All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v3 00/25] block layer: split block APIs in global state and I/O
@ 2021-10-12  8:48 Emanuele Giuseppe Esposito
  2021-10-12  8:48 ` [PATCH v3 01/25] main-loop.h: introduce qemu_in_main_thread() Emanuele Giuseppe Esposito
                   ` (24 more replies)
  0 siblings, 25 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

Currently, block layer APIs like block-backend.h contain a mix of
functions that are either running in the main loop and under the
BQL, or are thread-safe functions and run in iothreads performing I/O.
The functions running under BQL also take care of modifying the
block graph, by using drain and/or aio_context_acquire/release.
This makes it very confusing to understand where each function
runs, and what assumptions it provided with regards to thread
safety.

We call the functions running under BQL "global state (GS) API", and
distinguish them from the thread-safe "I/O API".

The aim of this series is to split the relevant block headers in
global state and I/O sub-headers. The division will be done in
this way:
header.h will be split in header-global-state.h, header-io.h and
header-common.h. The latter will just contain the data structures
needed by header-global-state and header-io, and common helpers
that are neither in GS nor in I/O. header.h will remain for
legacy and to avoid changing all includes in all QEMU c files,
but will only include the two new headers. No function shall be
added in header.c .
Once we split all relevant headers, it will be much easier to see what
uses the AioContext lock and remove it, which is the overall main
goal of this and other series that I posted/will post.

In addition to splitting the relevant headers shown in this series,
it is also very helpful splitting the function pointers in some
block structures, to understand what runs under AioContext lock and
what doesn't. This is what patches 19-25 do.

Each function in the GS API will have an assertion, checking
that it is always running under BQL.
I/O functions are instead thread safe (or so should be), meaning
that they *can* run under BQL, but also in an iothread in another
AioContext. Therefore they do not provide any assertion, and
need to be audited manually to verify the correctness.

Adding assetions has helped finding 2 bugs already, as shown in
my series "Migration: fix missing iothread locking".

Tested this series by running unit tests, qemu-iotests and qtests
(x86_64).
Some functions in the GS API are used everywhere but not
properly tested. Therefore their assertion is never actually run in
the tests, so despite my very careful auditing, it is not impossible
to exclude that some will trigger while actually using QEMU.

Patch 1 introduces qemu_in_main_thread(), the function used in
all assertions. This had to be introduced otherwise all unit tests
would fail, since they run in the main loop but use the code in
stubs/iothread.c
Patches 2-14 and 19-25 (with the exception of patch 9, that is an additional
assert) are all structured in the same way: first we split the header
and in the next (even) patch we add assertions.
The rest of the patches ontain either both assertions and split,
or have no assertions.

Next steps once this get reviewed:
1) audit the GS API and replace the AioContext lock with drains,
or remove them when not necessary (requires further discussion).
2) [optional as it should be already the case] audit the I/O API
and check that thread safety is guaranteed

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
v2 -> v3:
* rename "graph API" into "global state API"
* change order of patches, block.h comes before block-backend.h
* change GS and I/O comment headers to avoid redundancy, all other
  headers refer to block-global-state.h and block-io.h
* fix typo on GS and I/O headers
* use assert instead of g_assert
* move bdrv_pwrite_sync, bdrv_block_status and bdrv_co_copy_range_{from/to}
  to the I/O API
* change assert_bdrv_graph_writable implementation, since we need
  to introduce additional drains
* remove transactions API split
* add preparation patch for blockdev.h (patch 13)
* backup-top -> copy-on-write
* change I/O comment in job.h into a better meaningful explanation
* fix all warnings given by checkpatch, mostly due to /* */ to be
  split in separate lines
* rebase on current master (c09124dcb8), and split the following new functions:
	blk_replace_bs (I/O)
	bdrv_bsc_is_data (I/O)
	bdrv_bsc_invalidate_range (I/O)
	bdrv_bsc_fill (I/O)
	bdrv_new_open_driver_opts (GS)
	blk_get_max_hw_iov (I/O)
  they are all added in patches 4 and 6.

v1 -> v2:
* remove the iothread locking bug fix, and send it as separate patch
* rename graph API -> global state API
* better documented patch 1 (qemu_in_main_thread)
* add and split all other block layer headers
* fix warnings given by checkpatch on multiline comments

Emanuele Giuseppe Esposito (25):
  main-loop.h: introduce qemu_in_main_thread()
  include/block/block: split header into I/O and global state API
  assertions for block global state API
  include/sysemu/block-backend: split header into I/O and global state
    (GS) API
  block/block-backend.c: assertions for block-backend
  include/block/block_int: split header into I/O and global state API
  assertions for block_int global state API
  block: introduce assert_bdrv_graph_writable
  include/block/blockjob_int.h: split header into I/O and GS API
  assertions for blockjob_int.h
  include/block/blockjob.h: global state API
  assertions for blockob.h global state API
  include/sysemu/blockdev.h: move drive_add and inline drive_def
  include/systemu/blockdev.h: global state API
  assertions for blockdev.h global state API
  include/block/snapshot: global state API + assertions
  block/copy-before-write.h: global state API + assertions
  block/coroutines: I/O API
  block_int-common.h: split function pointers in BlockDriver
  block_int-common.h: assertion in the callers of BlockDriver function
    pointers
  block_int-common.h: split function pointers in BdrvChildClass
  block_int-common.h: assertions in the callers of BdrvChildClass
    function pointers
  block-backend-common.h: split function pointers in BlockDevOps
  job.h: split function pointers in JobDriver
  job.h: assertions in the callers of JobDriver funcion pointers

 block.c                                     |  188 ++-
 block/backup.c                              |    1 +
 block/block-backend.c                       |  104 +-
 block/commit.c                              |    4 +
 block/copy-before-write.c                   |    2 +
 block/copy-before-write.h                   |    7 +
 block/coroutines.h                          |    7 +
 block/dirty-bitmap.c                        |    1 +
 block/io.c                                  |   37 +
 block/meson.build                           |    7 +-
 block/mirror.c                              |    4 +
 block/monitor/bitmap-qmp-cmds.c             |    6 +
 block/monitor/block-hmp-cmds.c              |    2 +-
 block/snapshot.c                            |   28 +
 block/stream.c                              |    2 +
 blockdev.c                                  |   52 +-
 blockjob.c                                  |   14 +
 include/block/block-common.h                |  389 +++++
 include/block/block-global-state.h          |  263 ++++
 include/block/block-io.h                    |  283 ++++
 include/block/block.h                       |  863 +----------
 include/block/block_int-common.h            | 1193 +++++++++++++++
 include/block/block_int-global-state.h      |  327 ++++
 include/block/block_int-io.h                |  163 ++
 include/block/block_int.h                   | 1478 +------------------
 include/block/blockjob.h                    |    9 +
 include/block/blockjob_int.h                |   28 +
 include/block/snapshot.h                    |   13 +-
 include/qemu/job.h                          |   16 +
 include/qemu/main-loop.h                    |   13 +
 include/sysemu/block-backend-common.h       |   92 ++
 include/sysemu/block-backend-global-state.h |  122 ++
 include/sysemu/block-backend-io.h           |  134 ++
 include/sysemu/block-backend.h              |  264 +---
 include/sysemu/blockdev.h                   |   20 +-
 job.c                                       |    9 +
 migration/savevm.c                          |    2 +
 softmmu/cpus.c                              |    5 +
 softmmu/qdev-monitor.c                      |    2 +
 softmmu/vl.c                                |   25 +-
 stubs/iothread-lock.c                       |    5 +
 41 files changed, 3544 insertions(+), 2640 deletions(-)
 create mode 100644 include/block/block-common.h
 create mode 100644 include/block/block-global-state.h
 create mode 100644 include/block/block-io.h
 create mode 100644 include/block/block_int-common.h
 create mode 100644 include/block/block_int-global-state.h
 create mode 100644 include/block/block_int-io.h
 create mode 100644 include/sysemu/block-backend-common.h
 create mode 100644 include/sysemu/block-backend-global-state.h
 create mode 100644 include/sysemu/block-backend-io.h

-- 
2.27.0



^ permalink raw reply	[flat|nested] 39+ messages in thread

* [PATCH v3 01/25] main-loop.h: introduce qemu_in_main_thread()
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-12  8:48 ` [PATCH v3 02/25] include/block/block: split header into I/O and global state API Emanuele Giuseppe Esposito
                   ` (23 subsequent siblings)
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

When invoked from the main loop, this function is the same
as qemu_mutex_iothread_locked, and returns true if the BQL is held.
When invoked from iothreads or tests, it returns true only
if the current AioContext is the Main Loop.

This essentially just extends qemu_mutex_iothread_locked to work
also in unit tests or other users like storage-daemon, that run
in the Main Loop but end up using the implementation in
stubs/iothread-lock.c.

Using qemu_mutex_iothread_locked in unit tests defaults to false
because they use the implementation in stubs/iothread-lock,
making all assertions added in next patches fail despite the
AioContext is still the main loop.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/qemu/main-loop.h | 13 +++++++++++++
 softmmu/cpus.c           |  5 +++++
 stubs/iothread-lock.c    |  5 +++++
 3 files changed, 23 insertions(+)

diff --git a/include/qemu/main-loop.h b/include/qemu/main-loop.h
index 8dbc6fcb89..6b8fa57c5d 100644
--- a/include/qemu/main-loop.h
+++ b/include/qemu/main-loop.h
@@ -245,6 +245,19 @@ AioContext *iohandler_get_aio_context(void);
  */
 bool qemu_mutex_iothread_locked(void);
 
+/**
+ * qemu_in_main_thread: same as qemu_mutex_iothread_locked when
+ * softmmu/cpus.c implementation is linked. Otherwise this function
+ * checks that the current AioContext is the global AioContext
+ * (main loop).
+ *
+ * This is useful when checking that the BQL is held, to avoid
+ * returning false when invoked by unit tests or other users like
+ * storage-daemon that end up using stubs/iothread-lock.c
+ * implementation.
+ */
+bool qemu_in_main_thread(void);
+
 /**
  * qemu_mutex_lock_iothread: Lock the main loop mutex.
  *
diff --git a/softmmu/cpus.c b/softmmu/cpus.c
index 071085f840..3f61a3c31d 100644
--- a/softmmu/cpus.c
+++ b/softmmu/cpus.c
@@ -481,6 +481,11 @@ bool qemu_mutex_iothread_locked(void)
     return iothread_locked;
 }
 
+bool qemu_in_main_thread(void)
+{
+    return qemu_mutex_iothread_locked();
+}
+
 /*
  * The BQL is taken from so many places that it is worth profiling the
  * callers directly, instead of funneling them all through a single function.
diff --git a/stubs/iothread-lock.c b/stubs/iothread-lock.c
index 5b45b7fc8b..ff7386e42c 100644
--- a/stubs/iothread-lock.c
+++ b/stubs/iothread-lock.c
@@ -6,6 +6,11 @@ bool qemu_mutex_iothread_locked(void)
     return false;
 }
 
+bool qemu_in_main_thread(void)
+{
+    return qemu_get_current_aio_context() == qemu_get_aio_context();
+}
+
 void qemu_mutex_lock_iothread_impl(const char *file, int line)
 {
 }
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 02/25] include/block/block: split header into I/O and global state API
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
  2021-10-12  8:48 ` [PATCH v3 01/25] main-loop.h: introduce qemu_in_main_thread() Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-14 20:31   ` Eric Blake
  2021-10-21 14:11   ` Stefan Hajnoczi
  2021-10-12  8:48 ` [PATCH v3 03/25] assertions for block " Emanuele Giuseppe Esposito
                   ` (22 subsequent siblings)
  24 siblings, 2 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

block.h currently contains a mix of functions:
some of them run under the BQL and modify the block layer graph,
others are instead thread-safe and perform I/O in iothreads.
It is not easy to understand which function is part of which
group (I/O vs GS), and this patch aims to clarify it.

The "GS" functions need the BQL, and often use
aio_context_acquire/release and/or drain to be sure they
can modify the graph safely.
The I/O function are instead thread safe, and can run in
any AioContext.

By splitting the header in two files, block-io.h
and block-global-state.h we have a clearer view on what
needs what kind of protection. block-common.h
instead contains common structures shared by both headers.

block.h is left there for legacy and to avoid changing
all includes in all c files that use the block APIs.

Assertions are added in the next patch.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 block.c                            |   3 +
 block/meson.build                  |   7 +-
 include/block/block-common.h       | 389 +++++++++++++
 include/block/block-global-state.h | 263 +++++++++
 include/block/block-io.h           | 283 ++++++++++
 include/block/block.h              | 863 +----------------------------
 6 files changed, 947 insertions(+), 861 deletions(-)
 create mode 100644 include/block/block-common.h
 create mode 100644 include/block/block-global-state.h
 create mode 100644 include/block/block-io.h

diff --git a/block.c b/block.c
index 45f653a88b..6fdb4d7712 100644
--- a/block.c
+++ b/block.c
@@ -67,12 +67,15 @@
 
 #define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */
 
+/* Protected by BQL */
 static QTAILQ_HEAD(, BlockDriverState) graph_bdrv_states =
     QTAILQ_HEAD_INITIALIZER(graph_bdrv_states);
 
+/* Protected by BQL */
 static QTAILQ_HEAD(, BlockDriverState) all_bdrv_states =
     QTAILQ_HEAD_INITIALIZER(all_bdrv_states);
 
+/* Protected by BQL */
 static QLIST_HEAD(, BlockDriver) bdrv_drivers =
     QLIST_HEAD_INITIALIZER(bdrv_drivers);
 
diff --git a/block/meson.build b/block/meson.build
index 66ee11e62c..41ac0eeb07 100644
--- a/block/meson.build
+++ b/block/meson.build
@@ -113,8 +113,11 @@ block_ss.add(module_block_h)
 wrapper_py = find_program('../scripts/block-coroutine-wrapper.py')
 block_gen_c = custom_target('block-gen.c',
                             output: 'block-gen.c',
-                            input: files('../include/block/block.h',
-                                         'coroutines.h'),
+                            input: files(
+                                      '../include/block/block-io.h',
+                                      '../include/block/block-global-state.h',
+                                      'coroutines.h'
+                                      ),
                             command: [wrapper_py, '@OUTPUT@', '@INPUT@'])
 block_ss.add(block_gen_c)
 
diff --git a/include/block/block-common.h b/include/block/block-common.h
new file mode 100644
index 0000000000..4f1fd8de21
--- /dev/null
+++ b/include/block/block-common.h
@@ -0,0 +1,389 @@
+#ifndef BLOCK_COMMON_H
+#define BLOCK_COMMON_H
+
+#include "block/aio.h"
+#include "block/aio-wait.h"
+#include "qemu/iov.h"
+#include "qemu/coroutine.h"
+#include "block/accounting.h"
+#include "block/dirty-bitmap.h"
+#include "block/blockjob.h"
+#include "qemu/hbitmap.h"
+#include "qemu/transactions.h"
+
+/*
+ * generated_co_wrapper
+ *
+ * Function specifier, which does nothing but mark functions to be
+ * generated by scripts/block-coroutine-wrapper.py
+ *
+ * Read more in docs/devel/block-coroutine-wrapper.rst
+ */
+#define generated_co_wrapper
+
+#define BLKDBG_EVENT(child, evt) \
+    do { \
+        if (child) { \
+            bdrv_debug_event(child->bs, evt); \
+        } \
+    } while (0)
+
+/* block.c */
+typedef struct BlockDriver BlockDriver;
+typedef struct BdrvChild BdrvChild;
+typedef struct BdrvChildClass BdrvChildClass;
+
+typedef struct BlockDriverInfo {
+    /* in bytes, 0 if irrelevant */
+    int cluster_size;
+    /* offset at which the VM state can be saved (0 if not possible) */
+    int64_t vm_state_offset;
+    bool is_dirty;
+    /*
+     * True if this block driver only supports compressed writes
+     */
+    bool needs_compressed_writes;
+} BlockDriverInfo;
+
+typedef struct BlockFragInfo {
+    uint64_t allocated_clusters;
+    uint64_t total_clusters;
+    uint64_t fragmented_clusters;
+    uint64_t compressed_clusters;
+} BlockFragInfo;
+
+typedef enum {
+    BDRV_REQ_COPY_ON_READ       = 0x1,
+    BDRV_REQ_ZERO_WRITE         = 0x2,
+
+    /*
+     * The BDRV_REQ_MAY_UNMAP flag is used in write_zeroes requests to indicate
+     * that the block driver should unmap (discard) blocks if it is guaranteed
+     * that the result will read back as zeroes. The flag is only passed to the
+     * driver if the block device is opened with BDRV_O_UNMAP.
+     */
+    BDRV_REQ_MAY_UNMAP          = 0x4,
+
+    BDRV_REQ_FUA                = 0x10,
+    BDRV_REQ_WRITE_COMPRESSED   = 0x20,
+
+    /*
+     * Signifies that this write request will not change the visible disk
+     * content.
+     */
+    BDRV_REQ_WRITE_UNCHANGED    = 0x40,
+
+    /*
+     * Forces request serialisation. Use only with write requests.
+     */
+    BDRV_REQ_SERIALISING        = 0x80,
+
+    /*
+     * Execute the request only if the operation can be offloaded or otherwise
+     * be executed efficiently, but return an error instead of using a slow
+     * fallback.
+     */
+    BDRV_REQ_NO_FALLBACK        = 0x100,
+
+    /*
+     * BDRV_REQ_PREFETCH makes sense only in the context of copy-on-read
+     * (i.e., together with the BDRV_REQ_COPY_ON_READ flag or when a COR
+     * filter is involved), in which case it signals that the COR operation
+     * need not read the data into memory (qiov) but only ensure they are
+     * copied to the top layer (i.e., that COR operation is done).
+     */
+    BDRV_REQ_PREFETCH  = 0x200,
+
+    /*
+     * If we need to wait for other requests, just fail immediately. Used
+     * only together with BDRV_REQ_SERIALISING.
+     */
+    BDRV_REQ_NO_WAIT = 0x400,
+
+    /* Mask of valid flags */
+    BDRV_REQ_MASK               = 0x7ff,
+} BdrvRequestFlags;
+
+#define BDRV_O_NO_SHARE    0x0001 /* don't share permissions */
+#define BDRV_O_RDWR        0x0002
+#define BDRV_O_RESIZE      0x0004 /* request permission for resizing the node */
+#define BDRV_O_SNAPSHOT    0x0008 /* open the file read only and save
+                                     writes in a snapshot */
+#define BDRV_O_TEMPORARY   0x0010 /* delete the file after use */
+#define BDRV_O_NOCACHE     0x0020 /* do not use the host page cache */
+#define BDRV_O_NATIVE_AIO  0x0080 /* use native AIO instead of the
+                                     thread pool */
+#define BDRV_O_NO_BACKING  0x0100 /* don't open the backing file */
+#define BDRV_O_NO_FLUSH    0x0200 /* disable flushing on this disk */
+#define BDRV_O_COPY_ON_READ 0x0400 /* copy read backing sectors into image */
+#define BDRV_O_INACTIVE    0x0800  /* consistency hint for migration handoff */
+#define BDRV_O_CHECK       0x1000  /* open solely for consistency check */
+#define BDRV_O_ALLOW_RDWR  0x2000  /* allow reopen to change from r/o to r/w */
+#define BDRV_O_UNMAP       0x4000  /* execute guest UNMAP/TRIM operations */
+#define BDRV_O_PROTOCOL    0x8000  /* if no block driver is explicitly given:
+                                      select an appropriate protocol driver,
+                                      ignoring the format layer */
+#define BDRV_O_NO_IO       0x10000 /* don't initialize for I/O */
+#define BDRV_O_AUTO_RDONLY 0x20000 /* degrade to read-only if opening
+                                      read-write fails */
+#define BDRV_O_IO_URING    0x40000 /* use io_uring instead of the thread pool */
+
+#define BDRV_O_CACHE_MASK  (BDRV_O_NOCACHE | BDRV_O_NO_FLUSH)
+
+
+/* Option names of options parsed by the block layer */
+
+#define BDRV_OPT_CACHE_WB       "cache.writeback"
+#define BDRV_OPT_CACHE_DIRECT   "cache.direct"
+#define BDRV_OPT_CACHE_NO_FLUSH "cache.no-flush"
+#define BDRV_OPT_READ_ONLY      "read-only"
+#define BDRV_OPT_AUTO_READ_ONLY "auto-read-only"
+#define BDRV_OPT_DISCARD        "discard"
+#define BDRV_OPT_FORCE_SHARE    "force-share"
+
+
+#define BDRV_SECTOR_BITS   9
+#define BDRV_SECTOR_SIZE   (1ULL << BDRV_SECTOR_BITS)
+
+#define BDRV_REQUEST_MAX_SECTORS MIN_CONST(SIZE_MAX >> BDRV_SECTOR_BITS, \
+                                           INT_MAX >> BDRV_SECTOR_BITS)
+#define BDRV_REQUEST_MAX_BYTES (BDRV_REQUEST_MAX_SECTORS << BDRV_SECTOR_BITS)
+
+/*
+ * We want allow aligning requests and disk length up to any 32bit alignment
+ * and don't afraid of overflow.
+ * To achieve it, and in the same time use some pretty number as maximum disk
+ * size, let's define maximum "length" (a limit for any offset/bytes request and
+ * for disk size) to be the greatest power of 2 less than INT64_MAX.
+ */
+#define BDRV_MAX_ALIGNMENT (1L << 30)
+#define BDRV_MAX_LENGTH (QEMU_ALIGN_DOWN(INT64_MAX, BDRV_MAX_ALIGNMENT))
+
+/*
+ * Allocation status flags for bdrv_block_status() and friends.
+ *
+ * Public flags:
+ * BDRV_BLOCK_DATA: allocation for data at offset is tied to this layer
+ * BDRV_BLOCK_ZERO: offset reads as zero
+ * BDRV_BLOCK_OFFSET_VALID: an associated offset exists for accessing raw data
+ * BDRV_BLOCK_ALLOCATED: the content of the block is determined by this
+ *                       layer rather than any backing, set by block layer
+ * BDRV_BLOCK_EOF: the returned pnum covers through end of file for this
+ *                 layer, set by block layer
+ *
+ * Internal flags:
+ * BDRV_BLOCK_RAW: for use by passthrough drivers, such as raw, to request
+ *                 that the block layer recompute the answer from the returned
+ *                 BDS; must be accompanied by just BDRV_BLOCK_OFFSET_VALID.
+ * BDRV_BLOCK_RECURSE: request that the block layer will recursively search for
+ *                     zeroes in file child of current block node inside
+ *                     returned region. Only valid together with both
+ *                     BDRV_BLOCK_DATA and BDRV_BLOCK_OFFSET_VALID. Should not
+ *                     appear with BDRV_BLOCK_ZERO.
+ *
+ * If BDRV_BLOCK_OFFSET_VALID is set, the map parameter represents the
+ * host offset within the returned BDS that is allocated for the
+ * corresponding raw guest data.  However, whether that offset
+ * actually contains data also depends on BDRV_BLOCK_DATA, as follows:
+ *
+ * DATA ZERO OFFSET_VALID
+ *  t    t        t       sectors read as zero, returned file is zero at offset
+ *  t    f        t       sectors read as valid from file at offset
+ *  f    t        t       sectors preallocated, read as zero, returned file not
+ *                        necessarily zero at offset
+ *  f    f        t       sectors preallocated but read from backing_hd,
+ *                        returned file contains garbage at offset
+ *  t    t        f       sectors preallocated, read as zero, unknown offset
+ *  t    f        f       sectors read from unknown file or offset
+ *  f    t        f       not allocated or unknown offset, read as zero
+ *  f    f        f       not allocated or unknown offset, read from backing_hd
+ */
+#define BDRV_BLOCK_DATA         0x01
+#define BDRV_BLOCK_ZERO         0x02
+#define BDRV_BLOCK_OFFSET_VALID 0x04
+#define BDRV_BLOCK_RAW          0x08
+#define BDRV_BLOCK_ALLOCATED    0x10
+#define BDRV_BLOCK_EOF          0x20
+#define BDRV_BLOCK_RECURSE      0x40
+
+typedef QTAILQ_HEAD(BlockReopenQueue, BlockReopenQueueEntry) BlockReopenQueue;
+
+typedef struct BDRVReopenState {
+    BlockDriverState *bs;
+    int flags;
+    BlockdevDetectZeroesOptions detect_zeroes;
+    bool backing_missing;
+    BlockDriverState *old_backing_bs; /* keep pointer for permissions update */
+    BlockDriverState *old_file_bs; /* keep pointer for permissions update */
+    QDict *options;
+    QDict *explicit_options;
+    void *opaque;
+} BDRVReopenState;
+
+/*
+ * Block operation types
+ */
+typedef enum BlockOpType {
+    BLOCK_OP_TYPE_BACKUP_SOURCE,
+    BLOCK_OP_TYPE_BACKUP_TARGET,
+    BLOCK_OP_TYPE_CHANGE,
+    BLOCK_OP_TYPE_COMMIT_SOURCE,
+    BLOCK_OP_TYPE_COMMIT_TARGET,
+    BLOCK_OP_TYPE_DATAPLANE,
+    BLOCK_OP_TYPE_DRIVE_DEL,
+    BLOCK_OP_TYPE_EJECT,
+    BLOCK_OP_TYPE_EXTERNAL_SNAPSHOT,
+    BLOCK_OP_TYPE_INTERNAL_SNAPSHOT,
+    BLOCK_OP_TYPE_INTERNAL_SNAPSHOT_DELETE,
+    BLOCK_OP_TYPE_MIRROR_SOURCE,
+    BLOCK_OP_TYPE_MIRROR_TARGET,
+    BLOCK_OP_TYPE_RESIZE,
+    BLOCK_OP_TYPE_STREAM,
+    BLOCK_OP_TYPE_REPLACE,
+    BLOCK_OP_TYPE_MAX,
+} BlockOpType;
+
+/* Block node permission constants */
+enum {
+    /**
+     * A user that has the "permission" of consistent reads is guaranteed that
+     * their view of the contents of the block device is complete and
+     * self-consistent, representing the contents of a disk at a specific
+     * point.
+     *
+     * For most block devices (including their backing files) this is true, but
+     * the property cannot be maintained in a few situations like for
+     * intermediate nodes of a commit block job.
+     */
+    BLK_PERM_CONSISTENT_READ    = 0x01,
+
+    /** This permission is required to change the visible disk contents. */
+    BLK_PERM_WRITE              = 0x02,
+
+    /**
+     * This permission (which is weaker than BLK_PERM_WRITE) is both enough and
+     * required for writes to the block node when the caller promises that
+     * the visible disk content doesn't change.
+     *
+     * As the BLK_PERM_WRITE permission is strictly stronger, either is
+     * sufficient to perform an unchanging write.
+     */
+    BLK_PERM_WRITE_UNCHANGED    = 0x04,
+
+    /** This permission is required to change the size of a block node. */
+    BLK_PERM_RESIZE             = 0x08,
+
+    /**
+     * This permission is required to change the node that this BdrvChild
+     * points to.
+     */
+    BLK_PERM_GRAPH_MOD          = 0x10,
+
+    BLK_PERM_ALL                = 0x1f,
+
+    DEFAULT_PERM_PASSTHROUGH    = BLK_PERM_CONSISTENT_READ
+                                 | BLK_PERM_WRITE
+                                 | BLK_PERM_WRITE_UNCHANGED
+                                 | BLK_PERM_RESIZE,
+
+    DEFAULT_PERM_UNCHANGED      = BLK_PERM_ALL & ~DEFAULT_PERM_PASSTHROUGH,
+};
+
+/*
+ * Flags that parent nodes assign to child nodes to specify what kind of
+ * role(s) they take.
+ *
+ * At least one of DATA, METADATA, FILTERED, or COW must be set for
+ * every child.
+ */
+enum BdrvChildRoleBits {
+    /*
+     * This child stores data.
+     * Any node may have an arbitrary number of such children.
+     */
+    BDRV_CHILD_DATA         = (1 << 0),
+
+    /*
+     * This child stores metadata.
+     * Any node may have an arbitrary number of metadata-storing
+     * children.
+     */
+    BDRV_CHILD_METADATA     = (1 << 1),
+
+    /*
+     * A child that always presents exactly the same visible data as
+     * the parent, e.g. by virtue of the parent forwarding all reads
+     * and writes.
+     * This flag is mutually exclusive with DATA, METADATA, and COW.
+     * Any node may have at most one filtered child at a time.
+     */
+    BDRV_CHILD_FILTERED     = (1 << 2),
+
+    /*
+     * Child from which to read all data that isn't allocated in the
+     * parent (i.e., the backing child); such data is copied to the
+     * parent through COW (and optionally COR).
+     * This field is mutually exclusive with DATA, METADATA, and
+     * FILTERED.
+     * Any node may have at most one such backing child at a time.
+     */
+    BDRV_CHILD_COW          = (1 << 3),
+
+    /*
+     * The primary child.  For most drivers, this is the child whose
+     * filename applies best to the parent node.
+     * Any node may have at most one primary child at a time.
+     */
+    BDRV_CHILD_PRIMARY      = (1 << 4),
+
+    /* Useful combination of flags */
+    BDRV_CHILD_IMAGE        = BDRV_CHILD_DATA
+                              | BDRV_CHILD_METADATA
+                              | BDRV_CHILD_PRIMARY,
+};
+
+/* Mask of BdrvChildRoleBits values */
+typedef unsigned int BdrvChildRole;
+
+typedef struct BdrvCheckResult {
+    int corruptions;
+    int leaks;
+    int check_errors;
+    int corruptions_fixed;
+    int leaks_fixed;
+    int64_t image_end_offset;
+    BlockFragInfo bfi;
+} BdrvCheckResult;
+
+typedef enum {
+    BDRV_FIX_LEAKS    = 1,
+    BDRV_FIX_ERRORS   = 2,
+} BdrvCheckMode;
+
+typedef struct BlockSizes {
+    uint32_t phys;
+    uint32_t log;
+} BlockSizes;
+
+typedef struct HDGeometry {
+    uint32_t heads;
+    uint32_t sectors;
+    uint32_t cylinders;
+} HDGeometry;
+
+/* Common functions that are neither I/O nor Global State */
+uint64_t bdrv_qapi_perm_to_blk_perm(BlockPermission qapi_perm);
+char *bdrv_perm_names(uint64_t perm);
+
+int bdrv_parse_aio(const char *mode, int *flags);
+
+int path_has_protocol(const char *path);
+int path_is_absolute(const char *path);
+char *path_combine(const char *base_path, const char *filename);
+
+char *bdrv_get_full_backing_filename_from_filename(const char *backed,
+                                                   const char *backing,
+                                                   Error **errp);
+char *bdrv_get_full_backing_filename(BlockDriverState *bs, Error **errp);
+
+#endif /* BLOCK_COMMON_H */
diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h
new file mode 100644
index 0000000000..b57e275da9
--- /dev/null
+++ b/include/block/block-global-state.h
@@ -0,0 +1,263 @@
+#ifndef BLOCK_GLOBAL_STATE_H
+#define BLOCK_GLOBAL_STATE_H
+
+#include "block-common.h"
+
+/*
+ * Global state (GS) API. These functions run under the BQL lock.
+ *
+ * If a function modifies the graph, it also uses drain and/or
+ * aio_context_acquire/release to be sure it has unique access.
+ * aio_context locking is needed together with BQL because of
+ * the thread-safe I/O API that concurrently runs and accesses
+ * the graph without the BQL.
+ *
+ * It is important to note that not all of these functions are
+ * necessarily limited to running under the BQL, but they would
+ * require additional auditing and many small thread-safety changes
+ * to move them into the I/O API. Often it's not worth doing that
+ * work since the APIs are only used with the BQL held at the
+ * moment, so they have been placed in the GS API (for now).
+ *
+ * All functions in this header must use this assertion:
+ * assert(qemu_in_main_thread());
+ * to catch when they are accidentally called without the BQL.
+ */
+
+/* disk I/O throttling */
+void bdrv_init(void);
+void bdrv_init_with_whitelist(void);
+bool bdrv_uses_whitelist(void);
+int bdrv_is_whitelisted(BlockDriver *drv, bool read_only);
+BlockDriver *bdrv_find_protocol(const char *filename,
+                                bool allow_protocol_prefix,
+                                Error **errp);
+BlockDriver *bdrv_find_format(const char *format_name);
+int bdrv_create(BlockDriver *drv, const char* filename,
+                QemuOpts *opts, Error **errp);
+int bdrv_create_file(const char *filename, QemuOpts *opts, Error **errp);
+
+BlockDriverState *bdrv_new(void);
+int bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
+                Error **errp);
+int bdrv_replace_node(BlockDriverState *from, BlockDriverState *to,
+                      Error **errp);
+BlockDriverState *bdrv_insert_node(BlockDriverState *bs, QDict *node_options,
+                                   int flags, Error **errp);
+int bdrv_drop_filter(BlockDriverState *bs, Error **errp);
+
+int bdrv_parse_cache_mode(const char *mode, int *flags, bool *writethrough);
+int bdrv_parse_discard_flags(const char *mode, int *flags);
+BdrvChild *bdrv_open_child(const char *filename,
+                           QDict *options, const char *bdref_key,
+                           BlockDriverState *parent,
+                           const BdrvChildClass *child_class,
+                           BdrvChildRole child_role,
+                           bool allow_none, Error **errp);
+BlockDriverState *bdrv_open_blockdev_ref(BlockdevRef *ref, Error **errp);
+int bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
+                        Error **errp);
+int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
+                           const char *bdref_key, Error **errp);
+BlockDriverState *bdrv_open(const char *filename, const char *reference,
+                            QDict *options, int flags, Error **errp);
+BlockDriverState *bdrv_new_open_driver_opts(BlockDriver *drv,
+                                            const char *node_name,
+                                            QDict *options, int flags,
+                                            Error **errp);
+BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name,
+                                       int flags, Error **errp);
+BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
+                                    BlockDriverState *bs, QDict *options,
+                                    bool keep_old_opts);
+void bdrv_reopen_queue_free(BlockReopenQueue *bs_queue);
+int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp);
+int bdrv_reopen(BlockDriverState *bs, QDict *opts, bool keep_old_opts,
+                Error **errp);
+int bdrv_reopen_set_read_only(BlockDriverState *bs, bool read_only,
+                              Error **errp);
+int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags);
+BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
+                                          const char *backing_file);
+void bdrv_refresh_filename(BlockDriverState *bs);
+void bdrv_refresh_limits(BlockDriverState *bs, Transaction *tran, Error **errp);
+int bdrv_commit(BlockDriverState *bs);
+int bdrv_make_empty(BdrvChild *c, Error **errp);
+int bdrv_change_backing_file(BlockDriverState *bs, const char *backing_file,
+                             const char *backing_fmt, bool warn);
+void bdrv_register(BlockDriver *bdrv);
+int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base,
+                           const char *backing_file_str);
+BlockDriverState *bdrv_find_overlay(BlockDriverState *active,
+                                    BlockDriverState *bs);
+BlockDriverState *bdrv_find_base(BlockDriverState *bs);
+bool bdrv_is_backing_chain_frozen(BlockDriverState *bs, BlockDriverState *base,
+                                  Error **errp);
+int bdrv_freeze_backing_chain(BlockDriverState *bs, BlockDriverState *base,
+                              Error **errp);
+void bdrv_unfreeze_backing_chain(BlockDriverState *bs, BlockDriverState *base);
+
+/*
+ * The units of offset and total_work_size may be chosen arbitrarily by the
+ * block driver; total_work_size may change during the course of the amendment
+ * operation
+ */
+typedef void BlockDriverAmendStatusCB(BlockDriverState *bs, int64_t offset,
+                                      int64_t total_work_size, void *opaque);
+int bdrv_amend_options(BlockDriverState *bs_new, QemuOpts *opts,
+                       BlockDriverAmendStatusCB *status_cb, void *cb_opaque,
+                       bool force,
+                       Error **errp);
+
+/* check if a named node can be replaced when doing drive-mirror */
+BlockDriverState *check_to_replace_node(BlockDriverState *parent_bs,
+                                        const char *node_name, Error **errp);
+
+/* async block I/O */
+void bdrv_aio_cancel(BlockAIOCB *acb);
+void bdrv_aio_cancel_async(BlockAIOCB *acb);
+void bdrv_invalidate_cache_all(Error **errp);
+int bdrv_inactivate_all(void);
+
+int bdrv_flush_all(void);
+void bdrv_close_all(void);
+void bdrv_drain(BlockDriverState *bs);
+void coroutine_fn bdrv_co_drain(BlockDriverState *bs);
+void bdrv_drain_all_begin(void);
+void bdrv_drain_all_end(void);
+void bdrv_drain_all(void);
+
+#define BDRV_POLL_WHILE(bs, cond) ({                       \
+    BlockDriverState *bs_ = (bs);                          \
+    AIO_WAIT_WHILE(bdrv_get_aio_context(bs_),              \
+                   cond); })
+
+int bdrv_has_zero_init_1(BlockDriverState *bs);
+int bdrv_has_zero_init(BlockDriverState *bs);
+void bdrv_lock_medium(BlockDriverState *bs, bool locked);
+void bdrv_eject(BlockDriverState *bs, bool eject_flag);
+BlockDriverState *bdrv_find_node(const char *node_name);
+BlockDeviceInfoList *bdrv_named_nodes_list(bool flat, Error **errp);
+XDbgBlockGraph *bdrv_get_xdbg_block_graph(Error **errp);
+BlockDriverState *bdrv_lookup_bs(const char *device,
+                                 const char *node_name,
+                                 Error **errp);
+bool bdrv_chain_contains(BlockDriverState *top, BlockDriverState *base);
+BlockDriverState *bdrv_next_node(BlockDriverState *bs);
+BlockDriverState *bdrv_next_all_states(BlockDriverState *bs);
+
+typedef struct BdrvNextIterator {
+    enum {
+        BDRV_NEXT_BACKEND_ROOTS,
+        BDRV_NEXT_MONITOR_OWNED,
+    } phase;
+    BlockBackend *blk;
+    BlockDriverState *bs;
+} BdrvNextIterator;
+
+BlockDriverState *bdrv_first(BdrvNextIterator *it);
+BlockDriverState *bdrv_next(BdrvNextIterator *it);
+void bdrv_next_cleanup(BdrvNextIterator *it);
+
+BlockDriverState *bdrv_next_monitor_owned(BlockDriverState *bs);
+void bdrv_iterate_format(void (*it)(void *opaque, const char *name),
+                         void *opaque, bool read_only);
+const char *bdrv_get_device_name(const BlockDriverState *bs);
+const char *bdrv_get_device_or_node_name(const BlockDriverState *bs);
+int bdrv_get_flags(BlockDriverState *bs);
+char *bdrv_dirname(BlockDriverState *bs, Error **errp);
+
+int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
+                      int64_t pos, int size);
+
+int bdrv_load_vmstate(BlockDriverState *bs, uint8_t *buf,
+                      int64_t pos, int size);
+
+void bdrv_img_create(const char *filename, const char *fmt,
+                     const char *base_filename, const char *base_fmt,
+                     char *options, uint64_t img_size, int flags,
+                     bool quiet, Error **errp);
+
+void bdrv_ref(BlockDriverState *bs);
+void bdrv_unref(BlockDriverState *bs);
+void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child);
+BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs,
+                             BlockDriverState *child_bs,
+                             const char *child_name,
+                             const BdrvChildClass *child_class,
+                             BdrvChildRole child_role,
+                             Error **errp);
+
+bool bdrv_op_is_blocked(BlockDriverState *bs, BlockOpType op, Error **errp);
+void bdrv_op_block(BlockDriverState *bs, BlockOpType op, Error *reason);
+void bdrv_op_unblock(BlockDriverState *bs, BlockOpType op, Error *reason);
+void bdrv_op_block_all(BlockDriverState *bs, Error *reason);
+void bdrv_op_unblock_all(BlockDriverState *bs, Error *reason);
+bool bdrv_op_blocker_is_empty(BlockDriverState *bs);
+
+int bdrv_debug_breakpoint(BlockDriverState *bs, const char *event,
+                           const char *tag);
+int bdrv_debug_remove_breakpoint(BlockDriverState *bs, const char *tag);
+int bdrv_debug_resume(BlockDriverState *bs, const char *tag);
+bool bdrv_debug_is_suspended(BlockDriverState *bs, const char *tag);
+
+/**
+ * Locks the AioContext of @bs if it's not the current AioContext. This avoids
+ * double locking which could lead to deadlocks: This is a coroutine_fn, so we
+ * know we already own the lock of the current AioContext.
+ *
+ * May only be called in the main thread.
+ */
+void coroutine_fn bdrv_co_lock(BlockDriverState *bs);
+
+/**
+ * Unlocks the AioContext of @bs if it's not the current AioContext.
+ */
+void coroutine_fn bdrv_co_unlock(BlockDriverState *bs);
+
+void bdrv_set_aio_context_ignore(BlockDriverState *bs,
+                                 AioContext *new_context, GSList **ignore);
+int bdrv_try_set_aio_context(BlockDriverState *bs, AioContext *ctx,
+                             Error **errp);
+int bdrv_child_try_set_aio_context(BlockDriverState *bs, AioContext *ctx,
+                                   BdrvChild *ignore_child, Error **errp);
+bool bdrv_child_can_set_aio_context(BdrvChild *c, AioContext *ctx,
+                                    GSList **ignore, Error **errp);
+bool bdrv_can_set_aio_context(BlockDriverState *bs, AioContext *ctx,
+                              GSList **ignore, Error **errp);
+
+int bdrv_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz);
+int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo);
+
+/**
+ * bdrv_drained_end_no_poll:
+ *
+ * Same as bdrv_drained_end(), but do not poll for the subgraph to
+ * actually become unquiesced.  Therefore, no graph changes will occur
+ * with this function.
+ *
+ * *drained_end_counter is incremented for every background operation
+ * that is scheduled, and will be decremented for every operation once
+ * it settles.  The caller must poll until it reaches 0.  The counter
+ * should be accessed using atomic operations only.
+ */
+void bdrv_drained_end_no_poll(BlockDriverState *bs, int *drained_end_counter);
+
+void bdrv_add_child(BlockDriverState *parent, BlockDriverState *child,
+                    Error **errp);
+void bdrv_del_child(BlockDriverState *parent, BdrvChild *child, Error **errp);
+
+/**
+ *
+ * bdrv_register_buf/bdrv_unregister_buf:
+ *
+ * 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.
+ */
+void bdrv_register_buf(BlockDriverState *bs, void *host, size_t size);
+void bdrv_unregister_buf(BlockDriverState *bs, void *host);
+
+void bdrv_cancel_in_flight(BlockDriverState *bs);
+
+#endif /* BLOCK_GLOBAL_STATE_H */
diff --git a/include/block/block-io.h b/include/block/block-io.h
new file mode 100644
index 0000000000..80df965072
--- /dev/null
+++ b/include/block/block-io.h
@@ -0,0 +1,283 @@
+#ifndef BLOCK_IO_H
+#define BLOCK_IO_H
+
+#include "block-common.h"
+
+/*
+ * I/O API functions. These functions are thread-safe, and therefore
+ * can run in any thread as long as the thread has called
+ * aio_context_acquire/release().
+ */
+
+int bdrv_replace_child_bs(BdrvChild *child, BlockDriverState *new_bs,
+                          Error **errp);
+
+int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset,
+                       int64_t bytes, BdrvRequestFlags flags);
+int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int64_t bytes);
+int bdrv_pwrite(BdrvChild *child, int64_t offset, const void *buf,
+                int64_t bytes);
+int bdrv_pwrite_sync(BdrvChild *child, int64_t offset,
+                     const void *buf, int64_t bytes);
+/*
+ * Efficiently zero a region of the disk image.  Note that this is a regular
+ * I/O request like read or write and should have a reasonable size.  This
+ * function is not suitable for zeroing the entire image in a single request
+ * because it may allocate memory for the entire region.
+ */
+int coroutine_fn bdrv_co_pwrite_zeroes(BdrvChild *child, int64_t offset,
+                                       int64_t bytes, BdrvRequestFlags flags);
+
+int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact,
+                                  PreallocMode prealloc, BdrvRequestFlags flags,
+                                  Error **errp);
+int generated_co_wrapper
+bdrv_truncate(BdrvChild *child, int64_t offset, bool exact,
+              PreallocMode prealloc, BdrvRequestFlags flags, Error **errp);
+
+int64_t bdrv_nb_sectors(BlockDriverState *bs);
+int64_t bdrv_getlength(BlockDriverState *bs);
+int64_t bdrv_get_allocated_file_size(BlockDriverState *bs);
+BlockMeasureInfo *bdrv_measure(BlockDriver *drv, QemuOpts *opts,
+                               BlockDriverState *in_bs, Error **errp);
+void bdrv_get_geometry(BlockDriverState *bs, uint64_t *nb_sectors_ptr);
+int coroutine_fn bdrv_co_delete_file(BlockDriverState *bs, Error **errp);
+void coroutine_fn bdrv_co_delete_file_noerr(BlockDriverState *bs);
+
+
+int generated_co_wrapper bdrv_check(BlockDriverState *bs, BdrvCheckResult *res,
+                                    BdrvCheckMode fix);
+
+/* sg packet commands */
+int bdrv_co_ioctl(BlockDriverState *bs, int req, void *buf);
+
+/* Invalidate any cached metadata used by image formats */
+int generated_co_wrapper bdrv_invalidate_cache(BlockDriverState *bs,
+                                               Error **errp);
+
+/* Ensure contents are flushed to disk.  */
+int generated_co_wrapper bdrv_flush(BlockDriverState *bs);
+int coroutine_fn bdrv_co_flush(BlockDriverState *bs);
+
+int generated_co_wrapper bdrv_pdiscard(BdrvChild *child, int64_t offset,
+                                       int64_t bytes);
+int bdrv_co_pdiscard(BdrvChild *child, int64_t offset, int64_t bytes);
+bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs);
+int bdrv_block_status(BlockDriverState *bs, int64_t offset,
+                      int64_t bytes, int64_t *pnum, int64_t *map,
+                      BlockDriverState **file);
+int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base,
+                            int64_t offset, int64_t bytes, int64_t *pnum,
+                            int64_t *map, BlockDriverState **file);
+int bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int64_t bytes,
+                      int64_t *pnum);
+int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base,
+                            bool include_base, int64_t offset, int64_t bytes,
+                            int64_t *pnum);
+int coroutine_fn bdrv_co_is_zero_fast(BlockDriverState *bs, int64_t offset,
+                                      int64_t bytes);
+
+bool bdrv_is_read_only(BlockDriverState *bs);
+int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only,
+                           bool ignore_allow_rdw, Error **errp);
+int bdrv_apply_auto_read_only(BlockDriverState *bs, const char *errmsg,
+                              Error **errp);
+bool bdrv_is_writable(BlockDriverState *bs);
+bool bdrv_is_sg(BlockDriverState *bs);
+bool bdrv_is_inserted(BlockDriverState *bs);
+const char *bdrv_get_format_name(BlockDriverState *bs);
+
+bool bdrv_supports_compressed_writes(BlockDriverState *bs);
+const char *bdrv_get_node_name(const BlockDriverState *bs);
+int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi);
+ImageInfoSpecific *bdrv_get_specific_info(BlockDriverState *bs,
+                                          Error **errp);
+BlockStatsSpecific *bdrv_get_specific_stats(BlockDriverState *bs);
+void bdrv_round_to_clusters(BlockDriverState *bs,
+                            int64_t offset, int64_t bytes,
+                            int64_t *cluster_offset,
+                            int64_t *cluster_bytes);
+
+void bdrv_get_backing_filename(BlockDriverState *bs,
+                               char *filename, int filename_size);
+
+int generated_co_wrapper
+bdrv_readv_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos);
+int generated_co_wrapper
+bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos);
+
+/*
+ * Returns the alignment in bytes that is required so that no bounce buffer
+ * is required throughout the stack
+ */
+size_t bdrv_min_mem_align(BlockDriverState *bs);
+/* Returns optimal alignment in bytes for bounce buffer */
+size_t bdrv_opt_mem_align(BlockDriverState *bs);
+void *qemu_blockalign(BlockDriverState *bs, size_t size);
+void *qemu_blockalign0(BlockDriverState *bs, size_t size);
+void *qemu_try_blockalign(BlockDriverState *bs, size_t size);
+void *qemu_try_blockalign0(BlockDriverState *bs, size_t size);
+bool bdrv_qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov);
+
+void bdrv_enable_copy_on_read(BlockDriverState *bs);
+void bdrv_disable_copy_on_read(BlockDriverState *bs);
+
+void bdrv_debug_event(BlockDriverState *bs, BlkdebugEvent event);
+
+#define BLKDBG_EVENT(child, evt) \
+    do { \
+        if (child) { \
+            bdrv_debug_event(child->bs, evt); \
+        } \
+    } while (0)
+
+/**
+ * bdrv_get_aio_context:
+ *
+ * Returns: the currently bound #AioContext
+ */
+AioContext *bdrv_get_aio_context(BlockDriverState *bs);
+/**
+ * Move the current coroutine to the AioContext of @bs and return the old
+ * AioContext of the coroutine. Increase bs->in_flight so that draining @bs
+ * will wait for the operation to proceed until the corresponding
+ * bdrv_co_leave().
+ *
+ * Consequently, you can't call drain inside a bdrv_co_enter/leave() section as
+ * this will deadlock.
+ */
+AioContext *coroutine_fn bdrv_co_enter(BlockDriverState *bs);
+
+/**
+ * Ends a section started by bdrv_co_enter(). Move the current coroutine back
+ * to old_ctx and decrease bs->in_flight again.
+ */
+void coroutine_fn bdrv_co_leave(BlockDriverState *bs, AioContext *old_ctx);
+
+/**
+ * Transfer control to @co in the aio context of @bs
+ */
+void bdrv_coroutine_enter(BlockDriverState *bs, Coroutine *co);
+
+AioContext *bdrv_child_get_parent_aio_context(BdrvChild *c);
+AioContext *child_of_bds_get_parent_aio_context(BdrvChild *c);
+
+void bdrv_io_plug(BlockDriverState *bs);
+void bdrv_io_unplug(BlockDriverState *bs);
+
+/**
+ * bdrv_parent_drained_begin_single:
+ *
+ * Begin a quiesced section for the parent of @c. If @poll is true, wait for
+ * any pending activity to cease.
+ */
+void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll);
+
+/**
+ * bdrv_parent_drained_end_single:
+ *
+ * End a quiesced section for the parent of @c.
+ *
+ * This polls @bs's AioContext until all scheduled sub-drained_ends
+ * have settled, which may result in graph changes.
+ */
+void bdrv_parent_drained_end_single(BdrvChild *c);
+
+/**
+ * bdrv_drain_poll:
+ *
+ * Poll for pending requests in @bs, its parents (except for @ignore_parent),
+ * and if @recursive is true its children as well (used for subtree drain).
+ *
+ * If @ignore_bds_parents is true, parents that are BlockDriverStates must
+ * ignore the drain request because they will be drained separately (used for
+ * drain_all).
+ *
+ * This is part of bdrv_drained_begin.
+ */
+bool bdrv_drain_poll(BlockDriverState *bs, bool recursive,
+                     BdrvChild *ignore_parent, bool ignore_bds_parents);
+
+/**
+ * bdrv_drained_begin:
+ *
+ * Begin a quiesced section for exclusive access to the BDS, by disabling
+ * external request sources including NBD server and device model. Note that
+ * this doesn't block timers or coroutines from submitting more requests, which
+ * means block_job_pause is still necessary.
+ *
+ * This function can be recursive.
+ */
+void bdrv_drained_begin(BlockDriverState *bs);
+
+/**
+ * bdrv_do_drained_begin_quiesce:
+ *
+ * Quiesces a BDS like bdrv_drained_begin(), but does not wait for already
+ * running requests to complete.
+ */
+void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
+                                   BdrvChild *parent, bool ignore_bds_parents);
+
+/**
+ * Like bdrv_drained_begin, but recursively begins a quiesced section for
+ * exclusive access to all child nodes as well.
+ */
+void bdrv_subtree_drained_begin(BlockDriverState *bs);
+
+/**
+ * bdrv_drained_end:
+ *
+ * End a quiescent section started by bdrv_drained_begin().
+ *
+ * This polls @bs's AioContext until all scheduled sub-drained_ends
+ * have settled.  On one hand, that may result in graph changes.  On
+ * the other, this requires that the caller either runs in the main
+ * loop; or that all involved nodes (@bs and all of its parents) are
+ * in the caller's AioContext.
+ */
+void bdrv_drained_end(BlockDriverState *bs);
+
+/**
+ * End a quiescent section started by bdrv_subtree_drained_begin().
+ */
+void bdrv_subtree_drained_end(BlockDriverState *bs);
+
+bool bdrv_can_store_new_dirty_bitmap(BlockDriverState *bs, const char *name,
+                                     uint32_t granularity, Error **errp);
+
+/**
+ *
+ * bdrv_co_copy_range:
+ *
+ * Do offloaded copy between two children. If the operation is not implemented
+ * by the driver, or if the backend storage doesn't support it, a negative
+ * error code will be returned.
+ *
+ * Note: block layer doesn't emulate or fallback to a bounce buffer approach
+ * because usually the caller shouldn't attempt offloaded copy any more (e.g.
+ * calling copy_file_range(2)) after the first error, thus it should fall back
+ * to a read+write path in the caller level.
+ *
+ * @src: Source child to copy data from
+ * @src_offset: offset in @src image to read data
+ * @dst: Destination child to copy data to
+ * @dst_offset: offset in @dst image to write data
+ * @bytes: number of bytes to copy
+ * @flags: request flags. Supported flags:
+ *         BDRV_REQ_ZERO_WRITE - treat the @src range as zero data and do zero
+ *                               write on @dst as if bdrv_co_pwrite_zeroes is
+ *                               called. Used to simplify caller code, or
+ *                               during BlockDriver.bdrv_co_copy_range_from()
+ *                               recursion.
+ *         BDRV_REQ_NO_SERIALISING - do not serialize with other overlapping
+ *                                   requests currently in flight.
+ *
+ * Returns: 0 if succeeded; negative error code if failed.
+ **/
+int coroutine_fn bdrv_co_copy_range(BdrvChild *src, int64_t src_offset,
+                                    BdrvChild *dst, int64_t dst_offset,
+                                    int64_t bytes, BdrvRequestFlags read_flags,
+                                    BdrvRequestFlags write_flags);
+
+#endif /* BLOCK_IO_H */
diff --git a/include/block/block.h b/include/block/block.h
index e5dd22b034..bf8c7a7cb5 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -1,864 +1,9 @@
 #ifndef BLOCK_H
 #define BLOCK_H
 
