cregit-Linux how code gets into the kernel

Release 4.9 fs/timerfd.c

Directory: fs
/*
 *  fs/timerfd.c
 *
 *  Copyright (C) 2007  Davide Libenzi <davidel@xmailserver.org>
 *
 *
 *  Thanks to Thomas Gleixner for code reviews and useful comments.
 *
 */

#include <linux/alarmtimer.h>
#include <linux/file.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/time.h>
#include <linux/hrtimer.h>
#include <linux/anon_inodes.h>
#include <linux/timerfd.h>
#include <linux/syscalls.h>
#include <linux/compat.h>
#include <linux/rcupdate.h>


struct timerfd_ctx {
	union {
		
struct hrtimer tmr;
		
struct alarm alarm;
	} 
t;
	
ktime_t tintv;
	
ktime_t moffs;
	
wait_queue_head_t wqh;
	
u64 ticks;
	
int clockid;
	
short unsigned expired;
	
short unsigned settime_flags;	/* to show in fdinfo */
	
struct rcu_head rcu;
	
struct list_head clist;
	
bool might_cancel;
};

static LIST_HEAD(cancel_list);
static DEFINE_SPINLOCK(cancel_lock);


static inline bool isalarm(struct timerfd_ctx *ctx) { return ctx->clockid == CLOCK_REALTIME_ALARM || ctx->clockid == CLOCK_BOOTTIME_ALARM; }

Contributors

PersonTokensPropCommitsCommitProp
todd poynortodd poynor1976.00%150.00%
davide libenzidavide libenzi624.00%150.00%
Total25100.00%2100.00%

/* * This gets called when the timer event triggers. We set the "expired" * flag, but we do not re-arm the timer (in case it's necessary, * tintv.tv64 != 0) until the timer is accessed. */
static void timerfd_triggered(struct timerfd_ctx *ctx) { unsigned long flags; spin_lock_irqsave(&ctx->wqh.lock, flags); ctx->expired = 1; ctx->ticks++; wake_up_locked(&ctx->wqh); spin_unlock_irqrestore(&ctx->wqh.lock, flags); }

Contributors

PersonTokensPropCommitsCommitProp
davide libenzidavide libenzi5187.93%375.00%
todd poynortodd poynor712.07%125.00%
Total58100.00%4100.00%


static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr) { struct timerfd_ctx *ctx = container_of(htmr, struct timerfd_ctx, t.tmr); timerfd_triggered(ctx); return HRTIMER_NORESTART; }

Contributors

PersonTokensPropCommitsCommitProp
todd poynortodd poynor3389.19%150.00%
davide libenzidavide libenzi410.81%150.00%
Total37100.00%2100.00%


static enum alarmtimer_restart timerfd_alarmproc(struct alarm *alarm, ktime_t now) { struct timerfd_ctx *ctx = container_of(alarm, struct timerfd_ctx, t.alarm); timerfd_triggered(ctx); return ALARMTIMER_NORESTART; }

Contributors

PersonTokensPropCommitsCommitProp
todd poynortodd poynor40100.00%1100.00%
Total40100.00%1100.00%

/* * Called when the clock was set to cancel the timers in the cancel * list. This will wake up processes waiting on these timers. The * wake-up requires ctx->ticks to be non zero, therefore we increment * it before calling wake_up_locked(). */
void timerfd_clock_was_set(void) { ktime_t moffs = ktime_mono_to_real((ktime_t){ .tv64 = 0 }); struct timerfd_ctx *ctx; unsigned long flags; rcu_read_lock(); list_for_each_entry_rcu(ctx, &cancel_list, clist) { if (!ctx->might_cancel) continue; spin_lock_irqsave(&ctx->wqh.lock, flags); if (ctx->moffs.tv64 != moffs.tv64) { ctx->moffs.tv64 = KTIME_MAX; ctx->ticks++; wake_up_locked(&ctx->wqh); } spin_unlock_irqrestore(&ctx->wqh.lock, flags); } rcu_read_unlock(); }

