| Message ID | 20190812213356.22097.20751.stgit@localhost.localdomain (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | mm / virtio: Provide support for unused page reporting | expand |
On Mon, Aug 12, 2019 at 02:33:56PM -0700, Alexander Duyck wrote: > From: Alexander Duyck <alexander.h.duyck@linux.intel.com> > > Add support for the page reporting feature provided by virtio-balloon. > Reporting differs from the regular balloon functionality in that is is > much less durable than a standard memory balloon. Instead of creating a > list of pages that cannot be accessed the pages are only inaccessible > while they are being indicated to the virtio interface. Once the > interface has acknowledged them they are placed back into their respective > free lists and are once again accessible by the guest system. > > Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com> > --- > drivers/virtio/Kconfig | 1 + > drivers/virtio/virtio_balloon.c | 65 +++++++++++++++++++++++++++++++++++ > include/uapi/linux/virtio_balloon.h | 1 + > 3 files changed, 67 insertions(+) > > diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig > index 078615cf2afc..4b2dd8259ff5 100644 > --- a/drivers/virtio/Kconfig > +++ b/drivers/virtio/Kconfig > @@ -58,6 +58,7 @@ config VIRTIO_BALLOON > tristate "Virtio balloon driver" > depends on VIRTIO > select MEMORY_BALLOON > + select PAGE_REPORTING > ---help--- > This driver supports increasing and decreasing the amount > of memory within a KVM guest. > diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c > index 2c19457ab573..52f9eeda1877 100644 > --- a/drivers/virtio/virtio_balloon.c > +++ b/drivers/virtio/virtio_balloon.c > @@ -19,6 +19,7 @@ > #include <linux/mount.h> > #include <linux/magic.h> > #include <linux/pseudo_fs.h> > +#include <linux/page_reporting.h> > > /* > * Balloon device works in 4K page units. So each page is pointed to by > @@ -37,6 +38,9 @@ > #define VIRTIO_BALLOON_FREE_PAGE_SIZE \ > (1 << (VIRTIO_BALLOON_FREE_PAGE_ORDER + PAGE_SHIFT)) > > +/* limit on the number of pages that can be on the reporting vq */ > +#define VIRTIO_BALLOON_VRING_HINTS_MAX 16 > + > #ifdef CONFIG_BALLOON_COMPACTION > static struct vfsmount *balloon_mnt; > #endif > @@ -46,6 +50,7 @@ enum virtio_balloon_vq { > VIRTIO_BALLOON_VQ_DEFLATE, > VIRTIO_BALLOON_VQ_STATS, > VIRTIO_BALLOON_VQ_FREE_PAGE, > + VIRTIO_BALLOON_VQ_REPORTING, > VIRTIO_BALLOON_VQ_MAX > }; > > @@ -113,6 +118,10 @@ struct virtio_balloon { > > /* To register a shrinker to shrink memory upon memory pressure */ > struct shrinker shrinker; > + > + /* Unused page reporting device */ > + struct virtqueue *reporting_vq; > + struct page_reporting_dev_info ph_dev_info; > }; > > static struct virtio_device_id id_table[] = { > @@ -152,6 +161,32 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq) > > } > > +void virtballoon_unused_page_report(struct page_reporting_dev_info *ph_dev_info, > + unsigned int nents) > +{ > + struct virtio_balloon *vb = > + container_of(ph_dev_info, struct virtio_balloon, ph_dev_info); > + struct virtqueue *vq = vb->reporting_vq; > + unsigned int unused, err; > + > + /* We should always be able to add these buffers to an empty queue. */ > + err = virtqueue_add_inbuf(vq, ph_dev_info->sg, nents, vb, > + GFP_NOWAIT | __GFP_NOWARN); > + > + /* > + * In the extremely unlikely case that something has changed and we > + * are able to trigger an error we will simply display a warning > + * and exit without actually processing the pages. > + */ > + if (WARN_ON(err)) > + return; > + > + virtqueue_kick(vq); > + > + /* When host has read buffer, this completes via balloon_ack */ > + wait_event(vb->acked, virtqueue_get_buf(vq, &unused)); > +} > + > static void set_page_pfns(struct virtio_balloon *vb, > __virtio32 pfns[], struct page *page) > { > @@ -476,6 +511,7 @@ static int init_vqs(struct virtio_balloon *vb) > names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate"; > names[VIRTIO_BALLOON_VQ_STATS] = NULL; > names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; > + names[VIRTIO_BALLOON_VQ_REPORTING] = NULL; > > if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) { > names[VIRTIO_BALLOON_VQ_STATS] = "stats"; > @@ -487,11 +523,19 @@ static int init_vqs(struct virtio_balloon *vb) > callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; > } > > + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) { > + names[VIRTIO_BALLOON_VQ_REPORTING] = "reporting_vq"; > + callbacks[VIRTIO_BALLOON_VQ_REPORTING] = balloon_ack; > + } > + > err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX, > vqs, callbacks, names, NULL, NULL); > if (err) > return err; > > + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) > + vb->reporting_vq = vqs[VIRTIO_BALLOON_VQ_REPORTING]; > + > vb->inflate_vq = vqs[VIRTIO_BALLOON_VQ_INFLATE]; > vb->deflate_vq = vqs[VIRTIO_BALLOON_VQ_DEFLATE]; > if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) { > @@ -931,12 +975,30 @@ static int virtballoon_probe(struct virtio_device *vdev) > if (err) > goto out_del_balloon_wq; > } > + > + vb->ph_dev_info.report = virtballoon_unused_page_report; > + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) { > + unsigned int capacity; > + > + capacity = min_t(unsigned int, > + virtqueue_get_vring_size(vb->reporting_vq) - 1, > + VIRTIO_BALLOON_VRING_HINTS_MAX); Hmm why - 1 exactly? This might end up being 0 in the unusual configuration of vq size 1. Also, VIRTIO_BALLOON_VRING_HINTS_MAX is a power of 2 but virtqueue_get_vring_size(vb->reporting_vq) - 1 won't be if we are using split rings - donnu if that matters. > + vb->ph_dev_info.capacity = capacity; > + > + err = page_reporting_startup(&vb->ph_dev_info); > + if (err) > + goto out_unregister_shrinker; > + } > + > virtio_device_ready(vdev); > > if (towards_target(vb)) > virtballoon_changed(vdev); > return 0; > > +out_unregister_shrinker: > + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) > + virtio_balloon_unregister_shrinker(vb); > out_del_balloon_wq: > if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) > destroy_workqueue(vb->balloon_wq); > @@ -965,6 +1027,8 @@ static void virtballoon_remove(struct virtio_device *vdev) > { > struct virtio_balloon *vb = vdev->priv; > > + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) > + page_reporting_shutdown(&vb->ph_dev_info); > if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) > virtio_balloon_unregister_shrinker(vb); > spin_lock_irq(&vb->stop_update_lock); > @@ -1034,6 +1098,7 @@ static int virtballoon_validate(struct virtio_device *vdev) > VIRTIO_BALLOON_F_DEFLATE_ON_OOM, > VIRTIO_BALLOON_F_FREE_PAGE_HINT, > VIRTIO_BALLOON_F_PAGE_POISON, > + VIRTIO_BALLOON_F_REPORTING, > }; > > static struct virtio_driver virtio_balloon_driver = { > diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h > index a1966cd7b677..19974392d324 100644 > --- a/include/uapi/linux/virtio_balloon.h > +++ b/include/uapi/linux/virtio_balloon.h > @@ -36,6 +36,7 @@ > #define VIRTIO_BALLOON_F_DEFLATE_ON_OOM 2 /* Deflate balloon on OOM */ > #define VIRTIO_BALLOON_F_FREE_PAGE_HINT 3 /* VQ to report free pages */ > #define VIRTIO_BALLOON_F_PAGE_POISON 4 /* Guest is using page poisoning */ > +#define VIRTIO_BALLOON_F_REPORTING 5 /* Page reporting virtqueue */ > > /* Size of a PFN in the balloon interface. */ > #define VIRTIO_BALLOON_PFN_SHIFT 12
On Tue, Sep 3, 2019 at 12:32 AM Michael S. Tsirkin <mst@redhat.com> wrote: > > On Mon, Aug 12, 2019 at 02:33:56PM -0700, Alexander Duyck wrote: > > From: Alexander Duyck <alexander.h.duyck@linux.intel.com> > > > > Add support for the page reporting feature provided by virtio-balloon. > > Reporting differs from the regular balloon functionality in that is is > > much less durable than a standard memory balloon. Instead of creating a > > list of pages that cannot be accessed the pages are only inaccessible > > while they are being indicated to the virtio interface. Once the > > interface has acknowledged them they are placed back into their respective > > free lists and are once again accessible by the guest system. > > > > Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com> > > --- > > drivers/virtio/Kconfig | 1 + > > drivers/virtio/virtio_balloon.c | 65 +++++++++++++++++++++++++++++++++++ > > include/uapi/linux/virtio_balloon.h | 1 + > > 3 files changed, 67 