1 files changed, 161 insertions, 193 deletions

diff --git a/fs/eventfd.c b/fs/eventfd.c
index 35470d9b96e6..3219e0d596fe 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  fs/eventfd.c
  *
@@ -9,7 +10,7 @@
 #include <linux/poll.h>
 #include <linux/init.h>
 #include <linux/fs.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/list.h>
@@ -21,6 +22,10 @@
 #include <linux/eventfd.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/idr.h>
+#include <linux/uio.h>
+
+static DEFINE_IDA(eventfd_ida);
 
 struct eventfd_ctx {
 	struct kref kref;
@@ -28,47 +33,56 @@ struct eventfd_ctx {
 	/*
 	 * 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.
+	 * wakeup is performed on "wqh". If EFD_SEMAPHORE flag was not
+	 * specified, 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;
+	int id;
 };
 
 /**
- * eventfd_signal - Adds @n to the eventfd counter.
+ * eventfd_signal_mask - Increment the event 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.
+ * @mask: [in] poll mask
  *
  * 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
+ * value, and we signal this as overflow condition by returning a EPOLLERR
  * to poll(2).
- *
- * Returns the amount by which the counter was incrememnted.  This will be less
- * than @n if the counter has overflowed.
  */
-__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
+void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask)
 {
 	unsigned long flags;
 
+	/*
+	 * Deadlock or stack overflow issues can happen if we recurse here
+	 * through waitqueue wakeup handlers. If the caller users potentially
+	 * nested waitqueues with custom wakeup handlers, then it should
+	 * check eventfd_signal_allowed() before calling this function. If
+	 * it returns false, the eventfd_signal() call should be deferred to a
+	 * safe context.
+	 */
+	if (WARN_ON_ONCE(current->in_eventfd))
+		return;
+
 	spin_lock_irqsave(&ctx->wqh.lock, flags);
-	if (ULLONG_MAX - ctx->count < n)
-		n = ULLONG_MAX - ctx->count;
-	ctx->count += n;
+	current->in_eventfd = 1;
+	if (ctx->count < ULLONG_MAX)
+		ctx->count++;
 	if (waitqueue_active(&ctx->wqh))
-		wake_up_locked_poll(&ctx->wqh, POLLIN);
+		wake_up_locked_poll(&ctx->wqh, EPOLLIN | mask);
+	current->in_eventfd = 0;
 	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
-
-	return n;
 }
-EXPORT_SYMBOL_GPL(eventfd_signal);
+EXPORT_SYMBOL_GPL(eventfd_signal_mask);
 
 static void eventfd_free_ctx(struct eventfd_ctx *ctx)
 {
+	if (ctx->id >= 0)
+		ida_free(&eventfd_ida, ctx->id);
 	kfree(ctx);
 }
 
@@ -80,24 +94,11 @@ static void eventfd_free(struct kref *kref)
 }
 
 /**
- * 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().
+ * with eventfd_ctx_fdget() or eventfd_ctx_fileget().
  */
 void eventfd_ctx_put(struct eventfd_ctx *ctx)
 {
@@ -109,36 +110,77 @@ static int eventfd_release(struct inode *inode, struct file *file)
 {
 	struct eventfd_ctx *ctx = file->private_data;
 
-	wake_up_poll(&ctx->wqh, POLLHUP);
+	wake_up_poll(&ctx->wqh, EPOLLHUP);
 	eventfd_ctx_put(ctx);
 	return 0;
 }
 
-static unsigned int eventfd_poll(struct file *file, poll_table *wait)
+static __poll_t eventfd_poll(struct file *file, poll_table *wait)
 {
 	struct eventfd_ctx *ctx = file->private_data;
-	unsigned int events = 0;
-	unsigned long flags;
+	__poll_t events = 0;
+	u64 count;
 
 	poll_wait(file, &ctx->wqh, wait);
 
-	spin_lock_irqsave(&ctx->wqh.lock, flags);
-	if (ctx->count > 0)
-		events |= POLLIN;
-	if (ctx->count == ULLONG_MAX)
-		events |= POLLERR;
-	if (ULLONG_MAX - 1 > ctx->count)
-		events |= POLLOUT;
-	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
+	/*
+	 * 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;
 }
 
-static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
+void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
 {
-	*cnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count;
+	lockdep_assert_held(&ctx->wqh.lock);
+
+	*cnt = ((ctx->flags & EFD_SEMAPHORE) && ctx->count) ? 1 : ctx->count;
 	ctx->count -= *cnt;
 }
+EXPORT_SYMBOL_GPL(eventfd_ctx_do_read);
 
 /**
  * eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue.
@@ -153,7 +195,7 @@ static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
  * 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_t *wait,
+int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt)
 {
 	unsigned long flags;
@@ -162,81 +204,44 @@ int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_t *wait,
 	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, POLLOUT);
+		wake_up_locked_poll(&ctx->wqh, EPOLLOUT);
 	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 
 	return *cnt != 0 ? 0 : -EAGAIN;
 }
 EXPORT_SYMBOL_GPL(eventfd_ctx_remove_wait_queue);
 
