X-Git-Url: https://repo.jachan.dev/qemu.git/blobdiff_plain/2f78e491d7b46542158ce0b8132ee4e05bc0ade4..53a5736f949a47fa7d890baf8472824263682c92:/async.c

diff --git a/async.c b/async.c
index 6e1b282aa7..0d218ab0e0 100644
--- a/async.c
+++ b/async.c
@@ -22,11 +22,14 @@
  * THE SOFTWARE.
  */
 
+#include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/aio.h"
 #include "block/thread-pool.h"
 #include "qemu/main-loop.h"
 #include "qemu/atomic.h"
+#include "block/raw-aio.h"
 
 /***********************************************************/
 /* bottom halves (can be seen as timers which expire ASAP) */
@@ -41,98 +44,126 @@ struct QEMUBH {
     bool deleted;
 };
 
+void aio_bh_schedule_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
+{
+    QEMUBH *bh;
+    bh = g_new(QEMUBH, 1);
+    *bh = (QEMUBH){
+        .ctx = ctx,
+        .cb = cb,
+        .opaque = opaque,
+    };
+    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_lockcnt_unlock(&ctx->list_lock);
+    aio_notify(ctx);
+}
+
 QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
 {
     QEMUBH *bh;
-    bh = g_malloc0(sizeof(QEMUBH));
-    bh->ctx = ctx;
-    bh->cb = cb;
-    bh->opaque = opaque;
-    qemu_mutex_lock(&ctx->bh_lock);
+    bh = g_new(QEMUBH, 1);
+    *bh = (QEMUBH){
+        .ctx = ctx,
+        .cb = cb,
+        .opaque = opaque,
+    };
+    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;
 }
 
+void aio_bh_call(QEMUBH *bh)
+{
+    bh->cb(bh->opaque);
+}
+
 /* Multiple occurrences of aio_bh_poll cannot be called concurrently */
 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;
-        if (!bh->deleted && bh->scheduled) {
-            bh->scheduled = 0;
-            /* Paired with write barrier in bh schedule to ensure reading for
-             * idle & callbacks coming after bh's scheduling.
-             */
-            smp_rmb();
-            if (!bh->idle)
+    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
+         * thread sees the zero before bh->cb has run, and thus will call
+         * aio_notify again if necessary.
+         */
+        if (atomic_xchg(&bh->scheduled, 0)) {
+            /* Idle BHs don't count as progress */
+            if (!bh->idle) {
                 ret = 1;
+            }
             bh->idle = 0;
-            bh->cb(bh->opaque);
+            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;
-            if (bh->deleted) {
+            if (bh->deleted && !bh->scheduled) {
                 *bhp = bh->next;
                 g_free(bh);
             } else {
                 bhp = &bh->next;
             }
         }
-        qemu_mutex_unlock(&ctx->bh_lock);
+        qemu_lockcnt_unlock(&ctx->list_lock);
     }
-
     return ret;
 }
 
 void qemu_bh_schedule_idle(QEMUBH *bh)
 {
-    if (bh->scheduled)
-        return;
     bh->idle = 1;
     /* Make sure that idle & any writes needed by the callback are done
      * before the locations are read in the aio_bh_poll.
      */
-    smp_wmb();
-    bh->scheduled = 1;
+    atomic_mb_set(&bh->scheduled, 1);
 }
 
 void qemu_bh_schedule(QEMUBH *bh)
 {
     AioContext *ctx;
 
-    if (bh->scheduled)
-        return;
     ctx = bh->ctx;
     bh->idle = 0;
-    /* Make sure that:
+    /* The memory barrier implicit in atomic_xchg makes sure that:
      * 1. idle & any writes needed by the callback are done before the
      *    locations are read in the aio_bh_poll.
      * 2. ctx is loaded before scheduled is set and the callback has a chance
      *    to execute.
      */
-    smp_mb();
-    bh->scheduled = 1;
-    aio_notify(ctx);
+    if (atomic_xchg(&bh->scheduled, 1) == 0) {
+        aio_notify(ctx);
+    }
 }
 
 
@@ -159,8 +190,9 @@ aio_compute_timeout(AioContext *ctx)
     int timeout = -1;
     QEMUBH *bh;
 
-    for (bh = ctx->first_bh; bh; bh = bh->next) {
-        if (!bh->deleted && bh->scheduled) {
+    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
                  * every 10ms */
@@ -186,6 +218,8 @@ aio_ctx_prepare(GSource *source, gint    *timeout)
 {
     AioContext *ctx = (AioContext *) source;
 
+    atomic_or(&ctx->notify_me, 1);
+
     /* We assume there is no timeout already supplied */
     *timeout = qemu_timeout_ns_to_ms(aio_compute_timeout(ctx));
 
@@ -202,10 +236,13 @@ aio_ctx_check(GSource *source)
     AioContext *ctx = (AioContext *) source;
     QEMUBH *bh;
 
+    atomic_and(&ctx->notify_me, ~1);
+    aio_notify_accept(ctx);
+
     for (bh = ctx->first_bh; bh; bh = bh->next) {
-        if (!bh->deleted && bh->scheduled) {
+        if (bh->scheduled) {
             return true;
-	}
+        }
     }
     return aio_pending(ctx) || (timerlistgroup_deadline_ns(&ctx->tlg) == 0);
 }
@@ -218,7 +255,7 @@ aio_ctx_dispatch(GSource     *source,
     AioContext *ctx = (AioContext *) source;
 
     assert(callback == NULL);
-    aio_dispatch(ctx);
+    aio_dispatch(ctx, true);
     return true;
 }
 