insertions(+) > > > > diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig > > index 078615cf2afc..4b2dd8259ff5 100644 > > --- a/drivers/virtio/Kconfig > > +++ b/drivers/virtio/Kconfig > > @@ -58,6 +58,7 @@ config VIRTIO_BALLOON > > tristate "Virtio balloon driver" > > depends on VIRTIO > > select MEMORY_BALLOON > > + select PAGE_REPORTING > > ---help--- > > This driver supports increasing and decreasing the amount > > of memory within a KVM guest. > > diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c > > index 2c19457ab573..52f9eeda1877 100644 > > --- a/drivers/virtio/virtio_balloon.c > > +++ b/drivers/virtio/virtio_balloon.c > > @@ -19,6 +19,7 @@ > > #include <linux/mount.h> > > #include <linux/magic.h> > > #include <linux/pseudo_fs.h> > > +#include <linux/page_reporting.h> > > > > /* > > * Balloon device works in 4K page units. So each page is pointed to by > > @@ -37,6 +38,9 @@ > > #define VIRTIO_BALLOON_FREE_PAGE_SIZE \ > > (1 << (VIRTIO_BALLOON_FREE_PAGE_ORDER + PAGE_SHIFT)) > > > > +/* limit on the number of pages that can be on the reporting vq */ > > +#define VIRTIO_BALLOON_VRING_HINTS_MAX 16 > > + > > #ifdef CONFIG_BALLOON_COMPACTION > > static struct vfsmount *balloon_mnt; > > #endif > > @@ -46,6 +50,7 @@ enum virtio_balloon_vq { > > VIRTIO_BALLOON_VQ_DEFLATE, > > VIRTIO_BALLOON_VQ_STATS, > > VIRTIO_BALLOON_VQ_FREE_PAGE, > > + VIRTIO_BALLOON_VQ_REPORTING, > > VIRTIO_BALLOON_VQ_MAX > > }; > > > > @@ -113,6 +118,10 @@ struct virtio_balloon { > > > > /* To register a shrinker to shrink memory upon memory pressure */ > > struct shrinker shrinker; > > + > > + /* Unused page reporting device */ > > + struct virtqueue *reporting_vq; > > + struct page_reporting_dev_info ph_dev_info; > > }; > > > > static struct virtio_device_id id_table[] = { > > @@ -152,6 +161,32 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq) > > > > } > > > > +void virtballoon_unused_page_report(struct page_reporting_dev_info *ph_dev_info, > > + unsigned int nents) > > +{ > > + struct virtio_balloon *vb = > > + container_of(ph_dev_info, struct virtio_balloon, ph_dev_info); > > + struct virtqueue *vq = vb->reporting_vq; > > + unsigned int unused, err; > > + > > + /* We should always be able to add these buffers to an empty queue. */ > > + err = virtqueue_add_inbuf(vq, ph_dev_info->sg, nents, vb, > > + GFP_NOWAIT | __GFP_NOWARN); > > + > > + /* > > + * In the extremely unlikely case that something has changed and we > > + * are able to trigger an error we will simply display a warning > > + * and exit without actually processing the pages. > > + */ > > + if (WARN_ON(err)) > > + return; > > + > > + virtqueue_kick(vq); > > + > > + /* When host has read buffer, this completes via balloon_ack */ > > + wait_event(vb->acked, virtqueue_get_buf(vq, &unused)); > > +} > > + > > static void set_page_pfns(struct virtio_balloon *vb, > > __virtio32 pfns[], struct page *page) > > { > > @@ -476,6 +511,7 @@ static int init_vqs(struct virtio_balloon *vb) > > names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate"; > > names[VIRTIO_BALLOON_VQ_STATS] = NULL; > > names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; > > + names[VIRTIO_BALLOON_VQ_REPORTING] = NULL; > > > > if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) { > > names[VIRTIO_BALLOON_VQ_STATS] = "stats"; > > @@ -487,11 +523,19 @@ static int init_vqs(struct virtio_balloon *vb) > > callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; > > } > > > > + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) { > > + names[VIRTIO_BALLOON_VQ_REPORTING] = "reporting_vq"; > > + callbacks[VIRTIO_BALLOON_VQ_REPORTING] = balloon_ack; > > + } > > + > > err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX, > > vqs, callbacks, names, NULL, NULL); > > if (err) > > return err; > > > > + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) > > + vb->reporting_vq = vqs[VIRTIO_BALLOON_VQ_REPORTING]; > > + > > vb->inflate_vq = vqs[VIRTIO_BALLOON_VQ_INFLATE]; > > vb->deflate_vq = vqs[VIRTIO_BALLOON_VQ_DEFLATE]; > > if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) { > > @@ -931,12 +975,30 @@ static int virtballoon_probe(struct virtio_device *vdev) > > if (err) > > goto