[Qemu-devel] [PATCHv2 07/20] block: honour alignment and limit in bdrv_co_do_write_zeroes

[Peter Lieven]

Signed-off-by: Peter Lieven <address@hidden>
---
 block.c |   57 +++++++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 41 insertions(+), 16 deletions(-)

diff --git a/block.c b/block.c
index 177720e..74ec342 100644
--- a/block.c
+++ b/block.c
@@ -2660,28 +2660,53 @@ static int coroutine_fn 
bdrv_co_do_write_zeroes(BlockDriverState *bs,
     BlockDriver *drv = bs->drv;
     QEMUIOVector qiov;
     struct iovec iov;
-    int ret;
+    int ret = 0;
 
-    /* TODO Emulate only part of misaligned requests instead of letting block
-     * drivers return -ENOTSUP and emulate everything */
+    /* if no limit is specified in the BlockDriverState use a default
+     * of 32768 512-byte sectors (16 MiB) per request.
+     */
+    int max_write_zeroes = bs->max_write_zeroes ? bs->max_write_zeroes : 32768;
 
-    /* First try the efficient write zeroes operation */
-    if (drv->bdrv_co_write_zeroes) {
-        ret = drv->bdrv_co_write_zeroes(bs, sector_num, nb_sectors, flags);
-        if (ret != -ENOTSUP) {
-            return ret;
+    while (nb_sectors > 0 && !ret) {
+        int num = nb_sectors;
+
+        /* align request */
+        if (bs->write_zeroes_alignment &&
+            num >= bs->write_zeroes_alignment &&
+            sector_num % bs->write_zeroes_alignment) {
+            if (num > bs->write_zeroes_alignment) {
+                num = bs->write_zeroes_alignment;
+            }
+            num -= sector_num % bs->write_zeroes_alignment;
         }
-    }
 
-    /* Fall back to bounce buffer if write zeroes is unsupported */
-    iov.iov_len  = nb_sectors * BDRV_SECTOR_SIZE;
-    iov.iov_base = qemu_blockalign(bs, iov.iov_len);
-    memset(iov.iov_base, 0, iov.iov_len);
-    qemu_iovec_init_external(&qiov, &iov, 1);
+        /* limit request size */
+        if (num > max_write_zeroes) {
+            num = max_write_zeroes;
+        }
 
-    ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, &qiov);
+        ret = -ENOTSUP;
+        /* First try the efficient write zeroes operation */
+        if (drv->bdrv_co_write_zeroes) {
+            ret = drv->bdrv_co_write_zeroes(bs, sector_num, num, flags);
+        }
+
+        if (ret == -ENOTSUP) {
+            /* Fall back to bounce buffer if write zeroes is unsupported */
+            iov.iov_len  = nb_sectors * BDRV_SECTOR_SIZE;
+            iov.iov_base = qemu_blockalign(bs, iov.iov_len);
+            memset(iov.iov_base, 0, iov.iov_len);
+            qemu_iovec_init_external(&qiov, &iov, 1);
+
+            ret = drv->bdrv_co_writev(bs, sector_num, num, &qiov);
+
+            qemu_vfree(iov.iov_base);
+        }
+
+        sector_num += num;
+        nb_sectors -= num;
+    }
 
-    qemu_vfree(iov.iov_base);
     return ret;
 }
 
-- 
1.7.9.5