kvm: split too big memory section on several memslots

Max memslot size supported by kvm on s390 is 8Tb,
move logic of splitting RAM in chunks upto 8T to KVM code.

This way it will hide KVM specific restrictions in KVM code
and won't affect board level design decisions. Which would allow
us to avoid misusing memory_region_allocate_system_memory() API
and eventually use a single hostmem backend for guest RAM.

Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20190924144751.24149-4-imammedo@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>

1 files changed, 80 insertions, 44 deletions

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index ff9b95c0d1..aabe097c41 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -140,6 +140,7 @@ bool kvm_direct_msi_allowed;
 bool kvm_ioeventfd_any_length_allowed;
 bool kvm_msi_use_devid;
 static bool kvm_immediate_exit;
+static hwaddr kvm_max_slot_size = ~0;
 
 static const KVMCapabilityInfo kvm_required_capabilites[] = {
     KVM_CAP_INFO(USER_MEMORY),
@@ -437,7 +438,7 @@ static int kvm_slot_update_flags(KVMMemoryListener *kml, KVMSlot *mem,
 static int kvm_section_update_flags(KVMMemoryListener *kml,
                                     MemoryRegionSection *section)
 {
-    hwaddr start_addr, size;
+    hwaddr start_addr, size, slot_size;
     KVMSlot *mem;
     int ret = 0;
 
@@ -448,13 +449,18 @@ static int kvm_section_update_flags(KVMMemoryListener *kml,
 
     kvm_slots_lock(kml);
 
-    mem = kvm_lookup_matching_slot(kml, start_addr, size);
-    if (!mem) {
-        /* We don't have a slot if we want to trap every access. */
-        goto out;
-    }
+    while (size && !ret) {
+        slot_size = MIN(kvm_max_slot_size, size);
+        mem = kvm_lookup_matching_slot(kml, start_addr, slot_size);
+        if (!mem) {
+            /* We don't have a slot if we want to trap every access. */
+            goto out;
+        }
 
-    ret = kvm_slot_update_flags(kml, mem, section->mr);
+        ret = kvm_slot_update_flags(kml, mem, section->mr);
+        start_addr += slot_size;
+        size -= slot_size;
+    }
 
 out:
     kvm_slots_unlock(kml);
@@ -527,11 +533,15 @@ static int kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml,
     struct kvm_dirty_log d = {};
     KVMSlot *mem;
     hwaddr start_addr, size;
+    hwaddr slot_size, slot_offset = 0;
     int ret = 0;
 
     size = kvm_align_section(section, &start_addr);
-    if (size) {
-        mem = kvm_lookup_matching_slot(kml, start_addr, size);
+    while (size) {
+        MemoryRegionSection subsection = *section;
+
+        slot_size = MIN(kvm_max_slot_size, size);
+        mem = kvm_lookup_matching_slot(kml, start_addr, slot_size);
         if (!mem) {
             /* We don't have a slot if we want to trap every access. */
             goto out;
@@ -549,11 +559,11 @@ static int kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml,
          * So for now, let's align to 64 instead of HOST_LONG_BITS here, in
          * a hope that sizeof(long) won't become >8 any time soon.
          */
-        size = ALIGN(((mem->memory_size) >> TARGET_PAGE_BITS),
-                     /*HOST_LONG_BITS*/ 64) / 8;
         if (!mem->dirty_bmap) {
+            hwaddr bitmap_size = ALIGN(((mem->memory_size) >> TARGET_PAGE_BITS),
+                                        /*HOST_LONG_BITS*/ 64) / 8;
             /* Allocate on the first log_sync, once and for all */
-            mem->dirty_bmap = g_malloc0(size);
+            mem->dirty_bmap = g_malloc0(bitmap_size);
         }
 
         d.dirty_bitmap = mem->dirty_bmap;
@@ -564,7 +574,13 @@ static int kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml,
             goto out;
         }
 
