diff options
Diffstat (limited to 'kernel')
42 files changed, 2620 insertions, 1045 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 90b53f6dc22..0a32cb21ec9 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -11,6 +11,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \ async.o +obj-y += groups.o ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files @@ -70,6 +71,7 @@ obj-$(CONFIG_STOP_MACHINE) += stop_machine.o obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o obj-$(CONFIG_AUDIT) += audit.o auditfilter.o obj-$(CONFIG_AUDITSYSCALL) += auditsc.o +obj-$(CONFIG_GCOV_KERNEL) += gcov/ obj-$(CONFIG_AUDIT_TREE) += audit_tree.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_KGDB) += kgdb.o diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 3fb789f6df9..3737a682cdf 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -843,6 +843,11 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) { char *token, *o = data ?: "all"; + unsigned long mask = (unsigned long)-1; + +#ifdef CONFIG_CPUSETS + mask = ~(1UL << cpuset_subsys_id); +#endif opts->subsys_bits = 0; opts->flags = 0; @@ -887,6 +892,15 @@ static int parse_cgroupfs_options(char *data, } } + /* + * Option noprefix was introduced just for backward compatibility + * with the old cpuset, so we allow noprefix only if mounting just + * the cpuset subsystem. + */ + if (test_bit(ROOT_NOPREFIX, &opts->flags) && + (opts->subsys_bits & mask)) + return -EINVAL; + /* We can't have an empty hierarchy */ if (!opts->subsys_bits) return -EINVAL; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index d5a7e17474e..7e75a41bd50 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -97,12 +97,6 @@ struct cpuset { struct cpuset *parent; /* my parent */ - /* - * Copy of global cpuset_mems_generation as of the most - * recent time this cpuset changed its mems_allowed. - */ - int mems_generation; - struct fmeter fmeter; /* memory_pressure filter */ /* partition number for rebuild_sched_domains() */ @@ -176,27 +170,6 @@ static inline int is_spread_slab(const struct cpuset *cs) return test_bit(CS_SPREAD_SLAB, &cs->flags); } -/* - * Increment this integer everytime any cpuset changes its - * mems_allowed value. Users of cpusets can track this generation - * number, and avoid having to lock and reload mems_allowed unless - * the cpuset they're using changes generation. - * - * A single, global generation is needed because cpuset_attach_task() could - * reattach a task to a different cpuset, which must not have its - * generation numbers aliased with those of that tasks previous cpuset. - * - * Generations are needed for mems_allowed because one task cannot - * modify another's memory placement. So we must enable every task, - * on every visit to __alloc_pages(), to efficiently check whether - * its current->cpuset->mems_allowed has changed, requiring an update - * of its current->mems_allowed. - * - * Since writes to cpuset_mems_generation are guarded by the cgroup lock - * there is no need to mark it atomic. - */ -static int cpuset_mems_generation; - static struct cpuset top_cpuset = { .flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), }; @@ -228,8 +201,9 @@ static struct cpuset top_cpuset = { * If a task is only holding callback_mutex, then it has read-only * access to cpusets. * - * The task_struct fields mems_allowed and mems_generation may only - * be accessed in the context of that task, so require no locks. + * Now, the task_struct fields mems_allowed and mempolicy may be changed + * by other task, we use alloc_lock in the task_struct fields to protect + * them. * * The cpuset_common_file_read() handlers only hold callback_mutex across * small pieces of code, such as when reading out possibly multi-word @@ -331,75 +305,22 @@ static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask) BUG_ON(!nodes_intersects(*pmask, node_states[N_HIGH_MEMORY])); } -/** - * cpuset_update_task_memory_state - update task memory placement - * - * If the current tasks cpusets mems_allowed changed behind our - * backs, update current->mems_allowed, mems_generation and task NUMA - * mempolicy to the new value. - * - * Task mempolicy is updated by rebinding it relative to the - * current->cpuset if a task has its memory placement changed. - * Do not call this routine if in_interrupt(). - * - * Call without callback_mutex or task_lock() held. May be - * called with or without cgroup_mutex held. Thanks in part to - * 'the_top_cpuset_hack', the task's cpuset pointer will never - * be NULL. This routine also might acquire callback_mutex during - * call. - * - * Reading current->cpuset->mems_generation doesn't need task_lock - * to guard the current->cpuset derefence, because it is guarded - * from concurrent freeing of current->cpuset using RCU. - * - * The rcu_dereference() is technically probably not needed, - * as I don't actually mind if I see a new cpuset pointer but - * an old value of mems_generation. However this really only - * matters on alpha systems using cpusets heavily. If I dropped - * that rcu_dereference(), it would save them a memory barrier. - * For all other arch's, rcu_dereference is a no-op anyway, and for - * alpha systems not using cpusets, another planned optimization, - * avoiding the rcu critical section for tasks in the root cpuset - * which is statically allocated, so can't vanish, will make this - * irrelevant. Better to use RCU as intended, than to engage in - * some cute trick to save a memory barrier that is impossible to - * test, for alpha systems using cpusets heavily, which might not - * even exist. - * - * This routine is needed to update the per-task mems_allowed data, - * within the tasks context, when it is trying to allocate memory - * (in various mm/mempolicy.c routines) and notices that some other - * task has been modifying its cpuset. +/* + * update task's spread flag if cpuset's page/slab spread flag is set + * + * Called with callback_mutex/cgroup_mutex held */ - -void cpuset_update_task_memory_state(void) +static void cpuset_update_task_spread_flag(struct cpuset *cs, + struct task_struct *tsk) { - int my_cpusets_mem_gen; - struct task_struct *tsk = current; - struct cpuset *cs; - - rcu_read_lock(); - my_cpusets_mem_gen = task_cs(tsk)->mems_generation; - rcu_read_unlock(); - - if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) { - mutex_lock(&callback_mutex); - task_lock(tsk); - cs = task_cs(tsk); /* Maybe changed when task not locked */ - guarantee_online_mems(cs, &tsk->mems_allowed); - tsk->cpuset_mems_generation = cs->mems_generation; - if (is_spread_page(cs)) - tsk->flags |= PF_SPREAD_PAGE; - else - tsk->flags &= ~PF_SPREAD_PAGE; - if (is_spread_slab(cs)) - tsk->flags |= PF_SPREAD_SLAB; - else - tsk->flags &= ~PF_SPREAD_SLAB; - task_unlock(tsk); - mutex_unlock(&callback_mutex); - mpol_rebind_task(tsk, &tsk->mems_allowed); - } + if (is_spread_page(cs)) + tsk->flags |= PF_SPREAD_PAGE; + else + tsk->flags &= ~PF_SPREAD_PAGE; + if (is_spread_slab(cs)) + tsk->flags |= PF_SPREAD_SLAB; + else + tsk->flags &= ~PF_SPREAD_SLAB; } /* @@ -1007,14 +928,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, * other task, the task_struct mems_allowed that we are hacking * is for our current task, which must allocate new pages for that * migrating memory region. - * - * We call cpuset_update_task_memory_state() before hacking - * our tasks mems_allowed, so that we are assured of being in - * sync with our tasks cpuset, and in particular, callbacks to - * cpuset_update_task_memory_state() from nested page allocations - * won't see any mismatch of our cpuset and task mems_generation - * values, so won't overwrite our hacked tasks mems_allowed - * nodemask. */ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, @@ -1022,22 +935,37 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, { struct task_struct *tsk = current; - cpuset_update_task_memory_state(); - - mutex_lock(&callback_mutex); tsk->mems_allowed = *to; - mutex_unlock(&callback_mutex); do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL); - mutex_lock(&callback_mutex); guarantee_online_mems(task_cs(tsk),&tsk->mems_allowed); - mutex_unlock(&callback_mutex); } /* - * Rebind task's vmas to cpuset's new mems_allowed, and migrate pages to new - * nodes if memory_migrate flag is set. Called with cgroup_mutex held. + * cpuset_change_task_nodemask - change task's mems_allowed and mempolicy + * @tsk: the task to change + * @newmems: new nodes that the task will be set + * + * In order to avoid seeing no nodes if the old and new nodes are disjoint, + * we structure updates as setting all new allowed nodes, then clearing newly + * disallowed ones. + * + * Called with task's alloc_lock held + */ +static void cpuset_change_task_nodemask(struct task_struct *tsk, + nodemask_t *newmems) +{ + nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); + mpol_rebind_task(tsk, &tsk->mems_allowed); + mpol_rebind_task(tsk, newmems); + tsk->mems_allowed = *newmems; +} + +/* + * Update task's mems_allowed and rebind its mempolicy and vmas' mempolicy + * of it to cpuset's new mems_allowed, and migrate pages to new nodes if + * memory_migrate flag is set. Called with cgroup_mutex held. */ static void cpuset_change_nodemask(struct task_struct *p, struct cgroup_scanner *scan) @@ -1046,12 +974,19 @@ static void cpuset_change_nodemask(struct task_struct *p, struct cpuset *cs; int migrate; const nodemask_t *oldmem = scan->data; + nodemask_t newmems; + + cs = cgroup_cs(scan->cg); + guarantee_online_mems(cs, &newmems); + + task_lock(p); + cpuset_change_task_nodemask(p, &newmems); + task_unlock(p); mm = get_task_mm(p); if (!mm) return; - cs = cgroup_cs(scan->cg); migrate = is_memory_migrate(cs); mpol_rebind_mm(mm, &cs->mems_allowed); @@ -1104,10 +1039,10 @@ static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem, /* * Handle user request to change the 'mems' memory placement * of a cpuset. Needs to validate the request, update the - * cpusets mems_allowed and mems_generation, and for each - * task in the cpuset, rebind any vma mempolicies and if - * the cpuset is marked 'memory_migrate', migrate the tasks - * pages to the new memory. + * cpusets mems_allowed, and for each task in the cpuset, + * update mems_allowed and rebind task's mempolicy and any vma + * mempolicies and if the cpuset is marked 'memory_migrate', + * migrate the tasks pages to the new memory. * * Call with cgroup_mutex held. May take callback_mutex during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, @@ -1160,7 +1095,6 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, mutex_lock(&callback_mutex); cs->mems_allowed = trialcs->mems_allowed; - cs->mems_generation = cpuset_mems_generation++; mutex_unlock(&callback_mutex); update_tasks_nodemask(cs, &oldmem, &heap); @@ -1193,6 +1127,46 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) } /* + * cpuset_change_flag - make a task's spread flags the same as its cpuset's + * @tsk: task to be updated + * @scan: struct cgroup_scanner containing the cgroup of the task + * + * Called by cgroup_scan_tasks() for each task in a cgroup. + * + * We don't need to re-check for the cgroup/cpuset membership, since we're + * holding cgroup_lock() at this point. + */ +static void cpuset_change_flag(struct task_struct *tsk, + struct cgroup_scanner *scan) +{ + cpuset_update_task_spread_flag(cgroup_cs(scan->cg), tsk); +} + +/* + * update_tasks_flags - update the spread flags of tasks in the cpuset. + * @cs: the cpuset in which each task's spread flags needs to be changed + * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks() + * + * Called with cgroup_mutex held + * + * The cgroup_scan_tasks() function will scan all the tasks in a cgroup, + * calling callback functions for each. + * + * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0 + * if @heap != NULL. + */ +static void update_tasks_flags(struct cpuset *cs, struct ptr_heap *heap) +{ + struct cgroup_scanner scan; + + scan.cg = cs->css.cgroup; + scan.test_task = NULL; + scan.process_task = cpuset_change_flag; + scan.heap = heap; + cgroup_scan_tasks(&scan); +} + +/* * update_flag - read a 0 or a 1 in a file and update associated flag * bit: the bit to update (see cpuset_flagbits_t) * cs: the cpuset to update @@ -1205,8 +1179,10 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int turning_on) { struct cpuset *trialcs; - int err; int balance_flag_changed; + int spread_flag_changed; + struct ptr_heap heap; + int err; trialcs = alloc_trial_cpuset(cs); if (!trialcs) @@ -1221,9 +1197,16 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, if (err < 0) goto out; + err = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL); + if (err < 0) + goto out; + balance_flag_changed = (is_sched_load_balance(cs) != is_sched_load_balance(trialcs)); + spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs)) + || (is_spread_page(cs) != is_spread_page(trialcs))); + mutex_lock(&callback_mutex); cs->flags = trialcs->flags; mutex_unlock(&callback_mutex); @@ -1231,6 +1214,9 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) async_rebuild_sched_domains(); + if (spread_flag_changed) + update_tasks_flags(cs, &heap); + heap_free(&heap); out: free_trial_cpuset(trialcs); return err; @@ -1372,15 +1358,20 @@ static void cpuset_attach(struct cgroup_subsys *ss, if (cs == &top_cpuset) { cpumask_copy(cpus_attach, cpu_possible_mask); + to = node_possible_map; } else { - mutex_lock(&callback_mutex); guarantee_online_cpus(cs, cpus_attach); - mutex_unlock(&callback_mutex); + guarantee_online_mems(cs, &to); } err = set_cpus_allowed_ptr(tsk, cpus_attach); if (err) return; + task_lock(tsk); + cpuset_change_task_nodemask(tsk, &to); + task_unlock(tsk); + cpuset_update_task_spread_flag(cs, tsk); + from = oldcs->mems_allowed; to = cs->mems_allowed; mm = get_task_mm(tsk); @@ -1442,11 +1433,9 @@ static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val) break; case FILE_SPREAD_PAGE: retval = update_flag(CS_SPREAD_PAGE, cs, val); - cs->mems_generation = cpuset_mems_generation++; break; case FILE_SPREAD_SLAB: retval = update_flag(CS_SPREAD_SLAB, cs, val); - cs->mems_generation = cpuset_mems_generation++; break; default: retval = -EINVAL; @@ -1786,8 +1775,6 @@ static struct cgroup_subsys_state *cpuset_create( struct cpuset *parent; if (!cont->parent) { - /* This is early initialization for the top cgroup */ - top_cpuset.mems_generation = cpuset_mems_generation++; return &top_cpuset.css; } parent = cgroup_cs(cont->parent); @@ -1799,7 +1786,6 @@ static struct cgroup_subsys_state *cpuset_create( return ERR_PTR(-ENOMEM); } - cpuset_update_task_memory_state(); cs->flags = 0; if (is_spread_page(parent)) set_bit(CS_SPREAD_PAGE, &cs->flags); @@ -1808,7 +1794,6 @@ static struct cgroup_subsys_state *cpuset_create( set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); cpumask_clear(cs->cpus_allowed); nodes_clear(cs->mems_allowed); - cs->mems_generation = cpuset_mems_generation++; fmeter_init(&cs->fmeter); cs->relax_domain_level = -1; @@ -1827,8 +1812,6 @@ static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont) { struct cpuset *cs = cgroup_cs(cont); - cpuset_update_task_memory_state(); - if (is_sched_load_balance(cs)) update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); @@ -1849,21 +1832,6 @@ struct cgroup_subsys cpuset_subsys = { .early_init = 1, }; -/* - * cpuset_init_early - just enough so that the calls to - * cpuset_update_task_memory_state() in early init code - * are harmless. - */ - -int __init cpuset_init_early(void) -{ - alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_NOWAIT); - - top_cpuset.mems_generation = cpuset_mems_generation++; - return 0; -} - - /** * cpuset_init - initialize cpusets at system boot * @@ -1874,11 +1842,13 @@ int __init cpuset_init(void) { int err = 0; + if (!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)) + BUG(); + cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); fmeter_init(&top_cpuset.fmeter); - top_cpuset.mems_generation = cpuset_mems_generation++; set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags); top_cpuset.relax_domain_level = -1; diff --git a/kernel/exit.c b/kernel/exit.c index b6c90b5ef50..628d41f0dd5 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -375,9 +375,8 @@ static void set_special_pids(struct pid *pid) } /* - * Let kernel threads use this to say that they - * allow a certain signal (since daemonize() will - * have disabled all of them by default). + * Let kernel threads use this to say that they allow a certain signal. + * Must not be used if kthread was cloned with CLONE_SIGHAND. */ int allow_signal(int sig) { @@ -385,14 +384,14 @@ int allow_signal(int sig) return -EINVAL; spin_lock_irq(¤t->sighand->siglock); + /* This is only needed for daemonize()'ed kthreads */ sigdelset(¤t->blocked, sig); - if (!current->mm) { - /* Kernel threads handle their own signals. - Let the signal code know it'll be handled, so - that they don't get converted to SIGKILL or - just silently dropped */ - current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2; - } + /* + * Kernel threads handle their own signals. Let the signal code + * know it'll be handled, so that they don't get converted to + * SIGKILL or just silently dropped. + */ + current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2; recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); return 0; @@ -591,7 +590,7 @@ retry: /* * Search in the siblings */ - list_for_each_entry(c, &p->parent->children, sibling) { + list_for_each_entry(c, &p->real_parent->children, sibling) { if (c->mm == mm) goto assign_new_owner; } @@ -758,7 +757,7 @@ static void reparent_thread(struct task_struct *father, struct task_struct *p, p->exit_signal = SIGCHLD; /* If it has exited notify the new parent about this child's death. */ - if (!p->ptrace && + if (!task_ptrace(p) && p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) { do_notify_parent(p, p->exit_signal); if (task_detached(p)) { @@ -783,7 +782,7 @@ static void forget_original_parent(struct task_struct *father) list_for_each_entry_safe(p, n, &father->children, sibling) { p->real_parent = reaper; if (p->parent == father) { - BUG_ON(p->ptrace); + BUG_ON(task_ptrace(p)); p->parent = p->real_parent; } reparent_thread(father, p, &dead_children); @@ -1081,6 +1080,18 @@ SYSCALL_DEFINE1(exit_group, int, error_code) return 0; } +struct wait_opts { + enum pid_type wo_type; + int wo_flags; + struct pid *wo_pid; + + struct siginfo __user *wo_info; + int __user *wo_stat; + struct rusage __user *wo_rusage; + + int notask_error; +}; + static struct pid *task_pid_type(struct task_struct *task, enum pid_type type) { struct pid *pid = NULL; @@ -1091,13 +1102,12 @@ static struct pid *task_pid_type(struct task_struct *task, enum pid_type type) return pid; } -static int eligible_child(enum pid_type type, struct pid *pid, int options, - struct task_struct *p) +static int eligible_child(struct wait_opts *wo, struct task_struct *p) { int err; - if (type < PIDTYPE_MAX) { - if (task_pid_type(p, type) != pid) + if (wo->wo_type < PIDTYPE_MAX) { + if (task_pid_type(p, wo->wo_type) != wo->wo_pid) return 0; } @@ -1106,8 +1116,8 @@ static int eligible_child(enum pid_type type, struct pid *pid, int options, * set; otherwise, wait for non-clone children *only*. (Note: * A "clone" child here is one that reports to its parent * using a signal other than SIGCHLD.) */ - if (((p->exit_signal != SIGCHLD) ^ ((options & __WCLONE) != 0)) - && !