-/**
- * eventfd_ctx_read - Reads the eventfd counter or wait if it is zero.
- * @ctx: [in] Pointer to eventfd context.
- * @no_wait: [in] Different from zero if the operation should not block.
- * @cnt: [out] Pointer to the 64-bit counter value.
- *
- * Returns %0 if successful, or the following error codes:
- *
- * -EAGAIN      : The operation would have blocked but @no_wait was non-zero.
- * -ERESTARTSYS : A signal interrupted the wait operation.
- *
- * If @no_wait is zero, the function might sleep until the eventfd internal
- * counter becomes greater than zero.
- */
-ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, __u64 *cnt)
+static ssize_t eventfd_read(struct kiocb *iocb, struct iov_iter *to)
 {
-	ssize_t res;
-	DECLARE_WAITQUEUE(wait, current);
+	struct file *file = iocb->ki_filp;
+	struct eventfd_ctx *ctx = file->private_data;
+	__u64 ucnt = 0;
 
+	if (iov_iter_count(to) < sizeof(ucnt))
+		return -EINVAL;
 	spin_lock_irq(&ctx->wqh.lock);
-	*cnt = 0;
-	res = -EAGAIN;
-	if (ctx->count > 0)
-		res = 0;
-	else if (!no_wait) {
-		__add_wait_queue(&ctx->wqh, &wait);
-		for (;;) {
-			set_current_state(TASK_INTERRUPTIBLE);
-			if (ctx->count > 0) {
-				res = 0;
-				break;
-			}
-			if (signal_pending(current)) {
-				res = -ERESTARTSYS;
-				break;
-			}
+	if (!ctx->count) {
+		if ((file->f_flags & O_NONBLOCK) ||
+		    (iocb->ki_flags & IOCB_NOWAIT)) {
 			spin_unlock_irq(&ctx->wqh.lock);
-			schedule();
-			spin_lock_irq(&ctx->wqh.lock);
+			return -EAGAIN;
+		}
+
+		if (wait_event_interruptible_locked_irq(ctx->wqh, ctx->count)) {
+			spin_unlock_irq(&ctx->wqh.lock);
+			return -ERESTARTSYS;
 		}
-		__remove_wait_queue(&ctx->wqh, &wait);
-		__set_current_state(TASK_RUNNING);
-	}
-	if (likely(res == 0)) {
-		eventfd_ctx_do_read(ctx, cnt);
-		if (waitqueue_active(&ctx->wqh))
-			wake_up_locked_poll(&ctx->wqh, POLLOUT);
 	}
+	eventfd_ctx_do_read(ctx, &ucnt);
+	current->in_eventfd = 1;
+	if (waitqueue_active(&ctx->wqh))
+		wake_up_locked_poll(&ctx->wqh, EPOLLOUT);
+	current->in_eventfd = 0;
 	spin_unlock_irq(&ctx->wqh.lock);
+	if (unlikely(copy_to_iter(&ucnt, sizeof(ucnt), to) != sizeof(ucnt)))
+		return -EFAULT;
 
-	return res;
-}
-EXPORT_SYMBOL_GPL(eventfd_ctx_read);
-
-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 cnt;
-
-	if (count < sizeof(cnt))
-		return -EINVAL;
-	res = eventfd_ctx_read(ctx, file->f_flags & O_NONBLOCK, &cnt);
-	if (res < 0)
-		return res;
-
-	return put_user(cnt, (__u64 __user *) buf) ? -EFAULT : sizeof(cnt);
+	return sizeof(ucnt);
 }
 
 static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t count,
@@ -245,9 +250,8 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c
 	struct eventfd_ctx *ctx = file->private_data;
 	ssize_t res;
 	__u64 ucnt;
-	DECLARE_WAITQUEUE(wait, current);
 
-	if (count < sizeof(ucnt))
+	if (count != sizeof(ucnt))
 		return -EINVAL;
 	if (copy_from_user(&ucnt, buf, sizeof(ucnt)))
 		return -EFAULT;
@@ -258,28 +262,17 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c
 	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);
+		res = wait_event_interruptible_locked_irq(ctx->wqh,
+				ULLONG_MAX - ctx->count > ucnt);
+		if (!res)
+			res = sizeof(ucnt);
 	}
 	if (likely(res > 0)) {
 		ctx->count += ucnt;
+		current->in_eventfd = 1;
 		if (waitqueue_active(&ctx->wqh))
-			wake_up_locked_poll(&ctx->wqh, POLLIN);
+			wake_up_locked_poll(&ctx->wqh, EPOLLIN);
+		current->in_eventfd = 0;
 	}
 	spin_unlock_irq(&ctx->wqh.lock);
 
