native preadv/pwritev support (Christoph Hellwig)

This ties up the preadv/pwritev syscalls to qemu if they are declared in
unistd.h.  This is the case currently on at least NetBSD and OpenBSD and
will hopefully soon be the case on Linux.

Thanks to Blue Swirl and Gerd Hoffmann for the configure autodetection
of preadv/pwritev.


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


git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@7021 c046a42c-6fe2-441c-8c8c-71466251a162

3 files changed, 101 insertions, 4 deletions

diff --git a/block.c b/block.c
index 8a78f14ed5..74d19ad288 100644
--- a/block.c
+++ b/block.c
@@ -1354,10 +1354,9 @@ static void bdrv_aio_bh_cb(void *opaque)
 {
     BlockDriverAIOCBSync *acb = opaque;
 
-    qemu_vfree(acb->bounce);
-
     if (!acb->is_write)
         qemu_iovec_from_buffer(acb->qiov, acb->bounce, acb->qiov->size);
+    qemu_vfree(acb->bounce);
     acb->common.cb(acb->common.opaque, acb->ret);
 
     qemu_aio_release(acb);
diff --git a/configure b/configure
index 15b785604c..412828e9ba 100755
--- a/configure
+++ b/configure
@@ -1108,6 +1108,19 @@ if $cc $ARCH_CFLAGS -o $TMPE $TMPC > /dev/null 2> /dev/null ; then
 fi
 
 ##########################################
+# preadv probe
+cat > $TMPC <<EOF
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <unistd.h>
+int main(void) { preadv; }
+EOF
+preadv=no
+if $cc $ARCH_CFLAGS -o $TMPE $TMPC > /dev/null 2> /dev/null ; then
+  preadv=yes
+fi
+
+##########################################
 # fdt probe
 if test "$fdt" = "yes" ; then
     fdt=no
@@ -1221,6 +1234,7 @@ echo "AIO support       $aio"
 echo "Install blobs     $blobs"
 echo "KVM support       $kvm"
 echo "fdt support       $fdt"
+echo "preadv support    $preadv"
 
 if test $sdl_too_old = "yes"; then
 echo "-> Your SDL version is too old - please upgrade to have SDL support"
@@ -1522,6 +1536,9 @@ fi
 if test "$iovec" = "yes" ; then
   echo "#define HAVE_IOVEC 1" >> $config_h
 fi
+if test "$preadv" = "yes" ; then
+  echo "#define HAVE_PREADV 1" >> $config_h
+fi
 if test "$fdt" = "yes" ; then
   echo "#define HAVE_FDT 1" >> $config_h
   echo "FDT_LIBS=-lfdt" >> $config_mak
diff --git a/posix-aio-compat.c b/posix-aio-compat.c
index 0eb77a50d3..c7fdac70b4 100644
--- a/posix-aio-compat.c
+++ b/posix-aio-compat.c
@@ -33,6 +33,12 @@ static int cur_threads = 0;
 static int idle_threads = 0;
 static TAILQ_HEAD(, qemu_paiocb) request_list;
 
+#ifdef HAVE_PREADV
+static int preadv_present = 1;
+#else
+static int preadv_present = 0;
+#endif
+
 static void die2(int err, const char *what)
 {
     fprintf(stderr, "%s failed: %s\n", what, strerror(err));
@@ -87,6 +93,36 @@ static size_t handle_aiocb_ioctl(struct qemu_paiocb *aiocb)
 	return ret;
 }
 
+#ifdef HAVE_PREADV
+
+static ssize_t
+qemu_preadv(int fd, const struct iovec *iov, int nr_iov, off_t offset)
+{
+    return preadv(fd, iov, nr_iov, offset);
+}
+
+static ssize_t
+qemu_pwritev(int fd, const struct iovec *iov, int nr_iov, off_t offset)
+{
+    return pwritev(fd, iov, nr_iov, offset);
+}
+
+#else
+
+static ssize_t
+qemu_preadv(int fd, const struct iovec *iov, int nr_iov, off_t offset)
+{
+    return -ENOSYS;
+}
+
+static ssize_t
+qemu_pwritev(int fd, const struct iovec *iov, int nr_iov, off_t offset)
+{
+    return -ENOSYS;
+}
+
+#endif
+
 /*
  * Check if we need to copy the data in the aiocb into a new
  * properly aligned buffer.
@@ -104,6 +140,29 @@ static int aiocb_needs_copy(struct qemu_paiocb *aiocb)
     return 0;
 }
 
+static size_t handle_aiocb_rw_vector(struct qemu_paiocb *aiocb)
+{
+    size_t offset = 0;
+    ssize_t len;
+
+    do {
+        if (aiocb->aio_type == QEMU_PAIO_WRITE)
+            len = qemu_pwritev(aiocb->aio_fildes,
+                               aiocb->aio_iov,
+                               aiocb->aio_niov,
+                               aiocb->aio_offset + offset);
+         else
+            len = qemu_preadv(aiocb->aio_fildes,
+                              aiocb->aio_iov,
+                              aiocb->aio_niov,
+                              aiocb->aio_offset + offset);
+    } while (len == -1 && errno == EINTR);
+
+    if (len == -1)
+        return -errno;
+    return len;
+}
+
 static size_t handle_aiocb_rw_linear(struct qemu_paiocb *aiocb, char *buf)
 {
     size_t offset = 0;
@@ -140,12 +199,34 @@ static size_t handle_aiocb_rw(struct qemu_paiocb *aiocb)
     size_t nbytes;
     char *buf;
 
-    if (!aiocb_needs_copy(aiocb) && aiocb->aio_niov == 1) {
+    if (!aiocb_needs_copy(aiocb)) {
         /*
          * If there is just a single buffer, and it is properly aligned
          * we can just use plain pread/pwrite without any problems.
          */
-        return handle_aiocb_rw_linear(aiocb, aiocb->aio_iov->iov_base);
+        if (aiocb->aio_niov == 1)
+             return handle_aiocb_rw_linear(aiocb, aiocb->aio_iov->iov_base);
+
+        /*
+         * We have more than one iovec, and all are properly aligned.
+         *
+         * Try preadv/pwritev first and fall back to linearizing the
+         * buffer if it's not supported.
+         */
+	if (preadv_present) {
+            nbytes = handle_aiocb_rw_vector(aiocb);
+            if (nbytes == aiocb->aio_nbytes)
+	        return nbytes;
+            if (nbytes < 0 && nbytes != -ENOSYS)
+                return nbytes;
+            preadv_present = 0;
+        }
+
+        /*
+         * XXX(hch): short read/write.  no easy way to handle the reminder
+         * using these interfaces.  For now retry using plain
+         * pread/pwrite?
+         */
     }
 
     /*