Contributors

PersonTokensPropCommitsCommitProp
thomas gleixnerthomas gleixner9380.87%240.00%
davide libenzidavide libenzi1613.91%120.00%
max asbockmax asbock54.35%120.00%
arjan van de venarjan van de ven10.87%120.00%
Total115100.00%5100.00%


static void timerfd_remove_cancel(struct timerfd_ctx *ctx) { if (ctx->might_cancel) { ctx->might_cancel = false; spin_lock(&cancel_lock); list_del_rcu(&ctx->clist); spin_unlock(&cancel_lock); } }

Contributors

PersonTokensPropCommitsCommitProp
thomas gleixnerthomas gleixner4497.78%150.00%
davide libenzidavide libenzi12.22%150.00%
Total45100.00%2100.00%


static bool timerfd_canceled(struct timerfd_ctx *ctx) { if (!ctx->might_cancel || ctx->moffs.tv64 != KTIME_MAX) return false; ctx->moffs = ktime_mono_to_real((ktime_t){ .tv64 = 0 }); return true; }

Contributors

PersonTokensPropCommitsCommitProp
thomas gleixnerthomas gleixner49100.00%3100.00%
Total49100.00%3100.00%


static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags) { if ((ctx->clockid == CLOCK_REALTIME || ctx->clockid == CLOCK_REALTIME_ALARM) && (flags & TFD_TIMER_ABSTIME) && (flags & TFD_TIMER_CANCEL_ON_SET)) { if (!ctx->might_cancel) { ctx->might_cancel = true; spin_lock(&cancel_lock); list_add_rcu(&ctx->clist, &cancel_list); spin_unlock(&cancel_lock); } } else if (ctx->might_cancel) { timerfd_remove_cancel(ctx); } }

Contributors

PersonTokensPropCommitsCommitProp
thomas gleixnerthomas gleixner8891.67%266.67%
todd poynortodd poynor88.33%133.33%
Total96100.00%3100.00%


static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) { ktime_t remaining; if (isalarm(ctx)) remaining = alarm_expires_remaining(&ctx->t.alarm); else remaining = hrtimer_expires_remaining_adjusted(&ctx->t.tmr); return remaining.tv64 < 0 ? ktime_set(0, 0): remaining; }

Contributors

PersonTokensPropCommitsCommitProp
thomas gleixnerthomas gleixner4064.52%375.00%
todd poynortodd poynor2235.48%125.00%
Total62100.00%4100.00%


static int timerfd_setup(struct timerfd_ctx *ctx, int flags, const struct itimerspec *ktmr) { enum hrtimer_mode htmode; ktime_t texp; int clockid = ctx->clockid; htmode = (flags & TFD_TIMER_ABSTIME) ? HRTIMER_MODE_ABS: HRTIMER_MODE_REL; texp = timespec_to_ktime(ktmr->it_value); ctx->expired = 0; ctx->ticks = 0; ctx->tintv = timespec_to_ktime(ktmr->it_interval); if (isalarm(ctx)) { alarm_init(&ctx->t.alarm, ctx->clockid == CLOCK_REALTIME_ALARM ? ALARM_REALTIME : ALARM_BOOTTIME, timerfd_alarmproc); } else { hrtimer_init(&ctx->t.tmr, clockid, htmode); hrtimer_set_expires(&ctx->t.tmr, texp); ctx->t.tmr.function = timerfd_tmrproc; } if (texp.tv64 != 0) { if (isalarm(ctx)) { if (flags & TFD_TIMER_ABSTIME) alarm_start(&ctx->t.alarm, texp); else alarm_start_relative(&ctx->t.alarm, texp); } else { hrtimer_start(&ctx->t.tmr, texp, htmode); } if (timerfd_canceled(ctx)) return -ECANCELED; } ctx->settime_flags = flags & TFD_SETTIME_FLAGS; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
davide libenzidavide libenzi11548.52%233.33%
todd poynortodd poynor8535.86%116.67%
thomas gleixnerthomas gleixner2410.13%116.67%
cyrill gorcunovcyrill gorcunov83.38%116.67%
arjan van de venarjan van de ven52.11%116.67%
Total237100.00%6100.00%


