diff options
Diffstat (limited to 'kernel')
46 files changed, 2854 insertions, 2704 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 982c50e..864ff75 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -4,7 +4,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ cpu.o exit.o itimer.o time.o softirq.o resource.o \ - sysctl.o capability.o ptrace.o timer.o user.o \ + sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o \ rcupdate.o extable.o params.o posix-timers.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ @@ -99,6 +99,7 @@ obj-$(CONFIG_SLOW_WORK) += slow-work.o obj-$(CONFIG_SLOW_WORK_DEBUG) += slow-work-debugfs.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o +obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is diff --git a/kernel/cpu.c b/kernel/cpu.c index b216886..291ac58 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -400,10 +400,9 @@ int disable_nonboot_cpus(void) if (cpu == first_cpu) continue; error = _cpu_down(cpu, 1); - if (!error) { + if (!error) cpumask_set_cpu(cpu, frozen_cpus); - printk("CPU%d is down\n", cpu); - } else { + else { printk(KERN_ERR "Error taking CPU%d down: %d\n", cpu, error); break; diff --git a/kernel/exit.c b/kernel/exit.c index 80ae941..6f50ef5 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -971,7 +971,7 @@ NORET_TYPE void do_exit(long code) exit_thread(); cgroup_exit(tsk, 1); - if (group_dead && tsk->signal->leader) + if (group_dead) disassociate_ctty(1); module_put(task_thread_info(tsk)->exec_domain->module); @@ -1009,7 +1009,7 @@ NORET_TYPE void do_exit(long code) tsk->flags |= PF_EXITPIDONE; if (tsk->io_context) - exit_io_context(); + exit_io_context(tsk); if (tsk->splice_pipe) __free_pipe_info(tsk->splice_pipe); diff --git a/kernel/fork.c b/kernel/fork.c index 3d6f121..1415dc4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -64,6 +64,7 @@ #include <linux/magic.h> #include <linux/perf_event.h> #include <linux/posix-timers.h> +#include <linux/user-return-notifier.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -249,6 +250,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) goto out; setup_thread_stack(tsk, orig); + clear_user_return_notifier(tsk); stackend = end_of_stack(tsk); *stackend = STACK_END_MAGIC; /* for overflow detection */ @@ -1315,7 +1317,8 @@ bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_io: - put_io_context(p->io_context); + if (p->io_context) + exit_io_context(p); bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: diff --git a/kernel/futex.c b/kernel/futex.c index fb65e82..d73ef1f 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -304,8 +304,14 @@ void put_futex_key(int fshared, union futex_key *key) */ static int fault_in_user_writeable(u32 __user *uaddr) { - int ret = get_user_pages(current, current->mm, (unsigned long)uaddr, - 1, 1, 0, NULL, NULL); + struct mm_struct *mm = current->mm; + int ret; + + down_read(&mm->mmap_sem); + ret = get_user_pages(current, mm, (unsigned long)uaddr, + 1, 1, 0, NULL, NULL); + up_read(&mm->mmap_sem); + return ret < 0 ? ret : 0; } diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 3e1c36e..d2f9239 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -557,7 +557,7 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) static int hrtimer_reprogram(struct hrtimer *timer, struct hrtimer_clock_base *base) { - ktime_t *expires_next = &__get_cpu_var(hrtimer_bases).expires_next; + struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset); int res; @@ -582,7 +582,16 @@ static int hrtimer_reprogram(struct hrtimer *timer, if (expires.tv64 < 0) return -ETIME; - if (expires.tv64 >= expires_next->tv64) + if (expires.tv64 >= cpu_base->expires_next.tv64) + return 0; + + /* + * If a hang was detected in the last timer interrupt then we + * do not schedule a timer which is earlier than the expiry + * which we enforced in the hang detection. We want the system + * to make progress. + */ + if (cpu_base->hang_detected) return 0; /* @@ -590,7 +599,7 @@ static int hrtimer_reprogram(struct hrtimer *timer, */ res = tick_program_event(expires, 0); if (!IS_ERR_VALUE(res)) - *expires_next = expires; + cpu_base->expires_next = expires; return res; } @@ -747,17 +756,33 @@ static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { } #endif /* CONFIG_HIGH_RES_TIMERS */ -#ifdef CONFIG_TIMER_STATS -void __timer_stats_hrtimer_set_start_info(struct hrtimer *timer, void *addr) +static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer) { +#ifdef CONFIG_TIMER_STATS if (timer->start_site) return; - - timer->start_site = addr; + timer->start_site = __builtin_return_address(0); memcpy(timer->start_comm, current->comm, TASK_COMM_LEN); timer->start_pid = current->pid; +#endif } + +static inline void timer_stats_hrtimer_clear_start_info(struct hrtimer *timer) +{ +#ifdef CONFIG_TIMER_STATS + timer->start_site = NULL; +#endif +} + +static inline void timer_stats_account_hrtimer(struct hrtimer *timer) +{ +#ifdef CONFIG_TIMER_STATS + if (likely(!timer_stats_active)) + return; + timer_stats_update_stats(timer, timer->start_pid, timer->start_site, + timer->function, timer->start_comm, 0); #endif +} /* * Counterpart to lock_hrtimer_base above: @@ -1217,29 +1242,6 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now) #ifdef CONFIG_HIGH_RES_TIMERS -static int force_clock_reprogram; - -/* - * After 5 iteration's attempts, we consider that hrtimer_interrupt() - * is hanging, which could happen with something that slows the interrupt - * such as the tracing. Then we force the clock reprogramming for each future - * hrtimer interrupts to avoid infinite loops and use the min_delta_ns - * threshold that we will overwrite. - * The next tick event will be scheduled to 3 times we currently spend on - * hrtimer_interrupt(). This gives a good compromise, the cpus will spend - * 1/4 of their time to process the hrtimer interrupts. This is enough to - * let it running without serious starvation. - */ - -static inline void -hrtimer_interrupt_hanging(struct clock_event_device *dev, - ktime_t try_time) -{ - force_clock_reprogram = 1; - dev->min_delta_ns = (unsigned long)try_time.tv64 * 3; - printk(KERN_WARNING "hrtimer: interrupt too slow, " - "forcing clock min delta to %lu ns\n", dev->min_delta_ns); -} /* * High resolution timer interrupt * Called with interrupts disabled @@ -1248,21 +1250,15 @@ void hrtimer_interrupt(struct clock_event_device *dev) { struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); struct hrtimer_clock_base *base; - ktime_t expires_next, now; - int nr_retries = 0; - int i; + ktime_t expires_next, now, entry_time, delta; + int i, retries = 0; BUG_ON(!cpu_base->hres_active); cpu_base->nr_events++; dev->next_event.tv64 = KTIME_MAX; - retry: - /* 5 retries is enough to notice a hang */ - if (!(++nr_retries % 5)) - hrtimer_interrupt_hanging(dev, ktime_sub(ktime_get(), now)); - - now = ktime_get(); - + entry_time = now = ktime_get(); +retry: expires_next.tv64 = KTIME_MAX; spin_lock(&cpu_base->lock); @@ -1324,10 +1320,48 @@ void hrtimer_interrupt(struct clock_event_device *dev) spin_unlock(&cpu_base->lock); /* Reprogramming necessary ? */ - if (expires_next.tv64 != KTIME_MAX) { - if (tick_program_event(expires_next, force_clock_reprogram)) - goto retry; + if (expires_next.tv64 == KTIME_MAX || + !tick_program_event(expires_next, 0)) { + cpu_base->hang_detected = 0; + return; } + + /* + * The next timer was already expired due to: + * - tracing + * - long lasting callbacks + * - being scheduled away when running in a VM + * + * We need to prevent that we loop forever in the hrtimer + * interrupt routine. We give it 3 attempts to avoid + * overreacting on some spurious event. + */ + now = ktime_get(); + cpu_base->nr_retries++; + if (++retries < 3) + goto retry; + /* + * Give the system a chance to do something else than looping + * here. We stored the entry time, so we know exactly how long + * we spent here. We schedule the next event this amount of + * time away. + */ + cpu_base->nr_hangs++; + cpu_base->hang_detected = 1; + delta = ktime_sub(now, entry_time); + if (delta.tv64 > cpu_base->max_hang_time.tv64) + cpu_base->max_hang_time = delta; + /* + * Limit it to a sensible value as we enforce a longer + * delay. Give the CPU at least 100ms to catch up. + */ + if (delta.tv64 > 100 * NSEC_PER_MSEC) + expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC); + else + expires_next = ktime_add(now, delta); + tick_program_event(expires_next, 1); + printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n", + ktime_to_ns(delta)); } /* diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c index cf5ee16..366eedf 100644 --- a/kernel/hw_breakpoint.c +++ b/kernel/hw_breakpoint.c @@ -52,7 +52,7 @@ static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned); /* Number of pinned task breakpoints in a cpu */ -static DEFINE_PER_CPU(unsigned int, task_bp_pinned[HBP_NUM]); +static DEFINE_PER_CPU(unsigned int, nr_task_bp_pinned[HBP_NUM]); /* Number of non-pinned cpu/task breakpoints in a cpu */ static DEFINE_PER_CPU(unsigned int, nr_bp_flexible); @@ -73,7 +73,7 @@ static DEFINE_MUTEX(nr_bp_mutex); static unsigned int max_task_bp_pinned(int cpu) { int i; - unsigned int *tsk_pinned = per_cpu(task_bp_pinned, cpu); + unsigned int *tsk_pinned = per_cpu(nr_task_bp_pinned, cpu); for (i = HBP_NUM -1; i >= 0; i--) { if (tsk_pinned[i] > 0) @@ -83,15 +83,51 @@ static unsigned int max_task_bp_pinned(int cpu) return 0; } +static int task_bp_pinned(struct task_struct *tsk) +{ + struct perf_event_context *ctx = tsk->perf_event_ctxp; + struct list_head *list; + struct perf_event *bp; + unsigned long flags; + int count = 0; + + if (WARN_ONCE(!ctx, "No perf context for this task")) + return 0; + + list = &ctx->event_list; + + spin_lock_irqsave(&ctx->lock, flags); + + /* + * The current breakpoint counter is not included in the list + * at the open() callback time + */ + list_for_each_entry(bp, list, event_entry) { + if (bp->attr.type == PERF_TYPE_BREAKPOINT) + count++; + } + + spin_unlock_irqrestore(&ctx->lock, flags); + + return count; +} + /* * Report the number of pinned/un-pinned breakpoints we have in * a given cpu (cpu > -1) or in all of them (cpu = -1). */ -static void fetch_bp_busy_slots(struct bp_busy_slots *slots, int cpu) +static void +fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp) { + int cpu = bp->cpu; + struct task_struct *tsk = bp->ctx->task; + if (cpu >= 0) { slots->pinned = per_cpu(nr_cpu_bp_pinned, cpu); - slots->pinned += max_task_bp_pinned(cpu); + if (!tsk) + slots->pinned += max_task_bp_pinned(cpu); + else + slots->pinned += task_bp_pinned(tsk); slots->flexible = per_cpu(nr_bp_flexible, cpu); return; @@ -101,7 +137,10 @@ static void fetch_bp_busy_slots(struct bp_busy_slots *slots, int cpu) unsigned int nr; nr = per_cpu(nr_cpu_bp_pinned, cpu); - nr += max_task_bp_pinned(cpu); + if (!tsk) + nr += max_task_bp_pinned(cpu); + else + nr += task_bp_pinned(tsk); if (nr > slots->pinned) slots->pinned = nr; @@ -118,35 +157,12 @@ static void fetch_bp_busy_slots(struct bp_busy_slots *slots, int cpu) */ static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable) { - int count = 0; - struct perf_event *bp; - struct perf_event_context *ctx = tsk->perf_event_ctxp; unsigned int *tsk_pinned; - struct list_head *list; - unsigned long flags; - - if (WARN_ONCE(!ctx, "No perf context for this task")) - return; - - list = &ctx->event_list; - - spin_lock_irqsave(&ctx->lock, flags); - - /* - * The current breakpoint counter is not included in the list - * at the open() callback time - */ - list_for_each_entry(bp, list, event_entry) { - if (bp->attr.type == PERF_TYPE_BREAKPOINT) - count++; - } + int count = 0; - spin_unlock_irqrestore(&ctx->lock, flags); + count = task_bp_pinned(tsk); - if (WARN_ONCE(count < 0, "No breakpoint counter found in the counter list")) - return; - - tsk_pinned = per_cpu(task_bp_pinned, cpu); + tsk_pinned = per_cpu(nr_task_bp_pinned, cpu); if (enable) { tsk_pinned[count]++; if (count > 0) @@ -193,7 +209,7 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable) * - If attached to a single cpu, check: * * (per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu) - * + max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM + * + max(per_cpu(nr_task_bp_pinned, cpu)))) < HBP_NUM * * -> If there are already non-pinned counters in this cpu, it means * there is already a free slot for them. @@ -204,7 +220,7 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable) * - If attached to every cpus, check: * * (per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *)) - * + max(per_cpu(task_bp_pinned, *)))) < HBP_NUM + * + max(per_cpu(nr_task_bp_pinned, *)))) < HBP_NUM * * -> This is roughly the same, except we check the number of per cpu * bp for every cpu and we keep the max one. Same for the per tasks @@ -216,7 +232,7 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable) * - If attached to a single cpu, check: * * ((per_cpu(nr_bp_flexible, cpu) > 1) + per_cpu(nr_cpu_bp_pinned, cpu) - * + max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM + * + max(per_cpu(nr_task_bp_pinned, cpu))) < HBP_NUM * * -> Same checks as before. But now the nr_bp_flexible, if any, must keep * one register at least (or they will never be fed). @@ -224,7 +240,7 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable) * - If attached to every cpus, check: * * ((per_cpu(nr_bp_flexible, *) > 1) + max(per_cpu(nr_cpu_bp_pinned, *)) - * + max(per_cpu(task_bp_pinned, *))) < HBP_NUM + * + max(per_cpu(nr_task_bp_pinned, *))) < HBP_NUM */ int reserve_bp_slot(struct perf_event *bp) { @@ -233,7 +249,7 @@ int reserve_bp_slot(struct perf_event *bp) mutex_lock(&nr_bp_mutex); - fetch_bp_busy_slots(&slots, bp->cpu); + fetch_bp_busy_slots(&slots, bp); /* Flexible counters need to keep at least one slot */ if (slots.pinned + (!!slots.flexible) == HBP_NUM) { @@ -259,7 +275,7 @@ void release_bp_slot(struct perf_event *bp) } -int __register_perf_hw_breakpoint(struct perf_event *bp) +int register_perf_hw_breakpoint(struct perf_event *bp) { int ret; @@ -276,19 +292,12 @@ int __register_perf_hw_breakpoint(struct perf_event *bp) * This is a quick hack that will be removed soon, once we remove * the tmp breakpoints from ptrace */ - if (!bp->attr.disabled || bp->callback == perf_bp_event) + if (!bp->attr.disabled || !bp->overflow_handler) ret = arch_validate_hwbkpt_settings(bp, bp->ctx->task); return ret; } -int register_perf_hw_breakpoint(struct perf_event *bp) -{ - bp->callback = perf_bp_event; - - return __register_perf_hw_breakpoint(bp); -} - /** * register_user_hw_breakpoint - register a hardware breakpoint for user space * @attr: breakpoint attributes @@ -297,7 +306,7 @@ int register_perf_hw_breakpoint(struct perf_event *bp) */ struct perf_event * register_user_hw_breakpoint(struct perf_event_attr *attr, - perf_callback_t triggered, + perf_overflow_handler_t triggered, struct task_struct *tsk) { return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered); @@ -311,19 +320,40 @@ EXPORT_SYMBOL_GPL(register_user_hw_breakpoint); * @triggered: callback to trigger when we hit the breakpoint * @tsk: pointer to 'task_struct' of the process to which the address belongs */ -struct perf_event * -modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr, - perf_callback_t triggered, - struct task_struct *tsk) +int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr) { - /* - * FIXME: do it without unregistering - * - We don't want to lose our slot - * - If the new bp is incorrect, don't lose the older one - */ - unregister_hw_breakpoint(bp); + u64 old_addr = bp->attr.bp_addr; + int old_type = bp->attr.bp_type; + int old_len = bp->attr.bp_len; + int err = 0; - return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered); + perf_event_disable(bp); + + bp->attr.bp_addr = attr->bp_addr; + bp->attr.bp_type = attr->bp_type; + bp->attr.bp_len = attr->bp_len; + + if (attr->disabled) + goto end; + + err = arch_validate_hwbkpt_settings(bp, bp->ctx->task); + if (!err) + perf_event_enable(bp); + + if (err) { + bp->attr.bp_addr = old_addr; + bp->attr.bp_type = old_type; + bp->attr.bp_len = old_len; + if (!bp->attr.disabled) + perf_event_enable(bp); + + return err; + } + +end: + bp->attr.disabled = attr->disabled; + + return 0; } EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint); @@ -348,7 +378,7 @@ EXPORT_SYMBOL_GPL(unregister_hw_breakpoint); */ struct perf_event ** register_wide_hw_breakpoint(struct perf_event_attr *attr, - perf_callback_t triggered) + perf_overflow_handler_t triggered) { struct perf_event **cpu_events, **pevent, *bp; long err; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index bde4c66..7305b29 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1067,7 +1067,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, kfree(action); #ifdef CONFIG_DEBUG_SHIRQ - if (irqflags & IRQF_SHARED) { + if (!retval && (irqflags & IRQF_SHARED)) { /* * It's a shared IRQ -- the driver ought to be prepared for it * to happen immediately, so let's make sure.... diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index 22b0a6e..e49ea1c 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -220,7 +220,7 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc, /* * If we are seeing only the odd spurious IRQ caused by * bus asynchronicity then don't eventually trigger an error, - * otherwise the couter becomes a doomsday timer for otherwise + * otherwise the counter becomes a doomsday timer for otherwise * working systems */ if (time_after(jiffies, desc->last_unhandled + HZ/10)) diff --git a/kernel/itimer.c b/kernel/itimer.c index b03451e..d802883 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -146,6 +146,7 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, { cputime_t cval, nval, cinterval, ninterval; s64 ns_ninterval, ns_nval; + u32 error, incr_error; struct cpu_itimer *it = &tsk->signal->it[clock_id]; nval = timeval_to_cputime(&value->it_value); @@ -153,8 +154,8 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, ninterval = timeval_to_cputime(&value->it_interval); ns_ninterval = timeval_to_ns(&value->it_interval); - it->incr_error = cputime_sub_ns(ninterval, ns_ninterval); - it->error = cputime_sub_ns(nval, ns_nval); + error = cputime_sub_ns(nval, ns_nval); + incr_error = cputime_sub_ns(ninterval, ns_ninterval); spin_lock_irq(&tsk->sighand->siglock); @@ -168,6 +169,8 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, } it->expires = nval; it->incr = ninterval; + it->error = error; + it->incr_error = incr_error; trace_itimer_state(clock_id == CPUCLOCK_VIRT ? ITIMER_VIRTUAL : ITIMER_PROF, value, nval); diff --git a/kernel/kgdb.c b/kernel/kgdb.c index 7d70146..2eb517e 100644 --- a/kernel/kgdb.c +++ b/kernel/kgdb.c @@ -129,6 +129,7 @@ struct task_struct *kgdb_usethread; struct task_struct *kgdb_contthread; int kgdb_single_step; +pid_t kgdb_sstep_pid; /* Our I/O buffers. */ static char remcom_in_buffer[BUFMAX]; @@ -541,12 +542,17 @@ static struct task_struct *getthread(struct pt_regs *regs, int tid) */ if (tid == 0 || tid == -1) tid = -atomic_read(&kgdb_active) - 2; - if (tid < 0) { + if (tid < -1 && tid > -NR_CPUS - 2) { if (kgdb_info[-tid - 2].task) return kgdb_info[-tid - 2].task; else return idle_task(-tid - 2); } + if (tid <= 0) { + printk(KERN_ERR "KGDB: Internal thread select error\n"); + dump_stack(); + return NULL; + } /* * find_task_by_pid_ns() does not take the tasklist lock anymore @@ -619,7 +625,8 @@ static void kgdb_flush_swbreak_addr(unsigned long addr) static int kgdb_activate_sw_breakpoints(void) { unsigned long addr; - int error = 0; + int error; + int ret = 0; int i; for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) { @@ -629,13 +636,16 @@ static int kgdb_activate_sw_breakpoints(void) addr = kgdb_break[i].bpt_addr; error = kgdb_arch_set_breakpoint(addr, kgdb_break[i].saved_instr); - if (error) - return error; + if (error) { + ret = error; + printk(KERN_INFO "KGDB: BP install failed: %lx", addr); + continue; + } kgdb_flush_swbreak_addr(addr); kgdb_break[i].state = BP_ACTIVE; } - return 0; + return ret; } static int kgdb_set_sw_break(unsigned long addr) @@ -682,7 +692,8 @@ static int kgdb_set_sw_break(unsigned long addr) static int kgdb_deactivate_sw_breakpoints(void) { unsigned long addr; - int error = 0; + int error; + int ret = 0; int i; for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) { @@ -691,13 +702,15 @@ static int kgdb_deactivate_sw_breakpoints(void) addr = kgdb_break[i].bpt_addr; error = kgdb_arch_remove_breakpoint(addr, kgdb_break[i].saved_instr); - if (error) - return error; + if (error) { + printk(KERN_INFO "KGDB: BP remove failed: %lx\n", addr); + ret = error; + } kgdb_flush_swbreak_addr(addr); kgdb_break[i].state = BP_SET; } - return 0; + return ret; } static int kgdb_remove_sw_break(unsigned long addr) @@ -1204,8 +1217,10 @@ static int gdb_cmd_exception_pass(struct kgdb_state *ks) return 1; } else { - error_packet(remcom_out_buffer, -EINVAL); - return 0; + kgdb_msg_write("KGDB only knows signal 9 (pass)" + " and 15 (pass and disconnect)\n" + "Executing a continue without signal passing\n", 0); + remcom_in_buffer[0] = 'c'; } /* Indicate fall through */ @@ -1395,6 +1410,7 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs) struct kgdb_state kgdb_var; struct kgdb_state *ks = &kgdb_var; unsigned long flags; + int sstep_tries = 100; int error = 0; int i, cpu; @@ -1425,13 +1441,14 @@ acquirelock: cpu_relax(); /* - * Do not start the debugger connection on this CPU if the last - * instance of the exception handler wanted to come into the - * debugger on a different CPU via a single step + * For single stepping, try to only enter on the processor + * that was single stepping. To gaurd against a deadlock, the + * kernel will only try for the value of sstep_tries before + * giving up and continuing on. */ if (atomic_read(&kgdb_cpu_doing_single_step) != -1 && - atomic_read(&kgdb_cpu_doing_single_step) != cpu) { - + (kgdb_info[cpu].task && + kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) { atomic_set(&kgdb_active, -1); touch_softlockup_watchdog(); clocksource_touch_watchdog(); @@ -1524,6 +1541,13 @@ acquirelock: } kgdb_restore: + if (atomic_read(&kgdb_cpu_doing_single_step) != -1) { + int sstep_cpu = atomic_read(&kgdb_cpu_doing_single_step); + if (kgdb_info[sstep_cpu].task) + kgdb_sstep_pid = kgdb_info[sstep_cpu].task->pid; + else + kgdb_sstep_pid = 0; + } /* Free kgdb_active */ atomic_set(&kgdb_active, -1); touch_softlockup_watchdog(); diff --git a/kernel/lockdep.c b/kernel/lockdep.c index f5dcd36..4f8df01 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -168,7 +168,7 @@ static void lock_time_inc(struct lock_time *lt, u64 time) if (time > lt->max) lt->max = time; - if (time < lt->min || !lt->min) + if (time < lt->min || !lt->nr) lt->min = time; lt->total += time; @@ -177,8 +177,15 @@ static void lock_time_inc(struct lock_time *lt, u64 time) static inline void lock_time_add(struct lock_time *src, struct lock_time *dst) { - dst->min += src->min; - dst->max += src->max; + if (!src->nr) + return; + + if (src->max > dst->max) + dst->max = src->max; + + if (src->min < dst->min || !dst->nr) + dst->min = src->min; + dst->total += src->total; dst->nr += src->nr; } @@ -379,7 +386,8 @@ static int save_trace(struct stack_trace *trace) * complete trace that maxes out the entries provided will be reported * as incomplete, friggin useless </rant> */ - if (trace->entries[trace->nr_entries-1] == ULONG_MAX) + if (trace->nr_entries != 0 && + trace->entries[trace->nr_entries-1] == ULONG_MAX) trace->nr_entries--; trace->max_entries = trace->nr_entries; diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 6b7ddba..e73e53c 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -36,7 +36,7 @@ /* * Each CPU has a list of per CPU events: */ -DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context); +static DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context); int perf_max_events __read_mostly = 1; static int perf_reserved_percpu __read_mostly; @@ -476,7 +476,7 @@ static void perf_event_remove_from_context(struct perf_event *event) if (!task) { /* * Per cpu events are removed via an smp call and - * the removal is always sucessful. + * the removal is always successful. */ smp_call_function_single(event->cpu, __perf_event_remove_from_context, @@ -567,7 +567,7 @@ static void __perf_event_disable(void *info) * is the current context on this CPU and preemption is disabled, * hence we can't get into perf_event_task_sched_out for this context. */ -static void perf_event_disable(struct perf_event *event) +void perf_event_disable(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; struct task_struct *task = ctx->task; @@ -845,7 +845,7 @@ perf_install_in_context(struct perf_event_context *ctx, if (!task) { /* * Per cpu events are installed via an smp call and - * the install is always sucessful. + * the install is always successful. */ smp_call_function_single(cpu, __perf_install_in_context, event, 1); @@ -971,7 +971,7 @@ static void __perf_event_enable(void *info) * perf_event_for_each_child or perf_event_for_each as described * for perf_event_disable. */ -static void perf_event_enable(struct perf_event *event) +void perf_event_enable(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; struct task_struct *task = ctx->task; @@ -1579,7 +1579,6 @@ static void __perf_event_init_context(struct perf_event_context *ctx, struct task_struct *task) { - memset(ctx, 0, sizeof(*ctx)); spin_lock_init(&ctx->lock); mutex_init(&ctx->mutex); INIT_LIST_HEAD(&ctx->group_list); @@ -1654,7 +1653,7 @@ static struct perf_event_context *find_get_context(pid_t pid, int cpu) } if (!ctx) { - ctx = kmalloc(sizeof(struct perf_event_context), GFP_KERNEL); + ctx = kzalloc(sizeof(struct perf_event_context), GFP_KERNEL); err = -ENOMEM; if (!ctx) goto errout; @@ -4011,6 +4010,7 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) event->pmu->read(event); data.addr = 0; + data.raw = NULL; data.period = event->hw.last_period; regs = get_irq_regs(); /* @@ -4080,8 +4080,7 @@ static void cpu_clock_perf_event_update(struct perf_event *event) u64 now; now = cpu_clock(cpu); - prev = atomic64_read(&event->hw.prev_count); - atomic64_set(&event->hw.prev_count, now); + prev = atomic64_xchg(&event->hw.prev_count, now); atomic64_add(now - prev, &event->count); } @@ -4286,15 +4285,8 @@ static void bp_perf_event_destroy(struct perf_event *event) static const struct pmu *bp_perf_event_init(struct perf_event *bp) { int err; - /* - * The breakpoint is already filled if we haven't created the counter - * through perf syscall - * FIXME: manage to get trigerred to NULL if it comes from syscalls - */ - if (!bp->callback) - err = register_perf_hw_breakpoint(bp); - else - err = __register_perf_hw_breakpoint(bp); + + err = register_perf_hw_breakpoint(bp); if (err) return ERR_PTR(err); @@ -4308,6 +4300,7 @@ void perf_bp_event(struct perf_event *bp, void *data) struct perf_sample_data sample; struct pt_regs *regs = data; + sample.raw = NULL; sample.addr = bp->attr.bp_addr; if (!perf_exclude_event(bp, regs)) @@ -4390,7 +4383,7 @@ perf_event_alloc(struct perf_event_attr *attr, struct perf_event_context *ctx, struct perf_event *group_leader, struct perf_event *parent_event, - perf_callback_t callback, + perf_overflow_handler_t overflow_handler, gfp_t gfpflags) { const struct pmu *pmu; @@ -4433,10 +4426,10 @@ perf_event_alloc(struct perf_event_attr *attr, event->state = PERF_EVENT_STATE_INACTIVE; - if (!callback && parent_event) - callback = parent_event->callback; + if (!overflow_handler && parent_event) + overflow_handler = parent_event->overflow_handler; - event->callback = callback; + event->overflow_handler = overflow_handler; if (attr->disabled) event->state = PERF_EVENT_STATE_OFF; @@ -4776,7 +4769,8 @@ err_put_context: */ struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, - pid_t pid, perf_callback_t callback) + pid_t pid, + perf_overflow_handler_t overflow_handler) { struct perf_event *event; struct perf_event_context *ctx; @@ -4793,7 +4787,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, } event = perf_event_alloc(attr, cpu, ctx, NULL, - NULL, callback, GFP_KERNEL); + NULL, overflow_handler, GFP_KERNEL); if (IS_ERR(event)) { err = PTR_ERR(event); goto err_put_context; @@ -5090,7 +5084,7 @@ again: */ int perf_event_init_task(struct task_struct *child) { - struct perf_event_context *child_ctx, *parent_ctx; + struct perf_event_context *child_ctx = NULL, *parent_ctx; struct perf_event_context *cloned_ctx; struct perf_event *event; struct task_struct *parent = current; @@ -5106,20 +5100,6 @@ int perf_event_init_task(struct task_struct *child) return 0; /* - * This is executed from the parent task context, so inherit - * events that have been marked for cloning. - * First allocate and initialize a context for the child. - */ - - child_ctx = kmalloc(sizeof(struct perf_event_context), GFP_KERNEL); - if (!child_ctx) - return -ENOMEM; - - __perf_event_init_context(child_ctx, child); - child->perf_event_ctxp = child_ctx; - get_task_struct(child); - - /* * If the parent's context is a clone, pin it so it won't get * swapped under us. */ @@ -5149,6 +5129,26 @@ int perf_event_init_task(struct task_struct *child) continue; } + if (!child->perf_event_ctxp) { + /* + * This is executed from the parent task context, so + * inherit events that have been marked for cloning. + * First allocate and initialize a context for the + * child. + */ + + child_ctx = kzalloc(sizeof(struct perf_event_context), + GFP_KERNEL); + if (!child_ctx) { + ret = -ENOMEM; + goto exit; + } + + __perf_event_init_context(child_ctx, child); + child->perf_event_ctxp = child_ctx; + get_task_struct(child); + } + ret = inherit_group(event, parent, parent_ctx, child, child_ctx); if (ret) { @@ -5177,6 +5177,7 @@ int perf_event_init_task(struct task_struct *child) get_ctx(child_ctx->parent_ctx); } +exit: mutex_unlock(&parent_ctx->mutex); perf_unpin_context(parent_ctx); diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c index dfdec52..3db49b9 100644 --- a/kernel/pm_qos_params.c +++ b/kernel/pm_qos_params.c @@ -29,7 +29,6 @@ #include <linux/pm_qos_params.h> #include <linux/sched.h> -#include <linux/smp_lock.