-#include "block/aio.h"
-#include "block/aio-wait.h"
-#include "qemu/iov.h"
-#include "qemu/coroutine.h"
-#include "block/accounting.h"
-#include "block/dirty-bitmap.h"
-#include "block/blockjob.h"
-#include "qemu/hbitmap.h"
-#include "qemu/transactions.h"
+#include "block-global-state.h"
+#include "block-io.h"
 
-/*
- * generated_co_wrapper
- *
- * Function specifier, which does nothing but mark functions to be
- * generated by scripts/block-coroutine-wrapper.py
- *
- * Read more in docs/devel/block-coroutine-wrapper.rst
- */
-#define generated_co_wrapper
+/* DO NOT ADD ANYTHING IN HERE. USE ONE OF THE HEADERS INCLUDED ABOVE */
 
-/* block.c */
-typedef struct BlockDriver BlockDriver;
-typedef struct BdrvChild BdrvChild;
-typedef struct BdrvChildClass BdrvChildClass;
-
-typedef struct BlockDriverInfo {
-    /* in bytes, 0 if irrelevant */
-    int cluster_size;
-    /* offset at which the VM state can be saved (0 if not possible) */
-    int64_t vm_state_offset;
-    bool is_dirty;
-    /*
-     * True if this block driver only supports compressed writes
-     */
-    bool needs_compressed_writes;
-} BlockDriverInfo;
-
-typedef struct BlockFragInfo {
-    uint64_t allocated_clusters;
-    uint64_t total_clusters;
-    uint64_t fragmented_clusters;
-    uint64_t compressed_clusters;
-} BlockFragInfo;
-
-typedef enum {
-    BDRV_REQ_COPY_ON_READ       = 0x1,
-    BDRV_REQ_ZERO_WRITE         = 0x2,
-
-    /*
-     * The BDRV_REQ_MAY_UNMAP flag is used in write_zeroes requests to indicate
-     * that the block driver should unmap (discard) blocks if it is guaranteed
-     * that the result will read back as zeroes. The flag is only passed to the
-     * driver if the block device is opened with BDRV_O_UNMAP.
-     */
-    BDRV_REQ_MAY_UNMAP          = 0x4,
-
-    BDRV_REQ_FUA                = 0x10,
-    BDRV_REQ_WRITE_COMPRESSED   = 0x20,
-
-    /* Signifies that this write request will not change the visible disk
-     * content. */
-    BDRV_REQ_WRITE_UNCHANGED    = 0x40,
-
-    /* Forces request serialisation. Use only with write requests. */
-    BDRV_REQ_SERIALISING        = 0x80,
-
-    /* Execute the request only if the operation can be offloaded or otherwise
-     * be executed efficiently, but return an error instead of using a slow
-     * fallback. */
-    BDRV_REQ_NO_FALLBACK        = 0x100,
-
-    /*
-     * BDRV_REQ_PREFETCH makes sense only in the context of copy-on-read
-     * (i.e., together with the BDRV_REQ_COPY_ON_READ flag or when a COR
-     * filter is involved), in which case it signals that the COR operation
-     * need not read the data into memory (qiov) but only ensure they are
-     * copied to the top layer (i.e., that COR operation is done).
-     */
-    BDRV_REQ_PREFETCH  = 0x200,
-
-    /*
-     * If we need to wait for other requests, just fail immediately. Used
-     * only together with BDRV_REQ_SERIALISING.
-     */
-    BDRV_REQ_NO_WAIT = 0x400,
-
-    /* Mask of valid flags */
-    BDRV_REQ_MASK               = 0x7ff,
-} BdrvRequestFlags;
-
-typedef struct BlockSizes {
-    uint32_t phys;
-    uint32_t log;
-} BlockSizes;
-
-typedef struct HDGeometry {
-    uint32_t heads;
-    uint32_t sectors;
-    uint32_t cylinders;
-} HDGeometry;
-
-#define BDRV_O_NO_SHARE    0x0001 /* don't share permissions */
-#define BDRV_O_RDWR        0x0002
-#define BDRV_O_RESIZE      0x0004 /* request permission for resizing the node */
-#define BDRV_O_SNAPSHOT    0x0008 /* open the file read only and save writes in a snapshot */
-#define BDRV_O_TEMPORARY   0x0010 /* delete the file after use */
-#define BDRV_O_NOCACHE     0x0020 /* do not use the host page cache */
-#define BDRV_O_NATIVE_AIO  0x0080 /* use native AIO instead of the thread pool */
-#define BDRV_O_NO_BACKING  0x0100 /* don't open the backing file */
-#define BDRV_O_NO_FLUSH    0x0200 /* disable flushing on this disk */
-#define BDRV_O_COPY_ON_READ 0x0400 /* copy read backing sectors into image */
-#define BDRV_O_INACTIVE    0x0800  /* consistency hint for migration handoff */
-#define BDRV_O_CHECK       0x1000  /* open solely for consistency check */
-#define BDRV_O_ALLOW_RDWR  0x2000  /* allow reopen to change from r/o to r/w */
-#define BDRV_O_UNMAP       0x4000  /* execute guest UNMAP/TRIM operations */
-#define BDRV_O_PROTOCOL    0x8000  /* if no block driver is explicitly given:
-                                      select an appropriate protocol driver,
-                                      ignoring the format layer */
-#define BDRV_O_NO_IO       0x10000 /* don't initialize for I/O */
-#define BDRV_O_AUTO_RDONLY 0x20000 /* degrade to read-only if opening read-write fails */
-#define BDRV_O_IO_URING    0x40000 /* use io_uring instead of the thread pool */
-
-#define BDRV_O_CACHE_MASK  (BDRV_O_NOCACHE | BDRV_O_NO_FLUSH)
-
-
-/* Option names of options parsed by the block layer */
-
-#define BDRV_OPT_CACHE_WB       "cache.writeback"
-#define BDRV_OPT_CACHE_DIRECT   "cache.direct"
-#define BDRV_OPT_CACHE_NO_FLUSH "cache.no-flush"
-#define BDRV_OPT_READ_ONLY      "read-only"
-#define BDRV_OPT_AUTO_READ_ONLY "auto-read-only"
-#define BDRV_OPT_DISCARD        "discard"
-#define BDRV_OPT_FORCE_SHARE    "force-share"
-
-
-#define BDRV_SECTOR_BITS   9
-#define BDRV_SECTOR_SIZE   (1ULL << BDRV_SECTOR_BITS)
-
-#define BDRV_REQUEST_MAX_SECTORS MIN_CONST(SIZE_MAX >> BDRV_SECTOR_BITS, \
-                                           INT_MAX >> BDRV_SECTOR_BITS)
-#define BDRV_REQUEST_MAX_BYTES (BDRV_REQUEST_MAX_SECTORS << BDRV_SECTOR_BITS)
-
-/*
- * We want allow aligning requests and disk length up to any 32bit alignment
- * and don't afraid of overflow.
- * To achieve it, and in the same time use some pretty number as maximum disk
- * size, let's define maximum "length" (a limit for any offset/bytes request and
- * for disk size) to be the greatest power of 2 less than INT64_MAX.
- */
-#define BDRV_MAX_ALIGNMENT (1L << 30)
-#define BDRV_MAX_LENGTH (QEMU_ALIGN_DOWN(INT64_MAX, BDRV_MAX_ALIGNMENT))
-
-/*
- * Allocation status flags for bdrv_block_status() and friends.
- *
- * Public flags:
- * BDRV_BLOCK_DATA: allocation for data at offset is tied to this layer
- * BDRV_BLOCK_ZERO: offset reads as zero
- * BDRV_BLOCK_OFFSET_VALID: an associated offset exists for accessing raw data
- * BDRV_BLOCK_ALLOCATED: the content of the block is determined by this
- *                       layer rather than any backing, set by block layer
- * BDRV_BLOCK_EOF: the returned pnum covers through end of file for this
- *                 layer, set by block layer
- *
- * Internal flags:
- * BDRV_BLOCK_RAW: for use by passthrough drivers, such as raw, to request
- *                 that the block layer recompute the answer from the returned
- *                 BDS; must be accompanied by just BDRV_BLOCK_OFFSET_VALID.
- * BDRV_BLOCK_RECURSE: request that the block layer will recursively search for
- *                     zeroes in file child of current block node inside
- *                     returned region. Only valid together with both
- *                     BDRV_BLOCK_DATA and BDRV_BLOCK_OFFSET_VALID. Should not
- *                     appear with BDRV_BLOCK_ZERO.
- *
- * If BDRV_BLOCK_OFFSET_VALID is set, the map parameter represents the
- * host offset within the returned BDS that is allocated for the
- * corresponding raw guest data.  However, whether that offset
- * actually contains data also depends on BDRV_BLOCK_DATA, as follows:
- *
- * DATA ZERO OFFSET_VALID
- *  t    t        t       sectors read as zero, returned file is zero at offset
- *  t    f        t       sectors read as valid from file at offset
- *  f    t        t       sectors preallocated, read as zero, returned file not
- *                        necessarily zero at offset
- *  f    f        t       sectors preallocated but read from backing_hd,
- *                        returned file contains garbage at offset
- *  t    t        f       sectors preallocated, read as zero, unknown offset
- *  t    f        f       sectors read from unknown file or offset
- *  f    t        f       not allocated or unknown offset, read as zero
- *  f    f        f       not allocated or unknown offset, read from backing_hd
- */
-#define BDRV_BLOCK_DATA         0x01
-#define BDRV_BLOCK_ZERO         0x02
-#define BDRV_BLOCK_OFFSET_VALID 0x04
-#define BDRV_BLOCK_RAW          0x08
-#define BDRV_BLOCK_ALLOCATED    0x10
-#define BDRV_BLOCK_EOF          0x20
-#define BDRV_BLOCK_RECURSE      0x40
-
-typedef QTAILQ_HEAD(BlockReopenQueue, BlockReopenQueueEntry) BlockReopenQueue;
-
-typedef struct BDRVReopenState {
-    BlockDriverState *bs;
-    int flags;
-    BlockdevDetectZeroesOptions detect_zeroes;
-    bool backing_missing;
-    BlockDriverState *old_backing_bs; /* keep pointer for permissions update */
-    BlockDriverState *old_file_bs; /* keep pointer for permissions update */
-    QDict *options;
-    QDict *explicit_options;
-    void *opaque;
-} BDRVReopenState;
-
-/*
- * Block operation types
- */
-typedef enum BlockOpType {
-    BLOCK_OP_TYPE_BACKUP_SOURCE,
-    BLOCK_OP_TYPE_BACKUP_TARGET,
-    BLOCK_OP_TYPE_CHANGE,
-    BLOCK_OP_TYPE_COMMIT_SOURCE,
-    BLOCK_OP_TYPE_COMMIT_TARGET,
-    BLOCK_OP_TYPE_DATAPLANE,
-    BLOCK_OP_TYPE_DRIVE_DEL,
-    BLOCK_OP_TYPE_EJECT,
-    BLOCK_OP_TYPE_EXTERNAL_SNAPSHOT,
-    BLOCK_OP_TYPE_INTERNAL_SNAPSHOT,
-    BLOCK_OP_TYPE_INTERNAL_SNAPSHOT_DELETE,
-    BLOCK_OP_TYPE_MIRROR_SOURCE,
-    BLOCK_OP_TYPE_MIRROR_TARGET,
-    BLOCK_OP_TYPE_RESIZE,
-    BLOCK_OP_TYPE_STREAM,
-    BLOCK_OP_TYPE_REPLACE,
-    BLOCK_OP_TYPE_MAX,
-} BlockOpType;
-
-/* Block node permission constants */
-enum {
-    /**
-     * A user that has the "permission" of consistent reads is guaranteed that
-     * their view of the contents of the block device is complete and
-     * self-consistent, representing the contents of a disk at a specific
-     * point.
-     *
-     * For most block devices (including their backing files) this is true, but
-     * the property cannot be maintained in a few situations like for
-     * intermediate nodes of a commit block job.
-     */
-    BLK_PERM_CONSISTENT_READ    = 0x01,
-
-    /** This permission is required to change the visible disk contents. */
-    BLK_PERM_WRITE              = 0x02,
-
-    /**
-     * This permission (which is weaker than BLK_PERM_WRITE) is both enough and
-     * required for writes to the block node when the caller promises that
-     * the visible disk content doesn't change.
-     *
-     * As the BLK_PERM_WRITE permission is strictly stronger, either is
-     * sufficient to perform an unchanging write.
-     */
-    BLK_PERM_WRITE_UNCHANGED    = 0x04,
-
-    /** This permission is required to change the size of a block node. */
-    BLK_PERM_RESIZE             = 0x08,
-
-    /**
-     * This permission is required to change the node that this BdrvChild
-     * points to.
-     */
-    BLK_PERM_GRAPH_MOD          = 0x10,
-
-    BLK_PERM_ALL                = 0x1f,
-
-    DEFAULT_PERM_PASSTHROUGH    = BLK_PERM_CONSISTENT_READ
-                                 | BLK_PERM_WRITE
-                                 | BLK_PERM_WRITE_UNCHANGED
-                                 | BLK_PERM_RESIZE,
-
-    DEFAULT_PERM_UNCHANGED      = BLK_PERM_ALL & ~DEFAULT_PERM_PASSTHROUGH,
-};
-
-/*
- * Flags that parent nodes assign to child nodes to specify what kind of
- * role(s) they take.
- *
- * At least one of DATA, METADATA, FILTERED, or COW must be set for
- * every child.
- */
-enum BdrvChildRoleBits {
-    /*
-     * This child stores data.
-     * Any node may have an arbitrary number of such children.
-     */
-    BDRV_CHILD_DATA         = (1 << 0),
-
-    /*
-     * This child stores metadata.
-     * Any node may have an arbitrary number of metadata-storing
-     * children.
-     */
-    BDRV_CHILD_METADATA     = (1 << 1),
-
-    /*
-     * A child that always presents exactly the same visible data as
-     * the parent, e.g. by virtue of the parent forwarding all reads
-     * and writes.
-     * This flag is mutually exclusive with DATA, METADATA, and COW.
-     * Any node may have at most one filtered child at a time.
-     */
-    BDRV_CHILD_FILTERED     = (1 << 2),
-
-    /*
-     * Child from which to read all data that isn't allocated in the
-     * parent (i.e., the backing child); such data is copied to the
-     * parent through COW (and optionally COR).
-     * This field is mutually exclusive with DATA, METADATA, and
-     * FILTERED.
-     * Any node may have at most one such backing child at a time.
-     */
-    BDRV_CHILD_COW          = (1 << 3),
-
-    /*
-     * The primary child.  For most drivers, this is the child whose
-     * filename applies best to the parent node.
-     * Any node may have at most one primary child at a time.
-     */
-    BDRV_CHILD_PRIMARY      = (1 << 4),
-
-    /* Useful combination of flags */
-    BDRV_CHILD_IMAGE        = BDRV_CHILD_DATA
-                              | BDRV_CHILD_METADATA
-                              | BDRV_CHILD_PRIMARY,
-};
-
-/* Mask of BdrvChildRoleBits values */
-typedef unsigned int BdrvChildRole;
-
-char *bdrv_perm_names(uint64_t perm);
-uint64_t bdrv_qapi_perm_to_blk_perm(BlockPermission qapi_perm);
-
-/* disk I/O throttling */
-void bdrv_init(void);
-void bdrv_init_with_whitelist(void);
-bool bdrv_uses_whitelist(void);
-int bdrv_is_whitelisted(BlockDriver *drv, bool read_only);
-BlockDriver *bdrv_find_protocol(const char *filename,
-                                bool allow_protocol_prefix,
-                                Error **errp);
-BlockDriver *bdrv_find_format(const char *format_name);
-int bdrv_create(BlockDriver *drv, const char* filename,
-                QemuOpts *opts, Error **errp);
-int bdrv_create_file(const char *filename, QemuOpts *opts, Error **errp);
-
-BlockDriverState *bdrv_new(void);
-int bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
-                Error **errp);
-int bdrv_replace_node(BlockDriverState *from, BlockDriverState *to,
-                      Error **errp);
-int bdrv_replace_child_bs(BdrvChild *child, BlockDriverState *new_bs,
-                          Error **errp);
-BlockDriverState *bdrv_insert_node(BlockDriverState *bs, QDict *node_options,
-                                   int flags, Error **errp);
-int bdrv_drop_filter(BlockDriverState *bs, Error **errp);
-
-int bdrv_parse_aio(const char *mode, int *flags);
-int bdrv_parse_cache_mode(const char *mode, int *flags, bool *writethrough);
-int bdrv_parse_discard_flags(const char *mode, int *flags);
-BdrvChild *bdrv_open_child(const char *filename,
-                           QDict *options, const char *bdref_key,
-                           BlockDriverState* parent,
-                           const BdrvChildClass *child_class,
-                           BdrvChildRole child_role,
-                           bool allow_none, Error **errp);
-BlockDriverState *bdrv_open_blockdev_ref(BlockdevRef *ref, Error **errp);
-int bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
-                        Error **errp);
-int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
-                           const char *bdref_key, Error **errp);
-BlockDriverState *bdrv_open(const char *filename, const char *reference,
-                            QDict *options, int flags, Error **errp);
-BlockDriverState *bdrv_new_open_driver_opts(BlockDriver *drv,
-                                            const char *node_name,
-                                            QDict *options, int flags,
-                                            Error **errp);
-BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name,
-                                       int flags, Error **errp);
-BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
-                                    BlockDriverState *bs, QDict *options,
-                                    bool keep_old_opts);
-void bdrv_reopen_queue_free(BlockReopenQueue *bs_queue);
-int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp);
-int bdrv_reopen(BlockDriverState *bs, QDict *opts, bool keep_old_opts,
-                Error **errp);
-int bdrv_reopen_set_read_only(BlockDriverState *bs, bool read_only,
-                              Error **errp);
-int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset,
-                       int64_t bytes, BdrvRequestFlags flags);
-int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags);
-int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int64_t bytes);
-int bdrv_pwrite(BdrvChild *child, int64_t offset, const void *buf,
-                int64_t bytes);
-int bdrv_pwrite_sync(BdrvChild *child, int64_t offset,
-                     const void *buf, int64_t bytes);
-/*
- * Efficiently zero a region of the disk image.  Note that this is a regular
- * I/O request like read or write and should have a reasonable size.  This
- * function is not suitable for zeroing the entire image in a single request
- * because it may allocate memory for the entire region.
- */
-int coroutine_fn bdrv_co_pwrite_zeroes(BdrvChild *child, int64_t offset,
-                                       int64_t bytes, BdrvRequestFlags flags);
-BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
-    const char *backing_file);
-void bdrv_refresh_filename(BlockDriverState *bs);
-
-int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact,
-                                  PreallocMode prealloc, BdrvRequestFlags flags,
-                                  Error **errp);
-int generated_co_wrapper
-bdrv_truncate(BdrvChild *child, int64_t offset, bool exact,
-              PreallocMode prealloc, BdrvRequestFlags flags, Error **errp);
-
-int64_t bdrv_nb_sectors(BlockDriverState *bs);
-int64_t bdrv_getlength(BlockDriverState *bs);
-int64_t bdrv_get_allocated_file_size(BlockDriverState *bs);
-BlockMeasureInfo *bdrv_measure(BlockDriver *drv, QemuOpts *opts,
-                               BlockDriverState *in_bs, Error **errp);
-void bdrv_get_geometry(BlockDriverState *bs, uint64_t *nb_sectors_ptr);
-void bdrv_refresh_limits(BlockDriverState *bs, Transaction *tran, Error **errp);
-int bdrv_commit(BlockDriverState *bs);
-int bdrv_make_empty(BdrvChild *c, Error **errp);
-int bdrv_change_backing_file(BlockDriverState *bs, const char *backing_file,
-                             const char *backing_fmt, bool warn);
-void bdrv_register(BlockDriver *bdrv);
-int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base,
-                           const char *backing_file_str);
-BlockDriverState *bdrv_find_overlay(BlockDriverState *active,
-                                    BlockDriverState *bs);
-BlockDriverState *bdrv_find_base(BlockDriverState *bs);
-bool bdrv_is_backing_chain_frozen(BlockDriverState *bs, BlockDriverState *base,
-                                  Error **errp);
-int bdrv_freeze_backing_chain(BlockDriverState *bs, BlockDriverState *base,
-                              Error **errp);
-void bdrv_unfreeze_backing_chain(BlockDriverState *bs, BlockDriverState *base);
-int coroutine_fn bdrv_co_delete_file(BlockDriverState *bs, Error **errp);
-void coroutine_fn bdrv_co_delete_file_noerr(BlockDriverState *bs);
-
-
-typedef struct BdrvCheckResult {
-    int corruptions;
-    int leaks;
-    int check_errors;
-    int corruptions_fixed;
-    int leaks_fixed;
-    int64_t image_end_offset;
-    BlockFragInfo bfi;
-} BdrvCheckResult;
-
-typedef enum {
-    BDRV_FIX_LEAKS    = 1,
-    BDRV_FIX_ERRORS   = 2,
-} BdrvCheckMode;
-
-int generated_co_wrapper bdrv_check(BlockDriverState *bs, BdrvCheckResult *res,
-                                    BdrvCheckMode fix);
-
-/* The units of offset and total_work_size may be chosen arbitrarily by the
- * block driver; total_work_size may change during the course of the amendment
- * operation */
-typedef void BlockDriverAmendStatusCB(BlockDriverState *bs, int64_t offset,
-                                      int64_t total_work_size, void *opaque);
-int bdrv_amend_options(BlockDriverState *bs_new, QemuOpts *opts,
-                       BlockDriverAmendStatusCB *status_cb, void *cb_opaque,
-                       bool force,
-                       Error **errp);
-
-/* check if a named node can be replaced when doing drive-mirror */
-BlockDriverState *check_to_replace_node(BlockDriverState *parent_bs,
-                                        const char *node_name, Error **errp);
-
-/* async block I/O */
-void bdrv_aio_cancel(BlockAIOCB *acb);
-void bdrv_aio_cancel_async(BlockAIOCB *acb);
-
-/* sg packet commands */
-int bdrv_co_ioctl(BlockDriverState *bs, int req, void *buf);
-
-/* Invalidate any cached metadata used by image formats */
-int generated_co_wrapper bdrv_invalidate_cache(BlockDriverState *bs,
-                                               Error **errp);
-void bdrv_invalidate_cache_all(Error **errp);
-int bdrv_inactivate_all(void);
-
-/* Ensure contents are flushed to disk.  */
-int generated_co_wrapper bdrv_flush(BlockDriverState *bs);
-int coroutine_fn bdrv_co_flush(BlockDriverState *bs);
-int bdrv_flush_all(void);
-void bdrv_close_all(void);
-void bdrv_drain(BlockDriverState *bs);
-void coroutine_fn bdrv_co_drain(BlockDriverState *bs);
-void bdrv_drain_all_begin(void);
-void bdrv_drain_all_end(void);
-void bdrv_drain_all(void);
-
-#define BDRV_POLL_WHILE(bs, cond) ({                       \
-    BlockDriverState *bs_ = (bs);                          \
-    AIO_WAIT_WHILE(bdrv_get_aio_context(bs_),              \
-                   cond); })
-
-int generated_co_wrapper bdrv_pdiscard(BdrvChild *child, int64_t offset,
-                                       int64_t bytes);
-int bdrv_co_pdiscard(BdrvChild *child, int64_t offset, int64_t bytes);
-int bdrv_has_zero_init_1(BlockDriverState *bs);
-int bdrv_has_zero_init(BlockDriverState *bs);
-bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs);
-int bdrv_block_status(BlockDriverState *bs, int64_t offset,
-                      int64_t bytes, int64_t *pnum, int64_t *map,
-                      BlockDriverState **file);
-int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base,
-                            int64_t offset, int64_t bytes, int64_t *pnum,
-                            int64_t *map, BlockDriverState **file);
-int bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int64_t bytes,
-                      int64_t *pnum);
-int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base,
-                            bool include_base, int64_t offset, int64_t bytes,
-                            int64_t *pnum);
-int coroutine_fn bdrv_co_is_zero_fast(BlockDriverState *bs, int64_t offset,
-                                      int64_t bytes);
-
-bool bdrv_is_read_only(BlockDriverState *bs);
-int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only,
-                           bool ignore_allow_rdw, Error **errp);
-int bdrv_apply_auto_read_only(BlockDriverState *bs, const char *errmsg,
-                              Error **errp);
-bool bdrv_is_writable(BlockDriverState *bs);
-bool bdrv_is_sg(BlockDriverState *bs);
-bool bdrv_is_inserted(BlockDriverState *bs);
-void bdrv_lock_medium(BlockDriverState *bs, bool locked);
-void bdrv_eject(BlockDriverState *bs, bool eject_flag);
-const char *bdrv_get_format_name(BlockDriverState *bs);
-BlockDriverState *bdrv_find_node(const char *node_name);
-BlockDeviceInfoList *bdrv_named_nodes_list(bool flat, Error **errp);
-XDbgBlockGraph *bdrv_get_xdbg_block_graph(Error **errp);
-BlockDriverState *bdrv_lookup_bs(const char *device,
-                                 const char *node_name,
-                                 Error **errp);
-bool bdrv_chain_contains(BlockDriverState *top, BlockDriverState *base);
-BlockDriverState *bdrv_next_node(BlockDriverState *bs);
-BlockDriverState *bdrv_next_all_states(BlockDriverState *bs);
-
-typedef struct BdrvNextIterator {
-    enum {
-        BDRV_NEXT_BACKEND_ROOTS,
-        BDRV_NEXT_MONITOR_OWNED,
-    } phase;
-    BlockBackend *blk;
-    BlockDriverState *bs;
-} BdrvNextIterator;
-
-BlockDriverState *bdrv_first(BdrvNextIterator *it);
-BlockDriverState *bdrv_next(BdrvNextIterator *it);
-void bdrv_next_cleanup(BdrvNextIterator *it);
-
-BlockDriverState *bdrv_next_monitor_owned(BlockDriverState *bs);
-bool bdrv_supports_compressed_writes(BlockDriverState *bs);
-void bdrv_iterate_format(void (*it)(void *opaque, const char *name),
-                         void *opaque, bool read_only);
-const char *bdrv_get_node_name(const BlockDriverState *bs);
-const char *bdrv_get_device_name(const BlockDriverState *bs);
-const char *bdrv_get_device_or_node_name(const BlockDriverState *bs);
-int bdrv_get_flags(BlockDriverState *bs);
-int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi);
-ImageInfoSpecific *bdrv_get_specific_info(BlockDriverState *bs,
-                                          Error **errp);
-BlockStatsSpecific *bdrv_get_specific_stats(BlockDriverState *bs);
-void bdrv_round_to_clusters(BlockDriverState *bs,
-                            int64_t offset, int64_t bytes,
-                            int64_t *cluster_offset,
-                            int64_t *cluster_bytes);
-
-void bdrv_get_backing_filename(BlockDriverState *bs,
-                               char *filename, int filename_size);
-char *bdrv_get_full_backing_filename(BlockDriverState *bs, Error **errp);
-char *bdrv_get_full_backing_filename_from_filename(const char *backed,
-                                                   const char *backing,
-                                                   Error **errp);
-char *bdrv_dirname(BlockDriverState *bs, Error **errp);
-
-int path_has_protocol(const char *path);
-int path_is_absolute(const char *path);
-char *path_combine(const char *base_path, const char *filename);
-
-int generated_co_wrapper
-bdrv_readv_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos);
-int generated_co_wrapper
-bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos);
-int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
-                      int64_t pos, int size);
-
-int bdrv_load_vmstate(BlockDriverState *bs, uint8_t *buf,
-                      int64_t pos, int size);
-
-void bdrv_img_create(const char *filename, const char *fmt,
-                     const char *base_filename, const char *base_fmt,
-                     char *options, uint64_t img_size, int flags,
-                     bool quiet, Error **errp);
-
-/* Returns the alignment in bytes that is required so that no bounce buffer
- * is required throughout the stack */
-size_t bdrv_min_mem_align(BlockDriverState *bs);
-/* Returns optimal alignment in bytes for bounce buffer */
-size_t bdrv_opt_mem_align(BlockDriverState *bs);
-void *qemu_blockalign(BlockDriverState *bs, size_t size);
-void *qemu_blockalign0(BlockDriverState *bs, size_t size);
-void *qemu_try_blockalign(BlockDriverState *bs, size_t size);
-void *qemu_try_blockalign0(BlockDriverState *bs, size_t size);
-bool bdrv_qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov);
-
-void bdrv_enable_copy_on_read(BlockDriverState *bs);
-void bdrv_disable_copy_on_read(BlockDriverState *bs);
-
-void bdrv_ref(BlockDriverState *bs);
-void bdrv_unref(BlockDriverState *bs);
-void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child);
-BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs,
-                             BlockDriverState *child_bs,
-                             const char *child_name,
-                             const BdrvChildClass *child_class,
-                             BdrvChildRole child_role,
-                             Error **errp);
-
-bool bdrv_op_is_blocked(BlockDriverState *bs, BlockOpType op, Error **errp);
-void bdrv_op_block(BlockDriverState *bs, BlockOpType op, Error *reason);
-void bdrv_op_unblock(BlockDriverState *bs, BlockOpType op, Error *reason);
-void bdrv_op_block_all(BlockDriverState *bs, Error *reason);
-void bdrv_op_unblock_all(BlockDriverState *bs, Error *reason);
-bool bdrv_op_blocker_is_empty(BlockDriverState *bs);
-
-#define BLKDBG_EVENT(child, evt) \
-    do { \
-        if (child) { \
-            bdrv_debug_event(child->bs, evt); \
-        } \
-    } while (0)
-
-void bdrv_debug_event(BlockDriverState *bs, BlkdebugEvent event);
-
-int bdrv_debug_breakpoint(BlockDriverState *bs, const char *event,
-                           const char *tag);
-int bdrv_debug_remove_breakpoint(BlockDriverState *bs, const char *tag);
-int bdrv_debug_resume(BlockDriverState *bs, const char *tag);
-bool bdrv_debug_is_suspended(BlockDriverState *bs, const char *tag);
-
-/**
- * bdrv_get_aio_context:
- *
- * Returns: the currently bound #AioContext
- */
-AioContext *bdrv_get_aio_context(BlockDriverState *bs);
-
-/**
- * Move the current coroutine to the AioContext of @bs and return the old
- * AioContext of the coroutine. Increase bs->in_flight so that draining @bs
- * will wait for the operation to proceed until the corresponding
- * bdrv_co_leave().
- *
- * Consequently, you can't call drain inside a bdrv_co_enter/leave() section as
- * this will deadlock.
- */
-AioContext *coroutine_fn bdrv_co_enter(BlockDriverState *bs);
-
-/**
- * Ends a section started by bdrv_co_enter(). Move the current coroutine back
- * to old_ctx and decrease bs->in_flight again.
- */
-void coroutine_fn bdrv_co_leave(BlockDriverState *bs, AioContext *old_ctx);
-
-/**
- * Locks the AioContext of @bs if it's not the current AioContext. This avoids
- * double locking which could lead to deadlocks: This is a coroutine_fn, so we
- * know we already own the lock of the current AioContext.
- *
- * May only be called in the main thread.
- */
-void coroutine_fn bdrv_co_lock(BlockDriverState *bs);
-
-/**
- * Unlocks the AioContext of @bs if it's not the current AioContext.
- */
-void coroutine_fn bdrv_co_unlock(BlockDriverState *bs);
-
-/**
- * Transfer control to @co in the aio context of @bs
- */
-void bdrv_coroutine_enter(BlockDriverState *bs, Coroutine *co);
-
-void bdrv_set_aio_context_ignore(BlockDriverState *bs,
-                                 AioContext *new_context, GSList **ignore);
-int bdrv_try_set_aio_context(BlockDriverState *bs, AioContext *ctx,
-                             Error **errp);
-int bdrv_child_try_set_aio_context(BlockDriverState *bs, AioContext *ctx,
-                                   BdrvChild *ignore_child, Error **errp);
-bool bdrv_child_can_set_aio_context(BdrvChild *c, AioContext *ctx,
-                                    GSList **ignore, Error **errp);
-bool bdrv_can_set_aio_context(BlockDriverState *bs, AioContext *ctx,
-                              GSList **ignore, Error **errp);
-AioContext *bdrv_child_get_parent_aio_context(BdrvChild *c);
-AioContext *child_of_bds_get_parent_aio_context(BdrvChild *c);
-
-int bdrv_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz);
-int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo);
-
-void bdrv_io_plug(BlockDriverState *bs);
-void bdrv_io_unplug(BlockDriverState *bs);
-
-/**
- * bdrv_parent_drained_begin_single:
- *
- * Begin a quiesced section for the parent of @c. If @poll is true, wait for
- * any pending activity to cease.
- */
-void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll);
-
-/**
- * bdrv_parent_drained_end_single:
- *
- * End a quiesced section for the parent of @c.
- *
- * This polls @bs's AioContext until all scheduled sub-drained_ends
- * have settled, which may result in graph changes.
- */
-void bdrv_parent_drained_end_single(BdrvChild *c);
-
-/**
- * bdrv_drain_poll:
- *
- * Poll for pending requests in @bs, its parents (except for @ignore_parent),
- * and if @recursive is true its children as well (used for subtree drain).
- *
- * If @ignore_bds_parents is true, parents that are BlockDriverStates must
- * ignore the drain request because they will be drained separately (used for
- * drain_all).
- *
- * This is part of bdrv_drained_begin.
- */
-bool bdrv_drain_poll(BlockDriverState *bs, bool recursive,
-                     BdrvChild *ignore_parent, bool ignore_bds_parents);
-
-/**
- * bdrv_drained_begin:
- *
- * Begin a quiesced section for exclusive access to the BDS, by disabling
- * external request sources including NBD server, block jobs, and device model.
- *
- * This function can be recursive.
- */
-void bdrv_drained_begin(BlockDriverState *bs);
-
-/**
- * bdrv_do_drained_begin_quiesce:
- *
- * Quiesces a BDS like bdrv_drained_begin(), but does not wait for already
- * running requests to complete.
- */
-void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
-                                   BdrvChild *parent, bool ignore_bds_parents);
-
-/**
- * Like bdrv_drained_begin, but recursively begins a quiesced section for
- * exclusive access to all child nodes as well.
- */
-void bdrv_subtree_drained_begin(BlockDriverState *bs);
-
-/**
- * bdrv_drained_end:
- *
- * End a quiescent section started by bdrv_drained_begin().
- *
- * This polls @bs's AioContext until all scheduled sub-drained_ends
- * have settled.  On one hand, that may result in graph changes.  On
- * the other, this requires that the caller either runs in the main
- * loop; or that all involved nodes (@bs and all of its parents) are
- * in the caller's AioContext.
- */
-void bdrv_drained_end(BlockDriverState *bs);
-
-/**
- * bdrv_drained_end_no_poll:
- *
- * Same as bdrv_drained_end(), but do not poll for the subgraph to
- * actually become unquiesced.  Therefore, no graph changes will occur
- * with this function.
- *
- * *drained_end_counter is incremented for every background operation
- * that is scheduled, and will be decremented for every operation once
- * it settles.  The caller must poll until it reaches 0.  The counter
- * should be accessed using atomic operations only.
- */
-void bdrv_drained_end_no_poll(BlockDriverState *bs, int *drained_end_counter);
-
-/**
- * End a quiescent section started by bdrv_subtree_drained_begin().
- */
-void bdrv_subtree_drained_end(BlockDriverState *bs);
-
-void bdrv_add_child(BlockDriverState *parent, BlockDriverState *child,
-                    Error **errp);
-void bdrv_del_child(BlockDriverState *parent, BdrvChild *child, Error **errp);
-
-bool bdrv_can_store_new_dirty_bitmap(BlockDriverState *bs, const char *name,
-                                     uint32_t granularity, Error **errp);
-/**
- *
- * bdrv_register_buf/bdrv_unregister_buf:
- *
- * 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.
- */
-void bdrv_register_buf(BlockDriverState *bs, void *host, size_t size);
-void bdrv_unregister_buf(BlockDriverState *bs, void *host);
-
-/**
- *
- * bdrv_co_copy_range:
- *
- * Do offloaded copy between two children. If the operation is not implemented
- * by the driver, or if the backend storage doesn't support it, a negative
- * error code will be returned.
- *
- * Note: block layer doesn't emulate or fallback to a bounce buffer approach
- * because usually the caller shouldn't attempt offloaded copy any more (e.g.
- * calling copy_file_range(2)) after the first error, thus it should fall back
- * to a read+write path in the caller level.
- *
- * @src: Source child to copy data from
- * @src_offset: offset in @src image to read data
- * @dst: Destination child to copy data to
- * @dst_offset: offset in @dst image to write data
- * @bytes: number of bytes to copy
- * @flags: request flags. Supported flags:
- *         BDRV_REQ_ZERO_WRITE - treat the @src range as zero data and do zero
- *                               write on @dst as if bdrv_co_pwrite_zeroes is
- *                               called. Used to simplify caller code, or
- *                               during BlockDriver.bdrv_co_copy_range_from()
- *                               recursion.
- *         BDRV_REQ_NO_SERIALISING - do not serialize with other overlapping
- *                                   requests currently in flight.
- *
- * Returns: 0 if succeeded; negative error code if failed.
- **/
-int coroutine_fn bdrv_co_copy_range(BdrvChild *src, int64_t src_offset,
-                                    BdrvChild *dst, int64_t dst_offset,
-                                    int64_t bytes, BdrvRequestFlags read_flags,
-                                    BdrvRequestFlags write_flags);
-
-void bdrv_cancel_in_flight(BlockDriverState *bs);
-
-#endif
+#endif /* BLOCK_H */
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 03/25] assertions for block global state API
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
  2021-10-12  8:48 ` [PATCH v3 01/25] main-loop.h: introduce qemu_in_main_thread() Emanuele Giuseppe Esposito
  2021-10-12  8:48 ` [PATCH v3 02/25] include/block/block: split header into I/O and global state API Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-12  8:48 ` [PATCH v3 04/25] include/sysemu/block-backend: split header into I/O and global state (GS) API Emanuele Giuseppe Esposito
                   ` (21 subsequent siblings)
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

All the global state (GS) API functions will check that
qemu_in_main_thread() returns true. If not, it means
that the safety of BQL cannot be guaranteed, and
they need to be moved to I/O.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block.c        | 136 +++++++++++++++++++++++++++++++++++++++++++++++--
 block/commit.c |   2 +
 block/io.c     |  20 ++++++++
 blockdev.c     |   1 +
 4 files changed, 156 insertions(+), 3 deletions(-)

diff --git a/block.c b/block.c
index 6fdb4d7712..672f946065 100644
--- a/block.c
+++ b/block.c
@@ -386,6 +386,7 @@ char *bdrv_get_full_backing_filename(BlockDriverState *bs, Error **errp)
 void bdrv_register(BlockDriver *bdrv)
 {
     assert(bdrv->format_name);
+    assert(qemu_in_main_thread());
     QLIST_INSERT_HEAD(&bdrv_drivers, bdrv, list);
 }
 
@@ -394,6 +395,8 @@ BlockDriverState *bdrv_new(void)
     BlockDriverState *bs;
     int i;
 
+    assert(qemu_in_main_thread());
+
     bs = g_new0(BlockDriverState, 1);
     QLIST_INIT(&bs->dirty_bitmaps);
     for (i = 0; i < BLOCK_OP_TYPE_MAX; i++) {
@@ -421,6 +424,7 @@ BlockDriverState *bdrv_new(void)
 static BlockDriver *bdrv_do_find_format(const char *format_name)
 {
     BlockDriver *drv1;
+    assert(qemu_in_main_thread());
 
     QLIST_FOREACH(drv1, &bdrv_drivers, list) {
         if (!strcmp(drv1->format_name, format_name)) {
@@ -436,6 +440,8 @@ BlockDriver *bdrv_find_format(const char *format_name)
     BlockDriver *drv1;
     int i;
 
+    assert(qemu_in_main_thread());
+
     drv1 = bdrv_do_find_format(format_name);
     if (drv1) {
         return drv1;
@@ -485,11 +491,13 @@ static int bdrv_format_is_whitelisted(const char *format_name, bool read_only)
 
 int bdrv_is_whitelisted(BlockDriver *drv, bool read_only)
 {
+    assert(qemu_in_main_thread());
     return bdrv_format_is_whitelisted(drv->format_name, read_only);
 }
 
 bool bdrv_uses_whitelist(void)
 {
+    assert(qemu_in_main_thread());
     return use_bdrv_whitelist;
 }
 
@@ -520,6 +528,8 @@ int bdrv_create(BlockDriver *drv, const char* filename,
 {
     int ret;
 
+    assert(qemu_in_main_thread());
+
     Coroutine *co;
     CreateCo cco = {
         .drv = drv,
@@ -695,6 +705,8 @@ int bdrv_create_file(const char *filename, QemuOpts *opts, Error **errp)
     QDict *qdict;
     int ret;
 
+    assert(qemu_in_main_thread());
+
     drv = bdrv_find_protocol(filename, true, errp);
     if (drv == NULL) {
         return -ENOENT;
@@ -792,6 +804,7 @@ int bdrv_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz)
 {
     BlockDriver *drv = bs->drv;
     BlockDriverState *filtered = bdrv_filter_bs(bs);
+    assert(qemu_in_main_thread());
 
     if (drv && drv->bdrv_probe_blocksizes) {
         return drv->bdrv_probe_blocksizes(bs, bsz);
@@ -812,6 +825,7 @@ int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo)
 {
     BlockDriver *drv = bs->drv;
     BlockDriverState *filtered = bdrv_filter_bs(bs);
+    assert(qemu_in_main_thread());
 
     if (drv && drv->bdrv_probe_geometry) {
         return drv->bdrv_probe_geometry(bs, geo);
@@ -866,6 +880,7 @@ static BlockDriver *find_hdev_driver(const char *filename)
 {
     int score_max = 0, score;
     BlockDriver *drv = NULL, *d;
+    assert(qemu_in_main_thread());
 
     QLIST_FOREACH(d, &bdrv_drivers, list) {
         if (d->bdrv_probe_device) {
@@ -883,6 +898,7 @@ static BlockDriver *find_hdev_driver(const char *filename)
 static BlockDriver *bdrv_do_find_protocol(const char *protocol)
 {
     BlockDriver *drv1;
+    assert(qemu_in_main_thread());
 
     QLIST_FOREACH(drv1, &bdrv_drivers, list) {
         if (drv1->protocol_name && !strcmp(drv1->protocol_name, protocol)) {
@@ -903,6 +919,7 @@ BlockDriver *bdrv_find_protocol(const char *filename,
     const char *p;
     int i;
 
+    assert(qemu_in_main_thread());
     /* TODO Drivers without bdrv_file_open must be specified explicitly */
 
     /*
@@ -968,6 +985,7 @@ BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size,
 {
     int score_max = 0, score;
     BlockDriver *drv = NULL, *d;
+    assert(qemu_in_main_thread());
 
     QLIST_FOREACH(d, &bdrv_drivers, list) {
         if (d->bdrv_probe) {
@@ -1115,6 +1133,7 @@ int bdrv_parse_aio(const char *mode, int *flags)
  */
 int bdrv_parse_discard_flags(const char *mode, int *flags)
 {
+    assert(qemu_in_main_thread());
     *flags &= ~BDRV_O_UNMAP;
 
     if (!strcmp(mode, "off") || !strcmp(mode, "ignore")) {
@@ -1135,6 +1154,7 @@ int bdrv_parse_discard_flags(const char *mode, int *flags)
  */
 int bdrv_parse_cache_mode(const char *mode, int *flags, bool *writethrough)
 {
+    assert(qemu_in_main_thread());
     *flags &= ~BDRV_O_CACHE_MASK;
 
     if (!strcmp(mode, "off") || !strcmp(mode, "none")) {
@@ -1499,6 +1519,7 @@ static void bdrv_assign_node_name(BlockDriverState *bs,
                                   Error **errp)
 {
     char *gen_node_name = NULL;
+    assert(qemu_in_main_thread());
 
     if (!node_name) {
         node_name = gen_node_name = id_generate(ID_BLOCK);
@@ -1623,6 +1644,8 @@ BlockDriverState *bdrv_new_open_driver_opts(BlockDriver *drv,
     BlockDriverState *bs;
     int ret;
 
+    assert(qemu_in_main_thread());
+
     bs = bdrv_new();
     bs->open_flags = flags;
     bs->options = options ?: qdict_new();
@@ -1648,6 +1671,7 @@ BlockDriverState *bdrv_new_open_driver_opts(BlockDriver *drv,
 BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name,
                                        int flags, Error **errp)
 {
+    assert(qemu_in_main_thread());
     return bdrv_new_open_driver_opts(drv, node_name, NULL, flags, errp);
 }
 
@@ -1742,6 +1766,7 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file,
 
     assert(bs->file == NULL);
     assert(options != NULL && bs->options != options);
+    assert(qemu_in_main_thread());
 
     opts = qemu_opts_create(&bdrv_runtime_opts, NULL, 0, &error_abort);
     if (!qemu_opts_absorb_qdict(opts, options, errp)) {
@@ -2999,6 +3024,8 @@ BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs,
     BdrvChild *child = NULL;
     Transaction *tran = tran_new();
 
+    assert(qemu_in_main_thread());
+
     ret = bdrv_attach_child_noperm(parent_bs, child_bs, child_name, child_class,
                                    child_role, &child, tran, errp);
     if (ret < 0) {
@@ -3025,6 +3052,8 @@ void bdrv_root_unref_child(BdrvChild *child)
 {
     BlockDriverState *child_bs;
 
+    assert(qemu_in_main_thread());
+
     child_bs = child->bs;
     bdrv_detach_child(child);
     bdrv_unref(child_bs);
@@ -3099,6 +3128,7 @@ static void bdrv_unset_inherits_from(BlockDriverState *root, BdrvChild *child,
 /* Callers must ensure that child->frozen is false. */
 void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child)
 {
+    assert(qemu_in_main_thread());
     if (child == NULL) {
         return;
     }
@@ -3249,6 +3279,8 @@ int bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
     int ret;
     Transaction *tran = tran_new();
 
+    assert(qemu_in_main_thread());
+
     ret = bdrv_set_backing_noperm(bs, backing_hd, tran, errp);
     if (ret < 0) {
         goto out;
@@ -3284,6 +3316,8 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
     QDict *tmp_parent_options = NULL;
     Error *local_err = NULL;
 
+    assert(qemu_in_main_thread());
+
     if (bs->backing != NULL) {
         goto free_exit;
     }
@@ -3443,6 +3477,8 @@ BdrvChild *bdrv_open_child(const char *filename,
 {
     BlockDriverState *bs;
 
+    assert(qemu_in_main_thread());
+
     bs = bdrv_open_child_bs(filename, options, bdref_key, parent, child_class,
                             child_role, allow_none, errp);
     if (bs == NULL) {
@@ -3465,6 +3501,8 @@ BlockDriverState *bdrv_open_blockdev_ref(BlockdevRef *ref, Error **errp)
     const char *reference = NULL;
     Visitor *v = NULL;
 
+    assert(qemu_in_main_thread());
+
     if (ref->type == QTYPE_QSTRING) {
         reference = ref->u.reference;
     } else {
@@ -3862,6 +3900,8 @@ close_and_fail:
 BlockDriverState *bdrv_open(const char *filename, const char *reference,
                             QDict *options, int flags, Error **errp)
 {
+    assert(qemu_in_main_thread());
+
     return bdrv_open_inherit(filename, reference, options, flags, NULL,
                              NULL, 0, errp);
 }
@@ -4116,12 +4156,15 @@ BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
                                     BlockDriverState *bs,
                                     QDict *options, bool keep_old_opts)
 {
+    assert(qemu_in_main_thread());
+
     return bdrv_reopen_queue_child(bs_queue, bs, options, NULL, 0, false,
                                    NULL, 0, keep_old_opts);
 }
 
 void bdrv_reopen_queue_free(BlockReopenQueue *bs_queue)
 {
+    assert(qemu_in_main_thread());
     if (bs_queue) {
         BlockReopenQueueEntry *bs_entry, *next;
         QTAILQ_FOREACH_SAFE(bs_entry, bs_queue, entry, next) {
@@ -4269,6 +4312,8 @@ int bdrv_reopen(BlockDriverState *bs, QDict *opts, bool keep_old_opts,
     BlockReopenQueue *queue;
     int ret;
 
+    assert(qemu_in_main_thread());
+
     bdrv_subtree_drained_begin(bs);
     if (ctx != qemu_get_aio_context()) {
         aio_context_release(ctx);
@@ -4290,6 +4335,8 @@ int bdrv_reopen_set_read_only(BlockDriverState *bs, bool read_only,
 {
     QDict *opts = qdict_new();
 
+    assert(qemu_in_main_thread());
+
     qdict_put_bool(opts, BDRV_OPT_READ_ONLY, read_only);
 
     return bdrv_reopen(bs, opts, true, errp);
@@ -4744,6 +4791,7 @@ static void bdrv_close(BlockDriverState *bs)
 void bdrv_close_all(void)
 {
     assert(job_next(NULL) == NULL);
+    assert(qemu_in_main_thread());
 
     /* Drop references from requests still in flight, such as canceled block
      * jobs whose AIO context has not been polled yet */
@@ -5025,11 +5073,15 @@ out:
 int bdrv_replace_node(BlockDriverState *from, BlockDriverState *to,
                       Error **errp)
 {
+    assert(qemu_in_main_thread());
+
     return bdrv_replace_node_common(from, to, true, false, errp);
 }
 
 int bdrv_drop_filter(BlockDriverState *bs, Error **errp)
 {
+    assert(qemu_in_main_thread());
+
     return bdrv_replace_node_common(bs, bdrv_filter_or_cow_bs(bs), true, true,
                                     errp);
 }
@@ -5052,6 +5104,8 @@ int bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
     int ret;
     Transaction *tran = tran_new();
 
+    assert(qemu_in_main_thread());
+
     assert(!bs_new->backing);
 
     ret = bdrv_attach_child_noperm(bs_new, bs_top, "backing",
@@ -5110,6 +5164,7 @@ static void bdrv_delete(BlockDriverState *bs)
 {
     assert(bdrv_op_blocker_is_empty(bs));
     assert(!bs->refcnt);
+    assert(qemu_in_main_thread());
 
     /* remove from list, if necessary */
     if (bs->node_name[0] != '\0') {
@@ -5154,6 +5209,8 @@ BlockDriverState *bdrv_insert_node(BlockDriverState *bs, QDict *options,
 
     node_name = qdict_get_try_str(options, "node-name");
 
+    assert(qemu_in_main_thread());
+
     new_node_bs = bdrv_new_open_driver_opts(drv, node_name, options, flags,
                                             errp);
     options = NULL; /* bdrv_new_open_driver() eats options */
@@ -5214,6 +5271,8 @@ int bdrv_change_backing_file(BlockDriverState *bs, const char *backing_file,
     BlockDriver *drv = bs->drv;
     int ret;
 
+    assert(qemu_in_main_thread());
+
     if (!drv) {
         return -ENOMEDIUM;
     }
@@ -5255,6 +5314,9 @@ int bdrv_change_backing_file(BlockDriverState *bs, const char *backing_file,
 BlockDriverState *bdrv_find_overlay(BlockDriverState *active,
                                     BlockDriverState *bs)
 {
+
+    assert(qemu_in_main_thread());
+
     bs = bdrv_skip_filters(bs);
     active = bdrv_skip_filters(active);
 
@@ -5272,6 +5334,8 @@ BlockDriverState *bdrv_find_overlay(BlockDriverState *active,
 /* Given a BDS, searches for the base layer. */
 BlockDriverState *bdrv_find_base(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
+
     return bdrv_find_overlay(bs, NULL);
 }
 
@@ -5286,6 +5350,8 @@ bool bdrv_is_backing_chain_frozen(BlockDriverState *bs, BlockDriverState *base,
     BlockDriverState *i;
     BdrvChild *child;
 
+    assert(qemu_in_main_thread());
+
     for (i = bs; i != base; i = child_bs(child)) {
         child = bdrv_filter_or_cow_child(i);
 
@@ -5312,6 +5378,8 @@ int bdrv_freeze_backing_chain(BlockDriverState *bs, BlockDriverState *base,
     BlockDriverState *i;
     BdrvChild *child;
 
+    assert(qemu_in_main_thread());
+
     if (bdrv_is_backing_chain_frozen(bs, base, errp)) {
         return -EPERM;
     }
@@ -5346,6 +5414,8 @@ void bdrv_unfreeze_backing_chain(BlockDriverState *bs, BlockDriverState *base)
     BlockDriverState *i;
     BdrvChild *child;
 
+    assert(qemu_in_main_thread());
+
     for (i = bs; i != base; i = child_bs(child)) {
         child = bdrv_filter_or_cow_child(i);
         if (child) {
@@ -5395,6 +5465,8 @@ int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base,
     g_autoptr(GSList) updated_children = NULL;
     GSList *p;
 
+    assert(qemu_in_main_thread());
+
     bdrv_ref(top);
     bdrv_subtree_drained_begin(top);
 
@@ -5606,7 +5678,6 @@ int64_t bdrv_getlength(BlockDriverState *bs)
 void bdrv_get_geometry(BlockDriverState *bs, uint64_t *nb_sectors_ptr)
 {
     int64_t nb_sectors = bdrv_nb_sectors(bs);
-
     *nb_sectors_ptr = nb_sectors < 0 ? 0 : nb_sectors;
 }
 
@@ -5656,6 +5727,8 @@ void bdrv_iterate_format(void (*it)(void *opaque, const char *name),
     int i;
     const char **formats = NULL;
 
+    assert(qemu_in_main_thread());
+
     QLIST_FOREACH(drv, &bdrv_drivers, list) {
         if (drv->format_name) {
             bool found = false;
@@ -5714,6 +5787,7 @@ BlockDriverState *bdrv_find_node(const char *node_name)
     BlockDriverState *bs;
 
     assert(node_name);
+    assert(qemu_in_main_thread());
 
