diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/compat.c | 2 | ||||
-rw-r--r-- | kernel/nsproxy.c | 3 | ||||
-rw-r--r-- | kernel/smp.c | 183 | ||||
-rw-r--r-- | kernel/sys.c | 288 | ||||
-rw-r--r-- | kernel/time.c | 4 |
5 files changed, 178 insertions, 302 deletions
diff --git a/kernel/compat.c b/kernel/compat.c index 36700e9..f4bddb9 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -593,7 +593,7 @@ COMPAT_SYSCALL_DEFINE5(waitid, else ret = put_compat_rusage(&ru, uru); if (ret) - return ret; + return -EFAULT; } BUG_ON(info.si_code & __SI_MASK); diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 78e2ecb..b781e66 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -153,8 +153,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) goto out; } - new_ns = create_new_namespaces(flags, tsk, - task_cred_xxx(tsk, user_ns), tsk->fs); + new_ns = create_new_namespaces(flags, tsk, user_ns, tsk->fs); if (IS_ERR(new_ns)) { err = PTR_ERR(new_ns); goto out; diff --git a/kernel/smp.c b/kernel/smp.c index 69f38bd..8e451f3 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -16,22 +16,12 @@ #include "smpboot.h" #ifdef CONFIG_USE_GENERIC_SMP_HELPERS -static struct { - struct list_head queue; - raw_spinlock_t lock; -} call_function __cacheline_aligned_in_smp = - { - .queue = LIST_HEAD_INIT(call_function.queue), - .lock = __RAW_SPIN_LOCK_UNLOCKED(call_function.lock), - }; - enum { CSD_FLAG_LOCK = 0x01, }; struct call_function_data { - struct call_single_data csd; - atomic_t refs; + struct call_single_data __percpu *csd; cpumask_var_t cpumask; cpumask_var_t cpumask_ipi; }; @@ -60,6 +50,11 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL, cpu_to_node(cpu))) return notifier_from_errno(-ENOMEM); + cfd->csd = alloc_percpu(struct call_single_data); + if (!cfd->csd) { + free_cpumask_var(cfd->cpumask); + return notifier_from_errno(-ENOMEM); + } break; #ifdef CONFIG_HOTPLUG_CPU @@ -70,6 +65,7 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) case CPU_DEAD_FROZEN: free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); + free_percpu(cfd->csd); break; #endif }; @@ -171,85 +167,6 @@ void generic_exec_single(int cpu, struct call_single_data *data, int wait) } /* - * Invoked by arch to handle an IPI for call function. Must be called with - * interrupts disabled. - */ -void generic_smp_call_function_interrupt(void) -{ - struct call_function_data *data; - int cpu = smp_processor_id(); - - /* - * Shouldn't receive this interrupt on a cpu that is not yet online. - */ - WARN_ON_ONCE(!cpu_online(cpu)); - - /* - * Ensure entry is visible on call_function_queue after we have - * entered the IPI. See comment in smp_call_function_many. - * If we don't have this, then we may miss an entry on the list - * and never get another IPI to process it. - */ - smp_mb(); - - /* - * It's ok to use list_for_each_rcu() here even though we may - * delete 'pos', since list_del_rcu() doesn't clear ->next - */ - list_for_each_entry_rcu(data, &call_function.queue, csd.list) { - int refs; - smp_call_func_t func; - - /* - * Since we walk the list without any locks, we might - * see an entry that was completed, removed from the - * list and is in the process of being reused. - * - * We must check that the cpu is in the cpumask before - * checking the refs, and both must