static int timerfd_release(struct inode *inode, struct file *file) { struct timerfd_ctx *ctx = file->private_data; timerfd_remove_cancel(ctx); if (isalarm(ctx)) alarm_cancel(&ctx->t.alarm); else hrtimer_cancel(&ctx->t.tmr); kfree_rcu(ctx, rcu); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
davide libenzidavide libenzi4058.82%133.33%
todd poynortodd poynor2029.41%133.33%
thomas gleixnerthomas gleixner811.76%133.33%
Total68100.00%3100.00%


static unsigned int timerfd_poll(struct file *file, poll_table *wait) { struct timerfd_ctx *ctx = file->private_data; unsigned int events = 0; unsigned long flags; poll_wait(file, &ctx->wqh, wait); spin_lock_irqsave(&ctx->wqh.lock, flags); if (ctx->ticks) events |= POLLIN; spin_unlock_irqrestore(&ctx->wqh.lock, flags); return events; }

Contributors

PersonTokensPropCommitsCommitProp
davide libenzidavide libenzi84100.00%3100.00%
Total84100.00%3100.00%


static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct timerfd_ctx *ctx = file->private_data; ssize_t res; u64 ticks = 0; if (count < sizeof(ticks)) return -EINVAL; spin_lock_irq(&ctx->wqh.lock); if (file->f_flags & O_NONBLOCK) res = -EAGAIN; else res = wait_event_interruptible_locked_irq(ctx->wqh, ctx->ticks); /* * If clock has changed, we do not care about the * ticks and we do not rearm the timer. Userspace must * reevaluate anyway. */ if (timerfd_canceled(ctx)) { ctx->ticks = 0; ctx->expired = 0; res = -ECANCELED; } if (ctx->ticks) { ticks = ctx->ticks; if (ctx->expired && ctx->tintv.tv64) { /* * If tintv.tv64 != 0, this is a periodic timer that * needs to be re-armed. We avoid doing it in the timer * callback to avoid DoS attacks specifying a very * short timer period. */ if (isalarm(ctx)) { ticks += alarm_forward_now( &ctx->t.alarm, ctx->tintv) - 1; alarm_restart(&ctx->t.alarm); } else { ticks += hrtimer_forward_now(&ctx->t.tmr, ctx->tintv) - 1; hrtimer_restart(&ctx->t.tmr); } } ctx->expired = 0; ctx->ticks = 0; } spin_unlock_irq(&ctx->wqh.lock); if (ticks) res = put_user(ticks, (u64 __user *) buf) ? -EFAULT: sizeof(ticks); return res; }

Contributors

PersonTokensPropCommitsCommitProp
davide libenzidavide libenzi17566.04%450.00%
todd poynortodd poynor4416.60%112.50%
thomas gleixnerthomas gleixner4015.09%225.00%
michal nazarewiczmichal nazarewicz62.26%112.50%
Total265100.00%8100.00%

#ifdef CONFIG_PROC_FS
static void timerfd_show(struct seq_file *m, struct file *file) { struct timerfd_ctx *ctx = file->private_data; struct itimerspec t; spin_lock_irq(&ctx->wqh.lock); t.it_value = ktime_to_timespec(timerfd_get_remaining(ctx)); t.it_interval = ktime_to_timespec(ctx->tintv); spin_unlock_irq(&ctx->wqh.lock); seq_printf(m, "clockid: %d\n" "ticks: %llu\n" "settime flags: 0%o\n" "it_value: (%llu, %llu)\n" "it_interval: (%llu, %llu)\n", ctx->clockid, (unsigned long long)ctx->ticks, ctx->settime_flags, (unsigned long long)t.it_value.tv_sec, (unsigned long long)t.it_value.tv_nsec, (unsigned long long)t.it_interval.tv_sec, (unsigned long long)t.it_interval.tv_nsec); }

Contributors

PersonTokensPropCommitsCommitProp
cyrill gorcunovcyrill gorcunov14298.61%150.00%
joe perchesjoe perches21.39%150.00%
Total144100.00%2100.00%