     QTAILQ_FOREACH(bs, &graph_bdrv_states, node_list) {
         if (!strcmp(node_name, bs->node_name)) {
@@ -5730,6 +5804,8 @@ BlockDeviceInfoList *bdrv_named_nodes_list(bool flat,
     BlockDeviceInfoList *list;
     BlockDriverState *bs;
 
+    assert(qemu_in_main_thread());
+
     list = NULL;
     QTAILQ_FOREACH(bs, &graph_bdrv_states, node_list) {
         BlockDeviceInfo *info = bdrv_block_device_info(NULL, bs, flat, errp);
@@ -5835,6 +5911,8 @@ XDbgBlockGraph *bdrv_get_xdbg_block_graph(Error **errp)
     BdrvChild *child;
     XDbgBlockGraphConstructor *gr = xdbg_graph_new();
 
+    assert(qemu_in_main_thread());
+
     for (blk = blk_all_next(NULL); blk; blk = blk_all_next(blk)) {
         char *allocated_name = NULL;
         const char *name = blk_name(blk);
@@ -5878,6 +5956,8 @@ BlockDriverState *bdrv_lookup_bs(const char *device,
     BlockBackend *blk;
     BlockDriverState *bs;
 
+    assert(qemu_in_main_thread());
+
     if (device) {
         blk = blk_by_name(device);
 
@@ -5909,6 +5989,9 @@ BlockDriverState *bdrv_lookup_bs(const char *device,
  * return false.  If either argument is NULL, return false. */
 bool bdrv_chain_contains(BlockDriverState *top, BlockDriverState *base)
 {
+
+    assert(qemu_in_main_thread());
+
     while (top && top != base) {
         top = bdrv_filter_or_cow_bs(top);
     }
@@ -5918,6 +6001,7 @@ bool bdrv_chain_contains(BlockDriverState *top, BlockDriverState *base)
 
 BlockDriverState *bdrv_next_node(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     if (!bs) {
         return QTAILQ_FIRST(&graph_bdrv_states);
     }
@@ -5926,6 +6010,7 @@ BlockDriverState *bdrv_next_node(BlockDriverState *bs)
 
 BlockDriverState *bdrv_next_all_states(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     if (!bs) {
         return QTAILQ_FIRST(&all_bdrv_states);
     }
@@ -5958,6 +6043,7 @@ const char *bdrv_get_parent_name(const BlockDriverState *bs)
 /* TODO check what callers really want: bs->node_name or blk_name() */
 const char *bdrv_get_device_name(const BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     return bdrv_get_parent_name(bs) ?: "";
 }
 
@@ -5967,22 +6053,26 @@ const char *bdrv_get_device_name(const BlockDriverState *bs)
  * absent, then this returns an empty (non-null) string. */
 const char *bdrv_get_device_or_node_name(const BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     return bdrv_get_parent_name(bs) ?: bs->node_name;
 }
 
 int bdrv_get_flags(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     return bs->open_flags;
 }
 
 int bdrv_has_zero_init_1(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     return 1;
 }
 
 int bdrv_has_zero_init(BlockDriverState *bs)
 {
     BlockDriverState *filtered;
+    assert(qemu_in_main_thread());
 
     if (!bs->drv) {
         return 0;
@@ -6079,6 +6169,7 @@ void bdrv_debug_event(BlockDriverState *bs, BlkdebugEvent event)
 
 static BlockDriverState *bdrv_find_debug_node(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     while (bs && bs->drv && !bs->drv->bdrv_debug_breakpoint) {
         bs = bdrv_primary_bs(bs);
     }
@@ -6094,6 +6185,7 @@ static BlockDriverState *bdrv_find_debug_node(BlockDriverState *bs)
 int bdrv_debug_breakpoint(BlockDriverState *bs, const char *event,
                           const char *tag)
 {
+    assert(qemu_in_main_thread());
     bs = bdrv_find_debug_node(bs);
     if (bs) {
         return bs->drv->bdrv_debug_breakpoint(bs, event, tag);
@@ -6104,6 +6196,7 @@ int bdrv_debug_breakpoint(BlockDriverState *bs, const char *event,
 
 int bdrv_debug_remove_breakpoint(BlockDriverState *bs, const char *tag)
 {
+    assert(qemu_in_main_thread());
     bs = bdrv_find_debug_node(bs);
     if (bs) {
         return bs->drv->bdrv_debug_remove_breakpoint(bs, tag);
@@ -6114,6 +6207,7 @@ int bdrv_debug_remove_breakpoint(BlockDriverState *bs, const char *tag)
 
 int bdrv_debug_resume(BlockDriverState *bs, const char *tag)
 {
+    assert(qemu_in_main_thread());
     while (bs && (!bs->drv || !bs->drv->bdrv_debug_resume)) {
         bs = bdrv_primary_bs(bs);
     }
@@ -6127,6 +6221,7 @@ int bdrv_debug_resume(BlockDriverState *bs, const char *tag)
 
 bool bdrv_debug_is_suspended(BlockDriverState *bs, const char *tag)
 {
+    assert(qemu_in_main_thread());
     while (bs && bs->drv && !bs->drv->bdrv_debug_is_suspended) {
         bs = bdrv_primary_bs(bs);
     }
@@ -6154,6 +6249,8 @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
     BlockDriverState *retval = NULL;
     BlockDriverState *bs_below;
 
+    assert(qemu_in_main_thread());
+
     if (!bs || !bs->drv || !backing_file) {
         return NULL;
     }
@@ -6252,6 +6349,7 @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
 
 void bdrv_init(void)
 {
+    assert(qemu_in_main_thread());
 #ifdef CONFIG_BDRV_WHITELIST_TOOLS
     use_bdrv_whitelist = 1;
 #endif
@@ -6260,6 +6358,7 @@ void bdrv_init(void)
 
 void bdrv_init_with_whitelist(void)
 {
+    assert(qemu_in_main_thread());
     use_bdrv_whitelist = 1;
     bdrv_init();
 }
@@ -6344,6 +6443,8 @@ void bdrv_invalidate_cache_all(Error **errp)
     BlockDriverState *bs;
     BdrvNextIterator it;
 
+    assert(qemu_in_main_thread());
+
     for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
         AioContext *aio_context = bdrv_get_aio_context(bs);
         int ret;
@@ -6443,6 +6544,8 @@ int bdrv_inactivate_all(void)
     int ret = 0;
     GSList *aio_ctxs = NULL, *ctx;
 
+    assert(qemu_in_main_thread());
+
     for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
         AioContext *aio_context = bdrv_get_aio_context(bs);
 
@@ -6520,6 +6623,7 @@ void bdrv_eject(BlockDriverState *bs, bool eject_flag)
 void bdrv_lock_medium(BlockDriverState *bs, bool locked)
 {
     BlockDriver *drv = bs->drv;
+    assert(qemu_in_main_thread());
 
     trace_bdrv_lock_medium(bs, locked);
 
@@ -6531,6 +6635,7 @@ void bdrv_lock_medium(BlockDriverState *bs, bool locked)
 /* Get a reference to bs */
 void bdrv_ref(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     bs->refcnt++;
 }
 
@@ -6539,6 +6644,7 @@ void bdrv_ref(BlockDriverState *bs)
  * deleted. */
 void bdrv_unref(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     if (!bs) {
         return;
     }
@@ -6556,6 +6662,7 @@ struct BdrvOpBlocker {
 bool bdrv_op_is_blocked(BlockDriverState *bs, BlockOpType op, Error **errp)
 {
     BdrvOpBlocker *blocker;
+    assert(qemu_in_main_thread());
     assert((int) op >= 0 && op < BLOCK_OP_TYPE_MAX);
     if (!QLIST_EMPTY(&bs->op_blockers[op])) {
         blocker = QLIST_FIRST(&bs->op_blockers[op]);
@@ -6570,6 +6677,7 @@ bool bdrv_op_is_blocked(BlockDriverState *bs, BlockOpType op, Error **errp)
 void bdrv_op_block(BlockDriverState *bs, BlockOpType op, Error *reason)
 {
     BdrvOpBlocker *blocker;
+    assert(qemu_in_main_thread());
     assert((int) op >= 0 && op < BLOCK_OP_TYPE_MAX);
 
     blocker = g_new0(BdrvOpBlocker, 1);
@@ -6580,6 +6688,7 @@ void bdrv_op_block(BlockDriverState *bs, BlockOpType op, Error *reason)
 void bdrv_op_unblock(BlockDriverState *bs, BlockOpType op, Error *reason)
 {
     BdrvOpBlocker *blocker, *next;
+    assert(qemu_in_main_thread());
     assert((int) op >= 0 && op < BLOCK_OP_TYPE_MAX);
     QLIST_FOREACH_SAFE(blocker, &bs->op_blockers[op], list, next) {
         if (blocker->reason == reason) {
@@ -6592,6 +6701,7 @@ void bdrv_op_unblock(BlockDriverState *bs, BlockOpType op, Error *reason)
 void bdrv_op_block_all(BlockDriverState *bs, Error *reason)
 {
     int i;
+    assert(qemu_in_main_thread());
     for (i = 0; i < BLOCK_OP_TYPE_MAX; i++) {
         bdrv_op_block(bs, i, reason);
     }
@@ -6600,6 +6710,7 @@ void bdrv_op_block_all(BlockDriverState *bs, Error *reason)
 void bdrv_op_unblock_all(BlockDriverState *bs, Error *reason)
 {
     int i;
+    assert(qemu_in_main_thread());
     for (i = 0; i < BLOCK_OP_TYPE_MAX; i++) {
         bdrv_op_unblock(bs, i, reason);
     }
@@ -6608,7 +6719,7 @@ void bdrv_op_unblock_all(BlockDriverState *bs, Error *reason)
 bool bdrv_op_blocker_is_empty(BlockDriverState *bs)
 {
     int i;
-
+    assert(qemu_in_main_thread());
     for (i = 0; i < BLOCK_OP_TYPE_MAX; i++) {
         if (!QLIST_EMPTY(&bs->op_blockers[i])) {
             return false;
@@ -6630,6 +6741,8 @@ void bdrv_img_create(const char *filename, const char *fmt,
     Error *local_err = NULL;
     int ret = 0;
 
+    assert(qemu_in_main_thread());
+
     /* Find driver and parse its options */
     drv = bdrv_find_format(fmt);
     if (!drv) {
@@ -7046,6 +7159,7 @@ static bool bdrv_parent_can_set_aio_context(BdrvChild *c, AioContext *ctx,
 bool bdrv_child_can_set_aio_context(BdrvChild *c, AioContext *ctx,
                                     GSList **ignore, Error **errp)
 {
+    assert(qemu_in_main_thread());
     if (g_slist_find(*ignore, c)) {
         return true;
     }
@@ -7064,6 +7178,8 @@ bool bdrv_can_set_aio_context(BlockDriverState *bs, AioContext *ctx,
         return true;
     }
 
+    assert(qemu_in_main_thread());
+
     QLIST_FOREACH(c, &bs->parents, next_parent) {
         if (!bdrv_parent_can_set_aio_context(c, ctx, ignore, errp)) {
             return false;
@@ -7084,6 +7200,8 @@ int bdrv_child_try_set_aio_context(BlockDriverState *bs, AioContext *ctx,
     GSList *ignore;
     bool ret;
 
+    assert(qemu_in_main_thread());
+
     ignore = ignore_child ? g_slist_prepend(NULL, ignore_child) : NULL;
     ret = bdrv_can_set_aio_context(bs, ctx, &ignore, errp);
     g_slist_free(ignore);
@@ -7102,6 +7220,7 @@ int bdrv_child_try_set_aio_context(BlockDriverState *bs, AioContext *ctx,
 int bdrv_try_set_aio_context(BlockDriverState *bs, AioContext *ctx,
                              Error **errp)
 {
+    assert(qemu_in_main_thread());
     return bdrv_child_try_set_aio_context(bs, ctx, NULL, errp);
 }
 
@@ -7115,6 +7234,7 @@ void bdrv_add_aio_context_notifier(BlockDriverState *bs,
         .detach_aio_context   = detach_aio_context,
         .opaque               = opaque
     };
+    assert(qemu_in_main_thread());
 
     QLIST_INSERT_HEAD(&bs->aio_notifiers, ban, list);
 }
@@ -7126,6 +7246,7 @@ void bdrv_remove_aio_context_notifier(BlockDriverState *bs,
                                       void *opaque)
 {
     BdrvAioNotifier *ban, *ban_next;
+    assert(qemu_in_main_thread());
 
     QLIST_FOREACH_SAFE(ban, &bs->aio_notifiers, list, ban_next) {
         if (ban->attached_aio_context == attached_aio_context &&
@@ -7150,6 +7271,7 @@ int bdrv_amend_options(BlockDriverState *bs, QemuOpts *opts,
                        bool force,
                        Error **errp)
 {
+    assert(qemu_in_main_thread());
     if (!bs->drv) {
         error_setg(errp, "Node is ejected");
         return -ENOMEDIUM;
@@ -7220,6 +7342,8 @@ BlockDriverState *check_to_replace_node(BlockDriverState *parent_bs,
     BlockDriverState *to_replace_bs = bdrv_find_node(node_name);
     AioContext *aio_context;
 
+    assert(qemu_in_main_thread());
+
     if (!to_replace_bs) {
         error_setg(errp, "Failed to find node with node-name='%s'", node_name);
         return NULL;
@@ -7381,6 +7505,8 @@ void bdrv_refresh_filename(BlockDriverState *bs)
     bool generate_json_filename; /* Whether our default implementation should
                                     fill exact_filename (false) or not (true) */
 
+    assert(qemu_in_main_thread());
+
     if (!drv) {
         return;
     }
@@ -7503,6 +7629,8 @@ char *bdrv_dirname(BlockDriverState *bs, Error **errp)
     BlockDriver *drv = bs->drv;
     BlockDriverState *child_bs;
 
+    assert(qemu_in_main_thread());
+
     if (!drv) {
         error_setg(errp, "Node '%s' is ejected", bs->node_name);
         return NULL;
@@ -7534,7 +7662,7 @@ char *bdrv_dirname(BlockDriverState *bs, Error **errp)
 void bdrv_add_child(BlockDriverState *parent_bs, BlockDriverState *child_bs,
                     Error **errp)
 {
-
+    assert(qemu_in_main_thread());
     if (!parent_bs->drv || !parent_bs->drv->bdrv_add_child) {
         error_setg(errp, "The node %s does not support adding a child",
                    bdrv_get_device_or_node_name(parent_bs));
@@ -7554,6 +7682,7 @@ void bdrv_del_child(BlockDriverState *parent_bs, BdrvChild *child, Error **errp)
 {
     BdrvChild *tmp;
 
+    assert(qemu_in_main_thread());
     if (!parent_bs->drv || !parent_bs->drv->bdrv_del_child) {
         error_setg(errp, "The node %s does not support removing a child",
                    bdrv_get_device_or_node_name(parent_bs));
@@ -7581,6 +7710,7 @@ int bdrv_make_empty(BdrvChild *c, Error **errp)
     BlockDriver *drv = c->bs->drv;
     int ret;
 
+    assert(qemu_in_main_thread());
     assert(c->perm & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED));
 
     if (!drv->bdrv_make_empty) {
diff --git a/block/commit.c b/block/commit.c
index 10cc5ff451..45a414a19b 100644
--- a/block/commit.c
+++ b/block/commit.c
@@ -433,6 +433,8 @@ int bdrv_commit(BlockDriverState *bs)
     QEMU_AUTO_VFREE uint8_t *buf = NULL;
     Error *local_err = NULL;
 
+    assert(qemu_in_main_thread());
+
     if (!drv)
         return -ENOMEDIUM;
 
diff --git a/block/io.c b/block/io.c
index bb0a254def..c5d7f8495e 100644
--- a/block/io.c
+++ b/block/io.c
@@ -164,6 +164,8 @@ void bdrv_refresh_limits(BlockDriverState *bs, Transaction *tran, Error **errp)
     BdrvChild *c;
     bool have_limits;
 
+    assert(qemu_in_main_thread());
+
     if (tran) {
         BdrvRefreshLimitsState *s = g_new(BdrvRefreshLimitsState, 1);
         *s = (BdrvRefreshLimitsState) {
@@ -544,6 +546,7 @@ void bdrv_drained_end(BlockDriverState *bs)
 
 void bdrv_drained_end_no_poll(BlockDriverState *bs, int *drained_end_counter)
 {
+    assert(qemu_in_main_thread());
     bdrv_do_drained_end(bs, false, NULL, false, drained_end_counter);
 }
 
@@ -586,12 +589,14 @@ void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent)
 void coroutine_fn bdrv_co_drain(BlockDriverState *bs)
 {
     assert(qemu_in_coroutine());
+    assert(qemu_in_main_thread());
     bdrv_drained_begin(bs);
     bdrv_drained_end(bs);
 }
 
 void bdrv_drain(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     bdrv_drained_begin(bs);
     bdrv_drained_end(bs);
 }
@@ -612,6 +617,7 @@ static bool bdrv_drain_all_poll(void)
 {
     BlockDriverState *bs = NULL;
     bool result = false;
+    assert(qemu_in_main_thread());
 
     /* bdrv_drain_poll() can't make changes to the graph and we are holding the
      * main AioContext lock, so iterating bdrv_next_all_states() is safe. */
@@ -640,6 +646,7 @@ static bool bdrv_drain_all_poll(void)
 void bdrv_drain_all_begin(void)
 {
     BlockDriverState *bs = NULL;
+    assert(qemu_in_main_thread());
 
     if (qemu_in_coroutine()) {
         bdrv_co_yield_to_drain(NULL, true, false, NULL, true, true, NULL);
@@ -696,6 +703,7 @@ void bdrv_drain_all_end(void)
 {
     BlockDriverState *bs = NULL;
     int drained_end_counter = 0;
+    assert(qemu_in_main_thread());
 
     /*
      * bdrv queue is managed by record/replay,
@@ -723,6 +731,7 @@ void bdrv_drain_all_end(void)
 
 void bdrv_drain_all(void)
 {
+    assert(qemu_in_main_thread());
     bdrv_drain_all_begin();
     bdrv_drain_all_end();
 }
@@ -2345,6 +2354,8 @@ int bdrv_flush_all(void)
     BlockDriverState *bs = NULL;
     int result = 0;
 
+    assert(qemu_in_main_thread());
+
     /*
      * bdrv queue is managed by record/replay,
      * creating new flush request for stopping
@@ -2731,6 +2742,7 @@ int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base,
 int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes,
                       int64_t *pnum, int64_t *map, BlockDriverState **file)
 {
+    assert(qemu_in_main_thread());
     return bdrv_block_status_above(bs, bdrv_filter_or_cow_bs(bs),
                                    offset, bytes, pnum, map, file);
 }
@@ -2800,6 +2812,7 @@ int bdrv_is_allocated_above(BlockDriverState *top,
                             int64_t bytes, int64_t *pnum)
 {
     int depth;
+
     int ret = bdrv_common_block_status_above(top, base, include_base, false,
                                              offset, bytes, pnum, NULL, NULL,
                                              &depth);
@@ -2878,6 +2891,7 @@ bdrv_co_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos)
 int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
                       int64_t pos, int size)
 {
+    assert(qemu_in_main_thread());
     QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, size);
     int ret = bdrv_writev_vmstate(bs, &qiov, pos);
 
@@ -2887,6 +2901,7 @@ int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
 int bdrv_load_vmstate(BlockDriverState *bs, uint8_t *buf,
                       int64_t pos, int size)
 {
+    assert(qemu_in_main_thread());
     QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, size);
     int ret = bdrv_readv_vmstate(bs, &qiov, pos);
 
@@ -2898,6 +2913,7 @@ int bdrv_load_vmstate(BlockDriverState *bs, uint8_t *buf,
 
 void bdrv_aio_cancel(BlockAIOCB *acb)
 {
+    assert(qemu_in_main_thread());
     qemu_aio_ref(acb);
     bdrv_aio_cancel_async(acb);
     while (acb->refcnt > 1) {
@@ -2922,6 +2938,7 @@ void bdrv_aio_cancel(BlockAIOCB *acb)
  * In either case the completion callback must be called. */
 void bdrv_aio_cancel_async(BlockAIOCB *acb)
 {
+    assert(qemu_in_main_thread());
     if (acb->aiocb_info->cancel_async) {
         acb->aiocb_info->cancel_async(acb);
     }
@@ -3292,6 +3309,7 @@ void bdrv_register_buf(BlockDriverState *bs, void *host, size_t size)
 {
     BdrvChild *child;
 
+    assert(qemu_in_main_thread());
     if (bs->drv && bs->drv->bdrv_register_buf) {
         bs->drv->bdrv_register_buf(bs, host, size);
     }
@@ -3304,6 +3322,7 @@ void bdrv_unregister_buf(BlockDriverState *bs, void *host)
 {
     BdrvChild *child;
 
+    assert(qemu_in_main_thread());
     if (bs->drv && bs->drv->bdrv_unregister_buf) {
         bs->drv->bdrv_unregister_buf(bs, host);
     }
@@ -3575,6 +3594,7 @@ out:
 
 void bdrv_cancel_in_flight(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     if (!bs || !bs->drv) {
         return;
     }
diff --git a/blockdev.c b/blockdev.c
index b35072644e..ae322ed10e 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -690,6 +690,7 @@ void blockdev_close_all_bdrv_states(void)
 /* Iterates over the list of monitor-owned BlockDriverStates */
 BlockDriverState *bdrv_next_monitor_owned(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     return bs ? QTAILQ_NEXT(bs, monitor_list)
               : QTAILQ_FIRST(&monitor_bdrv_states);
 }
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 04/25] include/sysemu/block-backend: split header into I/O and global state (GS) API
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (2 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 03/25] assertions for block " Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-21 14:28   ` Stefan Hajnoczi
  2021-10-12  8:48 ` [PATCH v3 05/25] block/block-backend.c: assertions for block-backend Emanuele Giuseppe Esposito
                   ` (20 subsequent siblings)
  24 siblings, 1 reply; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

Similarly to the previous patches, split block-backend.h
in block-backend-io.h and block-backend-global-state.h

In addition, remove "block/block.h" include as it seems
it is not necessary anymore, together with "qemu/iov.h"

block-backend-common.h contains the structures shared between
the two headers, and the functions that can't be categorized as
I/O or global state.

Assertions are added in the next patch.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 block/block-backend.c                       |   9 +-
 include/sysemu/block-backend-common.h       |  74 ++++++
 include/sysemu/block-backend-global-state.h | 122 +++++++++
 include/sysemu/block-backend-io.h           | 134 ++++++++++
 include/sysemu/block-backend.h              | 264 +-------------------
 5 files changed, 339 insertions(+), 264 deletions(-)
 create mode 100644 include/sysemu/block-backend-common.h
 create mode 100644 include/sysemu/block-backend-global-state.h
 create mode 100644 include/sysemu/block-backend-io.h

diff --git a/block/block-backend.c b/block/block-backend.c
index ba2b5ebb10..d8d99f4396 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -78,6 +78,7 @@ struct BlockBackend {
     bool allow_aio_context_change;
     bool allow_write_beyond_eof;
 
+    /* Protected by BQL lock */
     NotifierList remove_bs_notifiers, insert_bs_notifiers;
     QLIST_HEAD(, BlockBackendAioNotifier) aio_notifiers;
 
@@ -110,12 +111,14 @@ static const AIOCBInfo block_backend_aiocb_info = {
 static void drive_info_del(DriveInfo *dinfo);
 static BlockBackend *bdrv_first_blk(BlockDriverState *bs);
 
-/* All BlockBackends */
+/* All BlockBackends. Protected by BQL lock. */
 static QTAILQ_HEAD(, BlockBackend) block_backends =
     QTAILQ_HEAD_INITIALIZER(block_backends);
 
-/* All BlockBackends referenced by the monitor and which are iterated through by
- * blk_next() */
+/*
+ * All BlockBackends referenced by the monitor and which are iterated through by
+ * blk_next(). Protected by BQL lock.
+ */
 static QTAILQ_HEAD(, BlockBackend) monitor_block_backends =
     QTAILQ_HEAD_INITIALIZER(monitor_block_backends);
 
diff --git a/include/sysemu/block-backend-common.h b/include/sysemu/block-backend-common.h
new file mode 100644
index 0000000000..52ff6a4d26
--- /dev/null
+++ b/include/sysemu/block-backend-common.h
@@ -0,0 +1,74 @@
+/*
+ * QEMU Block backends
+ *
+ * Copyright (C) 2014-2016 Red Hat, Inc.
+ *
+ * Authors:
+ *  Markus Armbruster <armbru@redhat.com>,
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1
+ * or later.  See the COPYING.LIB file in the top-level directory.
+ */
+
+#ifndef BLOCK_BACKEND_COMMON_H
+#define BLOCK_BACKEND_COMMON_H
+
+#include "block/throttle-groups.h"
+
+/* Callbacks for block device models */
+typedef struct BlockDevOps {
+    /*
+     * Runs when virtual media changed (monitor commands eject, change)
+     * Argument load is true on load and false on eject.
+     * Beware: doesn't run when a host device's physical media
+     * changes.  Sure would be useful if it did.
+     * Device models with removable media must implement this callback.
+     */
+    void (*change_media_cb)(void *opaque, bool load, Error **errp);
+    /*
+     * Runs when an eject request is issued from the monitor, the tray
+     * is closed, and the medium is locked.
+     * Device models that do not implement is_medium_locked will not need
+     * this callback.  Device models that can lock the medium or tray might
+     * want to implement the callback and unlock the tray when "force" is
+     * true, even if they do not support eject requests.
+     */
+    void (*eject_request_cb)(void *opaque, bool force);
+    /*
+     * Is the virtual tray open?
+     * Device models implement this only when the device has a tray.
+     */
+    bool (*is_tray_open)(void *opaque);
+    /*
+     * Is the virtual medium locked into the device?
+     * Device models implement this only when device has such a lock.
+     */
+    bool (*is_medium_locked)(void *opaque);
+    /*
+     * Runs when the size changed (e.g. monitor command block_resize)
+     */
+    void (*resize_cb)(void *opaque);
+    /*
+     * Runs when the backend receives a drain request.
+     */
+    void (*drained_begin)(void *opaque);
+    /*
+     * Runs when the backend's last drain request ends.
+     */
+    void (*drained_end)(void *opaque);
+    /*
+     * Is the device still busy?
+     */
+    bool (*drained_poll)(void *opaque);
+} BlockDevOps;
+
+/*
+ * This struct is embedded in (the private) BlockBackend struct and contains
+ * fields that must be public. This is in particular for QLIST_ENTRY() and
+ * friends so that BlockBackends can be kept in lists outside block-backend.c
+ */
+typedef struct BlockBackendPublic {
+    ThrottleGroupMember throttle_group_member;
+} BlockBackendPublic;
+
+#endif /* BLOCK_BACKEND_COMMON_H */
diff --git a/include/sysemu/block-backend-global-state.h b/include/sysemu/block-backend-global-state.h
new file mode 100644
index 0000000000..4001b1c02a
--- /dev/null
+++ b/include/sysemu/block-backend-global-state.h
@@ -0,0 +1,122 @@
+/*
+ * QEMU Block backends
+ *
+ * Copyright (C) 2014-2016 Red Hat, Inc.
+ *
+ * Authors:
+ *  Markus Armbruster <armbru@redhat.com>,
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1
+ * or later.  See the COPYING.LIB file in the top-level directory.
+ */
+
+#ifndef BLOCK_BACKEND_GS_H
+#define BLOCK_BACKEND_GS_H
+
+#include "block-backend-common.h"
+
+/*
+ * Global state (GS) API. These functions run under the BQL lock.
+ *
+ * See include/block/block-global-state.h for more information about
+ * the GS API.
+ */
+
+BlockBackend *blk_new(AioContext *ctx, uint64_t perm, uint64_t shared_perm);
+BlockBackend *blk_new_with_bs(BlockDriverState *bs, uint64_t perm,
+                              uint64_t shared_perm, Error **errp);
+BlockBackend *blk_new_open(const char *filename, const char *reference,
+                           QDict *options, int flags, Error **errp);
+int blk_get_refcnt(BlockBackend *blk);
+void blk_ref(BlockBackend *blk);
+void blk_unref(BlockBackend *blk);
+void blk_remove_all_bs(void);
+const char *blk_name(const BlockBackend *blk);
+BlockBackend *blk_by_name(const char *name);
+BlockBackend *blk_next(BlockBackend *blk);
+BlockBackend *blk_all_next(BlockBackend *blk);
+bool monitor_add_blk(BlockBackend *blk, const char *name, Error **errp);
+void monitor_remove_blk(BlockBackend *blk);
+
+BlockBackendPublic *blk_get_public(BlockBackend *blk);
+BlockBackend *blk_by_public(BlockBackendPublic *public);
+
+void blk_remove_bs(BlockBackend *blk);
+int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp);
+bool bdrv_has_blk(BlockDriverState *bs);
+bool bdrv_is_root_node(BlockDriverState *bs);
+int blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
+                 Error **errp);
+void blk_get_perm(BlockBackend *blk, uint64_t *perm, uint64_t *shared_perm);
+
+void blk_iostatus_enable(BlockBackend *blk);
+bool blk_iostatus_is_enabled(const BlockBackend *blk);
+BlockDeviceIoStatus blk_iostatus(const BlockBackend *blk);
+void blk_iostatus_disable(BlockBackend *blk);
+void blk_iostatus_reset(BlockBackend *blk);
+void blk_iostatus_set_err(BlockBackend *blk, int error);
+int blk_attach_dev(BlockBackend *blk, DeviceState *dev);
+void blk_detach_dev(BlockBackend *blk, DeviceState *dev);
+DeviceState *blk_get_attached_dev(BlockBackend *blk);
+char *blk_get_attached_dev_id(BlockBackend *blk);
+BlockBackend *blk_by_dev(void *dev);
+BlockBackend *blk_by_qdev_id(const char *id, Error **errp);
+void blk_set_dev_ops(BlockBackend *blk, const BlockDevOps *ops, void *opaque);
+
+int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags);
+int64_t blk_nb_sectors(BlockBackend *blk);
+int blk_commit_all(void);
+void blk_drain(BlockBackend *blk);
+void blk_drain_all(void);
+void blk_set_on_error(BlockBackend *blk, BlockdevOnError on_read_error,
+                      BlockdevOnError on_write_error);
+bool blk_supports_write_perm(BlockBackend *blk);
+bool blk_is_sg(BlockBackend *blk);
+bool blk_enable_write_cache(BlockBackend *blk);
+void blk_set_enable_write_cache(BlockBackend *blk, bool wce);
+void blk_lock_medium(BlockBackend *blk, bool locked);
+void blk_eject(BlockBackend *blk, bool eject_flag);
+int blk_get_flags(BlockBackend *blk);
+void blk_set_guest_block_size(BlockBackend *blk, int align);
+bool blk_op_is_blocked(BlockBackend *blk, BlockOpType op, Error **errp);
+void blk_op_unblock(BlockBackend *blk, BlockOpType op, Error *reason);
+void blk_op_block_all(BlockBackend *blk, Error *reason);
+void blk_op_unblock_all(BlockBackend *blk, Error *reason);
+int blk_set_aio_context(BlockBackend *blk, AioContext *new_context,
+                        Error **errp);
+void blk_add_aio_context_notifier(BlockBackend *blk,
+        void (*attached_aio_context)(AioContext *new_context, void *opaque),
+        void (*detach_aio_context)(void *opaque), void *opaque);
+void blk_remove_aio_context_notifier(BlockBackend *blk,
+                                     void (*attached_aio_context)(AioContext *,
+                                                                  void *),
+                                     void (*detach_aio_context)(void *),
+                                     void *opaque);
+void blk_add_remove_bs_notifier(BlockBackend *blk, Notifier *notify);
+void blk_add_insert_bs_notifier(BlockBackend *blk, Notifier *notify);
+BlockBackendRootState *blk_get_root_state(BlockBackend *blk);
+void blk_update_root_state(BlockBackend *blk);
+bool blk_get_detect_zeroes_from_root_state(BlockBackend *blk);
+int blk_get_open_flags_from_root_state(BlockBackend *blk);
+
+int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf,
+                     int64_t pos, int size);
+int blk_load_vmstate(BlockBackend *blk, uint8_t *buf, int64_t pos, int size);
+int blk_probe_blocksizes(BlockBackend *blk, BlockSizes *bsz);
+int blk_probe_geometry(BlockBackend *blk, HDGeometry *geo);
+BlockAIOCB *blk_abort_aio_request(BlockBackend *blk,
+                                  BlockCompletionFunc *cb,
+                                  void *opaque, int ret);
+
+void blk_set_io_limits(BlockBackend *blk, ThrottleConfig *cfg);
+void blk_io_limits_disable(BlockBackend *blk);
+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);
+
+const BdrvChild *blk_root(BlockBackend *blk);
+
+#endif /* BLOCK_BACKEND_GS_H */
diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h
new file mode 100644
index 0000000000..ba5d8118b1
--- /dev/null
+++ b/include/sysemu/block-backend-io.h
@@ -0,0 +1,134 @@
+/*
+ * QEMU Block backends
+ *
+ * Copyright (C) 2014-2016 Red Hat, Inc.
+ *
+ * Authors:
+ *  Markus Armbruster <armbru@redhat.com>,
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1
+ * or later.  See the COPYING.LIB file in the top-level directory.
+ */
+
+#ifndef BLOCK_BACKEND_IO_H
+#define BLOCK_BACKEND_IO_H
+
+#include "block-backend-common.h"
+
+/*
+ * I/O API functions. These functions are thread-safe.
+ *
+ * See include/block/block-io.h for more information about
+ * the I/O API.
+ */
+
+BlockDriverState *blk_bs(BlockBackend *blk);
+
+int blk_replace_bs(BlockBackend *blk, BlockDriverState *new_bs, Error **errp);
+
+void blk_set_allow_write_beyond_eof(BlockBackend *blk, bool allow);
+void blk_set_allow_aio_context_change(BlockBackend *blk, bool allow);
+void blk_set_disable_request_queuing(BlockBackend *blk, bool disable);
+
+int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int bytes);
+int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int bytes,
+               BdrvRequestFlags flags);
+int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset,
+                               unsigned int bytes, QEMUIOVector *qiov,
+                               BdrvRequestFlags flags);
+int coroutine_fn blk_co_pwritev_part(BlockBackend *blk, int64_t offset,
+                                     unsigned int bytes,
+                                     QEMUIOVector *qiov, size_t qiov_offset,
+                                     BdrvRequestFlags flags);
+int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset,
+                               unsigned int bytes, QEMUIOVector *qiov,
+                               BdrvRequestFlags flags);
+
+static inline int coroutine_fn blk_co_pread(BlockBackend *blk, int64_t offset,
+                                            unsigned int bytes, void *buf,
+                                            BdrvRequestFlags flags)
+{
+    QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes);
+
+    return blk_co_preadv(blk, offset, bytes, &qiov, flags);
+}
+
+static inline int coroutine_fn blk_co_pwrite(BlockBackend *blk, int64_t offset,
+                                             unsigned int bytes, void *buf,
+                                             BdrvRequestFlags flags)
+{
+    QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes);
+
+    return blk_co_pwritev(blk, offset, bytes, &qiov, flags);
+}
+
+BlockAIOCB *blk_aio_pwrite_zeroes(BlockBackend *blk, int64_t offset,
+                                  int bytes, BdrvRequestFlags flags,
+                                  BlockCompletionFunc *cb, void *opaque);
+
+BlockAIOCB *blk_aio_preadv(BlockBackend *blk, int64_t offset,
+                           QEMUIOVector *qiov, BdrvRequestFlags flags,
+                           BlockCompletionFunc *cb, void *opaque);
+BlockAIOCB *blk_aio_pwritev(BlockBackend *blk, int64_t offset,
+                            QEMUIOVector *qiov, BdrvRequestFlags flags,
+                            BlockCompletionFunc *cb, void *opaque);
+BlockAIOCB *blk_aio_flush(BlockBackend *blk,
+                          BlockCompletionFunc *cb, void *opaque);
+BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk, int64_t offset, int bytes,
+                             BlockCompletionFunc *cb, void *opaque);
+void blk_aio_cancel(BlockAIOCB *acb);
+void blk_aio_cancel_async(BlockAIOCB *acb);
+int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf);
+BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
+                          BlockCompletionFunc *cb, void *opaque);
+int blk_co_pdiscard(BlockBackend *blk, int64_t offset, int bytes);
+int blk_co_flush(BlockBackend *blk);
+int blk_flush(BlockBackend *blk);
+void blk_inc_in_flight(BlockBackend *blk);
+void blk_dec_in_flight(BlockBackend *blk);
+bool blk_is_inserted(BlockBackend *blk);
+bool blk_is_available(BlockBackend *blk);
+int64_t blk_getlength(BlockBackend *blk);
+void blk_get_geometry(BlockBackend *blk, uint64_t *nb_sectors_ptr);
+void *blk_try_blockalign(BlockBackend *blk, size_t size);
+void *blk_blockalign(BlockBackend *blk, size_t size);
+bool blk_is_writable(BlockBackend *blk);
+BlockdevOnError blk_get_on_error(BlockBackend *blk, bool is_read);
+BlockErrorAction blk_get_error_action(BlockBackend *blk, bool is_read,
+                                      int error);
+void blk_error_action(BlockBackend *blk, BlockErrorAction action,
+                      bool is_read, int error);
+int blk_get_max_iov(BlockBackend *blk);
+int blk_get_max_hw_iov(BlockBackend *blk);
+
+void blk_invalidate_cache(BlockBackend *blk, Error **errp);
+
+void blk_io_plug(BlockBackend *blk);
+void blk_io_unplug(BlockBackend *blk);
+AioContext *blk_get_aio_context(BlockBackend *blk);
+BlockAcctStats *blk_get_stats(BlockBackend *blk);
+void *blk_aio_get(const AIOCBInfo *aiocb_info, BlockBackend *blk,
+                  BlockCompletionFunc *cb, void *opaque);
+int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, const void *buf,
+                          int bytes);
+int blk_pdiscard(BlockBackend *blk, int64_t offset, int bytes);
+int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset,
+                      int bytes, BdrvRequestFlags flags);
+int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset,
+                                      int bytes, BdrvRequestFlags flags);
+int blk_truncate(BlockBackend *blk, int64_t offset, bool exact,
+                 PreallocMode prealloc, BdrvRequestFlags flags, Error **errp);
+
+uint32_t blk_get_request_alignment(BlockBackend *blk);
+uint32_t blk_get_max_transfer(BlockBackend *blk);
+uint64_t blk_get_max_hw_transfer(BlockBackend *blk);
+
+int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in,
+                                   BlockBackend *blk_out, int64_t off_out,
+                                   int bytes, BdrvRequestFlags read_flags,
+                                   BdrvRequestFlags write_flags);
+
+
+int blk_make_empty(BlockBackend *blk, Error **errp);
+
+#endif /* BLOCK_BACKEND_IO_H */
diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h
index 82bae55161..038be9fc40 100644
--- a/include/sysemu/block-backend.h
+++ b/include/sysemu/block-backend.h
@@ -13,267 +13,9 @@
 #ifndef BLOCK_BACKEND_H
 #define BLOCK_BACKEND_H
 
-#include "qemu/iov.h"
-#include "block/throttle-groups.h"
+#include "block-backend-global-state.h"
+#include "block-backend-io.h"
 
-/*
- * TODO Have to include block/block.h for a bunch of block layer
- * types.  Unfortunately, this pulls in the whole BlockDriverState
- * API, which we don't want used by many BlockBackend users.  Some of
- * the types belong here, and the rest should be split into a common
- * header and one for the BlockDriverState API.
- */
-#include "block/block.h"
-
-/* Callbacks for block device models */
-typedef struct BlockDevOps {
-    /*
-     * Runs when virtual media changed (monitor commands eject, change)
-     * Argument load is true on load and false on eject.
-     * Beware: doesn't run when a host device's physical media
-     * changes.  Sure would be useful if it did.
-     * Device models with removable media must implement this callback.
-     */
-    void (*change_media_cb)(void *opaque, bool load, Error **errp);
-    /*
-     * Runs when an eject request is issued from the monitor, the tray
-     * is closed, and the medium is locked.
-     * Device models that do not implement is_medium_locked will not need
-     * this callback.  Device models that can lock the medium or tray might
-     * want to implement the callback and unlock the tray when "force" is
-     * true, even if they do not support eject requests.
-     */
-    void (*eject_request_cb)(void *opaque, bool force);
-    /*
-     * Is the virtual tray open?
-     * Device models implement this only when the device has a tray.
-     */
-    bool (*is_tray_open)(void *opaque);
-    /*
-     * Is the virtual medium locked into the device?
-     * Device models implement this only when device has such a lock.
-     */
-    bool (*is_medium_locked)(void *opaque);
-    /*
-     * Runs when the size changed (e.g. monitor command block_resize)
-     */
-    void (*resize_cb)(void *opaque);
-    /*
-     * Runs when the backend receives a drain request.
-     */
-    void (*drained_begin)(void *opaque);
-    /*
-     * Runs when the backend's last drain request ends.
-     */
-    void (*drained_end)(void *opaque);
-    /*
-     * Is the device still busy?
-     */
-    bool (*drained_poll)(void *opaque);
-} BlockDevOps;
-
-/* This struct is embedded in (the private) BlockBackend struct and contains
- * fields that must be public. This is in particular for QLIST_ENTRY() and
- * friends so that BlockBackends can be kept in lists outside block-backend.c
- * */
-typedef struct BlockBackendPublic {
-    ThrottleGroupMember throttle_group_member;
-} BlockBackendPublic;
-
-BlockBackend *blk_new(AioContext *ctx, uint64_t perm, uint64_t shared_perm);
-BlockBackend *blk_new_with_bs(BlockDriverState *bs, uint64_t perm,
-                              uint64_t shared_perm, Error **errp);
-BlockBackend *blk_new_open(const char *filename, const char *reference,
-                           QDict *options, int flags, Error **errp);
-int blk_get_refcnt(BlockBackend *blk);
-void blk_ref(BlockBackend *blk);
-void blk_unref(BlockBackend *blk);
-void blk_remove_all_bs(void);
-const char *blk_name(const BlockBackend *blk);
-BlockBackend *blk_by_name(const char *name);
-BlockBackend *blk_next(BlockBackend *blk);
-BlockBackend *blk_all_next(BlockBackend *blk);
-bool monitor_add_blk(BlockBackend *blk, const char *name, Error **errp);
-void monitor_remove_blk(BlockBackend *blk);
-
-BlockBackendPublic *blk_get_public(BlockBackend *blk);
-BlockBackend *blk_by_public(BlockBackendPublic *public);
-
-BlockDriverState *blk_bs(BlockBackend *blk);
-void blk_remove_bs(BlockBackend *blk);
-int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp);
-int blk_replace_bs(BlockBackend *blk, BlockDriverState *new_bs, Error **errp);
-bool bdrv_has_blk(BlockDriverState *bs);
-bool bdrv_is_root_node(BlockDriverState *bs);
-int blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
-                 Error **errp);
-void blk_get_perm(BlockBackend *blk, uint64_t *perm, uint64_t *shared_perm);
-
-void blk_set_allow_write_beyond_eof(BlockBackend *blk, bool allow);
-void blk_set_allow_aio_context_change(BlockBackend *blk, bool allow);
-void blk_set_disable_request_queuing(BlockBackend *blk, bool disable);
-void blk_iostatus_enable(BlockBackend *blk);
-bool blk_iostatus_is_enabled(const BlockBackend *blk);
-BlockDeviceIoStatus blk_iostatus(const BlockBackend *blk);
-void blk_iostatus_disable(BlockBackend *blk);
-void blk_iostatus_reset(BlockBackend *blk);
-void blk_iostatus_set_err(BlockBackend *blk, int error);
-int blk_attach_dev(BlockBackend *blk, DeviceState *dev);
-void blk_detach_dev(BlockBackend *blk, DeviceState *dev);
-DeviceState *blk_get_attached_dev(BlockBackend *blk);
-char *blk_get_attached_dev_id(BlockBackend *blk);
-BlockBackend *blk_by_dev(void *dev);
-BlockBackend *blk_by_qdev_id(const char *id, Error **errp);
-void blk_set_dev_ops(BlockBackend *blk, const BlockDevOps *ops, void *opaque);
-int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset,
-                               unsigned int bytes, QEMUIOVector *qiov,
-                               BdrvRequestFlags flags);
-int coroutine_fn blk_co_pwritev_part(BlockBackend *blk, int64_t offset,
-                                     unsigned int bytes,
-                                     QEMUIOVector *qiov, size_t qiov_offset,
-                                     BdrvRequestFlags flags);
-int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset,
-                               unsigned int bytes, QEMUIOVector *qiov,
-                               BdrvRequestFlags flags);
-
-static inline int coroutine_fn blk_co_pread(BlockBackend *blk, int64_t offset,
-                                            unsigned int bytes, void *buf,
-                                            BdrvRequestFlags flags)
-{
-    QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes);
-
-    return blk_co_preadv(blk, offset, bytes, &qiov, flags);
-}
-
-static inline int coroutine_fn blk_co_pwrite(BlockBackend *blk, int64_t offset,
-                                             unsigned int bytes, void *buf,
-                                             BdrvRequestFlags flags)
-{
-    QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes);
-
-    return blk_co_pwritev(blk, offset, bytes, &qiov, flags);
-}
-
-int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset,
-                      int bytes, BdrvRequestFlags flags);
-BlockAIOCB *blk_aio_pwrite_zeroes(BlockBackend *blk, int64_t offset,
-                                  int bytes, BdrvRequestFlags flags,
-                                  BlockCompletionFunc *cb, void *opaque);
-int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags);
-int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int bytes);
-int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int bytes,
-               BdrvRequestFlags flags);
-int64_t blk_getlength(BlockBackend *blk);
-void blk_get_geometry(BlockBackend *blk, uint64_t *nb_sectors_ptr);
-int64_t blk_nb_sectors(BlockBackend *blk);
-BlockAIOCB *blk_aio_preadv(BlockBackend *blk, int64_t offset,
-                           QEMUIOVector *qiov, BdrvRequestFlags flags,
-                           BlockCompletionFunc *cb, void *opaque);
-BlockAIOCB *blk_aio_pwritev(BlockBackend *blk, int64_t offset,
-                            QEMUIOVector *qiov, BdrvRequestFlags flags,
-                            BlockCompletionFunc *cb, void *opaque);
-BlockAIOCB *blk_aio_flush(BlockBackend *blk,
-                          BlockCompletionFunc *cb, void *opaque);
-BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk, int64_t offset, int bytes,
-                             BlockCompletionFunc *cb, void *opaque);
-void blk_aio_cancel(BlockAIOCB *acb);
-void blk_aio_cancel_async(BlockAIOCB *acb);
-int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf);
-BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
-                          BlockCompletionFunc *cb, void *opaque);
-int blk_co_pdiscard(BlockBackend *blk, int64_t offset, int bytes);
-int blk_co_flush(BlockBackend *blk);
-int blk_flush(BlockBackend *blk);
-int blk_commit_all(void);
-void blk_inc_in_flight(BlockBackend *blk);
-void blk_dec_in_flight(BlockBackend *blk);
-void blk_drain(BlockBackend *blk);
-void blk_drain_all(void);
-void blk_set_on_error(BlockBackend *blk, BlockdevOnError on_read_error,
-                      BlockdevOnError on_write_error);
-BlockdevOnError blk_get_on_error(BlockBackend *blk, bool is_read);
-BlockErrorAction blk_get_error_action(BlockBackend *blk, bool is_read,
-                                      int error);
-void blk_error_action(BlockBackend *blk, BlockErrorAction action,
-                      bool is_read, int error);
-bool blk_supports_write_perm(BlockBackend *blk);
-bool blk_is_writable(BlockBackend *blk);
-bool blk_is_sg(BlockBackend *blk);
-bool blk_enable_write_cache(BlockBackend *blk);
-void blk_set_enable_write_cache(BlockBackend *blk, bool wce);
-void blk_invalidate_cache(BlockBackend *blk, Error **errp);
-bool blk_is_inserted(BlockBackend *blk);
-bool blk_is_available(BlockBackend *blk);
-void blk_lock_medium(BlockBackend *blk, bool locked);
-void blk_eject(BlockBackend *blk, bool eject_flag);
-int blk_get_flags(BlockBackend *blk);
-uint32_t blk_get_request_alignment(BlockBackend *blk);
-uint32_t blk_get_max_transfer(BlockBackend *blk);
-uint64_t blk_get_max_hw_transfer(BlockBackend *blk);
-int blk_get_max_iov(BlockBackend *blk);
-int blk_get_max_hw_iov(BlockBackend *blk);
-void blk_set_guest_block_size(BlockBackend *blk, int align);
-void *blk_try_blockalign(BlockBackend *blk, size_t size);
-void *blk_blockalign(BlockBackend *blk, size_t size);
-bool blk_op_is_blocked(BlockBackend *blk, BlockOpType op, Error **errp);
-void blk_op_unblock(BlockBackend *blk, BlockOpType op, Error *reason);
-void blk_op_block_all(BlockBackend *blk, Error *reason);
-void blk_op_unblock_all(BlockBackend *blk, Error *reason);
-AioContext *blk_get_aio_context(BlockBackend *blk);
-int blk_set_aio_context(BlockBackend *blk, AioContext *new_context,
-                        Error **errp);
-void blk_add_aio_context_notifier(BlockBackend *blk,
-        void (*attached_aio_context)(AioContext *new_context, void *opaque),
-        void (*detach_aio_context)(void *opaque), void *opaque);
-void blk_remove_aio_context_notifier(BlockBackend *blk,
-                                     void (*attached_aio_context)(AioContext *,
-                                                                  void *),
-                                     void (*detach_aio_context)(void *),
-                                     void *opaque);
-void blk_add_remove_bs_notifier(BlockBackend *blk, Notifier *notify);
-void blk_add_insert_bs_notifier(BlockBackend *blk, Notifier *notify);
-void blk_io_plug(BlockBackend *blk);
-void blk_io_unplug(BlockBackend *blk);
-BlockAcctStats *blk_get_stats(BlockBackend *blk);
-BlockBackendRootState *blk_get_root_state(BlockBackend *blk);
-void blk_update_root_state(BlockBackend *blk);
-bool blk_get_detect_zeroes_from_root_state(BlockBackend *blk);
-int blk_get_open_flags_from_root_state(BlockBackend *blk);
-
-void *blk_aio_get(const AIOCBInfo *aiocb_info, BlockBackend *blk,
-                  BlockCompletionFunc *cb, void *opaque);
-int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset,
-                                      int bytes, BdrvRequestFlags flags);
-int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, const void *buf,
-                          int bytes);
-int blk_truncate(BlockBackend *blk, int64_t offset, bool exact,
-                 PreallocMode prealloc, BdrvRequestFlags flags, Error **errp);
-int blk_pdiscard(BlockBackend *blk, int64_t offset, int bytes);
-int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf,
-                     int64_t pos, int size);
-int blk_load_vmstate(BlockBackend *blk, uint8_t *buf, int64_t pos, int size);
-int blk_probe_blocksizes(BlockBackend *blk, BlockSizes *bsz);
-int blk_probe_geometry(BlockBackend *blk, HDGeometry *geo);
-BlockAIOCB *blk_abort_aio_request(BlockBackend *blk,
-                                  BlockCompletionFunc *cb,
-                                  void *opaque, int ret);
-
-void blk_set_io_limits(BlockBackend *blk, ThrottleConfig *cfg);
-void blk_io_limits_disable(BlockBackend *blk);
-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);
-
-int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in,
-                                   BlockBackend *blk_out, int64_t off_out,
-                                   int bytes, BdrvRequestFlags read_flags,
-                                   BdrvRequestFlags write_flags);
-
-const BdrvChild *blk_root(BlockBackend *blk);
-
-int blk_make_empty(BlockBackend *blk, Error **errp);
+/* DO NOT ADD ANYTHING IN HERE. USE ONE OF THE HEADERS INCLUDED ABOVE */
 
 #endif
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 05/25] block/block-backend.c: assertions for block-backend
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (3 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 04/25] include/sysemu/block-backend: split header into I/O and global state (GS) API Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-12  8:48 ` [PATCH v3 06/25] include/block/block_int: split header into I/O and global state API Emanuele Giuseppe Esposito
                   ` (19 subsequent siblings)
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

All the global state (GS) API functions will check that
qemu_in_main_thread() returns true. If not, it means
that the safety of BQL cannot be guaranteed, and
they need to be moved to I/O.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block/block-backend.c  | 90 +++++++++++++++++++++++++++++++++++++++++-
 softmmu/qdev-monitor.c |  2 +
 2 files changed, 91 insertions(+), 1 deletion(-)

diff --git a/block/block-backend.c b/block/block-backend.c
index d8d99f4396..55aaaf7527 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -227,6 +227,7 @@ static void blk_root_activate(BdrvChild *child, Error **errp)
 
 void blk_set_force_allow_inactivate(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     blk->force_allow_inactivate = true;
 }
 
@@ -345,6 +346,8 @@ BlockBackend *blk_new(AioContext *ctx, uint64_t perm, uint64_t shared_perm)
 {
     BlockBackend *blk;
 
+    assert(qemu_in_main_thread());
+
     blk = g_new0(BlockBackend, 1);
     blk->refcnt = 1;
     blk->ctx = ctx;
@@ -382,6 +385,8 @@ BlockBackend *blk_new_with_bs(BlockDriverState *bs, uint64_t perm,
 {
     BlockBackend *blk = blk_new(bdrv_get_aio_context(bs), perm, shared_perm);
 
+    assert(qemu_in_main_thread());
+
     if (blk_insert_bs(blk, bs, errp) < 0) {
         blk_unref(blk);
         return NULL;
@@ -410,6 +415,8 @@ BlockBackend *blk_new_open(const char *filename, const char *reference,
     uint64_t perm = 0;
     uint64_t shared = BLK_PERM_ALL;
 
