cregit-Linux how code gets into the kernel

Release 4.17 fs/eventfd.c

Directory: fs
/*
 *  fs/eventfd.c
 *
 *  Copyright (C) 2007  Davide Libenzi <davidel@xmailserver.org>
 *
 */

#include <linux/file.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/sched/signal.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/anon_inodes.h>
#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/kref.h>
#include <linux/eventfd.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>


struct eventfd_ctx {
	
struct kref kref;
	
wait_queue_head_t wqh;
	/*
         * Every time that a write(2) is performed on an eventfd, the
         * value of the __u64 being written is added to "count" and a
         * wakeup is performed on "wqh". A read(2) will return the "count"
         * value to userspace, and will reset "count" to zero. The kernel
         * side eventfd_signal() also, adds to the "count" counter and
         * issue a wakeup.
         */
	
__u64 count;
	
unsigned int flags;
};

/**
 * eventfd_signal - Adds @n to the eventfd counter.
 * @ctx: [in] Pointer to the eventfd context.
 * @n: [in] Value of the counter to be added to the eventfd internal counter.
 *          The value cannot be negative.
 *
 * This function is supposed to be called by the kernel in paths that do not
 * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
 * value, and we signal this as overflow condition by returning a EPOLLERR
 * to poll(2).
 *
 * Returns the amount by which the counter was incremented.  This will be less
 * than @n if the counter has overflowed.
 */

__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) { unsigned long flags; spin_lock_irqsave(&ctx->wqh.lock, flags); if (ULLONG_MAX - ctx->count < n) n = ULLONG_MAX - ctx->count; ctx->count += n; if (waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLIN); spin_unlock_irqrestore(&ctx->wqh.lock, flags); return n; }

Contributors

PersonTokensPropCommitsCommitProp
Davide Libenzi8596.59%466.67%
Sha Zhengju22.27%116.67%
Linus Torvalds11.14%116.67%
Total88100.00%6100.00%

EXPORT_SYMBOL_GPL(eventfd_signal);
static void eventfd_free_ctx(struct eventfd_ctx *ctx) { kfree(ctx); }

Contributors

PersonTokensPropCommitsCommitProp
Davide Libenzi16100.00%1100.00%
Total16100.00%1100.00%


static void eventfd_free(struct kref *kref) { struct eventfd_ctx *ctx = container_of(kref, struct eventfd_ctx, kref); eventfd_free_ctx(ctx); }

Contributors

PersonTokensPropCommitsCommitProp
Davide Libenzi31100.00%2100.00%
Total31100.00%2100.00%

/** * eventfd_ctx_put - Releases a reference to the internal eventfd context. * @ctx: [in] Pointer to eventfd context. * * The eventfd context reference must have been previously acquired either * with eventfd_ctx_fdget() or eventfd_ctx_fileget(). */
void eventfd_ctx_put(struct eventfd_ctx *ctx) { kref_put(&ctx->kref, eventfd_free); }

Contributors

PersonTokensPropCommitsCommitProp
Davide Libenzi20100.00%1100.00%
Total20100.00%1100.00%

EXPORT_SYMBOL_GPL(eventfd_ctx_put);
static int eventfd_release(struct inode *inode, struct file *file) { struct eventfd_ctx *ctx = file->private_data; wake_up_poll(&ctx->wqh, EPOLLHUP); eventfd_ctx_put(ctx); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Davide Libenzi4297.67%266.67%
Linus Torvalds12.33%133.33%
Total43100.00%3100.00%


static __poll_t eventfd_poll(struct file *file, poll_table *wait) { struct eventfd_ctx *ctx = file->private_data; __poll_t events = 0; u64 count; poll_wait(file, &ctx->wqh, wait); /* * All writes to ctx->count occur within ctx->wqh.lock. This read * can be done outside ctx->wqh.lock because we know that poll_wait * takes that lock (through add_wait_queue) if our caller will sleep. * * The read _can_ therefore seep into add_wait_queue's critical * section, but cannot move above it! add_wait_queue's spin_lock acts * as an acquire barrier and ensures that the read be ordered properly * against the writes. The following CAN happen and is safe: * * poll write * ----------------- ------------ * lock ctx->wqh.lock (in poll_wait) * count = ctx->count * __add_wait_queue * unlock ctx->wqh.lock * lock ctx->qwh.lock * ctx->count += n * if (waitqueue_active) * wake_up_locked_poll * unlock ctx->qwh.lock * eventfd_poll returns 0 * * but the following, which would miss a wakeup, cannot happen: * * poll write * ----------------- ------------ * count = ctx->count (INVALID!) * lock ctx->qwh.lock * ctx->count += n * **waitqueue_active is false** * **no wake_up_locked_poll!** * unlock ctx->qwh.lock * lock ctx->wqh.lock (in poll_wait) * __add_wait_queue * unlock ctx->wqh.lock * eventfd_poll returns 0 */ count = READ_ONCE(ctx->count); if (count > 0) events |= EPOLLIN; if (count == ULLONG_MAX) events |= EPOLLERR; if (ULLONG_MAX - 1 > count) events |= EPOLLOUT; return events; }

