Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:
 "virtio, vhost: fixes, tweaks

  No new features but a bunch of tweaks such as switching balloon from
  oom notifier to shrinker"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  vhost/scsi: increase VHOST_SCSI_PREALLOC_PROT_SGLS to 2048
  vhost: allow vhost-scsi driver to be built-in
  virtio: pci-legacy: Validate queue pfn
  virtio: mmio-v1: Validate queue PFN
  virtio_balloon: replace oom notifier with shrinker
  virtio-balloon: kzalloc the vb struct
  virtio-balloon: remove BUG() in init_vqs

5 files changed, 99 insertions, 64 deletions

diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig
index cfdecea..b580885 100644
--- a/drivers/vhost/Kconfig
+++ b/drivers/vhost/Kconfig
@@ -12,7 +12,7 @@ config VHOST_NET
 
 config VHOST_SCSI
 	tristate "VHOST_SCSI TCM fabric driver"
-	depends on TARGET_CORE && EVENTFD && m
+	depends on TARGET_CORE && EVENTFD
 	select VHOST
 	default n
 	---help---
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 76f8d64..c24bb69 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -55,7 +55,7 @@
 #define VHOST_SCSI_DEFAULT_TAGS 256
 #define VHOST_SCSI_PREALLOC_SGLS 2048
 #define VHOST_SCSI_PREALLOC_UPAGES 2048
-#define VHOST_SCSI_PREALLOC_PROT_SGLS 512
+#define VHOST_SCSI_PREALLOC_PROT_SGLS 2048
 
 struct vhost_scsi_inflight {
 	/* Wait for the flush operation to finish */
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 3988c09..d1c1f62 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -27,7 +27,6 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/balloon_compaction.h>
-#include <linux/oom.h>
 #include <linux/wait.h>
 #include <linux/mm.h>
 #include <linux/mount.h>
@@ -40,13 +39,8 @@
  */
 #define VIRTIO_BALLOON_PAGES_PER_PAGE (unsigned)(PAGE_SIZE >> VIRTIO_BALLOON_PFN_SHIFT)
 #define VIRTIO_BALLOON_ARRAY_PFNS_MAX 256
-#define OOM_VBALLOON_DEFAULT_PAGES 256
 #define VIRTBALLOON_OOM_NOTIFY_PRIORITY 80
 
-static int oom_pages = OOM_VBALLOON_DEFAULT_PAGES;
-module_param(oom_pages, int, S_IRUSR | S_IWUSR);
-MODULE_PARM_DESC(oom_pages, "pages to free on OOM");
-
 #ifdef CONFIG_BALLOON_COMPACTION
 static struct vfsmount *balloon_mnt;
 #endif
@@ -86,8 +80,8 @@ struct virtio_balloon {
 	/* Memory statistics */
 	struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
 
-	/* To register callback in oom notifier call chain */
-	struct notifier_block nb;
+	/* To register a shrinker to shrink memory upon memory pressure */
+	struct shrinker shrinker;
 };
 
 static struct virtio_device_id id_table[] = {
@@ -365,38 +359,6 @@ static void update_balloon_size(struct virtio_balloon *vb)
 		      &actual);
 }
 
-/*
- * virtballoon_oom_notify - release pages when system is under severe
- *			    memory pressure (called from out_of_memory())
- * @self : notifier block struct
- * @dummy: not used
- * @parm : returned - number of freed pages
- *
- * The balancing of memory by use of the virtio balloon should not cause
- * the termination of processes while there are pages in the balloon.
- * If virtio balloon manages to release some memory, it will make the
- * system return and retry the allocation that forced the OOM killer
- * to run.
- */
-static int virtballoon_oom_notify(struct notifier_block *self,
-				  unsigned long dummy, void *parm)
-{
-	struct virtio_balloon *vb;
-	unsigned long *freed;
-	unsigned num_freed_pages;
-
-	vb = container_of(self, struct virtio_balloon, nb);
-	if (!virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
-		return NOTIFY_OK;
-
-	freed = parm;
-	num_freed_pages = leak_balloon(vb, oom_pages);
-	update_balloon_size(vb);
-	*freed += num_freed_pages;
-
-	return NOTIFY_OK;
-}
-
 static void update_balloon_stats_func(struct work_struct *work)
 {
 	struct virtio_balloon *vb;
@@ -455,9 +417,13 @@ static int init_vqs(struct virtio_balloon *vb)
 		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();
+		err = virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb,
+					   GFP_KERNEL);
+		if (err) {
+			dev_warn(&vb->vdev->dev, "%s: add stat_vq failed\n",
+				 __func__);
+			return err;
+		}
 		virtqueue_kick(vb->stats_vq);
 	}
 	return 0;
@@ -546,6 +512,52 @@ static struct file_system_type balloon_fs = {
 