out_del_balloon_wq; > > } > > + > > + vb->ph_dev_info.report = virtballoon_unused_page_report; > > + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) { > > + unsigned int capacity; > > + > > + capacity = min_t(unsigned int, > > + virtqueue_get_vring_size(vb->reporting_vq) - 1, > > + VIRTIO_BALLOON_VRING_HINTS_MAX); > > Hmm why - 1 exactly? > This might end up being 0 in the unusual configuration of vq size 1. > Also, VIRTIO_BALLOON_VRING_HINTS_MAX is a power of 2 but > virtqueue_get_vring_size(vb->reporting_vq) - 1 won't > be if we are using split rings - donnu if that matters. Is a vq size of 1 valid? Does that mean you can use that 1 descriptor? Odds are I probably misunderstood the ring config in the other hinting implementation. Looking it over now I guess it was adding one additional entry for a command header and that was why it was reserving one additional slot. I can update the code to drop the "- 1" if the ring is capable of being fully utilized. Thanks. - Alex
On Tue, Sep 03, 2019 at 07:13:32AM -0700, Alexander Duyck wrote: > On Tue, Sep 3, 2019 at 12:32 AM Michael S. Tsirkin <mst@redhat.com> wrote: > > > > On Mon, Aug 12, 2019 at 02:33:56PM -0700, Alexander Duyck wrote: > > > From: Alexander Duyck <alexander.h.duyck@linux.intel.com> > > > > > > Add support for the page reporting feature provided by virtio-balloon. > > > Reporting differs from the regular balloon functionality in that is is > > > much less durable than a standard memory balloon. Instead of creating a > > > list of pages that cannot be accessed the pages are only inaccessible > > > while they are being indicated to the virtio interface. Once the > > > interface has acknowledged them they are placed back into their respective > > > free lists and are once again accessible by the guest system. > > > > > > Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com> > > > --- > > > drivers/virtio/Kconfig | 1 + > > > drivers/virtio/virtio_balloon.c | 65 +++++++++++++++++++++++++++++++++++ > > > include/uapi/linux/virtio_balloon.h | 1 + > > > 3 files changed, 67 insertions(+) > > > > > > diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig > > > index 078615cf2afc..4b2dd8259ff5 100644 > > > --- a/drivers/virtio/Kconfig > > > +++ b/drivers/virtio/Kconfig > > > @@ -58,6 +58,7 @@ config VIRTIO_BALLOON > > > tristate "Virtio balloon driver" > > > depends on VIRTIO > > > select MEMORY_BALLOON > > > + select PAGE_REPORTING > > > ---help--- > > > This driver supports increasing and decreasing the amount > > > of memory within a KVM guest. > > > diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c > > > index 2c19457ab573..52f9eeda1877 100644 > > > --- a/drivers/virtio/virtio_balloon.c > > > +++ b/drivers/virtio/virtio_balloon.c > > > @@ -19,6 +19,7 @@ > > > #include <linux/mount.h> > > > #include <linux/magic.h> > > > #include <linux/pseudo_fs.h> > > > +#include <linux/page_reporting.h> > > > > > > /* > > > * Balloon device works in 4K page units. So each page is pointed to by > > > @@ -37,6 +38,9 @@ > > > #define VIRTIO_BALLOON_FREE_PAGE_SIZE \ > > > (1 << (VIRTIO_BALLOON_FREE_PAGE_ORDER + PAGE_SHIFT)) > > > > > > +/* limit on the number of pages that can be on the reporting vq */ > > > +#define VIRTIO_BALLOON_VRING_HINTS_MAX 16 > > > + > > > #ifdef CONFIG_BALLOON_COMPACTION > > > static struct vfsmount *balloon_mnt; > > > #endif > > > @@ -46,6 +50,7 @@ enum virtio_balloon_vq { > > > VIRTIO_BALLOON_VQ_DEFLATE, > > > VIRTIO_BALLOON_VQ_STATS, > > > VIRTIO_BALLOON_VQ_FREE_PAGE, > > > + VIRTIO_BALLOON_VQ_REPORTING, > > > VIRTIO_BALLOON_VQ_MAX > > > }; > > > > > > @@ -113,6 +118,10 @@ struct virtio_balloon { > > > > > > /* To register a shrinker to shrink memory upon memory pressure */ > > > struct shrinker shrinker; > > > + > > > + /* Unused page reporting device */ > > > + struct virtqueue *reporting_vq; > > > + struct page_reporting_dev_info ph_dev_info; > > > }; > > > > > > static struct virtio_device_id id_table[] = { > > > @@ -152,6 +161,32 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq) > > > > > > } > > > > > > +void virtballoon_unused_page_report(struct page_reporting_dev_info *ph_dev_info, > > > + unsigned