raw-posix: add Linux native AIO support

Now that do have a nicer interface to work against we can add Linux native
AIO support.  It's an extremly thing layer just setting up an iocb for
the io_submit system call in the submission path, and registering an
eventfd with the qemu poll handler to do complete the iocbs directly
from there.

This started out based on Anthony's earlier AIO patch, but after
estimated 42,000 rewrites and just as many build system changes
there's not much left of it.

To enable native kernel aio use the aio=native sub-command on the
drive command line.  I have also added an option to qemu-io to
test the aio support without needing a guest.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

2 files changed, 31 insertions, 5 deletions

diff --git a/block/raw-posix-aio.h b/block/raw-posix-aio.h
index 6761cd3..244bc8b 100644
--- a/block/raw-posix-aio.h
+++ b/block/raw-posix-aio.h
@@ -33,4 +33,10 @@ BlockDriverAIOCB *paio_ioctl(BlockDriverState *bs, int fd,
         unsigned long int req, void *buf,
         BlockDriverCompletionFunc *cb, void *opaque);
 
+/* linux-aio.c - Linux native implementation */
+void *laio_init(void);
+BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque, int type);
+
 #endif /* QEMU_RAW_POSIX_AIO_H */
diff --git a/block/raw-posix.c b/block/raw-posix.c
index ca9bc61..8a7dc15 100644
--- a/block/raw-posix.c
+++ b/block/raw-posix.c
@@ -115,6 +115,7 @@ typedef struct BDRVRawState {
     int fd_got_error;
     int fd_media_changed;
 #endif
+    int use_aio;
     uint8_t* aligned_buf;
 } BDRVRawState;
 
@@ -159,6 +160,7 @@ static int raw_open_common(BlockDriverState *bs, const char *filename,
     }
     s->fd = fd;
     s->aligned_buf = NULL;
+
     if ((bdrv_flags & BDRV_O_NOCACHE)) {
         s->aligned_buf = qemu_blockalign(bs, ALIGNED_BUFFER_SIZE);
         if (s->aligned_buf == NULL) {
@@ -166,9 +168,22 @@ static int raw_open_common(BlockDriverState *bs, const char *filename,
         }
     }
 
-    s->aio_ctx = paio_init();
-    if (!s->aio_ctx) {
-        goto out_free_buf;
+#ifdef CONFIG_LINUX_AIO
+    if ((bdrv_flags & (BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) ==
+                      (BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) {
+        s->aio_ctx = laio_init();
+        if (!s->aio_ctx) {
+            goto out_free_buf;
+        }
+        s->use_aio = 1;
+    } else
+#endif
+    {
+        s->aio_ctx = paio_init();
+        if (!s->aio_ctx) {
+            goto out_free_buf;
+        }
+        s->use_aio = 0;
     }
 
     return 0;
@@ -524,8 +539,13 @@ static BlockDriverAIOCB *raw_aio_submit(BlockDriverState *bs,
      * boundary.  Check if this is the case or telll the low-level
      * driver that it needs to copy the buffer.
      */
-    if (s->aligned_buf && !qiov_is_aligned(qiov)) {
-        type |= QEMU_AIO_MISALIGNED;
+    if (s->aligned_buf) {
+        if (!qiov_is_aligned(qiov)) {
+            type |= QEMU_AIO_MISALIGNED;
+        } else if (s->use_aio) {
+            return laio_submit(bs, s->aio_ctx, s->fd, sector_num, qiov,
+	                       nb_sectors, cb, opaque, type);
+        }
     }
 
     return paio_submit(bs, s->aio_ctx, s->fd, sector_num, qiov, nb_sectors,