3 files changed, 165 insertions, 21 deletions

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 9dd588042880..bfec7c29486d 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -24,11 +24,12 @@
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 #include <linux/delay.h>
+#include <linux/slab.h>
 
 struct virtio_balloon
 {
         struct virtio_device *vdev;
-        struct virtqueue *inflate_vq, *deflate_vq;
+        struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
 
         /* Where the ballooning thread waits for config to change. */
         wait_queue_head_t config_change;
@@ -49,6 +50,10 @@ struct virtio_balloon
         /* The array of pfns we tell the Host about. */
         unsigned int num_pfns;
         u32 pfns[256];
+
+        /* Memory statistics */
+        int need_stats_update;
+        struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
 };
 
 static struct virtio_device_id id_table[] = {
@@ -98,7 +103,8 @@ static void fill_balloon(struct virtio_balloon *vb, size_t num)
         num = min(num, ARRAY_SIZE(vb->pfns));
 
         for (vb->num_pfns = 0; vb->num_pfns < num; vb->num_pfns++) {
-                struct page *page = alloc_page(GFP_HIGHUSER | __GFP_NORETRY);
+                struct page *page = alloc_page(GFP_HIGHUSER | __GFP_NORETRY |
+                                        __GFP_NOMEMALLOC | __GFP_NOWARN);
                 if (!page) {
                         if (printk_ratelimit())
                                 dev_printk(KERN_INFO, &vb->vdev->dev,
@@ -154,6 +160,72 @@ static void leak_balloon(struct virtio_balloon *vb, size_t num)
         }
 }
 
+static inline void update_stat(struct virtio_balloon *vb, int idx,
+                               u16 tag, u64 val)
+{
+        BUG_ON(idx >= VIRTIO_BALLOON_S_NR);
+        vb->stats[idx].tag = tag;
+        vb->stats[idx].val = val;
+}
+
+#define pages_to_bytes(x) ((u64)(x) << PAGE_SHIFT)
+
+static void update_balloon_stats(struct virtio_balloon *vb)
+{
+        unsigned long events[NR_VM_EVENT_ITEMS];
+        struct sysinfo i;
+        int idx = 0;
+
+        all_vm_events(events);
+        si_meminfo(&i);
+
+        update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_IN,
+                                pages_to_bytes(events[PSWPIN]));
+        update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_OUT,
+                                pages_to_bytes(events[PSWPOUT]));
+        update_stat(vb, idx++, VIRTIO_BALLOON_S_MAJFLT, events[PGMAJFAULT]);
+        update_stat(vb, idx++, VIRTIO_BALLOON_S_MINFLT, events[PGFAULT]);
+        update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMFREE,
+                                pages_to_bytes(i.freeram));
+        update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMTOT,
+                                pages_to_bytes(i.totalram));
+}
+
+/*
+ * While most virtqueues communicate guest-initiated requests to the hypervisor,
+ * the stats queue operates in reverse.  The driver initializes the virtqueue
+ * with a single buffer.  From that point forward, all conversations consist of
+ * a hypervisor request (a call to this function) which directs us to refill
+ * the virtqueue with a fresh stats buffer.  Since stats collection can sleep,
+ * we notify our kthread which does the actual work via stats_handle_request().
+ */
+static void stats_request(struct virtqueue *vq)
+{
+        struct virtio_balloon *vb;
+        unsigned int len;
+
+        vb = vq->vq_ops->get_buf(vq, &len);
+        if (!vb)
+                return;
+        vb->need_stats_update = 1;
+        wake_up(&vb->config_change);
+}
+
+static void stats_handle_request(struct virtio_balloon *vb)
+{
+        struct virtqueue *vq;
+        struct scatterlist sg;
+
+        vb->need_stats_update = 0;
+        update_balloon_stats(vb);
+
+        vq = vb->stats_vq;
+        sg_init_one(&sg, vb->stats, sizeof(vb->stats));
+        if (vq->vq_ops->add_buf(vq, &sg, 1, 0, vb) < 0)
+                BUG();
+        vq->vq_ops->kick(vq);
+}
+
 static void virtballoon_changed(struct virtio_device *vdev)
 {
         struct virtio_balloon *vb = vdev->priv;
@@ -190,8 +262,11 @@ static int balloon(void *_vballoon)
                 try_to_freeze();
                 wait_event_interruptible(vb->config_change,
                                          (diff = towards_target(vb)) != 0
+                                         || vb->need_stats_update
                                          || kthread_should_stop()
                                          || freezing(current));
+                if (vb->need_stats_update)
+                        stats_handle_request(vb);
                 if (diff > 0)
                         fill_balloon(vb, diff);
                 else if (diff < 0)
@@ -204,10 +279,10 @@ static int balloon(void *_vballoon)
 static int virtballoon_probe(struct virtio_device *vdev)
 {
         struct virtio_balloon *vb;
-        struct virtqueue *vqs[2];
-        vq_callback_t *callbacks[] = { balloon_ack, balloon_ack };
-        const char *names[] = { "inflate", "deflate" };
-        int err;
+        struct virtqueue *vqs[3];
+        vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
+        const char *names[] = { "inflate", "deflate", "stats" };
+        int err, nvqs;
 
         vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL);
         if (!vb) {
@@ -219,14 +294,31 @@ static int virtballoon_probe(struct virtio_device *vdev)
         vb->num_pages = 0;
         init_waitqueue_head(&vb->config_change);
         vb->vdev = vdev;
+        vb->need_stats_update = 0;
 
-        /* We expect two virtqueues. */
-        err = vdev->config->find_vqs(vdev, 2, vqs, callbacks, names);
+        /* We expect two virtqueues: inflate and deflate,
+         * and optionally stat. */
+        nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
+        err = vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names);
         if (err)
                 goto out_free_vb;
 
         vb->inflate_vq = vqs[0];
         vb->deflate_vq = vqs[1];
+        if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
+                struct scatterlist sg;
+                vb->stats_vq = vqs[2];
+
+                /*
+                 * Prime this virtqueue with one buffer so the hypervisor can
+                 * use it to signal us later.
+                 */
+                sg_init_one(&sg, vb->stats, sizeof vb->stats);
+                if (vb->stats_vq->vq_ops->add_buf(vb->stats_vq,
+                                                  &sg, 1, 0, vb) < 0)
+                        BUG();
+                vb->stats_vq->vq_ops->kick(vb->stats_vq);
+        }
 
         vb->thread = kthread_run(balloon, vb, "vballoon");
         if (IS_ERR(vb->thread)) {
@@ -264,9 +356,12 @@ static void __devexit virtballoon_remove(struct virtio_device *vdev)
         kfree(vb);
 }
 
-static unsigned int features[] = { VIRTIO_BALLOON_F_MUST_TELL_HOST };
+static unsigned int features[] = {
+        VIRTIO_BALLOON_F_MUST_TELL_HOST,
+        VIRTIO_BALLOON_F_STATS_VQ,
+};
 
-static struct virtio_driver virtio_balloon = {
+static struct virtio_driver virtio_balloon_driver = {
         .feature_table = features,
         .feature_table_size = ARRAY_SIZE(features),
         .driver.name =  KBUILD_MODNAME,
@@ -279,12 +374,12 @@ static struct virtio_driver virtio_balloon = {
 
 static int __init init(void)
 {
-        return register_virtio_driver(&virtio_balloon);
+        return register_virtio_driver(&virtio_balloon_driver);
 }
 
 static void __exit fini(void)
 {
-        unregister_virtio_driver(&virtio_balloon);
+        unregister_virtio_driver(&virtio_balloon_driver);
 }
 module_init(init);
 module_exit(fini);
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index 28d9cf7cf72f..24747aef1952 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/list.h>
 #include <linux/pci.h>
+#include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/virtio.h>
 #include <linux/virtio_config.h>
@@ -473,7 +474,8 @@ static void vp_del_vqs(struct virtio_device *vdev)
 
         list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
                 info = vq->priv;
-                if (vp_dev->per_vq_vectors)
+                if (vp_dev->per_vq_vectors &&
+                        info->msix_vector != VIRTIO_MSI_NO_VECTOR)
                         free_irq(vp_dev->msix_entries[info->msix_vector].vector,
                                  vq);
                 vp_del_vq(vq);
@@ -648,6 +650,7 @@ static int __devinit virtio_pci_probe(struct pci_dev *pci_dev,
                 goto out_req_regions;
 
         pci_set_drvdata(pci_dev, vp_dev);
+        pci_set_master(pci_dev);
 
