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, 151 insertions, 0 deletions

diff --git a/util/fdmon-epoll.c b/util/fdmon-epoll.c
new file mode 100644
index 0000000000..29c1454469
--- /dev/null
+++ b/util/fdmon-epoll.c
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * epoll(7) file descriptor monitoring
+ */
+
+#include "qemu/osdep.h"
+#include <sys/epoll.h>
+#include "qemu/rcu_queue.h"
+#include "aio-posix.h"
+
+/* The fd number threshold to switch to epoll */
+#define EPOLL_ENABLE_THRESHOLD 64
+
+void fdmon_epoll_disable(AioContext *ctx)
+{
+    if (ctx->epollfd >= 0) {
+        close(ctx->epollfd);
+        ctx->epollfd = -1;
+    }
+
+    /* Switch back */
+    ctx->fdmon_ops = &fdmon_poll_ops;
+}
+
+static inline int epoll_events_from_pfd(int pfd_events)
+{
+    return (pfd_events & G_IO_IN ? EPOLLIN : 0) |
+           (pfd_events & G_IO_OUT ? EPOLLOUT : 0) |
+           (pfd_events & G_IO_HUP ? EPOLLHUP : 0) |
+           (pfd_events & G_IO_ERR ? EPOLLERR : 0);
+}
+
+static void fdmon_epoll_update(AioContext *ctx, AioHandler *node, bool is_new)
+{
+    struct epoll_event event;
+    int r;
+    int ctl;
+
+    if (!node->pfd.events) {
+        ctl = EPOLL_CTL_DEL;
+    } else {
+        event.data.ptr = node;
+        event.events = epoll_events_from_pfd(node->pfd.events);
+        ctl = is_new ? EPOLL_CTL_ADD : EPOLL_CTL_MOD;
+    }
+
+    r = epoll_ctl(ctx->epollfd, ctl, node->pfd.fd, &event);
+    if (r) {
+        fdmon_epoll_disable(ctx);
+    }
+}
+
+static int fdmon_epoll_wait(AioContext *ctx, AioHandlerList *ready_list,
+                            int64_t timeout)
+{
+    GPollFD pfd = {
+        .fd = ctx->epollfd,
+        .events = G_IO_IN | G_IO_OUT | G_IO_HUP | G_IO_ERR,
+    };
+    AioHandler *node;
+    int i, ret = 0;
+    struct epoll_event events[128];
+
+    /* Fall back while external clients are disabled */
+    if (atomic_read(&ctx->external_disable_cnt)) {
+        return fdmon_poll_ops.wait(ctx, ready_list, timeout);
+    }
+
+    if (timeout > 0) {
+        ret = qemu_poll_ns(&pfd, 1, timeout);
+        if (ret > 0) {
+            timeout = 0;
+        }
+    }
+    if (timeout <= 0 || ret > 0) {
+        ret = epoll_wait(ctx->epollfd, events,
+                         ARRAY_SIZE(events),
+                         timeout);
+        if (ret <= 0) {
+            goto out;
+        }
+        for (i = 0; i < ret; i++) {
+            int ev = events[i].events;
+            int revents = (ev & EPOLLIN ? G_IO_IN : 0) |
+                          (ev & EPOLLOUT ? G_IO_OUT : 0) |
+                          (ev & EPOLLHUP ? G_IO_HUP : 0) |
+                          (ev & EPOLLERR ? G_IO_ERR : 0);
+
+            node = events[i].data.ptr;
+            aio_add_ready_handler(ready_list, node, revents);
+        }
+    }
+out:
+    return ret;
+}
+
+static const FDMonOps fdmon_epoll_ops = {
+    .update = fdmon_epoll_update,
+    .wait = fdmon_epoll_wait,
+};
+
+static bool fdmon_epoll_try_enable(AioContext *ctx)
+{
+    AioHandler *node;
+    struct epoll_event event;
+
+    QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
+        int r;
+        if (QLIST_IS_INSERTED(node, node_deleted) || !node->pfd.events) {
+            continue;
+        }
+        event.events = epoll_events_from_pfd(node->pfd.events);
+        event.data.ptr = node;
+        r = epoll_ctl(ctx->epollfd, EPOLL_CTL_ADD, node->pfd.fd, &event);
+        if (r) {
+            return false;
+        }
+    }
+
+    ctx->fdmon_ops = &fdmon_epoll_ops;
+    return true;
+}
+
+bool fdmon_epoll_try_upgrade(AioContext *ctx, unsigned npfd)
+{
+    if (ctx->epollfd < 0) {
+        return false;
+    }
+
+    /* Do not upgrade while external clients are disabled */
+    if (atomic_read(&ctx->external_disable_cnt)) {
+        return false;
+    }
+
+    if (npfd >= EPOLL_ENABLE_THRESHOLD) {
+        if (fdmon_epoll_try_enable(ctx)) {
+            return true;
+        } else {
+            fdmon_epoll_disable(ctx);
+        }
+    }
+    return false;
+}
+
+void fdmon_epoll_setup(AioContext *ctx)
+{
+    ctx->epollfd = epoll_create1(EPOLL_CLOEXEC);
+    if (ctx->epollfd == -1) {
+        fprintf(stderr, "Failed to create epoll instance: %s", strerror(errno));
+    }
+}