linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Alexander Duyck <alexander.duyck@gmail.com>
To: virtio-dev@lists.oasis-open.org, kvm@vger.kernel.org,
	mst@redhat.com, david@redhat.com, dave.hansen@intel.com,
	linux-kernel@vger.kernel.org, willy@infradead.org,
	mhocko@kernel.org, linux-mm@kvack.org, vbabka@suse.cz,
	akpm@linux-foundation.org, mgorman@techsingularity.net,
	linux-arm-kernel@lists.infradead.org, osalvador@suse.de
Cc: yang.zhang.wz@gmail.com, pagupta@redhat.com,
	konrad.wilk@oracle.com, nitesh@redhat.com, riel@surriel.com,
	lcapitulino@redhat.com, wei.w.wang@intel.com,
	aarcange@redhat.com, pbonzini@redhat.com,
	dan.j.williams@intel.com, alexander.h.duyck@linux.intel.com
Subject: [PATCH v10 QEMU 3/3] virtio-balloon: Provide a interface for unused page reporting
Date: Wed, 18 Sep 2019 10:53:58 -0700	[thread overview]
Message-ID: <20190918175358.23606.22732.stgit@localhost.localdomain> (raw)
In-Reply-To: <20190918175109.23474.67039.stgit@localhost.localdomain>

From: Alexander Duyck <alexander.h.duyck@linux.intel.com>

Add support for what I am referring to as "unused page reporting".
Basically the idea is to function very similar to how the balloon works
in that we basically end up madvising the page as not being used. However
we don't really need to bother with any deflate type logic since the page
will be faulted back into the guest when it is read or written to.

This is meant to be a simplification of the existing balloon interface
to use for providing hints to what memory needs to be freed. I am assuming
this is safe to do as the deflate logic does not actually appear to do very
much other than tracking what subpages have been released and which ones
haven't.

Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
---
 hw/virtio/virtio-balloon.c         |   46 ++++++++++++++++++++++++++++++++++--
 include/hw/virtio/virtio-balloon.h |    2 +-
 2 files changed, 45 insertions(+), 3 deletions(-)

diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
index 003b3ebcfdfb..7a30df63bc77 100644
--- a/hw/virtio/virtio-balloon.c
+++ b/hw/virtio/virtio-balloon.c
@@ -320,6 +320,40 @@ static void balloon_stats_set_poll_interval(Object *obj, Visitor *v,
     balloon_stats_change_timer(s, 0);
 }
 
+static void virtio_balloon_handle_report(VirtIODevice *vdev, VirtQueue *vq)
+{
+    VirtIOBalloon *dev = VIRTIO_BALLOON(vdev);
+    VirtQueueElement *elem;
+
+    while ((elem = virtqueue_pop(vq, sizeof(VirtQueueElement)))) {
+    	unsigned int i;
+
+        for (i = 0; i < elem->in_num; i++) {
+            void *addr = elem->in_sg[i].iov_base;
+            size_t size = elem->in_sg[i].iov_len;
+            ram_addr_t ram_offset;
+            size_t rb_page_size;
+            RAMBlock *rb;
+
+            if (qemu_balloon_is_inhibited() || dev->poison_val)
+                continue;
+
+            rb = qemu_ram_block_from_host(addr, false, &ram_offset);
+            rb_page_size = qemu_ram_pagesize(rb);
+
+            /* For now we will simply ignore unaligned memory regions */
+            if ((ram_offset | size) & (rb_page_size - 1))
+                continue;
+
+            ram_block_discard_range(rb, ram_offset, size);
+        }
+
+        virtqueue_push(vq, elem, 0);
+        virtio_notify(vdev, vq);
+        g_free(elem);
+    }
+}
+
 static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
 {
     VirtIOBalloon *s = VIRTIO_BALLOON(vdev);
@@ -627,7 +661,8 @@ static size_t virtio_balloon_config_size(VirtIOBalloon *s)
         return sizeof(struct virtio_balloon_config);
     }
     if (virtio_has_feature(features, VIRTIO_BALLOON_F_PAGE_POISON) ||
-        virtio_has_feature(features, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+        virtio_has_feature(features, VIRTIO_BALLOON_F_FREE_PAGE_HINT) ||
+        virtio_has_feature(features, VIRTIO_BALLOON_F_REPORTING)) {
         return sizeof(struct virtio_balloon_config);
     }
     return offsetof(struct virtio_balloon_config, free_page_report_cmd_id);
@@ -715,7 +750,8 @@ 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);
-    if (virtio_has_feature(f, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+    if (virtio_has_feature(f, VIRTIO_BALLOON_F_FREE_PAGE_HINT) ||
+        virtio_has_feature(f, VIRTIO_BALLOON_F_REPORTING)) {
         virtio_add_feature(&f, VIRTIO_BALLOON_F_PAGE_POISON);
     }
 
@@ -805,6 +841,10 @@ static void virtio_balloon_device_realize(DeviceState *dev, Error **errp)
     s->dvq = virtio_add_queue(vdev, 128, virtio_balloon_handle_output);
     s->svq = virtio_add_queue(vdev, 128, virtio_balloon_receive_stats);
 
