vfio: move eventfd support code for VFIO_PCI to a separate file
The virqfd functionality that is used by VFIO_PCI to implement interrupt masking and unmasking via an eventfd, is generic enough and can be reused by another driver. Move it to a separate file in order to allow the code to be shared. Signed-off-by: Antonios Motakis <a.motakis@virtualopensystems.com> Signed-off-by: Baptiste Reynal <b.reynal@virtualopensystems.com> Reviewed-by: Eric Auger <eric.auger@linaro.org> Tested-by: Eric Auger <eric.auger@linaro.org> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
This commit is contained in:
Antonios Motakis
Alex Williamson
parent
09bbcb8810
commit
7e992d6927
|
|
@ -1,4 +1,5 @@
|
|||
|
||||
vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o
|
||||
vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o \
|
||||
../virqfd.o
|
||||
|
||||
obj-$(CONFIG_VFIO_PCI) += vfio-pci.o
|
||||
|
|
|
|||
|
|
@ -19,227 +19,12 @@
|
|||
#include <linux/msi.h>
|
||||
#include <linux/pci.h>
|
||||
#include <linux/file.h>
|
||||
#include <linux/poll.h>
|
||||
#include <linux/vfio.h>
|
||||
#include <linux/wait.h>
|
||||
#include <linux/workqueue.h>
|
||||
#include <linux/slab.h>
|
||||
|
||||
#include "vfio_pci_private.h"
|
||||
|
||||
/*
|
||||
* IRQfd - generic
|
||||
*/
|
||||
struct virqfd {
|
||||
void *opaque;
|
||||
struct eventfd_ctx *eventfd;
|
||||
int (*handler)(void *, void *);
|
||||
void (*thread)(void *, void *);
|
||||
void *data;
|
||||
struct work_struct inject;
|
||||
wait_queue_t wait;
|
||||
poll_table pt;
|
||||
struct work_struct shutdown;
|
||||
struct virqfd **pvirqfd;
|
||||
};
|
||||
|
||||
static struct workqueue_struct *vfio_irqfd_cleanup_wq;
|
||||
DEFINE_SPINLOCK(virqfd_lock);
|
||||
|
||||
int __init vfio_virqfd_init(void)
|
||||
{
|
||||
vfio_irqfd_cleanup_wq =
|
||||
create_singlethread_workqueue("vfio-irqfd-cleanup");
|
||||
if (!vfio_irqfd_cleanup_wq)
|
||||
return -ENOMEM;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
void vfio_virqfd_exit(void)
|
||||
{
|
||||
destroy_workqueue(vfio_irqfd_cleanup_wq);
|
||||
}
|
||||
|
||||
static void virqfd_deactivate(struct virqfd *virqfd)
|
||||
{
|
||||
queue_work(vfio_irqfd_cleanup_wq, &virqfd->shutdown);
|
||||
}
|
||||
|
||||
static int virqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key)
|
||||
{
|
||||
struct virqfd *virqfd = container_of(wait, struct virqfd, wait);
|
||||
unsigned long flags = (unsigned long)key;
|
||||
|
||||
if (flags & POLLIN) {
|
||||
/* An event has been signaled, call function */
|
||||
if ((!virqfd->handler ||
|
||||
virqfd->handler(virqfd->opaque, virqfd->data)) &&
|
||||
virqfd->thread)
|
||||
schedule_work(&virqfd->inject);
|
||||
}
|
||||
|
||||
if (flags & POLLHUP) {
|
||||
unsigned long flags;
|
||||
spin_lock_irqsave(&virqfd_lock, flags);
|
||||
|
||||
/*
|
||||
* The eventfd is closing, if the virqfd has not yet been
|
||||
* queued for release, as determined by testing whether the
|
||||
* virqfd pointer to it is still valid, queue it now. As
|
||||
* with kvm irqfds, we know we won't race against the virqfd
|
||||
* going away because we hold the lock to get here.