(options & __WALL)) + if (((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) + && !(wo->wo_flags & __WALL)) return 0; err = security_task_wait(p); @@ -1117,14 +1127,15 @@ static int eligible_child(enum pid_type type, struct pid *pid, int options, return 1; } -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) +static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p, + pid_t pid, uid_t uid, int why, int status) { - int retval = rusagep ? getrusage(p, RUSAGE_BOTH, rusagep) : 0; + struct siginfo __user *infop; + int retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; put_task_struct(p); + infop = wo->wo_info; if (!retval) retval = put_user(SIGCHLD, &infop->si_signo); if (!retval) @@ -1148,19 +1159,18 @@ static int wait_noreap_copyout(struct task_struct *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(struct task_struct *p, int options, - struct siginfo __user *infop, - int __user *stat_addr, struct rusage __user *ru) +static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) { unsigned long state; int retval, status, traced; pid_t pid = task_pid_vnr(p); uid_t uid = __task_cred(p)->uid; + struct siginfo __user *infop; - if (!likely(options & WEXITED)) + if (!likely(wo->wo_flags & WEXITED)) return 0; - if (unlikely(options & WNOWAIT)) { + if (unlikely(wo->wo_flags & WNOWAIT)) { int exit_code = p->exit_code; int why, status; @@ -1173,8 +1183,7 @@ static int wait_task_zombie(struct task_struct *p, int options, why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED; status = exit_code & 0x7f; } - return wait_noreap_copyout(p, pid, uid, why, - status, infop, ru); + return wait_noreap_copyout(wo, p, pid, uid, why, status); } /* @@ -1188,11 +1197,13 @@ static int wait_task_zombie(struct task_struct *p, int options, } traced = ptrace_reparented(p); - - if (likely(!traced)) { + /* + * It can be ptraced but not reparented, check + * !task_detached() to filter out sub-threads. + */ + if (likely(!traced) && likely(!task_detached(p))) { struct signal_struct *psig; struct signal_struct *sig; - struct task_cputime cputime; /* * The resource counters for the group leader are in its @@ -1205,26 +1216,23 @@ static int wait_task_zombie(struct task_struct *p, int options, * p->signal fields, because they are only touched by * __exit_signal, which runs with tasklist_lock * write-locked anyway, and so is excluded here. We do - * need to protect the access to p->parent->signal fields, + * need to protect the access to parent->signal fields, * as other threads in the parent group can be right * here reaping other children at the same time. - * - * We use thread_group_cputime() to get times for the thread - * group, which consolidates times for all threads in the - * group including the group leader. */ - thread_group_cputime(p, &cputime); - spin_lock_irq(&p->parent->sighand->siglock); - psig = p->parent->signal; + spin_lock_irq(&p->real_parent->sighand->siglock); + psig = p->real_parent->signal; sig = p->signal; psig->cutime = cputime_add(psig->cutime, - cputime_add(cputime.utime, - sig->cutime)); + cputime_add(p->utime, + cputime_add(sig->utime, + sig->cutime))); psig->cstime = cputime_add(psig->cstime, - cputime_add(cputime.stime, - sig->cstime)); + cputime_add(p->stime, + cputime_add(sig->stime, + sig->cstime))); psig->cgtime = cputime_add(psig->cgtime, cputime_add(p->gtime, @@ -1246,7 +1254,7 @@ static int wait_task_zombie(struct task_struct *p, int options, sig->oublock + sig->coublock; task_io_accounting_add(&psig->ioac, &p->ioac); task_io_accounting_add(&psig->ioac, &sig->ioac); - spin_unlock_irq(&p->parent->sighand->siglock); + spin_unlock_irq(&p->real_parent->sighand->siglock); } /* @@ -1255,11 +1263,14 @@ static int wait_task_zombie(struct task_struct *p, int options, */ read_unlock(&tasklist_lock); - retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; + retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; status = (p->signal->flags & SIGNAL_GROUP_EXIT) ? p->signal->group_exit_code : p->exit_code; - if (!retval && stat_addr) - retval = put_user(status, stat_addr); + if (!retval && wo->wo_stat) + retval = put_user(status, wo->wo_stat); + + infop = wo->wo_info; if (!retval && infop) retval = put_user(SIGCHLD, &infop->si_signo); if (!retval && infop) @@ -1327,15 +1338,18 @@ static int *task_stopped_code(struct task_struct *p, bool ptrace) * 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(int ptrace, struct task_struct *p, - int options, struct siginfo __user *infop, - int __user *stat_addr, struct rusage __user *ru) +static int wait_task_stopped(struct wait_opts *wo, + int ptrace, struct task_struct *p) { + struct siginfo __user *infop; int retval, exit_code, *p_code, why; uid_t uid = 0; /* unneeded, required by compiler */ pid_t pid; - if (!(options & WUNTRACED)) + /* + * Traditionally we see ptrace'd stopped tasks regardless of options. + */ + if (!ptrace && !(wo->wo_flags & WUNTRACED)) return 0; exit_code = 0; @@ -1349,7 +1363,7 @@ static int wait_task_stopped(int ptrace, struct task_struct *p, if (!exit_code) goto unlock_sig; - if (!unlikely(options & WNOWAIT)) + if (!unlikely(wo->wo_flags & WNOWAIT)) *p_code = 0; /* don't need the RCU readlock here as we're holding a spinlock */ @@ -1371,14 +1385,15 @@ unlock_sig: why = ptrace ? CLD_TRAPPED : CLD_STOPPED; read_unlock(&tasklist_lock); - if (unlikely(options & WNOWAIT)) - return wait_noreap_copyout(p, pid, uid, - why, exit_code, - infop, ru); + if (unlikely(wo->wo_flags & WNOWAIT)) + return wait_noreap_copyout(wo, p, pid, uid, why, exit_code); - retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; - if (!retval && stat_addr) - retval = put_user((exit_code << 8) | 0x7f, stat_addr); + retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; + if (!retval && wo->wo_stat) + retval = put_user((exit_code << 8) | 0x7f, wo->wo_stat); + + infop = wo->wo_info; if (!retval && infop) retval = put_user(SIGCHLD, &infop->si_signo); if (!retval && infop) @@ -1405,15 +1420,13 @@ unlock_sig: * 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(struct task_struct *p, int options, - struct siginfo __user *infop, - int __user *stat_addr, struct rusage __user *ru) +static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) { int retval; pid_t pid; uid_t uid; - if (!unlikely(options & WCONTINUED)) + if (!unlikely(wo->wo_flags & WCONTINUED)) return 0; if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) @@ -1425,7 +1438,7 @@ static int wait_task_continued(struct task_struct *p, int options, spin_unlock_irq(&p->sighand->siglock); return 0; } - if (!unlikely(options & WNOWAIT)) + if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; uid = __task_cred(p)->uid; spin_unlock_irq(&p->sighand->siglock); @@ -1434,17 +1447,17 @@ static int wait_task_continued(struct task_struct *p, int options, get_task_struct(p); read_unlock(&tasklist_lock); - if (!infop) { - retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; + if (!wo->wo_info) { + retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; put_task_struct(p); - if (!retval && stat_addr) - retval = put_user(0xffff, stat_addr); + if (!retval && wo->wo_stat) + retval = put_user(0xffff, wo->wo_stat); if (!retval) retval = pid; } else { - retval = wait_noreap_copyout(p, pid, uid, - CLD_CONTINUED, SIGCONT, - infop, ru); + retval = wait_noreap_copyout(wo, p, pid, uid, + CLD_CONTINUED, SIGCONT); BUG_ON(retval == 0); } @@ -1454,19 +1467,16 @@ static int wait_task_continued(struct task_struct *p, int options, /* * Consider @p for a wait by @parent. * - * -ECHILD should be in *@notask_error before the first call. + * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; - * then *@notask_error is 0 if @p is an eligible child, + * then ->notask_error is 0 if @p is an eligible child, * or another error from security_task_wait(), or still -ECHILD. */ -static int wait_consider_task(struct task_struct *parent, int ptrace, - struct task_struct *p, int *notask_error, - enum pid_type type, struct pid *pid, int options, - struct siginfo __user *infop, - int __user *stat_addr, struct rusage __user *ru) +static int wait_consider_task(struct wait_opts *wo, struct task_struct *parent, + int ptrace, struct task_struct *p) { - int ret = eligible_child(type, pid, options, p); + int ret = eligible_child(wo, p); if (!ret) return ret; @@ -1478,17 +1488,17 @@ static int wait_consider_task(struct task_struct *parent, int ptrace, * to look for security policy problems, rather * than for mysterious wait bugs. */ - if (*notask_error) - *notask_error = ret; + if (wo->notask_error) + wo->notask_error = ret; return 0; } - if (likely(!ptrace) && unlikely(p->ptrace)) { + if (likely(!ptrace) && unlikely(task_ptrace(p))) { /* * This child is hidden by ptrace. * We aren't allowed to see it now, but eventually we will. */ - *notask_error = 0; + wo->notask_error = 0; return 0; } @@ -1499,34 +1509,30 @@ static int wait_consider_task(struct task_struct *parent, int ptrace, * We don't reap group leaders with subthreads. */ if (p->exit_state == EXIT_ZOMBIE && !delay_group_leader(p)) - return wait_task_zombie(p, options, infop, stat_addr, ru); + return wait_task_zombie(wo, p); /* * It's stopped or running now, so it might * later continue, exit, or stop again. */ - *notask_error = 0; + wo->notask_error = 0; if (task_stopped_code(p, ptrace)) - return wait_task_stopped(ptrace, p, options, - infop, stat_addr, ru); + return wait_task_stopped(wo, ptrace, p); - return wait_task_continued(p, options, infop, stat_addr, ru); + return wait_task_continued(wo, p); } /* * Do the work of do_wait() for one thread in the group, @tsk. * - * -ECHILD should be in *@notask_error before the first call. + * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; then - * *@notask_error is 0 if there were any eligible children, + * ->notask_error is 0 if there were any eligible children, * or another error from security_task_wait(), or still -ECHILD. */ -static int do_wait_thread(struct task_struct *tsk, int *notask_error, - enum pid_type type, struct pid *pid, int options, - struct siginfo __user *infop, int __user *stat_addr, - struct rusage __user *ru) +static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; @@ -1535,9 +1541,7 @@ static int do_wait_thread(struct task_struct *tsk, int *notask_error, * Do not consider detached threads. */ if (!task_detached(p)) { - int ret = wait_consider_task(tsk, 0, p, notask_error, - type, pid, options, - infop, stat_addr, ru); + int ret = wait_consider_task(wo, tsk, 0, p); if (ret) return ret; } @@ -1546,22 +1550,12 @@ static int do_wait_thread(struct task_struct *tsk, int *notask_error, return 0; } -static int ptrace_do_wait(struct task_struct *tsk, int *notask_error, - enum pid_type type, struct pid *pid, int options, - struct siginfo __user *infop, int __user *stat_addr, - struct rusage __user *ru) +static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; - /* - * Traditionally we see ptrace'd stopped tasks regardless of options. - */ - options |= WUNTRACED; - list_for_each_entry(p, &tsk->ptraced, ptrace_entry) { - int ret = wait_consider_task(tsk, 1, p, notask_error, - type, pid, options, - infop, stat_addr, ru); + int ret = wait_consider_task(wo, tsk, 1, p); if (ret) return ret; } @@ -1569,65 +1563,59 @@ static int ptrace_do_wait(struct task_struct *tsk, int *notask_error, return 0; } -static long do_wait(enum pid_type type, struct pid *pid, int options, - struct siginfo __user *infop, int __user *stat_addr, - struct rusage __user *ru) +static long do_wait(struct wait_opts *wo) { DECLARE_WAITQUEUE(wait, current); struct task_struct *tsk; int retval; - trace_sched_process_wait(pid); + trace_sched_process_wait(wo->wo_pid); add_wait_queue(¤t->signal->wait_chldexit,&wait); repeat: /* * If there is nothing that can match our critiera just get out. - * We will clear @retval to zero if we see any child that might later - * match our criteria, even if we are not able to reap it yet. + * We will clear ->notask_error to zero if we see any child that + * might later match our criteria, even if we are not able to reap + * it yet. */ - retval = -ECHILD; - if ((type < PIDTYPE_MAX) && (!pid || hlist_empty(&pid->tasks[type]))) - goto end; + wo->notask_error = -ECHILD; + if ((wo->wo_type < PIDTYPE_MAX) && + (!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type]))) + goto notask; - current->state = TASK_INTERRUPTIBLE; + set_current_state(TASK_INTERRUPTIBLE); read_lock(&tasklist_lock); tsk = current; do { - int tsk_result = do_wait_thread(tsk, &retval, - type, pid, options, - infop, stat_addr, ru); - if (!tsk_result) - tsk_result = ptrace_do_wait(tsk, &retval, - type, pid, options, - infop, stat_addr, ru); - if (tsk_result) { - /* - * tasklist_lock is unlocked and we have a final result. - */ - retval = tsk_result; + retval = do_wait_thread(wo, tsk); + if (retval) + goto end; + + retval = ptrace_do_wait(wo, tsk); + if (retval) goto end; - } - if (options & __WNOTHREAD) + if (wo->wo_flags & __WNOTHREAD) break; - tsk = next_thread(tsk); - BUG_ON(tsk->signal != current->signal); - } while (tsk != current); + } while_each_thread(current, tsk); read_unlock(&tasklist_lock); - if (!retval && !(options & WNOHANG)) { +notask: + retval = wo->notask_error; + if (!retval && !(wo->wo_flags & WNOHANG)) { retval = -ERESTARTSYS; if (!signal_pending(current)) { schedule(); goto repeat; } } - end: - current->state = TASK_RUNNING; + __set_current_state(TASK_RUNNING); remove_wait_queue(¤t->signal->wait_chldexit,&wait); - if (infop) { + if (wo->wo_info) { + struct siginfo __user *infop = wo->wo_info; + if (retval > 0) retval = 0; else { @@ -1656,6 +1644,7 @@ end: SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, infop, int, options, struct rusage __user *, ru) { + struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; @@ -1685,7 +1674,14 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, if (type < PIDTYPE_MAX) pid = find_get_pid(upid); - ret = do_wait(type, pid, options, infop, NULL, ru); + + wo.wo_type = type; + wo.wo_pid = pid; + wo.wo_flags = options; + wo.wo_info = infop; + wo.wo_stat = NULL; + wo.wo_rusage = ru; + ret = do_wait(&wo); put_pid(pid); /* avoid REGPARM breakage on x86: */ @@ -1696,6 +1692,7 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, int, options, struct rusage __user *, ru) { + struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; @@ -1717,7 +1714,13 @@ SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, pid = find_get_pid(upid); } - ret = do_wait(type, pid, options | WEXITED, NULL, stat_addr, ru); + wo.wo_type = type; + wo.wo_pid = pid; + wo.wo_flags = options | WEXITED; + wo.wo_info = NULL; + wo.wo_stat = stat_addr; + wo.wo_rusage = ru; + ret = do_wait(&wo); put_pid(pid); /* avoid REGPARM breakage on x86: */ diff --git a/kernel/fork.c b/kernel/fork.c index 4430eb1376f..467746b3f0a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -178,7 +178,7 @@ void __init fork_init(unsigned long mempages) /* create a slab on which task_structs can be allocated */ task_struct_cachep = kmem_cache_create("task_struct", sizeof(struct task_struct), - ARCH_MIN_TASKALIGN, SLAB_PANIC, NULL); + ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL); #endif /* do the arch specific task caches init */ @@ -1029,7 +1029,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); - clear_tsk_thread_flag(p, TIF_SIGPENDING); init_sigpending(&p->pending); p->utime = cputime_zero; @@ -1470,20 +1469,20 @@ void __init proc_caches_init(void) { sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU, - sighand_ctor); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU| + SLAB_NOTRACK, sighand_ctor); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); mm_cachep = kmem_cache_create("mm_struct", sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC); mmap_init(); } diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig new file mode 100644 index 00000000000..22e9dcfaa3d --- /dev/null +++ b/kernel/gcov/Kconfig @@ -0,0 +1,48 @@ +menu "GCOV-based kernel profiling" + +config GCOV_KERNEL + bool "Enable gcov-based kernel profiling" + depends on DEBUG_FS && CONSTRUCTORS + default n + ---help--- + This option enables gcov-based code profiling (e.g. for code coverage + measurements). + + If unsure, say N. + + Additionally specify CONFIG_GCOV_PROFILE_ALL=y to get profiling data + for the entire kernel. To enable profiling for specific files or + directories, add a line similar to the following to the respective + Makefile: + + For a single file (e.g. main.o): + GCOV_PROFILE_main.o := y + + For all files in one directory: + GCOV_PROFILE := y + + To exclude files from being profiled even when CONFIG_GCOV_PROFILE_ALL + is specified, use: + + GCOV_PROFILE_main.o := n + and: + GCOV_PROFILE := n + + Note that the debugfs filesystem has to be mounted to access + profiling data. + +config GCOV_PROFILE_ALL + bool "Profile entire Kernel" + depends on GCOV_KERNEL + depends on S390 || X86 + default n + ---help--- + This options activates profiling for the entire kernel. + + If unsure, say N. + + Note that a kernel compiled with profiling flags will be significantly + larger and run slower. Also be sure to exclude files from profiling + which are not linked to the kernel image to prevent linker errors. + +endmenu diff --git a/kernel/gcov/Makefile b/kernel/gcov/Makefile new file mode 100644 index 00000000000..3f761001d51 --- /dev/null +++ b/kernel/gcov/Makefile @@ -0,0 +1,3 @@ +EXTRA_CFLAGS := -DSRCTREE='"$(srctree)"' -DOBJTREE='"$(objtree)"' + +obj-$(CONFIG_GCOV_KERNEL) := base.o fs.o gcc_3_4.o diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c new file mode 100644 index 00000000000..9b22d03cc58 --- /dev/null +++ b/kernel/gcov/base.c @@ -0,0 +1,148 @@ +/* + * This code maintains a list of active profiling data structures. + * + * Copyright IBM Corp. 2009 + * Author(s): Peter Oberparleiter <oberpar@linux.vnet.ibm.com> + * + * Uses gcc-internal data definitions. + * Based on the gcov-kernel patch by: + * Hubertus Franke <frankeh@us.ibm.com> + * Nigel Hinds <nhinds@us.ibm.com> + * Rajan Ravindran <rajancr@us.ibm.com> + * Peter Oberparleiter <oberpar@linux.vnet.ibm.com> + * Paul Larson + */ + +#define pr_fmt(fmt) "gcov: " fmt + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include "gcov.h" + +static struct gcov_info *gcov_info_head; +static int gcov_events_enabled; +static DEFINE_MUTEX(gcov_lock); + +/* + * __gcov_init is called by gcc-generated constructor code for each object + * file compiled with -fprofile-arcs. + */ +void __gcov_init(struct gcov_info *info) +{ + static unsigned