The following changes since commit 9548cbeffffd4253e38570d29b8cff0bf77c998f: iotests/copy-before-write: specify required_fmts (2022-07-12 13:21:02 +0530) are available in the Git repository at: https://gitlab.com/hreitz/qemu.git tags/pull-block-2022-07-12 for you to fetch changes up to 85c4bf8aa6c93c24876e8870ae7cf8ab2e5a96cf: vl: Unlink absolute PID file path (2022-07-12 14:31:15 +0200) ---------------------------------------------------------------- Block patches: - Refactoring for non-coroutine variants of bdrv/blk_co_* functions: Auto-generate more of them with the block coroutine wrapper generator script - iotest fixes - Both for the storage daemon and the system emulator: Fix PID file handling when daemonizing (store the absolute path and delete that on exit, which is necessary because daemonizing will change the working directory to /) ---------------------------------------------------------------- Alberto Faria (28): block: Add a 'flags' param to bdrv_{pread,pwrite,pwrite_sync}() block: Change bdrv_{pread,pwrite,pwrite_sync}() param order block: Make bdrv_{pread,pwrite}() return 0 on success crypto: Make block callbacks return 0 on success block: Make bdrv_co_pwrite() take a const buffer block: Make 'bytes' param of bdrv_co_{pread,pwrite,preadv,pwritev}() an int64_t block: Implement bdrv_{pread,pwrite,pwrite_zeroes}() using generated_co_wrapper block: Add bdrv_co_pwrite_sync() block: Use bdrv_co_pwrite_sync() when caller is coroutine_fn block/qcow2: Use bdrv_pwrite_sync() in qcow2_mark_dirty() block: Make blk_{pread,pwrite}() return 0 on success block: Add a 'flags' param to blk_pread() block: Change blk_{pread,pwrite}() param order block: Make 'bytes' param of blk_{pread,pwrite}() an int64_t block: Make blk_co_pwrite() take a const buffer block: Implement blk_{pread,pwrite}() using generated_co_wrapper block: Add blk_{preadv,pwritev}() block: Add blk_[co_]preadv_part() block: Export blk_pwritev_part() in block-backend-io.h block: Change blk_pwrite_compressed() param order block: Add blk_co_pwrite_compressed() block: Implement blk_pwrite_zeroes() using generated_co_wrapper block: Implement blk_pdiscard() using generated_co_wrapper block: Implement blk_flush() using generated_co_wrapper block: Add blk_co_ioctl() block: Add blk_co_truncate() block: Reorganize some declarations in block-backend-io.h block: Remove remaining unused symbols in coroutines.h Hanna Reitz (5): qsd: Do not use error_report() before monitor_init iotests/297: Have mypy ignore unused ignores qsd: Unlink absolute PID file path vl: Conditionally register PID file unlink notifier vl: Unlink absolute PID file path John Snow (2): tests/qemu-iotests: hotfix for 307, 223 output tests/qemu-iotests: skip 108 when FUSE is not loaded block/coroutines.h | 44 -------- include/block/block-io.h | 22 ++-- include/block/block_int-io.h | 4 +- include/crypto/block.h | 32 +++--- include/sysemu/block-backend-io.h | 97 ++++++++++------- block.c | 10 +- block/blklogwrites.c | 6 +- block/block-backend.c | 150 +++++++++++--------------- block/bochs.c | 10 +- block/cloop.c | 12 +-- block/commit.c | 4 +- block/crypto.c | 58 +++++----- block/dmg.c | 36 +++---- block/export/fuse.c | 4 +- block/io.c | 55 +--------- block/parallels-ext.c | 6 +- block/parallels.c | 14 +-- block/qcow.c | 55 +++++----- block/qcow2-bitmap.c | 14 +-- block/qcow2-cache.c | 9 +- block/qcow2-cluster.c | 19 ++-- block/qcow2-refcount.c | 58 +++++----- block/qcow2-snapshot.c | 53 +++++----- block/qcow2.c | 84 +++++++-------- block/qed.c | 21 ++-- block/vdi.c | 20 ++-- block/vhdx-log.c | 23 ++-- block/vhdx.c | 56 +++++----- block/vmdk.c | 80 +++++++------- block/vpc.c | 35 +++--- block/vvfat.c | 11 +- crypto/block-luks.c | 8 +- crypto/block.c | 6 +- hw/arm/allwinner-h3.c | 2 +- hw/arm/aspeed.c | 2 +- hw/block/block.c | 2 +- hw/block/fdc.c | 20 ++-- hw/block/hd-geometry.c | 2 +- hw/block/m25p80.c | 2 +- hw/block/nand.c | 47 ++++---- hw/block/onenand.c | 32 +++--- hw/block/pflash_cfi01.c | 4 +- hw/block/pflash_cfi02.c | 4 +- hw/ide/atapi.c | 4 +- hw/misc/mac_via.c | 6 +- hw/misc/sifive_u_otp.c | 14 +-- hw/nvram/eeprom_at24c.c | 8 +- hw/nvram/spapr_nvram.c | 16 +-- hw/nvram/xlnx-bbram.c | 4 +- hw/nvram/xlnx-efuse.c | 4 +- hw/ppc/pnv_pnor.c | 6 +- hw/sd/sd.c | 4 +- migration/block.c | 8 +- nbd/server.c | 8 +- qemu-img.c | 41 +++---- qemu-io-cmds.c | 20 ++-- softmmu/vl.c | 42 ++++++-- storage-daemon/qemu-storage-daemon.c | 17 ++- tests/unit/test-block-iothread.c | 153 ++++++++++++++++++++++++--- tests/unit/test-crypto-block.c | 38 +++---- block/meson.build | 1 + tests/qemu-iotests/108 | 5 + tests/qemu-iotests/223.out | 4 +- tests/qemu-iotests/307.out | 4 +- tests/qemu-iotests/mypy.ini | 2 +- 65 files changed, 856 insertions(+), 786 deletions(-) -- 2.35.3 From: Alberto Faria <afaria@redhat.com> For consistency with other I/O functions, and in preparation to implement them using generated_co_wrapper. Callers were updated using this Coccinelle script: @@ expression child, offset, buf, bytes; @@ - bdrv_pread(child, offset, buf, bytes) + bdrv_pread(child, offset, buf, bytes, 0) @@ expression child, offset, buf, bytes; @@ - bdrv_pwrite(child, offset, buf, bytes) + bdrv_pwrite(child, offset, buf, bytes, 0) @@ expression child, offset, buf, bytes; @@ - bdrv_pwrite_sync(child, offset, buf, bytes) + bdrv_pwrite_sync(child, offset, buf, bytes, 0) Resulting overly-long lines were then fixed by hand. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Message-Id: <20220609152744.3891847-2-afaria@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/block/block-io.h | 7 ++-- block/blklogwrites.c | 4 +-- block/bochs.c | 6 ++-- block/cloop.c | 10 +++--- block/crypto.c | 4 +-- block/dmg.c | 24 +++++++------- block/io.c | 13 ++++---- block/parallels-ext.c | 4 +-- block/parallels.c | 12 +++---- block/qcow.c | 27 ++++++++------- block/qcow2-bitmap.c | 14 ++++---- block/qcow2-cache.c | 7 ++-- block/qcow2-cluster.c | 21 ++++++------ block/qcow2-refcount.c | 42 +++++++++++------------ block/qcow2-snapshot.c | 39 +++++++++++----------- block/qcow2.c | 44 ++++++++++++------------ block/qed.c | 8 ++--- block/vdi.c | 10 +++--- block/vhdx-log.c | 19 +++++------ block/vhdx.c | 32 ++++++++++-------- block/vmdk.c | 57 ++++++++++++++------------------ block/vpc.c | 19 ++++++----- block/vvfat.c | 7 ++-- tests/unit/test-block-iothread.c | 8 ++--- 24 files changed, 219 insertions(+), 219 deletions(-) diff --git a/include/block/block-io.h b/include/block/block-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-io.h +++ b/include/block/block-io.h @@ -XXX,XX +XXX,XX @@ int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset, int64_t bytes, BdrvRequestFlags flags); int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags); -int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int64_t bytes); +int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int64_t bytes, + BdrvRequestFlags flags); int bdrv_pwrite(BdrvChild *child, int64_t offset, const void *buf, - int64_t bytes); + int64_t bytes, BdrvRequestFlags flags); int bdrv_pwrite_sync(BdrvChild *child, int64_t offset, - const void *buf, int64_t bytes); + const void *buf, int64_t bytes, BdrvRequestFlags flags); /* * Efficiently zero a region of the disk image. Note that this is a regular * I/O request like read or write and should have a reasonable size. This diff --git a/block/blklogwrites.c b/block/blklogwrites.c index XXXXXXX..XXXXXXX 100644 --- a/block/blklogwrites.c +++ b/block/blklogwrites.c @@ -XXX,XX +XXX,XX @@ static uint64_t blk_log_writes_find_cur_log_sector(BdrvChild *log, while (cur_idx < nr_entries) { int read_ret = bdrv_pread(log, cur_sector << sector_bits, &cur_entry, - sizeof(cur_entry)); + sizeof(cur_entry), 0); if (read_ret < 0) { error_setg_errno(errp, -read_ret, "Failed to read log entry %"PRIu64, cur_idx); @@ -XXX,XX +XXX,XX @@ static int blk_log_writes_open(BlockDriverState *bs, QDict *options, int flags, log_sb.nr_entries = cpu_to_le64(0); log_sb.sectorsize = cpu_to_le32(BDRV_SECTOR_SIZE); } else { - ret = bdrv_pread(s->log_file, 0, &log_sb, sizeof(log_sb)); + ret = bdrv_pread(s->log_file, 0, &log_sb, sizeof(log_sb), 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read log superblock"); goto fail_log; diff --git a/block/bochs.c b/block/bochs.c index XXXXXXX..XXXXXXX 100644 --- a/block/bochs.c +++ b/block/bochs.c @@ -XXX,XX +XXX,XX @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags, return -EINVAL; } - ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs)); + ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs), 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags, } ret = bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_bitmap, - s->catalog_size * 4); + s->catalog_size * 4, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num) /* read in bitmap for current extent */ ret = bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8), - &bitmap_entry, 1); + &bitmap_entry, 1, 0); if (ret < 0) { return ret; } diff --git a/block/cloop.c b/block/cloop.c index XXXXXXX..XXXXXXX 100644 --- a/block/cloop.c +++ b/block/cloop.c @@ -XXX,XX +XXX,XX @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags, } /* read header */ - ret = bdrv_pread(bs->file, 128, &s->block_size, 4); + ret = bdrv_pread(bs->file, 128, &s->block_size, 4, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags, return -EINVAL; } - ret = bdrv_pread(bs->file, 128 + 4, &s->n_blocks, 4); + ret = bdrv_pread(bs->file, 128 + 4, &s->n_blocks, 4, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags, return -ENOMEM; } - ret = bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size); + ret = bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static inline int cloop_read_block(BlockDriverState *bs, int block_num) int ret; uint32_t bytes = s->offsets[block_num + 1] - s->offsets[block_num]; - ret = bdrv_pread(bs->file, s->offsets[block_num], - s->compressed_block, bytes); + ret = bdrv_pread(bs->file, s->offsets[block_num], s->compressed_block, + bytes, 0); if (ret != bytes) { return -1; } diff --git a/block/crypto.c b/block/crypto.c index XXXXXXX..XXXXXXX 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_read_func(QCryptoBlock *block, BlockDriverState *bs = opaque; ssize_t ret; - ret = bdrv_pread(bs->file, offset, buf, buflen); + ret = bdrv_pread(bs->file, offset, buf, buflen, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read encryption header"); return ret; @@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_write_func(QCryptoBlock *block, BlockDriverState *bs = opaque; ssize_t ret; - ret = bdrv_pwrite(bs->file, offset, buf, buflen); + ret = bdrv_pwrite(bs->file, offset, buf, buflen, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not write encryption header"); return ret; diff --git a/block/dmg.c b/block/dmg.c index XXXXXXX..XXXXXXX 100644 --- a/block/dmg.c +++ b/block/dmg.c @@ -XXX,XX +XXX,XX @@ static int read_uint64(BlockDriverState *bs, int64_t offset, uint64_t *result) uint64_t buffer; int ret; - ret = bdrv_pread(bs->file, offset, &buffer, 8); + ret = bdrv_pread(bs->file, offset, &buffer, 8, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int read_uint32(BlockDriverState *bs, int64_t offset, uint32_t *result) uint32_t buffer; int ret; - ret = bdrv_pread(bs->file, offset, &buffer, 4); + ret = bdrv_pread(bs->file, offset, &buffer, 4, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int64_t dmg_find_koly_offset(BdrvChild *file, Error **errp) offset = length - 511 - 512; } length = length < 515 ? length : 515; - ret = bdrv_pread(file, offset, buffer, length); + ret = bdrv_pread(file, offset, buffer, length, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed while reading UDIF trailer"); return ret; @@ -XXX,XX +XXX,XX @@ static int dmg_read_resource_fork(BlockDriverState *bs, DmgHeaderState *ds, offset += 4; buffer = g_realloc(buffer, count); - ret = bdrv_pread(bs->file, offset, buffer, count); + ret = bdrv_pread(bs->file, offset, buffer, count, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int dmg_read_plist_xml(BlockDriverState *bs, DmgHeaderState *ds, buffer = g_malloc(info_length + 1); buffer[info_length] = '\0'; - ret = bdrv_pread(bs->file, info_begin, buffer, info_length); + ret = bdrv_pread(bs->file, info_begin, buffer, info_length, 0); if (ret != info_length) { ret = -EINVAL; goto fail; @@ -XXX,XX +XXX,XX @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num) case UDZO: { /* zlib compressed */ /* we need to buffer, because only the chunk as whole can be * inflated. */ - ret = bdrv_pread(bs->file, s->offsets[chunk], - s->compressed_chunk, s->lengths[chunk]); + ret = bdrv_pread(bs->file, s->offsets[chunk], s->compressed_chunk, + s->lengths[chunk], 0); if (ret != s->lengths[chunk]) { return -1; } @@ -XXX,XX +XXX,XX @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num) } /* we need to buffer, because only the chunk as whole can be * inflated. */ - ret = bdrv_pread(bs->file, s->offsets[chunk], - s->compressed_chunk, s->lengths[chunk]); + ret = bdrv_pread(bs->file, s->offsets[chunk], s->compressed_chunk, + s->lengths[chunk], 0); if (ret != s->lengths[chunk]) { return -1; } @@ -XXX,XX +XXX,XX @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num) } /* we need to buffer, because only the chunk as whole can be * inflated. */ - ret = bdrv_pread(bs->file, s->offsets[chunk], - s->compressed_chunk, s->lengths[chunk]); + ret = bdrv_pread(bs->file, s->offsets[chunk], s->compressed_chunk, + s->lengths[chunk], 0); if (ret != s->lengths[chunk]) { return -1; } @@ -XXX,XX +XXX,XX @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num) break; case UDRW: /* copy */ ret = bdrv_pread(bs->file, s->offsets[chunk], - s->uncompressed_chunk, s->lengths[chunk]); + s->uncompressed_chunk, s->lengths[chunk], 0); if (ret != s->lengths[chunk]) { return -1; } diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) } /* See bdrv_pwrite() for the return codes */ -int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int64_t bytes) +int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int64_t bytes, + BdrvRequestFlags flags) { int ret; QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); @@ -XXX,XX +XXX,XX @@ int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int64_t bytes) return -EINVAL; } - ret = bdrv_preadv(child, offset, bytes, &qiov, 0); + ret = bdrv_preadv(child, offset, bytes, &qiov, flags); return ret < 0 ? ret : bytes; } @@ -XXX,XX +XXX,XX @@ int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int64_t bytes) -EACCES Trying to write a read-only device */ int bdrv_pwrite(BdrvChild *child, int64_t offset, const void *buf, - int64_t bytes) + int64_t bytes, BdrvRequestFlags flags) { int ret; QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); @@ -XXX,XX +XXX,XX @@ int bdrv_pwrite(BdrvChild *child, int64_t offset, const void *buf, return -EINVAL; } - ret = bdrv_pwritev(child, offset, bytes, &qiov, 0); + ret = bdrv_pwritev(child, offset, bytes, &qiov, flags); return ret < 0 ? ret : bytes; } @@ -XXX,XX +XXX,XX @@ int bdrv_pwrite(BdrvChild *child, int64_t offset, const void *buf, * Returns 0 on success, -errno in error cases. */ int bdrv_pwrite_sync(BdrvChild *child, int64_t offset, - const void *buf, int64_t count) + const void *buf, int64_t count, BdrvRequestFlags flags) { int ret; IO_CODE(); - ret = bdrv_pwrite(child, offset, buf, count); + ret = bdrv_pwrite(child, offset, buf, count, flags); if (ret < 0) { return ret; } diff --git a/block/parallels-ext.c b/block/parallels-ext.c index XXXXXXX..XXXXXXX 100644 --- a/block/parallels-ext.c +++ b/block/parallels-ext.c @@ -XXX,XX +XXX,XX @@ static int parallels_load_bitmap_data(BlockDriverState *bs, bdrv_dirty_bitmap_deserialize_ones(bitmap, offset, count, false); } else { ret = bdrv_pread(bs->file, entry << BDRV_SECTOR_BITS, buf, - s->cluster_size); + s->cluster_size, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read bitmap data cluster"); @@ -XXX,XX +XXX,XX @@ int parallels_read_format_extension(BlockDriverState *bs, assert(ext_off > 0); - ret = bdrv_pread(bs->file, ext_off, ext_cluster, s->cluster_size); + ret = bdrv_pread(bs->file, ext_off, ext_cluster, s->cluster_size, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read Format Extension cluster"); goto out; diff --git a/block/parallels.c b/block/parallels.c index XXXXXXX..XXXXXXX 100644 --- a/block/parallels.c +++ b/block/parallels.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int parallels_co_flush_to_os(BlockDriverState *bs) if (off + to_write > s->header_size) { to_write = s->header_size - off; } - ret = bdrv_pwrite(bs->file, off, (uint8_t *)s->header + off, - to_write); + ret = bdrv_pwrite(bs->file, off, (uint8_t *)s->header + off, to_write, + 0); if (ret < 0) { qemu_co_mutex_unlock(&s->lock); return ret; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn parallels_co_check(BlockDriverState *bs, ret = 0; if (flush_bat) { - ret = bdrv_pwrite_sync(bs->file, 0, s->header, s->header_size); + ret = bdrv_pwrite_sync(bs->file, 0, s->header, s->header_size, 0); if (ret < 0) { res->check_errors++; goto out; @@ -XXX,XX +XXX,XX @@ static int parallels_update_header(BlockDriverState *bs) if (size > s->header_size) { size = s->header_size; } - return bdrv_pwrite_sync(bs->file, 0, s->header, size); + return bdrv_pwrite_sync(bs->file, 0, s->header, size, 0); } static int parallels_open(BlockDriverState *bs, QDict *options, int flags, @@ -XXX,XX +XXX,XX @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags, return -EINVAL; } - ret = bdrv_pread(bs->file, 0, &ph, sizeof(ph)); + ret = bdrv_pread(bs->file, 0, &ph, sizeof(ph), 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags, s->header_size = size; } - ret = bdrv_pread(bs->file, 0, s->header, s->header_size); + ret = bdrv_pread(bs->file, 0, s->header, s->header_size, 0); if (ret < 0) { goto fail; } diff --git a/block/qcow.c b/block/qcow.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -XXX,XX +XXX,XX @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } - ret = bdrv_pread(bs->file, 0, &header, sizeof(header)); + ret = bdrv_pread(bs->file, 0, &header, sizeof(header), 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, } ret = bdrv_pread(bs->file, s->l1_table_offset, s->l1_table, - s->l1_size * sizeof(uint64_t)); + s->l1_size * sizeof(uint64_t), 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } ret = bdrv_pread(bs->file, header.backing_file_offset, - bs->auto_backing_file, len); + bs->auto_backing_file, len, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs, BLKDBG_EVENT(bs->file, BLKDBG_L1_UPDATE); ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset + l1_index * sizeof(tmp), - &tmp, sizeof(tmp)); + &tmp, sizeof(tmp), 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs, if (new_l2_table) { memset(l2_table, 0, s->l2_size * sizeof(uint64_t)); ret = bdrv_pwrite_sync(bs->file, l2_offset, l2_table, - s->l2_size * sizeof(uint64_t)); + s->l2_size * sizeof(uint64_t), 0); if (ret < 0) { return ret; } } else { ret = bdrv_pread(bs->file, l2_offset, l2_table, - s->l2_size * sizeof(uint64_t)); + s->l2_size * sizeof(uint64_t), 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs, /* write the cluster content */ BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO); ret = bdrv_pwrite(bs->file, cluster_offset, s->cluster_cache, - s->cluster_size); + s->cluster_size, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs, return -EIO; } BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO); - ret = bdrv_pwrite(bs->file, - cluster_offset + i, + ret = bdrv_pwrite(bs->file, cluster_offset + i, s->cluster_data, - BDRV_SECTOR_SIZE); + BDRV_SECTOR_SIZE, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs, BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE); } ret = bdrv_pwrite_sync(bs->file, l2_offset + l2_index * sizeof(tmp), - &tmp, sizeof(tmp)); + &tmp, sizeof(tmp), 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset) csize = cluster_offset >> (63 - s->cluster_bits); csize &= (s->cluster_size - 1); BLKDBG_EVENT(bs->file, BLKDBG_READ_COMPRESSED); - ret = bdrv_pread(bs->file, coffset, s->cluster_data, csize); + ret = bdrv_pread(bs->file, coffset, s->cluster_data, csize, 0); if (ret != csize) return -1; if (decompress_buffer(s->cluster_cache, s->cluster_size, @@ -XXX,XX +XXX,XX @@ static int qcow_make_empty(BlockDriverState *bs) int ret; memset(s->l1_table, 0, l1_length); - if (bdrv_pwrite_sync(bs->file, s->l1_table_offset, s->l1_table, - l1_length) < 0) + if (bdrv_pwrite_sync(bs->file, s->l1_table_offset, s->l1_table, l1_length, + 0) < 0) return -1; ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length, false, PREALLOC_MODE_OFF, 0, NULL); diff --git a/block/qcow2-bitmap.c b/block/qcow2-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-bitmap.c +++ b/block/qcow2-bitmap.c @@ -XXX,XX +XXX,XX @@ static int bitmap_table_load(BlockDriverState *bs, Qcow2BitmapTable *tb, } assert(tb->size <= BME_MAX_TABLE_SIZE); - ret = bdrv_pread(bs->file, tb->offset, - table, tb->size * BME_TABLE_ENTRY_SIZE); + ret = bdrv_pread(bs->file, tb->offset, table, + tb->size * BME_TABLE_ENTRY_SIZE, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int load_bitmap_data(BlockDriverState *bs, * already cleared */ } } else { - ret = bdrv_pread(bs->file, data_offset, buf, s->cluster_size); + ret = bdrv_pread(bs->file, data_offset, buf, s->cluster_size, 0); if (ret < 0) { goto finish; } @@ -XXX,XX +XXX,XX @@ static Qcow2BitmapList *bitmap_list_load(BlockDriverState *bs, uint64_t offset, } dir_end = dir + size; - ret = bdrv_pread(bs->file, offset, dir, size); + ret = bdrv_pread(bs->file, offset, dir, size, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read bitmap