summaryrefslogtreecommitdiff
path: root/drivers/virtio
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/virtio')
-rw-r--r--drivers/virtio/virtio_balloon.c52
-rw-r--r--drivers/virtio/virtio_pci_legacy.c16
-rw-r--r--drivers/virtio/virtio_ring.c32
3 files changed, 84 insertions, 16 deletions
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index f6ea8f4ba..4e7003db1 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -30,6 +30,7 @@
#include <linux/oom.h>
#include <linux/wait.h>
#include <linux/mm.h>
+#include <linux/mount.h>
/*
* Balloon device works in 4K page units. So each page is pointed to by
@@ -45,6 +46,10 @@ static int oom_pages = OOM_VBALLOON_DEFAULT_PAGES;
module_param(oom_pages, int, S_IRUSR | S_IWUSR);
MODULE_PARM_DESC(oom_pages, "pages to free on OOM");
+#ifdef CONFIG_BALLOON_COMPACTION
+static struct vfsmount *balloon_mnt;
+#endif
+
struct virtio_balloon {
struct virtio_device *vdev;
struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
@@ -492,6 +497,24 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info,
return MIGRATEPAGE_SUCCESS;
}
+
+static struct dentry *balloon_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data)
+{
+ static const struct dentry_operations ops = {
+ .d_dname = simple_dname,
+ };
+
+ return mount_pseudo(fs_type, "balloon-kvm:", NULL, &ops,
+ BALLOON_KVM_MAGIC);
+}
+
+static struct file_system_type balloon_fs = {
+ .name = "balloon-kvm",
+ .mount = balloon_mount,
+ .kill_sb = kill_anon_super,
+};
+
#endif /* CONFIG_BALLOON_COMPACTION */
static int virtballoon_probe(struct virtio_device *vdev)
@@ -521,9 +544,6 @@ static int virtballoon_probe(struct virtio_device *vdev)
vb->vdev = vdev;
balloon_devinfo_init(&vb->vb_dev_info);
-#ifdef CONFIG_BALLOON_COMPACTION
- vb->vb_dev_info.migratepage = virtballoon_migratepage;
-#endif
err = init_vqs(vb);
if (err)
@@ -533,13 +553,33 @@ static int virtballoon_probe(struct virtio_device *vdev)
vb->nb.priority = VIRTBALLOON_OOM_NOTIFY_PRIORITY;
err = register_oom_notifier(&vb->nb);
if (err < 0)
- goto out_oom_notify;
+ goto out_del_vqs;
+
+#ifdef CONFIG_BALLOON_COMPACTION
+ balloon_mnt = kern_mount(&balloon_fs);
+ if (IS_ERR(balloon_mnt)) {
+ err = PTR_ERR(balloon_mnt);
+ unregister_oom_notifier(&vb->nb);
+ goto out_del_vqs;
+ }
+
+ vb->vb_dev_info.migratepage = virtballoon_migratepage;
+ vb->vb_dev_info.inode = alloc_anon_inode(balloon_mnt->mnt_sb);
+ if (IS_ERR(vb->vb_dev_info.inode)) {
+ err = PTR_ERR(vb->vb_dev_info.inode);
+ kern_unmount(balloon_mnt);
+ unregister_oom_notifier(&vb->nb);
+ vb->vb_dev_info.inode = NULL;
+ goto out_del_vqs;
+ }
+ vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
+#endif
virtio_device_ready(vdev);
return 0;
-out_oom_notify:
+out_del_vqs:
vdev->config->del_vqs(vdev);
out_free_vb:
kfree(vb);
@@ -573,6 +613,8 @@ static void virtballoon_remove(struct virtio_device *vdev)
cancel_work_sync(&vb->update_balloon_stats_work);
remove_common(vb);
+ if (vb->vb_dev_info.inode)
+ iput(vb->vb_dev_info.inode);
kfree(vb);
}
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index 8c4e61783..6d9e5173d 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -212,10 +212,18 @@ int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev)
return -ENODEV;
}
- rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
- if (rc)
- rc = dma_set_mask_and_coherent(&pci_dev->dev,
- DMA_BIT_MASK(32));
+ rc = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(64));
+ if (rc) {
+ rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32));
+ } else {
+ /*
+ * The virtio ring base address is expressed as a 32-bit PFN,
+ * with a page size of 1 << VIRTIO_PCI_QUEUE_ADDR_SHIFT.
+ */
+ dma_set_coherent_mask(&pci_dev->dev,
+ DMA_BIT_MASK(32 + VIRTIO_PCI_QUEUE_ADDR_SHIFT));
+ }
+
if (rc)
dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA. Trying to continue, but this might not work.\n");
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 2ebf30e57..6b2cd922d 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -117,7 +117,10 @@ struct vring_virtqueue {
#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
/*
- * The interaction between virtio and a possible IOMMU is a mess.
+ * Modern virtio devices have feature bits to specify whether they need a
+ * quirk and bypass the IOMMU. If not there, just use the DMA API.
+ *
+ * If there, the interaction between virtio and DMA API is messy.
*
* On most systems with virtio, physical addresses match bus addresses,
* and it doesn't particularly matter whether we use the DMA API.
@@ -133,10 +136,18 @@ struct vring_virtqueue {
*
* For the time being, we preserve historic behavior and bypass the DMA
* API.
+ *
+ * TODO: install a per-device DMA ops structure that does the right thing
+ * taking into account all the above quirks, and use the DMA API
+ * unconditionally on data path.
*/
static bool vring_use_dma_api(struct virtio_device *vdev)
{
+ if (!virtio_has_iommu_quirk(vdev))
+ return true;
+
+ /* Otherwise, we are left to guess. */
/*
* In theory, it's possible to have a buggy QEMU-supposed
* emulated Q35 IOMMU and Xen enabled at the same time. On
@@ -156,7 +167,7 @@ static bool vring_use_dma_api(struct virtio_device *vdev)
* making all of the arch DMA ops work on the vring device itself
* is a mess. For now, we use the parent device for DMA ops.
*/
-struct device *vring_dma_dev(const struct vring_virtqueue *vq)
+static struct device *vring_dma_dev(const struct vring_virtqueue *vq)
{
return vq->vq.vdev->dev.parent;
}
@@ -417,6 +428,7 @@ unmap_release:
if (indirect)
kfree(desc);
+ END_USE(vq);
return -EIO;
}
@@ -720,7 +732,8 @@ void virtqueue_disable_cb(struct virtqueue *_vq)
if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
- vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
}
}
@@ -752,7 +765,8 @@ unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
* entry. Always do both to keep code simple. */
if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
- vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
}
vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
END_USE(vq);
@@ -820,10 +834,11 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
* more to do. */
/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
* either clear the flags bit or point the event index at the next
- * entry. Always do both to keep code simple. */
+ * entry. Always update the event index to keep code simple. */
if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
- vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
}
/* TODO: tune this threshold */
bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
@@ -941,7 +956,8 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
/* No callback? Tell other side not to bother us. */
if (!callback) {
vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
- vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
}
/* Put everything in free lists. */
@@ -1101,6 +1117,8 @@ void vring_transport_features(struct virtio_device *vdev)
break;
case VIRTIO_F_VERSION_1:
break;
+ case VIRTIO_F_IOMMU_PLATFORM:
+ break;
default:
/* We don't understand this bit. */
__virtio_clear_bit(vdev, i);
generated by cgit v1.2.3-54-g00ecf (git 2.45.2) at 2025-10-27 13:45:25 +0000