|
||||
*/
|
||||
if (*(virqfd->pvirqfd) == virqfd) {
|
||||
*(virqfd->pvirqfd) = NULL;
|
||||
virqfd_deactivate(virqfd);
|
||||
}
|
||||
|
||||
spin_unlock_irqrestore(&virqfd_lock, flags);
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static void virqfd_ptable_queue_proc(struct file *file,
|
||||
wait_queue_head_t *wqh, poll_table *pt)
|
||||
{
|
||||
struct virqfd *virqfd = container_of(pt, struct virqfd, pt);
|
||||
add_wait_queue(wqh, &virqfd->wait);
|
||||
}
|
||||
|
||||
static void virqfd_shutdown(struct work_struct *work)
|
||||
{
|
||||
struct virqfd *virqfd = container_of(work, struct virqfd, shutdown);
|
||||
u64 cnt;
|
||||
|
||||
eventfd_ctx_remove_wait_queue(virqfd->eventfd, &virqfd->wait, &cnt);
|
||||
flush_work(&virqfd->inject);
|
||||
eventfd_ctx_put(virqfd->eventfd);
|
||||
|
||||
kfree(virqfd);
|
||||
}
|
||||
|
||||
static void virqfd_inject(struct work_struct *work)
|
||||
{
|
||||
struct virqfd *virqfd = container_of(work, struct virqfd, inject);
|
||||
if (virqfd->thread)
|
||||
virqfd->thread(virqfd->opaque, virqfd->data);
|
||||
}
|
||||
|
||||
int vfio_virqfd_enable(void *opaque,
|
||||
int (*handler)(void *, void *),
|
||||
void (*thread)(void *, void *),
|
||||
void *data, struct virqfd **pvirqfd, int fd)
|
||||
{
|
||||
struct fd irqfd;
|
||||
struct eventfd_ctx *ctx;
|
||||
struct virqfd *virqfd;
|
||||
int ret = 0;
|
||||
unsigned int events;
|
||||
|
||||
virqfd = kzalloc(sizeof(*virqfd), GFP_KERNEL);
|
||||
if (!virqfd)
|
||||
return -ENOMEM;
|
||||
|
||||
virqfd->pvirqfd = pvirqfd;
|
||||
virqfd->opaque = opaque;
|
||||
virqfd->handler = handler;
|
||||
virqfd->thread = thread;
|
||||
virqfd->data = data;
|
||||
|
||||
INIT_WORK(&virqfd->shutdown, virqfd_shutdown);
|
||||
INIT_WORK(&virqfd->inject, virqfd_inject);
|
||||
|
||||
irqfd = fdget(fd);
|
||||
if (!irqfd.file) {
|
||||
ret = -EBADF;
|
||||
goto err_fd;
|
||||
}
|
||||
|
||||
ctx = eventfd_ctx_fileget(irqfd.file);
|
||||
if (IS_ERR(ctx)) {
|
||||
ret = PTR_ERR(ctx);
|
||||
goto err_ctx;
|
||||
}
|
||||
|
||||
virqfd->eventfd = ctx;
|
||||
|
||||
/*
|
||||
* virqfds can be released by closing the eventfd or directly
|
||||
* through ioctl. These are both done through a workqueue, so
|
||||
* we update the pointer to the virqfd under lock to avoid
|
||||
* pushing multiple jobs to release the same virqfd.
|
||||
*/
|
||||
spin_lock_irq(&virqfd_lock);
|
||||
|
||||
if (*pvirqfd) {
|
||||
spin_unlock_irq(&virqfd_lock);
|
||||
ret = -EBUSY;
|
||||
goto err_busy;
|
||||
}
|
||||
*pvirqfd = virqfd;
|
||||
|
||||
spin_unlock_irq(&virqfd_lock);
|
||||
|
||||
/*
|
||||
* Install our own custom wake-up handling so we are notified via
|
||||
* a callback whenever someone signals the underlying eventfd.
|
||||
*/
|
||||
init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup);
|
||||
init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc);
|
||||
|
||||
events = irqfd.file->f_op->poll(irqfd.file, &virqfd->pt);
|
||||
|
||||
/*
|
||||
* Check if there was an event already pending on the eventfd
|
||||
* before we registered and trigger it as if we didn't miss it.
