diff --git a/drivers/lguest/lg.h b/drivers/lguest/lg.h index d4e8979735cb002f9f97cf929a1b45a900f2ddc6..9c3138265f8e4fa62892321c97cd62d88c52584c 100644 --- a/drivers/lguest/lg.h +++ b/drivers/lguest/lg.h @@ -82,7 +82,7 @@ struct lg_cpu { struct lg_eventfd { unsigned long addr; - struct file *event; + struct eventfd_ctx *event; }; struct lg_eventfd_map { diff --git a/drivers/lguest/lguest_user.c b/drivers/lguest/lguest_user.c index 32e297121058a3d7dc52fbd6d347eab496c08252..9f9a2953b3830dd42b9f1eb1f06649ed9870e5e3 100644 --- a/drivers/lguest/lguest_user.c +++ b/drivers/lguest/lguest_user.c @@ -50,7 +50,7 @@ static int add_eventfd(struct lguest *lg, unsigned long addr, int fd) /* Now append new entry. */ new->map[new->num].addr = addr; - new->map[new->num].event = eventfd_fget(fd); + new->map[new->num].event = eventfd_ctx_fdget(fd); if (IS_ERR(new->map[new->num].event)) { kfree(new); return PTR_ERR(new->map[new->num].event); @@ -357,7 +357,7 @@ static int close(struct inode *inode, struct file *file) /* Release any eventfds they registered. */ for (i = 0; i < lg->eventfds->num; i++) - fput(lg->eventfds->map[i].event); + eventfd_ctx_put(lg->eventfds->map[i].event); kfree(lg->eventfds); /* If lg->dead doesn't contain an error code it will be NULL or a diff --git a/fs/aio.c b/fs/aio.c index 76da12537956cf0635c5615303f8cbb0fb8337a7..d065b2c3273ea03615ae883558100b4962a2ddbb 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -485,6 +485,8 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req) { assert_spin_locked(&ctx->ctx_lock); + if (req->ki_eventfd != NULL) + eventfd_ctx_put(req->ki_eventfd); if (req->ki_dtor) req->ki_dtor(req); if (req->ki_iovec != &req->ki_inline_vec) @@ -509,8 +511,6 @@ static void aio_fput_routine(struct work_struct *data) /* Complete the fput(s) */ if (req->ki_filp != NULL) __fput(req->ki_filp); - if (req->ki_eventfd != NULL) - __fput(req->ki_eventfd); /* Link the iocb into the context's free list */ spin_lock_irq(&ctx->ctx_lock); @@ -528,8 +528,6 @@ static void aio_fput_routine(struct work_struct *data) */ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req) { - int schedule_putreq = 0; - dprintk(KERN_DEBUG "aio_put(%p): f_count=%ld\n", req, atomic_long_read(&req->ki_filp->f_count)); @@ -549,24 +547,16 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req) * we would not be holding the last reference to the file*, so * this function will be executed w/out any aio kthread wakeup. */ - if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count))) - schedule_putreq++; - else - req->ki_filp = NULL; - if (req->ki_eventfd != NULL) { - if (unlikely(atomic_long_dec_and_test(&req->ki_eventfd->f_count))) - schedule_putreq++; - else - req->ki_eventfd = NULL; - } - if (unlikely(schedule_putreq)) { + if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count))) { get_ioctx(ctx); spin_lock(&fput_lock); list_add(&req->ki_list, &fput_head); spin_unlock(&fput_lock); queue_work(aio_wq, &fput_work); - } else + } else { + req->ki_filp = NULL; really_put_req(ctx, req); + } return 1; } @@ -1622,7 +1612,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, * an eventfd() fd, and will be signaled for each completed * event using the eventfd_signal() function. */ - req->ki_eventfd = eventfd_fget((int) iocb->aio_resfd); + req->ki_eventfd = eventfd_ctx_fdget((int) iocb->aio_resfd); if (IS_ERR(req->ki_eventfd)) { ret = PTR_ERR(req->ki_eventfd); req->ki_eventfd = NULL; diff --git a/fs/eventfd.c b/fs/eventfd.c index 3f0e1974abdcfbfb8cd8afff3a19346667768672..31d12de83a2a9584245e8c983e6c5f0e1a74ea29 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -14,35 +14,44 @@ #include #include #include -#include #include #include +#include +#include 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 - * size eventfd_signal() also, adds to the "count" counter and + * side eventfd_signal() also, adds to the "count" counter and * issue a wakeup. */ __u64 count; unsigned int flags; }; -/* - * Adds "n" to the eventfd counter "count". Returns "n" in case of - * success, or a value lower then "n" in case of coutner overflow. - * 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 returining a POLLERR to poll(2). +/** + * 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 returining a POLLERR + * to poll(2). + * + * Returns @n in case of success, a non-negative number lower than @n in case + * of overflow, or