directory"); goto fail; @@ -XXX,XX +XXX,XX @@ static int bitmap_list_store(BlockDriverState *bs, Qcow2BitmapList *bm_list, goto fail; } - ret = bdrv_pwrite(bs->file, dir_offset, dir, dir_size); + ret = bdrv_pwrite(bs->file, dir_offset, dir, dir_size, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, goto fail; } - ret = bdrv_pwrite(bs->file, off, buf, s->cluster_size); + ret = bdrv_pwrite(bs->file, off, buf, s->cluster_size, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to write bitmap '%s' to file", bm_name); @@ -XXX,XX +XXX,XX @@ static int store_bitmap(BlockDriverState *bs, Qcow2Bitmap *bm, Error **errp) } bitmap_table_to_be(tb, tb_size); - ret = bdrv_pwrite(bs->file, tb_offset, tb, tb_size * sizeof(tb[0])); + ret = bdrv_pwrite(bs->file, tb_offset, tb, tb_size * sizeof(tb[0]), 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to write bitmap '%s' to file", bm_name); diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cache.c +++ b/block/qcow2-cache.c @@ -XXX,XX +XXX,XX @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i) } ret = bdrv_pwrite(bs->file, c->entries[i].offset, - qcow2_cache_get_table_addr(c, i), c->table_size); + qcow2_cache_get_table_addr(c, i), c->table_size, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c, BLKDBG_EVENT(bs->file, BLKDBG_L2_LOAD); } - ret = bdrv_pread(bs->file, offset, - qcow2_cache_get_table_addr(c, i), - c->table_size); + ret = bdrv_pread(bs->file, offset, qcow2_cache_get_table_addr(c, i), + c->table_size, 0); if (ret < 0) { return ret; } diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size, BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_WRITE_TABLE); for(i = 0; i < s->l1_size; i++) new_l1_table[i] = cpu_to_be64(new_l1_table[i]); - ret = bdrv_pwrite_sync(bs->file, new_l1_table_offset, - new_l1_table, new_l1_size2); + ret = bdrv_pwrite_sync(bs->file, new_l1_table_offset, new_l1_table, + new_l1_size2, 0); if (ret < 0) goto fail; for(i = 0; i < s->l1_size; i++) @@ -XXX,XX +XXX,XX @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size, BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_ACTIVATE_TABLE); stl_be_p(data, new_l1_size); stq_be_p(data + 4, new_l1_table_offset); - ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, l1_size), - data, sizeof(data)); + ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, l1_size), data, + sizeof(data), 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index) BLKDBG_EVENT(bs->file, BLKDBG_L1_UPDATE); ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset + L1E_SIZE * l1_start_index, - buf, bufsize); + buf, bufsize, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, (void **)&l2_slice); } else { /* load inactive L2 tables from disk */ - ret = bdrv_pread(bs->file, slice_offset, l2_slice, slice_size2); + ret = bdrv_pread(bs->file, slice_offset, l2_slice, + slice_size2, 0); } if (ret < 0) { goto fail; @@ -XXX,XX +XXX,XX @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, goto fail; } - ret = bdrv_pwrite(bs->file, slice_offset, - l2_slice, slice_size2); + ret = bdrv_pwrite(bs->file, slice_offset, l2_slice, + slice_size2, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_expand_zero_clusters(BlockDriverState *bs, l1_table = new_l1_table; - ret = bdrv_pread(bs->file, s->snapshots[i].l1_table_offset, - l1_table, l1_size2); + ret = bdrv_pread(bs->file, s->snapshots[i].l1_table_offset, l1_table, + l1_size2, 0); if (ret < 0) { goto fail; } diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -XXX,XX +XXX,XX @@ int qcow2_refcount_init(BlockDriverState *bs) } BLKDBG_EVENT(bs->file, BLKDBG_REFTABLE_LOAD); ret = bdrv_pread(bs->file, s->refcount_table_offset, - s->refcount_table, refcount_table_size2); + s->refcount_table, refcount_table_size2, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int alloc_refcount_block(BlockDriverState *bs, BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_HOOKUP); ret = bdrv_pwrite_sync(bs->file, s->refcount_table_offset + refcount_table_index * REFTABLE_ENTRY_SIZE, - &data64, sizeof(data64)); + &data64, sizeof(data64), 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int64_t qcow2_refcount_area(BlockDriverState *bs, uint64_t start_offset, BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_WRITE_TABLE); ret = bdrv_pwrite_sync(bs->file, table_offset, new_table, - table_size * REFTABLE_ENTRY_SIZE); + table_size * REFTABLE_ENTRY_SIZE, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int64_t qcow2_refcount_area(BlockDriverState *bs, uint64_t start_offset, data.d32 = cpu_to_be32(table_clusters); BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_SWITCH_TABLE); ret = bdrv_pwrite_sync(bs->file, - offsetof(QCowHeader, refcount_table_offset), - &data, sizeof(data)); + offsetof(QCowHeader, refcount_table_offset), &data, + sizeof(data), 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs, } l1_allocated = true; - ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size2); + ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size2, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ fail: cpu_to_be64s(&l1_table[i]); } - ret = bdrv_pwrite_sync(bs->file, l1_table_offset, - l1_table, l1_size2); + ret = bdrv_pwrite_sync(bs->file, l1_table_offset, l1_table, l1_size2, + 0); for (i = 0; i < l1_size; i++) { be64_to_cpus(&l1_table[i]); @@ -XXX,XX +XXX,XX @@ static int fix_l2_entry_by_zero(BlockDriverState *bs, BdrvCheckResult *res, } ret = bdrv_pwrite_sync(bs->file, l2e_offset, &l2_table[idx], - l2_entry_size(s)); + l2_entry_size(s), 0); if (ret < 0) { fprintf(stderr, "ERROR: Failed to overwrite L2 " "table entry: %s\n", strerror(-ret)); @@ -XXX,XX +XXX,XX @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res, bool metadata_overlap; /* Read L2 table from disk */ - ret = bdrv_pread(bs->file, l2_offset, l2_table, l2_size_bytes); + ret = bdrv_pread(bs->file, l2_offset, l2_table, l2_size_bytes, 0); if (ret < 0) { fprintf(stderr, "ERROR: I/O error in check_refcounts_l2\n"); res->check_errors++; @@ -XXX,XX +XXX,XX @@ static int check_refcounts_l1(BlockDriverState *bs, } /* Read L1 table entries from disk */ - ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size_bytes); + ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size_bytes, 0); if (ret < 0) { fprintf(stderr, "ERROR: I/O error in check_refcounts_l1\n"); res->check_errors++; @@ -XXX,XX +XXX,XX @@ static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res, } ret = bdrv_pread(bs->file, l2_offset, l2_table, - s->l2_size * l2_entry_size(s)); + s->l2_size * l2_entry_size(s), 0); if (ret < 0) { fprintf(stderr, "ERROR: Could not read L2 table: %s\n", strerror(-ret)); @@ -XXX,XX +XXX,XX @@ static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res, goto fail; } - ret = bdrv_pwrite(bs->file, l2_offset, l2_table, - s->cluster_size); + ret = bdrv_pwrite(bs->file, l2_offset, l2_table, s->cluster_size, + 0); if (ret < 0) { fprintf(stderr, "ERROR: Could not write L2 table: %s\n", strerror(-ret)); @@ -XXX,XX +XXX,XX @@ static int rebuild_refcounts_write_refblocks( refblock_index * s->cluster_size); ret = bdrv_pwrite(bs->file, refblock_offset, on_disk_refblock, - s->cluster_size); + s->cluster_size, 0); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR writing refblock"); return ret; @@ -XXX,XX +XXX,XX @@ static int rebuild_refcount_structure(BlockDriverState *bs, assert(reftable_length < INT_MAX); ret = bdrv_pwrite(bs->file, reftable_offset, on_disk_reftable, - reftable_length); + reftable_length, 0); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR writing reftable"); goto fail; @@ -XXX,XX +XXX,XX @@ static int rebuild_refcount_structure(BlockDriverState *bs, ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, refcount_table_offset), &reftable_offset_and_clusters, - sizeof(reftable_offset_and_clusters)); + sizeof(reftable_offset_and_clusters), 0); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR setting reftable"); goto fail; @@ -XXX,XX +XXX,XX @@ int qcow2_check_metadata_overlap(BlockDriverState *bs, int ign, int64_t offset, return -ENOMEM; } - ret = bdrv_pread(bs->file, l1_ofs, l1, l1_sz2); + ret = bdrv_pread(bs->file, l1_ofs, l1, l1_sz2, 0); if (ret < 0) { g_free(l1); return ret; @@ -XXX,XX +XXX,XX @@ static int flush_refblock(BlockDriverState *bs, uint64_t **reftable, return ret; } - ret = bdrv_pwrite(bs->file, offset, refblock, s->cluster_size); + ret = bdrv_pwrite(bs->file, offset, refblock, s->cluster_size, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to write refblock"); return ret; @@ -XXX,XX +XXX,XX @@ int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order, } ret = bdrv_pwrite(bs->file, new_reftable_offset, new_reftable, - new_reftable_size * REFTABLE_ENTRY_SIZE); + new_reftable_size * REFTABLE_ENTRY_SIZE, 0); for (i = 0; i < new_reftable_size; i++) { be64_to_cpus(&new_reftable[i]); @@ -XXX,XX +XXX,XX @@ int qcow2_shrink_reftable(BlockDriverState *bs) } ret = bdrv_pwrite_sync(bs->file, s->refcount_table_offset, reftable_tmp, - s->refcount_table_size * REFTABLE_ENTRY_SIZE); + s->refcount_table_size * REFTABLE_ENTRY_SIZE, 0); /* * If the write in the reftable failed the image may contain a partially * overwritten reftable. In this case it would be better to clear the diff --git a/block/qcow2-snapshot.c b/block/qcow2-snapshot.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-snapshot.c +++ b/block/qcow2-snapshot.c @@ -XXX,XX +XXX,XX @@ static int qcow2_do_read_snapshots(BlockDriverState *bs, bool repair, /* Read statically sized part of the snapshot header */ offset = ROUND_UP(offset, 8); - ret = bdrv_pread(bs->file, offset, &h, sizeof(h)); + ret = bdrv_pread(bs->file, offset, &h, sizeof(h), 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read snapshot table"); goto fail; @@ -XXX,XX +XXX,XX @@ static int qcow2_do_read_snapshots(BlockDriverState *bs, bool repair, /* Read known extra data */ ret = bdrv_pread(bs->file, offset, &extra, - MIN(sizeof(extra), sn->extra_data_size)); + MIN(sizeof(extra), sn->extra_data_size), 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read snapshot table"); goto fail; @@ -XXX,XX +XXX,XX @@ static int qcow2_do_read_snapshots(BlockDriverState *bs, bool repair, unknown_extra_data_size = sn->extra_data_size - sizeof(extra); sn->unknown_extra_data = g_malloc(unknown_extra_data_size); ret = bdrv_pread(bs->file, offset, sn->unknown_extra_data, - unknown_extra_data_size); + unknown_extra_data_size, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read snapshot table"); @@ -XXX,XX +XXX,XX @@ static int qcow2_do_read_snapshots(BlockDriverState *bs, bool repair, /* Read snapshot ID */ sn->id_str = g_malloc(id_str_size + 1); - ret = bdrv_pread(bs->file, offset, sn->id_str, id_str_size); + ret = bdrv_pread(bs->file, offset, sn->id_str, id_str_size, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read snapshot table"); goto fail; @@ -XXX,XX +XXX,XX @@ static int qcow2_do_read_snapshots(BlockDriverState *bs, bool repair, /* Read snapshot name */ sn->name = g_malloc(name_size + 1); - ret = bdrv_pread(bs->file, offset, sn->name, name_size); + ret = bdrv_pread(bs->file, offset, sn->name, name_size, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read snapshot table"); goto fail; @@ -XXX,XX +XXX,XX @@ int qcow2_write_snapshots(BlockDriverState *bs) h.name_size = cpu_to_be16(name_size); offset = ROUND_UP(offset, 8); - ret = bdrv_pwrite(bs->file, offset, &h, sizeof(h)); + ret = bdrv_pwrite(bs->file, offset, &h, sizeof(h), 0); if (ret < 0) { goto fail; } offset += sizeof(h); - ret = bdrv_pwrite(bs->file, offset, &extra, sizeof(extra)); + ret = bdrv_pwrite(bs->file, offset, &extra, sizeof(extra), 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_write_snapshots(BlockDriverState *bs) assert(sn->unknown_extra_data); ret = bdrv_pwrite(bs->file, offset, sn->unknown_extra_data, - unknown_extra_data_size); + unknown_extra_data_size, 0); if (ret < 0) { goto fail; } offset += unknown_extra_data_size; } - ret = bdrv_pwrite(bs->file, offset, sn->id_str, id_str_size); + ret = bdrv_pwrite(bs->file, offset, sn->id_str, id_str_size, 0); if (ret < 0) { goto fail; } offset += id_str_size; - ret = bdrv_pwrite(bs->file, offset, sn->name, name_size); + ret = bdrv_pwrite(bs->file, offset, sn->name, name_size, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_write_snapshots(BlockDriverState *bs) header_data.snapshots_offset = cpu_to_be64(snapshots_offset); ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots), - &header_data, sizeof(header_data)); + &header_data, sizeof(header_data), 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int coroutine_fn qcow2_check_read_snapshot_table(BlockDriverState *bs, /* qcow2_do_open() discards this information in check mode */ ret = bdrv_pread(bs->file, offsetof(QCowHeader, nb_snapshots), - &snapshot_table_pointer, sizeof(snapshot_table_pointer)); + &snapshot_table_pointer, sizeof(snapshot_table_pointer), + 0); if (ret < 0) { result->check_errors++; fprintf(stderr, "ERROR failed to read the snapshot table pointer from " @@ -XXX,XX +XXX,XX @@ int coroutine_fn qcow2_check_read_snapshot_table(BlockDriverState *bs, snapshot_table_pointer.nb_snapshots = cpu_to_be32(s->nb_snapshots); ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots), &snapshot_table_pointer.nb_snapshots, - sizeof(snapshot_table_pointer.nb_snapshots)); + sizeof(snapshot_table_pointer.nb_snapshots), 0); if (ret < 0) { result->check_errors++; fprintf(stderr, "ERROR failed to update the snapshot count in the " @@ -XXX,XX +XXX,XX @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info) } ret = bdrv_pwrite(bs->file, sn->l1_table_offset, l1_table, - s->l1_size * L1E_SIZE); + s->l1_size * L1E_SIZE, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id) goto fail; } - ret = bdrv_pread(bs->file, sn->l1_table_offset, - sn_l1_table, sn_l1_bytes); + ret = bdrv_pread(bs->file, sn->l1_table_offset, sn_l1_table, sn_l1_bytes, + 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id) } ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset, sn_l1_table, - cur_l1_bytes); + cur_l1_bytes, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_snapshot_load_tmp(BlockDriverState *bs, return -ENOMEM; } - ret = bdrv_pread(bs->file, sn->l1_table_offset, - new_l1_table, new_l1_bytes); + ret = bdrv_pread(bs->file, sn->l1_table_offset, new_l1_table, + new_l1_bytes, 0); if (ret < 0) { error_setg(errp, "Failed to read l1 table for snapshot"); qemu_vfree(new_l1_table); diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static ssize_t qcow2_crypto_hdr_read_func(QCryptoBlock *block, size_t offset, return -1; } - ret = bdrv_pread(bs->file, - s->crypto_header.offset + offset, buf, buflen); + ret = bdrv_pread(bs->file, s->crypto_header.offset + offset, buf, buflen, + 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read encryption header"); return -1; @@ -XXX,XX +XXX,XX @@ static ssize_t qcow2_crypto_hdr_write_func(QCryptoBlock *block, size_t offset, return -1; } - ret = bdrv_pwrite(bs->file, - s->crypto_header.offset + offset, buf, buflen); + ret = bdrv_pwrite(bs->file, s->crypto_header.offset + offset, buf, buflen, + 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read encryption header"); return -1; @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, printf("attempting to read extended header in offset %lu\n", offset); #endif - ret = bdrv_pread(bs->file, offset, &ext, sizeof(ext)); + ret = bdrv_pread(bs->file, offset, &ext, sizeof(ext), 0); if (ret < 0) { error_setg_errno(errp, -ret, "qcow2_read_extension: ERROR: " "pread fail from offset %" PRIu64, offset); @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, sizeof(bs->backing_format)); return 2; } - ret = bdrv_pread(bs->file, offset, bs->backing_format, ext.len); + ret = bdrv_pread(bs->file, offset, bs->backing_format, ext.len, 0); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR: ext_backing_format: " "Could not read format name"); @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, case QCOW2_EXT_MAGIC_FEATURE_TABLE: if (p_feature_table != NULL) { void *feature_table = g_malloc0(ext.len + 2 * sizeof(Qcow2Feature)); - ret = bdrv_pread(bs->file, offset , feature_table, ext.len); + ret = bdrv_pread(bs->file, offset, feature_table, ext.len, 0); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR: ext_feature_table: " "Could not read table"); @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, return -EINVAL; } - ret = bdrv_pread(bs->file, offset, &s->crypto_header, ext.len); + ret = bdrv_pread(bs->file, offset, &s->crypto_header, ext.len, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Unable to read CRYPTO header extension"); @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, break; } - ret = bdrv_pread(bs->file, offset, &bitmaps_ext, ext.len); + ret = bdrv_pread(bs->file, offset, &bitmaps_ext, ext.len, 0); if (ret < 0) { error_setg_errno(errp, -ret, "bitmaps_ext: " "Could not read ext header"); @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, case QCOW2_EXT_MAGIC_DATA_FILE: { s->image_data_file = g_malloc0(ext.len + 1); - ret = bdrv_pread(bs->file, offset, s->image_data_file, ext.len); + ret = bdrv_pread(bs->file, offset, s->image_data_file, ext.len, 0); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR: Could not read data file name"); @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, uext->len = ext.len; QLIST_INSERT_HEAD(&s->unknown_header_ext, uext, next); - ret = bdrv_pread(bs->file, offset , uext->data, uext->len); + ret = bdrv_pread(bs->file, offset, uext->data, uext->len, 0); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR: unknown extension: " "Could not read data"); @@ -XXX,XX +XXX,XX @@ int qcow2_mark_dirty(BlockDriverState *bs) val = cpu_to_be64(s->incompatible_features | QCOW2_INCOMPAT_DIRTY); ret = bdrv_pwrite(bs->file, offsetof(QCowHeader, incompatible_features), - &val, sizeof(val)); + &val, sizeof(val), 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, uint64_t l1_vm_state_index; bool update_header = false; - ret = bdrv_pread(bs->file, 0, &header, sizeof(header)); + ret = bdrv_pread(bs->file, 0, &header, sizeof(header), 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read qcow2 header"); goto fail; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, s->unknown_header_fields_size = header.header_length - sizeof(header); s->unknown_header_fields = g_malloc(s->unknown_header_fields_size); ret = bdrv_pread(bs->file, sizeof(header), s->unknown_header_fields, - s->unknown_header_fields_size); + s->unknown_header_fields_size, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read unknown qcow2 header " "fields"); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, goto fail; } ret = bdrv_pread(bs->file, s->l1_table_offset, s->l1_table, - s->l1_size * L1E_SIZE); + s->l1_size * L1E_SIZE, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read L1 table"); goto fail; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, goto fail; } ret = bdrv_pread(bs->file, header.backing_file_offset, - bs->auto_backing_file, len); + bs->auto_backing_file, len, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read backing file name"); goto fail; @@ -XXX,XX +XXX,XX @@ int qcow2_update_header(BlockDriverState *bs) } /* Write the new header */ - ret = bdrv_pwrite(bs->file, 0, header, s->cluster_size); + ret = bdrv_pwrite(bs->file, 0, header, s->cluster_size, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset, /* write updated header.size */ offset = cpu_to_be64(offset); - ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, size), - &offset, sizeof(offset)); + ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, size), &offset, + sizeof(offset), 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to update the image size"); goto fail; @@ -XXX,XX +XXX,XX @@ static int make_completely_empty(BlockDriverState *bs) l1_ofs_rt_ofs_cls.reftable_offset = cpu_to_be64(s->cluster_size); l1_ofs_rt_ofs_cls.reftable_clusters = cpu_to_be32(1); ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, l1_table_offset), - &l1_ofs_rt_ofs_cls, sizeof(l1_ofs_rt_ofs_cls)); + &l1_ofs_rt_ofs_cls, sizeof(l1_ofs_rt_ofs_cls), 0); if (ret < 0) { goto fail_broken_refcounts; } @@ -XXX,XX +XXX,XX @@ static int make_completely_empty(BlockDriverState *bs) /* Enter the first refblock into the reftable */ rt_entry = cpu_to_be64(2 * s->cluster_size); - ret = bdrv_pwrite_sync(bs->file, s->cluster_size, - &rt_entry, sizeof(rt_entry)); + ret = bdrv_pwrite_sync(bs->file, s->cluster_size, &rt_entry, + sizeof(rt_entry), 0); if (ret < 0) { goto fail_broken_refcounts; } diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ int qed_write_header_sync(BDRVQEDState *s) int ret; qed_header_cpu_to_le(&s->header, &le); - ret = bdrv_pwrite(s->bs->file, 0, &le, sizeof(le)); + ret = bdrv_pwrite(s->bs->file, 0, &le, sizeof(le), 0); if (ret != sizeof(le)) { return ret; } @@ -XXX,XX +XXX,XX @@ static int qed_read_string(BdrvChild *file, uint64_t offset, size_t n, if (n >= buflen) { return -EINVAL; } - ret = bdrv_pread(file, offset, buf, n); + ret = bdrv_pread(file, offset, buf, n, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_do_open(BlockDriverState *bs, QDict *options, int64_t file_size; int ret; - ret = bdrv_pread(bs->file, 0, &le_header, sizeof(le_header)); + ret = bdrv_pread(bs->file, 0, &le_header, sizeof(le_header), 0); if (ret < 0) { error_setg(errp, "Failed to read QED header"); return ret; @@ -XXX,XX +XXX,XX @@ static int bdrv_qed_change_backing_file(BlockDriverState *bs, } /* Write new header */ - ret = bdrv_pwrite_sync(bs->file, 0, buffer, buffer_len); + ret = bdrv_pwrite_sync(bs->file, 0, buffer, buffer_len, 0); g_free(buffer); if (ret == 0) { memcpy(&s->header, &new_header, sizeof(new_header)); diff --git a/block/vdi.c b/block/vdi.c index XXXXXXX..XXXXXXX 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -XXX,XX +XXX,XX @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags, logout("\n"); - ret = bdrv_pread(bs->file, 0, &header, sizeof(header)); + ret = bdrv_pread(bs->file, 0, &header, sizeof(header), 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags, } ret = bdrv_pread(bs->file, header.offset_bmap, s->bmap, - bmap_size * SECTOR_SIZE); + bmap_size * SECTOR_SIZE, 0); if (ret < 0) { goto fail_free_bmap; } @@ -XXX,XX +XXX,XX @@ vdi_co_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes, * so this full-cluster write does not overlap a partial write * of the same cluster, issued from the "else" branch. */ - ret = bdrv_pwrite(bs->file, data_offset, block, s->block_size); + ret = bdrv_pwrite(bs->file, data_offset, block, s->block_size, 0); qemu_co_rwlock_unlock(&s->bmap_lock); } else { nonallocating_write: @@ -XXX,XX +XXX,XX @@ nonallocating_write: assert(VDI_IS_ALLOCATED(bmap_first)); *header = s->header; vdi_header_to_le(header); - ret = bdrv_pwrite(bs->file, 0, header, sizeof(*header)); + ret = bdrv_pwrite(bs->file, 0, header, sizeof(*header), 0); g_free(header); if (ret < 0) { @@ -XXX,XX +XXX,XX @@ nonallocating_write: logout("will write %u block map sectors starting from entry %u\n", n_sectors, bmap_first); ret = bdrv_pwrite(bs->file, offset * SECTOR_SIZE, base, - n_sectors * SECTOR_SIZE); + n_sectors * SECTOR_SIZE, 0); } return ret < 0 ? ret : 0; diff --git a/block/vhdx-log.c b/block/vhdx-log.