+    assert(qemu_in_main_thread());
+
     /*
      * blk_new_open() is mainly used in .bdrv_create implementations and the
      * tools where sharing isn't a major concern because the BDS stays private
@@ -487,6 +494,7 @@ static void drive_info_del(DriveInfo *dinfo)
 
 int blk_get_refcnt(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     return blk ? blk->refcnt : 0;
 }
 
@@ -497,6 +505,7 @@ int blk_get_refcnt(BlockBackend *blk)
 void blk_ref(BlockBackend *blk)
 {
     assert(blk->refcnt > 0);
+    assert(qemu_in_main_thread());
     blk->refcnt++;
 }
 
@@ -507,6 +516,7 @@ void blk_ref(BlockBackend *blk)
  */
 void blk_unref(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     if (blk) {
         assert(blk->refcnt > 0);
         if (blk->refcnt > 1) {
@@ -527,6 +537,7 @@ void blk_unref(BlockBackend *blk)
  */
 BlockBackend *blk_all_next(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     return blk ? QTAILQ_NEXT(blk, link)
                : QTAILQ_FIRST(&block_backends);
 }
@@ -535,6 +546,8 @@ void blk_remove_all_bs(void)
 {
     BlockBackend *blk = NULL;
 
+    assert(qemu_in_main_thread());
+
     while ((blk = blk_all_next(blk)) != NULL) {
         AioContext *ctx = blk_get_aio_context(blk);
 
@@ -558,6 +571,7 @@ void blk_remove_all_bs(void)
  */
 BlockBackend *blk_next(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     return blk ? QTAILQ_NEXT(blk, monitor_link)
                : QTAILQ_FIRST(&monitor_block_backends);
 }
@@ -624,6 +638,7 @@ static void bdrv_next_reset(BdrvNextIterator *it)
 
 BlockDriverState *bdrv_first(BdrvNextIterator *it)
 {
+    assert(qemu_in_main_thread());
     bdrv_next_reset(it);
     return bdrv_next(it);
 }
@@ -661,6 +676,7 @@ bool monitor_add_blk(BlockBackend *blk, const char *name, Error **errp)
 {
     assert(!blk->name);
     assert(name && name[0]);
+    assert(qemu_in_main_thread());
 
     if (!id_wellformed(name)) {
         error_setg(errp, "Invalid device name");
@@ -688,6 +704,8 @@ bool monitor_add_blk(BlockBackend *blk, const char *name, Error **errp)
  */
 void monitor_remove_blk(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
+
     if (!blk->name) {
         return;
     }
@@ -703,6 +721,7 @@ void monitor_remove_blk(BlockBackend *blk)
  */
 const char *blk_name(const BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     return blk->name ?: "";
 }
 
@@ -714,6 +733,7 @@ BlockBackend *blk_by_name(const char *name)
 {
     BlockBackend *blk = NULL;
 
+    assert(qemu_in_main_thread());
     assert(name);
     while ((blk = blk_next(blk)) != NULL) {
         if (!strcmp(name, blk->name)) {
@@ -748,6 +768,7 @@ static BlockBackend *bdrv_first_blk(BlockDriverState *bs)
  */
 bool bdrv_has_blk(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     return bdrv_first_blk(bs) != NULL;
 }
 
@@ -758,6 +779,7 @@ bool bdrv_is_root_node(BlockDriverState *bs)
 {
     BdrvChild *c;
 
+    assert(qemu_in_main_thread());
     QLIST_FOREACH(c, &bs->parents, next_parent) {
         if (c->klass != &child_root) {
             return false;
@@ -807,6 +829,7 @@ BlockBackend *blk_by_legacy_dinfo(DriveInfo *dinfo)
  */
 BlockBackendPublic *blk_get_public(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     return &blk->public;
 }
 
@@ -815,6 +838,7 @@ BlockBackendPublic *blk_get_public(BlockBackend *blk)
  */
 BlockBackend *blk_by_public(BlockBackendPublic *public)
 {
+    assert(qemu_in_main_thread());
     return container_of(public, BlockBackend, public);
 }
 
@@ -827,6 +851,8 @@ void blk_remove_bs(BlockBackend *blk)
     BlockDriverState *bs;
     BdrvChild *root;
 
+    assert(qemu_in_main_thread());
+
     notifier_list_notify(&blk->remove_bs_notifiers, blk);
     if (tgm->throttle_state) {
         bs = blk_bs(blk);
@@ -854,6 +880,7 @@ void blk_remove_bs(BlockBackend *blk)
 int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp)
 {
     ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
+    assert(qemu_in_main_thread());
     bdrv_ref(bs);
     blk->root = bdrv_root_attach_child(bs, "root", &child_root,
                                        BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY,
@@ -888,6 +915,7 @@ int blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
 {
     int ret;
 
+    assert(qemu_in_main_thread());
     if (blk->root && !blk->disable_perm) {
         ret = bdrv_child_try_set_perm(blk->root, perm, shared_perm, errp);
         if (ret < 0) {
@@ -903,6 +931,7 @@ int blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
 
 void blk_get_perm(BlockBackend *blk, uint64_t *perm, uint64_t *shared_perm)
 {
+    assert(qemu_in_main_thread());
     *perm = blk->perm;
     *shared_perm = blk->shared_perm;
 }
@@ -913,6 +942,7 @@ void blk_get_perm(BlockBackend *blk, uint64_t *perm, uint64_t *shared_perm)
  */
 int blk_attach_dev(BlockBackend *blk, DeviceState *dev)
 {
+    assert(qemu_in_main_thread());
     if (blk->dev) {
         return -EBUSY;
     }
@@ -938,6 +968,7 @@ int blk_attach_dev(BlockBackend *blk, DeviceState *dev)
 void blk_detach_dev(BlockBackend *blk, DeviceState *dev)
 {
     assert(blk->dev == dev);
+    assert(qemu_in_main_thread());
     blk->dev = NULL;
     blk->dev_ops = NULL;
     blk->dev_opaque = NULL;
@@ -951,6 +982,7 @@ void blk_detach_dev(BlockBackend *blk, DeviceState *dev)
  */
 DeviceState *blk_get_attached_dev(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     return blk->dev;
 }
 
@@ -959,6 +991,7 @@ DeviceState *blk_get_attached_dev(BlockBackend *blk)
 char *blk_get_attached_dev_id(BlockBackend *blk)
 {
     DeviceState *dev = blk->dev;
+    assert(qemu_in_main_thread());
 
     if (!dev) {
         return g_strdup("");
@@ -979,6 +1012,8 @@ BlockBackend *blk_by_dev(void *dev)
 {
     BlockBackend *blk = NULL;
 
+    assert(qemu_in_main_thread());
+
     assert(dev != NULL);
     while ((blk = blk_all_next(blk)) != NULL) {
         if (blk->dev == dev) {
@@ -996,6 +1031,7 @@ BlockBackend *blk_by_dev(void *dev)
 void blk_set_dev_ops(BlockBackend *blk, const BlockDevOps *ops,
                      void *opaque)
 {
+    assert(qemu_in_main_thread());
     blk->dev_ops = ops;
     blk->dev_opaque = opaque;
 
@@ -1017,6 +1053,7 @@ void blk_set_dev_ops(BlockBackend *blk, const BlockDevOps *ops,
  */
 void blk_dev_change_media_cb(BlockBackend *blk, bool load, Error **errp)
 {
+    assert(qemu_in_main_thread());
     if (blk->dev_ops && blk->dev_ops->change_media_cb) {
         bool tray_was_open, tray_is_open;
         Error *local_err = NULL;
@@ -1108,6 +1145,7 @@ static void blk_root_resize(BdrvChild *child)
 
 void blk_iostatus_enable(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     blk->iostatus_enabled = true;
     blk->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
 }
@@ -1116,6 +1154,7 @@ void blk_iostatus_enable(BlockBackend *blk)
  * enables it _and_ the VM is configured to stop on errors */
 bool blk_iostatus_is_enabled(const BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     return (blk->iostatus_enabled &&
            (blk->on_write_error == BLOCKDEV_ON_ERROR_ENOSPC ||
             blk->on_write_error == BLOCKDEV_ON_ERROR_STOP   ||
@@ -1124,16 +1163,19 @@ bool blk_iostatus_is_enabled(const BlockBackend *blk)
 
 BlockDeviceIoStatus blk_iostatus(const BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     return blk->iostatus;
 }
 
 void blk_iostatus_disable(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     blk->iostatus_enabled = false;
 }
 
 void blk_iostatus_reset(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     if (blk_iostatus_is_enabled(blk)) {
         blk->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
     }
@@ -1141,6 +1183,7 @@ void blk_iostatus_reset(BlockBackend *blk)
 
 void blk_iostatus_set_err(BlockBackend *blk, int error)
 {
+    assert(qemu_in_main_thread());
     assert(blk_iostatus_is_enabled(blk));
     if (blk->iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
         blk->iostatus = error == ENOSPC ? BLOCK_DEVICE_IO_STATUS_NOSPACE :
@@ -1373,6 +1416,7 @@ int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset,
 
 int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags)
 {
+    assert(qemu_in_main_thread());
     return bdrv_make_zero(blk->root, flags);
 }
 
@@ -1401,6 +1445,7 @@ BlockAIOCB *blk_abort_aio_request(BlockBackend *blk,
                                   void *opaque, int ret)
 {
     struct BlockBackendAIOCB *acb;
+    assert(qemu_in_main_thread());
 
     blk_inc_in_flight(blk);
     acb = blk_aio_get(&block_backend_aiocb_info, blk, cb, opaque);
@@ -1551,6 +1596,7 @@ void blk_get_geometry(BlockBackend *blk, uint64_t *nb_sectors_ptr)
 
 int64_t blk_nb_sectors(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     if (!blk_is_available(blk)) {
         return -ENOMEDIUM;
     }
@@ -1576,6 +1622,7 @@ BlockAIOCB *blk_aio_pwritev(BlockBackend *blk, int64_t offset,
 
 void blk_aio_cancel(BlockAIOCB *acb)
 {
+    assert(qemu_in_main_thread());
     bdrv_aio_cancel(acb);
 }
 
@@ -1739,6 +1786,8 @@ void blk_drain(BlockBackend *blk)
 {
     BlockDriverState *bs = blk_bs(blk);
 
+    assert(qemu_in_main_thread());
+
     if (bs) {
         bdrv_drained_begin(bs);
     }
@@ -1756,6 +1805,8 @@ void blk_drain_all(void)
 {
     BlockBackend *blk = NULL;
 
+    assert(qemu_in_main_thread());
+
     bdrv_drain_all_begin();
 
     while ((blk = blk_all_next(blk)) != NULL) {
@@ -1775,6 +1826,7 @@ void blk_drain_all(void)
 void blk_set_on_error(BlockBackend *blk, BlockdevOnError on_read_error,
                       BlockdevOnError on_write_error)
 {
+    assert(qemu_in_main_thread());
     blk->on_read_error = on_read_error;
     blk->on_write_error = on_write_error;
 }
@@ -1858,6 +1910,7 @@ void blk_error_action(BlockBackend *blk, BlockErrorAction action,
 bool blk_supports_write_perm(BlockBackend *blk)
 {
     BlockDriverState *bs = blk_bs(blk);
+    assert(qemu_in_main_thread());
 
     if (bs) {
         return !bdrv_is_read_only(bs);
@@ -1878,6 +1931,7 @@ bool blk_is_writable(BlockBackend *blk)
 bool blk_is_sg(BlockBackend *blk)
 {
     BlockDriverState *bs = blk_bs(blk);
+    assert(qemu_in_main_thread());
 
     if (!bs) {
         return false;
@@ -1888,17 +1942,20 @@ bool blk_is_sg(BlockBackend *blk)
 
 bool blk_enable_write_cache(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     return blk->enable_write_cache;
 }
 
 void blk_set_enable_write_cache(BlockBackend *blk, bool wce)
 {
+    assert(qemu_in_main_thread());
     blk->enable_write_cache = wce;
 }
 
 void blk_invalidate_cache(BlockBackend *blk, Error **errp)
 {
     BlockDriverState *bs = blk_bs(blk);
+    assert(qemu_in_main_thread());
 
     if (!bs) {
         error_setg(errp, "Device '%s' has no medium", blk->name);
@@ -1911,7 +1968,6 @@ void blk_invalidate_cache(BlockBackend *blk, Error **errp)
 bool blk_is_inserted(BlockBackend *blk)
 {
     BlockDriverState *bs = blk_bs(blk);
-
     return bs && bdrv_is_inserted(bs);
 }
 
@@ -1923,6 +1979,7 @@ bool blk_is_available(BlockBackend *blk)
 void blk_lock_medium(BlockBackend *blk, bool locked)
 {
     BlockDriverState *bs = blk_bs(blk);
+    assert(qemu_in_main_thread());
 
     if (bs) {
         bdrv_lock_medium(bs, locked);
@@ -1932,6 +1989,8 @@ void blk_lock_medium(BlockBackend *blk, bool locked)
 void blk_eject(BlockBackend *blk, bool eject_flag)
 {
     BlockDriverState *bs = blk_bs(blk);
+    assert(qemu_in_main_thread());
+
     char *id;
 
     if (bs) {
@@ -1949,6 +2008,7 @@ void blk_eject(BlockBackend *blk, bool eject_flag)
 int blk_get_flags(BlockBackend *blk)
 {
     BlockDriverState *bs = blk_bs(blk);
+    assert(qemu_in_main_thread());
 
     if (bs) {
         return bdrv_get_flags(bs);
@@ -2002,6 +2062,7 @@ int blk_get_max_iov(BlockBackend *blk)
 
 void blk_set_guest_block_size(BlockBackend *blk, int align)
 {
+    assert(qemu_in_main_thread());
     blk->guest_block_size = align;
 }
 
@@ -2018,6 +2079,7 @@ void *blk_blockalign(BlockBackend *blk, size_t size)
 bool blk_op_is_blocked(BlockBackend *blk, BlockOpType op, Error **errp)
 {
     BlockDriverState *bs = blk_bs(blk);
+    assert(qemu_in_main_thread());
 
     if (!bs) {
         return false;
@@ -2029,6 +2091,7 @@ bool blk_op_is_blocked(BlockBackend *blk, BlockOpType op, Error **errp)
 void blk_op_unblock(BlockBackend *blk, BlockOpType op, Error *reason)
 {
     BlockDriverState *bs = blk_bs(blk);
+    assert(qemu_in_main_thread());
 
     if (bs) {
         bdrv_op_unblock(bs, op, reason);
@@ -2038,6 +2101,7 @@ void blk_op_unblock(BlockBackend *blk, BlockOpType op, Error *reason)
 void blk_op_block_all(BlockBackend *blk, Error *reason)
 {
     BlockDriverState *bs = blk_bs(blk);
+    assert(qemu_in_main_thread());
 
     if (bs) {
         bdrv_op_block_all(bs, reason);
@@ -2047,6 +2111,7 @@ void blk_op_block_all(BlockBackend *blk, Error *reason)
 void blk_op_unblock_all(BlockBackend *blk, Error *reason)
 {
     BlockDriverState *bs = blk_bs(blk);
+    assert(qemu_in_main_thread());
 
     if (bs) {
         bdrv_op_unblock_all(bs, reason);
@@ -2101,6 +2166,7 @@ static int blk_do_set_aio_context(BlockBackend *blk, AioContext *new_context,
 int blk_set_aio_context(BlockBackend *blk, AioContext *new_context,
                         Error **errp)
 {
+    assert(qemu_in_main_thread());
     return blk_do_set_aio_context(blk, new_context, true, errp);
 }
 
@@ -2137,6 +2203,7 @@ void blk_add_aio_context_notifier(BlockBackend *blk,
 {
     BlockBackendAioNotifier *notifier;
     BlockDriverState *bs = blk_bs(blk);
+    assert(qemu_in_main_thread());
 
     notifier = g_new(BlockBackendAioNotifier, 1);
     notifier->attached_aio_context = attached_aio_context;
@@ -2159,6 +2226,8 @@ void blk_remove_aio_context_notifier(BlockBackend *blk,
     BlockBackendAioNotifier *notifier;
     BlockDriverState *bs = blk_bs(blk);
 
+    assert(qemu_in_main_thread());
+
     if (bs) {
         bdrv_remove_aio_context_notifier(bs, attached_aio_context,
                                          detach_aio_context, opaque);
@@ -2179,11 +2248,13 @@ void blk_remove_aio_context_notifier(BlockBackend *blk,
 
 void blk_add_remove_bs_notifier(BlockBackend *blk, Notifier *notify)
 {
+    assert(qemu_in_main_thread());
     notifier_list_add(&blk->remove_bs_notifiers, notify);
 }
 
 void blk_add_insert_bs_notifier(BlockBackend *blk, Notifier *notify)
 {
+    assert(qemu_in_main_thread());
     notifier_list_add(&blk->insert_bs_notifiers, notify);
 }
 
@@ -2245,6 +2316,7 @@ int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf,
                      int64_t pos, int size)
 {
     int ret;
+    assert(qemu_in_main_thread());
 
     if (!blk_is_available(blk)) {
         return -ENOMEDIUM;
@@ -2264,6 +2336,7 @@ int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf,
 
 int blk_load_vmstate(BlockBackend *blk, uint8_t *buf, int64_t pos, int size)
 {
+    assert(qemu_in_main_thread());
     if (!blk_is_available(blk)) {
         return -ENOMEDIUM;
     }
@@ -2273,6 +2346,7 @@ int blk_load_vmstate(BlockBackend *blk, uint8_t *buf, int64_t pos, int size)
 
 int blk_probe_blocksizes(BlockBackend *blk, BlockSizes *bsz)
 {
+    assert(qemu_in_main_thread());
     if (!blk_is_available(blk)) {
         return -ENOMEDIUM;
     }
@@ -2282,6 +2356,7 @@ int blk_probe_blocksizes(BlockBackend *blk, BlockSizes *bsz)
 
 int blk_probe_geometry(BlockBackend *blk, HDGeometry *geo)
 {
+    assert(qemu_in_main_thread());
     if (!blk_is_available(blk)) {
         return -ENOMEDIUM;
     }
@@ -2295,6 +2370,7 @@ int blk_probe_geometry(BlockBackend *blk, HDGeometry *geo)
  */
 void blk_update_root_state(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     assert(blk->root);
 
     blk->root_state.open_flags    = blk->root->bs->open_flags;
@@ -2307,6 +2383,7 @@ void blk_update_root_state(BlockBackend *blk)
  */
 bool blk_get_detect_zeroes_from_root_state(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     return blk->root_state.detect_zeroes;
 }
 
@@ -2316,17 +2393,20 @@ bool blk_get_detect_zeroes_from_root_state(BlockBackend *blk)
  */
 int blk_get_open_flags_from_root_state(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     return blk->root_state.open_flags;
 }
 
 BlockBackendRootState *blk_get_root_state(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     return &blk->root_state;
 }
 
 int blk_commit_all(void)
 {
     BlockBackend *blk = NULL;
+    assert(qemu_in_main_thread());
 
     while ((blk = blk_all_next(blk)) != NULL) {
         AioContext *aio_context = blk_get_aio_context(blk);
@@ -2351,6 +2431,7 @@ int blk_commit_all(void)
 /* throttling disk I/O limits */
 void blk_set_io_limits(BlockBackend *blk, ThrottleConfig *cfg)
 {
+    assert(qemu_in_main_thread());
     throttle_group_config(&blk->public.throttle_group_member, cfg);
 }
 
@@ -2359,6 +2440,7 @@ void blk_io_limits_disable(BlockBackend *blk)
     BlockDriverState *bs = blk_bs(blk);
     ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
     assert(tgm->throttle_state);
+    assert(qemu_in_main_thread());
     if (bs) {
         bdrv_drained_begin(bs);
     }
@@ -2372,12 +2454,14 @@ void blk_io_limits_disable(BlockBackend *blk)
 void blk_io_limits_enable(BlockBackend *blk, const char *group)
 {
     assert(!blk->public.throttle_group_member.throttle_state);
+    assert(qemu_in_main_thread());
     throttle_group_register_tgm(&blk->public.throttle_group_member,
                                 group, blk_get_aio_context(blk));
 }
 
 void blk_io_limits_update_group(BlockBackend *blk, const char *group)
 {
+    assert(qemu_in_main_thread());
     /* this BB is not part of any group */
     if (!blk->public.throttle_group_member.throttle_state) {
         return;
@@ -2445,11 +2529,13 @@ static void blk_root_drained_end(BdrvChild *child, int *drained_end_counter)
 
 void blk_register_buf(BlockBackend *blk, void *host, size_t size)
 {
+    assert(qemu_in_main_thread());
     bdrv_register_buf(blk_bs(blk), host, size);
 }
 
 void blk_unregister_buf(BlockBackend *blk, void *host)
 {
+    assert(qemu_in_main_thread());
     bdrv_unregister_buf(blk_bs(blk), host);
 }
 
@@ -2474,11 +2560,13 @@ int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in,
 
 const BdrvChild *blk_root(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     return blk->root;
 }
 
 int blk_make_empty(BlockBackend *blk, Error **errp)
 {
+    assert(qemu_in_main_thread());
     if (!blk_is_available(blk)) {
         error_setg(errp, "No medium inserted");
         return -ENOMEDIUM;
diff --git a/softmmu/qdev-monitor.c b/softmmu/qdev-monitor.c
index 0705f00846..7312635224 100644
--- a/softmmu/qdev-monitor.c
+++ b/softmmu/qdev-monitor.c
@@ -942,6 +942,8 @@ BlockBackend *blk_by_qdev_id(const char *id, Error **errp)
     DeviceState *dev;
     BlockBackend *blk;
 
+    assert(qemu_in_main_thread());
+
     dev = find_device_state(id, errp);
     if (dev == NULL) {
         return NULL;
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 06/25] include/block/block_int: split header into I/O and global state API
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (4 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 05/25] block/block-backend.c: assertions for block-backend Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-21 14:35   ` Stefan Hajnoczi
  2021-10-12  8:48 ` [PATCH v3 07/25] assertions for block_int " Emanuele Giuseppe Esposito
                   ` (18 subsequent siblings)
  24 siblings, 1 reply; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

Similarly to the previous patch, split block_int.h
in block_int-io.h and block_int-global-state.h

block_int-common.h contains the structures shared between
the two headers, and the functions that can't be categorized as
I/O or global state.

Assertions are added in the next patch.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 blockdev.c                             |    5 +
 include/block/block_int-common.h       | 1164 +++++++++++++++++++
 include/block/block_int-global-state.h |  319 +++++
 include/block/block_int-io.h           |  163 +++
 include/block/block_int.h              | 1478 +-----------------------
 5 files changed, 1654 insertions(+), 1475 deletions(-)
 create mode 100644 include/block/block_int-common.h
 create mode 100644 include/block/block_int-global-state.h
 create mode 100644 include/block/block_int-io.h

diff --git a/blockdev.c b/blockdev.c
index ae322ed10e..ddba382abd 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -63,6 +63,7 @@
 #include "qemu/main-loop.h"
 #include "qemu/throttle-options.h"
 
+/* Protected by BQL lock */
 QTAILQ_HEAD(, BlockDriverState) monitor_bdrv_states =
     QTAILQ_HEAD_INITIALIZER(monitor_bdrv_states);
 
