Pull request

-----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCAAdFiEEhpWov9P5fNqsNXdanKSrs4Grc8gFAl5o3EQACgkQnKSrs4Gr
 c8jbYwgAupuS62MCITszybRE5Ote5CL80QDbMXNsZnZh6YBIGhPCqW2zdI2+m0zu
 +qoN6x6dxxNUWCvNlhbOcA45fiZVmYzS69TiEo21kCDijoK+h8+W+YbXuxGR2xJi
 cZMm8Q1DiK6Lj3vyfiwkFf4ns3VNz9DhI9hXu6CcpSkNcp79elQu87JJbzEWWWWy
 uEc7uEyBr0uCAKLEJvaLzzzWE2D2i6qKlmj3G17UbDNgCJ/Q/5HX13RUfMrgNgiP
 wmpcJ5MsB3Prz3K4XMMytUKXX/M8zpRLahp3p31t9qHelTWC3Lk1U4xzLPTJZPlm
 if/lrGRCRml+DKb9keBjWeTF4U31vg==
 =LftU
 -----END PGP SIGNATURE-----

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

Pull request

# gpg: Signature made Wed 11 Mar 2020 12:40:36 GMT
# gpg:                using RSA key 8695A8BFD3F97CDAAC35775A9CA4ABB381AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>" [full]
# gpg:                 aka "Stefan Hajnoczi <stefanha@gmail.com>" [full]
# Primary key fingerprint: 8695 A8BF D3F9 7CDA AC35  775A 9CA4 ABB3 81AB 73C8

* remotes/stefanha/tags/block-pull-request:
  aio-posix: remove idle poll handlers to improve scalability
  aio-posix: support userspace polling of fd monitoring
  aio-posix: add io_uring fd monitoring implementation
  aio-posix: simplify FDMonOps->update() prototype
  aio-posix: extract ppoll(2) and epoll(7) fd monitoring
  aio-posix: move RCU_READ_LOCK() into run_poll_handlers()
  aio-posix: completely stop polling when disabled
  aio-posix: remove confusing QLIST_SAFE_REMOVE()
  qemu/queue.h: clear linked list pointers on remove

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

MAINTAINERS

@@ -1885,6 +1885,8 @@ L: qemu-block@nongnu.org
 S: Supported
 F: util/async.c
 F: util/aio-*.c
+F: util/aio-*.h
+F: util/fdmon-*.c
 F: block/io.c
 F: migration/block*
 F: include/block/aio.h

configure

@@ -4093,6 +4093,11 @@ if test "$linux_io_uring" != "no" ; then
     linux_io_uring_cflags=$($pkg_config --cflags liburing)
     linux_io_uring_libs=$($pkg_config --libs liburing)
     linux_io_uring=yes
+
+    # io_uring is used in libqemuutil.a where per-file -libs variables are not
+    # seen by programs linking the archive.  It's not ideal, but just add the
+    # library dependency globally.
+    LIBS="$linux_io_uring_libs $LIBS"
   else
     if test "$linux_io_uring" = "yes" ; then
       feature_not_found "linux io_uring" "Install liburing devel"

include/block/aio.h

@@ -14,6 +14,9 @@
 #ifndef QEMU_AIO_H
 #define QEMU_AIO_H
 
+#ifdef CONFIG_LINUX_IO_URING
+#include <liburing.h>
+#endif
 #include "qemu/queue.h"
 #include "qemu/event_notifier.h"
 #include "qemu/thread.h"
@@ -52,6 +55,56 @@ struct ThreadPool;
 struct LinuxAioState;
 struct LuringState;
 
+/* Is polling disabled? */
+bool aio_poll_disabled(AioContext *ctx);
+
+/* Callbacks for file descriptor monitoring implementations */
+typedef struct {
+    /*
+     * update:
+     * @ctx: the AioContext
+     * @old_node: the existing handler or NULL if this file descriptor is being
+     *            monitored for the first time
+     * @new_node: the new handler or NULL if this file descriptor is being
+     *            removed
+     *
+     * Add/remove/modify a monitored file descriptor.
+     *
+     * Called with ctx->list_lock acquired.
+     */
+    void (*update)(AioContext *ctx, AioHandler *old_node, AioHandler *new_node);
+
+    /*
+     * wait:
+     * @ctx: the AioContext
+     * @ready_list: list for handlers that become ready
+     * @timeout: maximum duration to wait, in nanoseconds
+     *
+     * Wait for file descriptors to become ready and place them on ready_list.
+     *
+     * Called with ctx->list_lock incremented but not locked.
+     *
+     * Returns: number of ready file descriptors.
+     */
+    int (*wait)(AioContext *ctx, AioHandlerList *ready_list, int64_t timeout);
+
+    /*
+     * need_wait:
+     * @ctx: the AioContext
+     *
+     * Tell aio_poll() when to stop userspace polling early because ->wait()
+     * has fds ready.
+     *
+     * File descriptor monitoring implementations that cannot poll fd readiness
+     * from userspace should use aio_poll_disabled() here.  This ensures that
+     * file descriptors are not starved by handlers that frequently make
+     * progress via userspace polling.
+     *
+     * Returns: true if ->wait() should be called, false otherwise.
+     */
+    bool (*need_wait)(AioContext *ctx);
+} FDMonOps;
+
 /*
  * Each aio_bh_poll() call carves off a slice of the BH list, so that newly
  * scheduled BHs are not processed until the next aio_bh_poll() call.  All
@@ -65,6 +118,8 @@ struct BHListSlice {
     QSIMPLEQ_ENTRY(BHListSlice) next;
 };
 
+typedef QSLIST_HEAD(, AioHandler) AioHandlerSList;
+
 struct AioContext {
     GSource source;
 
@@ -150,6 +205,10 @@ struct AioContext {
      * locking.
      */
     struct LuringState *linux_io_uring;
+
+    /* State for file descriptor monitoring using Linux io_uring */
+    struct io_uring fdmon_io_uring;
+    AioHandlerSList submit_list;
 #endif
 