-        kvm_get_dirty_pages_log_range(section, d.dirty_bitmap);
+        subsection.offset_within_region += slot_offset;
+        subsection.size = int128_make64(slot_size);
+        kvm_get_dirty_pages_log_range(&subsection, d.dirty_bitmap);
+
+        slot_offset += slot_size;
+        start_addr += slot_size;
+        size -= slot_size;
     }
 out:
     return ret;
@@ -972,6 +988,14 @@ kvm_check_extension_list(KVMState *s, const KVMCapabilityInfo *list)
     return NULL;
 }
 
+void kvm_set_max_memslot_size(hwaddr max_slot_size)
+{
+    g_assert(
+        ROUND_UP(max_slot_size, qemu_real_host_page_size) == max_slot_size
+    );
+    kvm_max_slot_size = max_slot_size;
+}
+
 static void kvm_set_phys_mem(KVMMemoryListener *kml,
                              MemoryRegionSection *section, bool add)
 {
@@ -979,7 +1003,7 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
     int err;
     MemoryRegion *mr = section->mr;
     bool writeable = !mr->readonly && !mr->rom_device;
-    hwaddr start_addr, size;
+    hwaddr start_addr, size, slot_size;
     void *ram;
 
     if (!memory_region_is_ram(mr)) {
@@ -1004,41 +1028,52 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
     kvm_slots_lock(kml);
 
     if (!add) {
-        mem = kvm_lookup_matching_slot(kml, start_addr, size);
-        if (!mem) {
-            goto out;
-        }
-        if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
-            kvm_physical_sync_dirty_bitmap(kml, section);
-        }
+        do {
+            slot_size = MIN(kvm_max_slot_size, size);
+            mem = kvm_lookup_matching_slot(kml, start_addr, slot_size);
+            if (!mem) {
+                goto out;
+            }
+            if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+                kvm_physical_sync_dirty_bitmap(kml, section);
+            }
 
-        /* unregister the slot */
-        g_free(mem->dirty_bmap);
-        mem->dirty_bmap = NULL;
-        mem->memory_size = 0;
-        mem->flags = 0;
-        err = kvm_set_user_memory_region(kml, mem, false);
-        if (err) {
-            fprintf(stderr, "%s: error unregistering slot: %s\n",
-                    __func__, strerror(-err));
-            abort();
-        }
+            /* unregister the slot */
+            g_free(mem->dirty_bmap);
+            mem->dirty_bmap = NULL;
+            mem->memory_size = 0;
+            mem->flags = 0;
+            err = kvm_set_user_memory_region(kml, mem, false);
+            if (err) {
+                fprintf(stderr, "%s: error unregistering slot: %s\n",
+                        __func__, strerror(-err));
+                abort();
+            }
+            start_addr += slot_size;
+            size -= slot_size;
+        } while (size);
         goto out;
     }
 
     /* register the new slot */
-    mem = kvm_alloc_slot(kml);
-    mem->memory_size = size;
-    mem->start_addr = start_addr;
-    mem->ram = ram;
-    mem->flags = kvm_mem_flags(mr);
-
-    err = kvm_set_user_memory_region(kml, mem, true);
-    if (err) {
-        fprintf(stderr, "%s: error registering slot: %s\n", __func__,
-                strerror(-err));
-        abort();
-    }
+    do {
+        slot_size = MIN(kvm_max_slot_size, size);
+        mem = kvm_alloc_slot(kml);
+        mem->memory_size = slot_size;
+        mem->start_addr = start_addr;
+        mem->ram = ram;
+        mem->flags = kvm_mem_flags(mr);
+
+        err = kvm_set_user_memory_region(kml, mem, true);
+        if (err) {
+            fprintf(stderr, "%s: error registering slot: %s\n", __func__,
+                    strerror(-err));
+            abort();
+        }
+        start_addr += slot_size;
+        ram += slot_size;
+        size -= slot_size;
+    } while (size);
 
 out:
     kvm_slots_unlock(kml);
@@ -2878,6 +2913,7 @@ static bool kvm_accel_has_memory(MachineState *ms, AddressSpace *as,
 
     for (i = 0; i < kvm->nr_as; ++i) {
         if (kvm->as[i].as == as && kvm->as[i].ml) {
+            size = MIN(kvm_max_slot_size, size);
             return NULL != kvm_lookup_matching_slot(kvm->as[i].ml,
                                                     start_addr, size);
         }