int gcov_version; + + mutex_lock(&gcov_lock); + if (gcov_version == 0) { + gcov_version = info->version; + /* + * Printing gcc's version magic may prove useful for debugging + * incompatibility reports. + */ + pr_info("version magic: 0x%x\n", gcov_version); + } + /* + * Add new profiling data structure to list and inform event + * listener. + */ + info->next = gcov_info_head; + gcov_info_head = info; + if (gcov_events_enabled) + gcov_event(GCOV_ADD, info); + mutex_unlock(&gcov_lock); +} +EXPORT_SYMBOL(__gcov_init); + +/* + * These functions may be referenced by gcc-generated profiling code but serve + * no function for kernel profiling. + */ +void __gcov_flush(void) +{ + /* Unused. */ +} +EXPORT_SYMBOL(__gcov_flush); + +void __gcov_merge_add(gcov_type *counters, unsigned int n_counters) +{ + /* Unused. */ +} +EXPORT_SYMBOL(__gcov_merge_add); + +void __gcov_merge_single(gcov_type *counters, unsigned int n_counters) +{ + /* Unused. */ +} +EXPORT_SYMBOL(__gcov_merge_single); + +void __gcov_merge_delta(gcov_type *counters, unsigned int n_counters) +{ + /* Unused. */ +} +EXPORT_SYMBOL(__gcov_merge_delta); + +/** + * gcov_enable_events - enable event reporting through gcov_event() + * + * Turn on reporting of profiling data load/unload-events through the + * gcov_event() callback. Also replay all previous events once. This function + * is needed because some events are potentially generated too early for the + * callback implementation to handle them initially. + */ +void gcov_enable_events(void) +{ + struct gcov_info *info; + + mutex_lock(&gcov_lock); + gcov_events_enabled = 1; + /* Perform event callback for previously registered entries. */ + for (info = gcov_info_head; info; info = info->next) + gcov_event(GCOV_ADD, info); + mutex_unlock(&gcov_lock); +} + +#ifdef CONFIG_MODULES +static inline int within(void *addr, void *start, unsigned long size) +{ + return ((addr >= start) && (addr < start + size)); +} + +/* Update list and generate events when modules are unloaded. */ +static int gcov_module_notifier(struct notifier_block *nb, unsigned long event, + void *data) +{ + struct module *mod = data; + struct gcov_info *info; + struct gcov_info *prev; + + if (event != MODULE_STATE_GOING) + return NOTIFY_OK; + mutex_lock(&gcov_lock); + prev = NULL; + /* Remove entries located in module from linked list. */ + for (info = gcov_info_head; info; info = info->next) { + if (within(info, mod->module_core, mod->core_size)) { + if (prev) + prev->next = info->next; + else + gcov_info_head = info->next; + if (gcov_events_enabled) + gcov_event(GCOV_REMOVE, info); + } else + prev = info; + } + mutex_unlock(&gcov_lock); + + return NOTIFY_OK; +} + +static struct notifier_block gcov_nb = { + .notifier_call = gcov_module_notifier, +}; + +static int __init gcov_init(void) +{ + return register_module_notifier(&gcov_nb); +} +device_initcall(gcov_init); +#endif /* CONFIG_MODULES */ diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c new file mode 100644 index 00000000000..ef3c3f88a7a --- /dev/null +++ b/kernel/gcov/fs.c @@ -0,0 +1,673 @@ +/* + * This code exports profiling data as debugfs files to userspace. + * + * Copyright IBM Corp. 2009 + * Author(s): Peter Oberparleiter <oberpar@linux.vnet.ibm.com> + * + * Uses gcc-internal data definitions. + * Based on the gcov-kernel patch by: + * Hubertus Franke <frankeh@us.ibm.com> + * Nigel Hinds <nhinds@us.ibm.com> + * Rajan Ravindran <rajancr@us.ibm.com> + * Peter Oberparleiter <oberpar@linux.vnet.ibm.com> + * Paul Larson + * Yi CDL Yang + */ + +#define pr_fmt(fmt) "gcov: " fmt + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/debugfs.h> +#include <linux/fs.h> +#include <linux/list.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <linux/mutex.h> +#include <linux/seq_file.h> +#include "gcov.h" + +/** + * struct gcov_node - represents a debugfs entry + * @list: list head for child node list + * @children: child nodes + * @all: list head for list of all nodes + * @parent: parent node + * @info: associated profiling data structure if not a directory + * @ghost: when an object file containing profiling data is unloaded we keep a + * copy of the profiling data here to allow collecting coverage data + * for cleanup code. Such a node is called a "ghost". + * @dentry: main debugfs entry, either a directory or data file + * @links: associated symbolic links + * @name: data file basename + * + * struct gcov_node represents an entity within the gcov/ subdirectory + * of debugfs. There are directory and data file nodes. The latter represent + * the actual synthesized data file plus any associated symbolic links which + * are needed by the gcov tool to work correctly. + */ +struct gcov_node { + struct list_head list; + struct list_head children; + struct list_head all; + struct gcov_node *parent; + struct gcov_info *info; + struct gcov_info *ghost; + struct dentry *dentry; + struct dentry **links; + char name[0]; +}; + +static const char objtree[] = OBJTREE; +static const char srctree[] = SRCTREE; +static struct gcov_node root_node; +static struct dentry *reset_dentry; +static LIST_HEAD(all_head); +static DEFINE_MUTEX(node_lock); + +/* If non-zero, keep copies of profiling data for unloaded modules. */ +static int gcov_persist = 1; + +static int __init gcov_persist_setup(char *str) +{ + unsigned long val; + + if (strict_strtoul(str, 0, &val)) { + pr_warning("invalid gcov_persist parameter '%s'\n", str); + return 0; + } + gcov_persist = val; + pr_info("setting gcov_persist to %d\n", gcov_persist); + + return 1; +} +__setup("gcov_persist=", gcov_persist_setup); + +/* + * seq_file.start() implementation for gcov data files. Note that the + * gcov_iterator interface is designed to be more restrictive than seq_file + * (no start from arbitrary position, etc.), to simplify the iterator + * implementation. + */ +static void *gcov_seq_start(struct seq_file *seq, loff_t *pos) +{ + loff_t i; + + gcov_iter_start(seq->private); + for (i = 0; i < *pos; i++) { + if (gcov_iter_next(seq->private)) + return NULL; + } + return seq->private; +} + +/* seq_file.next() implementation for gcov data files. */ +static void *gcov_seq_next(struct seq_file *seq, void *data, loff_t *pos) +{ + struct gcov_iterator *iter = data; + + if (gcov_iter_next(iter)) + return NULL; + (*pos)++; + + return iter; +} + +/* seq_file.show() implementation for gcov data files. */ +static int gcov_seq_show(struct seq_file *seq, void *data) +{ + struct gcov_iterator *iter = data; + + if (gcov_iter_write(iter, seq)) + return -EINVAL; + return 0; +} + +static void gcov_seq_stop(struct seq_file *seq, void *data) +{ + /* Unused. */ +} + +static const struct seq_operations gcov_seq_ops = { + .start = gcov_seq_start, + .next = gcov_seq_next, + .show = gcov_seq_show, + .stop = gcov_seq_stop, +}; + +/* + * Return the profiling data set for a given node. This can either be the + * original profiling data structure or a duplicate (also called "ghost") + * in case the associated object file has been unloaded. + */ +static struct gcov_info *get_node_info(struct gcov_node *node) +{ + if (node->info) + return node->info; + + return node->ghost; +} + +/* + * open() implementation for gcov data files. Create a copy of the profiling + * data set and initialize the iterator and seq_file interface. + */ +static int gcov_seq_open(struct inode *inode, struct file *file) +{ + struct gcov_node *node = inode->i_private; + struct gcov_iterator *iter; + struct seq_file *seq; + struct gcov_info *info; + int rc = -ENOMEM; + + mutex_lock(&node_lock); + /* + * Read from a profiling data copy to minimize reference tracking + * complexity and concurrent access. + */ + info = gcov_info_dup(get_node_info(node)); + if (!info) + goto out_unlock; + iter = gcov_iter_new(info); + if (!iter) + goto err_free_info; + rc = seq_open(file, &gcov_seq_ops); + if (rc) + goto err_free_iter_info; + seq = file->private_data; + seq->private = iter; +out_unlock: + mutex_unlock(&node_lock); + return rc; + +err_free_iter_info: + gcov_iter_free(iter); +err_free_info: + gcov_info_free(info); + goto out_unlock; +} + +/* + * release() implementation for gcov data files. Release resources allocated + * by open(). + */ +static int gcov_seq_release(struct inode *inode, struct file *file) +{ + struct gcov_iterator *iter; + struct gcov_info *info; + struct seq_file *seq; + + seq = file->private_data; + iter = seq->private; + info = gcov_iter_get_info(iter); + gcov_iter_free(iter); + gcov_info_free(info); + seq_release(inode, file); + + return 0; +} + +/* + * Find a node by the associated data file name. Needs to be called with + * node_lock held. + */ +static struct gcov_node *get_node_by_name(const char *name) +{ + struct gcov_node *node; + struct gcov_info *info; + + list_for_each_entry(node, &all_head, all) { + info = get_node_info(node); + if (info && (strcmp(info->filename, name) == 0)) + return node; + } + + return NULL; +} + +static void remove_node(struct gcov_node *node); + +/* + * write() implementation for gcov data files. Reset profiling data for the + * associated file. If the object file has been unloaded (i.e. this is + * a "ghost" node), remove the debug fs node as well. + */ +static ssize_t gcov_seq_write(struct file *file, const char __user *addr, + size_t len, loff_t *pos) +{ + struct seq_file *seq; + struct gcov_info *info; + struct gcov_node *node; + + seq = file->private_data; + info = gcov_iter_get_info(seq->private); + mutex_lock(&node_lock); + node = get_node_by_name(info->filename); + if (node) { + /* Reset counts or remove node for unloaded modules. */ + if (node->ghost) + remove_node(node); + else + gcov_info_reset(node->info); + } + /* Reset counts for open file. */ + gcov_info_reset(info); + mutex_unlock(&node_lock); + + return len; +} + +/* + * Given a string <path> representing a file path of format: + * path/to/file.gcda + * construct and return a new string: + * <dir/>path/to/file.<ext> + */ +static char *link_target(const char *dir, const char *path, const char *ext) +{ + char *target; + char *old_ext; + char *copy; + + copy = kstrdup(path, GFP_KERNEL); + if (!copy) + return NULL; + old_ext = strrchr(copy, '.'); + if (old_ext) + *old_ext = '\0'; + if (dir) + target = kasprintf(GFP_KERNEL, "%s/%s.%s", dir, copy, ext); + else + target = kasprintf(GFP_KERNEL, "%s.%s", copy, ext); + kfree(copy); + + return target; +} + +/* + * Construct a string representing the symbolic link target for the given + * gcov data file name and link type. Depending on the link type and the + * location of the data file, the link target can either point to a + * subdirectory of srctree, objtree or in an external location. + */ +static char *get_link_target(const char *filename, const struct gcov_link *ext) +{ + const char *rel; + char *result; + + if (strncmp(filename, objtree, strlen(objtree)) == 0) { + rel = filename + strlen(objtree) + 1; + if (ext->dir == SRC_TREE) + result = link_target(srctree, rel, ext->ext); + else + result = link_target(objtree, rel, ext->ext); + } else { + /* External compilation. */ + result = link_target(NULL, filename, ext->ext); + } + + return result; +} + +#define SKEW_PREFIX ".tmp_" + +/* + * For a filename .tmp_filename.ext return filename.ext. Needed to compensate + * for filename skewing caused by the mod-versioning mechanism. + */ +static const char *deskew(const char *basename) +{ + if (strncmp(basename, SKEW_PREFIX, sizeof(SKEW_PREFIX) - 1) == 0) + return basename + sizeof(SKEW_PREFIX) - 1; + return basename; +} + +/* + * Create links to additional files (usually .c and .gcno files) which the + * gcov tool expects to find in the same directory as the gcov data file. + */ +static void add_links(struct gcov_node *node, struct dentry *parent) +{ + char *basename; + char *target; + int num; + int i; + + for (num = 0; gcov_link[num].ext; num++) + /* Nothing. */; + node->links = kcalloc(num, sizeof(struct dentry *), GFP_KERNEL); + if (!node->links) + return; + for (i = 0; i < num; i++) { + target = get_link_target(get_node_info(node)->filename, + &gcov_link[i]); + if (!target) + goto out_err; + basename = strrchr(target, '/'); + if (!basename) + goto out_err; + basename++; + node->links[i] = debugfs_create_symlink(deskew(basename), + parent, target); + if (!node->links[i]) + goto out_err; + kfree(target); + } + + return; +out_err: + kfree(target); + while (i-- > 0) + debugfs_remove(node->links[i]); + kfree(node->links); + node->links = NULL; +} + +static const struct file_operations gcov_data_fops = { + .open = gcov_seq_open, + .release = gcov_seq_release, + .read = seq_read, + .llseek = seq_lseek, + .write = gcov_seq_write, +}; + +/* Basic initialization of a new node. */ +static void init_node(struct gcov_node *node, struct gcov_info *info, + const char *name, struct gcov_node *parent) +{ + INIT_LIST_HEAD(&node->list); + INIT_LIST_HEAD(&node->children); + INIT_LIST_HEAD(&node->all); + node->info = info; + node->parent = parent; + if (name) + strcpy(node->name, name); +} + +/* + * Create a new node and associated debugfs entry. Needs to be called with + * node_lock held. + */ +static struct gcov_node *new_node(struct gcov_node *parent, + struct gcov_info *info, const char *name) +{ + struct gcov_node *node; + + node = kzalloc(sizeof(struct gcov_node) + strlen(name) + 1, GFP_KERNEL); + if (!node) { + pr_warning("out of memory\n"); + return NULL; + } + init_node(node, info, name, parent); + /* Differentiate between gcov data file nodes and directory nodes. */ + if (info) { + node->dentry = debugfs_create_file(deskew(node->name), 0600, + parent->dentry, node, &gcov_data_fops); + } else + node->dentry = debugfs_create_dir(node->name, parent->dentry); + if (!node->dentry) { + pr_warning("could not create file\n"); + kfree(node); + return NULL; + } + if (info) + add_links(node, parent->dentry); + list_add(&node->list, &parent->children); + list_add(&node->all, &all_head); + + return node; +} + +/* Remove symbolic links associated with node. */ +static void remove_links(struct gcov_node *node) +{ + int i; + + if (!node->links) + return; + for (i = 0; gcov_link[i].ext; i++) + debugfs_remove(node->links[i]); + kfree(node->links); + node->links = NULL; +} + +/* + * Remove node from all lists and debugfs and release associated resources. + * Needs to be called with node_lock held. + */ +static void release_node(struct gcov_node *node) +{ + list_del(&node->list); + list_del(&node->all); + debugfs_remove(node->dentry); + remove_links(node); + if (node->ghost) + gcov_info_free(node->ghost); + kfree(node); +} + +/* Release node and empty parents. Needs to be called with node_lock held. */ +static void remove_node(struct gcov_node *node) +{ + struct gcov_node *parent; + + while ((node != &root_node) && list_empty(&node->children)) { + parent = node->parent; + release_node(node); + node = parent; + } +} + +/* + * Find child node with given basename. Needs to be called with node_lock + * held. + */ +static struct gcov_node *get_child_by_name(struct gcov_node *parent, + const char *name) +{ + struct gcov_node *node; + + list_for_each_entry(node, &parent->children, list) { + if (strcmp(node->name, name) == 0) + return node; + } + + return NULL; +} + +/* + * write() implementation for reset file. Reset all profiling data to zero + * and remove ghost nodes. + */ +static ssize_t reset_write(struct file *file, const char __user *addr, + size_t len, loff_t *pos) +{ + struct gcov_node *node; + + mutex_lock(&node_lock); +restart: + list_for_each_entry(node, &all_head, all) { + if (node->info) + gcov_info_reset(node->info); + else if (list_empty(&node->children)) { + remove_node(node); + /* Several nodes may have gone - restart loop. */ + goto restart; + } + } + mutex_unlock(&node_lock); + + return len; +} + +/* read() implementation for reset file. Unused. */ +static ssize_t reset_read(struct file *file, char __user *addr, size_t len, + loff_t *pos) +{ + /* Allow read operation so that a recursive copy won't fail. */ + return 0; +} + +static const struct file_operations gcov_reset_fops = { + .write = reset_write, + .read = reset_read, +}; + +/* + * Create a node for a given profiling data set and add it to all lists and + * debugfs. Needs to be called with node_lock held. + */ +static void add_node(struct gcov_info *info) +{ + char *filename; + char *curr; + char *next; + struct gcov_node *parent; + struct gcov_node *node; + + filename = kstrdup(info->filename, GFP_KERNEL); + if (!filename) + return; + parent = &root_node; + /* Create directory nodes along the path. */ + for (curr = filename; (next = strchr(curr, '/')); curr = next + 1) { + if (curr == next) + continue; + *next = 0; + if (strcmp(curr, ".") == 0) + continue; + if (strcmp(curr, "..") == 0) { + if (!parent->parent) + goto err_remove; + parent = parent->parent; + continue; + } + node = get_child_by_name(parent, curr); + if (!node) { + node = new_node(parent, NULL, curr); + if (!node) + goto err_remove; + } + parent = node; + } + /* Create file node. */ + node = new_node(parent, info, curr); + if (!node) + goto err_remove; +out: + kfree(filename); + return; + +err_remove: + remove_node(parent); + goto out; +} + +/* + * The profiling data set associated with this node is being unloaded. Store a + * copy of the profiling data and turn this node into a "ghost". + */ +static int ghost_node(struct gcov_node *node) +{ + node->ghost = gcov_info_dup(node->info); + if (!node->ghost) { + pr_warning("could not save data for '%s' (out of memory)\n", + node->info->filename); + return -ENOMEM; + } + node->info = NULL; + + return 0; +} + +/* + * Profiling data for this node has been loaded again. Add profiling data + * from previous instantiation and turn this node into a regular node. + */ +static void revive_node(struct gcov_node *node, struct gcov_info *info) +{ + if (gcov_info_is_compatible(node->ghost, info)) + gcov_info_add(info, node->ghost); + else { + pr_warning("discarding saved data for '%s' (version changed)\n", + info->filename); + } + gcov_info_free(node->ghost); + node->ghost = NULL; + node->info = info; +} + +/* + * Callback to create/remove profiling files when code compiled with + * -fprofile-arcs is loaded/unloaded. + */ +void gcov_event(enum gcov_action action, struct gcov_info *info) +{ + struct gcov_node *node; + + mutex_lock(&node_lock); + node = get_node_by_name(info->filename); + switch (action) { + case GCOV_ADD: + /* Add new node or revive ghost. */ + if (!node) { + add_node(info); + break; + } + if (gcov_persist) + revive_node(node, info); + else { + pr_warning("could not add '%s' (already exists)\n", + info->filename); + } + break; + case GCOV_REMOVE: + /* Remove node or turn into ghost. */ + if (!node) { + pr_warning("could not remove '%s' (not found)\n", + info->filename); + break; + } + if (gcov_persist) { + if (!ghost_node(node)) + break; + } + remove_node(node); + break; + } + mutex_unlock(&node_lock); +} + +/* Create debugfs entries. */ +static __init int gcov_fs_init(void) +{ + int rc = -EIO; + + init_node(&root_node, NULL, NULL, NULL); + /* + * /sys/kernel/debug/gcov will be parent for the reset control file + * and all profiling files. + */ + root_node.dentry = debugfs_create_dir("gcov", NULL); + if (!root_node.dentry) + goto err_remove; + /* + * Create reset file which resets all profiling counts when written + * to. + */ + reset_dentry = debugfs_create_file("reset", 0600, root_node.dentry, + NULL, &gcov_reset_fops); + if (!reset_dentry) + goto err_remove; + /* Replay previous events to get our fs hierarchy up-to-date. */ + gcov_enable_events(); + return 0; + +err_remove: + pr_err("init failed\n"); + if (root_node.dentry) + debugfs_remove(root_node.dentry); + + return rc; +} +device_initcall(gcov_fs_init); diff --git a/kernel/gcov/gcc_3_4.c b/kernel/gcov/gcc_3_4.c new file mode 100644 index 00000000000..ae5bb426003 --- /dev/null +++ b/kernel/gcov/gcc_3_4.c @@ -0,0 +1,447 @@ +/* + * This code provides functions to handle gcc's profiling data format + * introduced with gcc 3.4. Future versions of gcc may change the gcov + * format (as happened before), so all format-specific information needs + * to be kept modular and easily exchangeable. + * + * This file is based on gcc-internal definitions. Functions and data + * structures are defined to be compatible with gcc counterparts. + * For a better understanding, refer to gcc source: gcc/gcov-io.h. + * + * Copyright IBM Corp. 2009 + * Author(s): Peter Oberparleiter <oberpar@linux.vnet.ibm.com> + * + * Uses gcc-internal data definitions. + */ + +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/seq_file.h> +#include <linux/vmalloc.h> +#include "gcov.h" + +/* Symbolic links to be created for each profiling data file. */ +const struct gcov_link gcov_link[] = { + { OBJ_TREE, "gcno" }, /* Link to .gcno file in $(objtree). */ + { 0, NULL}, +}; + +/* + * Determine whether a counter is active. Based on gcc magic. Doesn't change + * at run-time. + */ +static int counter_active(struct gcov_info *info, unsigned int type) +{ + return (1 << type) & info->ctr_mask; +} + +/* Determine number of active counters. Based on gcc magic. */ +static unsigned int num_counter_active(struct gcov_info *info) +{ + unsigned int i; + unsigned int result = 0; + + for (i = 0; i < GCOV_COUNTERS; i++) { + if (counter_active(info, i)) + result++; + } + return result; +} + +/** + * gcov_info_reset - reset profiling data to zero + * @info: profiling data set + */ +void gcov_info_reset(struct gcov_info *info) +{ + unsigned int active = num_counter_active(info); + unsigned int i; + + for (i = 0; i < active; i++) { + memset(info->counts[i].values, 0, + info->counts[i].num * sizeof(gcov_type)); + } +} + +/** + * gcov_info_is_compatible - check if profiling data can be added + * @info1: first profiling data set + * @info2: second profiling data set + * + * Returns non-zero if profiling data can be added, zero otherwise. + */ +int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2) +{ + return (info1->stamp == info2->stamp); +} + +/** + * gcov_info_add - add up profiling data + * @dest: profiling data set to which data is added + * @source: profiling data set which is added + * + * Adds profiling counts of @source to @dest. + */ +void gcov_info_add(struct gcov_info *dest, struct gcov_info *source) +{ + unsigned int i; + unsigned int j; + + for (i = 0; i < num_counter_active(dest); i++) { + for (j = 0; j < dest->counts[i].num; j++) { + dest->counts[i].values[j] += + source->counts[i].values[j]; + } + } +} + +/* Get size of function info entry. Based on gcc magic. */ +static size_t get_fn_size(struct gcov_info *info) +{ + size_t size; + + size = sizeof(struct gcov_fn_info) + num_counter_active(info) * + sizeof(unsigned int); + if (__alignof__(struct gcov_fn_info) > sizeof(unsigned int)) + size = ALIGN(size, __alignof__(struct gcov_fn_info)); + return size; +} + +/* Get address of function info entry. Based on gcc magic. */ +static struct gcov_fn_info *get_fn_info(struct gcov_info *info, unsigned int fn) +{ + return (struct gcov_fn_info *) + ((char *) info->functions + fn * get_fn_size(info)); +} + +/** + * gcov_info_dup - duplicate profiling data set + * @info: profiling data set to duplicate + * + * Return newly allocated duplicate on success, %NULL on error. + */ +struct gcov_info *gcov_info_dup(struct gcov_info *info) +{ + struct gcov_info *dup; + unsigned int i; + unsigned int active; + + /* Duplicate gcov_info. */ + active = num_counter_active(info); + dup = kzalloc(sizeof(struct gcov_info) + + sizeof(struct gcov_ctr_info) * active, GFP_KERNEL); + if (!dup) + return NULL; + dup->version = info->version; + dup->stamp = info->stamp; + dup->n_functions = info->n_functions; + dup->ctr_mask = info->ctr_mask; + /* Duplicate filename. */ + dup->filename = kstrdup(info->filename, GFP_KERNEL); + if (!dup->filename) + goto err_free; + /* Duplicate table of functions. */ + dup->functions = kmemdup(info->functions, info->n_functions * + get_fn_size(info), GFP_KERNEL); + if (!dup->functions) + goto err_free; + /* Duplicate counter arrays. */ + for (i = 0; i < active ; i++) { + struct gcov_ctr_info *ctr = &info->counts[i]; + size_t size = ctr->num * sizeof(gcov_type); + + dup->counts[i].num = ctr->num; + dup->counts[i].merge = ctr->merge; + dup->counts[i].values = vmalloc(size); + if (!dup->counts[i].values) + goto err_free; + memcpy(dup->counts[i].values, ctr->values, size); + } + return dup; + +err_free: + gcov_info_free(dup); + return NULL; +} + +/** + * gcov_info_free - release memory for profiling data set duplicate + * @info: profiling data set duplicate to free + */ +void gcov_info_free(struct gcov_info *info) +{ + unsigned int active = num_counter_active(info); + unsigned int i; + + for (i = 0; i < active ; i++) + vfree(info->counts[i].values); + kfree(info->functions); + kfree(info->filename); + kfree(info); +} + +/** + * struct type_info - iterator helper array + * @ctr_type: counter type + * @offset: index of the first value of the current function for this type + * + * This array is needed to convert the in-memory data format into the in-file + * data format: + * + * In-memory: + * for each counter type + * for each function + * values + * + * In-file: + * for each function + * for each counter type + * values + * + * See gcc source gcc/gcov-io.h for more information on data organization. + */ +struct type_info { + int ctr_type; + unsigned int offset; +}; + +/** + * struct gcov_iterator - specifies current file position in logical records + * @info: associated profiling data + * @record: record type + * @function: function number + * @type: counter type + * @count: index into values array + * @num_types: number of counter types + * @type_info: helper array to get values-array offset for current function + */ +struct gcov_iterator { + struct gcov_info *info; + + int record; + unsigned int function; + unsigned int type; + unsigned int count; + + int num_types; + struct type_info type_info[0]; +}; + +static struct gcov_fn_info *get_func(struct gcov_iterator *iter) +{ + return get_fn_info(iter->info, iter->function); +} + +static struct type_info *get_type(struct gcov_iterator *iter) +{ + return &iter->type_info[iter->type]; +} + +/** + * gcov_iter_new - allocate and initialize profiling data iterator + * @info: profiling data set to be iterated + * + * Return file iterator on success, %NULL otherwise. + */ +struct gcov_iterator *gcov_iter_new(struct gcov_info *info) +{ + struct gcov_iterator *iter; + + iter = kzalloc(sizeof(struct gcov_iterator) + + num_counter_active(info) * sizeof(struct type_info), + GFP_KERNEL); + if (iter) + iter->info = info; + + return iter; +} + +/** + * gcov_iter_free - release memory for iterator + * @iter: file iterator to free + */ +void gcov_iter_free(struct gcov_iterator *iter) +{ + kfree(iter); +} + +/** + * gcov_iter_get_info - return profiling data set for given file iterator + * @iter: file iterator + */ +struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter) +{ + return iter->info; +} + +/** + * gcov_iter_start - reset file iterator to starting position + * @iter: file iterator + */ +void gcov_iter_start(struct gcov_iterator *iter) +{ + int i; + + iter->record = 0; + iter->function = 0; + iter->type = 0; + iter->count = 0; + iter->num_types = 0; + for (i = 0; i < GCOV_COUNTERS; i++) { + if (counter_active(iter->info, i)) { + iter->type_info[iter->num_types].ctr_type = i; + iter->type_info[iter->num_types++].offset = 0; + } + } +} + +/* Mapping of logical record number to actual file content. */ +#define RECORD_FILE_MAGIC 0 +#define RECORD_GCOV_VERSION 1 +#define RECORD_TIME_STAMP 2 +#define RECORD_FUNCTION_TAG 3 +#define RECORD_FUNCTON_TAG_LEN 4 +#define RECORD_FUNCTION_IDENT 5 +#define RECORD_FUNCTION_CHECK 6 +#define RECORD_COUNT_TAG 7 +#define RECORD_COUNT_LEN 8 +#define RECORD_COUNT 9 + +/** + * gcov_iter_next - advance file iterator to next logical record + * @iter: file iterator + * + * Return zero if new position is valid, non-zero if iterator has reached end. + */ +int gcov_iter_next(struct gcov_iterator *iter) +{ + switch (iter->record) { + case RECORD_FILE_MAGIC: + case RECORD_GCOV_VERSION: + case RECORD_FUNCTION_TAG: + case RECORD_FUNCTON_TAG_LEN: + case RECORD_FUNCTION_IDENT: + case RECORD_COUNT_TAG: + /* Advance to next record */ + iter->record++; + break; + case RECORD_COUNT: + /* Advance to next count */ + iter->count++; + /* fall through */ + case RECORD_COUNT_LEN: + if (iter->count < get_func(iter)->n_ctrs[iter->type]) { + iter->record = 9; + break; + } + /* Advance to next counter type */ + get_type(iter)->offset += iter->count; + iter->count = 0; + iter->type++; + /* fall through */ + case RECORD_FUNCTION_CHECK: + if (iter->type < iter->num_types) { + iter->record = 7; + break; + } + /* Advance to next function */ + iter->type = 0; + iter->function++; + /* fall through */ + case RECORD_TIME_STAMP: + if (iter->function < iter->info->n_functions) + iter->record = 3; + else + iter->record = -1; + break; + } + /* Check for EOF. */ + if (iter->record == -1) + return -EINVAL; + else + return 0; +} + +/** + * seq_write_gcov_u32 - write 32 bit number in gcov format to seq_file + * @seq: seq_file handle + * @v: value to be stored + * + * Number format defined by gcc: numbers are recorded in the 32 bit + * unsigned binary form of the endianness of the machine generating the + * file. + */ +static int seq_write_gcov_u32(struct seq_file *seq, u32 v) +{ + return seq_write(seq, &v, sizeof(v)); +} + +/** + * seq_write_gcov_u64 - write 64 bit number in gcov format to seq_file + * @seq: seq_file handle + * @v: value to be stored + * + * Number format defined by gcc: numbers are recorded in the 32 bit + * unsigned binary form of the endianness of the machine generating the + * file. 64 bit numbers are stored as two 32 bit numbers, the low part + * first. + */ +static int seq_write_gcov_u64(struct seq_file *seq, u64 v) +{ + u32 data[2]; + + data[0] = (v & 0xffffffffUL); + data[1] = (v >> 32); + return seq_write(seq, data, sizeof(data)); +} + +/** + * gcov_iter_write - write data for current pos to seq_file + * @iter: file iterator + * @seq: seq_file handle + * + * Return zero on success, non-zero otherwise. + */ +int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq) +{ + int rc = -EINVAL; + + switch (iter->record) { + case RECORD_FILE_MAGIC: + rc = seq_write_gcov_u32(seq, GCOV_DATA_MAGIC); + break; + case RECORD_GCOV_VERSION: + rc = seq_write_gcov_u32(seq, iter->info->version); + break; + case RECORD_TIME_STAMP: + rc = seq_write_gcov_u32(seq, iter->info->stamp); + break; + case RECORD_FUNCTION_TAG: + rc = seq_write_gcov_u32(seq, GCOV_TAG_FUNCTION); + break; + case RECORD_FUNCTON_TAG_LEN: + rc = seq_write_gcov_u32(seq, 2); + break; + case RECORD_FUNCTION_IDENT: + rc = seq_write_gcov_u32(seq, get_func(iter)->ident); + break; + case RECORD_FUNCTION_CHECK: + rc = seq_write_gcov_u32(seq, get_func(iter)->checksum); + break; + case RECORD_COUNT_TAG: + rc = seq_write_gcov_u32(seq, + GCOV_TAG_FOR_COUNTER(get_type(iter)->ctr_type)); + break; + case RECORD_COUNT_LEN: + rc = seq_write_gcov_u32(seq, + get_func(iter)->n_ctrs[iter->type] * 2); + break; + case RECORD_COUNT: + rc = seq_write_gcov_u64(seq, + iter->info->counts[iter->type]. + values[iter->count + get_type(iter)->offset]); + break; + } + return rc; +} diff --git a/kernel/gcov/gcov.h b/kernel/gcov/gcov.h new file mode 100644 index 00000000000..060073ebf7a --- /dev/null +++ b/kernel/gcov/gcov.h @@ -0,0 +1,128 @@ +/* + * Profiling infrastructure declarations. + * + * This file is based on gcc-internal definitions. Data structures are + * defined to be compatible with gcc counterparts. For a better + * understanding, refer to gcc source: gcc/gcov-io.h. + * + * Copyright IBM Corp. 2009 + * Author(s): Peter Oberparleiter <oberpar@linux.vnet.ibm.com> + * + * Uses gcc-internal data definitions. + */ + +#ifndef GCOV_H +#define GCOV_H GCOV_H + +#include <linux/types.h> + +/* + * Profiling data types used for gcc 3.4 and above - these are defined by + * gcc and need to be kept as close to the original definition as possible to + * remain compatible. + */ +#define GCOV_COUNTERS 5 +#define GCOV_DATA_MAGIC ((unsigned int) 0x67636461) +#define GCOV_TAG_FUNCTION ((unsigned int) 0x01000000) +#define GCOV_TAG_COUNTER_BASE ((unsigned int) 0x01a10000) +#define GCOV_TAG_FOR_COUNTER(count) \ + (GCOV_TAG_COUNTER_BASE + ((unsigned int) (count) << 17)) + +#if BITS_PER_LONG >= 64 +typedef long gcov_type; +#else +typedef long long gcov_type; +#endif + +/** + * struct gcov_fn_info - profiling meta data per function + * @ident: object file-unique function identifier + * @checksum: function checksum + * @n_ctrs: number of values per counter type belonging to this function + * + * This data is generated by gcc during compilation and doesn't change + * at run-time. + */ +struct gcov_fn_info { + unsigned int ident; + unsigned int checksum; + unsigned int n_ctrs[0]; +}; + +/** + * struct gcov_ctr_info - profiling data per counter type + * @num: number of counter values for this type + * @values: array of counter values for this type + * @merge: merge function for counter values of this type (unused) + * + * This data is generated by gcc during compilation and doesn't change + * at run-time with the exception of the values array. + */ +struct gcov_ctr_info { + unsigned int num; + gcov_type *values; + void (*merge)(gcov_type *, unsigned int); +}; + +/** + * struct gcov_info - profiling data per object file + * @version: gcov version magic indicating the gcc version used for compilation + * @next: list head for a singly-linked list + * @stamp: time stamp + * @filename: name of the associated gcov data file + * @n_functions: number of instrumented functions + * @functions: function data + * @ctr_mask: mask specifying which counter types are active + * @counts: counter data per counter type + * + * This data is generated by gcc during compilation and doesn't change + * at run-time with the exception of the next pointer. + */ +struct gcov_info { + unsigned int version; + struct gcov_info *next; + unsigned int stamp; + const char *filename; + unsigned int n_functions; + const struct gcov_fn_info *functions; + unsigned int ctr_mask; + struct gcov_ctr_info counts[0]; +}; + +/* Base interface. */ +enum gcov_action { + GCOV_ADD, + GCOV_REMOVE, +}; + +void gcov_event(enum gcov_action action, struct gcov_info *info); +void gcov_enable_events(void); + +/* Iterator control. */ +struct seq_file; +struct gcov_iterator; + +struct gcov_iterator *gcov_iter_new(struct gcov_info *info); +void gcov_iter_free(struct gcov_iterator *iter); +void gcov_iter_start(struct gcov_iterator *iter); +int gcov_iter_next(struct gcov_iterator *iter); +int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq); +struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter); + +/* gcov_info control. */ +void gcov_info_reset(struct gcov_info *info); +int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2); +void gcov_info_add(struct gcov_info *dest, struct gcov_info *source); +struct gcov_info *gcov_info_dup(struct gcov_info *info); +void gcov_info_free(struct gcov_info *info); + +struct gcov_link { + enum { + OBJ_TREE, + SRC_TREE, + } dir; + const char *ext; +}; +extern const struct gcov_link gcov_link[]; + +#endif /* GCOV_H */ diff --git a/kernel/groups.c b/kernel/groups.c new file mode 100644 index 00000000000..2b45b2ee396 --- /dev/null +++ b/kernel/groups.c @@ -0,0 +1,288 @@ +/* + * Supplementary group IDs + */ +#include <linux/cred.