* [PATCH v24 2/2] virtio-balloon: VIRTIO_BALLOON_F_FREE_PAGE_HINT
From: Wei Wang @ 2018-01-24 10:42 UTC (permalink / raw)
To: virtio-dev, linux-kernel, virtualization, kvm, linux-mm, mst,
mhocko, akpm
Cc: yang.zhang.wz, riel, quan.xu0, liliang.opensource, pbonzini,
nilal
In-Reply-To: <1516790562-37889-1-git-send-email-wei.w.wang@intel.com>
Negotiation of the VIRTIO_BALLOON_F_FREE_PAGE_HINT feature indicates the
support of reporting hints of guest free pages to host via virtio-balloon.
Host requests the guest to report free pages by sending a new cmd
id to the guest via the free_page_report_cmd_id configuration register.
When the guest starts to report, the first element added to the free page
vq is the cmd id given by host. When the guest finishes the reporting
of all the free pages, VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID is added
to the vq to tell host that the reporting is done. Host may also requests
the guest to stop the reporting in advance by sending the stop cmd id to
the guest via the configuration register.
Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Signed-off-by: Liang Li <liang.z.li@intel.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
---
drivers/virtio/virtio_balloon.c | 265 +++++++++++++++++++++++++++++++-----
include/uapi/linux/virtio_balloon.h | 7 +
2 files changed, 236 insertions(+), 36 deletions(-)
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index a1fb52c..4440873 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -51,9 +51,21 @@ MODULE_PARM_DESC(oom_pages, "pages to free on OOM");
static struct vfsmount *balloon_mnt;
#endif
+/* The number of virtqueues supported by virtio-balloon */
+#define VIRTIO_BALLOON_VQ_NUM 4
+#define VIRTIO_BALLOON_VQ_ID_INFLATE 0
+#define VIRTIO_BALLOON_VQ_ID_DEFLATE 1
+#define VIRTIO_BALLOON_VQ_ID_STATS 2
+#define VIRTIO_BALLOON_VQ_ID_FREE_PAGE 3
+
struct virtio_balloon {
struct virtio_device *vdev;
- struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
+ struct virtqueue *inflate_vq, *deflate_vq, *stats_vq, *free_page_vq;
+
+ /* Balloon's own wq for cpu-intensive work items */
+ struct workqueue_struct *balloon_wq;
+ /* The free page reporting work item submitted to the balloon wq */
+ struct work_struct report_free_page_work;
/* The balloon servicing is delegated to a freezable workqueue. */
struct work_struct update_balloon_stats_work;
@@ -63,6 +75,13 @@ struct virtio_balloon {
spinlock_t stop_update_lock;
bool stop_update;
+ /* Start to report free pages */
+ bool report_free_page;
+ /* Stores the cmd id given by host to start the free page reporting */
+ __virtio32 start_cmd_id;
+ /* Stores STOP_ID as a sign to tell host that the reporting is done */
+ __virtio32 stop_cmd_id;
+
/* Waiting for host to ack the pages we released. */
wait_queue_head_t acked;
@@ -281,6 +300,53 @@ static unsigned int update_balloon_stats(struct virtio_balloon *vb)
return idx;
}
+static int add_one_sg(struct virtqueue *vq, unsigned long pfn, uint32_t len)
+{
+ struct scatterlist sg;
+ unsigned int unused;
+ int ret = 0;
+
+ sg_init_table(&sg, 1);
+ sg_set_page(&sg, pfn_to_page(pfn), len, 0);
+
+ /* Detach all the used buffers from the vq */
+ while (virtqueue_get_buf(vq, &unused))
+ ;
+
+ /*
+ * Since this is an optimization feature, losing a couple of free
+ * pages to report isn't important. We simply return without adding
+ * the page if the vq is full.
+ * We are adding one entry each time, which essentially results in no
+ * memory allocation, so the GFP_KERNEL flag below can be ignored.
+ * There is always one entry reserved for the cmd id to use.
+ */
+ if (vq->num_free > 1)
+ ret = virtqueue_add_inbuf(vq, &sg, 1, vq, GFP_KERNEL);
+
+ if (vq->num_free < virtqueue_get_vring_size(vq) / 2)
+ virtqueue_kick(vq);
+
+ return ret;
+}
+
+static void send_cmd_id(struct virtio_balloon *vb, __virtio32 *cmd_id)
+{
+ struct scatterlist sg;
+ struct virtqueue *vq = vb->free_page_vq;
+
+ if (unlikely(!virtio_has_feature(vb->vdev,
+ VIRTIO_BALLOON_F_FREE_PAGE_HINT)))
+ return;
+
+ sg_init_one(&sg, cmd_id, sizeof(*cmd_id));
+
+ if (virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL))
+ __virtio_clear_bit(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT);
+
+ virtqueue_kick(vq);
+}
+
/*
* While most virtqueues communicate guest-initiated requests to the hypervisor,
* the stats queue operates in reverse. The driver initializes the virtqueue
@@ -316,17 +382,6 @@ static void stats_handle_request(struct virtio_balloon *vb)
virtqueue_kick(vq);
}
-static void virtballoon_changed(struct virtio_device *vdev)
-{
- struct virtio_balloon *vb = vdev->priv;
- unsigned long flags;
-
- spin_lock_irqsave(&vb->stop_update_lock, flags);
- if (!vb->stop_update)
- queue_work(system_freezable_wq, &vb->update_balloon_size_work);
- spin_unlock_irqrestore(&vb->stop_update_lock, flags);
-}
-
static inline s64 towards_target(struct virtio_balloon *vb)
{
s64 target;
@@ -343,6 +398,49 @@ static inline s64 towards_target(struct virtio_balloon *vb)
return target - vb->num_pages;
}
+static void virtballoon_changed(struct virtio_device *vdev)
+{
+ struct virtio_balloon *vb = vdev->priv;
+ unsigned long flags;
+ __u32 cmd_id;
+ s64 diff = towards_target(vb);
+
+ if (diff) {
+ spin_lock_irqsave(&vb->stop_update_lock, flags);
+ if (!vb->stop_update)
+ queue_work(system_freezable_wq,
+ &vb->update_balloon_size_work);
+ spin_unlock_irqrestore(&vb->stop_update_lock, flags);
+ }
+
+ if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+ virtio_cread(vdev, struct virtio_balloon_config,
+ free_page_report_cmd_id, &cmd_id);
+ if (cmd_id == VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID) {
+ vb->report_free_page = false;
+ } else {
+ /*
+ * The request is queued only when the ack of the
+ * previous request has been sent to host, which is
+ * indicated by start_cmd_id set to
+ * VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID. Otherwise,
+ * simply update the start_cmd_id, and when the
+ * previous queued work runs, the latest cmd id will
+ * be sent to host.
+ */
+ spin_lock_irqsave(&vb->stop_update_lock, flags);
+ if (!vb->stop_update &&
+ virtio32_to_cpu(vdev, vb->start_cmd_id) ==
+ VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID)
+ queue_work(vb->balloon_wq,
+ &vb->report_free_page_work);
+ vb->report_free_page = true;
+ vb->start_cmd_id = cpu_to_virtio32(vdev, cmd_id);
+ spin_unlock_irqrestore(&vb->stop_update_lock, flags);
+ }
+ }
+}
+
static void update_balloon_size(struct virtio_balloon *vb)
{
u32 actual = vb->num_pages;
@@ -417,42 +515,108 @@ static void update_balloon_size_func(struct work_struct *work)
static int init_vqs(struct virtio_balloon *vb)
{
- struct virtqueue *vqs[3];
- vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
- static const char * const names[] = { "inflate", "deflate", "stats" };
- int err, nvqs;
+ struct virtqueue *vqs[VIRTIO_BALLOON_VQ_NUM];
+ vq_callback_t *callbacks[VIRTIO_BALLOON_VQ_NUM];
+ const char *names[VIRTIO_BALLOON_VQ_NUM];
+ struct scatterlist sg;
+ int ret;
/*
- * We expect two virtqueues: inflate and deflate, and
- * optionally stat.
+ * Inflateq and deflateq are used unconditionally. The names[]
+ * will be NULL if the related feature is not enabled, which will
+ * cause no allocation for the corresponding virtqueue in find_vqs.
*/
- nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
- err = virtio_find_vqs(vb->vdev, nvqs, vqs, callbacks, names, NULL);
- if (err)
- return err;
+ callbacks[VIRTIO_BALLOON_VQ_ID_INFLATE] = balloon_ack;
+ names[VIRTIO_BALLOON_VQ_ID_INFLATE] = "inflate";
+ callbacks[VIRTIO_BALLOON_VQ_ID_DEFLATE] = balloon_ack;
+ names[VIRTIO_BALLOON_VQ_ID_DEFLATE] = "deflate";
+ names[VIRTIO_BALLOON_VQ_ID_STATS] = NULL;
+ names[VIRTIO_BALLOON_VQ_ID_FREE_PAGE] = NULL;
- vb->inflate_vq = vqs[0];
- vb->deflate_vq = vqs[1];
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
- struct scatterlist sg;
- unsigned int num_stats;
- vb->stats_vq = vqs[2];
+ names[VIRTIO_BALLOON_VQ_ID_STATS] = "stats";
+ callbacks[VIRTIO_BALLOON_VQ_ID_STATS] = stats_request;
+ }
+
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+ names[VIRTIO_BALLOON_VQ_ID_FREE_PAGE] = "free_page_vq";
+ callbacks[VIRTIO_BALLOON_VQ_ID_FREE_PAGE] = NULL;
+ }
+
+ ret = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_NUM,
+ vqs, callbacks, names, NULL, NULL);
+ if (ret)
+ return ret;
+ vb->inflate_vq = vqs[VIRTIO_BALLOON_VQ_ID_INFLATE];
+ vb->deflate_vq = vqs[VIRTIO_BALLOON_VQ_ID_DEFLATE];
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
+ vb->stats_vq = vqs[VIRTIO_BALLOON_VQ_ID_STATS];
/*
* Prime this virtqueue with one buffer so the hypervisor can
* use it to signal us later (it can't be broken yet!).
*/
- num_stats = update_balloon_stats(vb);
-
- sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
- if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL)
- < 0)
- BUG();
+ sg_init_one(&sg, vb->stats, sizeof(vb->stats));
+ ret = virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb,
+ GFP_KERNEL);
+ if (ret) {
+ dev_warn(&vb->vdev->dev, "%s: add stat_vq failed\n",
+ __func__);
+ return ret;
+ }
virtqueue_kick(vb->stats_vq);
}
+
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
+ vb->free_page_vq = vqs[VIRTIO_BALLOON_VQ_ID_FREE_PAGE];
+
return 0;
}
+static bool virtio_balloon_send_free_pages(void *opaque, unsigned long pfn,
+ unsigned long nr_pages)
+{
+ struct virtio_balloon *vb = (struct virtio_balloon *)opaque;
+ uint32_t len = nr_pages << PAGE_SHIFT;
+ int ret;
+
+ if (!vb->report_free_page ||
+ unlikely(!virtio_has_feature(vb->vdev,
+ VIRTIO_BALLOON_F_FREE_PAGE_HINT)))
+ return false;
+
+ ret = add_one_sg(vb->free_page_vq, pfn, len);
+ if (unlikely(ret))
+ __virtio_clear_bit(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT);
+
+ return !ret;
+}
+
+static void report_free_page_func(struct work_struct *work)
+{
+ struct virtio_balloon *vb;
+ unsigned long flags;
+
+ vb = container_of(work, struct virtio_balloon, report_free_page_work);
+
+ /* Start by sending the obtained cmd id to the host with an outbuf */
+ send_cmd_id(vb, &vb->start_cmd_id);
+
+ /*
+ * Set start_cmd_id to VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID to
+ * indicate a new request can be queued.
+ */
+ spin_lock_irqsave(&vb->stop_update_lock, flags);
+ vb->start_cmd_id = cpu_to_virtio32(vb->vdev,
+ VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID);
+ spin_unlock_irqrestore(&vb->stop_update_lock, flags);
+
+ walk_free_mem_block(vb, 0, &virtio_balloon_send_free_pages);
+
+ /* End by sending the stop id to the host with an outbuf */
+ send_cmd_id(vb, &vb->stop_cmd_id);
+}
+
#ifdef CONFIG_BALLOON_COMPACTION
/*
* virtballoon_migratepage - perform the balloon page migration on behalf of
@@ -537,6 +701,7 @@ static struct file_system_type balloon_fs = {
static int virtballoon_probe(struct virtio_device *vdev)
{
struct virtio_balloon *vb;
+ __u32 poison_val;
int err;
if (!vdev->config->get) {
@@ -566,18 +731,37 @@ static int virtballoon_probe(struct virtio_device *vdev)
if (err)
goto out_free_vb;
+ if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+ vb->balloon_wq = alloc_workqueue("balloon-wq",
+ WQ_FREEZABLE | WQ_CPU_INTENSIVE, 0);
+ if (!vb->balloon_wq) {
+ err = -ENOMEM;
+ goto out_del_vqs;
+ }
+ INIT_WORK(&vb->report_free_page_work, report_free_page_func);
+ vb->start_cmd_id = cpu_to_virtio32(vdev,
+ VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID);
+ vb->stop_cmd_id = cpu_to_virtio32(vdev,
+ VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID);
+ if(virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) {
+ poison_val = PAGE_POISON;
+ virtio_cwrite(vb->vdev, struct virtio_balloon_config,
+ poison_val, &poison_val);
+ }
+ }
+
vb->nb.notifier_call = virtballoon_oom_notify;
vb->nb.priority = VIRTBALLOON_OOM_NOTIFY_PRIORITY;
err = register_oom_notifier(&vb->nb);
if (err < 0)
- goto out_del_vqs;
+ goto out_del_balloon_wq;
#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;
+ goto out_del_balloon_wq;
}
vb->vb_dev_info.migratepage = virtballoon_migratepage;
@@ -587,7 +771,7 @@ static int virtballoon_probe(struct virtio_device *vdev)
kern_unmount(balloon_mnt);
unregister_oom_notifier(&vb->nb);
vb->vb_dev_info.inode = NULL;
- goto out_del_vqs;
+ goto out_del_balloon_wq;
}
vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
#endif
@@ -598,6 +782,8 @@ static int virtballoon_probe(struct virtio_device *vdev)
virtballoon_changed(vdev);
return 0;
+out_del_balloon_wq:
+ destroy_workqueue(vb->balloon_wq);
out_del_vqs:
vdev->config->del_vqs(vdev);
out_free_vb:
@@ -630,6 +816,8 @@ static void virtballoon_remove(struct virtio_device *vdev)
spin_unlock_irq(&vb->stop_update_lock);
cancel_work_sync(&vb->update_balloon_size_work);
cancel_work_sync(&vb->update_balloon_stats_work);
+ cancel_work_sync(&vb->report_free_page_work);
+ destroy_workqueue(vb->balloon_wq);
remove_common(vb);
#ifdef CONFIG_BALLOON_COMPACTION
@@ -674,6 +862,9 @@ static int virtballoon_restore(struct virtio_device *vdev)
static int virtballoon_validate(struct virtio_device *vdev)
{
+ if (!page_poisoning_enabled())
+ __virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON);
+
__virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM);
return 0;
}
@@ -682,6 +873,8 @@ static unsigned int features[] = {
VIRTIO_BALLOON_F_MUST_TELL_HOST,
VIRTIO_BALLOON_F_STATS_VQ,
VIRTIO_BALLOON_F_DEFLATE_ON_OOM,
+ VIRTIO_BALLOON_F_FREE_PAGE_HINT,
+ VIRTIO_BALLOON_F_PAGE_POISON,
};
static struct virtio_driver virtio_balloon_driver = {
diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h
index 343d7dd..3f97067 100644
--- a/include/uapi/linux/virtio_balloon.h
+++ b/include/uapi/linux/virtio_balloon.h
@@ -34,15 +34,22 @@
#define VIRTIO_BALLOON_F_MUST_TELL_HOST 0 /* Tell before reclaiming pages */
#define VIRTIO_BALLOON_F_STATS_VQ 1 /* Memory Stats virtqueue */
#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 */
/* Size of a PFN in the balloon interface. */
#define VIRTIO_BALLOON_PFN_SHIFT 12
+#define VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID 0
struct virtio_balloon_config {
/* Number of pages host wants Guest to give up. */
__u32 num_pages;
/* Number of pages we've actually got in balloon. */
__u32 actual;
+ /* Free page report command id, readonly by guest */
+ __u32 free_page_report_cmd_id;
+ /* Stores PAGE_POISON if page poisoning is in use */
+ __u32 poison_val;
};
#define VIRTIO_BALLOON_S_SWAP_IN 0 /* Amount of memory swapped in */
--
2.7.4
^ permalink raw reply related
* Re: [virtio-dev] Re: [PATCH v22 2/3] virtio-balloon: VIRTIO_BALLOON_F_FREE_PAGE_VQ
From: Wei Wang @ 2018-01-24 11:28 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: yang.zhang.wz, virtio-dev, riel, quan.xu0, kvm, nilal,
liliang.opensource, linux-kernel, mhocko, linux-mm, pbonzini,
akpm, virtualization
In-Reply-To: <20180124062723-mutt-send-email-mst@kernel.org>
On 01/24/2018 12:29 PM, Michael S. Tsirkin wrote:
> On Mon, Jan 22, 2018 at 07:25:45PM +0800, Wei Wang wrote:
>> On 01/19/2018 08:39 PM, Michael S. Tsirkin wrote:
>>> On Fri, Jan 19, 2018 at 11:44:21AM +0800, Wei Wang wrote:
>>>> On 01/18/2018 12:44 AM, Michael S. Tsirkin wrote:
>>>>> On Wed, Jan 17, 2018 at 01:10:11PM +0800, Wei Wang wrote:
>>>>>
>>>>>> + vb->start_cmd_id = cmd_id;
>>>>>> + queue_work(vb->balloon_wq, &vb->report_free_page_work);
>>>>> It seems that if a command was already queued (with a different id),
>>>>> this will result in new command id being sent to host twice, which will
>>>>> likely confuse the host.