Contributors

PersonTokensPropCommitsCommitProp
Davide Libenzi7584.27%120.00%
Chris Mason55.62%120.00%
Paolo Bonzini44.49%120.00%
Linus Torvalds33.37%120.00%
Al Viro22.25%120.00%
Total89100.00%5100.00%


static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) { *cnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count; ctx->count -= *cnt; }

Contributors

PersonTokensPropCommitsCommitProp
Davide Libenzi39100.00%2100.00%
Total39100.00%2100.00%

/** * eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue. * @ctx: [in] Pointer to eventfd context. * @wait: [in] Wait queue to be removed. * @cnt: [out] Pointer to the 64-bit counter value. * * Returns %0 if successful, or the following error codes: * * -EAGAIN : The operation would have blocked. * * This is used to atomically remove a wait queue entry from the eventfd wait * queue head, and read/reset the counter value. */
int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt) { unsigned long flags; spin_lock_irqsave(&ctx->wqh.lock, flags); eventfd_ctx_do_read(ctx, cnt); __remove_wait_queue(&ctx->wqh, wait); if (*cnt != 0 && waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLOUT); spin_unlock_irqrestore(&ctx->wqh.lock, flags); return *cnt != 0 ? 0 : -EAGAIN; }

Contributors

PersonTokensPropCommitsCommitProp
Davide Libenzi9797.98%250.00%
Ingo Molnar11.01%125.00%
Linus Torvalds11.01%125.00%
Total99100.00%4100.00%

EXPORT_SYMBOL_GPL(eventfd_ctx_remove_wait_queue);
static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct eventfd_ctx *ctx = file->private_data; ssize_t res; __u64 ucnt = 0; DECLARE_WAITQUEUE(wait, current); if (count < sizeof(ucnt)) return -EINVAL; spin_lock_irq(&ctx->wqh.lock); res = -EAGAIN; if (ctx->count > 0) res = sizeof(ucnt); else if (!(file->f_flags & O_NONBLOCK)) { __add_wait_queue(&ctx->wqh, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (ctx->count > 0) { res = sizeof(ucnt); break; } if (signal_pending(current)) { res = -ERESTARTSYS; break; } spin_unlock_irq(&ctx->wqh.lock); schedule(); spin_lock_irq(&ctx->wqh.lock); } __remove_wait_queue(&ctx->wqh, &wait); __set_current_state(TASK_RUNNING); } if (likely(res > 0)) { eventfd_ctx_do_read(ctx, &ucnt); if (waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLOUT); } spin_unlock_irq(&ctx->wqh.lock); if (res > 0 && put_user(ucnt, (__u64 __user *)buf)) return -EFAULT; return res; }

Contributors

PersonTokensPropCommitsCommitProp
Davide Libenzi20675.46%571.43%
Eric Biggers6624.18%114.29%
Linus Torvalds10.37%114.29%
Total273100.00%7100.00%


static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct eventfd_ctx *ctx = file->private_data; ssize_t res; __u64 ucnt; DECLARE_WAITQUEUE(wait, current); if (count < sizeof(ucnt)) return -EINVAL; if (copy_from_user(&ucnt, buf, sizeof(ucnt))) return -EFAULT; if (ucnt == ULLONG_MAX) return -EINVAL; spin_lock_irq(&ctx->wqh.lock); res = -EAGAIN; if (ULLONG_MAX - ctx->count > ucnt) res = sizeof(ucnt); else if (!(file->f_flags & O_NONBLOCK)) { __add_wait_queue(&ctx->wqh, &wait); for (res = 0;;) { set_current_state(TASK_INTERRUPTIBLE); if (ULLONG_MAX - ctx->count > ucnt) { res = sizeof(ucnt); break; } if (signal_pending(current)) { res = -ERESTARTSYS; break; } spin_unlock_irq(&ctx->wqh.lock); schedule(); spin_lock_irq(&ctx->wqh.lock); } __remove_wait_queue(&ctx->wqh, &wait); __set_current_state(TASK_RUNNING); } if (likely(res > 0)) { ctx->count += ucnt; if (waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLIN); } spin_unlock_irq(&ctx->wqh.lock); return res; }

Contributors

PersonTokensPropCommitsCommitProp
Davide Libenzi28399.65%480.00%
Linus Torvalds10.35%120.00%
Total284100.00%5100.00%

#ifdef CONFIG_PROC_FS
static void eventfd_show_fdinfo(struct seq_file *m, struct file *f) { struct eventfd_ctx *ctx = f->private_data; spin_lock_irq(&ctx->wqh.lock); seq_printf(m, "eventfd-count: %16llx\n", (unsigned long long)ctx->count); spin_unlock_irq(&ctx->wqh.lock); }