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/security.h> +#include <linux/syscalls.h> +#include <asm/uaccess.h> + +/* init to 2 - one for init_task, one to ensure it is never freed */ +struct group_info init_groups = { .usage = ATOMIC_INIT(2) }; + +struct group_info *groups_alloc(int gidsetsize) +{ + struct group_info *group_info; + int nblocks; + int i; + + nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK; + /* Make sure we always allocate at least one indirect block pointer */ + nblocks = nblocks ? : 1; + group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER); + if (!group_info) + return NULL; + group_info->ngroups = gidsetsize; + group_info->nblocks = nblocks; + atomic_set(&group_info->usage, 1); + + if (gidsetsize <= NGROUPS_SMALL) + group_info->blocks[0] = group_info->small_block; + else { + for (i = 0; i < nblocks; i++) { + gid_t *b; + b = (void *)__get_free_page(GFP_USER); + if (!b) + goto out_undo_partial_alloc; + group_info->blocks[i] = b; + } + } + return group_info; + +out_undo_partial_alloc: + while (--i >= 0) { + free_page((unsigned long)group_info->blocks[i]); + } + kfree(group_info); + return NULL; +} + +EXPORT_SYMBOL(groups_alloc); + +void groups_free(struct group_info *group_info) +{ + if (group_info->blocks[0] != group_info->small_block) { + int i; + for (i = 0; i < group_info->nblocks; i++) + free_page((unsigned long)group_info->blocks[i]); + } + kfree(group_info); +} + +EXPORT_SYMBOL(groups_free); + +/* export the group_info to a user-space array */ +static int groups_to_user(gid_t __user *grouplist, + const struct group_info *group_info) +{ + int i; + unsigned int count = group_info->ngroups; + + for (i = 0; i < group_info->nblocks; i++) { + unsigned int cp_count = min(NGROUPS_PER_BLOCK, count); + unsigned int len = cp_count * sizeof(*grouplist); + + if (copy_to_user(grouplist, group_info->blocks[i], len)) + return -EFAULT; + + grouplist += NGROUPS_PER_BLOCK; + count -= cp_count; + } + return 0; +} + +/* fill a group_info from a user-space array - it must be allocated already */ +static int groups_from_user(struct group_info *group_info, + gid_t __user *grouplist) +{ + int i; + unsigned int count = group_info->ngroups; + + for (i = 0; i < group_info->nblocks; i++) { + unsigned int cp_count = min(NGROUPS_PER_BLOCK, count); + unsigned int len = cp_count * sizeof(*grouplist); + + if (copy_from_user(group_info->blocks[i], grouplist, len)) + return -EFAULT; + + grouplist += NGROUPS_PER_BLOCK; + count -= cp_count; + } + return 0; +} + +/* a simple Shell sort */ +static void groups_sort(struct group_info *group_info) +{ + int base, max, stride; + int gidsetsize = group_info->ngroups; + + for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1) + ; /* nothing */ + stride /= 3; + + while (stride) { + max = gidsetsize - stride; + for (base = 0; base < max; base++) { + int left = base; + int right = left + stride; + gid_t tmp = GROUP_AT(group_info, right); + + while (left >= 0 && GROUP_AT(group_info, left) > tmp) { + GROUP_AT(group_info, right) = + GROUP_AT(group_info, left); + right = left; + left -= stride; + } + GROUP_AT(group_info, right) = tmp; + } + stride /= 3; + } +} + +/* a simple bsearch */ +int groups_search(const struct group_info *group_info, gid_t grp) +{ + unsigned int left, right; + + if (!group_info) + return 0; + + left = 0; + right = group_info->ngroups; + while (left < right) { + unsigned int mid = (left+right)/2; + int cmp = grp - GROUP_AT(group_info, mid); + if (cmp > 0) + left = mid + 1; + else if (cmp < 0) + right = mid; + else + return 1; + } + return 0; +} + +/** + * set_groups - Change a group subscription in a set of credentials + * @new: The newly prepared set of credentials to alter + * @group_info: The group list to install + * + * Validate a group subscription and, if valid, insert it into a set + * of credentials. + */ +int set_groups(struct cred *new, struct group_info *group_info) +{ + int retval; + + retval = security_task_setgroups(group_info); + if (retval) + return retval; + + put_group_info(new->group_info); + groups_sort(group_info); + get_group_info(group_info); + new->group_info = group_info; + return 0; +} + +EXPORT_SYMBOL(set_groups); + +/** + * set_current_groups - Change current's group subscription + * @group_info: The group list to impose + * + * Validate a group subscription and, if valid, impose it upon current's task + * security record. + */ +int set_current_groups(struct group_info *group_info) +{ + struct cred *new; + int ret; + + new = prepare_creds(); + if (!new) + return -ENOMEM; + + ret = set_groups(new, group_info); + if (ret < 0) { + abort_creds(new); + return ret; + } + + return commit_creds(new); +} + +EXPORT_SYMBOL(set_current_groups); + +SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist) +{ + const struct cred *cred = current_cred(); + int i; + + if (gidsetsize < 0) + return -EINVAL; + + /* no need to grab task_lock here; it cannot change */ + i = cred->group_info->ngroups; + if (gidsetsize) { + if (i > gidsetsize) { + i = -EINVAL; + goto out; + } + if (groups_to_user(grouplist, cred->group_info)) { + i = -EFAULT; + goto out; + } + } +out: + return i; +} + +/* + * SMP: Our groups are copy-on-write. We can set them safely + * without another task interfering. + */ + +SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) +{ + struct group_info *group_info; + int retval; + + if (!capable(CAP_SETGID)) + return -EPERM; + if ((unsigned)gidsetsize > NGROUPS_MAX) + return -EINVAL; + + group_info = groups_alloc(gidsetsize); + if (!group_info) + return -ENOMEM; + retval = groups_from_user(group_info, grouplist); + if (retval) { + put_group_info(group_info); + return retval; + } + + retval = set_current_groups(group_info); + put_group_info(group_info); + + return retval; +} + +/* + * Check whether we're fsgid/egid or in the supplemental group.. + */ +int in_group_p(gid_t grp) +{ + const struct cred *cred = current_cred(); + int retval = 1; + + if (grp != cred->fsgid) + retval = groups_search(cred->group_info, grp); + return retval; +} + +EXPORT_SYMBOL(in_group_p); + +int in_egroup_p(gid_t grp) +{ + const struct cred *cred = current_cred(); + int retval = 1; + + if (grp != cred->egid) + retval = groups_search(cred->group_info, grp); + return retval; +} + +EXPORT_SYMBOL(in_egroup_p); diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index b675a67c9ac..9002958a96e 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -380,6 +380,8 @@ ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs) return res; } +EXPORT_SYMBOL_GPL(ktime_add_safe); + #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static struct debug_obj_descr hrtimer_debug_descr; diff --git a/kernel/kfifo.c b/kernel/kfifo.c index bc41ad0f24f..26539e3228e 100644 --- a/kernel/kfifo.c +++ b/kernel/kfifo.c @@ -72,9 +72,9 @@ struct kfifo *kfifo_alloc(unsigned int size, gfp_t gfp_mask, spinlock_t *lock) /* * round up to the next power of 2, since our 'let the indices - * wrap' tachnique works only in this case. + * wrap' technique works only in this case. */ - if (size & (size - 1)) { + if (!is_power_of_2(size)) { BUG_ON(size > 0x80000000); size = roundup_pow_of_two(size); } diff --git a/kernel/kthread.c b/kernel/kthread.c index 41c88fe4050..9b1a7de2697 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -9,6 +9,7 @@ #include <linux/kthread.h> #include <linux/completion.h> #include <linux/err.h> +#include <linux/cpuset.h> #include <linux/unistd.h> #include <linux/file.h> #include <linux/module.h> @@ -26,7 +27,6 @@ struct kthread_create_info /* Information passed to kthread() from kthreadd. */ int (*threadfn)(void *data); void *data; - struct completion started; /* Result passed back to kthread_create() from kthreadd. */ struct task_struct *result; @@ -35,17 +35,13 @@ struct kthread_create_info struct list_head list; }; -struct kthread_stop_info -{ - struct task_struct *k; - int err; - struct completion done; +struct kthread { + int should_stop; + struct completion exited; }; -/* Thread stopping is done by setthing this var: lock serializes - * multiple kthread_stop calls. */ -static DEFINE_MUTEX(kthread_stop_lock); -static struct kthread_stop_info kthread_stop_info; +#define to_kthread(tsk) \ + container_of((tsk)->vfork_done, struct kthread, exited) /** * kthread_should_stop - should this kthread return now? @@ -56,36 +52,35 @@ static struct kthread_stop_info kthread_stop_info; */ int kthread_should_stop(void) { - return (kthread_stop_info.k == current); + return to_kthread(current)->should_stop; } EXPORT_SYMBOL(kthread_should_stop); static int kthread(void *_create) { + /* Copy data: it's on kthread's stack */ struct kthread_create_info *create = _create; - int (*threadfn)(void *data); - void *data; - int ret = -EINTR; + int (*threadfn)(void *data) = create->threadfn; + void *data = create->data; + struct kthread self; + int ret; - /* Copy data: it's on kthread's stack */ - threadfn = create->threadfn; - data = create->data; + self.should_stop = 0; + init_completion(&self.exited); + current->vfork_done = &self.exited; /* OK, tell user we're spawned, wait for stop or wakeup */ __set_current_state(TASK_UNINTERRUPTIBLE); create->result = current; - complete(&create->started); + complete(&create->done); schedule(); - if (!kthread_should_stop()) + ret = -EINTR; + if (!self.should_stop) ret = threadfn(data); - /* It might have exited on its own, w/o kthread_stop. Check. */ - if (kthread_should_stop()) { - kthread_stop_info.err = ret; - complete(&kthread_stop_info.done); - } - return 0; + /* we can't just return, we must preserve "self" on stack */ + do_exit(ret); } static void create_kthread(struct kthread_create_info *create) @@ -94,11 +89,10 @@ static void create_kthread(struct kthread_create_info *create) /* We want our own signal handler (we take no signals by default). */ pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD); - if (pid < 0) + if (pid < 0) { create->result = ERR_PTR(pid); - else - wait_for_completion(&create->started); - complete(&create->done); + complete(&create->done); + } } /** @@ -129,7 +123,6 @@ struct task_struct *kthread_create(int (*threadfn)(void *data), create.threadfn = threadfn; create.data = data; - init_completion(&create.started); init_completion(&create.done); spin_lock(&kthread_create_lock); @@ -197,30 +190,22 @@ EXPORT_SYMBOL(kthread_bind); */ int kthread_stop(struct task_struct *k) { + struct kthread *kthread; int ret; - mutex_lock(&kthread_stop_lock); - - /* It could exit after stop_info.k set, but before wake_up_process. */ - get_task_struct(k); - trace_sched_kthread_stop(k); + get_task_struct(k); - /* Must init completion *before* thread sees kthread_stop_info.k */ - init_completion(&kthread_stop_info.done); - smp_wmb(); + kthread = to_kthread(k); + barrier(); /* it might have exited */ + if (k->vfork_done != NULL) { + kthread->should_stop = 1; + wake_up_process(k); + wait_for_completion(&kthread->exited); + } + ret = k->exit_code; - /* Now set kthread_should_stop() to true, and wake it up. */ - kthread_stop_info.k = k; - wake_up_process(k); put_task_struct(k); - - /* Once it dies, reset stop ptr, gather result and we're done. */ - wait_for_completion(&kthread_stop_info.done); - kthread_stop_info.k = NULL; - ret = kthread_stop_info.err; - mutex_unlock(&kthread_stop_lock); - trace_sched_kthread_stop_ret(ret); return ret; @@ -236,6 +221,7 @@ int kthreadd(void *unused) ignore_signals(tsk); set_user_nice(tsk, KTHREAD_NICE_LEVEL); set_cpus_allowed_ptr(tsk, cpu_all_mask); + set_mems_allowed(node_possible_map); current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG; diff --git a/kernel/module.c b/kernel/module.c index e4ab36ce767..38928fcaff2 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2216,6 +2216,10 @@ static noinline struct module *load_module(void __user *umod, mod->unused_gpl_crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab_unused_gpl"); #endif +#ifdef CONFIG_CONSTRUCTORS + mod->ctors = section_objs(hdr, sechdrs, secstrings, ".ctors", + sizeof(*mod->ctors), &mod->num_ctors); +#endif #ifdef CONFIG_MARKERS mod->markers = section_objs(hdr, sechdrs, secstrings, "__markers", @@ -2389,6 +2393,17 @@ static noinline struct module *load_module(void __user *umod, goto free_hdr; } +/* Call module constructors. */ +static void do_mod_ctors(struct module *mod) +{ +#ifdef CONFIG_CONSTRUCTORS + unsigned long i; + + for (i = 0; i < mod->num_ctors; i++) + mod->ctors[i](); +#endif +} + /* This is where the real work happens */ SYSCALL_DEFINE3(init_module, void __user *, umod, unsigned long, len, const char __user *, uargs) @@ -2417,6 +2432,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_COMING, mod); + do_mod_ctors(mod); /* Start the module */ if (mod->init != NULL) ret = do_one_initcall(mod->init); @@ -2899,7 +2915,7 @@ void print_modules(void) struct module *mod; char buf[8]; - printk("Modules linked in:"); + printk(KERN_DEFAULT "Modules linked in:"); /* Most callers should already have preempt disabled, but make sure */ preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 63598dca2d0..09b4ff9711b 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -26,19 +26,14 @@ static struct kmem_cache *nsproxy_cachep; struct nsproxy init_nsproxy = INIT_NSPROXY(init_nsproxy); -/* - * creates a copy of "orig" with refcount 1. - */ -static inline struct nsproxy *clone_nsproxy(struct nsproxy *orig) +static inline struct nsproxy *create_nsproxy(void) { - struct nsproxy *ns; + struct nsproxy *nsproxy; - ns = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL); - if (ns) { - memcpy(ns, orig, sizeof(struct nsproxy)); - atomic_set(&ns->count, 1); - } - return ns; + nsproxy = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL); + if (nsproxy) + atomic_set(&nsproxy->count, 1); + return nsproxy; } /* @@ -52,7 +47,7 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, struct nsproxy *new_nsp; int err; - new_nsp = clone_nsproxy(tsk->nsproxy); + new_nsp = create_nsproxy(); if (!new_nsp) return ERR_PTR(-ENOMEM); diff --git a/kernel/pid.c b/kernel/pid.c index b2e5f78fd28..31310b5d3f5 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -378,26 +378,15 @@ EXPORT_SYMBOL(pid_task); /* * Must be called under rcu_read_lock() or with tasklist_lock read-held. */ -struct task_struct *find_task_by_pid_type_ns(int type, int nr, - struct pid_namespace *ns) +struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) { - return pid_task(find_pid_ns(nr, ns), type); + return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID); } -EXPORT_SYMBOL(find_task_by_pid_type_ns); - struct task_struct *find_task_by_vpid(pid_t vnr) { - return find_task_by_pid_type_ns(PIDTYPE_PID, vnr, - current->nsproxy->pid_ns); -} -EXPORT_SYMBOL(find_task_by_vpid); - -struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) -{ - return find_task_by_pid_type_ns(PIDTYPE_PID, nr, ns); + return find_task_by_pid_ns(vnr, current->nsproxy->pid_ns); } -EXPORT_SYMBOL(find_task_by_pid_ns); struct pid *get_task_pid(struct task_struct *task, enum pid_type type) { diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 2d1001b4858..821722ae58a 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -67,9 +67,10 @@ err_alloc: return NULL; } -static struct pid_namespace *create_pid_namespace(unsigned int level) +static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_pid_ns) { struct pid_namespace *ns; + unsigned int level = parent_pid_ns->level + 1; int i; ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL); @@ -86,6 +87,7 @@ static struct pid_namespace *create_pid_namespace(unsigned int level) kref_init(&ns->kref); ns->level = level; + ns->parent = get_pid_ns(parent_pid_ns); set_bit(0, ns->pidmap[0].page); atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1); @@ -114,25 +116,11 @@ static void destroy_pid_namespace(struct pid_namespace *ns) struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old_ns) { - struct pid_namespace *new_ns; - - BUG_ON(!old_ns); - new_ns = get_pid_ns(old_ns); if (!(flags & CLONE_NEWPID)) - goto out; - - new_ns = ERR_PTR(-EINVAL); + return get_pid_ns(old_ns); if (flags & CLONE_THREAD) - goto out_put; - - new_ns = create_pid_namespace(old_ns->level + 1); - if (!IS_ERR(new_ns)) - new_ns->parent = get_pid_ns(old_ns); - -out_put: - put_pid_ns(old_ns); -out: - return new_ns; + return ERR_PTR(-EINVAL); + return create_pid_namespace(old_ns); } void free_pid_ns(struct kref *kref) diff --git a/kernel/power/process.c b/kernel/power/process.c index ca634019497..da2072d7381 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -117,9 +117,12 @@ int freeze_processes(void) if (error) goto Exit; printk("done."); + + oom_killer_disable(); Exit: BUG_ON(in_atomic()); printk("\n"); + return error; } @@ -145,6 +148,8 @@ static void thaw_tasks(bool nosig_only) void thaw_processes(void) { + oom_killer_enable(); + printk("Restarting tasks ... "); thaw_tasks(true); thaw_tasks(false); diff --git a/kernel/printk.c b/kernel/printk.c index 5052b5497c6..b4d97b54c1e 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -687,20 +687,35 @@ asmlinkage int vprintk(const char *fmt, va_list args) sizeof(printk_buf) - printed_len, fmt, args); + p = printk_buf; + + /* Do we have a loglevel in the string? */ + if (p[0] == '<') { + unsigned char c = p[1]; + if (c && p[2] == '>') { + switch (c) { + case '0' ... '7': /* loglevel */ + current_log_level = c - '0'; + /* Fallthrough - make sure we're on a new line */ + case 'd': /* KERN_DEFAULT */ + if (!new_text_line) { + emit_log_char('\n'); + new_text_line = 1; + } + /* Fallthrough - skip the loglevel */ + case 'c': /* KERN_CONT */ + p += 3; + break; + } + } + } + /* * Copy the output into log_buf. If the caller didn't provide * appropriate log level tags, we insert them here */ - for (p = printk_buf; *p; p++) { + for ( ; *p; p++) { if (new_text_line) { - /* If a token, set current_log_level and skip over */ - if (p[0] == '<' && p[1] >= '0' && p[1] <= '7' && - p[2] == '>') { - current_log_level = p[1] - '0'; - p += 3; - printed_len -= 3; - } - /* Always output the token */ emit_log_char('<'); emit_log_char(current_log_level + '0'); diff --git a/kernel/profile.c b/kernel/profile.c index 28cf26ad2d2..69911b5745e 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -365,7 +365,7 @@ static int __cpuinit profile_cpu_callback(struct notifier_block *info, node = cpu_to_node(cpu); per_cpu(cpu_profile_flip, cpu) = 0; if (!per_cpu(cpu_profile_hits, cpu)[1]) { - page = alloc_pages_node(node, + page = alloc_pages_exact_node(node, GFP_KERNEL | __GFP_ZERO, 0); if (!page) @@ -373,7 +373,7 @@ static int __cpuinit profile_cpu_callback(struct notifier_block *info, per_cpu(cpu_profile_hits, cpu)[1] = page_address(page); } if (!per_cpu(cpu_profile_hits, cpu)[0]) { - page = alloc_pages_node(node, + page = alloc_pages_exact_node(node, GFP_KERNEL | __GFP_ZERO, 0); if (!page) @@ -564,14 +564,14 @@ static int create_hash_tables(void) int node = cpu_to_node(cpu); struct page *page; - page = alloc_pages_node(node, + page = alloc_pages_exact_node(node, GFP_KERNEL | __GFP_ZERO | GFP_THISNODE, 0); if (!page) goto out_cleanup; per_cpu(cpu_profile_hits, cpu)[1] = (struct profile_hit *)page_address(page); - page = alloc_pages_node(node, + page = alloc_pages_exact_node(node, GFP_KERNEL | __GFP_ZERO | GFP_THISNODE, 0); if (!page) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index f6d8b8cb5e3..61c78b2c07b 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -167,67 +167,82 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode) int ptrace_attach(struct task_struct *task) { int retval; - unsigned long flags; audit_ptrace(task); retval = -EPERM; + if (unlikely(task->flags & PF_KTHREAD)) + goto out; if (same_thread_group(task, current)) goto out; - /* Protect the target's credential calculations against our + /* + * Protect exec's credential calculations against our interference; * interference; SUID, SGID and LSM creds get determined differently * under ptrace. */ retval = mutex_lock_interruptible(&task->cred_guard_mutex); - if (retval < 0) + if (retval < 0) goto out; - retval = -EPERM; -repeat: - /* - * Nasty, nasty. - * - * We want to hold both the task-lock and the - * tasklist_lock for writing at the same time. - * But that's against the rules (tasklist_lock - * is taken for reading by interrupts on other - * cpu's that may have task_lock). - */ task_lock(task); - if (!write_trylock_irqsave(&tasklist_lock, flags)) { - task_unlock(task); - do { - cpu_relax(); - } while (!write_can_lock(&tasklist_lock)); - goto repeat; - } - - if (!task->mm) - goto bad; - /* the same process cannot be attached many times */ - if (task->ptrace & PT_PTRACED) - goto bad; retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH); + task_unlock(task); if (retval) - goto bad; + goto unlock_creds; - /* Go */ - task->ptrace |= PT_PTRACED; + write_lock_irq(&tasklist_lock); + retval = -EPERM; + if (unlikely(task->exit_state)) + goto unlock_tasklist; + if (task->ptrace) + goto unlock_tasklist; + + task->ptrace = PT_PTRACED; if (capable(CAP_SYS_PTRACE)) task->ptrace |= PT_PTRACE_CAP; __ptrace_link(task, current); - send_sig_info(SIGSTOP, SEND_SIG_FORCED, task); -bad: - write_unlock_irqrestore(&tasklist_lock, flags); - task_unlock(task); + + retval = 0; +unlock_tasklist: + write_unlock_irq(&tasklist_lock); +unlock_creds: mutex_unlock(&task->cred_guard_mutex); out: return retval; } +/** + * ptrace_traceme -- helper for PTRACE_TRACEME + * + * Performs checks and sets PT_PTRACED. + * Should be used by all ptrace implementations for PTRACE_TRACEME. + */ +int ptrace_traceme(void) +{ + int ret = -EPERM; + + write_lock_irq(&tasklist_lock); + /* Are we already being traced? */ + if (!current->ptrace) { + ret = security_ptrace_traceme(current->parent); + /* + * Check PF_EXITING to ensure ->real_parent has not passed + * exit_ptrace(). Otherwise we don't report the error but + * pretend ->real_parent untraces us right after return. + */ + if (!ret && !