@@ -287,17 +280,22 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c
 }
 
 #ifdef CONFIG_PROC_FS
-static int eventfd_show_fdinfo(struct seq_file *m, struct file *f)
+static void eventfd_show_fdinfo(struct seq_file *m, struct file *f)
 {
 	struct eventfd_ctx *ctx = f->private_data;
-	int ret;
+	__u64 cnt;
 
 	spin_lock_irq(&ctx->wqh.lock);
-	ret = seq_printf(m, "eventfd-count: %16llx\n",
-			 (unsigned long long)ctx->count);
+	cnt = ctx->count;
 	spin_unlock_irq(&ctx->wqh.lock);
 
-	return ret;
+	seq_printf(m,
+		   "eventfd-count: %16llx\n"
+		   "eventfd-id: %d\n"
+		   "eventfd-semaphore: %d\n",
+		   cnt,
+		   ctx->id,
+		   !!(ctx->flags & EFD_SEMAPHORE));
 }
 #endif
 
@@ -307,7 +305,7 @@ static const struct file_operations eventfd_fops = {
 #endif
 	.release	= eventfd_release,
 	.poll		= eventfd_poll,
-	.read		= eventfd_read,
+	.read_iter	= eventfd_read,
 	.write		= eventfd_write,
 	.llseek		= noop_llseek,
 };
@@ -349,16 +347,10 @@ EXPORT_SYMBOL_GPL(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;
+	CLASS(fd, f)(fd);
+	if (fd_empty(f))
+		return ERR_PTR(-EBADF);
+	return eventfd_ctx_fileget(fd_file(f));
 }
 EXPORT_SYMBOL_GPL(eventfd_ctx_fdget);
 
@@ -373,83 +365,59 @@ EXPORT_SYMBOL_GPL(eventfd_ctx_fdget);
  */
 struct eventfd_ctx *eventfd_ctx_fileget(struct file *file)
 {
+	struct eventfd_ctx *ctx;
+
 	if (file->f_op != &eventfd_fops)
 		return ERR_PTR(-EINVAL);
 
-	return eventfd_ctx_get(file->private_data);
+	ctx = file->private_data;
+	kref_get(&ctx->kref);
+	return ctx;
 }
 EXPORT_SYMBOL_GPL(eventfd_ctx_fileget);
 
-/**
- * eventfd_file_create - Creates an eventfd file pointer.
- * @count: Initial eventfd counter value.
- * @flags: Flags for the eventfd file.
- *
- * This function creates an eventfd file pointer, w/out installing it into
- * the fd table. This is useful when the eventfd file is used during the
- * initialization of data structures that require extra setup after the eventfd
- * creation. So the eventfd creation is split into the file pointer creation
- * phase, and the file descriptor installation phase.
- * In this way races with userspace closing the newly installed file descriptor
- * can be avoided.
- * Returns an eventfd file pointer, or a proper error pointer.
- */
-struct file *eventfd_file_create(unsigned int count, int flags)
+static int do_eventfd(unsigned int count, int flags)
 {
-	struct file *file;
-	struct eventfd_ctx *ctx;
+	struct eventfd_ctx *ctx __free(kfree) = NULL;
 
 	/* Check the EFD_* constants for consistency.  */
 	BUILD_BUG_ON(EFD_CLOEXEC != O_CLOEXEC);
 	BUILD_BUG_ON(EFD_NONBLOCK != O_NONBLOCK);
+	BUILD_BUG_ON(EFD_SEMAPHORE != (1 << 0));
 
 	if (flags & ~EFD_FLAGS_SET)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
 	kref_init(&ctx->kref);
 	init_waitqueue_head(&ctx->wqh);
 	ctx->count = count;
 	ctx->flags = flags;
 
-	file = anon_inode_getfile("[eventfd]", &eventfd_fops, ctx,
-				  O_RDWR | (flags & EFD_SHARED_FCNTL_FLAGS));
-	if (IS_ERR(file))
-		eventfd_free_ctx(ctx);
+	flags &= EFD_SHARED_FCNTL_FLAGS;
+	flags |= O_RDWR;
 
-	return file;
+	FD_PREPARE(fdf, flags,
+		   anon_inode_getfile_fmode("[eventfd]", &eventfd_fops, ctx,
+					    flags, FMODE_NOWAIT));
+	if (fdf.err)
+		return fdf.err;
+
+	ctx->id = ida_alloc(&eventfd_ida, GFP_KERNEL);
+	retain_and_null_ptr(ctx);
+	return fd_publish(fdf);
 }
 
 SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags)
 {
-	int fd, error;
-	struct file *file;
-
-	error = get_unused_fd_flags(flags & EFD_SHARED_FCNTL_FLAGS);
-	if (error < 0)
-		return error;
-	fd = error;
-
-	file = eventfd_file_create(count, flags);
-	if (IS_ERR(file)) {
-		error = PTR_ERR(file);
-		goto err_put_unused_fd;
-	}
-	fd_install(fd, file);
-
-	return fd;
-
-err_put_unused_fd:
-	put_unused_fd(fd);
-
-	return error;
+	return do_eventfd(count, flags);
 }
 
 SYSCALL_DEFINE1(eventfd, unsigned int, count)
 {
-	return sys_eventfd2(count, 0);
+	return do_eventfd(count, 0);
 }