Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   David Hildenbrand <david@redhat.com>
To:     linux-kernel@vger.kernel.org
Cc:     linux-mm@kvack.org, virtio-dev@lists.oasis-open.org,
        virtualization@lists.linux-foundation.org, kvm@vger.kernel.org,
        Michal Hocko <mhocko@kernel.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        "Michael S . Tsirkin" <mst@redhat.com>,
        David Hildenbrand <david@redhat.com>,
        Jason Wang <jasowang@redhat.com>,
        Oscar Salvador <osalvador@suse.de>,
        Igor Mammedov <imammedo@redhat.com>,
        Dave Young <dyoung@redhat.com>,
        Dan Williams <dan.j.williams@intel.com>,
        Pavel Tatashin <pasha.tatashin@soleen.com>,
        Stefan Hajnoczi <stefanha@redhat.com>,
        Vlastimil Babka <vbabka@suse.cz>
Subject: [PATCH v1 07/11] virtio-mem: Allow to offline partially unplugged memory blocks
Date:   Mon,  2 Mar 2020 14:49:37 +0100
Message-Id: <20200302134941.315212-8-david@redhat.com>
In-Reply-To: <20200302134941.315212-1-david@redhat.com>
References: <20200302134941.315212-1-david@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Dropping the reference count of PageOffline() pages allows offlining
code to skip them. However, we also have to convert PG_reserved to
another flag - let's use PG_dirty - so has_unmovable_pages() will
properly handle them. PG_reserved pages get detected as unmovable right
away.

We need the flag to see if we are onlining pages the first time, or if
we allocated them via alloc_contig_range().

Properly take care of offlining code also modifying the stats and
special handling in case the driver gets unloaded.

Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 drivers/virtio/virtio_mem.c | 64 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 63 insertions(+), 1 deletion(-)

diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index 5b26d57be551..2916f8b970fa 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -570,6 +570,53 @@ static void virtio_mem_notify_online(struct virtio_m=
em *vm, unsigned long mb_id,
 		virtio_mem_retry(vm);
 }
=20
+static void virtio_mem_notify_going_offline(struct virtio_mem *vm,
+					    unsigned long mb_id)
+{
+	const unsigned long nr_pages =3D PFN_DOWN(vm->subblock_size);
+	unsigned long pfn;
+	int sb_id, i;
+
+	for (sb_id =3D 0; sb_id < vm->nb_sb_per_mb; sb_id++) {
+		if (virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1))
+			continue;
+		/*
+		 * Drop our reference to the pages so the memory can get
+		 * offlined and add the unplugged pages to the managed
+		 * page counters (so offlining code can correctly subtract
+		 * them again).
+		 */
+		pfn =3D PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) +
+			       sb_id * vm->subblock_size);
+		adjust_managed_page_count(pfn_to_page(pfn), nr_pages);
+		for (i =3D 0; i < nr_pages; i++)
+			page_ref_dec(pfn_to_page(pfn + i));
+	}
+}
+
+static void virtio_mem_notify_cancel_offline(struct virtio_mem *vm,
+					     unsigned long mb_id)
+{
+	const unsigned long nr_pages =3D PFN_DOWN(vm->subblock_size);
+	unsigned long pfn;
+	int sb_id, i;
+
+	for (sb_id =3D 0; sb_id < vm->nb_sb_per_mb; sb_id++) {
+		if (virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1))
+			continue;
+		/*
+		 * Get the reference we dropped when going offline and
+		 * subtract the unplugged pages from the managed page
+		 * counters.
+		 */
+		pfn =3D PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) +
+			       sb_id * vm->subblock_size);
+		adjust_managed_page_count(pfn_to_page(pfn), -nr_pages);
+		for (i =3D 0; i < nr_pages; i++)
+			page_ref_inc(pfn_to_page(pfn + i));
+	}
+}
+
 /*
  * This callback will either be called synchronously from add_memory() o=
r
  * asynchronously (e.g., triggered via user space). We have to be carefu=
l
@@ -616,6 +663,7 @@ static int virtio_mem_memory_notifier_cb(struct notif=
ier_block *nb,
 			break;
 		}
 		vm->hotplug_active =3D true;
+		virtio_mem_notify_going_offline(vm, mb_id);
 		break;
 	case MEM_GOING_ONLINE:
 		mutex_lock(&vm->hotplug_mutex);
@@ -640,6 +688,12 @@ static int virtio_mem_memory_notifier_cb(struct noti=
fier_block *nb,
 		mutex_unlock(&vm->hotplug_mutex);
 		break;
 	case MEM_CANCEL_OFFLINE:
+		if (!vm->hotplug_active)
+			break;
+		virtio_mem_notify_cancel_offline(vm, mb_id);
+		vm->hotplug_active =3D false;
+		mutex_unlock(&vm->hotplug_mutex);
+		break;
 	case MEM_CANCEL_ONLINE:
 		if (!vm->hotplug_active)
 			break;
@@ -666,8 +720,11 @@ static void virtio_mem_set_fake_offline(unsigned lon=
g pfn,
 		struct page *page =3D pfn_to_page(pfn);
=20
 		__SetPageOffline(page);
-		if (!onlined)
+		if (!onlined) {
 			SetPageDirty(page);
+			/* FIXME: remove after cleanups */
+			ClearPageReserved(page);
+		}
 	}
 }
=20
@@ -1717,6 +1774,11 @@ static void virtio_mem_remove(struct virtio_device=
 *vdev)
 		rc =3D virtio_mem_mb_remove(vm, mb_id);
 		BUG_ON(rc);
 	}
+	/*
+	 * After we unregistered our callbacks, user space can no longer
+	 * offline partially plugged online memory blocks. No need to worry
+	 * about them.
+	 */
=20
 	/* unregister callbacks */
 	unregister_virtio_mem_device(vm);
--=20
2.24.1