 #endif /* CONFIG_BALLOON_COMPACTION */
 
+static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker,
+						  struct shrink_control *sc)
+{
+	unsigned long pages_to_free, pages_freed = 0;
+	struct virtio_balloon *vb = container_of(shrinker,
+					struct virtio_balloon, shrinker);
+
+	pages_to_free = sc->nr_to_scan * VIRTIO_BALLOON_PAGES_PER_PAGE;
+
+	/*
+	 * One invocation of leak_balloon can deflate at most
+	 * VIRTIO_BALLOON_ARRAY_PFNS_MAX balloon pages, so we call it
+	 * multiple times to deflate pages till reaching pages_to_free.
+	 */
+	while (vb->num_pages && pages_to_free) {
+		pages_to_free -= pages_freed;
+		pages_freed += leak_balloon(vb, pages_to_free);
+	}
+	update_balloon_size(vb);
+
+	return pages_freed / VIRTIO_BALLOON_PAGES_PER_PAGE;
+}
+
+static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker,
+						   struct shrink_control *sc)
+{
+	struct virtio_balloon *vb = container_of(shrinker,
+					struct virtio_balloon, shrinker);
+
+	return vb->num_pages / VIRTIO_BALLOON_PAGES_PER_PAGE;
+}
+
+static void virtio_balloon_unregister_shrinker(struct virtio_balloon *vb)
+{
+	unregister_shrinker(&vb->shrinker);
+}
+
+static int virtio_balloon_register_shrinker(struct virtio_balloon *vb)
+{
+	vb->shrinker.scan_objects = virtio_balloon_shrinker_scan;
+	vb->shrinker.count_objects = virtio_balloon_shrinker_count;
+	vb->shrinker.seeks = DEFAULT_SEEKS;
+
+	return register_shrinker(&vb->shrinker);
+}
+
 static int virtballoon_probe(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb;
@@ -557,7 +569,7 @@ static int virtballoon_probe(struct virtio_device *vdev)
 		return -EINVAL;
 	}
 
-	vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL);
+	vdev->priv = vb = kzalloc(sizeof(*vb), GFP_KERNEL);
 	if (!vb) {
 		err = -ENOMEM;
 		goto out;
@@ -566,8 +578,6 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	INIT_WORK(&vb->update_balloon_stats_work, update_balloon_stats_func);
 	INIT_WORK(&vb->update_balloon_size_work, update_balloon_size_func);
 	spin_lock_init(&vb->stop_update_lock);
-	vb->stop_update = false;
-	vb->num_pages = 0;
 	mutex_init(&vb->balloon_lock);
 	init_waitqueue_head(&vb->acked);
 	vb->vdev = vdev;
@@ -578,17 +588,10 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	if (err)
 		goto out_free_vb;
 
-	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;
-
 #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;
 	}
 
@@ -597,13 +600,19 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	if (IS_ERR(vb->vb_dev_info.inode)) {
 		err = PTR_ERR(vb->vb_dev_info.inode);
 		kern_unmount(balloon_mnt);
-		unregister_oom_notifier(&vb->nb);
-		vb->vb_dev_info.inode = NULL;
 		goto out_del_vqs;
 	}
 	vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
 #endif
-
+	/*
+	 * We continue to use VIRTIO_BALLOON_F_DEFLATE_ON_OOM to decide if a
+	 * shrinker needs to be registered to relieve memory pressure.
+	 */
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) {
+		err = virtio_balloon_register_shrinker(vb);
+		if (err)
+			goto out_del_vqs;
+	}
 	virtio_device_ready(vdev);
 
 	if (towards_target(vb))
@@ -635,8 +644,8 @@ static void virtballoon_remove(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb = vdev->priv;
 
-	unregister_oom_notifier(&vb->nb);
-
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
+		virtio_balloon_unregister_shrinker(vb);
 	spin_lock_irq(&vb->stop_update_lock);
 	vb->stop_update = true;
 	spin_unlock_irq(&vb->stop_update_lock);
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index 67763d3..4cd9ea5 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -397,9 +397,23 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 	/* Activate the queue */
 	writel(virtqueue_get_vring_size(vq), vm_dev->base + VIRTIO_MMIO_QUEUE_NUM);
 	if (vm_dev->version == 1) {
+		u64 q_pfn = virtqueue_get_desc_addr(vq) >> PAGE_SHIFT;
+
+		/*
+		 * virtio-mmio v1 uses a 32bit QUEUE PFN. If we have something
+		 * that doesn't fit in 32bit, fail the setup rather than
+		 * pretending to be successful.
+		 */
+		if (q_pfn >> 32) {
+			dev_err(&vdev->dev,
+				"platform bug: legacy virtio-mmio must not be used with RAM above 0x%llxGB\n",
+				0x1ULL << (32 + PAGE_SHIFT - 30));
+			err = -E2BIG;
+			goto error_bad_pfn;
+		}
+
 		writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_QUEUE_ALIGN);
-		writel(virtqueue_get_desc_addr(vq) >> PAGE_SHIFT,
-				vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+		writel(q_pfn, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
 	} else {
 		u64 addr;
 
@@ -430,6 +444,8 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 
 	return vq;
 
+error_bad_pfn:
+	vring_del_virtqueue(vq);
 error_new_virtqueue:
 	if (vm_dev->version == 1) {
 		writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index 2780886..de062fb 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -122,6 +122,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	struct virtqueue *vq;
 	u16 num;
 	int err;
+	u64 q_pfn;
 
 	/* Select the queue we're interested in */
 	iowrite16(index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
@@ -141,9 +142,17 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	if (!vq)
 		return ERR_PTR(-ENOMEM);
 
+	q_pfn = virtqueue_get_desc_addr(vq) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT;
+	if (q_pfn >> 32) {
+		dev_err(&vp_dev->pci_dev->dev,
+			"platform bug: legacy virtio-mmio must not be used with RAM above 0x%llxGB\n",
+			0x1ULL << (32 + PAGE_SHIFT - 30));
+		err = -E2BIG;
+		goto out_del_vq;
+	}
+
 	/* activate the queue */
-	iowrite32(virtqueue_get_desc_addr(vq) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT,
-		  vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+	iowrite32(q_pfn, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
 
 	vq->priv = (void __force *)vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY;
 
@@ -160,6 +169,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 
 out_deactivate:
 	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+out_del_vq:
 	vring_del_virtqueue(vq);
 	return ERR_PTR(err);
 }