[RFC][QEMU PATCH] KVM: Support for guest free page hinting

From: Nitesh Narayan Lal <nitesh@redhat.com>
To: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
	pbonzini@redhat.com, lcapitulino@redhat.com, pagupta@redhat.com,
	wei.w.wang@intel.com, yang.zhang.wz@gmail.com, riel@surriel.com,
	david@redhat.com, mst@redhat.com, dodgen@google.com,
	konrad.wilk@oracle.com, dhildenb@redhat.com, aarcange@redhat.com
Cc: Nitesh Narayan Lal <nitesh@redhat.com>
Subject: [RFC][QEMU PATCH] KVM: Support for guest free page hinting
Date: Mon,  4 Feb 2019 15:20:38 -0500	[thread overview]
Message-ID: <20190204202038.2471-1-nitesh@redhat.com> (raw)
In-Reply-To: <20190204201854.2328-1-nitesh@redhat.com>

This patch enables QEMU to recieve free page address from the guest
and to use madvise to make them available to the host.
---
 hw/virtio/trace-events                        |  1 +
 hw/virtio/virtio-balloon.c                    | 82 +++++++++++++++++++
 hw/virtio/virtio.c                            | 25 ++++++
 include/hw/virtio/virtio-access.h             |  1 +
 include/hw/virtio/virtio-balloon.h            |  2 +-
 .../standard-headers/linux/virtio_balloon.h   |  1 +
 6 files changed, 111 insertions(+), 1 deletion(-)

diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events
index 07bcbe9e85..e3ab66f126 100644
--- a/hw/virtio/trace-events
+++ b/hw/virtio/trace-events
@@ -46,3 +46,4 @@ virtio_balloon_handle_output(const char *name, uint64_t gpa) "section name: %s g
 virtio_balloon_get_config(uint32_t num_pages, uint32_t actual) "num_pages: %d actual: %d"
 virtio_balloon_set_config(uint32_t actual, uint32_t oldactual) "actual: %d oldactual: %d"
 virtio_balloon_to_target(uint64_t target, uint32_t num_pages) "balloon target: 0x%"PRIx64" num_pages: %d"
+virtio_balloon_hinting_request(unsigned long pfn, unsigned int num_pages) "Guest page hinting request: %lu num_pages: %d"
diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
index a12677d4d5..464d7d0d82 100644
--- a/hw/virtio/virtio-balloon.c
+++ b/hw/virtio/virtio-balloon.c
@@ -33,6 +33,13 @@
 
 #define BALLOON_PAGE_SIZE  (1 << VIRTIO_BALLOON_PFN_SHIFT)
 
+struct guest_pages {
+	unsigned long pfn;
+	unsigned int order;
+};
+
+void page_hinting_request(uint64_t addr, uint32_t len);
+
 static void balloon_page(void *addr, int deflate)
 {
     if (!qemu_balloon_is_inhibited()) {
@@ -207,6 +214,77 @@ static void balloon_stats_set_poll_interval(Object *obj, Visitor *v,
     balloon_stats_change_timer(s, 0);
 }
 
+static void *gpa2hva(MemoryRegion **p_mr, hwaddr addr, Error **errp)
+{
+    MemoryRegionSection mrs = memory_region_find(get_system_memory(),
+                                                 addr, 1);
+
+    if (!mrs.mr) {
+        error_setg(errp, "No memory is mapped at address 0x%" HWADDR_PRIx, addr);
+        return NULL;
+    }
+
+    if (!memory_region_is_ram(mrs.mr) && !memory_region_is_romd(mrs.mr)) {
+        error_setg(errp, "Memory at address 0x%" HWADDR_PRIx "is not RAM", addr);
+        memory_region_unref(mrs.mr);
+        return NULL;
+    }
+
+    *p_mr = mrs.mr;
+    return qemu_map_ram_ptr(mrs.mr->ram_block, mrs.offset_within_region);
+}
+
+void page_hinting_request(uint64_t addr, uint32_t len)
+{
+    Error *local_err = NULL;
+    MemoryRegion *mr = NULL;
+    void *hvaddr;
+    int ret = 0;
+    struct guest_pages *guest_obj;
+    int i = 0;
+    void *hvaddr_to_free;
+    unsigned long pfn, pfn_end;
+    uint64_t gpaddr_to_free;
+
+    hvaddr = gpa2hva(&mr, addr, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+        return;
+    }
+    guest_obj = hvaddr;
+
+    while (i < len) {
+        pfn = guest_obj[i].pfn;
+	pfn_end = guest_obj[i].pfn + (1 << guest_obj[i].order) - 1;
+	trace_virtio_balloon_hinting_request(pfn,(1 << guest_obj[i].order));
+	while (pfn <= pfn_end) {
+	        gpaddr_to_free = pfn << VIRTIO_BALLOON_PFN_SHIFT;
+	        hvaddr_to_free = gpa2hva(&mr, gpaddr_to_free, &local_err);
+	        if (local_err) {
+			error_report_err(local_err);
+		        return;
+		}
+		ret = qemu_madvise((void *)hvaddr_to_free, 4096, QEMU_MADV_DONTNEED);
+		if (ret == -1)
+		    printf("\n%d:%s Error: Madvise failed with error:%d\n", __LINE__, __func__, ret);
+		pfn++;
+	}
+	i++;
+    }
+}
+
+static void virtio_balloon_page_hinting(VirtIODevice *vdev, VirtQueue *vq)
+{
+    uint64_t addr;
+    uint32_t len;
+    VirtQueueElement elem = {};
+
+    pop_hinting_addr(vq, &addr, &len);
+    page_hinting_request(addr, len);
+    virtqueue_push(vq, &elem, 0);
+    virtio_notify(vdev, vq);
+}
+
 static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
 {
     VirtIOBalloon *s = VIRTIO_BALLOON(vdev);
@@ -376,6 +454,7 @@ static uint64_t virtio_balloon_get_features(VirtIODevice *vdev, uint64_t f,
     VirtIOBalloon *dev = VIRTIO_BALLOON(vdev);
     f |= dev->host_features;
     virtio_add_feature(&f, VIRTIO_BALLOON_F_STATS_VQ);
+    virtio_add_feature(&f, VIRTIO_BALLOON_F_HINTING);
     return f;
 }
 
