diff options
| -rw-r--r-- | Documentation/vfio.txt | 2 | ||||
| -rw-r--r-- | arch/x86/xen/setup.c | 4 | ||||
| -rw-r--r-- | drivers/block/rbd.c | 7 | ||||
| -rw-r--r-- | drivers/vfio/pci/vfio_pci_intrs.c | 76 | ||||
| -rw-r--r-- | net/ceph/messenger.c | 5 |
5 files changed, 65 insertions, 29 deletions
diff --git a/Documentation/vfio.txt b/Documentation/vfio.txt index 0cb6685c8029..8eda3635a17d 100644 --- a/Documentation/vfio.txt +++ b/Documentation/vfio.txt @@ -133,7 +133,7 @@ character devices for this group: $ lspci -n -s 0000:06:0d.0 06:0d.0 0401: 1102:0002 (rev 08) # echo 0000:06:0d.0 > /sys/bus/pci/devices/0000:06:0d.0/driver/unbind -# echo 1102 0002 > /sys/bus/pci/drivers/vfio/new_id +# echo 1102 0002 > /sys/bus/pci/drivers/vfio-pci/new_id Now we need to look at what other devices are in the group to free it for use by VFIO: diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index d11ca11d14fc..e2d62d697b5d 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -17,6 +17,7 @@ #include <asm/e820.h> #include <asm/setup.h> #include <asm/acpi.h> +#include <asm/numa.h> #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> @@ -544,4 +545,7 @@ void __init xen_arch_setup(void) disable_cpufreq(); WARN_ON(set_pm_idle_to_default()); fiddle_vdso(); +#ifdef CONFIG_NUMA + numa_off = 1; +#endif } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 9917943a3572..54a55f03115d 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -246,13 +246,12 @@ static int rbd_open(struct block_device *bdev, fmode_t mode) { struct rbd_device *rbd_dev = bdev->bd_disk->private_data; - rbd_get_dev(rbd_dev); - - set_device_ro(bdev, rbd_dev->read_only); - if ((mode & FMODE_WRITE) && rbd_dev->read_only) return -EROFS; + rbd_get_dev(rbd_dev); + set_device_ro(bdev, rbd_dev->read_only); + return 0; } diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 211a4920b88a..d8dedc7d3910 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -76,9 +76,24 @@ static int virqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key) schedule_work(&virqfd->inject); } - if (flags & POLLHUP) - /* The eventfd is closing, detach from VFIO */ - virqfd_deactivate(virqfd); + if (flags & POLLHUP) { + unsigned long flags; + spin_lock_irqsave(&virqfd->vdev->irqlock, flags); + + /* + * The eventfd is closing, if the virqfd has not yet been + * queued for release, as determined by testing whether the + * vdev 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 wqh->lock to get here. + */ + if (*(virqfd->pvirqfd) == virqfd) { + *(virqfd->pvirqfd) = NULL; + virqfd_deactivate(virqfd); + } + + spin_unlock_irqrestore(&virqfd->vdev->irqlock, flags); + } return 0; } @@ -93,7 +108,6 @@ static void virqfd_ptable_queue_proc(struct file *file, static void virqfd_shutdown(struct work_struct *work) { struct virqfd *virqfd = container_of(work, struct virqfd, shutdown); - struct virqfd **pvirqfd = virqfd->pvirqfd; u64 cnt; eventfd_ctx_remove_wait_queue(virqfd->eventfd, &virqfd->wait, &cnt); @@ -101,7 +115,6 @@ static void virqfd_shutdown(struct work_struct *work) eventfd_ctx_put(virqfd->eventfd); kfree(virqfd); - *pvirqfd = NULL; } static void virqfd_inject(struct work_struct *work) @@ -122,15 +135,11 @@ static int virqfd_enable(struct vfio_pci_device *vdev, int ret = 0; unsigned int events; - if (*pvirqfd) - return -EBUSY; - virqfd = kzalloc(sizeof(*virqfd), GFP_KERNEL); if (!virqfd) return -ENOMEM; virqfd->pvirqfd = pvirqfd; - *pvirqfd = virqfd; virqfd->vdev = vdev; virqfd->handler = handler; virqfd->thread = thread; @@ -154,6 +163,23 @@ static int virqfd_enable(struct vfio_pci_device *vdev, 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(&vdev->irqlock); + + if (*pvirqfd) { + spin_unlock_irq(&vdev->irqlock); + ret = -EBUSY; + goto fail; + } + *pvirqfd = virqfd; + + spin_unlock_irq(&vdev->irqlock); + + /* * Install our own custom wake-up handling so we are notified via * a callback whenever someone signals the underlying eventfd. */ @@ -187,19 +213,29 @@ fail: fput(file); kfree(virqfd); - *pvirqfd = NULL; return ret; } -static void virqfd_disable(struct virqfd *virqfd) +static void virqfd_disable(struct vfio_pci_device *vdev, + struct virqfd **pvirqfd) { - if (!virqfd) - return; + unsigned long flags; + + spin_lock_irqsave(&vdev->irqlock, flags); + + if (*pvirqfd) { + virqfd_deactivate(*pvirqfd); + *pvirqfd = NULL; + } - virqfd_deactivate(virqfd); + spin_unlock_irqrestore(&vdev->irqlock, flags); - /* Block until we know all outstanding shutdown jobs have completed. */ + /* + * 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); } @@ -392,8 +428,8 @@ static int vfio_intx_set_signal(struct vfio_pci_device *vdev, int fd) static void vfio_intx_disable(struct vfio_pci_device *vdev) { vfio_intx_set_signal(vdev, -1); - virqfd_disable(vdev->ctx[0].unmask); - virqfd_disable(vdev->ctx[0].mask); + virqfd_disable(vdev, &vdev->ctx[0].unmask); + virqfd_disable(vdev, &vdev->ctx[0].mask); vdev->irq_type = VFIO_PCI_NUM_IRQS; vdev->num_ctx = 0; kfree(vdev->ctx); @@ -539,8 +575,8 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix) vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix); for (i = 0; i < vdev->num_ctx; i++) { - virqfd_disable(vdev->ctx[i].unmask); - virqfd_disable(vdev->ctx[i].mask); + virqfd_disable(vdev, &vdev->ctx[i].unmask); + virqfd_disable(vdev, &vdev->ctx[i].mask); } if (msix) { @@ -577,7 +613,7 @@ static int vfio_pci_set_intx_unmask(struct vfio_pci_device *vdev, vfio_send_intx_eventfd, NULL, &vdev->ctx[0].unmask, fd); - virqfd_disable(vdev->ctx[0].unmask); + virqfd_disable(vdev, &vdev->ctx[0].unmask); } return 0; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 24c5eea8c45b..159aa8bef9e7 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1073,16 +1073,13 @@ static int write_partial_msg_pages(struct ceph_connection *con) BUG_ON(kaddr == NULL); base = kaddr + con->out_msg_pos.page_pos + bio_offset; crc = crc32c(crc, base, len); + kunmap(page); msg->footer.data_crc = cpu_to_le32(crc); con->out_msg_pos.did_page_crc = true; } ret = ceph_tcp_sendpage(con->sock, page, con->out_msg_pos.page_pos + bio_offset, len, 1); - - if (do_datacrc) - kunmap(page); - if (ret <= 0) goto out; |