     /* TimerLists for calling timers - one per clock type.  Has its own
@@ -168,13 +227,21 @@ struct AioContext {
     int64_t poll_grow;      /* polling time growth factor */
     int64_t poll_shrink;    /* polling time shrink factor */
 
+    /*
+     * List of handlers participating in userspace polling.  Protected by
+     * ctx->list_lock.  Iterated and modified mostly by the event loop thread
+     * from aio_poll() with ctx->list_lock incremented.  aio_set_fd_handler()
+     * only touches the list to delete nodes if ctx->list_lock's count is zero.
+     */
+    AioHandlerList poll_aio_handlers;
+
     /* Are we in polling mode or monitoring file descriptors? */
     bool poll_started;
 
     /* epoll(7) state used when built with CONFIG_EPOLL */
     int epollfd;
-    bool epoll_enabled;
+
-    bool epoll_available;
+    const FDMonOps *fdmon_ops;
 };
 
 /**

include/qemu/queue.h

@@ -142,6 +142,8 @@ struct {                                                                \
                 (elm)->field.le_next->field.le_prev =                   \
                     (elm)->field.le_prev;                               \
         *(elm)->field.le_prev = (elm)->field.le_next;                   \
+        (elm)->field.le_next = NULL;                                    \
+        (elm)->field.le_prev = NULL;                                    \
 } while (/*CONSTCOND*/0)
 
 /*
@@ -225,12 +227,15 @@ struct {                                                                \
 } while (/*CONSTCOND*/0)
 
 #define QSLIST_REMOVE_HEAD(head, field) do {                             \
-        (head)->slh_first = (head)->slh_first->field.sle_next;          \
+        typeof((head)->slh_first) elm = (head)->slh_first;               \
+        (head)->slh_first = elm->field.sle_next;                         \
+        elm->field.sle_next = NULL;                                      \
 } while (/*CONSTCOND*/0)
 
 #define QSLIST_REMOVE_AFTER(slistelm, field) do {                       \
-        (slistelm)->field.sle_next =                                    \
+        typeof(slistelm) next = (slistelm)->field.sle_next;             \
-            QSLIST_NEXT(QSLIST_NEXT((slistelm), field), field);         \
+        (slistelm)->field.sle_next = next->field.sle_next;              \
+        next->field.sle_next = NULL;                                    \
 } while (/*CONSTCOND*/0)
 
 #define QSLIST_REMOVE(head, elm, type, field) do {                      \
@@ -241,6 +246,7 @@ struct {                                                                \
         while (curelm->field.sle_next != (elm))                         \
             curelm = curelm->field.sle_next;                            \
         curelm->field.sle_next = curelm->field.sle_next->field.sle_next; \
+        (elm)->field.sle_next = NULL;                                   \
     }                                                                   \
 } while (/*CONSTCOND*/0)
 
@@ -304,8 +310,10 @@ struct {                                                                \
 } while (/*CONSTCOND*/0)
 
 #define QSIMPLEQ_REMOVE_HEAD(head, field) do {                          \
-    if (((head)->sqh_first = (head)->sqh_first->field.sqe_next) == NULL)\
+    typeof((head)->sqh_first) elm = (head)->sqh_first;                  \
+    if (((head)->sqh_first = elm->field.sqe_next) == NULL)              \
         (head)->sqh_last = &(head)->sqh_first;                          \
+    elm->field.sqe_next = NULL;                                         \
 } while (/*CONSTCOND*/0)
 
 #define QSIMPLEQ_SPLIT_AFTER(head, elm, field, removed) do {            \
@@ -329,6 +337,7 @@ struct {                                                                \
         if ((curelm->field.sqe_next =                                   \
             curelm->field.sqe_next->field.sqe_next) == NULL)            \
                 (head)->sqh_last = &(curelm)->field.sqe_next;           \
+        (elm)->field.sqe_next = NULL;                                   \
     }                                                                   \
 } while (/*CONSTCOND*/0)
 
@@ -446,6 +455,8 @@ union {                                                                 \
             (head)->tqh_circ.tql_prev = (elm)->field.tqe_circ.tql_prev; \
         (elm)->field.tqe_circ.tql_prev->tql_next = (elm)->field.tqe_next; \
         (elm)->field.tqe_circ.tql_prev = NULL;                          \
+        (elm)->field.tqe_circ.tql_next = NULL;                          \
+        (elm)->field.tqe_next = NULL;                                   \
 } while (/*CONSTCOND*/0)
 
 /* remove @left, @right and all elements in between from @head */

util/Makefile.objs

@@ -5,6 +5,9 @@ util-obj-y += aiocb.o async.o aio-wait.o thread-pool.o qemu-timer.o
 util-obj-y += main-loop.o
 util-obj-$(call lnot,$(CONFIG_ATOMIC64)) += atomic64.o
 util-obj-$(CONFIG_POSIX) += aio-posix.o
+util-obj-$(CONFIG_POSIX) += fdmon-poll.o
+util-obj-$(CONFIG_EPOLL_CREATE1) += fdmon-epoll.o
+util-obj-$(CONFIG_LINUX_IO_URING) += fdmon-io_uring.o
 util-obj-$(CONFIG_POSIX) += compatfd.o
 util-obj-$(CONFIG_POSIX) += event_notifier-posix.o
 util-obj-$(CONFIG_POSIX) += mmap-alloc.o

util/aio-posix.c

@@ -20,191 +20,25 @@
 #include "qemu/sockets.h"
 #include "qemu/cutils.h"
 #include "trace.h"
-#ifdef CONFIG_EPOLL_CREATE1
+#include "aio-posix.h"
-#include <sys/epoll.h>
-#endif
 
-struct AioHandler
+/* Stop userspace polling on a handler if it isn't active for some time */
+#define POLL_IDLE_INTERVAL_NS (7 * NANOSECONDS_PER_SECOND)
+
+bool aio_poll_disabled(AioContext *ctx)
 {
-    GPollFD pfd;
+    return atomic_read(&ctx->poll_disable_cnt);
-    IOHandler *io_read;
+}
-    IOHandler *io_write;
-    AioPollFn *io_poll;
-    IOHandler *io_poll_begin;
-    IOHandler *io_poll_end;
-    void *opaque;
-    bool is_external;
-    QLIST_ENTRY(AioHandler) node;
-    QLIST_ENTRY(AioHandler) node_ready; /* only used during aio_poll() */
-    QLIST_ENTRY(AioHandler) node_deleted;
-};
 
-/* Add a handler to a ready list */
+void aio_add_ready_handler(AioHandlerList *ready_list,
-static void add_ready_handler(AioHandlerList *ready_list,
+                           AioHandler *node,
-                              AioHandler *node,
+                           int revents)
-                              int revents)
 {
     QLIST_SAFE_REMOVE(node, node_ready); /* remove from nested parent's list */
     node->pfd.revents = revents;
     QLIST_INSERT_HEAD(ready_list, node, node_ready);
 }
 
-#ifdef CONFIG_EPOLL_CREATE1
-
-/* The fd number threshold to switch to epoll */
-#define EPOLL_ENABLE_THRESHOLD 64
-
-static void aio_epoll_disable(AioContext *ctx)
-{
-    ctx->epoll_enabled = false;
-    if (!ctx->epoll_available) {
-        return;
-    }
-    ctx->epoll_available = false;
-    close(ctx->epollfd);
-}
-
-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 bool aio_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->epoll_enabled = true;
-    return true;
-}
-
-static void aio_epoll_update(AioContext *ctx, AioHandler *node, bool is_new)
-{
-    struct epoll_event event;
-    int r;
-    int ctl;
-
-    if (!ctx->epoll_enabled) {
-        return;
-    }
-    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) {
-        aio_epoll_disable(ctx);
-    }
-}
-
-static int aio_epoll(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];
-
-    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;
-            add_ready_handler(ready_list, node, revents);
-        }
-    }
-out:
-    return ret;
-}
-
-static bool aio_epoll_enabled(AioContext *ctx)
-{
-    /* Fall back to ppoll when external clients are disabled. */
-    return !aio_external_disabled(ctx) && ctx->epoll_enabled;
-}
-
-static bool aio_epoll_check_poll(AioContext *ctx, GPollFD *pfds,
-                                 unsigned npfd, int64_t timeout)
-{
-    if (!ctx->epoll_available) {
-        return false;
-    }
-    if (aio_epoll_enabled(ctx)) {
-        return true;
-    }
-    if (npfd >= EPOLL_ENABLE_THRESHOLD) {
-        if (aio_epoll_try_enable(ctx)) {
-            return true;
-        } else {
-            aio_epoll_disable(ctx);
-        }
-    }
-    return false;
-}
-
-#else
-
-static void aio_epoll_update(AioContext *ctx, AioHandler *node, bool is_new)
-{
-}
-
-static int aio_epoll(AioContext *ctx, AioHandlerList *ready_list,
-                     int64_t timeout)
-{
-    assert(false);
-}
-
-static bool aio_epoll_enabled(AioContext *ctx)
-{
-    return false;
-}
-
-static bool aio_epoll_check_poll(AioContext *ctx, GPollFD *pfds,
-                          unsigned npfd, int64_t timeout)
-{
-    return false;
-}
-
-#endif
-
 static AioHandler *find_aio_handler(AioContext *ctx, int fd)
 {
     AioHandler *node;
@@ -231,16 +65,23 @@ static bool aio_remove_fd_handler(AioContext *ctx, AioHandler *node)
         g_source_remove_poll(&ctx->source, &node->pfd);
     }
 
+    node->pfd.revents = 0;
+
+    /* If the fd monitor has already marked it deleted, leave it alone */
+    if (QLIST_IS_INSERTED(node, node_deleted)) {
+        return false;
+    }
+
     /* If a read is in progress, just mark the node as deleted */
     if (qemu_lockcnt_count(&ctx->list_lock)) {
         QLIST_INSERT_HEAD_RCU(&ctx->deleted_aio_handlers, node, node_deleted);
-        node->pfd.revents = 0;
         return false;
     }
     /* Otherwise, delete it for real.  We can't just mark it as
      * deleted because deleted nodes are only cleaned up while
      * no one is walking the handlers list.
      */
+    QLIST_SAFE_REMOVE(node, node_poll);
     QLIST_REMOVE(node, node);
     return true;
 }
@@ -300,9 +141,6 @@ void aio_set_fd_handler(AioContext *ctx,
 
         QLIST_INSERT_HEAD_RCU(&ctx->aio_handlers, new_node, node);
     }
-    if (node) {
-        deleted = aio_remove_fd_handler(ctx, node);
-    }
 
     /* No need to order poll_disable_cnt writes against other updates;
      * the counter is only used to avoid wasting time and latency on
@@ -313,11 +151,9 @@ void aio_set_fd_handler(AioContext *ctx,
     atomic_set(&ctx->poll_disable_cnt,
                atomic_read(&ctx->poll_disable_cnt) + poll_disable_change);
 
-    if (new_node) {
+    ctx->fdmon_ops->update(ctx, node, new_node);
-        aio_epoll_update(ctx, new_node, is_new);
+    if (node) {
-    } else if (node) {
+        deleted = aio_remove_fd_handler(ctx, node);
-        /* Unregister deleted fd_handler */
-        aio_epoll_update(ctx, node, false);
     }
     qemu_lockcnt_unlock(&ctx->list_lock);
     aio_notify(ctx);
@@ -361,18 +197,19 @@ void aio_set_event_notifier_poll(AioContext *ctx,
                     (IOHandler *)io_poll_end);
 }
 
-static void poll_set_started(AioContext *ctx, bool started)
+static bool poll_set_started(AioContext *ctx, bool started)
 {
     AioHandler *node;
+    bool progress = false;
 
     if (started == ctx->poll_started) {
-        return;
+        return false;
     }
 
     ctx->poll_started = started;
 
     qemu_lockcnt_inc(&ctx->list_lock);
-    QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
+    QLIST_FOREACH(node, &ctx->poll_aio_handlers, node_poll) {
         IOHandler *fn;
 
         if (QLIST_IS_INSERTED(node, node_deleted)) {
@@ -388,8 +225,15 @@ static void poll_set_started(AioContext *ctx, bool started)
         if (fn) {
             fn(node->opaque);
         }
+
+        /* Poll one last time in case ->io_poll_end() raced with the event */
+        if (!started) {
+            progress = node->io_poll(node->opaque) || progress;
+        }
     }
     qemu_lockcnt_dec(&ctx->list_lock);
+
+    return progress;
 }
 
 
@@ -446,6 +290,7 @@ static void aio_free_deleted_handlers(AioContext *ctx)
     while ((node = QLIST_FIRST_RCU(&ctx->deleted_aio_handlers))) {
         QLIST_REMOVE(node, node);
         QLIST_REMOVE(node, node_deleted);
+        QLIST_SAFE_REMOVE(node, node_poll);
         g_free(node);
     }
 
@@ -460,6 +305,22 @@ static bool aio_dispatch_handler(AioContext *ctx, AioHandler *node)
     revents = node->pfd.revents & node->pfd.events;
     node->pfd.revents = 0;
 
+    /*
+     * Start polling AioHandlers when they become ready because activity is
+     * likely to continue.  Note that starvation is theoretically possible when
+     * fdmon_supports_polling(), but only until the fd fires for the first
+     * time.
+     */
+    if (!QLIST_IS_INSERTED(node, node_deleted) &&
+        !QLIST_IS_INSERTED(node, node_poll) &&
+        node->io_poll) {
+        trace_poll_add(ctx, node, node->pfd.fd, revents);
+        if (ctx->poll_started && node->io_poll_begin) {
+            node->io_poll_begin(node->opaque);
+        }
+        QLIST_INSERT_HEAD(&ctx->poll_aio_handlers, node, node_poll);
+    }
+
     if (!QLIST_IS_INSERTED(node, node_deleted) &&
         (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) &&
         aio_node_check(ctx, node->is_external) &&
@@ -493,7 +354,7 @@ static bool aio_dispatch_ready_handlers(AioContext *ctx,
     AioHandler *node;
 
     while ((node = QLIST_FIRST(ready_list))) {
-        QLIST_SAFE_REMOVE(node, node_ready);
+        QLIST_REMOVE(node, node_ready);
         progress = aio_dispatch_handler(ctx, node) || progress;
     }
 
@@ -524,71 +385,19 @@ void aio_dispatch(AioContext *ctx)
     timerlistgroup_run_timers(&ctx->tlg);
 }
 
-/* These thread-local variables are used only in a small part of aio_poll
+static bool run_poll_handlers_once(AioContext *ctx,
- * around the call to the poll() system call.  In particular they are not
+                                   int64_t now,
- * used while aio_poll is performing callbacks, which makes it much easier
+                                   int64_t *timeout)
- * 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 bool run_poll_handlers_once(AioContext *ctx, int64_t *timeout)
 {
     bool progress = false;
     AioHandler *node;
+    AioHandler *tmp;
 
-    /*
+    QLIST_FOREACH_SAFE(node, &ctx->poll_aio_handlers, node_poll, tmp) {
-     * Optimization: ->io_poll() handlers often contain RCU read critical
+        if (aio_node_check(ctx, node->is_external) &&
-     * sections and we therefore see many rcu_read_lock() -> rcu_read_unlock()
-     * -> rcu_read_lock() -> ... sequences with expensive memory
-     * synchronization primitives.  Make the entire polling loop an RCU
-     * critical section because nested rcu_read_lock()/rcu_read_unlock() calls
-     * are cheap.
-     */
-    RCU_READ_LOCK_GUARD();
-
-    QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
-        if (!QLIST_IS_INSERTED(node, node_deleted) && node->io_poll &&
-            aio_node_check(ctx, node->is_external) &&
             node->io_poll(node->opaque)) {
+            node->poll_idle_timeout = now + POLL_IDLE_INTERVAL_NS;
+
             /*
              * Polling was successful, exit try_poll_mode immediately
              * to adjust the next polling time.
@@ -605,6 +414,50 @@ static bool run_poll_handlers_once(AioContext *ctx, int64_t *timeout)
     return progress;
 }
 
+static bool fdmon_supports_polling(AioContext *ctx)
+{
+    return ctx->fdmon_ops->need_wait != aio_poll_disabled;
+}
+
+static bool remove_idle_poll_handlers(AioContext *ctx, int64_t now)
+{
+    AioHandler *node;
+    AioHandler *tmp;
+    bool progress = false;
+
+    /*
+     * File descriptor monitoring implementations without userspace polling
+     * support suffer from starvation when a subset of handlers is polled
+     * because fds will not be processed in a timely fashion.  Don't remove
+     * idle poll handlers.
+     */
+    if (!fdmon_supports_polling(ctx)) {
+        return false;
+    }
+
+    QLIST_FOREACH_SAFE(node, &ctx->poll_aio_handlers, node_poll, tmp) {
+        if (node->poll_idle_timeout == 0LL) {
+            node->poll_idle_timeout = now + POLL_IDLE_INTERVAL_NS;
+        } else if (now >= node->poll_idle_timeout) {
+            trace_poll_remove(ctx, node, node->pfd.fd);
+            node->poll_idle_timeout = 0LL;
+            QLIST_SAFE_REMOVE(node, node_poll);
+            if (ctx->poll_started && node->io_poll_end) {
+                node->io_poll_end(node->opaque);
+
+                /*
+                 * Final poll in case ->io_poll_end() races with an event.
+                 * Nevermind about re-adding the handler in the rare case where
+                 * this causes progress.
+                 */
+                progress = node->io_poll(node->opaque) || progress;
+            }
+        }
+    }
+
+    return progress;
+}
+
 /* run_poll_handlers:
  * @ctx: the AioContext
  * @max_ns: maximum time to poll for, in nanoseconds
@@ -628,13 +481,28 @@ static bool run_poll_handlers(AioContext *ctx, int64_t max_ns, int64_t *timeout)
 
     trace_run_poll_handlers_begin(ctx, max_ns, *timeout);
 
+    /*
+     * Optimization: ->io_poll() handlers often contain RCU read critical
+     * sections and we therefore see many rcu_read_lock() -> rcu_read_unlock()
+     * -> rcu_read_lock() -> ... sequences with expensive memory
+     * synchronization primitives.  Make the entire polling loop an RCU
+     * critical section because nested rcu_read_lock()/rcu_read_unlock() calls
+     * are cheap.
+     */
+    RCU_READ_LOCK_GUARD();
+
     start_time = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
     do {
-        progress = run_poll_handlers_once(ctx, timeout);
+        progress = run_poll_handlers_once(ctx, start_time, timeout);
         elapsed_time = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - start_time;
         max_ns = qemu_soonest_timeout(*timeout, max_ns);
         assert(!(max_ns && progress));
-    } while (elapsed_time < max_ns && !atomic_read(&ctx->poll_disable_cnt));
+    } while (elapsed_time < max_ns && !ctx->fdmon_ops->need_wait(ctx));
+
+    if (remove_idle_poll_handlers(ctx, start_time + elapsed_time)) {
+        *timeout = 0;
+        progress = true;
+    }
 
     /* If time has passed with no successful polling, adjust *timeout to
      * keep the same ending time.
@@ -660,9 +528,14 @@ static bool run_poll_handlers(AioContext *ctx, int64_t max_ns, int64_t *timeout)
  */
 static bool try_poll_mode(AioContext *ctx, int64_t *timeout)
 {
-    int64_t max_ns = qemu_soonest_timeout(*timeout, ctx->poll_ns);
+    int64_t max_ns;
 
-    if (max_ns && !atomic_read(&ctx->poll_disable_cnt)) {
+    if (QLIST_EMPTY_RCU(&ctx->poll_aio_handlers)) {
+        return false;
+    }
+
+    max_ns = qemu_soonest_timeout(*timeout, ctx->poll_ns);
+    if (max_ns && !ctx->fdmon_ops->need_wait(ctx)) {
         poll_set_started(ctx, true);
 
         if (run_poll_handlers(ctx, max_ns, timeout)) {
@@ -670,19 +543,17 @@ static bool try_poll_mode(AioContext *ctx, int64_t *timeout)
         }
     }
 
-    poll_set_started(ctx, false);
+    if (poll_set_started(ctx, false)) {
+        *timeout = 0;
+        return true;
+    }
 
-    /* Even if we don't run busy polling, try polling once in case it can make
+    return false;
-     * progress and the caller will be able to avoid ppoll(2)/epoll_wait(2).
-     */
-    return run_poll_handlers_once(ctx, timeout);
 }
 
 bool aio_poll(AioContext *ctx, bool blocking)
 {
     AioHandlerList ready_list = QLIST_HEAD_INITIALIZER(ready_list);
-    AioHandler *node;
-    int i;
     int ret = 0;
     bool progress;
     int64_t timeout;
@@ -714,27 +585,8 @@ bool aio_poll(AioContext *ctx, bool blocking)
     /* If polling is allowed, non-blocking aio_poll does not need the
      * system call---a single round of run_poll_handlers_once suffices.
      */
-    if (timeout || atomic_read(&ctx->poll_disable_cnt)) {
+    if (timeout || ctx->fdmon_ops->need_wait(ctx)) {
-        assert(npfd == 0);
+        ret = ctx->fdmon_ops->wait(ctx, &ready_list, timeout);
-
-        /* fill pollfds */
-
-        if (!aio_epoll_enabled(ctx)) {
-            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);
-                }
-            }
-        }
-
-        /* wait until next event */
-        if (aio_epoll_check_poll(ctx, pollfds, npfd, timeout)) {
-            npfd = 0; /* pollfds[] is not being used */
-            ret = aio_epoll(ctx, &ready_list, timeout);
-        } else  {
-            ret = qemu_poll_ns(pollfds, npfd, timeout);
-        }
     }
 
     if (blocking) {
@@ -783,19 +635,6 @@ bool aio_poll(AioContext *ctx, bool blocking)
         }
     }
 
-    /* if we have any readable fds, dispatch event */
-    if (ret > 0) {
-        for (i = 0; i < npfd; i++) {
-            int revents = pollfds[i].revents;
-
-            if (revents) {
-                add_ready_handler(&ready_list, nodes[i], revents);
-            }
-        }
-    }
-
-    npfd = 0;
-
     progress |= aio_bh_poll(ctx);
 
     if (ret > 0) {
@@ -813,23 +652,21 @@ bool aio_poll(AioContext *ctx, bool blocking)
 
 void aio_context_setup(AioContext *ctx)
 {
-#ifdef CONFIG_EPOLL_CREATE1
+    ctx->fdmon_ops = &fdmon_poll_ops;
-    assert(!ctx->epollfd);
+    ctx->epollfd = -1;
-    ctx->epollfd = epoll_create1(EPOLL_CLOEXEC);
+
-    if (ctx->epollfd == -1) {
+    /* Use the fastest fd monitoring implementation if available */
-        fprintf(stderr, "Failed to create epoll instance: %s", strerror(errno));
+    if (fdmon_io_uring_setup(ctx)) {
-        ctx->epoll_available = false;
+        return;
-    } else {
-        ctx->epoll_available = true;
     }
-#endif
+
+    fdmon_epoll_setup(ctx);
 }
 
 void aio_context_destroy(AioContext *ctx)
 {
-#ifdef CONFIG_EPOLL_CREATE1
+    fdmon_io_uring_destroy(ctx);
-    aio_epoll_disable(ctx);
+    fdmon_epoll_disable(ctx);
-#endif
 }
 
 void aio_context_set_poll_params(AioContext *ctx, int64_t max_ns,

util/aio-posix.h

@@ -0,0 +1,81 @@
+/*
+ * AioContext POSIX event loop implementation internal APIs
+ *
+ * Copyright IBM, Corp. 2008
+ * Copyright Red Hat, Inc. 2020
+ *
+ * Authors:
+ *  Anthony Liguori   <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
+ */
+
+#ifndef AIO_POSIX_H
+#define AIO_POSIX_H
+
+#include "block/aio.h"
+
+struct AioHandler {
+    GPollFD pfd;
+    IOHandler *io_read;
+    IOHandler *io_write;
+    AioPollFn *io_poll;
+    IOHandler *io_poll_begin;
+    IOHandler *io_poll_end;
+    void *opaque;
+    QLIST_ENTRY(AioHandler) node;
+    QLIST_ENTRY(AioHandler) node_ready; /* only used during aio_poll() */
+    QLIST_ENTRY(AioHandler) node_deleted;
+    QLIST_ENTRY(AioHandler) node_poll;
+#ifdef CONFIG_LINUX_IO_URING
+    QSLIST_ENTRY(AioHandler) node_submitted;
+    unsigned flags; /* see fdmon-io_uring.c */
+#endif
+    int64_t poll_idle_timeout; /* when to stop userspace polling */
+    bool is_external;
+};
+
+/* Add a handler to a ready list */
+void aio_add_ready_handler(AioHandlerList *ready_list, AioHandler *node,
+                           int revents);
+
+extern const FDMonOps fdmon_poll_ops;
+
+#ifdef CONFIG_EPOLL_CREATE1
+bool fdmon_epoll_try_upgrade(AioContext *ctx, unsigned npfd);
+void fdmon_epoll_setup(AioContext *ctx);
+void fdmon_epoll_disable(AioContext *ctx);
+#else
+static inline bool fdmon_epoll_try_upgrade(AioContext *ctx, unsigned npfd)
+{
+    return false;
+}
+
+static inline void fdmon_epoll_setup(AioContext *ctx)
+{
+}
+
+static inline void fdmon_epoll_disable(AioContext *ctx)
+{
+}
+#endif /* !CONFIG_EPOLL_CREATE1 */
+
+#ifdef CONFIG_LINUX_IO_URING
+bool fdmon_io_uring_setup(AioContext *ctx);
+void fdmon_io_uring_destroy(AioContext *ctx);
+#else
+static inline bool fdmon_io_uring_setup(AioContext *ctx)
+{
+    return false;
+}
+
+static inline void fdmon_io_uring_destroy(AioContext *ctx)
+{
+}
+#endif /* !CONFIG_LINUX_IO_URING */
+
+#endif /* AIO_POSIX_H */

util/fdmon-epoll.c

@@ -0,0 +1,155 @@
+/* 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 *old_node,
+                               AioHandler *new_node)
+{
+    struct epoll_event event = {
+        .data.ptr = new_node,
+        .events = new_node ? epoll_events_from_pfd(new_node->pfd.events) : 0,
+    };
+    int r;
+
+    if (!new_node) {
+        r = epoll_ctl(ctx->epollfd, EPOLL_CTL_DEL, old_node->pfd.fd, &event);
+    } else if (!old_node) {
+        r = epoll_ctl(ctx->epollfd, EPOLL_CTL_ADD, new_node->pfd.fd, &event);
+    } else {
+        r = epoll_ctl(ctx->epollfd, EPOLL_CTL_MOD, new_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,
+    .need_wait = aio_poll_disabled,
+};
+
+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));
+    }
+}