>>>> I think that case won't happen, because
>>>> - the host sends a cmd id to the guest via the config, while the guest acks
>>>> back the received cmd id via the virtqueue;
>>>> - the guest ack back a cmd id only when a new cmd id is received from the
>>>> host, that is the above check:
>>>>
>>>> if (cmd_id != vb->start_cmd_id) { --> the driver only queues the
>>>> reporting work only when a new cmd id is received
>>>> /*
>>>> * Host requests to start the reporting by sending a
>>>> * new cmd id.
>>>> */
>>>> WRITE_ONCE(vb->report_free_page, true);
>>>> vb->start_cmd_id = cmd_id;
>>>> queue_work(vb->balloon_wq,
>>>> &vb->report_free_page_work);
>>>> }
>>>>
>>>> So the same cmd id wouldn't queue the reporting work twice.
>>>>
>>> Like this:
>>>
>>> vb->start_cmd_id = cmd_id;
>>> queue_work(vb->balloon_wq, &vb->report_free_page_work);
>>>
>>> command id changes
>>>
>>> vb->start_cmd_id = cmd_id;
>>>
>>> work executes
>>>
>>> queue_work(vb->balloon_wq, &vb->report_free_page_work);
>>>
>>> work executes again
>>>
>> If we think about the whole working flow, I think this case couldn't happen:
>>
>> 1) device send cmd_id=1 to driver;
>> 2) driver receives cmd_id=1 in the config and acks cmd_id=1 to the device
>> via the vq;
>> 3) device revives cmd_id=1;
>> 4) device wants to stop the reporting by sending cmd_id=STOP;
>> 5) driver receives cmd_id=STOP from the config, and acks cmd_id=STOP to the
>> device via the vq;
>> 6) device sends cmd_id=2 to driver;
>> ...
>>
>> cmd_id=2 won't come after cmd_id=1, there will be a STOP cmd in between them
>> (STOP won't queue the work).
>>
>> How about defining the correct device behavior in the spec:
>> The device Should NOT send a second cmd id to the driver until a STOP cmd
>> ack for the previous cmd id has been received from the guest.
>>
>>
>> Best,
>> Wei
> I think we should just fix races in the driver rather than introduce
> random restrictions in the device.
>
> If device wants to start a new sequence, it should be able to
> do just that without a complicated back and forth with several
> roundtrips through the driver.
>
OK, I've fixed it in the new version, v24. Please have a check there.
Thanks.
(Other changes based on the comments on v23 have also been included)
Best,
Wei
^ permalink raw reply
* Re: [PATCH v24 2/2] virtio-balloon: VIRTIO_BALLOON_F_FREE_PAGE_HINT
From: Michael S. Tsirkin @ 2018-01-24 17:15 UTC (permalink / raw)
To: Wei Wang
Cc: yang.zhang.wz, virtio-dev, riel, quan.xu0, kvm, nilal,
liliang.opensource, linux-kernel, mhocko, linux-mm, pbonzini,
akpm, virtualization
In-Reply-To: <1516790562-37889-3-git-send-email-wei.w.wang@intel.com>
On Wed, Jan 24, 2018 at 06:42:42PM +0800, Wei Wang wrote:
> Negotiation of the VIRTIO_BALLOON_F_FREE_PAGE_HINT feature indicates the
> support of reporting hints of guest free pages to host via virtio-balloon.
>
> Host requests the guest to report free pages by sending a new cmd
> id to the guest via the free_page_report_cmd_id configuration register.
>
> When the guest starts to report, the first element added to the free page
> vq is the cmd id given by host. When the guest finishes the reporting
> of all the free pages, VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID is added
> to the vq to tell host that the reporting is done. Host may also requests
> the guest to stop the reporting in advance by sending the stop cmd id to
> the guest via the configuration register.
>
> Signed-off-by: Wei Wang <wei.w.wang@intel.com>
> Signed-off-by: Liang Li <liang.z.li@intel.com>
> Cc: Michael S. Tsirkin <mst@redhat.com>
> Cc: Michal Hocko <mhocko@kernel.org>
> ---
> drivers/virtio/virtio_balloon.c | 265 +++++++++++++++++++++++++++++++-----
> include/uapi/linux/virtio_balloon.h | 7 +
> 2 files changed, 236 insertions(+), 36 deletions(-)
>
> diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
> index a1fb52c..4440873 100644
> --- a/drivers/virtio/virtio_balloon.c
> +++ b/drivers/virtio/virtio_balloon.c
> @@ -51,9 +51,21 @@ MODULE_PARM_DESC(oom_pages, "pages to free on OOM");
> static struct vfsmount *balloon_mnt;
> #endif
>
> +/* The number of virtqueues supported by virtio-balloon */
> +#define VIRTIO_BALLOON_VQ_NUM 4
> +#define VIRTIO_BALLOON_VQ_ID_INFLATE 0
> +#define VIRTIO_BALLOON_VQ_ID_DEFLATE 1
> +#define VIRTIO_BALLOON_VQ_ID_STATS 2
> +#define VIRTIO_BALLOON_VQ_ID_FREE_PAGE 3
> +
Please do an enum instead of defines. VQ_ID can be just VQ
(it's not an ID, it's just the number).
> struct virtio_balloon {
> struct virtio_device *vdev;
> - struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
> + struct virtqueue *inflate_vq, *deflate_vq, *stats_vq, *free_page_vq;
> +
> + /* Balloon's own wq for cpu-intensive work items */
> + struct workqueue_struct *balloon_wq;
> + /* The free page reporting work item submitted to the balloon wq */
> + struct work_struct report_free_page_work;
>
> /* The balloon servicing is delegated to a freezable workqueue. */
> struct work_struct update_balloon_stats_work;
> @@ -63,6 +75,13 @@ struct virtio_balloon {
> spinlock_t stop_update_lock;
> bool stop_update;
>
> + /* Start to report free pages */
> + bool report_free_page;
> + /* Stores the cmd id given by host to start the free page reporting */
> + __virtio32 start_cmd_id;
> + /* Stores STOP_ID as a sign to tell host that the reporting is done */
> + __virtio32 stop_cmd_id;
> +
> /* Waiting for host to ack the pages we released. */
> wait_queue_head_t acked;
>
> @@ -281,6 +300,53 @@ static unsigned int update_balloon_stats(struct virtio_balloon *vb)
> return idx;
> }
>
> +static int add_one_sg(struct virtqueue *vq, unsigned long pfn, uint32_t len)
> +{
> + struct scatterlist sg;
> + unsigned int unused;
> + int ret = 0;
> +
> + sg_init_table(&sg, 1);
> + sg_set_page(&sg, pfn_to_page(pfn), len, 0);
> +
> + /* Detach all the used buffers from the vq */
> + while (virtqueue_get_buf(vq, &unused))
> + ;
> +
> + /*
> + * Since this is an optimization feature, losing a couple of free
> + * pages to report isn't important. We simply return without adding
> + * the page if the vq is full.
> + * We are adding one entry each time, which essentially results in no
> + * memory allocation, so the GFP_KERNEL flag below can be ignored.
> + * There is always one entry reserved for the cmd id to use.
> + */
> + if (vq->num_free > 1)
> + ret = virtqueue_add_inbuf(vq, &sg, 1, vq, GFP_KERNEL);
> +
> + if (vq->num_free < virtqueue_get_vring_size(vq) / 2)
> + virtqueue_kick(vq);
> +
> + return ret;
> +}
> +
> +static void send_cmd_id(struct virtio_balloon *vb, __virtio32 *cmd_id)
> +{
> + struct scatterlist sg;
> + struct virtqueue *vq = vb->free_page_vq;
> +
> + if (unlikely(!virtio_has_feature(vb->vdev,
> + VIRTIO_BALLOON_F_FREE_PAGE_HINT)))
> + return;
> +
> + sg_init_one(&sg, cmd_id, sizeof(*cmd_id));
> +
> + if (virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL))
> + __virtio_clear_bit(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT);
What is this doing? Basically handling the case where vq is broken?
It's kind of ugly to tweak feature bits, most code assumes they never
change. Please just return an error to caller instead and handle it
there.
You can then avoid sprinking the check for the feature bit
all over the code.
> +
> + virtqueue_kick(vq);
> +}
> +
> /*
> * While most virtqueues communicate guest-initiated requests to the hypervisor,
> * the stats queue operates in reverse. The driver initializes the virtqueue
> @@ -316,17 +382,6 @@ static void stats_handle_request(struct virtio_balloon *vb)
> virtqueue_kick(vq);
> }
>
> -static void virtballoon_changed(struct virtio_device *vdev)
> -{
> - struct virtio_balloon *vb = vdev->priv;
> - unsigned long flags;
> -
> - spin_lock_irqsave(&vb->stop_update_lock, flags);
> - if (!vb->stop_update)
> - queue_work(system_freezable_wq, &vb->update_balloon_size_work);
> - spin_unlock_irqrestore(&vb->stop_update_lock, flags);
> -}
> -
> static inline s64 towards_target(struct virtio_balloon *vb)
> {
> s64 target;
> @@ -343,6 +398,49 @@ static inline s64 towards_target(struct virtio_balloon *vb)
> return target - vb->num_pages;
> }
>
> +static void virtballoon_changed(struct virtio_device *vdev)
> +{
> + struct virtio_balloon *vb = vdev->priv;
> + unsigned long flags;
> + __u32 cmd_id;
> + s64 diff = towards_target(vb);
> +
> + if (diff) {
> + spin_lock_irqsave(&vb->stop_update_lock, flags);
> + if (!vb->stop_update)
> + queue_work(system_freezable_wq,
> + &vb->update_balloon_size_work);
> + spin_unlock_irqrestore(&vb->stop_update_lock, flags);
> + }
> +
> + if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
> + virtio_cread(vdev, struct virtio_balloon_config,
> + free_page_report_cmd_id, &cmd_id);
> + if (cmd_id == VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID) {
> + vb->report_free_page = false;
> + } else {
> + /*
> + * The request is queued only when the ack of the
> + * previous request has been sent to host, which is
> + * indicated by start_cmd_id set to
> + * VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID. Otherwise,
> + * simply update the start_cmd_id, and when the
> + * previous queued work runs, the latest cmd id will
> + * be sent to host.
> + */
One thing I don't like about this one is that the previous request
will still try to run to completion.
And it all seems pretty complex.
How about:
- pass cmd id to a queued work
- queued work gets that cmd id, stores a copy and uses that,
re-checking periodically - stop if cmd id changes:
will replace report_free_page too since that's set to
stop.
This means you do not reuse the queued cmd id also
for the buffer - which is probably for the best.
> + spin_lock_irqsave(&vb->stop_update_lock, flags);
> + if (!vb->stop_update &&
> + virtio32_to_cpu(vdev, vb->start_cmd_id) ==
> + VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID)
> + queue_work(vb->balloon_wq,
> + &vb->report_free_page_work);
> + vb->report_free_page = true;
> + vb->start_cmd_id = cpu_to_virtio32(vdev, cmd_id);
> + spin_unlock_irqrestore(&vb->stop_update_lock, flags);
While it's ok to set cmd id here because of the lock, it is easier
to understand code if you set up everything before you queue the
command.
> + }
> + }
> +}
> +
> static void update_balloon_size(struct virtio_balloon *vb)
> {
> u32 actual = vb->num_pages;
> @@ -417,42 +515,108 @@ static void update_balloon_size_func(struct work_struct *work)
>
> static int init_vqs(struct virtio_balloon *vb)
> {
> - struct virtqueue *vqs[3];
> - vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
> - static const char * const names[] = { "inflate", "deflate", "stats" };
> - int err, nvqs;
> + struct virtqueue *vqs[VIRTIO_BALLOON_VQ_NUM];
> + vq_callback_t *callbacks[VIRTIO_BALLOON_VQ_NUM];
> + const char *names[VIRTIO_BALLOON_VQ_NUM];
> + struct scatterlist sg;
> + int ret;
>
> /*
> - * We expect two virtqueues: inflate and deflate, and
> - * optionally stat.
> + * Inflateq and deflateq are used unconditionally. The names[]
> + * will be NULL if the related feature is not enabled, which will
> + * cause no allocation for the corresponding virtqueue in find_vqs.
> */
> - nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
> - err = virtio_find_vqs(vb->vdev, nvqs, vqs, callbacks, names, NULL);
> - if (err)
> - return err;
> + callbacks[VIRTIO_BALLOON_VQ_ID_INFLATE] = balloon_ack;
> + names[VIRTIO_BALLOON_VQ_ID_INFLATE] = "inflate";
> + callbacks[VIRTIO_BALLOON_VQ_ID_DEFLATE] = balloon_ack;
> + names[VIRTIO_BALLOON_VQ_ID_DEFLATE] = "deflate";
> + names[VIRTIO_BALLOON_VQ_ID_STATS] = NULL;
> + names[VIRTIO_BALLOON_VQ_ID_FREE_PAGE] = NULL;
>
> - vb->inflate_vq = vqs[0];
> - vb->deflate_vq = vqs[1];
> if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
> - struct scatterlist sg;
> - unsigned int num_stats;
> - vb->stats_vq = vqs[2];
> + names[VIRTIO_BALLOON_VQ_ID_STATS] = "stats";
> + callbacks[VIRTIO_BALLOON_VQ_ID_STATS] = stats_request;
> + }
> +
> + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
> + names[VIRTIO_BALLOON_VQ_ID_FREE_PAGE] = "free_page_vq";
> + callbacks[VIRTIO_BALLOON_VQ_ID_FREE_PAGE] = NULL;
> + }
> +
> + ret = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_NUM,
> + vqs, callbacks, names, NULL, NULL);
> + if (ret)
> + return ret;
>
> + vb->inflate_vq = vqs[VIRTIO_BALLOON_VQ_ID_INFLATE];
> + vb->deflate_vq = vqs[VIRTIO_BALLOON_VQ_ID_DEFLATE];
> + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
> + vb->stats_vq = vqs[VIRTIO_BALLOON_VQ_ID_STATS];
> /*
> * Prime this virtqueue with one buffer so the hypervisor can
> * use it to signal us later (it can't be broken yet!).