|
||||
*/
|
||||
if (events & POLLIN) {
|
||||
if ((!handler || handler(opaque, data)) && thread)
|
||||
schedule_work(&virqfd->inject);
|
||||
}
|
||||
|
||||
/*
|
||||
* Do not drop the file until the irqfd is fully initialized,
|
||||
* otherwise we might race against the POLLHUP.
|
||||
*/
|
||||
fdput(irqfd);
|
||||
|
||||
return 0;
|
||||
err_busy:
|
||||
eventfd_ctx_put(ctx);
|
||||
err_ctx:
|
||||
fdput(irqfd);
|
||||
err_fd:
|
||||
kfree(virqfd);
|
||||
|
||||
return ret;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(vfio_virqfd_enable);
|
||||
|
||||
void vfio_virqfd_disable(struct virqfd **pvirqfd)
|
||||
{
|
||||
unsigned long flags;
|
||||
|
||||
spin_lock_irqsave(&virqfd_lock, flags);
|
||||
|
||||
if (*pvirqfd) {
|
||||
virqfd_deactivate(*pvirqfd);
|
||||
*pvirqfd = NULL;
|
||||
}
|
||||
|
||||
spin_unlock_irqrestore(&virqfd_lock, flags);
|
||||
|
||||
/*
|
||||
* Block until we know all outstanding shutdown jobs have completed.
|
||||
* Even if we don't queue the job, flush the wq to be sure it's
|
||||
* been released.
|
||||
*/
|
||||
flush_workqueue(vfio_irqfd_cleanup_wq);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(vfio_virqfd_disable);
|
||||
|
||||
/*
|
||||
* INTx
|
||||
*/
|
||||
|
|
|
|||
|
|
@ -87,9 +87,6 @@ extern ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf,
|
|||
extern int vfio_pci_init_perm_bits(void);
|
||||
extern void vfio_pci_uninit_perm_bits(void);
|
||||
|
||||
extern int vfio_virqfd_init(void);
|
||||
extern void vfio_virqfd_exit(void);
|
||||
|
||||
extern int vfio_config_init(struct vfio_pci_device *vdev);
|
||||
extern void vfio_config_free(struct vfio_pci_device *vdev);
|
||||
#endif /* VFIO_PCI_PRIVATE_H */
|
||||
|
|
|
|||
|
|
@ -0,0 +1,213 @@
|
|||
/*
|
||||
* VFIO generic eventfd code for IRQFD support.
|
||||
* Derived from drivers/vfio/pci/vfio_pci_intrs.c
|
||||
*
|
||||
* Copyright (C) 2012 Red Hat, Inc. All rights reserved.
|
||||
* Author: Alex Williamson <alex.williamson@redhat.com>
|
||||
*
|
||||
* This program is free software; you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License version 2 as
|
||||
* published by the Free Software Foundation.
|
||||
*/
|
||||
|
||||
#include <linux/vfio.h>
|
||||
#include <linux/eventfd.h>
|
||||
#include <linux/file.h>
|
||||
#include <linux/slab.h>
|
||||
|
||||
static struct workqueue_struct *vfio_irqfd_cleanup_wq;
|
||||
DEFINE_SPINLOCK(virqfd_lock);
|
||||
|
||||
int __init vfio_virqfd_init(void)
|
||||
{
|
||||
vfio_irqfd_cleanup_wq =
|
||||
create_singlethread_workqueue("vfio-irqfd-cleanup");
|
||||
if (!vfio_irqfd_cleanup_wq)
|
||||
return -ENOMEM;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
void vfio_virqfd_exit(void)
|
||||
{
|
||||
destroy_workqueue(vfio_irqfd_cleanup_wq);
|
||||
}
|
||||
|
||||
static void virqfd_deactivate(struct virqfd *virqfd)
|
||||
{
|
||||
queue_work(vfio_irqfd_cleanup_wq, &virqfd->shutdown);
|
||||
}
|
||||
|
||||
static int virqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key)
|
||||
{
|
||||
struct virqfd *virqfd = container_of(wait, struct virqfd, wait);
|
||||
unsigned long flags = (unsigned long)key;
|
||||
|
||||
if (flags & POLLIN) {
|
||||
/* An event has been signaled, call function */
|
||||
if ((!virqfd->handler ||
|
||||
virqfd->handler(virqfd->opaque, virqfd->data)) &&
|
||||
virqfd->thread)
|
||||
schedule_work(&virqfd->inject);
|
||||
}
|
||||
|
||||
if (flags & POLLHUP) {
|
||||
unsigned long flags;
|
||||
spin_lock_irqsave(&virqfd_lock, flags);
|
||||
|
||||
/*
|
||||
* The eventfd is closing, if the virqfd has not yet been
|
||||
* queued for release, as determined by testing whether the
|
||||
* virqfd pointer to it is still valid, queue it now. As
|
||||
* with kvm irqfds, we know we won't race against the virqfd
|
||||
* going away because we hold the lock to get here.
