[Qemu-devel] [7021] native preadv/pwritev support (Christoph Hellwig)

[Anthony Liguori <anthony@codemonkey.ws>]

Revision: 7021
          http://svn.sv.gnu.org/viewvc/?view=rev&root=qemu&revision=7021
Author:   aliguori
Date:     2009-04-07 18:43:28 +0000 (Tue, 07 Apr 2009)
Log Message:
-----------
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>

Modified Paths:
--------------
    trunk/block.c
    trunk/configure
    trunk/posix-aio-compat.c

Modified: trunk/block.c
===================================================================
--- trunk/block.c	2009-04-07 18:43:24 UTC (rev 7020)
+++ trunk/block.c	2009-04-07 18:43:28 UTC (rev 7021)
@@ -1354,10 +1354,9 @@
 {
     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);

Modified: trunk/configure
===================================================================
--- trunk/configure	2009-04-07 18:43:24 UTC (rev 7020)
+++ trunk/configure	2009-04-07 18:43:28 UTC (rev 7021)
@@ -1108,6 +1108,19 @@
 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 "Install blobs     $blobs"
 echo "KVM support       $kvm"
 echo "fdt support       $fdt"
+echo "preadv support    $preadv"
 
 if test $sdl_too_old = "yes"; then
 echo "-> Your SDL version is too old - please upgrade to have SDL support"
@@ -1522,6 +1536,9 @@
 if test "$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

Modified: trunk/posix-aio-compat.c
===================================================================
--- trunk/posix-aio-compat.c	2009-04-07 18:43:24 UTC (rev 7020)
+++ trunk/posix-aio-compat.c	2009-04-07 18:43:28 UTC (rev 7021)
@@ -33,6 +33,12 @@
 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 @@
 	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 @@
     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 @@
     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?
+         */
     }
 
     /*