memory: Introduce RamDiscardManager for RAM memory regions

We have some special RAM memory regions (managed by virtio-mem), whereby
the guest agreed to only use selected memory ranges. "unused" parts are
discarded so they won't consume memory - to logically unplug these memory
ranges. Before the VM is allowed to use such logically unplugged memory
again, coordination with the hypervisor is required.

This results in "sparse" mmaps/RAMBlocks/memory regions, whereby only
coordinated parts are valid to be used/accessed by the VM.

In most cases, we don't care about that - e.g., in KVM, we simply have a
single KVM memory slot. However, in case of vfio, registering the
whole region with the kernel results in all pages getting pinned, and
therefore an unexpected high memory consumption - discarding of RAM in
that context is broken.

Let's introduce a way to coordinate discarding/populating memory within a
RAM memory region with such special consumers of RAM memory regions: they
can register as listeners and get updates on memory getting discarded and
populated. Using this machinery, vfio will be able to map only the
currently populated parts, resulting in discarded parts not getting pinned
and not consuming memory.

A RamDiscardManager has to be set for a memory region before it is getting
mapped, and cannot change while the memory region is mapped.

Note: At some point, we might want to let RAMBlock users (esp. vfio used
for nvme://) consume this interface as well. We'll need RAMBlock notifier
calls when a RAMBlock is getting mapped/unmapped (via the corresponding
memory region), so we can properly register a listener there as well.

Reviewed-by: Pankaj Gupta <pankaj.gupta@cloud.ionos.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Dr. David Alan Gilbert <dgilbert@redhat.com>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Auger Eric <eric.auger@redhat.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: teawater <teawaterz@linux.alibaba.com>
Cc: Marek Kedzierski <mkedzier@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210413095531.25603-2-david@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>

1 files changed, 71 insertions, 0 deletions

diff --git a/softmmu/memory.c b/softmmu/memory.c
index f0161515e9..d20a9dec44 100644
--- a/softmmu/memory.c
+++ b/softmmu/memory.c
@@ -2027,6 +2027,70 @@ int memory_region_iommu_num_indexes(IOMMUMemoryRegion *iommu_mr)
     return imrc->num_indexes(iommu_mr);
 }
 
+RamDiscardManager *memory_region_get_ram_discard_manager(MemoryRegion *mr)
+{
+    if (!memory_region_is_mapped(mr) || !memory_region_is_ram(mr)) {
+        return NULL;
+    }
+    return mr->rdm;
+}
+
+void memory_region_set_ram_discard_manager(MemoryRegion *mr,
+                                           RamDiscardManager *rdm)
+{
+    g_assert(memory_region_is_ram(mr) && !memory_region_is_mapped(mr));
+    g_assert(!rdm || !mr->rdm);
+    mr->rdm = rdm;
+}
+
+uint64_t ram_discard_manager_get_min_granularity(const RamDiscardManager *rdm,
+                                                 const MemoryRegion *mr)
+{
+    RamDiscardManagerClass *rdmc = RAM_DISCARD_MANAGER_GET_CLASS(rdm);
+
+    g_assert(rdmc->get_min_granularity);
+    return rdmc->get_min_granularity(rdm, mr);
+}
+
+bool ram_discard_manager_is_populated(const RamDiscardManager *rdm,
+                                      const MemoryRegionSection *section)
+{
+    RamDiscardManagerClass *rdmc = RAM_DISCARD_MANAGER_GET_CLASS(rdm);
+
+    g_assert(rdmc->is_populated);
+    return rdmc->is_populated(rdm, section);
+}
+
+int ram_discard_manager_replay_populated(const RamDiscardManager *rdm,
+                                         MemoryRegionSection *section,
+                                         ReplayRamPopulate replay_fn,
+                                         void *opaque)
+{
+    RamDiscardManagerClass *rdmc = RAM_DISCARD_MANAGER_GET_CLASS(rdm);
+
+    g_assert(rdmc->replay_populated);
+    return rdmc->replay_populated(rdm, section, replay_fn, opaque);
+}
+
+void ram_discard_manager_register_listener(RamDiscardManager *rdm,
+                                           RamDiscardListener *rdl,
+                                           MemoryRegionSection *section)
+{
+    RamDiscardManagerClass *rdmc = RAM_DISCARD_MANAGER_GET_CLASS(rdm);
+
+    g_assert(rdmc->register_listener);
+    rdmc->register_listener(rdm, rdl, section);
+}
+
+void ram_discard_manager_unregister_listener(RamDiscardManager *rdm,
+                                             RamDiscardListener *rdl)
+{
+    RamDiscardManagerClass *rdmc = RAM_DISCARD_MANAGER_GET_CLASS(rdm);
+
+    g_assert(rdmc->unregister_listener);
+    rdmc->unregister_listener(rdm, rdl);
+}
+
 void memory_region_set_log(MemoryRegion *mr, bool log, unsigned client)
 {
     uint8_t mask = 1 << client;
@@ -3320,10 +3384,17 @@ static const TypeInfo iommu_memory_region_info = {
     .abstract           = true,
 };
 
+static const TypeInfo ram_discard_manager_info = {
+    .parent             = TYPE_INTERFACE,
+    .name               = TYPE_RAM_DISCARD_MANAGER,
+    .class_size         = sizeof(RamDiscardManagerClass),
+};
+
 static void memory_register_types(void)
 {
     type_register_static(&memory_region_info);
     type_register_static(&iommu_memory_region_info);
+    type_register_static(&ram_discard_manager_info);
 }
 
 type_init(memory_register_types)