be set before - * executing the callback on this cpu. - */ - - if (!cpumask_test_cpu(cpu, data->cpumask)) - continue; - - smp_rmb(); - - if (atomic_read(&data->refs) == 0) - continue; - - func = data->csd.func; /* save for later warn */ - func(data->csd.info); - - /* - * If the cpu mask is not still set then func enabled - * interrupts (BUG), and this cpu took another smp call - * function interrupt and executed func(info) twice - * on this cpu. That nested execution decremented refs. - */ - if (!cpumask_test_and_clear_cpu(cpu, data->cpumask)) { - WARN(1, "%pf enabled interrupts and double executed\n", func); - continue; - } - - refs = atomic_dec_return(&data->refs); - WARN_ON(refs < 0); - - if (refs) - continue; - - WARN_ON(!cpumask_empty(data->cpumask)); - - raw_spin_lock(&call_function.lock); - list_del_rcu(&data->csd.list); - raw_spin_unlock(&call_function.lock); - - csd_unlock(&data->csd); - } - -} - -/* * Invoked by arch to handle an IPI for call function single. Must be * called from the arch with interrupts disabled. */ @@ -453,8 +370,7 @@ void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { struct call_function_data *data; - unsigned long flags; - int refs, cpu, next_cpu, this_cpu = smp_processor_id(); + int cpu, next_cpu, this_cpu = smp_processor_id(); /* * Can deadlock when called with interrupts disabled. @@ -486,50 +402,13 @@ void smp_call_function_many(const struct cpumask *mask, } data = &__get_cpu_var(cfd_data); - csd_lock(&data->csd); - - /* This BUG_ON verifies our reuse assertions and can be removed */ - BUG_ON(atomic_read(&data->refs) || !cpumask_empty(data->cpumask)); - - /* - * The global call function queue list add and delete are protected - * by a lock, but the list is traversed without any lock, relying - * on the rcu list add and delete to allow safe concurrent traversal. - * We reuse the call function data without waiting for any grace - * period after some other cpu removes it from the global queue. - * This means a cpu might find our data block as it is being - * filled out. - * - * We hold off the interrupt handler on the other cpu by - * ordering our writes to the cpu mask vs our setting of the - * refs counter. We assert only the cpu owning the data block - * will set a bit in cpumask, and each bit will only be cleared - * by the subject cpu. Each cpu must first find its bit is - * set and then check that refs is set indicating the element is - * ready to be processed, otherwise it must skip the entry. - * - * On the previous iteration refs was set to 0 by another cpu. - * To avoid the use of transitivity, set the counter to 0 here - * so the wmb will pair with the rmb in the interrupt handler. - */ - atomic_set(&data->refs, 0); /* convert 3rd to 1st party write */ - - data->csd.func = func; - data->csd.info = info; - /* Ensure 0 refs is visible before mask. Also orders func and info */ - smp_wmb(); - - /* We rely on the "and" being processed before the store */ cpumask_and(data->cpumask, mask, cpu_online_mask); cpumask_clear_cpu(this_cpu, data->cpumask); - refs = cpumask_weight(data->cpumask); /* Some callers race with other cpus changing the passed mask */ - if (unlikely(!refs)) { - csd_unlock(&data->csd); + if (unlikely(!cpumask_weight(data->cpumask))) return; - } /* * After we put an entry into