@@ -1207,6 +1208,8 @@ typedef struct BlkActionState BlkActionState;
  *
  * Only prepare() may fail. In a single transaction, only one of commit() or
  * abort() will be called. clean() will always be called if it is present.
+ *
+ * Always run under BQL.
  */
 typedef struct BlkActionOps {
     size_t instance_size;
@@ -2316,6 +2319,8 @@ static TransactionProperties *get_transaction_properties(
 /*
  * 'Atomic' group operations.  The operations are performed as a set, and if
  * any fail then we roll back all operations in the group.
+ *
+ * Always run under BQL.
  */
 void qmp_transaction(TransactionActionList *dev_list,
                      bool has_props,
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
new file mode 100644
index 0000000000..79a3d801d2
--- /dev/null
+++ b/include/block/block_int-common.h
@@ -0,0 +1,1164 @@
+/*
+ * QEMU System Emulator block driver
+ *
+ * Copyright (c) 2003 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef BLOCK_INT_COMMON_H
+#define BLOCK_INT_COMMON_H
+
+#include "block/accounting.h"
+#include "block/block.h"
+#include "block/aio-wait.h"
+#include "qemu/queue.h"
+#include "qemu/coroutine.h"
+#include "qemu/stats64.h"
+#include "qemu/timer.h"
+#include "qemu/hbitmap.h"
+#include "block/snapshot.h"
+#include "qemu/throttle.h"
+#include "qemu/rcu.h"
+
+#define BLOCK_FLAG_LAZY_REFCOUNTS   8
+
+#define BLOCK_OPT_SIZE              "size"
+#define BLOCK_OPT_ENCRYPT           "encryption"
+#define BLOCK_OPT_ENCRYPT_FORMAT    "encrypt.format"
+#define BLOCK_OPT_COMPAT6           "compat6"
+#define BLOCK_OPT_HWVERSION         "hwversion"
+#define BLOCK_OPT_BACKING_FILE      "backing_file"
+#define BLOCK_OPT_BACKING_FMT       "backing_fmt"
+#define BLOCK_OPT_CLUSTER_SIZE      "cluster_size"
+#define BLOCK_OPT_TABLE_SIZE        "table_size"
+#define BLOCK_OPT_PREALLOC          "preallocation"
+#define BLOCK_OPT_SUBFMT            "subformat"
+#define BLOCK_OPT_COMPAT_LEVEL      "compat"
+#define BLOCK_OPT_LAZY_REFCOUNTS    "lazy_refcounts"
+#define BLOCK_OPT_ADAPTER_TYPE      "adapter_type"
+#define BLOCK_OPT_REDUNDANCY        "redundancy"
+#define BLOCK_OPT_NOCOW             "nocow"
+#define BLOCK_OPT_EXTENT_SIZE_HINT  "extent_size_hint"
+#define BLOCK_OPT_OBJECT_SIZE       "object_size"
+#define BLOCK_OPT_REFCOUNT_BITS     "refcount_bits"
+#define BLOCK_OPT_DATA_FILE         "data_file"
+#define BLOCK_OPT_DATA_FILE_RAW     "data_file_raw"
+#define BLOCK_OPT_COMPRESSION_TYPE  "compression_type"
+#define BLOCK_OPT_EXTL2             "extended_l2"
+
+#define BLOCK_PROBE_BUF_SIZE        512
+
+enum BdrvTrackedRequestType {
+    BDRV_TRACKED_READ,
+    BDRV_TRACKED_WRITE,
+    BDRV_TRACKED_DISCARD,
+    BDRV_TRACKED_TRUNCATE,
+};
+
+/*
+ * That is not quite good that BdrvTrackedRequest structure is public,
+ * as block/io.c is very careful about incoming offset/bytes being
+ * correct. Be sure to assert bdrv_check_request() succeeded after any
+ * modification of BdrvTrackedRequest object out of block/io.c
+ */
+typedef struct BdrvTrackedRequest {
+    BlockDriverState *bs;
+    int64_t offset;
+    int64_t bytes;
+    enum BdrvTrackedRequestType type;
+
+    bool serialising;
+    int64_t overlap_offset;
+    int64_t overlap_bytes;
+
+    QLIST_ENTRY(BdrvTrackedRequest) list;
+    Coroutine *co; /* owner, used for deadlock detection */
+    CoQueue wait_queue; /* coroutines blocked on this request */
+
+    struct BdrvTrackedRequest *waiting_for;
+} BdrvTrackedRequest;
+
+
+struct BlockDriver {
+    const char *format_name;
+    int instance_size;
+
+    /*
+     * Set to true if the BlockDriver is a block filter. Block filters pass
+     * certain callbacks that refer to data (see block.c) to their bs->file
+     * or bs->backing (whichever one exists) if the driver doesn't implement
+     * them. Drivers that do not wish to forward must implement them and return
+     * -ENOTSUP.
+     * Note that filters are not allowed to modify data.
+     *
+     * Filters generally cannot have more than a single filtered child,
+     * because the data they present must at all times be the same as
+     * that on their filtered child.  That would be impossible to
+     * achieve for multiple filtered children.
+     * (And this filtered child must then be bs->file or bs->backing.)
+     */
+    bool is_filter;
+    /*
+     * Set to true if the BlockDriver is a format driver.  Format nodes
+     * generally do not expect their children to be other format nodes
+     * (except for backing files), and so format probing is disabled
+     * on those children.
+     */
+    bool is_format;
+    /*
+     * Return true if @to_replace can be replaced by a BDS with the
+     * same data as @bs without it affecting @bs's behavior (that is,
+     * without it being visible to @bs's parents).
+     */
+    bool (*bdrv_recurse_can_replace)(BlockDriverState *bs,
+                                     BlockDriverState *to_replace);
+
+    int (*bdrv_probe)(const uint8_t *buf, int buf_size, const char *filename);
+    int (*bdrv_probe_device)(const char *filename);
+
+    /*
+     * Any driver implementing this callback is expected to be able to handle
+     * NULL file names in its .bdrv_open() implementation.
+     */
+    void (*bdrv_parse_filename)(const char *filename, QDict *options,
+                                Error **errp);
+    /*
+     * Drivers not implementing bdrv_parse_filename nor bdrv_open should have
+     * this field set to true, except ones that are defined only by their
+     * child's bs.
+     * An example of the last type will be the quorum block driver.
+     */
+    bool bdrv_needs_filename;
+
+    /*
+     * Set if a driver can support backing files. This also implies the
+     * following semantics:
+     *
+     *  - Return status 0 of .bdrv_co_block_status means that corresponding
+     *    blocks are not allocated in this layer of backing-chain
+     *  - For such (unallocated) blocks, read will:
+     *    - fill buffer with zeros if there is no backing file
+     *    - read from the backing file otherwise, where the block layer
+     *      takes care of reading zeros beyond EOF if backing file is short
+     */
+    bool supports_backing;
+
+    /* For handling image reopen for split or non-split files */
+    int (*bdrv_reopen_prepare)(BDRVReopenState *reopen_state,
+                               BlockReopenQueue *queue, Error **errp);
+    void (*bdrv_reopen_commit)(BDRVReopenState *reopen_state);
+    void (*bdrv_reopen_commit_post)(BDRVReopenState *reopen_state);
+    void (*bdrv_reopen_abort)(BDRVReopenState *reopen_state);
+    void (*bdrv_join_options)(QDict *options, QDict *old_options);
+
+    int (*bdrv_open)(BlockDriverState *bs, QDict *options, int flags,
+                     Error **errp);
+
+    /* Protocol drivers should implement this instead of bdrv_open */
+    int (*bdrv_file_open)(BlockDriverState *bs, QDict *options, int flags,
+                          Error **errp);
+    void (*bdrv_close)(BlockDriverState *bs);
+
+
+    int coroutine_fn (*bdrv_co_create)(BlockdevCreateOptions *opts,
+                                       Error **errp);
+    int coroutine_fn (*bdrv_co_create_opts)(BlockDriver *drv,
+                                            const char *filename,
+                                            QemuOpts *opts,
+                                            Error **errp);
+
+    int coroutine_fn (*bdrv_co_amend)(BlockDriverState *bs,
+                                      BlockdevAmendOptions *opts,
+                                      bool force,
+                                      Error **errp);
+
+    int (*bdrv_amend_options)(BlockDriverState *bs,
+                              QemuOpts *opts,
+                              BlockDriverAmendStatusCB *status_cb,
+                              void *cb_opaque,
+                              bool force,
+                              Error **errp);
+
+    int (*bdrv_make_empty)(BlockDriverState *bs);
+
+    /*
+     * Refreshes the bs->exact_filename field. If that is impossible,
+     * bs->exact_filename has to be left empty.
+     */
+    void (*bdrv_refresh_filename)(BlockDriverState *bs);
+
+    /*
+     * Gathers the open options for all children into @target.
+     * A simple format driver (without backing file support) might
+     * implement this function like this:
+     *
+     *     QINCREF(bs->file->bs->full_open_options);
+     *     qdict_put(target, "file", bs->file->bs->full_open_options);
+     *
+     * If not specified, the generic implementation will simply put
+     * all children's options under their respective name.
+     *
+     * @backing_overridden is true when bs->backing seems not to be
+     * the child that would result from opening bs->backing_file.
+     * Therefore, if it is true, the backing child's options should be
+     * gathered; otherwise, there is no need since the backing child
+     * is the one implied by the image header.
+     *
+     * Note that ideally this function would not be needed.  Every
+     * block driver which implements it is probably doing something
+     * shady regarding its runtime option structure.
+     */
+    void (*bdrv_gather_child_options)(BlockDriverState *bs, QDict *target,
+                                      bool backing_overridden);
+
+    /*
+     * Returns an allocated string which is the directory name of this BDS: It
+     * will be used to make relative filenames absolute by prepending this
+     * function's return value to them.
+     */
+    char *(*bdrv_dirname)(BlockDriverState *bs, Error **errp);
+
+    /* aio */
+    BlockAIOCB *(*bdrv_aio_preadv)(BlockDriverState *bs,
+        int64_t offset, int64_t bytes, QEMUIOVector *qiov,
+        BdrvRequestFlags flags, BlockCompletionFunc *cb, void *opaque);
+    BlockAIOCB *(*bdrv_aio_pwritev)(BlockDriverState *bs,
+        int64_t offset, int64_t bytes, QEMUIOVector *qiov,
+        BdrvRequestFlags flags, BlockCompletionFunc *cb, void *opaque);
+    BlockAIOCB *(*bdrv_aio_flush)(BlockDriverState *bs,
+        BlockCompletionFunc *cb, void *opaque);
+    BlockAIOCB *(*bdrv_aio_pdiscard)(BlockDriverState *bs,
+        int64_t offset, int bytes,
+        BlockCompletionFunc *cb, void *opaque);
+
+    int coroutine_fn (*bdrv_co_readv)(BlockDriverState *bs,
+        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
+
+    /**
+     * @offset: position in bytes to read at
+     * @bytes: number of bytes to read
+     * @qiov: the buffers to fill with read data
+     * @flags: currently unused, always 0
+     *
+     * @offset and @bytes will be a multiple of 'request_alignment',
+     * but the length of individual @qiov elements does not have to
+     * be a multiple.
+     *
+     * @bytes will always equal the total size of @qiov, and will be
+     * no larger than 'max_transfer'.
+     *
+     * The buffer in @qiov may point directly to guest memory.
+     */
+    int coroutine_fn (*bdrv_co_preadv)(BlockDriverState *bs,
+        int64_t offset, int64_t bytes, QEMUIOVector *qiov,
+        BdrvRequestFlags flags);
+
+    int coroutine_fn (*bdrv_co_preadv_part)(BlockDriverState *bs,
+        int64_t offset, int64_t bytes,
+        QEMUIOVector *qiov, size_t qiov_offset,
+        BdrvRequestFlags flags);
+
+    int coroutine_fn (*bdrv_co_writev)(BlockDriverState *bs,
+        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
+        int flags);
+    /**
+     * @offset: position in bytes to write at
+     * @bytes: number of bytes to write
+     * @qiov: the buffers containing data to write
+     * @flags: zero or more bits allowed by 'supported_write_flags'
+     *
+     * @offset and @bytes will be a multiple of 'request_alignment',
+     * but the length of individual @qiov elements does not have to
+     * be a multiple.
+     *
+     * @bytes will always equal the total size of @qiov, and will be
+     * no larger than 'max_transfer'.
+     *
+     * The buffer in @qiov may point directly to guest memory.
+     */
+    int coroutine_fn (*bdrv_co_pwritev)(BlockDriverState *bs,
+        int64_t offset, int64_t bytes, QEMUIOVector *qiov,
+        BdrvRequestFlags flags);
+    int coroutine_fn (*bdrv_co_pwritev_part)(BlockDriverState *bs,
+        int64_t offset, int64_t bytes, QEMUIOVector *qiov, size_t qiov_offset,
+        BdrvRequestFlags flags);
+
+    /*
+     * Efficiently zero a region of the disk image.  Typically an image format
+     * would use a compact metadata representation to implement this.  This
+     * function pointer may be NULL or return -ENOSUP and .bdrv_co_writev()
+     * will be called instead.
+     */
+    int coroutine_fn (*bdrv_co_pwrite_zeroes)(BlockDriverState *bs,
+        int64_t offset, int64_t bytes, BdrvRequestFlags flags);
+    int coroutine_fn (*bdrv_co_pdiscard)(BlockDriverState *bs,
+        int64_t offset, int64_t bytes);
+
+    /*
+     * Map [offset, offset + nbytes) range onto a child of @bs to copy from,
+     * and invoke bdrv_co_copy_range_from(child, ...), or invoke
+     * bdrv_co_copy_range_to() if @bs is the leaf child to copy data from.
+     *
+     * See the comment of bdrv_co_copy_range for the parameter and return value
+     * semantics.
+     */
+    int coroutine_fn (*bdrv_co_copy_range_from)(BlockDriverState *bs,
+                                                BdrvChild *src,
+                                                int64_t offset,
+                                                BdrvChild *dst,
+                                                int64_t dst_offset,
+                                                int64_t bytes,
+                                                BdrvRequestFlags read_flags,
+                                                BdrvRequestFlags write_flags);
+
+    /*
+     * Map [offset, offset + nbytes) range onto a child of bs to copy data to,
+     * and invoke bdrv_co_copy_range_to(child, src, ...), or perform the copy
+     * operation if @bs is the leaf and @src has the same BlockDriver.  Return
+     * -ENOTSUP if @bs is the leaf but @src has a different BlockDriver.
+     *
+     * See the comment of bdrv_co_copy_range for the parameter and return value
+     * semantics.
+     */
+    int coroutine_fn (*bdrv_co_copy_range_to)(BlockDriverState *bs,
+                                              BdrvChild *src,
+                                              int64_t src_offset,
+                                              BdrvChild *dst,
+                                              int64_t dst_offset,
+                                              int64_t bytes,
+                                              BdrvRequestFlags read_flags,
+                                              BdrvRequestFlags write_flags);
+
+    /*
+     * Building block for bdrv_block_status[_above] and
+     * bdrv_is_allocated[_above].  The driver should answer only
+     * according to the current layer, and should only need to set
+     * BDRV_BLOCK_DATA, BDRV_BLOCK_ZERO, BDRV_BLOCK_OFFSET_VALID,
+     * and/or BDRV_BLOCK_RAW; if the current layer defers to a backing
+     * layer, the result should be 0 (and not BDRV_BLOCK_ZERO).  See
+     * block.h for the overall meaning of the bits.  As a hint, the
+     * flag want_zero is true if the caller cares more about precise
+     * mappings (favor accurate _OFFSET_VALID/_ZERO) or false for
+     * overall allocation (favor larger *pnum, perhaps by reporting
+     * _DATA instead of _ZERO).  The block layer guarantees input
+     * clamped to bdrv_getlength() and aligned to request_alignment,
+     * as well as non-NULL pnum, map, and file; in turn, the driver
+     * must return an error or set pnum to an aligned non-zero value.
+     *
+     * Note that @bytes is just a hint on how big of a region the
+     * caller wants to inspect.  It is not a limit on *pnum.
+     * Implementations are free to return larger values of *pnum if
+     * doing so does not incur a performance penalty.
+     *
+     * block/io.c's bdrv_co_block_status() will utilize an unclamped
+     * *pnum value for the block-status cache on protocol nodes, prior
+     * to clamping *pnum for return to its caller.
+     */
+    int coroutine_fn (*bdrv_co_block_status)(BlockDriverState *bs,
+        bool want_zero, int64_t offset, int64_t bytes, int64_t *pnum,
+        int64_t *map, BlockDriverState **file);
+
+    /*
+     * This informs the driver that we are no longer interested in the result
+     * of in-flight requests, so don't waste the time if possible.
+     *
+     * One example usage is to avoid waiting for an nbd target node reconnect
+     * timeout during job-cancel with force=true.
+     */
+    void (*bdrv_cancel_in_flight)(BlockDriverState *bs);
+
+    /*
+     * Invalidate any cached meta-data.
+     */
+    void coroutine_fn (*bdrv_co_invalidate_cache)(BlockDriverState *bs,
+                                                  Error **errp);
+    int (*bdrv_inactivate)(BlockDriverState *bs);
+
+    /*
+     * Flushes all data for all layers by calling bdrv_co_flush for underlying
+     * layers, if needed. This function is needed for deterministic
+     * synchronization of the flush finishing callback.
+     */
+    int coroutine_fn (*bdrv_co_flush)(BlockDriverState *bs);
+
+    /* Delete a created file. */
+    int coroutine_fn (*bdrv_co_delete_file)(BlockDriverState *bs,
+                                            Error **errp);
+
+    /*
+     * Flushes all data that was already written to the OS all the way down to
+     * the disk (for example file-posix.c calls fsync()).
+     */
+    int coroutine_fn (*bdrv_co_flush_to_disk)(BlockDriverState *bs);
+
+    /*
+     * Flushes all internal caches to the OS. The data may still sit in a
+     * writeback cache of the host OS, but it will survive a crash of the qemu
+     * process.
+     */
+    int coroutine_fn (*bdrv_co_flush_to_os)(BlockDriverState *bs);
+
+    /*
+     * Drivers setting this field must be able to work with just a plain
+     * filename with '<protocol_name>:' as a prefix, and no other options.
+     * Options may be extracted from the filename by implementing
+     * bdrv_parse_filename.
+     */
+    const char *protocol_name;
+
+    /*
+     * Truncate @bs to @offset bytes using the given @prealloc mode
+     * when growing.  Modes other than PREALLOC_MODE_OFF should be
+     * rejected when shrinking @bs.
+     *
+     * If @exact is true, @bs must be resized to exactly @offset.
+     * Otherwise, it is sufficient for @bs (if it is a host block
+     * device and thus there is no way to resize it) to be at least
+     * @offset bytes in length.
+     *
+     * If @exact is true and this function fails but would succeed
+     * with @exact = false, it should return -ENOTSUP.
+     */
+    int coroutine_fn (*bdrv_co_truncate)(BlockDriverState *bs, int64_t offset,
+                                         bool exact, PreallocMode prealloc,
+                                         BdrvRequestFlags flags, Error **errp);
+    int64_t (*bdrv_getlength)(BlockDriverState *bs);
+    bool has_variable_length;
+    int64_t (*bdrv_get_allocated_file_size)(BlockDriverState *bs);
+    BlockMeasureInfo *(*bdrv_measure)(QemuOpts *opts, BlockDriverState *in_bs,
+                                      Error **errp);
+
+    int coroutine_fn (*bdrv_co_pwritev_compressed)(BlockDriverState *bs,
+        int64_t offset, int64_t bytes, QEMUIOVector *qiov);
+    int coroutine_fn (*bdrv_co_pwritev_compressed_part)(BlockDriverState *bs,
+        int64_t offset, int64_t bytes, QEMUIOVector *qiov,
+        size_t qiov_offset);
+
+    int (*bdrv_snapshot_create)(BlockDriverState *bs,
+                                QEMUSnapshotInfo *sn_info);
+    int (*bdrv_snapshot_goto)(BlockDriverState *bs,
+                              const char *snapshot_id);
+    int (*bdrv_snapshot_delete)(BlockDriverState *bs,
+                                const char *snapshot_id,
+                                const char *name,
+                                Error **errp);
+    int (*bdrv_snapshot_list)(BlockDriverState *bs,
+                              QEMUSnapshotInfo **psn_info);
+    int (*bdrv_snapshot_load_tmp)(BlockDriverState *bs,
+                                  const char *snapshot_id,
+                                  const char *name,
+                                  Error **errp);
+    int (*bdrv_get_info)(BlockDriverState *bs, BlockDriverInfo *bdi);
+
+    ImageInfoSpecific *(*bdrv_get_specific_info)(BlockDriverState *bs,
+                                                 Error **errp);
+    BlockStatsSpecific *(*bdrv_get_specific_stats)(BlockDriverState *bs);
+
+    int coroutine_fn (*bdrv_save_vmstate)(BlockDriverState *bs,
+                                          QEMUIOVector *qiov,
+                                          int64_t pos);
+    int coroutine_fn (*bdrv_load_vmstate)(BlockDriverState *bs,
+                                          QEMUIOVector *qiov,
+                                          int64_t pos);
+
+    int (*bdrv_change_backing_file)(BlockDriverState *bs,
+        const char *backing_file, const char *backing_fmt);
+
+    /* removable device specific */
+    bool (*bdrv_is_inserted)(BlockDriverState *bs);
+    void (*bdrv_eject)(BlockDriverState *bs, bool eject_flag);
+    void (*bdrv_lock_medium)(BlockDriverState *bs, bool locked);
+
+    /* to control generic scsi devices */
+    BlockAIOCB *(*bdrv_aio_ioctl)(BlockDriverState *bs,
+        unsigned long int req, void *buf,
+        BlockCompletionFunc *cb, void *opaque);
+    int coroutine_fn (*bdrv_co_ioctl)(BlockDriverState *bs,
+                                      unsigned long int req, void *buf);
+
+    /* List of options for creating images, terminated by name == NULL */
+    QemuOptsList *create_opts;
+
+    /* List of options for image amend */
+    QemuOptsList *amend_opts;
+
+    /*
+     * If this driver supports reopening images this contains a
+     * NULL-terminated list of the runtime options that can be
+     * modified. If an option in this list is unspecified during
+     * reopen then it _must_ be reset to its default value or return
+     * an error.
+     */
+    const char *const *mutable_opts;
+
+    /*
+     * Returns 0 for completed check, -errno for internal errors.
+     * The check results are stored in result.
+     */
+    int coroutine_fn (*bdrv_co_check)(BlockDriverState *bs,
+                                      BdrvCheckResult *result,
+                                      BdrvCheckMode fix);
+
+    void (*bdrv_debug_event)(BlockDriverState *bs, BlkdebugEvent event);
+
+    /* TODO Better pass a option string/QDict/QemuOpts to add any rule? */
+    int (*bdrv_debug_breakpoint)(BlockDriverState *bs, const char *event,
+        const char *tag);
+    int (*bdrv_debug_remove_breakpoint)(BlockDriverState *bs,
+        const char *tag);
+    int (*bdrv_debug_resume)(BlockDriverState *bs, const char *tag);
+    bool (*bdrv_debug_is_suspended)(BlockDriverState *bs, const char *tag);
+
+    void (*bdrv_refresh_limits)(BlockDriverState *bs, Error **errp);
+
+    /*
+     * Returns 1 if newly created images are guaranteed to contain only
+     * zeros, 0 otherwise.
+     */
+    int (*bdrv_has_zero_init)(BlockDriverState *bs);
+
+    /*
+     * Remove fd handlers, timers, and other event loop callbacks so the event
+     * loop is no longer in use.  Called with no in-flight requests and in
+     * depth-first traversal order with parents before child nodes.
+     */
+    void (*bdrv_detach_aio_context)(BlockDriverState *bs);
+
+    /*
+     * Add fd handlers, timers, and other event loop callbacks so I/O requests
+     * can be processed again.  Called with no in-flight requests and in
+     * depth-first traversal order with child nodes before parent nodes.
+     */
+    void (*bdrv_attach_aio_context)(BlockDriverState *bs,
+                                    AioContext *new_context);
+
+    /* io queue for linux-aio */
+    void (*bdrv_io_plug)(BlockDriverState *bs);
+    void (*bdrv_io_unplug)(BlockDriverState *bs);
+
+    /**
+     * Try to get @bs's logical and physical block size.
+     * On success, store them in @bsz and return zero.
+     * On failure, return negative errno.
+     */
+    /* I/O API, even though if it's a filter jumps on parent */
+    int (*bdrv_probe_blocksizes)(BlockDriverState *bs, BlockSizes *bsz);
+    /**
+     * Try to get @bs's geometry (cyls, heads, sectors)
+     * On success, store them in @geo and return 0.
+     * On failure return -errno.
+     * Only drivers that want to override guest geometry implement this
+     * callback; see hd_geometry_guess().
+     */
+    /* I/O API, even though if it's a filter jumps on parent */
+    int (*bdrv_probe_geometry)(BlockDriverState *bs, HDGeometry *geo);
+
+    /**
+     * bdrv_co_drain_begin is called if implemented in the beginning of a
+     * drain operation to drain and stop any internal sources of requests in
+     * the driver.
+     * bdrv_co_drain_end is called if implemented at the end of the drain.
+     *
+     * They should be used by the driver to e.g. manage scheduled I/O
+     * requests, or toggle an internal state. After the end of the drain new
+     * requests will continue normally.
+     */
+    void coroutine_fn (*bdrv_co_drain_begin)(BlockDriverState *bs);
+    void coroutine_fn (*bdrv_co_drain_end)(BlockDriverState *bs);
+
+    void (*bdrv_add_child)(BlockDriverState *parent, BlockDriverState *child,
+                           Error **errp);
+    void (*bdrv_del_child)(BlockDriverState *parent, BdrvChild *child,
+                           Error **errp);
+
+    /**
+     * Informs the block driver that a permission change is intended. The
+     * driver checks whether the change is permissible and may take other
+     * preparations for the change (e.g. get file system locks). This operation
+     * is always followed either by a call to either .bdrv_set_perm or
+     * .bdrv_abort_perm_update.
+     *
+     * Checks whether the requested set of cumulative permissions in @perm
+     * can be granted for accessing @bs and whether no other users are using
+     * permissions other than those given in @shared (both arguments take
+     * BLK_PERM_* bitmasks).
+     *
+     * If both conditions are met, 0 is returned. Otherwise, -errno is returned
+     * and errp is set to an error describing the conflict.
+     */
+    int (*bdrv_check_perm)(BlockDriverState *bs, uint64_t perm,
+                           uint64_t shared, Error **errp);
+
+    /**
+     * Called to inform the driver that the set of cumulative set of used
+     * permissions for @bs has changed to @perm, and the set of sharable
+     * permission to @shared. The driver can use this to propagate changes to
+     * its children (i.e. request permissions only if a parent actually needs
+     * them).
+     *
+     * This function is only invoked after bdrv_check_perm(), so block drivers
+     * may rely on preparations made in their .bdrv_check_perm implementation.
+     */
+    void (*bdrv_set_perm)(BlockDriverState *bs, uint64_t perm, uint64_t shared);
+
+    /*
+     * Called to inform the driver that after a previous bdrv_check_perm()
+     * call, the permission update is not performed and any preparations made
+     * for it (e.g. taken file locks) need to be undone.
+     *
+     * This function can be called even for nodes that never saw a
+     * bdrv_check_perm() call. It is a no-op then.
+     */
+    void (*bdrv_abort_perm_update)(BlockDriverState *bs);
+
+    /**
+     * Returns in @nperm and @nshared the permissions that the driver for @bs
+     * needs on its child @c, based on the cumulative permissions requested by
+     * the parents in @parent_perm and @parent_shared.
+     *
+     * If @c is NULL, return the permissions for attaching a new child for the
+     * given @child_class and @role.
+     *
+     * If @reopen_queue is non-NULL, don't return the currently needed
+     * permissions, but those that will be needed after applying the
+     * @reopen_queue.
+     */
+     void (*bdrv_child_perm)(BlockDriverState *bs, BdrvChild *c,
+                             BdrvChildRole role,
+                             BlockReopenQueue *reopen_queue,
+                             uint64_t parent_perm, uint64_t parent_shared,
+                             uint64_t *nperm, uint64_t *nshared);
+
+    bool (*bdrv_supports_persistent_dirty_bitmap)(BlockDriverState *bs);
+    bool (*bdrv_co_can_store_new_dirty_bitmap)(BlockDriverState *bs,
+                                               const char *name,
+                                               uint32_t granularity,
+                                               Error **errp);
+    int (*bdrv_co_remove_persistent_dirty_bitmap)(BlockDriverState *bs,
+                                                  const char *name,
+                                                  Error **errp);
+
+    /**
+     * Register/unregister a buffer for I/O. For example, when the driver is
+     * interested to know the memory areas that will later be used in iovs, so
+     * 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.
+     */
+    void (*bdrv_register_buf)(BlockDriverState *bs, void *host, size_t size);
+    void (*bdrv_unregister_buf)(BlockDriverState *bs, void *host);
+    QLIST_ENTRY(BlockDriver) list;
+
+    /*
+     * Pointer to a NULL-terminated array of names of strong options
+     * that can be specified for bdrv_open(). A strong option is one
+     * that changes the data of a BDS.
+     * If this pointer is NULL, the array is considered empty.
+     * "filename" and "driver" are always considered strong.
+     */
+    const char *const *strong_runtime_opts;
+};
+
+static inline bool block_driver_can_compress(BlockDriver *drv)
+{
+    return drv->bdrv_co_pwritev_compressed ||
+           drv->bdrv_co_pwritev_compressed_part;
+}
+
+typedef struct BlockLimits {
+    /*
+     * Alignment requirement, in bytes, for offset/length of I/O
+     * requests. Must be a power of 2 less than INT_MAX; defaults to
+     * 1 for drivers with modern byte interfaces, and to 512
+     * otherwise.
+     */
+    uint32_t request_alignment;
+
+    /*
+     * Maximum number of bytes that can be discarded at once. Must be multiple
+     * of pdiscard_alignment, but need not be power of 2. May be 0 if no
+     * inherent 64-bit limit.
+     */
+    int64_t max_pdiscard;
+
+    /*
+     * Optimal alignment for discard requests in bytes. A power of 2
+     * is best but not mandatory.  Must be a multiple of
+     * bl.request_alignment, and must be less than max_pdiscard if
+     * that is set. May be 0 if bl.request_alignment is good enough
+     */
+    uint32_t pdiscard_alignment;
+
+    /*
+     * Maximum number of bytes that can zeroized at once. Must be multiple of
+     * pwrite_zeroes_alignment. 0 means no limit.
+     */
+    int64_t max_pwrite_zeroes;
+
+    /*
+     * Optimal alignment for write zeroes requests in bytes. A power
+     * of 2 is best but not mandatory.  Must be a multiple of
+     * bl.request_alignment, and must be less than max_pwrite_zeroes
+     * if that is set. May be 0 if bl.request_alignment is good
+     * enough
+     */
+    uint32_t pwrite_zeroes_alignment;
+
+    /*
+     * Optimal transfer length in bytes.  A power of 2 is best but not
+     * mandatory.  Must be a multiple of bl.request_alignment, or 0 if
+     * no preferred size
+     */
+    uint32_t opt_transfer;
+
+    /*
+     * Maximal transfer length in bytes.  Need not be power of 2, but
+     * must be multiple of opt_transfer and bl.request_alignment, or 0
+     * for no 32-bit limit.  For now, anything larger than INT_MAX is
+     * clamped down.
+     */
+    uint32_t max_transfer;
+
+    /*
+     * Maximal hardware transfer length in bytes.  Applies whenever
+     * transfers to the device bypass the kernel I/O scheduler, for
+     * example with SG_IO.  If larger than max_transfer or if zero,
+     * blk_get_max_hw_transfer will fall back to max_transfer.
+     */
+    uint64_t max_hw_transfer;
+
+    /*
+     * Maximal number of scatter/gather elements allowed by the hardware.
+     * Applies whenever transfers to the device bypass the kernel I/O
+     * scheduler, for example with SG_IO.  If larger than max_iov
+     * or if zero, blk_get_max_hw_iov will fall back to max_iov.
+     */
+    int max_hw_iov;
+
+
+    /* memory alignment, in bytes so that no bounce buffer is needed */
+    size_t min_mem_alignment;
+
+    /* memory alignment, in bytes, for bounce buffer */
+    size_t opt_mem_alignment;
+
+    /* maximum number of iovec elements */
+    int max_iov;
+} BlockLimits;
+
+typedef struct BdrvOpBlocker BdrvOpBlocker;
+
+typedef struct BdrvAioNotifier {
+    void (*attached_aio_context)(AioContext *new_context, void *opaque);
+    void (*detach_aio_context)(void *opaque);
+
+    void *opaque;
+    bool deleted;
+
+    QLIST_ENTRY(BdrvAioNotifier) list;
+} BdrvAioNotifier;
+
+struct BdrvChildClass {
+    /*
+     * If true, bdrv_replace_node() doesn't change the node this BdrvChild
+     * points to.
+     */
+    bool stay_at_node;
+
+    /*
+     * If true, the parent is a BlockDriverState and bdrv_next_all_states()
+     * will return it. This information is used for drain_all, where every node
+     * will be drained separately, so the drain only needs to be propagated to
+     * non-BDS parents.
+     */
+    bool parent_is_bds;
+
+    void (*inherit_options)(BdrvChildRole role, bool parent_is_format,
+                            int *child_flags, QDict *child_options,
+                            int parent_flags, QDict *parent_options);
+
+    void (*change_media)(BdrvChild *child, bool load);
+    void (*resize)(BdrvChild *child);
+
+    /*
+     * Returns a name that is supposedly more useful for human users than the
+     * node name for identifying the node in question (in particular, a BB
+     * name), or NULL if the parent can't provide a better name.
+     */
+    const char *(*get_name)(BdrvChild *child);
+
+    /*
+     * Returns a malloced string that describes the parent of the child for a
+     * human reader. This could be a node-name, BlockBackend name, qdev ID or
+     * QOM path of the device owning the BlockBackend, job type and ID etc. The
+     * caller is responsible for freeing the memory.
+     */
+    char *(*get_parent_desc)(BdrvChild *child);
+
+    /*
+     * If this pair of functions is implemented, the parent doesn't issue new
+     * requests after returning from .drained_begin() until .drained_end() is
+     * called.
+     *
+     * These functions must not change the graph (and therefore also must not
+     * call aio_poll(), which could change the graph indirectly).
+     *
+     * If drained_end() schedules background operations, it must atomically
+     * increment *drained_end_counter for each such operation and atomically
+     * decrement it once the operation has settled.
+     *
+     * Note that this can be nested. If drained_begin() was called twice, new
+     * I/O is allowed only after drained_end() was called twice, too.
+     */
+    void (*drained_begin)(BdrvChild *child);
+    void (*drained_end)(BdrvChild *child, int *drained_end_counter);
+
+    /*
+     * Returns whether the parent has pending requests for the child. This
+     * callback is polled after .drained_begin() has been called until all
+     * activity on the child has stopped.
+     */
+    bool (*drained_poll)(BdrvChild *child);
+
+    /*
+     * Notifies the parent that the child has been activated/inactivated (e.g.
+     * when migration is completing) and it can start/stop requesting
+     * permissions and doing I/O on it.
+     */
+    void (*activate)(BdrvChild *child, Error **errp);
+    int (*inactivate)(BdrvChild *child);
+
+    void (*attach)(BdrvChild *child);
+    void (*detach)(BdrvChild *child);
+
+    /*
+     * Notifies the parent that the filename of its child has changed (e.g.
+     * because the direct child was removed from the backing chain), so that it
+     * can update its reference.
+     */
+    int (*update_filename)(BdrvChild *child, BlockDriverState *new_base,
+                           const char *filename, Error **errp);
+
+    bool (*can_set_aio_ctx)(BdrvChild *child, AioContext *ctx,
+                            GSList **ignore, Error **errp);
+    void (*set_aio_ctx)(BdrvChild *child, AioContext *ctx, GSList **ignore);
+
+    AioContext *(*get_parent_aio_context)(BdrvChild *child);
+};
+
+extern const BdrvChildClass child_of_bds;
+
+struct BdrvChild {
+    BlockDriverState *bs;
+    char *name;
+    const BdrvChildClass *klass;
+    BdrvChildRole role;
+    void *opaque;
+
+    /**
+     * Granted permissions for operating on this BdrvChild (BLK_PERM_* bitmask)
+     */
+    uint64_t perm;
+
+    /**
+     * Permissions that can still be granted to other users of @bs while this
+     * BdrvChild is still attached to it. (BLK_PERM_* bitmask)
+     */
+    uint64_t shared_perm;
+
+    /*
+     * This link is frozen: the child can neither be replaced nor
+     * detached from the parent.
+     */
+    bool frozen;
+
+    /*
+     * How many times the parent of this child has been drained
+     * (through klass->drained_*).
+     * Usually, this is equal to bs->quiesce_counter (potentially
+     * reduced by bdrv_drain_all_count).  It may differ while the
+     * child is entering or leaving a drained section.
+     */
+    int parent_quiesce_counter;
+
+    QLIST_ENTRY(BdrvChild) next;
+    QLIST_ENTRY(BdrvChild) next_parent;
+};
+
+/*
+ * Allows bdrv_co_block_status() to cache one data region for a
+ * protocol node.
+ *
+ * @valid: Whether the cache is valid (should be accessed with atomic
+ *         functions so this can be reset by RCU readers)
+ * @data_start: Offset where we know (or strongly assume) is data
+ * @data_end: Offset where the data region ends (which is not necessarily
+ *            the start of a zeroed region)
+ */
+typedef struct BdrvBlockStatusCache {
+    struct rcu_head rcu;
+
+    bool valid;
+    int64_t data_start;
+    int64_t data_end;
+} BdrvBlockStatusCache;
+
+struct BlockDriverState {
+    /*
+     * Protected by big QEMU lock or read-only after opening.  No special
+     * locking needed during I/O...
+     */
+    int open_flags; /* flags used to open the file, re-used for re-open */
+    bool encrypted; /* if true, the media is encrypted */
+    bool sg;        /* if true, the device is a /dev/sg* */
+    bool probed;    /* if true, format was probed rather than specified */
+    bool force_share; /* if true, always allow all shared permissions */
+    bool implicit;  /* if true, this filter node was automatically inserted */
+
+    BlockDriver *drv; /* NULL means no media */
+    void *opaque;
+
+    AioContext *aio_context; /* event loop used for fd handlers, timers, etc */
+    /*
+     * long-running tasks intended to always use the same AioContext as this
+     * BDS may register themselves in this list to be notified of changes
+     * regarding this BDS's context
+     */
+    QLIST_HEAD(, BdrvAioNotifier) aio_notifiers;
+    bool walking_aio_notifiers; /* to make removal during iteration safe */
+
+    char filename[PATH_MAX];
+    /*
+     * If not empty, this image is a diff in relation to backing_file.
+     * Note that this is the name given in the image header and
+     * therefore may or may not be equal to .backing->bs->filename.
+     * If this field contains a relative path, it is to be resolved
+     * relatively to the overlay's location.
+     */
+    char backing_file[PATH_MAX];
+    /*
+     * The backing filename indicated by the image header.  Contrary
+     * to backing_file, if we ever open this file, auto_backing_file
+     * is replaced by the resulting BDS's filename (i.e. after a
+     * bdrv_refresh_filename() run).
+     */
+    char auto_backing_file[PATH_MAX];
+    char backing_format[16]; /* if non-zero and backing_file exists */
+
+    QDict *full_open_options;
+    char exact_filename[PATH_MAX];
+
+    BdrvChild *backing;
+    BdrvChild *file;
+
+    /* I/O Limits */
+    BlockLimits bl;
+
+    /*
+     * Flags honored during pread
+     */
+    unsigned int supported_read_flags;
+    /*
+     * Flags honored during pwrite (so far: BDRV_REQ_FUA,
+     * BDRV_REQ_WRITE_UNCHANGED).
+     * If a driver does not support BDRV_REQ_WRITE_UNCHANGED, those
+     * writes will be issued as normal writes without the flag set.
+     * This is important to note for drivers that do not explicitly
+     * request a WRITE permission for their children and instead take
+     * the same permissions as their parent did (this is commonly what
+     * block filters do).  Such drivers have to be aware that the
+     * parent may have taken a WRITE_UNCHANGED permission only and is
+     * issuing such requests.  Drivers either must make sure that
+     * these requests do not result in plain WRITE accesses (usually
+     * by supporting BDRV_REQ_WRITE_UNCHANGED, and then forwarding
+     * every incoming write request as-is, including potentially that
+     * flag), or they have to explicitly take the WRITE permission for
+     * their children.
+     */
+    unsigned int 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;
+    /*
+     * Flags honoured during truncate (so far: BDRV_REQ_ZERO_WRITE).
+     *
+     * If BDRV_REQ_ZERO_WRITE is given, the truncate operation must make sure
+     * that any added space reads as all zeros. If this can't be guaranteed,
+     * the operation must fail.
+     */
+    unsigned int supported_truncate_flags;
+
+    /* the following member gives a name to every node on the bs graph. */
+    char node_name[32];
+    /* element of the list of named nodes building the graph */
+    QTAILQ_ENTRY(BlockDriverState) node_list;
+    /* element of the list of all BlockDriverStates (all_bdrv_states) */
+    QTAILQ_ENTRY(BlockDriverState) bs_list;
+    /* element of the list of monitor-owned BDS */
+    QTAILQ_ENTRY(BlockDriverState) monitor_list;
+    int refcnt;
+
+    /* operation blockers. Protected by BQL. */
+    QLIST_HEAD(, BdrvOpBlocker) op_blockers[BLOCK_OP_TYPE_MAX];
+
+    /*
+     * The node that this node inherited default options from (and a reopen on
+     * which can affect this node by changing these defaults). This is always a
+     * parent node of this node.
+     */
+    BlockDriverState *inherits_from;
+    QLIST_HEAD(, BdrvChild) children;
+    QLIST_HEAD(, BdrvChild) parents;
+
+    QDict *options;
+    QDict *explicit_options;
+    BlockdevDetectZeroesOptions detect_zeroes;
+
+    /* The error object in use for blocking operations on backing_hd */
+    Error *backing_blocker;
+
+    /* Protected by AioContext lock */
+
+    /*
+     * If we are reading a disk image, give its size in sectors.
+     * Generally read-only; it is written to by load_snapshot and
+     * save_snaphost, but the block layer is quiescent during those.
+     */
+    int64_t total_sectors;
+
+    /* threshold limit for writes, in bytes. "High water mark". */
+    uint64_t write_threshold_offset;
+
+    /*
+     * Writing to the list requires the BQL _and_ the dirty_bitmap_mutex.
+     * Reading from the list can be done with either the BQL or the
+     * dirty_bitmap_mutex.  Modifying a bitmap only requires
+     * dirty_bitmap_mutex.
+     */
+    QemuMutex dirty_bitmap_mutex;
+    QLIST_HEAD(, BdrvDirtyBitmap) dirty_bitmaps;
+
+    /* Offset after the highest byte written to */
+    Stat64 wr_highest_offset;
+
+    /*
+     * If true, copy read backing sectors into image.  Can be >1 if more
+     * than one client has requested copy-on-read.  Accessed with atomic
+     * ops.
+     */
+    int copy_on_read;
+
+    /*
+     * number of in-flight requests; overall and serialising.
+     * Accessed with atomic ops.
+     */
+    unsigned int in_flight;
+    unsigned int serialising_in_flight;
+
+    /*
+     * counter for nested bdrv_io_plug.
+     * Accessed with atomic ops.
+     */
+    unsigned io_plugged;
+
+    /* do we need to tell the quest if we have a volatile write cache? */
+    int enable_write_cache;
+
+    /* Accessed with atomic ops.  */
+    int quiesce_counter;
+    int recursive_quiesce_counter;
+
+    unsigned int write_gen;               /* Current data generation */
+
+    /* Protected by reqs_lock.  */
+    CoMutex reqs_lock;
+    QLIST_HEAD(, BdrvTrackedRequest) tracked_requests;
+    CoQueue flush_queue;                  /* Serializing flush queue */
+    bool active_flush_req;                /* Flush request in flight? */
+
+    /* Only read/written by whoever has set active_flush_req to true.  */
+    unsigned int flushed_gen;             /* Flushed write generation */
+
+    /* BdrvChild links to this node may never be frozen */
+    bool never_freeze;
+
+    /* Lock for block-status cache RCU writers */
+    CoMutex bsc_modify_lock;
+    /* Always non-NULL, but must only be dereferenced under an RCU read guard */
+    BdrvBlockStatusCache *block_status_cache;
+};
+
+struct BlockBackendRootState {
+    int open_flags;
+    BlockdevDetectZeroesOptions detect_zeroes;
+};
+
+typedef enum BlockMirrorBackingMode {
+    /*
+     * Reuse the existing backing chain from the source for the target.
+     * - sync=full: Set backing BDS to NULL.
+     * - sync=top:  Use source's backing BDS.
+     * - sync=none: Use source as the backing BDS.
+     */
+    MIRROR_SOURCE_BACKING_CHAIN,
+
+    /* Open the target's backing chain completely anew */
+    MIRROR_OPEN_BACKING_CHAIN,
+
+    /* Do not change the target's backing BDS after job completion */
+    MIRROR_LEAVE_BACKING_CHAIN,
+} BlockMirrorBackingMode;
+
+
+/*
+ * Essential block drivers which must always be statically linked into qemu, and
+ * which therefore can be accessed without using bdrv_find_format()
+ */
+extern BlockDriver bdrv_file;
+extern BlockDriver bdrv_raw;
+extern BlockDriver bdrv_qcow2;
+
+extern unsigned int bdrv_drain_all_count;
+extern QemuOptsList bdrv_create_opts_simple;
+
+/* Common functions that are neither I/O nor Global State */
+
+static inline BlockDriverState *child_bs(BdrvChild *child)
+{
+    return child ? child->bs : NULL;
+}
+
+int bdrv_check_request(int64_t offset, int64_t bytes, Error **errp);
+int get_tmp_filename(char *filename, int size);
+void bdrv_parse_filename_strip_prefix(const char *filename, const char *prefix,
+                                      QDict *options);
+
+bool bdrv_backing_overridden(BlockDriverState *bs);
+
+int bdrv_check_qiov_request(int64_t offset, int64_t bytes,
+                            QEMUIOVector *qiov, size_t qiov_offset,
+                            Error **errp);
+
+#ifdef _WIN32
+int is_windows_drive(const char *filename);
+#endif
+
+#endif /* BLOCK_INT_COMMON_H */
diff --git a/include/block/block_int-global-state.h b/include/block/block_int-global-state.h
new file mode 100644
index 0000000000..d08e80222c
--- /dev/null
+++ b/include/block/block_int-global-state.h
@@ -0,0 +1,319 @@
+/*
+ * QEMU System Emulator block driver
+ *
+ * Copyright (c) 2003 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef BLOCK_INT_GLOBAL_STATE_H
+#define BLOCK_INT_GLOBAL_STATE_H
+
+#include "block_int-common.h"
+
+/*
+ * Global state (GS) API. These functions run under the BQL lock.
+ *
+ * See include/block/block-global-state.h for more information about
+ * the GS API.
+ */
+
+void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent);
+void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent);
+
+BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size,
+                            const char *filename);
+
+/**
+ * stream_start:
+ * @job_id: The id of the newly-created job, or %NULL to use the
+ * device name of @bs.
+ * @bs: Block device to operate on.
+ * @base: Block device that will become the new base, or %NULL to
+ * flatten the whole backing file chain onto @bs.
+ * @backing_file_str: The file name that will be written to @bs as the
+ * the new backing file if the job completes. Ignored if @base is %NULL.
+ * @creation_flags: Flags that control the behavior of the Job lifetime.
+ *                  See @BlockJobCreateFlags
+ * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
+ * @on_error: The action to take upon error.
+ * @filter_node_name: The node name that should be assigned to the filter
+ *                    driver that the stream job inserts into the graph above
+ *                    @bs. NULL means that a node name should be autogenerated.
+ * @errp: Error object.
+ *
+ * Start a streaming operation on @bs.  Clusters that are unallocated
+ * in @bs, but allocated in any image between @base and @bs (both
+ * exclusive) will be written to @bs.  At the end of a successful
+ * streaming job, the backing file of @bs will be changed to
+ * @backing_file_str in the written image and to @base in the live
+ * BlockDriverState.
+ */
+void stream_start(const char *job_id, BlockDriverState *bs,
+                  BlockDriverState *base, const char *backing_file_str,
+                  BlockDriverState *bottom,
+                  int creation_flags, int64_t speed,
+                  BlockdevOnError on_error,
+                  const char *filter_node_name,
+                  Error **errp);
+
+/**
+ * commit_start:
+ * @job_id: The id of the newly-created job, or %NULL to use the
+ * device name of @bs.
+ * @bs: Active block device.
+ * @top: Top block device to be committed.
+ * @base: Block device that will be written into, and become the new top.
+ * @creation_flags: Flags that control the behavior of the Job lifetime.
+ *                  See @BlockJobCreateFlags
+ * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
+ * @on_error: The action to take upon error.
+ * @backing_file_str: String to use as the backing file in @top's overlay
+ * @filter_node_name: The node name that should be assigned to the filter
+ * driver that the commit job inserts into the graph above @top. NULL means
+ * that a node name should be autogenerated.
+ * @errp: Error object.
+ *
+ */
+void commit_start(const char *job_id, BlockDriverState *bs,
+                  BlockDriverState *base, BlockDriverState *top,
+                  int creation_flags, int64_t speed,
+                  BlockdevOnError on_error, const char *backing_file_str,
+                  const char *filter_node_name, Error **errp);
+/**
+ * commit_active_start:
+ * @job_id: The id of the newly-created job, or %NULL to use the
+ * device name of @bs.
+ * @bs: Active block device to be committed.
+ * @base: Block device that will be written into, and become the new top.
+ * @creation_flags: Flags that control the behavior of the Job lifetime.
+ *                  See @BlockJobCreateFlags
+ * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
+ * @on_error: The action to take upon error.
+ * @filter_node_name: The node name that should be assigned to the filter
+ * driver that the commit job inserts into the graph above @bs. NULL means that
+ * a node name should be autogenerated.
+ * @cb: Completion function for the job.
+ * @opaque: Opaque pointer value passed to @cb.
+ * @auto_complete: Auto complete the job.
+ * @errp: Error object.
+ *
+ */
+BlockJob *commit_active_start(const char *job_id, BlockDriverState *bs,
+                              BlockDriverState *base, int creation_flags,
+                              int64_t speed, BlockdevOnError on_error,
+                              const char *filter_node_name,
+                              BlockCompletionFunc *cb, void *opaque,
+                              bool auto_complete, Error **errp);
+/*
+ * mirror_start:
+ * @job_id: The id of the newly-created job, or %NULL to use the
+ * device name of @bs.
+ * @bs: Block device to operate on.
+ * @target: Block device to write to.
+ * @replaces: Block graph node name to replace once the mirror is done. Can
+ *            only be used when full mirroring is selected.
+ * @creation_flags: Flags that control the behavior of the Job lifetime.
+ *                  See @BlockJobCreateFlags
+ * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
+ * @granularity: The chosen granularity for the dirty bitmap.
+ * @buf_size: The amount of data that can be in flight at one time.
+ * @mode: Whether to collapse all images in the chain to the target.
+ * @backing_mode: How to establish the target's backing chain after completion.
+ * @zero_target: Whether the target should be explicitly zero-initialized
+ * @on_source_error: The action to take upon error reading from the source.
+ * @on_target_error: The action to take upon error writing to the target.
+ * @unmap: Whether to unmap target where source sectors only contain zeroes.
+ * @filter_node_name: The node name that should be assigned to the filter
+ * driver that the mirror job inserts into the graph above @bs. NULL means that
+ * a node name should be autogenerated.
+ * @copy_mode: When to trigger writes to the target.
+ * @errp: Error object.
+ *
+ * Start a mirroring operation on @bs.  Clusters that are allocated
+ * in @bs will be written to @target until the job is cancelled or
+ * manually completed.  At the end of a successful mirroring job,
+ * @bs will be switched to read from @target.
+ */
+void mirror_start(const char *job_id, BlockDriverState *bs,
+                  BlockDriverState *target, const char *replaces,
+                  int creation_flags, int64_t speed,
+                  uint32_t granularity, int64_t buf_size,
+                  MirrorSyncMode mode, BlockMirrorBackingMode backing_mode,
+                  bool zero_target,
+                  BlockdevOnError on_source_error,
+                  BlockdevOnError on_target_error,
+                  bool unmap, const char *filter_node_name,
+                  MirrorCopyMode copy_mode, Error **errp);
+
+/*
+ * backup_job_create:
+ * @job_id: The id of the newly-created job, or %NULL to use the
+ * device name of @bs.
+ * @bs: Block device to operate on.
+ * @target: Block device to write to.
+ * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
+ * @sync_mode: What parts of the disk image should be copied to the destination.
+ * @sync_bitmap: The dirty bitmap if sync_mode is 'bitmap' or 'incremental'
+ * @bitmap_mode: The bitmap synchronization policy to use.
+ * @perf: Performance options. All actual fields assumed to be present,
+ *        all ".has_*" fields are ignored.
+ * @on_source_error: The action to take upon error reading from the source.
+ * @on_target_error: The action to take upon error writing to the target.
+ * @creation_flags: Flags that control the behavior of the Job lifetime.
+ *                  See @BlockJobCreateFlags
+ * @cb: Completion function for the job.
+ * @opaque: Opaque pointer value passed to @cb.
+ * @txn: Transaction that this job is part of (may be NULL).
+ *
+ * Create a backup operation on @bs.  Clusters in @bs are written to @target
+ * until the job is cancelled or manually completed.
+ */
+BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
+                            BlockDriverState *target, int64_t speed,
+                            MirrorSyncMode sync_mode,
+                            BdrvDirtyBitmap *sync_bitmap,
+                            BitmapSyncMode bitmap_mode,
+                            bool compress,
+                            const char *filter_node_name,
+                            BackupPerf *perf,
+                            BlockdevOnError on_source_error,
+                            BlockdevOnError on_target_error,
+                            int creation_flags,
+                            BlockCompletionFunc *cb, void *opaque,
+                            JobTxn *txn, Error **errp);
+
+BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
+                                  const char *child_name,
+                                  const BdrvChildClass *child_class,
+                                  BdrvChildRole child_role,
+                                  uint64_t perm, uint64_t shared_perm,
+                                  void *opaque, Error **errp);
+void bdrv_root_unref_child(BdrvChild *child);
+
+void bdrv_get_cumulative_perm(BlockDriverState *bs, uint64_t *perm,
+                              uint64_t *shared_perm);
+
+/**
+ * Sets a BdrvChild's permissions.  Avoid if the parent is a BDS; use
+ * bdrv_child_refresh_perms() instead and make the parent's
+ * .bdrv_child_perm() implementation return the correct values.
+ */
+int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
+                            Error **errp);
+
+/**
+ * Calls bs->drv->bdrv_child_perm() and updates the child's permission
+ * masks with the result.
+ * Drivers should invoke this function whenever an event occurs that
+ * makes their .bdrv_child_perm() implementation return different
+ * values than before, but which will not result in the block layer
+ * automatically refreshing the permissions.
+ */
+int bdrv_child_refresh_perms(BlockDriverState *bs, BdrvChild *c, Error **errp);
+
+bool bdrv_recurse_can_replace(BlockDriverState *bs,
+                              BlockDriverState *to_replace);
+
+/*
+ * Default implementation for BlockDriver.bdrv_child_perm() that can
+ * be used by block filters and image formats, as long as they use the
+ * child_of_bds child class and set an appropriate BdrvChildRole.
+ */
+void bdrv_default_perms(BlockDriverState *bs, BdrvChild *c,
+                        BdrvChildRole role, BlockReopenQueue *reopen_queue,
+                        uint64_t perm, uint64_t shared,
+                        uint64_t *nperm, uint64_t *nshared);
+
+const char *bdrv_get_parent_name(const BlockDriverState *bs);
+void blk_dev_change_media_cb(BlockBackend *blk, bool load, Error **errp);
+bool blk_dev_has_removable_media(BlockBackend *blk);
+void blk_dev_eject_request(BlockBackend *blk, bool force);
+bool blk_dev_is_medium_locked(BlockBackend *blk);
+
+void bdrv_restore_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap *backup);
+
+void bdrv_set_monitor_owned(BlockDriverState *bs);
+
+void blockdev_close_all_bdrv_states(void);
+
+BlockDriverState *bds_tree_init(QDict *bs_opts, Error **errp);
+
+/**
+ * Simple implementation of bdrv_co_create_opts for protocol drivers
+ * which only support creation via opening a file
+ * (usually existing raw storage device)
+ */
+int coroutine_fn bdrv_co_create_opts_simple(BlockDriver *drv,
+                                            const char *filename,
+                                            QemuOpts *opts,
+                                            Error **errp);
+
+BdrvDirtyBitmap *block_dirty_bitmap_lookup(const char *node,
+                                           const char *name,
+                                           BlockDriverState **pbs,
+                                           Error **errp);
+BdrvDirtyBitmap *block_dirty_bitmap_merge(const char *node, const char *target,
+                                          BlockDirtyBitmapMergeSourceList *bms,
+                                          HBitmap **backup, Error **errp);
+BdrvDirtyBitmap *block_dirty_bitmap_remove(const char *node, const char *name,
+                                           bool release,
+                                           BlockDriverState **bitmap_bs,
+                                           Error **errp);
+
+
+BlockDriverState *bdrv_skip_implicit_filters(BlockDriverState *bs);
+
+/**
+ * bdrv_add_aio_context_notifier:
+ *
+ * If a long-running job intends to be always run in the same AioContext as a
+ * certain BDS, it may use this function to be notified of changes regarding the
+ * association of the BDS to an AioContext.
+ *
+ * attached_aio_context() is called after the target BDS has been attached to a
+ * new AioContext; detach_aio_context() is called before the target BDS is being
+ * detached from its old AioContext.
+ */
+void bdrv_add_aio_context_notifier(BlockDriverState *bs,
+        void (*attached_aio_context)(AioContext *new_context, void *opaque),
+        void (*detach_aio_context)(void *opaque), void *opaque);
+
+/**
+ * bdrv_remove_aio_context_notifier:
+ *
+ * Unsubscribe of change notifications regarding the BDS's AioContext. The
+ * parameters given here have to be the same as those given to
+ * bdrv_add_aio_context_notifier().
+ */
+void bdrv_remove_aio_context_notifier(BlockDriverState *bs,
+                                      void (*aio_context_attached)(AioContext *,
+                                                                   void *),
+                                      void (*aio_context_detached)(void *),
+                                      void *opaque);
+
+/**
+ * End all quiescent sections started by bdrv_drain_all_begin(). This is
+ * needed when deleting a BDS before bdrv_drain_all_end() is called.
+ *
+ * NOTE: this is an internal helper for bdrv_close() *only*. No one else
+ * should call it.
+ */
+void bdrv_drain_all_end_quiesce(BlockDriverState *bs);
+
+#endif /* BLOCK_INT_GLOBAL_STATE*/
diff --git a/include/block/block_int-io.h b/include/block/block_int-io.h
new file mode 100644
index 0000000000..f74eb46ff8
--- /dev/null
+++ b/include/block/block_int-io.h
@@ -0,0 +1,163 @@
+/*
+ * QEMU System Emulator block driver
+ *
+ * Copyright (c) 2003 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef BLOCK_INT_IO_H
+#define BLOCK_INT_IO_H
+
+#include "block_int-common.h"
+
+/*
+ * I/O API functions. These functions are thread-safe.
+ *
+ * See include/block/block-io.h for more information about
+ * the I/O API.
+ */
+
+int coroutine_fn bdrv_co_preadv(BdrvChild *child,
+    int64_t offset, int64_t bytes, QEMUIOVector *qiov,
+    BdrvRequestFlags flags);
+int coroutine_fn bdrv_co_preadv_part(BdrvChild *child,
+    int64_t offset, int64_t bytes,
+    QEMUIOVector *qiov, size_t qiov_offset, BdrvRequestFlags flags);
+int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
+    int64_t offset, int64_t bytes, QEMUIOVector *qiov,
+    BdrvRequestFlags flags);
+int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child,
+    int64_t offset, int64_t bytes,
+    QEMUIOVector *qiov, size_t qiov_offset, BdrvRequestFlags flags);
+
+static inline int coroutine_fn bdrv_co_pread(BdrvChild *child,
+    int64_t offset, unsigned int bytes, void *buf, BdrvRequestFlags flags)
+{
+    QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes);
+
+    return bdrv_co_preadv(child, offset, bytes, &qiov, flags);
+}
+
+static inline int coroutine_fn bdrv_co_pwrite(BdrvChild *child,
+    int64_t offset, unsigned int bytes, void *buf, BdrvRequestFlags flags)
+{
+    QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes);
+
+    return bdrv_co_pwritev(child, offset, bytes, &qiov, flags);
+}
+
+bool coroutine_fn bdrv_make_request_serialising(BdrvTrackedRequest *req,
+                                                uint64_t align);
+BdrvTrackedRequest *coroutine_fn bdrv_co_get_self_request(BlockDriverState *bs);
+
+/**
+ * bdrv_wakeup:
+ * @bs: The BlockDriverState for which an I/O operation has been completed.
+ *
+ * Wake up the main thread if it is waiting on BDRV_POLL_WHILE.  During
+ * synchronous I/O on a BlockDriverState that is attached to another
+ * I/O thread, the main thread lets the I/O thread's event loop run,
+ * waiting for the I/O operation to complete.  A bdrv_wakeup will wake
+ * up the main thread if necessary.
+ *
+ * Manual calls to bdrv_wakeup are rarely necessary, because
+ * bdrv_dec_in_flight already calls it.
+ */
+void bdrv_wakeup(BlockDriverState *bs);
+
+bool blk_dev_has_tray(BlockBackend *blk);
+bool blk_dev_is_tray_open(BlockBackend *blk);
+
+void bdrv_set_dirty(BlockDriverState *bs, int64_t offset, int64_t bytes);
+
+void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out);
+bool bdrv_dirty_bitmap_merge_internal(BdrvDirtyBitmap *dest,
+                                      const BdrvDirtyBitmap *src,
+                                      HBitmap **backup, bool lock);
+
+void bdrv_inc_in_flight(BlockDriverState *bs);
+void bdrv_dec_in_flight(BlockDriverState *bs);
+
+int coroutine_fn bdrv_co_copy_range_from(BdrvChild *src, int64_t src_offset,
+                                         BdrvChild *dst, int64_t dst_offset,
+                                         int64_t bytes,
+                                         BdrvRequestFlags read_flags,
+                                         BdrvRequestFlags write_flags);
+int coroutine_fn bdrv_co_copy_range_to(BdrvChild *src, int64_t src_offset,
+                                       BdrvChild *dst, int64_t dst_offset,
+                                       int64_t bytes,
+                                       BdrvRequestFlags read_flags,
+                                       BdrvRequestFlags write_flags);
+
+int refresh_total_sectors(BlockDriverState *bs, int64_t hint);
+
+BdrvChild *bdrv_cow_child(BlockDriverState *bs);
+BdrvChild *bdrv_filter_child(BlockDriverState *bs);
+BdrvChild *bdrv_filter_or_cow_child(BlockDriverState *bs);
+BdrvChild *bdrv_primary_child(BlockDriverState *bs);
+BlockDriverState *bdrv_skip_filters(BlockDriverState *bs);
+BlockDriverState *bdrv_backing_chain_next(BlockDriverState *bs);
+
+static inline BlockDriverState *bdrv_cow_bs(BlockDriverState *bs)
+{
+    return child_bs(bdrv_cow_child(bs));
+}
+
+static inline BlockDriverState *bdrv_filter_bs(BlockDriverState *bs)
+{
+    return child_bs(bdrv_filter_child(bs));
+}
+
+static inline BlockDriverState *bdrv_filter_or_cow_bs(BlockDriverState *bs)
+{
+    return child_bs(bdrv_filter_or_cow_child(bs));
+}
+
+static inline BlockDriverState *bdrv_primary_bs(BlockDriverState *bs)
+{
+    return child_bs(bdrv_primary_child(bs));
+}
+
+/**
+ * Check whether the given offset is in the cached block-status data
+ * region.
+ *
+ * If it is, and @pnum is not NULL, *pnum is set to
+ * `bsc.data_end - offset`, i.e. how many bytes, starting from
+ * @offset, are data (according to the cache).
+ * Otherwise, *pnum is not touched.
+ */
+bool bdrv_bsc_is_data(BlockDriverState *bs, int64_t offset, int64_t *pnum);
+
+/**
+ * If [offset, offset + bytes) overlaps with the currently cached
+ * block-status region, invalidate the cache.
+ *
+ * (To be used by I/O paths that cause data regions to be zero or
+ * holes.)
+ */
+void bdrv_bsc_invalidate_range(BlockDriverState *bs,
+                               int64_t offset, int64_t bytes);
+
+/**
+ * Mark the range [offset, offset + bytes) as a data region.
+ */
+void bdrv_bsc_fill(BlockDriverState *bs, int64_t offset, int64_t bytes);
+
+#endif /* BLOCK_INT_IO_H */
diff --git a/include/block/block_int.h b/include/block/block_int.h
index f4c75e8ba9..7d50b6bbd1 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -24,1481 +24,9 @@
 #ifndef BLOCK_INT_H
 #define BLOCK_INT_H
 
-#include "block/accounting.h"
-#include "block/block.h"
-#include "block/aio-wait.h"
-#include "qemu/queue.h"
-#include "qemu/coroutine.h"
-#include "qemu/stats64.h"
-#include "qemu/timer.h"
-#include "qemu/hbitmap.h"
-#include "block/snapshot.h"
-#include "qemu/throttle.h"
-#include "qemu/rcu.h"
+#include "block_int-global-state.h"
+#include "block_int-io.h"
 