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx-log.c +++ b/block/vhdx-log.c @@ -XXX,XX +XXX,XX @@ static int vhdx_log_peek_hdr(BlockDriverState *bs, VHDXLogEntries *log, offset = log->offset + read; - ret = bdrv_pread(bs->file, offset, hdr, sizeof(VHDXLogEntryHeader)); + ret = bdrv_pread(bs->file, offset, hdr, sizeof(VHDXLogEntryHeader), 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_log_read_sectors(BlockDriverState *bs, VHDXLogEntries *log, } offset = log->offset + read; - ret = bdrv_pread(bs->file, offset, buffer, VHDX_LOG_SECTOR_SIZE); + ret = bdrv_pread(bs->file, offset, buffer, VHDX_LOG_SECTOR_SIZE, 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_log_write_sectors(BlockDriverState *bs, VHDXLogEntries *log, /* full */ break; } - ret = bdrv_pwrite(bs->file, offset, buffer_tmp, - VHDX_LOG_SECTOR_SIZE); + ret = bdrv_pwrite(bs->file, offset, buffer_tmp, VHDX_LOG_SECTOR_SIZE, + 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_log_flush_desc(BlockDriverState *bs, VHDXLogDescriptor *desc, /* count is only > 1 if we are writing zeroes */ for (i = 0; i < count; i++) { ret = bdrv_pwrite_sync(bs->file, file_offset, buffer, - VHDX_LOG_SECTOR_SIZE); + VHDX_LOG_SECTOR_SIZE, 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s, if (i == 0 && leading_length) { /* partial sector at the front of the buffer */ ret = bdrv_pread(bs->file, file_offset, merged_sector, - VHDX_LOG_SECTOR_SIZE); + VHDX_LOG_SECTOR_SIZE, 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s, sector_write = merged_sector; } else if (i == sectors - 1 && trailing_length) { /* partial sector at the end of the buffer */ - ret = bdrv_pread(bs->file, - file_offset, - merged_sector + trailing_length, - VHDX_LOG_SECTOR_SIZE - trailing_length); + ret = bdrv_pread(bs->file, file_offset, + merged_sector + trailing_length, + VHDX_LOG_SECTOR_SIZE - trailing_length, 0); if (ret < 0) { goto exit; } diff --git a/block/vhdx.c b/block/vhdx.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -XXX,XX +XXX,XX @@ static int vhdx_write_header(BdrvChild *file, VHDXHeader *hdr, buffer = qemu_blockalign(bs_file, VHDX_HEADER_SIZE); if (read) { /* if true, we can't assume the extra reserved bytes are 0 */ - ret = bdrv_pread(file, offset, buffer, VHDX_HEADER_SIZE); + ret = bdrv_pread(file, offset, buffer, VHDX_HEADER_SIZE, 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_write_header(BdrvChild *file, VHDXHeader *hdr, vhdx_header_le_export(hdr, header_le); vhdx_update_checksum(buffer, VHDX_HEADER_SIZE, offsetof(VHDXHeader, checksum)); - ret = bdrv_pwrite_sync(file, offset, header_le, sizeof(VHDXHeader)); + ret = bdrv_pwrite_sync(file, offset, header_le, sizeof(VHDXHeader), 0); exit: qemu_vfree(buffer); @@ -XXX,XX +XXX,XX @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s, /* We have to read the whole VHDX_HEADER_SIZE instead of * sizeof(VHDXHeader), because the checksum is over the whole * region */ - ret = bdrv_pread(bs->file, VHDX_HEADER1_OFFSET, buffer, - VHDX_HEADER_SIZE); + ret = bdrv_pread(bs->file, VHDX_HEADER1_OFFSET, buffer, VHDX_HEADER_SIZE, + 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s, } } - ret = bdrv_pread(bs->file, VHDX_HEADER2_OFFSET, buffer, - VHDX_HEADER_SIZE); + ret = bdrv_pread(bs->file, VHDX_HEADER2_OFFSET, buffer, VHDX_HEADER_SIZE, + 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int vhdx_open_region_tables(BlockDriverState *bs, BDRVVHDXState *s) buffer = qemu_blockalign(bs, VHDX_HEADER_BLOCK_SIZE); ret = bdrv_pread(bs->file, VHDX_REGION_TABLE_OFFSET, buffer, - VHDX_HEADER_BLOCK_SIZE); + VHDX_HEADER_BLOCK_SIZE, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) buffer = qemu_blockalign(bs, VHDX_METADATA_TABLE_MAX_SIZE); ret = bdrv_pread(bs->file, s->metadata_rt.file_offset, buffer, - VHDX_METADATA_TABLE_MAX_SIZE); + VHDX_METADATA_TABLE_MAX_SIZE, 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) s->metadata_entries.file_parameters_entry.offset + s->metadata_rt.file_offset, &s->params, - sizeof(s->params)); + sizeof(s->params), + 0); if (ret < 0) { goto exit; @@ -XXX,XX +XXX,XX @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) s->metadata_entries.virtual_disk_size_entry.offset + s->metadata_rt.file_offset, &s->virtual_disk_size, - sizeof(uint64_t)); + sizeof(uint64_t), + 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) s->metadata_entries.logical_sector_size_entry.offset + s->metadata_rt.file_offset, &s->logical_sector_size, - sizeof(uint32_t)); + sizeof(uint32_t), + 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) s->metadata_entries.phys_sector_size_entry.offset + s->metadata_rt.file_offset, &s->physical_sector_size, - sizeof(uint32_t)); + sizeof(uint32_t), + 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags, QLIST_INIT(&s->regions); /* validate the file signature */ - ret = bdrv_pread(bs->file, 0, &signature, sizeof(uint64_t)); + ret = bdrv_pread(bs->file, 0, &signature, sizeof(uint64_t), 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } - ret = bdrv_pread(bs->file, s->bat_offset, s->bat, s->bat_rt.length); + ret = bdrv_pread(bs->file, s->bat_offset, s->bat, s->bat_rt.length, 0); if (ret < 0) { goto fail; } diff --git a/block/vmdk.c b/block/vmdk.c index XXXXXXX..XXXXXXX 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -XXX,XX +XXX,XX @@ static int vmdk_read_cid(BlockDriverState *bs, int parent, uint32_t *pcid) int ret; desc = g_malloc0(DESC_SIZE); - ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE); + ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE, 0); if (ret < 0) { goto out; } @@ -XXX,XX +XXX,XX @@ static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid) desc = g_malloc0(DESC_SIZE); tmp_desc = g_malloc0(DESC_SIZE); - ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE); + ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE, 0); if (ret < 0) { goto out; } @@ -XXX,XX +XXX,XX @@ static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid) pstrcat(desc, DESC_SIZE, tmp_desc); } - ret = bdrv_pwrite_sync(bs->file, s->desc_offset, desc, DESC_SIZE); + ret = bdrv_pwrite_sync(bs->file, s->desc_offset, desc, DESC_SIZE, 0); out: g_free(desc); @@ -XXX,XX +XXX,XX @@ static int vmdk_parent_open(BlockDriverState *bs) int ret; desc = g_malloc0(DESC_SIZE + 1); - ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE); + ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE, 0); if (ret < 0) { goto out; } @@ -XXX,XX +XXX,XX @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent, return -ENOMEM; } - ret = bdrv_pread(extent->file, - extent->l1_table_offset, - extent->l1_table, - l1_size); + ret = bdrv_pread(extent->file, extent->l1_table_offset, extent->l1_table, + l1_size, 0); if (ret < 0) { bdrv_refresh_filename(extent->file->bs); error_setg_errno(errp, -ret, @@ -XXX,XX +XXX,XX @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent, ret = -ENOMEM; goto fail_l1; } - ret = bdrv_pread(extent->file, - extent->l1_backup_table_offset, - extent->l1_backup_table, - l1_size); + ret = bdrv_pread(extent->file, extent->l1_backup_table_offset, + extent->l1_backup_table, l1_size, 0); if (ret < 0) { bdrv_refresh_filename(extent->file->bs); error_setg_errno(errp, -ret, @@ -XXX,XX +XXX,XX @@ static int vmdk_open_vmfs_sparse(BlockDriverState *bs, VMDK3Header header; VmdkExtent *extent = NULL; - ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header)); + ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header), 0); if (ret < 0) { bdrv_refresh_filename(file->bs); error_setg_errno(errp, -ret, @@ -XXX,XX +XXX,XX @@ static int vmdk_open_se_sparse(BlockDriverState *bs, assert(sizeof(const_header) == SECTOR_SIZE); - ret = bdrv_pread(file, 0, &const_header, sizeof(const_header)); + ret = bdrv_pread(file, 0, &const_header, sizeof(const_header), 0); if (ret < 0) { bdrv_refresh_filename(file->bs); error_setg_errno(errp, -ret, @@ -XXX,XX +XXX,XX @@ static int vmdk_open_se_sparse(BlockDriverState *bs, assert(sizeof(volatile_header) == SECTOR_SIZE); - ret = bdrv_pread(file, - const_header.volatile_header_offset * SECTOR_SIZE, - &volatile_header, sizeof(volatile_header)); + ret = bdrv_pread(file, const_header.volatile_header_offset * SECTOR_SIZE, + &volatile_header, sizeof(volatile_header), 0); if (ret < 0) { bdrv_refresh_filename(file->bs); error_setg_errno(errp, -ret, @@ -XXX,XX +XXX,XX @@ static char *vmdk_read_desc(BdrvChild *file, uint64_t desc_offset, Error **errp) size = MIN(size, (1 << 20) - 1); /* avoid unbounded allocation */ buf = g_malloc(size + 1); - ret = bdrv_pread(file, desc_offset, buf, size); + ret = bdrv_pread(file, desc_offset, buf, size, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read from file"); g_free(buf); @@ -XXX,XX +XXX,XX @@ static int vmdk_open_vmdk4(BlockDriverState *bs, int64_t l1_backup_offset = 0; bool compressed; - ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header)); + ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header), 0); if (ret < 0) { bdrv_refresh_filename(file->bs); error_setg_errno(errp, -ret, @@ -XXX,XX +XXX,XX @@ static int vmdk_open_vmdk4(BlockDriverState *bs, } QEMU_PACKED eos_marker; } QEMU_PACKED footer; - ret = bdrv_pread(file, - bs->file->bs->total_sectors * 512 - 1536, - &footer, sizeof(footer)); + ret = bdrv_pread(file, bs->file->bs->total_sectors * 512 - 1536, + &footer, sizeof(footer), 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read footer"); return ret; @@ -XXX,XX +XXX,XX @@ static int get_whole_cluster(BlockDriverState *bs, /* qcow2 emits this on bs->file instead of bs->backing */ BLKDBG_EVENT(extent->file, BLKDBG_COW_READ); ret = bdrv_pread(bs->backing, offset, whole_grain, - skip_start_bytes); + skip_start_bytes, 0); if (ret < 0) { ret = VMDK_ERROR; goto exit; @@ -XXX,XX +XXX,XX @@ static int get_whole_cluster(BlockDriverState *bs, } BLKDBG_EVENT(extent->file, BLKDBG_COW_WRITE); ret = bdrv_pwrite(extent->file, cluster_offset, whole_grain, - skip_start_bytes); + skip_start_bytes, 0); if (ret < 0) { ret = VMDK_ERROR; goto exit; @@ -XXX,XX +XXX,XX @@ static int get_whole_cluster(BlockDriverState *bs, BLKDBG_EVENT(extent->file, BLKDBG_COW_READ); ret = bdrv_pread(bs->backing, offset + skip_end_bytes, whole_grain + skip_end_bytes, - cluster_bytes - skip_end_bytes); + cluster_bytes - skip_end_bytes, 0); if (ret < 0) { ret = VMDK_ERROR; goto exit; @@ -XXX,XX +XXX,XX @@ static int get_whole_cluster(BlockDriverState *bs, BLKDBG_EVENT(extent->file, BLKDBG_COW_WRITE); ret = bdrv_pwrite(extent->file, cluster_offset + skip_end_bytes, whole_grain + skip_end_bytes, - cluster_bytes - skip_end_bytes); + cluster_bytes - skip_end_bytes, 0); if (ret < 0) { ret = VMDK_ERROR; goto exit; @@ -XXX,XX +XXX,XX @@ static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data, if (bdrv_pwrite(extent->file, ((int64_t)m_data->l2_offset * 512) + (m_data->l2_index * sizeof(offset)), - &offset, sizeof(offset)) < 0) { + &offset, sizeof(offset), 0) < 0) { return VMDK_ERROR; } /* update backup L2 table */ @@ -XXX,XX +XXX,XX @@ static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data, if (bdrv_pwrite(extent->file, ((int64_t)m_data->l2_offset * 512) + (m_data->l2_index * sizeof(offset)), - &offset, sizeof(offset)) < 0) { + &offset, sizeof(offset), 0) < 0) { return VMDK_ERROR; } } @@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs, if (bdrv_pread(extent->file, (int64_t)l2_offset * 512, l2_table, - l2_size_bytes + l2_size_bytes, + 0 ) != l2_size_bytes) { return VMDK_ERROR; } @@ -XXX,XX +XXX,XX @@ static int vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset, cluster_buf = g_malloc(buf_bytes); uncomp_buf = g_malloc(cluster_bytes); BLKDBG_EVENT(extent->file, BLKDBG_READ_COMPRESSED); - ret = bdrv_pread(extent->file, - cluster_offset, - cluster_buf, buf_bytes); + ret = bdrv_pread(extent->file, cluster_offset, cluster_buf, buf_bytes, 0); if (ret < 0) { goto out; } diff --git a/block/vpc.c b/block/vpc.c index XXXXXXX..XXXXXXX 100644 --- a/block/vpc.c +++ b/block/vpc.c @@ -XXX,XX +XXX,XX @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } - ret = bdrv_pread(bs->file, 0, &s->footer, sizeof(s->footer)); + ret = bdrv_pread(bs->file, 0, &s->footer, sizeof(s->footer), 0); if (ret < 0) { error_setg(errp, "Unable to read VHD header"); goto fail; @@ -XXX,XX +XXX,XX @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, } /* If a fixed disk, the footer is found only at the end of the file */ - ret = bdrv_pread(bs->file, offset - sizeof(*footer), - footer, sizeof(*footer)); + ret = bdrv_pread(bs->file, offset - sizeof(*footer), footer, + sizeof(*footer), 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, if (disk_type == VHD_DYNAMIC) { ret = bdrv_pread(bs->file, be64_to_cpu(footer->data_offset), - &dyndisk_header, sizeof(dyndisk_header)); + &dyndisk_header, sizeof(dyndisk_header), 0); if (ret < 0) { error_setg(errp, "Error reading dynamic VHD header"); goto fail; @@ -XXX,XX +XXX,XX @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, s->bat_offset = be64_to_cpu(dyndisk_header.table_offset); ret = bdrv_pread(bs->file, s->bat_offset, s->pagetable, - pagetable_size); + pagetable_size, 0); if (ret < 0) { error_setg(errp, "Error reading pagetable"); goto fail; @@ -XXX,XX +XXX,XX @@ static inline int64_t get_image_offset(BlockDriverState *bs, uint64_t offset, s->last_bitmap_offset = bitmap_offset; memset(bitmap, 0xff, s->bitmap_size); - r = bdrv_pwrite_sync(bs->file, bitmap_offset, bitmap, s->bitmap_size); + r = bdrv_pwrite_sync(bs->file, bitmap_offset, bitmap, s->bitmap_size, + 0); if (r < 0) { *err = r; return -2; @@ -XXX,XX +XXX,XX @@ static int rewrite_footer(BlockDriverState *bs) BDRVVPCState *s = bs->opaque; int64_t offset = s->free_data_block_offset; - ret = bdrv_pwrite_sync(bs->file, offset, &s->footer, sizeof(s->footer)); + ret = bdrv_pwrite_sync(bs->file, offset, &s->footer, sizeof(s->footer), 0); if (ret < 0) return ret; @@ -XXX,XX +XXX,XX @@ static int64_t alloc_block(BlockDriverState *bs, int64_t offset) /* Initialize the block's bitmap */ memset(bitmap, 0xff, s->bitmap_size); ret = bdrv_pwrite_sync(bs->file, s->free_data_block_offset, bitmap, - s->bitmap_size); + s->bitmap_size, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int64_t alloc_block(BlockDriverState *bs, int64_t offset) /* Write BAT entry to disk */ bat_offset = s->bat_offset + (4 * index); bat_value = cpu_to_be32(s->pagetable[index]); - ret = bdrv_pwrite_sync(bs->file, bat_offset, &bat_value, 4); + ret = bdrv_pwrite_sync(bs->file, bat_offset, &bat_value, 4, 0); if (ret < 0) goto fail; diff --git a/block/vvfat.c b/block/vvfat.c index XXXXXXX..XXXXXXX 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -XXX,XX +XXX,XX @@ static int vvfat_read(BlockDriverState *bs, int64_t sector_num, " allocated\n", sector_num, n >> BDRV_SECTOR_BITS)); if (bdrv_pread(s->qcow, sector_num * BDRV_SECTOR_SIZE, - buf + i * 0x200, n) < 0) { + buf + i * 0x200, n, 0) < 0) { return -1; } i += (n >> BDRV_SECTOR_BITS) - 1; @@ -XXX,XX +XXX,XX @@ static uint32_t get_cluster_count_for_direntry(BDRVVVFATState* s, return -1; } res = bdrv_pwrite(s->qcow, offset * BDRV_SECTOR_SIZE, - s->cluster_buffer, BDRV_SECTOR_SIZE); + s->cluster_buffer, BDRV_SECTOR_SIZE, + 0); if (res < 0) { return -2; } @@ -XXX,XX +XXX,XX @@ DLOG(checkpoint()); */ DLOG(fprintf(stderr, "Write to qcow backend: %d + %d\n", (int)sector_num, nb_sectors)); ret = bdrv_pwrite(s->qcow, sector_num * BDRV_SECTOR_SIZE, buf, - nb_sectors * BDRV_SECTOR_SIZE); + nb_sectors * BDRV_SECTOR_SIZE, 0); if (ret < 0) { fprintf(stderr, "Error writing to qcow backend\n"); return ret; diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_sync_op_pread(BdrvChild *c) int ret; /* Success */ - ret = bdrv_pread(c, 0, buf, sizeof(buf)); + ret = bdrv_pread(c, 0, buf, sizeof(buf), 0); g_assert_cmpint(ret, ==, 512); /* Early error: Negative offset */ - ret = bdrv_pread(c, -2, buf, sizeof(buf)); + ret = bdrv_pread(c, -2, buf, sizeof(buf), 0); g_assert_cmpint(ret, ==, -EIO); } @@ -XXX,XX +XXX,XX @@ static void test_sync_op_pwrite(BdrvChild *c) int ret; /* Success */ - ret = bdrv_pwrite(c, 0, buf, sizeof(buf)); + ret = bdrv_pwrite(c, 0, buf, sizeof(buf), 0); g_assert_cmpint(ret, ==, 512); /* Early error: Negative offset */ - ret = bdrv_pwrite(c, -2, buf, sizeof(buf)); + ret = bdrv_pwrite(c, -2, buf, sizeof(buf), 0); g_assert_cmpint(ret, ==, -EIO); } -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Swap 'buf' and 'bytes' around for consistency with bdrv_co_{pread,pwrite}(), and in preparation to implement these functions using generated_co_wrapper. Callers were updated using this Coccinelle script: @@ expression child, offset, buf, bytes, flags; @@ - bdrv_pread(child, offset, buf, bytes, flags) + bdrv_pread(child, offset, bytes, buf, flags) @@ expression child, offset, buf, bytes, flags; @@ - bdrv_pwrite(child, offset, buf, bytes, flags) + bdrv_pwrite(child, offset, bytes, buf, flags) @@ expression child, offset, buf, bytes, flags; @@ - bdrv_pwrite_sync(child, offset, buf, bytes, flags) + bdrv_pwrite_sync(child, offset, bytes, buf, flags) Resulting overly-long lines were then fixed by hand. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Message-Id: <20220609152744.3891847-3-afaria@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/block/block-io.h | 10 +++--- block/blklogwrites.c | 6 ++-- block/bochs.c | 10 +++--- block/cloop.c | 10 +++--- block/crypto.c | 4 +-- block/dmg.c | 26 +++++++-------- block/io.c | 12 +++---- block/parallels-ext.c | 6 ++-- block/parallels.c | 10 +++--- block/qcow.c | 34 +++++++++---------- block/qcow2-bitmap.c | 14 ++++---- block/qcow2-cache.c | 8 ++--- block/qcow2-cluster.c | 22 ++++++------- block/qcow2-refcount.c | 56 +++++++++++++++++--------------- block/qcow2-snapshot.c | 48 +++++++++++++-------------- block/qcow2.c | 47 ++++++++++++++------------- block/qed.c | 8 ++--- block/vdi.c | 14 ++++---- block/vhdx-log.c | 18 +++++----- block/vhdx.c | 28 ++++++++-------- block/vmdk.c | 50 ++++++++++++++-------------- block/vpc.c | 22 ++++++------- block/vvfat.c | 10 +++--- tests/unit/test-block-iothread.c | 8 ++--- 24 files changed, 242 insertions(+), 239 deletions(-) diff --git a/include/block/block-io.h b/include/block/block-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-io.h +++ b/include/block/block-io.h @@ -XXX,XX +XXX,XX @@ int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset, int64_t bytes, BdrvRequestFlags flags); int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags); -int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int64_t bytes, +int bdrv_pread(BdrvChild *child, int64_t offset, int64_t bytes, void *buf, BdrvRequestFlags flags); -int bdrv_pwrite(BdrvChild *child, int64_t offset, const void *buf, - int64_t bytes, BdrvRequestFlags flags); -int bdrv_pwrite_sync(BdrvChild *child, int64_t offset, - const void *buf, int64_t bytes, BdrvRequestFlags flags); +int bdrv_pwrite(BdrvChild *child, int64_t offset, int64_t bytes, + const void *buf, BdrvRequestFlags flags); +int bdrv_pwrite_sync(BdrvChild *child, int64_t offset, int64_t bytes, + const void *buf, BdrvRequestFlags flags); /* * Efficiently zero a region of the disk image. Note that this is a regular * I/O request like read or write and should have a reasonable size. This diff --git a/block/blklogwrites.c b/block/blklogwrites.c index XXXXXXX..XXXXXXX 100644 --- a/block/blklogwrites.c +++ b/block/blklogwrites.c @@ -XXX,XX +XXX,XX @@ static uint64_t blk_log_writes_find_cur_log_sector(BdrvChild *log, struct log_write_entry cur_entry; while (cur_idx < nr_entries) { - int read_ret = bdrv_pread(log, cur_sector << sector_bits, &cur_entry, - sizeof(cur_entry), 0); + int read_ret = bdrv_pread(log, cur_sector << sector_bits, + sizeof(cur_entry), &cur_entry, 0); if (read_ret < 0) { error_setg_errno(errp, -read_ret, "Failed to read log entry %"PRIu64, cur_idx); @@ -XXX,XX +XXX,XX @@ static int blk_log_writes_open(BlockDriverState *bs, QDict *options, int flags, log_sb.nr_entries = cpu_to_le64(0); log_sb.sectorsize = cpu_to_le32(BDRV_SECTOR_SIZE); } else { - ret = bdrv_pread(s->log_file, 0, &log_sb, sizeof(log_sb), 0); + ret = bdrv_pread(s->log_file, 0, sizeof(log_sb), &log_sb, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read log superblock"); goto fail_log; diff --git a/block/bochs.c b/block/bochs.c index XXXXXXX..XXXXXXX 100644 --- a/block/bochs.c +++ b/block/bochs.c @@ -XXX,XX +XXX,XX @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags, return -EINVAL; } - ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs), 0); + ret = bdrv_pread(bs->file, 0, sizeof(bochs), &bochs, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags, return -ENOMEM; } - ret = bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_bitmap, - s->catalog_size * 4, 0); + ret = bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_size * 4, + s->catalog_bitmap, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num) (s->extent_blocks + s->bitmap_blocks)); /* read in bitmap for current extent */ - ret = bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8), - &bitmap_entry, 1, 0); + ret = bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8), 1, + &bitmap_entry, 0); if (ret < 0) { return ret; } diff --git a/block/cloop.c b/block/cloop.c index XXXXXXX..XXXXXXX 100644 --- a/block/cloop.c +++ b/block/cloop.c @@ -XXX,XX +XXX,XX @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags, } /* read header */ - ret = bdrv_pread(bs->file, 128, &s->block_size, 4, 0); + ret = bdrv_pread(bs->file, 128, 4, &s->block_size, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags, return -EINVAL; } - ret = bdrv_pread(bs->file, 128 + 4, &s->n_blocks, 4, 0); + ret = bdrv_pread(bs->file, 128 + 4, 4, &s->n_blocks, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags, return -ENOMEM; } - ret = bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size, 0); + ret = bdrv_pread(bs->file, 128 + 4 + 4, offsets_size, s->offsets, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static inline int cloop_read_block(BlockDriverState *bs, int block_num) int ret; uint32_t bytes = s->offsets[block_num + 1] - s->offsets[block_num]; - ret = bdrv_pread(bs->file, s->offsets[block_num], s->compressed_block, - bytes, 0); + ret = bdrv_pread(bs->file, s->offsets[block_num], bytes, + s->compressed_block, 0); if (ret != bytes) { return -1; } diff --git a/block/crypto.c b/block/crypto.c index XXXXXXX..XXXXXXX 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_read_func(QCryptoBlock *block, BlockDriverState *bs = opaque; ssize_t ret; - ret = bdrv_pread(bs->file, offset, buf, buflen, 0); + ret = bdrv_pread(bs->file, offset, buflen, buf, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read encryption header"); return ret; @@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_write_func(QCryptoBlock *block, BlockDriverState *bs = opaque; ssize_t ret; - ret = bdrv_pwrite(bs->file, offset, buf, buflen, 0); + ret = bdrv_pwrite(bs->file, offset, buflen, buf, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not write encryption header"); return ret; diff --git a/block/dmg.c b/block/dmg.c index XXXXXXX..XXXXXXX 100644 --- a/block/dmg.c +++ b/block/dmg.c @@ -XXX,XX +XXX,XX @@ static int read_uint64(BlockDriverState *bs, int64_t offset, uint64_t *result) uint64_t buffer; int ret; - ret = bdrv_pread(bs->file, offset, &buffer, 8, 0); + ret = bdrv_pread(bs->file, offset, 8, &buffer, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int read_uint32(BlockDriverState *bs, int64_t offset, uint32_t *result) uint32_t buffer; int ret; - ret = bdrv_pread(bs->file, offset, &buffer, 4, 0); + ret = bdrv_pread(bs->file, offset, 4, &buffer, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int64_t dmg_find_koly_offset(BdrvChild *file, Error **errp) offset = length - 511 - 512; } length = length < 515 ? length : 515; - ret = bdrv_pread(file, offset, buffer, length, 0); + ret = bdrv_pread(file, offset, length, buffer, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed while reading UDIF trailer"); return ret; @@ -XXX,XX +XXX,XX @@ static int dmg_read_resource_fork(BlockDriverState *bs, DmgHeaderState *ds, offset += 4; buffer = g_realloc(buffer, count); - ret = bdrv_pread(bs->file, offset, buffer, count, 0); + ret = bdrv_pread(bs->file, offset, count, buffer, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int dmg_read_plist_xml(BlockDriverState *bs, DmgHeaderState *ds, buffer = g_malloc(info_length + 1); buffer[info_length] = '\0'; - ret = bdrv_pread(bs->file, info_begin, buffer, info_length, 0); + ret = bdrv_pread(bs->file, info_begin, info_length, buffer, 0); if (ret != info_length) { ret = -EINVAL; goto fail; @@ -XXX,XX +XXX,XX @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num) case UDZO: { /* zlib compressed */ /* we need to buffer, because only the chunk as whole can be * inflated. */ - ret = bdrv_pread(bs->file, s->offsets[chunk], s->compressed_chunk, - s->lengths[chunk], 0); + ret = bdrv_pread(bs->file, s->offsets[chunk], s->lengths[chunk], + s->compressed_chunk, 0); if (ret != s->lengths[chunk]) { return -1; } @@ -XXX,XX +XXX,XX @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num) } /* we need to buffer, because only the chunk as whole can be * inflated. */ - ret = bdrv_pread(bs->file, s->offsets[chunk], s->compressed_chunk, - s->lengths[chunk], 0); + ret = bdrv_pread(bs->file, s->offsets[chunk], s->lengths[chunk], + s->compressed_chunk, 0); if (ret != s->lengths[chunk]) { return -1; } @@ -XXX,XX +XXX,XX @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num) } /* we need to buffer, because only the chunk as whole can be * inflated. */ - ret = bdrv_pread(bs->file, s->offsets[chunk], s->compressed_chunk, - s->lengths[chunk], 0); + ret = bdrv_pread(bs->file, s->offsets[chunk], s->lengths[chunk], + s->compressed_chunk, 0); if (ret != s->lengths[chunk]) { return -1; } @@ -XXX,XX +XXX,XX @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num) } break; case UDRW: /* copy */ - ret = bdrv_pread(bs->file, s->offsets[chunk], - s->uncompressed_chunk, s->lengths[chunk], 0); + ret = bdrv_pread(bs->file, s->offsets[chunk], s->lengths[chunk], + s->uncompressed_chunk, 0); if (ret != s->lengths[chunk]) { return -1; } diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) } /* See bdrv_pwrite() for the return codes */ -int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int64_t bytes, +int bdrv_pread(BdrvChild *child, int64_t offset, int64_t bytes, void *buf, BdrvRequestFlags flags) { int ret; @@ -XXX,XX +XXX,XX @@ int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int64_t bytes, -EINVAL Invalid offset or number of bytes -EACCES Trying to write a read-only device */ -int bdrv_pwrite(BdrvChild *child, int64_t offset, const void *buf, - int64_t bytes, BdrvRequestFlags flags) +int bdrv_pwrite(BdrvChild *child, int64_t offset, int64_t bytes, + const void *buf, BdrvRequestFlags flags) { int ret; QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); @@ -XXX,XX +XXX,XX @@ int bdrv_pwrite(BdrvChild *child, int64_t offset, const void *buf, * * Returns 0 on success, -errno in error cases. */ -int bdrv_pwrite_sync(BdrvChild *child, int64_t offset, - const void *buf, int64_t count, BdrvRequestFlags flags) +int bdrv_pwrite_sync(BdrvChild *child, int64_t offset, int64_t bytes, + const void *buf, BdrvRequestFlags flags) { int ret; IO_CODE(); - ret = bdrv_pwrite(child, offset, buf, count, flags); + ret = bdrv_pwrite(child, offset, bytes, buf, flags); if (ret < 0) { return ret; } diff --git a/block/parallels-ext.c b/block/parallels-ext.c index XXXXXXX..XXXXXXX 100644 --- a/block/parallels-ext.c +++ b/block/parallels-ext.c @@ -XXX,XX +XXX,XX @@ static int parallels_load_bitmap_data(BlockDriverState *bs, if (entry == 1) { bdrv_dirty_bitmap_deserialize_ones(bitmap, offset, count, false); } else { - ret = bdrv_pread(bs->file, entry << BDRV_SECTOR_BITS, buf, - s->cluster_size, 0); + ret = bdrv_pread(bs->file, entry << BDRV_SECTOR_BITS, + s->cluster_size, buf, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read bitmap data cluster"); @@ -XXX,XX +XXX,XX @@ int parallels_read_format_extension(BlockDriverState *bs, assert(ext_off > 0); - ret = bdrv_pread(bs->file, ext_off, ext_cluster, s->cluster_size, 0); + ret = bdrv_pread(bs->file, ext_off, s->cluster_size, ext_cluster, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read Format Extension cluster"); goto out; diff --git a/block/parallels.c b/block/parallels.c index XXXXXXX..XXXXXXX 100644 --- a/block/parallels.c +++ b/block/parallels.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int parallels_co_flush_to_os(BlockDriverState *bs) if (off + to_write > s->header_size) { to_write = s->header_size - off; } - ret = bdrv_pwrite(bs->file, off, (uint8_t *)s->header + off, to_write, + ret = bdrv_pwrite(bs->file, off, to_write, (uint8_t *)s->header + off, 0); if (ret < 0) { qemu_co_mutex_unlock(&s->lock); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn parallels_co_check(BlockDriverState *bs, ret = 0; if (flush_bat) { - ret = bdrv_pwrite_sync(bs->file, 0, s->header, s->header_size, 0); + ret = bdrv_pwrite_sync(bs->file, 0, s->header_size, s->header, 0); if (ret < 0) { res->check_errors++; goto out; @@ -XXX,XX +XXX,XX @@ static int parallels_update_header(BlockDriverState *bs) if (size > s->header_size) { size = s->header_size; } - return bdrv_pwrite_sync(bs->file, 0, s->header, size, 0); + return bdrv_pwrite_sync(bs->file, 0, size, s->header, 0); } static int parallels_open(BlockDriverState *bs, QDict *options, int flags, @@ -XXX,XX +XXX,XX @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags, return -EINVAL; } - ret = bdrv_pread(bs->file, 0, &ph, sizeof(ph), 0); + ret = bdrv_pread(bs->file, 0, sizeof(ph), &ph, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags, s->header_size = size; } - ret = bdrv_pread(bs->file, 0, s->header, s->header_size, 0); + ret = bdrv_pread(bs->file, 0, s->header_size, s->header, 0); if (ret < 0) { goto fail; } diff --git a/block/qcow.c b/block/qcow.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -XXX,XX +XXX,XX @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } - ret = bdrv_pread(bs->file, 0, &header, sizeof(header), 0); + ret = bdrv_pread(bs->file, 0, sizeof(header), &header, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } - ret = bdrv_pread(bs->file, s->l1_table_offset, s->l1_table, - s->l1_size * sizeof(uint64_t), 0); + ret = bdrv_pread(bs->file, s->l1_table_offset, + s->l1_size * sizeof(uint64_t), s->l1_table, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, ret = -EINVAL; goto fail; } - ret = bdrv_pread(bs->file, header.backing_file_offset, - bs->auto_backing_file, len, 0); + ret = bdrv_pread(bs->file, header.backing_file_offset, len, + bs->auto_backing_file, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs, BLKDBG_EVENT(bs->file, BLKDBG_L1_UPDATE); ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset + l1_index * sizeof(tmp), - &tmp, sizeof(tmp), 0); + sizeof(tmp), &tmp, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs, BLKDBG_EVENT(bs->file, BLKDBG_L2_LOAD); if (new_l2_table) { memset(l2_table, 0, s->l2_size * sizeof(uint64_t)); - ret = bdrv_pwrite_sync(bs->file, l2_offset, l2_table, - s->l2_size * sizeof(uint64_t), 0); + ret = bdrv_pwrite_sync(bs->file, l2_offset, + s->l2_size * sizeof(uint64_t), l2_table, 0); if (ret < 0) { return ret; } } else { - ret = bdrv_pread(bs->file, l2_offset, l2_table, - s->l2_size * sizeof(uint64_t), 0); + ret = bdrv_pread(bs->file, l2_offset, s->l2_size * sizeof(uint64_t), + l2_table, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs, cluster_offset = QEMU_ALIGN_UP(cluster_offset, s->cluster_size); /* write the cluster content */ BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO); - ret = bdrv_pwrite(bs->file, cluster_offset, s->cluster_cache, - s->cluster_size, 0); + ret = bdrv_pwrite(bs->file, cluster_offset, s->cluster_size, + s->cluster_cache, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs, } BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO); ret = bdrv_pwrite(bs->file, cluster_offset + i, - s->cluster_data, - BDRV_SECTOR_SIZE, 0); + BDRV_SECTOR_SIZE, + s->cluster_data, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs, BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE); } ret = bdrv_pwrite_sync(bs->file, l2_offset + l2_index * sizeof(tmp), - &tmp, sizeof(tmp), 0); + sizeof(tmp), &tmp, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset) csize = cluster_offset >> (63 - s->cluster_bits); csize &= (s->cluster_size - 1); BLKDBG_EVENT(bs->file, BLKDBG_READ_COMPRESSED); - ret = bdrv_pread(bs->file, coffset, s->cluster_data, csize, 0); + ret = bdrv_pread(bs->file, coffset, csize, s->cluster_data, 0); if (ret != csize) return -1; if (decompress_buffer(s->cluster_cache, s->cluster_size, @@ -XXX,XX +XXX,XX @@ static int qcow_make_empty(BlockDriverState *bs) int ret; memset(s->l1_table, 0, l1_length); - if (bdrv_pwrite_sync(bs->file, s->l1_table_offset, s->l1_table, l1_length, + if (bdrv_pwrite_sync(bs->file, s->l1_table_offset, l1_length, s->l1_table, 0) < 0) return -1; ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length, false, diff --git a/block/qcow2-bitmap.c b/block/qcow2-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-bitmap.c +++ b/block/qcow2-bitmap.c @@ -XXX,XX +XXX,XX @@ static int bitmap_table_load(BlockDriverState *bs, Qcow2BitmapTable *tb, } assert(tb->size <= BME_MAX_TABLE_SIZE); - ret = bdrv_pread(bs->file, tb->offset, table, - tb->size * BME_TABLE_ENTRY_SIZE, 0); + ret = bdrv_pread(bs->file, tb->offset, tb->size * BME_TABLE_ENTRY_SIZE, + table, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int load_bitmap_data(BlockDriverState *bs, * already cleared */ } } else { - ret = bdrv_pread(bs->file, data_offset, buf, s->cluster_size, 0); + ret = bdrv_pread(bs->file, data_offset, s->cluster_size, buf, 0); if (ret < 0) { goto finish; } @@ -XXX,XX +XXX,XX @@ static Qcow2BitmapList *bitmap_list_load(BlockDriverState *bs, uint64_t offset, } dir_end = dir + size; - ret = bdrv_pread(bs->file, offset, dir, size, 0); + ret = bdrv_pread(bs->file, offset, size, dir, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read bitmap directory"); goto fail; @@ -XXX,XX +XXX,XX @@ static int bitmap_list_store(BlockDriverState *bs, Qcow2BitmapList *bm_list, goto fail; } - ret = bdrv_pwrite(bs->file, dir_offset, dir, dir_size, 0); + ret = bdrv_pwrite(bs->file, dir_offset, dir_size, dir, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, goto fail; } - ret = bdrv_pwrite(bs->file, off, buf, s->cluster_size, 0); + ret = bdrv_pwrite(bs->file, off, s->cluster_size, buf, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to write bitmap '%s' to file", bm_name); @@ -XXX,XX +XXX,XX @@ static int store_bitmap(BlockDriverState *bs, Qcow2Bitmap *bm, Error **errp) } bitmap_table_to_be(tb, tb_size); - ret = bdrv_pwrite(bs->file, tb_offset, tb, tb_size * sizeof(tb[0]), 0); + ret = bdrv_pwrite(bs->file, tb_offset, tb_size * sizeof(tb[0]), tb, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to write bitmap '%s' to file", bm_name); diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cache.c +++ b/block/qcow2-cache.c @@ -XXX,XX +XXX,XX @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i) BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE); } - ret = bdrv_pwrite(bs->file, c->entries[i].offset, - qcow2_cache_get_table_addr(c, i), c->table_size, 0); + ret = bdrv_pwrite(bs->file, c->entries[i].offset, c->table_size, + qcow2_cache_get_table_addr(c, i), 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c, BLKDBG_EVENT(bs->file, BLKDBG_L2_LOAD); } - ret = bdrv_pread(bs->file, offset, qcow2_cache_get_table_addr(c, i), - c->table_size, 0); + ret = bdrv_pread(bs->file, offset, c->table_size, + qcow2_cache_get_table_addr(c, i), 0); if (ret < 0) { return ret; } diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size, BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_WRITE_TABLE); for(i = 0; i < s->l1_size; i++) new_l1_table[i] = cpu_to_be64(new_l1_table[i]); - ret = bdrv_pwrite_sync(bs->file, new_l1_table_offset, new_l1_table, - new_l1_size2, 0); + ret = bdrv_pwrite_sync(bs->file, new_l1_table_offset, new_l1_size2, + new_l1_table, 0); if (ret < 0) goto fail; for(i = 0; i < s->l1_size; i++) @@ -XXX,XX +XXX,XX @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size, BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_ACTIVATE_TABLE); stl_be_p(data, new_l1_size); stq_be_p(data + 4, new_l1_table_offset); - ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, l1_size), data, - sizeof(data), 0); + ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, l1_size), + sizeof(data), data, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index) BLKDBG_EVENT(bs->file, BLKDBG_L1_UPDATE); ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset + L1E_SIZE * l1_start_index, - buf, bufsize, 0); + bufsize, buf, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, (void **)&l2_slice); } else { /* load inactive L2 tables from disk */ - ret = bdrv_pread(bs->file, slice_offset, l2_slice, - slice_size2, 0); + ret = bdrv_pread(bs->file, slice_offset, slice_size2, + l2_slice, 0); } if (ret < 0) { goto fail; @@ -XXX,XX +XXX,XX @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, goto fail; } - ret = bdrv_pwrite(bs->file, slice_offset, l2_slice, - slice_size2, 0); + ret = bdrv_pwrite(bs->file, slice_offset, slice_size2, + l2_slice, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_expand_zero_clusters(BlockDriverState *bs, l1_table = new_l1_table; - ret = bdrv_pread(bs->file, s->snapshots[i].l1_table_offset, l1_table, - l1_size2, 0); + ret = bdrv_pread(bs->file, s->snapshots[i].l1_table_offset, l1_size2, + l1_table, 0); if (ret < 0) { goto fail; } diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -XXX,XX +XXX,XX @@ int qcow2_refcount_init(BlockDriverState *bs) } BLKDBG_EVENT(bs->file, BLKDBG_REFTABLE_LOAD); ret = bdrv_pread(bs->file, s->refcount_table_offset, - s->refcount_table, refcount_table_size2, 0); + refcount_table_size2, s->refcount_table, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int alloc_refcount_block(BlockDriverState *bs, BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_HOOKUP); ret = bdrv_pwrite_sync(bs->file, s->refcount_table_offset + refcount_table_index * REFTABLE_ENTRY_SIZE, - &data64, sizeof(data64), 0); + sizeof(data64), &data64, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int64_t qcow2_refcount_area(BlockDriverState *bs, uint64_t start_offset, } BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_WRITE_TABLE); - ret = bdrv_pwrite_sync(bs->file, table_offset, new_table, - table_size * REFTABLE_ENTRY_SIZE, 0); + ret = bdrv_pwrite_sync(bs->file, table_offset, + table_size * REFTABLE_ENTRY_SIZE, new_table, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int64_t qcow2_refcount_area(BlockDriverState *bs, uint64_t start_offset, data.d32 = cpu_to_be32(table_clusters); BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_SWITCH_TABLE); ret = bdrv_pwrite_sync(bs->file, - offsetof(QCowHeader, refcount_table_offset), &data, - sizeof(data), 0); + offsetof(QCowHeader, refcount_table_offset), + sizeof(data), &data, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs, } l1_allocated = true; - ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size2, 0); + ret = bdrv_pread(bs->file, l1_table_offset, l1_size2, l1_table, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ fail: cpu_to_be64s(&l1_table[i]); } - ret = bdrv_pwrite_sync(bs->file, l1_table_offset, l1_table, l1_size2, + ret = bdrv_pwrite_sync(bs->file, l1_table_offset, l1_size2, l1_table, 0); for (i = 0; i < l1_size; i++) { @@ -XXX,XX +XXX,XX @@ static int fix_l2_entry_by_zero(BlockDriverState *bs, BdrvCheckResult *res, goto fail; } - ret = bdrv_pwrite_sync(bs->file, l2e_offset, &l2_table[idx], - l2_entry_size(s), 0); + ret = bdrv_pwrite_sync(bs->file, l2e_offset, l2_entry_size(s), + &l2_table[idx], 0); if (ret < 0) { fprintf(stderr, "ERROR: Failed to overwrite L2 " "table entry: %s\n", strerror(-ret)); @@ -XXX,XX +XXX,XX @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res, bool metadata_overlap; /* Read L2 table from disk */ - ret = bdrv_pread(bs->file, l2_offset, l2_table, l2_size_bytes, 0); + ret = bdrv_pread(bs->file, l2_offset, l2_size_bytes, l2_table, 0); if (ret < 0) { fprintf(stderr, "ERROR: I/O error in check_refcounts_l2\n"); res->check_errors++; @@ -XXX,XX +XXX,XX @@ static int check_refcounts_l1(BlockDriverState *bs, } /* Read L1 table entries from disk */ - ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size_bytes, 0); + ret = bdrv_pread(bs->file, l1_table_offset, l1_size_bytes, l1_table, 0); if (ret < 0) { fprintf(stderr, "ERROR: I/O error in check_refcounts_l1\n"); res->check_errors++; @@ -XXX,XX +XXX,XX @@ static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res, } } - ret = bdrv_pread(bs->file, l2_offset, l2_table, - s->l2_size * l2_entry_size(s), 0); + ret = bdrv_pread(bs->file, l2_offset, s->l2_size * l2_entry_size(s), + l2_table, 0); if (ret < 0) { fprintf(stderr, "ERROR: Could not read L2 table: %s\n", strerror(-ret)); @@ -XXX,XX +XXX,XX @@ static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res, goto fail; } - ret = bdrv_pwrite(bs->file, l2_offset, l2_table, s->cluster_size, + ret = bdrv_pwrite(bs->file, l2_offset, s->cluster_size, l2_table, 0); if (ret < 0) { fprintf(stderr, "ERROR: Could not write L2 table: %s\n", @@ -XXX,XX +XXX,XX @@ static int rebuild_refcounts_write_refblocks( on_disk_refblock = (void *)((char *) *refcount_table + refblock_index * s->cluster_size); - ret = bdrv_pwrite(bs->file, refblock_offset, on_disk_refblock, - s->cluster_size, 0); + ret = bdrv_pwrite(bs->file, refblock_offset, s->cluster_size, + on_disk_refblock, 0); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR writing refblock"); return ret; @@ -XXX,XX +XXX,XX @@ static int rebuild_refcount_structure(BlockDriverState *bs, } assert(reftable_length < INT_MAX); - ret = bdrv_pwrite(bs->file, reftable_offset, on_disk_reftable, - reftable_length, 0); + ret = bdrv_pwrite(bs->file, reftable_offset, reftable_length, + on_disk_reftable, 0); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR writing reftable"); goto fail; @@ -XXX,XX +XXX,XX @@ static int rebuild_refcount_structure(BlockDriverState *bs, cpu_to_be32(reftable_clusters); ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, refcount_table_offset), - &reftable_offset_and_clusters, - sizeof(reftable_offset_and_clusters), 0); + sizeof(reftable_offset_and_clusters), + &reftable_offset_and_clusters, 0); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR setting reftable"); goto fail; @@ -XXX,XX +XXX,XX @@ int qcow2_check_metadata_overlap(BlockDriverState *bs, int ign, int64_t offset, return -ENOMEM; } - ret = bdrv_pread(bs->file, l1_ofs, l1, l1_sz2, 0); + ret = bdrv_pread(bs->file, l1_ofs, l1_sz2, l1, 0); if (ret < 0) { g_free(l1); return ret; @@ -XXX,XX +XXX,XX @@ static int flush_refblock(BlockDriverState *bs, uint64_t **reftable, return ret; } - ret = bdrv_pwrite(bs->file, offset, refblock, s->cluster_size, 0); + ret = bdrv_pwrite(bs->file, offset, s->cluster_size, refblock, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to write refblock"); return ret; @@ -XXX,XX +XXX,XX @@ int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order, cpu_to_be64s(&new_reftable[i]); } - ret = bdrv_pwrite(bs->file, new_reftable_offset, new_reftable, - new_reftable_size * REFTABLE_ENTRY_SIZE, 0); + ret = bdrv_pwrite(bs->file, new_reftable_offset, + new_reftable_size * REFTABLE_ENTRY_SIZE, new_reftable, + 0); for (i = 0; i < new_reftable_size; i++) { be64_to_cpus(&new_reftable[i]); @@ -XXX,XX +XXX,XX @@ int qcow2_shrink_reftable(BlockDriverState *bs) reftable_tmp[i] = unused_block ? 