> */
> - num_stats = update_balloon_stats(vb);
> -
> - sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
> - if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL)
> - < 0)
> - BUG();
> + sg_init_one(&sg, vb->stats, sizeof(vb->stats));
> + ret = virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb,
> + GFP_KERNEL);
> + if (ret) {
> + dev_warn(&vb->vdev->dev, "%s: add stat_vq failed\n",
> + __func__);
> + return ret;
> + }
> virtqueue_kick(vb->stats_vq);
> }
> +
> + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
> + vb->free_page_vq = vqs[VIRTIO_BALLOON_VQ_ID_FREE_PAGE];
> +
> return 0;
> }
>
> +static bool virtio_balloon_send_free_pages(void *opaque, unsigned long pfn,
> + unsigned long nr_pages)
> +{
> + struct virtio_balloon *vb = (struct virtio_balloon *)opaque;
> + uint32_t len = nr_pages << PAGE_SHIFT;
> + int ret;
> +
> + if (!vb->report_free_page ||
> + unlikely(!virtio_has_feature(vb->vdev,
> + VIRTIO_BALLOON_F_FREE_PAGE_HINT)))
> + return false;
> +
> + ret = add_one_sg(vb->free_page_vq, pfn, len);
> + if (unlikely(ret))
> + __virtio_clear_bit(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT);
> +
> + return !ret;
> +}
> +
> +static void report_free_page_func(struct work_struct *work)
> +{
> + struct virtio_balloon *vb;
> + unsigned long flags;
> +
> + vb = container_of(work, struct virtio_balloon, report_free_page_work);
> +
> + /* Start by sending the obtained cmd id to the host with an outbuf */
> + send_cmd_id(vb, &vb->start_cmd_id);
> +
> + /*
> + * Set start_cmd_id to VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID to
> + * indicate a new request can be queued.
> + */
> + spin_lock_irqsave(&vb->stop_update_lock, flags);
> + vb->start_cmd_id = cpu_to_virtio32(vb->vdev,
> + VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID);
> + spin_unlock_irqrestore(&vb->stop_update_lock, flags);
> +
> + walk_free_mem_block(vb, 0, &virtio_balloon_send_free_pages);
Can you teach walk_free_mem_block to return the && of all
return calls, so caller knows whether it completed?
> +
> + /* End by sending the stop id to the host with an outbuf */
> + send_cmd_id(vb, &vb->stop_cmd_id);
> +}
> +
> #ifdef CONFIG_BALLOON_COMPACTION
> /*
> * virtballoon_migratepage - perform the balloon page migration on behalf of
> @@ -537,6 +701,7 @@ static struct file_system_type balloon_fs = {
> static int virtballoon_probe(struct virtio_device *vdev)
> {
> struct virtio_balloon *vb;
> + __u32 poison_val;
> int err;
>
> if (!vdev->config->get) {
> @@ -566,18 +731,37 @@ static int virtballoon_probe(struct virtio_device *vdev)
> if (err)
> goto out_free_vb;
>
> + if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
> + vb->balloon_wq = alloc_workqueue("balloon-wq",
> + WQ_FREEZABLE | WQ_CPU_INTENSIVE, 0);
balloon_wq is initialized conditionally here but destroyed
unconditionally below. That will crash when not initialized
I think.
> + if (!vb->balloon_wq) {
> + err = -ENOMEM;
> + goto out_del_vqs;
> + }
> + INIT_WORK(&vb->report_free_page_work, report_free_page_func);
> + vb->start_cmd_id = cpu_to_virtio32(vdev,
> + VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID);
> + vb->stop_cmd_id = cpu_to_virtio32(vdev,
> + VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID);
> + if(virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) {
> + poison_val = PAGE_POISON;
> + virtio_cwrite(vb->vdev, struct virtio_balloon_config,
> + poison_val, &poison_val);
> + }
> + }
> +
> vb->nb.notifier_call = virtballoon_oom_notify;
> vb->nb.priority = VIRTBALLOON_OOM_NOTIFY_PRIORITY;
> err = register_oom_notifier(&vb->nb);
> if (err < 0)
> - goto out_del_vqs;
> + goto out_del_balloon_wq;
>
> #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;
> + goto out_del_balloon_wq;
> }
>
> vb->vb_dev_info.migratepage = virtballoon_migratepage;
> @@ -587,7 +771,7 @@ static int virtballoon_probe(struct virtio_device *vdev)
> kern_unmount(balloon_mnt);
> unregister_oom_notifier(&vb->nb);
> vb->vb_dev_info.inode = NULL;
> - goto out_del_vqs;
> + goto out_del_balloon_wq;
> }
> vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
> #endif
> @@ -598,6 +782,8 @@ static int virtballoon_probe(struct virtio_device *vdev)
> virtballoon_changed(vdev);
> return 0;
>
> +out_del_balloon_wq:
> + destroy_workqueue(vb->balloon_wq);
> out_del_vqs:
> vdev->config->del_vqs(vdev);
> out_free_vb:
> @@ -630,6 +816,8 @@ static void virtballoon_remove(struct virtio_device *vdev)
> spin_unlock_irq(&vb->stop_update_lock);
> cancel_work_sync(&vb->update_balloon_size_work);
> cancel_work_sync(&vb->update_balloon_stats_work);
> + cancel_work_sync(&vb->report_free_page_work);
> + destroy_workqueue(vb->balloon_wq);
>
> remove_common(vb);
> #ifdef CONFIG_BALLOON_COMPACTION
> @@ -674,6 +862,9 @@ static int virtballoon_restore(struct virtio_device *vdev)
>
> static int virtballoon_validate(struct virtio_device *vdev)
> {
> + if (!page_poisoning_enabled())
> + __virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON);
> +
> __virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM);
> return 0;
> }
> @@ -682,6 +873,8 @@ static unsigned int features[] = {
> VIRTIO_BALLOON_F_MUST_TELL_HOST,
> VIRTIO_BALLOON_F_STATS_VQ,
> VIRTIO_BALLOON_F_DEFLATE_ON_OOM,
> + VIRTIO_BALLOON_F_FREE_PAGE_HINT,
> + VIRTIO_BALLOON_F_PAGE_POISON,
> };
>
> static struct virtio_driver virtio_balloon_driver = {
> diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h
> index 343d7dd..3f97067 100644
> --- a/include/uapi/linux/virtio_balloon.h
> +++ b/include/uapi/linux/virtio_balloon.h
> @@ -34,15 +34,22 @@
> #define VIRTIO_BALLOON_F_MUST_TELL_HOST 0 /* Tell before reclaiming pages */
> #define VIRTIO_BALLOON_F_STATS_VQ 1 /* Memory Stats virtqueue */
> #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 */
>
> /* Size of a PFN in the balloon interface. */
> #define VIRTIO_BALLOON_PFN_SHIFT 12
>
> +#define VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID 0
> struct virtio_balloon_config {
> /* Number of pages host wants Guest to give up. */
> __u32 num_pages;
> /* Number of pages we've actually got in balloon. */
> __u32 actual;
> + /* Free page report command id, readonly by guest */
> + __u32 free_page_report_cmd_id;
> + /* Stores PAGE_POISON if page poisoning is in use */
> + __u32 poison_val;
> };
>
> #define VIRTIO_BALLOON_S_SWAP_IN 0 /* Amount of memory swapped in */
> --
> 2.7.4
^ permalink raw reply
* Re: [PATCH v23 2/2] virtio-balloon: VIRTIO_BALLOON_F_FREE_PAGE_VQ
From: Michael S. Tsirkin @ 2018-01-24 17:32 UTC (permalink / raw)
To: Wei Wang
Cc: yang.zhang.wz, virtio-dev, riel, quan.xu0, kvm, nilal,
liliang.opensource, linux-kernel, mhocko, linux-mm, pbonzini,
akpm, virtualization
In-Reply-To: <5A681E03.1030007@intel.com>
On Wed, Jan 24, 2018 at 01:47:47PM +0800, Wei Wang wrote:
> On 01/24/2018 01:01 PM, Michael S. Tsirkin wrote:
> > On Wed, Jan 24, 2018 at 10:50:27AM +0800, Wei Wang wrote:
> > This will not DTRT in all cases. It's quite possible
> > that host does not need the kick when ring is half full but
> > does need it later when ring is full.
> > You can kick at ring half full as optimization but you absolutely
> > still must kick on ring full. Something like:
> >
> > if (vq->num_free == virtqueue_get_vring_size(vq) / 2 ||
> > vq->num_free <= 2)
>
> Right. Would "if (vq->num_free < virtqueue_get_vring_size(vq) / 2" be
> better?
>
>
> Best,
> Wei
It gives more kicks ... this reminds me, you need to validate
that vring size is at least 2, otherwise fail probe.
--
MST
^ permalink raw reply
* Re: [PATCH net 1/2] vhost: use mutex_lock_nested() in vhost_dev_lock_vqs()
From: David Miller @ 2018-01-24 21:38 UTC (permalink / raw)
To: jasowang; +Cc: netdev, virtualization, linux-kernel, mst
In-Reply-To: <1516699646-7321-1-git-send-email-jasowang@redhat.com>
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 23 Jan 2018 17:27:25 +0800
> We used to call mutex_lock() in vhost_dev_lock_vqs() which tries to
> hold mutexes of all virtqueues. This may confuse lockdep to report a
> possible deadlock because of trying to hold locks belong to same
> class. Switch to use mutex_lock_nested() to avoid false positive.
>
> Fixes: 6b1e6cc7855b0 ("vhost: new device IOTLB API")
> Reported-by: syzbot+dbb7c1161485e61b0241@syzkaller.appspotmail.com
> Signed-off-by: Jason Wang <jasowang@redhat.com>
Michael, I see you ACK'd this, meaning that you're OK with these two
fixes going via my net tree?
Thanks.
^ permalink raw reply
* Re: [PATCH net 1/2] vhost: use mutex_lock_nested() in vhost_dev_lock_vqs()
From: Michael S. Tsirkin @ 2018-01-24 21:46 UTC (permalink / raw)
To: David Miller; +Cc: netdev, linux-kernel, virtualization
In-Reply-To: <20180124.163830.2180124252515802160.davem@davemloft.net>
On Wed, Jan 24, 2018 at 04:38:30PM -0500, David Miller wrote:
> From: Jason Wang <jasowang@redhat.com>
> Date: Tue, 23 Jan 2018 17:27:25 +0800
>
> > We used to call mutex_lock() in vhost_dev_lock_vqs() which tries to
> > hold mutexes of all virtqueues. This may confuse lockdep to report a
> > possible deadlock because of trying to hold locks belong to same
> > class. Switch to use mutex_lock_nested() to avoid false positive.
> >
> > Fixes: 6b1e6cc7855b0 ("vhost: new device IOTLB API")
> > Reported-by: syzbot+dbb7c1161485e61b0241@syzkaller.appspotmail.com
> > Signed-off-by: Jason Wang <jasowang@redhat.com>
>
> Michael, I see you ACK'd this, meaning that you're OK with these two
> fixes going via my net tree?
>
> Thanks.
Yes - this seems to be what Jason wanted (judging by the net
tag in the subject) and I'm fine with it.
Thanks a lot.
--
MST
^ permalink raw reply
* Re: [PATCH net 1/2] vhost: use mutex_lock_nested() in vhost_dev_lock_vqs()
From: David Miller @ 2018-01-24 21:55 UTC (permalink / raw)
To: mst; +Cc: netdev, linux-kernel, virtualization
In-Reply-To: <20180124234511-mutt-send-email-mst@kernel.org>
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 24 Jan 2018 23:46:19 +0200
> On Wed, Jan 24, 2018 at 04:38:30PM -0500, David Miller wrote:
>> From: Jason Wang <jasowang@redhat.com>
>> Date: Tue, 23 Jan 2018 17:27:25 +0800
>>
>> > We used to call mutex_lock() in vhost_dev_lock_vqs() which tries to
>> > hold mutexes of all virtqueues. This may confuse lockdep to report a
>> > possible deadlock because of trying to hold locks belong to same
>> > class. Switch to use mutex_lock_nested() to avoid false positive.
>> >
>> > Fixes: 6b1e6cc7855b0 ("vhost: new device IOTLB API")
>> > Reported-by: syzbot+dbb7c1161485e61b0241@syzkaller.appspotmail.com
>> > Signed-off-by: Jason Wang <jasowang@redhat.com>
>>
>> Michael, I see you ACK'd this, meaning that you're OK with these two
>> fixes going via my net tree?
>>
>> Thanks.
>
> Yes - this seems to be what Jason wanted (judging by the net
> tag in the subject) and I'm fine with it.
> Thanks a lot.
Great, not a problem, done.
^ permalink raw reply
* Re: [PATCH v24 2/2] virtio-balloon: VIRTIO_BALLOON_F_FREE_PAGE_HINT
From: Wei Wang @ 2018-01-25 3:32 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: yang.zhang.wz, virtio-dev, riel, quan.xu0, kvm, nilal,
liliang.opensource, linux-kernel, mhocko, linux-mm, pbonzini,
akpm, virtualization
In-Reply-To: <20180124183349-mutt-send-email-mst@kernel.org>
On 01/25/2018 01:15 AM, Michael S. Tsirkin wrote:
> On Wed, Jan 24, 2018 at 06:42:42PM +0800, Wei Wang wrote:
> +
> +static void report_free_page_func(struct work_struct *work)
> +{
> + struct virtio_balloon *vb;
> + unsigned long flags;
> +
> + vb = container_of(work, struct virtio_balloon, report_free_page_work);
> +
> + /* Start by sending the obtained cmd id to the host with an outbuf */
> + send_cmd_id(vb, &vb->start_cmd_id);
> +
> + /*
> + * Set start_cmd_id to VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID to
> + * indicate a new request can be queued.
> + */
> + spin_lock_irqsave(&vb->stop_update_lock, flags);
> + vb->start_cmd_id = cpu_to_virtio32(vb->vdev,
> + VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID);
> + spin_unlock_irqrestore(&vb->stop_update_lock, flags);
> +
> + walk_free_mem_block(vb, 0, &virtio_balloon_send_free_pages);
> Can you teach walk_free_mem_block to return the && of all
> return calls, so caller knows whether it completed?
There will be two cases that can cause walk_free_mem_block to return
without completing:
1) host requests to stop in advance
2) vq->broken
How about letting walk_free_mem_block simply return the value returned
by its callback (i.e. virtio_balloon_send_free_pages)?
For host requests to stop, it returns "1", and the above only bails out
when walk_free_mem_block return a "< 0" value.
Best,
Wei
^ permalink raw reply
* Confirm
From: Solen win @ 2018-01-25 4:31 UTC (permalink / raw)
To: virtualization
[-- Attachment #1.1: Type: text/plain, Size: 1 bytes --]
[-- Attachment #1.2: Type: text/html, Size: 26 bytes --]
[-- Attachment #2: Type: text/plain, Size: 183 bytes --]
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply
* [PATCH v25 0/2] Virtio-balloon: support free page reporting
From: Wei Wang @ 2018-01-25 9:14 UTC (permalink / raw)
To: virtio-dev, linux-kernel, virtualization, kvm, linux-mm, mst,
mhocko, akpm
Cc: yang.zhang.wz, riel, quan.xu0, liliang.opensource, pbonzini,
nilal
This patch series is separated from the previous "Virtio-balloon
Enhancement" series. The new feature, VIRTIO_BALLOON_F_FREE_PAGE_HINT,
implemented by this series enables the virtio-balloon driver to report
hints of guest free pages to the host. It can be used to accelerate live
migration of VMs. Here is an introduction of this usage:
Live migration needs to transfer the VM's memory from the source machine
to the destination round by round. For the 1st round, all the VM's memory
is transferred. From the 2nd round, only the pieces of memory that were
written by the guest (after the 1st round) are transferred. One method
that is popularly used by the hypervisor to track which part of memory is
written is to write-protect all the guest memory.
The second feature enables the optimization of the 1st round memory
transfer - the hypervisor can skip the transfer of guest free pages in the
1st round. It is not concerned that the memory pages are used after they
are given to the hypervisor as a hint of the free pages, because they will
be tracked by the hypervisor and transferred in the next round if they are
used and written.
ChangeLog:
v24->v25:
- mm: change walk_free_mem_block to return 0 (instead of true) on
completing the report, and return a non-zero value from the
callabck, which stops the reporting.
- virtio-balloon:
- use enum instead of define for VIRTIO_BALLOON_VQ_INFLATE etc.
