *lock, int print_owner) printk_task(rt_mutex_owner(lock)); printk("\n"); } - if (rt_mutex_owner(lock)) { - printk("... acquired at: "); - print_symbol("%s\n", lock->acquire_ip); - } -} - -static void printk_waiter(struct rt_mutex_waiter *w) -{ - printk("-------------------------\n"); - printk("| waiter struct %p:\n", w); - printk("| w->list_entry: [DP:%p/%p|SP:%p/%p|PRI:%d]\n", - w->list_entry.plist.prio_list.prev, w->list_entry.plist.prio_list.next, - w->list_entry.plist.node_list.prev, w->list_entry.plist.node_list.next, - w->list_entry.prio); - printk("| w->pi_list_entry: [DP:%p/%p|SP:%p/%p|PRI:%d]\n", - w->pi_list_entry.plist.prio_list.prev, w->pi_list_entry.plist.prio_list.next, - w->pi_list_entry.plist.node_list.prev, w->pi_list_entry.plist.node_list.next, - w->pi_list_entry.prio); - printk("\n| lock:\n"); - printk_lock(w->lock, 1); - printk("| w->ti->task:\n"); - printk_task(w->task); - printk("| blocked at: "); - print_symbol("%s\n", w->ip); - printk("-------------------------\n"); -} - -static void show_task_locks(task_t *p) -{ - switch (p->state) { - case TASK_RUNNING: printk("R"); break; - case TASK_INTERRUPTIBLE: printk("S"); break; - case TASK_UNINTERRUPTIBLE: printk("D"); break; - case TASK_STOPPED: printk("T"); break; - case EXIT_ZOMBIE: printk("Z"); break; - case EXIT_DEAD: printk("X"); break; - default: printk("?"); break; - } - printk_task(p); - if (p->pi_blocked_on) { - struct rt_mutex *lock = p->pi_blocked_on->lock; - - printk(" blocked on:"); - printk_lock(lock, 1); - } else - printk(" (not blocked)\n"); -} - -void rt_mutex_show_held_locks(task_t *task, int verbose) -{ - struct list_head *curr, *cursor = NULL; - struct rt_mutex *lock; - task_t *t; - unsigned long flags; - int count = 0; - - if (!rt_trace_on) - return; - - if (verbose) { - printk("------------------------------\n"); - printk("| showing all locks held by: | ("); - printk_task_short(task); - printk("):\n"); - printk("------------------------------\n"); - } - -next: - spin_lock_irqsave(&task->held_list_lock, flags); - list_for_each(curr, &task->held_list_head) { - if (cursor && curr != cursor) - continue; - lock = list_entry(curr, struct rt_mutex, held_list_entry); - t = rt_mutex_owner(lock); - WARN_ON(t != task); - count++; - cursor = curr->next; - spin_unlock_irqrestore(&task->held_list_lock, flags); - - printk("\n#%03d: ", count); - printk_lock(lock, 0); - goto next; - } - spin_unlock_irqrestore(&task->held_list_lock, flags); - - printk("\n"); -} - -void rt_mutex_show_all_locks(void) -{ - task_t *g, *p; - int count = 10; - int unlock = 1; - - printk("\n"); - printk("----------------------\n"); - printk("| showing all tasks: |\n"); - printk("----------------------\n"); - - /* - * Here we try to get the tasklist_lock as hard as possible, - * if not successful after 2 seconds we ignore it (but keep - * trying). This is to enable a debug printout even if a - * tasklist_lock-holding task deadlocks or crashes. - */ -retry: - if (!read_trylock(&tasklist_lock)) { - if (count == 10) - printk("hm, tasklist_lock locked, retrying... "); - if (count) { - count--; - printk(" #%d", 10-count); - mdelay(200); - goto retry; - } - printk(" ignoring it.\n"); - unlock = 0; - } - if (count != 10) - printk(" locked it.\n"); - - do_each_thread(g, p) { - show_task_locks(p); - if (!unlock) - if (read_trylock(&tasklist_lock)) - unlock = 1; - } while_each_thread(g, p); - - printk("\n"); - - printk("-----------------------------------------\n"); - printk("| showing all locks held in the system: |\n"); - printk("-----------------------------------------\n"); - - do_each_thread(g, p) { - rt_mutex_show_held_locks(p, 0); - if (!unlock) - if (read_trylock(&tasklist_lock)) - unlock = 1; - } while_each_thread(g, p); - - - printk("=============================================\n\n"); - - if (unlock) - read_unlock(&tasklist_lock); -} - -void rt_mutex_debug_check_no_locks_held(task_t *task) -{ - struct rt_mutex_waiter *w; - struct list_head *curr; - struct rt_mutex *lock; - - if (!rt_trace_on) - return; - if (!rt_prio(task->normal_prio) && rt_prio(task->prio)) { - printk("BUG: PI priority boost leaked!\n"); - printk_task(task); - printk("\n"); - } - if (list_empty(&task->held_list_head)) - return; - - spin_lock(&task->pi_lock); - plist_for_each_entry(w, &task->pi_waiters, pi_list_entry) { - TRACE_OFF(); - - printk("hm, PI interest held at exit time? Task:\n"); - printk_task(task); - printk_waiter(w); - return; - } - spin_unlock(&task->pi_lock); - - list_for_each(curr, &task->held_list_head) { - lock = list_entry(curr, struct rt_mutex, held_list_entry); - - printk("BUG: %s/%d, lock held at task exit time!\n", - task->comm, task->pid); - printk_lock(lock, 1); - if (rt_mutex_owner(lock) != task) - printk("exiting task is not even the owner??\n"); - } -} - -int rt_mutex_debug_check_no_locks_freed(const void *from, unsigned long len) -{ - const void *to = from + len; - struct list_head *curr; - struct rt_mutex *lock; - unsigned long flags; - void *lock_addr; - - if (!rt_trace_on) - return 0; - - spin_lock_irqsave(¤t->held_list_lock, flags); - list_for_each(curr, ¤t->held_list_head) { - lock = list_entry(curr, struct rt_mutex, held_list_entry); - lock_addr = lock; - if (lock_addr < from || lock_addr >= to) - continue; - TRACE_OFF(); - - printk("BUG: %s/%d, active lock [%p(%p-%p)] freed!\n", - current->comm, current->pid, lock, from, to); - dump_stack(); - printk_lock(lock, 1); - if (rt_mutex_owner(lock) != current) - printk("freeing task is not even the owner??\n"); - return 1; - } - spin_unlock_irqrestore(¤t->held_list_lock, flags); - - return 0; } void rt_mutex_debug_task_free(struct task_struct *task) @@ -395,85 +170,41 @@ void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter) current->comm, current->pid); printk_lock(waiter->lock, 1); - printk("... trying at: "); - print_symbol("%s\n", waiter->ip); - printk("\n2) %s/%d is blocked on this lock:\n", task->comm, task->pid); printk_lock(waiter->deadlock_lock, 1); - rt_mutex_show_held_locks(current, 1); - rt_mutex_show_held_locks(task, 1); + debug_show_held_locks(current); + debug_show_held_locks(task); printk("\n%s/%d's [blocked] stackdump:\n\n", task->comm, task->pid); show_stack(task, NULL); printk("\n%s/%d's [current] stackdump:\n\n", current->comm, current->pid); dump_stack(); - rt_mutex_show_all_locks(); + debug_show_all_locks(); + printk("[ turning off deadlock detection." "Please report this trace. ]\n\n"); local_irq_disable(); } -void debug_rt_mutex_lock(struct rt_mutex *lock __IP_DECL__) +void debug_rt_mutex_lock(struct rt_mutex *lock) { - unsigned long flags; - - if (rt_trace_on) { - TRACE_WARN_ON_LOCKED(!list_empty(&lock->held_list_entry)); - - spin_lock_irqsave(¤t->held_list_lock, flags); - list_add_tail(&lock->held_list_entry, ¤t->held_list_head); - spin_unlock_irqrestore(¤t->held_list_lock, flags); - - lock->acquire_ip = ip; - } } void debug_rt_mutex_unlock(struct rt_mutex *lock) { - unsigned long flags; - - if (rt_trace_on) { - TRACE_WARN_ON_LOCKED(rt_mutex_owner(lock) != current); - TRACE_WARN_ON_LOCKED(list_empty(&lock->held_list_entry)); - - spin_lock_irqsave(¤t->held_list_lock, flags); - list_del_init(&lock->held_list_entry); - spin_unlock_irqrestore(¤t->held_list_lock, flags); - } + TRACE_WARN_ON_LOCKED(rt_mutex_owner(lock) != current); } -void debug_rt_mutex_proxy_lock(struct rt_mutex *lock, - struct task_struct *powner __IP_DECL__) +void +debug_rt_mutex_proxy_lock(struct rt_mutex *lock, struct task_struct *powner) { - unsigned long flags; - - if (rt_trace_on) { - TRACE_WARN_ON_LOCKED(!list_empty(&lock->held_list_entry)); - - spin_lock_irqsave(&powner->held_list_lock, flags); - list_add_tail(&lock->held_list_entry, &powner->held_list_head); - spin_unlock_irqrestore(&powner->held_list_lock, flags); - - lock->acquire_ip = ip; - } } void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock) { - unsigned long flags; - - if (rt_trace_on) { - struct task_struct *owner = rt_mutex_owner(lock); - - TRACE_WARN_ON_LOCKED(!owner); - TRACE_WARN_ON_LOCKED(list_empty(&lock->held_list_entry)); - - spin_lock_irqsave(&owner->held_list_lock, flags); - list_del_init(&lock->held_list_entry); - spin_unlock_irqrestore(&owner->held_list_lock, flags); - } + TRACE_WARN_ON_LOCKED(!rt_mutex_owner(lock)); } void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) @@ -493,17 +224,15 @@ void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter) void debug_rt_mutex_init(struct rt_mutex *lock, const char *name) { - void *addr = lock; - - if (rt_trace_on) { - rt_mutex_debug_check_no_locks_freed(addr, - sizeof(struct rt_mutex)); - INIT_LIST_HEAD(&lock->held_list_entry); - lock->name = name; - } + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lock->name = name; } -void rt_mutex_deadlock_account_lock(struct rt_mutex *lock, task_t *task) +void +rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task) { } diff --git a/kernel/rtmutex-debug.h b/kernel/rtmutex-debug.h index 7612fbc62d7..14193d596d7 100644 --- a/kernel/rtmutex-debug.h +++ b/kernel/rtmutex-debug.h @@ -9,20 +9,16 @@ * This file contains macros used solely by rtmutex.c. Debug version. */ -#define __IP_DECL__ , unsigned long ip -#define __IP__ , ip -#define __RET_IP__ , (unsigned long)__builtin_return_address(0) - extern void rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task); extern void rt_mutex_deadlock_account_unlock(struct task_struct *task); extern void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); extern void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter); extern void debug_rt_mutex_init(struct rt_mutex *lock, const char *name); -extern void debug_rt_mutex_lock(struct rt_mutex *lock __IP_DECL__); +extern void debug_rt_mutex_lock(struct rt_mutex *lock); extern void debug_rt_mutex_unlock(struct rt_mutex *lock); extern void debug_rt_mutex_proxy_lock(struct rt_mutex *lock, - struct task_struct *powner __IP_DECL__); + struct task_struct *powner); extern void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock); extern void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *waiter, struct rt_mutex *lock); diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c index e82c2f84824..494dac872a1 100644 --- a/kernel/rtmutex-tester.c +++ b/kernel/rtmutex-tester.c @@ -33,7 +33,7 @@ struct test_thread_data { }; static struct test_thread_data thread_data[MAX_RT_TEST_THREADS]; -static task_t *threads[MAX_RT_TEST_THREADS]; +static struct task_struct *threads[MAX_RT_TEST_THREADS]; static struct rt_mutex mutexes[MAX_RT_TEST_MUTEXES]; enum test_opcodes { @@ -361,8 +361,8 @@ static ssize_t sysfs_test_command(struct sys_device *dev, const char *buf, static ssize_t sysfs_test_status(struct sys_device *dev, char *buf) { struct test_thread_data *td; + struct task_struct *tsk; char *curr = buf; - task_t *tsk; int i; td = container_of(dev, struct test_thread_data, sysdev); diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c index 45d61016da5..d2ef13b485e 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -157,12 +157,11 @@ int max_lock_depth = 1024; * Decreases task's usage by one - may thus free the task. * Returns 0 or -EDEADLK. */ -static int rt_mutex_adjust_prio_chain(task_t *task, +static int rt_mutex_adjust_prio_chain(struct task_struct *task, int deadlock_detect, struct rt_mutex *orig_lock, struct rt_mutex_waiter *orig_waiter, - struct task_struct *top_task - __IP_DECL__) + struct task_struct *top_task) { struct rt_mutex *lock; struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter; @@ -283,6 +282,7 @@ static int rt_mutex_adjust_prio_chain(task_t *task, spin_unlock_irqrestore(&task->pi_lock, flags); out_put_task: put_task_struct(task); + return ret; } @@ -357,7 +357,7 @@ static inline int try_to_steal_lock(struct rt_mutex *lock) * * Must be called with lock->wait_lock held. */ -static int try_to_take_rt_mutex(struct rt_mutex *lock __IP_DECL__) +static int try_to_take_rt_mutex(struct rt_mutex *lock) { /* * We have to be careful here if the atomic speedups are @@ -384,7 +384,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock __IP_DECL__) return 0; /* We got the lock. */ - debug_rt_mutex_lock(lock __IP__); + debug_rt_mutex_lock(lock); rt_mutex_set_owner(lock, current, 0); @@ -402,13 +402,12 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock __IP_DECL__) */ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, - int detect_deadlock - __IP_DECL__) + int detect_deadlock) { + struct task_struct *owner = rt_mutex_owner(lock); struct rt_mutex_waiter *top_waiter = waiter; - task_t *owner = rt_mutex_owner(lock); - int boost = 0, res; unsigned long flags; + int boost = 0, res; spin_lock_irqsave(¤t->pi_lock, flags); __rt_mutex_adjust_prio(current); @@ -454,7 +453,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, spin_unlock(&lock->wait_lock); res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter, - current __IP__); + current); spin_lock(&lock->wait_lock); @@ -526,12 +525,12 @@ static void wakeup_next_waiter(struct rt_mutex *lock) * Must be called with lock->wait_lock held */ static void remove_waiter(struct rt_mutex *lock, - struct rt_mutex_waiter *waiter __IP_DECL__) + struct rt_mutex_waiter *waiter) { int first = (waiter == rt_mutex_top_waiter(lock)); - int boost = 0; - task_t *owner = rt_mutex_owner(lock); + struct task_struct *owner = rt_mutex_owner(lock); unsigned long flags; + int boost = 0; spin_lock_irqsave(¤t->pi_lock, flags); plist_del(&waiter->list_entry, &lock->wait_list); @@ -568,7 +567,7 @@ static void remove_waiter(struct rt_mutex *lock, spin_unlock(&lock->wait_lock); - rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current __IP__); + rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current); spin_lock(&lock->wait_lock); } @@ -595,7 +594,7 @@ void rt_mutex_adjust_pi(struct task_struct *task) get_task_struct(task); spin_unlock_irqrestore(&task->pi_lock, flags); - rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task __RET_IP__); + rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task); } /* @@ -604,7 +603,7 @@ void rt_mutex_adjust_pi(struct task_struct *task) static int __sched rt_mutex_slowlock(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - int detect_deadlock __IP_DECL__) + int detect_deadlock) { struct rt_mutex_waiter waiter; int ret = 0; @@ -615,7 +614,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, spin_lock(&lock->wait_lock); /* Try to acquire the lock again: */ - if (try_to_take_rt_mutex(lock __IP__)) { + if (try_to_take_rt_mutex(lock)) { spin_unlock(&lock->wait_lock); return 0; } @@ -629,7 +628,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, for (;;) { /* Try to acquire the lock: */ - if (try_to_take_rt_mutex(lock __IP__)) + if (try_to_take_rt_mutex(lock)) break; /* @@ -653,7 +652,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, */ if (!waiter.task) { ret = task_blocks_on_rt_mutex(lock, &waiter, - detect_deadlock __IP__); + detect_deadlock); /* * If we got woken up by the owner then start loop * all over without going into schedule to try @@ -680,7 +679,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, set_current_state(TASK_RUNNING); if (unlikely(waiter.task)) - remove_waiter(lock, &waiter __IP__); + remove_waiter(lock, &waiter); /* * try_to_take_rt_mutex() sets the waiter bit @@ -711,7 +710,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, * Slow path try-lock function: */ static inline int -rt_mutex_slowtrylock(struct rt_mutex *lock __IP_DECL__) +rt_mutex_slowtrylock(struct rt_mutex *lock) { int ret = 0; @@ -719,7 +718,7 @@ rt_mutex_slowtrylock(struct rt_mutex *lock __IP_DECL__) if (likely(rt_mutex_owner(lock) != current)) { - ret = try_to_take_rt_mutex(lock __IP__); + ret = try_to_take_rt_mutex(lock); /* * try_to_take_rt_mutex() sets the lock waiters * bit unconditionally. Clean this up. @@ -769,13 +768,13 @@ rt_mutex_fastlock(struct rt_mutex *lock, int state, int detect_deadlock, int (*slowfn)(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - int detect_deadlock __IP_DECL__)) + int detect_deadlock)) { if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) { rt_mutex_deadlock_account_lock(lock, current); return 0; } else - return slowfn(lock, state, NULL, detect_deadlock __RET_IP__); + return slowfn(lock, state, NULL, detect_deadlock); } static inline int @@ -783,24 +782,24 @@ rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, int detect_deadlock, int (*slowfn)(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - int detect_deadlock __IP_DECL__)) + int detect_deadlock)) { if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) { rt_mutex_deadlock_account_lock(lock, current); return 0; } else - return slowfn(lock, state, timeout, detect_deadlock __RET_IP__); + return slowfn(lock, state, timeout, detect_deadlock); } static inline int rt_mutex_fasttrylock(struct rt_mutex *lock, - int (*slowfn)(struct rt_mutex *lock __IP_DECL__)) + int (*slowfn)(struct rt_mutex *lock)) { if (likely(rt_mutex_cmpxchg(lock, NULL, current))) { rt_mutex_deadlock_account_lock(lock, current); return 1; } - return slowfn(lock __RET_IP__); + return slowfn(lock); } static inline void @@ -948,7 +947,7 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner) { __rt_mutex_init(lock, NULL); - debug_rt_mutex_proxy_lock(lock, proxy_owner __RET_IP__); + debug_rt_mutex_proxy_lock(lock, proxy_owner); rt_mutex_set_owner(lock, proxy_owner, 0); rt_mutex_deadlock_account_lock(lock, proxy_owner); } diff --git a/kernel/rtmutex.h b/kernel/rtmutex.h index 1e0fca13ff7..a1a1dd06421 100644 --- a/kernel/rtmutex.h +++ b/kernel/rtmutex.h @@ -10,9 +10,6 @@ * Non-debug version. */ -#define __IP_DECL__ -#define __IP__ -#define __RET_IP__ #define rt_mutex_deadlock_check(l) (0) #define rt_mutex_deadlock_account_lock(m, t) do { } while (0) #define rt_mutex_deadlock_account_unlock(l) do { } while (0) diff --git a/kernel/rwsem.c b/kernel/rwsem.c new file mode 100644 index 00000000000..291ded556aa --- /dev/null +++ b/kernel/rwsem.c @@ -0,0 +1,147 @@ +/* kernel/rwsem.c: R/W semaphores, public implementation + * + * Written by David Howells (dhowells@redhat.com). + * Derived from asm-i386/semaphore.h + */ + +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/rwsem.h> + +#include <asm/system.h> +#include <asm/atomic.h> + +/* + * lock for reading + */ +void down_read(struct rw_semaphore *sem) +{ + might_sleep(); + rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_); + + __down_read(sem); +} + +EXPORT_SYMBOL(down_read); + +/* + * trylock for reading -- returns 1 if successful, 0 if contention + */ +int down_read_trylock(struct rw_semaphore *sem) +{ + int ret = __down_read_trylock(sem); + + if (ret == 1) + rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_); + return ret; +} + +EXPORT_SYMBOL(down_read_trylock); + +/* + * lock for writing + */ +void down_write(struct rw_semaphore *sem) +{ + might_sleep(); + rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_); + + __down_write(sem); +} + +EXPORT_SYMBOL(down_write); + +/* + * trylock for writing -- returns 1 if successful, 0 if contention + */ +int down_write_trylock(struct rw_semaphore *sem) +{ + int ret = __down_write_trylock(sem); + + if (ret == 1) + rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_); + return ret; +} + +EXPORT_SYMBOL(down_write_trylock); + +/* + * release a read lock + */ +void up_read(struct rw_semaphore *sem) +{ + rwsem_release(&sem->dep_map, 1, _RET_IP_); + + __up_read(sem); +} + +EXPORT_SYMBOL(up_read); + +/* + * release a write lock + */ +void up_write(struct rw_semaphore *sem) +{ + rwsem_release(&sem->dep_map, 1, _RET_IP_); + + __up_write(sem); +} + +EXPORT_SYMBOL(up_write); + +/* + * downgrade write lock to read lock + */ +void downgrade_write(struct rw_semaphore *sem) +{ + /* + * lockdep: a downgraded write will live on as a write + * dependency. + */ + __downgrade_write(sem); +} + +EXPORT_SYMBOL(downgrade_write); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +void down_read_nested(struct rw_semaphore *sem, int subclass) +{ + might_sleep(); + rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_); + + __down_read(sem); +} + +EXPORT_SYMBOL(down_read_nested); + +void down_read_non_owner(struct rw_semaphore *sem) +{ + might_sleep(); + + __down_read(sem); +} + +EXPORT_SYMBOL(down_read_non_owner); + +void down_write_nested(struct rw_semaphore *sem, int subclass) +{ + might_sleep(); + rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_); + + __down_write_nested(sem, subclass); +} + +EXPORT_SYMBOL(down_write_nested); + +void up_read_non_owner(struct rw_semaphore *sem) +{ + __up_read(sem); +} + +EXPORT_SYMBOL(up_read_non_owner); + +#endif + + diff --git a/kernel/sched.c b/kernel/sched.c index 2629c1711fd..4ee400f9d56 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -30,6 +30,7 @@ #include <linux/capability.h> #include <linux/completion.h> #include <linux/kernel_stat.h> +#include <linux/debug_locks.h> #include <linux/security.h> #include <linux/notifier.h> #include <linux/profile.h> @@ -178,20 +179,15 @@ static unsigned int static_prio_timeslice(int static_prio) return SCALE_PRIO(DEF_TIMESLICE, static_prio); } -static inline unsigned int task_timeslice(task_t *p) +static inline unsigned int task_timeslice(struct task_struct *p) { return static_prio_timeslice(p->static_prio); } -#define task_hot(p, now, sd) ((long long) ((now) - (p)->last_ran) \ - < (long long) (sd)->cache_hot_time) - /* * These are the runqueue data structures: */ -typedef struct runqueue runqueue_t; - struct prio_array { unsigned int nr_active; DECLARE_BITMAP(bitmap, MAX_PRIO+1); /* include 1 bit for delimiter */ @@ -205,7 +201,7 @@ struct prio_array { * (such as the load balancing or the thread migration code), lock * acquire operations must be ordered by ascending &runqueue. */ -struct runqueue { +struct rq { spinlock_t lock; /* @@ -229,9 +225,9 @@ struct runqueue { unsigned long expired_timestamp; unsigned long long timestamp_last_tick; - task_t *curr, *idle; + struct task_struct *curr, *idle; struct mm_struct *prev_mm; - prio_array_t *active, *expired, arrays[2]; + struct prio_array *active, *expired, arrays[2]; int best_expired_prio; atomic_t nr_iowait; @@ -242,7 +238,7 @@ struct runqueue { int active_balance; int push_cpu; - task_t *migration_thread; + struct task_struct *migration_thread; struct list_head migration_queue; #endif @@ -265,9 +261,10 @@ struct runqueue { unsigned long ttwu_cnt; unsigned long ttwu_local; #endif + struct lock_class_key rq_lock_key; }; -static DEFINE_PER_CPU(struct runqueue, runqueues); +static DEFINE_PER_CPU(struct rq, runqueues); /* * The domain tree (rq->sd) is protected by RCU's quiescent state transition. @@ -276,8 +273,8 @@ static DEFINE_PER_CPU(struct runqueue, runqueues); * The domain tree of any CPU may only be accessed from within * preempt-disabled sections. */ -#define for_each_domain(cpu, domain) \ -for (domain = rcu_dereference(cpu_rq(cpu)->sd); domain; domain = domain->parent) +#define for_each_domain(cpu, __sd) \ + for (__sd = rcu_dereference(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent) #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) #define this_rq() (&__get_cpu_var(runqueues)) @@ -292,26 +289,33 @@ for (domain = rcu_dereference(cpu_rq(cpu)->sd); domain; domain = domain->parent) #endif #ifndef __ARCH_WANT_UNLOCKED_CTXSW -static inline int task_running(runqueue_t *rq, task_t *p) +static inline int task_running(struct rq *rq, struct task_struct *p) { return rq->curr == p; } -static inline void prepare_lock_switch(runqueue_t *rq, task_t *next) +static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) { } -static inline void finish_lock_switch(runqueue_t *rq, task_t *prev) +static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) { #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ rq->lock.owner = current; #endif + /* + * If we are tracking spinlock dependencies then we have to + * fix up the runqueue lock - which gets 'carried over' from + * prev into current: + */ + spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); + spin_unlock_irq(&rq->lock); } #else /* __ARCH_WANT_UNLOCKED_CTXSW */ -static inline int task_running(runqueue_t *rq, task_t *p) +static inline int task_running(struct rq *rq, struct task_struct *p) { #ifdef CONFIG_SMP return p->oncpu; @@ -320,7 +324,7 @@ static inline int task_running(runqueue_t *rq, task_t *p) #endif } -static inline void prepare_lock_switch(runqueue_t *rq, task_t *next) +static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) { #ifdef CONFIG_SMP /* @@ -337,7 +341,7 @@ static inline void prepare_lock_switch(runqueue_t *rq, task_t *next) #endif } -static inline void finish_lock_switch(runqueue_t *rq, task_t *prev) +static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) { #ifdef CONFIG_SMP /* @@ -358,10 +362,10 @@ static inline void finish_lock_switch(runqueue_t *rq, task_t *prev) * __task_rq_lock - lock the runqueue a given task resides on. * Must be called interrupts disabled. */ -static inline runqueue_t *__task_rq_lock(task_t *p) +static inline struct rq *__task_rq_lock(struct task_struct *p) __acquires(rq->lock) { - struct runqueue *rq; + struct rq *rq; repeat_lock_task: rq = task_rq(p); @@ -378,10 +382,10 @@ repeat_lock_task: * interrupts. Note the ordering: we can safely lookup the task_rq without * explicitly disabling preemption. */ -static runqueue_t *task_rq_lock(task_t *p, unsigned long *flags) +static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) __acquires(rq->lock) { - struct runqueue *rq; + struct rq *rq; repeat_lock_task: local_irq_save(*flags); @@ -394,13 +398,13 @@ repeat_lock_task: return rq; } -static inline void __task_rq_unlock(runqueue_t *rq) +static inline void __task_rq_unlock(struct rq *rq) __releases(rq->lock) { spin_unlock(&rq->lock); } -static inline void task_rq_unlock(runqueue_t *rq, unsigned long *flags) +static inline void task_rq_unlock(struct rq *rq, unsigned long *flags) __releases(rq->lock) { spin_unlock_irqrestore(&rq->lock, *flags); @@ -420,7 +424,7 @@ static int show_schedstat(struct seq_file *seq, void *v) seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION); seq_printf(seq, "timestamp %lu\n", jiffies); for_each_online_cpu(cpu) { - runqueue_t *rq = cpu_rq(cpu); + struct rq *rq = cpu_rq(cpu); #ifdef CONFIG_SMP struct sched_domain *sd; int dcnt = 0; @@ -507,10 +511,10 @@ struct file_operations proc_schedstat_operations = { /* * rq_lock - lock a given runqueue and disable interrupts. */ -static inline runqueue_t *this_rq_lock(void) +static inline struct rq *this_rq_lock(void) __acquires(rq->lock) { - runqueue_t *rq; + struct rq *rq; local_irq_disable(); rq = this_rq(); @@ -535,7 +539,7 @@ static inline runqueue_t *this_rq_lock(void) * long it was from the *first* time it was queued to the time that it * finally hit a cpu. */ -static inline void sched_info_dequeued(task_t *t) +static inline void sched_info_dequeued(struct task_struct *t) { t->sched_info.last_queued = 0; } @@ -545,10 +549,10 @@ static inline void sched_info_dequeued(task_t *t) * long it was waiting to run. We also note when it began so that we * can keep stats on how long its timeslice is. */ -static void sched_info_arrive(task_t *t) +static void