int nents) > > > +{ > > > + struct virtio_balloon *vb = > > > + container_of(ph_dev_info, struct virtio_balloon, ph_dev_info); > > > + struct virtqueue *vq = vb->reporting_vq; > > > + unsigned int unused, err; > > > + > > > + /* We should always be able to add these buffers to an empty queue. */ > > > + err = virtqueue_add_inbuf(vq, ph_dev_info->sg, nents, vb, > > > + GFP_NOWAIT | __GFP_NOWARN); > > > + > > > + /* > > > + * In the extremely unlikely case that something has changed and we > > > + * are able to trigger an error we will simply display a warning > > > + * and exit without actually processing the pages. > > > + */ > > > + if (WARN_ON(err)) > > > + return; > > > + > > > + virtqueue_kick(vq); > > > + > > > + /* When host has read buffer, this completes via balloon_ack */ > > > + wait_event(vb->acked, virtqueue_get_buf(vq, &unused)); > > > +} > > > + > > > static void set_page_pfns(struct virtio_balloon *vb, > > > __virtio32 pfns[], struct page *page) > > > { > > > @@ -476,6 +511,7 @@ static int init_vqs(struct virtio_balloon *vb) > > > names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate"; > > > names[VIRTIO_BALLOON_VQ_STATS] = NULL; > > > names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; > > > + names[VIRTIO_BALLOON_VQ_REPORTING] = NULL; > > > > > > if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) { > > > names[VIRTIO_BALLOON_VQ_STATS] = "stats"; > > > @@ -487,11 +523,19 @@ static int init_vqs(struct virtio_balloon *vb) > > > callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; > > > } > > > > > > + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) { > > > + names[VIRTIO_BALLOON_VQ_REPORTING] = "reporting_vq"; > > > + callbacks[VIRTIO_BALLOON_VQ_REPORTING] = balloon_ack; > > > + } > > > + > > > err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX, > > > vqs, callbacks, names, NULL, NULL); > > > if (err) > > > return err; > > > > > > + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) > > > + vb->reporting_vq = vqs[VIRTIO_BALLOON_VQ_REPORTING]; > > > + > > > vb->inflate_vq = vqs[VIRTIO_BALLOON_VQ_INFLATE]; > > > vb->deflate_vq = vqs[VIRTIO_BALLOON_VQ_DEFLATE]; > > > if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) { > > > @@ -931,12 +975,30 @@ static int virtballoon_probe(struct virtio_device *vdev) > > > if (err) > > > goto out_del_balloon_wq; > > > } > > > + > > > + vb->ph_dev_info.report = virtballoon_unused_page_report; > > > + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) { > > > + unsigned int capacity; > > > + > > > + capacity = min_t(unsigned int, > > > + virtqueue_get_vring_size(vb->reporting_vq) - 1, > > > + VIRTIO_BALLOON_VRING_HINTS_MAX); > > > > Hmm why - 1 exactly? > > This might end up being 0 in the unusual configuration of vq size 1. > > Also, VIRTIO_BALLOON_VRING_HINTS_MAX is a power of 2 but > > virtqueue_get_vring_size(vb->reporting_vq) - 1 won't > > be if we are using split rings - donnu if that matters. > > Is a vq size of 1 valid? > Does that mean you can use that 1 descriptor? It seems to be according to the spec, and linux seems to accept that without issues, and only put 1 descriptor there. > Odds are I probably misunderstood the ring config in the other hinting > implementation. Looking it over now I guess it was adding one > additional entry for a command header and that was why it was > reserving one additional slot. I can update the code to drop the "- 1" > if the ring is capable of being fully utilized. > > Thanks. > > - Alex It should be. I just hacked qemu to have 1 descriptor sized ring and everything seems to work.
