From b474155fdc38f86f516c14ba9a6f934616d589ef Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Wed, 4 Aug 2021 03:27:22 -0400
Subject: [PATCH 1/2] aio-wait: delegate polling of main AioContext if BQL not
 held

RH-Author: Andrew Jones <drjones@redhat.com>
Message-id: <20210729134448.4995-2-drjones@redhat.com>
Patchwork-id: 101935
O-Subject: [RHEL-8.5.0 qemu-kvm PATCH v2 1/2] aio-wait: delegate polling of main AioContext if BQL not held
Bugzilla: 1969848
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Auger Eric <eric.auger@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>

From: Paolo Bonzini <pbonzini@redhat.com>

Any thread that is not a iothread returns NULL for qemu_get_current_aio_context().
As a result, it would also return true for
in_aio_context_home_thread(qemu_get_aio_context()), causing
AIO_WAIT_WHILE to invoke aio_poll() directly.  This is incorrect
if the BQL is not held, because aio_poll() does not expect to
run concurrently from multiple threads, and it can actually
happen when savevm writes to the vmstate file from the
migration thread.

Therefore, restrict in_aio_context_home_thread to return true
for the main AioContext only if the BQL is held.

The function is moved to aio-wait.h because it is mostly used
there and to avoid a circular reference between main-loop.h
and block/aio.h.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20200407140746.8041-5-pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 3c18a92dc4b55ca8cc37a755ed119f11c0f34099)
Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
 include/block/aio-wait.h | 22 ++++++++++++++++++++++
 include/block/aio.h      | 29 ++++++++++-------------------
 2 files changed, 32 insertions(+), 19 deletions(-)

diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h
index afeeb18f95..716d2639df 100644
--- a/include/block/aio-wait.h
+++ b/include/block/aio-wait.h
@@ -26,6 +26,7 @@
 #define QEMU_AIO_WAIT_H
 
 #include "block/aio.h"
+#include "qemu/main-loop.h"
 
 /**
  * AioWait:
@@ -124,4 +125,25 @@ void aio_wait_kick(void);
  */
 void aio_wait_bh_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque);
 
+/**
+ * in_aio_context_home_thread:
+ * @ctx: the aio context
+ *
+ * Return whether we are running in the thread that normally runs @ctx.  Note
+ * that acquiring/releasing ctx does not affect the outcome, each AioContext
+ * still only has one home thread that is responsible for running it.
+ */
+static inline bool in_aio_context_home_thread(AioContext *ctx)
+{
+    if (ctx == qemu_get_current_aio_context()) {
+        return true;
+    }
+
+    if (ctx == qemu_get_aio_context()) {
+        return qemu_mutex_iothread_locked();
+    } else {
+        return false;
+    }
+}
+
 #endif /* QEMU_AIO_WAIT_H */
diff --git a/include/block/aio.h b/include/block/aio.h
index 6b0d52f732..9d28e247df 100644
--- a/include/block/aio.h
+++ b/include/block/aio.h
@@ -60,12 +60,16 @@ struct AioContext {
     QLIST_HEAD(, AioHandler) aio_handlers;
 
     /* Used to avoid unnecessary event_notifier_set calls in aio_notify;
-     * accessed with atomic primitives.  If this field is 0, everything
-     * (file descriptors, bottom halves, timers) will be re-evaluated
-     * before the next blocking poll(), thus the event_notifier_set call
-     * can be skipped.  If it is non-zero, you may need to wake up a
-     * concurrent aio_poll or the glib main event loop, making
-     * event_notifier_set necessary.
+     * only written from the AioContext home thread, or under the BQL in
+     * the case of the main AioContext.  However, it is read from any
+     * thread so it is still accessed with atomic primitives.
+     *
+     * If this field is 0, everything (file descriptors, bottom halves,
+     * timers) will be re-evaluated before the next blocking poll() or
+     * io_uring wait; therefore, the event_notifier_set call can be
+     * skipped.  If it is non-zero, you may need to wake up a concurrent
+     * aio_poll or the glib main event loop, making event_notifier_set
+     * necessary.
      *
      * Bit 0 is reserved for GSource usage of the AioContext, and is 1
      * between a call to aio_ctx_prepare and the next call to aio_ctx_check.
@@ -580,19 +584,6 @@ void aio_co_enter(AioContext *ctx, struct Coroutine *co);
  */
 AioContext *qemu_get_current_aio_context(void);
 
-/**
- * in_aio_context_home_thread:
- * @ctx: the aio context
- *
- * Return whether we are running in the thread that normally runs @ctx.  Note
- * that acquiring/releasing ctx does not affect the outcome, each AioContext
- * still only has one home thread that is responsible for running it.
- */
-static inline bool in_aio_context_home_thread(AioContext *ctx)
-{
-    return ctx == qemu_get_current_aio_context();
-}
-
 /**
  * aio_context_setup:
  * @ctx: the aio context
-- 
2.27.0