sched_info_arrive(struct task_struct *t) { unsigned long now = jiffies, diff = 0; - struct runqueue *rq = task_rq(t); + struct rq *rq = task_rq(t); if (t->sched_info.last_queued) diff = now - t->sched_info.last_queued; @@ -579,7 +583,7 @@ static void sched_info_arrive(task_t *t) * the timestamp if it is already not set. It's assumed that * sched_info_dequeued() will clear that stamp when appropriate. */ -static inline void sched_info_queued(task_t *t) +static inline void sched_info_queued(struct task_struct *t) { if (!t->sched_info.last_queued) t->sched_info.last_queued = jiffies; @@ -589,9 +593,9 @@ static inline void sched_info_queued(task_t *t) * Called when a process ceases being the active-running process, either * voluntarily or involuntarily. Now we can calculate how long we ran. */ -static inline void sched_info_depart(task_t *t) +static inline void sched_info_depart(struct task_struct *t) { - struct runqueue *rq = task_rq(t); + struct rq *rq = task_rq(t); unsigned long diff = jiffies - t->sched_info.last_arrival; t->sched_info.cpu_time += diff; @@ -605,9 +609,10 @@ static inline void sched_info_depart(task_t *t) * their time slice. (This may also be called when switching to or from * the idle task.) We are only called when prev != next. */ -static inline void sched_info_switch(task_t *prev, task_t *next) +static inline void +sched_info_switch(struct task_struct *prev, struct task_struct *next) { - struct runqueue *rq = task_rq(prev); + struct rq *rq = task_rq(prev); /* * prev now departs the cpu. It's not interesting to record @@ -628,7 +633,7 @@ static inline void sched_info_switch(task_t *prev, task_t *next) /* * Adding/removing a task to/from a priority array: */ -static void dequeue_task(struct task_struct *p, prio_array_t *array) +static void dequeue_task(struct task_struct *p, struct prio_array *array) { array->nr_active--; list_del(&p->run_list); @@ -636,7 +641,7 @@ static void dequeue_task(struct task_struct *p, prio_array_t *array) __clear_bit(p->prio, array->bitmap); } -static void enqueue_task(struct task_struct *p, prio_array_t *array) +static void enqueue_task(struct task_struct *p, struct prio_array *array) { sched_info_queued(p); list_add_tail(&p->run_list, array->queue + p->prio); @@ -649,12 +654,13 @@ static void enqueue_task(struct task_struct *p, prio_array_t *array) * Put task to the end of the run list without the overhead of dequeue * followed by enqueue. */ -static void requeue_task(struct task_struct *p, prio_array_t *array) +static void requeue_task(struct task_struct *p, struct prio_array *array) { list_move_tail(&p->run_list, array->queue + p->prio); } -static inline void enqueue_task_head(struct task_struct *p, prio_array_t *array) +static inline void +enqueue_task_head(struct task_struct *p, struct prio_array *array) { list_add(&p->run_list, array->queue + p->prio); __set_bit(p->prio, array->bitmap); @@ -677,7 +683,7 @@ static inline void enqueue_task_head(struct task_struct *p, prio_array_t *array) * Both properties are important to certain workloads. */ -static inline int __normal_prio(task_t *p) +static inline int __normal_prio(struct task_struct *p) { int bonus, prio; @@ -713,7 +719,7 @@ static inline int __normal_prio(task_t *p) #define RTPRIO_TO_LOAD_WEIGHT(rp) \ (PRIO_TO_LOAD_WEIGHT(MAX_RT_PRIO) + LOAD_WEIGHT(rp)) -static void set_load_weight(task_t *p) +static void set_load_weight(struct task_struct *p) { if (has_rt_policy(p)) { #ifdef CONFIG_SMP @@ -731,23 +737,25 @@ static void set_load_weight(task_t *p) p->load_weight = PRIO_TO_LOAD_WEIGHT(p->static_prio); } -static inline void inc_raw_weighted_load(runqueue_t *rq, const task_t *p) +static inline void +inc_raw_weighted_load(struct rq *rq, const struct task_struct *p) { rq->raw_weighted_load += p->load_weight; } -static inline void dec_raw_weighted_load(runqueue_t *rq, const task_t *p) +static inline void +dec_raw_weighted_load(struct rq *rq, const struct task_struct *p) { rq->raw_weighted_load -= p->load_weight; } -static inline void inc_nr_running(task_t *p, runqueue_t *rq) +static inline void inc_nr_running(struct task_struct *p, struct rq *rq) { rq->nr_running++; inc_raw_weighted_load(rq, p); } -static inline void dec_nr_running(task_t *p, runqueue_t *rq) +static inline void dec_nr_running(struct task_struct *p, struct rq *rq) { rq->nr_running--; dec_raw_weighted_load(rq, p); @@ -760,7 +768,7 @@ static inline void dec_nr_running(task_t *p, runqueue_t *rq) * setprio syscalls, and whenever the interactivity * estimator recalculates. */ -static inline int normal_prio(task_t *p) +static inline int normal_prio(struct task_struct *p) { int prio; @@ -778,7 +786,7 @@ static inline int normal_prio(task_t *p) * interactivity modifiers. Will be RT if the task got * RT-boosted. If not then it returns p->normal_prio. */ -static int effective_prio(task_t *p) +static int effective_prio(struct task_struct *p) { p->normal_prio = normal_prio(p); /* @@ -794,9 +802,9 @@ static int effective_prio(task_t *p) /* * __activate_task - move a task to the runqueue. */ -static void __activate_task(task_t *p, runqueue_t *rq) +static void __activate_task(struct task_struct *p, struct rq *rq) { - prio_array_t *target = rq->active; + struct prio_array *target = rq->active; if (batch_task(p)) target = rq->expired; @@ -807,7 +815,7 @@ static void __activate_task(task_t *p, runqueue_t *rq) /* * __activate_idle_task - move idle task to the _front_ of runqueue. */ -static inline void __activate_idle_task(task_t *p, runqueue_t *rq) +static inline void __activate_idle_task(struct task_struct *p, struct rq *rq) { enqueue_task_head(p, rq->active); inc_nr_running(p, rq); @@ -817,7 +825,7 @@ static inline void __activate_idle_task(task_t *p, runqueue_t *rq) * Recalculate p->normal_prio and p->prio after having slept, * updating the sleep-average too: */ -static int recalc_task_prio(task_t *p, unsigned long long now) +static int recalc_task_prio(struct task_struct *p, unsigned long long now) { /* Caller must always ensure 'now >= p->timestamp' */ unsigned long sleep_time = now - p->timestamp; @@ -889,7 +897,7 @@ static int recalc_task_prio(task_t *p, unsigned long long now) * Update all the scheduling statistics stuff. (sleep average * calculation, priority modifiers, etc.) */ -static void activate_task(task_t *p, runqueue_t *rq, int local) +static void activate_task(struct task_struct *p, struct rq *rq, int local) { unsigned long long now; @@ -897,7 +905,7 @@ static void activate_task(task_t *p, runqueue_t *rq, int local) #ifdef CONFIG_SMP if (!local) { /* Compensate for drifting sched_clock */ - runqueue_t *this_rq = this_rq(); + struct rq *this_rq = this_rq(); now = (now - this_rq->timestamp_last_tick) + rq->timestamp_last_tick; } @@ -936,7 +944,7 @@ static void activate_task(task_t *p, runqueue_t *rq, int local) /* * deactivate_task - remove a task from the runqueue. */ -static void deactivate_task(struct task_struct *p, runqueue_t *rq) +static void deactivate_task(struct task_struct *p, struct rq *rq) { dec_nr_running(p, rq); dequeue_task(p, p->array); @@ -956,7 +964,7 @@ static void deactivate_task(struct task_struct *p, runqueue_t *rq) #define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) #endif -static void resched_task(task_t *p) +static void resched_task(struct task_struct *p) { int cpu; @@ -977,7 +985,7 @@ static void resched_task(task_t *p) smp_send_reschedule(cpu); } #else -static inline void resched_task(task_t *p) +static inline void resched_task(struct task_struct *p) { assert_spin_locked(&task_rq(p)->lock); set_tsk_need_resched(p); @@ -988,7 +996,7 @@ static inline void resched_task(task_t *p) * task_curr - is this task currently executing on a CPU? * @p: the task in question. */ -inline int task_curr(const task_t *p) +inline int task_curr(const struct task_struct *p) { return cpu_curr(task_cpu(p)) == p; } @@ -1000,22 +1008,23 @@ unsigned long weighted_cpuload(const int cpu) } #ifdef CONFIG_SMP -typedef struct { +struct migration_req { struct list_head list; - task_t *task; + struct task_struct *task; int dest_cpu; struct completion done; -} migration_req_t; +}; /* * The task's runqueue lock must be held. * Returns true if you have to wait for migration thread. */ -static int migrate_task(task_t *p, int dest_cpu, migration_req_t *req) +static int +migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req) { - runqueue_t *rq = task_rq(p); + struct rq *rq = task_rq(p); /* * If the task is not on a runqueue (and not running), then @@ -1030,6 +1039,7 @@ static int migrate_task(task_t *p, int dest_cpu, migration_req_t *req) req->task = p; req->dest_cpu = dest_cpu; list_add(&req->list, &rq->migration_queue); + return 1; } @@ -1042,10 +1052,10 @@ static int migrate_task(task_t *p, int dest_cpu, migration_req_t *req) * smp_call_function() if an IPI is sent by the same process we are * waiting to become inactive. */ -void wait_task_inactive(task_t *p) +void wait_task_inactive(struct task_struct *p) { unsigned long flags; - runqueue_t *rq; + struct rq *rq; int preempted; repeat: @@ -1076,7 +1086,7 @@ repeat: * to another CPU then no harm is done and the purpose has been * achieved as well. */ -void kick_process(task_t *p) +void kick_process(struct task_struct *p) { int cpu; @@ -1096,7 +1106,7 @@ void kick_process(task_t *p) */ static inline unsigned long source_load(int cpu, int type) { - runqueue_t *rq = cpu_rq(cpu); + struct rq *rq = cpu_rq(cpu); if (type == 0) return rq->raw_weighted_load; @@ -1110,7 +1120,7 @@ static inline unsigned long source_load(int cpu, int type) */ static inline unsigned long target_load(int cpu, int type) { - runqueue_t *rq = cpu_rq(cpu); + struct rq *rq = cpu_rq(cpu); if (type == 0) return rq->raw_weighted_load; @@ -1123,10 +1133,10 @@ static inline unsigned long target_load(int cpu, int type) */ static inline unsigned long cpu_avg_load_per_task(int cpu) { - runqueue_t *rq = cpu_rq(cpu); + struct rq *rq = cpu_rq(cpu); unsigned long n = rq->nr_running; - return n ? rq->raw_weighted_load / n : SCHED_LOAD_SCALE; + return n ? rq->raw_weighted_load / n : SCHED_LOAD_SCALE; } /* @@ -1279,7 +1289,7 @@ nextlevel: * Returns the CPU we should wake onto. */ #if defined(ARCH_HAS_SCHED_WAKE_IDLE) -static int wake_idle(int cpu, task_t *p) +static int wake_idle(int cpu, struct task_struct *p) { cpumask_t tmp; struct sched_domain *sd; @@ -1302,7 +1312,7 @@ static int wake_idle(int cpu, task_t *p) return cpu; } #else -static inline int wake_idle(int cpu, task_t *p) +static inline int wake_idle(int cpu, struct task_struct *p) { return cpu; } @@ -1322,15 +1332,15 @@ static inline int wake_idle(int cpu, task_t *p) * * returns failure only if the task is already active. */ -static int try_to_wake_up(task_t *p, unsigned int state, int sync) +static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) { int cpu, this_cpu, success = 0; unsigned long flags; long old_state; - runqueue_t *rq; + struct rq *rq; #ifdef CONFIG_SMP - unsigned long load, this_load; struct sched_domain *sd, *this_sd = NULL; + unsigned long load, this_load; int new_cpu; #endif @@ -1480,15 +1490,14 @@ out: return success; } -int fastcall wake_up_process(task_t *p) +int fastcall wake_up_process(struct task_struct *p) { return try_to_wake_up(p, TASK_STOPPED | TASK_TRACED | TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE, 0); } - EXPORT_SYMBOL(wake_up_process); -int fastcall wake_up_state(task_t *p, unsigned int state) +int fastcall wake_up_state(struct task_struct *p, unsigned int state) { return try_to_wake_up(p, state, 0); } @@ -1497,7 +1506,7 @@ int fastcall wake_up_state(task_t *p, unsigned int state) * Perform scheduler related setup for a newly forked process p. * p is forked by current. */ -void fastcall sched_fork(task_t *p, int clone_flags) +void fastcall sched_fork(struct task_struct *p, int clone_flags) { int cpu = get_cpu(); @@ -1565,11 +1574,11 @@ void fastcall sched_fork(task_t *p, int clone_flags) * that must be done for every newly created context, then puts the task * on the runqueue and wakes it. */ -void fastcall wake_up_new_task(task_t *p, unsigned long clone_flags) +void fastcall wake_up_new_task(struct task_struct *p, unsigned long clone_flags) { + struct rq *rq, *this_rq; unsigned long flags; int this_cpu, cpu; - runqueue_t *rq, *this_rq; rq = task_rq_lock(p, &flags); BUG_ON(p->state != TASK_RUNNING); @@ -1649,10 +1658,10 @@ void fastcall wake_up_new_task(task_t *p, unsigned long clone_flags) * artificially, because any timeslice recovered here * was given away by the parent in the first place.) */ -void fastcall sched_exit(task_t *p) +void fastcall sched_exit(struct task_struct *p) { unsigned long flags; - runqueue_t *rq; + struct rq *rq; /* * If the child was a (relative-) CPU hog then decrease @@ -1683,7 +1692,7 @@ void fastcall sched_exit(task_t *p) * prepare_task_switch sets up locking and calls architecture specific * hooks. */ -static inline void prepare_task_switch(runqueue_t *rq, task_t *next) +static inline void prepare_task_switch(struct rq *rq, struct task_struct *next) { prepare_lock_switch(rq, next); prepare_arch_switch(next); @@ -1704,7 +1713,7 @@ static inline void prepare_task_switch(runqueue_t *rq, task_t *next) * with the lock held can cause deadlocks; see schedule() for * details.) */ -static inline void finish_task_switch(runqueue_t *rq, task_t *prev) +static inline void finish_task_switch(struct rq *rq, struct task_struct *prev) __releases(rq->lock) { struct mm_struct *mm = rq->prev_mm; @@ -1742,10 +1751,11 @@ static inline void finish_task_switch(runqueue_t *rq, task_t *prev) * schedule_tail - first thing a