Merge remote-tracking branch 'remotes/famz/tags/for-upstream' into staging

# gpg: Signature made Fri 28 Oct 2016 15:47:39 BST
# gpg:                using RSA key 0xCA35624C6A9171C6
# gpg: Good signature from "Fam Zheng <famz@redhat.com>"
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 5003 7CB7 9706 0F76 F021  AD56 CA35 624C 6A91 71C6

* remotes/famz/tags/for-upstream:
  aio: convert from RFifoLock to QemuRecMutex
  qemu-thread: introduce QemuRecMutex
  iothread: release AioContext around aio_poll
  block: only call aio_poll on the current thread's AioContext
  qemu-img: call aio_context_acquire/release around block job
  qemu-io: acquire AioContext
  block: prepare bdrv_reopen_multiple to release AioContext
  replication: pass BlockDriverState to reopen_backing_file
  iothread: detach all block devices before stopping them
  aio: introduce qemu_get_current_aio_context
  sheepdog: use BDRV_POLL_WHILE
  nfs: use BDRV_POLL_WHILE
  nfs: move nfs_set_events out of the while loops
  block: introduce BDRV_POLL_WHILE
  qed: Implement .bdrv_drain
  block: change drain to look only at one child at a time
  block: add BDS field to count in-flight requests
  mirror: use bdrv_drained_begin/bdrv_drained_end
  blockjob: introduce .drain callback for jobs
  replication: interrupt failover if the main device is closed

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

8 files changed, 98 insertions, 64 deletions

diff --git a/include/block/aio.h b/include/block/aio.h
index b9fe2cb37e..c7ae27c91c 100644
--- a/include/block/aio.h
+++ b/include/block/aio.h
@@ -18,7 +18,6 @@
 #include "qemu/queue.h"
 #include "qemu/event_notifier.h"
 #include "qemu/thread.h"
-#include "qemu/rfifolock.h"
 #include "qemu/timer.h"
 
 typedef struct BlockAIOCB BlockAIOCB;
@@ -54,7 +53,7 @@ struct AioContext {
     GSource source;
 
     /* Protects all fields from multi-threaded access */
-    RFifoLock lock;
+    QemuRecMutex lock;
 
     /* The list of registered AIO handlers */
     QLIST_HEAD(, AioHandler) aio_handlers;
@@ -116,9 +115,6 @@ struct AioContext {
     bool notified;
     EventNotifier notifier;
 
-    /* Scheduling this BH forces the event loop it iterate */
-    QEMUBH *notify_dummy_bh;
-
     /* Thread pool for performing work and receiving completion callbacks */
     struct ThreadPool *thread_pool;
 
@@ -453,6 +449,24 @@ static inline bool aio_node_check(AioContext *ctx, bool is_external)
 }
 
 /**
+ * Return the AioContext whose event loop runs in the current thread.
+ *
+ * If called from an IOThread this will be the IOThread's AioContext.  If
+ * called from another thread it will be the main loop AioContext.
+ */
+AioContext *qemu_get_current_aio_context(void);
+
+/**
+ * @ctx: the aio context
+ *
+ * Return whether we are running in the I/O thread that manages @ctx.
+ */
+static inline bool aio_context_in_iothread(AioContext *ctx)
+{
+    return ctx == qemu_get_current_aio_context();
+}
+
+/**
  * aio_context_setup:
  * @ctx: the aio context
  *
diff --git a/include/block/block.h b/include/block/block.h
index 398a050176..b7dc7d54ae 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -218,7 +218,7 @@ BlockDriverState *bdrv_open(const char *filename, const char *reference,
 BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
                                     BlockDriverState *bs,
                                     QDict *options, int flags);
-int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp);
+int bdrv_reopen_multiple(AioContext *ctx, BlockReopenQueue *bs_queue, Error **errp);
 int bdrv_reopen(BlockDriverState *bs, int bdrv_flags, Error **errp);
 int bdrv_reopen_prepare(BDRVReopenState *reopen_state,
                         BlockReopenQueue *queue, Error **errp);
@@ -334,6 +334,35 @@ void bdrv_drain(BlockDriverState *bs);
 void coroutine_fn bdrv_co_drain(BlockDriverState *bs);
 void bdrv_drain_all(void);
 
