Merge remote-tracking branch 'remotes/stefanha/tags/block-pull-request' into staging

Pull request

# gpg: Signature made Thu 30 Jan 2020 21:31:02 GMT
# gpg:                using RSA key 8695A8BFD3F97CDAAC35775A9CA4ABB381AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>" [full]
# gpg:                 aka "Stefan Hajnoczi <stefanha@gmail.com>" [full]
# Primary key fingerprint: 8695 A8BF D3F9 7CDA AC35  775A 9CA4 ABB3 81AB 73C8

* remotes/stefanha/tags/block-pull-request:
  tests/qemu-iotests: use AIOMODE with various tests
  tests/qemu-iotests: enable testing with aio options
  qemu-nbd: adds option for aio engines
  qemu-img: adds option to use aio engine for benchmarking
  qemu-io: adds option to use aio engine
  block/io_uring: adds userspace completion polling
  block: add trace events for io_uring
  block/file-posix.c: extend to use io_uring
  blockdev: adds bdrv_parse_aio to use io_uring
  util/async: add aio interfaces for io_uring
  stubs: add stubs for io_uring interface
  block/io_uring: implements interfaces for io_uring
  block/block: add BDRV flag for io_uring
  qapi/block-core: add option for io_uring
  configure: permit use of io_uring
  block/io: take bs->reqs_lock in bdrv_mark_request_serialising
  block/io: wait for serialising requests when a request becomes serialising
  block: eliminate BDRV_REQ_NO_SERIALISING

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 30 insertions, 15 deletions

diff --git a/include/block/aio.h b/include/block/aio.h
index 6b0d52f..7ba9bd7 100644
--- a/include/block/aio.h
+++ b/include/block/aio.h
@@ -49,6 +49,7 @@ typedef void IOHandler(void *opaque);
 struct Coroutine;
 struct ThreadPool;
 struct LinuxAioState;
+struct LuringState;
 
 struct AioContext {
     GSource source;
@@ -117,11 +118,19 @@ struct AioContext {
     struct ThreadPool *thread_pool;
 
 #ifdef CONFIG_LINUX_AIO
-    /* State for native Linux AIO.  Uses aio_context_acquire/release for
+    /*
+     * State for native Linux AIO.  Uses aio_context_acquire/release for
      * locking.
      */
     struct LinuxAioState *linux_aio;
 #endif
+#ifdef CONFIG_LINUX_IO_URING
+    /*
+     * State for Linux io_uring.  Uses aio_context_acquire/release for
+     * locking.
+     */
+    struct LuringState *linux_io_uring;
+#endif
 
     /* TimerLists for calling timers - one per clock type.  Has its own
      * locking.
@@ -386,6 +395,11 @@ struct LinuxAioState *aio_setup_linux_aio(AioContext *ctx, Error **errp);
 /* Return the LinuxAioState bound to this AioContext */
 struct LinuxAioState *aio_get_linux_aio(AioContext *ctx);
 
+/* Setup the LuringState bound to this AioContext */
+struct LuringState *aio_setup_linux_io_uring(AioContext *ctx, Error **errp);
+
+/* Return the LuringState bound to this AioContext */
+struct LuringState *aio_get_linux_io_uring(AioContext *ctx);
 /**
  * aio_timer_new_with_attrs:
  * @ctx: the aio context
diff --git a/include/block/block.h b/include/block/block.h
index e9dcfef..6cd5663 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -51,18 +51,6 @@ typedef enum {
      */
     BDRV_REQ_MAY_UNMAP          = 0x4,
 
-    /*
-     * The BDRV_REQ_NO_SERIALISING flag is only valid for reads and means that
-     * we don't want wait_serialising_requests() during the read operation.
-     *
-     * This flag is used for backup copy-on-write operations, when we need to
-     * read old data before write (write notifier triggered). It is okay since
-     * we already waited for other serializing requests in the initiating write
-     * (see bdrv_aligned_pwritev), and it is necessary if the initiating write
-     * is already serializing (without the flag, the read would deadlock
-     * waiting for the serialising write to complete).
-     */
-    BDRV_REQ_NO_SERIALISING     = 0x8,
     BDRV_REQ_FUA                = 0x10,
     BDRV_REQ_WRITE_COMPRESSED   = 0x20,
 
@@ -126,6 +114,7 @@ typedef struct HDGeometry {
                                       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)
 
@@ -300,6 +289,7 @@ void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
 void bdrv_replace_node(BlockDriverState *from, BlockDriverState *to,
                        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,
diff --git a/include/block/block_int.h b/include/block/block_int.h
index dd033d0..640fb82 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -999,8 +999,7 @@ 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_wait_serialising_requests(BdrvTrackedRequest *self);
-void bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align);
+bool coroutine_fn bdrv_mark_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);
diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h
index 4629f24..251b10d 100644
--- a/include/block/raw-aio.h
+++ b/include/block/raw-aio.h
@@ -57,6 +57,18 @@ void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context);
 void laio_io_plug(BlockDriverState *bs, LinuxAioState *s);
 void laio_io_unplug(BlockDriverState *bs, LinuxAioState *s);
 #endif
+/* io_uring.c - Linux io_uring implementation */
+#ifdef CONFIG_LINUX_IO_URING
+typedef struct LuringState LuringState;
+LuringState *luring_init(Error **errp);
+void luring_cleanup(LuringState *s);
+int coroutine_fn luring_co_submit(BlockDriverState *bs, LuringState *s, int fd,
+                                uint64_t offset, QEMUIOVector *qiov, int type);
+void luring_detach_aio_context(LuringState *s, AioContext *old_context);
+void luring_attach_aio_context(LuringState *s, AioContext *new_context);
+void luring_io_plug(BlockDriverState *bs, LuringState *s);
+void luring_io_unplug(BlockDriverState *bs, LuringState *s);
+#endif
 
 #ifdef _WIN32
 typedef struct QEMUWin32AIOState QEMUWin32AIOState;