0 : cpu_to_be64(s->refcount_table[i]); } - ret = bdrv_pwrite_sync(bs->file, s->refcount_table_offset, reftable_tmp, - s->refcount_table_size * REFTABLE_ENTRY_SIZE, 0); + ret = bdrv_pwrite_sync(bs->file, s->refcount_table_offset, + s->refcount_table_size * REFTABLE_ENTRY_SIZE, + reftable_tmp, 0); /* * If the write in the reftable failed the image may contain a partially * overwritten reftable. In this case it would be better to clear the diff --git a/block/qcow2-snapshot.c b/block/qcow2-snapshot.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-snapshot.c +++ b/block/qcow2-snapshot.c @@ -XXX,XX +XXX,XX @@ static int qcow2_do_read_snapshots(BlockDriverState *bs, bool repair, /* Read statically sized part of the snapshot header */ offset = ROUND_UP(offset, 8); - ret = bdrv_pread(bs->file, offset, &h, sizeof(h), 0); + ret = bdrv_pread(bs->file, offset, sizeof(h), &h, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read snapshot table"); goto fail; @@ -XXX,XX +XXX,XX @@ static int qcow2_do_read_snapshots(BlockDriverState *bs, bool repair, } /* Read known extra data */ - ret = bdrv_pread(bs->file, offset, &extra, - MIN(sizeof(extra), sn->extra_data_size), 0); + ret = bdrv_pread(bs->file, offset, + MIN(sizeof(extra), sn->extra_data_size), &extra, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read snapshot table"); goto fail; @@ -XXX,XX +XXX,XX @@ static int qcow2_do_read_snapshots(BlockDriverState *bs, bool repair, /* Store unknown extra data */ unknown_extra_data_size = sn->extra_data_size - sizeof(extra); sn->unknown_extra_data = g_malloc(unknown_extra_data_size); - ret = bdrv_pread(bs->file, offset, sn->unknown_extra_data, - unknown_extra_data_size, 0); + ret = bdrv_pread(bs->file, offset, unknown_extra_data_size, + sn->unknown_extra_data, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read snapshot table"); @@ -XXX,XX +XXX,XX @@ static int qcow2_do_read_snapshots(BlockDriverState *bs, bool repair, /* Read snapshot ID */ sn->id_str = g_malloc(id_str_size + 1); - ret = bdrv_pread(bs->file, offset, sn->id_str, id_str_size, 0); + ret = bdrv_pread(bs->file, offset, id_str_size, sn->id_str, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read snapshot table"); goto fail; @@ -XXX,XX +XXX,XX @@ static int qcow2_do_read_snapshots(BlockDriverState *bs, bool repair, /* Read snapshot name */ sn->name = g_malloc(name_size + 1); - ret = bdrv_pread(bs->file, offset, sn->name, name_size, 0); + ret = bdrv_pread(bs->file, offset, name_size, sn->name, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read snapshot table"); goto fail; @@ -XXX,XX +XXX,XX @@ int qcow2_write_snapshots(BlockDriverState *bs) h.name_size = cpu_to_be16(name_size); offset = ROUND_UP(offset, 8); - ret = bdrv_pwrite(bs->file, offset, &h, sizeof(h), 0); + ret = bdrv_pwrite(bs->file, offset, sizeof(h), &h, 0); if (ret < 0) { goto fail; } offset += sizeof(h); - ret = bdrv_pwrite(bs->file, offset, &extra, sizeof(extra), 0); + ret = bdrv_pwrite(bs->file, offset, sizeof(extra), &extra, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_write_snapshots(BlockDriverState *bs) assert(unknown_extra_data_size <= BDRV_REQUEST_MAX_BYTES); assert(sn->unknown_extra_data); - ret = bdrv_pwrite(bs->file, offset, sn->unknown_extra_data, - unknown_extra_data_size, 0); + ret = bdrv_pwrite(bs->file, offset, unknown_extra_data_size, + sn->unknown_extra_data, 0); if (ret < 0) { goto fail; } offset += unknown_extra_data_size; } - ret = bdrv_pwrite(bs->file, offset, sn->id_str, id_str_size, 0); + ret = bdrv_pwrite(bs->file, offset, id_str_size, sn->id_str, 0); if (ret < 0) { goto fail; } offset += id_str_size; - ret = bdrv_pwrite(bs->file, offset, sn->name, name_size, 0); + ret = bdrv_pwrite(bs->file, offset, name_size, sn->name, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_write_snapshots(BlockDriverState *bs) header_data.snapshots_offset = cpu_to_be64(snapshots_offset); ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots), - &header_data, sizeof(header_data), 0); + sizeof(header_data), &header_data, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int coroutine_fn qcow2_check_read_snapshot_table(BlockDriverState *bs, /* qcow2_do_open() discards this information in check mode */ ret = bdrv_pread(bs->file, offsetof(QCowHeader, nb_snapshots), - &snapshot_table_pointer, sizeof(snapshot_table_pointer), + sizeof(snapshot_table_pointer), &snapshot_table_pointer, 0); if (ret < 0) { result->check_errors++; @@ -XXX,XX +XXX,XX @@ int coroutine_fn qcow2_check_read_snapshot_table(BlockDriverState *bs, snapshot_table_pointer.nb_snapshots = cpu_to_be32(s->nb_snapshots); ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots), - &snapshot_table_pointer.nb_snapshots, - sizeof(snapshot_table_pointer.nb_snapshots), 0); + sizeof(snapshot_table_pointer.nb_snapshots), + &snapshot_table_pointer.nb_snapshots, 0); if (ret < 0) { result->check_errors++; fprintf(stderr, "ERROR failed to update the snapshot count in the " @@ -XXX,XX +XXX,XX @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info) goto fail; } - ret = bdrv_pwrite(bs->file, sn->l1_table_offset, l1_table, - s->l1_size * L1E_SIZE, 0); + ret = bdrv_pwrite(bs->file, sn->l1_table_offset, s->l1_size * L1E_SIZE, + l1_table, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id) goto fail; } - ret = bdrv_pread(bs->file, sn->l1_table_offset, sn_l1_table, sn_l1_bytes, + ret = bdrv_pread(bs->file, sn->l1_table_offset, sn_l1_bytes, sn_l1_table, 0); if (ret < 0) { goto fail; @@ -XXX,XX +XXX,XX @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id) goto fail; } - ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset, sn_l1_table, - cur_l1_bytes, 0); + ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset, cur_l1_bytes, + sn_l1_table, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int qcow2_snapshot_load_tmp(BlockDriverState *bs, return -ENOMEM; } - ret = bdrv_pread(bs->file, sn->l1_table_offset, new_l1_table, - new_l1_bytes, 0); + ret = bdrv_pread(bs->file, sn->l1_table_offset, new_l1_bytes, + new_l1_table, 0); if (ret < 0) { error_setg(errp, "Failed to read l1 table for snapshot"); qemu_vfree(new_l1_table); diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static ssize_t qcow2_crypto_hdr_read_func(QCryptoBlock *block, size_t offset, return -1; } - ret = bdrv_pread(bs->file, s->crypto_header.offset + offset, buf, buflen, + ret = bdrv_pread(bs->file, s->crypto_header.offset + offset, buflen, buf, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read encryption header"); @@ -XXX,XX +XXX,XX @@ static ssize_t qcow2_crypto_hdr_write_func(QCryptoBlock *block, size_t offset, return -1; } - ret = bdrv_pwrite(bs->file, s->crypto_header.offset + offset, buf, buflen, + ret = bdrv_pwrite(bs->file, s->crypto_header.offset + offset, buflen, buf, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read encryption header"); @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, printf("attempting to read extended header in offset %lu\n", offset); #endif - ret = bdrv_pread(bs->file, offset, &ext, sizeof(ext), 0); + ret = bdrv_pread(bs->file, offset, sizeof(ext), &ext, 0); if (ret < 0) { error_setg_errno(errp, -ret, "qcow2_read_extension: ERROR: " "pread fail from offset %" PRIu64, offset); @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, sizeof(bs->backing_format)); return 2; } - ret = bdrv_pread(bs->file, offset, bs->backing_format, ext.len, 0); + ret = bdrv_pread(bs->file, offset, ext.len, bs->backing_format, 0); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR: ext_backing_format: " "Could not read format name"); @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, case QCOW2_EXT_MAGIC_FEATURE_TABLE: if (p_feature_table != NULL) { void *feature_table = g_malloc0(ext.len + 2 * sizeof(Qcow2Feature)); - ret = bdrv_pread(bs->file, offset, feature_table, ext.len, 0); + ret = bdrv_pread(bs->file, offset, ext.len, feature_table, 0); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR: ext_feature_table: " "Could not read table"); @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, return -EINVAL; } - ret = bdrv_pread(bs->file, offset, &s->crypto_header, ext.len, 0); + ret = bdrv_pread(bs->file, offset, ext.len, &s->crypto_header, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Unable to read CRYPTO header extension"); @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, break; } - ret = bdrv_pread(bs->file, offset, &bitmaps_ext, ext.len, 0); + ret = bdrv_pread(bs->file, offset, ext.len, &bitmaps_ext, 0); if (ret < 0) { error_setg_errno(errp, -ret, "bitmaps_ext: " "Could not read ext header"); @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, case QCOW2_EXT_MAGIC_DATA_FILE: { s->image_data_file = g_malloc0(ext.len + 1); - ret = bdrv_pread(bs->file, offset, s->image_data_file, ext.len, 0); + ret = bdrv_pread(bs->file, offset, ext.len, s->image_data_file, 0); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR: Could not read data file name"); @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, uext->len = ext.len; QLIST_INSERT_HEAD(&s->unknown_header_ext, uext, next); - ret = bdrv_pread(bs->file, offset, uext->data, uext->len, 0); + ret = bdrv_pread(bs->file, offset, uext->len, uext->data, 0); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR: unknown extension: " "Could not read data"); @@ -XXX,XX +XXX,XX @@ int qcow2_mark_dirty(BlockDriverState *bs) val = cpu_to_be64(s->incompatible_features | QCOW2_INCOMPAT_DIRTY); ret = bdrv_pwrite(bs->file, offsetof(QCowHeader, incompatible_features), - &val, sizeof(val), 0); + sizeof(val), &val, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, uint64_t l1_vm_state_index; bool update_header = false; - ret = bdrv_pread(bs->file, 0, &header, sizeof(header), 0); + ret = bdrv_pread(bs->file, 0, sizeof(header), &header, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read qcow2 header"); goto fail; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, if (header.header_length > sizeof(header)) { s->unknown_header_fields_size = header.header_length - sizeof(header); s->unknown_header_fields = g_malloc(s->unknown_header_fields_size); - ret = bdrv_pread(bs->file, sizeof(header), s->unknown_header_fields, - s->unknown_header_fields_size, 0); + ret = bdrv_pread(bs->file, sizeof(header), + s->unknown_header_fields_size, + s->unknown_header_fields, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read unknown qcow2 header " "fields"); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, ret = -ENOMEM; goto fail; } - ret = bdrv_pread(bs->file, s->l1_table_offset, s->l1_table, - s->l1_size * L1E_SIZE, 0); + ret = bdrv_pread(bs->file, s->l1_table_offset, s->l1_size * L1E_SIZE, + s->l1_table, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read L1 table"); goto fail; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, ret = -EINVAL; goto fail; } - ret = bdrv_pread(bs->file, header.backing_file_offset, - bs->auto_backing_file, len, 0); + ret = bdrv_pread(bs->file, header.backing_file_offset, len, + bs->auto_backing_file, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read backing file name"); goto fail; @@ -XXX,XX +XXX,XX @@ int qcow2_update_header(BlockDriverState *bs) } /* Write the new header */ - ret = bdrv_pwrite(bs->file, 0, header, s->cluster_size, 0); + ret = bdrv_pwrite(bs->file, 0, s->cluster_size, header, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset, /* write updated header.size */ offset = cpu_to_be64(offset); - ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, size), &offset, - sizeof(offset), 0); + ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, size), + sizeof(offset), &offset, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to update the image size"); goto fail; @@ -XXX,XX +XXX,XX @@ static int make_completely_empty(BlockDriverState *bs) l1_ofs_rt_ofs_cls.reftable_offset = cpu_to_be64(s->cluster_size); l1_ofs_rt_ofs_cls.reftable_clusters = cpu_to_be32(1); ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, l1_table_offset), - &l1_ofs_rt_ofs_cls, sizeof(l1_ofs_rt_ofs_cls), 0); + sizeof(l1_ofs_rt_ofs_cls), &l1_ofs_rt_ofs_cls, 0); if (ret < 0) { goto fail_broken_refcounts; } @@ -XXX,XX +XXX,XX @@ static int make_completely_empty(BlockDriverState *bs) /* Enter the first refblock into the reftable */ rt_entry = cpu_to_be64(2 * s->cluster_size); - ret = bdrv_pwrite_sync(bs->file, s->cluster_size, &rt_entry, - sizeof(rt_entry), 0); + ret = bdrv_pwrite_sync(bs->file, s->cluster_size, sizeof(rt_entry), + &rt_entry, 0); if (ret < 0) { goto fail_broken_refcounts; } diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ int qed_write_header_sync(BDRVQEDState *s) int ret; qed_header_cpu_to_le(&s->header, &le); - ret = bdrv_pwrite(s->bs->file, 0, &le, sizeof(le), 0); + ret = bdrv_pwrite(s->bs->file, 0, sizeof(le), &le, 0); if (ret != sizeof(le)) { return ret; } @@ -XXX,XX +XXX,XX @@ static int qed_read_string(BdrvChild *file, uint64_t offset, size_t n, if (n >= buflen) { return -EINVAL; } - ret = bdrv_pread(file, offset, buf, n, 0); + ret = bdrv_pread(file, offset, n, buf, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_do_open(BlockDriverState *bs, QDict *options, int64_t file_size; int ret; - ret = bdrv_pread(bs->file, 0, &le_header, sizeof(le_header), 0); + ret = bdrv_pread(bs->file, 0, sizeof(le_header), &le_header, 0); if (ret < 0) { error_setg(errp, "Failed to read QED header"); return ret; @@ -XXX,XX +XXX,XX @@ static int bdrv_qed_change_backing_file(BlockDriverState *bs, } /* Write new header */ - ret = bdrv_pwrite_sync(bs->file, 0, buffer, buffer_len, 0); + ret = bdrv_pwrite_sync(bs->file, 0, buffer_len, buffer, 0); g_free(buffer); if (ret == 0) { memcpy(&s->header, &new_header, sizeof(new_header)); diff --git a/block/vdi.c b/block/vdi.c index XXXXXXX..XXXXXXX 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -XXX,XX +XXX,XX @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags, logout("\n"); - ret = bdrv_pread(bs->file, 0, &header, sizeof(header), 0); + ret = bdrv_pread(bs->file, 0, sizeof(header), &header, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } - ret = bdrv_pread(bs->file, header.offset_bmap, s->bmap, - bmap_size * SECTOR_SIZE, 0); + ret = bdrv_pread(bs->file, header.offset_bmap, bmap_size * SECTOR_SIZE, + s->bmap, 0); if (ret < 0) { goto fail_free_bmap; } @@ -XXX,XX +XXX,XX @@ vdi_co_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes, * so this full-cluster write does not overlap a partial write * of the same cluster, issued from the "else" branch. */ - ret = bdrv_pwrite(bs->file, data_offset, block, s->block_size, 0); + ret = bdrv_pwrite(bs->file, data_offset, s->block_size, block, 0); qemu_co_rwlock_unlock(&s->bmap_lock); } else { nonallocating_write: @@ -XXX,XX +XXX,XX @@ nonallocating_write: assert(VDI_IS_ALLOCATED(bmap_first)); *header = s->header; vdi_header_to_le(header); - ret = bdrv_pwrite(bs->file, 0, header, sizeof(*header), 0); + ret = bdrv_pwrite(bs->file, 0, sizeof(*header), header, 0); g_free(header); if (ret < 0) { @@ -XXX,XX +XXX,XX @@ nonallocating_write: base = ((uint8_t *)&s->bmap[0]) + bmap_first * SECTOR_SIZE; logout("will write %u block map sectors starting from entry %u\n", n_sectors, bmap_first); - ret = bdrv_pwrite(bs->file, offset * SECTOR_SIZE, base, - n_sectors * SECTOR_SIZE, 0); + ret = bdrv_pwrite(bs->file, offset * SECTOR_SIZE, + n_sectors * SECTOR_SIZE, base, 0); } return ret < 0 ? ret : 0; diff --git a/block/vhdx-log.c b/block/vhdx-log.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx-log.c +++ b/block/vhdx-log.c @@ -XXX,XX +XXX,XX @@ static int vhdx_log_peek_hdr(BlockDriverState *bs, VHDXLogEntries *log, offset = log->offset + read; - ret = bdrv_pread(bs->file, offset, hdr, sizeof(VHDXLogEntryHeader), 0); + ret = bdrv_pread(bs->file, offset, sizeof(VHDXLogEntryHeader), hdr, 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_log_read_sectors(BlockDriverState *bs, VHDXLogEntries *log, } offset = log->offset + read; - ret = bdrv_pread(bs->file, offset, buffer, VHDX_LOG_SECTOR_SIZE, 0); + ret = bdrv_pread(bs->file, offset, VHDX_LOG_SECTOR_SIZE, buffer, 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_log_write_sectors(BlockDriverState *bs, VHDXLogEntries *log, /* full */ break; } - ret = bdrv_pwrite(bs->file, offset, buffer_tmp, VHDX_LOG_SECTOR_SIZE, + ret = bdrv_pwrite(bs->file, offset, VHDX_LOG_SECTOR_SIZE, buffer_tmp, 0); if (ret < 0) { goto exit; @@ -XXX,XX +XXX,XX @@ static int vhdx_log_flush_desc(BlockDriverState *bs, VHDXLogDescriptor *desc, /* count is only > 1 if we are writing zeroes */ for (i = 0; i < count; i++) { - ret = bdrv_pwrite_sync(bs->file, file_offset, buffer, - VHDX_LOG_SECTOR_SIZE, 0); + ret = bdrv_pwrite_sync(bs->file, file_offset, VHDX_LOG_SECTOR_SIZE, + buffer, 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s, if (i == 0 && leading_length) { /* partial sector at the front of the buffer */ - ret = bdrv_pread(bs->file, file_offset, merged_sector, - VHDX_LOG_SECTOR_SIZE, 0); + ret = bdrv_pread(bs->file, file_offset, VHDX_LOG_SECTOR_SIZE, + merged_sector, 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s, } else if (i == sectors - 1 && trailing_length) { /* partial sector at the end of the buffer */ ret = bdrv_pread(bs->file, file_offset, - merged_sector + trailing_length, - VHDX_LOG_SECTOR_SIZE - trailing_length, 0); + VHDX_LOG_SECTOR_SIZE - trailing_length, + merged_sector + trailing_length, 0); if (ret < 0) { goto exit; } diff --git a/block/vhdx.c b/block/vhdx.