+    if (virtio_has_feature(s->host_features, VIRTIO_BALLOON_F_REPORTING)) {
+        s->rvq = virtio_add_queue(vdev, 32, virtio_balloon_handle_report);
+    }
+
     if (virtio_has_feature(s->host_features,
                            VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
         s->free_page_vq = virtio_add_queue(vdev, VIRTQUEUE_MAX_SIZE,
@@ -931,6 +971,8 @@ static Property virtio_balloon_properties[] = {
      */
     DEFINE_PROP_BOOL("qemu-4-0-config-size", VirtIOBalloon,
                      qemu_4_0_config_size, false),
+    DEFINE_PROP_BIT("unused-page-reporting", VirtIOBalloon, host_features,
+                    VIRTIO_BALLOON_F_REPORTING, true),
     DEFINE_PROP_LINK("iothread", VirtIOBalloon, iothread, TYPE_IOTHREAD,
                      IOThread *),
     DEFINE_PROP_END_OF_LIST(),
diff --git a/include/hw/virtio/virtio-balloon.h b/include/hw/virtio/virtio-balloon.h
index 7fe78e5c14d7..db5bf7127112 100644
--- a/include/hw/virtio/virtio-balloon.h
+++ b/include/hw/virtio/virtio-balloon.h
@@ -42,7 +42,7 @@ enum virtio_balloon_free_page_report_status {
 
 typedef struct VirtIOBalloon {
     VirtIODevice parent_obj;
-    VirtQueue *ivq, *dvq, *svq, *free_page_vq;
+    VirtQueue *ivq, *dvq, *svq, *free_page_vq, *rvq;
     uint32_t free_page_report_status;
     uint32_t num_pages;
     uint32_t actual;


  parent reply	other threads:[~2019-09-18 17:54 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-09-18 17:52 [PATCH v10 0/6] mm / virtio: Provide support " Alexander Duyck
2019-09-18 17:52 ` [PATCH v10 1/6] mm: Adjust shuffle code to allow for future coalescing Alexander Duyck
2019-09-18 17:52 ` [PATCH v10 2/6] mm: Use zone and order instead of free area in free_list manipulators Alexander Duyck
2019-09-18 17:52 ` [PATCH v10 3/6] mm: Introduce Reported pages Alexander Duyck
2019-09-21 15:25   ` [mm] 0f5b256b2c: will-it-scale.per_process_ops -1.2% regression kernel test robot
2019-09-23  8:15   ` [PATCH v10 3/6] mm: Introduce Reported pages Michael S. Tsirkin
2019-09-23 14:50     ` Alexander Duyck
2019-09-23 15:00       ` Michael S. Tsirkin
2019-09-23 15:28         ` Alexander Duyck
2019-09-23 15:37           ` Michael S. Tsirkin
2019-09-23 15:45             ` David Hildenbrand
2019-09-23 15:47               ` David Hildenbrand
2019-09-23 15:50                 ` Michael S. Tsirkin
2019-09-23 15:53                   ` David Hildenbrand
2019-09-23 15:49               ` Michael S. Tsirkin
2019-09-23 16:39               ` Alexander Duyck
2019-09-18 17:52 ` [PATCH v10 4/6] mm: Add device side and notifier for unused page reporting Alexander Duyck
2019-09-18 17:53 ` [PATCH v10 5/6] virtio-balloon: Pull page poisoning config out of free page hinting Alexander Duyck
2019-09-18 17:58   ` Michael S. Tsirkin
2019-09-18 18:05     ` Alexander Duyck
2019-09-18 17:53 ` [PATCH v10 6/6] virtio-balloon: Add support for providing unused page reports to host Alexander Duyck
2019-09-18 17:53 ` [PATCH v10 QEMU 1/3] virtio-ballon: Implement support for page poison tracking feature Alexander Duyck
2019-09-18 17:53 ` [PATCH v10 QEMU 2/3] virtio-balloon: Add bit to notify guest of unused page reporting Alexander Duyck
2019-09-18 17:53 ` Alexander Duyck [this message]
2019-09-24 14:23 ` [PATCH v10 0/6] mm / virtio: Provide support for " Michal Hocko
2019-09-24 15:20   ` Alexander Duyck
2019-09-26 12:22     ` Michal Hocko
2019-09-26 15:13       ` Alexander Duyck
2019-09-24 15:32   ` David Hildenbrand
2019-09-24 15:51     ` Nitesh Narayan Lal
2019-09-24 17:07     ` Alexander Duyck
2019-09-24 17:28       ` David Hildenbrand

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190918175358.23606.22732.stgit@localhost.localdomain \
    --to=alexander.duyck@gmail.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.h.duyck@linux.intel.com \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@intel.com \
    --cc=david@redhat.com \
    --cc=konrad.wilk@oracle.com \
    --cc=kvm@vger.kernel.org \
    --cc=lcapitulino@redhat.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@techsingularity.net \
    --cc=mhocko@kernel.org \
    --cc=mst@redhat.com \
    --cc=nitesh@redhat.com \
    --cc=osalvador@suse.de \
    --cc=pagupta@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=riel@surriel.com \
    --cc=vbabka@suse.cz \
    --cc=virtio-dev@lists.oasis-open.org \
    --cc=wei.w.wang@intel.com \
    --cc=willy@infradead.org \
    --cc=yang.zhang.wz@gmail.com \
    --subject='Re: [PATCH v10 QEMU 3/3] virtio-balloon: Provide a interface for unused page reporting' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).