|
||||
*/
|
||||
if (*(virqfd->pvirqfd) == virqfd) {
|
||||
*(virqfd->pvirqfd) = NULL;
|
||||
virqfd_deactivate(virqfd);
|
||||
}
|
||||
|
||||
spin_unlock_irqrestore(&virqfd_lock, flags);
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static void virqfd_ptable_queue_proc(struct file *file,
|
||||
wait_queue_head_t *wqh, poll_table *pt)
|
||||
{
|
||||
struct virqfd *virqfd = container_of(pt, struct virqfd, pt);
|
||||
add_wait_queue(wqh, &virqfd->wait);
|
||||
}
|
||||
|
||||
static void virqfd_shutdown(struct work_struct *work)
|
||||
{
|
||||
struct virqfd *virqfd = container_of(work, struct virqfd, shutdown);
|
||||
u64 cnt;
|
||||
|
||||
eventfd_ctx_remove_wait_queue(virqfd->eventfd, &virqfd->wait, &cnt);
|
||||
flush_work(&virqfd->inject);
|
||||
eventfd_ctx_put(virqfd->eventfd);
|
||||
|
||||
kfree(virqfd);
|
||||
}
|
||||
|
||||
static void virqfd_inject(struct work_struct *work)
|
||||
{
|
||||
struct virqfd *virqfd = container_of(work, struct virqfd, inject);
|
||||
if (virqfd->thread)
|
||||
virqfd->thread(virqfd->opaque, virqfd->data);
|
||||
}
|
||||
|
||||
int vfio_virqfd_enable(void *opaque,
|
||||
int (*handler)(void *, void *),
|
||||
void (*thread)(void *, void *),
|
||||
void *data, struct virqfd **pvirqfd, int fd)
|
||||
{
|
||||
struct fd irqfd;
|
||||
struct eventfd_ctx *ctx;
|
||||
struct virqfd *virqfd;
|
||||
int ret = 0;
|
||||
unsigned int events;
|
||||
|
||||
virqfd = kzalloc(sizeof(*virqfd), GFP_KERNEL);
|
||||
if (!virqfd)
|
||||
return -ENOMEM;
|
||||
|
||||
virqfd->pvirqfd = pvirqfd;
|
||||
virqfd->opaque = opaque;
|
||||
virqfd->handler = handler;
|
||||
virqfd->thread = thread;
|
||||
virqfd->data = data;
|
||||
|
||||
INIT_WORK(&virqfd->shutdown, virqfd_shutdown);
|
||||
INIT_WORK(&virqfd->inject, virqfd_inject);
|
||||
|
||||
irqfd = fdget(fd);
|
||||
if (!irqfd.file) {
|
||||
ret = -EBADF;
|
||||
goto err_fd;
|
||||
}
|
||||
|
||||
ctx = eventfd_ctx_fileget(irqfd.file);
|
||||
if (IS_ERR(ctx)) {
|
||||
ret = PTR_ERR(ctx);
|
||||
goto err_ctx;
|
||||
}
|
||||
|
||||
virqfd->eventfd = ctx;
|
||||
|
||||
/*
|
||||
* virqfds can be released by closing the eventfd or directly
|
||||
* through ioctl. These are both done through a workqueue, so
|
||||
* we update the pointer to the virqfd under lock to avoid
|
||||
* pushing multiple jobs to release the same virqfd.