- avoid __virtio_clear_bit when bailing out;
- a new method to avoid reporting the some cmd id to host twice
- destroy_workqueue can cancel free page work when the feature is
negotiated;
- fail probe when the free page vq size is less than 2.
v23->v24:
- change feature name VIRTIO_BALLOON_F_FREE_PAGE_VQ to
VIRTIO_BALLOON_F_FREE_PAGE_HINT
- kick when vq->num_free < half full, instead of "= half full"
- replace BUG_ON with bailing out
- check vb->balloon_wq in probe(), if null, bail out
- add a new feature bit for page poisoning
- solve the corner case that one cmd id being sent to host twice
v22->v23:
- change to kick the device when the vq is half-way full;
- open-code batch_free_page_sg into add_one_sg;
- change cmd_id from "uint32_t" to "__virtio32";
- reserver one entry in the vq for teh driver to send cmd_id, instead
of busywaiting for an available entry;
- add "stop_update" check before queue_work for prudence purpose for
now, will have a separate patch to discuss this flag check later;
- init_vqs: change to put some variables on stack to have simpler
implementation;
- add destroy_workqueue(vb->balloon_wq);
v21->v22:
- add_one_sg: some code and comment re-arrangement
- send_cmd_id: handle a cornercase
For previous ChangeLog, please reference
https://lwn.net/Articles/743660/
Wei Wang (2):
mm: support reporting free page blocks
virtio-balloon: VIRTIO_BALLOON_F_FREE_PAGE_HINT
drivers/virtio/virtio_balloon.c | 251 ++++++++++++++++++++++++++++++------
include/linux/mm.h | 6 +
include/uapi/linux/virtio_balloon.h | 7 +
mm/page_alloc.c | 96 ++++++++++++++
4 files changed, 324 insertions(+), 36 deletions(-)
--
2.7.4
^ permalink raw reply
* [PATCH v25 1/2] mm: support reporting free page blocks
From: Wei Wang @ 2018-01-25 9:14 UTC (permalink / raw)
To: virtio-dev, linux-kernel, virtualization, kvm, linux-mm, mst,
mhocko, akpm
Cc: yang.zhang.wz, riel, quan.xu0, liliang.opensource, pbonzini,
nilal
In-Reply-To: <1516871646-22741-1-git-send-email-wei.w.wang@intel.com>
This patch adds support to walk through the free page blocks in the
system and report them via a callback function. Some page blocks may
leave the free list after zone->lock is released, so it is the caller's
responsibility to either detect or prevent the use of such pages.
One use example of this patch is to accelerate live migration by skipping
the transfer of free pages reported from the guest. A popular method used
by the hypervisor to track which part of memory is written during live
migration is to write-protect all the guest memory. So, those pages that
are reported as free pages but are written after the report function
returns will be captured by the hypervisor, and they will be added to the
next round of memory transfer.
Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Signed-off-by: Liang Li <liang.z.li@intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Michal Hocko <mhocko@kernel.org>
---
include/linux/mm.h | 6 ++++
mm/page_alloc.c | 96 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 102 insertions(+)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ea818ff..e65ae2e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1938,6 +1938,12 @@ extern void free_area_init_node(int nid, unsigned long * zones_size,
unsigned long zone_start_pfn, unsigned long *zholes_size);
extern void free_initmem(void);
+extern int walk_free_mem_block(void *opaque,
+ int min_order,
+ int (*report_pfn_range)(void *opaque,
+ unsigned long pfn,
+ unsigned long num));
+
/*
* Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK)
* into the buddy system. The freed pages will be poisoned with pattern
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 76c9688..0f08039 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4899,6 +4899,102 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
show_swap_cache_info();
}
+/*
+ * Walk through a free page list and report the found pfn range via the
+ * callback.
+ *
+ * Return 0 if it completes the reporting. Otherwise, return the Non-zero
+ * value returned from the callback.
+ */
+static int walk_free_page_list(void *opaque,
+ struct zone *zone,
+ int order,
+ enum migratetype mt,
+ int (*report_pfn_range)(void *,
+ unsigned long,
+ unsigned long))
+{
+ struct page *page;
+ struct list_head *list;
+ unsigned long pfn, flags;
+ bool ret = 0;
+
+ spin_lock_irqsave(&zone->lock, flags);
+ list = &zone->free_area[order].free_list[mt];
+ list_for_each_entry(page, list, lru) {
+ pfn = page_to_pfn(page);
+ ret = report_pfn_range(opaque, pfn, 1 << order);
+ if (ret)
+ break;
+ }
+ spin_unlock_irqrestore(&zone->lock, flags);
+
+ return ret;
+}
+
+/**
+ * walk_free_mem_block - Walk through the free page blocks in the system
+ * @opaque: the context passed from the caller
+ * @min_order: the minimum order of free lists to check
+ * @report_pfn_range: the callback to report the pfn range of the free pages
+ *
+ * If the callback returns a non-zero value, stop iterating the list of free
+ * page blocks. Otherwise, continue to report.
+ *
+ * Please note that there are no locking guarantees for the callback and
+ * that the reported pfn range might be freed or disappear after the
+ * callback returns so the caller has to be very careful how it is used.
+ *
+ * The callback itself must not sleep or perform any operations which would
+ * require any memory allocations directly (not even GFP_NOWAIT/GFP_ATOMIC)
+ * or via any lock dependency. It is generally advisable to implement
+ * the callback as simple as possible and defer any heavy lifting to a
+ * different context.
+ *
+ * There is no guarantee that each free range will be reported only once
+ * during one walk_free_mem_block invocation.
+ *
+ * pfn_to_page on the given range is strongly discouraged and if there is
+ * an absolute need for that make sure to contact MM people to discuss
+ * potential problems.
+ *
+ * The function itself might sleep so it cannot be called from atomic
+ * contexts.
+ *
+ * In general low orders tend to be very volatile and so it makes more
+ * sense to query larger ones first for various optimizations which like
+ * ballooning etc... This will reduce the overhead as well.
+ *
+ * Return 0 if it completes the reporting. Otherwise, return the non-zero
+ * value returned from the callback.
+ */
+int walk_free_mem_block(void *opaque,
+ int min_order,
+ int (*report_pfn_range)(void *opaque,
+ unsigned long pfn,
+ unsigned long num))
+{
+ struct zone *zone;
+ int order;
+ enum migratetype mt;
+ bool ret;
+
+ for_each_populated_zone(zone) {
+ for (order = MAX_ORDER - 1; order >= min_order; order--) {
+ for (mt = 0; mt < MIGRATE_TYPES; mt++) {
+ ret = walk_free_page_list(opaque, zone,
+ order, mt,
+ report_pfn_range);
+ if (ret)
+ return ret;
+ }
+ }
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(walk_free_mem_block);
+
static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
{
zoneref->zone = zone;
--
2.7.4
^ permalink raw reply related
* [PATCH v25 2/2] virtio-balloon: VIRTIO_BALLOON_F_FREE_PAGE_HINT
From: Wei Wang @ 2018-01-25 9:14 UTC (permalink / raw)
To: virtio-dev, linux-kernel, virtualization, kvm, linux-mm, mst,
mhocko, akpm
Cc: yang.zhang.wz, riel, quan.xu0, liliang.opensource, pbonzini,
nilal
In-Reply-To: <1516871646-22741-1-git-send-email-wei.w.wang@intel.com>
Negotiation of the VIRTIO_BALLOON_F_FREE_PAGE_HINT feature indicates the
support of reporting hints of guest free pages to host via virtio-balloon.
Host requests the guest to report free pages by sending a new cmd
id to the guest via the free_page_report_cmd_id configuration register.
When the guest starts to report, the first element added to the free page
vq is the cmd id given by host. When the guest finishes the reporting
of all the free pages, VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID is added
to the vq to tell host that the reporting is done. Host may also requests
the guest to stop the reporting in advance by sending the stop cmd id to
the guest via the configuration register.
Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Signed-off-by: Liang Li <liang.z.li@intel.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
---
drivers/virtio/virtio_balloon.c | 251 ++++++++++++++++++++++++++++++------
include/uapi/linux/virtio_balloon.h | 7 +
2 files changed, 222 insertions(+), 36 deletions(-)
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index a1fb52c..114985b 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -51,9 +51,22 @@ MODULE_PARM_DESC(oom_pages, "pages to free on OOM");
static struct vfsmount *balloon_mnt;
#endif
+enum virtio_balloon_vq {
+ VIRTIO_BALLOON_VQ_INFLATE,
+ VIRTIO_BALLOON_VQ_DEFLATE,
+ VIRTIO_BALLOON_VQ_STATS,
+ VIRTIO_BALLOON_VQ_FREE_PAGE,
+ VIRTIO_BALLOON_VQ_MAX
+};
+
struct virtio_balloon {
struct virtio_device *vdev;
- struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
+ struct virtqueue *inflate_vq, *deflate_vq, *stats_vq, *free_page_vq;
+
+ /* Balloon's own wq for cpu-intensive work items */
+ struct workqueue_struct *balloon_wq;
+ /* The free page reporting work item submitted to the balloon wq */
+ struct work_struct report_free_page_work;
/* The balloon servicing is delegated to a freezable workqueue. */
struct work_struct update_balloon_stats_work;
@@ -63,6 +76,11 @@ struct virtio_balloon {
spinlock_t stop_update_lock;
bool stop_update;
+ /* The new cmd id received from host */
+ uint32_t cmd_id_received;
+ /* The cmd id that is in use */
+ __virtio32 cmd_id_use;
+
/* Waiting for host to ack the pages we released. */
wait_queue_head_t acked;
@@ -316,17 +334,6 @@ static void stats_handle_request(struct virtio_balloon *vb)
virtqueue_kick(vq);
}
-static void virtballoon_changed(struct virtio_device *vdev)
-{
- struct virtio_balloon *vb = vdev->priv;
- unsigned long flags;
-
- spin_lock_irqsave(&vb->stop_update_lock, flags);
- if (!vb->stop_update)
- queue_work(system_freezable_wq, &vb->update_balloon_size_work);
- spin_unlock_irqrestore(&vb->stop_update_lock, flags);
-}
-
static inline s64 towards_target(struct virtio_balloon *vb)
{
s64 target;
@@ -343,6 +350,34 @@ static inline s64 towards_target(struct virtio_balloon *vb)
return target - vb->num_pages;
}
+static void virtballoon_changed(struct virtio_device *vdev)
+{
+ struct virtio_balloon *vb = vdev->priv;
+ unsigned long flags;
+ s64 diff = towards_target(vb);
+
+ if (diff) {
+ spin_lock_irqsave(&vb->stop_update_lock, flags);
+ if (!vb->stop_update)
+ queue_work(system_freezable_wq,
+ &vb->update_balloon_size_work);
+ spin_unlock_irqrestore(&vb->stop_update_lock, flags);
+ }
+
+ if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+ virtio_cread(vdev, struct virtio_balloon_config,
+ free_page_report_cmd_id, &vb->cmd_id_received);
+ if (vb->cmd_id_received !=
+ VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID) {
+ spin_lock_irqsave(&vb->stop_update_lock, flags);
+ if (!vb->stop_update)
+ queue_work(vb->balloon_wq,
+ &vb->report_free_page_work);
+ spin_unlock_irqrestore(&vb->stop_update_lock, flags);
+ }
+ }
+}
+
static void update_balloon_size(struct virtio_balloon *vb)
{
u32 actual = vb->num_pages;
@@ -417,42 +452,151 @@ static void update_balloon_size_func(struct work_struct *work)
static int init_vqs(struct virtio_balloon *vb)
{
- struct virtqueue *vqs[3];
- vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
- static const char * const names[] = { "inflate", "deflate", "stats" };
- int err, nvqs;
+ struct virtqueue *vqs[VIRTIO_BALLOON_VQ_MAX];
+ vq_callback_t *callbacks[VIRTIO_BALLOON_VQ_MAX];
+ const char *names[VIRTIO_BALLOON_VQ_MAX];
+ struct scatterlist sg;
+ int ret;
/*
- * We expect two virtqueues: inflate and deflate, and
- * optionally stat.
+ * Inflateq and deflateq are used unconditionally. The names[]
+ * will be NULL if the related feature is not enabled, which will
+ * cause no allocation for the corresponding virtqueue in find_vqs.
*/
- nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
- err = virtio_find_vqs(vb->vdev, nvqs, vqs, callbacks, names, NULL);
- if (err)
- return err;
+ callbacks[VIRTIO_BALLOON_VQ_INFLATE] = balloon_ack;
+ names[VIRTIO_BALLOON_VQ_INFLATE] = "inflate";
+ callbacks[VIRTIO_BALLOON_VQ_DEFLATE] = balloon_ack;
+ names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate";
+ names[VIRTIO_BALLOON_VQ_STATS] = NULL;
+ names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
- vb->inflate_vq = vqs[0];
- vb->deflate_vq = vqs[1];
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
- struct scatterlist sg;
- unsigned int num_stats;
- vb->stats_vq = vqs[2];
+ names[VIRTIO_BALLOON_VQ_STATS] = "stats";
+ callbacks[VIRTIO_BALLOON_VQ_STATS] = stats_request;
+ }
+
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+ names[VIRTIO_BALLOON_VQ_FREE_PAGE] = "free_page_vq";
+ callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
+ }
+
+ ret = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX,
+ vqs, callbacks, names, NULL, NULL);
+ if (ret)
+ return ret;
+ 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)) {
+ vb->stats_vq = vqs[VIRTIO_BALLOON_VQ_STATS];
/*
* Prime this virtqueue with one buffer so the hypervisor can
* use it to signal us later (it can't be broken yet!).
*/
- num_stats = update_balloon_stats(vb);
-
- sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
- if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL)
- < 0)
- BUG();
+ sg_init_one(&sg, vb->stats, sizeof(vb->stats));
+ ret = virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb,
+ GFP_KERNEL);
+ if (ret) {
+ dev_warn(&vb->vdev->dev, "%s: add stat_vq failed\n",
+ __func__);
+ return ret;
+ }
virtqueue_kick(vb->stats_vq);
}
+
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
+ vb->free_page_vq = vqs[VIRTIO_BALLOON_VQ_FREE_PAGE];
+
return 0;
}
+static int add_one_sg(struct virtqueue *vq, unsigned long pfn, uint32_t len)
+{
+ struct scatterlist sg;
+ unsigned int unused;
+ int ret = 0;
+
+ sg_init_table(&sg, 1);
+ sg_set_page(&sg, pfn_to_page(pfn), len, 0);
+
+ /* Detach all the used buffers from the vq */
+ while (virtqueue_get_buf(vq, &unused))
+ ;
+
+ /*
+ * Since this is an optimization feature, losing a couple of free
+ * pages to report isn't important. We simply return without adding
+ * the page if the vq is full.
+ * We are adding one entry each time, which essentially results in no
+ * memory allocation, so the GFP_KERNEL flag below can be ignored.
+ * There is always one entry reserved for the cmd id to use.
+ */
+ if (vq->num_free > 1)
+ ret = virtqueue_add_inbuf(vq, &sg, 1, vq, GFP_KERNEL);
+
+ if (vq->num_free == virtqueue_get_vring_size(vq) / 2 ||
+ vq->num_free <= 2)
+ virtqueue_kick(vq);
+
+ return ret;
+}
+
+static int virtio_balloon_send_free_pages(void *opaque, unsigned long pfn,
+ unsigned long nr_pages)
+{
+ struct virtio_balloon *vb = (struct virtio_balloon *)opaque;
+ uint32_t len = nr_pages << PAGE_SHIFT;
+
+ /*
+ * If a stop id or a new cmd id was just received from host, stop
+ * the reporting, and return 1 to indicate an active stop.
+ */
+ if (virtio32_to_cpu(vb->vdev, vb->cmd_id_use) != vb->cmd_id_received)
+ return 1;
+
+ return add_one_sg(vb->free_page_vq, pfn, len);
+}
+
+static int send_cmd_id(struct virtio_balloon *vb, uint32_t cmd_id)
+{
+ struct scatterlist sg;
+ struct virtqueue *vq = vb->free_page_vq;
+ int ret;
+
+ vb->cmd_id_use = cpu_to_virtio32(vb->vdev, cmd_id);
+ sg_init_one(&sg, &vb->cmd_id_use, sizeof(vb->cmd_id_use));
+
+ ret = virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
+ virtqueue_kick(vq);
+
+ return ret;
+}
+
+static void report_free_page_func(struct work_struct *work)
+{
+ struct virtio_balloon *vb;
+ int ret;
+
+ vb = container_of(work, struct virtio_balloon, report_free_page_work);
+
+ /* Start by sending the received cmd id to host with an outbuf */
+ ret = send_cmd_id(vb, vb->cmd_id_received);
+ if (unlikely(ret))
+ goto err;
+
+ ret = walk_free_mem_block(vb, 0, &virtio_balloon_send_free_pages);
+ if (unlikely(ret < 0))
+ goto err;
+
+ /* End by sending a stop id to host with an outbuf */
+ ret = send_cmd_id(vb, VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID);
+ if (likely(!ret))
+ return;
+err:
+ dev_err(&vb->vdev->dev, "%s failure: free page vq is broken\n",
+ __func__);
+}
+
#ifdef CONFIG_BALLOON_COMPACTION
/*
* virtballoon_migratepage - perform the balloon page migration on behalf of
@@ -537,6 +681,7 @@ static struct file_system_type balloon_fs = {
static int virtballoon_probe(struct virtio_device *vdev)
{
struct virtio_balloon *vb;
+ __u32 poison_val;
int err;
if (!vdev->config->get) {
@@ -566,18 +711,39 @@ static int virtballoon_probe(struct virtio_device *vdev)
if (err)
goto out_free_vb;
+ if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+ /*
+ * There is always one entry reserved for cmd id, so the ring
+ * size needs to be at least two to report free page hint.