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -XXX,XX +XXX,XX @@ static int vhdx_write_header(BdrvChild *file, VHDXHeader *hdr, buffer = qemu_blockalign(bs_file, VHDX_HEADER_SIZE); if (read) { /* if true, we can't assume the extra reserved bytes are 0 */ - ret = bdrv_pread(file, offset, buffer, VHDX_HEADER_SIZE, 0); + ret = bdrv_pread(file, offset, VHDX_HEADER_SIZE, buffer, 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_write_header(BdrvChild *file, VHDXHeader *hdr, vhdx_header_le_export(hdr, header_le); vhdx_update_checksum(buffer, VHDX_HEADER_SIZE, offsetof(VHDXHeader, checksum)); - ret = bdrv_pwrite_sync(file, offset, header_le, sizeof(VHDXHeader), 0); + ret = bdrv_pwrite_sync(file, offset, sizeof(VHDXHeader), header_le, 0); exit: qemu_vfree(buffer); @@ -XXX,XX +XXX,XX @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s, /* We have to read the whole VHDX_HEADER_SIZE instead of * sizeof(VHDXHeader), because the checksum is over the whole * region */ - ret = bdrv_pread(bs->file, VHDX_HEADER1_OFFSET, buffer, VHDX_HEADER_SIZE, + ret = bdrv_pread(bs->file, VHDX_HEADER1_OFFSET, VHDX_HEADER_SIZE, buffer, 0); if (ret < 0) { goto fail; @@ -XXX,XX +XXX,XX @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s, } } - ret = bdrv_pread(bs->file, VHDX_HEADER2_OFFSET, buffer, VHDX_HEADER_SIZE, + ret = bdrv_pread(bs->file, VHDX_HEADER2_OFFSET, VHDX_HEADER_SIZE, buffer, 0); if (ret < 0) { goto fail; @@ -XXX,XX +XXX,XX @@ static int vhdx_open_region_tables(BlockDriverState *bs, BDRVVHDXState *s) * whole block */ buffer = qemu_blockalign(bs, VHDX_HEADER_BLOCK_SIZE); - ret = bdrv_pread(bs->file, VHDX_REGION_TABLE_OFFSET, buffer, - VHDX_HEADER_BLOCK_SIZE, 0); + ret = bdrv_pread(bs->file, VHDX_REGION_TABLE_OFFSET, + VHDX_HEADER_BLOCK_SIZE, buffer, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) buffer = qemu_blockalign(bs, VHDX_METADATA_TABLE_MAX_SIZE); - ret = bdrv_pread(bs->file, s->metadata_rt.file_offset, buffer, - VHDX_METADATA_TABLE_MAX_SIZE, 0); + ret = bdrv_pread(bs->file, s->metadata_rt.file_offset, + VHDX_METADATA_TABLE_MAX_SIZE, buffer, 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) ret = bdrv_pread(bs->file, s->metadata_entries.file_parameters_entry.offset + s->metadata_rt.file_offset, - &s->params, sizeof(s->params), + &s->params, 0); if (ret < 0) { @@ -XXX,XX +XXX,XX @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) ret = bdrv_pread(bs->file, s->metadata_entries.virtual_disk_size_entry.offset + s->metadata_rt.file_offset, - &s->virtual_disk_size, sizeof(uint64_t), + &s->virtual_disk_size, 0); if (ret < 0) { goto exit; @@ -XXX,XX +XXX,XX @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) ret = bdrv_pread(bs->file, s->metadata_entries.logical_sector_size_entry.offset + s->metadata_rt.file_offset, - &s->logical_sector_size, sizeof(uint32_t), + &s->logical_sector_size, 0); if (ret < 0) { goto exit; @@ -XXX,XX +XXX,XX @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) ret = bdrv_pread(bs->file, s->metadata_entries.phys_sector_size_entry.offset + s->metadata_rt.file_offset, - &s->physical_sector_size, sizeof(uint32_t), + &s->physical_sector_size, 0); if (ret < 0) { goto exit; @@ -XXX,XX +XXX,XX @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags, QLIST_INIT(&s->regions); /* validate the file signature */ - ret = bdrv_pread(bs->file, 0, &signature, sizeof(uint64_t), 0); + ret = bdrv_pread(bs->file, 0, sizeof(uint64_t), &signature, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } - ret = bdrv_pread(bs->file, s->bat_offset, s->bat, s->bat_rt.length, 0); + ret = bdrv_pread(bs->file, s->bat_offset, s->bat_rt.length, s->bat, 0); if (ret < 0) { goto fail; } diff --git a/block/vmdk.c b/block/vmdk.c index XXXXXXX..XXXXXXX 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -XXX,XX +XXX,XX @@ static int vmdk_read_cid(BlockDriverState *bs, int parent, uint32_t *pcid) int ret; desc = g_malloc0(DESC_SIZE); - ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE, 0); + ret = bdrv_pread(bs->file, s->desc_offset, DESC_SIZE, desc, 0); if (ret < 0) { goto out; } @@ -XXX,XX +XXX,XX @@ static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid) desc = g_malloc0(DESC_SIZE); tmp_desc = g_malloc0(DESC_SIZE); - ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE, 0); + ret = bdrv_pread(bs->file, s->desc_offset, DESC_SIZE, desc, 0); if (ret < 0) { goto out; } @@ -XXX,XX +XXX,XX @@ static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid) pstrcat(desc, DESC_SIZE, tmp_desc); } - ret = bdrv_pwrite_sync(bs->file, s->desc_offset, desc, DESC_SIZE, 0); + ret = bdrv_pwrite_sync(bs->file, s->desc_offset, DESC_SIZE, desc, 0); out: g_free(desc); @@ -XXX,XX +XXX,XX @@ static int vmdk_parent_open(BlockDriverState *bs) int ret; desc = g_malloc0(DESC_SIZE + 1); - ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE, 0); + ret = bdrv_pread(bs->file, s->desc_offset, DESC_SIZE, desc, 0); if (ret < 0) { goto out; } @@ -XXX,XX +XXX,XX @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent, return -ENOMEM; } - ret = bdrv_pread(extent->file, extent->l1_table_offset, extent->l1_table, - l1_size, 0); + ret = bdrv_pread(extent->file, extent->l1_table_offset, l1_size, + extent->l1_table, 0); if (ret < 0) { bdrv_refresh_filename(extent->file->bs); error_setg_errno(errp, -ret, @@ -XXX,XX +XXX,XX @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent, goto fail_l1; } ret = bdrv_pread(extent->file, extent->l1_backup_table_offset, - extent->l1_backup_table, l1_size, 0); + l1_size, extent->l1_backup_table, 0); if (ret < 0) { bdrv_refresh_filename(extent->file->bs); error_setg_errno(errp, -ret, @@ -XXX,XX +XXX,XX @@ static int vmdk_open_vmfs_sparse(BlockDriverState *bs, VMDK3Header header; VmdkExtent *extent = NULL; - ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header), 0); + ret = bdrv_pread(file, sizeof(magic), sizeof(header), &header, 0); if (ret < 0) { bdrv_refresh_filename(file->bs); error_setg_errno(errp, -ret, @@ -XXX,XX +XXX,XX @@ static int vmdk_open_se_sparse(BlockDriverState *bs, assert(sizeof(const_header) == SECTOR_SIZE); - ret = bdrv_pread(file, 0, &const_header, sizeof(const_header), 0); + ret = bdrv_pread(file, 0, sizeof(const_header), &const_header, 0); if (ret < 0) { bdrv_refresh_filename(file->bs); error_setg_errno(errp, -ret, @@ -XXX,XX +XXX,XX @@ static int vmdk_open_se_sparse(BlockDriverState *bs, assert(sizeof(volatile_header) == SECTOR_SIZE); ret = bdrv_pread(file, const_header.volatile_header_offset * SECTOR_SIZE, - &volatile_header, sizeof(volatile_header), 0); + sizeof(volatile_header), &volatile_header, 0); if (ret < 0) { bdrv_refresh_filename(file->bs); error_setg_errno(errp, -ret, @@ -XXX,XX +XXX,XX @@ static char *vmdk_read_desc(BdrvChild *file, uint64_t desc_offset, Error **errp) size = MIN(size, (1 << 20) - 1); /* avoid unbounded allocation */ buf = g_malloc(size + 1); - ret = bdrv_pread(file, desc_offset, buf, size, 0); + ret = bdrv_pread(file, desc_offset, size, buf, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read from file"); g_free(buf); @@ -XXX,XX +XXX,XX @@ static int vmdk_open_vmdk4(BlockDriverState *bs, int64_t l1_backup_offset = 0; bool compressed; - ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header), 0); + ret = bdrv_pread(file, sizeof(magic), sizeof(header), &header, 0); if (ret < 0) { bdrv_refresh_filename(file->bs); error_setg_errno(errp, -ret, @@ -XXX,XX +XXX,XX @@ static int vmdk_open_vmdk4(BlockDriverState *bs, } QEMU_PACKED footer; ret = bdrv_pread(file, bs->file->bs->total_sectors * 512 - 1536, - &footer, sizeof(footer), 0); + sizeof(footer), &footer, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to read footer"); return ret; @@ -XXX,XX +XXX,XX @@ static int get_whole_cluster(BlockDriverState *bs, if (copy_from_backing) { /* qcow2 emits this on bs->file instead of bs->backing */ BLKDBG_EVENT(extent->file, BLKDBG_COW_READ); - ret = bdrv_pread(bs->backing, offset, whole_grain, - skip_start_bytes, 0); + ret = bdrv_pread(bs->backing, offset, skip_start_bytes, + whole_grain, 0); if (ret < 0) { ret = VMDK_ERROR; goto exit; } } BLKDBG_EVENT(extent->file, BLKDBG_COW_WRITE); - ret = bdrv_pwrite(extent->file, cluster_offset, whole_grain, - skip_start_bytes, 0); + ret = bdrv_pwrite(extent->file, cluster_offset, skip_start_bytes, + whole_grain, 0); if (ret < 0) { ret = VMDK_ERROR; goto exit; @@ -XXX,XX +XXX,XX @@ static int get_whole_cluster(BlockDriverState *bs, /* qcow2 emits this on bs->file instead of bs->backing */ BLKDBG_EVENT(extent->file, BLKDBG_COW_READ); ret = bdrv_pread(bs->backing, offset + skip_end_bytes, - whole_grain + skip_end_bytes, - cluster_bytes - skip_end_bytes, 0); + cluster_bytes - skip_end_bytes, + whole_grain + skip_end_bytes, 0); if (ret < 0) { ret = VMDK_ERROR; goto exit; @@ -XXX,XX +XXX,XX @@ static int get_whole_cluster(BlockDriverState *bs, } BLKDBG_EVENT(extent->file, BLKDBG_COW_WRITE); ret = bdrv_pwrite(extent->file, cluster_offset + skip_end_bytes, - whole_grain + skip_end_bytes, - cluster_bytes - skip_end_bytes, 0); + cluster_bytes - skip_end_bytes, + whole_grain + skip_end_bytes, 0); if (ret < 0) { ret = VMDK_ERROR; goto exit; @@ -XXX,XX +XXX,XX @@ static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data, if (bdrv_pwrite(extent->file, ((int64_t)m_data->l2_offset * 512) + (m_data->l2_index * sizeof(offset)), - &offset, sizeof(offset), 0) < 0) { + sizeof(offset), &offset, 0) < 0) { return VMDK_ERROR; } /* update backup L2 table */ @@ -XXX,XX +XXX,XX @@ static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data, if (bdrv_pwrite(extent->file, ((int64_t)m_data->l2_offset * 512) + (m_data->l2_index * sizeof(offset)), - &offset, sizeof(offset), 0) < 0) { + sizeof(offset), &offset, 0) < 0) { return VMDK_ERROR; } } @@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs, BLKDBG_EVENT(extent->file, BLKDBG_L2_LOAD); if (bdrv_pread(extent->file, (int64_t)l2_offset * 512, - l2_table, l2_size_bytes, + l2_table, 0 ) != l2_size_bytes) { return VMDK_ERROR; @@ -XXX,XX +XXX,XX @@ static int vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset, cluster_buf = g_malloc(buf_bytes); uncomp_buf = g_malloc(cluster_bytes); BLKDBG_EVENT(extent->file, BLKDBG_READ_COMPRESSED); - ret = bdrv_pread(extent->file, cluster_offset, cluster_buf, buf_bytes, 0); + ret = bdrv_pread(extent->file, cluster_offset, buf_bytes, cluster_buf, 0); if (ret < 0) { goto out; } diff --git a/block/vpc.c b/block/vpc.c index XXXXXXX..XXXXXXX 100644 --- a/block/vpc.c +++ b/block/vpc.c @@ -XXX,XX +XXX,XX @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } - ret = bdrv_pread(bs->file, 0, &s->footer, sizeof(s->footer), 0); + ret = bdrv_pread(bs->file, 0, sizeof(s->footer), &s->footer, 0); if (ret < 0) { error_setg(errp, "Unable to read VHD header"); goto fail; @@ -XXX,XX +XXX,XX @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, } /* If a fixed disk, the footer is found only at the end of the file */ - ret = bdrv_pread(bs->file, offset - sizeof(*footer), footer, - sizeof(*footer), 0); + ret = bdrv_pread(bs->file, offset - sizeof(*footer), sizeof(*footer), + footer, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, if (disk_type == VHD_DYNAMIC) { ret = bdrv_pread(bs->file, be64_to_cpu(footer->data_offset), - &dyndisk_header, sizeof(dyndisk_header), 0); + sizeof(dyndisk_header), &dyndisk_header, 0); if (ret < 0) { error_setg(errp, "Error reading dynamic VHD header"); goto fail; @@ -XXX,XX +XXX,XX @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, s->bat_offset = be64_to_cpu(dyndisk_header.table_offset); - ret = bdrv_pread(bs->file, s->bat_offset, s->pagetable, - pagetable_size, 0); + ret = bdrv_pread(bs->file, s->bat_offset, pagetable_size, + s->pagetable, 0); if (ret < 0) { error_setg(errp, "Error reading pagetable"); goto fail; @@ -XXX,XX +XXX,XX @@ static inline int64_t get_image_offset(BlockDriverState *bs, uint64_t offset, s->last_bitmap_offset = bitmap_offset; memset(bitmap, 0xff, s->bitmap_size); - r = bdrv_pwrite_sync(bs->file, bitmap_offset, bitmap, s->bitmap_size, + r = bdrv_pwrite_sync(bs->file, bitmap_offset, s->bitmap_size, bitmap, 0); if (r < 0) { *err = r; @@ -XXX,XX +XXX,XX @@ static int rewrite_footer(BlockDriverState *bs) BDRVVPCState *s = bs->opaque; int64_t offset = s->free_data_block_offset; - ret = bdrv_pwrite_sync(bs->file, offset, &s->footer, sizeof(s->footer), 0); + ret = bdrv_pwrite_sync(bs->file, offset, sizeof(s->footer), &s->footer, 0); if (ret < 0) return ret; @@ -XXX,XX +XXX,XX @@ static int64_t alloc_block(BlockDriverState *bs, int64_t offset) /* Initialize the block's bitmap */ memset(bitmap, 0xff, s->bitmap_size); - ret = bdrv_pwrite_sync(bs->file, s->free_data_block_offset, bitmap, - s->bitmap_size, 0); + ret = bdrv_pwrite_sync(bs->file, s->free_data_block_offset, + s->bitmap_size, bitmap, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int64_t alloc_block(BlockDriverState *bs, int64_t offset) /* Write BAT entry to disk */ bat_offset = s->bat_offset + (4 * index); bat_value = cpu_to_be32(s->pagetable[index]); - ret = bdrv_pwrite_sync(bs->file, bat_offset, &bat_value, 4, 0); + ret = bdrv_pwrite_sync(bs->file, bat_offset, 4, &bat_value, 0); if (ret < 0) goto fail; diff --git a/block/vvfat.c b/block/vvfat.c index XXXXXXX..XXXXXXX 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -XXX,XX +XXX,XX @@ static int vvfat_read(BlockDriverState *bs, int64_t sector_num, DLOG(fprintf(stderr, "sectors %" PRId64 "+%" PRId64 " allocated\n", sector_num, n >> BDRV_SECTOR_BITS)); - if (bdrv_pread(s->qcow, sector_num * BDRV_SECTOR_SIZE, - buf + i * 0x200, n, 0) < 0) { + if (bdrv_pread(s->qcow, sector_num * BDRV_SECTOR_SIZE, n, + buf + i * 0x200, 0) < 0) { return -1; } i += (n >> BDRV_SECTOR_BITS) - 1; @@ -XXX,XX +XXX,XX @@ static uint32_t get_cluster_count_for_direntry(BDRVVVFATState* s, return -1; } res = bdrv_pwrite(s->qcow, offset * BDRV_SECTOR_SIZE, - s->cluster_buffer, BDRV_SECTOR_SIZE, + BDRV_SECTOR_SIZE, s->cluster_buffer, 0); if (res < 0) { return -2; @@ -XXX,XX +XXX,XX @@ DLOG(checkpoint()); * Use qcow backend. Commit later. */ DLOG(fprintf(stderr, "Write to qcow backend: %d + %d\n", (int)sector_num, nb_sectors)); - ret = bdrv_pwrite(s->qcow, sector_num * BDRV_SECTOR_SIZE, buf, - nb_sectors * BDRV_SECTOR_SIZE, 0); + ret = bdrv_pwrite(s->qcow, sector_num * BDRV_SECTOR_SIZE, + nb_sectors * BDRV_SECTOR_SIZE, buf, 0); if (ret < 0) { fprintf(stderr, "Error writing to qcow backend\n"); return ret; diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_sync_op_pread(BdrvChild *c) int ret; /* Success */ - ret = bdrv_pread(c, 0, buf, sizeof(buf), 0); + ret = bdrv_pread(c, 0, sizeof(buf), buf, 0); g_assert_cmpint(ret, ==, 512); /* Early error: Negative offset */ - ret = bdrv_pread(c, -2, buf, sizeof(buf), 0); + ret = bdrv_pread(c, -2, sizeof(buf), buf, 0); g_assert_cmpint(ret, ==, -EIO); } @@ -XXX,XX +XXX,XX @@ static void test_sync_op_pwrite(BdrvChild *c) int ret; /* Success */ - ret = bdrv_pwrite(c, 0, buf, sizeof(buf), 0); + ret = bdrv_pwrite(c, 0, sizeof(buf), buf, 0); g_assert_cmpint(ret, ==, 512); /* Early error: Negative offset */ - ret = bdrv_pwrite(c, -2, buf, sizeof(buf), 0); + ret = bdrv_pwrite(c, -2, sizeof(buf), buf, 0); g_assert_cmpint(ret, ==, -EIO); } -- 2.35.3 From: Alberto Faria <afaria@redhat.com> They currently return the value of their 'bytes' parameter on success. Make them return 0 instead, for consistency with other I/O functions and in preparation to implement them using generated_co_wrapper. This also makes it clear that short reads/writes are not possible. The few callers that rely on the previous behavior are adjusted accordingly by hand. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220609152744.3891847-4-afaria@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- block/cloop.c | 2 +- block/crypto.c | 4 ++-- block/dmg.c | 10 +++++----- block/io.c | 10 ++-------- block/qcow.c | 2 +- block/qcow2.c | 4 ++-- block/qed.c | 7 +------ block/vdi.c | 2 +- block/vmdk.c | 5 ++--- tests/unit/test-block-iothread.c | 4 ++-- 10 files changed, 19 insertions(+), 31 deletions(-) diff --git a/block/cloop.c b/block/cloop.c index XXXXXXX..XXXXXXX 100644 --- a/block/cloop.c +++ b/block/cloop.c @@ -XXX,XX +XXX,XX @@ static inline int cloop_read_block(BlockDriverState *bs, int block_num) ret = bdrv_pread(bs->file, s->offsets[block_num], bytes, s->compressed_block, 0); - if (ret != bytes) { + if (ret < 0) { return -1; } diff --git a/block/crypto.c b/block/crypto.c index XXXXXXX..XXXXXXX 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_read_func(QCryptoBlock *block, error_setg_errno(errp, -ret, "Could not read encryption header"); return ret; } - return ret; + return buflen; } static ssize_t block_crypto_write_func(QCryptoBlock *block, @@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_write_func(QCryptoBlock *block, error_setg_errno(errp, -ret, "Could not write encryption header"); return ret; } - return ret; + return buflen; } diff --git a/block/dmg.c b/block/dmg.c index XXXXXXX..XXXXXXX 100644 --- a/block/dmg.c +++ b/block/dmg.c @@ -XXX,XX +XXX,XX @@ static int dmg_read_plist_xml(BlockDriverState *bs, DmgHeaderState *ds, buffer = g_malloc(info_length + 1); buffer[info_length] = '\0'; ret = bdrv_pread(bs->file, info_begin, info_length, buffer, 0); - if (ret != info_length) { + if (ret < 0) { ret = -EINVAL; goto fail; } @@ -XXX,XX +XXX,XX @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num) * inflated. */ ret = bdrv_pread(bs->file, s->offsets[chunk], s->lengths[chunk], s->compressed_chunk, 0); - if (ret != s->lengths[chunk]) { + if (ret < 0) { return -1; } @@ -XXX,XX +XXX,XX @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num) * inflated. */ ret = bdrv_pread(bs->file, s->offsets[chunk], s->lengths[chunk], s->compressed_chunk, 0); - if (ret != s->lengths[chunk]) { + if (ret < 0) { return -1; } @@ -XXX,XX +XXX,XX @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num) * inflated. */ ret = bdrv_pread(bs->file, s->offsets[chunk], s->lengths[chunk], s->compressed_chunk, 0); - if (ret != s->lengths[chunk]) { + if (ret < 0) { return -1; } @@ -XXX,XX +XXX,XX @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num) case UDRW: /* copy */ ret = bdrv_pread(bs->file, s->offsets[chunk], s->lengths[chunk], s->uncompressed_chunk, 0); - if (ret != s->lengths[chunk]) { + if (ret < 0) { return -1; } break; diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) int bdrv_pread(BdrvChild *child, int64_t offset, int64_t bytes, void *buf, BdrvRequestFlags flags) { - int ret; QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); IO_CODE(); @@ -XXX,XX +XXX,XX @@ int bdrv_pread(BdrvChild *child, int64_t offset, int64_t bytes, void *buf, return -EINVAL; } - ret = bdrv_preadv(child, offset, bytes, &qiov, flags); - - return ret < 0 ? ret : bytes; + return bdrv_preadv(child, offset, bytes, &qiov, flags); } /* Return no. of bytes on success or < 0 on error. Important errors are: @@ -XXX,XX +XXX,XX @@ int bdrv_pread(BdrvChild *child, int64_t offset, int64_t bytes, void *buf, int bdrv_pwrite(BdrvChild *child, int64_t offset, int64_t bytes, const void *buf, BdrvRequestFlags flags) { - int ret; QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); IO_CODE(); @@ -XXX,XX +XXX,XX @@ int bdrv_pwrite(BdrvChild *child, int64_t offset, int64_t bytes, return -EINVAL; } - ret = bdrv_pwritev(child, offset, bytes, &qiov, flags); - - return ret < 0 ? ret : bytes; + return bdrv_pwritev(child, offset, bytes, &qiov, flags); } /* diff --git a/block/qcow.c b/block/qcow.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -XXX,XX +XXX,XX @@ static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset) csize &= (s->cluster_size - 1); BLKDBG_EVENT(bs->file, BLKDBG_READ_COMPRESSED); ret = bdrv_pread(bs->file, coffset, csize, s->cluster_data, 0); - if (ret != csize) + if (ret < 0) return -1; if (decompress_buffer(s->cluster_cache, s->cluster_size, s->cluster_data, csize) < 0) { diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static ssize_t qcow2_crypto_hdr_read_func(QCryptoBlock *block, size_t offset, error_setg_errno(errp, -ret, "Could not read encryption header"); return -1; } - return ret; + return buflen; } @@ -XXX,XX +XXX,XX @@ static ssize_t qcow2_crypto_hdr_write_func(QCryptoBlock *block, size_t offset, error_setg_errno(errp, -ret, "Could not read encryption header"); return -1; } - return ret; + return buflen; } static QDict* diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static void qed_header_cpu_to_le(const QEDHeader *cpu, QEDHeader *le) int qed_write_header_sync(BDRVQEDState *s) { QEDHeader le; - int ret; qed_header_cpu_to_le(&s->header, &le); - ret = bdrv_pwrite(s->bs->file, 0, sizeof(le), &le, 0); - if (ret != sizeof(le)) { - return ret; - } - return 0; + return bdrv_pwrite(s->bs->file, 0, sizeof(le), &le, 0); } /** diff --git a/block/vdi.c b/block/vdi.c index XXXXXXX..XXXXXXX 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -XXX,XX +XXX,XX @@ nonallocating_write: n_sectors * SECTOR_SIZE, base, 0); } - return ret < 0 ? ret : 0; + return ret; } static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options, diff --git a/block/vmdk.c b/block/vmdk.c index XXXXXXX..XXXXXXX 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -XXX,XX +XXX,XX @@ static int vmdk_parent_open(BlockDriverState *bs) if (ret < 0) { goto out; } - ret = 0; p_name = strstr(desc, "parentFileNameHint"); if (p_name != NULL) { @@ -XXX,XX +XXX,XX @@ static char *vmdk_read_desc(BdrvChild *file, uint64_t desc_offset, Error **errp) g_free(buf); return NULL; } - buf[ret] = 0; + buf[size] = 0; return buf; } @@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs, l2_size_bytes, l2_table, 0 - ) != l2_size_bytes) { + ) < 0) { return VMDK_ERROR; } diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_sync_op_pread(BdrvChild *c) /* Success */ ret = bdrv_pread(c, 0, sizeof(buf), buf, 0); - g_assert_cmpint(ret, ==, 512); + g_assert_cmpint(ret, ==, 0); /* Early error: Negative offset */ ret = bdrv_pread(c, -2, sizeof(buf), buf, 0); @@ -XXX,XX +XXX,XX @@ static void test_sync_op_pwrite(BdrvChild *c) /* Success */ ret = bdrv_pwrite(c, 0, sizeof(buf), buf, 0); - g_assert_cmpint(ret, ==, 512); + g_assert_cmpint(ret, ==, 0); /* Early error: Negative offset */ ret = bdrv_pwrite(c, -2, sizeof(buf), buf, 0); -- 2.35.3 From: Alberto Faria <afaria@redhat.com> They currently return the value of their headerlen/buflen parameter on success. Returning 0 instead makes it clear that short reads/writes are not possible. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220609152744.3891847-5-afaria@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/crypto/block.h | 32 ++++++++++----------- block/crypto.c | 52 +++++++++++++++++----------------- block/qcow2.c | 22 +++++++------- crypto/block-luks.c | 8 +++--- crypto/block.c | 6 ++-- tests/unit/test-crypto-block.c | 38 ++++++++++++------------- 6 files changed, 79 insertions(+), 79 deletions(-) diff --git a/include/crypto/block.h b/include/crypto/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/crypto/block.h +++ b/include/crypto/block.h @@ -XXX,XX +XXX,XX @@ typedef struct QCryptoBlock QCryptoBlock; /* See also QCryptoBlockFormat, QCryptoBlockCreateOptions * and QCryptoBlockOpenOptions in qapi/crypto.json */ -typedef ssize_t (*QCryptoBlockReadFunc)(QCryptoBlock *block, - size_t offset, - uint8_t *buf, - size_t buflen, - void *opaque, - Error **errp); +typedef int (*QCryptoBlockReadFunc)(QCryptoBlock *block, + size_t offset, + uint8_t *buf, + size_t buflen, + void *opaque, + Error **errp); -typedef ssize_t (*QCryptoBlockInitFunc)(QCryptoBlock *block, - size_t headerlen, - void *opaque, - Error **errp); +typedef int (*QCryptoBlockInitFunc)(QCryptoBlock *block, + size_t headerlen, + void *opaque, + Error **errp); -typedef ssize_t (*QCryptoBlockWriteFunc)(QCryptoBlock *block, - size_t offset, - const uint8_t *buf, - size_t buflen, - void *opaque, - Error **errp); +typedef int (*QCryptoBlockWriteFunc)(QCryptoBlock *block, + size_t offset, + const uint8_t *buf, + size_t buflen, + void *opaque, + Error **errp); /** * qcrypto_block_has_format: diff --git a/block/crypto.c b/block/crypto.c index XXXXXXX..XXXXXXX 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -XXX,XX +XXX,XX @@ static int block_crypto_probe_generic(QCryptoBlockFormat format, } -static ssize_t block_crypto_read_func(QCryptoBlock *block, - size_t offset, - uint8_t *buf, - size_t buflen, - void *opaque, - Error **errp) +static int block_crypto_read_func(QCryptoBlock *block, + size_t offset, + uint8_t *buf, + size_t buflen, + void *opaque, + Error **errp) { BlockDriverState *bs = opaque; ssize_t ret; @@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_read_func(QCryptoBlock *block, error_setg_errno(errp, -ret, "Could not read encryption header"); return ret; } - return buflen; + return 0; } -static ssize_t block_crypto_write_func(QCryptoBlock *block, - size_t offset, - const uint8_t *buf, - size_t buflen, - void *opaque, - Error **errp) +static int block_crypto_write_func(QCryptoBlock *block, + size_t offset, + const uint8_t *buf, + size_t buflen, + void *opaque, + Error **errp) { BlockDriverState *bs = opaque; ssize_t ret; @@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_write_func(QCryptoBlock *block, error_setg_errno(errp, -ret, "Could not write encryption header"); return ret; } - return buflen; + return 0; } @@ -XXX,XX +XXX,XX @@ struct BlockCryptoCreateData { }; -static ssize_t block_crypto_create_write_func(QCryptoBlock *block, - size_t offset, - const uint8_t *buf, - size_t buflen, - void *opaque, - Error **errp) +static int block_crypto_create_write_func(QCryptoBlock *block, + size_t offset, + const uint8_t *buf, + size_t buflen, + void *opaque, + Error **errp) { struct BlockCryptoCreateData *data = opaque; ssize_t ret; @@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_create_write_func(QCryptoBlock *block, error_setg_errno(errp, -ret, "Could not write encryption header"); return ret; } - return ret; + return 0; } -static ssize_t block_crypto_create_init_func(QCryptoBlock *block, - size_t headerlen, - void *opaque, - Error **errp) +static int block_crypto_create_init_func(QCryptoBlock *block, + size_t headerlen, + void *opaque, + Error **errp) { struct BlockCryptoCreateData *data = opaque; Error *local_error = NULL; @@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_create_init_func(QCryptoBlock *block, data->prealloc, 0, &local_error); if (ret >= 0) { - return ret; + return 0; } error: diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int qcow2_probe(const uint8_t *buf, int buf_size, const char *filename) } -static ssize_t qcow2_crypto_hdr_read_func(QCryptoBlock *block, size_t offset, - uint8_t *buf, size_t buflen, - void *opaque, Error **errp) +static int qcow2_crypto_hdr_read_func(QCryptoBlock *block, size_t offset, + uint8_t *buf, size_t buflen, + void *opaque, Error **errp) { BlockDriverState *bs = opaque; BDRVQcow2State *s = bs->opaque; @@ -XXX,XX +XXX,XX @@ static ssize_t qcow2_crypto_hdr_read_func(QCryptoBlock *block, size_t offset, error_setg_errno(errp, -ret, "Could not read encryption header"); return -1; } - return buflen; + return 0; } -static ssize_t qcow2_crypto_hdr_init_func(QCryptoBlock *block, size_t headerlen, - void *opaque, Error **errp) +static int qcow2_crypto_hdr_init_func(QCryptoBlock *block, size_t headerlen, + void *opaque, Error **errp) { BlockDriverState *bs = opaque; BDRVQcow2State *s = bs->opaque; @@ -XXX,XX +XXX,XX @@ static ssize_t qcow2_crypto_hdr_init_func(QCryptoBlock *block, size_t headerlen, return -1; } - return ret; + return 0; } -static ssize_t qcow2_crypto_hdr_write_func(QCryptoBlock *block, size_t offset, - const uint8_t *buf, size_t buflen, - void *opaque, Error **errp) +static int qcow2_crypto_hdr_write_func(QCryptoBlock *block, size_t offset, + const uint8_t *buf, size_t buflen, + void *opaque, Error **errp) { BlockDriverState *bs = opaque; BDRVQcow2State *s = bs->opaque; @@ -XXX,XX +XXX,XX @@ static ssize_t qcow2_crypto_hdr_write_func(QCryptoBlock *block, size_t offset, error_setg_errno(errp, -ret, "Could not read encryption header"); return -1; } - return buflen; + return 0; } static QDict* diff --git a/crypto/block-luks.c b/crypto/block-luks.c index XXXXXXX..XXXXXXX 100644 --- a/crypto/block-luks.c +++ b/crypto/block-luks.c @@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_load_header(QCryptoBlock *block, void *opaque, Error **errp) { - ssize_t rv; + int rv; size_t i; QCryptoBlockLUKS *luks = block->opaque; @@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_store_key(QCryptoBlock *block, QCRYPTO_BLOCK_LUKS_SECTOR_SIZE, splitkey, splitkeylen, opaque, - errp) != splitkeylen) { + errp) < 0) { goto cleanup; } @@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_load_key(QCryptoBlock *block, g_autofree uint8_t *splitkey = NULL; size_t splitkeylen; g_autofree uint8_t *possiblekey = NULL; - ssize_t rv; + int rv; g_autoptr(QCryptoCipher) cipher = NULL; uint8_t keydigest[QCRYPTO_BLOCK_LUKS_DIGEST_LEN]; g_autoptr(QCryptoIVGen) ivgen = NULL; @@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_erase_key(QCryptoBlock *block, garbagesplitkey, splitkeylen, opaque, - &local_err) != splitkeylen) { + &local_err) < 0) { error_propagate(errp, local_err); return -1; } diff --git a/crypto/block.c b/crypto/block.c index XXXXXXX..XXXXXXX 100644 --- a/crypto/block.c +++ b/crypto/block.c @@ -XXX,XX +XXX,XX @@ QCryptoBlock *qcrypto_block_create(QCryptoBlockCreateOptions *options, } -static ssize_t qcrypto_block_headerlen_hdr_init_func(QCryptoBlock *block, +static int qcrypto_block_headerlen_hdr_init_func(QCryptoBlock *block, size_t headerlen, void *opaque, Error **errp) { size_t *headerlenp = opaque; @@ -XXX,XX +XXX,XX @@ static ssize_t qcrypto_block_headerlen_hdr_init_func(QCryptoBlock *block, } -static ssize_t qcrypto_block_headerlen_hdr_write_func(QCryptoBlock *block, +static int qcrypto_block_headerlen_hdr_write_func(QCryptoBlock *block, size_t offset, const uint8_t *buf, size_t buflen, void *opaque, Error **errp) { /* Discard the bytes, we're not actually writing to an image */ - return buflen; + return 0; } diff --git a/tests/unit/test-crypto-block.c b/tests/unit/test-crypto-block.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-crypto-block.c +++ b/tests/unit/test-crypto-block.c @@ -XXX,XX +XXX,XX @@ static struct QCryptoBlockTestData { }; -static ssize_t test_block_read_func(QCryptoBlock *block, - size_t offset, - uint8_t *buf, - size_t buflen, - void *opaque, - Error **errp) +static int test_block_read_func(QCryptoBlock *block, + size_t offset, + uint8_t *buf, + size_t buflen, + void *opaque, + Error **errp) { Buffer *header = opaque; @@ -XXX,XX +XXX,XX @@ static ssize_t test_block_read_func(QCryptoBlock *block, memcpy(buf, header->buffer + offset, buflen); - return buflen; + return 0; } -static ssize_t test_block_init_func(QCryptoBlock *block, - size_t headerlen, - void *opaque, - Error **errp) +static int test_block_init_func(QCryptoBlock *block, + size_t headerlen, + void *opaque, + Error **errp) { Buffer *header = opaque; @@ -XXX,XX +XXX,XX @@ static ssize_t test_block_init_func(QCryptoBlock *block, buffer_reserve(header, headerlen); - return headerlen; + return 0; } -static ssize_t test_block_write_func(QCryptoBlock *block, - size_t offset, - const uint8_t *buf, - size_t buflen, - void *opaque, - Error **errp) +static int test_block_write_func(QCryptoBlock *block, + size_t offset, + const uint8_t *buf, + size_t buflen, + void *opaque, + Error **errp) { Buffer *header = opaque; @@ -XXX,XX +XXX,XX @@ static ssize_t test_block_write_func(QCryptoBlock *block, memcpy(header->buffer + offset, buf, buflen); header->offset = offset + buflen; - return buflen; + return 0; } -- 2.35.3 From: Alberto Faria <afaria@redhat.com> It does not mutate the buffer. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220609152744.3891847-6-afaria@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/block/block_int-io.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/block/block_int-io.h b/include/block/block_int-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-io.h +++ b/include/block/block_int-io.h @@ -XXX,XX +XXX,XX @@ static inline int coroutine_fn bdrv_co_pread(BdrvChild *child, } static inline int coroutine_fn bdrv_co_pwrite(BdrvChild *child, - int64_t offset, unsigned int bytes, void *buf, BdrvRequestFlags flags) + int64_t offset, unsigned int bytes, const void *buf, BdrvRequestFlags flags) { QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); IO_CODE(); -- 2.35.3 From: Alberto Faria <afaria@redhat.com> For consistency with other I/O functions, and in preparation to implement bdrv_{pread,pwrite}() using generated_co_wrapper. unsigned int fits in int64_t, so all callers remain correct. bdrv_check_request32() is called further down the stack and causes -EIO to be returned if 'bytes' is negative or greater than BDRV_REQUEST_MAX_BYTES, which in turns never exceeds SIZE_MAX. Signed-off-by: Alberto Faria <afaria@redhat.com> Message-Id: <20220609152744.3891847-7-afaria@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- block/coroutines.h | 4 ++-- include/block/block_int-io.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/block/coroutines.h b/block/coroutines.h index XXXXXXX..XXXXXXX 100644 --- a/block/coroutines.h +++ b/block/coroutines.h @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_do_flush(BlockBackend *blk); */ int generated_co_wrapper -bdrv_preadv(BdrvChild *child, int64_t offset, unsigned int bytes, +bdrv_preadv(BdrvChild *child, int64_t offset, int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); int generated_co_wrapper -bdrv_pwritev(BdrvChild *child, int64_t offset, unsigned int bytes, +bdrv_pwritev(BdrvChild *child, int64_t offset, int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); int generated_co_wrapper diff --git a/include/block/block_int-io.h b/include/block/block_int-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-io.h +++ b/include/block/block_int-io.h @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child, QEMUIOVector *qiov, size_t qiov_offset, BdrvRequestFlags flags); static inline int coroutine_fn bdrv_co_pread(BdrvChild *child, - int64_t offset, unsigned int bytes, void *buf, BdrvRequestFlags flags) + int64_t offset, int64_t bytes, void *buf, BdrvRequestFlags flags) { QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); IO_CODE(); @@ -XXX,XX +XXX,XX @@ static inline int coroutine_fn bdrv_co_pread(BdrvChild *child, } static inline int coroutine_fn bdrv_co_pwrite(BdrvChild *child, - int64_t offset, unsigned int bytes, const void *buf, BdrvRequestFlags flags) + int64_t offset, int64_t bytes, const void *buf, BdrvRequestFlags flags) { QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); IO_CODE(); -- 2.35.3 From: Alberto Faria <afaria@redhat.com> bdrv_{pread,pwrite}() now return -EIO instead of -EINVAL when 'bytes' is negative, making them consistent with bdrv_{preadv,pwritev}() and bdrv_co_{pread,pwrite,preadv,pwritev}(). bdrv_pwrite_zeroes() now also calls trace_bdrv_co_pwrite_zeroes() and clears the BDRV_REQ_MAY_UNMAP flag when appropriate, which it didn't previously. Signed-off-by: Alberto Faria <afaria@redhat.com> Message-Id: <20220609152744.3891847-8-afaria@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/block/block-io.h | 15 +++++++++------ block/io.c | 41 ---------------------------------------- 2 files changed, 9 insertions(+), 47 deletions(-) diff --git a/include/block/block-io.h b/include/block/block-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-io.h +++ b/include/block/block-io.h @@ -XXX,XX +XXX,XX @@ * to catch when they are accidentally called by the wrong API. */ -int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset, - int64_t bytes, BdrvRequestFlags flags); +int generated_co_wrapper bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset, + int64_t bytes, + BdrvRequestFlags flags); int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags); -int bdrv_pread(BdrvChild *child, int64_t offset, int64_t bytes, void *buf, - BdrvRequestFlags flags); -int bdrv_pwrite(BdrvChild *child, int64_t offset, int64_t bytes, - const void *buf, BdrvRequestFlags flags); +int generated_co_wrapper bdrv_pread(BdrvChild *child, int64_t offset, + int64_t bytes, void *buf, + BdrvRequestFlags flags); +int generated_co_wrapper bdrv_pwrite(BdrvChild *child, int64_t offset, + int64_t bytes, const void *buf, + BdrvRequestFlags flags); int bdrv_pwrite_sync(BdrvChild *child, int64_t offset, int64_t bytes, const void *buf, BdrvRequestFlags flags); /* diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static int bdrv_check_request32(int64_t offset, int64_t bytes, return 0; } -int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset, - int64_t bytes, BdrvRequestFlags flags) -{ - IO_CODE(); - return bdrv_pwritev(child, offset, bytes, NULL, - BDRV_REQ_ZERO_WRITE | flags); -} - /* * Completely zero out a block device with the help of bdrv_pwrite_zeroes. * The operation is sped up by checking the block status and only writing @@ -XXX,XX +XXX,XX @@ int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) } } -/* See bdrv_pwrite() for the return codes */ -int bdrv_pread(BdrvChild *child, int64_t offset, int64_t bytes, void *buf, - BdrvRequestFlags flags) -{ - QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); - IO_CODE(); - - if (bytes < 0) { - return -EINVAL; - } - - return bdrv_preadv(child, offset, bytes, &qiov, flags); -} - -/* Return no. of bytes on success or < 0 on error. Important errors are: - -EIO generic I/O error (may happen for all errors) - -ENOMEDIUM No media inserted. - -EINVAL Invalid offset or number of bytes - -EACCES Trying to write a read-only device -*/ -int bdrv_pwrite(BdrvChild *child, int64_t offset, int64_t bytes, - const void *buf, BdrvRequestFlags flags) -{ - QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); - IO_CODE(); - - if (bytes < 0) { - return -EINVAL; - } - - return bdrv_pwritev(child, offset, bytes, &qiov, flags); -} - /* * Writes to the file and ensures that no writes are reordered across this * request (acts as a barrier) -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Also convert bdrv_pwrite_sync() to being implemented using generated_co_wrapper. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220609152744.3891847-9-afaria@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/block/block-io.h | 8 ++++++-- block/io.c | 9 +++++---- 2 files changed, 11 insertions(+), 6 deletions(-) diff --git a/include/block/block-io.h b/include/block/block-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-io.h +++ b/include/block/block-io.h @@ -XXX,XX +XXX,XX @@ int generated_co_wrapper bdrv_pread(BdrvChild *child, int64_t offset, int generated_co_wrapper bdrv_pwrite(BdrvChild *child, int64_t offset, int64_t bytes, const void *buf, BdrvRequestFlags flags); -int bdrv_pwrite_sync(BdrvChild *child, int64_t offset, int64_t bytes, - const void *buf, BdrvRequestFlags flags); +int generated_co_wrapper bdrv_pwrite_sync(BdrvChild *child, int64_t offset, + int64_t bytes, const void *buf, + BdrvRequestFlags flags); +int coroutine_fn bdrv_co_pwrite_sync(BdrvChild *child, int64_t offset, + int64_t bytes, const void *buf, + BdrvRequestFlags flags); /* * Efficiently zero a region of the disk image. Note that this is a regular * I/O request like read or write and should have a reasonable size. This diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) * * Returns 0 on success, -errno in error cases. */ -int bdrv_pwrite_sync(BdrvChild *child, int64_t offset, int64_t bytes, - const void *buf, BdrvRequestFlags flags) +int coroutine_fn bdrv_co_pwrite_sync(BdrvChild *child, int64_t offset, + int64_t bytes, const void *buf, + BdrvRequestFlags flags) { int ret; IO_CODE(); - ret = bdrv_pwrite(child, offset, bytes, buf, flags); + ret = bdrv_co_pwrite(child, offset, bytes, buf, flags); if (ret < 0) { return ret; } - ret = bdrv_flush(child->bs); + ret = bdrv_co_flush(child->bs); if (ret < 0) { return ret; } -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Convert uses of bdrv_pwrite_sync() into bdrv_co_pwrite_sync() when the callers are already coroutine_fn. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <v.sementsov-og@mail.ru> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220609152744.3891847-10-afaria@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- block/parallels.c | 2 +- block/qcow2-snapshot.c | 6 +++--- block/qcow2.c | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/block/parallels.c b/block/parallels.c index XXXXXXX..XXXXXXX 100644 --- a/block/parallels.c +++ b/block/parallels.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn parallels_co_check(BlockDriverState *bs, ret = 0; if (flush_bat) { - ret = bdrv_pwrite_sync(bs->file, 0, s->header_size, s->header, 0); + ret = bdrv_co_pwrite_sync(bs->file, 0, s->header_size, s->header, 0); if (ret < 0) { res->check_errors++; goto out; diff --git a/block/qcow2-snapshot.c b/block/qcow2-snapshot.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-snapshot.c +++ b/block/qcow2-snapshot.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn qcow2_check_read_snapshot_table(BlockDriverState *bs, assert(fix & BDRV_FIX_ERRORS); snapshot_table_pointer.nb_snapshots = cpu_to_be32(s->nb_snapshots); - ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots), - sizeof(snapshot_table_pointer.nb_snapshots), - &snapshot_table_pointer.nb_snapshots, 0); + ret = bdrv_co_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots), + sizeof(snapshot_table_pointer.nb_snapshots), + &snapshot_table_pointer.nb_snapshots, 0); if (ret < 0) { result->check_errors++; fprintf(stderr, "ERROR failed to update the snapshot count in the " diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset, /* write updated header.size */ offset = cpu_to_be64(offset); - ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, size), - sizeof(offset), &offset, 0); + ret = bdrv_co_pwrite_sync(bs->file, offsetof(QCowHeader, size), + sizeof(offset), &offset, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to update the image size"); goto fail; -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Use bdrv_pwrite_sync() instead of calling bdrv_pwrite() and bdrv_flush() separately. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220609152744.3891847-11-afaria@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- block/qcow2.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ int qcow2_mark_dirty(BlockDriverState *bs) } val = cpu_to_be64(s->incompatible_features | QCOW2_INCOMPAT_DIRTY); - ret = bdrv_pwrite(bs->file, offsetof(QCowHeader, incompatible_features), - sizeof(val), &val, 0); - if (ret < 0) { - return ret; - } - ret = bdrv_flush(bs->file->bs); + ret = bdrv_pwrite_sync(bs->file, + offsetof(QCowHeader, incompatible_features), + sizeof(val), &val, 0); if (ret < 0) { return ret; } -- 2.35.3 From: John Snow <jsnow@redhat.com> Fixes: 58a6fdcc Signed-off-by: John Snow <jsnow@redhat.com> Tested-by: Daniel P. Berrangé <berrange@redhat.com> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Message-Id: <20220616142659.3184115-2-jsnow@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/223.out | 4 ++-- tests/qemu-iotests/307.out | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tests/qemu-iotests/223.out b/tests/qemu-iotests/223.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/223.out +++ b/tests/qemu-iotests/223.out @@ -XXX,XX +XXX,XX @@ exports available: 3 export: 'n2' description: some text size: 4194304 - flags: 0xced ( flush fua trim zeroes df cache fast-zero ) + flags: 0xded ( flush fua trim zeroes df multi cache fast-zero ) min block: 1 opt block: 4096 max block: 33554432 @@ -XXX,XX +XXX,XX @@ exports available: 3 export: 'n2' description: some text size: 4194304 - flags: 0xced ( flush fua trim zeroes df cache fast-zero ) + flags: 0xded ( flush fua trim zeroes df multi cache fast-zero ) min block: 1 opt block: 4096 max block: 33554432 diff --git a/tests/qemu-iotests/307.out b/tests/qemu-iotests/307.