         /* we use the subsystem vendor/device id as the virtio vendor/device
          * id.  this allows us to use the same PCI vendor/device id for all
@@ -702,7 +705,7 @@ static struct pci_driver virtio_pci_driver = {
         .name           = "virtio-pci",
         .id_table       = virtio_pci_id_table,
         .probe          = virtio_pci_probe,
-        .remove         = virtio_pci_remove,
+        .remove         = __devexit_p(virtio_pci_remove),
 #ifdef CONFIG_PM
         .suspend        = virtio_pci_suspend,
         .resume         = virtio_pci_resume,
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index fbd2ecde93e4..0f90634bcb85 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -20,6 +20,25 @@
 #include <linux/virtio_ring.h>
 #include <linux/virtio_config.h>
 #include <linux/device.h>
+#include <linux/slab.h>
+
+/* virtio guest is communicating with a virtual "device" that actually runs on
+ * a host processor.  Memory barriers are used to control SMP effects. */
+#ifdef CONFIG_SMP
+/* Where possible, use SMP barriers which are more lightweight than mandatory
+ * barriers, because mandatory barriers control MMIO effects on accesses
+ * through relaxed memory I/O windows (which virtio does not use). */
+#define virtio_mb() smp_mb()
+#define virtio_rmb() smp_rmb()
+#define virtio_wmb() smp_wmb()
+#else
+/* We must force memory ordering even if guest is UP since host could be
+ * running on another CPU, but SMP barriers are defined to barrier() in that
+ * configuration. So fall back to mandatory barriers instead. */
+#define virtio_mb() mb()
+#define virtio_rmb() rmb()
+#define virtio_wmb() wmb()
+#endif
 
 #ifdef DEBUG
 /* For development, we want to crash whenever the ring is screwed. */
@@ -36,10 +55,9 @@
                         panic("%s:in_use = %i\n",               \
                               (_vq)->vq.name, (_vq)->in_use);   \
                 (_vq)->in_use = __LINE__;                       \
-                mb();                                           \
         } while (0)
 #define END_USE(_vq) \
-        do { BUG_ON(!(_vq)->in_use); (_vq)->in_use = 0; mb(); } while(0)
+        do { BUG_ON(!(_vq)->in_use); (_vq)->in_use = 0; } while(0)
 #else
 #define BAD_RING(_vq, fmt, args...)                             \
         do {                                                    \
@@ -221,13 +239,13 @@ static void vring_kick(struct virtqueue *_vq)
         START_USE(vq);
         /* Descriptors and available array need to be set before we expose the
          * new available array entries. */
-        wmb();
+        virtio_wmb();
 
         vq->vring.avail->idx += vq->num_added;
         vq->num_added = 0;
 
         /* Need to update avail index before checking if we should notify */
-        mb();
+        virtio_mb();
 
         if (!(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY))
                 /* Prod other side to tell it about changes. */
@@ -286,7 +304,7 @@ static void *vring_get_buf(struct virtqueue *_vq, unsigned int *len)
         }
 
         /* Only get used array entries after they have been exposed by host. */
-        rmb();
+        virtio_rmb();
 
         i = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].id;
         *len = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].len;
@@ -324,7 +342,7 @@ static bool vring_enable_cb(struct virtqueue *_vq)
         /* We optimistically turn back on interrupts, then check if there was
          * more to do. */
         vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
-        mb();
+        virtio_mb();
         if (unlikely(more_used(vq))) {
                 END_USE(vq);
                 return false;
@@ -334,6 +352,30 @@ static bool vring_enable_cb(struct virtqueue *_vq)
         return true;
 }
 
+static void *vring_detach_unused_buf(struct virtqueue *_vq)
+{
+        struct vring_virtqueue *vq = to_vvq(_vq);
+        unsigned int i;
+        void *buf;
+
+        START_USE(vq);
+
+        for (i = 0; i < vq->vring.num; i++) {
+                if (!vq->data[i])
+                        continue;
+                /* detach_buf clears data, so grab it now. */
+                buf = vq->data[i];
+                detach_buf(vq, i);
+                END_USE(vq);
+                return buf;
+        }
+        /* That should have freed everything. */
+        BUG_ON(vq->num_free != vq->vring.num);
+
+        END_USE(vq);
+        return NULL;
+}
+
 irqreturn_t vring_interrupt(int irq, void *_vq)
 {
         struct vring_virtqueue *vq = to_vvq(_vq);
@@ -360,6 +402,7 @@ static struct virtqueue_ops vring_vq_ops = {
         .kick = vring_kick,
         .disable_cb = vring_disable_cb,
         .enable_cb = vring_enable_cb,
+        .detach_unused_buf = vring_detach_unused_buf,
 };
 
 struct virtqueue *vring_new_virtqueue(unsigned int num,
@@ -406,8 +449,11 @@ struct virtqueue *vring_new_virtqueue(unsigned int num,
         /* Put everything in free lists. */
         vq->num_free = num;
         vq->free_head = 0;
-        for (i = 0; i < num-1; i++)
+        for (i = 0; i < num-1; i++) {
                 vq->vring.desc[i].next = i+1;
+                vq->data[i] = NULL;
+        }
+        vq->data[i] = NULL;
 
         return &vq->vq;
 }