[PATCH v1 03/13] numa: Teach ram block notifiers about resizeable ram blocks

[David Hildenbrand <david@redhat.com>]

Ram block notifiers are currently not aware of resizes. Especially to
handle resizes during migration, but also to implement actually resizeable
ram blocks (make everything between used_length and max_length
inaccessible), 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>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Cc: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Anthony Perard <anthony.perard@citrix.com>
Cc: Paul Durrant <paul@xen.org>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: xen-devel@lists.xenproject.org
Cc: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 exec.c                     | 13 +++++++++++--
 hw/core/numa.c             | 22 +++++++++++++++++-----
 hw/i386/xen/xen-mapcache.c |  7 ++++---
 include/exec/ramlist.h     | 13 +++++++++----
 target/i386/hax-mem.c      |  5 +++--
 target/i386/sev.c          | 18 ++++++++++--------
 util/vfio-helpers.c        | 17 +++++++++--------
 7 files changed, 63 insertions(+), 32 deletions(-)

diff --git a/exec.c b/exec.c
index dfd43d27c6..b75250e773 100644
--- a/exec.c
+++ b/exec.c
@@ -2129,6 +2129,8 @@ 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;
+
     assert(block);
 
     newsize = HOST_PAGE_ALIGN(newsize);
@@ -2153,6 +2155,11 @@ 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,
@@ -2312,7 +2319,8 @@ static void ram_block_add(RAMBlock *new_block, Error **errp, bool shared)
         qemu_madvise(new_block->host, new_block->max_length, QEMU_MADV_HUGEPAGE);
         /* MADV_DONTFORK is also needed by KVM in absence of synchronous MMU */
         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);
     }
 }
 
@@ -2492,7 +2500,8 @@ 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();
diff --git a/hw/core/numa.c b/hw/core/numa.c
index 6599c69e05..e28ad24fcd 100644
--- a/hw/core/numa.c
+++ b/hw/core/numa.c
@@ -902,11 +902,12 @@ 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;
 }
@@ -923,20 +924,31 @@ 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);
+        }
     }
 }
diff --git a/hw/i386/xen/xen-mapcache.c b/hw/i386/xen/xen-mapcache.c
index 5b120ed44b..d6dcea65d1 100644
--- a/hw/i386/xen/xen-mapcache.c
+++ b/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);
         }
         if (munmap(entry->vaddr_base, entry->size) != 0) {
             perror("unmap fails");
@@ -211,7 +212,7 @@ 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;
@@ -452,7 +453,7 @@ 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);
diff --git a/include/exec/ramlist.h b/include/exec/ramlist.h
index bc4faa1b00..293c0ddabe 100644
--- a/include/exec/ramlist.h
+++ b/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);
 
diff --git a/target/i386/hax-mem.c b/target/i386/hax-mem.c
index 6bb5a24917..454d7fb212 100644
--- a/target/i386/hax-mem.c
+++ b/target/i386/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();
     }
diff --git a/target/i386/sev.c b/target/i386/sev.c
index 024bb24e51..6b4cee24a2 100644
--- a/target/i386/sev.c
+++ b/target/i386/sev.c
@@ -129,7 +129,8 @@ sev_set_guest_state(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;
@@ -146,19 +147,20 @@ 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;
@@ -175,13 +177,13 @@ 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);
     }
 }
 
diff --git a/util/vfio-helpers.c b/util/vfio-helpers.c
index 71e02e7f35..61a0cf6e12 100644
--- a/util/vfio-helpers.c
+++ b/util/vfio-helpers.c
@@ -372,25 +372,26 @@ 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: %d", host, size, ret);
+        error_report("qemu_vfio_dma_map(%p, %zu) failed: %d", host,
+                     max_size, 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);
     }
 }
-- 
2.24.1