On Wed, Sep 4, 2019 at 3:44 AM Michael S. Tsirkin <mst@redhat.com> wrote: > > On Tue, Sep 03, 2019 at 07:13:32AM -0700, Alexander Duyck wrote: > > On Tue, Sep 3, 2019 at 12:32 AM Michael S. Tsirkin <mst@redhat.com> wrote: > > > > > > On Mon, Aug 12, 2019 at 02:33:56PM -0700, Alexander Duyck wrote: > > > > From: Alexander Duyck <alexander.h.duyck@linux.intel.com> > > > > > > > > Add support for the page reporting feature provided by virtio-balloon. > > > > Reporting differs from the regular balloon functionality in that is is > > > > much less durable than a standard memory balloon. Instead of creating a > > > > list of pages that cannot be accessed the pages are only inaccessible > > > > while they are being indicated to the virtio interface. Once the > > > > interface has acknowledged them they are placed back into their respective > > > > free lists and are once again accessible by the guest system. > > > > > > > > Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com> > > > > --- > > > > drivers/virtio/Kconfig | 1 + > > > > drivers/virtio/virtio_balloon.c | 65 +++++++++++++++++++++++++++++++++++ > > > > include/uapi/linux/virtio_balloon.h | 1 + > > > > 3 files changed, 67 insertions(+) > > > > > > > > diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig > > > > index 078615cf2afc..4b2dd8259ff5 100644 > > > > --- a/drivers/virtio/Kconfig > > > > +++ b/drivers/virtio/Kconfig > > > > @@ -58,6 +58,7 @@ config VIRTIO_BALLOON > > > > tristate "Virtio balloon driver" > > > > depends on VIRTIO > > > > select MEMORY_BALLOON > > > > + select PAGE_REPORTING > > > > ---help--- > > > > This driver supports increasing and decreasing the amount > > > > of memory within a KVM guest. > > > > diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c > > > > index 2c19457ab573..52f9eeda1877 100644 > > > > --- a/drivers/virtio/virtio_balloon.c > > > > +++ b/drivers/virtio/virtio_balloon.c > > > > @@ -19,6 +19,7 @@ > > > > #include <linux/mount.h> > > > > #include <linux/magic.h> > > > > #include <linux/pseudo_fs.h> > > > > +#include <linux/page_reporting.h> > > > > > > > > /* > > > > * Balloon device works in 4K page units. So each page is pointed to by > > > > @@ -37,6 +38,9 @@ > > > > #define VIRTIO_BALLOON_FREE_PAGE_SIZE \ > > > > (1 << (VIRTIO_BALLOON_FREE_PAGE_ORDER + PAGE_SHIFT)) > > > > > > > > +/* limit on the number of pages that can be on the reporting vq */ > > > > +#define VIRTIO_BALLOON_VRING_HINTS_MAX 16 > > > > + > > > > #ifdef CONFIG_BALLOON_COMPACTION > > > > static struct vfsmount *balloon_mnt; > > > > #endif > > > > @@ -46,6 +50,7 @@ enum virtio_balloon_vq { > > > > VIRTIO_BALLOON_VQ_DEFLATE, > > > > VIRTIO_BALLOON_VQ_STATS, > > > > VIRTIO_BALLOON_VQ_FREE_PAGE, > > > > + VIRTIO_BALLOON_VQ_REPORTING, > > > > VIRTIO_BALLOON_VQ_MAX > > > > }; > > > > > > > > @@ -113,6 +118,10 @@ struct virtio_balloon { > > > > > > > > /* To register a shrinker to shrink memory upon memory pressure */ > > > > struct shrinker shrinker; > > > > + > > > > + /* Unused page reporting device */ > > > > + struct virtqueue *reporting_vq; > > > > + struct page_reporting_dev_info ph_dev_info; > > > > }; > > > > > > > > static struct virtio_device_id id_table[] = { > > > > @@ -152,6 +161,32 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq) > > > > > > > > } > > > > > > > > +void virtballoon_unused_page_report(struct page_reporting_dev_info *ph_dev_info, > > > > + unsigned int nents) > > > > +{ > > > > + struct virtio_balloon *vb = > > > > + container_of(ph_dev_info, struct virtio_balloon, ph_dev_info); > > > > + struct virtqueue *vq = vb->reporting_vq; > > > > + unsigned int unused, err; > > > > + > > > > + /* We should always be able to add these buffers to an empty queue. */ > > > > + err = virtqueue_add_inbuf(vq, ph_dev_info->sg, nents, vb, > > > > + GFP_NOWAIT | __GFP_NOWARN); > > > > + > > > > + /* > > > > + * In the extremely unlikely case that something has changed and we > > > > + * are able to trigger an error we will simply display a warning > > > > + * and exit without actually processing the pages. > > > > + */ > > > > + if (WARN_ON(err)) > > > > + return; > > > > + > > > > + virtqueue_kick(vq); > > > > + > > > > + /* When host has read buffer, this completes via balloon_ack */ > > > > + wait_event(vb->acked, virtqueue_get_buf(vq, &unused)); > > > > +} > > > > + > > > > static void set_page_pfns(struct virtio_balloon *vb, > > > > __virtio32 pfns[], struct page *page) > > > > { > > > > @@ -476,6 +511,7 @@ static int init_vqs(struct virtio_balloon *vb) > > > > names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate"; > > > > names[VIRTIO_BALLOON_VQ_STATS] = NULL; > > > > names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; > > > > + names[VIRTIO_BALLOON_VQ_REPORTING] = NULL; > > > > > > > > if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) { > > > > names[VIRTIO_BALLOON_VQ_STATS] = "stats"; > > > > @@ -487,11 +523,19 @@ static int init_vqs(struct virtio_balloon *vb) > > > > callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; > > > > } > > > > > > > > + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) { > > > > + names[VIRTIO_BALLOON_VQ_REPORTING] = "reporting_vq"; > > > > + callbacks[VIRTIO_BALLOON_VQ_REPORTING] = balloon_ack; > > > > + } > > > > + > > > > err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX, > > > > vqs, callbacks, names, NULL, NULL); > > > > if (err) > > > > return err; > > > > > > > > + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) > > > > + vb->reporting_vq = vqs[VIRTIO_BALLOON_VQ_REPORTING]; > > > > + > > > > vb->inflate_vq = vqs[VIRTIO_BALLOON_VQ_INFLATE]; > > > > vb->deflate_vq = vqs[VIRTIO_BALLOON_VQ_DEFLATE]; > > > > if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) { > > > > @@ -931,12 +975,30 @@ static int virtballoon_probe(struct virtio_device *vdev) > > > > if (err) > > > > goto out_del_balloon_wq; > > > > } > > > > + > > > > + vb->ph_dev_info.report = virtballoon_unused_page_report; > > > > + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) { > > > > + unsigned int capacity; > > > > + > > > > + capacity = min_t(unsigned int, > > > > + virtqueue_get_vring_size(vb->reporting_vq) - 1, > > > > + VIRTIO_BALLOON_VRING_HINTS_MAX); > > > > > > Hmm why - 1 exactly? > > > This might end up being 0 in the unusual configuration of vq size 1. > > > Also, VIRTIO_BALLOON_VRING_HINTS_MAX is a power of 2 but > > > virtqueue_get_vring_size(vb->reporting_vq) - 1 won't > > > be if we are using split rings - donnu if that matters. > > > > Is a vq size of 1 valid? > > Does that mean you can use that 1 descriptor? > > It seems to be according to the spec, and linux seems to accept that > without issues, and only put 1 descriptor there. > > > Odds are I probably misunderstood the ring config in the other hinting > > implementation. Looking it over now I guess it was adding one > > additional entry for a command header and that was why it was > > reserving one additional slot. I can update the code to drop the "- 1" > > if the ring is capable of being fully utilized. > > > > Thanks. > > > > - Alex > > It should be. I just hacked qemu to have 1 descriptor sized ring > and everything seems to work. Okay. I will update the code to make the capacity equal to the vring size and max out oat HINTS_MAX. I also have a fix that will make sure we return an error if we attempt to enable the page hinting with a capacity of 0 just in case. I'll post the updated v7 later today. Thanks. - Alex
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 078615cf2afc..4b2dd8259ff5 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -58,6 +58,7 @@ config VIRTIO_BALLOON tristate "Virtio balloon driver" depends on VIRTIO select MEMORY_BALLOON + select PAGE_REPORTING ---help--- This driver supports increasing and decreasing the amount of memory within a KVM guest. diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 2c19457ab573..52f9eeda1877 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -19,6 +19,7 @@ #include <linux/mount.h> #include <linux/magic.h> #include <linux/pseudo_fs.h> +#include <linux/page_reporting.h> /* * Balloon device works in 4K page units. So each page is pointed to by @@ -37,6 +38,9 @@ #define VIRTIO_BALLOON_FREE_PAGE_SIZE \ (1 << (VIRTIO_BALLOON_FREE_PAGE_ORDER + PAGE_SHIFT)) +/* limit on the number of pages that can be on the reporting vq */ +#define VIRTIO_BALLOON_VRING_HINTS_MAX 16 + #ifdef CONFIG_BALLOON_COMPACTION static struct vfsmount *balloon_mnt; #endif @@ -46,6 +50,7 @@ enum virtio_balloon_vq { VIRTIO_BALLOON_VQ_DEFLATE, VIRTIO_BALLOON_VQ_STATS, VIRTIO_BALLOON_VQ_FREE_PAGE, + VIRTIO_BALLOON_VQ_REPORTING, VIRTIO_BALLOON_VQ_MAX }; @@ -113,6 +118,10 @@ struct virtio_balloon { /* To register a shrinker to shrink memory upon memory pressure */ struct shrinker shrinker; + + /* Unused page reporting device */ + struct virtqueue *reporting_vq; + struct