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/time.h> @@ -344,37 +343,33 @@ int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier) } EXPORT_SYMBOL_GPL(pm_qos_remove_notifier); -#define PID_NAME_LEN sizeof("process_1234567890") -static char name[PID_NAME_LEN]; +#define PID_NAME_LEN 32 static int pm_qos_power_open(struct inode *inode, struct file *filp) { int ret; long pm_qos_class; + char name[PID_NAME_LEN]; - lock_kernel(); pm_qos_class = find_pm_qos_object_by_minor(iminor(inode)); if (pm_qos_class >= 0) { filp->private_data = (void *)pm_qos_class; - sprintf(name, "process_%d", current->pid); + snprintf(name, PID_NAME_LEN, "process_%d", current->pid); ret = pm_qos_add_requirement(pm_qos_class, name, PM_QOS_DEFAULT_VALUE); - if (ret >= 0) { - unlock_kernel(); + if (ret >= 0) return 0; - } } - unlock_kernel(); - return -EPERM; } static int pm_qos_power_release(struct inode *inode, struct file *filp) { int pm_qos_class; + char name[PID_NAME_LEN]; pm_qos_class = (long)filp->private_data; - sprintf(name, "process_%d", current->pid); + snprintf(name, PID_NAME_LEN, "process_%d", current->pid); pm_qos_remove_requirement(pm_qos_class, name); return 0; @@ -385,13 +380,14 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf, { s32 value; int pm_qos_class; + char name[PID_NAME_LEN]; pm_qos_class = (long)filp->private_data; if (count != sizeof(s32)) return -EINVAL; if (copy_from_user(&value, buf, sizeof(s32))) return -EFAULT; - sprintf(name, "process_%d", current->pid); + snprintf(name, PID_NAME_LEN, "process_%d", current->pid); pm_qos_update_requirement(pm_qos_class, name, value); return sizeof(s32); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 5c9dc22..438ff45 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -384,7 +384,8 @@ int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp) /* * Validate the clockid_t for a new CPU-clock timer, and initialize the timer. - * This is called from sys_timer_create with the new timer already locked. + * This is called from sys_timer_create() and do_cpu_nanosleep() with the + * new timer already all-zeros initialized. */ int posix_cpu_timer_create(struct k_itimer *new_timer) { @@ -396,8 +397,6 @@ int posix_cpu_timer_create(struct k_itimer *new_timer) return -EINVAL; INIT_LIST_HEAD(&new_timer->it.cpu.entry); - new_timer->it.cpu.incr.sched = 0; - new_timer->it.cpu.expires.sched = 0; read_lock(&tasklist_lock); if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) { diff --git a/kernel/power/Makefile b/kernel/power/Makefile index c3b81c3..4319181 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_PM_SLEEP) += console.o obj-$(CONFIG_FREEZER) += process.o obj-$(CONFIG_SUSPEND) += suspend.o obj-$(CONFIG_PM_TEST_SUSPEND) += suspend_test.o -obj-$(CONFIG_HIBERNATION) += swsusp.o hibernate.o snapshot.o swap.o user.o +obj-$(CONFIG_HIBERNATION) += hibernate.o snapshot.o swap.o user.o obj-$(CONFIG_HIBERNATION_NVS) += hibernate_nvs.o obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 04a9e90..bbfe472 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -32,6 +32,7 @@ static int noresume = 0; static char resume_file[256] = CONFIG_PM_STD_PARTITION; dev_t swsusp_resume_device; sector_t swsusp_resume_block; +int in_suspend __nosavedata = 0; enum { HIBERNATION_INVALID, @@ -202,6 +203,35 @@ static void platform_recover(int platform_mode) } /** + * swsusp_show_speed - print the time elapsed between two events. + * @start: Starting event. + * @stop: Final event. + * @nr_pages - number of pages processed between @start and @stop + * @msg - introductory message to print + */ + +void swsusp_show_speed(struct timeval *start, struct timeval *stop, + unsigned nr_pages, char *msg) +{ + s64 elapsed_centisecs64; + int centisecs; + int k; + int kps; + + elapsed_centisecs64 = timeval_to_ns(stop) - timeval_to_ns(start); + do_div(elapsed_centisecs64, NSEC_PER_SEC / 100); + centisecs = elapsed_centisecs64; + if (centisecs == 0) + centisecs = 1; /* avoid div-by-zero */ + k = nr_pages * (PAGE_SIZE / 1024); + kps = (k * 100) / centisecs; + printk(KERN_INFO "PM: %s %d kbytes in %d.%02d seconds (%d.%02d MB/s)\n", + msg, k, + centisecs / 100, centisecs % 100, + kps / 1000, (kps % 1000) / 10); +} + +/** * create_image - freeze devices that need to be frozen with interrupts * off, create the hibernation image and thaw those devices. Control * reappears in this routine after a restore. diff --git a/kernel/power/main.c b/kernel/power/main.c index 347d2cc..0998c71 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -220,6 +220,7 @@ static struct attribute_group attr_group = { #ifdef CONFIG_PM_RUNTIME struct workqueue_struct *pm_wq; +EXPORT_SYMBOL_GPL(pm_wq); static int __init pm_start_workqueue(void) { diff --git a/kernel/power/process.c b/kernel/power/process.c index cc2e553..5ade1bd 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/syscalls.h> #include <linux/freezer.h> +#include <linux/delay.h> /* * Timeout for stopping processes @@ -41,7 +42,7 @@ static int try_to_freeze_tasks(bool sig_only) do_gettimeofday(&start); end_time = jiffies + TIMEOUT; - do { + while (true) { todo = 0; read_lock(&tasklist_lock); do_each_thread(g, p) { @@ -62,10 +63,15 @@ static int try_to_freeze_tasks(bool sig_only) todo++; } while_each_thread(g, p); read_unlock(&tasklist_lock); - yield(); /* Yield is okay here */ - if (time_after(jiffies, end_time)) + if (!todo || time_after(jiffies, end_time)) break; - } while (todo); + + /* + * We need to retry, but first give the freezing tasks some + * time to enter the regrigerator. + */ + msleep(10); + } do_gettimeofday(&end); elapsed_csecs64 = timeval_to_ns(&end) - timeval_to_ns(&start); diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 890f6b1..09b2b0a 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -38,6 +38,107 @@ struct swsusp_header { static struct swsusp_header *swsusp_header; +/** + * The following functions are used for tracing the allocated + * swap pages, so that they can be freed in case of an error. + */ + +struct swsusp_extent { + struct rb_node node; + unsigned long start; + unsigned long end; +}; + +static struct rb_root swsusp_extents = RB_ROOT; + +static int swsusp_extents_insert(unsigned long swap_offset) +{ + struct rb_node **new = &(swsusp_extents.rb_node); + struct rb_node *parent = NULL; + struct swsusp_extent *ext; + + /* Figure out where to put the new node */ + while (*new) { + ext = container_of(*new, struct swsusp_extent, node); + parent = *new; + if (swap_offset < ext->start) { + /* Try to merge */ + if (swap_offset == ext->start - 1) { + ext->start--; + return 0; + } + new = &((*new)->rb_left); + } else if (swap_offset > ext->end) { + /* Try to merge */ + if (swap_offset == ext->end + 1) { + ext->end++; + return 0; + } + new = &((*new)->rb_right); + } else { + /* It already is in the tree */ + return -EINVAL; + } + } + /* Add the new node and rebalance the tree. */ + ext = kzalloc(sizeof(struct swsusp_extent), GFP_KERNEL); + if (!ext) + return -ENOMEM; + + ext->start = swap_offset; + ext->end = swap_offset; + rb_link_node(&ext->node, parent, new); + rb_insert_color(&ext->node, &swsusp_extents); + return 0; +} + +/** + * alloc_swapdev_block - allocate a swap page and register that it has + * been allocated, so that it can be freed in case of an error. + */ + +sector_t alloc_swapdev_block(int swap) +{ + unsigned long offset; + + offset = swp_offset(get_swap_page_of_type(swap)); + if (offset) { + if (swsusp_extents_insert(offset)) + swap_free(swp_entry(swap, offset)); + else + return swapdev_block(swap, offset); + } + return 0; +} + +/** + * free_all_swap_pages - free swap pages allocated for saving image data. + * It also frees the extents used to register which swap entres had been + * allocated. + */ + +void free_all_swap_pages(int swap) +{ + struct rb_node *node; + + while ((node = swsusp_extents.rb_node)) { + struct swsusp_extent *ext; + unsigned long offset; + + ext = container_of(node, struct swsusp_extent, node); + rb_erase(node, &swsusp_extents); + for (offset = ext->start; offset <= ext->end; offset++) + swap_free(swp_entry(swap, offset)); + + kfree(ext); + } +} + +int swsusp_swap_in_use(void) +{ + return (swsusp_extents.rb_node != NULL); +} + /* * General things */ @@ -336,7 +437,7 @@ static int save_image(struct swap_map_handle *handle, if (ret) break; if (!(nr_pages % m)) - printk("\b\b\b\b%3d%%", nr_pages / m); + printk(KERN_CONT "\b\b\b\b%3d%%", nr_pages / m); nr_pages++; } err2 = wait_on_bio_chain(&bio); @@ -344,9 +445,9 @@ static int save_image(struct swap_map_handle *handle, if (!ret) ret = err2; if (!ret) - printk("\b\b\b\bdone\n"); + printk(KERN_CONT "\b\b\b\bdone\n"); else - printk("\n"); + printk(KERN_CONT "\n"); swsusp_show_speed(&start, &stop, nr_to_write, "Wrote"); return ret; } diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c index 6a07f4d..5b3601b 100644 --- a/kernel/power/swsusp.c +++ b/kernel/power/swsusp.c @@ -56,133 +56,3 @@ #include "power.h" int in_suspend __nosavedata = 0; - -/** - * The following functions are used for tracing the allocated - * swap pages, so that they can be freed in case of an error. - */ - -struct swsusp_extent { - struct rb_node node; - unsigned long start; - unsigned long end; -}; - -static struct rb_root swsusp_extents = RB_ROOT; - -static int swsusp_extents_insert(unsigned long swap_offset) -{ - struct rb_node **new = &(swsusp_extents.rb_node); - struct rb_node *parent = NULL; - struct swsusp_extent *ext; - - /* Figure out where to put the new node */ - while (*new) { - ext = container_of(*new, struct swsusp_extent, node); - parent = *new; - if (swap_offset < ext->start) { - /* Try to merge */ - if (swap_offset == ext->start - 1) { - ext->start--; - return 0; - } - new = &((*new)->rb_left); - } else if (swap_offset > ext->end) { - /* Try to merge */ - if (swap_offset == ext->end + 1) { - ext->end++; - return 0; - } - new = &((*new)->rb_right); - } else { - /* It already is in the tree */ - return -EINVAL; - } - } - /* Add the new node and rebalance the tree. */ - ext = kzalloc(sizeof(struct swsusp_extent), GFP_KERNEL); - if (!ext) - return -ENOMEM; - - ext->start = swap_offset; - ext->end = swap_offset; - rb_link_node(&ext->node, parent, new); - rb_insert_color(&ext->node, &swsusp_extents); - return 0; -} - -/** - * alloc_swapdev_block - allocate a swap page and register that it has - * been allocated, so that it can be freed in case of an error. - */ - -sector_t alloc_swapdev_block(int swap) -{ - unsigned long offset; - - offset = swp_offset(get_swap_page_of_type(swap)); - if (offset) { - if (swsusp_extents_insert(offset)) - swap_free(swp_entry(swap, offset)); - else - return swapdev_block(swap, offset); - } - return 0; -} - -/** - * free_all_swap_pages - free swap pages allocated for saving image data. - * It also frees the extents used to register which swap entres had been - * allocated. - */ - -void free_all_swap_pages(int swap) -{ - struct rb_node *node; - - while ((node = swsusp_extents.rb_node)) { - struct swsusp_extent *ext; - unsigned long offset; - - ext = container_of(node, struct swsusp_extent, node); - rb_erase(node, &swsusp_extents); - for (offset = ext->start; offset <= ext->end; offset++) - swap_free(swp_entry(swap, offset)); - - kfree(ext); - } -} - -int swsusp_swap_in_use(void) -{ - return (swsusp_extents.rb_node != NULL); -} - -/** - * swsusp_show_speed - print the time elapsed between two events represented by - * @start and @stop - * - * @nr_pages - number of pages processed between @start and @stop - * @msg - introductory message to print - */ - -void swsusp_show_speed(struct timeval *start, struct timeval *stop, - unsigned nr_pages, char *msg) -{ - s64 elapsed_centisecs64; - int centisecs; - int k; - int kps; - - elapsed_centisecs64 = timeval_to_ns(stop) - timeval_to_ns(start); - do_div(elapsed_centisecs64, NSEC_PER_SEC / 100); - centisecs = elapsed_centisecs64; - if (centisecs == 0) - centisecs = 1; /* avoid div-by-zero */ - k = nr_pages * (PAGE_SIZE / 1024); - kps = (k * 100) / centisecs; - printk(KERN_INFO "PM: %s %d kbytes in %d.%02d seconds (%d.%02d MB/s)\n", - msg, k, - centisecs / 100, centisecs % 100, - kps / 1000, (kps % 1000) / 10); -} diff --git a/kernel/resource.c b/kernel/resource.c index fb11a58..dc15686 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -308,35 +308,37 @@ static int find_resource(struct resource *root, struct resource *new, void *alignf_data) { struct resource *this = root->child; + resource_size_t start, end; - new->start = root->start; + start = root->start; /* * Skip past an allocated resource that starts at 0, since the assignment * of this->start - 1 to new->end below would cause an underflow. */ if (this && this->start == 0) { - new->start = this->end + 1; + start = this->end + 1; this = this->sibling; } for(;;) { if (this) - new->end = this->start - 1; + end = this->start - 1; else - new->end = root->end; - if (new->start < min) - new->start = min; - if (new->end > max) - new->end = max; - new->start = ALIGN(new->start, align); + end = root->end; + if (start < min) + start = min; + if (end > max) + end = max; + start = ALIGN(start, align); if (alignf) alignf(alignf_data, new, size, align); - if (new->start < new->end && new->end - new->start >= size - 1) { - new->end = new->start + size - 1; + if (start < end && end - start >= size - 1) { + new->start = start; + new->end = start + size - 1; return 0; } if (!this) break; - new->start = this->end + 1; + start = this->end + 1; this = this->sibling; } return -EBUSY; diff --git a/kernel/sched.c b/kernel/sched.c index bc68037..ff39cad 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -7449,17 +7449,16 @@ static struct ctl_table sd_ctl_dir[] = { .procname = "sched_domain", .mode = 0555, }, - {0, }, + {} }; static struct ctl_table sd_ctl_root[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, .child = sd_ctl_dir, }, - {0, }, + {} }; static struct ctl_table *sd_alloc_ctl_entry(int n) diff --git a/kernel/slow-work.c b/kernel/slow-work.c index 00889bd..7494bbf 100644 --- a/kernel/slow-work.c +++ b/kernel/slow-work.c @@ -49,7 +49,6 @@ static const int slow_work_max_vslow = 99; ctl_table slow_work_sysctls[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "min-threads", .data = &slow_work_min_threads, .maxlen = sizeof(unsigned), @@ -59,7 +58,6 @@ ctl_table slow_work_sysctls[] = { .extra2 = &slow_work_max_threads, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "max-threads", .data = &slow_work_max_threads, .maxlen = sizeof(unsigned), @@ -69,16 +67,15 @@ ctl_table slow_work_sysctls[] = { .extra2 = (void *) &slow_work_max_max_threads, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "vslow-percentage", .data = &vslow_work_proportion, .maxlen = sizeof(unsigned), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = (void *) &slow_work_min_vslow, .extra2 = (void *) &slow_work_max_vslow, }, - { .ctl_name = 0 } + {} }; #endif diff --git a/kernel/sys.c b/kernel/sys.c index 9968c5f..585d6cd 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -8,7 +8,6 @@ #include <linux/mm.h> #include <linux/utsname.h> #include <linux/mman.h> -#include <linux/smp_lock.h> #include <linux/notifier.h> #include <linux/reboot.h> #include <linux/prctl.h> @@ -349,6 +348,9 @@ void kernel_power_off(void) machine_power_off(); } EXPORT_SYMBOL_GPL(kernel_power_off); + +static DEFINE_MUTEX(reboot_mutex); + /* * Reboot system call: for obvious reasons only root may call it, * and even root needs to set up some magic numbers in the registers @@ -381,7 +383,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off) cmd = LINUX_REBOOT_CMD_HALT; - lock_kernel(); + mutex_lock(&reboot_mutex); switch (cmd) { case LINUX_REBOOT_CMD_RESTART: kernel_restart(NULL); @@ -397,20 +399,18 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, case LINUX_REBOOT_CMD_HALT: kernel_halt(); - unlock_kernel(); do_exit(0); panic("cannot halt"); case LINUX_REBOOT_CMD_POWER_OFF: kernel_power_off(); - unlock_kernel(); do_exit(0); break; case LINUX_REBOOT_CMD_RESTART2: if (strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1) < 0) { - unlock_kernel(); - return -EFAULT; + ret = -EFAULT; + break; } buffer[sizeof(buffer) - 1] = '\0'; @@ -433,7 +433,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, ret = -EINVAL; break; } - unlock_kernel(); + mutex_unlock(&reboot_mutex); return ret; } diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index e06d0b8..695384f 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -48,8 +48,10 @@ cond_syscall(sys_shutdown); cond_syscall(sys_sendmsg); cond_syscall(compat_sys_sendmsg); cond_syscall(sys_recvmsg); +cond_syscall(sys_recvmmsg); cond_syscall(compat_sys_recvmsg); cond_syscall(compat_sys_recvfrom); +cond_syscall(compat_sys_recvmmsg); cond_syscall(sys_socketcall); cond_syscall(sys_futex); cond_syscall(compat_sys_futex); @@ -139,7 +141,6 @@ cond_syscall(sys_pciconfig_read); cond_syscall(sys_pciconfig_write); cond_syscall(sys_pciconfig_iobase); cond_syscall(sys32_ipc); -cond_syscall(sys32_sysctl); cond_syscall(ppc_rtas); cond_syscall(sys_spu_run); cond_syscall(sys_spu_create); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b9e5a45..554ac48 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -27,7 +27,6 @@ #include <linux/security.h> #include <linux/ctype.h> #include <linux/kmemcheck.h> -#include <linux/smp_lock.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> @@ -61,7 +60,6 @@ #include <asm/io.h> #endif -static int deprecated_sysctl_warning(struct __sysctl_args *args); #if defined(CONFIG_SYSCTL) @@ -210,31 +208,26 @@ extern int lock_stat; static struct ctl_table root_table[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, .child = kern_table, }, { - .ctl_name = CTL_VM, .procname = "vm", .mode = 0555, .child = vm_table, }, { - .ctl_name = CTL_FS, .procname = "fs", .mode = 0555, .child = fs_table, }, { - .ctl_name = CTL_DEBUG, .procname = "debug", .mode = 0555, .child = debug_table, }, { - .ctl_name = CTL_DEV, .procname = "dev", .mode = 0555, .child = dev_table, @@ -243,7 +236,7 @@ static struct ctl_table root_table[] = { * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt */ - { .ctl_name = 0 } + { } }; #ifdef CONFIG_SCHED_DEBUG @@ -259,198 +252,170 @@ static int max_sched_shares_ratelimit = NSEC_PER_SEC; /* 1 second */ static struct ctl_table kern_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_child_runs_first", .data = &sysctl_sched_child_runs_first, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_SCHED_DEBUG { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_min_granularity_ns", .data = &sysctl_sched_min_granularity, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &sched_proc_update_handler, - .strategy = &sysctl_intvec, + .proc_handler = sched_proc_update_handler, .extra1 = &min_sched_granularity_ns, .extra2 = &max_sched_granularity_ns, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_latency_ns", .data = &sysctl_sched_latency, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &sched_proc_update_handler, - .strategy = &sysctl_intvec, + .proc_handler = sched_proc_update_handler, .extra1 = &min_sched_granularity_ns, .extra2 = &max_sched_granularity_ns, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_wakeup_granularity_ns", .data = &sysctl_sched_wakeup_granularity, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &sched_proc_update_handler, - .strategy = &sysctl_intvec, + .proc_handler = sched_proc_update_handler, .extra1 = &min_wakeup_granularity_ns, .extra2 = &max_wakeup_granularity_ns, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_shares_ratelimit", .data = &sysctl_sched_shares_ratelimit, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &sched_proc_update_handler, + .proc_handler = sched_proc_update_handler, .extra1 = &min_sched_shares_ratelimit, .extra2 = &max_sched_shares_ratelimit, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_tunable_scaling", .data = &sysctl_sched_tunable_scaling, .maxlen = sizeof(enum sched_tunable_scaling), .mode = 0644, - .proc_handler = &sched_proc_update_handler, - .strategy = &sysctl_intvec, + .proc_handler = sched_proc_update_handler, .extra1 = &min_sched_tunable_scaling, .extra2 = &max_sched_tunable_scaling, }, - { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_shares_thresh", .data = &sysctl_sched_shares_thresh, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_migration_cost", .data = &sysctl_sched_migration_cost, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_nr_migrate", .data = &sysctl_sched_nr_migrate, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_time_avg", .data = &sysctl_sched_time_avg, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "timer_migration", .data = &sysctl_timer_migration, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, #endif { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_rt_period_us", .data = &sysctl_sched_rt_period, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &sched_rt_handler, + .proc_handler = sched_rt_handler, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_rt_runtime_us", .data = &sysctl_sched_rt_runtime, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &sched_rt_handler, + .proc_handler = sched_rt_handler, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_compat_yield", .data = &sysctl_sched_compat_yield, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_PROVE_LOCKING { - .ctl_name = CTL_UNNUMBERED, .procname = "prove_locking", .data = &prove_locking, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_LOCK_STAT { - .ctl_name = CTL_UNNUMBERED, .procname = "lock_stat", .data = &lock_stat, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { - .ctl_name = KERN_PANIC, .procname = "panic", .data = &panic_timeout, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_CORE_USES_PID, .procname = "core_uses_pid", .data = &core_uses_pid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_CORE_PATTERN, .procname = "core_pattern", .data = core_pattern, .maxlen = CORENAME_MAX_SIZE, .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, + .proc_handler = proc_dostring, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "core_pipe_limit", .data = &core_pipe_limit, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_PROC_SYSCTL { .procname = "tainted", .maxlen = sizeof(long), .mode = 0644, - .proc_handler = &proc_taint, + .proc_handler = proc_taint, }, #endif #ifdef CONFIG_LATENCYTOP @@ -459,181 +424,160 @@ static struct ctl_table kern_table[] = { .data = &latencytop_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_BLK_DEV_INITRD { - .ctl_name = KERN_REALROOTDEV, .procname = "real-root-dev", .data = &real_root_dev, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { - .ctl_name = CTL_UNNUMBERED, .procname = "print-fatal-signals", .data = &print_fatal_signals, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_SPARC { - .ctl_name = KERN_SPARC_REBOOT, .procname = "reboot-cmd", .data = reboot_command, .maxlen = 256, .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, + .proc_handler = proc_dostring, }, { - .ctl_name = KERN_SPARC_STOP_A, .procname = "stop-a", .data = &stop_a_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_SPARC_SCONS_PWROFF, .procname = "scons-poweroff", .data = &scons_pwroff, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_SPARC64 { - .ctl_name = CTL_UNNUMBERED, .procname = "tsb-ratio", .data = &sysctl_tsb_ratio, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef __hppa__ { - .ctl_name = KERN_HPPA_PWRSW, .procname = "soft-power", .data = &pwrsw_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_HPPA_UNALIGNED, .procname = "unaligned-trap", .data = &unaligned_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { - .ctl_name = KERN_CTLALTDEL, .procname = "ctrl-alt-del", .data = &C_A_D, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_FUNCTION_TRACER { - .ctl_name = CTL_UNNUMBERED, .procname = "ftrace_enabled", .data = &ftrace_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &ftrace_enable_sysctl, + .proc_handler = ftrace_enable_sysctl, }, #endif #ifdef CONFIG_STACK_TRACER { - .ctl_name = CTL_UNNUMBERED, .procname = "stack_tracer_enabled", .data = &stack_tracer_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &stack_trace_sysctl, + .proc_handler = stack_trace_sysctl, }, #endif #ifdef CONFIG_TRACING { - .ctl_name = CTL_UNNUMBERED, .procname = "ftrace_dump_on_oops", .data = &ftrace_dump_on_oops, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_MODULES { - .ctl_name = KERN_MODPROBE, .procname = "modprobe", .data = &modprobe_path, .maxlen = KMOD_PATH_LEN, .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, + .proc_handler = proc_dostring, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "modules_disabled", .data = &modules_disabled, .maxlen = sizeof(int), .mode = 0644, /* only handle a transition from default "0" to "1" */ - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = &one, .extra2 = &one, }, #endif #if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET) { - .ctl_name = KERN_HOTPLUG, .procname = "hotplug", .data = &uevent_helper, .maxlen = UEVENT_HELPER_PATH_LEN, .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, + .proc_handler = proc_dostring, }, #endif #ifdef CONFIG_CHR_DEV_SG { - .ctl_name = KERN_SG_BIG_BUFF, .procname = "sg-big-buff", .data = &sg_big_buff, .maxlen = sizeof (int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_BSD_PROCESS_ACCT { - .ctl_name = KERN_ACCT, .procname = "acct", .data = &acct_parm, .maxlen = 3*sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_MAGIC_SYSRQ { - .ctl_name = KERN_SYSRQ, .procname = "sysrq", .data = &__sysrq_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_PROC_SYSCTL @@ -642,215 +586,188 @@ static struct ctl_table kern_table[] = { .data = NULL, .maxlen = sizeof (int), .mode = 0600, - .proc_handler = &proc_do_cad_pid, + .proc_handler = proc_do_cad_pid, }, #endif { - .ctl_name = KERN_MAX_THREADS, .procname = "threads-max", .data = &max_threads, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_RANDOM, .procname = "random", .mode = 0555, .child = random_table, }, { - .ctl_name = KERN_OVERFLOWUID, .procname = "overflowuid", .data = &overflowuid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &minolduid, .extra2 = &maxolduid, }, { - .ctl_name = KERN_OVERFLOWGID, .procname = "overflowgid", .data = &overflowgid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &minolduid, .extra2 = &maxolduid, }, #ifdef CONFIG_S390 #ifdef CONFIG_MATHEMU { - .ctl_name = KERN_IEEE_EMULATION_WARNINGS, .procname = "ieee_emulation_warnings", .data = &sysctl_ieee_emulation_warnings, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { - .ctl_name = KERN_S390_USER_DEBUG_LOGGING, .procname = "userprocess_debug", .data = &sysctl_userprocess_debug, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { - .ctl_name = KERN_PIDMAX, .procname = "pid_max", .data = &pid_max, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &pid_max_min, .extra2 = &pid_max_max, }, { - .ctl_name = KERN_PANIC_ON_OOPS, .procname = "panic_on_oops", .data = &panic_on_oops, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #if defined CONFIG_PRINTK { - .ctl_name = KERN_PRINTK, .procname = "printk", .data = &console_loglevel, .maxlen = 4*sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_PRINTK_RATELIMIT, .procname = "printk_ratelimit", .data = &printk_ratelimit_state.interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = KERN_PRINTK_RATELIMIT_BURST, .procname = "printk_ratelimit_burst", .data = &printk_ratelimit_state.burst, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "printk_delay", .data = &printk_delay_msec, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &ten_thousand, }, #endif { - .ctl_name = KERN_NGROUPS_MAX, .procname = "ngroups_max", .data = &ngroups_max, .maxlen = sizeof (int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) { - .ctl_name = KERN_UNKNOWN_NMI_PANIC, .procname = "unknown_nmi_panic", .data = &unknown_nmi_panic, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .procname = "nmi_watchdog", .data = &nmi_watchdog_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_nmi_enabled, + .proc_handler = proc_nmi_enabled, }, #endif #if defined(CONFIG_X86) { - .ctl_name = KERN_PANIC_ON_NMI, .procname = "panic_on_unrecovered_nmi", .data = &panic_on_unrecovered_nmi, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "panic_on_io_nmi", .data = &panic_on_io_nmi, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_BOOTLOADER_TYPE, .procname = "bootloader_type", .data = &bootloader_type, .maxlen = sizeof (int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "bootloader_version", .data = &bootloader_version, .maxlen = sizeof (int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "kstack_depth_to_print", .data = &kstack_depth_to_print, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "io_delay_type", .data = &io_delay_type, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #if defined(CONFIG_MMU) { - .ctl_name = KERN_RANDOMIZE, .procname = "randomize_va_space", .data = &randomize_va_space, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #if defined(CONFIG_S390) && defined(CONFIG_SMP) { - .ctl_name = KERN_SPIN_RETRY, .procname = "spin_retry", .data = &spin_retry, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #if defined(CONFIG_ACPI_SLEEP) && defined(CONFIG_X86) @@ -859,123 +776,104 @@ static struct ctl_table kern_table[] = { .data = &acpi_realmode_flags, .maxlen = sizeof (unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, }, #endif #ifdef CONFIG_IA64 { - .ctl_name = KERN_IA64_UNALIGNED, .procname = "ignore-unaligned-usertrap", .data = &no_unaligned_warning, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "unaligned-dump-stack", .data = &unaligned_dump_stack, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_DETECT_SOFTLOCKUP { - .ctl_name = CTL_UNNUMBERED, .procname = "softlockup_panic", .data = &softlockup_panic, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "softlockup_thresh", .data = &softlockup_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dosoftlockup_thresh, - .strategy = &sysctl_intvec, + .proc_handler = proc_dosoftlockup_thresh, .extra1 = &neg_one, .extra2 = &sixty, }, #endif #ifdef CONFIG_DETECT_HUNG_TASK { - .ctl_name = CTL_UNNUMBERED, .procname = "hung_task_panic", .data = &sysctl_hung_task_panic, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "hung_task_check_count", .data = &sysctl_hung_task_check_count, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_doulongvec_minmax, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "hung_task_timeout_secs", .data = &sysctl_hung_task_timeout_secs, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_dohung_task_timeout_secs, - .strategy = &sysctl_intvec, + .proc_handler = proc_dohung_task_timeout_secs, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "hung_task_warnings", .data = &sysctl_hung_task_warnings, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_doulongvec_minmax, }, #endif #ifdef CONFIG_COMPAT { - .ctl_name = KERN_COMPAT_LOG, .procname = "compat-log", .data = &compat_log, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_RT_MUTEXES { - .ctl_name = KERN_MAX_LOCK_DEPTH, .procname = "max_lock_depth", .data = &max_lock_depth, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { - .ctl_name = CTL_UNNUMBERED, .procname = "poweroff_cmd", .data = &poweroff_cmd, .maxlen = POWEROFF_CMD_PATH_LEN, .