-#define BLOCK_FLAG_LAZY_REFCOUNTS   8
-
-#define BLOCK_OPT_SIZE              "size"
-#define BLOCK_OPT_ENCRYPT           "encryption"
-#define BLOCK_OPT_ENCRYPT_FORMAT    "encrypt.format"
-#define BLOCK_OPT_COMPAT6           "compat6"
-#define BLOCK_OPT_HWVERSION         "hwversion"
-#define BLOCK_OPT_BACKING_FILE      "backing_file"
-#define BLOCK_OPT_BACKING_FMT       "backing_fmt"
-#define BLOCK_OPT_CLUSTER_SIZE      "cluster_size"
-#define BLOCK_OPT_TABLE_SIZE        "table_size"
-#define BLOCK_OPT_PREALLOC          "preallocation"
-#define BLOCK_OPT_SUBFMT            "subformat"
-#define BLOCK_OPT_COMPAT_LEVEL      "compat"
-#define BLOCK_OPT_LAZY_REFCOUNTS    "lazy_refcounts"
-#define BLOCK_OPT_ADAPTER_TYPE      "adapter_type"
-#define BLOCK_OPT_REDUNDANCY        "redundancy"
-#define BLOCK_OPT_NOCOW             "nocow"
-#define BLOCK_OPT_EXTENT_SIZE_HINT  "extent_size_hint"
-#define BLOCK_OPT_OBJECT_SIZE       "object_size"
-#define BLOCK_OPT_REFCOUNT_BITS     "refcount_bits"
-#define BLOCK_OPT_DATA_FILE         "data_file"
-#define BLOCK_OPT_DATA_FILE_RAW     "data_file_raw"
-#define BLOCK_OPT_COMPRESSION_TYPE  "compression_type"
-#define BLOCK_OPT_EXTL2             "extended_l2"
-
-#define BLOCK_PROBE_BUF_SIZE        512
-
-enum BdrvTrackedRequestType {
-    BDRV_TRACKED_READ,
-    BDRV_TRACKED_WRITE,
-    BDRV_TRACKED_DISCARD,
-    BDRV_TRACKED_TRUNCATE,
-};
-
-/*
- * That is not quite good that BdrvTrackedRequest structure is public,
- * as block/io.c is very careful about incoming offset/bytes being
- * correct. Be sure to assert bdrv_check_request() succeeded after any
- * modification of BdrvTrackedRequest object out of block/io.c
- */
-typedef struct BdrvTrackedRequest {
-    BlockDriverState *bs;
-    int64_t offset;
-    int64_t bytes;
-    enum BdrvTrackedRequestType type;
-
-    bool serialising;
-    int64_t overlap_offset;
-    int64_t overlap_bytes;
-
-    QLIST_ENTRY(BdrvTrackedRequest) list;
-    Coroutine *co; /* owner, used for deadlock detection */
-    CoQueue wait_queue; /* coroutines blocked on this request */
-
-    struct BdrvTrackedRequest *waiting_for;
-} BdrvTrackedRequest;
-
-int bdrv_check_qiov_request(int64_t offset, int64_t bytes,
-                            QEMUIOVector *qiov, size_t qiov_offset,
-                            Error **errp);
-int bdrv_check_request(int64_t offset, int64_t bytes, Error **errp);
-
-struct BlockDriver {
-    const char *format_name;
-    int instance_size;
-
-    /* set to true if the BlockDriver is a block filter. Block filters pass
-     * certain callbacks that refer to data (see block.c) to their bs->file
-     * or bs->backing (whichever one exists) if the driver doesn't implement
-     * them. Drivers that do not wish to forward must implement them and return
-     * -ENOTSUP.
-     * Note that filters are not allowed to modify data.
-     *
-     * Filters generally cannot have more than a single filtered child,
-     * because the data they present must at all times be the same as
-     * that on their filtered child.  That would be impossible to
-     * achieve for multiple filtered children.
-     * (And this filtered child must then be bs->file or bs->backing.)
-     */
-    bool is_filter;
-    /*
-     * Set to true if the BlockDriver is a format driver.  Format nodes
-     * generally do not expect their children to be other format nodes
-     * (except for backing files), and so format probing is disabled
-     * on those children.
-     */
-    bool is_format;
-    /*
-     * Return true if @to_replace can be replaced by a BDS with the
-     * same data as @bs without it affecting @bs's behavior (that is,
-     * without it being visible to @bs's parents).
-     */
-    bool (*bdrv_recurse_can_replace)(BlockDriverState *bs,
-                                     BlockDriverState *to_replace);
-
-    int (*bdrv_probe)(const uint8_t *buf, int buf_size, const char *filename);
-    int (*bdrv_probe_device)(const char *filename);
-
-    /* Any driver implementing this callback is expected to be able to handle
-     * NULL file names in its .bdrv_open() implementation */
-    void (*bdrv_parse_filename)(const char *filename, QDict *options, Error **errp);
-    /* Drivers not implementing bdrv_parse_filename nor bdrv_open should have
-     * this field set to true, except ones that are defined only by their
-     * child's bs.
-     * An example of the last type will be the quorum block driver.
-     */
-    bool bdrv_needs_filename;
-
-    /*
-     * Set if a driver can support backing files. This also implies the
-     * following semantics:
-     *
-     *  - Return status 0 of .bdrv_co_block_status means that corresponding
-     *    blocks are not allocated in this layer of backing-chain
-     *  - For such (unallocated) blocks, read will:
-     *    - fill buffer with zeros if there is no backing file
-     *    - read from the backing file otherwise, where the block layer
-     *      takes care of reading zeros beyond EOF if backing file is short
-     */
-    bool supports_backing;
-
-    /* For handling image reopen for split or non-split files */
-    int (*bdrv_reopen_prepare)(BDRVReopenState *reopen_state,
-                               BlockReopenQueue *queue, Error **errp);
-    void (*bdrv_reopen_commit)(BDRVReopenState *reopen_state);
-    void (*bdrv_reopen_commit_post)(BDRVReopenState *reopen_state);
-    void (*bdrv_reopen_abort)(BDRVReopenState *reopen_state);
-    void (*bdrv_join_options)(QDict *options, QDict *old_options);
-
-    int (*bdrv_open)(BlockDriverState *bs, QDict *options, int flags,
-                     Error **errp);
-
-    /* Protocol drivers should implement this instead of bdrv_open */
-    int (*bdrv_file_open)(BlockDriverState *bs, QDict *options, int flags,
-                          Error **errp);
-    void (*bdrv_close)(BlockDriverState *bs);
-
-
-    int coroutine_fn (*bdrv_co_create)(BlockdevCreateOptions *opts,
-                                       Error **errp);
-    int coroutine_fn (*bdrv_co_create_opts)(BlockDriver *drv,
-                                            const char *filename,
-                                            QemuOpts *opts,
-                                            Error **errp);
-
-    int coroutine_fn (*bdrv_co_amend)(BlockDriverState *bs,
-                                      BlockdevAmendOptions *opts,
-                                      bool force,
-                                      Error **errp);
-
-    int (*bdrv_amend_options)(BlockDriverState *bs,
-                              QemuOpts *opts,
-                              BlockDriverAmendStatusCB *status_cb,
-                              void *cb_opaque,
-                              bool force,
-                              Error **errp);
-
-    int (*bdrv_make_empty)(BlockDriverState *bs);
-
-    /*
-     * Refreshes the bs->exact_filename field. If that is impossible,
-     * bs->exact_filename has to be left empty.
-     */
-    void (*bdrv_refresh_filename)(BlockDriverState *bs);
-
-    /*
-     * Gathers the open options for all children into @target.
-     * A simple format driver (without backing file support) might
-     * implement this function like this:
-     *
-     *     QINCREF(bs->file->bs->full_open_options);
-     *     qdict_put(target, "file", bs->file->bs->full_open_options);
-     *
-     * If not specified, the generic implementation will simply put
-     * all children's options under their respective name.
-     *
-     * @backing_overridden is true when bs->backing seems not to be
-     * the child that would result from opening bs->backing_file.
-     * Therefore, if it is true, the backing child's options should be
-     * gathered; otherwise, there is no need since the backing child
-     * is the one implied by the image header.
-     *
-     * Note that ideally this function would not be needed.  Every
-     * block driver which implements it is probably doing something
-     * shady regarding its runtime option structure.
-     */
-    void (*bdrv_gather_child_options)(BlockDriverState *bs, QDict *target,
-                                      bool backing_overridden);
-
-    /*
-     * Returns an allocated string which is the directory name of this BDS: It
-     * will be used to make relative filenames absolute by prepending this
-     * function's return value to them.
-     */
-    char *(*bdrv_dirname)(BlockDriverState *bs, Error **errp);
-
-    /* aio */
-    BlockAIOCB *(*bdrv_aio_preadv)(BlockDriverState *bs,
-        int64_t offset, int64_t bytes, QEMUIOVector *qiov,
-        BdrvRequestFlags flags, BlockCompletionFunc *cb, void *opaque);
-    BlockAIOCB *(*bdrv_aio_pwritev)(BlockDriverState *bs,
-        int64_t offset, int64_t bytes, QEMUIOVector *qiov,
-        BdrvRequestFlags flags, BlockCompletionFunc *cb, void *opaque);
-    BlockAIOCB *(*bdrv_aio_flush)(BlockDriverState *bs,
-        BlockCompletionFunc *cb, void *opaque);
-    BlockAIOCB *(*bdrv_aio_pdiscard)(BlockDriverState *bs,
-        int64_t offset, int bytes,
-        BlockCompletionFunc *cb, void *opaque);
-
-    int coroutine_fn (*bdrv_co_readv)(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
-
-    /**
-     * @offset: position in bytes to read at
-     * @bytes: number of bytes to read
-     * @qiov: the buffers to fill with read data
-     * @flags: currently unused, always 0
-     *
-     * @offset and @bytes will be a multiple of 'request_alignment',
-     * but the length of individual @qiov elements does not have to
-     * be a multiple.
-     *
-     * @bytes will always equal the total size of @qiov, and will be
-     * no larger than 'max_transfer'.
-     *
-     * The buffer in @qiov may point directly to guest memory.
-     */
-    int coroutine_fn (*bdrv_co_preadv)(BlockDriverState *bs,
-        int64_t offset, int64_t bytes, QEMUIOVector *qiov,
-        BdrvRequestFlags flags);
-    int coroutine_fn (*bdrv_co_preadv_part)(BlockDriverState *bs,
-        int64_t offset, int64_t bytes,
-        QEMUIOVector *qiov, size_t qiov_offset, BdrvRequestFlags flags);
-    int coroutine_fn (*bdrv_co_writev)(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov, int flags);
-    /**
-     * @offset: position in bytes to write at
-     * @bytes: number of bytes to write
-     * @qiov: the buffers containing data to write
-     * @flags: zero or more bits allowed by 'supported_write_flags'
-     *
-     * @offset and @bytes will be a multiple of 'request_alignment',
-     * but the length of individual @qiov elements does not have to
-     * be a multiple.
-     *
-     * @bytes will always equal the total size of @qiov, and will be
-     * no larger than 'max_transfer'.
-     *
-     * The buffer in @qiov may point directly to guest memory.
-     */
-    int coroutine_fn (*bdrv_co_pwritev)(BlockDriverState *bs,
-        int64_t offset, int64_t bytes, QEMUIOVector *qiov,
-        BdrvRequestFlags flags);
-    int coroutine_fn (*bdrv_co_pwritev_part)(BlockDriverState *bs,
-        int64_t offset, int64_t bytes, QEMUIOVector *qiov, size_t qiov_offset,
-        BdrvRequestFlags flags);
-
-    /*
-     * Efficiently zero a region of the disk image.  Typically an image format
-     * would use a compact metadata representation to implement this.  This
-     * function pointer may be NULL or return -ENOSUP and .bdrv_co_writev()
-     * will be called instead.
-     */
-    int coroutine_fn (*bdrv_co_pwrite_zeroes)(BlockDriverState *bs,
-        int64_t offset, int64_t bytes, BdrvRequestFlags flags);
-    int coroutine_fn (*bdrv_co_pdiscard)(BlockDriverState *bs,
-        int64_t offset, int64_t bytes);
-
-    /* Map [offset, offset + nbytes) range onto a child of @bs to copy from,
-     * and invoke bdrv_co_copy_range_from(child, ...), or invoke
-     * bdrv_co_copy_range_to() if @bs is the leaf child to copy data from.
-     *
-     * See the comment of bdrv_co_copy_range for the parameter and return value
-     * semantics.
-     */
-    int coroutine_fn (*bdrv_co_copy_range_from)(BlockDriverState *bs,
-                                                BdrvChild *src,
-                                                int64_t offset,
-                                                BdrvChild *dst,
-                                                int64_t dst_offset,
-                                                int64_t bytes,
-                                                BdrvRequestFlags read_flags,
-                                                BdrvRequestFlags write_flags);
-
-    /* Map [offset, offset + nbytes) range onto a child of bs to copy data to,
-     * and invoke bdrv_co_copy_range_to(child, src, ...), or perform the copy
-     * operation if @bs is the leaf and @src has the same BlockDriver.  Return
-     * -ENOTSUP if @bs is the leaf but @src has a different BlockDriver.
-     *
-     * See the comment of bdrv_co_copy_range for the parameter and return value
-     * semantics.
-     */
-    int coroutine_fn (*bdrv_co_copy_range_to)(BlockDriverState *bs,
-                                              BdrvChild *src,
-                                              int64_t src_offset,
-                                              BdrvChild *dst,
-                                              int64_t dst_offset,
-                                              int64_t bytes,
-                                              BdrvRequestFlags read_flags,
-                                              BdrvRequestFlags write_flags);
-
-    /*
-     * Building block for bdrv_block_status[_above] and
-     * bdrv_is_allocated[_above].  The driver should answer only
-     * according to the current layer, and should only need to set
-     * BDRV_BLOCK_DATA, BDRV_BLOCK_ZERO, BDRV_BLOCK_OFFSET_VALID,
-     * and/or BDRV_BLOCK_RAW; if the current layer defers to a backing
-     * layer, the result should be 0 (and not BDRV_BLOCK_ZERO).  See
-     * block.h for the overall meaning of the bits.  As a hint, the
-     * flag want_zero is true if the caller cares more about precise
-     * mappings (favor accurate _OFFSET_VALID/_ZERO) or false for
-     * overall allocation (favor larger *pnum, perhaps by reporting
-     * _DATA instead of _ZERO).  The block layer guarantees input
-     * clamped to bdrv_getlength() and aligned to request_alignment,
-     * as well as non-NULL pnum, map, and file; in turn, the driver
-     * must return an error or set pnum to an aligned non-zero value.
-     *
-     * Note that @bytes is just a hint on how big of a region the
-     * caller wants to inspect.  It is not a limit on *pnum.
-     * Implementations are free to return larger values of *pnum if
-     * doing so does not incur a performance penalty.
-     *
-     * block/io.c's bdrv_co_block_status() will utilize an unclamped
-     * *pnum value for the block-status cache on protocol nodes, prior
-     * to clamping *pnum for return to its caller.
-     */
-    int coroutine_fn (*bdrv_co_block_status)(BlockDriverState *bs,
-        bool want_zero, int64_t offset, int64_t bytes, int64_t *pnum,
-        int64_t *map, BlockDriverState **file);
-
-    /*
-     * This informs the driver that we are no longer interested in the result
-     * of in-flight requests, so don't waste the time if possible.
-     *
-     * One example usage is to avoid waiting for an nbd target node reconnect
-     * timeout during job-cancel with force=true.
-     */
-    void (*bdrv_cancel_in_flight)(BlockDriverState *bs);
-
-    /*
-     * Invalidate any cached meta-data.
-     */
-    void coroutine_fn (*bdrv_co_invalidate_cache)(BlockDriverState *bs,
-                                                  Error **errp);
-    int (*bdrv_inactivate)(BlockDriverState *bs);
-
-    /*
-     * Flushes all data for all layers by calling bdrv_co_flush for underlying
-     * layers, if needed. This function is needed for deterministic
-     * synchronization of the flush finishing callback.
-     */
-    int coroutine_fn (*bdrv_co_flush)(BlockDriverState *bs);
-
-    /* Delete a created file. */
-    int coroutine_fn (*bdrv_co_delete_file)(BlockDriverState *bs,
-                                            Error **errp);
-
-    /*
-     * Flushes all data that was already written to the OS all the way down to
-     * the disk (for example file-posix.c calls fsync()).
-     */
-    int coroutine_fn (*bdrv_co_flush_to_disk)(BlockDriverState *bs);
-
-    /*
-     * Flushes all internal caches to the OS. The data may still sit in a
-     * writeback cache of the host OS, but it will survive a crash of the qemu
-     * process.
-     */
-    int coroutine_fn (*bdrv_co_flush_to_os)(BlockDriverState *bs);
-
-    /*
-     * Drivers setting this field must be able to work with just a plain
-     * filename with '<protocol_name>:' as a prefix, and no other options.
-     * Options may be extracted from the filename by implementing
-     * bdrv_parse_filename.
-     */
-    const char *protocol_name;
-
-    /*
-     * Truncate @bs to @offset bytes using the given @prealloc mode
-     * when growing.  Modes other than PREALLOC_MODE_OFF should be
-     * rejected when shrinking @bs.
-     *
-     * If @exact is true, @bs must be resized to exactly @offset.
-     * Otherwise, it is sufficient for @bs (if it is a host block
-     * device and thus there is no way to resize it) to be at least
-     * @offset bytes in length.
-     *
-     * If @exact is true and this function fails but would succeed
-     * with @exact = false, it should return -ENOTSUP.
-     */
-    int coroutine_fn (*bdrv_co_truncate)(BlockDriverState *bs, int64_t offset,
-                                         bool exact, PreallocMode prealloc,
-                                         BdrvRequestFlags flags, Error **errp);
-
-    int64_t (*bdrv_getlength)(BlockDriverState *bs);
-    bool has_variable_length;
-    int64_t (*bdrv_get_allocated_file_size)(BlockDriverState *bs);
-    BlockMeasureInfo *(*bdrv_measure)(QemuOpts *opts, BlockDriverState *in_bs,
-                                      Error **errp);
-
-    int coroutine_fn (*bdrv_co_pwritev_compressed)(BlockDriverState *bs,
-        int64_t offset, int64_t bytes, QEMUIOVector *qiov);
-    int coroutine_fn (*bdrv_co_pwritev_compressed_part)(BlockDriverState *bs,
-        int64_t offset, int64_t bytes, QEMUIOVector *qiov, size_t qiov_offset);
-
-    int (*bdrv_snapshot_create)(BlockDriverState *bs,
-                                QEMUSnapshotInfo *sn_info);
-    int (*bdrv_snapshot_goto)(BlockDriverState *bs,
-                              const char *snapshot_id);
-    int (*bdrv_snapshot_delete)(BlockDriverState *bs,
-                                const char *snapshot_id,
-                                const char *name,
-                                Error **errp);
-    int (*bdrv_snapshot_list)(BlockDriverState *bs,
-                              QEMUSnapshotInfo **psn_info);
-    int (*bdrv_snapshot_load_tmp)(BlockDriverState *bs,
-                                  const char *snapshot_id,
-                                  const char *name,
-                                  Error **errp);
-    int (*bdrv_get_info)(BlockDriverState *bs, BlockDriverInfo *bdi);
-    ImageInfoSpecific *(*bdrv_get_specific_info)(BlockDriverState *bs,
-                                                 Error **errp);
-    BlockStatsSpecific *(*bdrv_get_specific_stats)(BlockDriverState *bs);
-
-    int coroutine_fn (*bdrv_save_vmstate)(BlockDriverState *bs,
-                                          QEMUIOVector *qiov,
-                                          int64_t pos);
-    int coroutine_fn (*bdrv_load_vmstate)(BlockDriverState *bs,
-                                          QEMUIOVector *qiov,
-                                          int64_t pos);
-
-    int (*bdrv_change_backing_file)(BlockDriverState *bs,
-        const char *backing_file, const char *backing_fmt);
-
-    /* removable device specific */
-    bool (*bdrv_is_inserted)(BlockDriverState *bs);
-    void (*bdrv_eject)(BlockDriverState *bs, bool eject_flag);
-    void (*bdrv_lock_medium)(BlockDriverState *bs, bool locked);
-
-    /* to control generic scsi devices */
-    BlockAIOCB *(*bdrv_aio_ioctl)(BlockDriverState *bs,
-        unsigned long int req, void *buf,
-        BlockCompletionFunc *cb, void *opaque);
-    int coroutine_fn (*bdrv_co_ioctl)(BlockDriverState *bs,
-                                      unsigned long int req, void *buf);
-
-    /* List of options for creating images, terminated by name == NULL */
-    QemuOptsList *create_opts;
-
-    /* List of options for image amend */
-    QemuOptsList *amend_opts;
-
-    /*
-     * If this driver supports reopening images this contains a
-     * NULL-terminated list of the runtime options that can be
-     * modified. If an option in this list is unspecified during
-     * reopen then it _must_ be reset to its default value or return
-     * an error.
-     */
-    const char *const *mutable_opts;
-
-    /*
-     * Returns 0 for completed check, -errno for internal errors.
-     * The check results are stored in result.
-     */
-    int coroutine_fn (*bdrv_co_check)(BlockDriverState *bs,
-                                      BdrvCheckResult *result,
-                                      BdrvCheckMode fix);
-
-    void (*bdrv_debug_event)(BlockDriverState *bs, BlkdebugEvent event);
-
-    /* TODO Better pass a option string/QDict/QemuOpts to add any rule? */
-    int (*bdrv_debug_breakpoint)(BlockDriverState *bs, const char *event,
-        const char *tag);
-    int (*bdrv_debug_remove_breakpoint)(BlockDriverState *bs,
-        const char *tag);
-    int (*bdrv_debug_resume)(BlockDriverState *bs, const char *tag);
-    bool (*bdrv_debug_is_suspended)(BlockDriverState *bs, const char *tag);
-
-    void (*bdrv_refresh_limits)(BlockDriverState *bs, Error **errp);
-
-    /*
-     * Returns 1 if newly created images are guaranteed to contain only
-     * zeros, 0 otherwise.
-     */
-    int (*bdrv_has_zero_init)(BlockDriverState *bs);
-
-    /* Remove fd handlers, timers, and other event loop callbacks so the event
-     * loop is no longer in use.  Called with no in-flight requests and in
-     * depth-first traversal order with parents before child nodes.
-     */
-    void (*bdrv_detach_aio_context)(BlockDriverState *bs);
-
-    /* Add fd handlers, timers, and other event loop callbacks so I/O requests
-     * can be processed again.  Called with no in-flight requests and in
-     * depth-first traversal order with child nodes before parent nodes.
-     */
-    void (*bdrv_attach_aio_context)(BlockDriverState *bs,
-                                    AioContext *new_context);
-
-    /* io queue for linux-aio */
-    void (*bdrv_io_plug)(BlockDriverState *bs);
-    void (*bdrv_io_unplug)(BlockDriverState *bs);
-
-    /**
-     * Try to get @bs's logical and physical block size.
-     * On success, store them in @bsz and return zero.
-     * On failure, return negative errno.
-     */
-    int (*bdrv_probe_blocksizes)(BlockDriverState *bs, BlockSizes *bsz);
-    /**
-     * Try to get @bs's geometry (cyls, heads, sectors)
-     * On success, store them in @geo and return 0.
-     * On failure return -errno.
-     * Only drivers that want to override guest geometry implement this
-     * callback; see hd_geometry_guess().
-     */
-    int (*bdrv_probe_geometry)(BlockDriverState *bs, HDGeometry *geo);
-
-    /**
-     * bdrv_co_drain_begin is called if implemented in the beginning of a
-     * drain operation to drain and stop any internal sources of requests in
-     * the driver.
-     * bdrv_co_drain_end is called if implemented at the end of the drain.
-     *
-     * They should be used by the driver to e.g. manage scheduled I/O
-     * requests, or toggle an internal state. After the end of the drain new
-     * requests will continue normally.
-     */
-    void coroutine_fn (*bdrv_co_drain_begin)(BlockDriverState *bs);
-    void coroutine_fn (*bdrv_co_drain_end)(BlockDriverState *bs);
-
-    void (*bdrv_add_child)(BlockDriverState *parent, BlockDriverState *child,
-                           Error **errp);
-    void (*bdrv_del_child)(BlockDriverState *parent, BdrvChild *child,
-                           Error **errp);
-
-    /**
-     * Informs the block driver that a permission change is intended. The
-     * driver checks whether the change is permissible and may take other
-     * preparations for the change (e.g. get file system locks). This operation
-     * is always followed either by a call to either .bdrv_set_perm or
-     * .bdrv_abort_perm_update.
-     *
-     * Checks whether the requested set of cumulative permissions in @perm
-     * can be granted for accessing @bs and whether no other users are using
-     * permissions other than those given in @shared (both arguments take
-     * BLK_PERM_* bitmasks).
-     *
-     * If both conditions are met, 0 is returned. Otherwise, -errno is returned
-     * and errp is set to an error describing the conflict.
-     */
-    int (*bdrv_check_perm)(BlockDriverState *bs, uint64_t perm,
-                           uint64_t shared, Error **errp);
-
-    /**
-     * Called to inform the driver that the set of cumulative set of used
-     * permissions for @bs has changed to @perm, and the set of sharable
-     * permission to @shared. The driver can use this to propagate changes to
-     * its children (i.e. request permissions only if a parent actually needs
-     * them).
-     *
-     * This function is only invoked after bdrv_check_perm(), so block drivers
-     * may rely on preparations made in their .bdrv_check_perm implementation.
-     */
-    void (*bdrv_set_perm)(BlockDriverState *bs, uint64_t perm, uint64_t shared);
-
-    /*
-     * Called to inform the driver that after a previous bdrv_check_perm()
-     * call, the permission update is not performed and any preparations made
-     * for it (e.g. taken file locks) need to be undone.
-     *
-     * This function can be called even for nodes that never saw a
-     * bdrv_check_perm() call. It is a no-op then.
-     */
-    void (*bdrv_abort_perm_update)(BlockDriverState *bs);
-
-    /**
-     * Returns in @nperm and @nshared the permissions that the driver for @bs
-     * needs on its child @c, based on the cumulative permissions requested by
-     * the parents in @parent_perm and @parent_shared.
-     *
-     * If @c is NULL, return the permissions for attaching a new child for the
-     * given @child_class and @role.
-     *
-     * If @reopen_queue is non-NULL, don't return the currently needed
-     * permissions, but those that will be needed after applying the
-     * @reopen_queue.
-     */
-     void (*bdrv_child_perm)(BlockDriverState *bs, BdrvChild *c,
-                             BdrvChildRole role,
-                             BlockReopenQueue *reopen_queue,
-                             uint64_t parent_perm, uint64_t parent_shared,
-                             uint64_t *nperm, uint64_t *nshared);
-
-    bool (*bdrv_supports_persistent_dirty_bitmap)(BlockDriverState *bs);
-    bool (*bdrv_co_can_store_new_dirty_bitmap)(BlockDriverState *bs,
-                                               const char *name,
-                                               uint32_t granularity,
-                                               Error **errp);
-    int (*bdrv_co_remove_persistent_dirty_bitmap)(BlockDriverState *bs,
-                                                  const char *name,
-                                                  Error **errp);
-
-    /**
-     * Register/unregister a buffer for I/O. For example, when the driver is
-     * interested to know the memory areas that will later be used in iovs, so
-     * 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.
-     */
-    void (*bdrv_register_buf)(BlockDriverState *bs, void *host, size_t size);
-    void (*bdrv_unregister_buf)(BlockDriverState *bs, void *host);
-    QLIST_ENTRY(BlockDriver) list;
-
-    /* Pointer to a NULL-terminated array of names of strong options
-     * that can be specified for bdrv_open(). A strong option is one
-     * that changes the data of a BDS.
-     * If this pointer is NULL, the array is considered empty.
-     * "filename" and "driver" are always considered strong. */
-    const char *const *strong_runtime_opts;
-};
-
-static inline bool block_driver_can_compress(BlockDriver *drv)
-{
-    return drv->bdrv_co_pwritev_compressed ||
-           drv->bdrv_co_pwritev_compressed_part;
-}
-
-typedef struct BlockLimits {
-    /* Alignment requirement, in bytes, for offset/length of I/O
-     * requests. Must be a power of 2 less than INT_MAX; defaults to
-     * 1 for drivers with modern byte interfaces, and to 512
-     * otherwise. */
-    uint32_t request_alignment;
-
-    /*
-     * Maximum number of bytes that can be discarded at once. Must be multiple
-     * of pdiscard_alignment, but need not be power of 2. May be 0 if no
-     * inherent 64-bit limit.
-     */
-    int64_t max_pdiscard;
-
-    /* Optimal alignment for discard requests in bytes. A power of 2
-     * is best but not mandatory.  Must be a multiple of
-     * bl.request_alignment, and must be less than max_pdiscard if
-     * that is set. May be 0 if bl.request_alignment is good enough */
-    uint32_t pdiscard_alignment;
-
-    /*
-     * Maximum number of bytes that can zeroized at once. Must be multiple of
-     * pwrite_zeroes_alignment. 0 means no limit.
-     */
-    int64_t max_pwrite_zeroes;
-
-    /* Optimal alignment for write zeroes requests in bytes. A power
-     * of 2 is best but not mandatory.  Must be a multiple of
-     * bl.request_alignment, and must be less than max_pwrite_zeroes
-     * if that is set. May be 0 if bl.request_alignment is good
-     * enough */
-    uint32_t pwrite_zeroes_alignment;
-
-    /* Optimal transfer length in bytes.  A power of 2 is best but not
-     * mandatory.  Must be a multiple of bl.request_alignment, or 0 if
-     * no preferred size */
-    uint32_t opt_transfer;
-
-    /* Maximal transfer length in bytes.  Need not be power of 2, but
-     * must be multiple of opt_transfer and bl.request_alignment, or 0
-     * for no 32-bit limit.  For now, anything larger than INT_MAX is
-     * clamped down. */
-    uint32_t max_transfer;
-
-    /* Maximal hardware transfer length in bytes.  Applies whenever
-     * transfers to the device bypass the kernel I/O scheduler, for
-     * example with SG_IO.  If larger than max_transfer or if zero,
-     * blk_get_max_hw_transfer will fall back to max_transfer.
-     */
-    uint64_t max_hw_transfer;
-
-    /* Maximal number of scatter/gather elements allowed by the hardware.
-     * Applies whenever transfers to the device bypass the kernel I/O
-     * scheduler, for example with SG_IO.  If larger than max_iov
-     * or if zero, blk_get_max_hw_iov will fall back to max_iov.
-     */
-    int max_hw_iov;
-
-    /* memory alignment, in bytes so that no bounce buffer is needed */
-    size_t min_mem_alignment;
-
-    /* memory alignment, in bytes, for bounce buffer */
-    size_t opt_mem_alignment;
-
-    /* maximum number of iovec elements */
-    int max_iov;
-} BlockLimits;
-
-typedef struct BdrvOpBlocker BdrvOpBlocker;
-
-typedef struct BdrvAioNotifier {
-    void (*attached_aio_context)(AioContext *new_context, void *opaque);
-    void (*detach_aio_context)(void *opaque);
-
-    void *opaque;
-    bool deleted;
-
-    QLIST_ENTRY(BdrvAioNotifier) list;
-} BdrvAioNotifier;
-
-struct BdrvChildClass {
-    /* If true, bdrv_replace_node() doesn't change the node this BdrvChild
-     * points to. */
-    bool stay_at_node;
-
-    /* If true, the parent is a BlockDriverState and bdrv_next_all_states()
-     * will return it. This information is used for drain_all, where every node
-     * will be drained separately, so the drain only needs to be propagated to
-     * non-BDS parents. */
-    bool parent_is_bds;
-
-    void (*inherit_options)(BdrvChildRole role, bool parent_is_format,
-                            int *child_flags, QDict *child_options,
-                            int parent_flags, QDict *parent_options);
-
-    void (*change_media)(BdrvChild *child, bool load);
-    void (*resize)(BdrvChild *child);
-
-    /* Returns a name that is supposedly more useful for human users than the
-     * node name for identifying the node in question (in particular, a BB
-     * name), or NULL if the parent can't provide a better name. */
-    const char *(*get_name)(BdrvChild *child);
-
-    /* Returns a malloced string that describes the parent of the child for a
-     * human reader. This could be a node-name, BlockBackend name, qdev ID or
-     * QOM path of the device owning the BlockBackend, job type and ID etc. The
-     * caller is responsible for freeing the memory. */
-    char *(*get_parent_desc)(BdrvChild *child);
-
-    /*
-     * If this pair of functions is implemented, the parent doesn't issue new
-     * requests after returning from .drained_begin() until .drained_end() is
-     * called.
-     *
-     * These functions must not change the graph (and therefore also must not
-     * call aio_poll(), which could change the graph indirectly).
-     *
-     * If drained_end() schedules background operations, it must atomically
-     * increment *drained_end_counter for each such operation and atomically
-     * decrement it once the operation has settled.
-     *
-     * Note that this can be nested. If drained_begin() was called twice, new
-     * I/O is allowed only after drained_end() was called twice, too.
-     */
-    void (*drained_begin)(BdrvChild *child);
-    void (*drained_end)(BdrvChild *child, int *drained_end_counter);
-
-    /*
-     * Returns whether the parent has pending requests for the child. This
-     * callback is polled after .drained_begin() has been called until all
-     * activity on the child has stopped.
-     */
-    bool (*drained_poll)(BdrvChild *child);
-
-    /* Notifies the parent that the child has been activated/inactivated (e.g.
-     * when migration is completing) and it can start/stop requesting
-     * permissions and doing I/O on it. */
-    void (*activate)(BdrvChild *child, Error **errp);
-    int (*inactivate)(BdrvChild *child);
-
-    void (*attach)(BdrvChild *child);
-    void (*detach)(BdrvChild *child);
-
-    /* Notifies the parent that the filename of its child has changed (e.g.
-     * because the direct child was removed from the backing chain), so that it
-     * can update its reference. */
-    int (*update_filename)(BdrvChild *child, BlockDriverState *new_base,
-                           const char *filename, Error **errp);
-
-    bool (*can_set_aio_ctx)(BdrvChild *child, AioContext *ctx,
-                            GSList **ignore, Error **errp);
-    void (*set_aio_ctx)(BdrvChild *child, AioContext *ctx, GSList **ignore);
-
-    AioContext *(*get_parent_aio_context)(BdrvChild *child);
-};
-
-extern const BdrvChildClass child_of_bds;
-
-struct BdrvChild {
-    BlockDriverState *bs;
-    char *name;
-    const BdrvChildClass *klass;
-    BdrvChildRole role;
-    void *opaque;
-
-    /**
-     * Granted permissions for operating on this BdrvChild (BLK_PERM_* bitmask)
-     */
-    uint64_t perm;
-
-    /**
-     * Permissions that can still be granted to other users of @bs while this
-     * BdrvChild is still attached to it. (BLK_PERM_* bitmask)
-     */
-    uint64_t shared_perm;
-
-    /*
-     * This link is frozen: the child can neither be replaced nor
-     * detached from the parent.
-     */
-    bool frozen;
-
-    /*
-     * How many times the parent of this child has been drained
-     * (through klass->drained_*).
-     * Usually, this is equal to bs->quiesce_counter (potentially
-     * reduced by bdrv_drain_all_count).  It may differ while the
-     * child is entering or leaving a drained section.
-     */
-    int parent_quiesce_counter;
-
-    QLIST_ENTRY(BdrvChild) next;
-    QLIST_ENTRY(BdrvChild) next_parent;
-};
-
-/*
- * Allows bdrv_co_block_status() to cache one data region for a
- * protocol node.
- *
- * @valid: Whether the cache is valid (should be accessed with atomic
- *         functions so this can be reset by RCU readers)
- * @data_start: Offset where we know (or strongly assume) is data
- * @data_end: Offset where the data region ends (which is not necessarily
- *            the start of a zeroed region)
- */
-typedef struct BdrvBlockStatusCache {
-    struct rcu_head rcu;
-
-    bool valid;
-    int64_t data_start;
-    int64_t data_end;
-} BdrvBlockStatusCache;
-
-struct BlockDriverState {
-    /* Protected by big QEMU lock or read-only after opening.  No special
-     * locking needed during I/O...
-     */
-    int open_flags; /* flags used to open the file, re-used for re-open */
-    bool encrypted; /* if true, the media is encrypted */
-    bool sg;        /* if true, the device is a /dev/sg* */
-    bool probed;    /* if true, format was probed rather than specified */
-    bool force_share; /* if true, always allow all shared permissions */
-    bool implicit;  /* if true, this filter node was automatically inserted */
-
-    BlockDriver *drv; /* NULL means no media */
-    void *opaque;
-
-    AioContext *aio_context; /* event loop used for fd handlers, timers, etc */
-    /* long-running tasks intended to always use the same AioContext as this
-     * BDS may register themselves in this list to be notified of changes
-     * regarding this BDS's context */
-    QLIST_HEAD(, BdrvAioNotifier) aio_notifiers;
-    bool walking_aio_notifiers; /* to make removal during iteration safe */
-
-    char filename[PATH_MAX];
-    /*
-     * If not empty, this image is a diff in relation to backing_file.
-     * Note that this is the name given in the image header and
-     * therefore may or may not be equal to .backing->bs->filename.
-     * If this field contains a relative path, it is to be resolved
-     * relatively to the overlay's location.
-     */
-    char backing_file[PATH_MAX];
-    /*
-     * The backing filename indicated by the image header.  Contrary
-     * to backing_file, if we ever open this file, auto_backing_file
-     * is replaced by the resulting BDS's filename (i.e. after a
-     * bdrv_refresh_filename() run).
-     */
-    char auto_backing_file[PATH_MAX];
-    char backing_format[16]; /* if non-zero and backing_file exists */
-
-    QDict *full_open_options;
-    char exact_filename[PATH_MAX];
-
-    BdrvChild *backing;
-    BdrvChild *file;
-
-    /* I/O Limits */
-    BlockLimits bl;
-
-    /*
-     * Flags honored during pread
-     */
-    unsigned int supported_read_flags;
-    /* Flags honored during pwrite (so far: BDRV_REQ_FUA,
-     * BDRV_REQ_WRITE_UNCHANGED).
-     * If a driver does not support BDRV_REQ_WRITE_UNCHANGED, those
-     * writes will be issued as normal writes without the flag set.
-     * This is important to note for drivers that do not explicitly
-     * request a WRITE permission for their children and instead take
-     * the same permissions as their parent did (this is commonly what
-     * block filters do).  Such drivers have to be aware that the
-     * parent may have taken a WRITE_UNCHANGED permission only and is
-     * issuing such requests.  Drivers either must make sure that
-     * these requests do not result in plain WRITE accesses (usually
-     * by supporting BDRV_REQ_WRITE_UNCHANGED, and then forwarding
-     * every incoming write request as-is, including potentially that
-     * flag), or they have to explicitly take the WRITE permission for
-     * their children. */
-    unsigned int 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;
-    /*
-     * Flags honoured during truncate (so far: BDRV_REQ_ZERO_WRITE).
-     *
-     * If BDRV_REQ_ZERO_WRITE is given, the truncate operation must make sure
-     * that any added space reads as all zeros. If this can't be guaranteed,
-     * the operation must fail.
-     */
-    unsigned int supported_truncate_flags;
-
-    /* the following member gives a name to every node on the bs graph. */
-    char node_name[32];
-    /* element of the list of named nodes building the graph */
-    QTAILQ_ENTRY(BlockDriverState) node_list;
-    /* element of the list of all BlockDriverStates (all_bdrv_states) */
-    QTAILQ_ENTRY(BlockDriverState) bs_list;
-    /* element of the list of monitor-owned BDS */
-    QTAILQ_ENTRY(BlockDriverState) monitor_list;
-    int refcnt;
-
-    /* operation blockers */
-    QLIST_HEAD(, BdrvOpBlocker) op_blockers[BLOCK_OP_TYPE_MAX];
-
-    /* The node that this node inherited default options from (and a reopen on
-     * which can affect this node by changing these defaults). This is always a
-     * parent node of this node. */
-    BlockDriverState *inherits_from;
-    QLIST_HEAD(, BdrvChild) children;
-    QLIST_HEAD(, BdrvChild) parents;
-
-    QDict *options;
-    QDict *explicit_options;
-    BlockdevDetectZeroesOptions detect_zeroes;
-
-    /* The error object in use for blocking operations on backing_hd */
-    Error *backing_blocker;
-
-    /* Protected by AioContext lock */
-
-    /* If we are reading a disk image, give its size in sectors.
-     * Generally read-only; it is written to by load_snapshot and
-     * save_snaphost, but the block layer is quiescent during those.
-     */
-    int64_t total_sectors;
-
-    /* threshold limit for writes, in bytes. "High water mark". */
-    uint64_t write_threshold_offset;
-
-    /* Writing to the list requires the BQL _and_ the dirty_bitmap_mutex.
-     * Reading from the list can be done with either the BQL or the
-     * dirty_bitmap_mutex.  Modifying a bitmap only requires
-     * dirty_bitmap_mutex.  */
-    QemuMutex dirty_bitmap_mutex;
-    QLIST_HEAD(, BdrvDirtyBitmap) dirty_bitmaps;
-
-    /* Offset after the highest byte written to */
-    Stat64 wr_highest_offset;
-
-    /* If true, copy read backing sectors into image.  Can be >1 if more
-     * than one client has requested copy-on-read.  Accessed with atomic
-     * ops.
-     */
-    int copy_on_read;
-
-    /* number of in-flight requests; overall and serialising.
-     * Accessed with atomic ops.
-     */
-    unsigned int in_flight;
-    unsigned int serialising_in_flight;
-
-    /* counter for nested bdrv_io_plug.
-     * Accessed with atomic ops.
-    */
-    unsigned io_plugged;
-
-    /* do we need to tell the quest if we have a volatile write cache? */
-    int enable_write_cache;
-
-    /* Accessed with atomic ops.  */
-    int quiesce_counter;
-    int recursive_quiesce_counter;
-
-    unsigned int write_gen;               /* Current data generation */
-
-    /* Protected by reqs_lock.  */
-    CoMutex reqs_lock;
-    QLIST_HEAD(, BdrvTrackedRequest) tracked_requests;
-    CoQueue flush_queue;                  /* Serializing flush queue */
-    bool active_flush_req;                /* Flush request in flight? */
-
-    /* Only read/written by whoever has set active_flush_req to true.  */
-    unsigned int flushed_gen;             /* Flushed write generation */
-
-    /* BdrvChild links to this node may never be frozen */
-    bool never_freeze;
-
-    /* Lock for block-status cache RCU writers */
-    CoMutex bsc_modify_lock;
-    /* Always non-NULL, but must only be dereferenced under an RCU read guard */
-    BdrvBlockStatusCache *block_status_cache;
-};
-
-struct BlockBackendRootState {
-    int open_flags;
-    BlockdevDetectZeroesOptions detect_zeroes;
-};
-
-typedef enum BlockMirrorBackingMode {
-    /* Reuse the existing backing chain from the source for the target.
-     * - sync=full: Set backing BDS to NULL.
-     * - sync=top:  Use source's backing BDS.
-     * - sync=none: Use source as the backing BDS. */
-    MIRROR_SOURCE_BACKING_CHAIN,
-
-    /* Open the target's backing chain completely anew */
-    MIRROR_OPEN_BACKING_CHAIN,
-
-    /* Do not change the target's backing BDS after job completion */
-    MIRROR_LEAVE_BACKING_CHAIN,
-} BlockMirrorBackingMode;
-
-
-/* Essential block drivers which must always be statically linked into qemu, and
- * which therefore can be accessed without using bdrv_find_format() */
-extern BlockDriver bdrv_file;
-extern BlockDriver bdrv_raw;
-extern BlockDriver bdrv_qcow2;
-
-int coroutine_fn bdrv_co_preadv(BdrvChild *child,
-    int64_t offset, int64_t bytes, QEMUIOVector *qiov,
-    BdrvRequestFlags flags);
-int coroutine_fn bdrv_co_preadv_part(BdrvChild *child,
-    int64_t offset, int64_t bytes,
-    QEMUIOVector *qiov, size_t qiov_offset, BdrvRequestFlags flags);
-int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
-    int64_t offset, int64_t bytes, QEMUIOVector *qiov,
-    BdrvRequestFlags flags);
-int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child,
-    int64_t offset, int64_t bytes,
-    QEMUIOVector *qiov, size_t qiov_offset, BdrvRequestFlags flags);
-
-static inline int coroutine_fn bdrv_co_pread(BdrvChild *child,
-    int64_t offset, unsigned int bytes, void *buf, BdrvRequestFlags flags)
-{
-    QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes);
-
-    return bdrv_co_preadv(child, offset, bytes, &qiov, flags);
-}
-
-static inline int coroutine_fn bdrv_co_pwrite(BdrvChild *child,
-    int64_t offset, unsigned int bytes, void *buf, BdrvRequestFlags flags)
-{
-    QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes);
-
-    return bdrv_co_pwritev(child, offset, bytes, &qiov, flags);
-}
-
-extern unsigned int bdrv_drain_all_count;
-void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent);
-void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent);
-
-bool coroutine_fn bdrv_make_request_serialising(BdrvTrackedRequest *req,
-                                                uint64_t align);
-BdrvTrackedRequest *coroutine_fn bdrv_co_get_self_request(BlockDriverState *bs);
-
-int get_tmp_filename(char *filename, int size);
-BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size,
-                            const char *filename);
-
-void bdrv_parse_filename_strip_prefix(const char *filename, const char *prefix,
-                                      QDict *options);
-
-bool bdrv_backing_overridden(BlockDriverState *bs);
-
-
-/**
- * bdrv_add_aio_context_notifier:
- *
- * If a long-running job intends to be always run in the same AioContext as a
- * certain BDS, it may use this function to be notified of changes regarding the
- * association of the BDS to an AioContext.
- *
- * attached_aio_context() is called after the target BDS has been attached to a
- * new AioContext; detach_aio_context() is called before the target BDS is being
- * detached from its old AioContext.
- */
-void bdrv_add_aio_context_notifier(BlockDriverState *bs,
-        void (*attached_aio_context)(AioContext *new_context, void *opaque),
-        void (*detach_aio_context)(void *opaque), void *opaque);
-
-/**
- * bdrv_remove_aio_context_notifier:
- *
- * Unsubscribe of change notifications regarding the BDS's AioContext. The
- * parameters given here have to be the same as those given to
- * bdrv_add_aio_context_notifier().
- */
-void bdrv_remove_aio_context_notifier(BlockDriverState *bs,
-                                      void (*aio_context_attached)(AioContext *,
-                                                                   void *),
-                                      void (*aio_context_detached)(void *),
-                                      void *opaque);
-
-/**
- * bdrv_wakeup:
- * @bs: The BlockDriverState for which an I/O operation has been completed.
- *
- * Wake up the main thread if it is waiting on BDRV_POLL_WHILE.  During
- * synchronous I/O on a BlockDriverState that is attached to another
- * I/O thread, the main thread lets the I/O thread's event loop run,
- * waiting for the I/O operation to complete.  A bdrv_wakeup will wake
- * up the main thread if necessary.
- *
- * Manual calls to bdrv_wakeup are rarely necessary, because
- * bdrv_dec_in_flight already calls it.
- */
-void bdrv_wakeup(BlockDriverState *bs);
-
-#ifdef _WIN32
-int is_windows_drive(const char *filename);
-#endif
-
-/**
- * stream_start:
- * @job_id: The id of the newly-created job, or %NULL to use the
- * device name of @bs.
- * @bs: Block device to operate on.
- * @base: Block device that will become the new base, or %NULL to
- * flatten the whole backing file chain onto @bs.
- * @backing_file_str: The file name that will be written to @bs as the
- * the new backing file if the job completes. Ignored if @base is %NULL.
- * @creation_flags: Flags that control the behavior of the Job lifetime.
- *                  See @BlockJobCreateFlags
- * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
- * @on_error: The action to take upon error.
- * @filter_node_name: The node name that should be assigned to the filter
- *                    driver that the stream job inserts into the graph above
- *                    @bs. NULL means that a node name should be autogenerated.
- * @errp: Error object.
- *
- * Start a streaming operation on @bs.  Clusters that are unallocated
- * in @bs, but allocated in any image between @base and @bs (both
- * exclusive) will be written to @bs.  At the end of a successful
- * streaming job, the backing file of @bs will be changed to
- * @backing_file_str in the written image and to @base in the live
- * BlockDriverState.
- */
-void stream_start(const char *job_id, BlockDriverState *bs,
-                  BlockDriverState *base, const char *backing_file_str,
-                  BlockDriverState *bottom,
-                  int creation_flags, int64_t speed,
-                  BlockdevOnError on_error,
-                  const char *filter_node_name,
-                  Error **errp);
-
-/**
- * commit_start:
- * @job_id: The id of the newly-created job, or %NULL to use the
- * device name of @bs.
- * @bs: Active block device.
- * @top: Top block device to be committed.
- * @base: Block device that will be written into, and become the new top.
- * @creation_flags: Flags that control the behavior of the Job lifetime.
- *                  See @BlockJobCreateFlags
- * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
- * @on_error: The action to take upon error.
- * @backing_file_str: String to use as the backing file in @top's overlay
- * @filter_node_name: The node name that should be assigned to the filter
- * driver that the commit job inserts into the graph above @top. NULL means
- * that a node name should be autogenerated.
- * @errp: Error object.
- *
- */
-void commit_start(const char *job_id, BlockDriverState *bs,
-                  BlockDriverState *base, BlockDriverState *top,
-                  int creation_flags, int64_t speed,
-                  BlockdevOnError on_error, const char *backing_file_str,
-                  const char *filter_node_name, Error **errp);
-/**
- * commit_active_start:
- * @job_id: The id of the newly-created job, or %NULL to use the
- * device name of @bs.
- * @bs: Active block device to be committed.
- * @base: Block device that will be written into, and become the new top.
- * @creation_flags: Flags that control the behavior of the Job lifetime.
- *                  See @BlockJobCreateFlags
- * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
- * @on_error: The action to take upon error.
- * @filter_node_name: The node name that should be assigned to the filter
- * driver that the commit job inserts into the graph above @bs. NULL means that
- * a node name should be autogenerated.
- * @cb: Completion function for the job.
- * @opaque: Opaque pointer value passed to @cb.
- * @auto_complete: Auto complete the job.
- * @errp: Error object.
- *
- */
-BlockJob *commit_active_start(const char *job_id, BlockDriverState *bs,
-                              BlockDriverState *base, int creation_flags,
-                              int64_t speed, BlockdevOnError on_error,
-                              const char *filter_node_name,
-                              BlockCompletionFunc *cb, void *opaque,
-                              bool auto_complete, Error **errp);
-/*
- * mirror_start:
- * @job_id: The id of the newly-created job, or %NULL to use the
- * device name of @bs.
- * @bs: Block device to operate on.
- * @target: Block device to write to.
- * @replaces: Block graph node name to replace once the mirror is done. Can
- *            only be used when full mirroring is selected.
- * @creation_flags: Flags that control the behavior of the Job lifetime.
- *                  See @BlockJobCreateFlags
- * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
- * @granularity: The chosen granularity for the dirty bitmap.
- * @buf_size: The amount of data that can be in flight at one time.
- * @mode: Whether to collapse all images in the chain to the target.
- * @backing_mode: How to establish the target's backing chain after completion.
- * @zero_target: Whether the target should be explicitly zero-initialized
- * @on_source_error: The action to take upon error reading from the source.
- * @on_target_error: The action to take upon error writing to the target.
- * @unmap: Whether to unmap target where source sectors only contain zeroes.
- * @filter_node_name: The node name that should be assigned to the filter
- * driver that the mirror job inserts into the graph above @bs. NULL means that
- * a node name should be autogenerated.
- * @copy_mode: When to trigger writes to the target.
- * @errp: Error object.
- *
- * Start a mirroring operation on @bs.  Clusters that are allocated
- * in @bs will be written to @target until the job is cancelled or
- * manually completed.  At the end of a successful mirroring job,
- * @bs will be switched to read from @target.
- */
-void mirror_start(const char *job_id, BlockDriverState *bs,
-                  BlockDriverState *target, const char *replaces,
-                  int creation_flags, int64_t speed,
-                  uint32_t granularity, int64_t buf_size,
-                  MirrorSyncMode mode, BlockMirrorBackingMode backing_mode,
-                  bool zero_target,
-                  BlockdevOnError on_source_error,
-                  BlockdevOnError on_target_error,
-                  bool unmap, const char *filter_node_name,
-                  MirrorCopyMode copy_mode, Error **errp);
-
-/*
- * backup_job_create:
- * @job_id: The id of the newly-created job, or %NULL to use the
- * device name of @bs.
- * @bs: Block device to operate on.
- * @target: Block device to write to.
- * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
- * @sync_mode: What parts of the disk image should be copied to the destination.
- * @sync_bitmap: The dirty bitmap if sync_mode is 'bitmap' or 'incremental'
- * @bitmap_mode: The bitmap synchronization policy to use.
- * @perf: Performance options. All actual fields assumed to be present,
- *        all ".has_*" fields are ignored.
- * @on_source_error: The action to take upon error reading from the source.
- * @on_target_error: The action to take upon error writing to the target.
- * @creation_flags: Flags that control the behavior of the Job lifetime.
- *                  See @BlockJobCreateFlags
- * @cb: Completion function for the job.
- * @opaque: Opaque pointer value passed to @cb.
- * @txn: Transaction that this job is part of (may be NULL).
- *
- * Create a backup operation on @bs.  Clusters in @bs are written to @target
- * until the job is cancelled or manually completed.
- */
-BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
-                            BlockDriverState *target, int64_t speed,
-                            MirrorSyncMode sync_mode,
-                            BdrvDirtyBitmap *sync_bitmap,
-                            BitmapSyncMode bitmap_mode,
-                            bool compress,
-                            const char *filter_node_name,
-                            BackupPerf *perf,
-                            BlockdevOnError on_source_error,
-                            BlockdevOnError on_target_error,
-                            int creation_flags,
-                            BlockCompletionFunc *cb, void *opaque,
-                            JobTxn *txn, Error **errp);
-
-BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
-                                  const char *child_name,
-                                  const BdrvChildClass *child_class,
-                                  BdrvChildRole child_role,
-                                  uint64_t perm, uint64_t shared_perm,
-                                  void *opaque, Error **errp);
-void bdrv_root_unref_child(BdrvChild *child);
-
-void bdrv_get_cumulative_perm(BlockDriverState *bs, uint64_t *perm,
-                              uint64_t *shared_perm);
-
-/**
- * Sets a BdrvChild's permissions.  Avoid if the parent is a BDS; use
- * bdrv_child_refresh_perms() instead and make the parent's
- * .bdrv_child_perm() implementation return the correct values.
- */
-int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
-                            Error **errp);
-
-/**
- * Calls bs->drv->bdrv_child_perm() and updates the child's permission
- * masks with the result.
- * Drivers should invoke this function whenever an event occurs that
- * makes their .bdrv_child_perm() implementation return different
- * values than before, but which will not result in the block layer
- * automatically refreshing the permissions.
- */
-int bdrv_child_refresh_perms(BlockDriverState *bs, BdrvChild *c, Error **errp);
-
-bool bdrv_recurse_can_replace(BlockDriverState *bs,
-                              BlockDriverState *to_replace);
-
-/*
- * Default implementation for BlockDriver.bdrv_child_perm() that can
- * be used by block filters and image formats, as long as they use the
- * child_of_bds child class and set an appropriate BdrvChildRole.
- */
-void bdrv_default_perms(BlockDriverState *bs, BdrvChild *c,
-                        BdrvChildRole role, BlockReopenQueue *reopen_queue,
-                        uint64_t perm, uint64_t shared,
-                        uint64_t *nperm, uint64_t *nshared);
-
-const char *bdrv_get_parent_name(const BlockDriverState *bs);
-void blk_dev_change_media_cb(BlockBackend *blk, bool load, Error **errp);
-bool blk_dev_has_removable_media(BlockBackend *blk);
-bool blk_dev_has_tray(BlockBackend *blk);
-void blk_dev_eject_request(BlockBackend *blk, bool force);
-bool blk_dev_is_tray_open(BlockBackend *blk);
-bool blk_dev_is_medium_locked(BlockBackend *blk);
-
-void bdrv_set_dirty(BlockDriverState *bs, int64_t offset, int64_t bytes);
-
-void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out);
-void bdrv_restore_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap *backup);
-bool bdrv_dirty_bitmap_merge_internal(BdrvDirtyBitmap *dest,
-                                      const BdrvDirtyBitmap *src,
-                                      HBitmap **backup, bool lock);
-
-void bdrv_inc_in_flight(BlockDriverState *bs);
-void bdrv_dec_in_flight(BlockDriverState *bs);
-
-void blockdev_close_all_bdrv_states(void);
-
-int coroutine_fn bdrv_co_copy_range_from(BdrvChild *src, int64_t src_offset,
-                                         BdrvChild *dst, int64_t dst_offset,
-                                         int64_t bytes,
-                                         BdrvRequestFlags read_flags,
-                                         BdrvRequestFlags write_flags);
-int coroutine_fn bdrv_co_copy_range_to(BdrvChild *src, int64_t src_offset,
-                                       BdrvChild *dst, int64_t dst_offset,
-                                       int64_t bytes,
-                                       BdrvRequestFlags read_flags,
-                                       BdrvRequestFlags write_flags);
-
-int refresh_total_sectors(BlockDriverState *bs, int64_t hint);
-
-void bdrv_set_monitor_owned(BlockDriverState *bs);
-BlockDriverState *bds_tree_init(QDict *bs_opts, Error **errp);
-
-/**
- * Simple implementation of bdrv_co_create_opts for protocol drivers
- * which only support creation via opening a file
- * (usually existing raw storage device)
- */
-int coroutine_fn bdrv_co_create_opts_simple(BlockDriver *drv,
-                                            const char *filename,
-                                            QemuOpts *opts,
-                                            Error **errp);
-extern QemuOptsList bdrv_create_opts_simple;
-
-BdrvDirtyBitmap *block_dirty_bitmap_lookup(const char *node,
-                                           const char *name,
-                                           BlockDriverState **pbs,
-                                           Error **errp);
-BdrvDirtyBitmap *block_dirty_bitmap_merge(const char *node, const char *target,
-                                          BlockDirtyBitmapMergeSourceList *bms,
-                                          HBitmap **backup, Error **errp);
-BdrvDirtyBitmap *block_dirty_bitmap_remove(const char *node, const char *name,
-                                           bool release,
-                                           BlockDriverState **bitmap_bs,
-                                           Error **errp);
-
-BdrvChild *bdrv_cow_child(BlockDriverState *bs);
-BdrvChild *bdrv_filter_child(BlockDriverState *bs);
-BdrvChild *bdrv_filter_or_cow_child(BlockDriverState *bs);
-BdrvChild *bdrv_primary_child(BlockDriverState *bs);
-BlockDriverState *bdrv_skip_implicit_filters(BlockDriverState *bs);
-BlockDriverState *bdrv_skip_filters(BlockDriverState *bs);
-BlockDriverState *bdrv_backing_chain_next(BlockDriverState *bs);
-
-static inline BlockDriverState *child_bs(BdrvChild *child)
-{
-    return child ? child->bs : NULL;
-}
-
-static inline BlockDriverState *bdrv_cow_bs(BlockDriverState *bs)
-{
-    return child_bs(bdrv_cow_child(bs));
-}
-
-static inline BlockDriverState *bdrv_filter_bs(BlockDriverState *bs)
-{
-    return child_bs(bdrv_filter_child(bs));
-}
-
-static inline BlockDriverState *bdrv_filter_or_cow_bs(BlockDriverState *bs)
-{
-    return child_bs(bdrv_filter_or_cow_child(bs));
-}
-
-static inline BlockDriverState *bdrv_primary_bs(BlockDriverState *bs)
-{
-    return child_bs(bdrv_primary_child(bs));
-}
-
-/**
- * End all quiescent sections started by bdrv_drain_all_begin(). This is
- * needed when deleting a BDS before bdrv_drain_all_end() is called.
- *
- * NOTE: this is an internal helper for bdrv_close() *only*. No one else
- * should call it.
- */
-void bdrv_drain_all_end_quiesce(BlockDriverState *bs);
-
-/**
- * Check whether the given offset is in the cached block-status data
- * region.
- *
- * If it is, and @pnum is not NULL, *pnum is set to
- * `bsc.data_end - offset`, i.e. how many bytes, starting from
- * @offset, are data (according to the cache).
- * Otherwise, *pnum is not touched.
- */
-bool bdrv_bsc_is_data(BlockDriverState *bs, int64_t offset, int64_t *pnum);
-
-/**
- * If [offset, offset + bytes) overlaps with the currently cached
- * block-status region, invalidate the cache.
- *
- * (To be used by I/O paths that cause data regions to be zero or
- * holes.)
- */
-void bdrv_bsc_invalidate_range(BlockDriverState *bs,
-                               int64_t offset, int64_t bytes);
-
-/**
- * Mark the range [offset, offset + bytes) as a data region.
- */
-void bdrv_bsc_fill(BlockDriverState *bs, int64_t offset, int64_t bytes);
+/* DO NOT ADD ANYTHING IN HERE. USE ONE OF THE HEADERS INCLUDED ABOVE */
 
 #endif /* BLOCK_INT_H */
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 07/25] assertions for block_int global state API
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (5 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 06/25] include/block/block_int: split header into I/O and global state API Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-12  8:48 ` [PATCH v3 08/25] block: introduce assert_bdrv_graph_writable Emanuele Giuseppe Esposito
                   ` (17 subsequent siblings)
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block.c                         | 17 +++++++++++++++++
 block/backup.c                  |  1 +
 block/block-backend.c           |  3 +++
 block/commit.c                  |  2 ++
 block/dirty-bitmap.c            |  1 +
 block/io.c                      |  6 ++++++
 block/mirror.c                  |  4 ++++
 block/monitor/bitmap-qmp-cmds.c |  6 ++++++
 block/stream.c                  |  2 ++
 blockdev.c                      |  7 +++++++
 10 files changed, 49 insertions(+)

diff --git a/block.c b/block.c
index 672f946065..41c5883c5c 100644
--- a/block.c
+++ b/block.c
@@ -653,6 +653,8 @@ int coroutine_fn bdrv_co_create_opts_simple(BlockDriver *drv,
     Error *local_err = NULL;
     int ret;
 
+    assert(qemu_in_main_thread());
+
     size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
     buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
     prealloc = qapi_enum_parse(&PreallocMode_lookup, buf,
@@ -2428,6 +2430,8 @@ void bdrv_get_cumulative_perm(BlockDriverState *bs, uint64_t *perm,
     uint64_t cumulative_perms = 0;
     uint64_t cumulative_shared_perms = BLK_PERM_ALL;
 
+    assert(qemu_in_main_thread());
+
     QLIST_FOREACH(c, &bs->parents, next_parent) {
         cumulative_perms |= c->perm;
         cumulative_shared_perms &= c->shared_perm;
@@ -2486,6 +2490,8 @@ int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
     Transaction *tran = tran_new();
     int ret;
 
+    assert(qemu_in_main_thread());
+
     bdrv_child_set_perm(c, perm, shared, tran);
 
     ret = bdrv_refresh_perms(c->bs, &local_err);
@@ -2516,6 +2522,8 @@ int bdrv_child_refresh_perms(BlockDriverState *bs, BdrvChild *c, Error **errp)
     uint64_t parent_perms, parent_shared;
     uint64_t perms, shared;
 
+    assert(qemu_in_main_thread());
+
     bdrv_get_cumulative_perm(bs, &parent_perms, &parent_shared);
     bdrv_child_perm(bs, c->bs, c, c->role, NULL,
                     parent_perms, parent_shared, &perms, &shared);
@@ -2658,6 +2666,7 @@ void bdrv_default_perms(BlockDriverState *bs, BdrvChild *c,
                         uint64_t perm, uint64_t shared,
                         uint64_t *nperm, uint64_t *nshared)
 {
+    assert(qemu_in_main_thread());
     if (role & BDRV_CHILD_FILTERED) {
         assert(!(role & (BDRV_CHILD_DATA | BDRV_CHILD_METADATA |
                          BDRV_CHILD_COW)));
@@ -2984,6 +2993,8 @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
     BdrvChild *child = NULL;
     Transaction *tran = tran_new();
 
+    assert(qemu_in_main_thread());
+
     ret = bdrv_attach_child_common(child_bs, child_name, child_class,
                                    child_role, perm, shared_perm, opaque,
                                    &child, tran, errp);
@@ -6027,6 +6038,8 @@ const char *bdrv_get_parent_name(const BlockDriverState *bs)
     BdrvChild *c;
     const char *name;
 
+    assert(qemu_in_main_thread());
+
     /* If multiple parents have a name, just pick the first one. */
     QLIST_FOREACH(c, &bs->parents, next_parent) {
         if (c->klass->get_name) {
@@ -7302,6 +7315,8 @@ bool bdrv_recurse_can_replace(BlockDriverState *bs,
 {
     BlockDriverState *filtered;
 
+    assert(qemu_in_main_thread());
+
     if (!bs || !bs->drv) {
         return false;
     }
@@ -7473,6 +7488,7 @@ static bool append_strong_runtime_options(QDict *d, BlockDriverState *bs)
  * would result in exactly bs->backing. */
 bool bdrv_backing_overridden(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     if (bs->backing) {
         return strcmp(bs->auto_backing_file,
                       bs->backing->bs->filename);
@@ -7861,6 +7877,7 @@ static BlockDriverState *bdrv_do_skip_filters(BlockDriverState *bs,
  */
 BlockDriverState *bdrv_skip_implicit_filters(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     return bdrv_do_skip_filters(bs, true);
 }
 
diff --git a/block/backup.c b/block/backup.c
index 21d5983779..c53041772c 100644
--- a/block/backup.c
+++ b/block/backup.c
@@ -372,6 +372,7 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
 
     assert(bs);
     assert(target);
+    assert(qemu_in_main_thread());
 
     /* QMP interface protects us from these cases */
     assert(sync_mode != MIRROR_SYNC_MODE_INCREMENTAL);
diff --git a/block/block-backend.c b/block/block-backend.c
index 55aaaf7527..6f36a54e82 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -1086,6 +1086,7 @@ static void blk_root_change_media(BdrvChild *child, bool load)
  */
 bool blk_dev_has_removable_media(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     return !blk->dev || (blk->dev_ops && blk->dev_ops->change_media_cb);
 }
 
@@ -1103,6 +1104,7 @@ bool blk_dev_has_tray(BlockBackend *blk)
  */
 void blk_dev_eject_request(BlockBackend *blk, bool force)
 {
+    assert(qemu_in_main_thread());
     if (blk->dev_ops && blk->dev_ops->eject_request_cb) {
         blk->dev_ops->eject_request_cb(blk->dev_opaque, force);
     }
@@ -1125,6 +1127,7 @@ bool blk_dev_is_tray_open(BlockBackend *blk)
  */
 bool blk_dev_is_medium_locked(BlockBackend *blk)
 {
+    assert(qemu_in_main_thread());
     if (blk->dev_ops && blk->dev_ops->is_medium_locked) {
         return blk->dev_ops->is_medium_locked(blk->dev_opaque);
     }
diff --git a/block/commit.c b/block/commit.c
index 45a414a19b..f639eb49c5 100644
--- a/block/commit.c
+++ b/block/commit.c
@@ -253,6 +253,8 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     uint64_t base_perms, iter_shared_perms;
     int ret;
 
+    assert(qemu_in_main_thread());
+
     assert(top != bs);
     if (bdrv_skip_filters(top) == bdrv_skip_filters(base)) {
         error_setg(errp, "Invalid files for merge: top and base are the same");
diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c
index 0ef46163e3..49462ca121 100644
--- a/block/dirty-bitmap.c
+++ b/block/dirty-bitmap.c
@@ -673,6 +673,7 @@ void bdrv_restore_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap *backup)
 {
     HBitmap *tmp = bitmap->bitmap;
     assert(!bdrv_dirty_bitmap_readonly(bitmap));
+    assert(qemu_in_main_thread());
     bitmap->bitmap = backup;
     hbitmap_free(tmp);
 }
diff --git a/block/io.c b/block/io.c
index c5d7f8495e..f271ab3684 100644
--- a/block/io.c
+++ b/block/io.c
@@ -560,6 +560,7 @@ void bdrv_subtree_drained_end(BlockDriverState *bs)
 void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent)
 {
     int i;
+    assert(qemu_in_main_thread());
 
     for (i = 0; i < new_parent->recursive_quiesce_counter; i++) {
         bdrv_do_drained_begin(child->bs, true, child, false, true);
@@ -571,6 +572,8 @@ void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent)
     int drained_end_counter = 0;
     int i;
 
+    assert(qemu_in_main_thread());
+
     for (i = 0; i < old_parent->recursive_quiesce_counter; i++) {
         bdrv_do_drained_end(child->bs, true, child, false,
                             &drained_end_counter);
@@ -690,6 +693,7 @@ void bdrv_drain_all_end_quiesce(BlockDriverState *bs)
 {
     int drained_end_counter = 0;
 
+    assert(qemu_in_main_thread());
     g_assert(bs->quiesce_counter > 0);
     g_assert(!bs->refcnt);
 
@@ -3419,6 +3423,7 @@ int coroutine_fn bdrv_co_copy_range_from(BdrvChild *src, int64_t src_offset,
 {
     trace_bdrv_co_copy_range_from(src, src_offset, dst, dst_offset, bytes,
                                   read_flags, write_flags);
+    assert(qemu_in_main_thread());
     return bdrv_co_copy_range_internal(src, src_offset, dst, dst_offset,
                                        bytes, read_flags, write_flags, true);
 }
@@ -3435,6 +3440,7 @@ int coroutine_fn bdrv_co_copy_range_to(BdrvChild *src, int64_t src_offset,
 {
     trace_bdrv_co_copy_range_to(src, src_offset, dst, dst_offset, bytes,
                                 read_flags, write_flags);
+    assert(qemu_in_main_thread());
     return bdrv_co_copy_range_internal(src, src_offset, dst, dst_offset,
                                        bytes, read_flags, write_flags, false);
 }
diff --git a/block/mirror.c b/block/mirror.c
index efec2c7674..00089e519b 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -1880,6 +1880,8 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
     bool is_none_mode;
     BlockDriverState *base;
 
+    assert(qemu_in_main_thread());
+
     if ((mode == MIRROR_SYNC_MODE_INCREMENTAL) ||
         (mode == MIRROR_SYNC_MODE_BITMAP)) {
         error_setg(errp, "Sync mode '%s' not supported",
@@ -1905,6 +1907,8 @@ BlockJob *commit_active_start(const char *job_id, BlockDriverState *bs,
     bool base_read_only;
     BlockJob *job;
 
+    assert(qemu_in_main_thread());
+
     base_read_only = bdrv_is_read_only(base);
 
     if (base_read_only) {
diff --git a/block/monitor/bitmap-qmp-cmds.c b/block/monitor/bitmap-qmp-cmds.c
index 9f11deec64..8b8d30287a 100644
--- a/block/monitor/bitmap-qmp-cmds.c
+++ b/block/monitor/bitmap-qmp-cmds.c
@@ -56,6 +56,8 @@ BdrvDirtyBitmap *block_dirty_bitmap_lookup(const char *node,
     BlockDriverState *bs;
     BdrvDirtyBitmap *bitmap;
 
+    assert(qemu_in_main_thread());
+
     if (!node) {
         error_setg(errp, "Node cannot be NULL");
         return NULL;
@@ -155,6 +157,8 @@ BdrvDirtyBitmap *block_dirty_bitmap_remove(const char *node, const char *name,
     BdrvDirtyBitmap *bitmap;
     AioContext *aio_context;
 
+    assert(qemu_in_main_thread());
+
     bitmap = block_dirty_bitmap_lookup(node, name, &bs, errp);
     if (!bitmap || !bs) {
         return NULL;
@@ -261,6 +265,8 @@ BdrvDirtyBitmap *block_dirty_bitmap_merge(const char *node, const char *target,
     BlockDirtyBitmapMergeSourceList *lst;
     Error *local_err = NULL;
 
+    assert(qemu_in_main_thread());
+
     dst = block_dirty_bitmap_lookup(node, target, &bs, errp);
     if (!dst) {
         return NULL;
diff --git a/block/stream.c b/block/stream.c
index 97bee482dc..b85c3742b2 100644
--- a/block/stream.c
+++ b/block/stream.c
@@ -216,6 +216,8 @@ void stream_start(const char *job_id, BlockDriverState *bs,
     QDict *opts;
     int ret;
 
+    assert(qemu_in_main_thread());
+
     assert(!(base && bottom));
     assert(!(backing_file_str && bottom));
 
diff --git a/blockdev.c b/blockdev.c
index ddba382abd..c1f6171c6c 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -69,6 +69,7 @@ QTAILQ_HEAD(, BlockDriverState) monitor_bdrv_states =
 
 void bdrv_set_monitor_owned(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     QTAILQ_INSERT_TAIL(&monitor_bdrv_states, bs, monitor_list);
 }
 
@@ -661,6 +662,7 @@ BlockDriverState *bds_tree_init(QDict *bs_opts, Error **errp)
 {
     int bdrv_flags = 0;
 
+    assert(qemu_in_main_thread());
     /* bdrv_open() defaults to the values in bdrv_flags (for compatibility
      * with other callers) rather than what we want as the real defaults.
      * Apply the defaults here instead. */
@@ -679,6 +681,7 @@ void blockdev_close_all_bdrv_states(void)
 {
     BlockDriverState *bs, *next_bs;
 
+    assert(qemu_in_main_thread());
     QTAILQ_FOREACH_SAFE(bs, &monitor_bdrv_states, monitor_list, next_bs) {
         AioContext *ctx = bdrv_get_aio_context(bs);
 
@@ -2332,6 +2335,8 @@ void qmp_transaction(TransactionActionList *dev_list,
     BlkActionState *state, *next;
     Error *local_err = NULL;
 
+    assert(qemu_in_main_thread());
+
     QTAILQ_HEAD(, BlkActionState) snap_bdrv_states;
     QTAILQ_INIT(&snap_bdrv_states);
 
@@ -3625,6 +3630,8 @@ void qmp_blockdev_del(const char *node_name, Error **errp)
     AioContext *aio_context;
     BlockDriverState *bs;
 
+    assert(qemu_in_main_thread());
+
     bs = bdrv_find_node(node_name);
     if (!bs) {
         error_setg(errp, "Failed to find node with node-name='%s'", node_name);
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 08/25] block: introduce assert_bdrv_graph_writable
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (6 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 07/25] assertions for block_int " Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-12 11:07   ` Paolo Bonzini
  2021-10-21 15:09   ` Stefan Hajnoczi
  2021-10-12  8:48 ` [PATCH v3 09/25] include/block/blockjob_int.h: split header into I/O and GS API Emanuele Giuseppe Esposito
                   ` (16 subsequent siblings)
  24 siblings, 2 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

We want to be sure that the functions that write the child and
parent list of a bs are under BQL and drain.