#else #define timerfd_show NULL #endif #ifdef CONFIG_CHECKPOINT_RESTORE
static long timerfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct timerfd_ctx *ctx = file->private_data; int ret = 0; switch (cmd) { case TFD_IOC_SET_TICKS: { u64 ticks; if (copy_from_user(&ticks, (u64 __user *)arg, sizeof(ticks))) return -EFAULT; if (!ticks) return -EINVAL; spin_lock_irq(&ctx->wqh.lock); if (!timerfd_canceled(ctx)) { ctx->ticks = ticks; wake_up_locked(&ctx->wqh); } else ret = -ECANCELED; spin_unlock_irq(&ctx->wqh.lock); break; } default: ret = -ENOTTY; break; } return ret; }

Contributors

PersonTokensPropCommitsCommitProp
cyrill gorcunovcyrill gorcunov141100.00%1100.00%
Total141100.00%1100.00%

#else #define timerfd_ioctl NULL #endif static const struct file_operations timerfd_fops = { .release = timerfd_release, .poll = timerfd_poll, .read = timerfd_read, .llseek = noop_llseek, .show_fdinfo = timerfd_show, .unlocked_ioctl = timerfd_ioctl, };
static int timerfd_fget(int fd, struct fd *p) { struct fd f = fdget(fd); if (!f.file) return -EBADF; if (f.file->f_op != &timerfd_fops) { fdput(f); return -EINVAL; } *p = f; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
davide libenzidavide libenzi4164.06%133.33%
al viroal viro2335.94%266.67%
Total64100.00%3100.00%

SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags) { int ufd; struct timerfd_ctx *ctx; /* Check the TFD_* constants for consistency. */ BUILD_BUG_ON(TFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(TFD_NONBLOCK != O_NONBLOCK); if ((flags & ~TFD_CREATE_FLAGS) || (clockid != CLOCK_MONOTONIC && clockid != CLOCK_REALTIME && clockid != CLOCK_REALTIME_ALARM && clockid != CLOCK_BOOTTIME && clockid != CLOCK_BOOTTIME_ALARM)) return -EINVAL; if (!capable(CAP_WAKE_ALARM) && (clockid == CLOCK_REALTIME_ALARM || clockid == CLOCK_BOOTTIME_ALARM)) return -EPERM; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; init_waitqueue_head(&ctx->wqh); ctx->clockid = clockid; if (isalarm(ctx)) alarm_init(&ctx->t.alarm, ctx->clockid == CLOCK_REALTIME_ALARM ? ALARM_REALTIME : ALARM_BOOTTIME, timerfd_alarmproc); else hrtimer_init(&ctx->t.tmr, clockid, HRTIMER_MODE_ABS); ctx->moffs = ktime_mono_to_real((ktime_t){ .tv64 = 0 }); ufd = anon_inode_getfd("[timerfd]", &timerfd_fops, ctx, O_RDWR | (flags & TFD_SHARED_FCNTL_FLAGS)); if (ufd < 0) kfree(ctx); return ufd; }
static int do_timerfd_settime(int ufd, int flags, const struct itimerspec *new, struct itimerspec *old) { struct fd f; struct timerfd_ctx *ctx; int ret; if ((flags & ~TFD_SETTIME_FLAGS) || !timespec_valid(&new->it_value) || !timespec_valid(&new->it_interval)) return -EINVAL; ret = timerfd_fget(ufd, &f); if (ret) return ret; ctx = f.file->private_data; if (!capable(CAP_WAKE_ALARM) && isalarm(ctx)) { fdput(f); return -EPERM; } timerfd_setup_cancel(ctx, flags); /* * We need to stop the existing timer before reprogramming * it to the new values. */ for (;;) { spin_lock_irq(&ctx->wqh.lock); if (isalarm(ctx)) { if (alarm_try_to_cancel(&ctx->t.alarm) >= 0) break; } else { if (hrtimer_try_to_cancel(&ctx->t.tmr) >= 0) break; } spin_unlock_irq(&ctx->wqh.lock); cpu_relax(); } /* * If the timer is expired and it's periodic, we need to advance it * because the caller may want to know the previous expiration time. * We do not update "ticks" and "expired" since the timer will be * re-programmed again in the following timerfd_setup() call. */ if (ctx->expired && ctx->tintv.tv64) { if (isalarm(ctx)) alarm_forward_now(&ctx->t.alarm, ctx->tintv); else hrtimer_forward_now(&ctx->t.tmr, ctx->tintv); } old->it_value = ktime_to_timespec(timerfd_get_remaining(ctx)); old->it_interval = ktime_to_timespec(ctx->tintv); /* * Re-program the timer to the new value ... */ ret = timerfd_setup(ctx, flags, new); spin_unlock_irq(&ctx->wqh.lock); fdput(f); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
davide libenzidavide libenzi16555.18%436.36%
todd poynortodd poynor5518.39%19.09%
al viroal viro4214.05%327.27%
eric carusoeric caruso248.03%19.09%
thomas gleixnerthomas gleixner134.35%218.18%
Total299100.00%11100.00%


