On 6/4/19 3:12 AM, David Hildenbrand wrote: > On 04.06.19 00:38, Alexander Duyck wrote: >> On Mon, Jun 3, 2019 at 10:04 AM Nitesh Narayan Lal wrote: >>> Enables the kernel to negotiate VIRTIO_BALLOON_F_HINTING feature with the >>> host. If it is available and page_hinting_flag is set to true, page_hinting >>> is enabled and its callbacks are configured along with the max_pages count >>> which indicates the maximum number of pages that can be isolated and hinted >>> at a time. Currently, only free pages of order >= (MAX_ORDER - 2) are >>> reported. To prevent any false OOM max_pages count is set to 16. >>> >>> By default page_hinting feature is enabled and gets loaded as soon >>> as the virtio-balloon driver is loaded. However, it could be disabled >>> by writing the page_hinting_flag which is a virtio-balloon parameter. >>> >>> Signed-off-by: Nitesh Narayan Lal >>> --- >>> drivers/virtio/virtio_balloon.c | 112 +++++++++++++++++++++++++++- >>> include/uapi/linux/virtio_balloon.h | 14 ++++ >>> 2 files changed, 125 insertions(+), 1 deletion(-) >>> >>> diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c >>> index f19061b585a4..40f09ea31643 100644 >>> --- a/drivers/virtio/virtio_balloon.c >>> +++ b/drivers/virtio/virtio_balloon.c >>> @@ -31,6 +31,7 @@ >>> #include >>> #include >>> #include >>> +#include >>> >>> /* >>> * Balloon device works in 4K page units. So each page is pointed to by >>> @@ -48,6 +49,7 @@ >>> /* The size of a free page block in bytes */ >>> #define VIRTIO_BALLOON_FREE_PAGE_SIZE \ >>> (1 << (VIRTIO_BALLOON_FREE_PAGE_ORDER + PAGE_SHIFT)) >>> +#define VIRTIO_BALLOON_PAGE_HINTING_MAX_PAGES 16 >>> >>> #ifdef CONFIG_BALLOON_COMPACTION >>> static struct vfsmount *balloon_mnt; >>> @@ -58,6 +60,7 @@ enum virtio_balloon_vq { >>> VIRTIO_BALLOON_VQ_DEFLATE, >>> VIRTIO_BALLOON_VQ_STATS, >>> VIRTIO_BALLOON_VQ_FREE_PAGE, >>> + VIRTIO_BALLOON_VQ_HINTING, >>> VIRTIO_BALLOON_VQ_MAX >>> }; >>> >>> @@ -67,7 +70,8 @@ enum virtio_balloon_config_read { >>> >>> struct virtio_balloon { >>> struct virtio_device *vdev; >>> - struct virtqueue *inflate_vq, *deflate_vq, *stats_vq, *free_page_vq; >>> + struct virtqueue *inflate_vq, *deflate_vq, *stats_vq, *free_page_vq, >>> + *hinting_vq; >>> >>> /* Balloon's own wq for cpu-intensive work items */ >>> struct workqueue_struct *balloon_wq; >>> @@ -125,6 +129,9 @@ struct virtio_balloon { >>> >>> /* To register a shrinker to shrink memory upon memory pressure */ >>> struct shrinker shrinker; >>> + >>> + /* object pointing at the array of isolated pages ready for hinting */ >>> + struct hinting_data *hinting_arr; >> Just make this an array of size VIRTIO_BALLOON_PAGE_HINTING_MAX_PAGES. >> It will save a bunch of complexity later. > +1 > > [...] >>> +struct virtio_balloon *hvb; >>> +bool page_hinting_flag = true; >>> +module_param(page_hinting_flag, bool, 0444); >>> +MODULE_PARM_DESC(page_hinting_flag, "Enable page hinting"); >>> + >>> +static bool virtqueue_kick_sync(struct virtqueue *vq) >>> +{ >>> + u32 len; >>> + >>> + if (likely(virtqueue_kick(vq))) { >>> + while (!virtqueue_get_buf(vq, &len) && >>> + !virtqueue_is_broken(vq)) >>> + cpu_relax(); >>> + return true; >> Is this a synchronous setup? It seems kind of wasteful to have a >> thread busy waiting here like this. It might make more sense to just >> make this work like the other balloon queues and have a wait event >> with a wake up in the interrupt handler for the queue. > +1 > > [...] > >>> + gpaddr = virt_to_phys(hvb->hinting_arr); >>> + hint_req->phys_addr = cpu_to_virtio64(hvb->vdev, gpaddr); >>> + hint_req->size = cpu_to_virtio32(hvb->vdev, entries); >>> + sg_init_one(&sg, hint_req, sizeof(*hint_req)); >>> + err = virtqueue_add_outbuf(vq, &sg, 1, hint_req, GFP_KERNEL); >>> + if (!err) >>> + virtqueue_kick_sync(hvb->hinting_vq); >>> + >>> + kfree(hint_req); >>> +} >>> + >>> +int page_hinting_prepare(void) >>> +{ >>> + hvb->hinting_arr = kmalloc_array(VIRTIO_BALLOON_PAGE_HINTING_MAX_PAGES, >>> + sizeof(*hvb->hinting_arr), GFP_KERNEL); >>> + if (!hvb->hinting_arr) >>> + return -ENOMEM; >>> + return 0; >>> +} >>> + >> Why make the hinting_arr a dynamic allocation? You should probably >> just make it a static array within the virtio_balloon structure. Then >> you don't have the risk of an allocation failing and messing up the >> hints. > +1 > >>> +void hint_pages(struct list_head *pages) >>> +{ >>> + struct page *page, *next; >>> + unsigned long pfn; >>> + int idx = 0, order; >>> + >>> + list_for_each_entry_safe(page, next, pages, lru) { >>> + pfn = page_to_pfn(page); >>> + order = page_private(page); >>> + hvb->hinting_arr[idx].phys_addr = pfn << PAGE_SHIFT; >>> + hvb->hinting_arr[idx].size = (1 << order) * PAGE_SIZE; >>> + idx++; >>> + } >>> + page_hinting_report(idx); >>> +} >>> + >> Getting back to my suggestion from earlier today. It might make sense >> to not bother with the PAGE_SHIFT or PAGE_SIZE multiplication if you >> just record everything in VIRTIO_BALLOON_PAGES intead of using the >> actual address and size. > I think I prefer "addr + size". > >> Same comment here. Make this array a part of virtio_balloon and you >> don't have to free it. >> >>> +static const struct page_hinting_cb hcb = { >>> + .prepare = page_hinting_prepare, >>> + .hint_pages = hint_pages, >>> + .cleanup = page_hinting_cleanup, >>> + .max_pages = VIRTIO_BALLOON_PAGE_HINTING_MAX_PAGES, >>> +}; >> With the above changes prepare and cleanup can be dropped. > +1 > >>> +#endif >>> + >>> static u32 page_to_balloon_pfn(struct page *page) >>> { >>> unsigned long pfn = page_to_pfn(page); >>> @@ -488,6 +574,7 @@ static int init_vqs(struct virtio_balloon *vb) >>> names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate"; >>> names[VIRTIO_BALLOON_VQ_STATS] = NULL; >>> names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; >>> + names[VIRTIO_BALLOON_VQ_HINTING] = NULL; >>> >>> if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) { >>> names[VIRTIO_BALLOON_VQ_STATS] = "stats"; >>> @@ -499,11 +586,18 @@ static int init_vqs(struct virtio_balloon *vb) >>> callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; >>> } >>> >>> + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_HINTING)) { >>> + names[VIRTIO_BALLOON_VQ_HINTING] = "hinting_vq"; >>> + callbacks[VIRTIO_BALLOON_VQ_HINTING] = NULL; >>> + } >>> err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX, >>> vqs, callbacks, names, NULL, NULL); >>> if (err) >>> return err; >>> >>> + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_HINTING)) >>> + vb->hinting_vq = vqs[VIRTIO_BALLOON_VQ_HINTING]; >>> + >>> 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)) { >>> @@ -942,6 +1036,14 @@ static int virtballoon_probe(struct virtio_device *vdev) >>> if (err) >>> goto out_del_balloon_wq; >>> } >>> + >>> +#ifdef CONFIG_PAGE_HINTING >>> + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_HINTING) && >>> + page_hinting_flag) { >>> + hvb = vb; >>> + page_hinting_enable(&hcb); >>> + } >>> +#endif >>> virtio_device_ready(vdev); >>> >>> if (towards_target(vb)) >>> @@ -989,6 +1091,12 @@ static void virtballoon_remove(struct virtio_device *vdev) >>> destroy_workqueue(vb->balloon_wq); >>> } >>> >>> +#ifdef CONFIG_PAGE_HINTING >>> + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_HINTING)) { > Nitesh, you should only disable if you actually enabled it > (page_hinting_flag). +1, thanks. > > -- Regards Nitesh