+#define BDRV_POLL_WHILE(bs, cond) ({                       \
+    bool waited_ = false;                                  \
+    BlockDriverState *bs_ = (bs);                          \
+    AioContext *ctx_ = bdrv_get_aio_context(bs_);          \
+    if (aio_context_in_iothread(ctx_)) {                   \
+        while ((cond)) {                                   \
+            aio_poll(ctx_, true);                          \
+            waited_ = true;                                \
+        }                                                  \
+    } else {                                               \
+        assert(qemu_get_current_aio_context() ==           \
+               qemu_get_aio_context());                    \
+        /* Ask bdrv_dec_in_flight to wake up the main      \
+         * QEMU AioContext.  Extra I/O threads never take  \
+         * other I/O threads' AioContexts (see for example \
+         * block_job_defer_to_main_loop for how to do it). \
+         */                                                \
+        assert(!bs_->wakeup);                              \
+        bs_->wakeup = true;                                \
+        while ((cond)) {                                   \
+            aio_context_release(ctx_);                     \
+            aio_poll(qemu_get_aio_context(), true);        \
+            aio_context_acquire(ctx_);                     \
+            waited_ = true;                                \
+        }                                                  \
+        bs_->wakeup = false;                               \
+    }                                                      \
+    waited_; })
+
 int bdrv_pdiscard(BlockDriverState *bs, int64_t offset, int count);
 int bdrv_co_pdiscard(BlockDriverState *bs, int64_t offset, int count);
 int bdrv_has_zero_init_1(BlockDriverState *bs);
diff --git a/include/block/block_int.h b/include/block/block_int.h
index e96e9ada57..e7ff58419c 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -62,8 +62,6 @@
 enum BdrvTrackedRequestType {
     BDRV_TRACKED_READ,
     BDRV_TRACKED_WRITE,
-    BDRV_TRACKED_FLUSH,
-    BDRV_TRACKED_IOCTL,
     BDRV_TRACKED_DISCARD,
 };
 
@@ -445,7 +443,7 @@ struct BlockDriverState {
                          note this is a reference count */
 
     CoQueue flush_queue;            /* Serializing flush queue */
-    BdrvTrackedRequest *active_flush_req; /* Flush request in flight */
+    bool active_flush_req;          /* Flush request in flight? */
     unsigned int write_gen;         /* Current data generation */
     unsigned int flushed_gen;       /* Flushed write generation */
 
@@ -473,9 +471,12 @@ struct BlockDriverState {
     /* Callback before write request is processed */
     NotifierWithReturnList before_write_notifiers;
 
-    /* number of in-flight serialising requests */
+    /* number of in-flight requests; overall and serialising */
+    unsigned int in_flight;
     unsigned int serialising_in_flight;
 
+    bool wakeup;
+
     /* Offset after the highest byte written to */
     uint64_t wr_highest_offset;
 
@@ -634,6 +635,21 @@ void bdrv_remove_aio_context_notifier(BlockDriverState *bs,
                                       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
@@ -787,6 +803,9 @@ bool bdrv_requests_pending(BlockDriverState *bs);
 void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out);
 void bdrv_undo_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap *in);
 
+void bdrv_inc_in_flight(BlockDriverState *bs);
+void bdrv_dec_in_flight(BlockDriverState *bs);
+
 void blockdev_close_all_bdrv_states(void);
 
 #endif /* BLOCK_INT_H */
diff --git a/include/block/blockjob.h b/include/block/blockjob.h
index 4ddb4ae2e1..2bb39f4d29 100644
--- a/include/block/blockjob.h
+++ b/include/block/blockjob.h
@@ -92,6 +92,13 @@ typedef struct BlockJobDriver {
      * besides job->blk to the new AioContext.
      */
     void (*attached_aio_context)(BlockJob *job, AioContext *new_context);
+
+    /*
+     * If the callback is not NULL, it will be invoked when the job has to be
+     * synchronously cancelled or completed; it should drain BlockDriverStates
+     * as required to ensure progress.
+     */
+    void (*drain)(BlockJob *job);
 } BlockJobDriver;
 
