numa: Teach ram block notifiers about resizeable ram blocks

Ram block notifiers are currently not aware of resizes. To properly
handle resizes during migration, we want to teach ram block notifiers about
resizeable ram.

Introduce the basic infrastructure but keep using max_size in the
existing notifiers. Supply the max_size when adding and removing ram
blocks. Also, notify on resizes.

Acked-by: Paul Durrant <paul@xen.org>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: xen-devel@lists.xenproject.org
Cc: haxm-team@intel.com
Cc: Paul Durrant <paul@xen.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Anthony Perard <anthony.perard@citrix.com>
Cc: Wenchao Wang <wenchao.wang@intel.com>
Cc: Colin Xu <colin.xu@intel.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210429112708.12291-3-david@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

hw/core/numa.c

@@ -805,11 +805,12 @@ void query_numa_node_mem(NumaNodeMem node_mem[], MachineState *ms)
 static int ram_block_notify_add_single(RAMBlock *rb, void *opaque)
 {
     const ram_addr_t max_size = qemu_ram_get_max_length(rb);
+    const ram_addr_t size = qemu_ram_get_used_length(rb);
     void *host = qemu_ram_get_host_addr(rb);
     RAMBlockNotifier *notifier = opaque;
 
     if (host) {
-        notifier->ram_block_added(notifier, host, max_size);
+        notifier->ram_block_added(notifier, host, size, max_size);
     }
     return 0;
 }
@@ -826,20 +827,31 @@ void ram_block_notifier_remove(RAMBlockNotifier *n)
     QLIST_REMOVE(n, next);
 }
 
-void ram_block_notify_add(void *host, size_t size)
+void ram_block_notify_add(void *host, size_t size, size_t max_size)
 {
     RAMBlockNotifier *notifier;
 
     QLIST_FOREACH(notifier, &ram_list.ramblock_notifiers, next) {
-        notifier->ram_block_added(notifier, host, size);
+        notifier->ram_block_added(notifier, host, size, max_size);
     }
 }
 
-void ram_block_notify_remove(void *host, size_t size)
+void ram_block_notify_remove(void *host, size_t size, size_t max_size)
 {
     RAMBlockNotifier *notifier;
 
     QLIST_FOREACH(notifier, &ram_list.ramblock_notifiers, next) {
-        notifier->ram_block_removed(notifier, host, size);
+        notifier->ram_block_removed(notifier, host, size, max_size);
+    }
+}
+
+void ram_block_notify_resize(void *host, size_t old_size, size_t new_size)
+{
+    RAMBlockNotifier *notifier;
+
+    QLIST_FOREACH(notifier, &ram_list.ramblock_notifiers, next) {
+        if (notifier->ram_block_resized) {
+            notifier->ram_block_resized(notifier, host, old_size, new_size);
+        }
     }
 }

hw/i386/xen/xen-mapcache.c

@@ -169,7 +169,8 @@ static void xen_remap_bucket(MapCacheEntry *entry,
 
     if (entry->vaddr_base != NULL) {
         if (!(entry->flags & XEN_MAPCACHE_ENTRY_DUMMY)) {
-            ram_block_notify_remove(entry->vaddr_base, entry->size);
+            ram_block_notify_remove(entry->vaddr_base, entry->size,
+                                    entry->size);
         }
 
         /*
@@ -224,7 +225,7 @@ static void xen_remap_bucket(MapCacheEntry *entry,
     }
 
     if (!(entry->flags & XEN_MAPCACHE_ENTRY_DUMMY)) {
-        ram_block_notify_add(vaddr_base, size);
+        ram_block_notify_add(vaddr_base, size, size);
     }
 
     entry->vaddr_base = vaddr_base;
@@ -465,7 +466,7 @@ static void xen_invalidate_map_cache_entry_unlocked(uint8_t *buffer)
     }
 
     pentry->next = entry->next;
-    ram_block_notify_remove(entry->vaddr_base, entry->size);
+    ram_block_notify_remove(entry->vaddr_base, entry->size, entry->size);
     if (munmap(entry->vaddr_base, entry->size) != 0) {
         perror("unmap fails");
         exit(-1);

include/exec/ramlist.h

@@ -65,15 +65,20 @@ void qemu_mutex_lock_ramlist(void);
 void qemu_mutex_unlock_ramlist(void);
 
 struct RAMBlockNotifier {
-    void (*ram_block_added)(RAMBlockNotifier *n, void *host, size_t size);
-    void (*ram_block_removed)(RAMBlockNotifier *n, void *host, size_t size);
+    void (*ram_block_added)(RAMBlockNotifier *n, void *host, size_t size,
+                            size_t max_size);
+    void (*ram_block_removed)(RAMBlockNotifier *n, void *host, size_t size,
+                              size_t max_size);
+    void (*ram_block_resized)(RAMBlockNotifier *n, void *host, size_t old_size,
+                              size_t new_size);
     QLIST_ENTRY(RAMBlockNotifier) next;
 };
 
 void ram_block_notifier_add(RAMBlockNotifier *n);
 void ram_block_notifier_remove(RAMBlockNotifier *n);
-void ram_block_notify_add(void *host, size_t size);
-void ram_block_notify_remove(void *host, size_t size);
+void ram_block_notify_add(void *host, size_t size, size_t max_size);
+void ram_block_notify_remove(void *host, size_t size, size_t max_size);
+void ram_block_notify_resize(void *host, size_t old_size, size_t new_size);
 
 void ram_block_dump(Monitor *mon);
 

softmmu/physmem.c

@@ -1807,6 +1807,7 @@ static int memory_try_enable_merging(void *addr, size_t len)
  */
 int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp)
 {
+    const ram_addr_t oldsize = block->used_length;
     const ram_addr_t unaligned_size = newsize;
 
     assert(block);
@@ -1843,6 +1844,11 @@ int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp)
         return -EINVAL;
     }
 
+    /* Notify before modifying the ram block and touching the bitmaps. */
+    if (block->host) {
+        ram_block_notify_resize(block->host, oldsize, newsize);
+    }
+
     cpu_physical_memory_clear_dirty_range(block->offset, block->used_length);
     block->used_length = newsize;
     cpu_physical_memory_set_dirty_range(block->offset, block->used_length,
@@ -2010,7 +2016,8 @@ static void ram_block_add(RAMBlock *new_block, Error **errp, bool shared)
             qemu_madvise(new_block->host, new_block->max_length,
                          QEMU_MADV_DONTFORK);
         }
-        ram_block_notify_add(new_block->host, new_block->max_length);
+        ram_block_notify_add(new_block->host, new_block->used_length,
+                             new_block->max_length);
     }
 }
 
@@ -2189,7 +2196,8 @@ void qemu_ram_free(RAMBlock *block)
     }
 
     if (block->host) {
-        ram_block_notify_remove(block->host, block->max_length);
+        ram_block_notify_remove(block->host, block->used_length,
+                                block->max_length);
     }
 
     qemu_mutex_lock_ramlist();

target/i386/hax/hax-mem.c

@@ -293,7 +293,8 @@ static MemoryListener hax_memory_listener = {
     .priority = 10,
 };
 
-static void hax_ram_block_added(RAMBlockNotifier *n, void *host, size_t size)
+static void hax_ram_block_added(RAMBlockNotifier *n, void *host, size_t size,
+                                size_t max_size)
 {
     /*
      * We must register each RAM block with the HAXM kernel module, or
@@ -304,7 +305,7 @@ static void hax_ram_block_added(RAMBlockNotifier *n, void *host, size_t size)
      * host physical pages for the RAM block as part of this registration
      * process, hence the name hax_populate_ram().
      */
-    if (hax_populate_ram((uint64_t)(uintptr_t)host, size) < 0) {
+    if (hax_populate_ram((uint64_t)(uintptr_t)host, max_size) < 0) {
         fprintf(stderr, "HAX failed to populate RAM\n");
         abort();
     }