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, + .proc_handler = proc_dostring, }, #ifdef CONFIG_KEYS { - .ctl_name = CTL_UNNUMBERED, .procname = "keys", .mode = 0555, .child = key_sysctls, @@ -983,17 +881,15 @@ static struct ctl_table kern_table[] = { #endif #ifdef CONFIG_RCU_TORTURE_TEST { - .ctl_name = CTL_UNNUMBERED, .procname = "rcutorture_runnable", .data = &rcutorture_runnable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_SLOW_WORK { - .ctl_name = CTL_UNNUMBERED, .procname = "slow-work", .mode = 0555, .child = slow_work_sysctls, @@ -1001,146 +897,127 @@ static struct ctl_table kern_table[] = { #endif #ifdef CONFIG_PERF_EVENTS { - .ctl_name = CTL_UNNUMBERED, .procname = "perf_event_paranoid", .data = &sysctl_perf_event_paranoid, .maxlen = sizeof(sysctl_perf_event_paranoid), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "perf_event_mlock_kb", .data = &sysctl_perf_event_mlock, .maxlen = sizeof(sysctl_perf_event_mlock), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "perf_event_max_sample_rate", .data = &sysctl_perf_event_sample_rate, .maxlen = sizeof(sysctl_perf_event_sample_rate), .mode = 0644, - .proc_handler = &proc_dointvec, + .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, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_BLOCK { - .ctl_name = CTL_UNNUMBERED, .procname = "blk_iopoll", .data = &blk_iopoll_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt */ - { .ctl_name = 0 } + { } }; static struct ctl_table vm_table[] = { { - .ctl_name = VM_OVERCOMMIT_MEMORY, .procname = "overcommit_memory", .data = &sysctl_overcommit_memory, .maxlen = sizeof(sysctl_overcommit_memory), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = VM_PANIC_ON_OOM, .procname = "panic_on_oom", .data = &sysctl_panic_on_oom, .maxlen = sizeof(sysctl_panic_on_oom), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "oom_kill_allocating_task", .data = &sysctl_oom_kill_allocating_task, .maxlen = sizeof(sysctl_oom_kill_allocating_task), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "oom_dump_tasks", .data = &sysctl_oom_dump_tasks, .maxlen = sizeof(sysctl_oom_dump_tasks), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = VM_OVERCOMMIT_RATIO, .procname = "overcommit_ratio", .data = &sysctl_overcommit_ratio, .maxlen = sizeof(sysctl_overcommit_ratio), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = VM_PAGE_CLUSTER, .procname = "page-cluster", .data = &page_cluster, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = VM_DIRTY_BACKGROUND, .procname = "dirty_background_ratio", .data = &dirty_background_ratio, .maxlen = sizeof(dirty_background_ratio), .mode = 0644, - .proc_handler = &dirty_background_ratio_handler, - .strategy = &sysctl_intvec, + .proc_handler = dirty_background_ratio_handler, .extra1 = &zero, .extra2 = &one_hundred, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "dirty_background_bytes", .data = &dirty_background_bytes, .maxlen = sizeof(dirty_background_bytes), .mode = 0644, - .proc_handler = &dirty_background_bytes_handler, - .strategy = &sysctl_intvec, + .proc_handler = dirty_background_bytes_handler, .extra1 = &one_ul, }, { - .ctl_name = VM_DIRTY_RATIO, .procname = "dirty_ratio", .data = &vm_dirty_ratio, .maxlen = sizeof(vm_dirty_ratio), .mode = 0644, - .proc_handler = &dirty_ratio_handler, - .strategy = &sysctl_intvec, + .proc_handler = dirty_ratio_handler, .extra1 = &zero, .extra2 = &one_hundred, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "dirty_bytes", .data = &vm_dirty_bytes, .maxlen = sizeof(vm_dirty_bytes), .mode = 0644, - .proc_handler = &dirty_bytes_handler, - .strategy = &sysctl_intvec, + .proc_handler = dirty_bytes_handler, .extra1 = &dirty_bytes_min, }, { @@ -1148,31 +1025,28 @@ static struct ctl_table vm_table[] = { .data = &dirty_writeback_interval, .maxlen = sizeof(dirty_writeback_interval), .mode = 0644, - .proc_handler = &dirty_writeback_centisecs_handler, + .proc_handler = dirty_writeback_centisecs_handler, }, { .procname = "dirty_expire_centisecs", .data = &dirty_expire_interval, .maxlen = sizeof(dirty_expire_interval), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = VM_NR_PDFLUSH_THREADS, .procname = "nr_pdflush_threads", .data = &nr_pdflush_threads, .maxlen = sizeof nr_pdflush_threads, .mode = 0444 /* read-only*/, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = VM_SWAPPINESS, .procname = "swappiness", .data = &vm_swappiness, .maxlen = sizeof(vm_swappiness), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one_hundred, }, @@ -1182,255 +1056,213 @@ static struct ctl_table vm_table[] = { .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &hugetlb_sysctl_handler, + .proc_handler = hugetlb_sysctl_handler, .extra1 = (void *)&hugetlb_zero, .extra2 = (void *)&hugetlb_infinity, }, { - .ctl_name = VM_HUGETLB_GROUP, .procname = "hugetlb_shm_group", .data = &sysctl_hugetlb_shm_group, .maxlen = sizeof(gid_t), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "hugepages_treat_as_movable", .data = &hugepages_treat_as_movable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &hugetlb_treat_movable_handler, + .proc_handler = hugetlb_treat_movable_handler, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nr_overcommit_hugepages", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &hugetlb_overcommit_handler, + .proc_handler = hugetlb_overcommit_handler, .extra1 = (void *)&hugetlb_zero, .extra2 = (void *)&hugetlb_infinity, }, #endif { - .ctl_name = VM_LOWMEM_RESERVE_RATIO, .procname = "lowmem_reserve_ratio", .data = &sysctl_lowmem_reserve_ratio, .maxlen = sizeof(sysctl_lowmem_reserve_ratio), .mode = 0644, - .proc_handler = &lowmem_reserve_ratio_sysctl_handler, - .strategy = &sysctl_intvec, + .proc_handler = lowmem_reserve_ratio_sysctl_handler, }, { - .ctl_name = VM_DROP_PAGECACHE, .procname = "drop_caches", .data = &sysctl_drop_caches, .maxlen = sizeof(int), .mode = 0644, .proc_handler = drop_caches_sysctl_handler, - .strategy = &sysctl_intvec, }, { - .ctl_name = VM_MIN_FREE_KBYTES, .procname = "min_free_kbytes", .data = &min_free_kbytes, .maxlen = sizeof(min_free_kbytes), .mode = 0644, - .proc_handler = &min_free_kbytes_sysctl_handler, - .strategy = &sysctl_intvec, + .proc_handler = min_free_kbytes_sysctl_handler, .extra1 = &zero, }, { - .ctl_name = VM_PERCPU_PAGELIST_FRACTION, .procname = "percpu_pagelist_fraction", .data = &percpu_pagelist_fraction, .maxlen = sizeof(percpu_pagelist_fraction), .mode = 0644, - .proc_handler = &percpu_pagelist_fraction_sysctl_handler, - .strategy = &sysctl_intvec, + .proc_handler = percpu_pagelist_fraction_sysctl_handler, .extra1 = &min_percpu_pagelist_fract, }, #ifdef CONFIG_MMU { - .ctl_name = VM_MAX_MAP_COUNT, .procname = "max_map_count", .data = &sysctl_max_map_count, .maxlen = sizeof(sysctl_max_map_count), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, #else { - .ctl_name = CTL_UNNUMBERED, .procname = "nr_trim_pages", .data = &sysctl_nr_trim_pages, .maxlen = sizeof(sysctl_nr_trim_pages), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, }, #endif { - .ctl_name = VM_LAPTOP_MODE, .procname = "laptop_mode", .data = &laptop_mode, .maxlen = sizeof(laptop_mode), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = VM_BLOCK_DUMP, .procname = "block_dump", .data = &block_dump, .maxlen = sizeof(block_dump), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, .extra1 = &zero, }, { - .ctl_name = VM_VFS_CACHE_PRESSURE, .procname = "vfs_cache_pressure", .data = &sysctl_vfs_cache_pressure, .maxlen = sizeof(sysctl_vfs_cache_pressure), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, .extra1 = &zero, }, #ifdef HAVE_ARCH_PICK_MMAP_LAYOUT { - .ctl_name = VM_LEGACY_VA_LAYOUT, .procname = "legacy_va_layout", .data = &sysctl_legacy_va_layout, .maxlen = sizeof(sysctl_legacy_va_layout), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, .extra1 = &zero, }, #endif #ifdef CONFIG_NUMA { - .ctl_name = VM_ZONE_RECLAIM_MODE, .procname = "zone_reclaim_mode", .data = &zone_reclaim_mode, .maxlen = sizeof(zone_reclaim_mode), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, .extra1 = &zero, }, { - .ctl_name = VM_MIN_UNMAPPED, .procname = "min_unmapped_ratio", .data = &sysctl_min_unmapped_ratio, .maxlen = sizeof(sysctl_min_unmapped_ratio), .mode = 0644, - .proc_handler = &sysctl_min_unmapped_ratio_sysctl_handler, - .strategy = &sysctl_intvec, + .proc_handler = sysctl_min_unmapped_ratio_sysctl_handler, .extra1 = &zero, .extra2 = &one_hundred, }, { - .ctl_name = VM_MIN_SLAB, .procname = "min_slab_ratio", .data = &sysctl_min_slab_ratio, .maxlen = sizeof(sysctl_min_slab_ratio), .mode = 0644, - .proc_handler = &sysctl_min_slab_ratio_sysctl_handler, - .strategy = &sysctl_intvec, + .proc_handler = sysctl_min_slab_ratio_sysctl_handler, .extra1 = &zero, .extra2 = &one_hundred, }, #endif #ifdef CONFIG_SMP { - .ctl_name = CTL_UNNUMBERED, .procname = "stat_interval", .data = &sysctl_stat_interval, .maxlen = sizeof(sysctl_stat_interval), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, #endif { - .ctl_name = CTL_UNNUMBERED, .procname = "mmap_min_addr", .data = &dac_mmap_min_addr, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &mmap_min_addr_handler, + .proc_handler = mmap_min_addr_handler, }, #ifdef CONFIG_NUMA { - .ctl_name = CTL_UNNUMBERED, .procname = "numa_zonelist_order", .data = &numa_zonelist_order, .maxlen = NUMA_ZONELIST_ORDER_LEN, .mode = 0644, - .proc_handler = &numa_zonelist_order_handler, - .strategy = &sysctl_string, + .proc_handler = numa_zonelist_order_handler, }, #endif #if (defined(CONFIG_X86_32) && !defined(CONFIG_UML))|| \ (defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL)) { - .ctl_name = VM_VDSO_ENABLED, .procname = "vdso_enabled", .data = &vdso_enabled, .maxlen = sizeof(vdso_enabled), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, .extra1 = &zero, }, #endif #ifdef CONFIG_HIGHMEM { - .ctl_name = CTL_UNNUMBERED, .procname = "highmem_is_dirtyable", .data = &vm_highmem_is_dirtyable, .maxlen = sizeof(vm_highmem_is_dirtyable), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, #endif { - .ctl_name = CTL_UNNUMBERED, .procname = "scan_unevictable_pages", .data = &scan_unevictable_pages, .maxlen = sizeof(scan_unevictable_pages), .mode = 0644, - .proc_handler = &scan_unevictable_handler, + .proc_handler = scan_unevictable_handler, }, #ifdef CONFIG_MEMORY_FAILURE { - .ctl_name = CTL_UNNUMBERED, .procname = "memory_failure_early_kill", .data = &sysctl_memory_failure_early_kill, .maxlen = sizeof(sysctl_memory_failure_early_kill), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "memory_failure_recovery", .data = &sysctl_memory_failure_recovery, .maxlen = sizeof(sysctl_memory_failure_recovery), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, @@ -1440,116 +1272,104 @@ static struct ctl_table vm_table[] = { * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt */ - { .ctl_name = 0 } + { } }; #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE) static struct ctl_table binfmt_misc_table[] = { - { .ctl_name = 0 } + { } }; #endif static struct ctl_table fs_table[] = { { - .ctl_name = FS_NRINODE, .procname = "inode-nr", .data = &inodes_stat, .maxlen = 2*sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = FS_STATINODE, .procname = "inode-state", .data = &inodes_stat, .maxlen = 7*sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .procname = "file-nr", .data = &files_stat, .maxlen = 3*sizeof(int), .mode = 0444, - .proc_handler = &proc_nr_files, + .proc_handler = proc_nr_files, }, { - .ctl_name = FS_MAXFILE, .procname = "file-max", .data = &files_stat.max_files, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nr_open", .data = &sysctl_nr_open, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = &sysctl_nr_open_min, .extra2 = &sysctl_nr_open_max, }, { - .ctl_name = FS_DENTRY, .procname = "dentry-state", .data = &dentry_stat, .maxlen = 6*sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = FS_OVERFLOWUID, .procname = "overflowuid", .data = &fs_overflowuid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &minolduid, .extra2 = &maxolduid, }, { - .ctl_name = FS_OVERFLOWGID, .procname = "overflowgid", .data = &fs_overflowgid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &minolduid, .extra2 = &maxolduid, }, #ifdef CONFIG_FILE_LOCKING { - .ctl_name = FS_LEASES, .procname = "leases-enable", .data = &leases_enable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_DNOTIFY { - .ctl_name = FS_DIR_NOTIFY, .procname = "dir-notify-enable", .data = &dir_notify_enable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_MMU #ifdef CONFIG_FILE_LOCKING { - .ctl_name = FS_LEASE_TIME, .procname = "lease-break-time", .data = &lease_break_time, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_AIO @@ -1558,19 +1378,18 @@ static struct ctl_table fs_table[] = { .data = &aio_nr, .maxlen = sizeof(aio_nr), .mode = 0444, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, }, { .procname = "aio-max-nr", .data = &aio_max_nr, .maxlen = sizeof(aio_max_nr), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, }, #endif /* CONFIG_AIO */ #ifdef CONFIG_INOTIFY_USER { - .ctl_name = FS_INOTIFY, .procname = "inotify", .mode = 0555, .child = inotify_table, @@ -1585,19 +1404,16 @@ static struct ctl_table fs_table[] = { #endif #endif { - .ctl_name = KERN_SETUID_DUMPABLE, .procname = "suid_dumpable", .data = &suid_dumpable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &two, }, #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE) { - .ctl_name = CTL_UNNUMBERED, .procname = "binfmt_misc", .mode = 0555, .child = binfmt_misc_table, @@ -1607,13 +1423,12 @@ static struct ctl_table fs_table[] = { * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt */ - { .ctl_name = 0 } + { } }; static struct ctl_table debug_table[] = { #if defined(CONFIG_X86) || defined(CONFIG_PPC) { - .ctl_name = CTL_UNNUMBERED, .procname = "exception-trace", .data = &show_unhandled_signals, .maxlen = sizeof(int), @@ -1621,11 +1436,11 @@ static struct ctl_table debug_table[] = { .proc_handler = proc_dointvec }, #endif - { .ctl_name = 0 } + { } }; static struct ctl_table dev_table[] = { - { .ctl_name = 0 } + { } }; static DEFINE_SPINLOCK(sysctl_lock); @@ -1779,122 +1594,6 @@ void register_sysctl_root(struct ctl_table_root *root) spin_unlock(&sysctl_lock); } -#ifdef CONFIG_SYSCTL_SYSCALL -/* Perform the actual read/write of a sysctl table entry. */ -static int do_sysctl_strategy(struct ctl_table_root *root, - struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - int op = 0, rc; - - if (oldval) - op |= MAY_READ; - if (newval) - op |= MAY_WRITE; - if (sysctl_perm(root, table, op)) - return -EPERM; - - if (table->strategy) { - rc = table->strategy(table, oldval, oldlenp, newval, newlen); - if (rc < 0) - return rc; - if (rc > 0) - return 0; - } - - /* If there is no strategy routine, or if the strategy returns - * zero, proceed with automatic r/w */ - if (table->data && table->maxlen) { - rc = sysctl_data(table, oldval, oldlenp, newval, newlen); - if (rc < 0) - return rc; - } - return 0; -} - -static int parse_table(int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, - struct ctl_table_root *root, - struct ctl_table *table) -{ - int n; -repeat: - if (!nlen) - return -ENOTDIR; - if (get_user(n, name)) - return -EFAULT; - for ( ; table->ctl_name || table->procname; table++) { - if (!table->ctl_name) - continue; - if (n == table->ctl_name) { - int error; - if (table->child) { - if (sysctl_perm(root, table, MAY_EXEC)) - return -EPERM; - name++; - nlen--; - table = table->child; - goto repeat; - } - error = do_sysctl_strategy(root, table, - oldval, oldlenp, - newval, newlen); - return error; - } - } - return -ENOTDIR; -} - -int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - struct ctl_table_header *head; - int error = -ENOTDIR; - - if (nlen <= 0 || nlen >= CTL_MAXNAME) - return -ENOTDIR; - if (oldval) { - int old_len; - if (!oldlenp || get_user(old_len, oldlenp)) - return -EFAULT; - } - - for (head = sysctl_head_next(NULL); head; - head = sysctl_head_next(head)) { - error = parse_table(name, nlen, oldval, oldlenp, - newval, newlen, - head->root, head->ctl_table); - if (error != -ENOTDIR) { - sysctl_head_finish(head); - break; - } - } - return error; -} - -SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args) -{ - struct __sysctl_args tmp; - int error; - - if (copy_from_user(&tmp, args, sizeof(tmp))) - return -EFAULT; - - error = deprecated_sysctl_warning(&tmp); - if (error) - goto out; - - lock_kernel(); - error = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, tmp.oldlenp, - tmp.newval, tmp.newlen); - unlock_kernel(); -out: - return error; -} -#endif /* CONFIG_SYSCTL_SYSCALL */ - /* * sysctl_perm does NOT grant the superuser all rights automatically, because * some sysctl variables are readonly even to root. @@ -1930,7 +1629,7 @@ int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op) static void sysctl_set_parent(struct ctl_table *parent, struct ctl_table *table) { - for (; table->ctl_name || table->procname; table++) { + for (; table->procname; table++) { table->parent = parent; if (table->child) sysctl_set_parent(table, table->child); @@ -1962,11 +1661,11 @@ static struct ctl_table *is_branch_in(struct ctl_table *branch, return NULL; /* ... and nothing else */ - if (branch[1].procname || branch[1].ctl_name) + if (branch[1].procname) return NULL; /* table should contain subdirectory with the same name */ - for (p = table; p->procname || p->ctl_name; p++) { + for (p = table; p->procname; p++) { if (!p->child) continue; if (p->procname && strcmp(p->procname, s) == 0) @@ -2011,9 +1710,6 @@ static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q) * * The members of the &struct ctl_table structure are used as follows: * - * ctl_name - This is the numeric sysctl value used by sysctl(2). The number - * must be unique within that level of sysctl - * * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not * enter a sysctl file * @@ -2028,8 +1724,6 @@ static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q) * * proc_handler - the text handler routine (described below) * - * strategy - the strategy routine (described below) - * * de - for internal use by the sysctl routines * * extra1, extra2 - extra pointers usable by the proc handler routines @@ -2042,19 +1736,6 @@ static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q) * struct enable minimal validation of the values being written to be * performed, and the mode field allows minimal authentication. * - * More sophisticated management can be enabled by the provision of a - * strategy routine with the table entry. This will be called before - * any automatic read or write of the data is performed. - * - * The strategy routine may return - * - * < 0 - Error occurred (error is passed to user process) - * - * 0 - OK - proceed with automatic read or write. - * - * > 0 - OK - read or write has been done by the strategy routine, so - * return immediately. - * * There must be a proc_handler routine for any terminal nodes * mirrored under /proc/sys (non-terminals are handled by a built-in * directory handler). Several default handlers are available to @@ -2081,13 +1762,13 @@ struct ctl_table_header *__register_sysctl_paths( struct ctl_table_set *set; /* Count the path components */ - for (npath = 0; path[npath].ctl_name || path[npath].procname; ++npath) + for (npath = 0; path[npath].procname; ++npath) ; /* * For each path component, allocate a 2-element ctl_table array. * The first array element will be filled with the sysctl entry - * for this, the second will be the sentinel (ctl_name == 0). + * for this, the second will be the sentinel (procname == 0). * * We allocate everything in one go so that we don't have to * worry about freeing additional memory in unregister_sysctl_table. @@ -2104,7 +1785,6 @@ struct ctl_table_header *__register_sysctl_paths( for (n = 0; n < npath; ++n, ++path) { /* Copy the procname */ new->procname = path->procname; - new->ctl_name = path->ctl_name; new->mode = 0555; *prevp = new; @@ -2966,286 +2646,6 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, #endif /* CONFIG_PROC_FS */ - -#ifdef CONFIG_SYSCTL_SYSCALL -/* - * General sysctl support routines - */ - -/* The generic sysctl data routine (used if no strategy routine supplied) */ -int sysctl_data(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - size_t len; - - /* Get out of I don't have a variable */ - if (!table->data || !table->maxlen) - return -ENOTDIR; - - if (oldval && oldlenp) { - if (get_user(len, oldlenp)) - return -EFAULT; - if (len) { - if (len > table->maxlen) - len = table->maxlen; - if (copy_to_user(oldval, table->data, len)) - return -EFAULT; - if (put_user(len, oldlenp)) - return -EFAULT; - } - } - - if (newval && newlen) { - if (newlen > table->maxlen) - newlen = table->maxlen; - - if (copy_from_user(table->data, newval, newlen)) - return -EFAULT; - } - return 1; -} - -/* The generic string strategy routine: */ -int sysctl_string(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - if (!table->data || !table->maxlen) - return -ENOTDIR; - - if (oldval && oldlenp) { - size_t bufsize; - if (get_user(bufsize, oldlenp)) - return -EFAULT; - if (bufsize) { - size_t len = strlen(table->data), copied; - - /* This shouldn't trigger for a well-formed sysctl */ - if (len > table->maxlen) - len = table->maxlen; - - /* Copy up to a max of bufsize-1 bytes of the string */ - copied = (len >= bufsize) ? bufsize - 1 : len; - - if (copy_to_user(oldval, table->data, copied) || - put_user(0, (char __user *)(oldval + copied))) - return -EFAULT; - if (put_user(len, oldlenp)) - return -EFAULT; - } - } - if (newval && newlen) { - size_t len = newlen; - if (len > table->maxlen) - len = table->maxlen; - if(copy_from_user(table->data, newval, len)) - return -EFAULT; - if (len == table->maxlen) - len--; - ((char *) table->data)[len] = 0; - } - return 1; -} - -/* - * This function makes sure that all of the integers in the vector - * are between the minimum and maximum values given in the arrays - * table->extra1 and table->extra2, respectively. - */ -int sysctl_intvec(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - - if (newval && newlen) { - int __user *vec = (int __user *) newval; - int *min = (int *) table->extra1; - int *max = (int *) table->extra2; - size_t length; - int i; - - if (newlen % sizeof(int) != 0) - return -EINVAL; - - if (!table->extra1 && !table->extra2) - return 0; - - if (newlen > table->maxlen) - newlen = table->maxlen; - length = newlen / sizeof(int); - - for (i = 0; i < length; i++) { - int value; - if (get_user(value, vec + i)) - return -EFAULT; - if (min && value < min[i]) - return -EINVAL; - if (max && value > max[i]) - return -EINVAL; - } - } - return 0; -} - -/* Strategy function to convert jiffies to seconds */ -int sysctl_jiffies(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - if (oldval && oldlenp) { - size_t olen; - - if (get_user(olen, oldlenp)) - return -EFAULT; - if (olen) { - int val; - - if (olen < sizeof(int)) - return -EINVAL; - - val = *(int *)(table->data) / HZ; - if (put_user(val, (int __user *)oldval)) - return -EFAULT; - if (put_user(sizeof(int), oldlenp)) - return -EFAULT; - } - } - if (newval && newlen) { - int new; - if (newlen != sizeof(int)) - return -EINVAL; - if (get_user(new, (int __user *)newval)) - return -EFAULT; - *(int *)(table->data) = new*HZ; - } - return 1; -} - -/* Strategy function to convert jiffies to seconds */ -int sysctl_ms_jiffies(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - if (oldval && oldlenp) { - size_t olen; - - if (get_user(olen, oldlenp)) - return -EFAULT; - if (olen) { - int val; - - if (olen < sizeof(int)) - return -EINVAL; - - val = jiffies_to_msecs(*(int *)(table->data)); - if (put_user(val, (int __user *)oldval)) - return -EFAULT; - if (put_user(sizeof(int), oldlenp)) - return -EFAULT; - } - } - if (newval && newlen) { - int new; - if (newlen != sizeof(int)) - return -EINVAL; - if (get_user(new, (int __user *)newval)) - return -EFAULT; - *(int *)(table->data) = msecs_to_jiffies(new); - } - return 1; -} - - - -#else /* CONFIG_SYSCTL_SYSCALL */ - - -SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args) -{ - struct __sysctl_args tmp; - int error; - - if (copy_from_user(&tmp, args, sizeof(tmp))) - return -EFAULT; - - error = deprecated_sysctl_warning(&tmp); - - /* If no error reading the parameters then just -ENOSYS ... */ - if (!error) - error = -ENOSYS; - - return error; -} - -int sysctl_data(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - return -ENOSYS; -} - -int sysctl_string(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - return -ENOSYS; -} - -int sysctl_intvec(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - return -ENOSYS; -} - -int sysctl_jiffies(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - return -ENOSYS; -} - -int sysctl_ms_jiffies(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - return -ENOSYS; -} - -#endif /* CONFIG_SYSCTL_SYSCALL */ - -static int deprecated_sysctl_warning(struct __sysctl_args *args) -{ - static int msg_count; - int name[CTL_MAXNAME]; - int i; - - /* Check args->nlen. */ - if (args->nlen < 0 || args->nlen > CTL_MAXNAME) - return -ENOTDIR; - - /* Read in the sysctl name for better debug message logging */ - for (i = 0; i < args->nlen; i++) - if (get_user(name[i], args->name + i)) - return -EFAULT; - - /* Ignore accesses to kernel.version */ - if ((args->nlen == 2) && (name[0] == CTL_KERN) && (name[1] == KERN_VERSION)) - return 0; - - if (msg_count < 5) { - msg_count++; - printk(KERN_INFO - "warning: process `%s' used the deprecated sysctl " - "system call with ", current->comm); - for (i = 0; i < args->nlen; i++) - printk("%d.", name[i]); - printk("\n"); - } - return 0; -} - /* * No sense putting this after each symbol definition, twice, * exception granted :-) @@ -3260,9 +2660,4 @@ EXPORT_SYMBOL(proc_doulongvec_minmax); EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax); EXPORT_SYMBOL(register_sysctl_table); EXPORT_SYMBOL(register_sysctl_paths); -EXPORT_SYMBOL(sysctl_intvec); -EXPORT_SYMBOL(sysctl_jiffies); -EXPORT_SYMBOL(sysctl_ms_jiffies); -EXPORT_SYMBOL(sysctl_string); -EXPORT_SYMBOL(sysctl_data); EXPORT_SYMBOL(unregister_sysctl_table); diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c new file mode 100644 index 0000000..b75dbf4 --- /dev/null +++ b/kernel/sysctl_binary.c @@ -0,0 +1,1507 @@ +#include <linux/stat.h> +#include <linux/sysctl.h> +#include "../fs/xfs/linux-2.6/xfs_sysctl.h" +#include <linux/sunrpc/debug.h> +#include <linux/string.h> +#include <net/ip_vs.h> +#include <linux/syscalls.h> +#include <linux/namei.h> +#include <linux/mount.h> +#include <linux/fs.h> +#include <linux/nsproxy.h> +#include <linux/pid_namespace.h> +#include <linux/file.h> +#include <linux/ctype.h> +#include <linux/netdevice.h> + +#ifdef CONFIG_SYSCTL_SYSCALL + +struct bin_table; +typedef ssize_t bin_convert_t(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen); + +static bin_convert_t bin_dir; +static bin_convert_t bin_string; +static bin_convert_t bin_intvec; +static bin_convert_t bin_ulongvec; +static bin_convert_t bin_uuid; +static bin_convert_t bin_dn_node_address; + +#define CTL_DIR bin_dir +#define CTL_STR bin_string +#define CTL_INT bin_intvec +#define CTL_ULONG bin_ulongvec +#define CTL_UUID bin_uuid +#define CTL_DNADR bin_dn_node_address + +#define BUFSZ 256 + +struct bin_table { + bin_convert_t *convert; + int ctl_name; + const char *procname; + const struct bin_table *child; +}; + +static const struct bin_table bin_random_table[] = { + { CTL_INT, RANDOM_POOLSIZE, "poolsize" }, + { CTL_INT, RANDOM_ENTROPY_COUNT, "entropy_avail" }, + { CTL_INT, RANDOM_READ_THRESH, "read_wakeup_threshold" }, + { CTL_INT, RANDOM_WRITE_THRESH, "write_wakeup_threshold" }, + { CTL_UUID, RANDOM_BOOT_ID, "boot_id" }, + { CTL_UUID, RANDOM_UUID, "uuid" }, + {} +}; + +static const struct bin_table bin_pty_table[] = { + { CTL_INT, PTY_MAX, "max" }, + { CTL_INT, PTY_NR, "nr" }, + {} +}; + +static const struct bin_table bin_kern_table[] = { + { CTL_STR, KERN_OSTYPE, "ostype" }, + { CTL_STR, KERN_OSRELEASE, "osrelease" }, + /* KERN_OSREV not used */ + { CTL_STR, KERN_VERSION, "version" }, + /* KERN_SECUREMASK not used */ + /* KERN_PROF not used */ + { CTL_STR, KERN_NODENAME, "hostname" }, + { CTL_STR, KERN_DOMAINNAME, "domainname" }, + + { CTL_INT, KERN_PANIC, "panic" }, + { CTL_INT, KERN_REALROOTDEV, "real-root-dev" }, + + { CTL_STR, KERN_SPARC_REBOOT, "reboot-cmd" }, + { CTL_INT, KERN_CTLALTDEL, "ctrl-alt-del" }, + { CTL_INT, KERN_PRINTK, "printk" }, + + /* KERN_NAMETRANS not used */ + /* KERN_PPC_HTABRECLAIM not used */ + /* KERN_PPC_ZEROPAGED not used */ + { CTL_INT, KERN_PPC_POWERSAVE_NAP, "powersave-nap" }, + + { CTL_STR, KERN_MODPROBE, "modprobe" }, + { CTL_INT, KERN_SG_BIG_BUFF, "sg-big-buff" }, + { CTL_INT, KERN_ACCT, "acct" }, + /* KERN_PPC_L2CR "l2cr" no longer used */ + + /* KERN_RTSIGNR not used */ + /* KERN_RTSIGMAX not used */ + + { CTL_ULONG, KERN_SHMMAX, "shmmax" }, + { CTL_INT, KERN_MSGMAX, "msgmax" }, + { CTL_INT, KERN_MSGMNB, "msgmnb" }, + /* KERN_MSGPOOL not used*/ + { CTL_INT, KERN_SYSRQ, "sysrq" }, + { CTL_INT, KERN_MAX_THREADS, "threads-max" }, + { CTL_DIR, KERN_RANDOM, "random", bin_random_table }, + { CTL_ULONG, KERN_SHMALL, "shmall" }, + { CTL_INT, KERN_MSGMNI, "msgmni" }, + { CTL_INT, KERN_SEM, "sem" }, + { CTL_INT, KERN_SPARC_STOP_A, "stop-a" }, + { CTL_INT, KERN_SHMMNI, "shmmni" }, + + { CTL_INT, KERN_OVERFLOWUID, "overflowuid" }, + { CTL_INT, KERN_OVERFLOWGID, "overflowgid" }, + + { CTL_STR, KERN_HOTPLUG, "hotplug", }, + { CTL_INT, KERN_IEEE_EMULATION_WARNINGS, "ieee_emulation_warnings" }, + + { CTL_INT, KERN_S390_USER_DEBUG_LOGGING, "userprocess_debug" }, + { CTL_INT, KERN_CORE_USES_PID, "core_uses_pid" }, + /* KERN_TAINTED "tainted" no longer used */ + { CTL_INT, KERN_CADPID, "cad_pid" }, + { CTL_INT, KERN_PIDMAX, "pid_max" }, + { CTL_STR, KERN_CORE_PATTERN, "core_pattern" }, + { CTL_INT, KERN_PANIC_ON_OOPS, "panic_on_oops" }, + { CTL_INT, KERN_HPPA_PWRSW, "soft-power" }, + { CTL_INT, KERN_HPPA_UNALIGNED, "unaligned-trap" }, + + { CTL_INT, KERN_PRINTK_RATELIMIT, "printk_ratelimit" }, + { CTL_INT, KERN_PRINTK_RATELIMIT_BURST, "printk_ratelimit_burst" }, + + { CTL_DIR, KERN_PTY, "pty", bin_pty_table }, + { CTL_INT, KERN_NGROUPS_MAX, "ngroups_max" }, + { CTL_INT, KERN_SPARC_SCONS_PWROFF, "scons-poweroff" }, + /* KERN_HZ_TIMER "hz_timer" no longer used */ + { CTL_INT, KERN_UNKNOWN_NMI_PANIC, "unknown_nmi_panic" }, + { CTL_INT, KERN_BOOTLOADER_TYPE, "bootloader_type" }, + { CTL_INT, KERN_RANDOMIZE, "randomize_va_space" }, + + { CTL_INT, KERN_SPIN_RETRY, "spin_retry" }, + /* KERN_ACPI_VIDEO_FLAGS "acpi_video_flags" no longer used */ + { CTL_INT, KERN_IA64_UNALIGNED, "ignore-unaligned-usertrap" }, + { CTL_INT, KERN_COMPAT_LOG, "compat-log" }, + { CTL_INT, KERN_MAX_LOCK_DEPTH, "max_lock_depth" }, + { CTL_INT, KERN_NMI_WATCHDOG, "nmi_watchdog" }, + { CTL_INT, KERN_PANIC_ON_NMI, "panic_on_unrecovered_nmi" }, + {} +}; + +static const struct bin_table bin_vm_table[] = { + { CTL_INT, VM_OVERCOMMIT_MEMORY, "overcommit_memory" }, + { CTL_INT, VM_PAGE_CLUSTER, "page-cluster" }, + { CTL_INT, VM_DIRTY_BACKGROUND, "dirty_background_ratio" }, + { CTL_INT, VM_DIRTY_RATIO, "dirty_ratio" }, + /* VM_DIRTY_WB_CS "dirty_writeback_centisecs" no longer used */ + /* VM_DIRTY_EXPIRE_CS "dirty_expire_centisecs" no longer used */ + { CTL_INT, VM_NR_PDFLUSH_THREADS, "nr_pdflush_threads" }, + { CTL_INT, VM_OVERCOMMIT_RATIO, "overcommit_ratio" }, + /* VM_PAGEBUF unused */ + /* VM_HUGETLB_PAGES "nr_hugepages" no longer used */ + { CTL_INT, VM_SWAPPINESS, "swappiness" }, + { CTL_INT, VM_LOWMEM_RESERVE_RATIO, "lowmem_reserve_ratio" }, + { CTL_INT, VM_MIN_FREE_KBYTES, "min_free_kbytes" }, + { CTL_INT, VM_MAX_MAP_COUNT, "max_map_count" }, + { CTL_INT, VM_LAPTOP_MODE, "laptop_mode" }, + { CTL_INT, VM_BLOCK_DUMP, "block_dump" }, + { CTL_INT, VM_HUGETLB_GROUP, "hugetlb_shm_group" }, + { CTL_INT, VM_VFS_CACHE_PRESSURE, "vfs_cache_pressure" }, + { CTL_INT, VM_LEGACY_VA_LAYOUT, "legacy_va_layout" }, + /* VM_SWAP_TOKEN_TIMEOUT unused */ + { CTL_INT, VM_DROP_PAGECACHE, "drop_caches" }, + { CTL_INT, VM_PERCPU_PAGELIST_FRACTION, "percpu_pagelist_fraction" }, + { CTL_INT, VM_ZONE_RECLAIM_MODE, "zone_reclaim_mode" }, + { CTL_INT, VM_MIN_UNMAPPED, "min_unmapped_ratio" }, + { CTL_INT, VM_PANIC_ON_OOM, "panic_on_oom" }, + { CTL_INT, VM_VDSO_ENABLED, "vdso_enabled" }, + { CTL_INT, VM_MIN_SLAB, "min_slab_ratio" }, + + {} +}; + +static const struct bin_table bin_net_core_table[] = { + { CTL_INT, NET_CORE_WMEM_MAX, "wmem_max" }, + { CTL_INT, NET_CORE_RMEM_MAX, "rmem_max" }, + { CTL_INT, NET_CORE_WMEM_DEFAULT, "wmem_default" }, + { CTL_INT, NET_CORE_RMEM_DEFAULT, "rmem_default" }, + /* NET_CORE_DESTROY_DELAY unused */ + { CTL_INT, NET_CORE_MAX_BACKLOG, "netdev_max_backlog" }, + /* NET_CORE_FASTROUTE unused */ + { CTL_INT, NET_CORE_MSG_COST, "message_cost" }, + { CTL_INT, NET_CORE_MSG_BURST, "message_burst" }, + { CTL_INT, NET_CORE_OPTMEM_MAX, "optmem_max" }, + /* NET_CORE_HOT_LIST_LENGTH unused */ + /* NET_CORE_DIVERT_VERSION unused */ + /* NET_CORE_NO_CONG_THRESH unused */ + /* NET_CORE_NO_CONG unused */ + /* NET_CORE_LO_CONG unused */ + /* NET_CORE_MOD_CONG unused */ + { CTL_INT, NET_CORE_DEV_WEIGHT, "dev_weight" }, + { CTL_INT, NET_CORE_SOMAXCONN, "somaxconn" }, + { CTL_INT, NET_CORE_BUDGET, "netdev_budget" }, + { CTL_INT, NET_CORE_AEVENT_ETIME, "xfrm_aevent_etime" }, + { CTL_INT, NET_CORE_AEVENT_RSEQTH, "xfrm_aevent_rseqth" }, + { CTL_INT, NET_CORE_WARNINGS, "warnings" }, + {}, +}; + +static const struct bin_table bin_net_unix_table[] = { + /* NET_UNIX_DESTROY_DELAY unused */ + /* NET_UNIX_DELETE_DELAY unused */ + { CTL_INT, NET_UNIX_MAX_DGRAM_QLEN, "max_dgram_qlen" }, + {} +}; + +static const struct bin_table bin_net_ipv4_route_table[] = { + { CTL_INT, NET_IPV4_ROUTE_FLUSH, "flush" }, + /* NET_IPV4_ROUTE_MIN_DELAY "min_delay" no longer used */ + /* NET_IPV4_ROUTE_MAX_DELAY "max_delay" no longer used */ + { CTL_INT, NET_IPV4_ROUTE_GC_THRESH, "gc_thresh" }, + { CTL_INT, NET_IPV4_ROUTE_MAX_SIZE, "max_size" }, + { CTL_INT, NET_IPV4_ROUTE_GC_MIN_INTERVAL, "gc_min_interval" }, + { CTL_INT, NET_IPV4_ROUTE_GC_MIN_INTERVAL_MS, "gc_min_interval_ms" }, + { CTL_INT, NET_IPV4_ROUTE_GC_TIMEOUT, "gc_timeout" }, + { CTL_INT, NET_IPV4_ROUTE_GC_INTERVAL, "gc_interval" }, + { CTL_INT, NET_IPV4_ROUTE_REDIRECT_LOAD, "redirect_load" }, + { CTL_INT, NET_IPV4_ROUTE_REDIRECT_NUMBER, "redirect_number" }, + { CTL_INT, NET_IPV4_ROUTE_REDIRECT_SILENCE, "redirect_silence" }, + { CTL_INT, NET_IPV4_ROUTE_ERROR_COST, "error_cost" }, + { CTL_INT, NET_IPV4_ROUTE_ERROR_BURST, "error_burst" }, + { CTL_INT, NET_IPV4_ROUTE_GC_ELASTICITY, "gc_elasticity" }, + { CTL_INT, NET_IPV4_ROUTE_MTU_EXPIRES, "mtu_expires" }, + { CTL_INT, NET_IPV4_ROUTE_MIN_PMTU, "min_pmtu" }, + { CTL_INT, NET_IPV4_ROUTE_MIN_ADVMSS, "min_adv_mss" }, + { CTL_INT, NET_IPV4_ROUTE_SECRET_INTERVAL, "secret_interval" }, + {} +}; + +static const struct bin_table bin_net_ipv4_conf_vars_table[] = { + { CTL_INT, NET_IPV4_CONF_FORWARDING, "forwarding" }, + { CTL_INT, NET_IPV4_CONF_MC_FORWARDING, "mc_forwarding" }, + + { CTL_INT, NET_IPV4_CONF_ACCEPT_REDIRECTS, "accept_redirects" }, + { CTL_INT, NET_IPV4_CONF_SECURE_REDIRECTS, "secure_redirects" }, + { CTL_INT, NET_IPV4_CONF_SEND_REDIRECTS, "send_redirects" }, + { CTL_INT, NET_IPV4_CONF_SHARED_MEDIA, "shared_media" }, + { CTL_INT, NET_IPV4_CONF_RP_FILTER, "rp_filter" }, + { CTL_INT, NET_IPV4_CONF_ACCEPT_SOURCE_ROUTE, "accept_source_route" }, + { CTL_INT, NET_IPV4_CONF_PROXY_ARP, "proxy_arp" }, + { CTL_INT, NET_IPV4_CONF_MEDIUM_ID, "medium_id" }, + { CTL_INT, NET_IPV4_CONF_BOOTP_RELAY, "bootp_relay" }, + { CTL_INT, NET_IPV4_CONF_LOG_MARTIANS, "log_martians" }, + { CTL_INT, NET_IPV4_CONF_TAG, "tag" }, + { CTL_INT, NET_IPV4_CONF_ARPFILTER, "arp_filter" }, + { CTL_INT, NET_IPV4_CONF_ARP_ANNOUNCE, "arp_announce" }, + { CTL_INT, NET_IPV4_CONF_ARP_IGNORE, "arp_ignore" }, + { CTL_INT, NET_IPV4_CONF_ARP_ACCEPT, "arp_accept" }, + { CTL_INT, NET_IPV4_CONF_ARP_NOTIFY, "arp_notify" }, + + { CTL_INT, NET_IPV4_CONF_NOXFRM, "disable_xfrm" }, + { CTL_INT, NET_IPV4_CONF_NOPOLICY, "disable_policy" }, + { CTL_INT, NET_IPV4_CONF_FORCE_IGMP_VERSION, "force_igmp_version" }, + { CTL_INT, NET_IPV4_CONF_PROMOTE_SECONDARIES, "promote_secondaries" }, + {} +}; + +static const struct bin_table bin_net_ipv4_conf_table[] = { + { CTL_DIR, NET_PROTO_CONF_ALL, "all", bin_net_ipv4_conf_vars_table }, + { CTL_DIR, NET_PROTO_CONF_DEFAULT, "default", bin_net_ipv4_conf_vars_table }, + { CTL_DIR, 0, NULL, bin_net_ipv4_conf_vars_table }, + {} +}; + +static const struct bin_table bin_net_neigh_vars_table[] = { + { CTL_INT, NET_NEIGH_MCAST_SOLICIT, "mcast_solicit" }, + { CTL_INT, NET_NEIGH_UCAST_SOLICIT, "ucast_solicit" }, + { CTL_INT, NET_NEIGH_APP_SOLICIT, "app_solicit" }, + /* NET_NEIGH_RETRANS_TIME "retrans_time" no longer used */ + { CTL_INT, NET_NEIGH_REACHABLE_TIME, "base_reachable_time" }, + { CTL_INT, NET_NEIGH_DELAY_PROBE_TIME, "delay_first_probe_time" }, + { CTL_INT, NET_NEIGH_GC_STALE_TIME, "gc_stale_time" }, + { CTL_INT, NET_NEIGH_UNRES_QLEN, "unres_qlen" }, + { CTL_INT, NET_NEIGH_PROXY_QLEN, "proxy_qlen" }, + /* NET_NEIGH_ANYCAST_DELAY "anycast_delay" no longer used */ + /* NET_NEIGH_PROXY_DELAY "proxy_delay" no longer used */ + /* NET_NEIGH_LOCKTIME "locktime" no longer used */ + { CTL_INT, NET_NEIGH_GC_INTERVAL, "gc_interval" }, + { CTL_INT, NET_NEIGH_GC_THRESH1, "gc_thresh1" }, + { CTL_INT, NET_NEIGH_GC_THRESH2, "gc_thresh2" }, + { CTL_INT, NET_NEIGH_GC_THRESH3, "gc_thresh3" }, + { CTL_INT, NET_NEIGH_RETRANS_TIME_MS, "retrans_time_ms" }, + { CTL_INT, NET_NEIGH_REACHABLE_TIME_MS, "base_reachable_time_ms" }, + {} +}; + +static const struct bin_table bin_net_neigh_table[] = { + { CTL_DIR, NET_PROTO_CONF_DEFAULT, "default", bin_net_neigh_vars_table }, + { CTL_DIR, 0, NULL, bin_net_neigh_vars_table }, + {} +}; + +static const struct bin_table bin_net_ipv4_netfilter_table[] = { + { CTL_INT, NET_IPV4_NF_CONNTRACK_MAX, "ip_conntrack_max" }, + + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT "ip_conntrack_tcp_timeout_syn_sent" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV "ip_conntrack_tcp_timeout_syn_recv" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED "ip_conntrack_tcp_timeout_established" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT "ip_conntrack_tcp_timeout_fin_wait" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT "ip_conntrack_tcp_timeout_close_wait" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK "ip_conntrack_tcp_timeout_last_ack" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT "ip_conntrack_tcp_timeout_time_wait" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE "ip_conntrack_tcp_timeout_close" no longer used */ + + /* NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT "ip_conntrack_udp_timeout" no longer used */ + /* NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT_STREAM "ip_conntrack_udp_timeout_stream" no longer used */ + /* NET_IPV4_NF_CONNTRACK_ICMP_TIMEOUT "ip_conntrack_icmp_timeout" no longer used */ + /* NET_IPV4_NF_CONNTRACK_GENERIC_TIMEOUT "ip_conntrack_generic_timeout" no longer used */ + + { CTL_INT, NET_IPV4_NF_CONNTRACK_BUCKETS, "ip_conntrack_buckets" }, + { CTL_INT, NET_IPV4_NF_CONNTRACK_LOG_INVALID, "ip_conntrack_log_invalid" }, + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS "ip_conntrack_tcp_timeout_max_retrans" no longer used */ + { CTL_INT, NET_IPV4_NF_CONNTRACK_TCP_LOOSE, "ip_conntrack_tcp_loose" }, + { CTL_INT, NET_IPV4_NF_CONNTRACK_TCP_BE_LIBERAL, "ip_conntrack_tcp_be_liberal" }, + { CTL_INT, NET_IPV4_NF_CONNTRACK_TCP_MAX_RETRANS, "ip_conntrack_tcp_max_retrans" }, + + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED "ip_conntrack_sctp_timeout_closed" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT "ip_conntrack_sctp_timeout_cookie_wait" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED "ip_conntrack_sctp_timeout_cookie_echoed" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED "ip_conntrack_sctp_timeout_established" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT "ip_conntrack_sctp_timeout_shutdown_sent" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD "ip_conntrack_sctp_timeout_shutdown_recd" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT "ip_conntrack_sctp_timeout_shutdown_ack_sent" no longer used */ + + { CTL_INT, NET_IPV4_NF_CONNTRACK_COUNT, "ip_conntrack_count" }, + { CTL_INT, NET_IPV4_NF_CONNTRACK_CHECKSUM, "ip_conntrack_checksum" }, + {} +}; + +static const struct bin_table bin_net_ipv4_table[] = { + {CTL_INT, NET_IPV4_FORWARD, "ip_forward" }, + + { CTL_DIR, NET_IPV4_CONF, "conf", bin_net_ipv4_conf_table }, + { CTL_DIR, NET_IPV4_NEIGH, "neigh", bin_net_neigh_table }, + { CTL_DIR, NET_IPV4_ROUTE, "route", bin_net_ipv4_route_table }, + /* NET_IPV4_FIB_HASH unused */ + { CTL_DIR, NET_IPV4_NETFILTER, "netfilter", bin_net_ipv4_netfilter_table }, + + { CTL_INT, NET_IPV4_TCP_TIMESTAMPS, "tcp_timestamps" }, + { CTL_INT, NET_IPV4_TCP_WINDOW_SCALING, "tcp_window_scaling" }, + { CTL_INT, NET_IPV4_TCP_SACK, "tcp_sack" }, + { CTL_INT, NET_IPV4_TCP_RETRANS_COLLAPSE, "tcp_retrans_collapse" }, + { CTL_INT, NET_IPV4_DEFAULT_TTL, "ip_default_ttl" }, + /* NET_IPV4_AUTOCONFIG unused */ + { CTL_INT, NET_IPV4_NO_PMTU_DISC, "ip_no_pmtu_disc" }, + { CTL_INT, NET_IPV4_NONLOCAL_BIND, "ip_nonlocal_bind" }, + { CTL_INT, NET_IPV4_TCP_SYN_RETRIES, "tcp_syn_retries" }, + { CTL_INT, NET_TCP_SYNACK_RETRIES, "tcp_synack_retries" }, + { CTL_INT, NET_TCP_MAX_ORPHANS, "tcp_max_orphans" }, + { CTL_INT, NET_TCP_MAX_TW_BUCKETS, "tcp_max_tw_buckets" }, + { CTL_INT, NET_IPV4_DYNADDR, "ip_dynaddr" }, + { CTL_INT, NET_IPV4_TCP_KEEPALIVE_TIME, "tcp_keepalive_time" }, + { CTL_INT, NET_IPV4_TCP_KEEPALIVE_PROBES, "tcp_keepalive_probes" }, + { CTL_INT, NET_IPV4_TCP_KEEPALIVE_INTVL, "tcp_keepalive_intvl" }, + { CTL_INT, NET_IPV4_TCP_RETRIES1, "tcp_retries1" }, + { CTL_INT, NET_IPV4_TCP_RETRIES2, "tcp_retries2" }, + { CTL_INT, NET_IPV4_TCP_FIN_TIMEOUT, "tcp_fin_timeout" }, + { CTL_INT, NET_TCP_SYNCOOKIES, "tcp_syncookies" }, + { CTL_INT, NET_TCP_TW_RECYCLE, "tcp_tw_recycle" }, + { CTL_INT, NET_TCP_ABORT_ON_OVERFLOW, "tcp_abort_on_overflow" }, + { CTL_INT, NET_TCP_STDURG, "tcp_stdurg" }, + { CTL_INT, NET_TCP_RFC1337, "tcp_rfc1337" }, + { CTL_INT, NET_TCP_MAX_SYN_BACKLOG, "tcp_max_syn_backlog" }, + { CTL_INT, NET_IPV4_LOCAL_PORT_RANGE, "ip_local_port_range" }, + { CTL_INT, NET_IPV4_IGMP_MAX_MEMBERSHIPS, "igmp_max_memberships" }, + { CTL_INT, NET_IPV4_IGMP_MAX_MSF, "igmp_max_msf" }, + { CTL_INT, NET_IPV4_INET_PEER_THRESHOLD, "inet_peer_threshold" }, + { CTL_INT, NET_IPV4_INET_PEER_MINTTL, "inet_peer_minttl" }, + { CTL_INT, NET_IPV4_INET_PEER_MAXTTL, "inet_peer_maxttl" }, + { CTL_INT, NET_IPV4_INET_PEER_GC_MINTIME, "inet_peer_gc_mintime" }, + { CTL_INT, NET_IPV4_INET_PEER_GC_MAXTIME, "inet_peer_gc_maxtime" }, + { CTL_INT, NET_TCP_ORPHAN_RETRIES, "tcp_orphan_retries" }, + { CTL_INT, NET_TCP_FACK, "tcp_fack" }, + { CTL_INT, NET_TCP_REORDERING, "tcp_reordering" }, + { CTL_INT, NET_TCP_ECN, "tcp_ecn" }, + { CTL_INT, NET_TCP_DSACK, "tcp_dsack" }, + { CTL_INT, NET_TCP_MEM, "tcp_mem" }, + { CTL_INT, NET_TCP_WMEM, "tcp_wmem" }, + { CTL_INT, NET_TCP_RMEM, "tcp_rmem" }, + { CTL_INT, NET_TCP_APP_WIN, "tcp_app_win" }, + { CTL_INT, NET_TCP_ADV_WIN_SCALE, "tcp_adv_win_scale" }, + { CTL_INT, NET_TCP_TW_REUSE, "tcp_tw_reuse" }, + { CTL_INT, NET_TCP_FRTO, "tcp_frto" }, + { CTL_INT, NET_TCP_FRTO_RESPONSE, "tcp_frto_response" }, + { CTL_INT, NET_TCP_LOW_LATENCY, "tcp_low_latency" }, + { CTL_INT, NET_TCP_NO_METRICS_SAVE, "tcp_no_metrics_save" }, + { CTL_INT, NET_TCP_MODERATE_RCVBUF, "tcp_moderate_rcvbuf" }, + { CTL_INT, NET_TCP_TSO_WIN_DIVISOR, "tcp_tso_win_divisor" }, + { CTL_STR, NET_TCP_CONG_CONTROL, "tcp_congestion_control" }, + { CTL_INT, NET_TCP_ABC, "tcp_abc" }, + { CTL_INT, NET_TCP_MTU_PROBING, "tcp_mtu_probing" }, + { CTL_INT, NET_TCP_BASE_MSS, "tcp_base_mss" }, + { CTL_INT, NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS, "tcp_workaround_signed_windows" }, + { CTL_INT, NET_TCP_DMA_COPYBREAK, "tcp_dma_copybreak" }, + { CTL_INT, NET_TCP_SLOW_START_AFTER_IDLE, "tcp_slow_start_after_idle" }, + { CTL_INT, NET_CIPSOV4_CACHE_ENABLE, "cipso_cache_enable" }, + { CTL_INT, NET_CIPSOV4_CACHE_BUCKET_SIZE, "cipso_cache_bucket_size" }, + { CTL_INT, NET_CIPSOV4_RBM_OPTFMT, "cipso_rbm_optfmt" }, + { CTL_INT, NET_CIPSOV4_RBM_STRICTVALID, "cipso_rbm_strictvalid" }, + /* NET_TCP_AVAIL_CONG_CONTROL "tcp_available_congestion_control" no longer used */ + { CTL_STR, NET_TCP_ALLOWED_CONG_CONTROL, "tcp_allowed_congestion_control" }, + { CTL_INT, NET_TCP_MAX_SSTHRESH, "tcp_max_ssthresh" }, + + { CTL_INT, NET_IPV4_ICMP_ECHO_IGNORE_ALL, "icmp_echo_ignore_all" }, + { CTL_INT, NET_IPV4_ICMP_ECHO_IGNORE_BROADCASTS, "icmp_echo_ignore_broadcasts" }, + { CTL_INT, NET_IPV4_ICMP_IGNORE_BOGUS_ERROR_RESPONSES, "icmp_ignore_bogus_error_responses" }, + { CTL_INT, NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR, "icmp_errors_use_inbound_ifaddr" }, + { CTL_INT, NET_IPV4_ICMP_RATELIMIT, "icmp_ratelimit" }, + { CTL_INT, NET_IPV4_ICMP_RATEMASK, "icmp_ratemask" }, + + { CTL_INT, NET_IPV4_IPFRAG_HIGH_THRESH, "ipfrag_high_thresh" }, + { CTL_INT, NET_IPV4_IPFRAG_LOW_THRESH, "ipfrag_low_thresh" }, + { CTL_INT, NET_IPV4_IPFRAG_TIME, "ipfrag_time" }, + + { CTL_INT, NET_IPV4_IPFRAG_SECRET_INTERVAL, "ipfrag_secret_interval" }, + /* NET_IPV4_IPFRAG_MAX_DIST "ipfrag_max_dist" no longer used */ + + { CTL_INT, 2088 /* NET_IPQ_QMAX */, "ip_queue_maxlen" }, + + /* NET_TCP_DEFAULT_WIN_SCALE unused */ + /* NET_TCP_BIC_BETA unused */ + /* NET_IPV4_TCP_MAX_KA_PROBES unused */ + /* NET_IPV4_IP_MASQ_DEBUG unused */ + /* NET_TCP_SYN_TAILDROP unused */ + /* NET_IPV4_ICMP_SOURCEQUENCH_RATE unused */ + /* NET_IPV4_ICMP_DESTUNREACH_RATE unused */ + /* NET_IPV4_ICMP_TIMEEXCEED_RATE unused */ + /* NET_IPV4_ICMP_PARAMPROB_RATE unused */ + /* NET_IPV4_ICMP_ECHOREPLY_RATE unused */ + /* NET_IPV4_ALWAYS_DEFRAG unused */ + {} +}; + +static const struct bin_table bin_net_ipx_table[] = { + { CTL_INT, NET_IPX_PPROP_BROADCASTING, "ipx_pprop_broadcasting" }, + /* NET_IPX_FORWARDING unused */ + {} +}; + +static const struct bin_table bin_net_atalk_table[] = { + { CTL_INT, NET_ATALK_AARP_EXPIRY_TIME, "aarp-expiry-time" }, + { CTL_INT, NET_ATALK_AARP_TICK_TIME, "aarp-tick-time" }, + { CTL_INT, NET_ATALK_AARP_RETRANSMIT_LIMIT, "aarp-retransmit-limit" }, + { CTL_INT, NET_ATALK_AARP_RESOLVE_TIME, "aarp-resolve-time" }, + {}, +}; + +static const struct bin_table bin_net_netrom_table[] = { + { CTL_INT, NET_NETROM_DEFAULT_PATH_QUALITY, "default_path_quality" }, + { CTL_INT, NET_NETROM_OBSOLESCENCE_COUNT_INITIALISER, "obsolescence_count_initialiser" }, + { CTL_INT, NET_NETROM_NETWORK_TTL_INITIALISER, "network_ttl_initialiser" }, + { CTL_INT, NET_NETROM_TRANSPORT_TIMEOUT, "transport_timeout" }, + { CTL_INT, NET_NETROM_TRANSPORT_MAXIMUM_TRIES, "transport_maximum_tries" }, + { CTL_INT, NET_NETROM_TRANSPORT_ACKNOWLEDGE_DELAY, "transport_acknowledge_delay" }, + { CTL_INT, NET_NETROM_TRANSPORT_BUSY_DELAY, "transport_busy_delay" }, + { CTL_INT, NET_NETROM_TRANSPORT_REQUESTED_WINDOW_SIZE, "transport_requested_window_size" }, + { CTL_INT, NET_NETROM_TRANSPORT_NO_ACTIVITY_TIMEOUT, "transport_no_activity_timeout" }, + { CTL_INT, NET_NETROM_ROUTING_CONTROL, "routing_control" }, + { CTL_INT, NET_NETROM_LINK_FAILS_COUNT, "link_fails_count" }, + { CTL_INT, NET_NETROM_RESET, "reset" }, + {} +}; + +static const struct bin_table bin_net_ax25_param_table[] = { + { CTL_INT, NET_AX25_IP_DEFAULT_MODE, "ip_default_mode" }, + { CTL_INT, NET_AX25_DEFAULT_MODE, "ax25_default_mode" }, + { CTL_INT, NET_AX25_BACKOFF_TYPE, "backoff_type" }, + { CTL_INT, NET_AX25_CONNECT_MODE, "connect_mode" }, + { CTL_INT, NET_AX25_STANDARD_WINDOW, "standard_window_size" }, + { CTL_INT, NET_AX25_EXTENDED_WINDOW, "extended_window_size" }, + { CTL_INT, NET_AX25_T1_TIMEOUT, "t1_timeout" }, + { CTL_INT, NET_AX25_T2_TIMEOUT, "t2_timeout" }, + { CTL_INT, NET_AX25_T3_TIMEOUT, "t3_timeout" }, + { CTL_INT, NET_AX25_IDLE_TIMEOUT, "idle_timeout" }, + { CTL_INT, NET_AX25_N2, "maximum_retry_count" }, + { CTL_INT, NET_AX25_PACLEN, "maximum_packet_length" }, + { CTL_INT, NET_AX25_PROTOCOL, "protocol" }, + { CTL_INT, NET_AX25_DAMA_SLAVE_TIMEOUT, "dama_slave_timeout" }, + {} +}; + +static const struct bin_table bin_net_ax25_table[] = { + { CTL_DIR, 0, NULL, bin_net_ax25_param_table }, + {} +}; + +static const struct bin_table bin_net_rose_table[] = { + { CTL_INT, NET_ROSE_RESTART_REQUEST_TIMEOUT, "restart_request_timeout" }, + { CTL_INT, NET_ROSE_CALL_REQUEST_TIMEOUT, "call_request_timeout" }, + { CTL_INT, NET_ROSE_RESET_REQUEST_TIMEOUT, "reset_request_timeout" }, + { CTL_INT, NET_ROSE_CLEAR_REQUEST_TIMEOUT, "clear_request_timeout" }, + { CTL_INT, NET_ROSE_ACK_HOLD_BACK_TIMEOUT, "acknowledge_hold_back_timeout" }, + { CTL_INT, NET_ROSE_ROUTING_CONTROL, "routing_control" }, + { CTL_INT, NET_ROSE_LINK_FAIL_TIMEOUT, "link_fail_timeout" }, + { CTL_INT, NET_ROSE_MAX_VCS, "maximum_virtual_circuits" }, + { CTL_INT, NET_ROSE_WINDOW_SIZE, "window_size" }, + { CTL_INT, NET_ROSE_NO_ACTIVITY_TIMEOUT, "no_activity_timeout" }, + {} +}; + +static const struct bin_table bin_net_ipv6_conf_var_table[] = { + { CTL_INT, NET_IPV6_FORWARDING, "forwarding" }, + { CTL_INT, NET_IPV6_HOP_LIMIT, "hop_limit" }, + { CTL_INT, NET_IPV6_MTU, "mtu" }, + { CTL_INT, NET_IPV6_ACCEPT_RA, "accept_ra" }, + { CTL_INT, NET_IPV6_ACCEPT_REDIRECTS, "accept_redirects" }, + { CTL_INT, NET_IPV6_AUTOCONF, "autoconf" }, + { CTL_INT, NET_IPV6_DAD_TRANSMITS, "dad_transmits" }, + { CTL_INT, NET_IPV6_RTR_SOLICITS, "router_solicitations" }, + { CTL_INT, NET_IPV6_RTR_SOLICIT_INTERVAL, "router_solicitation_interval" }, + { CTL_INT, NET_IPV6_RTR_SOLICIT_DELAY, "router_solicitation_delay" }, + { CTL_INT, NET_IPV6_USE_TEMPADDR, "use_tempaddr" }, + { CTL_INT, NET_IPV6_TEMP_VALID_LFT, "temp_valid_lft" }, + { CTL_INT, NET_IPV6_TEMP_PREFERED_LFT, "temp_prefered_lft" }, + { CTL_INT, NET_IPV6_REGEN_MAX_RETRY, "regen_max_retry" }, + { CTL_INT, NET_IPV6_MAX_DESYNC_FACTOR, "max_desync_factor" }, + { CTL_INT, NET_IPV6_MAX_ADDRESSES, "max_addresses" }, + { CTL_INT, NET_IPV6_FORCE_MLD_VERSION, "force_mld_version" }, + { CTL_INT, NET_IPV6_ACCEPT_RA_DEFRTR, "accept_ra_defrtr" }, + { CTL_INT, NET_IPV6_ACCEPT_RA_PINFO, "accept_ra_pinfo" }, + { CTL_INT, NET_IPV6_ACCEPT_RA_RTR_PREF, "accept_ra_rtr_pref" }, + { CTL_INT, NET_IPV6_RTR_PROBE_INTERVAL, "router_probe_interval" }, + { CTL_INT, NET_IPV6_ACCEPT_RA_RT_INFO_MAX_PLEN, "accept_ra_rt_info_max_plen" }, + { CTL_INT, NET_IPV6_PROXY_NDP, "proxy_ndp" }, + { CTL_INT, NET_IPV6_ACCEPT_SOURCE_ROUTE, "accept_source_route" }, + {} +}; + +static const struct bin_table bin_net_ipv6_conf_table[] = { + { CTL_DIR, NET_PROTO_CONF_ALL, "all", bin_net_ipv6_conf_var_table }, + { CTL_DIR, NET_PROTO_CONF_DEFAULT, "default", bin_net_ipv6_conf_var_table }, + { CTL_DIR, 0, NULL, bin_net_ipv6_conf_var_table }, + {} +}; + +static const struct bin_table bin_net_ipv6_route_table[] = { + /* NET_IPV6_ROUTE_FLUSH "flush" no longer used */ + { CTL_INT, NET_IPV6_ROUTE_GC_THRESH, "gc_thresh" }, + { CTL_INT, NET_IPV6_ROUTE_MAX_SIZE, "max_size" }, + { CTL_INT, NET_IPV6_ROUTE_GC_MIN_INTERVAL, "gc_min_interval" }, + { CTL_INT, NET_IPV6_ROUTE_GC_TIMEOUT, "gc_timeout" }, + { CTL_INT, NET_IPV6_ROUTE_GC_INTERVAL, "gc_interval" }, + { CTL_INT, NET_IPV6_ROUTE_GC_ELASTICITY, "gc_elasticity" }, + { CTL_INT, NET_IPV6_ROUTE_MTU_EXPIRES, "mtu_expires" }, + { CTL_INT, NET_IPV6_ROUTE_MIN_ADVMSS, "min_adv_mss" }, + { CTL_INT, NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS, "gc_min_interval_ms" }, + {} +}; + +static const struct bin_table bin_net_ipv6_icmp_table[] = { + { CTL_INT, NET_IPV6_ICMP_RATELIMIT, "ratelimit" }, + {} +}; + +static const struct bin_table bin_net_ipv6_table[] = { + { CTL_DIR, NET_IPV6_CONF, "conf", bin_net_ipv6_conf_table }, + { CTL_DIR, NET_IPV6_NEIGH, "neigh", bin_net_neigh_table }, + { CTL_DIR, NET_IPV6_ROUTE, "route", bin_net_ipv6_route_table }, + { CTL_DIR, NET_IPV6_ICMP, "icmp", bin_net_ipv6_icmp_table }, + { CTL_INT, NET_IPV6_BINDV6ONLY, "bindv6only" }, + { CTL_INT, NET_IPV6_IP6FRAG_HIGH_THRESH, "ip6frag_high_thresh" }, + { CTL_INT, NET_IPV6_IP6FRAG_LOW_THRESH, "ip6frag_low_thresh" }, + { CTL_INT, NET_IPV6_IP6FRAG_TIME, "ip6frag_time" }, + { CTL_INT, NET_IPV6_IP6FRAG_SECRET_INTERVAL, "ip6frag_secret_interval" }, + { CTL_INT, NET_IPV6_MLD_MAX_MSF, "mld_max_msf" }, + { CTL_INT, 2088 /* IPQ_QMAX */, "ip6_queue_maxlen" }, + {} +}; + +static const struct bin_table bin_net_x25_table[] = { + { CTL_INT, NET_X25_RESTART_REQUEST_TIMEOUT, "restart_request_timeout" }, + { CTL_INT, NET_X25_CALL_REQUEST_TIMEOUT, "call_request_timeout" }, + { CTL_INT, NET_X25_RESET_REQUEST_TIMEOUT, "reset_request_timeout" }, + { CTL_INT, NET_X25_CLEAR_REQUEST_TIMEOUT, "clear_request_timeout" }, + { CTL_INT, NET_X25_ACK_HOLD_BACK_TIMEOUT, "acknowledgement_hold_back_timeout" }, + { CTL_INT, NET_X25_FORWARD, "x25_forward" }, + {} +}; + +static const struct bin_table bin_net_tr_table[] = { + { CTL_INT, NET_TR_RIF_TIMEOUT, "rif_timeout" }, + {} +}; + + +static const struct bin_table bin_net_decnet_conf_vars[] = { + { CTL_INT, NET_DECNET_CONF_DEV_FORWARDING, "forwarding" }, + { CTL_INT, NET_DECNET_CONF_DEV_PRIORITY, "priority" }, + { CTL_INT, NET_DECNET_CONF_DEV_T2, "t2" }, + { CTL_INT, NET_DECNET_CONF_DEV_T3, "t3" }, + {} +}; + +static const struct bin_table bin_net_decnet_conf[] = { + { CTL_DIR, NET_DECNET_CONF_ETHER, "ethernet", bin_net_decnet_conf_vars }, + { CTL_DIR, NET_DECNET_CONF_GRE, "ipgre", bin_net_decnet_conf_vars }, + { CTL_DIR, NET_DECNET_CONF_X25, "x25", bin_net_decnet_conf_vars }, + { CTL_DIR, NET_DECNET_CONF_PPP, "ppp", bin_net_decnet_conf_vars }, + { CTL_DIR, NET_DECNET_CONF_DDCMP, "ddcmp", bin_net_decnet_conf_vars }, + { CTL_DIR, NET_DECNET_CONF_LOOPBACK, "loopback", bin_net_decnet_conf_vars }, + { CTL_DIR, 0, NULL, bin_net_decnet_conf_vars }, + {} +}; + +static const struct bin_table bin_net_decnet_table[] = { + { CTL_DIR, NET_DECNET_CONF, "conf", bin_net_decnet_conf }, + { CTL_DNADR, NET_DECNET_NODE_ADDRESS, "node_address" }, + { CTL_STR, NET_DECNET_NODE_NAME, "node_name" }, + { CTL_STR, NET_DECNET_DEFAULT_DEVICE, "default_device" }, + { CTL_INT, NET_DECNET_TIME_WAIT, "time_wait" }, + { CTL_INT, NET_DECNET_DN_COUNT, "dn_count" }, + { CTL_INT, NET_DECNET_DI_COUNT, "di_count" }, + { CTL_INT, NET_DECNET_DR_COUNT, "dr_count" }, + { CTL_INT, NET_DECNET_DST_GC_INTERVAL, "dst_gc_interval" }, + { CTL_INT, NET_DECNET_NO_FC_MAX_CWND, "no_fc_max_cwnd" }, + { CTL_INT, NET_DECNET_MEM, "decnet_mem" }, + { CTL_INT, NET_DECNET_RMEM, "decnet_rmem" }, + { CTL_INT, NET_DECNET_WMEM, "decnet_wmem" }, + { CTL_INT, NET_DECNET_DEBUG_LEVEL, "debug" }, + {} +}; + +static const struct bin_table bin_net_sctp_table[] = { + { CTL_INT, NET_SCTP_RTO_INITIAL, "rto_initial" }, + { CTL_INT, NET_SCTP_RTO_MIN, "rto_min" }, + { CTL_INT, NET_SCTP_RTO_MAX, "rto_max" }, + { CTL_INT, NET_SCTP_RTO_ALPHA, "rto_alpha_exp_divisor" }, + { CTL_INT, NET_SCTP_RTO_BETA, "rto_beta_exp_divisor" }, + { CTL_INT, NET_SCTP_VALID_COOKIE_LIFE, "valid_cookie_life" }, + { CTL_INT, NET_SCTP_ASSOCIATION_MAX_RETRANS, "association_max_retrans" }, + { CTL_INT, NET_SCTP_PATH_MAX_RETRANS, "path_max_retrans" }, + { CTL_INT, NET_SCTP_MAX_INIT_RETRANSMITS, "max_init_retransmits" }, + { CTL_INT, NET_SCTP_HB_INTERVAL, "hb_interval" }, + { CTL_INT, NET_SCTP_PRESERVE_ENABLE, "cookie_preserve_enable" }, + { CTL_INT, NET_SCTP_MAX_BURST, "max_burst" }, + { CTL_INT, NET_SCTP_ADDIP_ENABLE, "addip_enable" }, + { CTL_INT, NET_SCTP_PRSCTP_ENABLE, "prsctp_enable" }, + { CTL_INT, NET_SCTP_SNDBUF_POLICY, "sndbuf_policy" }, + { CTL_INT, NET_SCTP_SACK_TIMEOUT, "sack_timeout" }, + { CTL_INT, NET_SCTP_RCVBUF_POLICY, "rcvbuf_policy" }, + {} +}; + +static const struct bin_table bin_net_llc_llc2_timeout_table[] = { + { CTL_INT, NET_LLC2_ACK_TIMEOUT, "ack" }, + { CTL_INT, NET_LLC2_P_TIMEOUT, "p" }, + { CTL_INT, NET_LLC2_REJ_TIMEOUT, "rej" }, + { CTL_INT, NET_LLC2_BUSY_TIMEOUT, "busy" }, + {} +}; + +static const struct bin_table bin_net_llc_station_table[] = { + { CTL_INT, NET_LLC_STATION_ACK_TIMEOUT, "ack_timeout" }, + {} +}; + +static const struct bin_table bin_net_llc_llc2_table[] = { + { CTL_DIR, NET_LLC2, "timeout", bin_net_llc_llc2_timeout_table }, + {} +}; + +static const struct bin_table bin_net_llc_table[] = { + { CTL_DIR, NET_LLC2, "llc2", bin_net_llc_llc2_table }, + { CTL_DIR, NET_LLC_STATION, "station", bin_net_llc_station_table }, + {} +}; + +static const struct bin_table bin_net_netfilter_table[] = { + { CTL_INT, NET_NF_CONNTRACK_MAX, "nf_conntrack_max" }, + /* NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT "nf_conntrack_tcp_timeout_syn_sent" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV "nf_conntrack_tcp_timeout_syn_recv" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED "nf_conntrack_tcp_timeout_established" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT "nf_conntrack_tcp_timeout_fin_wait" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT "nf_conntrack_tcp_timeout_close_wait" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK "nf_conntrack_tcp_timeout_last_ack" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT "nf_conntrack_tcp_timeout_time_wait" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE "nf_conntrack_tcp_timeout_close" no longer used */ + /* NET_NF_CONNTRACK_UDP_TIMEOUT "nf_conntrack_udp_timeout" no longer used */ + /* NET_NF_CONNTRACK_UDP_TIMEOUT_STREAM "nf_conntrack_udp_timeout_stream" no longer used */ + /* NET_NF_CONNTRACK_ICMP_TIMEOUT "nf_conntrack_icmp_timeout" no longer used */ + /* NET_NF_CONNTRACK_GENERIC_TIMEOUT "nf_conntrack_generic_timeout" no longer used */ + { CTL_INT, NET_NF_CONNTRACK_BUCKETS, "nf_conntrack_buckets" }, + { CTL_INT, NET_NF_CONNTRACK_LOG_INVALID, "nf_conntrack_log_invalid" }, + /* NET_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS "nf_conntrack_tcp_timeout_max_retrans" no longer used */ + { CTL_INT, NET_NF_CONNTRACK_TCP_LOOSE, "nf_conntrack_tcp_loose" }, + { CTL_INT, NET_NF_CONNTRACK_TCP_BE_LIBERAL, "nf_conntrack_tcp_be_liberal" }, + { CTL_INT, NET_NF_CONNTRACK_TCP_MAX_RETRANS, "nf_conntrack_tcp_max_retrans" }, + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED "nf_conntrack_sctp_timeout_closed" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT "nf_conntrack_sctp_timeout_cookie_wait" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED "nf_conntrack_sctp_timeout_cookie_echoed" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED "nf_conntrack_sctp_timeout_established" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT "nf_conntrack_sctp_timeout_shutdown_sent" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD "nf_conntrack_sctp_timeout_shutdown_recd" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT "nf_conntrack_sctp_timeout_shutdown_ack_sent" no longer used */ + { CTL_INT, NET_NF_CONNTRACK_COUNT, "nf_conntrack_count" }, + /* NET_NF_CONNTRACK_ICMPV6_TIMEOUT "nf_conntrack_icmpv6_timeout" no longer used */ + /* NET_NF_CONNTRACK_FRAG6_TIMEOUT "nf_conntrack_frag6_timeout" no longer used */ + { CTL_INT, NET_NF_CONNTRACK_FRAG6_LOW_THRESH, "nf_conntrack_frag6_low_thresh" }, + { CTL_INT, NET_NF_CONNTRACK_FRAG6_HIGH_THRESH, "nf_conntrack_frag6_high_thresh" }, + { CTL_INT, NET_NF_CONNTRACK_CHECKSUM, "nf_conntrack_checksum" }, + + {} +}; + +static const struct bin_table bin_net_irda_table[] = { + { CTL_INT, NET_IRDA_DISCOVERY, "discovery" }, + { CTL_STR, NET_IRDA_DEVNAME, "devname" }, + { CTL_INT, NET_IRDA_DEBUG, "debug" }, + { CTL_INT, NET_IRDA_FAST_POLL, "fast_poll_increase" }, + { CTL_INT, NET_IRDA_DISCOVERY_SLOTS, "discovery_slots" }, + { CTL_INT, NET_IRDA_DISCOVERY_TIMEOUT, "discovery_timeout" }, + { CTL_INT, NET_IRDA_SLOT_TIMEOUT, "slot_timeout" }, + { CTL_INT, NET_IRDA_MAX_BAUD_RATE, "max_baud_rate" }, + { CTL_INT, NET_IRDA_MIN_TX_TURN_TIME, "min_tx_turn_time" }, + { CTL_INT, NET_IRDA_MAX_TX_DATA_SIZE, "max_tx_data_size" }, + { CTL_INT, NET_IRDA_MAX_TX_WINDOW, "max_tx_window" }, + { CTL_INT, NET_IRDA_MAX_NOREPLY_TIME, "max_noreply_time" }, + { CTL_INT, NET_IRDA_WARN_NOREPLY_TIME, "warn_noreply_time" }, + { CTL_INT, NET_IRDA_LAP_KEEPALIVE_TIME, "lap_keepalive_time" }, + {} +}; + +static const struct bin_table bin_net_table[] = { + { CTL_DIR, NET_CORE, "core", bin_net_core_table }, + /* NET_ETHER not used */ + /* NET_802 not used */ + { CTL_DIR, NET_UNIX, "unix", bin_net_unix_table }, + { CTL_DIR, NET_IPV4, "ipv4", bin_net_ipv4_table }, + { CTL_DIR, NET_IPX, "ipx", bin_net_ipx_table }, + { CTL_DIR, NET_ATALK, "appletalk", bin_net_atalk_table }, + { CTL_DIR, NET_NETROM, "netrom", bin_net_netrom_table }, + { CTL_DIR, NET_AX25, "ax25", bin_net_ax25_table }, + /* NET_BRIDGE "bridge" no longer used */ + { CTL_DIR, NET_ROSE, "rose", bin_net_rose_table }, + { CTL_DIR, NET_IPV6, "ipv6", bin_net_ipv6_table }, + { CTL_DIR, NET_X25, "x25", bin_net_x25_table }, + { CTL_DIR, NET_TR, "token-ring", bin_net_tr_table }, + { CTL_DIR, NET_DECNET, "decnet", bin_net_decnet_table }, + /* NET_ECONET not used */ + { CTL_DIR, NET_SCTP, "sctp", bin_net_sctp_table }, + { CTL_DIR, NET_LLC, "llc", bin_net_llc_table }, + { CTL_DIR, NET_NETFILTER, "netfilter", bin_net_netfilter_table }, + /* NET_DCCP "dccp" no longer used */ + { CTL_DIR, NET_IRDA, "irda", bin_net_irda_table }, + { CTL_INT, 2089, "nf_conntrack_max" }, + {} +}; + +static const struct bin_table bin_fs_quota_table[] = { + { CTL_INT, FS_DQ_LOOKUPS, "lookups" }, + { CTL_INT, FS_DQ_DROPS, "drops" }, + { CTL_INT, FS_DQ_READS, "reads" }, + { CTL_INT, FS_DQ_WRITES, "writes" }, + { CTL_INT, FS_DQ_CACHE_HITS, "cache_hits" }, + { CTL_INT, FS_DQ_ALLOCATED, "allocated_dquots" }, + { CTL_INT, FS_DQ_FREE, "free_dquots" }, + { CTL_INT, FS_DQ_SYNCS, "syncs" }, + { CTL_INT, FS_DQ_WARNINGS, "warnings" }, + {} +}; + +static const struct bin_table bin_fs_xfs_table[] = { + { CTL_INT, XFS_SGID_INHERIT, "irix_sgid_inherit" }, + { CTL_INT, XFS_SYMLINK_MODE, "irix_symlink_mode" }, + { CTL_INT, XFS_PANIC_MASK, "panic_mask" }, + + { CTL_INT, XFS_ERRLEVEL, "error_level" }, + { CTL_INT, XFS_SYNCD_TIMER, "xfssyncd_centisecs" }, + { CTL_INT, XFS_INHERIT_SYNC, "inherit_sync" }, + { CTL_INT, XFS_INHERIT_NODUMP, "inherit_nodump" }, + { CTL_INT, XFS_INHERIT_NOATIME, "inherit_noatime" }, + { CTL_INT, XFS_BUF_TIMER, "xfsbufd_centisecs" }, + { CTL_INT, XFS_BUF_AGE, "age_buffer_centisecs" }, + { CTL_INT, XFS_INHERIT_NOSYM, "inherit_nosymlinks" }, + { CTL_INT, XFS_ROTORSTEP, "rotorstep" }, + { CTL_INT, XFS_INHERIT_NODFRG, "inherit_nodefrag" }, + { CTL_INT, XFS_FILESTREAM_TIMER, "filestream_centisecs" }, + { CTL_INT, XFS_STATS_CLEAR, "stats_clear" }, + {} +}; + +static const struct bin_table bin_fs_ocfs2_nm_table[] = { + { CTL_STR, 1, "hb_ctl_path" }, + {} +}; + +static const struct bin_table bin_fs_ocfs2_table[] = { + { CTL_DIR, 1, "nm", bin_fs_ocfs2_nm_table }, + {} +}; + +static const struct bin_table bin_inotify_table[] = { + { CTL_INT, INOTIFY_MAX_USER_INSTANCES, "max_user_instances" }, + { CTL_INT, INOTIFY_MAX_USER_WATCHES, "max_user_watches" }, + { CTL_INT, INOTIFY_MAX_QUEUED_EVENTS, "max_queued_events" }, + {} +}; + +static const struct bin_table bin_fs_table[] = { + { CTL_INT, FS_NRINODE, "inode-nr" }, + { CTL_INT, FS_STATINODE, "inode-state" }, + /* FS_MAXINODE unused */ + /* FS_NRDQUOT unused */ + /* FS_MAXDQUOT unused */ + /* FS_NRFILE "file-nr" no longer used */ + { CTL_INT, FS_MAXFILE, "file-max" }, + { CTL_INT, FS_DENTRY, "dentry-state" }, + /* FS_NRSUPER unused */ + /* FS_MAXUPSER unused */ + { CTL_INT, FS_OVERFLOWUID, "overflowuid" }, + { CTL_INT, FS_OVERFLOWGID, "overflowgid" }, + { CTL_INT, FS_LEASES, "leases-enable" }, + { CTL_INT, FS_DIR_NOTIFY, "dir-notify-enable" }, + { CTL_INT, FS_LEASE_TIME, "lease-break-time" }, + { CTL_DIR, FS_DQSTATS, "quota", bin_fs_quota_table }, + { CTL_DIR, FS_XFS, "xfs", bin_fs_xfs_table }, + { CTL_ULONG, FS_AIO_NR, "aio-nr" }, + { CTL_ULONG, FS_AIO_MAX_NR, "aio-max-nr" }, + { CTL_DIR, FS_INOTIFY, "inotify", bin_inotify_table }, + { CTL_DIR, FS_OCFS2, "ocfs2", bin_fs_ocfs2_table }, + { CTL_INT, KERN_SETUID_DUMPABLE, "suid_dumpable" }, + {} +}; + +static const struct bin_table bin_ipmi_table[] = { + { CTL_INT, DEV_IPMI_POWEROFF_POWERCYCLE, "poweroff_powercycle" }, + {} +}; + +static const struct bin_table bin_mac_hid_files[] = { + /* DEV_MAC_HID_KEYBOARD_SENDS_LINUX_KEYCODES unused */ + /* DEV_MAC_HID_KEYBOARD_LOCK_KEYCODES unused */ + { CTL_INT, DEV_MAC_HID_MOUSE_BUTTON_EMULATION, "mouse_button_emulation" }, + { CTL_INT, DEV_MAC_HID_MOUSE_BUTTON2_KEYCODE, "mouse_button2_keycode" }, + { CTL_INT, DEV_MAC_HID_MOUSE_BUTTON3_KEYCODE, "mouse_button3_keycode" }, + /* DEV_MAC_HID_ADB_MOUSE_SENDS_KEYCODES unused */ + {} +}; + +static const struct bin_table bin_raid_table[] = { + { CTL_INT, DEV_RAID_SPEED_LIMIT_MIN, "speed_limit_min" }, + { CTL_INT, DEV_RAID_SPEED_LIMIT_MAX, "speed_limit_max" }, + {} +}; + +static const struct bin_table bin_scsi_table[] = { + { CTL_INT, DEV_SCSI_LOGGING_LEVEL, "logging_level" }, + {} +}; + +static const struct bin_table bin_dev_table[] = { + /* DEV_CDROM "cdrom" no longer used */ + /* DEV_HWMON unused */ + /* DEV_PARPORT "parport" no longer used */ + { CTL_DIR, DEV_RAID, "raid", bin_raid_table }, + { CTL_DIR, DEV_MAC_HID, "mac_hid", bin_mac_hid_files }, + { CTL_DIR, DEV_SCSI, "scsi", bin_scsi_table }, + { CTL_DIR, DEV_IPMI, "ipmi", bin_ipmi_table }, + {} +}; + +static const struct bin_table bin_bus_isa_table[] = { + { CTL_INT, BUS_ISA_MEM_BASE, "membase" }, + { CTL_INT, BUS_ISA_PORT_BASE, "portbase" }, + { CTL_INT, BUS_ISA_PORT_SHIFT, "portshift" }, + {} +}; + +static const struct bin_table bin_bus_table[] = { + { CTL_DIR, CTL_BUS_ISA, "isa", bin_bus_isa_table }, + {} +}; + + +static const struct bin_table bin_s390dbf_table[] = { + { CTL_INT, 5678 /* CTL_S390DBF_STOPPABLE */, "debug_stoppable" }, + { CTL_INT, 5679 /* CTL_S390DBF_ACTIVE */, "debug_active" }, + {} +}; + +static const struct bin_table bin_sunrpc_table[] = { + /* CTL_RPCDEBUG "rpc_debug" no longer used */ + /* CTL_NFSDEBUG "nfs_debug" no longer used */ + /* CTL_NFSDDEBUG "nfsd_debug" no longer used */ + /* CTL_NLMDEBUG "nlm_debug" no longer used */ + + { CTL_INT, CTL_SLOTTABLE_UDP, "udp_slot_table_entries" }, + { CTL_INT, CTL_SLOTTABLE_TCP, "tcp_slot_table_entries" }, + { CTL_INT, CTL_MIN_RESVPORT, "min_resvport" }, + { CTL_INT, CTL_MAX_RESVPORT, "max_resvport" }, + {} +}; + +static const struct bin_table bin_pm_table[] = { + /* frv specific */ + /* 1 == CTL_PM_SUSPEND "suspend" no longer used" */ + { CTL_INT, 2 /* CTL_PM_CMODE */, "cmode" }, + { CTL_INT, 3 /* CTL_PM_P0 */, "p0" }, + { CTL_INT, 4 /* CTL_PM_CM */, "cm" }, + {} +}; + +static const struct bin_table bin_root_table[] = { + { CTL_DIR, CTL_KERN, "kernel", bin_kern_table }, + { CTL_DIR, CTL_VM, "vm", bin_vm_table }, + { CTL_DIR, CTL_NET, "net", bin_net_table }, + /* CTL_PROC not used */ + { CTL_DIR, CTL_FS, "fs", bin_fs_table }, + /* CTL_DEBUG "debug" no longer used */ + { CTL_DIR, CTL_DEV, "dev", bin_dev_table }, + { CTL_DIR, CTL_BUS, "bus", bin_bus_table }, + { CTL_DIR, CTL_ABI, "abi" }, + /* CTL_CPU not used */ + /* CTL_ARLAN "arlan" no longer used */ + { CTL_DIR, CTL_S390DBF, "s390dbf", bin_s390dbf_table }, + { CTL_DIR, CTL_SUNRPC, "sunrpc", bin_sunrpc_table }, + { CTL_DIR, CTL_PM, "pm", bin_pm_table }, + {} +}; + +static ssize_t bin_dir(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + return -ENOTDIR; +} + + +static ssize_t bin_string(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + ssize_t result, copied = 0; + + if (oldval && oldlen) { + char __user *lastp; + loff_t pos = 0; + int ch; + + result = vfs_read(file, oldval, oldlen, &pos); + if (result < 0) + goto out; + + copied = result; + lastp = oldval + copied - 1; + + result = -EFAULT; + if (get_user(ch, lastp)) + goto out; + + /* Trim off the trailing newline */ + if (ch == '\n') { + result = -EFAULT; + if (put_user('\0', lastp)) + goto out; + copied -= 1; + } + } + + if (newval && newlen) { + loff_t pos = 0; + + result = vfs_write(file, newval, newlen, &pos); + if (result < 0) + goto out; + } + + result = copied; +out: + return result; +} + +static ssize_t bin_intvec(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + mm_segment_t old_fs = get_fs(); + ssize_t copied = 0; + char *buffer; + ssize_t result; + + result = -ENOMEM; + buffer = kmalloc(BUFSZ, GFP_KERNEL); + if (!buffer) + goto out; + + if (oldval && oldlen) { + unsigned __user *vec = oldval; + size_t length = oldlen / sizeof(*vec); + loff_t pos = 0; + char *str, *end; + int i; + + set_fs(KERNEL_DS); + result = vfs_read(file, buffer, BUFSZ - 1, &pos); + set_fs(old_fs); + if (result < 0) + goto out_kfree; + + str = buffer; + end = str + result; + *end++ = '\0'; + for (i = 0; i < length; i++) { + unsigned long value; + + value = simple_strtoul(str, &str, 10); + while (isspace(*str)) + str++; + + result = -EFAULT; + if (put_user(value, vec + i)) + goto out_kfree; + + copied += sizeof(*vec); + if (!isdigit(*str)) + break; + } + } + + if (newval && newlen) { + unsigned __user *vec = newval; + size_t length = newlen / sizeof(*vec); + loff_t pos = 0; + char *str, *end; + int i; + + str = buffer; + end = str + BUFSZ; + for (i = 0; i < length; i++) { + unsigned long value; + + result = -EFAULT; + if (get_user(value, vec + i)) + goto out_kfree; + + str += snprintf(str, end - str, "%lu\t", value); + } + + set_fs(KERNEL_DS); + result = vfs_write(file, buffer, str - buffer, &pos); + set_fs(old_fs); + if (result < 0) + goto out_kfree; + } + result = copied; +out_kfree: + kfree(buffer); +out: + return result; +} + +static ssize_t bin_ulongvec(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + mm_segment_t old_fs = get_fs(); + ssize_t copied = 0; + char *buffer; + ssize_t result; + + result = -ENOMEM; + buffer = kmalloc(BUFSZ, GFP_KERNEL); + if (!buffer) + goto out; + + if (oldval && oldlen) { + unsigned long __user *vec = oldval; + size_t length = oldlen / sizeof(*vec); + loff_t pos = 0; + char *str, *end; + int i; + + set_fs(KERNEL_DS); + result = vfs_read(file, buffer, BUFSZ - 1, &pos); + set_fs(old_fs); + if (result < 0) + goto out_kfree; + + str = buffer; + end = str + result; + *end++ = '\0'; + for (i = 0; i < length; i++) { + unsigned long value; + + value = simple_strtoul(str, &str, 10); + while (isspace(*str)) + str++; + + result = -EFAULT; + if (put_user(value, vec + i)) + goto out_kfree; + + copied += sizeof(*vec); + if (!isdigit(*str)) + break; + } + } + + if (newval && newlen) { + unsigned long __user *vec = newval; + size_t length = newlen / sizeof(*vec); + loff_t pos = 0; + char *str, *end; + int i; + + str = buffer; + end = str + BUFSZ; + for (i = 0; i < length; i++) { + unsigned long value; + + result = -EFAULT; + if (get_user(value, vec + i)) + goto out_kfree; + + str += snprintf(str, end - str, "%lu\t", value); + } + + set_fs(KERNEL_DS); + result = vfs_write(file, buffer, str - buffer, &pos); + set_fs(old_fs); + if (result < 0) + goto out_kfree; + } + result = copied; +out_kfree: + kfree(buffer); +out: + return result; +} + +static unsigned hex_value(int ch) +{ + return isdigit(ch) ? ch - '0' : ((ch | 0x20) - 'a') + 10; +} + +static ssize_t bin_uuid(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + mm_segment_t old_fs = get_fs(); + ssize_t result, copied = 0; + + /* Only supports reads */ + if (oldval && oldlen) { + loff_t pos = 0; + char buf[40], *str = buf; + unsigned char uuid[16]; + int i; + + set_fs(KERNEL_DS); + result = vfs_read(file, buf, sizeof(buf) - 1, &pos); + set_fs(old_fs); + if (result < 0) + goto out; + + buf[result] = '\0'; + + /* Convert the uuid to from a string to binary */ + for (i = 0; i < 16; i++) { + result = -EIO; + if (!isxdigit(str[0]) || !isxdigit(str[1])) + goto out; + + uuid[i] = (hex_value(str[0]) << 4) | hex_value(str[1]); + str += 2; + if (*str == '-') + str++; + } + + if (oldlen > 16) + oldlen = 16; + + result = -EFAULT; + if (copy_to_user(oldval, uuid, oldlen)) + goto out; + + copied = oldlen; + } + result = copied; +out: + return result; +} + +static ssize_t bin_dn_node_address(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + mm_segment_t old_fs = get_fs(); + ssize_t result, copied = 0; + + if (oldval && oldlen) { + loff_t pos = 0; + char buf[15], *nodep; + unsigned long area, node; + __le16 dnaddr; + + set_fs(KERNEL_DS); + result = vfs_read(file, buf, sizeof(buf) - 1, &pos); + set_fs(old_fs); + if (result < 0) + goto out; + + buf[result] = '\0'; + + /* Convert the decnet addresss to binary */ + result = -EIO; + nodep = strchr(buf, '.') + 1; + if (!nodep) + goto out; + + area = simple_strtoul(buf, NULL, 10); + node = simple_strtoul(nodep, NULL, 10); + + result = -EIO; + if ((area > 63)||(node > 1023)) + goto out; + + dnaddr = cpu_to_le16((area << 10) | node); + + result = -EFAULT; + if (put_user(dnaddr, (__le16 __user *)oldval)) + goto out; + + copied = sizeof(dnaddr); + } + + if (newval && newlen) { + loff_t pos = 0; + __le16 dnaddr; + char buf[15]; + int len; + + result = -EINVAL; + if (newlen != sizeof(dnaddr)) + goto out; + + result = -EFAULT; + if (get_user(dnaddr, (__le16 __user *)newval)) + goto out; + + len = snprintf(buf, sizeof(buf), "%hu.%hu", + le16_to_cpu(dnaddr) >> 10, + le16_to_cpu(dnaddr) & 0x3ff); + + set_fs(KERNEL_DS); + result = vfs_write(file, buf, len, &pos); + set_fs(old_fs); + if (result < 0) + goto out; + } + + result = copied; +out: + return result; +} + +static const struct bin_table *get_sysctl(const int *name, int nlen, char *path) +{ + const struct bin_table *table = &bin_root_table[0]; + int ctl_name; + + /* The binary sysctl tables have a small maximum depth so + * there is no danger of overflowing our path as it PATH_MAX + * bytes long. + */ + memcpy(path, "sys/", 4); + path += 4; + +repeat: + if (!nlen) + return ERR_PTR(-ENOTDIR); + ctl_name = *name; + name++; + nlen--; + for ( ; table->convert; table++) { + int len = 0; + + /* + * For a wild card entry map from ifindex to network + * device name. + */ + if (!table->ctl_name) { +#ifdef CONFIG_NET + struct net *net = current->nsproxy->net_ns; + struct net_device *dev; + dev = dev_get_by_index(net, ctl_name); + if (dev) { + len = strlen(dev->name); + memcpy(path, dev->name, len); + dev_put(dev); + } +#endif + /* Use the well known sysctl number to proc name mapping */ + } else if (ctl_name == table->ctl_name) { + len = strlen(table->procname); + memcpy(path, table->procname, len); + } + if (len) { + path += len; + if (table->child) { + *path++ = '/'; + table = table->child; + goto repeat; + } + *path = '\0'; + return table; + } + } + return ERR_PTR(-ENOTDIR); +} + +static char *sysctl_getname(const int *name, int nlen, const struct bin_table **tablep) +{ + char *tmp, *result; + + result = ERR_PTR(-ENOMEM); + tmp = __getname(); + if (tmp) { + const struct bin_table *table = get_sysctl(name, nlen, tmp); + result = tmp; + *tablep = table; + if (IS_ERR(table)) { + __putname(tmp); + result = ERR_CAST(table); + } + } + return result; +} + +static ssize_t binary_sysctl(const int *name, int nlen, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + const struct bin_table *table = NULL; + struct nameidata nd; + struct vfsmount *mnt; + struct file *file; + ssize_t result; + char *pathname; + int flags; + int acc_mode, fmode; + + pathname = sysctl_getname(name, nlen, &table); + result = PTR_ERR(pathname); + if (IS_ERR(pathname)) + goto out; + + /* How should the sysctl be accessed? */ + if (oldval && oldlen && newval && newlen) { + flags = O_RDWR; + acc_mode = MAY_READ | MAY_WRITE; + fmode = FMODE_READ | FMODE_WRITE; + } else if (newval && newlen) { + flags = O_WRONLY; + acc_mode = MAY_WRITE; + fmode = FMODE_WRITE; + } else if (oldval && oldlen) { + flags = O_RDONLY; + acc_mode = MAY_READ; + fmode = FMODE_READ; + } else { + result = 0; + goto out_putname; + } + + mnt = current->nsproxy->pid_ns->proc_mnt; + result = vfs_path_lookup(mnt->mnt_root, mnt, pathname, 0, &nd); + if (result) + goto out_putname; + + result = may_open(&nd.path, acc_mode, fmode); + if (result) + goto out_putpath; + + file = dentry_open(nd.path.dentry, nd.path.mnt, flags, current_cred()); + result = PTR_ERR(file); + if (IS_ERR(file)) + goto out_putname; + + result = table->convert(file, oldval, oldlen, newval, newlen); + + fput(file); +out_putname: + putname(pathname); +out: + return result; + +out_putpath: + path_put(&nd.path); + goto out_putname; +} + + +#else /* CONFIG_SYSCTL_SYSCALL */ + +static ssize_t binary_sysctl(const int *name, int nlen, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + return -ENOSYS; +} + +#endif /* CONFIG_SYSCTL_SYSCALL */ + + +static void deprecated_sysctl_warning(const int *name, int nlen) +{ + int i; + + if (printk_ratelimit()) { + printk(KERN_INFO + "warning: process `%s' used the deprecated sysctl " + "system call with ", current->comm); + for (i = 0; i < nlen; i++) + printk("%d.", name[i]); + printk("\n"); + } + return; +} + +static ssize_t do_sysctl(int __user *args_name, int nlen, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + int name[CTL_MAXNAME]; + int i; + + /* Check args->nlen. */ + if (nlen < 0 || nlen > CTL_MAXNAME) + return -ENOTDIR; + /* Read in the sysctl name for simplicity */ + for (i = 0; i < nlen; i++) + if (get_user(name[i], args_name + i)) + return -EFAULT; + + deprecated_sysctl_warning(name, nlen); + + return binary_sysctl(name, nlen, oldval, oldlen, newval, newlen); +} + +SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args) +{ + struct __sysctl_args tmp; + size_t oldlen = 0; + ssize_t result; + + if (copy_from_user(&tmp, args, sizeof(tmp))) + return -EFAULT; + + if (tmp.oldval && !tmp.oldlenp) + return -EFAULT; + + if (tmp.oldlenp && get_user(oldlen, tmp.oldlenp)) + return -EFAULT; + + result = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, oldlen, + tmp.newval, tmp.newlen); + + if (result >= 0) { + oldlen = result; + result = 0; + } + + if (tmp.oldlenp && put_user(oldlen, tmp.oldlenp)) + return -EFAULT; + + return result; +} + + +#ifdef CONFIG_COMPAT +#include <asm/compat.h> + +struct compat_sysctl_args { + compat_uptr_t name; + int nlen; + compat_uptr_t oldval; + compat_uptr_t oldlenp; + compat_uptr_t newval; + compat_size_t newlen; + compat_ulong_t __unused[4]; +}; + +asmlinkage long compat_sys_sysctl(struct compat_sysctl_args __user *args) +{ + struct compat_sysctl_args tmp; + compat_size_t __user *compat_oldlenp; + size_t oldlen = 0; + ssize_t result; + + if (copy_from_user(&tmp, args, sizeof(tmp))) + return -EFAULT; + + if (tmp.oldval && !tmp.oldlenp) + return -EFAULT; + + compat_oldlenp = compat_ptr(tmp.oldlenp); + if (compat_oldlenp && get_user(oldlen, compat_oldlenp)) + return -EFAULT; + + result = do_sysctl(compat_ptr(tmp.name), tmp.nlen, + compat_ptr(tmp.oldval), oldlen, + compat_ptr(tmp.newval), tmp.newlen); + + if (result >= 0) { + oldlen = result; + result = 0; + } + + if (compat_oldlenp && put_user(oldlen, compat_oldlenp)) + return -EFAULT; + + return result; +} + +#endif /* CONFIG_COMPAT */ diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c index b6e7aae..04cdcf7 100644 --- a/kernel/sysctl_check.c +++ b/kernel/sysctl_check.c @@ -5,1239 +5,6 @@ #include <linux/string.h> #include <net/ip_vs.h> -struct trans_ctl_table { - int ctl_name; - const char *procname; - const struct trans_ctl_table *child; -}; - -static const struct trans_ctl_table trans_random_table[] = { - { RANDOM_POOLSIZE, "poolsize" }, - { RANDOM_ENTROPY_COUNT, "entropy_avail" }, - { RANDOM_READ_THRESH, "read_wakeup_threshold" }, - { RANDOM_WRITE_THRESH, "write_wakeup_threshold" }, - { RANDOM_BOOT_ID, "boot_id" }, - { RANDOM_UUID, "uuid" }, - {} -}; - -static const struct trans_ctl_table trans_pty_table[] = { - { PTY_MAX, "max" }, - { PTY_NR, "nr" }, - {} -}; - -static const struct trans_ctl_table trans_kern_table[] = { - { KERN_OSTYPE, "ostype" }, - { KERN_OSRELEASE, "osrelease" }, - /* KERN_OSREV not used */ - { KERN_VERSION, "version" }, - /* KERN_SECUREMASK not used */ - /* KERN_PROF not used */ - { KERN_NODENAME, "hostname" }, - { KERN_DOMAINNAME, "domainname" }, - - { KERN_PANIC, "panic" }, - { KERN_REALROOTDEV, "real-root-dev" }, - - { KERN_SPARC_REBOOT, "reboot-cmd" }, - { KERN_CTLALTDEL, "ctrl-alt-del" }, - { KERN_PRINTK, "printk" }, - - /* KERN_NAMETRANS not used */ - /* KERN_PPC_HTABRECLAIM not used */ - /* KERN_PPC_ZEROPAGED not used */ - { KERN_PPC_POWERSAVE_NAP, "powersave-nap" }, - - { KERN_MODPROBE, "modprobe" }, - { KERN_SG_BIG_BUFF, "sg-big-buff" }, - { KERN_ACCT, "acct" }, - { KERN_PPC_L2CR, "l2cr" }, - - /* KERN_RTSIGNR not used */ - /* KERN_RTSIGMAX not used */ - - { KERN_SHMMAX, "shmmax" }, - { KERN_MSGMAX, "msgmax" }, - { KERN_MSGMNB, "msgmnb" }, - /* KERN_MSGPOOL not used*/ - { KERN_SYSRQ, "sysrq" }, - { KERN_MAX_THREADS, "threads-max" }, - { KERN_RANDOM, "random", trans_random_table }, - { KERN_SHMALL, "shmall" }, - { KERN_MSGMNI, "msgmni" }, - { KERN_SEM, "sem" }, - { KERN_SPARC_STOP_A, "stop-a" }, - { KERN_SHMMNI, "shmmni" }, - - { KERN_OVERFLOWUID, "overflowuid" }, - { KERN_OVERFLOWGID, "overflowgid" }, - - { KERN_HOTPLUG, "hotplug", }, - { KERN_IEEE_EMULATION_WARNINGS, "ieee_emulation_warnings" }, - - { KERN_S390_USER_DEBUG_LOGGING, "userprocess_debug" }, - { KERN_CORE_USES_PID, "core_uses_pid" }, - { KERN_TAINTED, "tainted" }, - { KERN_CADPID, "cad_pid" }, - { KERN_PIDMAX, "pid_max" }, - { KERN_CORE_PATTERN, "core_pattern" }, - { KERN_PANIC_ON_OOPS, "panic_on_oops" }, - { KERN_HPPA_PWRSW, "soft-power" }, - { KERN_HPPA_UNALIGNED, "unaligned-trap" }, - - { KERN_PRINTK_RATELIMIT, "printk_ratelimit" }, - { KERN_PRINTK_RATELIMIT_BURST, "printk_ratelimit_burst" }, - - { KERN_PTY, "pty", trans_pty_table }, - { KERN_NGROUPS_MAX, "ngroups_max" }, - { KERN_SPARC_SCONS_PWROFF, "scons-poweroff" }, - { KERN_HZ_TIMER, "hz_timer" }, - { KERN_UNKNOWN_NMI_PANIC, "unknown_nmi_panic" }, - { KERN_BOOTLOADER_TYPE, "bootloader_type" }, - { KERN_RANDOMIZE, "randomize_va_space" }, - - { KERN_SPIN_RETRY, "spin_retry" }, - { KERN_ACPI_VIDEO_FLAGS, "acpi_video_flags" }, - { KERN_IA64_UNALIGNED, "ignore-unaligned-usertrap" }, - { KERN_COMPAT_LOG, "compat-log" }, - { KERN_MAX_LOCK_DEPTH, "max_lock_depth" }, - { KERN_NMI_WATCHDOG, "nmi_watchdog" }, - { KERN_PANIC_ON_NMI, "panic_on_unrecovered_nmi" }, - {} -}; - -static const struct trans_ctl_table trans_vm_table[] = { - { VM_OVERCOMMIT_MEMORY, "overcommit_memory" }, - { VM_PAGE_CLUSTER, "page-cluster" }, - { VM_DIRTY_BACKGROUND, "dirty_background_ratio" }, - { VM_DIRTY_RATIO, "dirty_ratio" }, - { VM_DIRTY_WB_CS, "dirty_writeback_centisecs" }, - { VM_DIRTY_EXPIRE_CS, "dirty_expire_centisecs" }, - { VM_NR_PDFLUSH_THREADS, "nr_pdflush_threads" }, - { VM_OVERCOMMIT_RATIO, "overcommit_ratio" }, - /* VM_PAGEBUF unused */ - { VM_HUGETLB_PAGES, "nr_hugepages" }, - { VM_SWAPPINESS, "swappiness" }, - { VM_LOWMEM_RESERVE_RATIO, "lowmem_reserve_ratio" }, - { VM_MIN_FREE_KBYTES, "min_free_kbytes" }, - { VM_MAX_MAP_COUNT, "max_map_count" }, - { VM_LAPTOP_MODE, "laptop_mode" }, - { VM_BLOCK_DUMP, "block_dump" }, - { VM_HUGETLB_GROUP, "hugetlb_shm_group" }, - { VM_VFS_CACHE_PRESSURE, "vfs_cache_pressure" }, - { VM_LEGACY_VA_LAYOUT, "legacy_va_layout" }, - /* VM_SWAP_TOKEN_TIMEOUT unused */ - { VM_DROP_PAGECACHE, "drop_caches" }, - { VM_PERCPU_PAGELIST_FRACTION, "percpu_pagelist_fraction" }, - { VM_ZONE_RECLAIM_MODE, "zone_reclaim_mode" }, - { VM_MIN_UNMAPPED, "min_unmapped_ratio" }, - { VM_PANIC_ON_OOM, "panic_on_oom" }, - { VM_VDSO_ENABLED, "vdso_enabled" }, - { VM_MIN_SLAB, "min_slab_ratio" }, - - {} -}; - -static const struct trans_ctl_table trans_net_core_table[] = { - { NET_CORE_WMEM_MAX, "wmem_max" }, - { NET_CORE_RMEM_MAX, "rmem_max" }, - { NET_CORE_WMEM_DEFAULT, "wmem_default" }, - { NET_CORE_RMEM_DEFAULT, "rmem_default" }, - /* NET_CORE_DESTROY_DELAY unused */ - { NET_CORE_MAX_BACKLOG, "netdev_max_backlog" }, - /* NET_CORE_FASTROUTE unused */ - { NET_CORE_MSG_COST, "message_cost" }, - { NET_CORE_MSG_BURST, "message_burst" }, - { NET_CORE_OPTMEM_MAX, "optmem_max" }, - /* NET_CORE_HOT_LIST_LENGTH unused */ - /* NET_CORE_DIVERT_VERSION unused */ - /* NET_CORE_NO_CONG_THRESH unused */ - /* NET_CORE_NO_CONG unused */ - /* NET_CORE_LO_CONG unused */ - /* NET_CORE_MOD_CONG unused */ - { NET_CORE_DEV_WEIGHT, "dev_weight" }, - { NET_CORE_SOMAXCONN, "somaxconn" }, - { NET_CORE_BUDGET, "netdev_budget" }, - { NET_CORE_AEVENT_ETIME, "xfrm_aevent_etime" }, - { NET_CORE_AEVENT_RSEQTH, "xfrm_aevent_rseqth" }, - { NET_CORE_WARNINGS, "warnings" }, - {}, -}; - -static const struct trans_ctl_table trans_net_unix_table[] = { - /* NET_UNIX_DESTROY_DELAY unused */ - /* NET_UNIX_DELETE_DELAY unused */ - { NET_UNIX_MAX_DGRAM_QLEN, "max_dgram_qlen" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv4_route_table[] = { - { NET_IPV4_ROUTE_FLUSH, "flush" }, - { NET_IPV4_ROUTE_MIN_DELAY, "min_delay" }, - { NET_IPV4_ROUTE_MAX_DELAY, "max_delay" }, - { NET_IPV4_ROUTE_GC_THRESH, "gc_thresh" }, - { NET_IPV4_ROUTE_MAX_SIZE, "max_size" }, - { NET_IPV4_ROUTE_GC_MIN_INTERVAL, "gc_min_interval" }, - { NET_IPV4_ROUTE_GC_TIMEOUT, "gc_timeout" }, - { NET_IPV4_ROUTE_GC_INTERVAL, "gc_interval" }, - { NET_IPV4_ROUTE_REDIRECT_LOAD, "redirect_load" }, - { NET_IPV4_ROUTE_REDIRECT_NUMBER, "redirect_number" }, - { NET_IPV4_ROUTE_REDIRECT_SILENCE, "redirect_silence" }, - { NET_IPV4_ROUTE_ERROR_COST, "error_cost" }, - { NET_IPV4_ROUTE_ERROR_BURST, "error_burst" }, - { NET_IPV4_ROUTE_GC_ELASTICITY, "gc_elasticity" }, - { NET_IPV4_ROUTE_MTU_EXPIRES, "mtu_expires" }, - { NET_IPV4_ROUTE_MIN_PMTU, "min_pmtu" }, - { NET_IPV4_ROUTE_MIN_ADVMSS, "min_adv_mss" }, - { NET_IPV4_ROUTE_SECRET_INTERVAL, "secret_interval" }, - { NET_IPV4_ROUTE_GC_MIN_INTERVAL_MS, "gc_min_interval_ms" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv4_conf_vars_table[] = { - { NET_IPV4_CONF_FORWARDING, "forwarding" }, - { NET_IPV4_CONF_MC_FORWARDING, "mc_forwarding" }, - - { NET_IPV4_CONF_PROXY_ARP, "proxy_arp" }, - { NET_IPV4_CONF_ACCEPT_REDIRECTS, "accept_redirects" }, - { NET_IPV4_CONF_SECURE_REDIRECTS, "secure_redirects" }, - { NET_IPV4_CONF_SEND_REDIRECTS, "send_redirects" }, - { NET_IPV4_CONF_SHARED_MEDIA, "shared_media" }, - { NET_IPV4_CONF_RP_FILTER, "rp_filter" }, - { NET_IPV4_CONF_ACCEPT_SOURCE_ROUTE, "accept_source_route" }, - { NET_IPV4_CONF_BOOTP_RELAY, "bootp_relay" }, - { NET_IPV4_CONF_LOG_MARTIANS, "log_martians" }, - { NET_IPV4_CONF_TAG, "tag" }, - { NET_IPV4_CONF_ARPFILTER, "arp_filter" }, - { NET_IPV4_CONF_MEDIUM_ID, "medium_id" }, - { NET_IPV4_CONF_NOXFRM, "disable_xfrm" }, - { NET_IPV4_CONF_NOPOLICY, "disable_policy" }, - { NET_IPV4_CONF_FORCE_IGMP_VERSION, "force_igmp_version" }, - - { NET_IPV4_CONF_ARP_ANNOUNCE, "arp_announce" }, - { NET_IPV4_CONF_ARP_IGNORE, "arp_ignore" }, - { NET_IPV4_CONF_PROMOTE_SECONDARIES, "promote_secondaries" }, - { NET_IPV4_CONF_ARP_ACCEPT, "arp_accept" }, - { NET_IPV4_CONF_ARP_NOTIFY, "arp_notify" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv4_conf_table[] = { - { NET_PROTO_CONF_ALL, "all", trans_net_ipv4_conf_vars_table }, - { NET_PROTO_CONF_DEFAULT, "default", trans_net_ipv4_conf_vars_table }, - { 0, NULL, trans_net_ipv4_conf_vars_table }, - {} -}; - -static const struct trans_ctl_table trans_net_neigh_vars_table[] = { - { NET_NEIGH_MCAST_SOLICIT, "mcast_solicit" }, - { NET_NEIGH_UCAST_SOLICIT, "ucast_solicit" }, - { NET_NEIGH_APP_SOLICIT, "app_solicit" }, - { NET_NEIGH_RETRANS_TIME, "retrans_time" }, - { NET_NEIGH_REACHABLE_TIME, "base_reachable_time" }, - { NET_NEIGH_DELAY_PROBE_TIME, "delay_first_probe_time" }, - { NET_NEIGH_GC_STALE_TIME, "gc_stale_time" }, - { NET_NEIGH_UNRES_QLEN, "unres_qlen" }, - { NET_NEIGH_PROXY_QLEN, "proxy_qlen" }, - { NET_NEIGH_ANYCAST_DELAY, "anycast_delay" }, - { NET_NEIGH_PROXY_DELAY, "proxy_delay" }, - { NET_NEIGH_LOCKTIME, "locktime" }, - { NET_NEIGH_GC_INTERVAL, "gc_interval" }, - { NET_NEIGH_GC_THRESH1, "gc_thresh1" }, - { NET_NEIGH_GC_THRESH2, "gc_thresh2" }, - { NET_NEIGH_GC_THRESH3, "gc_thresh3" }, - { NET_NEIGH_RETRANS_TIME_MS, "retrans_time_ms" }, - { NET_NEIGH_REACHABLE_TIME_MS, "base_reachable_time_ms" }, - {} -}; - -static const struct trans_ctl_table trans_net_neigh_table[] = { - { NET_PROTO_CONF_DEFAULT, "default", trans_net_neigh_vars_table }, - { 0, NULL, trans_net_neigh_vars_table }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv4_netfilter_table[] = { - { NET_IPV4_NF_CONNTRACK_MAX, "ip_conntrack_max" }, - - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT, "ip_conntrack_tcp_timeout_syn_sent" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV, "ip_conntrack_tcp_timeout_syn_recv" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED, "ip_conntrack_tcp_timeout_established" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT, "ip_conntrack_tcp_timeout_fin_wait" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT, "ip_conntrack_tcp_timeout_close_wait" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK, "ip_conntrack_tcp_timeout_last_ack" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT, "ip_conntrack_tcp_timeout_time_wait" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE, "ip_conntrack_tcp_timeout_close" }, - - { NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT, "ip_conntrack_udp_timeout" }, - { NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT_STREAM, "ip_conntrack_udp_timeout_stream" }, - { NET_IPV4_NF_CONNTRACK_ICMP_TIMEOUT, "ip_conntrack_icmp_timeout" }, - { NET_IPV4_NF_CONNTRACK_GENERIC_TIMEOUT, "ip_conntrack_generic_timeout" }, - - { NET_IPV4_NF_CONNTRACK_BUCKETS, "ip_conntrack_buckets" }, - { NET_IPV4_NF_CONNTRACK_LOG_INVALID, "ip_conntrack_log_invalid" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS, "ip_conntrack_tcp_timeout_max_retrans" }, - { NET_IPV4_NF_CONNTRACK_TCP_LOOSE, "ip_conntrack_tcp_loose" }, - { NET_IPV4_NF_CONNTRACK_TCP_BE_LIBERAL, "ip_conntrack_tcp_be_liberal" }, - { NET_IPV4_NF_CONNTRACK_TCP_MAX_RETRANS, "ip_conntrack_tcp_max_retrans" }, - - { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED, "ip_conntrack_sctp_timeout_closed" }, - { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT, "ip_conntrack_sctp_timeout_cookie_wait" }, - { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED, "ip_conntrack_sctp_timeout_cookie_echoed" }, - { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED, "ip_conntrack_sctp_timeout_established" }, - { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT, "ip_conntrack_sctp_timeout_shutdown_sent" }, - { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD, "ip_conntrack_sctp_timeout_shutdown_recd" }, - { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT, "ip_conntrack_sctp_timeout_shutdown_ack_sent" }, - - { NET_IPV4_NF_CONNTRACK_COUNT, "ip_conntrack_count" }, - { NET_IPV4_NF_CONNTRACK_CHECKSUM, "ip_conntrack_checksum" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv4_table[] = { - { NET_IPV4_FORWARD, "ip_forward" }, - { NET_IPV4_DYNADDR, "ip_dynaddr" }, - - { NET_IPV4_CONF, "conf", trans_net_ipv4_conf_table }, - { NET_IPV4_NEIGH, "neigh", trans_net_neigh_table }, - { NET_IPV4_ROUTE, "route", trans_net_ipv4_route_table }, - /* NET_IPV4_FIB_HASH unused */ - { NET_IPV4_NETFILTER, "netfilter", trans_net_ipv4_netfilter_table }, - - { NET_IPV4_TCP_TIMESTAMPS, "tcp_timestamps" }, - { NET_IPV4_TCP_WINDOW_SCALING, "tcp_window_scaling" }, - { NET_IPV4_TCP_SACK, "tcp_sack" }, - { NET_IPV4_TCP_RETRANS_COLLAPSE, "tcp_retrans_collapse" }, - { NET_IPV4_DEFAULT_TTL, "ip_default_ttl" }, - /* NET_IPV4_AUTOCONFIG unused */ - { NET_IPV4_NO_PMTU_DISC, "ip_no_pmtu_disc" }, - { NET_IPV4_TCP_SYN_RETRIES, "tcp_syn_retries" }, - { NET_IPV4_IPFRAG_HIGH_THRESH, "ipfrag_high_thresh" }, - { NET_IPV4_IPFRAG_LOW_THRESH, "ipfrag_low_thresh" }, - { NET_IPV4_IPFRAG_TIME, "ipfrag_time" }, - /* NET_IPV4_TCP_MAX_KA_PROBES unused */ - { NET_IPV4_TCP_KEEPALIVE_TIME, "tcp_keepalive_time" }, - { NET_IPV4_TCP_KEEPALIVE_PROBES, "tcp_keepalive_probes" }, - { NET_IPV4_TCP_RETRIES1, "tcp_retries1" }, - { NET_IPV4_TCP_RETRIES2, "tcp_retries2" }, - { NET_IPV4_TCP_FIN_TIMEOUT, "tcp_fin_timeout" }, - /* NET_IPV4_IP_MASQ_DEBUG unused */ - { NET_TCP_SYNCOOKIES, "tcp_syncookies" }, - { NET_TCP_STDURG, "tcp_stdurg" }, - { NET_TCP_RFC1337, "tcp_rfc1337" }, - /* NET_TCP_SYN_TAILDROP unused */ - { NET_TCP_MAX_SYN_BACKLOG, "tcp_max_syn_backlog" }, - { NET_IPV4_LOCAL_PORT_RANGE, "ip_local_port_range" }, - { NET_IPV4_ICMP_ECHO_IGNORE_ALL, "icmp_echo_ignore_all" }, - { NET_IPV4_ICMP_ECHO_IGNORE_BROADCASTS, "icmp_echo_ignore_broadcasts" }, - /* NET_IPV4_ICMP_SOURCEQUENCH_RATE unused */ - /* NET_IPV4_ICMP_DESTUNREACH_RATE unused */ - /* NET_IPV4_ICMP_TIMEEXCEED_RATE unused */ - /* NET_IPV4_ICMP_PARAMPROB_RATE unused */ - /* NET_IPV4_ICMP_ECHOREPLY_RATE unused */ - { NET_IPV4_ICMP_IGNORE_BOGUS_ERROR_RESPONSES, "icmp_ignore_bogus_error_responses" }, - { NET_IPV4_IGMP_MAX_MEMBERSHIPS, "igmp_max_memberships" }, - { NET_TCP_TW_RECYCLE, "tcp_tw_recycle" }, - /* NET_IPV4_ALWAYS_DEFRAG unused */ - { NET_IPV4_TCP_KEEPALIVE_INTVL, "tcp_keepalive_intvl" }, - { NET_IPV4_INET_PEER_THRESHOLD, "inet_peer_threshold" }, - { NET_IPV4_INET_PEER_MINTTL, "inet_peer_minttl" }, - { NET_IPV4_INET_PEER_MAXTTL, "inet_peer_maxttl" }, - { NET_IPV4_INET_PEER_GC_MINTIME, "inet_peer_gc_mintime" }, - { NET_IPV4_INET_PEER_GC_MAXTIME, "inet_peer_gc_maxtime" }, - { NET_TCP_ORPHAN_RETRIES, "tcp_orphan_retries" }, - { NET_TCP_ABORT_ON_OVERFLOW, "tcp_abort_on_overflow" }, - { NET_TCP_SYNACK_RETRIES, "tcp_synack_retries" }, - { NET_TCP_MAX_ORPHANS, "tcp_max_orphans" }, - { NET_TCP_MAX_TW_BUCKETS, "tcp_max_tw_buckets" }, - { NET_TCP_FACK, "tcp_fack" }, - { NET_TCP_REORDERING, "tcp_reordering" }, - { NET_TCP_ECN, "tcp_ecn" }, - { NET_TCP_DSACK, "tcp_dsack" }, - { NET_TCP_MEM, "tcp_mem" }, - { NET_TCP_WMEM, "tcp_wmem" }, - { NET_TCP_RMEM, "tcp_rmem" }, - { NET_TCP_APP_WIN, "tcp_app_win" }, - { NET_TCP_ADV_WIN_SCALE, "tcp_adv_win_scale" }, - { NET_IPV4_NONLOCAL_BIND, "ip_nonlocal_bind" }, - { NET_IPV4_ICMP_RATELIMIT, "icmp_ratelimit" }, - { NET_IPV4_ICMP_RATEMASK, "icmp_ratemask" }, - { NET_TCP_TW_REUSE, "tcp_tw_reuse" }, - { NET_TCP_FRTO, "tcp_frto" }, - { NET_TCP_LOW_LATENCY, "tcp_low_latency" }, - { NET_IPV4_IPFRAG_SECRET_INTERVAL, "ipfrag_secret_interval" }, - { NET_IPV4_IGMP_MAX_MSF, "igmp_max_msf" }, - { NET_TCP_NO_METRICS_SAVE, "tcp_no_metrics_save" }, - /* NET_TCP_DEFAULT_WIN_SCALE unused */ - { NET_TCP_MODERATE_RCVBUF, "tcp_moderate_rcvbuf" }, - { NET_TCP_TSO_WIN_DIVISOR, "tcp_tso_win_divisor" }, - /* NET_TCP_BIC_BETA unused */ - { NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR, "icmp_errors_use_inbound_ifaddr" }, - { NET_TCP_CONG_CONTROL, "tcp_congestion_control" }, - { NET_TCP_ABC, "tcp_abc" }, - { NET_IPV4_IPFRAG_MAX_DIST, "ipfrag_max_dist" }, - { NET_TCP_MTU_PROBING, "tcp_mtu_probing" }, - { NET_TCP_BASE_MSS, "tcp_base_mss" }, - { NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS, "tcp_workaround_signed_windows" }, - { NET_TCP_DMA_COPYBREAK, "tcp_dma_copybreak" }, - { NET_TCP_SLOW_START_AFTER_IDLE, "tcp_slow_start_after_idle" }, - { NET_CIPSOV4_CACHE_ENABLE, "cipso_cache_enable" }, - { NET_CIPSOV4_CACHE_BUCKET_SIZE, "cipso_cache_bucket_size" }, - { NET_CIPSOV4_RBM_OPTFMT, "cipso_rbm_optfmt" }, - { NET_CIPSOV4_RBM_STRICTVALID, "cipso_rbm_strictvalid" }, - { NET_TCP_AVAIL_CONG_CONTROL, "tcp_available_congestion_control" }, - { NET_TCP_ALLOWED_CONG_CONTROL, "tcp_allowed_congestion_control" }, - { NET_TCP_MAX_SSTHRESH, "tcp_max_ssthresh" }, - { NET_TCP_FRTO_RESPONSE, "tcp_frto_response" }, - { 2088 /* NET_IPQ_QMAX */, "ip_queue_maxlen" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipx_table[] = { - { NET_IPX_PPROP_BROADCASTING, "ipx_pprop_broadcasting" }, - /* NET_IPX_FORWARDING unused */ - {} -}; - -static const struct trans_ctl_table trans_net_atalk_table[] = { - { NET_ATALK_AARP_EXPIRY_TIME, "aarp-expiry-time" }, - { NET_ATALK_AARP_TICK_TIME, "aarp-tick-time" }, - { NET_ATALK_AARP_RETRANSMIT_LIMIT, "aarp-retransmit-limit" }, - { NET_ATALK_AARP_RESOLVE_TIME, "aarp-resolve-time" }, - {}, -}; - -static const struct trans_ctl_table trans_net_netrom_table[] = { - { NET_NETROM_DEFAULT_PATH_QUALITY, "default_path_quality" }, - { NET_NETROM_OBSOLESCENCE_COUNT_INITIALISER, "obsolescence_count_initialiser" }, - { NET_NETROM_NETWORK_TTL_INITIALISER, "network_ttl_initialiser" }, - { NET_NETROM_TRANSPORT_TIMEOUT, "transport_timeout" }, - { NET_NETROM_TRANSPORT_MAXIMUM_TRIES, "transport_maximum_tries" }, - { NET_NETROM_TRANSPORT_ACKNOWLEDGE_DELAY, "transport_acknowledge_delay" }, - { NET_NETROM_TRANSPORT_BUSY_DELAY, "transport_busy_delay" }, - { NET_NETROM_TRANSPORT_REQUESTED_WINDOW_SIZE, "transport_requested_window_size" }, - { NET_NETROM_TRANSPORT_NO_ACTIVITY_TIMEOUT, "transport_no_activity_timeout" }, - { NET_NETROM_ROUTING_CONTROL, "routing_control" }, - { NET_NETROM_LINK_FAILS_COUNT, "link_fails_count" }, - { NET_NETROM_RESET, "reset" }, - {} -}; - -static const struct trans_ctl_table trans_net_ax25_param_table[] = { - { NET_AX25_IP_DEFAULT_MODE, "ip_default_mode" }, - { NET_AX25_DEFAULT_MODE, "ax25_default_mode" }, - { NET_AX25_BACKOFF_TYPE, "backoff_type" }, - { NET_AX25_CONNECT_MODE, "connect_mode" }, - { NET_AX25_STANDARD_WINDOW, "standard_window_size" }, - { NET_AX25_EXTENDED_WINDOW, "extended_window_size" }, - { NET_AX25_T1_TIMEOUT, "t1_timeout" }, - { NET_AX25_T2_TIMEOUT, "t2_timeout" }, - { NET_AX25_T3_TIMEOUT, "t3_timeout" }, - { NET_AX25_IDLE_TIMEOUT, "idle_timeout" }, - { NET_AX25_N2, "maximum_retry_count" }, - { NET_AX25_PACLEN, "maximum_packet_length" }, - { NET_AX25_PROTOCOL, "protocol" }, - { NET_AX25_DAMA_SLAVE_TIMEOUT, "dama_slave_timeout" }, - {} -}; - -static const struct trans_ctl_table trans_net_ax25_table[] = { - { 0, NULL, trans_net_ax25_param_table }, - {} -}; - -static const struct trans_ctl_table trans_net_bridge_table[] = { - { NET_BRIDGE_NF_CALL_ARPTABLES, "bridge-nf-call-arptables" }, - { NET_BRIDGE_NF_CALL_IPTABLES, "bridge-nf-call-iptables" }, - { NET_BRIDGE_NF_CALL_IP6TABLES, "bridge-nf-call-ip6tables" }, - { NET_BRIDGE_NF_FILTER_VLAN_TAGGED, "bridge-nf-filter-vlan-tagged" }, - { NET_BRIDGE_NF_FILTER_PPPOE_TAGGED, "bridge-nf-filter-pppoe-tagged" }, - {} -}; - -static const struct trans_ctl_table trans_net_rose_table[] = { - { NET_ROSE_RESTART_REQUEST_TIMEOUT, "restart_request_timeout" }, - { NET_ROSE_CALL_REQUEST_TIMEOUT, "call_request_timeout" }, - { NET_ROSE_RESET_REQUEST_TIMEOUT, "reset_request_timeout" }, - { NET_ROSE_CLEAR_REQUEST_TIMEOUT, "clear_request_timeout" }, - { NET_ROSE_ACK_HOLD_BACK_TIMEOUT, "acknowledge_hold_back_timeout" }, - { NET_ROSE_ROUTING_CONTROL, "routing_control" }, - { NET_ROSE_LINK_FAIL_TIMEOUT, "link_fail_timeout" }, - { NET_ROSE_MAX_VCS, "maximum_virtual_circuits" }, - { NET_ROSE_WINDOW_SIZE, "window_size" }, - { NET_ROSE_NO_ACTIVITY_TIMEOUT, "no_activity_timeout" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv6_conf_var_table[] = { - { NET_IPV6_FORWARDING, "forwarding" }, - { NET_IPV6_HOP_LIMIT, "hop_limit" }, - { NET_IPV6_MTU, "mtu" }, - { NET_IPV6_ACCEPT_RA, "accept_ra" }, - { NET_IPV6_ACCEPT_REDIRECTS, "accept_redirects" }, - { NET_IPV6_AUTOCONF, "autoconf" }, - { NET_IPV6_DAD_TRANSMITS, "dad_transmits" }, - { NET_IPV6_RTR_SOLICITS, "router_solicitations" }, - { NET_IPV6_RTR_SOLICIT_INTERVAL, "router_solicitation_interval" }, - { NET_IPV6_RTR_SOLICIT_DELAY, "router_solicitation_delay" }, - { NET_IPV6_USE_TEMPADDR, "use_tempaddr" }, - { NET_IPV6_TEMP_VALID_LFT, "temp_valid_lft" }, - { NET_IPV6_TEMP_PREFERED_LFT, "temp_prefered_lft" }, - { NET_IPV6_REGEN_MAX_RETRY, "regen_max_retry" }, - { NET_IPV6_MAX_DESYNC_FACTOR, "max_desync_factor" }, - { NET_IPV6_MAX_ADDRESSES, "max_addresses" }, - { NET_IPV6_FORCE_MLD_VERSION, "force_mld_version" }, - { NET_IPV6_ACCEPT_RA_DEFRTR, "accept_ra_defrtr" }, - { NET_IPV6_ACCEPT_RA_PINFO, "accept_ra_pinfo" }, - { NET_IPV6_ACCEPT_RA_RTR_PREF, "accept_ra_rtr_pref" }, - { NET_IPV6_RTR_PROBE_INTERVAL, "router_probe_interval" }, - { NET_IPV6_ACCEPT_RA_RT_INFO_MAX_PLEN, "accept_ra_rt_info_max_plen" }, - { NET_IPV6_PROXY_NDP, "proxy_ndp" }, - { NET_IPV6_ACCEPT_SOURCE_ROUTE, "accept_source_route" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv6_conf_table[] = { - { NET_PROTO_CONF_ALL, "all", trans_net_ipv6_conf_var_table }, - { NET_PROTO_CONF_DEFAULT, "default", trans_net_ipv6_conf_var_table }, - { 0, NULL, trans_net_ipv6_conf_var_table }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv6_route_table[] = { - { NET_IPV6_ROUTE_FLUSH, "flush" }, - { NET_IPV6_ROUTE_GC_THRESH, "gc_thresh" }, - { NET_IPV6_ROUTE_MAX_SIZE, "max_size" }, - { NET_IPV6_ROUTE_GC_MIN_INTERVAL, "gc_min_interval" }, - { NET_IPV6_ROUTE_GC_TIMEOUT, "gc_timeout" }, - { NET_IPV6_ROUTE_GC_INTERVAL, "gc_interval" }, - { NET_IPV6_ROUTE_GC_ELASTICITY, "gc_elasticity" }, - { NET_IPV6_ROUTE_MTU_EXPIRES, "mtu_expires" }, - { NET_IPV6_ROUTE_MIN_ADVMSS, "min_adv_mss" }, - { NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS, "gc_min_interval_ms" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv6_icmp_table[] = { - { NET_IPV6_ICMP_RATELIMIT, "ratelimit" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv6_table[] = { - { NET_IPV6_CONF, "conf", trans_net_ipv6_conf_table }, - { NET_IPV6_NEIGH, "neigh", trans_net_neigh_table }, - { NET_IPV6_ROUTE, "route", trans_net_ipv6_route_table }, - { NET_IPV6_ICMP, "icmp", trans_net_ipv6_icmp_table }, - { NET_IPV6_BINDV6ONLY, "bindv6only" }, - { NET_IPV6_IP6FRAG_HIGH_THRESH, "ip6frag_high_thresh" }, - { NET_IPV6_IP6FRAG_LOW_THRESH, "ip6frag_low_thresh" }, - { NET_IPV6_IP6FRAG_TIME, "ip6frag_time" }, - { NET_IPV6_IP6FRAG_SECRET_INTERVAL, "ip6frag_secret_interval" }, - { NET_IPV6_MLD_MAX_MSF, "mld_max_msf" }, - { 2088 /* IPQ_QMAX */, "ip6_queue_maxlen" }, - {} -}; - -static const struct trans_ctl_table trans_net_x25_table[] = { - { NET_X25_RESTART_REQUEST_TIMEOUT, "restart_request_timeout" }, - { NET_X25_CALL_REQUEST_TIMEOUT, "call_request_timeout" }, - { NET_X25_RESET_REQUEST_TIMEOUT, "reset_request_timeout" }, - { NET_X25_CLEAR_REQUEST_TIMEOUT, "clear_request_timeout" }, - { NET_X25_ACK_HOLD_BACK_TIMEOUT, "acknowledgement_hold_back_timeout" }, - { NET_X25_FORWARD, "x25_forward" }, - {} -}; - -static const struct trans_ctl_table trans_net_tr_table[] = { - { NET_TR_RIF_TIMEOUT, "rif_timeout" }, - {} -}; - - -static const struct trans_ctl_table trans_net_decnet_conf_vars[] = { - { NET_DECNET_CONF_DEV_FORWARDING, "forwarding" }, - { NET_DECNET_CONF_DEV_PRIORITY, "priority" }, - { NET_DECNET_CONF_DEV_T2, "t2" }, - { NET_DECNET_CONF_DEV_T3, "t3" }, - {} -}; - -static const struct trans_ctl_table trans_net_decnet_conf[] = { - { 0, NULL, trans_net_decnet_conf_vars }, - {} -}; - -static const struct trans_ctl_table trans_net_decnet_table[] = { - { NET_DECNET_CONF, "conf", trans_net_decnet_conf }, - { NET_DECNET_NODE_ADDRESS, "node_address" }, - { NET_DECNET_NODE_NAME, "node_name" }, - { NET_DECNET_DEFAULT_DEVICE, "default_device" }, - { NET_DECNET_TIME_WAIT, "time_wait" }, - { NET_DECNET_DN_COUNT, "dn_count" }, - { NET_DECNET_DI_COUNT, "di_count" }, - { NET_DECNET_DR_COUNT, "dr_count" }, - { NET_DECNET_DST_GC_INTERVAL, "dst_gc_interval" }, - { NET_DECNET_NO_FC_MAX_CWND, "no_fc_max_cwnd" }, - { NET_DECNET_MEM, "decnet_mem" }, - { NET_DECNET_RMEM, "decnet_rmem" }, - { NET_DECNET_WMEM, "decnet_wmem" }, - { NET_DECNET_DEBUG_LEVEL, "debug" }, - {} -}; - -static const struct trans_ctl_table trans_net_sctp_table[] = { - { NET_SCTP_RTO_INITIAL, "rto_initial" }, - { NET_SCTP_RTO_MIN, "rto_min" }, - { NET_SCTP_RTO_MAX, "rto_max" }, - { NET_SCTP_RTO_ALPHA, "rto_alpha_exp_divisor" }, - { NET_SCTP_RTO_BETA, "rto_beta_exp_divisor" }, - { NET_SCTP_VALID_COOKIE_LIFE, "valid_cookie_life" }, - { NET_SCTP_ASSOCIATION_MAX_RETRANS, "association_max_retrans" }, - { NET_SCTP_PATH_MAX_RETRANS, "path_max_retrans" }, - { NET_SCTP_MAX_INIT_RETRANSMITS, "max_init_retransmits" }, - { NET_SCTP_HB_INTERVAL, "hb_interval" }, - { NET_SCTP_PRESERVE_ENABLE, "cookie_preserve_enable" }, - { NET_SCTP_MAX_BURST, "max_burst" }, - { NET_SCTP_ADDIP_ENABLE, "addip_enable" }, - { NET_SCTP_PRSCTP_ENABLE, "prsctp_enable" }, - { NET_SCTP_SNDBUF_POLICY, "sndbuf_policy" }, - { NET_SCTP_SACK_TIMEOUT, "sack_timeout" }, - { NET_SCTP_RCVBUF_POLICY, "rcvbuf_policy" }, - {} -}; - -static const struct trans_ctl_table trans_net_llc_llc2_timeout_table[] = { - { NET_LLC2_ACK_TIMEOUT, "ack" }, - { NET_LLC2_P_TIMEOUT, "p" }, - { NET_LLC2_REJ_TIMEOUT, "rej" }, - { NET_LLC2_BUSY_TIMEOUT, "busy" }, - {} -}; - -static const struct trans_ctl_table trans_net_llc_station_table[] = { - { NET_LLC_STATION_ACK_TIMEOUT, "ack_timeout" }, - {} -}; - -static const struct trans_ctl_table trans_net_llc_llc2_table[] = { - { NET_LLC2, "timeout", trans_net_llc_llc2_timeout_table }, - {} -}; - -static const struct trans_ctl_table trans_net_llc_table[] = { - { NET_LLC2, "llc2", trans_net_llc_llc2_table }, - { NET_LLC_STATION, "station", trans_net_llc_station_table }, - {} -}; - -static const struct trans_ctl_table trans_net_netfilter_table[] = { - { NET_NF_CONNTRACK_MAX, "nf_conntrack_max" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT, "nf_conntrack_tcp_timeout_syn_sent" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV, "nf_conntrack_tcp_timeout_syn_recv" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED, "nf_conntrack_tcp_timeout_established" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT, "nf_conntrack_tcp_timeout_fin_wait" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT, "nf_conntrack_tcp_timeout_close_wait" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK, "nf_conntrack_tcp_timeout_last_ack" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT, "nf_conntrack_tcp_timeout_time_wait" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE, "nf_conntrack_tcp_timeout_close" }, - { NET_NF_CONNTRACK_UDP_TIMEOUT, "nf_conntrack_udp_timeout" }, - { NET_NF_CONNTRACK_UDP_TIMEOUT_STREAM, "nf_conntrack_udp_timeout_stream" }, - { NET_NF_CONNTRACK_ICMP_TIMEOUT, "nf_conntrack_icmp_timeout" }, - { NET_NF_CONNTRACK_GENERIC_TIMEOUT, "nf_conntrack_generic_timeout" }, - { NET_NF_CONNTRACK_BUCKETS, "nf_conntrack_buckets" }, - { NET_NF_CONNTRACK_LOG_INVALID, "nf_conntrack_log_invalid" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS, "nf_conntrack_tcp_timeout_max_retrans" }, - { NET_NF_CONNTRACK_TCP_LOOSE, "nf_conntrack_tcp_loose" }, - { NET_NF_CONNTRACK_TCP_BE_LIBERAL, "nf_conntrack_tcp_be_liberal" }, - { NET_NF_CONNTRACK_TCP_MAX_RETRANS, "nf_conntrack_tcp_max_retrans" }, - { NET_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED, "nf_conntrack_sctp_timeout_closed" }, - { NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT, "nf_conntrack_sctp_timeout_cookie_wait" }, - { NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED, "nf_conntrack_sctp_timeout_cookie_echoed" }, - { NET_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED, "nf_conntrack_sctp_timeout_established" }, - { NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT, "nf_conntrack_sctp_timeout_shutdown_sent" }, - { NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD, "nf_conntrack_sctp_timeout_shutdown_recd" }, - { NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT, "nf_conntrack_sctp_timeout_shutdown_ack_sent" }, - { NET_NF_CONNTRACK_COUNT, "nf_conntrack_count" }, - { NET_NF_CONNTRACK_ICMPV6_TIMEOUT, "nf_conntrack_icmpv6_timeout" }, - { NET_NF_CONNTRACK_FRAG6_TIMEOUT, "nf_conntrack_frag6_timeout" }, - { NET_NF_CONNTRACK_FRAG6_LOW_THRESH, "nf_conntrack_frag6_low_thresh" }, - { NET_NF_CONNTRACK_FRAG6_HIGH_THRESH, "nf_conntrack_frag6_high_thresh" }, - { NET_NF_CONNTRACK_CHECKSUM, "nf_conntrack_checksum" }, - - {} -}; - -static const struct trans_ctl_table trans_net_dccp_table[] = { - { NET_DCCP_DEFAULT, "default" }, - {} -}; - -static const struct trans_ctl_table trans_net_irda_table[] = { - { NET_IRDA_DISCOVERY, "discovery" }, - { NET_IRDA_DEVNAME, "devname" }, - { NET_IRDA_DEBUG, "debug" }, - { NET_IRDA_FAST_POLL, "fast_poll_increase" }, - { NET_IRDA_DISCOVERY_SLOTS, "discovery_slots" }, - { NET_IRDA_DISCOVERY_TIMEOUT, "discovery_timeout" }, - { NET_IRDA_SLOT_TIMEOUT, "slot_timeout" }, - { NET_IRDA_MAX_BAUD_RATE, "max_baud_rate" }, - { NET_IRDA_MIN_TX_TURN_TIME, "min_tx_turn_time" }, - { NET_IRDA_MAX_TX_DATA_SIZE, "max_tx_data_size" }, - { NET_IRDA_MAX_TX_WINDOW, "max_tx_window" }, - { NET_IRDA_MAX_NOREPLY_TIME, "max_noreply_time" }, - { NET_IRDA_WARN_NOREPLY_TIME, "warn_noreply_time" }, - { NET_IRDA_LAP_KEEPALIVE_TIME, "lap_keepalive_time" }, - {} -}; - -static const struct trans_ctl_table trans_net_table[] = { - { NET_CORE, "core", trans_net_core_table }, - /* NET_ETHER not used */ - /* NET_802 not used */ - { NET_UNIX, "unix", trans_net_unix_table }, - { NET_IPV4, "ipv4", trans_net_ipv4_table }, - { NET_IPX, "ipx", trans_net_ipx_table }, - { NET_ATALK, "appletalk", trans_net_atalk_table }, - { NET_NETROM, "netrom", trans_net_netrom_table }, - { NET_AX25, "ax25", trans_net_ax25_table }, - { NET_BRIDGE, "bridge", trans_net_bridge_table }, - { NET_ROSE, "rose", trans_net_rose_table }, - { NET_IPV6, "ipv6", trans_net_ipv6_table }, - { NET_X25, "x25", trans_net_x25_table }, - { NET_TR, "token-ring", trans_net_tr_table }, - { NET_DECNET, "decnet", trans_net_decnet_table }, - /* NET_ECONET not used */ - { NET_SCTP, "sctp", trans_net_sctp_table }, - { NET_LLC, "llc", trans_net_llc_table }, - { NET_NETFILTER, "netfilter", trans_net_netfilter_table }, - { NET_DCCP, "dccp", trans_net_dccp_table }, - { NET_IRDA, "irda", trans_net_irda_table }, - { 2089, "nf_conntrack_max" }, - {} -}; - -static const struct trans_ctl_table trans_fs_quota_table[] = { - { FS_DQ_LOOKUPS, "lookups" }, - { FS_DQ_DROPS, "drops" }, - { FS_DQ_READS, "reads" }, - { FS_DQ_WRITES, "writes" }, - { FS_DQ_CACHE_HITS, "cache_hits" }, - { FS_DQ_ALLOCATED, "allocated_dquots" }, - { FS_DQ_FREE, "free_dquots" }, - { FS_DQ_SYNCS, "syncs" }, - { FS_DQ_WARNINGS, "warnings" }, - {} -}; - -static const struct trans_ctl_table trans_fs_xfs_table[] = { - { XFS_SGID_INHERIT, "irix_sgid_inherit" }, - { XFS_SYMLINK_MODE, "irix_symlink_mode" }, - { XFS_PANIC_MASK, "panic_mask" }, - - { XFS_ERRLEVEL, "error_level" }, - { XFS_SYNCD_TIMER, "xfssyncd_centisecs" }, - { XFS_INHERIT_SYNC, "inherit_sync" }, - { XFS_INHERIT_NODUMP, "inherit_nodump" }, - { XFS_INHERIT_NOATIME, "inherit_noatime" }, - { XFS_BUF_TIMER, "xfsbufd_centisecs" }, - { XFS_BUF_AGE, "age_buffer_centisecs" }, - { XFS_INHERIT_NOSYM, "inherit_nosymlinks" }, - { XFS_ROTORSTEP, "rotorstep" }, - { XFS_INHERIT_NODFRG, "inherit_nodefrag" }, - { XFS_FILESTREAM_TIMER, "filestream_centisecs" }, - { XFS_STATS_CLEAR, "stats_clear" }, - {} -}; - -static const struct trans_ctl_table trans_fs_ocfs2_nm_table[] = { - { 1, "hb_ctl_path" }, - {} -}; - -static const struct trans_ctl_table trans_fs_ocfs2_table[] = { - { 1, "nm", trans_fs_ocfs2_nm_table }, - {} -}; - -static const struct trans_ctl_table trans_inotify_table[] = { - { INOTIFY_MAX_USER_INSTANCES, "max_user_instances" }, - { INOTIFY_MAX_USER_WATCHES, "max_user_watches" }, - { INOTIFY_MAX_QUEUED_EVENTS, "max_queued_events" }, - {} -}; - -static const struct trans_ctl_table trans_fs_table[] = { - { FS_NRINODE, "inode-nr" }, - { FS_STATINODE, "inode-state" }, - /* FS_MAXINODE unused */ - /* FS_NRDQUOT unused */ - /* FS_MAXDQUOT unused */ - { FS_NRFILE, "file-nr" }, - { FS_MAXFILE, "file-max" }, - { FS_DENTRY, "dentry-state" }, - /* FS_NRSUPER unused */ - /* FS_MAXUPSER unused */ - { FS_OVERFLOWUID, "overflowuid" }, - { FS_OVERFLOWGID, "overflowgid" }, - { FS_LEASES, "leases-enable" }, - { FS_DIR_NOTIFY, "dir-notify-enable" }, - { FS_LEASE_TIME, "lease-break-time" }, - { FS_DQSTATS, "quota", trans_fs_quota_table }, - { FS_XFS, "xfs", trans_fs_xfs_table }, - { FS_AIO_NR, "aio-nr" }, - { FS_AIO_MAX_NR, "aio-max-nr" }, - { FS_INOTIFY, "inotify", trans_inotify_table }, - { FS_OCFS2, "ocfs2", trans_fs_ocfs2_table }, - { KERN_SETUID_DUMPABLE, "suid_dumpable" }, - {} -}; - -static const struct trans_ctl_table trans_debug_table[] = { - {} -}; - -static const struct trans_ctl_table trans_cdrom_table[] = { - { DEV_CDROM_INFO, "info" }, - { DEV_CDROM_AUTOCLOSE, "autoclose" }, - { DEV_CDROM_AUTOEJECT, "autoeject" }, - { DEV_CDROM_DEBUG, "debug" }, - { DEV_CDROM_LOCK, "lock" }, - { DEV_CDROM_CHECK_MEDIA, "check_media" }, - {} -}; - -static const struct trans_ctl_table trans_ipmi_table[] = { - { DEV_IPMI_POWEROFF_POWERCYCLE, "poweroff_powercycle" }, - {} -}; - -static const struct trans_ctl_table trans_mac_hid_files[] = { - /* DEV_MAC_HID_KEYBOARD_SENDS_LINUX_KEYCODES unused */ - /* DEV_MAC_HID_KEYBOARD_LOCK_KEYCODES unused */ - { DEV_MAC_HID_MOUSE_BUTTON_EMULATION, "mouse_button_emulation" }, - { DEV_MAC_HID_MOUSE_BUTTON2_KEYCODE, "mouse_button2_keycode" }, - { DEV_MAC_HID_MOUSE_BUTTON3_KEYCODE, "mouse_button3_keycode" }, - /* DEV_MAC_HID_ADB_MOUSE_SENDS_KEYCODES unused */ - {} -}; - -static const struct trans_ctl_table trans_raid_table[] = { - { DEV_RAID_SPEED_LIMIT_MIN, "speed_limit_min" }, - { DEV_RAID_SPEED_LIMIT_MAX, "speed_limit_max" }, - {} -}; - -static const struct trans_ctl_table trans_scsi_table[] = { - { DEV_SCSI_LOGGING_LEVEL, "logging_level" }, - {} -}; - -static const struct trans_ctl_table trans_parport_default_table[] = { - { DEV_PARPORT_DEFAULT_TIMESLICE, "timeslice" }, - { DEV_PARPORT_DEFAULT_SPINTIME, "spintime" }, - {} -}; - -static const struct trans_ctl_table trans_parport_device_table[] = { - { DEV_PARPORT_DEVICE_TIMESLICE, "timeslice" }, - {} -}; - -static const struct trans_ctl_table trans_parport_devices_table[] = { - { DEV_PARPORT_DEVICES_ACTIVE, "active" }, - { 0, NULL, trans_parport_device_table }, - {} -}; - -static const struct trans_ctl_table trans_parport_parport_table[] = { - { DEV_PARPORT_SPINTIME, "spintime" }, - { DEV_PARPORT_BASE_ADDR, "base-addr" }, - { DEV_PARPORT_IRQ, "irq" }, - { DEV_PARPORT_DMA, "dma" }, - { DEV_PARPORT_MODES, "modes" }, - { DEV_PARPORT_DEVICES, "devices", trans_parport_devices_table }, - { DEV_PARPORT_AUTOPROBE, "autoprobe" }, - { DEV_PARPORT_AUTOPROBE + 1, "autoprobe0" }, - { DEV_PARPORT_AUTOPROBE + 2, "autoprobe1" }, - { DEV_PARPORT_AUTOPROBE + 3, "autoprobe2" }, - { DEV_PARPORT_AUTOPROBE + 4, "autoprobe3" }, - {} -}; -static const struct trans_ctl_table trans_parport_table[] = { - { DEV_PARPORT_DEFAULT, "default", trans_parport_default_table }, - { 0, NULL, trans_parport_parport_table }, - {} -}; - -static const struct trans_ctl_table trans_dev_table[] = { - { DEV_CDROM, "cdrom", trans_cdrom_table }, - /* DEV_HWMON unused */ - { DEV_PARPORT, "parport", trans_parport_table }, - { DEV_RAID, "raid", trans_raid_table }, - { DEV_MAC_HID, "mac_hid", trans_mac_hid_files }, - { DEV_SCSI, "scsi", trans_scsi_table }, - { DEV_IPMI, "ipmi", trans_ipmi_table }, - {} -}; - -static const struct trans_ctl_table trans_bus_isa_table[] = { - { BUS_ISA_MEM_BASE, "membase" }, - { BUS_ISA_PORT_BASE, "portbase" }, - { BUS_ISA_PORT_SHIFT, "portshift" }, - {} -}; - -static const struct trans_ctl_table trans_bus_table[] = { - { CTL_BUS_ISA, "isa", trans_bus_isa_table }, - {} -}; - -static const struct trans_ctl_table trans_arlan_conf_table0[] = { - { 1, "spreadingCode" }, - { 2, "channelNumber" }, - { 3, "scramblingDisable" }, - { 4, "txAttenuation" }, - { 5, "systemId" }, - { 6, "maxDatagramSize" }, - { 7, "maxFrameSize" }, - { 8, "maxRetries" }, - { 9, "receiveMode" }, - { 10, "priority" }, - { 11, "rootOrRepeater" }, - { 12, "SID" }, - { 13, "registrationMode" }, - { 14, "registrationFill" }, - { 15, "localTalkAddress" }, - { 16, "codeFormat" }, - { 17, "numChannels" }, - { 18, "channel1" }, - { 19, "channel2" }, - { 20, "channel3" }, - { 21, "channel4" }, - { 22, "txClear" }, - { 23, "txRetries" }, - { 24, "txRouting" }, - { 25, "txScrambled" }, - { 26, "rxParameter" }, - { 27, "txTimeoutMs" }, - { 28, "waitCardTimeout" }, - { 29, "channelSet" }, - { 30, "name" }, - { 31, "waitTime" }, - { 32, "lParameter" }, - { 33, "_15" }, - { 34, "headerSize" }, - { 36, "tx_delay_ms" }, - { 37, "retries" }, - { 38, "ReTransmitPacketMaxSize" }, - { 39, "waitReTransmitPacketMaxSize" }, - { 40, "fastReTransCount" }, - { 41, "driverRetransmissions" }, - { 42, "txAckTimeoutMs" }, - { 43, "registrationInterrupts" }, - { 44, "hardwareType" }, - { 45, "radioType" }, - { 46, "writeEEPROM" }, - { 47, "writeRadioType" }, - { 48, "entry_exit_debug" }, - { 49, "debug" }, - { 50, "in_speed" }, - { 51, "out_speed" }, - { 52, "in_speed10" }, - { 53, "out_speed10" }, - { 54, "in_speed_max" }, - { 55, "out_speed_max" }, - { 56, "measure_rate" }, - { 57, "pre_Command_Wait" }, - { 58, "rx_tweak1" }, - { 59, "rx_tweak2" }, - { 60, "tx_queue_len" }, - - { 150, "arlan0-txRing" }, - { 151, "arlan0-rxRing" }, - { 152, "arlan0-18" }, - { 153, "arlan0-ring" }, - { 154, "arlan0-shm-cpy" }, - { 155, "config0" }, - { 156, "reset0" }, - {} -}; - -static const struct trans_ctl_table trans_arlan_conf_table1[] = { - { 1, "spreadingCode" }, - { 2, "channelNumber" }, - { 3, "scramblingDisable" }, - { 4, "txAttenuation" }, - { 5, "systemId" }, - { 6, "maxDatagramSize" }, - { 7, "maxFrameSize" }, - { 8, "maxRetries" }, - { 9, "receiveMode" }, - { 10, "priority" }, - { 11, "rootOrRepeater" }, - { 12, "SID" }, - { 13, "registrationMode" }, - { 14, "registrationFill" }, - { 15, "localTalkAddress" }, - { 16, "codeFormat" }, - { 17, "numChannels" }, - { 18, "channel1" }, - { 19, "channel2" }, - { 20, "channel3" }, - { 21, "channel4" }, - { 22, "txClear" }, - { 23, "txRetries" }, - { 24, "txRouting" }, - { 25, "txScrambled" }, - { 26, "rxParameter" }, - { 27, "txTimeoutMs" }, - { 28, "waitCardTimeout" }, - { 29, "channelSet" }, - { 30, "name" }, - { 31, "waitTime" }, - { 32, "lParameter" }, - { 33, "_15" }, - { 34, "headerSize" }, - { 36, "tx_delay_ms" }, - { 37, "retries" }, - { 38, "ReTransmitPacketMaxSize" }, - { 39, "waitReTransmitPacketMaxSize" }, - { 40, "fastReTransCount" }, - { 41, "driverRetransmissions" }, - { 42, "txAckTimeoutMs" }, - { 43, "registrationInterrupts" }, - { 44, "hardwareType" }, - { 45, "radioType" }, - { 46, "writeEEPROM" }, - { 47, "writeRadioType" }, - { 48, "entry_exit_debug" }, - { 49, "debug" }, - { 50, "in_speed" }, - { 51, "out_speed" }, - { 52, "in_speed10" }, - { 53, "out_speed10" }, - { 54, "in_speed_max" }, - { 55, "out_speed_max" }, - { 56, "measure_rate" }, - { 57, "pre_Command_Wait" }, - { 58, "rx_tweak1" }, - { 59, "rx_tweak2" }, - { 60, "tx_queue_len" }, - - { 150, "arlan1-txRing" }, - { 151, "arlan1-rxRing" }, - { 152, "arlan1-18" }, - { 153, "arlan1-ring" }, - { 154, "arlan1-shm-cpy" }, - { 155, "config1" }, - { 156, "reset1" }, - {} -}; - -static const struct trans_ctl_table trans_arlan_conf_table2[] = { - { 1, "spreadingCode" }, - { 2, "channelNumber" }, - { 3, "scramblingDisable" }, - { 4, "txAttenuation" }, - { 5, "systemId" }, - { 6, "maxDatagramSize" }, - { 7, "maxFrameSize" }, - { 8, "maxRetries" }, - { 9, "receiveMode" }, - { 10, "priority" }, - { 11, "rootOrRepeater" }, - { 12, "SID" }, - { 13, "registrationMode" }, - { 14, "registrationFill" }, - { 15, "localTalkAddress" }, - { 16, "codeFormat" }, - { 17, "numChannels" }, - { 18, "channel1" }, - { 19, "channel2" }, - { 20, "channel3" }, - { 21, "channel4" }, - { 22, "txClear" }, - { 23, "txRetries" }, - { 24, "txRouting" }, - { 25, "txScrambled" }, - { 26, "rxParameter" }, - { 