BQL prevents from concurrent writings from the GS API, while
drains protect from I/O.

TODO: drains are missing in some functions using this assert.
Therefore a proper assertion will fail. Because adding drains
requires additional discussions, they will be added in future
series.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 block.c                                |  5 +++++
 block/io.c                             | 11 +++++++++++
 include/block/block_int-global-state.h | 10 +++++++++-
 3 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/block.c b/block.c
index 41c5883c5c..94bff5c757 100644
--- a/block.c
+++ b/block.c
@@ -2734,12 +2734,14 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
         if (child->klass->detach) {
             child->klass->detach(child);
         }
+        assert_bdrv_graph_writable(old_bs);
         QLIST_REMOVE(child, next_parent);
     }
 
     child->bs = new_bs;
 
     if (new_bs) {
+        assert_bdrv_graph_writable(new_bs);
         QLIST_INSERT_HEAD(&new_bs->parents, child, next_parent);
 
         /*
@@ -2940,6 +2942,7 @@ static int bdrv_attach_child_noperm(BlockDriverState *parent_bs,
         return ret;
     }
 
+    assert_bdrv_graph_writable(parent_bs);
     QLIST_INSERT_HEAD(&parent_bs->children, *child, next);
     /*
      * child is removed in bdrv_attach_child_common_abort(), so don't care to
@@ -3140,6 +3143,7 @@ static void bdrv_unset_inherits_from(BlockDriverState *root, BdrvChild *child,
 void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child)
 {
     assert(qemu_in_main_thread());
+    assert_bdrv_graph_writable(parent);
     if (child == NULL) {
         return;
     }
@@ -4903,6 +4907,7 @@ static void bdrv_remove_filter_or_cow_child_abort(void *opaque)
     BdrvRemoveFilterOrCowChild *s = opaque;
     BlockDriverState *parent_bs = s->child->opaque;
 
+    assert_bdrv_graph_writable(parent_bs);
     QLIST_INSERT_HEAD(&parent_bs->children, s->child, next);
     if (s->is_backing) {
         parent_bs->backing = s->child;
diff --git a/block/io.c b/block/io.c
index f271ab3684..1c71e354d6 100644
--- a/block/io.c
+++ b/block/io.c
@@ -740,6 +740,17 @@ void bdrv_drain_all(void)
     bdrv_drain_all_end();
 }
 
+void assert_bdrv_graph_writable(BlockDriverState *bs)
+{
+    /*
+     * TODO: this function is incomplete. Because the users of this
+     * assert lack the necessary drains, check only for BQL.
+     * Once the necessary drains are added,
+     * assert also for qatomic_read(&bs->quiesce_counter) > 0
+     */
+    assert(qemu_in_main_thread());
+}
+
 /**
  * Remove an active request from the tracked requests list
  *
diff --git a/include/block/block_int-global-state.h b/include/block/block_int-global-state.h
index d08e80222c..6bd7746409 100644
--- a/include/block/block_int-global-state.h
+++ b/include/block/block_int-global-state.h
@@ -316,4 +316,12 @@ void bdrv_remove_aio_context_notifier(BlockDriverState *bs,
  */
 void bdrv_drain_all_end_quiesce(BlockDriverState *bs);
 
-#endif /* BLOCK_INT_GLOBAL_STATE*/
+/**
+ * Make sure that the function is either running under
+ * drain and BQL. The latter protects from concurrent writings
+ * from the GS API, while the former prevents concurrent reads
+ * from I/O.
+ */
+void assert_bdrv_graph_writable(BlockDriverState *bs);
+
+#endif /* BLOCK_INT_GLOBAL_STATE */
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 09/25] include/block/blockjob_int.h: split header into I/O and GS API
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (7 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 08/25] block: introduce assert_bdrv_graph_writable Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-12  8:48 ` [PATCH v3 10/25] assertions for blockjob_int.h Emanuele Giuseppe Esposito
                   ` (15 subsequent siblings)
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

Since the I/O functions are not many, keep a single file.
Also split the function pointers in BlockJobDriver.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/block/blockjob_int.h | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/include/block/blockjob_int.h b/include/block/blockjob_int.h
index 6633d83da2..718d7b92d2 100644
--- a/include/block/blockjob_int.h
+++ b/include/block/blockjob_int.h
@@ -38,6 +38,13 @@ struct BlockJobDriver {
     /** Generic JobDriver callbacks and settings */
     JobDriver job_driver;
 
+    /*
+     * I/O API functions. These functions are thread-safe.
+     *
+     * See include/block/block-io.h for more information about
+     * the I/O API.
+     */
+
     /*
      * Returns whether the job has pending requests for the child or will
      * submit new requests before the next pause point. This callback is polled
@@ -46,6 +53,13 @@ struct BlockJobDriver {
      */
     bool (*drained_poll)(BlockJob *job);
 
+    /*
+     * Global state (GS) API. These functions run under the BQL lock.
+     *
+     * See include/block/block-global-state.h for more information about
+     * the GS API.
+     */
+
     /*
      * If the callback is not NULL, it will be invoked before the job is
      * resumed in a new AioContext.  This is the place to move any resources
@@ -56,6 +70,13 @@ struct BlockJobDriver {
     void (*set_speed)(BlockJob *job, int64_t speed);
 };
 
+/*
+ * Global state (GS) API. These functions run under the BQL lock.
+ *
+ * See include/block/block-global-state.h for more information about
+ * the GS API.
+ */
+
 /**
  * block_job_create:
  * @job_id: The id of the newly-created job, or %NULL to have one
@@ -98,6 +119,13 @@ void block_job_free(Job *job);
  */
 void block_job_user_resume(Job *job);
 
+/*
+ * I/O API functions. These functions are thread-safe.
+ *
+ * See include/block/block-io.h for more information about
+ * the I/O API.
+ */
+
 /**
  * block_job_ratelimit_get_delay:
  *
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 10/25] assertions for blockjob_int.h
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (8 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 09/25] include/block/blockjob_int.h: split header into I/O and GS API Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-12  8:48 ` [PATCH v3 11/25] include/block/blockjob.h: global state API Emanuele Giuseppe Esposito
                   ` (14 subsequent siblings)
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 blockjob.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/blockjob.c b/blockjob.c
index 4bad1408cb..fbd6c7d873 100644
--- a/blockjob.c
+++ b/blockjob.c
@@ -83,6 +83,7 @@ BlockJob *block_job_get(const char *id)
 
 void block_job_free(Job *job)
 {
+    assert(qemu_in_main_thread());
     BlockJob *bjob = container_of(job, BlockJob, job);
 
     block_job_remove_all_bdrv(bjob);
@@ -436,6 +437,8 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver,
     BlockBackend *blk;
     BlockJob *job;
 
+    assert(qemu_in_main_thread());
+
     if (job_id == NULL && !(flags & JOB_INTERNAL)) {
         job_id = bdrv_get_device_name(bs);
     }
@@ -504,6 +507,7 @@ void block_job_iostatus_reset(BlockJob *job)
 
 void block_job_user_resume(Job *job)
 {
+    assert(qemu_in_main_thread());
     BlockJob *bjob = container_of(job, BlockJob, job);
     block_job_iostatus_reset(bjob);
 }
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 11/25] include/block/blockjob.h: global state API
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (9 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 10/25] assertions for blockjob_int.h Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-21 14:35   ` Stefan Hajnoczi
  2021-10-12  8:48 ` [PATCH v3 12/25] assertions for blockob.h " Emanuele Giuseppe Esposito
                   ` (13 subsequent siblings)
  24 siblings, 1 reply; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

blockjob functions run always under the BQL lock.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 include/block/blockjob.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/include/block/blockjob.h b/include/block/blockjob.h
index d200f33c10..fa0c3f7a47 100644
--- a/include/block/blockjob.h
+++ b/include/block/blockjob.h
@@ -77,6 +77,13 @@ typedef struct BlockJob {
     GSList *nodes;
 } BlockJob;
 
+/*
+ * Global state (GS) API. These functions run under the BQL lock.
+ *
+ * See include/block/block-global-state.h for more information about
+ * the GS API.
+ */
+
 /**
  * block_job_next:
  * @job: A block job, or %NULL.
@@ -158,6 +165,8 @@ BlockJobInfo *block_job_query(BlockJob *job, Error **errp);
  */
 void block_job_iostatus_reset(BlockJob *job);
 
+/* Common functions that are neither I/O nor Global State */
+
 /**
  * block_job_is_internal:
  * @job: The job to determine if it is user-visible or not.
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 12/25] assertions for blockob.h global state API
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (10 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 11/25] include/block/blockjob.h: global state API Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-12  8:48 ` [PATCH v3 13/25] include/sysemu/blockdev.h: move drive_add and inline drive_def Emanuele Giuseppe Esposito
                   ` (12 subsequent siblings)
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 blockjob.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/blockjob.c b/blockjob.c
index fbd6c7d873..4982f6a2b5 100644
--- a/blockjob.c
+++ b/blockjob.c
@@ -61,6 +61,7 @@ static bool is_block_job(Job *job)
 
 BlockJob *block_job_next(BlockJob *bjob)
 {
+    assert(qemu_in_main_thread());
     Job *job = bjob ? &bjob->job : NULL;
 
     do {
@@ -72,6 +73,7 @@ BlockJob *block_job_next(BlockJob *bjob)
 
 BlockJob *block_job_get(const char *id)
 {
+    assert(qemu_in_main_thread());
     Job *job = job_get(id);
 
     if (job && is_block_job(job)) {
@@ -185,6 +187,7 @@ static const BdrvChildClass child_job = {
 
 void block_job_remove_all_bdrv(BlockJob *job)
 {
+    assert(qemu_in_main_thread());
     /*
      * bdrv_root_unref_child() may reach child_job_[can_]set_aio_ctx(),
      * which will also traverse job->nodes, so consume the list one by
@@ -207,6 +210,7 @@ void block_job_remove_all_bdrv(BlockJob *job)
 bool block_job_has_bdrv(BlockJob *job, BlockDriverState *bs)
 {
     GSList *el;
+    assert(qemu_in_main_thread());
 
     for (el = job->nodes; el; el = el->next) {
         BdrvChild *c = el->data;
@@ -223,6 +227,7 @@ int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs,
 {
     BdrvChild *c;
     bool need_context_ops;
+    assert(qemu_in_main_thread());
 
     bdrv_ref(bs);
 
@@ -272,6 +277,8 @@ bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
     const BlockJobDriver *drv = block_job_driver(job);
     int64_t old_speed = job->speed;
 
+    assert(qemu_in_main_thread());
+
     if (job_apply_verb(&job->job, JOB_VERB_SET_SPEED, errp) < 0) {
         return false;
     }
@@ -309,6 +316,8 @@ BlockJobInfo *block_job_query(BlockJob *job, Error **errp)
     BlockJobInfo *info;
     uint64_t progress_current, progress_total;
 
+    assert(qemu_in_main_thread());
+
     if (block_job_is_internal(job)) {
         error_setg(errp, "Cannot query QEMU internal jobs");
         return NULL;
@@ -498,6 +507,7 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver,
 
 void block_job_iostatus_reset(BlockJob *job)
 {
+    assert(qemu_in_main_thread());
     if (job->iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
         return;
     }
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 13/25] include/sysemu/blockdev.h: move drive_add and inline drive_def
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (11 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 12/25] assertions for blockob.h " Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-12 11:06   ` Paolo Bonzini
  2021-10-21 15:08   ` Stefan Hajnoczi
  2021-10-12  8:48 ` [PATCH v3 14/25] include/systemu/blockdev.h: global state API Emanuele Giuseppe Esposito
                   ` (11 subsequent siblings)
  24 siblings, 2 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

drive_add is only used in softmmu/vl.c, so it can be a static
function there, and drive_def is only a particular use case of
qemu_opts_parse_noisily, so it can be inlined.

Also remove drive_mark_claimed_by_board, as it is only defined
but not implemented (nor used) anywhere.

This also helps simplifying next patch.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 block/monitor/block-hmp-cmds.c |  2 +-
 blockdev.c                     | 27 +--------------------------
 include/sysemu/blockdev.h      |  6 ++----
 softmmu/vl.c                   | 25 ++++++++++++++++++++++++-
 4 files changed, 28 insertions(+), 32 deletions(-)

diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c
index 2ac4aedfff..bfb3c043a0 100644
--- a/block/monitor/block-hmp-cmds.c
+++ b/block/monitor/block-hmp-cmds.c
@@ -101,7 +101,7 @@ void hmp_drive_add(Monitor *mon, const QDict *qdict)
         return;
     }
 
-    opts = drive_def(optstr);
+    opts = qemu_opts_parse_noisily(qemu_find_opts("drive"), optstr, false);
     if (!opts)
         return;
 
diff --git a/blockdev.c b/blockdev.c
index c1f6171c6c..1bf49ef610 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -73,7 +73,7 @@ void bdrv_set_monitor_owned(BlockDriverState *bs)
     QTAILQ_INSERT_TAIL(&monitor_bdrv_states, bs, monitor_list);
 }
 
-static const char *const if_name[IF_COUNT] = {
+const char *const if_name[IF_COUNT] = {
     [IF_NONE] = "none",
     [IF_IDE] = "ide",
     [IF_SCSI] = "scsi",
@@ -199,31 +199,6 @@ static int drive_index_to_unit_id(BlockInterfaceType type, int index)
     return max_devs ? index % max_devs : index;
 }
 
-QemuOpts *drive_def(const char *optstr)
-{
-    return qemu_opts_parse_noisily(qemu_find_opts("drive"), optstr, false);
-}
-
-QemuOpts *drive_add(BlockInterfaceType type, int index, const char *file,
-                    const char *optstr)
-{
-    QemuOpts *opts;
-
-    opts = drive_def(optstr);
-    if (!opts) {
-        return NULL;
-    }
-    if (type != IF_DEFAULT) {
-        qemu_opt_set(opts, "if", if_name[type], &error_abort);
-    }
-    if (index >= 0) {
-        qemu_opt_set_number(opts, "index", index, &error_abort);
-    }
-    if (file)
-        qemu_opt_set(opts, "file", file, &error_abort);
-    return opts;
-}
-
 DriveInfo *drive_get(BlockInterfaceType type, int bus, int unit)
 {
     BlockBackend *blk;
diff --git a/include/sysemu/blockdev.h b/include/sysemu/blockdev.h
index 32c2d6023c..960b54d320 100644
--- a/include/sysemu/blockdev.h
+++ b/include/sysemu/blockdev.h
@@ -27,6 +27,8 @@ typedef enum {
     IF_COUNT
 } BlockInterfaceType;
 
+extern const char *const if_name[];
+
 struct DriveInfo {
     BlockInterfaceType type;
     int bus;
@@ -45,16 +47,12 @@ BlockBackend *blk_by_legacy_dinfo(DriveInfo *dinfo);
 void override_max_devs(BlockInterfaceType type, int max_devs);
 
 DriveInfo *drive_get(BlockInterfaceType type, int bus, int unit);
-void drive_mark_claimed_by_board(void);
 void drive_check_orphaned(void);
 DriveInfo *drive_get_by_index(BlockInterfaceType type, int index);
 int drive_get_max_bus(BlockInterfaceType type);
 int drive_get_max_devs(BlockInterfaceType type);
 DriveInfo *drive_get_next(BlockInterfaceType type);
 
-QemuOpts *drive_def(const char *optstr);
-QemuOpts *drive_add(BlockInterfaceType type, int index, const char *file,
-                    const char *optstr);
 DriveInfo *drive_new(QemuOpts *arg, BlockInterfaceType block_default_type,
                      Error **errp);
 
diff --git a/softmmu/vl.c b/softmmu/vl.c
index 55ab70eb97..2e76300820 100644
--- a/softmmu/vl.c
+++ b/softmmu/vl.c
@@ -625,6 +625,27 @@ static int drive_enable_snapshot(void *opaque, QemuOpts *opts, Error **errp)
     return 0;
 }
 
+static QemuOpts *drive_add(BlockInterfaceType type, int index,
+                           const char *file, const char *optstr)
+{
+    QemuOpts *opts;
+
+    opts = qemu_opts_parse_noisily(qemu_find_opts("drive"), optstr, false);
+    if (!opts) {
+        return NULL;
+    }
+    if (type != IF_DEFAULT) {
+        qemu_opt_set(opts, "if", if_name[type], &error_abort);
+    }
+    if (index >= 0) {
+        qemu_opt_set_number(opts, "index", index, &error_abort);
+    }
+    if (file) {
+        qemu_opt_set(opts, "file", file, &error_abort);
+    }
+    return opts;
+}
+
 static void default_drive(int enable, int snapshot, BlockInterfaceType type,
                           int index, const char *optstr)
 {
@@ -2844,7 +2865,9 @@ void qemu_init(int argc, char **argv, char **envp)
                     break;
                 }
             case QEMU_OPTION_drive:
-                if (drive_def(optarg) == NULL) {
+                opts = qemu_opts_parse_noisily(qemu_find_opts("drive"),
+                                               optarg, false);
+                if (opts == NULL) {
                     exit(1);
                 }
                 break;
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 14/25] include/systemu/blockdev.h: global state API
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (12 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 13/25] include/sysemu/blockdev.h: move drive_add and inline drive_def Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-12 11:07   ` Paolo Bonzini
  2021-10-12  8:48 ` [PATCH v3 15/25] assertions for blockdev.h " Emanuele Giuseppe Esposito
                   ` (10 subsequent siblings)
  24 siblings, 1 reply; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

blockdev functions run always under the BQL lock.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 include/sysemu/blockdev.h | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/include/sysemu/blockdev.h b/include/sysemu/blockdev.h
index 960b54d320..cc9dfb5181 100644
--- a/include/sysemu/blockdev.h
+++ b/include/sysemu/blockdev.h
@@ -40,7 +40,13 @@ struct DriveInfo {
     QTAILQ_ENTRY(DriveInfo) next;
 };
 
-DriveInfo *blk_legacy_dinfo(BlockBackend *blk);
+/*
+ * Global state (GS) API. These functions run under the BQL lock.
+ *
+ * See include/block/block-global-state.h for more information about
+ * the GS API.
+ */
+
 DriveInfo *blk_set_legacy_dinfo(BlockBackend *blk, DriveInfo *dinfo);
 BlockBackend *blk_by_legacy_dinfo(DriveInfo *dinfo);
 
@@ -50,10 +56,14 @@ DriveInfo *drive_get(BlockInterfaceType type, int bus, int unit);
 void drive_check_orphaned(void);
 DriveInfo *drive_get_by_index(BlockInterfaceType type, int index);
 int drive_get_max_bus(BlockInterfaceType type);
-int drive_get_max_devs(BlockInterfaceType type);
 DriveInfo *drive_get_next(BlockInterfaceType type);
 
 DriveInfo *drive_new(QemuOpts *arg, BlockInterfaceType block_default_type,
                      Error **errp);
 
+/* Common functions that are neither I/O nor Global State */
+
+DriveInfo *blk_legacy_dinfo(BlockBackend *blk);
+int drive_get_max_devs(BlockInterfaceType type);
+
 #endif
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 15/25] assertions for blockdev.h global state API
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (13 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 14/25] include/systemu/blockdev.h: global state API Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-12  8:48 ` [PATCH v3 16/25] include/block/snapshot: global state API + assertions Emanuele Giuseppe Esposito
                   ` (9 subsequent siblings)
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block/block-backend.c |  2 ++
 blockdev.c            | 12 ++++++++++++
 2 files changed, 14 insertions(+)

diff --git a/block/block-backend.c b/block/block-backend.c
index 6f36a54e82..f2c724b487 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -805,6 +805,7 @@ DriveInfo *blk_legacy_dinfo(BlockBackend *blk)
 DriveInfo *blk_set_legacy_dinfo(BlockBackend *blk, DriveInfo *dinfo)
 {
     assert(!blk->legacy_dinfo);
+    assert(qemu_in_main_thread());
     return blk->legacy_dinfo = dinfo;
 }
 
@@ -815,6 +816,7 @@ DriveInfo *blk_set_legacy_dinfo(BlockBackend *blk, DriveInfo *dinfo)
 BlockBackend *blk_by_legacy_dinfo(DriveInfo *dinfo)
 {
     BlockBackend *blk = NULL;
+    assert(qemu_in_main_thread());
 
     while ((blk = blk_next(blk)) != NULL) {
         if (blk->legacy_dinfo == dinfo) {
diff --git a/blockdev.c b/blockdev.c
index 1bf49ef610..f4bde8a8d2 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -113,6 +113,8 @@ void override_max_devs(BlockInterfaceType type, int max_devs)
     BlockBackend *blk;
     DriveInfo *dinfo;
 
+    assert(qemu_in_main_thread());
+
     if (max_devs <= 0) {
         return;
     }
@@ -204,6 +206,8 @@ DriveInfo *drive_get(BlockInterfaceType type, int bus, int unit)
     BlockBackend *blk;
     DriveInfo *dinfo;
 
+    assert(qemu_in_main_thread());
+
     for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
         dinfo = blk_legacy_dinfo(blk);
         if (dinfo && dinfo->type == type
@@ -226,6 +230,8 @@ void drive_check_orphaned(void)
     Location loc;
     bool orphans = false;
 
+    assert(qemu_in_main_thread());
+
     for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
         dinfo = blk_legacy_dinfo(blk);
         /*
@@ -259,6 +265,7 @@ void drive_check_orphaned(void)
 
 DriveInfo *drive_get_by_index(BlockInterfaceType type, int index)
 {
+    assert(qemu_in_main_thread());
     return drive_get(type,
                      drive_index_to_bus_id(type, index),
                      drive_index_to_unit_id(type, index));
@@ -270,6 +277,8 @@ int drive_get_max_bus(BlockInterfaceType type)
     BlockBackend *blk;
     DriveInfo *dinfo;
 
+    assert(qemu_in_main_thread());
+
     max_bus = -1;
     for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
         dinfo = blk_legacy_dinfo(blk);
@@ -286,6 +295,7 @@ int drive_get_max_bus(BlockInterfaceType type)
 DriveInfo *drive_get_next(BlockInterfaceType type)
 {
     static int next_block_unit[IF_COUNT];
+    assert(qemu_in_main_thread());
 
     return drive_get(type, 0, next_block_unit[type]++);
 }
@@ -766,6 +776,8 @@ DriveInfo *drive_new(QemuOpts *all_opts, BlockInterfaceType block_default_type,
     const char *filename;
     int i;
 
+    assert(qemu_in_main_thread());
+
     /* Change legacy command line options into QMP ones */
     static const struct {
         const char *from;
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 16/25] include/block/snapshot: global state API + assertions
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (14 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 15/25] assertions for blockdev.h " Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-12  8:48 ` [PATCH v3 17/25] block/copy-before-write.h: " Emanuele Giuseppe Esposito
                   ` (8 subsequent siblings)
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

Snapshots run also under the BQL lock, so they all are
in the global state API. The aiocontext lock that they hold
is currently an overkill and in future could be removed.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block/snapshot.c         | 28 ++++++++++++++++++++++++++++
 include/block/snapshot.h | 13 +++++++++++--
 migration/savevm.c       |  2 ++
 3 files changed, 41 insertions(+), 2 deletions(-)

diff --git a/block/snapshot.c b/block/snapshot.c
index ccacda8bd5..3dd3c9d3bd 100644
--- a/block/snapshot.c
+++ b/block/snapshot.c
@@ -57,6 +57,8 @@ int bdrv_snapshot_find(BlockDriverState *bs, QEMUSnapshotInfo *sn_info,
     QEMUSnapshotInfo *sn_tab, *sn;
     int nb_sns, i, ret;
 
+    assert(qemu_in_main_thread());
+
     ret = -ENOENT;
     nb_sns = bdrv_snapshot_list(bs, &sn_tab);
     if (nb_sns < 0) {
@@ -105,6 +107,7 @@ bool bdrv_snapshot_find_by_id_and_name(BlockDriverState *bs,
     bool ret = false;
 
     assert(id || name);
+    assert(qemu_in_main_thread());
 
     nb_sns = bdrv_snapshot_list(bs, &sn_tab);
     if (nb_sns < 0) {
@@ -200,6 +203,7 @@ static BlockDriverState *bdrv_snapshot_fallback(BlockDriverState *bs)
 int bdrv_can_snapshot(BlockDriverState *bs)
 {
     BlockDriver *drv = bs->drv;
+    assert(qemu_in_main_thread());
     if (!drv || !bdrv_is_inserted(bs) || bdrv_is_read_only(bs)) {
         return 0;
     }
@@ -220,6 +224,9 @@ int bdrv_snapshot_create(BlockDriverState *bs,
 {
     BlockDriver *drv = bs->drv;
     BlockDriverState *fallback_bs = bdrv_snapshot_fallback(bs);
+
+    assert(qemu_in_main_thread());
+
     if (!drv) {
         return -ENOMEDIUM;
     }
@@ -240,6 +247,8 @@ int bdrv_snapshot_goto(BlockDriverState *bs,
     BdrvChild **fallback_ptr;
     int ret, open_ret;
 
+    assert(qemu_in_main_thread());
+
     if (!drv) {
         error_setg(errp, "Block driver is closed");
         return -ENOMEDIUM;
@@ -348,6 +357,8 @@ int bdrv_snapshot_delete(BlockDriverState *bs,
     BlockDriverState *fallback_bs = bdrv_snapshot_fallback(bs);
     int ret;
 
+    assert(qemu_in_main_thread());
+
     if (!drv) {
         error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, bdrv_get_device_name(bs));
         return -ENOMEDIUM;
@@ -380,6 +391,8 @@ int bdrv_snapshot_list(BlockDriverState *bs,
 {
     BlockDriver *drv = bs->drv;
     BlockDriverState *fallback_bs = bdrv_snapshot_fallback(bs);
+
+    assert(qemu_in_main_thread());
     if (!drv) {
         return -ENOMEDIUM;
     }
@@ -419,6 +432,8 @@ int bdrv_snapshot_load_tmp(BlockDriverState *bs,
 {
     BlockDriver *drv = bs->drv;
 
+    assert(qemu_in_main_thread());
+
     if (!drv) {
         error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, bdrv_get_device_name(bs));
         return -ENOMEDIUM;
@@ -447,6 +462,8 @@ int bdrv_snapshot_load_tmp_by_id_or_name(BlockDriverState *bs,
     int ret;
     Error *local_err = NULL;
 
+    assert(qemu_in_main_thread());
+
     ret = bdrv_snapshot_load_tmp(bs, id_or_name, NULL, &local_err);
     if (ret == -ENOENT || ret == -EINVAL) {
         error_free(local_err);
@@ -515,6 +532,8 @@ bool bdrv_all_can_snapshot(bool has_devices, strList *devices,
     g_autoptr(GList) bdrvs = NULL;
     GList *iterbdrvs;
 
+    assert(qemu_in_main_thread());
+
     if (bdrv_all_get_snapshot_devices(has_devices, devices, &bdrvs, errp) < 0) {
         return false;
     }
@@ -549,6 +568,8 @@ int bdrv_all_delete_snapshot(const char *name,
     g_autoptr(GList) bdrvs = NULL;
     GList *iterbdrvs;
 
+    assert(qemu_in_main_thread());
+
     if (bdrv_all_get_snapshot_devices(has_devices, devices, &bdrvs, errp) < 0) {
         return -1;
     }
@@ -588,6 +609,8 @@ int bdrv_all_goto_snapshot(const char *name,
     g_autoptr(GList) bdrvs = NULL;
     GList *iterbdrvs;
 
+    assert(qemu_in_main_thread());
+
     if (bdrv_all_get_snapshot_devices(has_devices, devices, &bdrvs, errp) < 0) {
         return -1;
     }
@@ -622,6 +645,8 @@ int bdrv_all_has_snapshot(const char *name,
     g_autoptr(GList) bdrvs = NULL;
     GList *iterbdrvs;
 
+    assert(qemu_in_main_thread());
+
     if (bdrv_all_get_snapshot_devices(has_devices, devices, &bdrvs, errp) < 0) {
         return -1;
     }
@@ -663,6 +688,7 @@ int bdrv_all_create_snapshot(QEMUSnapshotInfo *sn,
 {
     g_autoptr(GList) bdrvs = NULL;
     GList *iterbdrvs;
+    assert(qemu_in_main_thread());
 
     if (bdrv_all_get_snapshot_devices(has_devices, devices, &bdrvs, errp) < 0) {
         return -1;
@@ -703,6 +729,8 @@ BlockDriverState *bdrv_all_find_vmstate_bs(const char *vmstate_bs,
     g_autoptr(GList) bdrvs = NULL;
     GList *iterbdrvs;
 
+    assert(qemu_in_main_thread());
+
     if (bdrv_all_get_snapshot_devices(has_devices, devices, &bdrvs, errp) < 0) {
         return NULL;
     }
diff --git a/include/block/snapshot.h b/include/block/snapshot.h
index 940345692f..cda82c1ba1 100644
--- a/include/block/snapshot.h
+++ b/include/block/snapshot.h
@@ -45,6 +45,13 @@ typedef struct QEMUSnapshotInfo {
     uint64_t icount; /* record/replay step */
 } QEMUSnapshotInfo;
 
+/*
+ * Global state (GS) API. These functions run under the BQL lock.
+ *
+ * See include/block/block-global-state.h for more information about
+ * the GS API.
+ */
+
 int bdrv_snapshot_find(BlockDriverState *bs, QEMUSnapshotInfo *sn_info,
                        const char *name);
 bool bdrv_snapshot_find_by_id_and_name(BlockDriverState *bs,
@@ -73,9 +80,11 @@ int bdrv_snapshot_load_tmp_by_id_or_name(BlockDriverState *bs,
                                          Error **errp);
 
 
-/* Group operations. All block drivers are involved.
+/*
+ * Group operations. All block drivers are involved.
  * These functions will properly handle dataplane (take aio_context_acquire
- * when appropriate for appropriate block drivers */
+ * when appropriate for appropriate block drivers
+ */
 
 bool bdrv_all_can_snapshot(bool has_devices, strList *devices,
                            Error **errp);
diff --git a/migration/savevm.c b/migration/savevm.c
index 7b7b64bd13..5dd740f8e7 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -2785,6 +2785,8 @@ bool save_snapshot(const char *name, bool overwrite, const char *vmstate,
     g_autoptr(GDateTime) now = g_date_time_new_now_local();
     AioContext *aio_context;
 
+    assert(qemu_in_main_thread());
+
     if (migration_is_blocked(errp)) {
         return false;
     }
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 17/25] block/copy-before-write.h: global state API + assertions
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (15 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 16/25] include/block/snapshot: global state API + assertions Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-21 15:10   ` Stefan Hajnoczi
  2021-10-12  8:48 ` [PATCH v3 18/25] block/coroutines: I/O API Emanuele Giuseppe Esposito
                   ` (7 subsequent siblings)
  24 siblings, 1 reply; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

copy-before-write functions always run under BQL lock.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
---
 block/copy-before-write.c | 2 ++
 block/copy-before-write.h | 7 +++++++
 2 files changed, 9 insertions(+)

diff --git a/block/copy-before-write.c b/block/copy-before-write.c
index c30a5ff8de..36a8d7ba52 100644
--- a/block/copy-before-write.c
+++ b/block/copy-before-write.c
@@ -223,6 +223,7 @@ BlockDriverState *bdrv_cbw_append(BlockDriverState *source,
     QDict *opts;
 
     assert(source->total_sectors == target->total_sectors);
+    assert(qemu_in_main_thread());
 
     opts = qdict_new();
     qdict_put_str(opts, "driver", "copy-before-write");
@@ -245,6 +246,7 @@ BlockDriverState *bdrv_cbw_append(BlockDriverState *source,
 
 void bdrv_cbw_drop(BlockDriverState *bs)
 {
+    assert(qemu_in_main_thread());
     bdrv_drop_filter(bs, &error_abort);
     bdrv_unref(bs);
 }
diff --git a/block/copy-before-write.h b/block/copy-before-write.h
index 51847e711a..9a45de2fce 100644
--- a/block/copy-before-write.h
+++ b/block/copy-before-write.h
@@ -29,6 +29,13 @@
 #include "block/block_int.h"
 #include "block/block-copy.h"
 
+/*
+ * Global state (GS) API. These functions run under the BQL lock.
+ *
+ * See include/block/block-global-state.h for more information about
+ * the GS API.
+ */
+
 BlockDriverState *bdrv_cbw_append(BlockDriverState *source,
                                   BlockDriverState *target,
                                   const char *filter_node_name,
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 18/25] block/coroutines: I/O API
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (16 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 17/25] block/copy-before-write.h: " Emanuele Giuseppe Esposito
@ 2021-10-12  8:48 ` Emanuele Giuseppe Esposito
  2021-10-12  8:49 ` [PATCH v3 19/25] block_int-common.h: split function pointers in BlockDriver Emanuele Giuseppe Esposito
                   ` (6 subsequent siblings)
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:48 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

block coroutines functions run in different aiocontext, and are
not protected by the BQL. Therefore are I/O.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block/coroutines.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/block/coroutines.h b/block/coroutines.h
index 514d169d23..079de537a0 100644
--- a/block/coroutines.h
+++ b/block/coroutines.h
@@ -27,6 +27,13 @@
 
 #include "block/block_int.h"
 
+/*
+ * I/O API functions. These functions are thread-safe.
+ *
+ * See include/block/block-io.h for more information about
+ * the I/O API.
+ */
+
 int coroutine_fn bdrv_co_check(BlockDriverState *bs,
                                BdrvCheckResult *res, BdrvCheckMode fix);
 int coroutine_fn bdrv_co_invalidate_cache(BlockDriverState *bs, Error **errp);
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 19/25] block_int-common.h: split function pointers in BlockDriver
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (17 preceding siblings ...)
  2021-10-12  8:48 ` [PATCH v3 18/25] block/coroutines: I/O API Emanuele Giuseppe Esposito
@ 2021-10-12  8:49 ` Emanuele Giuseppe Esposito
  2021-10-12  8:49 ` [PATCH v3 20/25] block_int-common.h: assertion in the callers of BlockDriver function pointers Emanuele Giuseppe Esposito
                   ` (5 subsequent siblings)
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:49 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

Similar to the header split, also the function pointers in BlockDriver
can be split in I/O and global state.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/block/block_int-common.h | 458 ++++++++++++++++---------------
 1 file changed, 237 insertions(+), 221 deletions(-)

diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 79a3d801d2..9857e775fe 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -96,6 +96,7 @@ typedef struct BdrvTrackedRequest {
 
 
 struct BlockDriver {
+    /* Fields initialized in struct definition and never changed. */
     const char *format_name;
     int instance_size;
 
@@ -121,23 +122,7 @@ struct BlockDriver {
      * on those children.
      */
     bool is_format;
-    /*
-     * Return true if @to_replace can be replaced by a BDS with the
-     * same data as @bs without it affecting @bs's behavior (that is,
-     * without it being visible to @bs's parents).
-     */
-    bool (*bdrv_recurse_can_replace)(BlockDriverState *bs,
-                                     BlockDriverState *to_replace);
 
-    int (*bdrv_probe)(const uint8_t *buf, int buf_size, const char *filename);
-    int (*bdrv_probe_device)(const char *filename);
-
-    /*
-     * Any driver implementing this callback is expected to be able to handle
-     * NULL file names in its .bdrv_open() implementation.
-     */
-    void (*bdrv_parse_filename)(const char *filename, QDict *options,
-                                Error **errp);
     /*
      * Drivers not implementing bdrv_parse_filename nor bdrv_open should have
      * this field set to true, except ones that are defined only by their
@@ -159,7 +144,66 @@ struct BlockDriver {
      */
     bool supports_backing;
 
-    /* For handling image reopen for split or non-split files */
+    /*
+     * Drivers setting this field must be able to work with just a plain
+     * filename with '<protocol_name>:' as a prefix, and no other options.
+     * Options may be extracted from the filename by implementing
+     * bdrv_parse_filename.
+     */
+    const char *protocol_name;
+
+    /* List of options for creating images, terminated by name == NULL */
+    QemuOptsList *create_opts;
+
+    /* List of options for image amend */
+    QemuOptsList *amend_opts;
+
+    /*
+     * If this driver supports reopening images this contains a
+     * NULL-terminated list of the runtime options that can be
+     * modified. If an option in this list is unspecified during
+     * reopen then it _must_ be reset to its default value or return
+     * an error.
+     */
+    const char *const *mutable_opts;
+
+    /*
+     * Pointer to a NULL-terminated array of names of strong options
+     * that can be specified for bdrv_open(). A strong option is one
+     * that changes the data of a BDS.
+     * If this pointer is NULL, the array is considered empty.
+     * "filename" and "driver" are always considered strong.
+     */
+    const char *const *strong_runtime_opts;
+
+    /*
+     * Global state (GS) API. These functions run under the BQL lock.
+     *
+     * See include/block/block-global-state.h for more information about
+     * the GS API.
+     */
+
+    /*
+     * Return true if @to_replace can be replaced by a BDS with the
+     * same data as @bs without it affecting @bs's behavior (that is,
+     * without it being visible to @bs's parents).
+     */
+    bool (*bdrv_recurse_can_replace)(BlockDriverState *bs,
+                                     BlockDriverState *to_replace);
+
+    int (*bdrv_probe)(const uint8_t *buf, int buf_size, const char *filename);
+    int (*bdrv_probe_device)(const char *filename);
+
+    /*
+     * Any driver implementing this callback is expected to be able to handle
+     * NULL file names in its .bdrv_open() implementation.
+     */
+    void (*bdrv_parse_filename)(const char *filename, QDict *options,
+                                Error **errp);
+
+    /*
+     * For handling image reopen for split or non-split files.
+     */
     int (*bdrv_reopen_prepare)(BDRVReopenState *reopen_state,
                                BlockReopenQueue *queue, Error **errp);
     void (*bdrv_reopen_commit)(BDRVReopenState *reopen_state);
@@ -175,19 +219,6 @@ struct BlockDriver {
                           Error **errp);
     void (*bdrv_close)(BlockDriverState *bs);
 
-
-    int coroutine_fn (*bdrv_co_create)(BlockdevCreateOptions *opts,
-                                       Error **errp);
-    int coroutine_fn (*bdrv_co_create_opts)(BlockDriver *drv,
-                                            const char *filename,
-                                            QemuOpts *opts,
-                                            Error **errp);
-
-    int coroutine_fn (*bdrv_co_amend)(BlockDriverState *bs,
-                                      BlockdevAmendOptions *opts,
-                                      bool force,
-                                      Error **errp);
-
     int (*bdrv_amend_options)(BlockDriverState *bs,
                               QemuOpts *opts,
                               BlockDriverAmendStatusCB *status_cb,
@@ -234,6 +265,182 @@ struct BlockDriver {
      */
     char *(*bdrv_dirname)(BlockDriverState *bs, Error **errp);
 
+    /*
+     * This informs the driver that we are no longer interested in the result
+     * of in-flight requests, so don't waste the time if possible.
+     *
+     * One example usage is to avoid waiting for an nbd target node reconnect
+     * timeout during job-cancel with force=true.
+     */
+    void (*bdrv_cancel_in_flight)(BlockDriverState *bs);
+
+    int (*bdrv_inactivate)(BlockDriverState *bs);
+
+    int (*bdrv_snapshot_create)(BlockDriverState *bs,
+                                QEMUSnapshotInfo *sn_info);
+    int (*bdrv_snapshot_goto)(BlockDriverState *bs,
+                              const char *snapshot_id);
+    int (*bdrv_snapshot_delete)(BlockDriverState *bs,
+                                const char *snapshot_id,
+                                const char *name,
+                                Error **errp);
+    int (*bdrv_snapshot_list)(BlockDriverState *bs,
+                              QEMUSnapshotInfo **psn_info);
+    int (*bdrv_snapshot_load_tmp)(BlockDriverState *bs,
+                                  const char *snapshot_id,
+                                  const char *name,
+                                  Error **errp);
+
+    int coroutine_fn (*bdrv_save_vmstate)(BlockDriverState *bs,
+                                          QEMUIOVector *qiov,
+                                          int64_t pos);
+    int coroutine_fn (*bdrv_load_vmstate)(BlockDriverState *bs,
+                                          QEMUIOVector *qiov,
+                                          int64_t pos);
+
+    int (*bdrv_change_backing_file)(BlockDriverState *bs,
+        const char *backing_file, const char *backing_fmt);
+
+    void (*bdrv_eject)(BlockDriverState *bs, bool eject_flag);
+    void (*bdrv_lock_medium)(BlockDriverState *bs, bool locked);
+
+    /* TODO Better pass a option string/QDict/QemuOpts to add any rule? */
+    int (*bdrv_debug_breakpoint)(BlockDriverState *bs, const char *event,
+        const char *tag);
+    int (*bdrv_debug_remove_breakpoint)(BlockDriverState *bs,
+        const char *tag);
+    int (*bdrv_debug_resume)(BlockDriverState *bs, const char *tag);
+    bool (*bdrv_debug_is_suspended)(BlockDriverState *bs, const char *tag);
+    void (*bdrv_refresh_limits)(BlockDriverState *bs, Error **errp);
+
+    /*
+     * Returns 1 if newly created images are guaranteed to contain only
+     * zeros, 0 otherwise.
+     */
+    int (*bdrv_has_zero_init)(BlockDriverState *bs);
+
+    /*
+     * Remove fd handlers, timers, and other event loop callbacks so the event
+     * loop is no longer in use.  Called with no in-flight requests and in
+     * depth-first traversal order with parents before child nodes.
+     */
+    void (*bdrv_detach_aio_context)(BlockDriverState *bs);
+
+    /*
+     * Add fd handlers, timers, and other event loop callbacks so I/O requests
+     * can be processed again.  Called with no in-flight requests and in
+     * depth-first traversal order with child nodes before parent nodes.
+     */
+    void (*bdrv_attach_aio_context)(BlockDriverState *bs,
+                                    AioContext *new_context);
+
+    /**
+     * Try to get @bs's logical and physical block size.
+     * On success, store them in @bsz and return zero.
+     * On failure, return negative errno.
+     */
+    int (*bdrv_probe_blocksizes)(BlockDriverState *bs, BlockSizes *bsz);
+    /**
+     * Try to get @bs's geometry (cyls, heads, sectors)
+     * On success, store them in @geo and return 0.
+     * On failure return -errno.
+     * Only drivers that want to override guest geometry implement this
+     * callback; see hd_geometry_guess().
+     */
+    int (*bdrv_probe_geometry)(BlockDriverState *bs, HDGeometry *geo);
+
+    void (*bdrv_add_child)(BlockDriverState *parent, BlockDriverState *child,
+                           Error **errp);
+    void (*bdrv_del_child)(BlockDriverState *parent, BdrvChild *child,
+                           Error **errp);
+
+    /**
+     * Informs the block driver that a permission change is intended. The
+     * driver checks whether the change is permissible and may take other
+     * preparations for the change (e.g. get file system locks). This operation
+     * is always followed either by a call to either .bdrv_set_perm or
+     * .bdrv_abort_perm_update.
+     *
+     * Checks whether the requested set of cumulative permissions in @perm
+     * can be granted for accessing @bs and whether no other users are using
+     * permissions other than those given in @shared (both arguments take
+     * BLK_PERM_* bitmasks).
+     *
+     * If both conditions are met, 0 is returned. Otherwise, -errno is returned
+     * and errp is set to an error describing the conflict.
+     */
+    int (*bdrv_check_perm)(BlockDriverState *bs, uint64_t perm,
+                           uint64_t shared, Error **errp);
+
+    /**
+     * Called to inform the driver that the set of cumulative set of used
+     * permissions for @bs has changed to @perm, and the set of sharable
+     * permission to @shared. The driver can use this to propagate changes to
+     * its children (i.e. request permissions only if a parent actually needs
+     * them).
+     *
+     * This function is only invoked after bdrv_check_perm(), so block drivers
+     * may rely on preparations made in their .bdrv_check_perm implementation.
+     */
+    void (*bdrv_set_perm)(BlockDriverState *bs, uint64_t perm, uint64_t shared);
+
+    /*
+     * Called to inform the driver that after a previous bdrv_check_perm()
+     * call, the permission update is not performed and any preparations made
+     * for it (e.g. taken file locks) need to be undone.
+     *
+     * This function can be called even for nodes that never saw a
+     * bdrv_check_perm() call. It is a no-op then.
+     */
+    void (*bdrv_abort_perm_update)(BlockDriverState *bs);
+
+    /**
+     * Returns in @nperm and @nshared the permissions that the driver for @bs
+     * needs on its child @c, based on the cumulative permissions requested by
+     * the parents in @parent_perm and @parent_shared.
+     *
+     * If @c is NULL, return the permissions for attaching a new child for the
+     * given @child_class and @role.
+     *
+     * If @reopen_queue is non-NULL, don't return the currently needed
+     * permissions, but those that will be needed after applying the
+     * @reopen_queue.
+     */
+     void (*bdrv_child_perm)(BlockDriverState *bs, BdrvChild *c,
+                             BdrvChildRole role,
+                             BlockReopenQueue *reopen_queue,
+                             uint64_t parent_perm, uint64_t parent_shared,
+                             uint64_t *nperm, uint64_t *nshared);
+
+    /**
+     * Register/unregister a buffer for I/O. For example, when the driver is
+     * interested to know the memory areas that will later be used in iovs, so
+     * 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.
+     */
+    void (*bdrv_register_buf)(BlockDriverState *bs, void *host, size_t size);
+    void (*bdrv_unregister_buf)(BlockDriverState *bs, void *host);
+    QLIST_ENTRY(BlockDriver) list;
+
+    /*
+     * I/O API functions. These functions are thread-safe.
+     *
+     * See include/block/block-io.h for more information about
+     * the I/O API.
+     */
+
+    int coroutine_fn (*bdrv_co_create)(BlockdevCreateOptions *opts,
+                                       Error **errp);
+    int coroutine_fn (*bdrv_co_create_opts)(BlockDriver *drv,
+                                            const char *filename,
+                                            QemuOpts *opts,
+                                            Error **errp);
+    int coroutine_fn (*bdrv_co_amend)(BlockDriverState *bs,
+                                      BlockdevAmendOptions *opts,
+                                      bool force,
+                                      Error **errp);
+
     /* aio */
     BlockAIOCB *(*bdrv_aio_preadv)(BlockDriverState *bs,
         int64_t offset, int64_t bytes, QEMUIOVector *qiov,
@@ -374,21 +581,11 @@ struct BlockDriver {
         bool want_zero, int64_t offset, int64_t bytes, int64_t *pnum,
         int64_t *map, BlockDriverState **file);
 
-    /*
-     * This informs the driver that we are no longer interested in the result
-     * of in-flight requests, so don't waste the time if possible.
-     *
-     * One example usage is to avoid waiting for an nbd target node reconnect
-     * timeout during job-cancel with force=true.
-     */
-    void (*bdrv_cancel_in_flight)(BlockDriverState *bs);
-
     /*
      * Invalidate any cached meta-data.
      */
     void coroutine_fn (*bdrv_co_invalidate_cache)(BlockDriverState *bs,
                                                   Error **errp);
-    int (*bdrv_inactivate)(BlockDriverState *bs);
 
     /*
      * Flushes all data for all layers by calling bdrv_co_flush for underlying
@@ -414,14 +611,6 @@ struct BlockDriver {
      */
     int coroutine_fn (*bdrv_co_flush_to_os)(BlockDriverState *bs);
 
-    /*
-     * Drivers setting this field must be able to work with just a plain
-     * filename with '<protocol_name>:' as a prefix, and no other options.
-     * Options may be extracted from the filename by implementing
-     * bdrv_parse_filename.
-     */
-    const char *protocol_name;
-
     /*
      * Truncate @bs to @offset bytes using the given @prealloc mode
      * when growing.  Modes other than PREALLOC_MODE_OFF should be
@@ -443,47 +632,20 @@ struct BlockDriver {
     int64_t (*bdrv_get_allocated_file_size)(BlockDriverState *bs);
     BlockMeasureInfo *(*bdrv_measure)(QemuOpts *opts, BlockDriverState *in_bs,
                                       Error **errp);
-
     int coroutine_fn (*bdrv_co_pwritev_compressed)(BlockDriverState *bs,
         int64_t offset, int64_t bytes, QEMUIOVector *qiov);
     int coroutine_fn (*bdrv_co_pwritev_compressed_part)(BlockDriverState *bs,
         int64_t offset, int64_t bytes, QEMUIOVector *qiov,
         size_t qiov_offset);
 
-    int (*bdrv_snapshot_create)(BlockDriverState *bs,
-                                QEMUSnapshotInfo *sn_info);
-    int (*bdrv_snapshot_goto)(BlockDriverState *bs,
-                              const char *snapshot_id);
-    int (*bdrv_snapshot_delete)(BlockDriverState *bs,
-                                const char *snapshot_id,
-                                const char *name,
-                                Error **errp);
-    int (*bdrv_snapshot_list)(BlockDriverState *bs,
-                              QEMUSnapshotInfo **psn_info);
-    int (*bdrv_snapshot_load_tmp)(BlockDriverState *bs,
-                                  const char *snapshot_id,
-                                  const char *name,
-                                  Error **errp);
     int (*bdrv_get_info)(BlockDriverState *bs, BlockDriverInfo *bdi);
 
     ImageInfoSpecific *(*bdrv_get_specific_info)(BlockDriverState *bs,
                                                  Error **errp);
     BlockStatsSpecific *(*bdrv_get_specific_stats)(BlockDriverState *bs);
 
-    int coroutine_fn (*bdrv_save_vmstate)(BlockDriverState *bs,
-                                          QEMUIOVector *qiov,
-                                          int64_t pos);
-    int coroutine_fn (*bdrv_load_vmstate)(BlockDriverState *bs,
-                                          QEMUIOVector *qiov,
-                                          int64_t pos);
-
-    int (*bdrv_change_backing_file)(BlockDriverState *bs,
-        const char *backing_file, const char *backing_fmt);
-
     /* removable device specific */
     bool (*bdrv_is_inserted)(BlockDriverState *bs);
-    void (*bdrv_eject)(BlockDriverState *bs, bool eject_flag);
-    void (*bdrv_lock_medium)(BlockDriverState *bs, bool locked);
 
     /* to control generic scsi devices */
     BlockAIOCB *(*bdrv_aio_ioctl)(BlockDriverState *bs,
@@ -492,21 +654,6 @@ struct BlockDriver {
     int coroutine_fn (*bdrv_co_ioctl)(BlockDriverState *bs,
                                       unsigned long int req, void *buf);
 
-    /* List of options for creating images, terminated by name == NULL */
-    QemuOptsList *create_opts;
-
-    /* List of options for image amend */
-    QemuOptsList *amend_opts;
-
-    /*
-     * If this driver supports reopening images this contains a
-     * NULL-terminated list of the runtime options that can be
-     * modified. If an option in this list is unspecified during
-     * reopen then it _must_ be reset to its default value or return
-     * an error.
-     */
-    const char *const *mutable_opts;
-
     /*
      * Returns 0 for completed check, -errno for internal errors.
      * The check results are stored in result.
@@ -517,58 +664,10 @@ struct BlockDriver {
 
     void (*bdrv_debug_event)(BlockDriverState *bs, BlkdebugEvent event);
 
-    /* TODO Better pass a option string/QDict/QemuOpts to add any rule? */
-    int (*bdrv_debug_breakpoint)(BlockDriverState *bs, const char *event,
-        const char *tag);
-    int (*bdrv_debug_remove_breakpoint)(BlockDriverState *bs,
-        const char *tag);
-    int (*bdrv_debug_resume)(BlockDriverState *bs, const char *tag);
-    bool (*bdrv_debug_is_suspended)(BlockDriverState *bs, const char *tag);
-
-    void (*bdrv_refresh_limits)(BlockDriverState *bs, Error **errp);
-
-    /*
-     * Returns 1 if newly created images are guaranteed to contain only
-     * zeros, 0 otherwise.
-     */
-    int (*bdrv_has_zero_init)(BlockDriverState *bs);
-
-    /*
-     * Remove fd handlers, timers, and other event loop callbacks so the event
-     * loop is no longer in use.  Called with no in-flight requests and in
-     * depth-first traversal order with parents before child nodes.
-     */
-    void (*bdrv_detach_aio_context)(BlockDriverState *bs);
-
-    /*
-     * Add fd handlers, timers, and other event loop callbacks so I/O requests
-     * can be processed again.  Called with no in-flight requests and in
-     * depth-first traversal order with child nodes before parent nodes.
-     */
-    void (*bdrv_attach_aio_context)(BlockDriverState *bs,
-                                    AioContext *new_context);
-
     /* io queue for linux-aio */
     void (*bdrv_io_plug)(BlockDriverState *bs);
     void (*bdrv_io_unplug)(BlockDriverState *bs);
 