@@ -228,11 +265,32 @@ aio_ctx_finalize(GSource     *source)
     AioContext *ctx = (AioContext *) source;
 
     thread_pool_free(ctx->thread_pool);
-    aio_set_event_notifier(ctx, &ctx->notifier, NULL);
+
+#ifdef CONFIG_LINUX_AIO
+    if (ctx->linux_aio) {
+        laio_detach_aio_context(ctx->linux_aio, ctx);
+        laio_cleanup(ctx->linux_aio);
+        ctx->linux_aio = NULL;
+    }
+#endif
+
+    qemu_lockcnt_lock(&ctx->list_lock);
+    assert(!qemu_lockcnt_count(&ctx->list_lock));
+    while (ctx->first_bh) {
+        QEMUBH *next = ctx->first_bh->next;
+
+        /* qemu_bh_delete() must have been called on BHs in this AioContext */
+        assert(ctx->first_bh->deleted);
+
+        g_free(ctx->first_bh);
+        ctx->first_bh = next;
+    }
+    qemu_lockcnt_unlock(&ctx->list_lock);
+
+    aio_set_event_notifier(ctx, &ctx->notifier, false, NULL, NULL);
     event_notifier_cleanup(&ctx->notifier);
-    rfifolock_destroy(&ctx->lock);
-    qemu_mutex_destroy(&ctx->bh_lock);
-    g_array_free(ctx->pollfds, TRUE);
+    qemu_rec_mutex_destroy(&ctx->lock);
+    qemu_lockcnt_destroy(&ctx->list_lock);
     timerlistgroup_deinit(&ctx->tlg);
 }
 
@@ -257,24 +315,33 @@ ThreadPool *aio_get_thread_pool(AioContext *ctx)
     return ctx->thread_pool;
 }
 
-void aio_set_dispatching(AioContext *ctx, bool dispatching)
+#ifdef CONFIG_LINUX_AIO
+LinuxAioState *aio_get_linux_aio(AioContext *ctx)
 {
-    ctx->dispatching = dispatching;
-    if (!dispatching) {
-        /* Write ctx->dispatching before reading e.g. bh->scheduled.
-         * Optimization: this is only needed when we're entering the "unsafe"
-         * phase where other threads must call event_notifier_set.
-         */
-        smp_mb();
+    if (!ctx->linux_aio) {
+        ctx->linux_aio = laio_init();
+        laio_attach_aio_context(ctx->linux_aio, ctx);
     }
+    return ctx->linux_aio;
 }
+#endif
 
 void aio_notify(AioContext *ctx)
 {
-    /* Write e.g. bh->scheduled before reading ctx->dispatching.  */
+    /* Write e.g. bh->scheduled before reading ctx->notify_me.  Pairs
+     * with atomic_or in aio_ctx_prepare or atomic_add in aio_poll.
+     */
     smp_mb();
-    if (!ctx->dispatching) {
+    if (ctx->notify_me) {
         event_notifier_set(&ctx->notifier);
+        atomic_mb_set(&ctx->notified, true);
+    }
+}
+
+void aio_notify_accept(AioContext *ctx)
+{
+    if (atomic_xchg(&ctx->notified, false)) {
+        event_notifier_test_and_clear(&ctx->notifier);
     }
 }
 
@@ -283,33 +350,55 @@ static void aio_timerlist_notify(void *opaque)
     aio_notify(opaque);
 }
 
-static void aio_rfifolock_cb(void *opaque)
+static void event_notifier_dummy_cb(EventNotifier *e)
 {
-    /* Kick owner thread in case they are blocked in aio_poll() */
-    aio_notify(opaque);
+}
+
+/* Returns true if aio_notify() was called (e.g. a BH was scheduled) */
+static bool event_notifier_poll(void *opaque)
+{
+    EventNotifier *e = opaque;
+    AioContext *ctx = container_of(e, AioContext, notifier);
+
+    return atomic_read(&ctx->notified);
 }
 
 AioContext *aio_context_new(Error **errp)
 {
     int ret;
     AioContext *ctx;
+
     ctx = (AioContext *) g_source_new(&aio_source_funcs, sizeof(AioContext));
+    aio_context_setup(ctx);
+
     ret = event_notifier_init(&ctx->notifier, false);
     if (ret < 0) {
-        g_source_destroy(&ctx->source);
         error_setg_errno(errp, -ret, "Failed to initialize event notifier");
-        return NULL;
+        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 *)
-                           event_notifier_test_and_clear);
-    ctx->pollfds = g_array_new(FALSE, FALSE, sizeof(GPollFD));
+                           event_notifier_dummy_cb,
+                           event_notifier_poll);
+#ifdef CONFIG_LINUX_AIO
+    ctx->linux_aio = NULL;
+#endif
     ctx->thread_pool = NULL;
-    qemu_mutex_init(&ctx->bh_lock);
-    rfifolock_init(&ctx->lock, aio_rfifolock_cb, ctx);
+    qemu_rec_mutex_init(&ctx->lock);
     timerlistgroup_init(&ctx->tlg, aio_timerlist_notify, ctx);
 
+    ctx->poll_ns = 0;
+    ctx->poll_max_ns = 0;
+    ctx->poll_grow = 0;
+    ctx->poll_shrink = 0;
+
     return ctx;
+fail:
+    g_source_destroy(&ctx->source);
+    return NULL;
 }
 
 void aio_context_ref(AioContext *ctx)
@@ -324,10 +413,10 @@ void aio_context_unref(AioContext *ctx)
 
 void aio_context_acquire(AioContext *ctx)
 {
-    rfifolock_lock(&ctx->lock);
+    qemu_rec_mutex_lock(&ctx->lock);
 }
 
 void aio_context_release(AioContext *ctx)
 {
-    rfifolock_unlock(&ctx->lock);
+    qemu_rec_mutex_unlock(&ctx->lock);
 }