[Qemu-devel] [PATCHv2-repost 1/3] qemu: memory notifiers

["Michael S. Tsirkin" <mst@redhat.com>]

This adds notifiers for phys memory changes: a set of callbacks that
vhost can register and update kernel accordingly.  Down the road, kvm
code can be switched to use these as well, instead of calling kvm code
directly from exec.c as is done now.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Avi Kivity <avi@redhat.com>

---
 cpu-common.h |   19 ++++++++++
 exec.c       |  111 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 127 insertions(+), 3 deletions(-)

diff --git a/cpu-common.h b/cpu-common.h
index 6302372..0ec9b72 100644
--- a/cpu-common.h
+++ b/cpu-common.h
@@ -8,6 +8,7 @@
 #endif
 
 #include "bswap.h"
+#include "qemu-queue.h"
 
 /* address in the RAM (different from a physical address) */
 typedef unsigned long ram_addr_t;
@@ -61,6 +62,24 @@ void cpu_physical_memory_unmap(void *buffer, target_phys_addr_t len,
 void *cpu_register_map_client(void *opaque, void (*callback)(void *opaque));
 void cpu_unregister_map_client(void *cookie);
 
+struct CPUPhysMemoryClient;
+typedef struct CPUPhysMemoryClient CPUPhysMemoryClient;
+struct CPUPhysMemoryClient {
+    void (*set_memory)(struct CPUPhysMemoryClient *client,
+                       target_phys_addr_t start_addr,
+                       ram_addr_t size,
+                       ram_addr_t phys_offset);
+    int (*sync_dirty_bitmap)(struct CPUPhysMemoryClient *client,
+                             target_phys_addr_t start_addr,
+                             target_phys_addr_t end_addr);
+    int (*migration_log)(struct CPUPhysMemoryClient *client,
+                         int enable);
+    QLIST_ENTRY(CPUPhysMemoryClient) list;
+};
+
+void cpu_register_phys_memory_client(CPUPhysMemoryClient *);
+void cpu_unregister_phys_memory_client(CPUPhysMemoryClient *);
+
 uint32_t ldub_phys(target_phys_addr_t addr);
 uint32_t lduw_phys(target_phys_addr_t addr);
 uint32_t ldl_phys(target_phys_addr_t addr);
diff --git a/exec.c b/exec.c
index 1190591..56c347b 100644
--- a/exec.c
+++ b/exec.c
@@ -1623,6 +1623,99 @@ const CPULogItem cpu_log_items[] = {
     { 0, NULL, NULL },
 };
 
+static QLIST_HEAD(memory_client_list, CPUPhysMemoryClient) memory_client_list
+    = QLIST_HEAD_INITIALIZER(memory_client_list);
+
+static void cpu_notify_set_memory(target_phys_addr_t start_addr,
+				  ram_addr_t size,
+				  ram_addr_t phys_offset)
+{
+    CPUPhysMemoryClient *client;
+    QLIST_FOREACH(client, &memory_client_list, list) {
+        client->set_memory(client, start_addr, size, phys_offset);
+    }
+}
+
+static int cpu_notify_sync_dirty_bitmap(target_phys_addr_t start,
+					target_phys_addr_t end)
+{
+    CPUPhysMemoryClient *client;
+    QLIST_FOREACH(client, &memory_client_list, list) {
+        int r = client->sync_dirty_bitmap(client, start, end);
+        if (r < 0)
+            return r;
+    }
+    return 0;
+}
+
+static int cpu_notify_migration_log(int enable)
+{
+    CPUPhysMemoryClient *client;
+    QLIST_FOREACH(client, &memory_client_list, list) {
+        int r = client->migration_log(client, enable);
+        if (r < 0)
+            return r;
+    }
+    return 0;
+}
+
+static void phys_page_for_each_in_l1_map(PhysPageDesc **phys_map,
+                                         CPUPhysMemoryClient *client)
+{
+    PhysPageDesc *pd;
+    int l1, l2;
+
+    for (l1 = 0; l1 < L1_SIZE; ++l1) {
+        pd = phys_map[l1];
+        if (!pd) {
+            continue;
+        }
+        for (l2 = 0; l2 < L2_SIZE; ++l2) {
+            if (pd[l2].phys_offset == IO_MEM_UNASSIGNED) {
+                continue;
+            }
+            client->set_memory(client, pd[l2].region_offset,
+                               TARGET_PAGE_SIZE, pd[l2].phys_offset);
+        }
+    }
+}
+
+static void phys_page_for_each(CPUPhysMemoryClient *client)
+{
+#if TARGET_PHYS_ADDR_SPACE_BITS > 32
+
+#if TARGET_PHYS_ADDR_SPACE_BITS > (32 + L1_BITS)
+#error unsupported TARGET_PHYS_ADDR_SPACE_BITS
+#endif
+    void **phys_map = (void **)l1_phys_map;
+    int l1;
+    if (!l1_phys_map) {
+        return;
+    }
+    for (l1 = 0; l1 < L1_SIZE; ++l1) {
+        if (phys_map[l1]) {
+            phys_page_for_each_in_l1_map(phys_map[l1], client);
+        }
+    }
+#else
+    if (!l1_phys_map) {
+        return;
+    }
+    phys_page_for_each_in_l1_map(l1_phys_map, client);
+#endif
+}
+
+void cpu_register_phys_memory_client(CPUPhysMemoryClient *client)
+{
+    QLIST_INSERT_HEAD(&memory_client_list, client, list);
+    phys_page_for_each(client);
+}
+
+void cpu_unregister_phys_memory_client(CPUPhysMemoryClient *client)
+{
+    QLIST_REMOVE(client, list);
+}
+
 static int cmp1(const char *s1, int n, const char *s2)
 {
     if (strlen(s2) != n)
@@ -1882,11 +1975,16 @@ void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t end,
 
 int cpu_physical_memory_set_dirty_tracking(int enable)
 {
+    int ret = 0;
     in_migration = enable;
     if (kvm_enabled()) {
-        return kvm_set_migration_log(enable);
+        ret = kvm_set_migration_log(enable);
     }
-    return 0;
+    if (ret < 0) {
+        return ret;
+    }
+    ret = cpu_notify_migration_log(!!enable);
+    return ret;
 }
 
 int cpu_physical_memory_get_dirty_tracking(void)
@@ -1899,8 +1997,13 @@ int cpu_physical_sync_dirty_bitmap(target_phys_addr_t start_addr,
 {
     int ret = 0;
 
-    if (kvm_enabled())
+    if (kvm_enabled()) {
         ret = kvm_physical_sync_dirty_bitmap(start_addr, end_addr);
+    }
+    if (ret < 0) {
+        return ret;
+    }
+    ret = cpu_notify_sync_dirty_bitmap(start_addr, end_addr);
     return ret;
 }
 
@@ -2315,6 +2418,8 @@ void cpu_register_physical_memory_offset(target_phys_addr_t start_addr,
     if (kvm_enabled())
         kvm_set_phys_mem(start_addr, size, phys_offset);
 
+    cpu_notify_set_memory(start_addr, size, phys_offset);
+
     if (phys_offset == IO_MEM_UNASSIGNED) {
         region_offset = start_addr;
     }
-- 
1.6.6.144.g5c3af