IOHandler *io_read;
IOHandler *io_write;
int deleted;
- int pollfds_idx;
void *opaque;
QLIST_ENTRY(AioHandler) node;
};
node->io_read = io_read;
node->io_write = io_write;
node->opaque = opaque;
- node->pollfds_idx = -1;
node->pfd.events = (io_read ? G_IO_IN | G_IO_HUP | G_IO_ERR : 0);
node->pfd.events |= (io_write ? G_IO_OUT | G_IO_ERR : 0);
return progress;
}
+/* These thread-local variables are used only in a small part of aio_poll
+ * around the call to the poll() system call. In particular they are not
+ * used while aio_poll is performing callbacks, which makes it much easier
+ * to think about reentrancy!
+ *
+ * Stack-allocated arrays would be perfect but they have size limitations;
+ * heap allocation is expensive enough that we want to reuse arrays across
+ * calls to aio_poll(). And because poll() has to be called without holding
+ * any lock, the arrays cannot be stored in AioContext. Thread-local data
+ * has none of the disadvantages of these three options.
+ */
+static __thread GPollFD *pollfds;
+static __thread AioHandler **nodes;
+static __thread unsigned npfd, nalloc;
+static __thread Notifier pollfds_cleanup_notifier;
+
+static void pollfds_cleanup(Notifier *n, void *unused)
+{
+ g_assert(npfd == 0);
+ g_free(pollfds);
+ g_free(nodes);
+ nalloc = 0;
+}
+
+static void add_pollfd(AioHandler *node)
+{
+ if (npfd == nalloc) {
+ if (nalloc == 0) {
+ pollfds_cleanup_notifier.notify = pollfds_cleanup;
+ qemu_thread_atexit_add(&pollfds_cleanup_notifier);
+ nalloc = 8;
+ } else {
+ g_assert(nalloc <= INT_MAX);
+ nalloc *= 2;
+ }
+ pollfds = g_renew(GPollFD, pollfds, nalloc);
+ nodes = g_renew(AioHandler *, nodes, nalloc);
+ }
+ nodes[npfd] = node;
+ pollfds[npfd] = (GPollFD) {
+ .fd = node->pfd.fd,
+ .events = node->pfd.events,
+ };
+ npfd++;
+}
+
bool aio_poll(AioContext *ctx, bool blocking)
{
AioHandler *node;
- bool was_dispatching;
- int ret;
+ int i, ret;
bool progress;
+ int64_t timeout;
- was_dispatching = ctx->dispatching;
+ aio_context_acquire(ctx);
progress = false;
/* aio_notify can avoid the expensive event_notifier_set if
* everything (file descriptors, bottom halves, timers) will
* be re-evaluated before the next blocking poll(). This is
* already true when aio_poll is called with blocking == false;
- * if blocking == true, it is only true after poll() returns.
- *
- * If we're in a nested event loop, ctx->dispatching might be true.
- * In that case we can restore it just before returning, but we
- * have to clear it now.
+ * if blocking == true, it is only true after poll() returns,
+ * so disable the optimization now.
*/
- aio_set_dispatching(ctx, !blocking);
+ if (blocking) {
+ atomic_add(&ctx->notify_me, 2);
+ }
ctx->walking_handlers++;
- g_array_set_size(ctx->pollfds, 0);
+ assert(npfd == 0);
/* fill pollfds */
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
- node->pollfds_idx = -1;
if (!node->deleted && node->pfd.events) {
- GPollFD pfd = {
- .fd = node->pfd.fd,
- .events = node->pfd.events,
- };
- node->pollfds_idx = ctx->pollfds->len;
- g_array_append_val(ctx->pollfds, pfd);
+ add_pollfd(node);
}
}
- ctx->walking_handlers--;
+ timeout = blocking ? aio_compute_timeout(ctx) : 0;
/* wait until next event */
- ret = qemu_poll_ns((GPollFD *)ctx->pollfds->data,
- ctx->pollfds->len,
- blocking ? aio_compute_timeout(ctx) : 0);
+ if (timeout) {
+ aio_context_release(ctx);
+ }
+ ret = qemu_poll_ns((GPollFD *)pollfds, npfd, timeout);
+ if (blocking) {
+ atomic_sub(&ctx->notify_me, 2);
+ }
+ if (timeout) {
+ aio_context_acquire(ctx);
+ }
+
+ aio_notify_accept(ctx);
/* if we have any readable fds, dispatch event */
if (ret > 0) {
- QLIST_FOREACH(node, &ctx->aio_handlers, node) {
- if (node->pollfds_idx != -1) {
- GPollFD *pfd = &g_array_index(ctx->pollfds, GPollFD,
- node->pollfds_idx);
- node->pfd.revents = pfd->revents;
- }
+ for (i = 0; i < npfd; i++) {
+ nodes[i]->pfd.revents = pollfds[i].revents;
}
}
+ npfd = 0;
+ ctx->walking_handlers--;
+
/* Run dispatch even if there were no readable fds to run timers */
- aio_set_dispatching(ctx, true);
if (aio_dispatch(ctx)) {
progress = true;
}
- aio_set_dispatching(ctx, was_dispatching);
+ aio_context_release(ctx);
+
return progress;
}