Contributors

PersonTokensPropCommitsCommitProp
Cyrill V. Gorcunov6098.36%150.00%
Joe Perches11.64%150.00%
Total61100.00%2100.00%

#endif static const struct file_operations eventfd_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = eventfd_show_fdinfo, #endif .release = eventfd_release, .poll = eventfd_poll, .read = eventfd_read, .write = eventfd_write, .llseek = noop_llseek, }; /** * eventfd_fget - Acquire a reference of an eventfd file descriptor. * @fd: [in] Eventfd file descriptor. * * Returns a pointer to the eventfd file structure in case of success, or the * following error pointer: * * -EBADF : Invalid @fd file descriptor. * -EINVAL : The @fd file descriptor is not an eventfd file. */
struct file *eventfd_fget(int fd) { struct file *file; file = fget(fd); if (!file) return ERR_PTR(-EBADF); if (file->f_op != &eventfd_fops) { fput(file); return ERR_PTR(-EINVAL); } return file; }

Contributors

PersonTokensPropCommitsCommitProp
Davide Libenzi60100.00%1100.00%
Total60100.00%1100.00%

EXPORT_SYMBOL_GPL(eventfd_fget); /** * eventfd_ctx_fdget - Acquires a reference to the internal eventfd context. * @fd: [in] Eventfd file descriptor. * * Returns a pointer to the internal eventfd context, otherwise the error * pointers returned by the following functions: * * eventfd_fget */
struct eventfd_ctx *eventfd_ctx_fdget(int fd) { struct eventfd_ctx *ctx; struct fd f = fdget(fd); if (!f.file) return ERR_PTR(-EBADF); ctx = eventfd_ctx_fileget(f.file); fdput(f); return ctx; }

Contributors

PersonTokensPropCommitsCommitProp
Davide Libenzi3665.45%150.00%
Al Viro1934.55%150.00%
Total55100.00%2100.00%

EXPORT_SYMBOL_GPL(eventfd_ctx_fdget); /** * eventfd_ctx_fileget - Acquires a reference to the internal eventfd context. * @file: [in] Eventfd file pointer. * * Returns a pointer to the internal eventfd context, otherwise the error * pointer: * * -EINVAL : The @fd file descriptor is not an eventfd file. */
struct eventfd_ctx *eventfd_ctx_fileget(struct file *file) { struct eventfd_ctx *ctx; if (file->f_op != &eventfd_fops) return ERR_PTR(-EINVAL); ctx = file->private_data; kref_get(&ctx->kref); return ctx; }

Contributors

PersonTokensPropCommitsCommitProp
Davide Libenzi3366.00%150.00%
Eric Biggers1734.00%150.00%
Total50100.00%2100.00%

EXPORT_SYMBOL_GPL(eventfd_ctx_fileget);
static int do_eventfd(unsigned int count, int flags) { struct eventfd_ctx *ctx; int fd; /* Check the EFD_* constants for consistency. */ BUILD_BUG_ON(EFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(EFD_NONBLOCK != O_NONBLOCK); if (flags & ~EFD_FLAGS_SET) return -EINVAL; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; kref_init(&ctx->kref); init_waitqueue_head(&ctx->wqh); ctx->count = count; ctx->flags = flags; fd = anon_inode_getfd("[eventfd]", &eventfd_fops, ctx, O_RDWR | (flags & EFD_SHARED_FCNTL_FLAGS)); if (fd < 0) eventfd_free_ctx(ctx); return fd; }

Contributors

PersonTokensPropCommitsCommitProp
Davide Libenzi7758.78%436.36%
Ulrich Drepper2821.37%327.27%
Dominik Brodowski118.40%19.09%
Eric Biggers75.34%19.09%
Al Viro43.05%19.09%
Roland Dreier43.05%19.09%
Total131100.00%11100.00%

SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags) { return do_eventfd(count, flags); } SYSCALL_DEFINE1(eventfd, unsigned int, count) { return do_eventfd(count, 0); }

Overall Contributors

PersonTokensPropCommitsCommitProp
Davide Libenzi120578.66%721.21%
Eric Biggers915.94%39.09%
Cyrill V. Gorcunov815.29%13.03%
Ulrich Drepper372.42%39.09%
Dominik Brodowski342.22%13.03%
Al Viro251.63%39.09%
Rusty Russell120.78%13.03%
Linus Torvalds90.59%13.03%
Heiko Carstens80.52%13.03%
Chris Mason50.33%13.03%
Arnd Bergmann50.33%13.03%
Paolo Bonzini40.26%13.03%
Roland Dreier40.26%13.03%
Tejun Heo30.20%13.03%
Sha Zhengju20.13%13.03%
Ingo Molnar20.13%26.06%
Adrian Bunk20.13%13.03%
Randy Dunlap10.07%13.03%
Joe Perches10.07%13.03%
Paul Gortmaker10.07%13.03%
Total1532100.00%33100.00%
Directory: fs
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with cregit.