27, "txTimeoutMs" }, - { 28, "waitCardTimeout" }, - { 29, "channelSet" }, - { 30, "name" }, - { 31, "waitTime" }, - { 32, "lParameter" }, - { 33, "_15" }, - { 34, "headerSize" }, - { 36, "tx_delay_ms" }, - { 37, "retries" }, - { 38, "ReTransmitPacketMaxSize" }, - { 39, "waitReTransmitPacketMaxSize" }, - { 40, "fastReTransCount" }, - { 41, "driverRetransmissions" }, - { 42, "txAckTimeoutMs" }, - { 43, "registrationInterrupts" }, - { 44, "hardwareType" }, - { 45, "radioType" }, - { 46, "writeEEPROM" }, - { 47, "writeRadioType" }, - { 48, "entry_exit_debug" }, - { 49, "debug" }, - { 50, "in_speed" }, - { 51, "out_speed" }, - { 52, "in_speed10" }, - { 53, "out_speed10" }, - { 54, "in_speed_max" }, - { 55, "out_speed_max" }, - { 56, "measure_rate" }, - { 57, "pre_Command_Wait" }, - { 58, "rx_tweak1" }, - { 59, "rx_tweak2" }, - { 60, "tx_queue_len" }, - - { 150, "arlan2-txRing" }, - { 151, "arlan2-rxRing" }, - { 152, "arlan2-18" }, - { 153, "arlan2-ring" }, - { 154, "arlan2-shm-cpy" }, - { 155, "config2" }, - { 156, "reset2" }, - {} -}; - -static const struct trans_ctl_table trans_arlan_conf_table3[] = { - { 1, "spreadingCode" }, - { 2, "channelNumber" }, - { 3, "scramblingDisable" }, - { 4, "txAttenuation" }, - { 5, "systemId" }, - { 6, "maxDatagramSize" }, - { 7, "maxFrameSize" }, - { 8, "maxRetries" }, - { 9, "receiveMode" }, - { 10, "priority" }, - { 11, "rootOrRepeater" }, - { 12, "SID" }, - { 13, "registrationMode" }, - { 14, "registrationFill" }, - { 15, "localTalkAddress" }, - { 16, "codeFormat" }, - { 17, "numChannels" }, - { 18, "channel1" }, - { 19, "channel2" }, - { 20, "channel3" }, - { 21, "channel4" }, - { 22, "txClear" }, - { 23, "txRetries" }, - { 24, "txRouting" }, - { 25, "txScrambled" }, - { 26, "rxParameter" }, - { 27, "txTimeoutMs" }, - { 28, "waitCardTimeout" }, - { 29, "channelSet" }, - { 30, "name" }, - { 31, "waitTime" }, - { 32, "lParameter" }, - { 33, "_15" }, - { 34, "headerSize" }, - { 36, "tx_delay_ms" }, - { 37, "retries" }, - { 38, "ReTransmitPacketMaxSize" }, - { 39, "waitReTransmitPacketMaxSize" }, - { 40, "fastReTransCount" }, - { 41, "driverRetransmissions" }, - { 42, "txAckTimeoutMs" }, - { 43, "registrationInterrupts" }, - { 44, "hardwareType" }, - { 45, "radioType" }, - { 46, "writeEEPROM" }, - { 47, "writeRadioType" }, - { 48, "entry_exit_debug" }, - { 49, "debug" }, - { 50, "in_speed" }, - { 51, "out_speed" }, - { 52, "in_speed10" }, - { 53, "out_speed10" }, - { 54, "in_speed_max" }, - { 55, "out_speed_max" }, - { 56, "measure_rate" }, - { 57, "pre_Command_Wait" }, - { 58, "rx_tweak1" }, - { 59, "rx_tweak2" }, - { 60, "tx_queue_len" }, - - { 150, "arlan3-txRing" }, - { 151, "arlan3-rxRing" }, - { 152, "arlan3-18" }, - { 153, "arlan3-ring" }, - { 154, "arlan3-shm-cpy" }, - { 155, "config3" }, - { 156, "reset3" }, - {} -}; - -static const struct trans_ctl_table trans_arlan_table[] = { - { 1, "arlan0", trans_arlan_conf_table0 }, - { 2, "arlan1", trans_arlan_conf_table1 }, - { 3, "arlan2", trans_arlan_conf_table2 }, - { 4, "arlan3", trans_arlan_conf_table3 }, - {} -}; - -static const struct trans_ctl_table trans_s390dbf_table[] = { - { 5678 /* CTL_S390DBF_STOPPABLE */, "debug_stoppable" }, - { 5679 /* CTL_S390DBF_ACTIVE */, "debug_active" }, - {} -}; - -static const struct trans_ctl_table trans_sunrpc_table[] = { - { CTL_RPCDEBUG, "rpc_debug" }, - { CTL_NFSDEBUG, "nfs_debug" }, - { CTL_NFSDDEBUG, "nfsd_debug" }, - { CTL_NLMDEBUG, "nlm_debug" }, - { CTL_SLOTTABLE_UDP, "udp_slot_table_entries" }, - { CTL_SLOTTABLE_TCP, "tcp_slot_table_entries" }, - { CTL_MIN_RESVPORT, "min_resvport" }, - { CTL_MAX_RESVPORT, "max_resvport" }, - {} -}; - -static const struct trans_ctl_table trans_pm_table[] = { - { 1 /* CTL_PM_SUSPEND */, "suspend" }, - { 2 /* CTL_PM_CMODE */, "cmode" }, - { 3 /* CTL_PM_P0 */, "p0" }, - { 4 /* CTL_PM_CM */, "cm" }, - {} -}; - -static const struct trans_ctl_table trans_frv_table[] = { - { 1, "cache-mode" }, - { 2, "pin-cxnr" }, - {} -}; - -static const struct trans_ctl_table trans_root_table[] = { - { CTL_KERN, "kernel", trans_kern_table }, - { CTL_VM, "vm", trans_vm_table }, - { CTL_NET, "net", trans_net_table }, - /* CTL_PROC not used */ - { CTL_FS, "fs", trans_fs_table }, - { CTL_DEBUG, "debug", trans_debug_table }, - { CTL_DEV, "dev", trans_dev_table }, - { CTL_BUS, "bus", trans_bus_table }, - { CTL_ABI, "abi" }, - /* CTL_CPU not used */ - { CTL_ARLAN, "arlan", trans_arlan_table }, - { CTL_S390DBF, "s390dbf", trans_s390dbf_table }, - { CTL_SUNRPC, "sunrpc", trans_sunrpc_table }, - { CTL_PM, "pm", trans_pm_table }, - { CTL_FRV, "frv", trans_frv_table }, - {} -}; - - - static int sysctl_depth(struct ctl_table *table) { @@ -1261,47 +28,6 @@ static struct ctl_table *sysctl_parent(struct ctl_table *table, int n) return table; } -static const struct trans_ctl_table *sysctl_binary_lookup(struct ctl_table *table) -{ - struct ctl_table *test; - const struct trans_ctl_table *ref; - int cur_depth; - - cur_depth = sysctl_depth(table); - - ref = trans_root_table; -repeat: - test = sysctl_parent(table, cur_depth); - for (; ref->ctl_name || ref->procname || ref->child; ref++) { - int match = 0; - - if (cur_depth && !ref->child) - continue; - - if (test->procname && ref->procname && - (strcmp(test->procname, ref->procname) == 0)) - match++; - - if (test->ctl_name && ref->ctl_name && - (test->ctl_name == ref->ctl_name)) - match++; - - if (!ref->ctl_name && !ref->procname) - match++; - - if (match) { - if (cur_depth != 0) { - cur_depth--; - ref = ref->child; - goto repeat; - } - goto out; - } - } - ref = NULL; -out: - return ref; -} static void sysctl_print_path(struct ctl_table *table) { @@ -1315,26 +41,6 @@ static void sysctl_print_path(struct ctl_table *table) } } printk(" "); - if (table->ctl_name) { - for (i = depth; i >= 0; i--) { - tmp = sysctl_parent(table, i); - printk(".%d", tmp->ctl_name); - } - } -} - -static void sysctl_repair_table(struct ctl_table *table) -{ - /* Don't complain about the classic default - * sysctl strategy routine. Maybe later we - * can get the tables fixed and complain about - * this. - */ - if (table->ctl_name && table->procname && - (table->proc_handler == proc_dointvec) && - (!table->strategy)) { - table->strategy = sysctl_data; - } } static struct ctl_table *sysctl_check_lookup(struct nsproxy *namespaces, @@ -1352,7 +58,7 @@ static struct ctl_table *sysctl_check_lookup(struct nsproxy *namespaces, ref = head->ctl_table; repeat: test = sysctl_parent(table, cur_depth); - for (; ref->ctl_name || ref->procname; ref++) { + for (; ref->procname; ref++) { int match = 0; if (cur_depth && !ref->child) continue; @@ -1361,10 +67,6 @@ repeat: (strcmp(test->procname, ref->procname) == 0)) match++; - if (test->ctl_name && ref->ctl_name && - (test->ctl_name == ref->ctl_name)) - match++; - if (match) { if (cur_depth != 0) { cur_depth--; @@ -1392,38 +94,6 @@ static void set_fail(const char **fail, struct ctl_table *table, const char *str *fail = str; } -static int sysctl_check_dir(struct nsproxy *namespaces, - struct ctl_table *table) -{ - struct ctl_table *ref; - int error; - - error = 0; - ref = sysctl_check_lookup(namespaces, table); - if (ref) { - int match = 0; - if ((!table->procname && !ref->procname) || - (table->procname && ref->procname && - (strcmp(table->procname, ref->procname) == 0))) - match++; - - if ((!table->ctl_name && !ref->ctl_name) || - (table->ctl_name && ref->ctl_name && - (table->ctl_name == ref->ctl_name))) - match++; - - if (match != 2) { - printk(KERN_ERR "%s: failed: ", __func__); - sysctl_print_path(table); - printk(" ref: "); - sysctl_print_path(ref); - printk("\n"); - error = -EINVAL; - } - } - return error; -} - static void sysctl_check_leaf(struct nsproxy *namespaces, struct ctl_table *table, const char **fail) { @@ -1434,37 +104,15 @@ static void sysctl_check_leaf(struct nsproxy *namespaces, set_fail(fail, table, "Sysctl already exists"); } -static void sysctl_check_bin_path(struct ctl_table *table, const char **fail) -{ - const struct trans_ctl_table *ref; - - ref = sysctl_binary_lookup(table); - if (table->ctl_name && !ref) - set_fail(fail, table, "Unknown sysctl binary path"); - if (ref) { - if (ref->procname && - (!table->procname || - (strcmp(table->procname, ref->procname) != 0))) - set_fail(fail, table, "procname does not match binary path procname"); - - if (ref->ctl_name && table->ctl_name && - (table->ctl_name != ref->ctl_name)) - set_fail(fail, table, "ctl_name does not match binary path ctl_name"); - } -} - int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table) { int error = 0; - for (; table->ctl_name || table->procname; table++) { + for (; table->procname; table++) { const char *fail = NULL; - sysctl_repair_table(table); if (table->parent) { if (table->procname && !table->parent->procname) set_fail(&fail, table, "Parent without procname"); - if (table->ctl_name && !table->parent->ctl_name) - set_fail(&fail, table, "Parent without ctl_name"); } if (!table->procname) set_fail(&fail, table, "No procname"); @@ -1477,21 +125,12 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table) set_fail(&fail, table, "Writable sysctl directory"); if (table->proc_handler) set_fail(&fail, table, "Directory with proc_handler"); - if (table->strategy) - set_fail(&fail, table, "Directory with strategy"); if (table->extra1) set_fail(&fail, table, "Directory with extra1"); if (table->extra2) set_fail(&fail, table, "Directory with extra2"); - if (sysctl_check_dir(namespaces, table)) - set_fail(&fail, table, "Inconsistent directory names"); } else { - if ((table->strategy == sysctl_data) || - (table->strategy == sysctl_string) || - (table->strategy == sysctl_intvec) || - (table->strategy == sysctl_jiffies) || - (table->strategy == sysctl_ms_jiffies) || - (table->proc_handler == proc_dostring) || + if ((table->proc_handler == proc_dostring) || (table->proc_handler == proc_dointvec) || (table->proc_handler == proc_dointvec_minmax) || (table->proc_handler == proc_dointvec_jiffies) || @@ -1513,14 +152,6 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table) set_fail(&fail, table, "No max"); } } -#ifdef CONFIG_SYSCTL_SYSCALL - if (table->ctl_name && !table->strategy) - set_fail(&fail, table, "Missing strategy"); -#endif -#if 0 - if (!table->ctl_name && table->strategy) - set_fail(&fail, table, "Strategy without ctl_name"); -#endif #ifdef CONFIG_PROC_SYSCTL if (table->procname && !table->proc_handler) set_fail(&fail, table, "No proc_handler"); @@ -1531,7 +162,6 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table) #endif sysctl_check_leaf(namespaces, table, &fail); } - sysctl_check_bin_path(table, &fail); if (table->mode > 0777) set_fail(&fail, table, "bogus .mode"); if (fail) { diff --git a/kernel/time.c b/kernel/time.c index 8047980..c6324d9 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -136,7 +136,6 @@ static inline void warp_clock(void) write_seqlock_irq(&xtime_lock); wall_to_monotonic.tv_sec -= sys_tz.tz_minuteswest * 60; xtime.tv_sec += sys_tz.tz_minuteswest * 60; - update_xtime_cache(0); write_sequnlock_irq(&xtime_lock); clock_was_set(); } diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 620b58a..20a8920 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -20,6 +20,8 @@ #include <linux/sysdev.h> #include <linux/tick.h> +#include "tick-internal.h" + /* The registered clock event devices */ static LIST_HEAD(clockevent_devices); static LIST_HEAD(clockevents_released); @@ -37,10 +39,9 @@ static DEFINE_SPINLOCK(clockevents_lock); * * Math helper, returns latch value converted to nanoseconds (bound checked) */ -unsigned long clockevent_delta2ns(unsigned long latch, - struct clock_event_device *evt) +u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt) { - u64 clc = ((u64) latch << evt->shift); + u64 clc = (u64) latch << evt->shift; if (unlikely(!evt->mult)) { evt->mult = 1; @@ -50,10 +51,10 @@ unsigned long clockevent_delta2ns(unsigned long latch, do_div(clc, evt->mult); if (clc < 1000) clc = 1000; - if (clc > LONG_MAX) - clc = LONG_MAX; + if (clc > KTIME_MAX) + clc = KTIME_MAX; - return (unsigned long) clc; + return clc; } EXPORT_SYMBOL_GPL(clockevent_delta2ns); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 5e18c6a..e85c234 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -39,7 +39,7 @@ void timecounter_init(struct timecounter *tc, tc->cycle_last = cc->read(cc); tc->nsec = start_tstamp; } -EXPORT_SYMBOL(timecounter_init); +EXPORT_SYMBOL_GPL(timecounter_init); /** * timecounter_read_delta - get nanoseconds since last call of this function @@ -83,7 +83,7 @@ u64 timecounter_read(struct timecounter *tc) return nsec; } -EXPORT_SYMBOL(timecounter_read); +EXPORT_SYMBOL_GPL(timecounter_read); u64 timecounter_cyc2time(struct timecounter *tc, cycle_t cycle_tstamp) @@ -105,7 +105,60 @@ u64 timecounter_cyc2time(struct timecounter *tc, return nsec; } -EXPORT_SYMBOL(timecounter_cyc2time); +EXPORT_SYMBOL_GPL(timecounter_cyc2time); + +/** + * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks + * @mult: pointer to mult variable + * @shift: pointer to shift variable + * @from: frequency to convert from + * @to: frequency to convert to + * @minsec: guaranteed runtime conversion range in seconds + * + * The function evaluates the shift/mult pair for the scaled math + * operations of clocksources and clockevents. + * + * @to and @from are frequency values in HZ. For clock sources @to is + * NSEC_PER_SEC == 1GHz and @from is the counter frequency. For clock + * event @to is the counter frequency and @from is NSEC_PER_SEC. + * + * The @minsec conversion range argument controls the time frame in + * seconds which must be covered by the runtime conversion with the + * calculated mult and shift factors. This guarantees that no 64bit + * overflow happens when the input value of the conversion is + * multiplied with the calculated mult factor. Larger ranges may + * reduce the conversion accuracy by chosing smaller mult and shift + * factors. + */ +void +clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec) +{ + u64 tmp; + u32 sft, sftacc= 32; + + /* + * Calculate the shift factor which is limiting the conversion + * range: + */ + tmp = ((u64)minsec * from) >> 32; + while (tmp) { + tmp >>=1; + sftacc--; + } + + /* + * Find the conversion shift/mult pair which has the best + * accuracy and fits the maxsec conversion range: + */ + for (sft = 32; sft > 0; sft--) { + tmp = (u64) to << sft; + do_div(tmp, from); + if ((tmp >> sftacc) == 0) + break; + } + *mult = tmp; + *shift = sft; +} /*[Clocksource internal variables]--------- * curr_clocksource: @@ -413,6 +466,47 @@ void clocksource_touch_watchdog(void) clocksource_resume_watchdog(); } +/** + * clocksource_max_deferment - Returns max time the clocksource can be deferred + * @cs: Pointer to clocksource + * + */ +static u64 clocksource_max_deferment(struct clocksource *cs) +{ + u64 max_nsecs, max_cycles; + + /* + * Calculate the maximum number of cycles that we can pass to the + * cyc2ns function without overflowing a 64-bit signed result. The + * maximum number of cycles is equal to ULLONG_MAX/cs->mult which + * is equivalent to the below. + * max_cycles < (2^63)/cs->mult + * max_cycles < 2^(log2((2^63)/cs->mult)) + * max_cycles < 2^(log2(2^63) - log2(cs->mult)) + * max_cycles < 2^(63 - log2(cs->mult)) + * max_cycles < 1 << (63 - log2(cs->mult)) + * Please note that we add 1 to the result of the log2 to account for + * any rounding errors, ensure the above inequality is satisfied and + * no overflow will occur. + */ + max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1)); + + /* + * The actual maximum number of cycles we can defer the clocksource is + * determined by the minimum of max_cycles and cs->mask. + */ + max_cycles = min_t(u64, max_cycles, (u64) cs->mask); + max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift); + + /* + * To ensure that the clocksource does not wrap whilst we are idle, + * limit the time the clocksource can be deferred by 12.5%. Please + * note a margin of 12.5% is used because this can be computed with + * a shift, versus say 10% which would require division. + */ + return max_nsecs - (max_nsecs >> 5); +} + #ifdef CONFIG_GENERIC_TIME /** @@ -511,6 +605,9 @@ static void clocksource_enqueue(struct clocksource *cs) */ int clocksource_register(struct clocksource *cs) { + /* calculate max idle time permitted for this clocksource */ + cs->max_idle_ns = clocksource_max_deferment(cs); + mutex_lock(&clocksource_mutex); clocksource_enqueue(cs); clocksource_select(); @@ -580,7 +677,7 @@ sysfs_show_current_clocksources(struct sys_device *dev, * @count: length of buffer * * Takes input from sysfs interface for manually overriding the default - * clocksource selction. + * clocksource selection. */ static ssize_t sysfs_override_clocksource(struct sys_device *dev, struct sysdev_attribute *attr, diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c index a96c0e2..0a8a213 100644 --- a/kernel/time/tick-oneshot.c +++ b/kernel/time/tick-oneshot.c @@ -50,9 +50,9 @@ int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires, dev->min_delta_ns += dev->min_delta_ns >> 1; printk(KERN_WARNING - "CE: %s increasing min_delta_ns to %lu nsec\n", + "CE: %s increasing min_delta_ns to %llu nsec\n", dev->name ? dev->name : "?", - dev->min_delta_ns << 1); + (unsigned long long) dev->min_delta_ns << 1); i = 0; } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 89aed59..f992762 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -134,18 +134,13 @@ __setup("nohz=", setup_tick_nohz); * value. We do this unconditionally on any cpu, as we don't know whether the * cpu, which has the update task assigned is in a long sleep. */ -static void tick_nohz_update_jiffies(void) +static void tick_nohz_update_jiffies(ktime_t now) { int cpu = smp_processor_id(); struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); unsigned long flags; - ktime_t now; - - if (!ts->tick_stopped) - return; cpumask_clear_cpu(cpu, nohz_cpu_mask); - now = ktime_get(); ts->idle_waketime = now; local_irq_save(flags); @@ -155,20 +150,17 @@ static void tick_nohz_update_jiffies(void) touch_softlockup_watchdog(); } -static void tick_nohz_stop_idle(int cpu) +static void tick_nohz_stop_idle(int cpu, ktime_t now) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + ktime_t delta; - if (ts->idle_active) { - ktime_t now, delta; - now = ktime_get(); - delta = ktime_sub(now, ts->idle_entrytime); - ts->idle_lastupdate = now; - ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta); - ts->idle_active = 0; + delta = ktime_sub(now, ts->idle_entrytime); + ts->idle_lastupdate = now; + ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta); + ts->idle_active = 0; - sched_clock_idle_wakeup_event(0); - } + sched_clock_idle_wakeup_event(0); } static ktime_t tick_nohz_start_idle(struct tick_sched *ts) @@ -216,6 +208,7 @@ void tick_nohz_stop_sched_tick(int inidle) struct tick_sched *ts; ktime_t last_update, expires, now; struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev; + u64 time_delta; int cpu; local_irq_save(flags); @@ -263,7 +256,7 @@ void tick_nohz_stop_sched_tick(int inidle) if (ratelimit < 10) { printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", - local_softirq_pending()); + (unsigned int) local_softirq_pending()); ratelimit++; } goto end; @@ -275,14 +268,18 @@ void tick_nohz_stop_sched_tick(int inidle) seq = read_seqbegin(&xtime_lock); last_update = last_jiffies_update; last_jiffies = jiffies; + time_delta = timekeeping_max_deferment(); } while (read_seqretry(&xtime_lock, seq)); - /* Get the next timer wheel timer */ - next_jiffies = get_next_timer_interrupt(last_jiffies); - delta_jiffies = next_jiffies - last_jiffies; - - if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu)) + if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) || + arch_needs_cpu(cpu)) { + next_jiffies = last_jiffies + 1; delta_jiffies = 1; + } else { + /* Get the next timer wheel timer */ + next_jiffies = get_next_timer_interrupt(last_jiffies); + delta_jiffies = next_jiffies - last_jiffies; + } /* * Do not stop the tick, if we are only one off * or if the cpu is required for rcu @@ -294,22 +291,51 @@ void tick_nohz_stop_sched_tick(int inidle) if ((long)delta_jiffies >= 1) { /* - * calculate the expiry time for the next timer wheel - * timer - */ - expires = ktime_add_ns(last_update, tick_period.tv64 * - delta_jiffies); - - /* * If this cpu is the one which updates jiffies, then * give up the assignment and let it be taken by the * cpu which runs the tick timer next, which might be * this cpu as well. If we don't drop this here the * jiffies might be stale and do_timer() never - * invoked. + * invoked. Keep track of the fact that it was the one + * which had the do_timer() duty last. If this cpu is + * the one which had the do_timer() duty last, we + * limit the sleep time to the timekeeping + * max_deferement value which we retrieved + * above. Otherwise we can sleep as long as we want. */ - if (cpu == tick_do_timer_cpu) + if (cpu == tick_do_timer_cpu) { tick_do_timer_cpu = TICK_DO_TIMER_NONE; + ts->do_timer_last = 1; + } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) { + time_delta = KTIME_MAX; + ts->do_timer_last = 0; + } else if (!ts->do_timer_last) { + time_delta = KTIME_MAX; + } + + /* + * calculate the expiry time for the next timer wheel + * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals + * that there is no timer pending or at least extremely + * far into the future (12 days for HZ=1000). In this + * case we set the expiry to the end of time. + */ + if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) { + /* + * Calculate the time delta for the next timer event. + * If the time delta exceeds the maximum time delta + * permitted by the current clocksource then adjust + * the time delta accordingly to ensure the + * clocksource does not wrap. + */ + time_delta = min_t(u64, time_delta, + tick_period.tv64 * delta_jiffies); + } + + if (time_delta < KTIME_MAX) + expires = ktime_add_ns(last_update, time_delta); + else + expires.tv64 = KTIME_MAX; if (delta_jiffies > 1) cpumask_set_cpu(cpu, nohz_cpu_mask); @@ -342,22 +368,19 @@ void tick_nohz_stop_sched_tick(int inidle) ts->idle_sleeps++; + /* Mark expires */ + ts->idle_expires = expires; + /* - * delta_jiffies >= NEXT_TIMER_MAX_DELTA signals that - * there is no timer pending or at least extremly far - * into the future (12 days for HZ=1000). In this case - * we simply stop the tick timer: + * If the expiration time == KTIME_MAX, then + * in this case we simply stop the tick timer. */ - if (unlikely(delta_jiffies >= NEXT_TIMER_MAX_DELTA)) { - ts->idle_expires.tv64 = KTIME_MAX; + if (unlikely(expires.tv64 == KTIME_MAX)) { if (ts->nohz_mode == NOHZ_MODE_HIGHRES) hrtimer_cancel(&ts->sched_timer); goto out; } - /* Mark expiries */ - ts->idle_expires = expires; - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { hrtimer_start(&ts->sched_timer, expires, HRTIMER_MODE_ABS_PINNED); @@ -436,7 +459,11 @@ void tick_nohz_restart_sched_tick(void) ktime_t now; local_irq_disable(); - tick_nohz_stop_idle(cpu); + if (ts->idle_active || (ts->inidle && ts->tick_stopped)) + now = ktime_get(); + + if (ts->idle_active) + tick_nohz_stop_idle(cpu, now); if (!ts->inidle || !ts->tick_stopped) { ts->inidle = 0; @@ -450,7 +477,6 @@ void tick_nohz_restart_sched_tick(void) /* Update jiffies first */ select_nohz_load_balancer(0); - now = ktime_get(); tick_do_update_jiffies64(now); cpumask_clear_cpu(cpu, nohz_cpu_mask); @@ -584,22 +610,18 @@ static void tick_nohz_switch_to_nohz(void) * timer and do not touch the other magic bits which need to be done * when idle is left. */ -static void tick_nohz_kick_tick(int cpu) +static void tick_nohz_kick_tick(int cpu, ktime_t now) { #if 0 /* Switch back to 2.6.27 behaviour */ struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); - ktime_t delta, now; - - if (!ts->tick_stopped) - return; + ktime_t delta; /* * Do not touch the tick device, when the next expiry is either * already reached or less/equal than the tick period. */ - now = ktime_get(); delta = ktime_sub(hrtimer_get_expires(&ts->sched_timer), now); if (delta.tv64 <= tick_period.tv64) return; @@ -608,9 +630,26 @@ static void tick_nohz_kick_tick(int cpu) #endif } +static inline void tick_check_nohz(int cpu) +{ + struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + ktime_t now; + + if (!ts->idle_active && !ts->tick_stopped) + return; + now = ktime_get(); + if (ts->idle_active) + tick_nohz_stop_idle(cpu, now); + if (ts->tick_stopped) { + tick_nohz_update_jiffies(now); + tick_nohz_kick_tick(cpu, now); + } +} + #else static inline void tick_nohz_switch_to_nohz(void) { } +static inline void tick_check_nohz(int cpu) { } #endif /* NO_HZ */ @@ -620,11 +659,7 @@ static inline void tick_nohz_switch_to_nohz(void) { } void tick_check_idle(int cpu) { tick_check_oneshot_broadcast(cpu); -#ifdef CONFIG_NO_HZ - tick_nohz_stop_idle(cpu); - tick_nohz_update_jiffies(); - tick_nohz_kick_tick(cpu); -#endif + tick_check_nohz(cpu); } /* diff --git a/kernel/time/timecompare.c b/kernel/time/timecompare.c index 71e7f1a..96ff643 100644 --- a/kernel/time/timecompare.c +++ b/kernel/time/timecompare.c @@ -40,7 +40,7 @@ ktime_t timecompare_transform(struct timecompare *sync, return ns_to_ktime(nsec); } -EXPORT_SYMBOL(timecompare_transform); +EXPORT_SYMBOL_GPL(timecompare_transform); int timecompare_offset(struct timecompare *sync, s64 *offset, @@ -131,7 +131,7 @@ int timecompare_offset(struct timecompare *sync, return used; } -EXPORT_SYMBOL(timecompare_offset); +EXPORT_SYMBOL_GPL(timecompare_offset); void __timecompare_update(struct timecompare *sync, u64 source_tstamp) @@ -188,4 +188,4 @@ void __timecompare_update(struct timecompare *sync, } } } -EXPORT_SYMBOL(__timecompare_update); +EXPORT_SYMBOL_GPL(__timecompare_update); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index c3a4e29..af4135f 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -165,19 +165,12 @@ struct timespec raw_time; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; -static struct timespec xtime_cache __attribute__ ((aligned (16))); -void update_xtime_cache(u64 nsec) -{ - xtime_cache = xtime; - timespec_add_ns(&xtime_cache, nsec); -} - /* must hold xtime_lock */ void timekeeping_leap_insert(int leapsecond) { xtime.tv_sec += leapsecond; wall_to_monotonic.tv_sec -= leapsecond; - update_vsyscall(&xtime, timekeeper.clock); + update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult); } #ifdef CONFIG_GENERIC_TIME @@ -332,12 +325,10 @@ int do_settimeofday(struct timespec *tv) xtime = *tv; - update_xtime_cache(0); - timekeeper.ntp_error = 0; ntp_clear(); - update_vsyscall(&xtime, timekeeper.clock); + update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult); write_sequnlock_irqrestore(&xtime_lock, flags); @@ -488,6 +479,17 @@ int timekeeping_valid_for_hres(void) } /** + * timekeeping_max_deferment - Returns max time the clocksource can be deferred + * + * Caller must observe xtime_lock via read_seqbegin/read_seqretry to + * ensure that the clocksource does not change! + */ +u64 timekeeping_max_deferment(void) +{ + return timekeeper.clock->max_idle_ns; +} + +/** * read_persistent_clock - Return time from the persistent clock. * * Weak dummy function for arches that do not yet support it. @@ -548,7 +550,6 @@ void __init timekeeping_init(void) } set_normalized_timespec(&wall_to_monotonic, -boot.tv_sec, -boot.tv_nsec); - update_xtime_cache(0); total_sleep_time.tv_sec = 0; total_sleep_time.tv_nsec = 0; write_sequnlock_irqrestore(&xtime_lock, flags); @@ -582,7 +583,6 @@ static int timekeeping_resume(struct sys_device *dev) wall_to_monotonic = timespec_sub(wall_to_monotonic, ts); total_sleep_time = timespec_add_safe(total_sleep_time, ts); } - update_xtime_cache(0); /* re-base the last cycle value */ timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock); timekeeper.ntp_error = 0; @@ -723,6 +723,49 @@ static void timekeeping_adjust(s64 offset) } /** + * logarithmic_accumulation - shifted accumulation of cycles + * + * This functions accumulates a shifted interval of cycles into + * into a shifted interval nanoseconds. Allows for O(log) accumulation + * loop. + * + * Returns the unconsumed cycles. + */ +static cycle_t logarithmic_accumulation(cycle_t offset, int shift) +{ + u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift; + + /* If the offset is smaller then a shifted interval, do nothing */ + if (offset < timekeeper.cycle_interval<<shift) + return offset; + + /* Accumulate one shifted interval */ + offset -= timekeeper.cycle_interval << shift; + timekeeper.clock->cycle_last += timekeeper.cycle_interval << shift; + + timekeeper.xtime_nsec += timekeeper.xtime_interval << shift; + while (timekeeper.xtime_nsec >= nsecps) { + timekeeper.xtime_nsec -= nsecps; + xtime.tv_sec++; + second_overflow(); + } + + /* Accumulate into raw time */ + raw_time.tv_nsec += timekeeper.raw_interval << shift;; + while (raw_time.tv_nsec >= NSEC_PER_SEC) { + raw_time.tv_nsec -= NSEC_PER_SEC; + raw_time.tv_sec++; + } + + /* Accumulate error between NTP and clock interval */ + timekeeper.ntp_error += tick_length << shift; + timekeeper.ntp_error -= timekeeper.xtime_interval << + (timekeeper.ntp_error_shift + shift); + + return offset; +} + +/** * update_wall_time - Uses the current clocksource to increment the wall time * * Called from the timer interrupt, must hold a write on xtime_lock. @@ -731,7 +774,7 @@ void update_wall_time(void) { struct clocksource *clock; cycle_t offset; - u64 nsecs; + int shift = 0, maxshift; /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) @@ -745,33 +788,22 @@ void update_wall_time(void) #endif timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift; - /* normally this loop will run just once, however in the - * case of lost or late ticks, it will accumulate correctly. + /* + * With NO_HZ we may have to accumulate many cycle_intervals + * (think "ticks") worth of time at once. To do this efficiently, + * we calculate the largest doubling multiple of cycle_intervals + * that is smaller then the offset. We then accumulate that + * chunk in one go, and then try to consume