8 files changed, 81 insertions, 12 deletions
diff --git a/include/block/block-common.h b/include/block/block-common.h
index fdb7306e78..061606e867 100644
--- a/include/block/block-common.h
+++ b/include/block/block-common.h
@@ -80,6 +80,15 @@ typedef enum {
      */
     BDRV_REQ_MAY_UNMAP          = 0x4,
 
+    /*
+     * An optimization hint when all QEMUIOVector elements are within
+     * previously registered bdrv_register_buf() memory ranges.
+     *
+     * Code that replaces the user's QEMUIOVector elements with bounce buffers
+     * must take care to clear this flag.
+     */
+    BDRV_REQ_REGISTERED_BUF     = 0x8,
+
     BDRV_REQ_FUA                = 0x10,
     BDRV_REQ_WRITE_COMPRESSED   = 0x20,
 
diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h
index 21265e3966..eba4ed23b4 100644
--- a/include/block/block-global-state.h
+++ b/include/block/block-global-state.h
@@ -243,9 +243,15 @@ void bdrv_del_child(BlockDriverState *parent, BdrvChild *child, Error **errp);
  * Register/unregister a buffer for I/O. For example, VFIO drivers are
  * interested to know the memory areas that would later be used for I/O, so
  * that they can prepare IOMMU mapping etc., to get better performance.
+ *
+ * Buffers must not overlap and they must be unregistered with the same <host,
+ * size> values that they were registered with.
+ *
+ * Returns: true on success, false on failure
  */
-void bdrv_register_buf(BlockDriverState *bs, void *host, size_t size);
-void bdrv_unregister_buf(BlockDriverState *bs, void *host);
+bool bdrv_register_buf(BlockDriverState *bs, void *host, size_t size,
+                       Error **errp);
+void bdrv_unregister_buf(BlockDriverState *bs, void *host, size_t size);
 
 void bdrv_cancel_in_flight(BlockDriverState *bs);
 
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 8947abab76..9c569be162 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -433,9 +433,12 @@ struct BlockDriver {
      * that it can do IOMMU mapping with VFIO etc., in order to get better
      * performance. In the case of VFIO drivers, this callback is used to do
      * DMA mapping for hot buffers.
+     *
+     * Returns: true on success, false on failure
      */
-    void (*bdrv_register_buf)(BlockDriverState *bs, void *host, size_t size);
-    void (*bdrv_unregister_buf)(BlockDriverState *bs, void *host);
+    bool (*bdrv_register_buf)(BlockDriverState *bs, void *host, size_t size,
+                              Error **errp);
+    void (*bdrv_unregister_buf)(BlockDriverState *bs, void *host, size_t size);
 
     /*
      * This field is modified only under the BQL, and is part of
@@ -1051,7 +1054,7 @@ struct BlockDriverState {
     /*
      * Flags honored during pread
      */
-    unsigned int supported_read_flags;
+    BdrvRequestFlags supported_read_flags;
     /*
      * Flags honored during pwrite (so far: BDRV_REQ_FUA,
      * BDRV_REQ_WRITE_UNCHANGED).
@@ -1069,12 +1072,12 @@ struct BlockDriverState {
      * flag), or they have to explicitly take the WRITE permission for
      * their children.
      */
-    unsigned int supported_write_flags;
+    BdrvRequestFlags supported_write_flags;
     /*
      * Flags honored during pwrite_zeroes (so far: BDRV_REQ_FUA,
      * BDRV_REQ_MAY_UNMAP, BDRV_REQ_WRITE_UNCHANGED)
      */
-    unsigned int supported_zero_flags;
+    BdrvRequestFlags supported_zero_flags;
     /*
      * Flags honoured during truncate (so far: BDRV_REQ_ZERO_WRITE).
      *
@@ -1082,7 +1085,7 @@ struct BlockDriverState {
      * that any added space reads as all zeros. If this can't be guaranteed,
      * the operation must fail.
      */
-    unsigned int supported_truncate_flags;
+    BdrvRequestFlags supported_truncate_flags;
 
     /* the following member gives a name to every node on the bs graph. */
     char node_name[32];
diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h
index c493510ee9..6feaa40ca7 100644
--- a/include/exec/cpu-common.h
+++ b/include/exec/cpu-common.h
@@ -92,6 +92,7 @@ void qemu_ram_set_uf_zeroable(RAMBlock *rb);
 bool qemu_ram_is_migratable(RAMBlock *rb);
 void qemu_ram_set_migratable(RAMBlock *rb);
 void qemu_ram_unset_migratable(RAMBlock *rb);
+int qemu_ram_get_fd(RAMBlock *rb);
 
 size_t qemu_ram_pagesize(RAMBlock *block);
 size_t qemu_ram_pagesize_largest(void);
diff --git a/include/hw/virtio/virtio-blk.h b/include/hw/virtio/virtio-blk.h
index d311c57cca..7f589b4146 100644
--- a/include/hw/virtio/virtio-blk.h
+++ b/include/hw/virtio/virtio-blk.h
@@ -19,6 +19,7 @@
 #include "hw/block/block.h"
 #include "sysemu/iothread.h"
 #include "sysemu/block-backend.h"
+#include "sysemu/block-ram-registrar.h"
 #include "qom/object.h"
 
