[RFC,v2,4/7] file-posix: Implement bdrv_co_copy_range
diff mbox series

Message ID 20180418030424.28980-5-famz@redhat.com
State New
Headers show
Series
  • qemu-img convert with copy offloading
Related show

Commit Message

Fam Zheng April 18, 2018, 3:04 a.m. UTC
With copy_file_range(2), we can implement the bdrv_co_copy_range
semantics.

Signed-off-by: Fam Zheng <famz@redhat.com>
---
 block/file-posix.c      | 99 +++++++++++++++++++++++++++++++++++++++++++++++--
 include/block/raw-aio.h | 10 ++++-
 2 files changed, 104 insertions(+), 5 deletions(-)

Comments

Stefan Hajnoczi May 3, 2018, 9:25 a.m. UTC | #1
On Wed, Apr 18, 2018 at 11:04:21AM +0800, Fam Zheng wrote:
> diff --git a/block/file-posix.c b/block/file-posix.c
> index 3794c0007a..45ad543481 100644
> --- a/block/file-posix.c
> +++ b/block/file-posix.c
> @@ -100,6 +100,7 @@
>  #ifdef CONFIG_XFS
>  #include <xfs/xfs.h>
>  #endif
> +#include <sys/syscall.h>

Is sys/syscall.h available on all systems?  I wasn't able to find it in
the POSIX specs.

>  
>  //#define DEBUG_BLOCK
>  
> @@ -185,6 +186,8 @@ typedef struct RawPosixAIOData {
>  #define aio_ioctl_cmd   aio_nbytes /* for QEMU_AIO_IOCTL */
>      off_t aio_offset;
>      int aio_type;
> +    int fd2;
> +    off_t offset2;

Is there a reason for abandoning the aio_* field naming convention?

>  } RawPosixAIOData;
>  
>  #if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
> @@ -1421,6 +1424,48 @@ static ssize_t handle_aiocb_write_zeroes(RawPosixAIOData *aiocb)
>      return -ENOTSUP;
>  }
>  
> +#ifdef __NR_copy_file_range
> +#define HAS_COPY_FILE_RANGE
> +#endif
> +
> +#ifdef HAS_COPY_FILE_RANGE
> +static off_t copy_file_range(int in_fd, off_t *in_off, int out_fd,
> +                             off_t *out_off, size_t len, unsigned int flags)
> +{
> +    return syscall(__NR_copy_file_range, in_fd, in_off, out_fd,
> +                   out_off, len, flags);
> +}
> +#endif

Further #ifdefs can be avoided by providing an implementation here:

#else
static off_t copy_file_range(int in_fd, off_t *in_off, int out_fd,
                             off_t *out_off, size_t len, unsigned int flags)
{
    errno = ENOSYS;
    return -1;
}
#endif /* !HAS_COPY_FILE_RANGE */

Patch
diff mbox series

diff --git a/block/file-posix.c b/block/file-posix.c
index 3794c0007a..45ad543481 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -100,6 +100,7 @@ 
 #ifdef CONFIG_XFS
 #include <xfs/xfs.h>
 #endif
+#include <sys/syscall.h>
 
 //#define DEBUG_BLOCK
 
@@ -185,6 +186,8 @@  typedef struct RawPosixAIOData {
 #define aio_ioctl_cmd   aio_nbytes /* for QEMU_AIO_IOCTL */
     off_t aio_offset;
     int aio_type;
+    int fd2;
+    off_t offset2;
 } RawPosixAIOData;
 
 #if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
@@ -1421,6 +1424,48 @@  static ssize_t handle_aiocb_write_zeroes(RawPosixAIOData *aiocb)
     return -ENOTSUP;
 }
 
+#ifdef __NR_copy_file_range
+#define HAS_COPY_FILE_RANGE
+#endif
+
+#ifdef HAS_COPY_FILE_RANGE
+static off_t copy_file_range(int in_fd, off_t *in_off, int out_fd,
+                             off_t *out_off, size_t len, unsigned int flags)
+{
+    return syscall(__NR_copy_file_range, in_fd, in_off, out_fd,
+                   out_off, len, flags);
+}
+#endif
+
+static ssize_t handle_aiocb_copy_range(RawPosixAIOData *aiocb)
+{
+#ifndef HAS_COPY_FILE_RANGE
+    return -ENOTSUP;
+#else
+    uint64_t bytes = aiocb->aio_nbytes;
+    off_t in_off = aiocb->aio_offset;
+    off_t out_off = aiocb->offset2;
+
+    while (bytes) {
+        ssize_t ret = copy_file_range(aiocb->aio_fildes, &in_off,
+                                      aiocb->fd2, &out_off,
+                                      bytes, 0);
+        if (ret == -EINTR) {
+            continue;
+        }
+        if (ret < 0) {
+            return -errno;
+        }
+        if (!ret) {
+            /* No progress (e.g. when beyond EOF), fall back to buffer I/O. */
+            return -ENOTSUP;
+        }
+        bytes -= ret;
+    }
+    return 0;
+#endif
+}
+
 static ssize_t handle_aiocb_discard(RawPosixAIOData *aiocb)
 {
     int ret = -EOPNOTSUPP;
@@ -1501,6 +1546,9 @@  static int aio_worker(void *arg)
     case QEMU_AIO_WRITE_ZEROES:
         ret = handle_aiocb_write_zeroes(aiocb);
         break;
+    case QEMU_AIO_COPY_RANGE:
+        ret = handle_aiocb_copy_range(aiocb);
+        break;
     default:
         fprintf(stderr, "invalid aio request (0x%x)\n", aiocb->aio_type);
         ret = -EINVAL;
@@ -1511,9 +1559,10 @@  static int aio_worker(void *arg)
     return ret;
 }
 