+ */
+ if (virtqueue_get_vring_size(vb->free_page_vq) < 2)
+ goto out_free_vb;
+ vb->balloon_wq = alloc_workqueue("balloon-wq",
+ WQ_FREEZABLE | WQ_CPU_INTENSIVE, 0);
+ if (!vb->balloon_wq) {
+ err = -ENOMEM;
+ goto out_del_vqs;
+ }
+ INIT_WORK(&vb->report_free_page_work, report_free_page_func);
+ if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) {
+ poison_val = PAGE_POISON;
+ virtio_cwrite(vb->vdev, struct virtio_balloon_config,
+ poison_val, &poison_val);
+ }
+ }
+
vb->nb.notifier_call = virtballoon_oom_notify;
vb->nb.priority = VIRTBALLOON_OOM_NOTIFY_PRIORITY;
err = register_oom_notifier(&vb->nb);
if (err < 0)
- goto out_del_vqs;
+ goto out_del_balloon_wq;
#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;
+ goto out_del_balloon_wq;
}
vb->vb_dev_info.migratepage = virtballoon_migratepage;
@@ -587,7 +753,7 @@ static int virtballoon_probe(struct virtio_device *vdev)
kern_unmount(balloon_mnt);
unregister_oom_notifier(&vb->nb);
vb->vb_dev_info.inode = NULL;
- goto out_del_vqs;
+ goto out_del_balloon_wq;
}
vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
#endif
@@ -598,6 +764,9 @@ static int virtballoon_probe(struct virtio_device *vdev)
virtballoon_changed(vdev);
return 0;
+out_del_balloon_wq:
+ if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
+ destroy_workqueue(vb->balloon_wq);
out_del_vqs:
vdev->config->del_vqs(vdev);
out_free_vb:
@@ -631,6 +800,11 @@ static void virtballoon_remove(struct virtio_device *vdev)
cancel_work_sync(&vb->update_balloon_size_work);
cancel_work_sync(&vb->update_balloon_stats_work);
+ if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+ cancel_work_sync(&vb->report_free_page_work);
+ destroy_workqueue(vb->balloon_wq);
+ }
+
remove_common(vb);
#ifdef CONFIG_BALLOON_COMPACTION
if (vb->vb_dev_info.inode)
@@ -674,6 +848,9 @@ static int virtballoon_restore(struct virtio_device *vdev)
static int virtballoon_validate(struct virtio_device *vdev)
{
+ if (!page_poisoning_enabled())
+ __virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON);
+
__virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM);
return 0;
}
@@ -682,6 +859,8 @@ static unsigned int features[] = {
VIRTIO_BALLOON_F_MUST_TELL_HOST,
VIRTIO_BALLOON_F_STATS_VQ,
VIRTIO_BALLOON_F_DEFLATE_ON_OOM,
+ VIRTIO_BALLOON_F_FREE_PAGE_HINT,
+ VIRTIO_BALLOON_F_PAGE_POISON,
};
static struct virtio_driver virtio_balloon_driver = {
diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h
index 343d7dd..3f97067 100644
--- a/include/uapi/linux/virtio_balloon.h
+++ b/include/uapi/linux/virtio_balloon.h
@@ -34,15 +34,22 @@
#define VIRTIO_BALLOON_F_MUST_TELL_HOST 0 /* Tell before reclaiming pages */
#define VIRTIO_BALLOON_F_STATS_VQ 1 /* Memory Stats virtqueue */
#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 */
/* Size of a PFN in the balloon interface. */
#define VIRTIO_BALLOON_PFN_SHIFT 12
+#define VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID 0
struct virtio_balloon_config {
/* Number of pages host wants Guest to give up. */
__u32 num_pages;
/* Number of pages we've actually got in balloon. */
__u32 actual;
+ /* Free page report command id, readonly by guest */
+ __u32 free_page_report_cmd_id;
+ /* Stores PAGE_POISON if page poisoning is in use */
+ __u32 poison_val;
};
#define VIRTIO_BALLOON_S_SWAP_IN 0 /* Amount of memory swapped in */
--
2.7.4
^ permalink raw reply related
* [PATCH v25 1/2 RESEND] mm: support reporting free page blocks
From: Wei Wang @ 2018-01-25 9:38 UTC (permalink / raw)
To: virtio-dev, linux-kernel, virtualization, kvm, linux-mm, mst,
mhocko, akpm
Cc: yang.zhang.wz, riel, quan.xu0, liliang.opensource, pbonzini,
nilal
This patch adds support to walk through the free page blocks in the
system and report them via a callback function. Some page blocks may
leave the free list after zone->lock is released, so it is the caller's
responsibility to either detect or prevent the use of such pages.
One use example of this patch is to accelerate live migration by skipping
the transfer of free pages reported from the guest. A popular method used
by the hypervisor to track which part of memory is written during live
migration is to write-protect all the guest memory. So, those pages that
are reported as free pages but are written after the report function
returns will be captured by the hypervisor, and they will be added to the
next round of memory transfer.
Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Signed-off-by: Liang Li <liang.z.li@intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Michal Hocko <mhocko@kernel.org>
---
include/linux/mm.h | 6 ++++
mm/page_alloc.c | 96 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 102 insertions(+)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ea818ff..e65ae2e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1938,6 +1938,12 @@ extern void free_area_init_node(int nid, unsigned long * zones_size,
unsigned long zone_start_pfn, unsigned long *zholes_size);
extern void free_initmem(void);
+extern int walk_free_mem_block(void *opaque,
+ int min_order,
+ int (*report_pfn_range)(void *opaque,
+ unsigned long pfn,
+ unsigned long num));
+
/*
* Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK)
* into the buddy system. The freed pages will be poisoned with pattern
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 76c9688..eda587f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4899,6 +4899,102 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
show_swap_cache_info();
}
+/*
+ * Walk through a free page list and report the found pfn range via the
+ * callback.
+ *
+ * Return 0 if it completes the reporting. Otherwise, return the Non-zero
+ * value returned from the callback.
+ */
+static int walk_free_page_list(void *opaque,
+ struct zone *zone,
+ int order,
+ enum migratetype mt,
+ int (*report_pfn_range)(void *,
+ unsigned long,
+ unsigned long))
+{
+ struct page *page;
+ struct list_head *list;
+ unsigned long pfn, flags;
+ int ret = 0;
+
+ spin_lock_irqsave(&zone->lock, flags);
+ list = &zone->free_area[order].free_list[mt];
+ list_for_each_entry(page, list, lru) {
+ pfn = page_to_pfn(page);
+ ret = report_pfn_range(opaque, pfn, 1 << order);
+ if (ret)
+ break;
+ }
+ spin_unlock_irqrestore(&zone->lock, flags);
+
+ return ret;
+}
+
+/**
+ * walk_free_mem_block - Walk through the free page blocks in the system
+ * @opaque: the context passed from the caller
+ * @min_order: the minimum order of free lists to check
+ * @report_pfn_range: the callback to report the pfn range of the free pages
+ *
+ * If the callback returns a non-zero value, stop iterating the list of free
+ * page blocks. Otherwise, continue to report.
+ *
+ * Please note that there are no locking guarantees for the callback and
+ * that the reported pfn range might be freed or disappear after the
+ * callback returns so the caller has to be very careful how it is used.
+ *
+ * The callback itself must not sleep or perform any operations which would
+ * require any memory allocations directly (not even GFP_NOWAIT/GFP_ATOMIC)
+ * or via any lock dependency. It is generally advisable to implement
+ * the callback as simple as possible and defer any heavy lifting to a
+ * different context.
+ *
+ * There is no guarantee that each free range will be reported only once
+ * during one walk_free_mem_block invocation.
+ *
+ * pfn_to_page on the given range is strongly discouraged and if there is
+ * an absolute need for that make sure to contact MM people to discuss
+ * potential problems.
+ *
+ * The function itself might sleep so it cannot be called from atomic
+ * contexts.
+ *
+ * In general low orders tend to be very volatile and so it makes more
+ * sense to query larger ones first for various optimizations which like
+ * ballooning etc... This will reduce the overhead as well.
+ *
+ * Return 0 if it completes the reporting. Otherwise, return the non-zero
+ * value returned from the callback.
+ */
+int walk_free_mem_block(void *opaque,
+ int min_order,
+ int (*report_pfn_range)(void *opaque,
+ unsigned long pfn,
+ unsigned long num))
+{
+ struct zone *zone;
+ int order;
+ enum migratetype mt;
+ int ret;
+
+ for_each_populated_zone(zone) {
+ for (order = MAX_ORDER - 1; order >= min_order; order--) {
+ for (mt = 0; mt < MIGRATE_TYPES; mt++) {
+ ret = walk_free_page_list(opaque, zone,
+ order, mt,
+ report_pfn_range);
+ if (ret)
+ return ret;
+ }
+ }
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(walk_free_mem_block);
+
static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
{
zoneref->zone = zone;
--
2.7.4
^ permalink raw reply related
* Re: [PATCH v24 2/2] virtio-balloon: VIRTIO_BALLOON_F_FREE_PAGE_HINT
From: Wei Wang @ 2018-01-25 9:45 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: yang.zhang.wz, virtio-dev, riel, quan.xu0, kvm, nilal,
liliang.opensource, linux-kernel, mhocko, linux-mm, pbonzini,
akpm, virtualization
In-Reply-To: <20180124183349-mutt-send-email-mst@kernel.org>
On 01/25/2018 01:15 AM, Michael S. Tsirkin wrote:
> On Wed, Jan 24, 2018 at 06:42:42PM +0800, Wei Wang wrote:
>>
>>
>> What is this doing? Basically handling the case where vq is broken?
>> It's kind of ugly to tweak feature bits, most code assumes they never
>> change. Please just return an error to caller instead and handle it
>> there.
>>
>> You can then avoid sprinking the check for the feature bit
>> all over the code.
>>
>
> One thing I don't like about this one is that the previous request
> will still try to run to completion.
>
> And it all seems pretty complex.
>
> How about:
> - pass cmd id to a queued work
> - queued work gets that cmd id, stores a copy and uses that,
> re-checking periodically - stop if cmd id changes:
> will replace report_free_page too since that's set to
> stop.
>
> This means you do not reuse the queued cmd id also
> for the buffer - which is probably for the best.
Thanks for the suggestion. Please have a check how it's implemented in v25.
Just a little reminder that work queue has internally ensured that there
is no re-entrant of the same queued function.
Best,
Wei
^ permalink raw reply
* Re: [virtio-dev] [PATCH v25 1/2 RESEND] mm: support reporting free page blocks
From: Wei Wang @ 2018-01-25 10:02 UTC (permalink / raw)
To: virtio-dev, linux-kernel, virtualization, kvm, linux-mm, mst,
mhocko, akpm
Cc: yang.zhang.wz, riel, quan.xu0, liliang.opensource, pbonzini,
nilal
In-Reply-To: <1516873107-34950-1-git-send-email-wei.w.wang@intel.com>
Hi Michal,
On 01/25/2018 05:38 PM, Wei Wang wrote:
> This patch adds support to walk through the free page blocks in the
> system and report them via a callback function. Some page blocks may
> leave the free list after zone->lock is released, so it is the caller's
> responsibility to either detect or prevent the use of such pages.
>
> One use example of this patch is to accelerate live migration by skipping
> the transfer of free pages reported from the guest. A popular method used
> by the hypervisor to track which part of memory is written during live
> migration is to write-protect all the guest memory. So, those pages that
> are reported as free pages but are written after the report function
> returns will be captured by the hypervisor, and they will be added to the
> next round of memory transfer.
>
> Signed-off-by: Wei Wang <wei.w.wang@intel.com>
> Signed-off-by: Liang Li <liang.z.li@intel.com>
> Cc: Michal Hocko <mhocko@kernel.org>
> Cc: Michael S. Tsirkin <mst@redhat.com>
> Acked-by: Michal Hocko <mhocko@kernel.org>
> ---
> include/linux/mm.h | 6 ++++
> mm/page_alloc.c | 96 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
> 2 files changed, 102 insertions(+)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index ea818ff..e65ae2e 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1938,6 +1938,12 @@ extern void free_area_init_node(int nid, unsigned long * zones_size,
> unsigned long zone_start_pfn, unsigned long *zholes_size);
> extern void free_initmem(void);
>
> +extern int walk_free_mem_block(void *opaque,
> + int min_order,
> + int (*report_pfn_range)(void *opaque,
> + unsigned long pfn,
> + unsigned long num));
> +
> /*
> * Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK)
> * into the buddy system. The freed pages will be poisoned with pattern
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 76c9688..eda587f 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -4899,6 +4899,102 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
> show_swap_cache_info();
> }
>
> +/*
> + * Walk through a free page list and report the found pfn range via the
> + * callback.
> + *
> + * Return 0 if it completes the reporting. Otherwise, return the Non-zero
> + * value returned from the callback.
> + */
> +static int walk_free_page_list(void *opaque,
> + struct zone *zone,
> + int order,
> + enum migratetype mt,
> + int (*report_pfn_range)(void *,
> + unsigned long,
> + unsigned long))
> +{
> + struct page *page;
> + struct list_head *list;
> + unsigned long pfn, flags;
> + int ret = 0;
> +
> + spin_lock_irqsave(&zone->lock, flags);
> + list = &zone->free_area[order].free_list[mt];
> + list_for_each_entry(page, list, lru) {
> + pfn = page_to_pfn(page);
> + ret = report_pfn_range(opaque, pfn, 1 << order);
> + if (ret)
> + break;
> + }
> + spin_unlock_irqrestore(&zone->lock, flags);
> +
> + return ret;
> +}
> +
> +/**
> + * walk_free_mem_block - Walk through the free page blocks in the system
> + * @opaque: the context passed from the caller
> + * @min_order: the minimum order of free lists to check
> + * @report_pfn_range: the callback to report the pfn range of the free pages
> + *
> + * If the callback returns a non-zero value, stop iterating the list of free
> + * page blocks. Otherwise, continue to report.
> + *
> + * Please note that there are no locking guarantees for the callback and
> + * that the reported pfn range might be freed or disappear after the
> + * callback returns so the caller has to be very careful how it is used.
> + *
> + * The callback itself must not sleep or perform any operations which would
> + * require any memory allocations directly (not even GFP_NOWAIT/GFP_ATOMIC)
> + * or via any lock dependency. It is generally advisable to implement
> + * the callback as simple as possible and defer any heavy lifting to a
> + * different context.
> + *
> + * There is no guarantee that each free range will be reported only once
> + * during one walk_free_mem_block invocation.
> + *
> + * pfn_to_page on the given range is strongly discouraged and if there is
> + * an absolute need for that make sure to contact MM people to discuss
> + * potential problems.
> + *
> + * The function itself might sleep so it cannot be called from atomic
> + * contexts.
> + *
> + * In general low orders tend to be very volatile and so it makes more
> + * sense to query larger ones first for various optimizations which like
> + * ballooning etc... This will reduce the overhead as well.
> + *
> + * Return 0 if it completes the reporting. Otherwise, return the non-zero
> + * value returned from the callback.
> + */
> +int walk_free_mem_block(void *opaque,
> + int min_order,
> + int (*report_pfn_range)(void *opaque,
> + unsigned long pfn,
> + unsigned long num))
> +{
> + struct zone *zone;
> + int order;
> + enum migratetype mt;
> + int ret;
> +
> + for_each_populated_zone(zone) {
> + for (order = MAX_ORDER - 1; order >= min_order; order--) {
> + for (mt = 0; mt < MIGRATE_TYPES; mt++) {
> + ret = walk_free_page_list(opaque, zone,
> + order, mt,
> + report_pfn_range);
> + if (ret)
> + return ret;
> + }
> + }
> + }
> +
> + return 0;
> +}
> +EXPORT_SYMBOL_GPL(walk_free_mem_block);
> +
> static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
> {
> zoneref->zone = zone;
Thanks for reviewing this mm patch. Just a reminder that this version
changes this function to return "zero/non-zero", instead of
"true/false". If you have a different thought, please let us know. Thanks.