freshly forked thread must call. * @prev: the thread we just switched away from. */ -asmlinkage void schedule_tail(task_t *prev) +asmlinkage void schedule_tail(struct task_struct *prev) __releases(rq->lock) { - runqueue_t *rq = this_rq(); + struct rq *rq = this_rq(); + finish_task_switch(rq, prev); #ifdef __ARCH_WANT_UNLOCKED_CTXSW /* In this case, finish_task_switch does not reenable preemption */ @@ -1759,8 +1769,9 @@ asmlinkage void schedule_tail(task_t *prev) * context_switch - switch to the new MM and the new * thread's register state. */ -static inline -task_t * context_switch(runqueue_t *rq, task_t *prev, task_t *next) +static inline struct task_struct * +context_switch(struct rq *rq, struct task_struct *prev, + struct task_struct *next) { struct mm_struct *mm = next->mm; struct mm_struct *oldmm = prev->active_mm; @@ -1777,6 +1788,7 @@ task_t * context_switch(runqueue_t *rq, task_t *prev, task_t *next) WARN_ON(rq->prev_mm); rq->prev_mm = oldmm; } + spin_release(&rq->lock.dep_map, 1, _THIS_IP_); /* Here we just switch the register state and the stack. */ switch_to(prev, next, prev); @@ -1857,12 +1869,21 @@ unsigned long nr_active(void) #ifdef CONFIG_SMP /* + * Is this task likely cache-hot: + */ +static inline int +task_hot(struct task_struct *p, unsigned long long now, struct sched_domain *sd) +{ + return (long long)(now - p->last_ran) < (long long)sd->cache_hot_time; +} + +/* * double_rq_lock - safely lock two runqueues * * Note this does not disable interrupts like task_rq_lock, * you need to do so manually before calling. */ -static void double_rq_lock(runqueue_t *rq1, runqueue_t *rq2) +static void double_rq_lock(struct rq *rq1, struct rq *rq2) __acquires(rq1->lock) __acquires(rq2->lock) { @@ -1886,7 +1907,7 @@ static void double_rq_lock(runqueue_t *rq1, runqueue_t *rq2) * Note this does not restore interrupts like task_rq_unlock, * you need to do so manually after calling. */ -static void double_rq_unlock(runqueue_t *rq1, runqueue_t *rq2) +static void double_rq_unlock(struct rq *rq1, struct rq *rq2) __releases(rq1->lock) __releases(rq2->lock) { @@ -1900,7 +1921,7 @@ static void double_rq_unlock(runqueue_t *rq1, runqueue_t *rq2) /* * double_lock_balance - lock the busiest runqueue, this_rq is locked already. */ -static void double_lock_balance(runqueue_t *this_rq, runqueue_t *busiest) +static void double_lock_balance(struct rq *this_rq, struct rq *busiest) __releases(this_rq->lock) __acquires(busiest->lock) __acquires(this_rq->lock) @@ -1921,11 +1942,11 @@ static void double_lock_balance(runqueue_t *this_rq, runqueue_t *busiest) * allow dest_cpu, which will force the cpu onto dest_cpu. Then * the cpu_allowed mask is restored. */ -static void sched_migrate_task(task_t *p, int dest_cpu) +static void sched_migrate_task(struct task_struct *p, int dest_cpu) { - migration_req_t req; - runqueue_t *rq; + struct migration_req req; unsigned long flags; + struct rq *rq; rq = task_rq_lock(p, &flags); if (!cpu_isset(dest_cpu, p->cpus_allowed) @@ -1936,11 +1957,13 @@ static void sched_migrate_task(task_t *p, int dest_cpu) if (migrate_task(p, dest_cpu, &req)) { /* Need to wait for migration thread (might exit: take ref). */ struct task_struct *mt = rq->migration_thread; + get_task_struct(mt); task_rq_unlock(rq, &flags); wake_up_process(mt); put_task_struct(mt); wait_for_completion(&req.done); + return; } out: @@ -1964,9 +1987,9 @@ void sched_exec(void) * pull_task - move a task from a remote runqueue to the local runqueue. * Both runqueues must be locked. */ -static -void pull_task(runqueue_t *src_rq, prio_array_t *src_array, task_t *p, - runqueue_t *this_rq, prio_array_t *this_array, int this_cpu) +static void pull_task(struct rq *src_rq, struct prio_array *src_array, + struct task_struct *p, struct rq *this_rq, + struct prio_array *this_array, int this_cpu) { dequeue_task(p, src_array); dec_nr_running(p, src_rq); @@ -1987,7 +2010,7 @@ void pull_task(runqueue_t *src_rq, prio_array_t *src_array, task_t *p, * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? */ static -int can_migrate_task(task_t *p, runqueue_t *rq, int this_cpu, +int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, struct sched_domain *sd, enum idle_type idle, int *all_pinned) { @@ -2019,6 +2042,7 @@ int can_migrate_task(task_t *p, runqueue_t *rq, int this_cpu, } #define rq_best_prio(rq) min((rq)->curr->prio, (rq)->best_expired_prio) + /* * move_tasks tries to move up to max_nr_move tasks and max_load_move weighted * load from busiest to this_rq, as part of a balancing operation within @@ -2026,18 +2050,17 @@ int can_migrate_task(task_t *p, runqueue_t *rq, int this_cpu, * * Called with both runqueues locked. */ -static int move_tasks(runqueue_t *this_rq, int this_cpu, runqueue_t *busiest, +static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, unsigned long max_nr_move, unsigned long max_load_move, struct sched_domain *sd, enum idle_type idle, int *all_pinned) { - prio_array_t *array, *dst_array; + int idx, pulled = 0, pinned = 0, this_best_prio, best_prio, + best_prio_seen, skip_for_load; + struct prio_array *array, *dst_array; struct list_head *head, *curr; - int idx, pulled = 0, pinned = 0, this_best_prio, busiest_best_prio; - int busiest_best_prio_seen; - int skip_for_load; /* skip the task based on weighted load issues */ + struct task_struct *tmp; long rem_load_move; - task_t *tmp; if (max_nr_move == 0 || max_load_move == 0) goto out; @@ -2045,15 +2068,15 @@ static int move_tasks(runqueue_t *this_rq, int this_cpu, runqueue_t *busiest, rem_load_move = max_load_move; pinned = 1; this_best_prio = rq_best_prio(this_rq); - busiest_best_prio = rq_best_prio(busiest); + best_prio = rq_best_prio(busiest); /* * Enable handling of the case where there is more than one task * with the best priority. If the current running task is one - * of those with prio==busiest_best_prio we know it won't be moved + * of those with prio==best_prio we know it won't be moved * and therefore it's safe to override the skip (based on load) of * any task we find with that prio. */ - busiest_best_prio_seen = busiest_best_prio == busiest->curr->prio; + best_prio_seen = best_prio == busiest->curr->prio; /* * We first consider expired tasks. Those will likely not be @@ -2089,7 +2112,7 @@ skip_bitmap: head = array->queue + idx; curr = head->prev; skip_queue: - tmp = list_entry(curr, task_t, run_list); + tmp = list_entry(curr, struct task_struct, run_list); curr = curr->prev; @@ -2100,10 +2123,11 @@ skip_queue: */ skip_for_load = tmp->load_weight > rem_load_move; if (skip_for_load && idx < this_best_prio) - skip_for_load = !busiest_best_prio_seen && idx == busiest_best_prio; + skip_for_load = !best_prio_seen && idx == best_prio; if (skip_for_load || !can_migrate_task(tmp, busiest, this_cpu, sd, idle, &pinned)) { - busiest_best_prio_seen |= idx == busiest_best_prio; + + best_prio_seen |= idx == best_prio; if (curr != head) goto skip_queue; idx++; @@ -2146,8 +2170,8 @@ out: /* * find_busiest_group finds and returns the busiest CPU group within the - * domain. It calculates and returns the amount of weighted load which should be - * moved to restore balance via the imbalance parameter. + * domain. It calculates and returns the amount of weighted load which + * should be moved to restore balance via the imbalance parameter. */ static struct sched_group * find_busiest_group(struct sched_domain *sd, int this_cpu, @@ -2188,7 +2212,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, sum_weighted_load = sum_nr_running = avg_load = 0; for_each_cpu_mask(i, group->cpumask) { - runqueue_t *rq = cpu_rq(i); + struct rq *rq = cpu_rq(i); if (*sd_idle && !idle_cpu(i)) *sd_idle = 0; @@ -2269,7 +2293,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, * capacity but still has some space to pick up some load * from other group and save more power */ - if (sum_nr_running <= group_capacity - 1) + if (sum_nr_running <= group_capacity - 1) { if (sum_nr_running > leader_nr_running || (sum_nr_running == leader_nr_running && first_cpu(group->cpumask) > @@ -2277,7 +2301,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, group_leader = group; leader_nr_running = sum_nr_running; } - + } group_next: #endif group = group->next; @@ -2332,8 +2356,7 @@ group_next: * moved */ if (*imbalance < busiest_load_per_task) { - unsigned long pwr_now, pwr_move; - unsigned long tmp; + unsigned long tmp, pwr_now, pwr_move; unsigned int imbn; small_imbalance: @@ -2405,22 +2428,23 @@ ret: /* * find_busiest_queue - find the busiest runqueue among the cpus in group. */ -static runqueue_t *find_busiest_queue(struct sched_group *group, - enum idle_type idle, unsigned long imbalance) +static struct rq * +find_busiest_queue(struct sched_group *group, enum idle_type idle, + unsigned long imbalance) { + struct rq *busiest = NULL, *rq; unsigned long max_load = 0; - runqueue_t *busiest = NULL, *rqi; int i; for_each_cpu_mask(i, group->cpumask) { - rqi = cpu_rq(i); + rq = cpu_rq(i); - if (rqi->nr_running == 1 && rqi->raw_weighted_load > imbalance) + if (rq->nr_running == 1 && rq->raw_weighted_load > imbalance) continue; - if (rqi->raw_weighted_load > max_load) { - max_load = rqi->raw_weighted_load; - busiest = rqi; + if (rq->raw_weighted_load > max_load) { + max_load = rq->raw_weighted_load; + busiest = rq; } } @@ -2433,22 +2457,24 @@ static runqueue_t *find_busiest_queue(struct sched_group *group, */ #define MAX_PINNED_INTERVAL 512 -#define minus_1_or_zero(n) ((n) > 0 ? (n) - 1 : 0) +static inline unsigned long minus_1_or_zero(unsigned long n) +{ + return n > 0 ? n - 1 : 0; +} + /* * Check this_cpu to ensure it is balanced within domain. Attempt to move * tasks if there is an imbalance. * * Called with this_rq unlocked. */ -static int load_balance(int this_cpu, runqueue_t *this_rq, +static int load_balance(int this_cpu, struct rq *this_rq, struct sched_domain *sd, enum idle_type idle) { + int nr_moved, all_pinned = 0, active_balance = 0, sd_idle = 0; struct sched_group *group; - runqueue_t *busiest; unsigned long imbalance; - int nr_moved, all_pinned = 0; - int active_balance = 0; - int sd_idle = 0; + struct rq *busiest; if (idle != NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER && !sched_smt_power_savings) @@ -2482,8 +2508,8 @@ static int load_balance(int this_cpu, runqueue_t *this_rq, */ double_rq_lock(this_rq, busiest); nr_moved = move_tasks(this_rq, this_cpu, busiest, - minus_1_or_zero(busiest->nr_running), - imbalance, sd, idle, &all_pinned); + minus_1_or_zero(busiest->nr_running), + imbalance, sd, idle, &all_pinned); double_rq_unlock(this_rq, busiest); /* All tasks on this runqueue were pinned by CPU affinity */ @@ -2556,7 +2582,8 @@ out_one_pinned: (sd->balance_interval < sd->max_interval)) sd->balance_interval *= 2; - if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && !sched_smt_power_savings) + if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && + !sched_smt_power_savings) return -1; return 0; } @@ -2568,11 +2595,11 @@ out_one_pinned: * Called from schedule when this_rq is about to become idle (NEWLY_IDLE). * this_rq is locked. */ -static int load_balance_newidle(int this_cpu, runqueue_t *this_rq, - struct sched_domain *sd) +static int +load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd) { struct sched_group *group; - runqueue_t *busiest = NULL; + struct rq *busiest = NULL; unsigned long imbalance; int nr_moved = 0; int sd_idle = 0; @@ -2618,9 +2645,11 @@ static int load_balance_newidle(int this_cpu, runqueue_t *this_rq, out_balanced: schedstat_inc(sd, lb_balanced[NEWLY_IDLE]); - if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && !sched_smt_power_savings) + if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && + !sched_smt_power_savings) return -1; sd->nr_balance_failed = 0; + return 0; } @@ -2628,16 +2657,15 @@ out_balanced: * idle_balance is called by schedule() if this_cpu is about to become * idle. Attempts to pull tasks from other CPUs. */ -static void idle_balance(int this_cpu, runqueue_t *this_rq) +static void idle_balance(int this_cpu, struct rq *this_rq) { struct sched_domain *sd; for_each_domain(this_cpu, sd) { if (sd->flags & SD_BALANCE_NEWIDLE) { - if (load_balance_newidle(this_cpu, this_rq, sd)) { - /* We've pulled tasks over so stop searching */ + /* If we've pulled tasks over stop searching: */ + if (load_balance_newidle(this_cpu, this_rq, sd)) break; - } } } } @@ -2650,14 +2678,14 @@ static void idle_balance(int this_cpu, runqueue_t *this_rq) * * Called with busiest_rq locked. */ -static void active_load_balance(runqueue_t *busiest_rq, int busiest_cpu) +static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) { - struct sched_domain *sd; - runqueue_t *target_rq; int target_cpu = busiest_rq->push_cpu; + struct sched_domain *sd; + struct rq *target_rq; + /* Is there any task to move? */ if (busiest_rq->nr_running <= 1) - /* no task to move */ return; target_rq = cpu_rq(target_cpu); @@ -2675,21 +2703,20 @@ static void active_load_balance(runqueue_t *busiest_rq, int busiest_cpu) /* Search for an sd spanning us and the target CPU. */ for_each_domain(target_cpu, sd) { if ((sd->flags & SD_LOAD_BALANCE) && - cpu_isset(busiest_cpu, sd->span)) + cpu_isset(busiest_cpu, sd->span)) break; } - if (unlikely(sd == NULL)) - goto out; - - schedstat_inc(sd, alb_cnt); + if (likely(sd)) { + schedstat_inc(sd, alb_cnt); - if (move_tasks(target_rq, target_cpu, busiest_rq, 1, - RTPRIO_TO_LOAD_WEIGHT(100), sd, SCHED_IDLE, NULL)) - schedstat_inc(sd, alb_pushed); - else - schedstat_inc(sd, alb_failed); -out: + if (move_tasks(target_rq, target_cpu, busiest_rq, 1, + RTPRIO_TO_LOAD_WEIGHT(100), sd, SCHED_IDLE, + NULL)) + schedstat_inc(sd, alb_pushed); + else + schedstat_inc(sd, alb_failed); + } spin_unlock(&target_rq->lock); } @@ -2702,23 +2729,27 @@ out: * Balancing parameters are set up in arch_init_sched_domains. */ -/* Don't have all balancing operations going off at once */ -#define CPU_OFFSET(cpu) (HZ * cpu / NR_CPUS) +/* Don't have all balancing operations going off at once: */ +static inline unsigned long cpu_offset(int cpu) +{ + return jiffies + cpu * HZ / NR_CPUS; +} -static void rebalance_tick(int this_cpu, runqueue_t *this_rq, - enum idle_type idle) +static void +rebalance_tick(int this_cpu, struct rq *this_rq, enum idle_type idle) { - unsigned long old_load, this_load; - unsigned long j = jiffies + CPU_OFFSET(this_cpu); + unsigned long this_load, interval, j = cpu_offset(this_cpu); struct sched_domain *sd; - int i; + int i, scale; this_load = this_rq->raw_weighted_load; - /* Update our load */ - for (i = 0; i < 3; i++) { - unsigned long new_load = this_load; - int scale = 1 << i; + + /* Update our load: */ + for (i = 0, scale = 1; i < 3; i++, scale <<= 1) { + unsigned long old_load, new_load; + old_load = this_rq->cpu_load[i]; + new_load = this_load; /* * Round up the averaging division if load is increasing. This * prevents us from getting stuck on 9 if the load is 10, for @@ -2730,8 +2761,6 @@ static void rebalance_tick(int this_cpu, runqueue_t *this_rq, } for_each_domain(this_cpu, sd) { - unsigned long interval; - if (!