util/fdmon-io_uring.c

@@ -0,0 +1,332 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Linux io_uring file descriptor monitoring
+ *
+ * The Linux io_uring API supports file descriptor monitoring with a few
+ * advantages over existing APIs like poll(2) and epoll(7):
+ *
+ * 1. Userspace polling of events is possible because the completion queue (cq
+ *    ring) is shared between the kernel and userspace.  This allows
+ *    applications that rely on userspace polling to also monitor file
+ *    descriptors in the same userspace polling loop.
+ *
+ * 2. Submission and completion is batched and done together in a single system
+ *    call.  This minimizes the number of system calls.
+ *
+ * 3. File descriptor monitoring is O(1) like epoll(7) so it scales better than
+ *    poll(2).
+ *
+ * 4. Nanosecond timeouts are supported so it requires fewer syscalls than
+ *    epoll(7).
+ *
+ * This code only monitors file descriptors and does not do asynchronous disk
+ * I/O.  Implementing disk I/O efficiently has other requirements and should
+ * use a separate io_uring so it does not make sense to unify the code.
+ *
+ * File descriptor monitoring is implemented using the following operations:
+ *
+ * 1. IORING_OP_POLL_ADD - adds a file descriptor to be monitored.
+ * 2. IORING_OP_POLL_REMOVE - removes a file descriptor being monitored.  When
+ *    the poll mask changes for a file descriptor it is first removed and then
+ *    re-added with the new poll mask, so this operation is also used as part
+ *    of modifying an existing monitored file descriptor.
+ * 3. IORING_OP_TIMEOUT - added every time a blocking syscall is made to wait
+ *    for events.  This operation self-cancels if another event completes
+ *    before the timeout.
+ *
+ * io_uring calls the submission queue the "sq ring" and the completion queue
+ * the "cq ring".  Ring entries are called "sqe" and "cqe", respectively.
+ *
+ * The code is structured so that sq/cq rings are only modified within
+ * fdmon_io_uring_wait().  Changes to AioHandlers are made by enqueuing them on
+ * ctx->submit_list so that fdmon_io_uring_wait() can submit IORING_OP_POLL_ADD
+ * and/or IORING_OP_POLL_REMOVE sqes for them.
+ */
+
+#include "qemu/osdep.h"
+#include <poll.h>
+#include "qemu/rcu_queue.h"
+#include "aio-posix.h"
+
+enum {
+    FDMON_IO_URING_ENTRIES  = 128, /* sq/cq ring size */
+
+    /* AioHandler::flags */
+    FDMON_IO_URING_PENDING  = (1 << 0),
+    FDMON_IO_URING_ADD      = (1 << 1),
+    FDMON_IO_URING_REMOVE   = (1 << 2),
+};
+
+static inline int poll_events_from_pfd(int pfd_events)
+{
+    return (pfd_events & G_IO_IN ? POLLIN : 0) |
+           (pfd_events & G_IO_OUT ? POLLOUT : 0) |
+           (pfd_events & G_IO_HUP ? POLLHUP : 0) |
+           (pfd_events & G_IO_ERR ? POLLERR : 0);
+}
+
+static inline int pfd_events_from_poll(int poll_events)
+{
+    return (poll_events & POLLIN ? G_IO_IN : 0) |
+           (poll_events & POLLOUT ? G_IO_OUT : 0) |
+           (poll_events & POLLHUP ? G_IO_HUP : 0) |
+           (poll_events & POLLERR ? G_IO_ERR : 0);
+}
+
+/*
+ * Returns an sqe for submitting a request.  Only be called within
+ * fdmon_io_uring_wait().
+ */
+static struct io_uring_sqe *get_sqe(AioContext *ctx)
+{
+    struct io_uring *ring = &ctx->fdmon_io_uring;
+    struct io_uring_sqe *sqe = io_uring_get_sqe(ring);
+    int ret;
+
+    if (likely(sqe)) {
+        return sqe;
+    }
+
+    /* No free sqes left, submit pending sqes first */
+    ret = io_uring_submit(ring);
+    assert(ret > 1);
+    sqe = io_uring_get_sqe(ring);
+    assert(sqe);
+    return sqe;
+}
+
+/* Atomically enqueue an AioHandler for sq ring submission */
+static void enqueue(AioHandlerSList *head, AioHandler *node, unsigned flags)
+{
+    unsigned old_flags;
+
+    old_flags = atomic_fetch_or(&node->flags, FDMON_IO_URING_PENDING | flags);
+    if (!(old_flags & FDMON_IO_URING_PENDING)) {
+        QSLIST_INSERT_HEAD_ATOMIC(head, node, node_submitted);
+    }
+}
+
+/* Dequeue an AioHandler for sq ring submission.  Called by fill_sq_ring(). */
+static AioHandler *dequeue(AioHandlerSList *head, unsigned *flags)
+{
+    AioHandler *node = QSLIST_FIRST(head);
+
+    if (!node) {
+        return NULL;
+    }
+
+    /* Doesn't need to be atomic since fill_sq_ring() moves the list */
+    QSLIST_REMOVE_HEAD(head, node_submitted);
+
+    /*
+     * Don't clear FDMON_IO_URING_REMOVE.  It's sticky so it can serve two
+     * purposes: telling fill_sq_ring() to submit IORING_OP_POLL_REMOVE and
+     * telling process_cqe() to delete the AioHandler when its
+     * IORING_OP_POLL_ADD completes.
+     */
+    *flags = atomic_fetch_and(&node->flags, ~(FDMON_IO_URING_PENDING |
+                                              FDMON_IO_URING_ADD));
+    return node;
+}
+
+static void fdmon_io_uring_update(AioContext *ctx,
+                                  AioHandler *old_node,
+                                  AioHandler *new_node)
+{
+    if (new_node) {
+        enqueue(&ctx->submit_list, new_node, FDMON_IO_URING_ADD);
+    }
+
+    if (old_node) {
+        /*
+         * Deletion is tricky because IORING_OP_POLL_ADD and
+         * IORING_OP_POLL_REMOVE are async.  We need to wait for the original
+         * IORING_OP_POLL_ADD to complete before this handler can be freed
+         * safely.
+         *
+         * It's possible that the file descriptor becomes ready and the
+         * IORING_OP_POLL_ADD cqe is enqueued before IORING_OP_POLL_REMOVE is
+         * submitted, too.
+         *
+         * Mark this handler deleted right now but don't place it on
+         * ctx->deleted_aio_handlers yet.  Instead, manually fudge the list
+         * entry to make QLIST_IS_INSERTED() think this handler has been
+         * inserted and other code recognizes this AioHandler as deleted.
+         *
+         * Once the original IORING_OP_POLL_ADD completes we enqueue the
