qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Stefan Hajnoczi <stefanha@redhat.com>
To: qemu-devel@nongnu.org
Cc: Ronnie Sahlberg <ronniesahlberg@gmail.com>,
	Peter Maydell <peter.maydell@linaro.org>,
	qemu-block@nongnu.org, Peter Lieven <pl@kamp.de>,
	Max Reitz <mreitz@redhat.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Kevin Wolf <kwolf@redhat.com>, Fam Zheng <famz@redhat.com>,
	Stefan Hajnoczi <stefanha@redhat.com>
Subject: [Qemu-devel] [PULL 05/11] file-posix: Implement bdrv_co_copy_range
Date: Mon,  4 Jun 2018 12:20:30 +0100	[thread overview]
Message-ID: <20180604112036.2715-6-stefanha@redhat.com> (raw)
In-Reply-To: <20180604112036.2715-1-stefanha@redhat.com>

From: Fam Zheng <famz@redhat.com>

With copy_file_range(2), we can implement the bdrv_co_copy_range
semantics.

Signed-off-by: Fam Zheng <famz@redhat.com>
Message-id: 20180601092648.24614-6-famz@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 configure               | 17 +++++++
 include/block/raw-aio.h | 10 ++++-
 block/file-posix.c      | 98 +++++++++++++++++++++++++++++++++++++++--
 3 files changed, 120 insertions(+), 5 deletions(-)

diff --git a/configure b/configure
index be6edc7b81..8c6ea9ba7f 100755
--- a/configure
+++ b/configure
@@ -5183,6 +5183,20 @@ if test "$fortify_source" != "no"; then
   fi
 fi
 
+###############################################
+# Check if copy_file_range is provided by glibc
+have_copy_file_range=no
+cat > $TMPC << EOF
+#include <unistd.h>
+int main(void) {
+  copy_file_range(0, NULL, 0, NULL, 0, 0);
+  return 0;
+}
+EOF
+if compile_prog "" "" ; then
+    have_copy_file_range=yes
+fi
+
 ##########################################
 # check if struct fsxattr is available via linux/fs.h
 
@@ -6286,6 +6300,9 @@ fi
 if test "$have_fsxattr" = "yes" ; then
     echo "HAVE_FSXATTR=y" >> $config_host_mak
 fi
+if test "$have_copy_file_range" = "yes" ; then
+    echo "HAVE_COPY_FILE_RANGE=y" >> $config_host_mak
+fi
 if test "$vte" = "yes" ; then
   echo "CONFIG_VTE=y" >> $config_host_mak
   echo "VTE_CFLAGS=$vte_cflags" >> $config_host_mak
diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h
index 9e47b8a629..0e717fd475 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
diff --git a/block/file-posix.c b/block/file-posix.c
index 5a602cfe37..513d371bb1 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -59,6 +59,7 @@
 #ifdef __linux__
 #include <sys/ioctl.h>
 #include <sys/param.h>
+#include <sys/syscall.h>
 #include <linux/cdrom.h>
 #include <linux/fd.h>
 #include <linux/fs.h>
@@ -187,6 +188,8 @@ typedef struct RawPosixAIOData {
 #define aio_ioctl_cmd   aio_nbytes /* for QEMU_AIO_IOCTL */
     off_t aio_offset;
     int aio_type;
+    int aio_fd2;
+    off_t aio_offset2;
 } RawPosixAIOData;
 
 #if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
@@ -1446,6 +1449,49 @@ static ssize_t handle_aiocb_write_zeroes(RawPosixAIOData *aiocb)
     return -ENOTSUP;
 }
 