Best,
Wei
^ permalink raw reply
* Re: [PATCH v24 2/2] virtio-balloon: VIRTIO_BALLOON_F_FREE_PAGE_HINT
From: Tetsuo Handa @ 2018-01-25 11:28 UTC (permalink / raw)
To: Wei Wang, Michael S. Tsirkin
Cc: yang.zhang.wz, virtio-dev, riel, quan.xu0, kvm, nilal,
liliang.opensource, linux-kernel, mhocko, linux-mm, pbonzini,
akpm, virtualization
In-Reply-To: <5A694FB5.5090803@intel.com>
On 2018/01/25 12:32, Wei Wang wrote:
> On 01/25/2018 01:15 AM, Michael S. Tsirkin wrote:
>> On Wed, Jan 24, 2018 at 06:42:42PM +0800, Wei Wang wrote:
>> +
>> +static void report_free_page_func(struct work_struct *work)
>> +{
>> + struct virtio_balloon *vb;
>> + unsigned long flags;
>> +
>> + vb = container_of(work, struct virtio_balloon, report_free_page_work);
>> +
>> + /* Start by sending the obtained cmd id to the host with an outbuf */
>> + send_cmd_id(vb, &vb->start_cmd_id);
>> +
>> + /*
>> + * Set start_cmd_id to VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID to
>> + * indicate a new request can be queued.
>> + */
>> + spin_lock_irqsave(&vb->stop_update_lock, flags);
>> + vb->start_cmd_id = cpu_to_virtio32(vb->vdev,
>> + VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID);
>> + spin_unlock_irqrestore(&vb->stop_update_lock, flags);
>> +
>> + walk_free_mem_block(vb, 0, &virtio_balloon_send_free_pages);
>> Can you teach walk_free_mem_block to return the && of all
>> return calls, so caller knows whether it completed?
>
> There will be two cases that can cause walk_free_mem_block to return without completing:
> 1) host requests to stop in advance
> 2) vq->broken
>
> How about letting walk_free_mem_block simply return the value returned by its callback (i.e. virtio_balloon_send_free_pages)?
>
> For host requests to stop, it returns "1", and the above only bails out when walk_free_mem_block return a "< 0" value.
I feel that virtio_balloon_send_free_pages is doing too heavy things.
It can be called for many times with IRQ disabled. Number of times
it is called depends on amount of free pages (and fragmentation state).
Generally, more free pages, more calls.
Then, why don't you allocate some pages for holding all pfn values
and then call walk_free_mem_block() only for storing pfn values
and then send pfn values without disabling IRQ?
^ permalink raw reply
* Re: [PATCH v24 2/2] virtio-balloon: VIRTIO_BALLOON_F_FREE_PAGE_HINT
From: Wei Wang @ 2018-01-25 12:55 UTC (permalink / raw)
To: Tetsuo Handa, Michael S. Tsirkin
Cc: yang.zhang.wz, virtio-dev, riel, quan.xu0, kvm, nilal,
liliang.opensource, linux-kernel, mhocko, linux-mm, pbonzini,
akpm, virtualization
In-Reply-To: <17068749-d2c7-61bb-4637-a1aee5a0d0fb@I-love.SAKURA.ne.jp>
On 01/25/2018 07:28 PM, Tetsuo Handa wrote:
> On 2018/01/25 12:32, Wei Wang wrote:
>> On 01/25/2018 01:15 AM, Michael S. Tsirkin wrote:
>>> On Wed, Jan 24, 2018 at 06:42:42PM +0800, Wei Wang wrote:
>>> +
>>> +static void report_free_page_func(struct work_struct *work)
>>> +{
>>> + struct virtio_balloon *vb;
>>> + unsigned long flags;
>>> +
>>> + vb = container_of(work, struct virtio_balloon, report_free_page_work);
>>> +
>>> + /* Start by sending the obtained cmd id to the host with an outbuf */
>>> + send_cmd_id(vb, &vb->start_cmd_id);
>>> +
>>> + /*
>>> + * Set start_cmd_id to VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID to
>>> + * indicate a new request can be queued.
>>> + */
>>> + spin_lock_irqsave(&vb->stop_update_lock, flags);
>>> + vb->start_cmd_id = cpu_to_virtio32(vb->vdev,
>>> + VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID);
>>> + spin_unlock_irqrestore(&vb->stop_update_lock, flags);
>>> +
>>> + walk_free_mem_block(vb, 0, &virtio_balloon_send_free_pages);
>>> Can you teach walk_free_mem_block to return the && of all
>>> return calls, so caller knows whether it completed?
>> There will be two cases that can cause walk_free_mem_block to return without completing:
>> 1) host requests to stop in advance
>> 2) vq->broken
>>
>> How about letting walk_free_mem_block simply return the value returned by its callback (i.e. virtio_balloon_send_free_pages)?
>>
>> For host requests to stop, it returns "1", and the above only bails out when walk_free_mem_block return a "< 0" value.
> I feel that virtio_balloon_send_free_pages is doing too heavy things.
>
> It can be called for many times with IRQ disabled. Number of times
> it is called depends on amount of free pages (and fragmentation state).
> Generally, more free pages, more calls.
>
> Then, why don't you allocate some pages for holding all pfn values
> and then call walk_free_mem_block() only for storing pfn values
> and then send pfn values without disabling IRQ?
We have actually tried many methods for this feature before, and what
you suggested is one of them, and you could also find the related
discussion in earlier versions. In addition to the complexity of that
method (if thinking deeper along that line), I can share the performance
(the live migration time) comparison of that method with this one in
this patch: ~405ms vs. ~260 ms.
The things that you worried about have also been discussed actually. The
strategy is that we start with something fundamental and increase
incrementally (if you check earlier versions, we also have a method
which makes the lock finer granularity, but we decided to leave this to
the future improvement for prudence purpose). If possible, please let
Michael review this patch, he already knows all those things. We will
finish this feature as soon as possible, and then discuss with you about
another one if you want. Thanks.
Best,
Wei
^ permalink raw reply
* Re: [PATCH v24 1/2] mm: support reporting free page blocks
From: Michael S. Tsirkin @ 2018-01-25 13:41 UTC (permalink / raw)
To: Wei Wang
Cc: yang.zhang.wz, virtio-dev, riel, quan.xu0, kvm, nilal,
liliang.opensource, linux-kernel, mhocko, linux-mm, pbonzini,
akpm, virtualization
In-Reply-To: <1516790562-37889-2-git-send-email-wei.w.wang@intel.com>
On Wed, Jan 24, 2018 at 06:42:41PM +0800, Wei Wang wrote:
> This patch adds support to walk through the free page blocks in the
> system and report them via a callback function. Some page blocks may
> leave the free list after zone->lock is released, so it is the caller's
> responsibility to either detect or prevent the use of such pages.
>
> One use example of this patch is to accelerate live migration by skipping
> the transfer of free pages reported from the guest. A popular method used
> by the hypervisor to track which part of memory is written during live
> migration is to write-protect all the guest memory. So, those pages that
> are reported as free pages but are written after the report function
> returns will be captured by the hypervisor, and they will be added to the
> next round of memory transfer.
>
> Signed-off-by: Wei Wang <wei.w.wang@intel.com>
> Signed-off-by: Liang Li <liang.z.li@intel.com>
> Cc: Michal Hocko <mhocko@kernel.org>
> Cc: Michael S. Tsirkin <mst@redhat.com>
> Acked-by: Michal Hocko <mhocko@kernel.org>
> ---
> include/linux/mm.h | 6 ++++
> mm/page_alloc.c | 91 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
> 2 files changed, 97 insertions(+)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index ea818ff..b3077dd 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1938,6 +1938,12 @@ extern void free_area_init_node(int nid, unsigned long * zones_size,
> unsigned long zone_start_pfn, unsigned long *zholes_size);
> extern void free_initmem(void);
>
> +extern void walk_free_mem_block(void *opaque,
> + int min_order,
> + bool (*report_pfn_range)(void *opaque,
> + unsigned long pfn,
> + unsigned long num));
> +
> /*
> * Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK)
> * into the buddy system. The freed pages will be poisoned with pattern
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 76c9688..705de22 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -4899,6 +4899,97 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
> show_swap_cache_info();
> }
>
> +/*
> + * Walk through a free page list and report the found pfn range via the
> + * callback.
> + *
> + * Return false if the callback requests to stop reporting. Otherwise,
> + * return true.
> + */
> +static bool walk_free_page_list(void *opaque,
> + struct zone *zone,
> + int order,
> + enum migratetype mt,
> + bool (*report_pfn_range)(void *,
> + unsigned long,
> + unsigned long))
> +{
> + struct page *page;
> + struct list_head *list;
> + unsigned long pfn, flags;
> + bool ret;
> +
> + spin_lock_irqsave(&zone->lock, flags);
> + list = &zone->free_area[order].free_list[mt];
> + list_for_each_entry(page, list, lru) {
> + pfn = page_to_pfn(page);
> + ret = report_pfn_range(opaque, pfn, 1 << order);
> + if (!ret)
> + break;
> + }
> + spin_unlock_irqrestore(&zone->lock, flags);
> +
> + return ret;
> +}
There are two issues with this API. One is that it is not
restarteable: if you return false, you start from the
beginning. So no way to drop lock, do something slow
and then proceed.
Another is that you are using it to report free page hints. Presumably
the point is to drop these pages - keeping them near head of the list
and reusing the reported ones will just make everything slower
invalidating the hint.
How about rotating these pages towards the end of the list?
Probably not on each call, callect reported pages and then
move them to tail when we exit.
Of course it's possible not all reporters want this.
So maybe change the callback to return int:
0 - page reported, move page to end of free list
> 0 - page skipped, proceed
< 0 - stop processing
> +
> +/**
> + * walk_free_mem_block - Walk through the free page blocks in the system
> + * @opaque: the context passed from the caller
> + * @min_order: the minimum order of free lists to check
> + * @report_pfn_range: the callback to report the pfn range of the free pages
> + *
> + * If the callback returns false, stop iterating the list of free page blocks.
> + * Otherwise, continue to report.
> + *
> + * Please note that there are no locking guarantees for the callback and
> + * that the reported pfn range might be freed or disappear after the
> + * callback returns so the caller has to be very careful how it is used.
> + *
> + * The callback itself must not sleep or perform any operations which would
> + * require any memory allocations directly (not even GFP_NOWAIT/GFP_ATOMIC)
> + * or via any lock dependency. It is generally advisable to implement
> + * the callback as simple as possible and defer any heavy lifting to a
> + * different context.
> + *
> + * There is no guarantee that each free range will be reported only once
> + * during one walk_free_mem_block invocation.
> + *
> + * pfn_to_page on the given range is strongly discouraged and if there is
> + * an absolute need for that make sure to contact MM people to discuss
> + * potential problems.
> + *
> + * The function itself might sleep so it cannot be called from atomic
> + * contexts.
> + *
> + * In general low orders tend to be very volatile and so it makes more
> + * sense to query larger ones first for various optimizations which like
> + * ballooning etc... This will reduce the overhead as well.
> + */
> +void walk_free_mem_block(void *opaque,
> + int min_order,
> + bool (*report_pfn_range)(void *opaque,
> + unsigned long pfn,
> + unsigned long num))
> +{
> + struct zone *zone;
> + int order;
> + enum migratetype mt;
> + bool ret;
> +
> + for_each_populated_zone(zone) {
> + for (order = MAX_ORDER - 1; order >= min_order; order--) {
> + for (mt = 0; mt < MIGRATE_TYPES; mt++) {
> + ret = walk_free_page_list(opaque, zone,
> + order, mt,
> + report_pfn_range);
> + if (!ret)
> + return;
> + }
> + }
> + }
> +}
> +EXPORT_SYMBOL_GPL(walk_free_mem_block);
> +
I think callers need a way to
1. distinguish between completion and exit on error
2. restart from where we stopped
So I would both accept and return the current zone
and a special value to mean "complete"
> static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
> {
> zoneref->zone = zone;
> --
> 2.7.4
^ permalink raw reply
* Re: [PATCH v25 1/2] mm: support reporting free page blocks
From: Michael S. Tsirkin @ 2018-01-25 13:46 UTC (permalink / raw)
To: Wei Wang
Cc: yang.zhang.wz, virtio-dev, riel, quan.xu0, kvm, nilal,
liliang.opensource, linux-kernel, mhocko, linux-mm, pbonzini,
akpm, virtualization
In-Reply-To: <1516871646-22741-2-git-send-email-wei.w.wang@intel.com>
On Thu, Jan 25, 2018 at 05:14:05PM +0800, Wei Wang wrote:
> This patch adds support to walk through the free page blocks in the
> system and report them via a callback function. Some page blocks may
> leave the free list after zone->lock is released, so it is the caller's
> responsibility to either detect or prevent the use of such pages.
>
> One use example of this patch is to accelerate live migration by skipping
> the transfer of free pages reported from the guest. A popular method used
> by the hypervisor to track which part of memory is written during live
> migration is to write-protect all the guest memory. So, those pages that
> are reported as free pages but are written after the report function
> returns will be captured by the hypervisor, and they will be added to the
> next round of memory transfer.
>
> Signed-off-by: Wei Wang <wei.w.wang@intel.com>
> Signed-off-by: Liang Li <liang.z.li@intel.com>
> Cc: Michal Hocko <mhocko@kernel.org>
> Cc: Michael S. Tsirkin <mst@redhat.com>
> Acked-by: Michal Hocko <mhocko@kernel.org>
Commented on v24 that this should be restartable. That comment
still applies.
> ---
> include/linux/mm.h | 6 ++++
> mm/page_alloc.c | 96 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
> 2 files changed, 102 insertions(+)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index ea818ff..e65ae2e 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1938,6 +1938,12 @@ extern void free_area_init_node(int nid, unsigned long * zones_size,
> unsigned long zone_start_pfn, unsigned long *zholes_size);
> extern void free_initmem(void);
>
> +extern int walk_free_mem_block(void *opaque,
> + int min_order,
> + int (*report_pfn_range)(void *opaque,
> + unsigned long pfn,
> + unsigned long num));
> +
> /*
> * Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK)
> * into the buddy system. The freed pages will be poisoned with pattern
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 76c9688..0f08039 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -4899,6 +4899,102 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
> show_swap_cache_info();
> }
>
> +/*
> + * Walk through a free page list and report the found pfn range via the
> + * callback.
> + *
> + * Return 0 if it completes the reporting. Otherwise, return the Non-zero
> + * value returned from the callback.
> + */
> +static int walk_free_page_list(void *opaque,
> + struct zone *zone,
> + int order,
> + enum migratetype mt,
> + int (*report_pfn_range)(void *,
> + unsigned long,
> + unsigned long))
> +{
> + struct page *page;
> + struct list_head *list;
> + unsigned long pfn, flags;
> + bool ret = 0;
> +
> + spin_lock_irqsave(&zone->lock, flags);
> + list = &zone->free_area[order].free_list[mt];
> + list_for_each_entry(page, list, lru) {
> + pfn = page_to_pfn(page);
> + ret = report_pfn_range(opaque, pfn, 1 << order);
> + if (ret)
> + break;
> + }
> + spin_unlock_irqrestore(&zone->lock, flags);
> +
> + return ret;
> +}
> +
> +/**
> + * walk_free_mem_block - Walk through the free page blocks in the system
> + * @opaque: the context passed from the caller
> + * @min_order: the minimum order of free lists to check
> + * @report_pfn_range: the callback to report the pfn range of the free pages
> + *
> + * If the callback returns a non-zero value, stop iterating the list of free
> + * page blocks. Otherwise, continue to report.
> + *
> + * Please note that there are no locking guarantees for the callback and
> + * that the reported pfn range might be freed or disappear after the
> + * callback returns so the caller has to be very careful how it is used.
> + *
> + * The callback itself must not sleep or perform any operations which would
> + * require any memory allocations directly (not even GFP_NOWAIT/GFP_ATOMIC)
> + * or via any lock dependency. It is generally advisable to implement
> + * the callback as simple as possible and defer any heavy lifting to a
> + * different context.
> + *
> + * There is no guarantee that each free range will be reported only once
> + * during one walk_free_mem_block invocation.
> + *
> + * pfn_to_page on the given range is strongly discouraged and if there is
> + * an absolute need for that make sure to contact MM people to discuss
> + * potential problems.
> + *
> + * The function itself might sleep so it cannot be called from atomic
> + * contexts.
> + *
> + * In general low orders tend to be very volatile and so it makes more
> + * sense to query larger ones first for various optimizations which like
> + * ballooning etc... This will reduce the overhead as well.
> + *
> + * Return 0 if it completes the reporting. Otherwise, return the non-zero
> + * value returned from the callback.
