irqfd fixes and enhancements

index a9e7de7..9656027 100644
@@ -28,7 +28,6 @@
 #include <linux/file.h>
 #include <linux/list.h>
 #include <linux/eventfd.h>
-#include <linux/srcu.h>
 
 /*
  * --------------------------------------------------------------------

@@ -38,8 +37,6 @@
  * --------------------------------------------------------------------
  */
 struct _irqfd {
-	struct mutex              lock;
-	struct srcu_struct        srcu;
 	struct kvm               *kvm;
 	int                       gsi;
 	struct list_head          list;

@@ -53,48 +50,12 @@ static void
 irqfd_inject(struct work_struct *work)
 {
 	struct _irqfd *irqfd = container_of(work, struct _irqfd, inject);
-	struct kvm *kvm;
-	int idx;
+	struct kvm *kvm = irqfd->kvm;
 
-	idx = srcu_read_lock(&irqfd->srcu);
-
-	kvm = rcu_dereference(irqfd->kvm);
-	if (kvm) {
-		mutex_lock(&kvm->irq_lock);
-		kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1);
-		kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0);
-		mutex_unlock(&kvm->irq_lock);
-	}
-
-	srcu_read_unlock(&irqfd->srcu, idx);
-}
-
-static void
-irqfd_disconnect(struct _irqfd *irqfd)
-{
-	struct kvm *kvm;
-
-	mutex_lock(&irqfd->lock);
-
-	kvm = rcu_dereference(irqfd->kvm);
-	rcu_assign_pointer(irqfd->kvm, NULL);
-
-	mutex_unlock(&irqfd->lock);
-
-	if (!kvm)
-		return;
-
-	mutex_lock(&kvm->lock);
-	list_del(&irqfd->list);
-	mutex_unlock(&kvm->lock);
-
-	/*
-	 * It is important to not drop the kvm reference until the next grace
-	 * period because there might be lockless references in flight up
-	 * until then
-	 */
-	synchronize_srcu(&irqfd->srcu);
-	kvm_put_kvm(kvm);
+	mutex_lock(&kvm->irq_lock);
+	kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1);
+	kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0);
+	mutex_unlock(&kvm->irq_lock);
 }
 
 static int

@@ -103,26 +64,24 @@ irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key)
 	struct _irqfd *irqfd = container_of(wait, struct _irqfd, wait);
 	unsigned long flags = (unsigned long)key;
 
+	/*
+	 * Assume we will be called with interrupts disabled
+	 */
 	if (flags & POLLIN)
 		/*
-		 * The POLLIN wake_up is called with interrupts disabled.
-		 * Therefore we need to defer the IRQ injection until later
-		 * since we need to acquire the kvm->lock to do so.
+		 * Defer the IRQ injection until later since we need to
+		 * acquire the kvm->lock to do so.
 		 */
 		schedule_work(&irqfd->inject);
 
 	if (flags & POLLHUP) {
 		/*
-		 * The POLLHUP is called unlocked, so it theoretically should
-		 * be safe to remove ourselves from the wqh using the locked
-		 * variant of remove_wait_queue()
+		 * for now, just remove ourselves from the list and let
+		 * the rest dangle.  We will fix this up later once
+		 * the races in eventfd are fixed
 		 */
-		remove_wait_queue(irqfd->wqh, &irqfd->wait);
-		flush_work(&irqfd->inject);
-		irqfd_disconnect(irqfd);
-
-		cleanup_srcu_struct(&irqfd->srcu);
-		kfree(irqfd);
+		__remove_wait_queue(irqfd->wqh, &irqfd->wait);
+		irqfd->wqh = NULL;
 	}
 
 	return 0;

@@ -150,8 +109,6 @@ kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags)
 	if (!irqfd)
 		return -ENOMEM;
 
-	mutex_init(&irqfd->lock);
-	init_srcu_struct(&irqfd->srcu);
 	irqfd->kvm = kvm;
 	irqfd->gsi = gsi;
 	INIT_LIST_HEAD(&irqfd->list);

@@ -172,8 +129,6 @@ kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags)
 
 	events = file->f_op->poll(file, &irqfd->pt);
 
-	kvm_get_kvm(kvm);
-
 	mutex_lock(&kvm->lock);
 	list_add_tail(&irqfd->list, &kvm->irqfds);
 	mutex_unlock(&kvm->lock);

@@ -211,6 +166,16 @@ kvm_irqfd_release(struct kvm *kvm)
 {
 	struct _irqfd *irqfd, *tmp;
 
-	list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds, list)
-		irqfd_disconnect(irqfd);
+	list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds, list) {
+		if (irqfd->wqh)
+			remove_wait_queue(irqfd->wqh, &irqfd->wait);
+
+		flush_work(&irqfd->inject);
+
+		mutex_lock(&kvm->lock);
+		list_del(&irqfd->list);
+		mutex_unlock(&kvm->lock);
+
+		kfree(irqfd);
+	}
 }

index d4e8979..9c31382 100644
@@ -82,7 +82,7 @@ struct lg_cpu {
 
 struct lg_eventfd {
 	unsigned long addr;
-	struct file *event;
+	struct eventfd_ctx *event;
 };
 
 struct lg_eventfd_map {

index 32e2971..9f9a295 100644
@@ -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

index 76da125..d065b2c 100644
@@ -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;

178 lines not on this page · raw message

index b16a957..47f7d93 100644
@@ -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)

index f45a8ae..3b85ba6 100644
@@ -8,10 +8,8 @@
 #ifndef _LINUX_EVENTFD_H
 #define _LINUX_EVENTFD_H
 
-#ifdef CONFIG_EVENTFD
-
-/* For O_CLOEXEC and O_NONBLOCK */
 #include <linux/fcntl.h>
+#include <linux/file.h>
 
 /*
  * 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 */
 

index 2451f48..5a90c6a 100644
@@ -141,7 +141,10 @@ struct kvm {
 	struct kvm_io_bus mmio_bus;
 	struct kvm_io_bus pio_bus;
 #ifdef CONFIG_HAVE_KVM_EVENTFD
-	struct list_head irqfds;
+	struct {
+		spinlock_t        lock;
+		struct list_head  items;
+	} irqfds;
 #endif
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;

231 lines not on this page · raw message

index 38ff31e..6710518 100644
@@ -490,6 +490,8 @@ struct kvm_x86_mce {
 };
 #endif
 
+#define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
+
 struct kvm_irqfd {
 	__u32 fd;
 	__u32 gsi;

58 lines not on this page · raw message

index 5a90c6a..d94ee72 100644
@@ -144,6 +144,8 @@ struct kvm {
 	struct {
 		spinlock_t        lock;
 		struct list_head  items;
+		atomic_t          outstanding;
+		wait_queue_head_t wqh;
 	} irqfds;
 #endif
 	struct kvm_vm_stat stat;

167 lines not on this page · raw message