-static int paio_submit_co(BlockDriverState *bs, int fd,
-                          int64_t offset, QEMUIOVector *qiov,
-                          int bytes, int type)
+static int paio_submit_co_full(BlockDriverState *bs, int fd,
+                               int64_t offset, int fd2, int64_t offset2,
+                               QEMUIOVector *qiov,
+                               int bytes, int type)
 {
     RawPosixAIOData *acb = g_new(RawPosixAIOData, 1);
     ThreadPool *pool;
@@ -1521,6 +1570,8 @@  static int paio_submit_co(BlockDriverState *bs, int fd,
     acb->bs = bs;
     acb->aio_type = type;
     acb->aio_fildes = fd;
+    acb->fd2 = fd2;
+    acb->offset2 = offset2;
 
     acb->aio_nbytes = bytes;
     acb->aio_offset = offset;
@@ -1536,6 +1587,13 @@  static int paio_submit_co(BlockDriverState *bs, int fd,
     return thread_pool_submit_co(pool, aio_worker, acb);
 }
 
+static inline int paio_submit_co(BlockDriverState *bs, int fd,
+                                 int64_t offset, QEMUIOVector *qiov,
+                                 int bytes, int type)
+{
+    return paio_submit_co_full(bs, fd, offset, -1, 0, qiov, bytes, type);
+}
+
 static BlockAIOCB *paio_submit(BlockDriverState *bs, int fd,
         int64_t offset, QEMUIOVector *qiov, int bytes,
         BlockCompletionFunc *cb, void *opaque, int type)
@@ -2312,6 +2370,35 @@  static void raw_abort_perm_update(BlockDriverState *bs)
     raw_handle_perm_lock(bs, RAW_PL_ABORT, 0, 0, NULL);
 }
 
+static int coroutine_fn raw_co_copy_range_from(BlockDriverState *bs,
+                                  BdrvChild *src, uint64_t src_offset,
+                                  BdrvChild *dst, uint64_t dst_offset,
+                                  uint64_t bytes, BdrvRequestFlags flags)
+{
+    return bdrv_co_copy_range_to(src, src_offset, dst, dst_offset, bytes, flags);
+}
+
+static int coroutine_fn raw_co_copy_range_to(BlockDriverState *bs,
+                                             BdrvChild *src, uint64_t src_offset,
+                                             BdrvChild *dst, uint64_t dst_offset,
+                                             uint64_t bytes, BdrvRequestFlags flags)
+{
+    BDRVRawState *s = bs->opaque;
+    BDRVRawState *src_s;
+
+    assert(dst->bs == bs);
+    if (src->bs->drv->bdrv_co_copy_range_to != raw_co_copy_range_to) {
+        return -ENOTSUP;
+    }
+
+    src_s = src->opaque;
+    if (fd_open(bs) < 0 || fd_open(bs) < 0) {
+        return -EIO;
+    }
+    return paio_submit_co_full(bs, src_s->fd, src_offset, s->fd, dst_offset,
+                               NULL, bytes, QEMU_AIO_COPY_RANGE);
+}
+
 BlockDriver bdrv_file = {
     .format_name = "file",
     .protocol_name = "file",
@@ -2334,6 +2421,8 @@  BlockDriver bdrv_file = {
     .bdrv_co_pwritev        = raw_co_pwritev,
     .bdrv_aio_flush = raw_aio_flush,
     .bdrv_aio_pdiscard = raw_aio_pdiscard,
+    .bdrv_co_copy_range_from = raw_co_copy_range_from,
+    .bdrv_co_copy_range_to  = raw_co_copy_range_to,
     .bdrv_refresh_limits = raw_refresh_limits,
     .bdrv_io_plug = raw_aio_plug,
     .bdrv_io_unplug = raw_aio_unplug,
@@ -2811,6 +2900,10 @@  static BlockDriver bdrv_host_device = {
     .bdrv_co_pwritev        = raw_co_pwritev,
     .bdrv_aio_flush	= raw_aio_flush,
     .bdrv_aio_pdiscard   = hdev_aio_pdiscard,
+    .bdrv_co_copy_range_from = raw_co_copy_range_from,
+    .bdrv_co_copy_range_to  = raw_co_copy_range_to,
+    .bdrv_co_copy_range_from = raw_co_copy_range_from,
+    .bdrv_co_copy_range_to  = raw_co_copy_range_to,
     .bdrv_refresh_limits = raw_refresh_limits,
     .bdrv_io_plug = raw_aio_plug,
     .bdrv_io_unplug = raw_aio_unplug,
diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h
index a4cdbbf1b7..324053020b 100644
--- a/include/block/raw-aio.h
+++ b/include/block/raw-aio.h
@@ -25,9 +25,15 @@ 
 #define QEMU_AIO_FLUSH        0x0008
 #define QEMU_AIO_DISCARD      0x0010
 #define QEMU_AIO_WRITE_ZEROES 0x0020
+#define QEMU_AIO_COPY_RANGE   0x0040
 #define QEMU_AIO_TYPE_MASK \
-        (QEMU_AIO_READ|QEMU_AIO_WRITE|QEMU_AIO_IOCTL|QEMU_AIO_FLUSH| \
-         QEMU_AIO_DISCARD|QEMU_AIO_WRITE_ZEROES)
+        (QEMU_AIO_READ | \
+         QEMU_AIO_WRITE | \
+         QEMU_AIO_IOCTL | \
+         QEMU_AIO_FLUSH | \
+         QEMU_AIO_DISCARD | \
+         QEMU_AIO_WRITE_ZEROES | \
+         QEMU_AIO_COPY_RANGE)
 
 /* AIO flags */
 #define QEMU_AIO_MISALIGNED   0x1000