page_reporting_dev_info ph_dev_info; }; static struct virtio_device_id id_table[] = { @@ -152,6 +161,32 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq) } +void virtballoon_unused_page_report(struct page_reporting_dev_info *ph_dev_info, + unsigned int nents) +{ + struct virtio_balloon *vb = + container_of(ph_dev_info, struct virtio_balloon, ph_dev_info); + struct virtqueue *vq = vb->reporting_vq; + unsigned int unused, err; + + /* We should always be able to add these buffers to an empty queue. */ + err = virtqueue_add_inbuf(vq, ph_dev_info->sg, nents, vb, + GFP_NOWAIT | __GFP_NOWARN); + + /* + * In the extremely unlikely case that something has changed and we + * are able to trigger an error we will simply display a warning + * and exit without actually processing the pages. + */ + if (WARN_ON(err)) + return; + + virtqueue_kick(vq); + + /* When host has read buffer, this completes via balloon_ack */ + wait_event(vb->acked, virtqueue_get_buf(vq, &unused)); +} + static void set_page_pfns(struct virtio_balloon *vb, __virtio32 pfns[], struct page *page) { @@ -476,6 +511,7 @@ static int init_vqs(struct virtio_balloon *vb) names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate"; names[VIRTIO_BALLOON_VQ_STATS] = NULL; names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; + names[VIRTIO_BALLOON_VQ_REPORTING] = NULL; if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) { names[VIRTIO_BALLOON_VQ_STATS] = "stats"; @@ -487,11 +523,19 @@ static int init_vqs(struct virtio_balloon *vb) callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; } + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) { + names[VIRTIO_BALLOON_VQ_REPORTING] = "reporting_vq"; + callbacks[VIRTIO_BALLOON_VQ_REPORTING] = balloon_ack; + } + err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX, vqs, callbacks, names, NULL, NULL); if (err) return err; + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) + vb->reporting_vq = vqs[VIRTIO_BALLOON_VQ_REPORTING]; + vb->inflate_vq = vqs[VIRTIO_BALLOON_VQ_INFLATE]; vb->deflate_vq = vqs[VIRTIO_BALLOON_VQ_DEFLATE]; if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) { @@ -931,12 +975,30 @@ static int virtballoon_probe(struct virtio_device *vdev) if (err) goto out_del_balloon_wq; } + + vb->ph_dev_info.report = virtballoon_unused_page_report; + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) { + unsigned int capacity; + + capacity = min_t(unsigned int, + virtqueue_get_vring_size(vb->reporting_vq) - 1, + VIRTIO_BALLOON_VRING_HINTS_MAX); + vb->ph_dev_info.capacity = capacity; + + err = page_reporting_startup(&vb->ph_dev_info); + if (err) + goto out_unregister_shrinker; + } + virtio_device_ready(vdev); if (towards_target(vb)) virtballoon_changed(vdev); return 0; +out_unregister_shrinker: + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) + virtio_balloon_unregister_shrinker(vb); out_del_balloon_wq: if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) destroy_workqueue(vb->balloon_wq); @@ -965,6 +1027,8 @@ static void virtballoon_remove(struct virtio_device *vdev) { struct virtio_balloon *vb = vdev->priv; + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) + page_reporting_shutdown(&vb->ph_dev_info); if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) virtio_balloon_unregister_shrinker(vb); spin_lock_irq(&vb->stop_update_lock); @@ -1034,6 +1098,7 @@ static int virtballoon_validate(struct virtio_device *vdev) VIRTIO_BALLOON_F_DEFLATE_ON_OOM, VIRTIO_BALLOON_F_FREE_PAGE_HINT, VIRTIO_BALLOON_F_PAGE_POISON, + VIRTIO_BALLOON_F_REPORTING, }; static struct virtio_driver virtio_balloon_driver = { diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h index a1966cd7b677..19974392d324 100644 --- a/include/uapi/linux/virtio_balloon.h +++ b/include/uapi/linux/virtio_balloon.h @@ -36,6 +36,7 @@ #define VIRTIO_BALLOON_F_DEFLATE_ON_OOM 2 /* Deflate balloon on OOM */ #define VIRTIO_BALLOON_F_FREE_PAGE_HINT 3 /* VQ to report free pages */ #define VIRTIO_BALLOON_F_PAGE_POISON 4 /* Guest is using page poisoning */ +#define VIRTIO_BALLOON_F_REPORTING 5 /* Page reporting virtqueue */ /* Size of a PFN in the balloon interface. */ #define VIRTIO_BALLOON_PFN_SHIFT 12