> + */
> +int walk_free_mem_block(void *opaque,
> + int min_order,
> + int (*report_pfn_range)(void *opaque,
> + unsigned long pfn,
> + unsigned long num))
> +{
> + struct zone *zone;
> + int order;
> + enum migratetype mt;
> + bool ret;
> +
> + for_each_populated_zone(zone) {
> + for (order = MAX_ORDER - 1; order >= min_order; order--) {
> + for (mt = 0; mt < MIGRATE_TYPES; mt++) {
> + ret = walk_free_page_list(opaque, zone,
> + order, mt,
> + report_pfn_range);
> + if (ret)
> + return ret;
> + }
> + }
> + }
> +
> + return 0;
> +}
> +EXPORT_SYMBOL_GPL(walk_free_mem_block);
> +
> static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
> {
> zoneref->zone = zone;
> --
> 2.7.4
^ permalink raw reply
* Re: [PATCH v25 2/2] virtio-balloon: VIRTIO_BALLOON_F_FREE_PAGE_HINT
From: Michael S. Tsirkin @ 2018-01-25 13:49 UTC (permalink / raw)
To: Wei Wang
Cc: yang.zhang.wz, virtio-dev, riel, quan.xu0, kvm, nilal,
liliang.opensource, linux-kernel, mhocko, linux-mm, pbonzini,
akpm, virtualization
In-Reply-To: <1516871646-22741-3-git-send-email-wei.w.wang@intel.com>
On Thu, Jan 25, 2018 at 05:14:06PM +0800, Wei Wang wrote:
> Negotiation of the VIRTIO_BALLOON_F_FREE_PAGE_HINT feature indicates the
> support of reporting hints of guest free pages to host via virtio-balloon.
>
> Host requests the guest to report free pages by sending a new cmd
> id to the guest via the free_page_report_cmd_id configuration register.
>
> When the guest starts to report, the first element added to the free page
> vq is the cmd id given by host. When the guest finishes the reporting
> of all the free pages, VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID is added
> to the vq to tell host that the reporting is done. Host may also requests
> the guest to stop the reporting in advance by sending the stop cmd id to
> the guest via the configuration register.
>
> Signed-off-by: Wei Wang <wei.w.wang@intel.com>
> Signed-off-by: Liang Li <liang.z.li@intel.com>
> Cc: Michael S. Tsirkin <mst@redhat.com>
> Cc: Michal Hocko <mhocko@kernel.org>
> ---
> drivers/virtio/virtio_balloon.c | 251 ++++++++++++++++++++++++++++++------
> include/uapi/linux/virtio_balloon.h | 7 +
> 2 files changed, 222 insertions(+), 36 deletions(-)
>
> diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
> index a1fb52c..114985b 100644
> --- a/drivers/virtio/virtio_balloon.c
> +++ b/drivers/virtio/virtio_balloon.c
> @@ -51,9 +51,22 @@ MODULE_PARM_DESC(oom_pages, "pages to free on OOM");
> static struct vfsmount *balloon_mnt;
> #endif
>
> +enum virtio_balloon_vq {
> + VIRTIO_BALLOON_VQ_INFLATE,
> + VIRTIO_BALLOON_VQ_DEFLATE,
> + VIRTIO_BALLOON_VQ_STATS,
> + VIRTIO_BALLOON_VQ_FREE_PAGE,
> + VIRTIO_BALLOON_VQ_MAX
> +};
> +
> struct virtio_balloon {
> struct virtio_device *vdev;
> - struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
> + struct virtqueue *inflate_vq, *deflate_vq, *stats_vq, *free_page_vq;
> +
> + /* Balloon's own wq for cpu-intensive work items */
> + struct workqueue_struct *balloon_wq;
> + /* The free page reporting work item submitted to the balloon wq */
> + struct work_struct report_free_page_work;
>
> /* The balloon servicing is delegated to a freezable workqueue. */
> struct work_struct update_balloon_stats_work;
> @@ -63,6 +76,11 @@ struct virtio_balloon {
> spinlock_t stop_update_lock;
> bool stop_update;
>
> + /* The new cmd id received from host */
> + uint32_t cmd_id_received;
> + /* The cmd id that is in use */
> + __virtio32 cmd_id_use;
> +
> /* Waiting for host to ack the pages we released. */
> wait_queue_head_t acked;
>
> @@ -316,17 +334,6 @@ static void stats_handle_request(struct virtio_balloon *vb)
> virtqueue_kick(vq);
> }
>
> -static void virtballoon_changed(struct virtio_device *vdev)
> -{
> - struct virtio_balloon *vb = vdev->priv;
> - unsigned long flags;
> -
> - spin_lock_irqsave(&vb->stop_update_lock, flags);
> - if (!vb->stop_update)
> - queue_work(system_freezable_wq, &vb->update_balloon_size_work);
> - spin_unlock_irqrestore(&vb->stop_update_lock, flags);
> -}
> -
> static inline s64 towards_target(struct virtio_balloon *vb)
> {
> s64 target;
> @@ -343,6 +350,34 @@ static inline s64 towards_target(struct virtio_balloon *vb)
> return target - vb->num_pages;
> }
>
> +static void virtballoon_changed(struct virtio_device *vdev)
> +{
> + struct virtio_balloon *vb = vdev->priv;
> + unsigned long flags;
> + s64 diff = towards_target(vb);
> +
> + if (diff) {
> + spin_lock_irqsave(&vb->stop_update_lock, flags);
> + if (!vb->stop_update)
> + queue_work(system_freezable_wq,
> + &vb->update_balloon_size_work);
> + spin_unlock_irqrestore(&vb->stop_update_lock, flags);
> + }
> +
> + if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
> + virtio_cread(vdev, struct virtio_balloon_config,
> + free_page_report_cmd_id, &vb->cmd_id_received);
> + if (vb->cmd_id_received !=
> + VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID) {
> + spin_lock_irqsave(&vb->stop_update_lock, flags);
> + if (!vb->stop_update)
> + queue_work(vb->balloon_wq,
> + &vb->report_free_page_work);
> + spin_unlock_irqrestore(&vb->stop_update_lock, flags);
> + }
> + }
> +}
> +
> static void update_balloon_size(struct virtio_balloon *vb)
> {
> u32 actual = vb->num_pages;
> @@ -417,42 +452,151 @@ static void update_balloon_size_func(struct work_struct *work)
>
> static int init_vqs(struct virtio_balloon *vb)
> {
> - struct virtqueue *vqs[3];
> - vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
> - static const char * const names[] = { "inflate", "deflate", "stats" };
> - int err, nvqs;
> + struct virtqueue *vqs[VIRTIO_BALLOON_VQ_MAX];
> + vq_callback_t *callbacks[VIRTIO_BALLOON_VQ_MAX];
> + const char *names[VIRTIO_BALLOON_VQ_MAX];
> + struct scatterlist sg;
> + int ret;
>
> /*
> - * We expect two virtqueues: inflate and deflate, and
> - * optionally stat.
> + * Inflateq and deflateq are used unconditionally. The names[]
> + * will be NULL if the related feature is not enabled, which will
> + * cause no allocation for the corresponding virtqueue in find_vqs.
> */
> - nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
> - err = virtio_find_vqs(vb->vdev, nvqs, vqs, callbacks, names, NULL);
> - if (err)
> - return err;
> + callbacks[VIRTIO_BALLOON_VQ_INFLATE] = balloon_ack;
> + names[VIRTIO_BALLOON_VQ_INFLATE] = "inflate";
> + callbacks[VIRTIO_BALLOON_VQ_DEFLATE] = balloon_ack;
> + names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate";
> + names[VIRTIO_BALLOON_VQ_STATS] = NULL;
> + names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
>
> - vb->inflate_vq = vqs[0];
> - vb->deflate_vq = vqs[1];
> if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
> - struct scatterlist sg;
> - unsigned int num_stats;
> - vb->stats_vq = vqs[2];
> + names[VIRTIO_BALLOON_VQ_STATS] = "stats";
> + callbacks[VIRTIO_BALLOON_VQ_STATS] = stats_request;
> + }
> +
> + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
> + names[VIRTIO_BALLOON_VQ_FREE_PAGE] = "free_page_vq";
> + callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
> + }
> +
> + ret = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX,
> + vqs, callbacks, names, NULL, NULL);
> + if (ret)
> + return ret;
>
> + 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)) {
> + vb->stats_vq = vqs[VIRTIO_BALLOON_VQ_STATS];
> /*
> * Prime this virtqueue with one buffer so the hypervisor can
> * use it to signal us later (it can't be broken yet!).
> */
> - num_stats = update_balloon_stats(vb);
> -
> - sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
> - if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL)
> - < 0)
> - BUG();
> + sg_init_one(&sg, vb->stats, sizeof(vb->stats));
> + ret = virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb,
> + GFP_KERNEL);
> + if (ret) {
> + dev_warn(&vb->vdev->dev, "%s: add stat_vq failed\n",
> + __func__);
> + return ret;
> + }
> virtqueue_kick(vb->stats_vq);
> }
> +
> + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
> + vb->free_page_vq = vqs[VIRTIO_BALLOON_VQ_FREE_PAGE];
> +
> return 0;
> }
>
> +static int add_one_sg(struct virtqueue *vq, unsigned long pfn, uint32_t len)
> +{
> + struct scatterlist sg;
> + unsigned int unused;
> + int ret = 0;
> +
> + sg_init_table(&sg, 1);
> + sg_set_page(&sg, pfn_to_page(pfn), len, 0);
> +
> + /* Detach all the used buffers from the vq */
> + while (virtqueue_get_buf(vq, &unused))
> + ;
> +
> + /*
> + * Since this is an optimization feature, losing a couple of free
> + * pages to report isn't important. We simply return without adding
> + * the page if the vq is full.
> + * We are adding one entry each time, which essentially results in no
> + * memory allocation, so the GFP_KERNEL flag below can be ignored.
> + * There is always one entry reserved for the cmd id to use.
> + */
> + if (vq->num_free > 1)
> + ret = virtqueue_add_inbuf(vq, &sg, 1, vq, GFP_KERNEL);
> +
> + if (vq->num_free == virtqueue_get_vring_size(vq) / 2 ||
> + vq->num_free <= 2)
> + virtqueue_kick(vq);
> +
> + return ret;
> +}
> +
> +static int virtio_balloon_send_free_pages(void *opaque, unsigned long pfn,
> + unsigned long nr_pages)
> +{
> + struct virtio_balloon *vb = (struct virtio_balloon *)opaque;
> + uint32_t len = nr_pages << PAGE_SHIFT;
> +
> + /*
> + * If a stop id or a new cmd id was just received from host, stop
> + * the reporting, and return 1 to indicate an active stop.
> + */
> + if (virtio32_to_cpu(vb->vdev, vb->cmd_id_use) != vb->cmd_id_received)
> + return 1;
> +
> + return add_one_sg(vb->free_page_vq, pfn, len);
> +}
> +
> +static int send_cmd_id(struct virtio_balloon *vb, uint32_t cmd_id)
> +{
> + struct scatterlist sg;
> + struct virtqueue *vq = vb->free_page_vq;
> + int ret;
> +
> + vb->cmd_id_use = cpu_to_virtio32(vb->vdev, cmd_id);
> + sg_init_one(&sg, &vb->cmd_id_use, sizeof(vb->cmd_id_use));
> +
> + ret = virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
> + virtqueue_kick(vq);
> +
> + return ret;
> +}
> +
> +static void report_free_page_func(struct work_struct *work)
> +{
> + struct virtio_balloon *vb;
> + int ret;
> +
> + vb = container_of(work, struct virtio_balloon, report_free_page_work);
> +
> + /* Start by sending the received cmd id to host with an outbuf */
> + ret = send_cmd_id(vb, vb->cmd_id_received);
> + if (unlikely(ret))
> + goto err;
> +
> + ret = walk_free_mem_block(vb, 0, &virtio_balloon_send_free_pages);
> + if (unlikely(ret < 0))
> + goto err;
> +
> + /* End by sending a stop id to host with an outbuf */
> + ret = send_cmd_id(vb, VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID);
> + if (likely(!ret))
> + return;
> +err:
> + dev_err(&vb->vdev->dev, "%s failure: free page vq is broken\n",
> + __func__);
> +}
> +
So that's very simple, but it only works well if the whole
free list fits in the queue or host processes the queue faster
than the guest. What if it doesn't?
If we had restartability you could just drop the lock
and wait for a vq interrupt to make more progress, which
would be better I think.
> #ifdef CONFIG_BALLOON_COMPACTION
> /*
> * virtballoon_migratepage - perform the balloon page migration on behalf of
> @@ -537,6 +681,7 @@ static struct file_system_type balloon_fs = {
> static int virtballoon_probe(struct virtio_device *vdev)
> {
> struct virtio_balloon *vb;
> + __u32 poison_val;
> int err;
>
> if (!vdev->config->get) {
> @@ -566,18 +711,39 @@ static int virtballoon_probe(struct virtio_device *vdev)
> if (err)
> goto out_free_vb;
>
> + if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
> + /*
> + * There is always one entry reserved for cmd id, so the ring
> + * size needs to be at least two to report free page hint.
> + */
> + if (virtqueue_get_vring_size(vb->free_page_vq) < 2)
> + goto out_free_vb;
> + vb->balloon_wq = alloc_workqueue("balloon-wq",
> + WQ_FREEZABLE | WQ_CPU_INTENSIVE, 0);
> + if (!vb->balloon_wq) {
> + err = -ENOMEM;
> + goto out_del_vqs;
> + }
> + INIT_WORK(&vb->report_free_page_work, report_free_page_func);
> + if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) {
> + poison_val = PAGE_POISON;
> + virtio_cwrite(vb->vdev, struct virtio_balloon_config,
> + poison_val, &poison_val);
> + }
> + }
> +
> vb->nb.notifier_call = virtballoon_oom_notify;
> vb->nb.priority = VIRTBALLOON_OOM_NOTIFY_PRIORITY;
> err = register_oom_notifier(&vb->nb);
> if (err < 0)
> - goto out_del_vqs;
> + goto out_del_balloon_wq;
>
> #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;
> + goto out_del_balloon_wq;
> }
>
> vb->vb_dev_info.migratepage = virtballoon_migratepage;
> @@ -587,7 +753,7 @@ static int virtballoon_probe(struct virtio_device *vdev)
> kern_unmount(balloon_mnt);
> unregister_oom_notifier(&vb->nb);
> vb->vb_dev_info.inode = NULL;
> - goto out_del_vqs;
> + goto out_del_balloon_wq;
> }
> vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
> #endif
> @@ -598,6 +764,9 @@ static int virtballoon_probe(struct virtio_device *vdev)
> virtballoon_changed(vdev);
> return 0;
>
> +out_del_balloon_wq:
> + if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
> + destroy_workqueue(vb->balloon_wq);
> out_del_vqs:
> vdev->config->del_vqs(vdev);
> out_free_vb:
> @@ -631,6 +800,11 @@ static void virtballoon_remove(struct virtio_device *vdev)
> cancel_work_sync(&vb->update_balloon_size_work);
> cancel_work_sync(&vb->update_balloon_stats_work);
>
> + if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
> + cancel_work_sync(&vb->report_free_page_work);
> + destroy_workqueue(vb->balloon_wq);
> + }
> +
> remove_common(vb);
> #ifdef CONFIG_BALLOON_COMPACTION
> if (vb->vb_dev_info.inode)
> @@ -674,6 +848,9 @@ static int virtballoon_restore(struct virtio_device *vdev)
>
> static int virtballoon_validate(struct virtio_device *vdev)
> {
> + if (!page_poisoning_enabled())
> + __virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON);
> +
> __virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM);
> return 0;
> }
> @@ -682,6 +859,8 @@ static unsigned int features[] = {
> VIRTIO_BALLOON_F_MUST_TELL_HOST,
> VIRTIO_BALLOON_F_STATS_VQ,
> VIRTIO_BALLOON_F_DEFLATE_ON_OOM,
> + VIRTIO_BALLOON_F_FREE_PAGE_HINT,
> + VIRTIO_BALLOON_F_PAGE_POISON,
> };
>
> static struct virtio_driver virtio_balloon_driver = {
> diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h
> index 343d7dd..3f97067 100644
> --- a/include/uapi/linux/virtio_balloon.h
> +++ b/include/uapi/linux/virtio_balloon.h
> @@ -34,15 +34,22 @@
> #define VIRTIO_BALLOON_F_MUST_TELL_HOST 0 /* Tell before reclaiming pages */
> #define VIRTIO_BALLOON_F_STATS_VQ 1 /* Memory Stats virtqueue */
> #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 */
>
> /* Size of a PFN in the balloon interface. */
> #define VIRTIO_BALLOON_PFN_SHIFT 12
>
> +#define VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID 0
> struct virtio_balloon_config {
> /* Number of pages host wants Guest to give up. */
> __u32 num_pages;
> /* Number of pages we've actually got in balloon. */
> __u32 actual;
> + /* Free page report command id, readonly by guest */
> + __u32 free_page_report_cmd_id;
> + /* Stores PAGE_POISON if page poisoning is in use */
> + __u32 poison_val;
> };
>
> #define VIRTIO_BALLOON_S_SWAP_IN 0 /* Amount of memory swapped in */
> --
> 2.7.4
^ permalink raw reply
* [PATCH net] vhost_net: stop device during reset owner
From: Jason Wang @ 2018-01-25 14:03 UTC (permalink / raw)
To: mst, virtualization, netdev, linux-kernel
We don't stop device before reset owner, this means we could try to
serve any virtqueue kick before reset dev->worker. This will result a
warn since the work was pending at llist during owner resetting. Fix
this by stopping device during owner reset.