static int do_timerfd_gettime(int ufd, struct itimerspec *t) { struct fd f; struct timerfd_ctx *ctx; int ret = timerfd_fget(ufd, &f); if (ret) return ret; ctx = f.file->private_data; spin_lock_irq(&ctx->wqh.lock); if (ctx->expired && ctx->tintv.tv64) { ctx->expired = 0; if (isalarm(ctx)) { ctx->ticks += alarm_forward_now( &ctx->t.alarm, ctx->tintv) - 1; alarm_restart(&ctx->t.alarm); } else { ctx->ticks += hrtimer_forward_now(&ctx->t.tmr, ctx->tintv) - 1; hrtimer_restart(&ctx->t.tmr); } } t->it_value = ktime_to_timespec(timerfd_get_remaining(ctx)); t->it_interval = ktime_to_timespec(ctx->tintv); spin_unlock_irq(&ctx->wqh.lock); fdput(f); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
davide libenzidavide libenzi11258.33%233.33%
todd poynortodd poynor4623.96%116.67%
al viroal viro3417.71%350.00%
Total192100.00%6100.00%

SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, const struct itimerspec __user *, utmr, struct itimerspec __user *, otmr) { struct itimerspec new, old; int ret; if (copy_from_user(&new, utmr, sizeof(new))) return -EFAULT; ret = do_timerfd_settime(ufd, flags, &new, &old); if (ret) return ret; if (otmr && copy_to_user(otmr, &old, sizeof(old))) return -EFAULT; return ret; } SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr) { struct itimerspec kotmr; int ret = do_timerfd_gettime(ufd, &kotmr); if (ret) return ret; return copy_to_user(otmr, &kotmr, sizeof(kotmr)) ? -EFAULT: 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, const struct compat_itimerspec __user *, utmr, struct compat_itimerspec __user *, otmr) { struct itimerspec new, old; int ret; if (get_compat_itimerspec(&new, utmr)) return -EFAULT; ret = do_timerfd_settime(ufd, flags, &new, &old); if (ret) return ret; if (otmr && put_compat_itimerspec(otmr, &old)) return -EFAULT; return ret; } COMPAT_SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct compat_itimerspec __user *, otmr) { struct itimerspec kotmr; int ret = do_timerfd_gettime(ufd, &kotmr); if (ret) return ret; return put_compat_itimerspec(otmr, &kotmr) ? -EFAULT: 0; } #endif

Overall Contributors

PersonTokensPropCommitsCommitProp
davide libenzidavide libenzi101137.21%515.62%
thomas gleixnerthomas gleixner44516.38%412.50%
todd poynortodd poynor43215.90%13.12%
al viroal viro37413.77%412.50%
cyrill gorcunovcyrill gorcunov33212.22%26.25%
eric carusoeric caruso461.69%13.12%
ulrich drepperulrich drepper210.77%412.50%
heiko carstensheiko carstens170.63%26.25%
max asbockmax asbock60.22%13.12%
arjan van de venarjan van de ven60.22%13.12%
michal nazarewiczmichal nazarewicz60.22%13.12%
arnd bergmannarnd bergmann50.18%13.12%
greg hackmanngreg hackmann40.15%13.12%
roland dreierroland dreier40.15%13.12%
adrian bunkadrian bunk30.11%13.12%
tejun heotejun heo30.11%13.12%
joe perchesjoe perches20.07%13.12%
Total2717100.00%32100.00%
Directory: fs