target/i386/sev.c

@@ -180,7 +180,8 @@ sev_set_guest_state(SevGuestState *sev, SevState new_state)
 }
 
 static void
-sev_ram_block_added(RAMBlockNotifier *n, void *host, size_t size)
+sev_ram_block_added(RAMBlockNotifier *n, void *host, size_t size,
+                    size_t max_size)
 {
     int r;
     struct kvm_enc_region range;
@@ -197,19 +198,20 @@ sev_ram_block_added(RAMBlockNotifier *n, void *host, size_t size)
     }
 
     range.addr = (__u64)(unsigned long)host;
-    range.size = size;
+    range.size = max_size;
 
-    trace_kvm_memcrypt_register_region(host, size);
+    trace_kvm_memcrypt_register_region(host, max_size);
     r = kvm_vm_ioctl(kvm_state, KVM_MEMORY_ENCRYPT_REG_REGION, &range);
     if (r) {
         error_report("%s: failed to register region (%p+%#zx) error '%s'",
-                     __func__, host, size, strerror(errno));
+                     __func__, host, max_size, strerror(errno));
         exit(1);
     }
 }
 
 static void
-sev_ram_block_removed(RAMBlockNotifier *n, void *host, size_t size)
+sev_ram_block_removed(RAMBlockNotifier *n, void *host, size_t size,
+                      size_t max_size)
 {
     int r;
     struct kvm_enc_region range;
@@ -226,13 +228,13 @@ sev_ram_block_removed(RAMBlockNotifier *n, void *host, size_t size)
     }
 
     range.addr = (__u64)(unsigned long)host;
-    range.size = size;
+    range.size = max_size;
 
-    trace_kvm_memcrypt_unregister_region(host, size);
+    trace_kvm_memcrypt_unregister_region(host, max_size);
     r = kvm_vm_ioctl(kvm_state, KVM_MEMORY_ENCRYPT_UNREG_REGION, &range);
     if (r) {
         error_report("%s: failed to unregister region (%p+%#zx)",
-                     __func__, host, size);
+                     __func__, host, max_size);
     }
 }
 

util/vfio-helpers.c

@@ -459,26 +459,26 @@ fail_container:
     return ret;
 }
 
-static void qemu_vfio_ram_block_added(RAMBlockNotifier *n,
-                                      void *host, size_t size)
+static void qemu_vfio_ram_block_added(RAMBlockNotifier *n, void *host,
+                                      size_t size, size_t max_size)
 {
     QEMUVFIOState *s = container_of(n, QEMUVFIOState, ram_notifier);
     int ret;
 
-    trace_qemu_vfio_ram_block_added(s, host, size);
-    ret = qemu_vfio_dma_map(s, host, size, false, NULL);
+    trace_qemu_vfio_ram_block_added(s, host, max_size);
+    ret = qemu_vfio_dma_map(s, host, max_size, false, NULL);
     if (ret) {
-        error_report("qemu_vfio_dma_map(%p, %zu) failed: %s", host, size,
+        error_report("qemu_vfio_dma_map(%p, %zu) failed: %s", host, max_size,
                      strerror(-ret));
     }
 }
 
-static void qemu_vfio_ram_block_removed(RAMBlockNotifier *n,
-                                        void *host, size_t size)
+static void qemu_vfio_ram_block_removed(RAMBlockNotifier *n, void *host,
+                                        size_t size, size_t max_size)
 {
     QEMUVFIOState *s = container_of(n, QEMUVFIOState, ram_notifier);
     if (host) {
-        trace_qemu_vfio_ram_block_removed(s, host, size);
+        trace_qemu_vfio_ram_block_removed(s, host, max_size);
         qemu_vfio_dma_unmap(s, host);
     }
 }