Reported-by: syzbot+eb17c6162478cc50632c@syzkaller.appspotmail.com
Fixes: 3a4d5c94e9593 ("vhost_net: a kernel-level virtio server")
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/vhost/net.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index c7bdeb6..5636c7c 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1208,6 +1208,7 @@ static long vhost_net_reset_owner(struct vhost_net *n)
}
vhost_net_stop(n, &tx_sock, &rx_sock);
vhost_net_flush(n);
+ vhost_dev_stop(&n->dev);
vhost_dev_reset_owner(&n->dev, umem);
vhost_net_vq_reset(n);
done:
--
2.7.4
^ permalink raw reply related
* Re: [PATCH v24 1/2] mm: support reporting free page blocks
From: Pankaj Gupta @ 2018-01-25 14:56 UTC (permalink / raw)
To: Wei Wang, Michael S. Tsirkin
Cc: yang zhang wz, virtio-dev, quan xu0, kvm, Rik van Riel, nilal,
liliang opensource, linux-kernel, mhocko, linux-mm,
niteshnarayanlal, pbonzini, akpm, virtualization
In-Reply-To: <20180125152933-mutt-send-email-mst@kernel.org>
>
> On Wed, Jan 24, 2018 at 06:42:41PM +0800, Wei Wang wrote:
> > This patch adds support to walk through the free page blocks in the
> > system and report them via a callback function. Some page blocks may
> > leave the free list after zone->lock is released, so it is the caller's
> > responsibility to either detect or prevent the use of such pages.
> >
> > One use example of this patch is to accelerate live migration by skipping
> > the transfer of free pages reported from the guest. A popular method used
> > by the hypervisor to track which part of memory is written during live
> > migration is to write-protect all the guest memory. So, those pages that
> > are reported as free pages but are written after the report function
> > returns will be captured by the hypervisor, and they will be added to the
> > next round of memory transfer.
> >
> > Signed-off-by: Wei Wang <wei.w.wang@intel.com>
> > Signed-off-by: Liang Li <liang.z.li@intel.com>
> > Cc: Michal Hocko <mhocko@kernel.org>
> > Cc: Michael S. Tsirkin <mst@redhat.com>
> > Acked-by: Michal Hocko <mhocko@kernel.org>
> > ---
> > include/linux/mm.h | 6 ++++
> > mm/page_alloc.c | 91
> > ++++++++++++++++++++++++++++++++++++++++++++++++++++++
> > 2 files changed, 97 insertions(+)
> >
> > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > index ea818ff..b3077dd 100644
> > --- a/include/linux/mm.h
> > +++ b/include/linux/mm.h
> > @@ -1938,6 +1938,12 @@ extern void free_area_init_node(int nid, unsigned
> > long * zones_size,
> > unsigned long zone_start_pfn, unsigned long *zholes_size);
> > extern void free_initmem(void);
> >
> > +extern void walk_free_mem_block(void *opaque,
> > + int min_order,
> > + bool (*report_pfn_range)(void *opaque,
> > + unsigned long pfn,
> > + unsigned long num));
> > +
> > /*
> > * Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK)
> > * into the buddy system. The freed pages will be poisoned with pattern
> > diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> > index 76c9688..705de22 100644
> > --- a/mm/page_alloc.c
> > +++ b/mm/page_alloc.c
> > @@ -4899,6 +4899,97 @@ void show_free_areas(unsigned int filter, nodemask_t
> > *nodemask)
> > show_swap_cache_info();
> > }
> >
> > +/*
> > + * Walk through a free page list and report the found pfn range via the
> > + * callback.
> > + *
> > + * Return false if the callback requests to stop reporting. Otherwise,
> > + * return true.
> > + */
> > +static bool walk_free_page_list(void *opaque,
> > + struct zone *zone,
> > + int order,
> > + enum migratetype mt,
> > + bool (*report_pfn_range)(void *,
> > + unsigned long,
> > + unsigned long))
> > +{
> > + struct page *page;
> > + struct list_head *list;
> > + unsigned long pfn, flags;
> > + bool ret;
> > +
> > + spin_lock_irqsave(&zone->lock, flags);
> > + list = &zone->free_area[order].free_list[mt];
> > + list_for_each_entry(page, list, lru) {
> > + pfn = page_to_pfn(page);
> > + ret = report_pfn_range(opaque, pfn, 1 << order);
> > + if (!ret)
> > + break;
> > + }
> > + spin_unlock_irqrestore(&zone->lock, flags);
> > +
> > + return ret;
> > +}
>
> There are two issues with this API. One is that it is not
> restarteable: if you return false, you start from the
> beginning. So no way to drop lock, do something slow
> and then proceed.
>
> Another is that you are using it to report free page hints. Presumably
> the point is to drop these pages - keeping them near head of the list
> and reusing the reported ones will just make everything slower
> invalidating the hint.
I think that's where patches[1] by 'Nitesh' will help: This patch-set
will send free page hints transparently to host and host decides to delete such
pages.
If I compare with patchset by 'Wei', host gets/asks free page hints and ignore
such pages during live migration. But as already discussed, if free pages are
still in guest memory there is no point of traversing & getting all such pages
again.
[1] https://www.spinics.net/lists/kvm/msg159790.html
>
> How about rotating these pages towards the end of the list?
> Probably not on each call, callect reported pages and then
> move them to tail when we exit.
>
> Of course it's possible not all reporters want this.
> So maybe change the callback to return int:
> 0 - page reported, move page to end of free list
> > 0 - page skipped, proceed
> < 0 - stop processing
>
>
> > +
> > +/**
> > + * walk_free_mem_block - Walk through the free page blocks in the system
> > + * @opaque: the context passed from the caller
> > + * @min_order: the minimum order of free lists to check
> > + * @report_pfn_range: the callback to report the pfn range of the free
> > pages
> > + *
> > + * If the callback returns false, stop iterating the list of free page
> > blocks.
> > + * Otherwise, continue to report.
> > + *
> > + * Please note that there are no locking guarantees for the callback and
> > + * that the reported pfn range might be freed or disappear after the
> > + * callback returns so the caller has to be very careful how it is used.
> > + *
> > + * The callback itself must not sleep or perform any operations which
> > would
> > + * require any memory allocations directly (not even
> > GFP_NOWAIT/GFP_ATOMIC)
> > + * or via any lock dependency. It is generally advisable to implement
> > + * the callback as simple as possible and defer any heavy lifting to a
> > + * different context.
> > + *
> > + * There is no guarantee that each free range will be reported only once
> > + * during one walk_free_mem_block invocation.
> > + *
> > + * pfn_to_page on the given range is strongly discouraged and if there is
> > + * an absolute need for that make sure to contact MM people to discuss
> > + * potential problems.
> > + *
> > + * The function itself might sleep so it cannot be called from atomic
> > + * contexts.
> > + *
> > + * In general low orders tend to be very volatile and so it makes more
> > + * sense to query larger ones first for various optimizations which like
> > + * ballooning etc... This will reduce the overhead as well.
> > + */
> > +void walk_free_mem_block(void *opaque,
> > + int min_order,
> > + bool (*report_pfn_range)(void *opaque,
> > + unsigned long pfn,
> > + unsigned long num))
> > +{
> > + struct zone *zone;
> > + int order;
> > + enum migratetype mt;
> > + bool ret;
> > +
> > + for_each_populated_zone(zone) {
> > + for (order = MAX_ORDER - 1; order >= min_order; order--) {
> > + for (mt = 0; mt < MIGRATE_TYPES; mt++) {
> > + ret = walk_free_page_list(opaque, zone,
> > + order, mt,
> > + report_pfn_range);
> > + if (!ret)
> > + return;
> > + }
> > + }
> > + }
> > +}
> > +EXPORT_SYMBOL_GPL(walk_free_mem_block);
> > +
>
> I think callers need a way to
> 1. distinguish between completion and exit on error
> 2. restart from where we stopped
>
> So I would both accept and return the current zone
> and a special value to mean "complete"
>
> > static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
> > {
> > zoneref->zone = zone;
> > --
> > 2.7.4
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
>
^ permalink raw reply
* Re: [PATCH v24 1/2] mm: support reporting free page blocks
From: Michael S. Tsirkin @ 2018-01-25 17:31 UTC (permalink / raw)
To: Pankaj Gupta
Cc: yang zhang wz, virtio-dev, quan xu0, kvm, Rik van Riel, nilal,
liliang opensource, linux-kernel, virtualization, linux-mm,
niteshnarayanlal, pbonzini, akpm, mhocko
In-Reply-To: <1582107341.3995759.1516892161298.JavaMail.zimbra@redhat.com>
On Thu, Jan 25, 2018 at 09:56:01AM -0500, Pankaj Gupta wrote:
>
> >
> > On Wed, Jan 24, 2018 at 06:42:41PM +0800, Wei Wang wrote:
> > > This patch adds support to walk through the free page blocks in the
> > > system and report them via a callback function. Some page blocks may
> > > leave the free list after zone->lock is released, so it is the caller's
> > > responsibility to either detect or prevent the use of such pages.
> > >
> > > One use example of this patch is to accelerate live migration by skipping
> > > the transfer of free pages reported from the guest. A popular method used
> > > by the hypervisor to track which part of memory is written during live
> > > migration is to write-protect all the guest memory. So, those pages that
> > > are reported as free pages but are written after the report function
> > > returns will be captured by the hypervisor, and they will be added to the
> > > next round of memory transfer.
> > >
> > > Signed-off-by: Wei Wang <wei.w.wang@intel.com>
> > > Signed-off-by: Liang Li <liang.z.li@intel.com>
> > > Cc: Michal Hocko <mhocko@kernel.org>
> > > Cc: Michael S. Tsirkin <mst@redhat.com>
> > > Acked-by: Michal Hocko <mhocko@kernel.org>
> > > ---
> > > include/linux/mm.h | 6 ++++
> > > mm/page_alloc.c | 91
> > > ++++++++++++++++++++++++++++++++++++++++++++++++++++++
> > > 2 files changed, 97 insertions(+)
> > >
> > > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > > index ea818ff..b3077dd 100644
> > > --- a/include/linux/mm.h
> > > +++ b/include/linux/mm.h
> > > @@ -1938,6 +1938,12 @@ extern void free_area_init_node(int nid, unsigned
> > > long * zones_size,
> > > unsigned long zone_start_pfn, unsigned long *zholes_size);
> > > extern void free_initmem(void);
> > >
> > > +extern void walk_free_mem_block(void *opaque,
> > > + int min_order,
> > > + bool (*report_pfn_range)(void *opaque,
> > > + unsigned long pfn,
> > > + unsigned long num));
> > > +
> > > /*
> > > * Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK)
> > > * into the buddy system. The freed pages will be poisoned with pattern
> > > diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> > > index 76c9688..705de22 100644
> > > --- a/mm/page_alloc.c
> > > +++ b/mm/page_alloc.c
> > > @@ -4899,6 +4899,97 @@ void show_free_areas(unsigned int filter, nodemask_t
> > > *nodemask)
> > > show_swap_cache_info();
> > > }
> > >
> > > +/*
> > > + * Walk through a free page list and report the found pfn range via the
> > > + * callback.
> > > + *
> > > + * Return false if the callback requests to stop reporting. Otherwise,
> > > + * return true.
> > > + */
> > > +static bool walk_free_page_list(void *opaque,
> > > + struct zone *zone,
> > > + int order,
> > > + enum migratetype mt,
> > > + bool (*report_pfn_range)(void *,
> > > + unsigned long,
> > > + unsigned long))
> > > +{
> > > + struct page *page;
> > > + struct list_head *list;
> > > + unsigned long pfn, flags;
> > > + bool ret;
> > > +
> > > + spin_lock_irqsave(&zone->lock, flags);
> > > + list = &zone->free_area[order].free_list[mt];
> > > + list_for_each_entry(page, list, lru) {
> > > + pfn = page_to_pfn(page);
> > > + ret = report_pfn_range(opaque, pfn, 1 << order);
> > > + if (!ret)
> > > + break;
> > > + }
> > > + spin_unlock_irqrestore(&zone->lock, flags);
> > > +
> > > + return ret;
> > > +}
> >
> > There are two issues with this API. One is that it is not
> > restarteable: if you return false, you start from the
> > beginning. So no way to drop lock, do something slow
> > and then proceed.
> >
> > Another is that you are using it to report free page hints. Presumably
> > the point is to drop these pages - keeping them near head of the list
> > and reusing the reported ones will just make everything slower
> > invalidating the hint.
>
> I think that's where patches[1] by 'Nitesh' will help: This patch-set
> will send free page hints transparently to host and host decides to delete such
> pages.
>
> If I compare with patchset by 'Wei', host gets/asks free page hints and ignore
> such pages during live migration. But as already discussed, if free pages are
> still in guest memory there is no point of traversing & getting all such pages
> again.
>
> [1] https://www.spinics.net/lists/kvm/msg159790.html
The main difference between Wei's and Nitesh's patches add hints to page
alloc/free path. It's this more risky performance-wise: you need to
enable it at guest boot, not just at migration time.
Maybe the overhead isn't big, unfortunately no one posted any
numbers yet.
--
MST
^ permalink raw reply
* Re: [PATCH v25 1/2 RESEND] mm: support reporting free page blocks
From: Andrew Morton @ 2018-01-25 22:41 UTC (permalink / raw)
To: Wei Wang
Cc: yang.zhang.wz, virtio-dev, riel, quan.xu0, kvm, mst, nilal,
liliang.opensource, linux-kernel, virtualization, linux-mm,
pbonzini, mhocko
In-Reply-To: <1516873107-34950-1-git-send-email-wei.w.wang@intel.com>
On Thu, 25 Jan 2018 17:38:27 +0800 Wei Wang <wei.w.wang@intel.com> wrote:
> This patch adds support to walk through the free page blocks in the
> system and report them via a callback function. Some page blocks may
> leave the free list after zone->lock is released, so it is the caller's
> responsibility to either detect or prevent the use of such pages.
>
> One use example of this patch is to accelerate live migration by skipping
> the transfer of free pages reported from the guest. A popular method used
> by the hypervisor to track which part of memory is written during live
> migration is to write-protect all the guest memory. So, those pages that
> are reported as free pages but are written after the report function
> returns will be captured by the hypervisor, and they will be added to the
> next round of memory transfer.
It would be useful if we had some quantitative testing results, so we
can see the real-world benefits from this change?
^ permalink raw reply
* [PATCH net-next 09/12] tools/virtio: switch to __ptr_ring_empty
From: Michael S. Tsirkin @ 2018-01-25 23:36 UTC (permalink / raw)
To: linux-kernel; +Cc: netdev, John Fastabend, David Miller, virtualization
In-Reply-To: <1516923320-16959-1-git-send-email-mst@redhat.com>
We don't rely on lockless guarantees, but it
seems cleaner than inverting __ptr_ring_peek.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
tools/virtio/ringtest/ptr_ring.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/virtio/ringtest/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c
index e6e8130..477899c 100644
--- a/tools/virtio/ringtest/ptr_ring.c
+++ b/tools/virtio/ringtest/ptr_ring.c
@@ -187,7 +187,7 @@ bool enable_kick()
bool avail_empty()
{
- return !__ptr_ring_peek(&array);
+ return __ptr_ring_empty(&array);
}
bool use_buf(unsigned *lenp, void **bufp)
--
MST
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox