qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Kevin Wolf <kwolf@redhat.com>
To: qemu-block@nongnu.org
Cc: kwolf@redhat.com, richard.henderson@linaro.org, qemu-devel@nongnu.org
Subject: [PULL v2 10/28] aio-posix: gracefully handle io_uring_queue_init() failure
Date: Tue, 11 Nov 2025 22:32:20 +0100	[thread overview]
Message-ID: <20251111213238.181992-11-kwolf@redhat.com> (raw)
In-Reply-To: <20251111213238.181992-1-kwolf@redhat.com>

From: Stefan Hajnoczi <stefanha@redhat.com>

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.h      | 12 ++----------
 util/aio-posix.c      | 28 +++++++++++++++++++++++++---
 util/fdmon-io_uring.c |  5 +++--
 3 files changed, 30 insertions(+), 15 deletions(-)

diff --git a/util/aio-posix.h b/util/aio-posix.h
index f9994ed79e..dfa1a51c0b 100644
--- a/util/aio-posix.h
+++ b/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 */
diff --git a/util/aio-posix.c b/util/aio-posix.c
index 9806a75c12..c0285a26a3 100644
--- a/util/aio-posix.c
+++ b/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);
diff --git a/util/fdmon-io_uring.c b/util/fdmon-io_uring.c
index 2460ac1556..bcfdddf398 100644
--- a/util/fdmon-io_uring.c
+++ b/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;
 }
 
-- 
2.51.1



  parent reply	other threads:[~2025-11-11 21:37 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-11 21:32 [PULL v2 00/28] Block layer patches Kevin Wolf
2025-11-11 21:32 ` [PULL v2 01/28] aio-posix: fix race between io_uring CQE and AioHandler deletion Kevin Wolf
2025-11-11 21:32 ` [PULL v2 02/28] aio-posix: fix fdmon-io_uring.c timeout stack variable lifetime Kevin Wolf
2025-11-11 21:32 ` [PULL v2 03/28] aio-posix: fix spurious return from ->wait() due to signals Kevin Wolf
2025-11-11 21:32 ` [PULL v2 04/28] aio-posix: keep polling enabled with fdmon-io_uring.c Kevin Wolf
2025-11-11 21:32 ` [PULL v2 05/28] tests/unit: skip test-nested-aio-poll with io_uring Kevin Wolf
2025-11-11 21:32 ` [PULL v2 06/28] aio-posix: integrate fdmon into glib event loop Kevin Wolf
2025-11-11 21:32 ` [PULL v2 07/28] aio: remove aio_context_use_g_source() Kevin Wolf
2025-11-11 21:32 ` [PULL v2 08/28] aio: free AioContext when aio_context_new() fails Kevin Wolf
2025-11-11 21:32 ` [PULL v2 09/28] aio: add errp argument to aio_context_setup() Kevin Wolf
2025-11-11 21:32 ` Kevin Wolf [this message]
2025-11-11 21:32 ` [PULL v2 11/28] aio-posix: unindent fdmon_io_uring_destroy() Kevin Wolf
2025-11-11 21:32 ` [PULL v2 12/28] aio-posix: add fdmon_ops->dispatch() Kevin Wolf
2025-11-11 21:32 ` [PULL v2 13/28] aio-posix: add aio_add_sqe() API for user-defined io_uring requests Kevin Wolf
2025-11-11 21:32 ` [PULL v2 14/28] block/io_uring: use aio_add_sqe() Kevin Wolf
2025-11-11 21:32 ` [PULL v2 15/28] block/io_uring: use non-vectored read/write when possible Kevin Wolf
2025-11-11 21:32 ` [PULL v2 16/28] block: replace TABs with space Kevin Wolf
2025-11-11 21:32 ` [PULL v2 17/28] block: Drop detach_subchain for bdrv_replace_node Kevin Wolf
2025-11-11 21:32 ` [PULL v2 18/28] iotests: Test resizing file node under raw with size/offset Kevin Wolf
2025-11-11 21:32 ` [PULL v2 19/28] qemu-img: Fix amend option parse error handling Kevin Wolf
2025-11-11 21:32 ` [PULL v2 20/28] iotests: Run iotests with sanitizers Kevin Wolf
2025-11-11 21:32 ` [PULL v2 21/28] qcow2: rename update_refcount_discard to queue_discard Kevin Wolf
2025-11-11 21:32 ` [PULL v2 22/28] qcow2: put discards in discard queue when discard-no-unref is enabled Kevin Wolf
2025-11-11 21:32 ` [PULL v2 23/28] tests/qemu-iotests/184: Fix skip message for qemu-img without throttle Kevin Wolf
2025-11-11 21:32 ` [PULL v2 24/28] tests/qemu-iotests: Improve the dry run list to speed up thorough testing Kevin Wolf
2025-11-11 21:32 ` [PULL v2 25/28] tests/qemu-iotest: Add more image formats to the " Kevin Wolf
2025-11-11 21:32 ` [PULL v2 26/28] block: Allow drivers to control protocol prefix at creation Kevin Wolf
2025-11-11 21:32 ` [PULL v2 27/28] qcow2, vmdk: Restrict creation with secondary file using protocol Kevin Wolf
2025-11-11 21:32 ` [PULL v2 28/28] qemu-img rebase: don't exceed IO_BUF_SIZE in one operation Kevin Wolf
2025-11-12 16:40   ` Thomas Huth
2025-11-12 16:42     ` Thomas Huth
2025-11-12 15:08 ` [PULL v2 00/28] Block layer patches Richard Henderson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20251111213238.181992-11-kwolf@redhat.com \
    --to=kwolf@redhat.com \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).