hw/arm/virt: Add 'compact-highmem' property

[mirror_qemu.git] / block / io_uring.c

diff --git a/block/io_uring.c b/block/io_uring.c
index a5c0d16220cf3bb240691201504429b7854c09d3..973e15d87693370dd3388f5119622ea2b525d30e 100644 (file)
--- a/block/io_uring.c
+++ b/block/io_uring.c
@@ -10,7 +10,6 @@
  */
 #include "qemu/osdep.h"
 #include <liburing.h>
-#include "qemu-common.h"
 #include "block/aio.h"
 #include "qemu/queue.h"
 #include "block/block.h"
@@ -73,12 +72,8 @@ static void luring_resubmit(LuringState *s, LuringAIOCB *luringcb)
 /**
  * luring_resubmit_short_read:
  *
- * Before Linux commit 9d93a3f5a0c ("io_uring: punt short reads to async
- * context") a buffered I/O request with the start of the file range in the
- * page cache could result in a short read.  Applications need to resubmit the
- * remaining read request.
- *
- * This is a slow path but recent kernels never take it.
+ * Short reads are rare but may occur. The remaining read request needs to be
+ * resubmitted.
  */
 static void luring_resubmit_short_read(LuringState *s, LuringAIOCB *luringcb,
                                        int nread)
@@ -89,7 +84,7 @@ static void luring_resubmit_short_read(LuringState *s, LuringAIOCB *luringcb,
     trace_luring_resubmit_short_read(s, luringcb, nread);
 
     /* Update read position */
-    luringcb->total_read = nread;
+    luringcb->total_read += nread;
     remaining = luringcb->qiov->size - luringcb->total_read;
 
     /* Shorten qiov */
@@ -103,7 +98,7 @@ static void luring_resubmit_short_read(LuringState *s, LuringAIOCB *luringcb,
                       remaining);
 
     /* Update sqe */
-    luringcb->sqeq.off = nread;
+    luringcb->sqeq.off += nread;
     luringcb->sqeq.addr = (__u64)(uintptr_t)luringcb->resubmit_qiov.iov;
     luringcb->sqeq.len = luringcb->resubmit_qiov.niov;
 
@@ -165,7 +160,21 @@ static void luring_process_completions(LuringState *s)
         total_bytes = ret + luringcb->total_read;
 
         if (ret < 0) {
-            if (ret == -EINTR) {
+            /*
+             * Only writev/readv/fsync requests on regular files or host block
+             * devices are submitted. Therefore -EAGAIN is not expected but it's
+             * known to happen sometimes with Linux SCSI. Submit again and hope
+             * the request completes successfully.
+             *
+             * For more information, see:
+             * https://lore.kernel.org/io-uring/20210727165811.284510-3-axboe@kernel.dk/T/#u
+             *
+             * If the code is changed to submit other types of requests in the
+             * future, then this workaround may need to be extended to deal with
+             * genuine -EAGAIN results that should not be resubmitted
+             * immediately.
+             */
+            if (ret == -EINTR || ret == -EAGAIN) {
                 luring_resubmit(s, luringcb);
                 continue;
             }
@@ -187,7 +196,7 @@ static void luring_process_completions(LuringState *s)
                     ret = 0;
                 }
             } else {
-                ret = -ENOSPC;;
+                ret = -ENOSPC;
             }
         }
 end:
@@ -231,7 +240,7 @@ static int ioq_submit(LuringState *s)
         trace_luring_io_uring_submit(s, ret);
         /* Prevent infinite loop if submission is refused */
         if (ret <= 0) {
-            if (ret == -EAGAIN) {
+            if (ret == -EAGAIN || ret == -EINTR) {
                 continue;
             }
             break;
@@ -274,6 +283,20 @@ static void qemu_luring_completion_cb(void *opaque)
     luring_process_completions_and_submit(s);
 }
 
+static bool qemu_luring_poll_cb(void *opaque)
+{
+    LuringState *s = opaque;
+
+    return io_uring_cq_ready(&s->ring);
+}
+
+static void qemu_luring_poll_ready(void *opaque)
+{
+    LuringState *s = opaque;
+
+    luring_process_completions_and_submit(s);
+}
+
 static void ioq_init(LuringQueue *io_q)
 {
     QSIMPLEQ_INIT(&io_q->submit_queue);
@@ -376,8 +399,8 @@ int coroutine_fn luring_co_submit(BlockDriverState *bs, LuringState *s, int fd,
 
 void luring_detach_aio_context(LuringState *s, AioContext *old_context)
 {
-    aio_set_fd_handler(old_context, s->ring.ring_fd, false, NULL, NULL, NULL,
-                       s);
+    aio_set_fd_handler(old_context, s->ring.ring_fd, false,
+                       NULL, NULL, NULL, NULL, s);
     qemu_bh_delete(s->completion_bh);
     s->aio_context = NULL;
 }
@@ -387,7 +410,8 @@ void luring_attach_aio_context(LuringState *s, AioContext *new_context)
     s->aio_context = new_context;
     s->completion_bh = aio_bh_new(new_context, qemu_luring_completion_bh, s);
     aio_set_fd_handler(s->aio_context, s->ring.ring_fd, false,
-                       qemu_luring_completion_cb, NULL, NULL, s);
+                       qemu_luring_completion_cb, NULL,
+                       qemu_luring_poll_cb, qemu_luring_poll_ready, s);
 }
 
 LuringState *luring_init(Error **errp)
@@ -413,6 +437,6 @@ LuringState *luring_init(Error **errp)
 void luring_cleanup(LuringState *s)
 {
     io_uring_queue_exit(&s->ring);
-    g_free(s);
     trace_luring_cleanup_state(s);
+    g_free(s);
 }