|
||||
*/
|
||||
spin_lock_irq(&virqfd_lock);
|
||||
|
||||
if (*pvirqfd) {
|
||||
spin_unlock_irq(&virqfd_lock);
|
||||
ret = -EBUSY;
|
||||
goto err_busy;
|
||||
}
|
||||
*pvirqfd = virqfd;
|
||||
|
||||
spin_unlock_irq(&virqfd_lock);
|
||||
|
||||
/*
|
||||
* Install our own custom wake-up handling so we are notified via
|
||||
* a callback whenever someone signals the underlying eventfd.
|
||||
*/
|
||||
init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup);
|
||||
init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc);
|
||||
|
||||
events = irqfd.file->f_op->poll(irqfd.file, &virqfd->pt);
|
||||
|
||||
/*
|
||||
* Check if there was an event already pending on the eventfd
|
||||
* before we registered and trigger it as if we didn't miss it.
|
||||
*/
|
||||
if (events & POLLIN) {
|
||||
if ((!handler || handler(opaque, data)) && thread)
|
||||
schedule_work(&virqfd->inject);
|
||||
}
|
||||
|
||||
/*
|
||||
* Do not drop the file until the irqfd is fully initialized,
|
||||
* otherwise we might race against the POLLHUP.
|
||||
*/
|
||||
fdput(irqfd);
|
||||
|
||||
return 0;
|
||||
err_busy:
|
||||
eventfd_ctx_put(ctx);
|
||||
err_ctx:
|
||||
fdput(irqfd);
|
||||
err_fd:
|
||||
kfree(virqfd);
|
||||
|
||||
return ret;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(vfio_virqfd_enable);
|
||||
|
||||
void vfio_virqfd_disable(struct virqfd **pvirqfd)
|
||||
{
|
||||
unsigned long flags;
|
||||
|
||||
spin_lock_irqsave(&virqfd_lock, flags);
|
||||
|
||||
if (*pvirqfd) {
|
||||
virqfd_deactivate(*pvirqfd);
|
||||
*pvirqfd = NULL;
|
||||
}
|
||||
|
||||
spin_unlock_irqrestore(&virqfd_lock, flags);
|
||||
|
||||
/*
|
||||
* Block until we know all outstanding shutdown jobs have completed.
|
||||
* Even if we don't queue the job, flush the wq to be sure it's
|
||||
* been released.
|
||||
*/
|
||||
flush_workqueue(vfio_irqfd_cleanup_wq);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(vfio_virqfd_disable);
|
||||
|
|
@ -14,6 +14,8 @@
|
|||
|
||||
#include <linux/iommu.h>
|
||||
#include <linux/mm.h>
|
||||
#include <linux/workqueue.h>
|
||||
#include <linux/poll.h>
|
||||
#include <uapi/linux/vfio.h>
|
||||
|
||||
/**
|
||||
|
|
@ -123,4 +125,29 @@ static inline long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group,
|
|||
return -ENOTTY;
|
||||
}
|
||||
#endif /* CONFIG_EEH */
|
||||
|
||||
/*
|
||||
* IRQfd - generic
|
||||
*/
|
||||
struct virqfd {
|
||||
void *opaque;
|
||||
struct eventfd_ctx *eventfd;
|
||||
int (*handler)(void *, void *);
|
||||
void (*thread)(void *, void *);
|
||||
void *data;
|
||||
struct work_struct inject;
|
||||
wait_queue_t wait;
|
||||
poll_table pt;
|
||||
struct work_struct shutdown;
|
||||
struct virqfd **pvirqfd;
|
||||
};
|
||||
|
||||
extern int vfio_virqfd_init(void);
|
||||
extern void vfio_virqfd_exit(void);
|
||||
extern int vfio_virqfd_enable(void *opaque,
|
||||
int (*handler)(void *, void *),
|
||||
void (*thread)(void *, void *),
|
||||
void *data, struct virqfd **pvirqfd, int fd);
|
||||
extern void vfio_virqfd_disable(struct virqfd **pvirqfd);
|
||||
|
||||
#endif /* VFIO_H */
|
||||
|
|
|
|||
Loading…
Reference in New Issue