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

# gpg: Signature made Mon 16 Jan 2017 13:38:52 GMT
# gpg:                using RSA key 0x9CA4ABB381AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>"
# gpg:                 aka "Stefan Hajnoczi <stefanha@gmail.com>"
# Primary key fingerprint: 8695 A8BF D3F9 7CDA AC35  775A 9CA4 ABB3 81AB 73C8

* remotes/stefanha/tags/block-pull-request:
  async: optimize aio_bh_poll
  aio: document locking
  aio-win32: remove walking_handlers, protecting AioHandler list with list_lock
  aio-posix: remove walking_handlers, protecting AioHandler list with list_lock
  aio: tweak walking in dispatch phase
  aio-posix: split aio_dispatch_handlers out of aio_dispatch
  qemu-thread: optimize QemuLockCnt with futexes on Linux
  aio: make ctx->list_lock a QemuLockCnt, subsuming ctx->walking_bh
  qemu-thread: introduce QemuLockCnt
  aio: rename bh_lock to list_lock
  block: get rid of bdrv_io_unplugged_begin/end

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

1 files changed, 25 insertions, 20 deletions

diff --git a/async.c b/async.c
index 2960171834..0d218ab0e0 100644
--- a/async.c
+++ b/async.c
@@ -53,14 +53,14 @@ void aio_bh_schedule_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
         .cb = cb,
         .opaque = opaque,
     };
-    qemu_mutex_lock(&ctx->bh_lock);
+    qemu_lockcnt_lock(&ctx->list_lock);
     bh->next = ctx->first_bh;
     bh->scheduled = 1;
     bh->deleted = 1;
     /* Make sure that the members are ready before putting bh into list */
     smp_wmb();
     ctx->first_bh = bh;
-    qemu_mutex_unlock(&ctx->bh_lock);
+    qemu_lockcnt_unlock(&ctx->list_lock);
     aio_notify(ctx);
 }
 
@@ -73,12 +73,12 @@ QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
         .cb = cb,
         .opaque = opaque,
     };
-    qemu_mutex_lock(&ctx->bh_lock);
+    qemu_lockcnt_lock(&ctx->list_lock);
     bh->next = ctx->first_bh;
     /* Make sure that the members are ready before putting bh into list */
     smp_wmb();
     ctx->first_bh = bh;
-    qemu_mutex_unlock(&ctx->bh_lock);
+    qemu_lockcnt_unlock(&ctx->list_lock);
     return bh;
 }
 
@@ -92,14 +92,13 @@ int aio_bh_poll(AioContext *ctx)
 {
     QEMUBH *bh, **bhp, *next;
     int ret;
+    bool deleted = false;
 
-    ctx->walking_bh++;
+    qemu_lockcnt_inc(&ctx->list_lock);
 
     ret = 0;
-    for (bh = ctx->first_bh; bh; bh = next) {
-        /* Make sure that fetching bh happens before accessing its members */
-        smp_read_barrier_depends();
-        next = bh->next;
+    for (bh = atomic_rcu_read(&ctx->first_bh); bh; bh = next) {
+        next = atomic_rcu_read(&bh->next);
         /* The atomic_xchg is paired with the one in qemu_bh_schedule.  The
          * implicit memory barrier ensures that the callback sees all writes
          * done by the scheduling thread.  It also ensures that the scheduling
@@ -114,13 +113,18 @@ int aio_bh_poll(AioContext *ctx)
             bh->idle = 0;
             aio_bh_call(bh);
         }
+        if (bh->deleted) {
+            deleted = true;
+        }
     }
 
-    ctx->walking_bh--;
-
     /* remove deleted bhs */
-    if (!ctx->walking_bh) {
-        qemu_mutex_lock(&ctx->bh_lock);
+    if (!deleted) {
+        qemu_lockcnt_dec(&ctx->list_lock);
+        return ret;
+    }
+
+    if (qemu_lockcnt_dec_and_lock(&ctx->list_lock)) {
         bhp = &ctx->first_bh;
         while (*bhp) {
             bh = *bhp;
@@ -131,9 +135,8 @@ int aio_bh_poll(AioContext *ctx)
                 bhp = &bh->next;
             }
         }
-        qemu_mutex_unlock(&ctx->bh_lock);
+        qemu_lockcnt_unlock(&ctx->list_lock);
     }
-
     return ret;
 }
 
@@ -187,7 +190,8 @@ aio_compute_timeout(AioContext *ctx)
     int timeout = -1;
     QEMUBH *bh;
 
-    for (bh = ctx->first_bh; bh; bh = bh->next) {
+    for (bh = atomic_rcu_read(&ctx->first_bh); bh;
+         bh = atomic_rcu_read(&bh->next)) {
         if (bh->scheduled) {
             if (bh->idle) {
                 /* idle bottom halves will be polled at least
@@ -270,7 +274,8 @@ aio_ctx_finalize(GSource     *source)
     }
 #endif
 
-    qemu_mutex_lock(&ctx->bh_lock);
+    qemu_lockcnt_lock(&ctx->list_lock);
+    assert(!qemu_lockcnt_count(&ctx->list_lock));
     while (ctx->first_bh) {
         QEMUBH *next = ctx->first_bh->next;
 
@@ -280,12 +285,12 @@ aio_ctx_finalize(GSource     *source)
         g_free(ctx->first_bh);
         ctx->first_bh = next;
     }
-    qemu_mutex_unlock(&ctx->bh_lock);
+    qemu_lockcnt_unlock(&ctx->list_lock);
 
     aio_set_event_notifier(ctx, &ctx->notifier, false, NULL, NULL);
     event_notifier_cleanup(&ctx->notifier);
     qemu_rec_mutex_destroy(&ctx->lock);
-    qemu_mutex_destroy(&ctx->bh_lock);
+    qemu_lockcnt_destroy(&ctx->list_lock);
     timerlistgroup_deinit(&ctx->tlg);
 }
 
@@ -372,6 +377,7 @@ AioContext *aio_context_new(Error **errp)
         goto fail;
     }
     g_source_set_can_recurse(&ctx->source, true);
+    qemu_lockcnt_init(&ctx->list_lock);
     aio_set_event_notifier(ctx, &ctx->notifier,
                            false,
                            (EventNotifierHandler *)
@@ -381,7 +387,6 @@ AioContext *aio_context_new(Error **errp)
     ctx->linux_aio = NULL;
 #endif
     ctx->thread_pool = NULL;
-    qemu_mutex_init(&ctx->bh_lock);
     qemu_rec_mutex_init(&ctx->lock);
     timerlistgroup_init(&ctx->tlg, aio_timerlist_notify, ctx);