(current->real_parent->flags & PF_EXITING)) { + current->ptrace = PT_PTRACED; + __ptrace_link(current, current->real_parent); + } + } + write_unlock_irq(&tasklist_lock); + + return ret; +} + /* * Called with irqs disabled, returns true if childs should reap themselves. */ @@ -409,37 +424,33 @@ static int ptrace_setoptions(struct task_struct *child, long data) static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info) { + unsigned long flags; int error = -ESRCH; - read_lock(&tasklist_lock); - if (likely(child->sighand != NULL)) { + if (lock_task_sighand(child, &flags)) { error = -EINVAL; - spin_lock_irq(&child->sighand->siglock); if (likely(child->last_siginfo != NULL)) { *info = *child->last_siginfo; error = 0; } - spin_unlock_irq(&child->sighand->siglock); + unlock_task_sighand(child, &flags); } - read_unlock(&tasklist_lock); return error; } static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info) { + unsigned long flags; int error = -ESRCH; - read_lock(&tasklist_lock); - if (likely(child->sighand != NULL)) { + if (lock_task_sighand(child, &flags)) { error = -EINVAL; - spin_lock_irq(&child->sighand->siglock); if (likely(child->last_siginfo != NULL)) { *child->last_siginfo = *info; error = 0; } - spin_unlock_irq(&child->sighand->siglock); + unlock_task_sighand(child, &flags); } - read_unlock(&tasklist_lock); return error; } @@ -566,72 +577,16 @@ int ptrace_request(struct task_struct *child, long request, return ret; } -/** - * ptrace_traceme -- helper for PTRACE_TRACEME - * - * Performs checks and sets PT_PTRACED. - * Should be used by all ptrace implementations for PTRACE_TRACEME. - */ -int ptrace_traceme(void) -{ - int ret = -EPERM; - - /* - * Are we already being traced? - */ -repeat: - task_lock(current); - if (!(current->ptrace & PT_PTRACED)) { - /* - * See ptrace_attach() comments about the locking here. - */ - unsigned long flags; - if (!write_trylock_irqsave(&tasklist_lock, flags)) { - task_unlock(current); - do { - cpu_relax(); - } while (!write_can_lock(&tasklist_lock)); - goto repeat; - } - - ret = security_ptrace_traceme(current->parent); - - /* - * Check PF_EXITING to ensure ->real_parent has not passed - * exit_ptrace(). Otherwise we don't report the error but - * pretend ->real_parent untraces us right after return. - */ - if (!ret && !(current->real_parent->flags & PF_EXITING)) { - current->ptrace |= PT_PTRACED; - __ptrace_link(current, current->real_parent); - } - - write_unlock_irqrestore(&tasklist_lock, flags); - } - task_unlock(current); - return ret; -} - -/** - * ptrace_get_task_struct -- grab a task struct reference for ptrace - * @pid: process id to grab a task_struct reference of - * - * This function is a helper for ptrace implementations. It checks - * permissions and then grabs a task struct for use of the actual - * ptrace implementation. - * - * Returns the task_struct for @pid or an ERR_PTR() on failure. - */ -struct task_struct *ptrace_get_task_struct(pid_t pid) +static struct task_struct *ptrace_get_task_struct(pid_t pid) { struct task_struct *child; - read_lock(&tasklist_lock); + rcu_read_lock(); child = find_task_by_vpid(pid); if (child) get_task_struct(child); + rcu_read_unlock(); - read_unlock(&tasklist_lock); if (!child) return ERR_PTR(-ESRCH); return child; diff --git a/kernel/res_counter.c b/kernel/res_counter.c index bf8e7534c80..e1338f07431 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -18,7 +18,7 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent) { spin_lock_init(&counter->lock); - counter->limit = (unsigned long long)LLONG_MAX; + counter->limit = RESOURCE_MAX; counter->parent = parent; } @@ -133,6 +133,16 @@ int res_counter_memparse_write_strategy(const char *buf, unsigned long long *res) { char *end; + + /* return RESOURCE_MAX(unlimited) if "-1" is specified */ + if (*buf == '-') { + *res = simple_strtoull(buf + 1, &end, 10); + if (*res != 1 || *end != '\0') + return -EINVAL; + *res = RESOURCE_MAX; + return 0; + } + /* FIXME - make memparse() take const char* args */ *res = memparse((char *)buf, &end); if (*end != '\0') diff --git a/kernel/sched.c b/kernel/sched.c index 00567959ab1..92e51287b98 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -7045,7 +7045,7 @@ static int migration_thread(void *data) if (cpu_is_offline(cpu)) { spin_unlock_irq(&rq->lock); - goto wait_to_die; + break; } if (rq->active_balance) { @@ -7071,16 +7071,7 @@ static int migration_thread(void *data) complete(&req->done); } __set_current_state(TASK_RUNNING); - return 0; -wait_to_die: - /* Wait for kthread_stop */ - set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop()) { - schedule(); - set_current_state(TASK_INTERRUPTIBLE); - } - __set_current_state(TASK_RUNNING); return 0; } @@ -7494,6 +7485,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) rq = task_rq_lock(p, &flags); __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1); task_rq_unlock(rq, &flags); + get_task_struct(p); cpu_rq(cpu)->migration_thread = p; break; @@ -7524,6 +7516,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) kthread_bind(cpu_rq(cpu)->migration_thread, cpumask_any(cpu_online_mask)); kthread_stop(cpu_rq(cpu)->migration_thread); + put_task_struct(cpu_rq(cpu)->migration_thread); cpu_rq(cpu)->migration_thread = NULL; break; @@ -7533,6 +7526,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) migrate_live_tasks(cpu); rq = cpu_rq(cpu); kthread_stop(rq->migration_thread); + put_task_struct(rq->migration_thread); rq->migration_thread = NULL; /* Idle task back to normal (off runqueue, low prio) */ spin_lock_irq(&rq->lock); diff --git a/kernel/signal.c b/kernel/signal.c index 809a228019a..ccf1ceedaeb 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -832,6 +832,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, { struct sigpending *pending; struct sigqueue *q; + int override_rlimit; trace_sched_signal_send(sig, t); @@ -863,9 +864,13 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, make sure at least one signal gets delivered and don't pass on the info struct. */ - q = __sigqueue_alloc(t, GFP_ATOMIC, (sig < SIGRTMIN && - (is_si_special(info) || - info->si_code >= 0))); + if (sig < SIGRTMIN) + override_rlimit = (is_si_special(info) || info->si_code >= 0); + else + override_rlimit = 0; + + q = __sigqueue_alloc(t, GFP_ATOMIC | __GFP_NOTRACK_FALSE_POSITIVE, + override_rlimit); if (q) { list_add_tail(&q->list, &pending->list); switch ((unsigned long) info) { @@ -1405,7 +1410,7 @@ int do_notify_parent(struct task_struct *tsk, int sig) /* do_notify_parent_cldstop should have been called instead. */ BUG_ON(task_is_stopped_or_traced(tsk)); - BUG_ON(!tsk->ptrace && + BUG_ON(!task_ptrace(tsk) && (tsk->group_leader != tsk || !thread_group_empty(tsk))); info.si_signo = sig; @@ -1444,7 +1449,7 @@ int do_notify_parent(struct task_struct *tsk, int sig) psig = tsk->parent->sighand; spin_lock_irqsave(&psig->siglock, flags); - if (!tsk->ptrace && sig == SIGCHLD && + if (!task_ptrace(tsk) && sig == SIGCHLD && (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN || (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT))) { /* @@ -1481,7 +1486,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why) struct task_struct *parent; struct sighand_struct *sighand; - if (tsk->ptrace & PT_PTRACED) + if (task_ptrace(tsk)) parent = tsk->parent; else { tsk = tsk->group_leader; @@ -1494,7 +1499,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why) * see comment in do_notify_parent() abot the following 3 lines */ rcu_read_lock(); - info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns); + info.si_pid = task_pid_nr_ns(tsk, parent->nsproxy->pid_ns); info.si_uid = __task_cred(tsk)->uid; rcu_read_unlock(); @@ -1530,7 +1535,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why) static inline int may_ptrace_stop(void) { - if (!likely(current->ptrace & PT_PTRACED)) + if (!likely(task_ptrace(current))) return 0; /* * Are we in the middle of do_coredump? @@ -1748,7 +1753,7 @@ static int do_signal_stop(int signr) static int ptrace_signal(int signr, siginfo_t *info, struct pt_regs *regs, void *cookie) { - if (!(current->ptrace & PT_PTRACED)) + if (!task_ptrace(current)) return signr; ptrace_signal_deliver(regs, cookie); diff --git a/kernel/slow-work.c b/kernel/slow-work.c index 521ed2004d6..09d7519557d 100644 --- a/kernel/slow-work.c +++ b/kernel/slow-work.c @@ -319,6 +319,15 @@ cant_get_ref: EXPORT_SYMBOL(slow_work_enqueue); /* + * Schedule a cull of the thread pool at some time in the near future + */ +static void slow_work_schedule_cull(void) +{ + mod_timer(&slow_work_cull_timer, + round_jiffies(jiffies + SLOW_WORK_CULL_TIMEOUT)); +} + +/* * Worker thread culling algorithm */ static bool slow_work_cull_thread(void) @@ -335,8 +344,7 @@ static bool slow_work_cull_thread(void) list_empty(&vslow_work_queue) && atomic_read(&slow_work_thread_count) > slow_work_min_threads) { - mod_timer(&slow_work_cull_timer, - jiffies + SLOW_WORK_CULL_TIMEOUT); + slow_work_schedule_cull(); do_cull = true; } } @@ -393,8 +401,7 @@ static int slow_work_thread(void *_data) list_empty(&vslow_work_queue) && atomic_read(&slow_work_thread_count) > slow_work_min_threads) - mod_timer(&slow_work_cull_timer, - jiffies + SLOW_WORK_CULL_TIMEOUT); + slow_work_schedule_cull(); continue; } @@ -458,7 +465,7 @@ static void slow_work_new_thread_execute(struct slow_work *work) if (atomic_dec_and_test(&slow_work_thread_count)) BUG(); /* we're running on a slow work thread... */ mod_timer(&slow_work_oom_timer, - jiffies + SLOW_WORK_OOM_TIMEOUT); + round_jiffies(jiffies + SLOW_WORK_OOM_TIMEOUT)); } else { /* ratelimit the starting of new threads */ mod_timer(&slow_work_oom_timer, jiffies + 1); @@ -502,8 +509,7 @@ static int slow_work_min_threads_sysctl(struct ctl_table *table, int write, if (n < 0 && !slow_work_may_not_start_new_thread) slow_work_enqueue(&slow_work_new_thread); else if (n > 0) - mod_timer(&slow_work_cull_timer, - jiffies + SLOW_WORK_CULL_TIMEOUT); + slow_work_schedule_cull(); } mutex_unlock(&slow_work_user_lock); } @@ -529,8 +535,7 @@ static int slow_work_max_threads_sysctl(struct ctl_table *table, int write, atomic_read(&slow_work_thread_count); if (n < 0) - mod_timer(&slow_work_cull_timer, - jiffies + SLOW_WORK_CULL_TIMEOUT); + slow_work_schedule_cull(); } mutex_unlock(&slow_work_user_lock); } diff --git a/kernel/softirq.c b/kernel/softirq.c index 258885a543d..3a94905fa5d 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -213,6 +213,7 @@ restart: do { if (pending & 1) { int prev_count = preempt_count(); + kstat_incr_softirqs_this_cpu(h - softirq_vec); trace_softirq_entry(h, softirq_vec); h->action(h); @@ -382,6 +383,17 @@ void __tasklet_hi_schedule(struct tasklet_struct *t) EXPORT_SYMBOL(__tasklet_hi_schedule); +void __tasklet_hi_schedule_first(struct tasklet_struct *t) +{ + BUG_ON(!irqs_disabled()); + + t->next = __get_cpu_var(tasklet_hi_vec).head; + __get_cpu_var(tasklet_hi_vec).head = t; + __raise_softirq_irqoff(HI_SOFTIRQ); +} + +EXPORT_SYMBOL(__tasklet_hi_schedule_first); + static void tasklet_action(struct softirq_action *a) { struct tasklet_struct *list; diff --git a/kernel/sys.c b/kernel/sys.c index 438d99a38c8..b3f1097c76f 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1113,289 +1113,6 @@ out: return err; } -/* - * Supplementary group IDs - */ - -/* init to 2 - one for init_task, one to ensure it is never freed */ -struct group_info init_groups = { .usage = ATOMIC_INIT(2) }; - -struct group_info *groups_alloc(int gidsetsize) -{ - struct group_info *group_info; - int nblocks; - int i; - - nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK; - /* Make sure we always allocate at least one indirect block pointer */ - nblocks = nblocks ? : 1; - group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER); - if (!group_info) - return NULL; - group_info->ngroups = gidsetsize; - group_info->nblocks = nblocks; - atomic_set(&group_info->usage, 1); - - if (gidsetsize <= NGROUPS_SMALL) - group_info->blocks[0] = group_info->small_block; - else { - for (i = 0; i < nblocks; i++) { - gid_t *b; - b = (void *)__get_free_page(GFP_USER); - if (!b) - goto out_undo_partial_alloc; - group_info->blocks[i] = b; - } - } - return group_info; - -out_undo_partial_alloc: - while (--i >= 0) { - free_page((unsigned long)group_info->blocks[i]); - } - kfree(group_info); - return NULL; -} - -EXPORT_SYMBOL(groups_alloc); - -void groups_free(struct group_info *group_info) -{ - if (group_info->blocks[0] != group_info->small_block) { - int i; - for (i = 0; i < group_info->nblocks; i++) - free_page((unsigned long)group_info->blocks[i]); - } - kfree(group_info); -} - -EXPORT_SYMBOL(groups_free); - -/* export the group_info to a user-space array */ -static int groups_to_user(gid_t __user *grouplist, - const struct group_info *group_info) -{ - int i; - unsigned int count = group_info->ngroups; - - for (i = 0; i < group_info->nblocks; i++) { - unsigned int cp_count = min(NGROUPS_PER_BLOCK, count); - unsigned int len = cp_count * sizeof(*grouplist); - - if (copy_to_user(grouplist, group_info->blocks[i], len)) - return -EFAULT; - - grouplist += NGROUPS_PER_BLOCK; - count -= cp_count; - } - return 0; -} - -/* fill a group_info from a user-space array - it must be allocated already */ -static int groups_from_user(struct group_info *group_info, - gid_t __user *grouplist) -{ - int i; - unsigned int count = group_info->ngroups; - - for (i = 0; i < group_info->nblocks; i++) { - unsigned int cp_count = min(NGROUPS_PER_BLOCK, count); - unsigned int len = cp_count * sizeof(*grouplist); - - if (copy_from_user(group_info->blocks[i], grouplist, len)) - return -EFAULT; - - grouplist += NGROUPS_PER_BLOCK; - count -= cp_count; - } - return 0; -} - -/* a simple Shell sort */ -static void groups_sort(struct group_info *group_info) -{ - int base, max, stride; - int gidsetsize = group_info->ngroups; - - for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1) - ; /* nothing */ - stride /= 3; - - while (stride) { - max = gidsetsize - stride; - for (base = 0; base < max; base++) { - int left = base; - int right = left + stride; - gid_t tmp = GROUP_AT(group_info, right); - - while (left >= 0 && GROUP_AT(group_info, left) > tmp) { - GROUP_AT(group_info, right) = - GROUP_AT(group_info, left); - right = left; - left -= stride; - } - GROUP_AT(group_info, right) = tmp; - } - stride /= 3; - } -} - -/* a simple bsearch */ -int groups_search(const struct group_info *group_info, gid_t grp) -{ - unsigned int left, right; - - if (!group_info) - return 0; - - left = 0; - right = group_info->ngroups; - while (left < right) { - unsigned int mid = (left+right)/2; - int cmp = grp - GROUP_AT(group_info, mid); - if (cmp > 0) - left = mid + 1; - else if (cmp < 0) - right = mid; - else - return 1; - } - return 0; -} - -/** - * set_groups - Change a group subscription in a set of credentials - * @new: The newly prepared set of credentials to alter - * @group_info: The group list to install - * - * Validate a group subscription and, if valid, insert it into a set - * of credentials. - */ -int set_groups(struct cred *new, struct group_info *group_info) -{ - int retval; - - retval = security_task_setgroups(group_info); - if (retval) - return retval; - - put_group_info(new->group_info); - groups_sort(group_info); - get_group_info(group_info); - new->group_info = group_info; - return 0; -} - -EXPORT_SYMBOL(set_groups); - -/** - * set_current_groups - Change current's group subscription - * @group_info: The group list to impose - * - * Validate a group subscription and, if valid, impose it upon current's task - * security record. - */ -int set_current_groups(struct group_info *group_info) -{ - struct cred *new; - int ret; - - new = prepare_creds(); - if (!new) - return -ENOMEM; - - ret = set_groups(new, group_info); - if (ret < 0) { - abort_creds(new); - return ret; - } - - return commit_creds(new); -} - -EXPORT_SYMBOL(set_current_groups); - -SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist) -{ - const struct cred *cred = current_cred(); - int i; - - if (gidsetsize < 0) - return -EINVAL; - - /* no need to grab task_lock here; it cannot change */ - i = cred->group_info->ngroups; - if (gidsetsize) { - if (i > gidsetsize) { - i = -EINVAL; - goto out; - } - if (groups_to_user(grouplist, cred->group_info)) { - i = -EFAULT; - goto out; - } - } -out: - return i; -} - -/* - * SMP: Our groups are copy-on-write. We can set them safely - * without another task interfering. - */ - -SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) -{ - struct group_info *group_info; - int retval; - - if (!capable(CAP_SETGID)) - return -EPERM; - if ((unsigned)gidsetsize > NGROUPS_MAX) - return -EINVAL; - - group_info = groups_alloc(gidsetsize); - if (!group_info) - return -ENOMEM; - retval = groups_from_user(group_info, grouplist); - if (retval) { - put_group_info(group_info); - return retval; - } - - retval = set_current_groups(group_info); - put_group_info(group_info); - - return retval; -} - -/* - * Check whether we're fsgid/egid or in the supplemental group.. - */ -int in_group_p(gid_t grp) -{ - const struct cred *cred = current_cred(); - int retval = 1; - - if (grp != cred->fsgid) - retval = groups_search(cred->group_info, grp); - return retval; -} - -EXPORT_SYMBOL(in_group_p); - -int in_egroup_p(gid_t grp) -{ - const struct cred *cred = current_cred(); - int retval = 1; - - if (grp != cred->egid) - retval = groups_search(cred->group_info, grp); - return retval; -} - -EXPORT_SYMBOL(in_egroup_p); - DECLARE_RWSEM(uts_sem); SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 0e51a35a448..62e4ff9968b 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -27,6 +27,7 @@ #include <linux/security.h> #include <linux/ctype.h> #include <linux/utsname.h> +#include <linux/kmemcheck.h> #include <linux/smp_lock.h> #include <linux/fs.h> #include <linux/init.h> @@ -967,6 +968,17 @@ static struct ctl_table kern_table[] = { .proc_handler = &proc_dointvec, }, #endif +#ifdef CONFIG_KMEMCHECK + { + .ctl_name = CTL_UNNUMBERED, + .procname = "kmemcheck", + .data = &kmemcheck_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif + /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt @@ -1325,7 +1337,6 @@ static struct ctl_table vm_table[] = { .extra2 = &one, }, #endif -#ifdef CONFIG_UNEVICTABLE_LRU { .ctl_name = CTL_UNNUMBERED, .procname = "scan_unevictable_pages", @@ -1334,7 +1345,6 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &scan_unevictable_handler, }, -#endif /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt @@ -2273,7 +2283,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, void *data) { #define TMPBUFLEN 21 - int *i, vleft, first=1, neg, val; + int *i, vleft, first = 1, neg; unsigned long lval; size_t left, len; @@ -2326,8 +2336,6 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, len = p-buf; if ((len < left) && *p && !isspace(*p)) break; - if (neg) - val = -val; s += len; left -= len; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 2aff39c6f10..e0f59a21c06 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -222,6 +222,15 @@ void tick_nohz_stop_sched_tick(int inidle) cpu = smp_processor_id(); ts = &per_cpu(tick_cpu_sched, cpu); + + /* + * Call to tick_nohz_start_idle stops the last_update_time from being + * updated. Thus, it must not be called in the event we are called from + * irq_exit() with the prior state different than idle. + */ + if (!inidle && !ts->inidle) + goto end; + now = tick_nohz_start_idle(ts); /* @@ -239,9 +248,6 @@ void tick_nohz_stop_sched_tick(int inidle) if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) goto end; - if (!inidle && !ts->inidle) - goto end; - ts->inidle = 1; if (need_resched()) diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 4a13e5a01ce..1551f47e766 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -18,6 +18,13 @@ config HAVE_FUNCTION_TRACER config HAVE_FUNCTION_GRAPH_TRACER bool +config HAVE_FUNCTION_GRAPH_FP_TEST + bool + help + An arch may pass in a unique value (frame pointer) to both the + entering and exiting of a function. On exit, the value is compared + and if it does not match, then it will panic the kernel. + config HAVE_FUNCTION_TRACE_MCOUNT_TEST bool help @@ -121,6 +128,7 @@ config FUNCTION_GRAPH_TRACER bool "Kernel Function Graph Tracer" depends on HAVE_FUNCTION_GRAPH_TRACER depends on FUNCTION_TRACER + depends on !X86_32 || !CC_OPTIMIZE_FOR_SIZE default y help Enable the kernel to trace a function at both its return @@ -147,7 +155,7 @@ config IRQSOFF_TRACER disabled by default and can be runtime (re-)started via: - echo 0 > /debugfs/tracing/tracing_max_latency + echo 0 > /sys/kernel/debug/tracing/tracing_max_latency (Note that kernel size and overhead increases with this option enabled. This option and the preempt-off timing option can be @@ -168,7 +176,7 @@ config PREEMPT_TRACER disabled by default and can be runtime (re-)started via: - echo 0 > /debugfs/tracing/tracing_max_latency + echo 0 > /sys/kernel/debug/tracing/tracing_max_latency (Note that kernel size and overhead increases with this option enabled. This option and the irqs-off timing option can be @@ -261,7 +269,7 @@ config PROFILE_ANNOTATED_BRANCHES This tracer profiles all the the likely and unlikely macros in the kernel. It will display the results in: - /debugfs/tracing/profile_annotated_branch + /sys/kernel/debug/tracing/profile_annotated_branch Note: this will add a significant overhead, only turn this on if you need to profile the system's use of these macros. @@ -274,7 +282,7 @@ config PROFILE_ALL_BRANCHES taken in the kernel is recorded whether it hit or miss. The results will be displayed in: - /debugfs/tracing/profile_branch + /sys/kernel/debug/tracing/profile_branch This option also enables the likely/unlikely profiler. @@ -323,7 +331,7 @@ config STACK_TRACER select KALLSYMS help This special tracer records the maximum stack footprint of the - kernel and displays it in debugfs/tracing/stack_trace. + kernel and displays it in /sys/kernel/debug/tracing/stack_trace. This tracer works by hooking into every function call that the kernel executes, and keeping a maximum stack depth value and diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index bb60732ade0..3718d55fb4c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1224,6 +1224,13 @@ static void ftrace_shutdown(int command) return; ftrace_start_up--; + /* + * Just warn in case of unbalance, no need to kill ftrace, it's not + * critical but the ftrace_call callers may be never nopped again after + * further ftrace uses. + */ + WARN_ON_ONCE(ftrace_start_up < 0); + if (!ftrace_start_up) command |= FTRACE_DISABLE_CALLS; diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c index 86cdf671d7e..1edaa9516e8 100644 --- a/kernel/trace/kmemtrace.c +++ b/kernel/trace/kmemtrace.c @@ -186,7 +186,7 @@ static int kmem_trace_init(struct trace_array *tr) int cpu; kmemtrace_array = tr; - for_each_cpu_mask(cpu, cpu_possible_map) + for_each_cpu(cpu, cpu_possible_mask) tracing_reset(tr, cpu); kmemtrace_start_probes(); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 2e642b2b725..04dac263825 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -10,6 +10,7 @@ #include <linux/debugfs.h> #include <linux/uaccess.h> #include <linux/hardirq.h> +#include <linux/kmemcheck.h> #include <linux/module.h> #include <linux/percpu.h> #include <linux/mutex.h> @@ -205,6 +206,7 @@ EXPORT_SYMBOL_GPL(tracing_is_on); #define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array)) #define RB_ALIGNMENT 4U #define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX) +#define RB_EVNT_MIN_SIZE 8U /* two 32bit words */ /* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */ #define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX @@ -414,6 +416,8 @@ struct ring_buffer_per_cpu { unsigned long overrun; unsigned long read; local_t entries; + local_t committing; + local_t commits; u64 write_stamp; u64 read_stamp; atomic_t record_disabled; @@ -617,12 +621,6 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) kfree(cpu_buffer); } -/* - * Causes compile errors if the struct buffer_page gets bigger - * than the struct page. - */ -extern int ring_buffer_page_too_big(void); - #ifdef CONFIG_HOTPLUG_CPU static int rb_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu); @@ -645,11 +643,6 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, int bsize; int cpu; - /* Paranoid! Optimizes out when all is well */ - if (sizeof(struct buffer_page) > sizeof(struct page)) - ring_buffer_page_too_big(); - - /* keep it in its own cache line */ buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()), GFP_KERNEL); @@ -665,8 +658,8 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, buffer->reader_lock_key = key; /* need at least two pages */ - if (buffer->pages == 1) - buffer->pages++; + if (buffer->pages < 2) + buffer->pages = 2; /* * In case of non-hotplug cpu, if the ring-buffer is allocated @@ -1010,12 +1003,12 @@ rb_event_index(struct ring_buffer_event *event) { unsigned long addr = (unsigned long)event; - return (addr & ~PAGE_MASK) - (PAGE_SIZE - BUF_PAGE_SIZE); + return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE; } static inline int -rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer, - struct ring_buffer_event *event) +rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer, + struct ring_buffer_event *event) { unsigned long addr = (unsigned long)event; unsigned long index; @@ -1028,31 +1021,6 @@ rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer, } static void -rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer, - struct ring_buffer_event *event) -{ - unsigned long addr = (unsigned long)event; - unsigned long index; - - index = rb_event_index(event); - addr &= PAGE_MASK; - - while (cpu_buffer->commit_page->page != (void *)addr) { - if (RB_WARN_ON(cpu_buffer, - cpu_buffer->commit_page == cpu_buffer->tail_page)) - return; - cpu_buffer->commit_page->page->commit = - cpu_buffer->commit_page->write; - rb_inc_page(cpu_buffer, &cpu_buffer->commit_page); - cpu_buffer->write_stamp = - cpu_buffer->commit_page->page->time_stamp; - } - - /* Now set the commit to the event's index */ - local_set(&cpu_buffer->commit_page->page->commit, index); -} - -static void rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) { /* @@ -1170,6 +1138,60 @@ static unsigned rb_calculate_event_length(unsigned length) return length; } +static inline void +rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_page *tail_page, + unsigned long tail, unsigned long length) +{ + struct ring_buffer_event *event; + + /* + * Only the event that crossed the page boundary + * must fill the old tail_page with padding. + */ + if (tail >= BUF_PAGE_SIZE) { + local_sub(length, &tail_page->write); + return; + } + + event = __rb_page_index(tail_page, tail); + kmemcheck_annotate_bitfield(event, bitfield); + + /* + * If this event is bigger than the minimum size, then + * we need to be careful that we don't subtract the + * write counter enough to allow another writer to slip + * in on this page. + * We put in a discarded commit instead, to make sure + * that this space is not used again. + * + * If we are less than the minimum size, we don't need to + * worry about it. + */ + if (tail > (BUF_PAGE_SIZE - RB_EVNT_MIN_SIZE)) { + /* No room for any events */ + + /* Mark the rest of the page with padding */ + rb_event_set_padding(event); + + /* Set the write back to the previous setting */ + local_sub(length, &tail_page->write); + return; + } + + /* Put in a discarded event */ + event->array[0] = (BUF_PAGE_SIZE - tail) - RB_EVNT_HDR_SIZE; + event->type_len = RINGBUF_TYPE_PADDING; + /* time delta must be non zero */ + event->time_delta = 1; + /* Account for this as an entry */ + local_inc(&tail_page->entries); + local_inc(&cpu_buffer->entries); + + /* Set write to end of buffer */ + length = (tail + length) - BUF_PAGE_SIZE; + local_sub(length, &tail_page->write); +} static struct ring_buffer_event * rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, @@ -1179,7 +1201,6 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, { struct buffer_page *next_page, *head_page, *reader_page; struct ring_buffer *buffer = cpu_buffer->buffer; - struct ring_buffer_event *event; bool lock_taken = false; unsigned long flags; @@ -1264,26 +1285,7 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, cpu_buffer->tail_page->page->time_stamp = *ts; } - /* - * The actual tail page has moved forward. - */ - if (tail < BUF_PAGE_SIZE) { - /* Mark the rest of the page with padding */ - event = __rb_page_index(tail_page, tail); - rb_event_set_padding(event); - } - - /* Set the write back to the previous setting */ - local_sub(length, &tail_page->write); - - /* - * If this was a commit entry that failed, - * increment that too - */ - if (tail_page == cpu_buffer->commit_page && - tail == rb_commit_index(cpu_buffer)) { - rb_set_commit_to_write(cpu_buffer); - } + rb_reset_tail(cpu_buffer, tail_page, tail, length); __raw_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); @@ -1293,7 +1295,7 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, out_reset: /* reset write */ - local_sub(length, &tail_page->write); + rb_reset_tail(cpu_buffer, tail_page, tail, length); if (likely(lock_taken)) __raw_spin_unlock(&cpu_buffer->lock); @@ -1323,10 +1325,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, /* We reserved something on the buffer */ - if (RB_WARN_ON(cpu_buffer, write > BUF_PAGE_SIZE)) - return NULL; - event = __rb_page_index(tail_page, tail); + kmemcheck_annotate_bitfield(event, bitfield); rb_update_event(event, type, length); /* The passed in type is zero for DATA */ @@ -1334,11 +1334,11 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, local_inc(&tail_page->entries); /* - * If this is a commit and the tail is zero, then update - * this page's time stamp. + * If this is the first commit on the page, then update + * its timestamp. */ - if (!tail && rb_is_commit(cpu_buffer, event)) - cpu_buffer->commit_page->page->time_stamp = *ts; + if (!tail) + tail_page->page->time_stamp = *ts; return event; } @@ -1407,16 +1407,16 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer, return -EAGAIN; /* Only a commited time event can update the write stamp */ - if (rb_is_commit(cpu_buffer, event)) { + if (rb_event_is_commit(cpu_buffer, event)) { /* - * If this is the first on the page, then we need to - * update the page itself, and just put in a zero. + * If this is the first on the page, then it was + * updated with the page itself. Try to discard it + * and if we can't just make it zero. */ if (rb_event_index(event)) { event->time_delta = *delta & TS_MASK; event->array[0] = *delta >> TS_SHIFT; } else { - cpu_buffer->commit_page->page->time_stamp = *ts; /* try to discard, since we do not need this */ if (!rb_try_to_discard(cpu_buffer, event)) { /* nope, just zero it */ @@ -1442,6 +1442,44 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer, return ret; } +static void rb_start_commit(struct ring_buffer_per_cpu *cpu_buffer) +{ + local_inc(&cpu_buffer->committing); + local_inc(&cpu_buffer->commits); +} + +static void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer) +{ + unsigned long commits; + + if (RB_WARN_ON(cpu_buffer, + !local_read(&cpu_buffer->committing))) + return; + + again: + commits = local_read(&cpu_buffer->commits); + /* synchronize with interrupts */ + barrier(); + if (local_read(&cpu_buffer->committing) == 1) + rb_set_commit_to_write(cpu_buffer); + + local_dec(&cpu_buffer->committing); + + /* synchronize with interrupts */ + barrier(); + + /* + * Need to account for interrupts coming in between the + * updating of the commit page and the clearing of the + * committing counter. + */ + if (unlikely(local_read(&cpu_buffer->commits) != commits) && + !local_read(&cpu_buffer->committing)) { + local_inc(&cpu_buffer->committing); + goto again; + } +} + static struct ring_buffer_event * rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer, unsigned long length) @@ -1451,6 +1489,8 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer, int commit = 0; int nr_loops = 0; + rb_start_commit(cpu_buffer); + length = rb_calculate_event_length(length); again: /* @@ -1463,7 +1503,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer, * Bail! */ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000)) - return NULL; + goto out_fail; ts = rb_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu); @@ -1494,7 +1534,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer, commit = rb_add_time_stamp(cpu_buffer, &ts, &delta); if (commit == -EBUSY) - return NULL; + goto out_fail; if (commit == -EAGAIN) goto again; @@ -1508,28 +1548,19 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer, if (unlikely(PTR_ERR(event) == -EAGAIN)) goto again; - if (!event) { - if (unlikely(commit)) - /* - * Ouch! We needed a timestamp and it was commited. But - * we didn't get our event reserved. - */ - rb_set_commit_to_write(cpu_buffer); - return NULL; - } + if (!event) + goto out_fail; - /* - * If the timestamp was commited, make the commit our entry - * now so that we will update it when needed. - */ - if (unlikely(commit)) - rb_set_commit_event(cpu_buffer, event); - else if (!rb_is_commit(cpu_buffer, event)) + if (!rb_event_is_commit(cpu_buffer, event)) delta = 0; event->time_delta = delta; return event; + + out_fail: + rb_end_commit(cpu_buffer); + return NULL; } #define TRACE_RECURSIVE_DEPTH 16 @@ -1639,13 +1670,14 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer, { local_inc(&cpu_buffer->entries); - /* Only process further if we own the commit */ - if (!rb_is_commit(cpu_buffer, event)) - return; - - cpu_buffer->write_stamp += event->time_delta; + /* + * The event first in the commit queue updates the + * time stamp. + */ + if (rb_event_is_commit(cpu_buffer, event)) + cpu_buffer->write_stamp += event->time_delta; - rb_set_commit_to_write(cpu_buffer); + rb_end_commit(cpu_buffer); } /** @@ -1734,15 +1766,15 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer, /* The event is discarded regardless */ rb_event_discard(event); + cpu = smp_processor_id(); + cpu_buffer = buffer->buffers[cpu]; + /* * This must only be called if the event has not been * committed yet. Thus we can assume that preemption * is still disabled. */ - RB_WARN_ON(buffer, preemptible()); - - cpu = smp_processor_id(); - cpu_buffer = buffer->buffers[cpu]; + RB_WARN_ON(buffer, !local_read(&cpu_buffer->committing)); if (!rb_try_to_discard(cpu_buffer, event)) goto out; @@ -1753,13 +1785,7 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer, */ local_inc(&cpu_buffer->entries); out: - /* - * If a write came in and pushed the tail page - * we still need to update the commit pointer - * if we were the commit. - */ - if (rb_is_commit(cpu_buffer, event)) - rb_set_commit_to_write(cpu_buffer); + rb_end_commit(cpu_buffer); trace_recursive_unlock(); @@ -2443,6 +2469,21 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) } EXPORT_SYMBOL_GPL(ring_buffer_iter_peek); +static inline int rb_ok_to_lock(void) +{ + /* + * If an NMI die dumps out the content of the ring buffer + * do not grab locks. We also permanently disable the ring + * buffer too. A one time deal is all you get from reading + * the ring buffer from an NMI. + */ + if (likely(!in_nmi() && !oops_in_progress)) + return 1; + + tracing_off_permanent(); + return 0; +} + /** * ring_buffer_peek - peek at the next event to be read * @buffer: The ring buffer to read @@ -2458,14 +2499,20 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; struct ring_buffer_event *event; unsigned long flags; + int dolock; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return NULL; + dolock = rb_ok_to_lock(); again: - spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + local_irq_save(flags); + if (dolock) + spin_lock(&cpu_buffer->reader_lock); event = rb_buffer_peek(buffer, cpu, ts); - spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + if (dolock) + spin_unlock(&cpu_buffer->reader_lock); + local_irq_restore(flags); if (event && event->type_len == RINGBUF_TYPE_PADDING) { cpu_relax(); @@ -2517,6 +2564,9 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts) struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event = NULL; unsigned long flags; + int dolock; + + dolock = rb_ok_to_lock(); again: /* might be called in atomic */ @@ -2526,7 +2576,9 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts) goto out; cpu_buffer = buffer->buffers[cpu]; - spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + local_irq_save(flags); + if (dolock) + spin_lock(&cpu_buffer->reader_lock); event = rb_buffer_peek(buffer, cpu, ts); if (!event) @@ -2535,7 +2587,9 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts) rb_advance_reader(cpu_buffer); out_unlock: - spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + if (dolock) + spin_unlock(&cpu_buffer->reader_lock); + local_irq_restore(flags); out: preempt_enable(); @@ -2677,6 +2731,8 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->overrun = 0; cpu_buffer->read = 0; local_set(&cpu_buffer->entries, 0); + local_set(&cpu_buffer->committing, 0); + local_set(&cpu_buffer->commits, 0); cpu_buffer->write_stamp = 0; cpu_buffer->read_stamp = 0; @@ -2731,12 +2787,25 @@ EXPORT_SYMBOL_GPL(ring_buffer_reset); int ring_buffer_empty(struct ring_buffer *buffer) { struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags; + int dolock; int cpu; + int ret; + + dolock = rb_ok_to_lock(); /* yes this is racy, but if you don't like the race, lock the buffer */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; - if (!rb_per_cpu_empty(cpu_buffer)) + local_irq_save(flags); + if (dolock) + spin_lock(&cpu_buffer->reader_lock); + ret = rb_per_cpu_empty(cpu_buffer); + if (dolock) + spin_unlock(&cpu_buffer->reader_lock); + local_irq_restore(flags); + + if (!ret) return 0; } @@ -2752,14 +2821,23 @@ EXPORT_SYMBOL_GPL(ring_buffer_empty); int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags; + int dolock; int ret; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 1; + dolock = rb_ok_to_lock(); + cpu_buffer = buffer->buffers[cpu]; + local_irq_save(flags); + if (dolock) + spin_lock(&cpu_buffer->reader_lock); ret = rb_per_cpu_empty(cpu_buffer); - + if (dolock) + spin_unlock(&cpu_buffer->reader_lock); + local_irq_restore(flags); return ret; } @@ -3105,7 +3183,7 @@ static int rb_cpu_notify(struct notifier_block *self, switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: - if (cpu_isset(cpu, *buffer->cpumask)) + if (cpumask_test_cpu(cpu, buffer->cpumask)) return NOTIFY_OK; buffer->buffers[cpu] = @@ -3116,7 +3194,7 @@ static int rb_cpu_notify(struct notifier_block *self, return NOTIFY_OK; } smp_wmb(); - cpu_set(cpu, *buffer->cpumask); + cpumask_set_cpu(cpu, buffer->cpumask); break; case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index 8d68e149a8b..573d3cc762c 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -102,8 +102,10 @@ static enum event_status read_page(int cpu) event = (void *)&rpage->data[i]; switch (event->type_len) { case RINGBUF_TYPE_PADDING: - /* We don't expect any padding */ - KILL_TEST(); + /* failed writes may be discarded events */ + if (!event->time_delta) + KILL_TEST(); + inc = event->array[0] + 4; break; case RINGBUF_TYPE_TIME_EXTEND: inc = 8; @@ -119,7 +121,7 @@ static enum event_status read_page(int cpu) KILL_TEST(); break; } - inc = event->array[0]; + inc = event->array[0] + 4; break; default: entry = ring_buffer_event_data(event); @@ -201,7 +203,7 @@ static void ring_buffer_producer(void) * Hammer the buffer for 10 secs (this may * make the system stall) */ - pr_info("Starting ring buffer hammer\n"); + trace_printk("Starting ring buffer hammer\n"); do_gettimeofday(&start_tv); do { struct ring_buffer_event *event; @@ -237,7 +239,7 @@ static void ring_buffer_producer(void) #endif } while (end_tv.tv_sec < (start_tv.tv_sec + RUN_TIME) && !kill_test); - pr_info("End ring buffer hammer\n"); + trace_printk("End ring buffer hammer\n"); if (consumer) { /* Init both completions here to avoid races */ @@ -260,49 +262,50 @@ static void ring_buffer_producer(void) overruns = ring_buffer_overruns(buffer); if (kill_test) - pr_info("ERROR!