aio-posix: gracefully handle io_uring_queue_init() failure

io_uring may not be available at runtime due to system policies (e.g.
the io_uring_disabled sysctl) or creation could fail due to file
descriptor resource limits.

Handle failure scenarios as follows:

If another AioContext already has io_uring, then fail AioContext
creation so that the aio_add_sqe() API is available uniformly from all
QEMU threads. Otherwise fall back to epoll(7) if io_uring is
unavailable.

Notes:
- Update the comment about selecting the fastest fdmon implementation.
  At this point it's not about speed anymore, it's about aio_add_sqe()
  API availability.
- Uppercase the error message when converting from error_report() to
  error_setg_errno() for consistency (but there are instances of
  lowercase in the codebase).
- It's easier to move the #ifdefs from aio-posix.h to aio-posix.c.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20251104022933.618123-11-stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

util/aio-posix.c

@@ -16,6 +16,7 @@
 #include "qemu/osdep.h"
 #include "block/block.h"
 #include "block/thread-pool.h"
+#include "qapi/error.h"
 #include "qemu/main-loop.h"
 #include "qemu/lockcnt.h"
 #include "qemu/rcu.h"
@@ -724,10 +725,29 @@ bool aio_context_setup(AioContext *ctx, Error **errp)
     ctx->epollfd = -1;
     ctx->epollfd_tag = NULL;
 
-    /* Use the fastest fd monitoring implementation if available */
-    if (fdmon_io_uring_setup(ctx)) {
-        return true;
+#ifdef CONFIG_LINUX_IO_URING
+    {
+        static bool need_io_uring;
+        Error *local_err = NULL; /* ERRP_GUARD() doesn't handle error_abort */
+
+        /* io_uring takes precedence because it provides aio_add_sqe() support */
+        if (fdmon_io_uring_setup(ctx, &local_err)) {
+            /*
+             * If one AioContext gets io_uring, then all AioContexts need io_uring
+             * so that aio_add_sqe() support is available across all threads.
+             */
+            need_io_uring = true;
+            return true;
+        }
+        if (need_io_uring) {
+            error_propagate(errp, local_err);
+            return false;
+        }
+
+        /* Silently fall back on systems where io_uring is unavailable */
+        error_free(local_err);
     }
+#endif /* CONFIG_LINUX_IO_URING */
 
     fdmon_epoll_setup(ctx);
     return true;
@@ -735,7 +755,9 @@ bool aio_context_setup(AioContext *ctx, Error **errp)
 
 void aio_context_destroy(AioContext *ctx)
 {
+#ifdef CONFIG_LINUX_IO_URING
     fdmon_io_uring_destroy(ctx);
+#endif
 
     qemu_lockcnt_lock(&ctx->list_lock);
     fdmon_epoll_disable(ctx);

util/aio-posix.h

@@ -18,6 +18,7 @@
 #define AIO_POSIX_H
 
 #include "block/aio.h"
+#include "qapi/error.h"
 
 struct AioHandler {
     GPollFD pfd;
@@ -72,17 +73,8 @@ static inline void fdmon_epoll_disable(AioContext *ctx)
 #endif /* !CONFIG_EPOLL_CREATE1 */
 
 #ifdef CONFIG_LINUX_IO_URING
-bool fdmon_io_uring_setup(AioContext *ctx);
+bool fdmon_io_uring_setup(AioContext *ctx, Error **errp);
 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-io_uring.c

@@ -45,6 +45,7 @@
 
 #include "qemu/osdep.h"
 #include <poll.h>
+#include "qapi/error.h"
 #include "qemu/rcu_queue.h"
 #include "aio-posix.h"
 
@@ -375,7 +376,7 @@ static const FDMonOps fdmon_io_uring_ops = {
     .gsource_dispatch = fdmon_io_uring_gsource_dispatch,
 };
 
-bool fdmon_io_uring_setup(AioContext *ctx)
+bool fdmon_io_uring_setup(AioContext *ctx, Error **errp)
 {
     int ret;
 
@@ -383,6 +384,7 @@ bool fdmon_io_uring_setup(AioContext *ctx)
 
     ret = io_uring_queue_init(FDMON_IO_URING_ENTRIES, &ctx->fdmon_io_uring, 0);
     if (ret != 0) {
+        error_setg_errno(errp, -ret, "Failed to initialize io_uring");
         return false;
     }
 
@@ -390,7 +392,6 @@ bool fdmon_io_uring_setup(AioContext *ctx)
     ctx->fdmon_ops = &fdmon_io_uring_ops;
     ctx->io_uring_fd_tag = g_source_add_unix_fd(&ctx->source,
             ctx->fdmon_io_uring.ring_fd, G_IO_IN);
-
     return true;
 }