+         * handler on the real ctx->deleted_aio_handlers list to be freed.
+         */
+        assert(!QLIST_IS_INSERTED(old_node, node_deleted));
+        old_node->node_deleted.le_prev = &old_node->node_deleted.le_next;
+
+        enqueue(&ctx->submit_list, old_node, FDMON_IO_URING_REMOVE);
+    }
+}
+
+static void add_poll_add_sqe(AioContext *ctx, AioHandler *node)
+{
+    struct io_uring_sqe *sqe = get_sqe(ctx);
+    int events = poll_events_from_pfd(node->pfd.events);
+
+    io_uring_prep_poll_add(sqe, node->pfd.fd, events);
+    io_uring_sqe_set_data(sqe, node);
+}
+
+static void add_poll_remove_sqe(AioContext *ctx, AioHandler *node)
+{
+    struct io_uring_sqe *sqe = get_sqe(ctx);
+
+    io_uring_prep_poll_remove(sqe, node);
+}
+
+/* Add a timeout that self-cancels when another cqe becomes ready */
+static void add_timeout_sqe(AioContext *ctx, int64_t ns)
+{
+    struct io_uring_sqe *sqe;
+    struct __kernel_timespec ts = {
+        .tv_sec = ns / NANOSECONDS_PER_SECOND,
+        .tv_nsec = ns % NANOSECONDS_PER_SECOND,
+    };
+
+    sqe = get_sqe(ctx);
+    io_uring_prep_timeout(sqe, &ts, 1, 0);
+}
+
+/* Add sqes from ctx->submit_list for submission */
+static void fill_sq_ring(AioContext *ctx)
+{
+    AioHandlerSList submit_list;
+    AioHandler *node;
+    unsigned flags;
+
+    QSLIST_MOVE_ATOMIC(&submit_list, &ctx->submit_list);
+
+    while ((node = dequeue(&submit_list, &flags))) {
+        /* Order matters, just in case both flags were set */
+        if (flags & FDMON_IO_URING_ADD) {
+            add_poll_add_sqe(ctx, node);
+        }
+        if (flags & FDMON_IO_URING_REMOVE) {
+            add_poll_remove_sqe(ctx, node);
+        }
+    }
+}
+
+/* Returns true if a handler became ready */
+static bool process_cqe(AioContext *ctx,
+                        AioHandlerList *ready_list,
+                        struct io_uring_cqe *cqe)
+{
+    AioHandler *node = io_uring_cqe_get_data(cqe);
+    unsigned flags;
+
+    /* poll_timeout and poll_remove have a zero user_data field */
+    if (!node) {
+        return false;
+    }
+
+    /*
+     * Deletion can only happen when IORING_OP_POLL_ADD completes.  If we race
+     * with enqueue() here then we can safely clear the FDMON_IO_URING_REMOVE
+     * bit before IORING_OP_POLL_REMOVE is submitted.
+     */
+    flags = atomic_fetch_and(&node->flags, ~FDMON_IO_URING_REMOVE);
+    if (flags & FDMON_IO_URING_REMOVE) {
+        QLIST_INSERT_HEAD_RCU(&ctx->deleted_aio_handlers, node, node_deleted);
+        return false;
+    }
+
+    aio_add_ready_handler(ready_list, node, pfd_events_from_poll(cqe->res));
+
+    /* IORING_OP_POLL_ADD is one-shot so we must re-arm it */
+    add_poll_add_sqe(ctx, node);
+    return true;
+}
+
+static int process_cq_ring(AioContext *ctx, AioHandlerList *ready_list)
+{
+    struct io_uring *ring = &ctx->fdmon_io_uring;
+    struct io_uring_cqe *cqe;
+    unsigned num_cqes = 0;
+    unsigned num_ready = 0;
+    unsigned head;
+
+    io_uring_for_each_cqe(ring, head, cqe) {
+        if (process_cqe(ctx, ready_list, cqe)) {
+            num_ready++;
+        }
+
+        num_cqes++;
+    }
+
+    io_uring_cq_advance(ring, num_cqes);
+    return num_ready;
+}
+
+static int fdmon_io_uring_wait(AioContext *ctx, AioHandlerList *ready_list,
+                               int64_t timeout)
+{
+    unsigned wait_nr = 1; /* block until at least one cqe is ready */
+    int ret;
+
+    /* 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) {
+        wait_nr = 0; /* non-blocking */
+    } else if (timeout > 0) {
+        add_timeout_sqe(ctx, timeout);
+    }
+
+    fill_sq_ring(ctx);
+
+    ret = io_uring_submit_and_wait(&ctx->fdmon_io_uring, wait_nr);
+    assert(ret >= 0);
+
+    return process_cq_ring(ctx, ready_list);
+}
+
+static bool fdmon_io_uring_need_wait(AioContext *ctx)
+{
+    return io_uring_cq_ready(&ctx->fdmon_io_uring);
+}
+
+static const FDMonOps fdmon_io_uring_ops = {
+    .update = fdmon_io_uring_update,
+    .wait = fdmon_io_uring_wait,
+    .need_wait = fdmon_io_uring_need_wait,
+};
+
+bool fdmon_io_uring_setup(AioContext *ctx)
+{
+    int ret;
+
+    ret = io_uring_queue_init(FDMON_IO_URING_ENTRIES, &ctx->fdmon_io_uring, 0);
+    if (ret != 0) {
+        return false;
+    }
+
+    QSLIST_INIT(&ctx->submit_list);
+    ctx->fdmon_ops = &fdmon_io_uring_ops;
+    return true;
+}
+
+void fdmon_io_uring_destroy(AioContext *ctx)
+{
+    if (ctx->fdmon_ops == &fdmon_io_uring_ops) {
+        AioHandler *node;
+
+        io_uring_queue_exit(&ctx->fdmon_io_uring);
+
+        /* No need to submit these anymore, just free them. */
+        while ((node = QSLIST_FIRST_RCU(&ctx->submit_list))) {
+            QSLIST_REMOVE_HEAD_RCU(&ctx->submit_list, node_submitted);
+            QLIST_REMOVE(node, node);
+            g_free(node);
+        }
+
+        ctx->fdmon_ops = &fdmon_poll_ops;
+    }
+}

util/fdmon-poll.c

@@ -0,0 +1,107 @@
+/* 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 *old_node,
+                              AioHandler *new_node)
+{
+    /* Do nothing, AioHandler already contains the state we'll need */
+}
+
+const FDMonOps fdmon_poll_ops = {
+    .update = fdmon_poll_update,
+    .wait = fdmon_poll_wait,
+    .need_wait = aio_poll_disabled,
+};

util/trace-events

@@ -5,6 +5,8 @@ run_poll_handlers_begin(void *ctx, int64_t max_ns, int64_t timeout) "ctx %p max_
 run_poll_handlers_end(void *ctx, bool progress, int64_t timeout) "ctx %p progress %d new timeout %"PRId64
 poll_shrink(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64
 poll_grow(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64
+poll_add(void *ctx, void *node, int fd, unsigned revents) "ctx %p node %p fd %d revents 0x%x"
+poll_remove(void *ctx, void *node, int fd) "ctx %p node %p fd %d"
 
 # async.c
 aio_co_schedule(void *ctx, void *co) "ctx %p co %p"