(sd->flags & SD_LOAD_BALANCE)) continue; @@ -2761,17 +2790,18 @@ static void rebalance_tick(int this_cpu, runqueue_t *this_rq, /* * on UP we do not need to balance between CPUs: */ -static inline void rebalance_tick(int cpu, runqueue_t *rq, enum idle_type idle) +static inline void rebalance_tick(int cpu, struct rq *rq, enum idle_type idle) { } -static inline void idle_balance(int cpu, runqueue_t *rq) +static inline void idle_balance(int cpu, struct rq *rq) { } #endif -static inline int wake_priority_sleeper(runqueue_t *rq) +static inline int wake_priority_sleeper(struct rq *rq) { int ret = 0; + #ifdef CONFIG_SCHED_SMT spin_lock(&rq->lock); /* @@ -2795,25 +2825,26 @@ EXPORT_PER_CPU_SYMBOL(kstat); * This is called on clock ticks and on context switches. * Bank in p->sched_time the ns elapsed since the last tick or switch. */ -static inline void update_cpu_clock(task_t *p, runqueue_t *rq, - unsigned long long now) +static inline void +update_cpu_clock(struct task_struct *p, struct rq *rq, unsigned long long now) { - unsigned long long last = max(p->timestamp, rq->timestamp_last_tick); - p->sched_time += now - last; + p->sched_time += now - max(p->timestamp, rq->timestamp_last_tick); } /* * Return current->sched_time plus any more ns on the sched_clock * that have not yet been banked. */ -unsigned long long current_sched_time(const task_t *tsk) +unsigned long long current_sched_time(const struct task_struct *p) { unsigned long long ns; unsigned long flags; + local_irq_save(flags); - ns = max(tsk->timestamp, task_rq(tsk)->timestamp_last_tick); - ns = tsk->sched_time + (sched_clock() - ns); + ns = max(p->timestamp, task_rq(p)->timestamp_last_tick); + ns = p->sched_time + sched_clock() - ns; local_irq_restore(flags); + return ns; } @@ -2827,11 +2858,16 @@ unsigned long long current_sched_time(const task_t *tsk) * increasing number of running tasks. We also ignore the interactivity * if a better static_prio task has expired: */ -#define EXPIRED_STARVING(rq) \ - ((STARVATION_LIMIT && ((rq)->expired_timestamp && \ - (jiffies - (rq)->expired_timestamp >= \ - STARVATION_LIMIT * ((rq)->nr_running) + 1))) || \ - ((rq)->curr->static_prio > (rq)->best_expired_prio)) +static inline int expired_starving(struct rq *rq) +{ + if (rq->curr->static_prio > rq->best_expired_prio) + return 1; + if (!STARVATION_LIMIT || !rq->expired_timestamp) + return 0; + if (jiffies - rq->expired_timestamp > STARVATION_LIMIT * rq->nr_running) + return 1; + return 0; +} /* * Account user cpu time to a process. @@ -2864,7 +2900,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset, cputime_t cputime) { struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; - runqueue_t *rq = this_rq(); + struct rq *rq = this_rq(); cputime64_t tmp; p->stime = cputime_add(p->stime, cputime); @@ -2894,7 +2930,7 @@ void account_steal_time(struct task_struct *p, cputime_t steal) { struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; cputime64_t tmp = cputime_to_cputime64(steal); - runqueue_t *rq = this_rq(); + struct rq *rq = this_rq(); if (p == rq->idle) { p->stime = cputime_add(p->stime, steal); @@ -2915,10 +2951,10 @@ void account_steal_time(struct task_struct *p, cputime_t steal) */ void scheduler_tick(void) { - int cpu = smp_processor_id(); - runqueue_t *rq = this_rq(); - task_t *p = current; unsigned long long now = sched_clock(); + struct task_struct *p = current; + int cpu = smp_processor_id(); + struct rq *rq = cpu_rq(cpu); update_cpu_clock(p, rq, now); @@ -2968,7 +3004,7 @@ void scheduler_tick(void) if (!rq->expired_timestamp) rq->expired_timestamp = jiffies; - if (!TASK_INTERACTIVE(p) || EXPIRED_STARVING(rq)) { + if (!TASK_INTERACTIVE(p) || expired_starving(rq)) { enqueue_task(p, rq->expired); if (p->static_prio < rq->best_expired_prio) rq->best_expired_prio = p->static_prio; @@ -3007,7 +3043,7 @@ out: } #ifdef CONFIG_SCHED_SMT -static inline void wakeup_busy_runqueue(runqueue_t *rq) +static inline void wakeup_busy_runqueue(struct rq *rq) { /* If an SMT runqueue is sleeping due to priority reasons wake it up */ if (rq->curr == rq->idle && rq->nr_running) @@ -3033,7 +3069,7 @@ static void wake_sleeping_dependent(int this_cpu) return; for_each_cpu_mask(i, sd->span) { - runqueue_t *smt_rq = cpu_rq(i); + struct rq *smt_rq = cpu_rq(i); if (i == this_cpu) continue; @@ -3050,7 +3086,8 @@ static void wake_sleeping_dependent(int this_cpu) * utilize, if another task runs on a sibling. This models the * slowdown effect of other tasks running on siblings: */ -static inline unsigned long smt_slice(task_t *p, struct sched_domain *sd) +static inline unsigned long +smt_slice(struct task_struct *p, struct sched_domain *sd) { return p->time_slice * (100 - sd->per_cpu_gain) / 100; } @@ -3061,7 +3098,8 @@ static inline unsigned long smt_slice(task_t *p, struct sched_domain *sd) * acquire their lock. As we only trylock the normal locking order does not * need to be obeyed. */ -static int dependent_sleeper(int this_cpu, runqueue_t *this_rq, task_t *p) +static int +dependent_sleeper(int this_cpu, struct rq *this_rq, struct task_struct *p) { struct sched_domain *tmp, *sd = NULL; int ret = 0, i; @@ -3081,8 +3119,8 @@ static int dependent_sleeper(int this_cpu, runqueue_t *this_rq, task_t *p) return 0; for_each_cpu_mask(i, sd->span) { - runqueue_t *smt_rq; - task_t *smt_curr; + struct task_struct *smt_curr; + struct rq *smt_rq; if (i == this_cpu) continue; @@ -3127,9 +3165,8 @@ unlock: static inline void wake_sleeping_dependent(int this_cpu) { } - -static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq, - task_t *p) +static inline int +dependent_sleeper(int this_cpu, struct rq *this_rq, struct task_struct *p) { return 0; } @@ -3142,12 +3179,13 @@ void fastcall add_preempt_count(int val) /* * Underflow? */ - BUG_ON((preempt_count() < 0)); + if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) + return; preempt_count() += val; /* * Spinlock count overflowing soon? */ - BUG_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK-10); + DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK-10); } EXPORT_SYMBOL(add_preempt_count); @@ -3156,11 +3194,15 @@ void fastcall sub_preempt_count(int val) /* * Underflow? */ - BUG_ON(val > preempt_count()); + if (DEBUG_LOCKS_WARN_ON(val > preempt_count())) + return; /* * Is the spinlock portion underflowing? */ - BUG_ON((val < PREEMPT_MASK) && !(preempt_count() & PREEMPT_MASK)); + if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) && + !(preempt_count() & PREEMPT_MASK))) + return; + preempt_count() -= val; } EXPORT_SYMBOL(sub_preempt_count); @@ -3178,14 +3220,14 @@ static inline int interactive_sleep(enum sleep_type sleep_type) */ asmlinkage void __sched schedule(void) { - long *switch_count; - task_t *prev, *next; - runqueue_t *rq; - prio_array_t *array; + struct task_struct *prev, *next; + struct prio_array *array; struct list_head *queue; unsigned long long now; unsigned long run_time; int cpu, idx, new_prio; + long *switch_count; + struct rq *rq; /* * Test if we are atomic. Since do_exit() needs to call into @@ -3275,7 +3317,7 @@ need_resched_nonpreemptible: idx = sched_find_first_bit(array->bitmap); queue = array->queue + idx; - next = list_entry(queue->next, task_t, run_list); + next = list_entry(queue->next, struct task_struct, run_list); if (!rt_task(next) && interactive_sleep(next->sleep_type)) { unsigned long long delta = now - next->timestamp; @@ -3338,7 +3380,6 @@ switch_tasks: if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) goto need_resched; } - EXPORT_SYMBOL(schedule); #ifdef CONFIG_PREEMPT @@ -3383,7 +3424,6 @@ need_resched: if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) goto need_resched; } - EXPORT_SYMBOL(preempt_schedule); /* @@ -3432,10 +3472,8 @@ need_resched: int default_wake_function(wait_queue_t *curr, unsigned mode, int sync, void *key) { - task_t *p = curr->private; - return try_to_wake_up(p, mode, sync); + return try_to_wake_up(curr->private, mode, sync); } - EXPORT_SYMBOL(default_wake_function); /* @@ -3453,13 +3491,11 @@ static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, struct list_head *tmp, *next; list_for_each_safe(tmp, next, &q->task_list) { - wait_queue_t *curr; - unsigned flags; - curr = list_entry(tmp, wait_queue_t, task_list); - flags = curr->flags; + wait_queue_t *curr = list_entry(tmp, wait_queue_t, task_list); + unsigned flags = curr->flags; + if (curr->func(curr, mode, sync, key) && - (flags & WQ_FLAG_EXCLUSIVE) && - !--nr_exclusive) + (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) break; } } @@ -3480,7 +3516,6 @@ void fastcall __wake_up(wait_queue_head_t *q, unsigned int mode, __wake_up_common(q, mode, nr_exclusive, 0, key); spin_unlock_irqrestore(&q->lock, flags); } - EXPORT_SYMBOL(__wake_up); /* @@ -3549,6 +3584,7 @@ EXPORT_SYMBOL(complete_all); void fastcall __sched wait_for_completion(struct completion *x) { might_sleep(); + spin_lock_irq(&x->wait.lock); if (!x->done) { DECLARE_WAITQUEUE(wait, current); @@ -3693,7 +3729,6 @@ void fastcall __sched interruptible_sleep_on(wait_queue_head_t *q) schedule(); SLEEP_ON_TAIL } - EXPORT_SYMBOL(interruptible_sleep_on); long fastcall __sched @@ -3709,7 +3744,6 @@ interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout) return timeout; } - EXPORT_SYMBOL(interruptible_sleep_on_timeout); void fastcall __sched sleep_on(wait_queue_head_t *q) @@ -3722,7 +3756,6 @@ void fastcall __sched sleep_on(wait_queue_head_t *q) schedule(); SLEEP_ON_TAIL } - EXPORT_SYMBOL(sleep_on); long fastcall __sched sleep_on_timeout(wait_queue_head_t *q, long timeout) @@ -3752,11 +3785,11 @@ EXPORT_SYMBOL(sleep_on_timeout); * * Used by the rt_mutex code to implement priority inheritance logic. */ -void rt_mutex_setprio(task_t *p, int prio) +void rt_mutex_setprio(struct task_struct *p, int prio) { + struct prio_array *array; unsigned long flags; - prio_array_t *array; - runqueue_t *rq; + struct rq *rq; int oldprio; BUG_ON(prio < 0 || prio > MAX_PRIO); @@ -3793,12 +3826,12 @@ void rt_mutex_setprio(task_t *p, int prio) #endif -void set_user_nice(task_t *p, long nice) +void set_user_nice(struct task_struct *p, long nice) { - unsigned long flags; - prio_array_t *array; - runqueue_t *rq; + struct prio_array *array; int old_prio, delta; + unsigned long flags; + struct rq *rq; if (TASK_NICE(p) == nice || nice < -20 || nice > 19) return; @@ -3849,10 +3882,11 @@ EXPORT_SYMBOL(set_user_nice); * @p: task * @nice: nice value */ -int can_nice(const task_t *p, const int nice) +int can_nice(const struct task_struct *p, const int nice) { /* convert nice value [19,-20] to rlimit style value [1,40] */ int nice_rlim = 20 - nice; + return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur || capable(CAP_SYS_NICE)); } @@ -3868,8 +3902,7 @@ int can_nice(const task_t *p, const int nice) */ asmlinkage long sys_nice(int increment) { - int retval; - long nice; + long nice, retval; /* * Setpriority might change our priority at the same moment. @@ -3908,7 +3941,7 @@ asmlinkage long sys_nice(int increment) * RT tasks are offset by -200. Normal tasks are centered * around 0, value goes from -16 to +15. */ -int task_prio(const task_t *p) +int task_prio(const struct task_struct *p) { return p->prio - MAX_RT_PRIO; } @@ -3917,7 +3950,7 @@ int task_prio(const task_t *p) * task_nice - return the nice value of a given task. * @p: the task in question. */ -int task_nice(const task_t *p) +int task_nice(const struct task_struct *p) { return TASK_NICE(p); } @@ -3936,7 +3969,7 @@ int idle_cpu(int cpu) * idle_task - return the idle task for a given cpu. * @cpu: the processor in question. */ -task_t *idle_task(int cpu) +struct task_struct *idle_task(int cpu) { return cpu_rq(cpu)->idle; } @@ -3945,7 +3978,7 @@ task_t *idle_task(int cpu) * find_process_by_pid - find a process with a matching PID value. * @pid: the pid in question. */ -static inline task_t *find_process_by_pid(pid_t pid) +static inline struct task_struct *find_process_by_pid(pid_t pid) { return pid ? find_task_by_pid(pid) : current; } @@ -3954,6 +3987,7 @@ static inline task_t *find_process_by_pid(pid_t pid) static void __setscheduler(struct