From 29d5339959b539767f6482adc00e02f0bb6083f9 Mon Sep 17 00:00:00 2001 From: Fam Zheng Date: Fri, 29 Jun 2018 06:11:45 +0200 Subject: [PATCH 41/57] file-posix: Implement bdrv_co_copy_range RH-Author: Fam Zheng Message-id: <20180629061153.12687-6-famz@redhat.com> Patchwork-id: 81156 O-Subject: [RHEL-7.6 qemu-kvm-rhev PATCH v2 05/13] file-posix: Implement bdrv_co_copy_range Bugzilla: 1482537 RH-Acked-by: Stefan Hajnoczi RH-Acked-by: Max Reitz RH-Acked-by: Kevin Wolf With copy_file_range(2), we can implement the bdrv_co_copy_range semantics. Signed-off-by: Fam Zheng Message-id: 20180601092648.24614-6-famz@redhat.com Signed-off-by: Stefan Hajnoczi (cherry picked from commit 1efad060d7e131dd52ecd1e038a6ddd37a3940c8) Signed-off-by: Fam Zheng Signed-off-by: Miroslav Rezanina --- block/file-posix.c | 98 +++++++++++++++++++++++++++++++++++++++++++++++-- configure | 17 +++++++++ include/block/raw-aio.h | 10 ++++- 3 files changed, 120 insertions(+), 5 deletions(-) diff --git a/block/file-posix.c b/block/file-posix.c index 370a483..29ff699 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -59,6 +59,7 @@ #ifdef __linux__ #include #include +#include #include #include #include @@ -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 aio_fd2; + off_t aio_offset2; } RawPosixAIOData; #if defined(__FreeBSD__) || defined(__FreeBSD_kernel__) @@ -1422,6 +1425,49 @@ 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; @@ -1502,6 +1548,9 @@ 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; @@ -1512,9 +1561,10 @@ 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; @@ -1522,6 +1572,8 @@ 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; @@ -1537,6 +1589,13 @@ 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) @@ -2346,6 +2405,35 @@ 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", @@ -2368,6 +2456,8 @@ 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, @@ -2845,6 +2935,8 @@ 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, diff --git a/configure b/configure index d2367f1..a869f19 100755 --- a/configure +++ b/configure @@ -5156,6 +5156,20 @@ if test "$fortify_source" != "no"; then fi fi +############################################### +# Check if copy_file_range is provided by glibc +have_copy_file_range=no +cat > $TMPC << EOF +#include +int main(void) { + copy_file_range(0, NULL, 0, NULL, 0, 0); + return 0; +} +EOF +if compile_prog "" "" ; then + have_copy_file_range=yes +fi + ########################################## # check if struct fsxattr is available via linux/fs.h @@ -6233,6 +6247,9 @@ fi if test "$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 a4cdbbf..3240530 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 -- 1.8.3.1