the list, data->cpumask @@ -537,34 +416,32 @@ void smp_call_function_many(const struct cpumask *mask, * a SMP function call, so data->cpumask will be zero. */ cpumask_copy(data->cpumask_ipi, data->cpumask); - raw_spin_lock_irqsave(&call_function.lock, flags); - /* - * Place entry at the _HEAD_ of the list, so that any cpu still - * observing the entry in generic_smp_call_function_interrupt() - * will not miss any other list entries: - */ - list_add_rcu(&data->csd.list, &call_function.queue); - /* - * We rely on the wmb() in list_add_rcu to complete our writes - * to the cpumask before this write to refs, which indicates - * data is on the list and is ready to be processed. - */ - atomic_set(&data->refs, refs); - raw_spin_unlock_irqrestore(&call_function.lock, flags); - /* - * Make the list addition visible before sending the ipi. - * (IPIs must obey or appear to obey normal Linux cache - * coherency rules -- see comment in generic_exec_single). - */ - smp_mb(); + for_each_cpu(cpu, data->cpumask) { + struct call_single_data *csd = per_cpu_ptr(data->csd, cpu); + struct call_single_queue *dst = + &per_cpu(call_single_queue, cpu); + unsigned long flags; + + csd_lock(csd); + csd->func = func; + csd->info = info; + + raw_spin_lock_irqsave(&dst->lock, flags); + list_add_tail(&csd->list, &dst->list); + raw_spin_unlock_irqrestore(&dst->lock, flags); + } /* Send a message to all CPUs in the map */ arch_send_call_function_ipi_mask(data->cpumask_ipi); - /* Optionally wait for the CPUs to complete */ - if (wait) - csd_lock_wait(&data->csd); + if (wait) { + for_each_cpu(cpu, data->cpumask) { + struct call_single_data *csd = + per_cpu_ptr(data->csd, cpu); + csd_lock_wait(csd); + } + } } EXPORT_SYMBOL(smp_call_function_many); diff --git a/kernel/sys.c b/kernel/sys.c index 265b376..840cfdad 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -47,6 +47,7 @@ #include <linux/syscalls.h> #include <linux/kprobes.h> #include <linux/user_namespace.h> +#include <linux/binfmts.h> #include <linux/kmsg_dump.h> /* Move somewhere else to avoid recompiling? */ @@ -2012,160 +2013,159 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = 0; switch (option) { - case PR_SET_PDEATHSIG: - if (!valid_signal(arg2)) { - error = -EINVAL; - break; - } - me->pdeath_signal = arg2; - break; - case PR_GET_PDEATHSIG: - error = put_user(me->pdeath_signal, (int __user *)arg2); - break; - case PR_GET_DUMPABLE: - error = get_dumpable(me->mm); + case PR_SET_PDEATHSIG: + if (!valid_signal(arg2)) { + error = -EINVAL; break; - case PR_SET_DUMPABLE: - if (arg2 < 0 || arg2 > 1) { - error = -EINVAL; - break; - } - set_dumpable(me->mm, arg2); + } + me->pdeath_signal = arg2; + break; + case PR_GET_PDEATHSIG: + error = put_user(me->pdeath_signal, (int __user *)arg2); + break; + case PR_GET_DUMPABLE: + error = get_dumpable(me->mm); + break; + case PR_SET_DUMPABLE: + if (arg2 != SUID_DUMP_DISABLE && arg2 != SUID_DUMP_USER) { + error = -EINVAL; break; + } + set_dumpable(me->mm, arg2); + break; - case PR_SET_UNALIGN: - error = SET_UNALIGN_CTL(me, arg2); - break; - case PR_GET_UNALIGN: - error = GET_UNALIGN_CTL(me, arg2); - break; - case PR_SET_FPEMU: - error = SET_FPEMU_CTL(me, arg2); - break; - case PR_GET_FPEMU: - error = GET_FPEMU_CTL(me, arg2); - break; - case PR_SET_FPEXC: - error = SET_FPEXC_CTL(me, arg2); - break; - case PR_GET_FPEXC: - error = GET_FPEXC_CTL(me, arg2); - break; - case PR_GET_TIMING: - error = PR_TIMING_STATISTICAL; - break; - case PR_SET_TIMING: - if (arg2 != PR_TIMING_STATISTICAL) - error = -EINVAL; - break; - case PR_SET_NAME: - comm[sizeof(me->comm)-1] = 0; - if (strncpy_from_user(comm, (char __user *)arg2, - sizeof(me->comm) - 1) < 0) - return -EFAULT; - set_task_comm(me, comm); - proc_comm_connector(me); - break; - case PR_GET_NAME: - get_task_comm(comm, me); - if (copy_to_user((char __user *)arg2, comm, - sizeof(comm))) - return -EFAULT; - break; - case PR_GET_ENDIAN: - error = GET_ENDIAN(me, arg2); - break; - case PR_SET_ENDIAN: - error = SET_ENDIAN(me, arg2); - break; - case PR_GET_SECCOMP: - error = prctl_get_seccomp(); - break; - case PR_SET_SECCOMP: - error = prctl_set_seccomp(arg2, (char __user *)arg3); - break; - case PR_GET_TSC: - error = GET_TSC_CTL(arg2); - break; - case PR_SET_TSC: - error = SET_TSC_CTL(arg2); - break; - case PR_TASK_PERF_EVENTS_DISABLE: - error = perf_event_task_disable(); - break; - case PR_TASK_PERF_EVENTS_ENABLE: - error = perf_event_task_enable(); - break; - case PR_GET_TIMERSLACK: - error = current->timer_slack_ns; - break; - case PR_SET_TIMERSLACK: - if (arg2 <= 0) - current->timer_slack_ns = + case PR_SET_UNALIGN: + error = SET_UNALIGN_CTL(me, arg2); + break; + case PR_GET_UNALIGN: + error = GET_UNALIGN_CTL(me, arg2); + break; + case PR_SET_FPEMU: + error = SET_FPEMU_CTL(me, arg2); + break; + case PR_GET_FPEMU: + error = GET_FPEMU_CTL(me, arg2); + break; + case PR_SET_FPEXC: + error = SET_FPEXC_CTL(me, arg2); + break; + case PR_GET_FPEXC: + error = GET_FPEXC_CTL(me, arg2); + break; + case PR_GET_TIMING: + error = PR_TIMING_STATISTICAL; + break; + case PR_SET_TIMING: + if (arg2 != PR_TIMING_STATISTICAL) + error = -EINVAL; + break; + case PR_SET_NAME: + comm[sizeof(me->comm) - 1] = 0; + if (strncpy_from_user(comm, (char __user *)arg2, + sizeof(me->comm) - 1) < 0) + return -EFAULT; + set_task_comm(me, comm); + proc_comm_connector(me); + break; + case PR_GET_NAME: + get_task_comm(comm, me); + if (copy_to_user((char __user *)arg2, comm, sizeof(comm))) + return -EFAULT; + break; + case PR_GET_ENDIAN: + error = GET_ENDIAN(me, arg2); + break; + case PR_SET_ENDIAN: + error = SET_ENDIAN(me, arg2); + break; + case PR_GET_SECCOMP: + error = prctl_get_seccomp(); + break; + case PR_SET_SECCOMP: + error = prctl_set_seccomp(arg2, (char __user *)arg3); + break; + case PR_GET_TSC: + error = GET_TSC_CTL(arg2); + break; + case PR_SET_TSC: + error = SET_TSC_CTL(arg2); + break; + case PR_TASK_PERF_EVENTS_DISABLE: + error = perf_event_task_disable(); + break; + case PR_TASK_PERF_EVENTS_ENABLE: + error = perf_event_task_enable(); + break; + case PR_GET_TIMERSLACK: + error = current->timer_slack_ns; + break; + case PR_SET_TIMERSLACK: + if (arg2 <= 0) + current->timer_slack_ns = current->default_timer_slack_ns; - else - current->timer_slack_ns = arg2; - break; - case PR_MCE_KILL: - if (arg4 | arg5) - return -EINVAL; - switch (arg2) { - case PR_MCE_KILL_CLEAR: - if (arg3 != 0) - return -EINVAL; - current->flags &= ~PF_MCE_PROCESS; - break; - case PR_MCE_KILL_SET: - current->flags |= PF_MCE_PROCESS; - if (arg3 == PR_MCE_KILL_EARLY) - current->flags |= PF_MCE_EARLY; - else if (arg3 == PR_MCE_KILL_LATE) - current->flags &= ~PF_MCE_EARLY; - else if (arg3 == PR_MCE_KILL_DEFAULT) - current->flags &= - ~(PF_MCE_EARLY|PF_MCE_PROCESS); - else - return -EINVAL; - break; - default: + else + current->timer_slack_ns = arg2; + break; + case PR_MCE_KILL: + if (arg4 | arg5) + return -EINVAL; + switch (arg2) { + case PR_MCE_KILL_CLEAR: + if (arg3 != 0) return -EINVAL; - } + current->flags &= ~PF_MCE_PROCESS; break; - case PR_MCE_KILL_GET: - if (arg2 | arg3 | arg4 | arg5) - return -EINVAL; - if (current->flags & PF_MCE_PROCESS) - error = (current->flags & PF_MCE_EARLY) ? - PR_MCE_KILL_EARLY : PR_MCE_KILL_LATE; + case PR_MCE_KILL_SET: + current->flags |= PF_MCE_PROCESS; + if (arg3 == PR_MCE_KILL_EARLY) + current->flags |= PF_MCE_EARLY; + else if (arg3 == PR_MCE_KILL_LATE) + current->flags &= ~PF_MCE_EARLY; + else if (arg3 == PR_MCE_KILL_DEFAULT) + current->flags &= + ~(PF_MCE_EARLY|PF_MCE_PROCESS); else - error = PR_MCE_KILL_DEFAULT; - break; - case PR_SET_MM: - error = prctl_set_mm(arg2, arg3, arg4, arg5); - break; - case PR_GET_TID_ADDRESS: - error = prctl_get_tid_address(me, (int __user **)arg2); - break; - case PR_SET_CHILD_SUBREAPER: - me->signal->is_child_subreaper = !!arg2; - break; - case PR_GET_CHILD_SUBREAPER: - error = put_user(me->signal->is_child_subreaper, - (int __user *) arg2); - break; - case PR_SET_NO_NEW_PRIVS: - if (arg2 != 1 || arg3 || arg4 || arg5) return -EINVAL; - - current->no_new_privs = 1; break; - case PR_GET_NO_NEW_PRIVS: - if (arg2 || arg3 || arg4 || arg5) - return -EINVAL; - return current->no_new_privs ? 1 : 0; default: - error = -EINVAL; - break; + return -EINVAL; + } + break; + case PR_MCE_KILL_GET: + if (arg2 | arg3 | arg4 | arg5) + return -EINVAL; + if (current->flags & PF_MCE_PROCESS) + error = (current->flags & PF_MCE_EARLY) ? + PR_MCE_KILL_EARLY : PR_MCE_KILL_LATE; + else + error = PR_MCE_KILL_DEFAULT; + break; + case PR_SET_MM: + error = prctl_set_mm(arg2, arg3, arg4, arg5); + break; + case PR_GET_TID_ADDRESS: + error = prctl_get_tid_address(me, (int __user **)arg2); + break; + case PR_SET_CHILD_SUBREAPER: + me->signal->is_child_subreaper = !!arg2; + break; + case PR_GET_CHILD_SUBREAPER: + error = put_user(me->signal->is_child_subreaper, + (int __user *)arg2); + break; + case PR_SET_NO_NEW_PRIVS: + if (arg2 != 1 || arg3 || arg4 || arg5) + return -EINVAL; + + current->no_new_privs = 1; + break; + case PR_GET_NO_NEW_PRIVS: + if (arg2 || arg3 || arg4 || arg5) + return -EINVAL; + return current->no_new_privs ? 1 : 0; + default: + error = -EINVAL; + break; } return error; } diff --git a/kernel/time.c b/kernel/time.c index c2a27dd..f8342a4 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -240,7 +240,7 @@ EXPORT_SYMBOL(current_fs_time); * Avoid unnecessary multiplications/divisions in the * two most common HZ cases: */ -inline unsigned int jiffies_to_msecs(const unsigned long j) +unsigned int jiffies_to_msecs(const unsigned long j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; @@ -256,7 +256,7 @@ inline unsigned int jiffies_to_msecs(const unsigned long j) } EXPORT_SYMBOL(jiffies_to_msecs); -inline unsigned int jiffies_to_usecs(const unsigned long j) +unsigned int jiffies_to_usecs(const unsigned long j) { #if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ) return (USEC_PER_SEC / HZ) * j; |