-    /**
-     * Try to get @bs's logical and physical block size.
-     * On success, store them in @bsz and return zero.
-     * On failure, return negative errno.
-     */
-    /* I/O API, even though if it's a filter jumps on parent */
-    int (*bdrv_probe_blocksizes)(BlockDriverState *bs, BlockSizes *bsz);
-    /**
-     * Try to get @bs's geometry (cyls, heads, sectors)
-     * On success, store them in @geo and return 0.
-     * On failure return -errno.
-     * Only drivers that want to override guest geometry implement this
-     * callback; see hd_geometry_guess().
-     */
-    /* I/O API, even though if it's a filter jumps on parent */
-    int (*bdrv_probe_geometry)(BlockDriverState *bs, HDGeometry *geo);
-
     /**
      * bdrv_co_drain_begin is called if implemented in the beginning of a
      * drain operation to drain and stop any internal sources of requests in
@@ -582,69 +681,6 @@ struct BlockDriver {
     void coroutine_fn (*bdrv_co_drain_begin)(BlockDriverState *bs);
     void coroutine_fn (*bdrv_co_drain_end)(BlockDriverState *bs);
 
-    void (*bdrv_add_child)(BlockDriverState *parent, BlockDriverState *child,
-                           Error **errp);
-    void (*bdrv_del_child)(BlockDriverState *parent, BdrvChild *child,
-                           Error **errp);
-
-    /**
-     * Informs the block driver that a permission change is intended. The
-     * driver checks whether the change is permissible and may take other
-     * preparations for the change (e.g. get file system locks). This operation
-     * is always followed either by a call to either .bdrv_set_perm or
-     * .bdrv_abort_perm_update.
-     *
-     * Checks whether the requested set of cumulative permissions in @perm
-     * can be granted for accessing @bs and whether no other users are using
-     * permissions other than those given in @shared (both arguments take
-     * BLK_PERM_* bitmasks).
-     *
-     * If both conditions are met, 0 is returned. Otherwise, -errno is returned
-     * and errp is set to an error describing the conflict.
-     */
-    int (*bdrv_check_perm)(BlockDriverState *bs, uint64_t perm,
-                           uint64_t shared, Error **errp);
-
-    /**
-     * Called to inform the driver that the set of cumulative set of used
-     * permissions for @bs has changed to @perm, and the set of sharable
-     * permission to @shared. The driver can use this to propagate changes to
-     * its children (i.e. request permissions only if a parent actually needs
-     * them).
-     *
-     * This function is only invoked after bdrv_check_perm(), so block drivers
-     * may rely on preparations made in their .bdrv_check_perm implementation.
-     */
-    void (*bdrv_set_perm)(BlockDriverState *bs, uint64_t perm, uint64_t shared);
-
-    /*
-     * Called to inform the driver that after a previous bdrv_check_perm()
-     * call, the permission update is not performed and any preparations made
-     * for it (e.g. taken file locks) need to be undone.
-     *
-     * This function can be called even for nodes that never saw a
-     * bdrv_check_perm() call. It is a no-op then.
-     */
-    void (*bdrv_abort_perm_update)(BlockDriverState *bs);
-
-    /**
-     * Returns in @nperm and @nshared the permissions that the driver for @bs
-     * needs on its child @c, based on the cumulative permissions requested by
-     * the parents in @parent_perm and @parent_shared.
-     *
-     * If @c is NULL, return the permissions for attaching a new child for the
-     * given @child_class and @role.
-     *
-     * If @reopen_queue is non-NULL, don't return the currently needed
-     * permissions, but those that will be needed after applying the
-     * @reopen_queue.
-     */
-     void (*bdrv_child_perm)(BlockDriverState *bs, BdrvChild *c,
-                             BdrvChildRole role,
-                             BlockReopenQueue *reopen_queue,
-                             uint64_t parent_perm, uint64_t parent_shared,
-                             uint64_t *nperm, uint64_t *nshared);
-
     bool (*bdrv_supports_persistent_dirty_bitmap)(BlockDriverState *bs);
     bool (*bdrv_co_can_store_new_dirty_bitmap)(BlockDriverState *bs,
                                                const char *name,
@@ -653,26 +689,6 @@ struct BlockDriver {
     int (*bdrv_co_remove_persistent_dirty_bitmap)(BlockDriverState *bs,
                                                   const char *name,
                                                   Error **errp);
-
-    /**
-     * Register/unregister a buffer for I/O. For example, when the driver is
-     * interested to know the memory areas that will later be used in iovs, so
-     * 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.
-     */
-    void (*bdrv_register_buf)(BlockDriverState *bs, void *host, size_t size);
-    void (*bdrv_unregister_buf)(BlockDriverState *bs, void *host);
-    QLIST_ENTRY(BlockDriver) list;
-
-    /*
-     * Pointer to a NULL-terminated array of names of strong options
-     * that can be specified for bdrv_open(). A strong option is one
-     * that changes the data of a BDS.
-     * If this pointer is NULL, the array is considered empty.
-     * "filename" and "driver" are always considered strong.
-     */
-    const char *const *strong_runtime_opts;
 };
 
 static inline bool block_driver_can_compress(BlockDriver *drv)
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 20/25] block_int-common.h: assertion in the callers of BlockDriver function pointers
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (18 preceding siblings ...)
  2021-10-12  8:49 ` [PATCH v3 19/25] block_int-common.h: split function pointers in BlockDriver Emanuele Giuseppe Esposito
@ 2021-10-12  8:49 ` Emanuele Giuseppe Esposito
  2021-10-12  8:49 ` [PATCH v3 21/25] block_int-common.h: split function pointers in BdrvChildClass Emanuele Giuseppe Esposito
                   ` (4 subsequent siblings)
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:49 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/block.c b/block.c
index 94bff5c757..40c4729b8d 100644
--- a/block.c
+++ b/block.c
@@ -1074,6 +1074,7 @@ int refresh_total_sectors(BlockDriverState *bs, int64_t hint)
 static void bdrv_join_options(BlockDriverState *bs, QDict *options,
                               QDict *old_options)
 {
+    assert(qemu_in_main_thread());
     if (bs->drv && bs->drv->bdrv_join_options) {
         bs->drv->bdrv_join_options(options, old_options);
     } else {
@@ -1566,6 +1567,7 @@ static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv,
 {
     Error *local_err = NULL;
     int i, ret;
+    assert(qemu_in_main_thread());
 
     bdrv_assign_node_name(bs, node_name, &local_err);
     if (local_err) {
@@ -1955,6 +1957,8 @@ static int bdrv_fill_options(QDict **options, const char *filename,
     BlockDriver *drv = NULL;
     Error *local_err = NULL;
 
+    assert(qemu_in_main_thread());
+
     /*
      * Caution: while qdict_get_try_str() is fine, getting non-string
      * types would require more care.  When @options come from
@@ -2148,6 +2152,7 @@ static void bdrv_child_perm(BlockDriverState *bs, BlockDriverState *child_bs,
                             uint64_t *nperm, uint64_t *nshared)
 {
     assert(bs->drv && bs->drv->bdrv_child_perm);
+    assert(qemu_in_main_thread());
     bs->drv->bdrv_child_perm(bs, c, role, reopen_queue,
                              parent_perm, parent_shared,
                              nperm, nshared);
@@ -2231,6 +2236,7 @@ static void bdrv_drv_set_perm_commit(void *opaque)
 {
     BlockDriverState *bs = opaque;
     uint64_t cumulative_perms, cumulative_shared_perms;
+    assert(qemu_in_main_thread());
 
     if (bs->drv->bdrv_set_perm) {
         bdrv_get_cumulative_perm(bs, &cumulative_perms,
@@ -2242,6 +2248,7 @@ static void bdrv_drv_set_perm_commit(void *opaque)
 static void bdrv_drv_set_perm_abort(void *opaque)
 {
     BlockDriverState *bs = opaque;
+    assert(qemu_in_main_thread());
 
     if (bs->drv->bdrv_abort_perm_update) {
         bs->drv->bdrv_abort_perm_update(bs);
@@ -2257,6 +2264,7 @@ static int bdrv_drv_set_perm(BlockDriverState *bs, uint64_t perm,
                              uint64_t shared_perm, Transaction *tran,
                              Error **errp)
 {
+    assert(qemu_in_main_thread());
     if (!bs->drv) {
         return 0;
     }
@@ -4221,6 +4229,7 @@ int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp)
 
     assert(qemu_get_current_aio_context() == qemu_get_aio_context());
     assert(bs_queue != NULL);
+    assert(qemu_in_main_thread());
 
     QTAILQ_FOREACH(bs_entry, bs_queue, entry) {
         ctx = bdrv_get_aio_context(bs_entry->state.bs);
@@ -4484,6 +4493,7 @@ static int bdrv_reopen_prepare(BDRVReopenState *reopen_state,
 
     assert(reopen_state != NULL);
     assert(reopen_state->bs->drv != NULL);
+    assert(qemu_in_main_thread());
     drv = reopen_state->bs->drv;
 
     /* This function and each driver's bdrv_reopen_prepare() remove
@@ -4694,6 +4704,7 @@ static void bdrv_reopen_commit(BDRVReopenState *reopen_state)
     bs = reopen_state->bs;
     drv = bs->drv;
     assert(drv != NULL);
+    assert(qemu_in_main_thread());
 
     /* If there are any driver level actions to take */
     if (drv->bdrv_reopen_commit) {
@@ -4735,6 +4746,7 @@ static void bdrv_reopen_abort(BDRVReopenState *reopen_state)
     assert(reopen_state != NULL);
     drv = reopen_state->bs->drv;
     assert(drv != NULL);
+    assert(qemu_in_main_thread());
 
     if (drv->bdrv_reopen_abort) {
         drv->bdrv_reopen_abort(reopen_state);
@@ -4748,6 +4760,7 @@ static void bdrv_close(BlockDriverState *bs)
     BdrvChild *child, *next;
 
     assert(!bs->refcnt);
+    assert(qemu_in_main_thread());
 
     bdrv_drained_begin(bs); /* complete I/O */
     bdrv_flush(bs);
@@ -6499,6 +6512,8 @@ static int bdrv_inactivate_recurse(BlockDriverState *bs)
     int ret;
     uint64_t cumulative_perms, cumulative_shared_perms;
 
+    assert(qemu_in_main_thread());
+
     if (!bs->drv) {
         return -ENOMEDIUM;
     }
@@ -7007,6 +7022,7 @@ static void bdrv_detach_aio_context(BlockDriverState *bs)
     BdrvAioNotifier *baf, *baf_tmp;
 
     assert(!bs->walking_aio_notifiers);
+    assert(qemu_in_main_thread());
     bs->walking_aio_notifiers = true;
     QLIST_FOREACH_SAFE(baf, &bs->aio_notifiers, list, baf_tmp) {
         if (baf->deleted) {
@@ -7034,6 +7050,7 @@ static void bdrv_attach_aio_context(BlockDriverState *bs,
                                     AioContext *new_context)
 {
     BdrvAioNotifier *ban, *ban_tmp;
+    assert(qemu_in_main_thread());
 
     if (bs->quiesce_counter) {
         aio_disable_external(new_context);
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 21/25] block_int-common.h: split function pointers in BdrvChildClass
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (19 preceding siblings ...)
  2021-10-12  8:49 ` [PATCH v3 20/25] block_int-common.h: assertion in the callers of BlockDriver function pointers Emanuele Giuseppe Esposito
@ 2021-10-12  8:49 ` Emanuele Giuseppe Esposito
  2021-10-12  8:49 ` [PATCH v3 22/25] block_int-common.h: assertions in the callers of BdrvChildClass function pointers Emanuele Giuseppe Esposito
                   ` (3 subsequent siblings)
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:49 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/block/block_int-common.h | 51 ++++++++++++++++++++------------
 1 file changed, 32 insertions(+), 19 deletions(-)

diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 9857e775fe..ea16099c53 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -805,12 +805,16 @@ struct BdrvChildClass {
      */
     bool parent_is_bds;
 
+    /*
+     * Global state (GS) API. These functions run under the BQL lock.
+     *
+     * See include/block/block-global-state.h for more information about
+     * the GS API.
+     */
     void (*inherit_options)(BdrvChildRole role, bool parent_is_format,
                             int *child_flags, QDict *child_options,
                             int parent_flags, QDict *parent_options);
-
     void (*change_media)(BdrvChild *child, bool load);
-    void (*resize)(BdrvChild *child);
 
     /*
      * Returns a name that is supposedly more useful for human users than the
@@ -827,6 +831,32 @@ struct BdrvChildClass {
      */
     char *(*get_parent_desc)(BdrvChild *child);
 
+    void (*attach)(BdrvChild *child);
+    void (*detach)(BdrvChild *child);
+
+    /*
+     * Notifies the parent that the filename of its child has changed (e.g.
+     * because the direct child was removed from the backing chain), so that it
+     * can update its reference.
+     */
+    int (*update_filename)(BdrvChild *child, BlockDriverState *new_base,
+                           const char *filename, Error **errp);
+
+    bool (*can_set_aio_ctx)(BdrvChild *child, AioContext *ctx,
+                        GSList **ignore, Error **errp);
+    void (*set_aio_ctx)(BdrvChild *child, AioContext *ctx, GSList **ignore);
+
+    AioContext *(*get_parent_aio_context)(BdrvChild *child);
+
+    /*
+     * I/O API functions. These functions are thread-safe.
+     *
+     * See include/block/block-io.h for more information about
+     * the I/O API.
+     */
+
+    void (*resize)(BdrvChild *child);
+
     /*
      * If this pair of functions is implemented, the parent doesn't issue new
      * requests after returning from .drained_begin() until .drained_end() is
@@ -859,23 +889,6 @@ struct BdrvChildClass {
      */
     void (*activate)(BdrvChild *child, Error **errp);
     int (*inactivate)(BdrvChild *child);
-
-    void (*attach)(BdrvChild *child);
-    void (*detach)(BdrvChild *child);
-
-    /*
-     * Notifies the parent that the filename of its child has changed (e.g.
-     * because the direct child was removed from the backing chain), so that it
-     * can update its reference.
-     */
-    int (*update_filename)(BdrvChild *child, BlockDriverState *new_base,
-                           const char *filename, Error **errp);
-
-    bool (*can_set_aio_ctx)(BdrvChild *child, AioContext *ctx,
-                            GSList **ignore, Error **errp);
-    void (*set_aio_ctx)(BdrvChild *child, AioContext *ctx, GSList **ignore);
-
-    AioContext *(*get_parent_aio_context)(BdrvChild *child);
 };
 
 extern const BdrvChildClass child_of_bds;
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 22/25] block_int-common.h: assertions in the callers of BdrvChildClass function pointers
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (20 preceding siblings ...)
  2021-10-12  8:49 ` [PATCH v3 21/25] block_int-common.h: split function pointers in BdrvChildClass Emanuele Giuseppe Esposito
@ 2021-10-12  8:49 ` Emanuele Giuseppe Esposito
  2021-10-12  8:49 ` [PATCH v3 23/25] block-backend-common.h: split function pointers in BlockDevOps Emanuele Giuseppe Esposito
                   ` (2 subsequent siblings)
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:49 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/block.c b/block.c
index 40c4729b8d..da80e89ad4 100644
--- a/block.c
+++ b/block.c
@@ -1462,6 +1462,7 @@ const BdrvChildClass child_of_bds = {
 
 AioContext *bdrv_child_get_parent_aio_context(BdrvChild *c)
 {
+    assert(qemu_in_main_thread());
     return c->klass->get_parent_aio_context(c);
 }
 
@@ -2085,6 +2086,7 @@ bool bdrv_is_writable(BlockDriverState *bs)
 
 static char *bdrv_child_user_desc(BdrvChild *c)
 {
+    assert(qemu_in_main_thread());
     return c->klass->get_parent_desc(c);
 }
 
@@ -2718,6 +2720,7 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
     int drain_saldo;
 
     assert(!child->frozen);
+    assert(qemu_in_main_thread());
 
     if (old_bs && new_bs) {
         assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs));
@@ -2806,6 +2809,8 @@ static void bdrv_attach_child_common_abort(void *opaque)
     BdrvChild *child = *s->child;
     BlockDriverState *bs = child->bs;
 
+    assert(qemu_in_main_thread());
+
     bdrv_replace_child_noperm(child, NULL);
 
     if (bdrv_get_aio_context(bs) != s->old_child_ctx) {
@@ -3164,6 +3169,7 @@ void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child)
 static void bdrv_parent_cb_change_media(BlockDriverState *bs, bool load)
 {
     BdrvChild *c;
+    assert(qemu_in_main_thread());
     QLIST_FOREACH(c, &bs->parents, next_parent) {
         if (c->klass->change_media) {
             c->klass->change_media(c, load);
@@ -3655,6 +3661,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
 
     assert(!child_class || !flags);
     assert(!child_class == !parent);
+    assert(qemu_in_main_thread());
 
     if (reference) {
         bool options_non_empty = options ? qdict_size(options) : false;
@@ -4041,6 +4048,7 @@ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue,
      * important to avoid graph changes between the recursive queuing here and
      * bdrv_reopen_multiple(). */
     assert(bs->quiesce_counter > 0);
+    assert(qemu_in_main_thread());
 
     if (bs_queue == NULL) {
         bs_queue = g_new0(BlockReopenQueue, 1);
@@ -7097,6 +7105,7 @@ void bdrv_set_aio_context_ignore(BlockDriverState *bs,
     BdrvChild *child, *parent;
 
     g_assert(qemu_get_current_aio_context() == qemu_get_aio_context());
+    assert(qemu_in_main_thread());
 
     if (old_context == new_context) {
         return;
@@ -7173,6 +7182,7 @@ static bool bdrv_parent_can_set_aio_context(BdrvChild *c, AioContext *ctx,
         return true;
     }
     *ignore = g_slist_prepend(*ignore, c);
+    assert(qemu_in_main_thread());
 
     /*
      * A BdrvChildClass that doesn't handle AioContext changes cannot
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 23/25] block-backend-common.h: split function pointers in BlockDevOps
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (21 preceding siblings ...)
  2021-10-12  8:49 ` [PATCH v3 22/25] block_int-common.h: assertions in the callers of BdrvChildClass function pointers Emanuele Giuseppe Esposito
@ 2021-10-12  8:49 ` Emanuele Giuseppe Esposito
  2021-10-12  8:49 ` [PATCH v3 24/25] job.h: split function pointers in JobDriver Emanuele Giuseppe Esposito
  2021-10-12  8:49 ` [PATCH v3 25/25] job.h: assertions in the callers of JobDriver funcion pointers Emanuele Giuseppe Esposito
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:49 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

Assertions in the callers of the funciton pointrs are already
added by previous patches.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/sysemu/block-backend-common.h | 28 ++++++++++++++++++++++-----
 1 file changed, 23 insertions(+), 5 deletions(-)

diff --git a/include/sysemu/block-backend-common.h b/include/sysemu/block-backend-common.h
index 52ff6a4d26..9ffd098458 100644
--- a/include/sysemu/block-backend-common.h
+++ b/include/sysemu/block-backend-common.h
@@ -17,6 +17,14 @@
 
 /* Callbacks for block device models */
 typedef struct BlockDevOps {
+
+    /*
+     * Global state (GS) API. These functions run under the BQL lock.
+     *
+     * See include/block/block-global-state.h for more information about
+     * the GS API.
+     */
+
     /*
      * Runs when virtual media changed (monitor commands eject, change)
      * Argument load is true on load and false on eject.
@@ -34,16 +42,26 @@ typedef struct BlockDevOps {
      * true, even if they do not support eject requests.
      */
     void (*eject_request_cb)(void *opaque, bool force);
-    /*
-     * Is the virtual tray open?
-     * Device models implement this only when the device has a tray.
-     */
-    bool (*is_tray_open)(void *opaque);
+
     /*
      * Is the virtual medium locked into the device?
      * Device models implement this only when device has such a lock.
      */
     bool (*is_medium_locked)(void *opaque);
+
+    /*
+     * I/O API functions. These functions are thread-safe.
+     *
+     * See include/block/block-io.h for more information about
+     * the I/O API.
+     */
+
+    /*
+     * Is the virtual tray open?
+     * Device models implement this only when the device has a tray.
+     */
+    bool (*is_tray_open)(void *opaque);
+
     /*
      * Runs when the size changed (e.g. monitor command block_resize)
      */
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 24/25] job.h: split function pointers in JobDriver
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (22 preceding siblings ...)
  2021-10-12  8:49 ` [PATCH v3 23/25] block-backend-common.h: split function pointers in BlockDevOps Emanuele Giuseppe Esposito
@ 2021-10-12  8:49 ` Emanuele Giuseppe Esposito
  2021-10-21 15:11   ` Stefan Hajnoczi
  2021-10-12  8:49 ` [PATCH v3 25/25] job.h: assertions in the callers of JobDriver funcion pointers Emanuele Giuseppe Esposito
  24 siblings, 1 reply; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:49 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

The job API will be handled separately in another serie.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 include/qemu/job.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/include/qemu/job.h b/include/qemu/job.h
index 6e67b6977f..7e9e59f4b8 100644
--- a/include/qemu/job.h
+++ b/include/qemu/job.h
@@ -169,12 +169,21 @@ typedef struct Job {
  * Callbacks and other information about a Job driver.
  */
 struct JobDriver {
+
+    /* Fields initialized in struct definition and never changed. */
+
     /** Derived Job struct size */
     size_t instance_size;
 
     /** Enum describing the operation */
     JobType job_type;
 
+    /*
+     * Functions run without regard to the BQL and may run in any
+     * arbitrary thread. These functions do not need to be thread-safe
+     * because the caller ensures that are invoked from one thread at time.
+     */
+
     /**
      * Mandatory: Entrypoint for the Coroutine.
      *
@@ -201,6 +210,13 @@ struct JobDriver {
      */
     void coroutine_fn (*resume)(Job *job);
 
+    /*
+     * Global state (GS) API. These functions run under the BQL lock.
+     *
+     * See include/block/block-global-state.h for more information about
+     * the GS API.
+     */
+
     /**
      * Called when the job is resumed by the user (i.e. user_paused becomes
      * false). .user_resume is called before .resume.
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* [PATCH v3 25/25] job.h: assertions in the callers of JobDriver funcion pointers
  2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
                   ` (23 preceding siblings ...)
  2021-10-12  8:49 ` [PATCH v3 24/25] job.h: split function pointers in JobDriver Emanuele Giuseppe Esposito
@ 2021-10-12  8:49 ` Emanuele Giuseppe Esposito
  24 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-12  8:49 UTC (permalink / raw)
  To: qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Emanuele Giuseppe Esposito, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Stefan Hajnoczi,
	Paolo Bonzini, Eric Blake

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 job.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/job.c b/job.c
index dbfa67bb0a..94b142684f 100644
--- a/job.c
+++ b/job.c
@@ -380,6 +380,8 @@ void job_ref(Job *job)
 
 void job_unref(Job *job)
 {
+    assert(qemu_in_main_thread());
+
     if (--job->refcnt == 0) {
         assert(job->status == JOB_STATUS_NULL);
         assert(!timer_pending(&job->sleep_timer));
@@ -601,6 +603,7 @@ bool job_user_paused(Job *job)
 void job_user_resume(Job *job, Error **errp)
 {
     assert(job);
+    assert(qemu_in_main_thread());
     if (!job->user_paused || job->pause_count <= 0) {
         error_setg(errp, "Can't resume a job that was not paused");
         return;
@@ -671,6 +674,7 @@ static void job_update_rc(Job *job)
 static void job_commit(Job *job)
 {
     assert(!job->ret);
+    assert(qemu_in_main_thread());
     if (job->driver->commit) {
         job->driver->commit(job);
     }
@@ -679,6 +683,7 @@ static void job_commit(Job *job)
 static void job_abort(Job *job)
 {
     assert(job->ret);
+    assert(qemu_in_main_thread());
     if (job->driver->abort) {
         job->driver->abort(job);
     }
@@ -686,6 +691,7 @@ static void job_abort(Job *job)
 
 static void job_clean(Job *job)
 {
+    assert(qemu_in_main_thread());
     if (job->driver->clean) {
         job->driver->clean(job);
     }
@@ -725,6 +731,7 @@ static int job_finalize_single(Job *job)
 
 static void job_cancel_async(Job *job, bool force)
 {
+    assert(qemu_in_main_thread());
     if (job->driver->cancel) {
         force = job->driver->cancel(job, force);
     } else {
@@ -824,6 +831,7 @@ static void job_completed_txn_abort(Job *job)
 
 static int job_prepare(Job *job)
 {
+    assert(qemu_in_main_thread());
     if (job->ret == 0 && job->driver->prepare) {
         job->ret = job->driver->prepare(job);
         job_update_rc(job);
@@ -1053,6 +1061,7 @@ void job_complete(Job *job, Error **errp)
 {
     /* Should not be reachable via external interface for internal jobs */
     assert(job->id);
+    assert(qemu_in_main_thread());
     if (job_apply_verb(job, JOB_VERB_COMPLETE, errp)) {
         return;
     }
-- 
2.27.0



^ permalink raw reply related	[flat|nested] 39+ messages in thread

* Re: [PATCH v3 13/25] include/sysemu/blockdev.h: move drive_add and inline drive_def
  2021-10-12  8:48 ` [PATCH v3 13/25] include/sysemu/blockdev.h: move drive_add and inline drive_def Emanuele Giuseppe Esposito
@ 2021-10-12 11:06   ` Paolo Bonzini
  2021-10-21 15:08   ` Stefan Hajnoczi
  1 sibling, 0 replies; 39+ messages in thread
From: Paolo Bonzini @ 2021-10-12 11:06 UTC (permalink / raw)
  To: Emanuele Giuseppe Esposito, qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Richard Henderson, Markus Armbruster, Dr. David Alan Gilbert,
	Hanna Reitz, Stefan Hajnoczi, Eric Blake

On 12/10/21 10:48, Emanuele Giuseppe Esposito wrote:
> +    if (type != IF_DEFAULT) {
> +        qemu_opt_set(opts, "if", if_name[type], &error_abort);
> +    }

To avoid exporting if_name, this can be replaced by a string argument 
directly.  But in any case this is okay for this series:

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>

Paolo



^ permalink raw reply	[flat|nested] 39+ messages in thread

* Re: [PATCH v3 14/25] include/systemu/blockdev.h: global state API
  2021-10-12  8:48 ` [PATCH v3 14/25] include/systemu/blockdev.h: global state API Emanuele Giuseppe Esposito
@ 2021-10-12 11:07   ` Paolo Bonzini
  0 siblings, 0 replies; 39+ messages in thread
From: Paolo Bonzini @ 2021-10-12 11:07 UTC (permalink / raw)
  To: Emanuele Giuseppe Esposito, qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Richard Henderson, Markus Armbruster, Dr. David Alan Gilbert,
	Hanna Reitz, Stefan Hajnoczi, Eric Blake

On 12/10/21 10:48, Emanuele Giuseppe Esposito wrote:
> +/* Common functions that are neither I/O nor Global State */
> +
> +DriveInfo *blk_legacy_dinfo(BlockBackend *blk);
> +int drive_get_max_devs(BlockInterfaceType type);
> +

blk_legacy_dinfo should count as global state (blk->legacy_dinfo is 
protected by BQL).

Paolo



^ permalink raw reply	[flat|nested] 39+ messages in thread

* Re: [PATCH v3 08/25] block: introduce assert_bdrv_graph_writable
  2021-10-12  8:48 ` [PATCH v3 08/25] block: introduce assert_bdrv_graph_writable Emanuele Giuseppe Esposito
@ 2021-10-12 11:07   ` Paolo Bonzini
  2021-10-21 15:09   ` Stefan Hajnoczi
  1 sibling, 0 replies; 39+ messages in thread
From: Paolo Bonzini @ 2021-10-12 11:07 UTC (permalink / raw)
  To: Emanuele Giuseppe Esposito, qemu-block
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, Juan Quintela, qemu-devel, John Snow,
	Richard Henderson, Markus Armbruster, Dr. David Alan Gilbert,
	Hanna Reitz, Stefan Hajnoczi, Eric Blake

On 12/10/21 10:48, Emanuele Giuseppe Esposito wrote:
> We want to be sure that the functions that write the child and
> parent list of a bs are under BQL and drain.
> 
> BQL prevents from concurrent writings from the GS API, while
> drains protect from I/O.
> 
> TODO: drains are missing in some functions using this assert.
> Therefore a proper assertion will fail. Because adding drains
> requires additional discussions, they will be added in future
> series.
> 
> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
> ---
>   block.c                                |  5 +++++
>   block/io.c                             | 11 +++++++++++
>   include/block/block_int-global-state.h | 10 +++++++++-
>   3 files changed, 25 insertions(+), 1 deletion(-)
> 
> diff --git a/block.c b/block.c
> index 41c5883c5c..94bff5c757 100644
> --- a/block.c
> +++ b/block.c
> @@ -2734,12 +2734,14 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
>           if (child->klass->detach) {
>               child->klass->detach(child);
>           }
> +        assert_bdrv_graph_writable(old_bs);
>           QLIST_REMOVE(child, next_parent);
>       }
>   
>       child->bs = new_bs;
>   
>       if (new_bs) {
> +        assert_bdrv_graph_writable(new_bs);
>           QLIST_INSERT_HEAD(&new_bs->parents, child, next_parent);
>   
>           /*
> @@ -2940,6 +2942,7 @@ static int bdrv_attach_child_noperm(BlockDriverState *parent_bs,
>           return ret;
>       }
>   
> +    assert_bdrv_graph_writable(parent_bs);
>       QLIST_INSERT_HEAD(&parent_bs->children, *child, next);
>       /*
>        * child is removed in bdrv_attach_child_common_abort(), so don't care to
> @@ -3140,6 +3143,7 @@ static void bdrv_unset_inherits_from(BlockDriverState *root, BdrvChild *child,
>   void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child)
>   {
>       assert(qemu_in_main_thread());
> +    assert_bdrv_graph_writable(parent);
>       if (child == NULL) {
>           return;
>       }
> @@ -4903,6 +4907,7 @@ static void bdrv_remove_filter_or_cow_child_abort(void *opaque)
>       BdrvRemoveFilterOrCowChild *s = opaque;
>       BlockDriverState *parent_bs = s->child->opaque;
>   
> +    assert_bdrv_graph_writable(parent_bs);
>       QLIST_INSERT_HEAD(&parent_bs->children, s->child, next);
>       if (s->is_backing) {
>           parent_bs->backing = s->child;
> diff --git a/block/io.c b/block/io.c
> index f271ab3684..1c71e354d6 100644
> --- a/block/io.c
> +++ b/block/io.c
> @@ -740,6 +740,17 @@ void bdrv_drain_all(void)
>       bdrv_drain_all_end();
>   }
>   
> +void assert_bdrv_graph_writable(BlockDriverState *bs)
> +{
> +    /*
> +     * TODO: this function is incomplete. Because the users of this
> +     * assert lack the necessary drains, check only for BQL.
> +     * Once the necessary drains are added,
> +     * assert also for qatomic_read(&bs->quiesce_counter) > 0
> +     */
> +    assert(qemu_in_main_thread());
> +}
> +
>   /**
>    * Remove an active request from the tracked requests list
>    *
> diff --git a/include/block/block_int-global-state.h b/include/block/block_int-global-state.h
> index d08e80222c..6bd7746409 100644
> --- a/include/block/block_int-global-state.h
> +++ b/include/block/block_int-global-state.h
> @@ -316,4 +316,12 @@ void bdrv_remove_aio_context_notifier(BlockDriverState *bs,
>    */
>   void bdrv_drain_all_end_quiesce(BlockDriverState *bs);
>   
> -#endif /* BLOCK_INT_GLOBAL_STATE*/
> +/**
> + * Make sure that the function is either running under
> + * drain and BQL. The latter protects from concurrent writings
> + * from the GS API, while the former prevents concurrent reads
> + * from I/O.
> + */
> +void assert_bdrv_graph_writable(BlockDriverState *bs);
> +
> +#endif /* BLOCK_INT_GLOBAL_STATE */
> 

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>



^ permalink raw reply	[flat|nested] 39+ messages in thread

* Re: [PATCH v3 02/25] include/block/block: split header into I/O and global state API
  2021-10-12  8:48 ` [PATCH v3 02/25] include/block/block: split header into I/O and global state API Emanuele Giuseppe Esposito
@ 2021-10-14 20:31   ` Eric Blake
  2021-10-15 10:05     ` Emanuele Giuseppe Esposito
  2021-10-21 14:11   ` Stefan Hajnoczi
  1 sibling, 1 reply; 39+ messages in thread
From: Eric Blake @ 2021-10-14 20:31 UTC (permalink / raw)
  To: Emanuele Giuseppe Esposito
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, qemu-block, Juan Quintela, qemu-devel,
	Richard Henderson, Markus Armbruster, Dr. David Alan Gilbert,
	Hanna Reitz, Stefan Hajnoczi, Paolo Bonzini, John Snow

On Tue, Oct 12, 2021 at 04:48:43AM -0400, Emanuele Giuseppe Esposito wrote:
> block.h currently contains a mix of functions:
> some of them run under the BQL and modify the block layer graph,
> others are instead thread-safe and perform I/O in iothreads.
> It is not easy to understand which function is part of which
> group (I/O vs GS), and this patch aims to clarify it.
> 
> The "GS" functions need the BQL, and often use
> aio_context_acquire/release and/or drain to be sure they
> can modify the graph safely.
> The I/O function are instead thread safe, and can run in
> any AioContext.
> 
> By splitting the header in two files, block-io.h
> and block-global-state.h we have a clearer view on what
> needs what kind of protection. block-common.h
> instead contains common structures shared by both headers.

s/instead //

> 
> block.h is left there for legacy and to avoid changing
> all includes in all c files that use the block APIs.
> 
> Assertions are added in the next patch.
> 
> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
> ---

> diff --git a/include/block/block-common.h b/include/block/block-common.h
> new file mode 100644
> index 0000000000..4f1fd8de21
> --- /dev/null
> +++ b/include/block/block-common.h
> @@ -0,0 +1,389 @@
> +#ifndef BLOCK_COMMON_H
> +#define BLOCK_COMMON_H

As a new file, it probably deserves a copyright/license blurb copied
from the file it is split out of.

> diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h
> new file mode 100644
> index 0000000000..b57e275da9
> --- /dev/null
> +++ b/include/block/block-global-state.h
> @@ -0,0 +1,263 @@
> +#ifndef BLOCK_GLOBAL_STATE_H
> +#define BLOCK_GLOBAL_STATE_H

Likewise, here and in all other newly-split files in your series.

> +++ b/include/block/block.h
> @@ -1,864 +1,9 @@
>  #ifndef BLOCK_H
>  #define BLOCK_H

Oh. There wasn't one to copy from :( Well, now's as good a time to fix
that as any.

-- 
Eric Blake, Principal Software Engineer
Red Hat, Inc.           +1-919-301-3266
Virtualization:  qemu.org | libvirt.org



^ permalink raw reply	[flat|nested] 39+ messages in thread

* Re: [PATCH v3 02/25] include/block/block: split header into I/O and global state API
  2021-10-14 20:31   ` Eric Blake
@ 2021-10-15 10:05     ` Emanuele Giuseppe Esposito
  0 siblings, 0 replies; 39+ messages in thread
From: Emanuele Giuseppe Esposito @ 2021-10-15 10:05 UTC (permalink / raw)
  To: Eric Blake
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, qemu-block, Juan Quintela, qemu-devel,
	Richard Henderson, Markus Armbruster, Dr. David Alan Gilbert,
	Hanna Reitz, Stefan Hajnoczi, Paolo Bonzini, John Snow

>> diff --git a/include/block/block-common.h b/include/block/block-common.h
>> new file mode 100644
>> index 0000000000..4f1fd8de21
>> --- /dev/null
>> +++ b/include/block/block-common.h
>> @@ -0,0 +1,389 @@
>> +#ifndef BLOCK_COMMON_H
>> +#define BLOCK_COMMON_H
> 
> As a new file, it probably deserves a copyright/license blurb copied
> from the file it is split out of.
> 
>> diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h
>> new file mode 100644
>> index 0000000000..b57e275da9
>> --- /dev/null
>> +++ b/include/block/block-global-state.h
>> @@ -0,0 +1,263 @@
>> +#ifndef BLOCK_GLOBAL_STATE_H
>> +#define BLOCK_GLOBAL_STATE_H
> 
> Likewise, here and in all other newly-split files in your series.

In general, as you might have seen, I kept the same copyright/license 
from the original file I split. But block.h seems to be the only header 
with no license.
> 
>> +++ b/include/block/block.h
>> @@ -1,864 +1,9 @@
>>   #ifndef BLOCK_H
>>   #define BLOCK_H
> 
> Oh. There wasn't one to copy from :( Well, now's as good a time to fix
> that as any.
> 
So now the question is which one to use, because I see 2 different types 
of copyrights templates:

- long version copyright, used in block_int.h, blockjob_int.h and many 
others

/*
  * QEMU System Emulator block driver
  *
  * Copyright (c) 2003 Fabrice Bellard
  *
  * Permission is hereby granted, free of charge, to any person 
obtaining a copy
[...]
  *
  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, 
EXPRESS OR
[...]
  */

- short version, used in block-backend.h and many others

/*
  * QEMU Block backends
  *
  * Copyright (C) 2014-2016 Red Hat, Inc.
  *
  * Authors:
  *  ....
  *
  * This work is licensed under the terms of the GNU LGPL, version 2.1
  * or later.  See the COPYING.LIB file in the top-level directory.
  */

Maybe since we are talking about block.h we should stick to the same 
format as block_int.h? I am not sure though.

Thank you,
Emanuele



^ permalink raw reply	[flat|nested] 39+ messages in thread

* Re: [PATCH v3 02/25] include/block/block: split header into I/O and global state API
  2021-10-12  8:48 ` [PATCH v3 02/25] include/block/block: split header into I/O and global state API Emanuele Giuseppe Esposito
  2021-10-14 20:31   ` Eric Blake
@ 2021-10-21 14:11   ` Stefan Hajnoczi
  1 sibling, 0 replies; 39+ messages in thread
From: Stefan Hajnoczi @ 2021-10-21 14:11 UTC (permalink / raw)
  To: Emanuele Giuseppe Esposito
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, qemu-block, Juan Quintela, qemu-devel,
	John Snow, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Paolo Bonzini, Eric Blake

[-- Attachment #1: Type: text/plain, Size: 1710 bytes --]

On Tue, Oct 12, 2021 at 04:48:43AM -0400, Emanuele Giuseppe Esposito wrote:
> block.h currently contains a mix of functions:
> some of them run under the BQL and modify the block layer graph,
> others are instead thread-safe and perform I/O in iothreads.
> It is not easy to understand which function is part of which
> group (I/O vs GS), and this patch aims to clarify it.
> 
> The "GS" functions need the BQL, and often use
> aio_context_acquire/release and/or drain to be sure they
> can modify the graph safely.
> The I/O function are instead thread safe, and can run in
> any AioContext.
> 
> By splitting the header in two files, block-io.h
> and block-global-state.h we have a clearer view on what
> needs what kind of protection. block-common.h
> instead contains common structures shared by both headers.
> 
> block.h is left there for legacy and to avoid changing
> all includes in all c files that use the block APIs.
> 
> Assertions are added in the next patch.
> 
> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
> ---
>  block.c                            |   3 +
>  block/meson.build                  |   7 +-
>  include/block/block-common.h       | 389 +++++++++++++
>  include/block/block-global-state.h | 263 +++++++++
>  include/block/block-io.h           | 283 ++++++++++
>  include/block/block.h              | 863 +----------------------------
>  6 files changed, 947 insertions(+), 861 deletions(-)
>  create mode 100644 include/block/block-common.h
>  create mode 100644 include/block/block-global-state.h
>  create mode 100644 include/block/block-io.h

Modulo Eric's comments:

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

^ permalink raw reply	[flat|nested] 39+ messages in thread

* Re: [PATCH v3 04/25] include/sysemu/block-backend: split header into I/O and global state (GS) API
  2021-10-12  8:48 ` [PATCH v3 04/25] include/sysemu/block-backend: split header into I/O and global state (GS) API Emanuele Giuseppe Esposito
@ 2021-10-21 14:28   ` Stefan Hajnoczi
  0 siblings, 0 replies; 39+ messages in thread
From: Stefan Hajnoczi @ 2021-10-21 14:28 UTC (permalink / raw)
  To: Emanuele Giuseppe Esposito
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, qemu-block, Juan Quintela, qemu-devel,
	John Snow, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Paolo Bonzini, Eric Blake

[-- Attachment #1: Type: text/plain, Size: 1220 bytes --]

On Tue, Oct 12, 2021 at 04:48:45AM -0400, Emanuele Giuseppe Esposito wrote:
> Similarly to the previous patches, split block-backend.h
> in block-backend-io.h and block-backend-global-state.h
> 
> In addition, remove "block/block.h" include as it seems
> it is not necessary anymore, together with "qemu/iov.h"
> 
> block-backend-common.h contains the structures shared between
> the two headers, and the functions that can't be categorized as
> I/O or global state.
> 
> Assertions are added in the next patch.
> 
> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
> ---
>  block/block-backend.c                       |   9 +-
>  include/sysemu/block-backend-common.h       |  74 ++++++
>  include/sysemu/block-backend-global-state.h | 122 +++++++++
>  include/sysemu/block-backend-io.h           | 134 ++++++++++
>  include/sysemu/block-backend.h              | 264 +-------------------
>  5 files changed, 339 insertions(+), 264 deletions(-)
>  create mode 100644 include/sysemu/block-backend-common.h
>  create mode 100644 include/sysemu/block-backend-global-state.h
>  create mode 100644 include/sysemu/block-backend-io.h

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

^ permalink raw reply	[flat|nested] 39+ messages in thread

* Re: [PATCH v3 06/25] include/block/block_int: split header into I/O and global state API
  2021-10-12  8:48 ` [PATCH v3 06/25] include/block/block_int: split header into I/O and global state API Emanuele Giuseppe Esposito
@ 2021-10-21 14:35   ` Stefan Hajnoczi
  0 siblings, 0 replies; 39+ messages in thread
From: Stefan Hajnoczi @ 2021-10-21 14:35 UTC (permalink / raw)
  To: Emanuele Giuseppe Esposito
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, qemu-block, Juan Quintela, qemu-devel,
	John Snow, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Paolo Bonzini, Eric Blake

[-- Attachment #1: Type: text/plain, Size: 1052 bytes --]

On Tue, Oct 12, 2021 at 04:48:47AM -0400, Emanuele Giuseppe Esposito wrote:
> Similarly to the previous patch, split block_int.h
> in block_int-io.h and block_int-global-state.h
> 
> block_int-common.h contains the structures shared between
> the two headers, and the functions that can't be categorized as
> I/O or global state.
> 
> Assertions are added in the next patch.
> 
> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
> ---
>  blockdev.c                             |    5 +
>  include/block/block_int-common.h       | 1164 +++++++++++++++++++
>  include/block/block_int-global-state.h |  319 +++++
>  include/block/block_int-io.h           |  163 +++
>  include/block/block_int.h              | 1478 +-----------------------
>  5 files changed, 1654 insertions(+), 1475 deletions(-)
>  create mode 100644 include/block/block_int-common.h
>  create mode 100644 include/block/block_int-global-state.h
>  create mode 100644 include/block/block_int-io.h

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

^ permalink raw reply	[flat|nested] 39+ messages in thread

* Re: [PATCH v3 11/25] include/block/blockjob.h: global state API
  2021-10-12  8:48 ` [PATCH v3 11/25] include/block/blockjob.h: global state API Emanuele Giuseppe Esposito
@ 2021-10-21 14:35   ` Stefan Hajnoczi
  0 siblings, 0 replies; 39+ messages in thread
From: Stefan Hajnoczi @ 2021-10-21 14:35 UTC (permalink / raw)
  To: Emanuele Giuseppe Esposito
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, qemu-block, Juan Quintela, qemu-devel,
	John Snow, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Paolo Bonzini, Eric Blake

[-- Attachment #1: Type: text/plain, Size: 341 bytes --]

On Tue, Oct 12, 2021 at 04:48:52AM -0400, Emanuele Giuseppe Esposito wrote:
> blockjob functions run always under the BQL lock.
> 
> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
> ---
>  include/block/blockjob.h | 9 +++++++++
>  1 file changed, 9 insertions(+)

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

^ permalink raw reply	[flat|nested] 39+ messages in thread

* Re: [PATCH v3 13/25] include/sysemu/blockdev.h: move drive_add and inline drive_def
  2021-10-12  8:48 ` [PATCH v3 13/25] include/sysemu/blockdev.h: move drive_add and inline drive_def Emanuele Giuseppe Esposito
  2021-10-12 11:06   ` Paolo Bonzini
@ 2021-10-21 15:08   ` Stefan Hajnoczi
  1 sibling, 0 replies; 39+ messages in thread
From: Stefan Hajnoczi @ 2021-10-21 15:08 UTC (permalink / raw)
  To: Emanuele Giuseppe Esposito
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, qemu-block, Juan Quintela, qemu-devel,
	John Snow, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Paolo Bonzini, Eric Blake

[-- Attachment #1: Type: text/plain, Size: 830 bytes --]

On Tue, Oct 12, 2021 at 04:48:54AM -0400, Emanuele Giuseppe Esposito wrote:
> drive_add is only used in softmmu/vl.c, so it can be a static
> function there, and drive_def is only a particular use case of
> qemu_opts_parse_noisily, so it can be inlined.
> 
> Also remove drive_mark_claimed_by_board, as it is only defined
> but not implemented (nor used) anywhere.
> 
> This also helps simplifying next patch.
> 
> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
> ---
>  block/monitor/block-hmp-cmds.c |  2 +-
>  blockdev.c                     | 27 +--------------------------
>  include/sysemu/blockdev.h      |  6 ++----
>  softmmu/vl.c                   | 25 ++++++++++++++++++++++++-
>  4 files changed, 28 insertions(+), 32 deletions(-)

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

^ permalink raw reply	[flat|nested] 39+ messages in thread

* Re: [PATCH v3 08/25] block: introduce assert_bdrv_graph_writable
  2021-10-12  8:48 ` [PATCH v3 08/25] block: introduce assert_bdrv_graph_writable Emanuele Giuseppe Esposito
  2021-10-12 11:07   ` Paolo Bonzini
@ 2021-10-21 15:09   ` Stefan Hajnoczi
  1 sibling, 0 replies; 39+ messages in thread
From: Stefan Hajnoczi @ 2021-10-21 15:09 UTC (permalink / raw)
  To: Emanuele Giuseppe Esposito
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, qemu-block, Juan Quintela, qemu-devel,
	John Snow, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Paolo Bonzini, Eric Blake

[-- Attachment #1: Type: text/plain, Size: 855 bytes --]

On Tue, Oct 12, 2021 at 04:48:49AM -0400, Emanuele Giuseppe Esposito wrote:
> We want to be sure that the functions that write the child and
> parent list of a bs are under BQL and drain.
> 
> BQL prevents from concurrent writings from the GS API, while
> drains protect from I/O.
> 
> TODO: drains are missing in some functions using this assert.
> Therefore a proper assertion will fail. Because adding drains
> requires additional discussions, they will be added in future
> series.
> 
> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
> ---
>  block.c                                |  5 +++++
>  block/io.c                             | 11 +++++++++++
>  include/block/block_int-global-state.h | 10 +++++++++-
>  3 files changed, 25 insertions(+), 1 deletion(-)

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

^ permalink raw reply	[flat|nested] 39+ messages in thread

* Re: [PATCH v3 17/25] block/copy-before-write.h: global state API + assertions
  2021-10-12  8:48 ` [PATCH v3 17/25] block/copy-before-write.h: " Emanuele Giuseppe Esposito
@ 2021-10-21 15:10   ` Stefan Hajnoczi
  0 siblings, 0 replies; 39+ messages in thread
From: Stefan Hajnoczi @ 2021-10-21 15:10 UTC (permalink / raw)
  To: Emanuele Giuseppe Esposito
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, qemu-block, Juan Quintela, qemu-devel,
	John Snow, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Paolo Bonzini, Eric Blake

[-- Attachment #1: Type: text/plain, Size: 435 bytes --]

On Tue, Oct 12, 2021 at 04:48:58AM -0400, Emanuele Giuseppe Esposito wrote:
> copy-before-write functions always run under BQL lock.
> 
> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
>  block/copy-before-write.c | 2 ++
>  block/copy-before-write.h | 7 +++++++
>  2 files changed, 9 insertions(+)

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

^ permalink raw reply	[flat|nested] 39+ messages in thread

* Re: [PATCH v3 24/25] job.h: split function pointers in JobDriver
  2021-10-12  8:49 ` [PATCH v3 24/25] job.h: split function pointers in JobDriver Emanuele Giuseppe Esposito
@ 2021-10-21 15:11   ` Stefan Hajnoczi
  0 siblings, 0 replies; 39+ messages in thread
From: Stefan Hajnoczi @ 2021-10-21 15:11 UTC (permalink / raw)
  To: Emanuele Giuseppe Esposito
  Cc: Kevin Wolf, Fam Zheng, Vladimir Sementsov-Ogievskiy,
	Daniel P. Berrangé,
	Eduardo Habkost, qemu-block, Juan Quintela, qemu-devel,
	John Snow, Richard Henderson, Markus Armbruster,
	Dr. David Alan Gilbert, Hanna Reitz, Paolo Bonzini, Eric Blake

[-- Attachment #1: Type: text/plain, Size: 351 bytes --]

On Tue, Oct 12, 2021 at 04:49:05AM -0400, Emanuele Giuseppe Esposito wrote:
> The job API will be handled separately in another serie.
> 
> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
> ---
>  include/qemu/job.h | 16 ++++++++++++++++
>  1 file changed, 16 insertions(+)

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

^ permalink raw reply	[flat|nested] 39+ messages in thread

end of thread, other threads:[~2021-10-21 15:14 UTC | newest]

Thread overview: 39+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-10-12  8:48 [PATCH v3 00/25] block layer: split block APIs in global state and I/O Emanuele Giuseppe Esposito
2021-10-12  8:48 ` [PATCH v3 01/25] main-loop.h: introduce qemu_in_main_thread() Emanuele Giuseppe Esposito
2021-10-12  8:48 ` [PATCH v3 02/25] include/block/block: split header into I/O and global state API Emanuele Giuseppe Esposito
2021-10-14 20:31   ` Eric Blake
2021-10-15 10:05     ` Emanuele Giuseppe Esposito
2021-10-21 14:11   ` Stefan Hajnoczi
2021-10-12  8:48 ` [PATCH v3 03/25] assertions for block " Emanuele Giuseppe Esposito
2021-10-12  8:48 ` [PATCH v3 04/25] include/sysemu/block-backend: split header into I/O and global state (GS) API Emanuele Giuseppe Esposito
2021-10-21 14:28   ` Stefan Hajnoczi
2021-10-12  8:48 ` [PATCH v3 05/25] block/block-backend.c: assertions for block-backend Emanuele Giuseppe Esposito
2021-10-12  8:48 ` [PATCH v3 06/25] include/block/block_int: split header into I/O and global state API Emanuele Giuseppe Esposito
2021-10-21 14:35   ` Stefan Hajnoczi
2021-10-12  8:48 ` [PATCH v3 07/25] assertions for block_int " Emanuele Giuseppe Esposito
2021-10-12  8:48 ` [PATCH v3 08/25] block: introduce assert_bdrv_graph_writable Emanuele Giuseppe Esposito
2021-10-12 11:07   ` Paolo Bonzini
2021-10-21 15:09   ` Stefan Hajnoczi
2021-10-12  8:48 ` [PATCH v3 09/25] include/block/blockjob_int.h: split header into I/O and GS API Emanuele Giuseppe Esposito
2021-10-12  8:48 ` [PATCH v3 10/25] assertions for blockjob_int.h Emanuele Giuseppe Esposito
2021-10-12  8:48 ` [PATCH v3 11/25] include/block/blockjob.h: global state API Emanuele Giuseppe Esposito
2021-10-21 14:35   ` Stefan Hajnoczi
2021-10-12  8:48 ` [PATCH v3 12/25] assertions for blockob.h " Emanuele Giuseppe Esposito
2021-10-12  8:48 ` [PATCH v3 13/25] include/sysemu/blockdev.h: move drive_add and inline drive_def Emanuele Giuseppe Esposito
2021-10-12 11:06   ` Paolo Bonzini
2021-10-21 15:08   ` Stefan Hajnoczi
2021-10-12  8:48 ` [PATCH v3 14/25] include/systemu/blockdev.h: global state API Emanuele Giuseppe Esposito
2021-10-12 11:07   ` Paolo Bonzini
2021-10-12  8:48 ` [PATCH v3 15/25] assertions for blockdev.h " Emanuele Giuseppe Esposito
2021-10-12  8:48 ` [PATCH v3 16/25] include/block/snapshot: global state API + assertions Emanuele Giuseppe Esposito
2021-10-12  8:48 ` [PATCH v3 17/25] block/copy-before-write.h: " Emanuele Giuseppe Esposito
2021-10-21 15:10   ` Stefan Hajnoczi
2021-10-12  8:48 ` [PATCH v3 18/25] block/coroutines: I/O API Emanuele Giuseppe Esposito
2021-10-12  8:49 ` [PATCH v3 19/25] block_int-common.h: split function pointers in BlockDriver Emanuele Giuseppe Esposito
2021-10-12  8:49 ` [PATCH v3 20/25] block_int-common.h: assertion in the callers of BlockDriver function pointers Emanuele Giuseppe Esposito
2021-10-12  8:49 ` [PATCH v3 21/25] block_int-common.h: split function pointers in BdrvChildClass Emanuele Giuseppe Esposito
2021-10-12  8:49 ` [PATCH v3 22/25] block_int-common.h: assertions in the callers of BdrvChildClass function pointers Emanuele Giuseppe Esposito
2021-10-12  8:49 ` [PATCH v3 23/25] block-backend-common.h: split function pointers in BlockDevOps Emanuele Giuseppe Esposito
2021-10-12  8:49 ` [PATCH v3 24/25] job.h: split function pointers in JobDriver Emanuele Giuseppe Esposito
2021-10-21 15:11   ` Stefan Hajnoczi
2021-10-12  8:49 ` [PATCH v3 25/25] job.h: assertions in the callers of JobDriver funcion pointers Emanuele Giuseppe Esposito

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.