+#ifndef HAVE_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)
+{
+#ifdef __NR_copy_file_range
+    return syscall(__NR_copy_file_range, in_fd, in_off, out_fd,
+                   out_off, len, flags);
+#else
+    errno = ENOSYS;
+    return -1;
+#endif
+}
+#endif
+
+static ssize_t handle_aiocb_copy_range(RawPosixAIOData *aiocb)
+{
+    uint64_t bytes = aiocb->aio_nbytes;
+    off_t in_off = aiocb->aio_offset;
+    off_t out_off = aiocb->aio_offset2;
+
+    while (bytes) {
+        ssize_t ret = copy_file_range(aiocb->aio_fildes, &in_off,
+                                      aiocb->aio_fd2, &out_off,
+                                      bytes, 0);
+        if (ret == -EINTR) {
+            continue;
+        }
+        if (ret < 0) {
+            if (errno == ENOSYS) {
+                return -ENOTSUP;
+            } else {
+                return -errno;
+            }
+        }
+        if (!ret) {
+            /* No progress (e.g. when beyond EOF), fall back to buffer I/O. */
+            return -ENOTSUP;
+        }
+        bytes -= ret;
+    }
+    return 0;
+}
+
 static ssize_t handle_aiocb_discard(RawPosixAIOData *aiocb)
 {
     int ret = -EOPNOTSUPP;
@@ -1526,6 +1572,9 @@ 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;
@@ -1536,9 +1585,10 @@ 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;
@@ -1546,6 +1596,8 @@ static int paio_submit_co(BlockDriverState *bs, int fd,
     acb->bs = bs;
     acb->aio_type = type;
     acb->aio_fildes = fd;
+    acb->aio_fd2 = fd2;
+    acb->aio_offset2 = offset2;
 
     acb->aio_nbytes = bytes;
     acb->aio_offset = offset;
@@ -1561,6 +1613,13 @@ 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)
@@ -2451,6 +2510,35 @@ 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->bs->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",
@@ -2474,6 +2562,8 @@ 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,
@@ -2952,6 +3042,8 @@ 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_refresh_limits = raw_refresh_limits,
     .bdrv_io_plug = raw_aio_plug,
     .bdrv_io_unplug = raw_aio_unplug,
-- 
2.17.1

  parent reply	other threads:[~2018-06-04 11:21 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-06-04 11:20 [Qemu-devel] [PULL 00/11] Block patches Stefan Hajnoczi
2018-06-04 11:20 ` [Qemu-devel] [PULL 01/11] block: Introduce API for copy offloading Stefan Hajnoczi
2018-06-04 11:20 ` [Qemu-devel] [PULL 02/11] raw: Check byte range uniformly Stefan Hajnoczi
2018-06-04 11:20 ` [Qemu-devel] [PULL 03/11] raw: Implement copy offloading Stefan Hajnoczi
2018-06-04 11:20 ` [Qemu-devel] [PULL 04/11] qcow2: " Stefan Hajnoczi
2018-06-04 11:20 ` Stefan Hajnoczi [this message]
2018-06-04 11:20 ` [Qemu-devel] [PULL 06/11] iscsi: Query and save device designator when opening Stefan Hajnoczi
2018-06-04 11:20 ` [Qemu-devel] [PULL 07/11] iscsi: Create and use iscsi_co_wait_for_task Stefan Hajnoczi
2018-06-04 11:20 ` [Qemu-devel] [PULL 08/11] iscsi: Implement copy offloading Stefan Hajnoczi
2018-06-04 11:20 ` [Qemu-devel] [PULL 09/11] block-backend: Add blk_co_copy_range Stefan Hajnoczi
2018-06-04 11:20 ` [Qemu-devel] [PULL 10/11] qemu-img: Convert with copy offloading Stefan Hajnoczi
2018-06-04 11:20 ` [Qemu-devel] [PULL 11/11] main-loop: drop spin_counter Stefan Hajnoczi
2018-06-05  9:38 ` [Qemu-devel] [PULL 00/11] Block patches Peter Maydell

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180604112036.2715-6-stefanha@redhat.com \
    --to=stefanha@redhat.com \
    --cc=famz@redhat.com \
    --cc=kwolf@redhat.com \
    --cc=mreitz@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peter.maydell@linaro.org \
    --cc=pl@kamp.de \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=ronniesahlberg@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).