aio-posix: extract ppoll(2) and epoll(7) fd monitoring

The ppoll(2) and epoll(7) file descriptor monitoring implementations are
mixed with the core util/aio-posix.c code.  Before adding another
implementation for Linux io_uring, extract out the existing
ones so there is a clear interface and the core code is simpler.

The new interface is AioContext->fdmon_ops, a pointer to a FDMonOps
struct.  See the patch for details.

Semantic changes:
1. ppoll(2) now reflects events from pollfds[] back into AioHandlers
   while we're still on the clock for adaptive polling.  This was
   already happening for epoll(7), so if it's really an issue then we'll
   need to fix both in the future.
2. epoll(7)'s fallback to ppoll(2) while external events are disabled
   was broken when the number of fds exceeded the epoll(7) upgrade
   threshold.  I guess this code path simply wasn't tested and no one
   noticed the bug.  I didn't go out of my way to fix it but the correct
   code is simpler than preserving the bug.

I also took some liberties in removing the unnecessary
AioContext->epoll_available (just check AioContext->epollfd != -1
instead) and AioContext->epoll_enabled (it's implicit if our
AioContext->fdmon_ops callbacks are being invoked) fields.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Link: https://lore.kernel.org/r/20200305170806.1313245-4-stefanha@redhat.com
Message-Id: <20200305170806.1313245-4-stefanha@redhat.com>

1 files changed, 104 insertions, 0 deletions

diff --git a/util/fdmon-poll.c b/util/fdmon-poll.c
new file mode 100644
index 0000000000..67992116b8
--- /dev/null
+++ b/util/fdmon-poll.c
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * poll(2) file descriptor monitoring
+ *
+ * Uses ppoll(2) when available, g_poll() otherwise.
+ */
+
+#include "qemu/osdep.h"
+#include "aio-posix.h"
+#include "qemu/rcu_queue.h"
+
+/*
+ * These thread-local variables are used only in fdmon_poll_wait() 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++;
+}
+
+static int fdmon_poll_wait(AioContext *ctx, AioHandlerList *ready_list,
+                            int64_t timeout)
+{
+    AioHandler *node;
+    int ret;
+
+    assert(npfd == 0);
+
+    QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
+        if (!QLIST_IS_INSERTED(node, node_deleted) && node->pfd.events
+                && aio_node_check(ctx, node->is_external)) {
+            add_pollfd(node);
+        }
+    }
+
+    /* epoll(7) is faster above a certain number of fds */
+    if (fdmon_epoll_try_upgrade(ctx, npfd)) {
+        return ctx->fdmon_ops->wait(ctx, ready_list, timeout);
+    }
+
+    ret = qemu_poll_ns(pollfds, npfd, timeout);
+    if (ret > 0) {
+        int i;
+
+        for (i = 0; i < npfd; i++) {
+            int revents = pollfds[i].revents;
+
+            if (revents) {
+                aio_add_ready_handler(ready_list, nodes[i], revents);
+            }
+        }
+    }
+
+    npfd = 0;
+    return ret;
+}
+
+static void fdmon_poll_update(AioContext *ctx, AioHandler *node, bool is_new)
+{
+    /* Do nothing, AioHandler already contains the state we'll need */
+}
+
+const FDMonOps fdmon_poll_ops = {
+    .update = fdmon_poll_update,
+    .wait = fdmon_poll_wait,
+};