 #define TYPE_VIRTIO_BLK "virtio-blk-device"
@@ -64,6 +65,7 @@ struct VirtIOBlock {
     struct VirtIOBlockDataPlane *dataplane;
     uint64_t host_features;
     size_t config_size;
+    BlockRAMRegistrar blk_ram_registrar;
 };
 
 typedef struct VirtIOBlockReq {
diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h
index aae33cce17..608fe45dcf 100644
--- a/include/qemu/coroutine.h
+++ b/include/qemu/coroutine.h
@@ -198,14 +198,25 @@ typedef struct CoQueue {
  */
 void qemu_co_queue_init(CoQueue *queue);
 
+typedef enum {
+    /*
+     * Enqueue at front instead of back. Use this to re-queue a request when
+     * its wait condition is not satisfied after being woken up.
+     */
+    CO_QUEUE_WAIT_FRONT = 0x1,
+} CoQueueWaitFlags;
+
 /**
  * Adds the current coroutine to the CoQueue and transfers control to the
  * caller of the coroutine.  The mutex is unlocked during the wait and
  * locked again afterwards.
  */
 #define qemu_co_queue_wait(queue, lock) \
-    qemu_co_queue_wait_impl(queue, QEMU_MAKE_LOCKABLE(lock))
-void coroutine_fn qemu_co_queue_wait_impl(CoQueue *queue, QemuLockable *lock);
+    qemu_co_queue_wait_impl(queue, QEMU_MAKE_LOCKABLE(lock), 0)
+#define qemu_co_queue_wait_flags(queue, lock, flags) \
+    qemu_co_queue_wait_impl(queue, QEMU_MAKE_LOCKABLE(lock), (flags))
+void coroutine_fn qemu_co_queue_wait_impl(CoQueue *queue, QemuLockable *lock,
+                                          CoQueueWaitFlags flags);
 
 /**
  * Removes the next coroutine from the CoQueue, and queue it to run after
diff --git a/include/sysemu/block-backend-global-state.h b/include/sysemu/block-backend-global-state.h
index 415f0c91d7..6858e39cb6 100644
--- a/include/sysemu/block-backend-global-state.h
+++ b/include/sysemu/block-backend-global-state.h
@@ -106,8 +106,8 @@ void blk_io_limits_enable(BlockBackend *blk, const char *group);
 void blk_io_limits_update_group(BlockBackend *blk, const char *group);
 void blk_set_force_allow_inactivate(BlockBackend *blk);
 
-void blk_register_buf(BlockBackend *blk, void *host, size_t size);
-void blk_unregister_buf(BlockBackend *blk, void *host);
+bool blk_register_buf(BlockBackend *blk, void *host, size_t size, Error **errp);
+void blk_unregister_buf(BlockBackend *blk, void *host, size_t size);
 
 const BdrvChild *blk_root(BlockBackend *blk);
 
diff --git a/include/sysemu/block-ram-registrar.h b/include/sysemu/block-ram-registrar.h
new file mode 100644
index 0000000000..d8b2f7942b
--- /dev/null
+++ b/include/sysemu/block-ram-registrar.h
@@ -0,0 +1,37 @@
+/*
+ * BlockBackend RAM Registrar
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#ifndef BLOCK_RAM_REGISTRAR_H
+#define BLOCK_RAM_REGISTRAR_H
+
+#include "exec/ramlist.h"
+
+/**
+ * struct BlockRAMRegistrar:
+ *
+ * Keeps RAMBlock memory registered with a BlockBackend using
+ * blk_register_buf() including hotplugged memory.
+ *
+ * Emulated devices or other BlockBackend users initialize a BlockRAMRegistrar
+ * with blk_ram_registrar_init() before submitting I/O requests with the
+ * BDRV_REQ_REGISTERED_BUF flag set.
+ */
+typedef struct {
+    BlockBackend *blk;
+    RAMBlockNotifier notifier;
+    bool ok;
+} BlockRAMRegistrar;
+
+void blk_ram_registrar_init(BlockRAMRegistrar *r, BlockBackend *blk);
+void blk_ram_registrar_destroy(BlockRAMRegistrar *r);
+
+/* Have all RAMBlocks been registered successfully? */
+static inline bool blk_ram_registrar_ok(BlockRAMRegistrar *r)
+{
+    return r->ok;
+}
+
+#endif /* BLOCK_RAM_REGISTRAR_H */