the next smaller + * doubled multiple. */ + shift = ilog2(offset) - ilog2(timekeeper.cycle_interval); + shift = max(0, shift); + /* Bound shift to one less then what overflows tick_length */ + maxshift = (8*sizeof(tick_length) - (ilog2(tick_length)+1)) - 1; + shift = min(shift, maxshift); while (offset >= timekeeper.cycle_interval) { - u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift; - - /* accumulate one interval */ - offset -= timekeeper.cycle_interval; - clock->cycle_last += timekeeper.cycle_interval; - - timekeeper.xtime_nsec += timekeeper.xtime_interval; - if (timekeeper.xtime_nsec >= nsecps) { - timekeeper.xtime_nsec -= nsecps; - xtime.tv_sec++; - second_overflow(); - } - - raw_time.tv_nsec += timekeeper.raw_interval; - if (raw_time.tv_nsec >= NSEC_PER_SEC) { - raw_time.tv_nsec -= NSEC_PER_SEC; - raw_time.tv_sec++; - } - - /* accumulate error between NTP and clock interval */ - timekeeper.ntp_error += tick_length; - timekeeper.ntp_error -= timekeeper.xtime_interval << - timekeeper.ntp_error_shift; + offset = logarithmic_accumulation(offset, shift); + shift--; } /* correct the clock when NTP error is too big */ @@ -807,11 +839,8 @@ void update_wall_time(void) timekeeper.ntp_error += timekeeper.xtime_nsec << timekeeper.ntp_error_shift; - nsecs = clocksource_cyc2ns(offset, timekeeper.mult, timekeeper.shift); - update_xtime_cache(nsecs); - /* check to see if there is a new clocksource to use */ - update_vsyscall(&xtime, timekeeper.clock); + update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult); } /** @@ -846,13 +875,13 @@ void monotonic_to_bootbased(struct timespec *ts) unsigned long get_seconds(void) { - return xtime_cache.tv_sec; + return xtime.tv_sec; } EXPORT_SYMBOL(get_seconds); struct timespec __current_kernel_time(void) { - return xtime_cache; + return xtime; } struct timespec current_kernel_time(void) @@ -862,8 +891,7 @@ struct timespec current_kernel_time(void) do { seq = read_seqbegin(&xtime_lock); - - now = xtime_cache; + now = xtime; } while (read_seqretry(&xtime_lock, seq)); return now; @@ -877,8 +905,7 @@ struct timespec get_monotonic_coarse(void) do { seq = read_seqbegin(&xtime_lock); - - now = xtime_cache; + now = xtime; mono = wall_to_monotonic; } while (read_seqretry(&xtime_lock, seq)); diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 1b5b7aa..9d80db4 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -150,6 +150,9 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now) P_ns(expires_next); P(hres_active); P(nr_events); + P(nr_retries); + P(nr_hangs); + P_ns(max_hang_time); #endif #undef P #undef P_ns @@ -204,10 +207,12 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu) return; } SEQ_printf(m, "%s\n", dev->name); - SEQ_printf(m, " max_delta_ns: %lu\n", dev->max_delta_ns); - SEQ_printf(m, " min_delta_ns: %lu\n", dev->min_delta_ns); - SEQ_printf(m, " mult: %lu\n", dev->mult); - SEQ_printf(m, " shift: %d\n", dev->shift); + SEQ_printf(m, " max_delta_ns: %llu\n", + (unsigned long long) dev->max_delta_ns); + SEQ_printf(m, " min_delta_ns: %llu\n", + (unsigned long long) dev->min_delta_ns); + SEQ_printf(m, " mult: %u\n", dev->mult); + SEQ_printf(m, " shift: %u\n", dev->shift); SEQ_printf(m, " mode: %d\n", dev->mode); SEQ_printf(m, " next_event: %Ld nsecs\n", (unsigned long long) ktime_to_ns(dev->next_event)); @@ -252,7 +257,7 @@ static int timer_list_show(struct seq_file *m, void *v) u64 now = ktime_to_ns(ktime_get()); int cpu; - SEQ_printf(m, "Timer List Version: v0.4\n"); + SEQ_printf(m, "Timer List Version: v0.5\n"); SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES); SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 874f289..88bd9ae 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1361,11 +1361,7 @@ int trace_array_vprintk(struct trace_array *tr, pause_graph_tracing(); raw_local_irq_save(irq_flags); __raw_spin_lock(&trace_buf_lock); - if (args == NULL) { - strncpy(trace_buf, fmt, TRACE_BUF_SIZE); - len = strlen(trace_buf); - } else - len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args); + len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args); size = sizeof(*entry) + len + 1; buffer = tr->buffer; @@ -1516,6 +1512,8 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos) int i = (int)*pos; void *ent; + WARN_ON_ONCE(iter->leftover); + (*pos)++; /* can't go backwards */ @@ -1614,8 +1612,16 @@ static void *s_start(struct seq_file *m, loff_t *pos) ; } else { - l = *pos - 1; - p = s_next(m, p, &l); + /* + * If we overflowed the seq_file before, then we want + * to just reuse the trace_seq buffer again. + */ + if (iter->leftover) + p = iter; + else { + l = *pos - 1; + p = s_next(m, p, &l); + } } trace_event_read_lock(); @@ -1923,6 +1929,7 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter) static int s_show(struct seq_file *m, void *v) { struct trace_iterator *iter = v; + int ret; if (iter->ent == NULL) { if (iter->tr) { @@ -1942,9 +1949,27 @@ static int s_show(struct seq_file *m, void *v) if (!(trace_flags & TRACE_ITER_VERBOSE)) print_func_help_header(m); } + } else if (iter->leftover) { + /* + * If we filled the seq_file buffer earlier, we + * want to just show it now. + */ + ret = trace_print_seq(m, &iter->seq); + + /* ret should this time be zero, but you never know */ + iter->leftover = ret; + } else { print_trace_line(iter); - trace_print_seq(m, &iter->seq); + ret = trace_print_seq(m, &iter->seq); + /* + * If we overflow the seq_file buffer, then it will + * ask us for this data again at start up. + * Use that instead. + * ret is 0 if seq_file write succeeded. + * -1 otherwise. + */ + iter->leftover = ret; } return 0; @@ -2898,6 +2923,10 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) else cpumask_clear_cpu(iter->cpu_file, tracing_reader_cpumask); + + if (iter->trace->pipe_close) + iter->trace->pipe_close(iter); + mutex_unlock(&trace_types_lock); free_cpumask_var(iter->started); @@ -3320,6 +3349,16 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, return cnt; } +static int mark_printk(const char *fmt, ...) +{ + int ret; + va_list args; + va_start(args, fmt); + ret = trace_vprintk(0, fmt, args); + va_end(args); + return ret; +} + static ssize_t tracing_mark_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) @@ -3346,7 +3385,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, } else buf[cnt] = '\0'; - cnt = trace_vprintk(0, buf, NULL); + cnt = mark_printk("%s", buf); kfree(buf); *fpos += cnt; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 1d7f483..7fa33ca 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -272,6 +272,7 @@ struct tracer_flags { * @pipe_open: called when the trace_pipe file is opened * @wait_pipe: override how the user waits for traces on trace_pipe * @close: called when the trace file is released + * @pipe_close: called when the trace_pipe file is released * @read: override the default read callback on trace_pipe * @splice_read: override the default splice_read callback on trace_pipe * @selftest: selftest to run on boot (see trace_selftest.c) @@ -290,6 +291,7 @@ struct tracer { void (*pipe_open)(struct trace_iterator *iter); void (*wait_pipe)(struct trace_iterator *iter); void (*close)(struct trace_iterator *iter); + void (*pipe_close)(struct trace_iterator *iter); ssize_t (*read)(struct trace_iterator *iter, struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 45e6c01..a43d009 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -14,9 +14,20 @@ #include "trace.h" #include "trace_output.h" -struct fgraph_data { +struct fgraph_cpu_data { pid_t last_pid; int depth; + int ignore; +}; + +struct fgraph_data { + struct fgraph_cpu_data *cpu_data; + + /* Place to preserve last processed entry. */ + struct ftrace_graph_ent_entry ent; + struct ftrace_graph_ret_entry ret; + int failed; + int cpu; }; #define TRACE_GRAPH_INDENT 2 @@ -384,7 +395,7 @@ verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data) if (!data) return TRACE_TYPE_HANDLED; - last_pid = &(per_cpu_ptr(data, cpu)->last_pid); + last_pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid); if (*last_pid == pid) return TRACE_TYPE_HANDLED; @@ -435,26 +446,49 @@ static struct ftrace_graph_ret_entry * get_return_for_leaf(struct trace_iterator *iter, struct ftrace_graph_ent_entry *curr) { - struct ring_buffer_iter *ring_iter; + struct fgraph_data *data = iter->private; + struct ring_buffer_iter *ring_iter = NULL; struct ring_buffer_event *event; struct ftrace_graph_ret_entry *next; - ring_iter = iter->buffer_iter[iter->cpu]; + /* + * If the previous output failed to write to the seq buffer, + * then we just reuse the data from before. + */ + if (data && data->failed) { + curr = &data->ent; + next = &data->ret; + } else { - /* First peek to compare current entry and the next one */ - if (ring_iter) - event = ring_buffer_iter_peek(ring_iter, NULL); - else { - /* We need to consume the current entry to see the next one */ - ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL); - event = ring_buffer_peek(iter->tr->buffer, iter->cpu, - NULL); - } + ring_iter = iter->buffer_iter[iter->cpu]; + + /* First peek to compare current entry and the next one */ + if (ring_iter) + event = ring_buffer_iter_peek(ring_iter, NULL); + else { + /* + * We need to consume the current entry to see + * the next one. + */ + ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL); + event = ring_buffer_peek(iter->tr->buffer, iter->cpu, + NULL); + } - if (!event) - return NULL; + if (!event) + return NULL; + + next = ring_buffer_event_data(event); - next = ring_buffer_event_data(event); + if (data) { + /* + * Save current and next entries for later reference + * if the output fails. + */ + data->ent = *curr; + data->ret = *next; + } + } if (next->ent.type != TRACE_GRAPH_RET) return NULL; @@ -640,7 +674,7 @@ print_graph_entry_leaf(struct trace_iterator *iter, if (data) { int cpu = iter->cpu; - int *depth = &(per_cpu_ptr(data, cpu)->depth); + int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth); /* * Comments display at + 1 to depth. Since @@ -688,7 +722,7 @@ print_graph_entry_nested(struct trace_iterator *iter, if (data) { int cpu = iter->cpu; - int *depth = &(per_cpu_ptr(data, cpu)->depth); + int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth); *depth = call->depth; } @@ -782,19 +816,34 @@ static enum print_line_t print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s, struct trace_iterator *iter) { - int cpu = iter->cpu; + struct fgraph_data *data = iter->private; struct ftrace_graph_ent *call = &field->graph_ent; struct ftrace_graph_ret_entry *leaf_ret; + static enum print_line_t ret; + int cpu = iter->cpu; if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func)) return TRACE_TYPE_PARTIAL_LINE; leaf_ret = get_return_for_leaf(iter, field); if (leaf_ret) - return print_graph_entry_leaf(iter, field, leaf_ret, s); + ret = print_graph_entry_leaf(iter, field, leaf_ret, s); else - return print_graph_entry_nested(iter, field, s, cpu); + ret = print_graph_entry_nested(iter, field, s, cpu); + if (data) { + /* + * If we failed to write our output, then we need to make + * note of it. Because we already consumed our entry. + */ + if (s->full) { + data->failed = 1; + data->cpu = cpu; + } else + data->failed = 0; + } + + return ret; } static enum print_line_t @@ -810,7 +859,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, if (data) { int cpu = iter->cpu; - int *depth = &(per_cpu_ptr(data, cpu)->depth); + int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth); /* * Comments display at + 1 to depth. This is the @@ -873,7 +922,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent, int i; if (data) - depth = per_cpu_ptr(data, iter->cpu)->depth; + depth = per_cpu_ptr(data->cpu_data, iter->cpu)->depth; if (print_graph_prologue(iter, s, 0, 0)) return TRACE_TYPE_PARTIAL_LINE; @@ -941,8 +990,33 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent, enum print_line_t print_graph_function(struct trace_iterator *iter) { + struct ftrace_graph_ent_entry *field; + struct fgraph_data *data = iter->private; struct trace_entry *entry = iter->ent; struct trace_seq *s = &iter->seq; + int cpu = iter->cpu; + int ret; + + if (data && per_cpu_ptr(data->cpu_data, cpu)->ignore) { + per_cpu_ptr(data->cpu_data, cpu)->ignore = 0; + return TRACE_TYPE_HANDLED; + } + + /* + * If the last output failed, there's a possibility we need + * to print out the missing entry which would never go out. + */ + if (data && data->failed) { + field = &data->ent; + iter->cpu = data->cpu; + ret = print_graph_entry(field, s, iter); + if (ret == TRACE_TYPE_HANDLED && iter->cpu != cpu) { + per_cpu_ptr(data->cpu_data, iter->cpu)->ignore = 1; + ret = TRACE_TYPE_NO_CONSUME; + } + iter->cpu = cpu; + return ret; + } switch (entry->type) { case TRACE_GRAPH_ENT: { @@ -952,7 +1026,7 @@ print_graph_function(struct trace_iterator *iter) * sizeof(struct ftrace_graph_ent_entry) is very small, * it can be safely saved at the stack. */ - struct ftrace_graph_ent_entry *field, saved; + struct ftrace_graph_ent_entry saved; trace_assign_type(field, entry); saved = *field; return print_graph_entry(&saved, s, iter); @@ -1030,31 +1104,54 @@ static void print_graph_headers(struct seq_file *s) static void graph_trace_open(struct trace_iterator *iter) { /* pid and depth on the last trace processed */ - struct fgraph_data *data = alloc_percpu(struct fgraph_data); + struct fgraph_data *data; int cpu; + iter->private = NULL; + + data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) - pr_warning("function graph tracer: not enough memory\n"); - else - for_each_possible_cpu(cpu) { - pid_t *pid = &(per_cpu_ptr(data, cpu)->last_pid); - int *depth = &(per_cpu_ptr(data, cpu)->depth); - *pid = -1; - *depth = 0; - } + goto out_err; + + data->cpu_data = alloc_percpu(struct fgraph_cpu_data); + if (!data->cpu_data) + goto out_err_free; + + for_each_possible_cpu(cpu) { + pid_t *pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid); + int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth); + int *ignore = &(per_cpu_ptr(data->cpu_data, cpu)->ignore); + *pid = -1; + *depth = 0; + *ignore = 0; + } iter->private = data; + + return; + + out_err_free: + kfree(data); + out_err: + pr_warning("function graph tracer: not enough memory\n"); } static void graph_trace_close(struct trace_iterator *iter) { - free_percpu(iter->private); + struct fgraph_data *data = iter->private; + + if (data) { + free_percpu(data->cpu_data); + kfree(data); + } } static struct tracer graph_trace __read_mostly = { .name = "function_graph", .open = graph_trace_open, + .pipe_open = graph_trace_open, .close = graph_trace_close, + .pipe_close = graph_trace_close, .wait_pipe = poll_wait_pipe, .init = graph_trace_init, .reset = graph_trace_reset, diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index aff5f80..b52d397 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -606,23 +606,22 @@ static int create_trace_probe(int argc, char **argv) */ struct trace_probe *tp; int i, ret = 0; - int is_return = 0; + int is_return = 0, is_delete = 0; char *symbol = NULL, *event = NULL, *arg = NULL, *group = NULL; unsigned long offset = 0; void *addr = NULL; char buf[MAX_EVENT_NAME_LEN]; - if (argc < 2) { - pr_info("Probe point is not specified.\n"); - return -EINVAL; - } - + /* argc must be >= 1 */ if (argv[0][0] == 'p') is_return = 0; else if (argv[0][0] == 'r') is_return = 1; + else if (argv[0][0] == '-') + is_delete = 1; else { - pr_info("Probe definition must be started with 'p' or 'r'.\n"); + pr_info("Probe definition must be started with 'p', 'r' or" + " '-'.\n"); return -EINVAL; } @@ -642,7 +641,29 @@ static int create_trace_probe(int argc, char **argv) return -EINVAL; } } + if (!group) + group = KPROBE_EVENT_SYSTEM; + if (is_delete) { + if (!event) { + pr_info("Delete command needs an event name.\n"); + return -EINVAL; + } + tp = find_probe_event(event, group); + if (!tp) { + pr_info("Event %s/%s doesn't exist.\n", group, event); + return -ENOENT; + } + /* delete an event */ + unregister_trace_probe(tp); + free_trace_probe(tp); + return 0; + } + + if (argc < 2) { + pr_info("Probe point is not specified.\n"); + return -EINVAL; + } if (isdigit(argv[1][0])) { if (is_return) { pr_info("Return probe point must be a symbol.\n"); @@ -671,8 +692,6 @@ static int create_trace_probe(int argc, char **argv) argc -= 2; argv += 2; /* setup a probe */ - if (!group) - group = KPROBE_EVENT_SYSTEM; if (!event) { /* Make a new event name */ if (symbol) @@ -1114,7 +1133,7 @@ static int kprobe_event_define_fields(struct ftrace_event_call *event_call) struct trace_probe *tp = (struct trace_probe *)event_call->data; ret = trace_define_common_fields(event_call); - if (!ret) + if (ret) return ret; DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0); @@ -1132,7 +1151,7 @@ static int kretprobe_event_define_fields(struct ftrace_event_call *event_call) struct trace_probe *tp = (struct trace_probe *)event_call->data; ret = trace_define_common_fields(event_call); - if (!ret) + if (ret) return ret; DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0); diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c index ddfa0fd..acb87d4 100644 --- a/kernel/trace/trace_ksym.c +++ b/kernel/trace/trace_ksym.c @@ -79,11 +79,12 @@ void ksym_collect_stats(unsigned long hbp_hit_addr) } #endif /* CONFIG_PROFILE_KSYM_TRACER */ -void ksym_hbp_handler(struct perf_event *hbp, void *data) +void ksym_hbp_handler(struct perf_event *hbp, int nmi, + struct perf_sample_data *data, + struct pt_regs *regs) { struct ring_buffer_event *event; struct ksym_trace_entry *entry; - struct pt_regs *regs = data; struct ring_buffer *buffer; int pc; diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index b6c12c6..8e46b33 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -23,13 +23,21 @@ static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly; static int next_event_type = __TRACE_LAST_TYPE + 1; -void trace_print_seq(struct seq_file *m, struct trace_seq *s) +int trace_print_seq(struct seq_file *m, struct trace_seq *s) { int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len; + int ret; + + ret = seq_write(m, s->buffer, len); - seq_write(m, s->buffer, len); + /* + * Only reset this buffer if we successfully wrote to the + * seq_file buffer. + */ + if (!ret) + trace_seq_init(s); - trace_seq_init(s); + return ret; } enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter) @@ -85,7 +93,7 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...) va_list ap; int ret; - if (!len) + if (s->full || !len) return 0; va_start(ap, fmt); @@ -93,8 +101,10 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...) va_end(ap); /* If we can't write it all, don't bother writing anything */ - if (ret >= len) + if (ret >= len) { + s->full = 1; return 0; + } s->len += ret; @@ -119,14 +129,16 @@ trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args) int len = (PAGE_SIZE - 1) - s->len; int ret; - if (!len) + if (s->full || !len) return 0; ret = vsnprintf(s->buffer + s->len, len, fmt, args); /* If we can't write it all, don't bother writing anything */ - if (ret >= len) + if (ret >= len) { + s->full = 1; return 0; + } s->len += ret; @@ -139,14 +151,16 @@ int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary) int len = (PAGE_SIZE - 1) - s->len; int ret; - if (!len) + if (s->full || !len) return 0; ret = bstr_printf(s->buffer + s->len, len, fmt, binary); /* If we can't write it all, don't bother writing anything */ - if (ret >= len) + if (ret >= len) { + s->full = 1; return 0; + } s->len += ret; @@ -167,8 +181,13 @@ int trace_seq_puts(struct trace_seq *s, const char *str) { int len = strlen(str); - if (len > ((PAGE_SIZE - 1) - s->len)) + if (s->full) + return 0; + + if (len > ((PAGE_SIZE - 1) - s->len)) { + s->full = 1; return 0; + } memcpy(s->buffer + s->len, str, len); s->len += len; @@ -178,9 +197,14 @@ int trace_seq_puts(struct trace_seq *s, const char *str) int trace_seq_putc(struct trace_seq *s, unsigned char c) { - if (s->len >= (PAGE_SIZE - 1)) + if (s->full) return 0; + if (s->len >= (PAGE_SIZE - 1)) { + s->full = 1; + return 0; + } + s->buffer[s->len++] = c; return 1; @@ -188,9 +212,14 @@ int trace_seq_putc(struct trace_seq *s, unsigned char c) int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len) { - if (len > ((PAGE_SIZE - 1) - s->len)) + if (s->full) return 0; + if (len > ((PAGE_SIZE - 1) - s->len)) { + s->full = 1; + return 0; + } + memcpy(s->buffer + s->len, mem, len); s->len += len; @@ -203,6 +232,9 @@ int trace_seq_putmem_hex(struct trace_seq *s, const void *mem, size_t len) const unsigned char *data = mem; int i, j; + if (s->full) + return 0; + #ifdef __BIG_ENDIAN for (i = 0, j = 0; i < len; i++) { #else @@ -220,8 +252,13 @@ void *trace_seq_reserve(struct trace_seq *s, size_t len) { void *ret; - if (len > ((PAGE_SIZE - 1) - s->len)) + if (s->full) + return 0; + + if (len > ((PAGE_SIZE - 1) - s->len)) { + s->full = 1; return NULL; + } ret = s->buffer + s->len; s->len += len; @@ -233,8 +270,14 @@ int trace_seq_path(struct trace_seq *s, struct path *path) { unsigned char *p; - if (s->len >= (PAGE_SIZE - 1)) + if (s->full) + return 0; + + if (s->len >= (PAGE_SIZE - 1)) { + s->full = 1; return 0; + } + p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len); if (!IS_ERR(p)) { p = mangle_path(s->buffer + s->len, p, "\n"); @@ -247,6 +290,7 @@ int trace_seq_path(struct trace_seq *s, struct path *path) return 1; } + s->full = 1; return 0; } @@ -373,6 +417,9 @@ int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm, unsigned long vmstart = 0; int ret = 1; + if (s->full) + return 0; + if (mm) { const struct vm_area_struct *vma; diff --git a/kernel/user-return-notifier.c b/kernel/user-return-notifier.c new file mode 100644 index 0000000..eb27fd3 --- /dev/null +++ b/kernel/user-return-notifier.c @@ -0,0 +1,44 @@ + +#include <linux/user-return-notifier.h> +#include <linux/percpu.h> +#include <linux/sched.h> +#include <linux/module.h> + +static DEFINE_PER_CPU(struct hlist_head, return_notifier_list); + +/* + * Request a notification when the current cpu returns to userspace. Must be + * called in atomic context. The notifier will also be called in atomic + * context. + */ +void user_return_notifier_register(struct user_return_notifier *urn) +{ + set_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY); + hlist_add_head(&urn->link, &__get_cpu_var(return_notifier_list)); +} +EXPORT_SYMBOL_GPL(user_return_notifier_register); + +/* + * Removes a registered user return notifier. Must be called from atomic + * context, and from the same cpu registration occured in. + */ +void user_return_notifier_unregister(struct user_return_notifier *urn) +{ + hlist_del(&urn->link); + if (hlist_empty(&__get_cpu_var(return_notifier_list))) + clear_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY); +} +EXPORT_SYMBOL_GPL(user_return_notifier_unregister); + +/* Calls registered user return notifiers */ +void fire_user_return_notifiers(void) +{ + struct user_return_notifier *urn; + struct hlist_node *tmp1, *tmp2; + struct hlist_head *head; + + head = &get_cpu_var(return_notifier_list); + hlist_for_each_entry_safe(urn, tmp1, tmp2, head, link) + urn->on_user_return(urn); + put_cpu_var(return_notifier_list); +} diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index 69eae35..a2cd77e 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -57,78 +57,47 @@ static int proc_do_uts_string(ctl_table *table, int write, #define proc_do_uts_string NULL #endif - -#ifdef CONFIG_SYSCTL_SYSCALL -/* The generic string strategy routine: */ -static int sysctl_uts_string(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - struct ctl_table uts_table; - int r, write; - write = newval && newlen; - memcpy(&uts_table, table, sizeof(uts_table)); - uts_table.data = get_uts(table, write); - r = sysctl_string(&uts_table, oldval, oldlenp, newval, newlen); - put_uts(table, write, uts_table.data); - return r; -} -#else -#define sysctl_uts_string NULL -#endif - static struct ctl_table uts_kern_table[] = { { - .ctl_name = KERN_OSTYPE, .procname = "ostype", .data = init_uts_ns.name.sysname, .maxlen = sizeof(init_uts_ns.name.sysname), .mode = 0444, .proc_handler = proc_do_uts_string, - .strategy = sysctl_uts_string, }, { - .ctl_name = KERN_OSRELEASE, .procname = "osrelease", .data = init_uts_ns.name.release, .maxlen = sizeof(init_uts_ns.name.release), .mode = 0444, .proc_handler = proc_do_uts_string, - .strategy = sysctl_uts_string, }, { - .ctl_name = KERN_VERSION, .procname = "version", .data = init_uts_ns.name.version, .maxlen = sizeof(init_uts_ns.name.version), .mode = 0444, .proc_handler = proc_do_uts_string, - .strategy = sysctl_uts_string, }, { - .ctl_name = KERN_NODENAME, .procname = "hostname", .data = init_uts_ns.name.nodename, .maxlen = sizeof(init_uts_ns.name.nodename), .mode = 0644, .proc_handler = proc_do_uts_string, - .strategy = sysctl_uts_string, }, { - .ctl_name = KERN_DOMAINNAME, .procname = "domainname", .data = init_uts_ns.name.domainname, .maxlen = sizeof(init_uts_ns.name.domainname), .mode = 0644, .proc_handler = proc_do_uts_string, - .strategy = sysctl_uts_string, }, {} }; static struct ctl_table uts_root_table[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, .child = uts_kern_table, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 67e526b..dee4865 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -68,6 +68,116 @@ struct workqueue_struct { #endif }; +#ifdef CONFIG_DEBUG_OBJECTS_WORK + +static struct debug_obj_descr work_debug_descr; + +/* + * fixup_init is called when: + * - an active object is initialized + */ +static int work_fixup_init(void *addr, enum debug_obj_state state) +{ + struct work_struct *work = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + cancel_work_sync(work); + debug_object_init(work, &work_debug_descr); + return 1; + default: + return 0; + } +} + +/* + * fixup_activate is called when: + * - an active object is activated + * - an unknown object is activated (might be a statically initialized object) + */ +static int work_fixup_activate(void *addr, enum debug_obj_state state) +{ + struct work_struct *work = addr; + + switch (state) { + + case ODEBUG_STATE_NOTAVAILABLE: + /* + * This is not really a fixup. The work struct was + * statically initialized. We just make sure that it + * is tracked in the object tracker. + */ + if (test_bit(WORK_STRUCT_STATIC, work_data_bits(work))) { + debug_object_init(work, &work_debug_descr); + debug_object_activate(work, &work_debug_descr); + return 0; + } + WARN_ON_ONCE(1); + return 0; + + case ODEBUG_STATE_ACTIVE: + WARN_ON(1); + + default: + return 0; + } +} + +/* + * fixup_free is called when: + * - an active object is freed + */ +static int work_fixup_free(void *addr, enum debug_obj_state state) +{ + struct work_struct *work = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + cancel_work_sync(work); + debug_object_free(work, &work_debug_descr); + return 1; + default: + return 0; + } +} + +static struct debug_obj_descr work_debug_descr = { + .name = "work_struct", + .fixup_init = work_fixup_init, + .fixup_activate = work_fixup_activate, + .fixup_free = work_fixup_free, +}; + +static inline void debug_work_activate(struct work_struct *work) +{ + debug_object_activate(work, &work_debug_descr); +} + +static inline void debug_work_deactivate(struct work_struct *work) +{ + debug_object_deactivate(work, &work_debug_descr); +} + +void __init_work(struct work_struct *work, int onstack) +{ + if (onstack) + debug_object_init_on_stack(work, &work_debug_descr); + else + debug_object_init(work, &work_debug_descr); +} +EXPORT_SYMBOL_GPL(__init_work); + +void destroy_work_on_stack(struct work_struct *work) +{ + debug_object_free(work, &work_debug_descr); +} +EXPORT_SYMBOL_GPL(destroy_work_on_stack); + +#else +static inline void debug_work_activate(struct work_struct *work) { } +static inline void debug_work_deactivate(struct work_struct *work) { } +#endif + /* Serializes the accesses to the list of workqueues. */ static DEFINE_SPINLOCK(workqueue_lock); static LIST_HEAD(workqueues); @@ -145,6 +255,7 @@ static void __queue_work(struct cpu_workqueue_struct *cwq, { unsigned long flags; + debug_work_activate(work); spin_lock_irqsave(&cwq->lock, flags); insert_work(cwq, work, &cwq->worklist); spin_unlock_irqrestore(&cwq->lock, flags); @@ -280,6 +391,7 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq) struct lockdep_map lockdep_map = work->lockdep_map; #endif trace_workqueue_execution(cwq->thread, work); + debug_work_deactivate(work); cwq->current_work = work; list_del_init(cwq->worklist.next); spin_unlock_irq(&cwq->lock); @@ -350,11 +462,18 @@ static void wq_barrier_func(struct work_struct *work) static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, struct wq_barrier *barr, struct list_head *head) { - INIT_WORK(&barr->work, wq_barrier_func); + /* + * debugobject calls are safe here even with cwq->lock locked + * as we know for sure that this will not trigger any of the + * checks and call back into the fixup functions where we + * might deadlock. + */ + INIT_WORK_ON_STACK(&barr->work, wq_barrier_func); __set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work)); init_completion(&barr->done); + debug_work_activate(&barr->work); insert_work(cwq, &barr->work, head); } @@ -372,8 +491,10 @@ static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq) } spin_unlock_irq(&cwq->lock); - if (active) + if (active) { wait_for_completion(&barr.done); + destroy_work_on_stack(&barr.work); + } return active; } @@ -451,6 +572,7 @@ out: return 0; wait_for_completion(&barr.done); + destroy_work_on_stack(&barr.work); return 1; } EXPORT_SYMBOL_GPL(flush_work); @@ -485,6 +607,7 @@ static int try_to_grab_pending(struct work_struct *work) */ smp_rmb(); if (cwq == get_wq_data(work)) { + debug_work_deactivate(work); list_del_init(&work->entry); ret = 1; } @@ -507,8 +630,10 @@ static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq, } spin_unlock_irq(&cwq->lock); - if (unlikely(running)) + if (unlikely(running)) { wait_for_completion(&barr.done); + destroy_work_on_stack(&barr.work); + } } static void wait_on_work(struct work_struct *work) |