task_struct *p, int policy, int prio) { BUG_ON(p->array); + p->policy = policy; p->rt_priority = prio; p->normal_prio = normal_prio(p); @@ -3977,11 +4011,10 @@ static void __setscheduler(struct task_struct *p, int policy, int prio) int sched_setscheduler(struct task_struct *p, int policy, struct sched_param *param) { - int retval; - int oldprio, oldpolicy = -1; - prio_array_t *array; + int retval, oldprio, oldpolicy = -1; + struct prio_array *array; unsigned long flags; - runqueue_t *rq; + struct rq *rq; /* may grab non-irq protected spin_locks */ BUG_ON(in_interrupt()); @@ -4079,9 +4112,9 @@ EXPORT_SYMBOL_GPL(sched_setscheduler); static int do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) { - int retval; struct sched_param lparam; struct task_struct *p; + int retval; if (!param || pid < 0) return -EINVAL; @@ -4097,6 +4130,7 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) read_unlock_irq(&tasklist_lock); retval = sched_setscheduler(p, policy, &lparam); put_task_struct(p); + return retval; } @@ -4132,8 +4166,8 @@ asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param __user *param) */ asmlinkage long sys_sched_getscheduler(pid_t pid) { + struct task_struct *p; int retval = -EINVAL; - task_t *p; if (pid < 0) goto out_nounlock; @@ -4160,8 +4194,8 @@ out_nounlock: asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param __user *param) { struct sched_param lp; + struct task_struct *p; int retval = -EINVAL; - task_t *p; if (!param || pid < 0) goto out_nounlock; @@ -4194,9 +4228,9 @@ out_unlock: long sched_setaffinity(pid_t pid, cpumask_t new_mask) { - task_t *p; - int retval; cpumask_t cpus_allowed; + struct task_struct *p; + int retval; lock_cpu_hotplug(); read_lock(&tasklist_lock); @@ -4282,8 +4316,8 @@ cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL; long sched_getaffinity(pid_t pid, cpumask_t *mask) { + struct task_struct *p; int retval; - task_t *p; lock_cpu_hotplug(); read_lock(&tasklist_lock); @@ -4342,9 +4376,8 @@ asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len, */ asmlinkage long sys_sched_yield(void) { - runqueue_t *rq = this_rq_lock(); - prio_array_t *array = current->array; - prio_array_t *target = rq->expired; + struct rq *rq = this_rq_lock(); + struct prio_array *array = current->array, *target = rq->expired; schedstat_inc(rq, yld_cnt); /* @@ -4378,6 +4411,7 @@ asmlinkage long sys_sched_yield(void) * no need to preempt or enable interrupts: */ __release(rq->lock); + spin_release(&rq->lock.dep_map, 1, _THIS_IP_); _raw_spin_unlock(&rq->lock); preempt_enable_no_resched(); @@ -4386,7 +4420,16 @@ asmlinkage long sys_sched_yield(void) return 0; } -static inline void __cond_resched(void) +static inline int __resched_legal(void) +{ + if (unlikely(preempt_count())) + return 0; + if (unlikely(system_state != SYSTEM_RUNNING)) + return 0; + return 1; +} + +static void __cond_resched(void) { #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP __might_sleep(__FILE__, __LINE__); @@ -4396,10 +4439,6 @@ static inline void __cond_resched(void) * PREEMPT_ACTIVE, which could trigger a second * cond_resched() call. */ - if (unlikely(preempt_count())) - return; - if (unlikely(system_state != SYSTEM_RUNNING)) - return; do { add_preempt_count(PREEMPT_ACTIVE); schedule(); @@ -4409,13 +4448,12 @@ static inline void __cond_resched(void) int __sched cond_resched(void) { - if (need_resched()) { + if (need_resched() && __resched_legal()) { __cond_resched(); return 1; } return 0; } - EXPORT_SYMBOL(cond_resched); /* @@ -4436,7 +4474,8 @@ int cond_resched_lock(spinlock_t *lock) ret = 1; spin_lock(lock); } - if (need_resched()) { + if (need_resched() && __resched_legal()) { + spin_release(&lock->dep_map, 1, _THIS_IP_); _raw_spin_unlock(lock); preempt_enable_no_resched(); __cond_resched(); @@ -4445,25 +4484,24 @@ int cond_resched_lock(spinlock_t *lock) } return ret; } - EXPORT_SYMBOL(cond_resched_lock); int __sched cond_resched_softirq(void) { BUG_ON(!in_softirq()); - if (need_resched()) { - __local_bh_enable(); + if (need_resched() && __resched_legal()) { + raw_local_irq_disable(); + _local_bh_enable(); + raw_local_irq_enable(); __cond_resched(); local_bh_disable(); return 1; } return 0; } - EXPORT_SYMBOL(cond_resched_softirq); - /** * yield - yield the current processor to other threads. * @@ -4475,7 +4513,6 @@ void __sched yield(void) set_current_state(TASK_RUNNING); sys_sched_yield(); } - EXPORT_SYMBOL(yield); /* @@ -4487,18 +4524,17 @@ EXPORT_SYMBOL(yield); */ void __sched io_schedule(void) { - struct runqueue *rq = &__raw_get_cpu_var(runqueues); + struct rq *rq = &__raw_get_cpu_var(runqueues); atomic_inc(&rq->nr_iowait); schedule(); atomic_dec(&rq->nr_iowait); } - EXPORT_SYMBOL(io_schedule); long __sched io_schedule_timeout(long timeout) { - struct runqueue *rq = &__raw_get_cpu_var(runqueues); + struct rq *rq = &__raw_get_cpu_var(runqueues); long ret; atomic_inc(&rq->nr_iowait); @@ -4565,9 +4601,9 @@ asmlinkage long sys_sched_get_priority_min(int policy) asmlinkage long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval) { + struct task_struct *p; int retval = -EINVAL; struct timespec t; - task_t *p; if (pid < 0) goto out_nounlock; @@ -4595,28 +4631,32 @@ out_unlock: static inline struct task_struct *eldest_child(struct task_struct *p) { - if (list_empty(&p->children)) return NULL; + if (list_empty(&p->children)) + return NULL; return list_entry(p->children.next,struct task_struct,sibling); } static inline struct task_struct *older_sibling(struct task_struct *p) { - if (p->sibling.prev==&p->parent->children) return NULL; + if (p->sibling.prev==&p->parent->children) + return NULL; return list_entry(p->sibling.prev,struct task_struct,sibling); } static inline struct task_struct *younger_sibling(struct task_struct *p) { - if (p->sibling.next==&p->parent->children) return NULL; + if (p->sibling.next==&p->parent->children) + return NULL; return list_entry(p->sibling.next,struct task_struct,sibling); } -static void show_task(task_t *p) +static const char *stat_nam[] = { "R", "S", "D", "T", "t", "Z", "X" }; + +static void show_task(struct task_struct *p) { - task_t *relative; - unsigned state; + struct task_struct *relative; unsigned long free = 0; - static const char *stat_nam[] = { "R", "S", "D", "T", "t", "Z", "X" }; + unsigned state; printk("%-13.13s ", p->comm); state = p->state ? __ffs(p->state) + 1 : 0; @@ -4667,7 +4707,7 @@ static void show_task(task_t *p) void show_state(void) { - task_t *g, *p; + struct task_struct *g, *p; #if (BITS_PER_LONG == 32) printk("\n" @@ -4689,7 +4729,7 @@ void show_state(void) } while_each_thread(g, p); read_unlock(&tasklist_lock); - mutex_debug_show_all_locks(); + debug_show_all_locks(); } /** @@ -4700,9 +4740,9 @@ void show_state(void) * NOTE: this function does not set the idle thread's NEED_RESCHED * flag, to make booting more robust. */ -void __devinit init_idle(task_t *idle, int cpu) +void __devinit init_idle(struct task_struct *idle, int cpu) { - runqueue_t *rq = cpu_rq(cpu); + struct rq *rq = cpu_rq(cpu); unsigned long flags; idle->timestamp = sched_clock(); @@ -4741,7 +4781,7 @@ cpumask_t nohz_cpu_mask = CPU_MASK_NONE; /* * This is how migration works: * - * 1) we queue a migration_req_t structure in the source CPU's + * 1) we queue a struct migration_req structure in the source CPU's * runqueue and wake up that CPU's migration thread. * 2) we down() the locked semaphore => thread blocks. * 3) migration thread wakes up (implicitly it forces the migrated @@ -4763,12 +4803,12 @@ cpumask_t nohz_cpu_mask = CPU_MASK_NONE; * task must not exit() & deallocate itself prematurely. The * call is not atomic; no spinlocks may be held. */ -int set_cpus_allowed(task_t *p, cpumask_t new_mask) +int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) { + struct migration_req req; unsigned long flags; + struct rq *rq; int ret = 0; - migration_req_t req; - runqueue_t *rq; rq = task_rq_lock(p, &flags); if (!cpus_intersects(new_mask, cpu_online_map)) { @@ -4791,9 +4831,9 @@ int set_cpus_allowed(task_t *p, cpumask_t new_mask) } out: task_rq_unlock(rq, &flags); + return ret; } - EXPORT_SYMBOL_GPL(set_cpus_allowed); /* @@ -4809,7 +4849,7 @@ EXPORT_SYMBOL_GPL(set_cpus_allowed); */ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) { - runqueue_t *rq_dest, *rq_src; + struct rq *rq_dest, *rq_src; int ret = 0; if (unlikely(cpu_is_offline(dest_cpu))) @@ -4854,16 +4894,16 @@ out: */ static int migration_thread(void *data) { - runqueue_t *rq; int cpu = (long)data; + struct rq *rq; rq = cpu_rq(cpu); BUG_ON(rq->migration_thread != current); set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { + struct migration_req *req; struct list_head *head; - migration_req_t *req; try_to_freeze(); @@ -4887,7 +4927,7 @@ static int migration_thread(void *data) set_current_state(TASK_INTERRUPTIBLE); continue; } - req = list_entry(head->next, migration_req_t, list); + req = list_entry(head->next, struct migration_req, list); list_del_init(head->next); spin_unlock(&rq->lock); @@ -4912,28 +4952,28 @@ wait_to_die: #ifdef CONFIG_HOTPLUG_CPU /* Figure out where task on dead CPU should go, use force if neccessary. */ -static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *tsk) +static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) { - runqueue_t *rq; unsigned long flags; - int dest_cpu; cpumask_t mask; + struct rq *rq; + int dest_cpu; restart: /* On same node? */ mask = node_to_cpumask(cpu_to_node(dead_cpu)); - cpus_and(mask, mask, tsk->cpus_allowed); + cpus_and(mask, mask, p->cpus_allowed); dest_cpu = any_online_cpu(mask); /* On any allowed CPU? */ if (dest_cpu == NR_CPUS) - dest_cpu = any_online_cpu(tsk->cpus_allowed); + dest_cpu = any_online_cpu(p->cpus_allowed); /* No more Mr. Nice Guy. */ if (dest_cpu == NR_CPUS) { - rq = task_rq_lock(tsk, &flags); - cpus_setall(tsk->cpus_allowed); - dest_cpu = any_online_cpu(tsk->cpus_allowed); + rq = task_rq_lock(p, &flags); + cpus_setall(p->cpus_allowed); + dest_cpu = any_online_cpu(p->cpus_allowed); task_rq_unlock(rq, &flags); /* @@ -4941,12 +4981,12 @@ restart: * kernel threads (both mm NULL), since they never * leave kernel. */ - if (tsk->mm && printk_ratelimit()) + if (p->mm && printk_ratelimit()) printk(KERN_INFO "process %d (%s) no " "longer affine to cpu%d\n", - tsk->pid, tsk->comm, dead_cpu); + p->pid, p->comm, dead_cpu); } - if (!__migrate_task(tsk, dead_cpu, dest_cpu)) + if (!__migrate_task(p, dead_cpu, dest_cpu)) goto restart; } @@ -4957,9 +4997,9 @@ restart: * their home CPUs. So we just add the counter to another CPU's counter, * to keep the global sum constant after CPU-down: */ -static void migrate_nr_uninterruptible(runqueue_t *rq_src) +static void migrate_nr_uninterruptible(struct rq *rq_src) { - runqueue_t *rq_dest = cpu_rq(any_online_cpu(CPU_MASK_ALL)); + struct rq *rq_dest = cpu_rq(any_online_cpu(CPU_MASK_ALL)); unsigned long flags; local_irq_save(flags); @@ -4973,48 +5013,51 @@ static void migrate_nr_uninterruptible(runqueue_t *rq_src) /* Run through task list and migrate tasks from the dead cpu. */ static void migrate_live_tasks(int src_cpu) { - struct task_struct *tsk, *t; + struct task_struct *p, *t; write_lock_irq(&tasklist_lock); - do_each_thread(t, tsk) { - if (tsk == current) + do_each_thread(t, p) { + if (p == current) continue; - if (task_cpu(tsk) == src_cpu) - move_task_off_dead_cpu(src_cpu, tsk); - } while_each_thread(t, tsk); + if (task_cpu(p) == src_cpu) + move_task_off_dead_cpu(src_cpu, p); + } while_each_thread(t, p); write_unlock_irq(&tasklist_lock); } /* Schedules idle task to be the next runnable task on current CPU. * It does so by boosting its priority to highest possible and adding it to - * the _front_ of runqueue. Used by CPU offline code. + * the _front_ of the runqueue. Used by CPU offline code. */ void sched_idle_next(void) { - int cpu = smp_processor_id(); - runqueue_t *rq = this_rq(); + int this_cpu = smp_processor_id(); + struct rq *rq = cpu_rq(this_cpu); struct task_struct *p = rq->idle; unsigned long flags; /* cpu has to be offline */ - BUG_ON(cpu_online(cpu)); + BUG_ON(cpu_online(this_cpu)); - /* Strictly not necessary since rest of the CPUs are stopped by now - * and interrupts disabled on current cpu. + /* + * Strictly not necessary since rest of the CPUs are stopped by now + * and interrupts disabled on the current cpu. */ spin_lock_irqsave(&rq->lock, flags); __setscheduler(p, SCHED_FIFO, MAX_RT_PRIO-1); - /* Add idle task to _front_ of it's priority queue */ + + /* Add idle task to the _front_ of its priority queue: */ __activate_idle_task(p, rq); spin_unlock_irqrestore(&rq->lock, flags); } -/* Ensures that the idle task is using init_mm right before its cpu goes +/* + * Ensures that the idle task is using init_mm right before its cpu goes * offline. */ void idle_task_exit(void) @@ -5028,17 +5071,17 @@ void idle_task_exit(void) mmdrop(mm); } -static void migrate_dead(unsigned int dead_cpu, task_t *tsk) +static void migrate_dead(unsigned int dead_cpu, struct task_struct *p) { - struct runqueue *rq = cpu_rq(dead_cpu); + struct rq *rq = cpu_rq(dead_cpu); /* Must be exiting, otherwise would be on tasklist. */ - BUG_ON(tsk->exit_state != EXIT_ZOMBIE && tsk->exit_state != EXIT_DEAD); + BUG_ON(p->exit_state != EXIT_ZOMBIE && p->exit_state != EXIT_DEAD); /* Cannot have done final schedule yet: would have vanished. */ - BUG_ON(tsk->flags & PF_DEAD); + BUG_ON(p->flags & PF_DEAD); - get_task_struct(tsk); + get_task_struct(p); /* * Drop lock around migration; if someone else moves it, @@ -5046,25 +5089,25 @@ static void migrate_dead(unsigned int dead_cpu, task_t *tsk) * fine. */ spin_unlock_irq(&rq->lock); - move_task_off_dead_cpu(dead_cpu, tsk); + move_task_off_dead_cpu(dead_cpu, p); spin_lock_irq(&rq->lock); - put_task_struct(tsk); + put_task_struct(p); } /* release_task() removes task from tasklist, so we won't find dead tasks. */ static void migrate_dead_tasks(unsigned int dead_cpu) { - unsigned arr, i; - struct runqueue *rq = cpu_rq(dead_cpu); + struct rq *rq = cpu_rq(dead_cpu); + unsigned int arr, i; for (arr = 0; arr < 2; arr++) { for (i = 0; i < MAX_PRIO; i++) { struct list_head *list = &rq->arrays[arr].queue[i]; + while (!list_empty(list)) - migrate_dead(dead_cpu, - list_entry(list->next, task_t, - run_list)); + migrate_dead(dead_cpu, list_entry(list->next, + struct task_struct, run_list)); } } } @@ -5074,14 +5117,13 @@ static void migrate_dead_tasks(unsigned int dead_cpu) * migration_call - callback that gets triggered when a CPU is added. * Here we can start up the necessary migration thread for the new CPU. */ -static int __cpuinit migration_call(struct notifier_block *nfb, - unsigned long action, - void *hcpu) +static int __cpuinit +migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) { - int cpu = (long)hcpu; struct task_struct *p; - struct runqueue *rq; + int cpu = (long)hcpu; unsigned long flags; + struct rq *rq; switch (action) { case CPU_UP_PREPARE: @@ -5096,10 +5138,12 @@ static int __cpuinit migration_call(struct notifier_block *nfb, task_rq_unlock(rq, &flags); cpu_rq(cpu)->migration_thread = p; break; + case CPU_ONLINE: /* Strictly unneccessary, as first user will wake it. */ wake_up_process(cpu_rq(cpu)->migration_thread); break; + #ifdef CONFIG_HOTPLUG_CPU case CPU_UP_CANCELED: if (!cpu_rq(cpu)->migration_thread) @@ -5110,6 +5154,7 @@ static int __cpuinit migration_call(struct notifier_block *nfb, kthread_stop(cpu_rq(cpu)->migration_thread); cpu_rq(cpu)->migration_thread = NULL; break; + case CPU_DEAD: migrate_live_tasks(cpu); rq = cpu_rq(cpu); @@ -5130,9 +5175,10 @@ static int __cpuinit migration_call(struct notifier_block *nfb, * the requestors. */ spin_lock_irq(&rq->lock); while (!list_empty(&rq->migration_queue)) { - migration_req_t *req; + struct migration_req *req; + req = list_entry(rq->migration_queue.next, - migration_req_t, list); + struct migration_req, list); list_del_init(&req->list); complete(&req->done); } @@ -5154,10 +5200,12 @@ static struct notifier_block __cpuinitdata migration_notifier = { int __init migration_init(void) { void *cpu = (void *)(long)smp_processor_id(); - /* Start one for boot CPU. */ + + /* Start one for the boot CPU: */ migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); migration_call(&migration_notifier, CPU_ONLINE, cpu); register_cpu_notifier(&migration_notifier); + return 0; } #endif @@ -5253,7 +5301,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu) } while (sd); } #else -#define sched_domain_debug(sd, cpu) {} +# define sched_domain_debug(sd, cpu) do { } while (0) #endif static int sd_degenerate(struct sched_domain *sd) @@ -5279,8 +5327,8 @@ static int sd_degenerate(struct sched_domain *sd) return 1; } -static int sd_parent_degenerate(struct sched_domain *sd, - struct sched_domain *parent) +static int +sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) { unsigned long cflags = sd->flags, pflags = parent->flags; @@ -5313,7 +5361,7 @@ static int sd_parent_degenerate(struct sched_domain *sd, */ static void cpu_attach_domain(struct sched_domain *sd, int cpu) { - runqueue_t *rq = cpu_rq(cpu); + struct rq *rq = cpu_rq(cpu); struct sched_domain *tmp; /* Remove the sched domains which do not contribute to scheduling. */ @@ -5575,8 +5623,8 @@ static void touch_cache(void *__cache, unsigned long __size) /* * Measure the cache-cost of one task migration. Returns in units of nsec. */ -static unsigned long long measure_one(void *cache, unsigned long size, - int source, int target) +static unsigned long long +measure_one(void *cache, unsigned long size, int source, int target) { cpumask_t mask, saved_mask; unsigned long long t0, t1, t2, t3, cost; @@ -5926,9 +5974,9 @@ static int find_next_best_node(int node, unsigned long *used_nodes) */ static cpumask_t sched_domain_node_span(int node) { - int i; - cpumask_t span, nodemask; DECLARE_BITMAP(used_nodes, MAX_NUMNODES); + cpumask_t span, nodemask; + int i; cpus_clear(span); bitmap_zero(used_nodes, MAX_NUMNODES); @@ -5939,6 +5987,7 @@ static cpumask_t sched_domain_node_span(int node) for (i = 1; i < SD_NODES_PER_DOMAIN; i++) { int next_node = find_next_best_node(node, used_nodes); + nodemask = node_to_cpumask(next_node); cpus_or(span, span, nodemask); } @@ -5948,19 +5997,23 @@ static cpumask_t sched_domain_node_span(int node) #endif int sched_smt_power_savings = 0, sched_mc_power_savings = 0; + /* - * At the moment, CONFIG_SCHED_SMT is never defined, but leave it in so we - * can switch it on easily if needed. + * SMT sched-domains: */ #ifdef CONFIG_SCHED_SMT static DEFINE_PER_CPU(struct sched_domain, cpu_domains); static struct sched_group sched_group_cpus[NR_CPUS]; + static int cpu_to_cpu_group(int cpu) { return cpu; } #endif +/* + * multi-core sched-domains: + */ #ifdef CONFIG_SCHED_MC static DEFINE_PER_CPU(struct sched_domain, core_domains); static struct sched_group *sched_group_core_bycpu[NR_CPUS]; @@ -5980,9 +6033,10 @@ static int cpu_to_core_group(int cpu) static DEFINE_PER_CPU(struct sched_domain, phys_domains); static struct sched_group *sched_group_phys_bycpu[NR_CPUS]; + static int cpu_to_phys_group(int cpu) { -#if defined(CONFIG_SCHED_MC) +#ifdef CONFIG_SCHED_MC cpumask_t mask = cpu_coregroup_map(cpu); return first_cpu(mask); #elif defined(CONFIG_SCHED_SMT) @@ -6528,6 +6582,7 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) { int err = 0; + #ifdef CONFIG_SCHED_SMT if (smt_capable()) err = sysfs_create_file(&cls->kset.kobj, @@ -6547,7 +6602,8 @@ static ssize_t sched_mc_power_savings_show(struct sys_device *dev, char *page) { return sprintf(page, "%u\n", sched_mc_power_savings); } -static ssize_t sched_mc_power_savings_store(struct sys_device *dev, const char *buf, size_t count) +static ssize_t sched_mc_power_savings_store(struct sys_device *dev, + const char *buf, size_t count) { return sched_power_savings_store(buf, count, 0); } @@ -6560,7 +6616,8 @@ static ssize_t sched_smt_power_savings_show(struct sys_device *dev, char *page) { return sprintf(page, "%u\n", sched_smt_power_savings); } -static ssize_t sched_smt_power_savings_store(struct sys_device *dev, const char *buf, size_t count) +static ssize_t sched_smt_power_savings_store(struct sys_device *dev, + const char *buf, size_t count) { return sched_power_savings_store(buf, count, 1); } @@ -6622,6 +6679,7 @@ int in_sched_functions(unsigned long addr) { /* Linker adds these: start and end of __sched functions */ extern char __sched_text_start[], __sched_text_end[]; + return in_lock_functions(addr) || (addr >= (unsigned long)__sched_text_start && addr < (unsigned long)__sched_text_end); @@ -6629,14 +6687,15 @@ int in_sched_functions(unsigned long addr) void __init sched_init(void) { - runqueue_t *rq; int i, j, k; for_each_possible_cpu(i) { - prio_array_t *array; + struct prio_array *array; + struct rq *rq; rq = cpu_rq(i); spin_lock_init(&rq->lock); + lockdep_set_class(&rq->lock, &rq->rq_lock_key); rq->nr_running = 0; rq->active = rq->arrays; rq->expired = rq->arrays + 1; @@ -6683,7 +6742,7 @@ void __init sched_init(void) #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP void __might_sleep(char *file, int line) { -#if defined(in_atomic) +#ifdef in_atomic static unsigned long prev_jiffy; /* ratelimiting */ if ((in_atomic() || irqs_disabled()) && @@ -6705,10 +6764,10 @@ EXPORT_SYMBOL(__might_sleep); #ifdef CONFIG_MAGIC_SYSRQ void normalize_rt_tasks(void) { + struct prio_array *array; struct task_struct *p; - prio_array_t *array; unsigned long flags; - runqueue_t *rq; + struct rq *rq; read_lock_irq(&tasklist_lock); for_each_process(p) { @@ -6752,7 +6811,7 @@ void normalize_rt_tasks(void) * * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! */ -task_t *curr_task(int cpu) +struct task_struct *curr_task(int cpu) { return cpu_curr(cpu); } @@ -6772,7 +6831,7 @@ task_t *curr_task(int cpu) * * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! */ -void set_curr_task(int cpu, task_t *p) +void set_curr_task(int cpu, struct task_struct *p) { cpu_curr(cpu) = p; } diff --git a/kernel/signal.c b/kernel/signal.c index 52adf53929f..7fe874d12fa 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -10,7 +10,6 @@ * to allow signals to be sent reliably. */ -#include <linux/config.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/smp_lock.h> @@ -584,7 +583,7 @@ static int check_kill_permission(int sig, struct siginfo *info, && !capable(CAP_KILL)) return error; - error = security_task_kill(t, info, sig); + error = security_task_kill(t, info, sig, 0); if (!error) audit_signal_info(sig, t); /* Let audit system see the signal */ return error; @@ -1107,7 +1106,7 @@ kill_proc_info(int sig, struct siginfo *info, pid_t pid) /* like kill_proc_info(), but doesn't use uid/euid of "current" */ int kill_proc_info_as_uid(int sig, struct siginfo *info, pid_t pid, - uid_t uid, uid_t euid) + uid_t uid, uid_t euid, u32 secid) { int ret = -EINVAL; struct task_struct *p; @@ -1127,6 +1126,9 @@ int kill_proc_info_as_uid(int sig, struct siginfo *info, pid_t pid, ret = -EPERM; goto out_unlock; } + ret = security_task_kill(p, info, sig, secid); + if (ret) + goto out_unlock; if (sig && p->sighand) { unsigned long flags; spin_lock_irqsave(&p->sighand->siglock, flags); diff --git a/kernel/softirq.c b/kernel/softirq.c index 8f03e3b89b5..215541e26c1 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -62,6 +62,119 @@ static inline void wakeup_softirqd(void) } /* + * This one is for softirq.c-internal use, + * where hardirqs are disabled legitimately: + */ +static void __local_bh_disable(unsigned long ip) +{ + unsigned long flags; + + WARN_ON_ONCE(in_irq()); + + raw_local_irq_save(flags); + add_preempt_count(SOFTIRQ_OFFSET); + /* + * Were softirqs turned off above: + */ + if (softirq_count() == SOFTIRQ_OFFSET) + trace_softirqs_off(ip); + raw_local_irq_restore(flags); +} + +void local_bh_disable(void) +{ + __local_bh_disable((unsigned long)__builtin_return_address(0)); +} + +EXPORT_SYMBOL(local_bh_disable); + +void __local_bh_enable(void) +{ + WARN_ON_ONCE(in_irq()); + + /* + * softirqs should never be enabled by __local_bh_enable(), + * it always nests inside local_bh_enable() sections: + */ + WARN_ON_ONCE(softirq_count() == SOFTIRQ_OFFSET); + + sub_preempt_count(SOFTIRQ_OFFSET); +} +EXPORT_SYMBOL_GPL(__local_bh_enable); + +/* + * Special-case - softirqs can safely be enabled in + * cond_resched_softirq(), or by __do_softirq(), + * without processing still-pending softirqs: + */ +void _local_bh_enable(void) +{ + WARN_ON_ONCE(in_irq()); + WARN_ON_ONCE(!irqs_disabled()); + + if (softirq_count() == SOFTIRQ_OFFSET) + trace_softirqs_on((unsigned long)__builtin_return_address(0)); + sub_preempt_count(SOFTIRQ_OFFSET); +} + +EXPORT_SYMBOL(_local_bh_enable); + +void local_bh_enable(void) +{ + unsigned long flags; + + WARN_ON_ONCE(in_irq()); + WARN_ON_ONCE(irqs_disabled()); + + local_irq_save(flags); + /* + * Are softirqs going to be turned on now: + */ + if (softirq_count() == SOFTIRQ_OFFSET) + trace_softirqs_on((unsigned long)__builtin_return_address(0)); + /* + * Keep preemption disabled until we are done with + * softirq processing: + */ + sub_preempt_count(SOFTIRQ_OFFSET - 1); + + if (unlikely(!in_interrupt() && local_softirq_pending())) + do_softirq(); + + dec_preempt_count(); + local_irq_restore(flags); + preempt_check_resched(); +} +EXPORT_SYMBOL(local_bh_enable); + +void local_bh_enable_ip(unsigned long ip) +{ + unsigned long flags; + + WARN_ON_ONCE(in_irq()); + + local_irq_save(flags); + /* + * Are softirqs going to be turned on now: + */ + if (softirq_count() == SOFTIRQ_OFFSET) + trace_softirqs_on(ip); + /* + * Keep preemption disabled until we are done with + * softirq processing: + */ + sub_preempt_count(SOFTIRQ_OFFSET - 1); + + if (unlikely(!in_interrupt() && local_softirq_pending())) + do_softirq(); + + dec_preempt_count(); + local_irq_restore(flags); + preempt_check_resched(); +} +EXPORT_SYMBOL(local_bh_enable_ip); + +/* * We restart softirq processing MAX_SOFTIRQ_RESTART times, * and we fall back to softirqd after that. * @@ -80,8 +193,11 @@ asmlinkage void __do_softirq(void) int cpu; pending = local_softirq_pending(); + account_system_vtime(current); + + __local_bh_disable((unsigned long)__builtin_return_address(0)); + trace_softirq_enter(); - local_bh_disable(); cpu = smp_processor_id(); restart: /* Reset the pending bitmask before enabling irqs */ @@ -109,7 +225,10 @@ restart: if (pending) wakeup_softirqd(); - __local_bh_enable(); + trace_softirq_exit(); + + account_system_vtime(current); + _local_bh_enable(); } #ifndef __ARCH_HAS_DO_SOFTIRQ @@ -136,23 +255,6 @@ EXPORT_SYMBOL(do_softirq); #endif -void local_bh_enable(void) -{ - WARN_ON(irqs_disabled()); - /* - * Keep preemption disabled until we are done with - * softirq processing: - */ - sub_preempt_count(SOFTIRQ_OFFSET - 1); - - if (unlikely(!in_interrupt() && local_softirq_pending())) - do_softirq(); - - dec_preempt_count(); - preempt_check_resched(); -} -EXPORT_SYMBOL(local_bh_enable); - #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED # define invoke_softirq() __do_softirq() #else @@ -165,6 +267,7 @@ EXPORT_SYMBOL(local_bh_enable); void irq_exit(void) { account_system_vtime(current); + trace_hardirq_exit(); sub_preempt_count(IRQ_EXIT_OFFSET); if (!in_interrupt() && local_softirq_pending()) invoke_softirq(); diff --git a/kernel/spinlock.c b/kernel/spinlock.c index d1b810782bc..bfd6ad9c033 100644 --- a/kernel/spinlock.c +++ b/kernel/spinlock.c @@ -9,11 +9,11 @@ * SMP and the DEBUG_SPINLOCK cases. (UP-nondebug inlines them) */ -#include <linux/config.h> #include <linux/linkage.h> #include <linux/preempt.h> #include <linux/spinlock.h> #include <linux/interrupt.h> +#include <linux/debug_locks.h> #include <linux/module.h> /* @@ -30,8 +30,10 @@ EXPORT_SYMBOL(generic__raw_read_trylock); int __lockfunc _spin_trylock(spinlock_t *lock) { preempt_disable(); - if (_raw_spin_trylock(lock)) + if (_raw_spin_trylock(lock)) { + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); return 1; + } preempt_enable(); return 0; @@ -41,8 +43,10 @@ EXPORT_SYMBOL(_spin_trylock); int __lockfunc _read_trylock(rwlock_t *lock) { preempt_disable(); - if (_raw_read_trylock(lock)) + if (_raw_read_trylock(lock)) { + rwlock_acquire_read(&lock->dep_map, 0, 1, _RET_IP_); return 1; + } preempt_enable(); return 0; @@ -52,19 +56,28 @@ EXPORT_SYMBOL(_read_trylock); int __lockfunc _write_trylock(rwlock_t *lock) { preempt_disable(); - if (_raw_write_trylock(lock)) + if (_raw_write_trylock(lock)) { + rwlock_acquire(&lock->dep_map, 0, 1, _RET_IP_); return 1; + } preempt_enable(); return 0; } EXPORT_SYMBOL(_write_trylock); -#if !defined(CONFIG_PREEMPT) || !defined(CONFIG_SMP) +/* + * If lockdep is enabled then we use the non-preemption spin-ops + * even on CONFIG_PREEMPT, because lockdep assumes that interrupts are + * not re-enabled during lock-acquire (which the preempt-spin-ops do): + */ +#if !defined(CONFIG_PREEMPT) || !defined(CONFIG_SMP) || \ + defined(CONFIG_PROVE_LOCKING) void __lockfunc _read_lock(rwlock_t *lock) { preempt_disable(); + rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_); _raw_read_lock(lock); } EXPORT_SYMBOL(_read_lock); @@ -75,7 +88,17 @@ unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock) local_irq_save(flags); preempt_disable(); + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); + /* + * On lockdep we dont want the hand-coded irq-enable of + * _raw_spin_lock_flags() code, because lockdep assumes + * that interrupts are not re-enabled during lock-acquire: + */ +#ifdef CONFIG_PROVE_LOCKING + _raw_spin_lock(lock); +#else _raw_spin_lock_flags(lock, &flags); +#endif return flags; } EXPORT_SYMBOL(_spin_lock_irqsave); @@ -84,6 +107,7 @@ void __lockfunc _spin_lock_irq(spinlock_t *lock) { local_irq_disable(); preempt_disable(); + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); _raw_spin_lock(lock); } EXPORT_SYMBOL(_spin_lock_irq); @@ -92,6 +116,7 @@ void __lockfunc _spin_lock_bh(spinlock_t *lock) { local_bh_disable(); preempt_disable(); + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); _raw_spin_lock(lock); } EXPORT_SYMBOL(_spin_lock_bh); @@ -102,6 +127,7 @@ unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock) local_irq_save(flags); preempt_disable(); + rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_); _raw_read_lock(lock); return flags; } @@ -111,6 +137,7 @@ void __lockfunc _read_lock_irq(rwlock_t *lock) { local_irq_disable(); preempt_disable(); + rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_); _raw_read_lock(lock); } EXPORT_SYMBOL(_read_lock_irq); @@ -119,6 +146,7 @@ void __lockfunc _read_lock_bh(rwlock_t *lock) { local_bh_disable(); preempt_disable(); + rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_); _raw_read_lock(lock); } EXPORT_SYMBOL(_read_lock_bh); @@ -129,6 +157,7 @@ unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock) local_irq_save(flags); preempt_disable(); + rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_); _raw_write_lock(lock); return flags; } @@ -138,6 +167,7 @@ void __lockfunc _write_lock_irq(rwlock_t *lock) { local_irq_disable(); preempt_disable(); + rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_); _raw_write_lock(lock); } EXPORT_SYMBOL(_write_lock_irq); @@ -146,6 +176,7 @@ void __lockfunc _write_lock_bh(rwlock_t *lock) { local_bh_disable(); preempt_disable(); + rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_); _raw_write_lock(lock); } EXPORT_SYMBOL(_write_lock_bh); @@ -153,6 +184,7 @@ EXPORT_SYMBOL(_write_lock_bh); void __lockfunc _spin_lock(spinlock_t *lock) { preempt_disable(); + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); _raw_spin_lock(lock); } @@ -161,6 +193,7 @@ EXPORT_SYMBOL(_spin_lock); void __lockfunc _write_lock(rwlock_t *lock) { preempt_disable(); + rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_); _raw_write_lock(lock); } @@ -256,8 +289,22 @@ BUILD_LOCK_OPS(write, rwlock); #endif /* CONFIG_PREEMPT */ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +void __lockfunc _spin_lock_nested(spinlock_t *lock, int subclass) +{ + preempt_disable(); + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + _raw_spin_lock(lock); +} + +EXPORT_SYMBOL(_spin_lock_nested); + +#endif + void __lockfunc _spin_unlock(spinlock_t *lock) { + spin_release(&lock->dep_map, 1, _RET_IP_); _raw_spin_unlock(lock); preempt_enable(); } @@ -265,6 +312,7 @@ EXPORT_SYMBOL(_spin_unlock); void __lockfunc _write_unlock(rwlock_t *lock) { + rwlock_release(&lock->dep_map, 1, _RET_IP_); _raw_write_unlock(lock); preempt_enable(); } @@ -272,6 +320,7 @@ EXPORT_SYMBOL(_write_unlock); void __lockfunc _read_unlock(rwlock_t *lock) { + rwlock_release(&lock->dep_map, 1, _RET_IP_); _raw_read_unlock(lock); preempt_enable(); } @@ -279,6 +328,7 @@ EXPORT_SYMBOL(_read_unlock); void __lockfunc _spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) { + spin_release(&lock->dep_map, 1, _RET_IP_); _raw_spin_unlock(lock); local_irq_restore(flags); preempt_enable(); @@ -287,6 +337,7 @@ EXPORT_SYMBOL(_spin_unlock_irqrestore); void __lockfunc _spin_unlock_irq(spinlock_t *lock) { + spin_release(&lock->dep_map, 1, _RET_IP_); _raw_spin_unlock(lock); local_irq_enable(); preempt_enable(); @@ -295,14 +346,16 @@ EXPORT_SYMBOL(_spin_unlock_irq); void __lockfunc _spin_unlock_bh(spinlock_t *lock) { + spin_release(&lock->dep_map, 1, _RET_IP_); _raw_spin_unlock(lock); preempt_enable_no_resched(); - local_bh_enable(); + local_bh_enable_ip((unsigned long)__builtin_return_address(0)); } EXPORT_SYMBOL(_spin_unlock_bh); void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags) { + rwlock_release(&lock->dep_map, 1, _RET_IP_); _raw_read_unlock(lock); local_irq_restore(flags); preempt_enable(); @@ -311,6 +364,7 @@ EXPORT_SYMBOL(_read_unlock_irqrestore); void __lockfunc _read_unlock_irq(rwlock_t *lock) { + rwlock_release(&lock->dep_map, 1, _RET_IP_); _raw_read_unlock(lock); local_irq_enable(); preempt_enable(); @@ -319,14 +373,16 @@ EXPORT_SYMBOL(_read_unlock_irq); void __lockfunc _read_unlock_bh(rwlock_t *lock) { + rwlock_release(&lock->dep_map, 1, _RET_IP_); _raw_read_unlock(lock); preempt_enable_no_resched(); - local_bh_enable(); + local_bh_enable_ip((unsigned long)__builtin_return_address(0)); } EXPORT_SYMBOL(_read_unlock_bh); void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags) { + rwlock_release(&lock->dep_map, 1, _RET_IP_); _raw_write_unlock(lock); local_irq_restore(flags); preempt_enable(); @@ -335,6 +391,7 @@ EXPORT_SYMBOL(_write_unlock_irqrestore); void __lockfunc _write_unlock_irq(rwlock_t *lock) { + rwlock_release(&lock->dep_map, 1, _RET_IP_); _raw_write_unlock(lock); local_irq_enable(); preempt_enable(); @@ -343,9 +400,10 @@ EXPORT_SYMBOL(_write_unlock_irq); void __lockfunc _write_unlock_bh(rwlock_t *lock) { + rwlock_release(&lock->dep_map, 1, _RET_IP_); _raw_write_unlock(lock); preempt_enable_no_resched(); - local_bh_enable(); + local_bh_enable_ip((unsigned long)__builtin_return_address(0)); } EXPORT_SYMBOL(_write_unlock_bh); @@ -353,11 +411,13 @@ int __lockfunc _spin_trylock_bh(spinlock_t *lock) { local_bh_disable(); preempt_disable(); - if (_raw_spin_trylock(lock)) + if (_raw_spin_trylock(lock)) { + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); return 1; + } preempt_enable_no_resched(); - local_bh_enable(); + local_bh_enable_ip((unsigned long)__builtin_return_address(0)); return 0; } EXPORT_SYMBOL(_spin_trylock_bh); diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c new file mode 100644 index 00000000000..b71816e47a3 --- /dev/null +++ b/kernel/stacktrace.c @@ -0,0 +1,24 @@ +/* + * kernel/stacktrace.c + * + * Stack trace management functions + * + * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + */ +#include <linux/sched.h> +#include <linux/kallsyms.h> +#include <linux/stacktrace.h> + +void print_stack_trace(struct stack_trace *trace, int spaces) +{ + int i, j; + + for (i = 0; i < trace->nr_entries; i++) { + unsigned long ip = trace->entries[i]; + + for (j = 0; j < spaces + 1; j++) + printk(" "); + print_ip_sym(ip); + } +} + diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 2c0aacc37c5..dcfb5d73146 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -4,7 +4,6 @@ #include <linux/cpu.h> #include <linux/err.h> #include <linux/syscalls.h> -#include <linux/kthread.h> #include <asm/atomic.h> #include <asm/semaphore.h> #include <asm/uaccess.h> @@ -26,11 +25,13 @@ static unsigned int stopmachine_num_threads; static atomic_t stopmachine_thread_ack; static DECLARE_MUTEX(stopmachine_mutex); -static int stopmachine(void *unused) +static int stopmachine(void *cpu) { int irqs_disabled = 0; int prepared = 0; + set_cpus_allowed(current, cpumask_of_cpu((int)(long)cpu)); + /* Ack: we are alive */ smp_mb(); /* Theoretically the ack = 0 might not be on this CPU yet. */ atomic_inc(&stopmachine_thread_ack); @@ -84,8 +85,7 @@ static void stopmachine_set_state(enum stopmachine_state state) static int stop_machine(void) { - int ret = 0; - unsigned int i; + int i, ret = 0; struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; /* One high-prio thread per cpu. We'll do this one. */ @@ -96,16 +96,11 @@ static int stop_machine(void) stopmachine_state = STOPMACHINE_WAIT; for_each_online_cpu(i) { - struct task_struct *tsk; if (i == raw_smp_processor_id()) continue; - tsk = kthread_create(stopmachine, NULL, "stopmachine"); - if (IS_ERR(tsk)) { - ret = PTR_ERR(tsk); + ret = kernel_thread(stopmachine, (void *)(long)i,CLONE_KERNEL); + if (ret < 0) break; - } - kthread_bind(tsk, i); - wake_up_process(tsk); stopmachine_num_threads++; } diff --git a/kernel/sys.c b/kernel/sys.c index 2d5179c67ce..dbb3b9c7ea6 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -4,7 +4,6 @@ * Copyright (C) 1991, 1992 Linus Torvalds */ -#include <linux/config.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/utsname.h> diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 93a2c539864..362a0cc3713 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -18,7 +18,6 @@ * Removed it and replaced it with older style, 03/23/00, Bill Wendling */ -#include <linux/config.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/swap.h> @@ -934,13 +933,15 @@ static ctl_table vm_table[] = { .extra1 = &zero, }, { - .ctl_name = VM_ZONE_RECLAIM_INTERVAL, - .procname = "zone_reclaim_interval", - .data = &zone_reclaim_interval, - .maxlen = sizeof(zone_reclaim_interval), + .ctl_name = VM_MIN_UNMAPPED, + .procname = "min_unmapped_ratio", + .data = &sysctl_min_unmapped_ratio, + .maxlen = sizeof(sysctl_min_unmapped_ratio), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = &sysctl_min_unmapped_ratio_sysctl_handler, + .strategy = &sysctl_intvec, + .extra1 = &zero, + .extra2 = &one_hundred, }, #endif #ifdef CONFIG_X86_32 diff --git a/kernel/timer.c b/kernel/timer.c index 5a896025306..396a3c024c2 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1208,7 +1208,7 @@ unsigned long wall_jiffies = INITIAL_JIFFIES; * playing with xtime and avenrun. */ #ifndef ARCH_HAVE_XTIME_LOCK -seqlock_t xtime_lock __cacheline_aligned_in_smp = SEQLOCK_UNLOCKED; +__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock); EXPORT_SYMBOL(xtime_lock); #endif @@ -1368,7 +1368,7 @@ asmlinkage long sys_getegid(void) static void process_timeout(unsigned long __data) { - wake_up_process((task_t *)__data); + wake_up_process((struct task_struct *)__data); } /** @@ -1559,6 +1559,13 @@ asmlinkage long sys_sysinfo(struct sysinfo __user *info) return 0; } +/* + * lockdep: we want to track each per-CPU base as a separate lock-class, + * but timer-bases are kmalloc()-ed, so we need to attach separate + * keys to them: + */ +static struct lock_class_key base_lock_keys[NR_CPUS]; + static int __devinit init_timers_cpu(int cpu) { int j; @@ -1594,6 +1601,8 @@ static int __devinit init_timers_cpu(int cpu) } spin_lock_init(&base->lock); + lockdep_set_class(&base->lock, base_lock_keys + cpu); + for (j = 0; j < TVN_SIZE; j++) { INIT_LIST_HEAD(base->tv5.vec + j); INIT_LIST_HEAD(base->tv4.vec + j); diff --git a/kernel/wait.c b/kernel/wait.c index 791681cfea9..a1d57aeb7f7 100644 --- a/kernel/wait.c +++ b/kernel/wait.c @@ -3,7 +3,6 @@ * * (C) 2004 William Irwin, Oracle */ -#include <linux/config.h> #include <linux/init.h> #include <linux/module.h> #include <linux/sched.h> @@ -11,6 +10,10 @@ #include <linux/wait.h> #include <linux/hash.h> +struct lock_class_key waitqueue_lock_key; + +EXPORT_SYMBOL(waitqueue_lock_key); + void fastcall add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait) { unsigned long flags; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 59f0b42bd89..90d2c600165 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -51,7 +51,7 @@ struct cpu_workqueue_struct { wait_queue_head_t work_done; struct workqueue_struct *wq; - task_t *thread; + struct task_struct *thread; int run_depth; /* Detect run_workqueue() recursion depth */ } ____cacheline_aligned; |