\n"); - pr_info("Time: %lld (usecs)\n", time); - pr_info("Overruns: %lld\n", overruns); + trace_printk("ERROR!\n"); + trace_printk("Time: %lld (usecs)\n", time); + trace_printk("Overruns: %lld\n", overruns); if (disable_reader) - pr_info("Read: (reader disabled)\n"); + trace_printk("Read: (reader disabled)\n"); else - pr_info("Read: %ld (by %s)\n", read, + trace_printk("Read: %ld (by %s)\n", read, read_events ? "events" : "pages"); - pr_info("Entries: %lld\n", entries); - pr_info("Total: %lld\n", entries + overruns + read); - pr_info("Missed: %ld\n", missed); - pr_info("Hit: %ld\n", hit); + trace_printk("Entries: %lld\n", entries); + trace_printk("Total: %lld\n", entries + overruns + read); + trace_printk("Missed: %ld\n", missed); + trace_printk("Hit: %ld\n", hit); /* Convert time from usecs to millisecs */ do_div(time, USEC_PER_MSEC); if (time) hit /= (long)time; else - pr_info("TIME IS ZERO??\n"); + trace_printk("TIME IS ZERO??\n"); - pr_info("Entries per millisec: %ld\n", hit); + trace_printk("Entries per millisec: %ld\n", hit); if (hit) { /* Calculate the average time in nanosecs */ avg = NSEC_PER_MSEC / hit; - pr_info("%ld ns per entry\n", avg); + trace_printk("%ld ns per entry\n", avg); } if (missed) { if (time) missed /= (long)time; - pr_info("Total iterations per millisec: %ld\n", hit + missed); + trace_printk("Total iterations per millisec: %ld\n", + hit + missed); /* it is possible that hit + missed will overflow and be zero */ if (!(hit + missed)) { - pr_info("hit + missed overflowed and totalled zero!\n"); + trace_printk("hit + missed overflowed and totalled zero!\n"); hit--; /* make it non zero */ } /* Caculate the average time in nanosecs */ avg = NSEC_PER_MSEC / (hit + missed); - pr_info("%ld ns per entry\n", avg); + trace_printk("%ld ns per entry\n", avg); } } @@ -353,7 +356,7 @@ static int ring_buffer_producer_thread(void *arg) ring_buffer_producer(); - pr_info("Sleeping for 10 secs\n"); + trace_printk("Sleeping for 10 secs\n"); set_current_state(TASK_INTERRUPTIBLE); schedule_timeout(HZ * SLEEP_TIME); __set_current_state(TASK_RUNNING); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8acd9b81a5d..076fa6f0ee4 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -344,7 +344,7 @@ static raw_spinlock_t ftrace_max_lock = /* * Copy the new maximum trace into the separate maximum-trace * structure. (this way the maximum trace is permanently saved, - * for later retrieval via /debugfs/tracing/latency_trace) + * for later retrieval via /sys/kernel/debug/tracing/latency_trace) */ static void __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) @@ -2191,11 +2191,12 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL)) return -ENOMEM; - mutex_lock(&tracing_cpumask_update_lock); err = cpumask_parse_user(ubuf, count, tracing_cpumask_new); if (err) goto err_unlock; + mutex_lock(&tracing_cpumask_update_lock); + local_irq_disable(); __raw_spin_lock(&ftrace_max_lock); for_each_tracing_cpu(cpu) { @@ -2223,8 +2224,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, return count; err_unlock: - mutex_unlock(&tracing_cpumask_update_lock); - free_cpumask_var(tracing_cpumask); + free_cpumask_var(tracing_cpumask_new); return err; } @@ -2414,21 +2414,20 @@ static const struct file_operations tracing_iter_fops = { static const char readme_msg[] = "tracing mini-HOWTO:\n\n" - "# mkdir /debug\n" - "# mount -t debugfs nodev /debug\n\n" - "# cat /debug/tracing/available_tracers\n" + "# mount -t debugfs nodev /sys/kernel/debug\n\n" + "# cat /sys/kernel/debug/tracing/available_tracers\n" "wakeup preemptirqsoff preemptoff irqsoff function sched_switch nop\n\n" - "# cat /debug/tracing/current_tracer\n" + "# cat /sys/kernel/debug/tracing/current_tracer\n" "nop\n" - "# echo sched_switch > /debug/tracing/current_tracer\n" - "# cat /debug/tracing/current_tracer\n" + "# echo sched_switch > /sys/kernel/debug/tracing/current_tracer\n" + "# cat /sys/kernel/debug/tracing/current_tracer\n" "sched_switch\n" - "# cat /debug/tracing/trace_options\n" + "# cat /sys/kernel/debug/tracing/trace_options\n" "noprint-parent nosym-offset nosym-addr noverbose\n" - "# echo print-parent > /debug/tracing/trace_options\n" - "# echo 1 > /debug/tracing/tracing_enabled\n" - "# cat /debug/tracing/trace > /tmp/trace.txt\n" - "# echo 0 > /debug/tracing/tracing_enabled\n" + "# echo print-parent > /sys/kernel/debug/tracing/trace_options\n" + "# echo 1 > /sys/kernel/debug/tracing/tracing_enabled\n" + "# cat /sys/kernel/debug/tracing/trace > /tmp/trace.txt\n" + "# echo 0 > /sys/kernel/debug/tracing/tracing_enabled\n" ; static ssize_t @@ -3627,7 +3626,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf, struct trace_seq *s; unsigned long cnt; - s = kmalloc(sizeof(*s), GFP_ATOMIC); + s = kmalloc(sizeof(*s), GFP_KERNEL); if (!s) return ENOMEM; diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index db6e54bdb59..936c621bbf4 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -27,8 +27,6 @@ #include "trace.h" #include "trace_output.h" -static DEFINE_MUTEX(filter_mutex); - enum filter_op_ids { OP_OR, @@ -178,7 +176,7 @@ static int filter_pred_string(struct filter_pred *pred, void *event, static int filter_pred_strloc(struct filter_pred *pred, void *event, int val1, int val2) { - int str_loc = *(int *)(event + pred->offset); + unsigned short str_loc = *(unsigned short *)(event + pred->offset); char *addr = (char *)(event + str_loc); int cmp, match; @@ -294,12 +292,12 @@ void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s) { struct event_filter *filter = call->filter; - mutex_lock(&filter_mutex); + mutex_lock(&event_mutex); if (filter->filter_string) trace_seq_printf(s, "%s\n", filter->filter_string); else trace_seq_printf(s, "none\n"); - mutex_unlock(&filter_mutex); + mutex_unlock(&event_mutex); } void print_subsystem_event_filter(struct event_subsystem *system, @@ -307,12 +305,12 @@ void print_subsystem_event_filter(struct event_subsystem *system, { struct event_filter *filter = system->filter; - mutex_lock(&filter_mutex); + mutex_lock(&event_mutex); if (filter->filter_string) trace_seq_printf(s, "%s\n", filter->filter_string); else trace_seq_printf(s, "none\n"); - mutex_unlock(&filter_mutex); + mutex_unlock(&event_mutex); } static struct ftrace_event_field * @@ -381,6 +379,7 @@ void destroy_preds(struct ftrace_event_call *call) filter_free_pred(filter->preds[i]); } kfree(filter->preds); + kfree(filter->filter_string); kfree(filter); call->filter = NULL; } @@ -433,7 +432,6 @@ static void filter_free_subsystem_preds(struct event_subsystem *system) filter->n_preds = 0; } - mutex_lock(&event_mutex); list_for_each_entry(call, &ftrace_events, list) { if (!call->define_fields) continue; @@ -443,7 +441,6 @@ static void filter_free_subsystem_preds(struct event_subsystem *system) remove_filter_string(call->filter); } } - mutex_unlock(&event_mutex); } static int filter_add_pred_fn(struct filter_parse_state *ps, @@ -546,6 +543,7 @@ static int filter_add_pred(struct filter_parse_state *ps, filter_pred_fn_t fn; unsigned long long val; int string_type; + int ret; pred->fn = filter_pred_none; @@ -581,7 +579,11 @@ static int filter_add_pred(struct filter_parse_state *ps, pred->not = 1; return filter_add_pred_fn(ps, call, pred, fn); } else { - if (strict_strtoull(pred->str_val, 0, &val)) { + if (field->is_signed) + ret = strict_strtoll(pred->str_val, 0, &val); + else + ret = strict_strtoull(pred->str_val, 0, &val); + if (ret) { parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0); return -EINVAL; } @@ -625,7 +627,6 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps, filter->preds[filter->n_preds] = pred; filter->n_preds++; - mutex_lock(&event_mutex); list_for_each_entry(call, &ftrace_events, list) { if (!call->define_fields) @@ -636,14 +637,12 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps, err = filter_add_pred(ps, call, pred); if (err) { - mutex_unlock(&event_mutex); filter_free_subsystem_preds(system); parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0); goto out; } replace_filter_string(call->filter, filter_string); } - mutex_unlock(&event_mutex); out: return err; } @@ -1070,12 +1069,12 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string) struct filter_parse_state *ps; - mutex_lock(&filter_mutex); + mutex_lock(&event_mutex); if (!strcmp(strstrip(filter_string), "0")) { filter_disable_preds(call); remove_filter_string(call->filter); - mutex_unlock(&filter_mutex); + mutex_unlock(&event_mutex); return 0; } @@ -1103,7 +1102,7 @@ out: postfix_clear(ps); kfree(ps); out_unlock: - mutex_unlock(&filter_mutex); + mutex_unlock(&event_mutex); return err; } @@ -1115,12 +1114,12 @@ int apply_subsystem_event_filter(struct event_subsystem *system, struct filter_parse_state *ps; - mutex_lock(&filter_mutex); + mutex_lock(&event_mutex); if (!strcmp(strstrip(filter_string), "0")) { filter_free_subsystem_preds(system); remove_filter_string(system->filter); - mutex_unlock(&filter_mutex); + mutex_unlock(&event_mutex); return 0; } @@ -1148,7 +1147,7 @@ out: postfix_clear(ps); kfree(ps); out_unlock: - mutex_unlock(&filter_mutex); + mutex_unlock(&event_mutex); return err; } diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index c9a0b7df44f..90f13476483 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -193,9 +193,11 @@ static void tracing_start_function_trace(void) static void tracing_stop_function_trace(void) { ftrace_function_enabled = 0; - /* OK if they are not registered */ - unregister_ftrace_function(&trace_stack_ops); - unregister_ftrace_function(&trace_ops); + + if (func_flags.val & TRACE_FUNC_OPT_STACK) + unregister_ftrace_function(&trace_stack_ops); + else + unregister_ftrace_function(&trace_ops); } static int func_set_flag(u32 old_flags, u32 bit, int set) diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 8b592418d8b..d2249abafb5 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -57,7 +57,8 @@ static struct tracer_flags tracer_flags = { /* Add a function return address to the trace stack on thread info.*/ int -ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth) +ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, + unsigned long frame_pointer) { unsigned long long calltime; int index; @@ -85,6 +86,7 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth) current->ret_stack[index].func = func; current->ret_stack[index].calltime = calltime; current->ret_stack[index].subtime = 0; + current->ret_stack[index].fp = frame_pointer; *depth = index; return 0; @@ -92,7 +94,8 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth) /* Retrieve a function return address to the trace stack on thread info.*/ static void -ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret) +ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, + unsigned long frame_pointer) { int index; @@ -106,6 +109,31 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret) return; } +#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST + /* + * The arch may choose to record the frame pointer used + * and check it here to make sure that it is what we expect it + * to be. If gcc does not set the place holder of the return + * address in the frame pointer, and does a copy instead, then + * the function graph trace will fail. This test detects this + * case. + * + * Currently, x86_32 with optimize for size (-Os) makes the latest + * gcc do the above. + */ + if (unlikely(current->ret_stack[index].fp != frame_pointer)) { + ftrace_graph_stop(); + WARN(1, "Bad frame pointer: expected %lx, received %lx\n" + " from func %pF return to %lx\n", + current->ret_stack[index].fp, + frame_pointer, + (void *)current->ret_stack[index].func, + current->ret_stack[index].ret); + *ret = (unsigned long)panic; + return; + } +#endif + *ret = current->ret_stack[index].ret; trace->func = current->ret_stack[index].func; trace->calltime = current->ret_stack[index].calltime; @@ -117,12 +145,12 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret) * Send the trace to the ring-buffer. * @return the original return address. */ -unsigned long ftrace_return_to_handler(void) +unsigned long ftrace_return_to_handler(unsigned long frame_pointer) { struct ftrace_graph_ret trace; unsigned long ret; - ftrace_pop_return_trace(&trace, &ret); + ftrace_pop_return_trace(&trace, &ret, frame_pointer); trace.rettime = trace_clock_local(); ftrace_graph_return(&trace); barrier(); diff --git a/kernel/user.c b/kernel/user.c index 850e0ba41c1..2c000e7132a 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -75,21 +75,6 @@ static void uid_hash_remove(struct user_struct *up) put_user_ns(up->user_ns); } -static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent) -{ - struct user_struct *user; - struct hlist_node *h; - - hlist_for_each_entry(user, h, hashent, uidhash_node) { - if (user->uid == uid) { - atomic_inc(&user->__count); - return user; - } - } - - return NULL; -} - #ifdef CONFIG_USER_SCHED static void sched_destroy_user(struct user_struct *up) @@ -119,6 +104,23 @@ static int sched_create_user(struct user_struct *up) { return 0; } #if defined(CONFIG_USER_SCHED) && defined(CONFIG_SYSFS) +static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent) +{ + struct user_struct *user; + struct hlist_node *h; + + hlist_for_each_entry(user, h, hashent, uidhash_node) { + if (user->uid == uid) { + /* possibly resurrect an "almost deleted" object */ + if (atomic_inc_return(&user->__count) == 1) + cancel_delayed_work(&user->work); + return user; + } + } + + return NULL; +} + static struct kset *uids_kset; /* represents the /sys/kernel/uids/ directory */ static DEFINE_MUTEX(uids_mutex); @@ -283,12 +285,12 @@ int __init uids_sysfs_init(void) return uids_user_create(&root_user); } -/* work function to remove sysfs directory for a user and free up +/* delayed work function to remove sysfs directory for a user and free up * corresponding structures. */ static void cleanup_user_struct(struct work_struct *w) { - struct user_struct *up = container_of(w, struct user_struct, work); + struct user_struct *up = container_of(w, struct user_struct, work.work); unsigned long flags; int remove_user = 0; @@ -297,15 +299,12 @@ static void cleanup_user_struct(struct work_struct *w) */ uids_mutex_lock(); - local_irq_save(flags); - - if (atomic_dec_and_lock(&up->__count, &uidhash_lock)) { + spin_lock_irqsave(&uidhash_lock, flags); + if (atomic_read(&up->__count) == 0) { uid_hash_remove(up); remove_user = 1; - spin_unlock_irqrestore(&uidhash_lock, flags); - } else { - local_irq_restore(flags); } + spin_unlock_irqrestore(&uidhash_lock, flags); if (!remove_user) goto done; @@ -331,16 +330,28 @@ done: */ static void free_user(struct user_struct *up, unsigned long flags) { - /* restore back the count */ - atomic_inc(&up->__count); spin_unlock_irqrestore(&uidhash_lock, flags); - - INIT_WORK(&up->work, cleanup_user_struct); - schedule_work(&up->work); + INIT_DELAYED_WORK(&up->work, cleanup_user_struct); + schedule_delayed_work(&up->work, msecs_to_jiffies(1000)); } #else /* CONFIG_USER_SCHED && CONFIG_SYSFS */ +static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent) +{ + struct user_struct *user; + struct hlist_node *h; + + hlist_for_each_entry(user, h, hashent, uidhash_node) { + if (user->uid == uid) { + atomic_inc(&user->__count); + return user; + } + } + + return NULL; +} + int uids_sysfs_init(void) { return 0; } static inline int uids_user_create(struct user_struct *up) { return 0; } static inline void uids_mutex_lock(void) { } diff --git a/kernel/utsname.c b/kernel/utsname.c index 815237a55af..8a82b4b8ea5 100644 --- a/kernel/utsname.c +++ b/kernel/utsname.c @@ -15,6 +15,16 @@ #include <linux/err.h> #include <linux/slab.h> +static struct uts_namespace *create_uts_ns(void) +{ + struct uts_namespace *uts_ns; + + uts_ns = kmalloc(sizeof(struct uts_namespace), GFP_KERNEL); + if (uts_ns) + kref_init(&uts_ns->kref); + return uts_ns; +} + /* * Clone a new ns copying an original utsname, setting refcount to 1 * @old_ns: namespace to clone @@ -24,14 +34,13 @@ static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns) { struct uts_namespace *ns; - ns = kmalloc(sizeof(struct uts_namespace), GFP_KERNEL); + ns = create_uts_ns(); if (!ns) return ERR_PTR(-ENOMEM); down_read(&uts_sem); memcpy(&ns->name, &old_ns->name, sizeof(ns->name)); up_read(&uts_sem); - kref_init(&ns->kref); return ns; } |