the following error codes: + * + * -EINVAL : The value of @n is negative. */ -int eventfd_signal(struct file *file, int n) +int eventfd_signal(struct eventfd_ctx *ctx, int n) { - struct eventfd_ctx *ctx = file->private_data; unsigned long flags; if (n < 0) @@ -59,9 +68,45 @@ int eventfd_signal(struct file *file, int n) } EXPORT_SYMBOL_GPL(eventfd_signal); +static void eventfd_free(struct kref *kref) +{ + struct eventfd_ctx *ctx = container_of(kref, struct eventfd_ctx, kref); + + kfree(ctx); +} + +/** + * eventfd_ctx_get - Acquires a reference to the internal eventfd context. + * @ctx: [in] Pointer to the eventfd context. + * + * Returns: In case of success, returns a pointer to the eventfd context. + */ +struct eventfd_ctx *eventfd_ctx_get(struct eventfd_ctx *ctx) +{ + kref_get(&ctx->kref); + return ctx; +} +EXPORT_SYMBOL_GPL(eventfd_ctx_get); + +/** + * 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_get() or eventfd_ctx_fdget()). + */ +void eventfd_ctx_put(struct eventfd_ctx *ctx) +{ + kref_put(&ctx->kref, eventfd_free); +} +EXPORT_SYMBOL_GPL(eventfd_ctx_put); + static int eventfd_release(struct inode *inode, struct file *file) { - kfree(file->private_data); + struct eventfd_ctx *ctx = file->private_data; + + wake_up_poll(&ctx->wqh, POLLHUP); + eventfd_ctx_put(ctx); return 0; } @@ -185,6 +230,16 @@ static const struct file_operations eventfd_fops = { .write = eventfd_write, }; +/** + * 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; @@ -201,6 +256,48 @@ struct file *eventfd_fget(int fd) } 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 file *file; + struct eventfd_ctx *ctx; + + file = eventfd_fget(fd); + if (IS_ERR(file)) + return (struct eventfd_ctx *) file; + ctx = eventfd_ctx_get(file->private_data); + fput(file); + + return ctx; +} +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) +{ + if (file->f_op != &eventfd_fops) + return ERR_PTR(-EINVAL); + + return eventfd_ctx_get(file->private_data); +} +EXPORT_SYMBOL_GPL(eventfd_ctx_fileget); + SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags) { int fd; @@ -217,6 +314,7 @@ SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags) if (!ctx) return -ENOMEM; + kref_init(&ctx->kref); init_waitqueue_head(&ctx->wqh); ctx->count = count; ctx->flags = flags; diff --git a/include/linux/aio.h b/include/linux/aio.h index b16a957030f87e16341efe5b41b476a04e742fc2..47f7d932a01d5d7694835b184429112f681f139b 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -121,9 +121,9 @@ struct kiocb { /* * If the aio_resfd field of the userspace iocb is not zero, - * this is the underlying file* to deliver event to. + * this is the underlying eventfd context to deliver events to. */ - struct file *ki_eventfd; + struct eventfd_ctx *ki_eventfd; }; #define is_sync_kiocb(iocb) ((iocb)->ki_key == KIOCB_SYNC_KEY) diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index f45a8ae5f8281bc51348b942a36899b8355f13d9..3b85ba6479f48e31f3173de8c2ff86959a190bb3 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -8,10 +8,8 @@ #ifndef _LINUX_EVENTFD_H #define _LINUX_EVENTFD_H -#ifdef CONFIG_EVENTFD - -/* For O_CLOEXEC and O_NONBLOCK */ #include +#include /* * CAREFUL: Check include/asm-generic/fcntl.h when defining @@ -27,16 +25,37 @@ #define EFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define EFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS | EFD_SEMAPHORE) +#ifdef CONFIG_EVENTFD + +struct eventfd_ctx *eventfd_ctx_get(struct eventfd_ctx *ctx); +void eventfd_ctx_put(struct eventfd_ctx *ctx); struct file *eventfd_fget(int fd); -int eventfd_signal(struct file *file, int n); +struct eventfd_ctx *eventfd_ctx_fdget(int fd); +struct eventfd_ctx *eventfd_ctx_fileget(struct file *file); +int eventfd_signal(struct eventfd_ctx *ctx, int n); #else /* CONFIG_EVENTFD */ -#define eventfd_fget(fd) ERR_PTR(-ENOSYS) -static inline int eventfd_signal(struct file *file, int n) -{ return 0; } +/* + * Ugly ugly ugly error layer to support modules that uses eventfd but + * pretend to work in !CONFIG_EVENTFD configurations. Namely, AIO. + */ +static inline struct eventfd_ctx *eventfd_ctx_fdget(int fd) +{ + return ERR_PTR(-ENOSYS); +} + +static inline int eventfd_signal(struct eventfd_ctx *ctx, int n) +{ + return -ENOSYS; +} + +static inline void eventfd_ctx_put(struct eventfd_ctx *ctx) +{ + +} -#endif /* CONFIG_EVENTFD */ +#endif #endif /* _LINUX_EVENTFD_H */