 /**
diff --git a/include/qemu/rfifolock.h b/include/qemu/rfifolock.h
deleted file mode 100644
index b23ab538a6..0000000000
--- a/include/qemu/rfifolock.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * Recursive FIFO lock
- *
- * Copyright Red Hat, Inc. 2013
- *
- * Authors:
- *  Stefan Hajnoczi   <stefanha@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- *
- */
-
-#ifndef QEMU_RFIFOLOCK_H
-#define QEMU_RFIFOLOCK_H
-
-#include "qemu/thread.h"
-
-/* Recursive FIFO lock
- *
- * This lock provides more features than a plain mutex:
- *
- * 1. Fairness - enforces FIFO order.
- * 2. Nesting - can be taken recursively.
- * 3. Contention callback - optional, called when thread must wait.
- *
- * The recursive FIFO lock is heavyweight so prefer other synchronization
- * primitives if you do not need its features.
- */
-typedef struct {
-    QemuMutex lock;             /* protects all fields */
-
-    /* FIFO order */
-    unsigned int head;          /* active ticket number */
-    unsigned int tail;          /* waiting ticket number */
-    QemuCond cond;              /* used to wait for our ticket number */
-
-    /* Nesting */
-    QemuThread owner_thread;    /* thread that currently has ownership */
-    unsigned int nesting;       /* amount of nesting levels */
-
-    /* Contention callback */
-    void (*cb)(void *);         /* called when thread must wait, with ->lock
-                                 * held so it may not recursively lock/unlock
-                                 */
-    void *cb_opaque;
-} RFifoLock;
-
-void rfifolock_init(RFifoLock *r, void (*cb)(void *), void *opaque);
-void rfifolock_destroy(RFifoLock *r);
-void rfifolock_lock(RFifoLock *r);
-void rfifolock_unlock(RFifoLock *r);
-
-#endif /* QEMU_RFIFOLOCK_H */
diff --git a/include/qemu/thread-posix.h b/include/qemu/thread-posix.h
index aa03567e5e..09d1e15728 100644
--- a/include/qemu/thread-posix.h
+++ b/include/qemu/thread-posix.h
@@ -4,6 +4,12 @@
 #include <pthread.h>
 #include <semaphore.h>
 
+typedef QemuMutex QemuRecMutex;
+#define qemu_rec_mutex_destroy qemu_mutex_destroy
+#define qemu_rec_mutex_lock qemu_mutex_lock
+#define qemu_rec_mutex_try_lock qemu_mutex_try_lock
+#define qemu_rec_mutex_unlock qemu_mutex_unlock
+
 struct QemuMutex {
     pthread_mutex_t lock;
 };
diff --git a/include/qemu/thread-win32.h b/include/qemu/thread-win32.h
index c7ce8dcd45..5fb6541ae9 100644
--- a/include/qemu/thread-win32.h
+++ b/include/qemu/thread-win32.h
@@ -8,6 +8,16 @@ struct QemuMutex {
     LONG owner;
 };
 
+typedef struct QemuRecMutex QemuRecMutex;
+struct QemuRecMutex {
+    CRITICAL_SECTION lock;
+};
+
+void qemu_rec_mutex_destroy(QemuRecMutex *mutex);
+void qemu_rec_mutex_lock(QemuRecMutex *mutex);
+int qemu_rec_mutex_trylock(QemuRecMutex *mutex);
+void qemu_rec_mutex_unlock(QemuRecMutex *mutex);
+
 struct QemuCond {
     LONG waiters, target;
     HANDLE sema;
diff --git a/include/qemu/thread.h b/include/qemu/thread.h
index 31237e93ee..e8e665f020 100644
--- a/include/qemu/thread.h
+++ b/include/qemu/thread.h
@@ -25,6 +25,9 @@ void qemu_mutex_lock(QemuMutex *mutex);
 int qemu_mutex_trylock(QemuMutex *mutex);
 void qemu_mutex_unlock(QemuMutex *mutex);
 
+/* Prototypes for other functions are in thread-posix.h/thread-win32.h.  */
+void qemu_rec_mutex_init(QemuRecMutex *mutex);
+
 void qemu_cond_init(QemuCond *cond);
 void qemu_cond_destroy(QemuCond *cond);