@@ -445,6 +524,7 @@ static void virtio_balloon_device_realize(DeviceState *dev, Error **errp)
     s->ivq = virtio_add_queue(vdev, 128, virtio_balloon_handle_output);
     s->dvq = virtio_add_queue(vdev, 128, virtio_balloon_handle_output);
     s->svq = virtio_add_queue(vdev, 128, virtio_balloon_receive_stats);
+    s->hvq = virtio_add_queue(vdev, 128, virtio_balloon_page_hinting);
 
     reset_stats(s);
 }
@@ -488,6 +568,8 @@ static void virtio_balloon_instance_init(Object *obj)
 
     object_property_add(obj, "guest-stats", "guest statistics",
                         balloon_stats_get_all, NULL, NULL, s, NULL);
+    object_property_add(obj, "guest-page-hinting", "guest page hinting",
+                        NULL, NULL, NULL, s, NULL);
 
     object_property_add(obj, "guest-stats-polling-interval", "int",
                         balloon_stats_get_poll_interval,
diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
index 22bd1ac34e..a0cdb232f0 100644
--- a/hw/virtio/virtio.c
+++ b/hw/virtio/virtio.c
@@ -847,6 +847,31 @@ static void *virtqueue_alloc_element(size_t sz, unsigned out_num, unsigned in_nu
     return elem;
 }
 
+void pop_hinting_addr(VirtQueue *vq, uint64_t *addr, uint32_t *len)
+{
+   VRingMemoryRegionCaches *caches;
+   VRingDesc desc;
+   MemoryRegionCache *desc_cache;
+   VirtIODevice *vdev = vq->vdev;
+   unsigned int head, max;
+
+   max = vq->vring.num;
+   if (!virtqueue_get_head(vq, vq->last_avail_idx++, &head)) {
+   	virtio_error(vdev, "Unable to read head");
+  	return;
+   }
+
+   caches = vring_get_region_caches(vq);
+   if (caches->desc.len < max * sizeof(VRingDesc)) {
+       virtio_error(vdev, "Cannot map descriptor ring");
+       return;
+   }
+   desc_cache = &caches->desc;
+   vring_desc_read(vdev, &desc, desc_cache, head);
+   *addr = desc.addr;
+   *len = desc.len;
+}
+
 void *virtqueue_pop(VirtQueue *vq, size_t sz)
 {
     unsigned int i, head, max;
diff --git a/include/hw/virtio/virtio-access.h b/include/hw/virtio/virtio-access.h
index bdf58f3119..0a55f2626f 100644
--- a/include/hw/virtio/virtio-access.h
+++ b/include/hw/virtio/virtio-access.h
@@ -23,6 +23,7 @@
 #define LEGACY_VIRTIO_IS_BIENDIAN 1
 #endif
 
+void pop_hinting_addr(VirtQueue *vq, uint64_t *addr, uint32_t *len);
 static inline bool virtio_access_is_big_endian(VirtIODevice *vdev)
 {
 #if defined(LEGACY_VIRTIO_IS_BIENDIAN)
diff --git a/include/hw/virtio/virtio-balloon.h b/include/hw/virtio/virtio-balloon.h
index e0df3528c8..774498a6ca 100644
--- a/include/hw/virtio/virtio-balloon.h
+++ b/include/hw/virtio/virtio-balloon.h
@@ -32,7 +32,7 @@ typedef struct virtio_balloon_stat_modern {
 
 typedef struct VirtIOBalloon {
     VirtIODevice parent_obj;
-    VirtQueue *ivq, *dvq, *svq;
+    VirtQueue *ivq, *dvq, *svq, *hvq;
     uint32_t num_pages;
     uint32_t actual;
     uint64_t stats[VIRTIO_BALLOON_S_NR];
diff --git a/include/standard-headers/linux/virtio_balloon.h b/include/standard-headers/linux/virtio_balloon.h
index 4dbb7dc6c0..f50c0d95ea 100644
--- a/include/standard-headers/linux/virtio_balloon.h
+++ b/include/standard-headers/linux/virtio_balloon.h
@@ -34,6 +34,7 @@
 #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_HINTING	5 /* Page hinting virtqueue */
 
 /* Size of a PFN in the balloon interface. */
 #define VIRTIO_BALLOON_PFN_SHIFT 12
-- 
2.17.2

