block: add cache=directsync parameter to -drive

This patch adds -drive cache=directsync for O_DIRECT | O_SYNC host file
I/O with no disk write cache presented to the guest.

This mode is useful when guests may not be sending flushes when
appropriate and therefore leave data at risk in case of power failure.
When cache=directsync is used, write operations are only completed to
the guest when data is safely on disk.

This new mode is like cache=writethrough but it bypasses the host page
cache.

Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

4 files changed, 14 insertions, 6 deletions

diff --git a/block.c b/block.c
index dbef3ae672..4186a2f340 100644
--- a/block.c
+++ b/block.c
@@ -448,6 +448,8 @@ int bdrv_parse_cache_flags(const char *mode, int *flags)
 
     if (!strcmp(mode, "off") || !strcmp(mode, "none")) {
         *flags |= BDRV_O_NOCACHE | BDRV_O_CACHE_WB;
+    } else if (!strcmp(mode, "directsync")) {
+        *flags |= BDRV_O_NOCACHE;
     } else if (!strcmp(mode, "writeback")) {
         *flags |= BDRV_O_CACHE_WB;
     } else if (!strcmp(mode, "unsafe")) {
@@ -1188,8 +1190,8 @@ int bdrv_pwrite_sync(BlockDriverState *bs, int64_t offset,
         return ret;
     }
 
-    /* No flush needed for cache=writethrough, it uses O_DSYNC */
-    if ((bs->open_flags & BDRV_O_CACHE_MASK) != 0) {
+    /* No flush needed for cache modes that use O_DSYNC */
+    if ((bs->open_flags & BDRV_O_CACHE_WB) != 0) {
         bdrv_flush(bs);
     }
 
diff --git a/qemu-config.c b/qemu-config.c
index 1eb6b9a709..139e07768b 100644
--- a/qemu-config.c
+++ b/qemu-config.c
@@ -55,7 +55,8 @@ static QemuOptsList qemu_drive_opts = {
         },{
             .name = "cache",
             .type = QEMU_OPT_STRING,
-            .help = "host cache usage (none, writeback, writethrough, unsafe)",
+            .help = "host cache usage (none, writeback, writethrough, "
+                    "directsync, unsafe)",
         },{
             .name = "aio",
             .type = QEMU_OPT_STRING,
diff --git a/qemu-img.c b/qemu-img.c
index 5e203c231f..10a3a8bb52 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -66,7 +66,8 @@ static void help(void)
            "  'filename' is a disk image filename\n"
            "  'fmt' is the disk image format. It is guessed automatically in most cases\n"
            "  'cache' is the cache mode used to write the output disk image, the valid\n"
-           "    options are: 'none', 'writeback' (default), 'writethrough' and 'unsafe'\n"
+           "    options are: 'none', 'writeback' (default), 'writethrough', 'directsync'\n"
+           "    and 'unsafe'\n"
            "  'size' is the disk image size in bytes. Optional suffixes\n"
            "    'k' or 'K' (kilobyte, 1024), 'M' (megabyte, 1024k), 'G' (gigabyte, 1024M)\n"
            "    and T (terabyte, 1024G) are supported. 'b' is ignored.\n"
diff --git a/qemu-options.hx b/qemu-options.hx
index d86815dc04..35d95d1d89 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -133,7 +133,7 @@ ETEXI
 DEF("drive", HAS_ARG, QEMU_OPTION_drive,
     "-drive [file=file][,if=type][,bus=n][,unit=m][,media=d][,index=i]\n"
     "       [,cyls=c,heads=h,secs=s[,trans=t]][,snapshot=on|off]\n"
-    "       [,cache=writethrough|writeback|none|unsafe][,format=f]\n"
+    "       [,cache=writethrough|writeback|none|directsync|unsafe][,format=f]\n"
     "       [,serial=s][,addr=A][,id=name][,aio=threads|native]\n"
     "       [,readonly=on|off]\n"
     "                use 'file' as a drive image\n", QEMU_ARCH_ALL)
@@ -164,7 +164,7 @@ These options have the same definition as they have in @option{-hdachs}.
 @item snapshot=@var{snapshot}
 @var{snapshot} is "on" or "off" and allows to enable snapshot for given drive (see @option{-snapshot}).
 @item cache=@var{cache}
-@var{cache} is "none", "writeback", "unsafe", or "writethrough" and controls how the host cache is used to access block data.
+@var{cache} is "none", "writeback", "unsafe", "directsync" or "writethrough" and controls how the host cache is used to access block data.
 @item aio=@var{aio}
 @var{aio} is "threads", or "native" and selects between pthread based disk I/O and native Linux AIO.
 @item format=@var{format}
@@ -199,6 +199,10 @@ The host page cache can be avoided entirely with @option{cache=none}.  This will
 attempt to do disk IO directly to the guests memory.  QEMU may still perform
 an internal copy of the data.
 
+The host page cache can be avoided while only sending write notifications to
+the guest when the data has been reported as written by the storage subsystem
+using @option{cache=directsync}.
+
 Some block drivers perform badly with @option{cache=writethrough}, most notably,
 qcow2.  If performance is more important than correctness,
 @option{cache=writeback} should be used with qcow2.