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/307.out +++ b/tests/qemu-iotests/307.out @@ -XXX,XX +XXX,XX @@ exports available: 2 export: 'export1' description: This is the writable second export size: 67108864 - flags: 0xced ( flush fua trim zeroes df cache fast-zero ) + flags: 0xded ( flush fua trim zeroes df multi cache fast-zero ) min block: XXX opt block: XXX max block: XXX @@ -XXX,XX +XXX,XX @@ exports available: 1 export: 'export1' description: This is the writable second export size: 67108864 - flags: 0xced ( flush fua trim zeroes df cache fast-zero ) + flags: 0xded ( flush fua trim zeroes df multi cache fast-zero ) min block: XXX opt block: XXX max block: XXX -- 2.35.3 From: John Snow <jsnow@redhat.com> In certain container environments we may not have FUSE at all, so skip the test in this circumstance too. Signed-off-by: John Snow <jsnow@redhat.com> Message-Id: <20220616142659.3184115-3-jsnow@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- tests/qemu-iotests/108 | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tests/qemu-iotests/108 b/tests/qemu-iotests/108 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/108 +++ b/tests/qemu-iotests/108 @@ -XXX,XX +XXX,XX @@ if sudo -n losetup &>/dev/null; then else loopdev=false + # Check for usable FUSE in the host environment: + if test ! -c "/dev/fuse"; then + _notrun 'No passwordless sudo nor usable /dev/fuse' + fi + # QSD --export fuse will either yield "Parameter 'id' is missing" # or "Invalid parameter 'fuse'", depending on whether there is # FUSE support or not. -- 2.35.3 From: Alberto Faria <afaria@redhat.com> They currently return the value of their 'bytes' parameter on success. Make them return 0 instead, for consistency with other I/O functions and in preparation to implement them using generated_co_wrapper. This also makes it clear that short reads/writes are not possible. Signed-off-by: Alberto Faria <afaria@redhat.com> Message-Id: <20220705161527.1054072-2-afaria@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- block.c | 8 +++++--- block/block-backend.c | 7 ++----- block/qcow.c | 6 +++--- hw/block/m25p80.c | 2 +- hw/misc/mac_via.c | 4 ++-- hw/misc/sifive_u_otp.c | 2 +- hw/nvram/eeprom_at24c.c | 8 ++++---- hw/nvram/spapr_nvram.c | 14 +++++++------- hw/ppc/pnv_pnor.c | 2 +- qemu-img.c | 25 +++++++++---------------- qemu-io-cmds.c | 18 ++++++++++++------ tests/unit/test-block-iothread.c | 4 ++-- 12 files changed, 49 insertions(+), 51 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static int find_image_format(BlockBackend *file, const char *filename, return ret; } - drv = bdrv_probe_all(buf, ret, filename); + drv = bdrv_probe_all(buf, sizeof(buf), filename); if (!drv) { error_setg(errp, "Could not determine image format: No compatible " "driver found"); - ret = -ENOENT; + *pdrv = NULL; + return -ENOENT; } + *pdrv = drv; - return ret; + return 0; } /** diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int bytes) ret = blk_do_preadv(blk, offset, bytes, &qiov, 0); blk_dec_in_flight(blk); - return ret < 0 ? ret : bytes; + return ret; } int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int bytes, BdrvRequestFlags flags) { - int ret; QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); IO_OR_GS_CODE(); - ret = blk_pwritev_part(blk, offset, bytes, &qiov, 0, flags); - - return ret < 0 ? ret : bytes; + return blk_pwritev_part(blk, offset, bytes, &qiov, 0, flags); } int64_t blk_getlength(BlockBackend *blk) diff --git a/block/qcow.c b/block/qcow.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow_co_create(BlockdevCreateOptions *opts, /* write all the data */ ret = blk_pwrite(qcow_blk, 0, &header, sizeof(header), 0); - if (ret != sizeof(header)) { + if (ret < 0) { goto exit; } if (qcow_opts->has_backing_file) { ret = blk_pwrite(qcow_blk, sizeof(header), qcow_opts->backing_file, backing_filename_len, 0); - if (ret != backing_filename_len) { + if (ret < 0) { goto exit; } } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow_co_create(BlockdevCreateOptions *opts, i++) { ret = blk_pwrite(qcow_blk, header_size + BDRV_SECTOR_SIZE * i, tmp, BDRV_SECTOR_SIZE, 0); - if (ret != BDRV_SECTOR_SIZE) { + if (ret < 0) { g_free(tmp); goto exit; } diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/m25p80.c +++ b/hw/block/m25p80.c @@ -XXX,XX +XXX,XX @@ static void m25p80_realize(SSIPeripheral *ss, Error **errp) trace_m25p80_binding(s); s->storage = blk_blockalign(s->blk, s->size); - if (blk_pread(s->blk, 0, s->storage, s->size) != s->size) { + if (blk_pread(s->blk, 0, s->storage, s->size) < 0) { error_setg(errp, "failed to read the initial flash content"); return; } diff --git a/hw/misc/mac_via.c b/hw/misc/mac_via.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mac_via.c +++ b/hw/misc/mac_via.c @@ -XXX,XX +XXX,XX @@ static void mos6522_q800_via1_realize(DeviceState *dev, Error **errp) return; } - len = blk_pread(v1s->blk, 0, v1s->PRAM, sizeof(v1s->PRAM)); - if (len != sizeof(v1s->PRAM)) { + ret = blk_pread(v1s->blk, 0, v1s->PRAM, sizeof(v1s->PRAM)); + if (ret < 0) { error_setg(errp, "can't read PRAM contents"); return; } diff --git a/hw/misc/sifive_u_otp.c b/hw/misc/sifive_u_otp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/sifive_u_otp.c +++ b/hw/misc/sifive_u_otp.c @@ -XXX,XX +XXX,XX @@ static void sifive_u_otp_realize(DeviceState *dev, Error **errp) return; } - if (blk_pread(s->blk, 0, s->fuse, filesize) != filesize) { + if (blk_pread(s->blk, 0, s->fuse, filesize) < 0) { error_setg(errp, "failed to read the initial flash content"); return; } diff --git a/hw/nvram/eeprom_at24c.c b/hw/nvram/eeprom_at24c.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/eeprom_at24c.c +++ b/hw/nvram/eeprom_at24c.c @@ -XXX,XX +XXX,XX @@ int at24c_eeprom_event(I2CSlave *s, enum i2c_event event) case I2C_START_RECV: DPRINTK("clear\n"); if (ee->blk && ee->changed) { - int len = blk_pwrite(ee->blk, 0, ee->mem, ee->rsize, 0); - if (len != ee->rsize) { + int ret = blk_pwrite(ee->blk, 0, ee->mem, ee->rsize, 0); + if (ret < 0) { ERR(TYPE_AT24C_EE " : failed to write backing file\n"); } @@ -XXX,XX +XXX,XX @@ void at24c_eeprom_reset(DeviceState *state) memset(ee->mem, 0, ee->rsize); if (ee->blk) { - int len = blk_pread(ee->blk, 0, ee->mem, ee->rsize); + int ret = blk_pread(ee->blk, 0, ee->mem, ee->rsize); - if (len != ee->rsize) { + if (ret < 0) { ERR(TYPE_AT24C_EE " : Failed initial sync with backing file\n"); } diff --git a/hw/nvram/spapr_nvram.c b/hw/nvram/spapr_nvram.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/spapr_nvram.c +++ b/hw/nvram/spapr_nvram.c @@ -XXX,XX +XXX,XX @@ static void rtas_nvram_store(PowerPCCPU *cpu, SpaprMachineState *spapr, { SpaprNvram *nvram = spapr->nvram; hwaddr offset, buffer, len; - int alen; + int ret; void *membuf; if ((nargs != 3) || (nret != 2)) { @@ -XXX,XX +XXX,XX @@ static void rtas_nvram_store(PowerPCCPU *cpu, SpaprMachineState *spapr, membuf = cpu_physical_memory_map(buffer, &len, false); - alen = len; + ret = 0; if (nvram->blk) { - alen = blk_pwrite(nvram->blk, offset, membuf, len, 0); + ret = blk_pwrite(nvram->blk, offset, membuf, len, 0); } assert(nvram->buf); @@ -XXX,XX +XXX,XX @@ static void rtas_nvram_store(PowerPCCPU *cpu, SpaprMachineState *spapr, cpu_physical_memory_unmap(membuf, len, 0, len); - rtas_st(rets, 0, (alen < len) ? RTAS_OUT_HW_ERROR : RTAS_OUT_SUCCESS); - rtas_st(rets, 1, (alen < 0) ? 0 : alen); + rtas_st(rets, 0, (ret < 0) ? RTAS_OUT_HW_ERROR : RTAS_OUT_SUCCESS); + rtas_st(rets, 1, (ret < 0) ? 0 : len); } static void spapr_nvram_realize(SpaprVioDevice *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void spapr_nvram_realize(SpaprVioDevice *dev, Error **errp) } if (nvram->blk) { - int alen = blk_pread(nvram->blk, 0, nvram->buf, nvram->size); + ret = blk_pread(nvram->blk, 0, nvram->buf, nvram->size); - if (alen != nvram->size) { + if (ret < 0) { error_setg(errp, "can't read spapr-nvram contents"); return; } diff --git a/hw/ppc/pnv_pnor.c b/hw/ppc/pnv_pnor.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ppc/pnv_pnor.c +++ b/hw/ppc/pnv_pnor.c @@ -XXX,XX +XXX,XX @@ static void pnv_pnor_realize(DeviceState *dev, Error **errp) s->storage = blk_blockalign(s->blk, s->size); - if (blk_pread(s->blk, 0, s->storage, s->size) != s->size) { + if (blk_pread(s->blk, 0, s->storage, s->size) < 0) { error_setg(errp, "failed to read the initial flash content"); return; } diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int img_dd(int argc, char **argv) in.buf = g_new(uint8_t, in.bsz); for (out_pos = 0; in_pos < size; block_count++) { - int in_ret, out_ret; + int bytes = (in_pos + in.bsz > size) ? size - in_pos : in.bsz; - if (in_pos + in.bsz > size) { - in_ret = blk_pread(blk1, in_pos, in.buf, size - in_pos); - } else { - in_ret = blk_pread(blk1, in_pos, in.buf, in.bsz); - } - if (in_ret < 0) { + ret = blk_pread(blk1, in_pos, in.buf, bytes); + if (ret < 0) { error_report("error while reading from input image file: %s", - strerror(-in_ret)); - ret = -1; + strerror(-ret)); goto out; } - in_pos += in_ret; + in_pos += bytes; - out_ret = blk_pwrite(blk2, out_pos, in.buf, in_ret, 0); - - if (out_ret < 0) { + ret = blk_pwrite(blk2, out_pos, in.buf, bytes, 0); + if (ret < 0) { error_report("error while writing to output image file: %s", - strerror(-out_ret)); - ret = -1; + strerror(-ret)); goto out; } - out_pos += out_ret; + out_pos += bytes; } out: diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -XXX,XX +XXX,XX @@ fail: static int do_pread(BlockBackend *blk, char *buf, int64_t offset, int64_t bytes, int64_t *total) { + int ret; + if (bytes > INT_MAX) { return -ERANGE; } - *total = blk_pread(blk, offset, (uint8_t *)buf, bytes); - if (*total < 0) { - return *total; + ret = blk_pread(blk, offset, (uint8_t *)buf, bytes); + if (ret < 0) { + return ret; } + *total = bytes; return 1; } static int do_pwrite(BlockBackend *blk, char *buf, int64_t offset, int64_t bytes, int flags, int64_t *total) { + int ret; + if (bytes > INT_MAX) { return -ERANGE; } - *total = blk_pwrite(blk, offset, (uint8_t *)buf, bytes, flags); - if (*total < 0) { - return *total; + ret = blk_pwrite(blk, offset, (uint8_t *)buf, bytes, flags); + if (ret < 0) { + return ret; } + *total = bytes; return 1; } diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_sync_op_blk_pread(BlockBackend *blk) /* Success */ ret = blk_pread(blk, 0, buf, sizeof(buf)); - g_assert_cmpint(ret, ==, 512); + g_assert_cmpint(ret, ==, 0); /* Early error: Negative offset */ ret = blk_pread(blk, -2, buf, sizeof(buf)); @@ -XXX,XX +XXX,XX @@ static void test_sync_op_blk_pwrite(BlockBackend *blk) /* Success */ ret = blk_pwrite(blk, 0, buf, sizeof(buf), 0); - g_assert_cmpint(ret, ==, 512); + g_assert_cmpint(ret, ==, 0); /* Early error: Negative offset */ ret = blk_pwrite(blk, -2, buf, sizeof(buf), 0); -- 2.35.3 From: Alberto Faria <afaria@redhat.com> For consistency with other I/O functions, and in preparation to implement it using generated_co_wrapper. Callers were updated using this Coccinelle script: @@ expression blk, offset, buf, bytes; @@ - blk_pread(blk, offset, buf, bytes) + blk_pread(blk, offset, buf, bytes, 0) It had no effect on hw/block/nand.c, presumably due to the #if, so that file was updated manually. Overly-long lines were then fixed by hand. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Greg Kurz <groug@kaod.org> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-3-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/sysemu/block-backend-io.h | 3 ++- block.c | 2 +- block/block-backend.c | 5 +++-- block/commit.c | 2 +- block/export/fuse.c | 2 +- hw/arm/allwinner-h3.c | 2 +- hw/arm/aspeed.c | 2 +- hw/block/block.c | 2 +- hw/block/fdc.c | 6 +++--- hw/block/hd-geometry.c | 2 +- hw/block/m25p80.c | 2 +- hw/block/nand.c | 12 ++++++------ hw/block/onenand.c | 12 ++++++------ hw/ide/atapi.c | 4 ++-- hw/misc/mac_via.c | 2 +- hw/misc/sifive_u_otp.c | 4 ++-- hw/nvram/eeprom_at24c.c | 2 +- hw/nvram/spapr_nvram.c | 2 +- hw/nvram/xlnx-bbram.c | 2 +- hw/nvram/xlnx-efuse.c | 2 +- hw/ppc/pnv_pnor.c | 2 +- hw/sd/sd.c | 2 +- migration/block.c | 4 ++-- nbd/server.c | 4 ++-- qemu-img.c | 12 ++++++------ qemu-io-cmds.c | 2 +- tests/unit/test-block-iothread.c | 4 ++-- 27 files changed, 52 insertions(+), 50 deletions(-) diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in, * the "I/O or GS" API. */ -int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int bytes); +int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int bytes, + BdrvRequestFlags flags); int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int bytes, BdrvRequestFlags flags); int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset, diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static int find_image_format(BlockBackend *file, const char *filename, return ret; } - ret = blk_pread(file, 0, buf, sizeof(buf)); + ret = blk_pread(file, 0, buf, sizeof(buf), 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read image for determining its " "format"); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ BlockAIOCB *blk_aio_pwrite_zeroes(BlockBackend *blk, int64_t offset, flags | BDRV_REQ_ZERO_WRITE, cb, opaque); } -int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int bytes) +int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int bytes, + BdrvRequestFlags flags) { int ret; QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); IO_OR_GS_CODE(); blk_inc_in_flight(blk); - ret = blk_do_preadv(blk, offset, bytes, &qiov, 0); + ret = blk_do_preadv(blk, offset, bytes, &qiov, flags); blk_dec_in_flight(blk); return ret; diff --git a/block/commit.c b/block/commit.c index XXXXXXX..XXXXXXX 100644 --- a/block/commit.c +++ b/block/commit.c @@ -XXX,XX +XXX,XX @@ int bdrv_commit(BlockDriverState *bs) goto ro_cleanup; } if (ret) { - ret = blk_pread(src, offset, buf, n); + ret = blk_pread(src, offset, buf, n, 0); if (ret < 0) { goto ro_cleanup; } diff --git a/block/export/fuse.c b/block/export/fuse.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/fuse.c +++ b/block/export/fuse.c @@ -XXX,XX +XXX,XX @@ static void fuse_read(fuse_req_t req, fuse_ino_t inode, return; } - ret = blk_pread(exp->common.blk, offset, buf, size); + ret = blk_pread(exp->common.blk, offset, buf, size, 0); if (ret >= 0) { fuse_reply_buf(req, buf, size); } else { diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ void allwinner_h3_bootrom_setup(AwH3State *s, BlockBackend *blk) const int64_t rom_size = 32 * KiB; g_autofree uint8_t *buffer = g_new0(uint8_t, rom_size); - if (blk_pread(blk, 8 * KiB, buffer, rom_size) < 0) { + if (blk_pread(blk, 8 * KiB, buffer, rom_size, 0) < 0) { error_setg(&error_fatal, "%s: failed to read BlockBackend data", __func__); return; diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ static void write_boot_rom(DriveInfo *dinfo, hwaddr addr, size_t rom_size, } storage = g_malloc0(rom_size); - if (blk_pread(blk, 0, storage, rom_size) < 0) { + if (blk_pread(blk, 0, storage, rom_size, 0) < 0) { error_setg(errp, "failed to read the initial flash content"); return; } diff --git a/hw/block/block.c b/hw/block/block.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/block.c +++ b/hw/block/block.c @@ -XXX,XX +XXX,XX @@ bool blk_check_size_and_read_all(BlockBackend *blk, void *buf, hwaddr size, * block device and read only on demand. */ assert(size <= BDRV_REQUEST_MAX_BYTES); - ret = blk_pread(blk, 0, buf, size); + ret = blk_pread(blk, 0, buf, size, 0); if (ret < 0) { error_setg_errno(errp, -ret, "can't read block backend"); return false; diff --git a/hw/block/fdc.c b/hw/block/fdc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/fdc.c +++ b/hw/block/fdc.c @@ -XXX,XX +XXX,XX @@ int fdctrl_transfer_handler(void *opaque, int nchan, int dma_pos, int dma_len) if (fdctrl->data_dir != FD_DIR_WRITE || len < FD_SECTOR_LEN || rel_pos != 0) { /* READ & SCAN commands and realign to a sector for WRITE */ - if (blk_pread(cur_drv->blk, fd_offset(cur_drv), - fdctrl->fifo, BDRV_SECTOR_SIZE) < 0) { + if (blk_pread(cur_drv->blk, fd_offset(cur_drv), fdctrl->fifo, + BDRV_SECTOR_SIZE, 0) < 0) { FLOPPY_DPRINTF("Floppy: error getting sector %d\n", fd_sector(cur_drv)); /* Sure, image size is too small... */ @@ -XXX,XX +XXX,XX @@ static uint32_t fdctrl_read_data(FDCtrl *fdctrl) return 0; } if (blk_pread(cur_drv->blk, fd_offset(cur_drv), fdctrl->fifo, - BDRV_SECTOR_SIZE) + BDRV_SECTOR_SIZE, 0) < 0) { FLOPPY_DPRINTF("error getting sector %d\n", fd_sector(cur_drv)); diff --git a/hw/block/hd-geometry.c b/hw/block/hd-geometry.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/hd-geometry.c +++ b/hw/block/hd-geometry.c @@ -XXX,XX +XXX,XX @@ static int guess_disk_lchs(BlockBackend *blk, blk_get_geometry(blk, &nb_sectors); - if (blk_pread(blk, 0, buf, BDRV_SECTOR_SIZE) < 0) { + if (blk_pread(blk, 0, buf, BDRV_SECTOR_SIZE, 0) < 0) { return -1; } /* test msdos magic */ diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/m25p80.c +++ b/hw/block/m25p80.c @@ -XXX,XX +XXX,XX @@ static void m25p80_realize(SSIPeripheral *ss, Error **errp) trace_m25p80_binding(s); s->storage = blk_blockalign(s->blk, s->size); - if (blk_pread(s->blk, 0, s->storage, s->size) < 0) { + if (blk_pread(s->blk, 0, s->storage, s->size, 0) < 0) { error_setg(errp, "failed to read the initial flash content"); return; } diff --git a/hw/block/nand.c b/hw/block/nand.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/nand.c +++ b/hw/block/nand.c @@ -XXX,XX +XXX,XX @@ static void glue(nand_blk_write_, NAND_PAGE_SIZE)(NANDFlashState *s) off = (s->addr & PAGE_MASK) + s->offset; soff = SECTOR_OFFSET(s->addr); if (blk_pread(s->blk, sector << BDRV_SECTOR_BITS, iobuf, - PAGE_SECTORS << BDRV_SECTOR_BITS) < 0) { + PAGE_SECTORS << BDRV_SECTOR_BITS, 0) < 0) { printf("%s: read error in sector %" PRIu64 "\n", __func__, sector); return; } @@ -XXX,XX +XXX,XX @@ static void glue(nand_blk_write_, NAND_PAGE_SIZE)(NANDFlashState *s) sector = off >> 9; soff = off & 0x1ff; if (blk_pread(s->blk, sector << BDRV_SECTOR_BITS, iobuf, - (PAGE_SECTORS + 2) << BDRV_SECTOR_BITS) < 0) { + (PAGE_SECTORS + 2) << BDRV_SECTOR_BITS, 0) < 0) { printf("%s: read error in sector %" PRIu64 "\n", __func__, sector); return; } @@ -XXX,XX +XXX,XX @@ static void glue(nand_blk_erase_, NAND_PAGE_SIZE)(NANDFlashState *s) addr = PAGE_START(addr); page = addr >> 9; if (blk_pread(s->blk, page << BDRV_SECTOR_BITS, iobuf, - BDRV_SECTOR_SIZE) < 0) { + BDRV_SECTOR_SIZE, 0) < 0) { printf("%s: read error in sector %" PRIu64 "\n", __func__, page); } memset(iobuf + (addr & 0x1ff), 0xff, (~addr & 0x1ff) + 1); @@ -XXX,XX +XXX,XX @@ static void glue(nand_blk_erase_, NAND_PAGE_SIZE)(NANDFlashState *s) page = i >> 9; if (blk_pread(s->blk, page << BDRV_SECTOR_BITS, iobuf, - BDRV_SECTOR_SIZE) < 0) { + BDRV_SECTOR_SIZE, 0) < 0) { printf("%s: read error in sector %" PRIu64 "\n", __func__, page); } memset(iobuf, 0xff, ((addr - 1) & 0x1ff) + 1); @@ -XXX,XX +XXX,XX @@ static void glue(nand_blk_load_, NAND_PAGE_SIZE)(NANDFlashState *s, if (s->blk) { if (s->mem_oob) { if (blk_pread(s->blk, SECTOR(addr) << BDRV_SECTOR_BITS, s->io, - PAGE_SECTORS << BDRV_SECTOR_BITS) < 0) { + PAGE_SECTORS << BDRV_SECTOR_BITS, 0) < 0) { printf("%s: read error in sector %" PRIu64 "\n", __func__, SECTOR(addr)); } @@ -XXX,XX +XXX,XX @@ static void glue(nand_blk_load_, NAND_PAGE_SIZE)(NANDFlashState *s, s->ioaddr = s->io + SECTOR_OFFSET(s->addr) + offset; } else { if (blk_pread(s->blk, PAGE_START(addr), s->io, - (PAGE_SECTORS + 2) << BDRV_SECTOR_BITS) < 0) { + (PAGE_SECTORS + 2) << BDRV_SECTOR_BITS, 0) < 0) { printf("%s: read error in sector %" PRIu64 "\n", __func__, PAGE_START(addr) >> 9); } diff --git a/hw/block/onenand.c b/hw/block/onenand.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/onenand.c +++ b/hw/block/onenand.c @@ -XXX,XX +XXX,XX @@ static void onenand_reset(OneNANDState *s, int cold) memset(s->blockwp, ONEN_LOCK_LOCKED, s->blocks); if (s->blk_cur && blk_pread(s->blk_cur, 0, s->boot[0], - 8 << BDRV_SECTOR_BITS) < 0) { + 8 << BDRV_SECTOR_BITS, 0) < 0) { hw_error("%s: Loading the BootRAM failed.\n", __func__); } } @@ -XXX,XX +XXX,XX @@ static inline int onenand_load_main(OneNANDState *s, int sec, int secn, assert(UINT32_MAX >> BDRV_SECTOR_BITS > secn); if (s->blk_cur) { return blk_pread(s->blk_cur, sec << BDRV_SECTOR_BITS, dest, - secn << BDRV_SECTOR_BITS) < 0; + secn << BDRV_SECTOR_BITS, 0) < 0; } else if (sec + secn > s->secs_cur) { return 1; } @@ -XXX,XX +XXX,XX @@ static inline int onenand_prog_main(OneNANDState *s, int sec, int secn, uint8_t *dp = 0; if (s->blk_cur) { dp = g_malloc(size); - if (!dp || blk_pread(s->blk_cur, offset, dp, size) < 0) { + if (!dp || blk_pread(s->blk_cur, offset, dp, size, 0) < 0) { result = 1; } } else { @@ -XXX,XX +XXX,XX @@ static inline int onenand_load_spare(OneNANDState *s, int sec, int secn, if (s->blk_cur) { uint32_t offset = (s->secs_cur + (sec >> 5)) << BDRV_SECTOR_BITS; - if (blk_pread(s->blk_cur, offset, buf, BDRV_SECTOR_SIZE) < 0) { + if (blk_pread(s->blk_cur, offset, buf, BDRV_SECTOR_SIZE, 0) < 0) { return 1; } memcpy(dest, buf + ((sec & 31) << 4), secn << 4); @@ -XXX,XX +XXX,XX @@ static inline int onenand_prog_spare(OneNANDState *s, int sec, int secn, if (s->blk_cur) { dp = g_malloc(512); if (!dp - || blk_pread(s->blk_cur, offset, dp, BDRV_SECTOR_SIZE) < 0) { + || blk_pread(s->blk_cur, offset, dp, BDRV_SECTOR_SIZE, 0) < 0) { result = 1; } else { dpp = dp + ((sec & 31) << 4); @@ -XXX,XX +XXX,XX @@ static inline int onenand_erase(OneNANDState *s, int sec, int num) goto fail; } if (blk_pread(s->blk_cur, erasesec << BDRV_SECTOR_BITS, tmpbuf, - BDRV_SECTOR_SIZE) < 0) { + BDRV_SECTOR_SIZE, 0) < 0) { goto fail; } memcpy(tmpbuf + ((sec & 31) << 4), blankbuf, 1 << 4); diff --git a/hw/ide/atapi.c b/hw/ide/atapi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ide/atapi.c +++ b/hw/ide/atapi.c @@ -XXX,XX +XXX,XX @@ cd_read_sector_sync(IDEState *s) switch (s->cd_sector_size) { case 2048: ret = blk_pread(s->blk, (int64_t)s->lba << ATAPI_SECTOR_BITS, - s->io_buffer, ATAPI_SECTOR_SIZE); + s->io_buffer, ATAPI_SECTOR_SIZE, 0); break; case 2352: ret = blk_pread(s->blk, (int64_t)s->lba << ATAPI_SECTOR_BITS, - s->io_buffer + 16, ATAPI_SECTOR_SIZE); + s->io_buffer + 16, ATAPI_SECTOR_SIZE, 0); if (ret >= 0) { cd_data_to_raw(s->io_buffer, s->lba); } diff --git a/hw/misc/mac_via.c b/hw/misc/mac_via.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mac_via.c +++ b/hw/misc/mac_via.c @@ -XXX,XX +XXX,XX @@ static void mos6522_q800_via1_realize(DeviceState *dev, Error **errp) return; } - ret = blk_pread(v1s->blk, 0, v1s->PRAM, sizeof(v1s->PRAM)); + ret = blk_pread(v1s->blk, 0, v1s->PRAM, sizeof(v1s->PRAM), 0); if (ret < 0) { error_setg(errp, "can't read PRAM contents"); return; diff --git a/hw/misc/sifive_u_otp.c b/hw/misc/sifive_u_otp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/sifive_u_otp.c +++ b/hw/misc/sifive_u_otp.c @@ -XXX,XX +XXX,XX @@ static uint64_t sifive_u_otp_read(void *opaque, hwaddr addr, unsigned int size) int32_t buf; if (blk_pread(s->blk, s->pa * SIFIVE_U_OTP_FUSE_WORD, &buf, - SIFIVE_U_OTP_FUSE_WORD) < 0) { + SIFIVE_U_OTP_FUSE_WORD, 0) < 0) { error_report("read error index<%d>", s->pa); return 0xff; } @@ -XXX,XX +XXX,XX @@ static void sifive_u_otp_realize(DeviceState *dev, Error **errp) return; } - if (blk_pread(s->blk, 0, s->fuse, filesize) < 0) { + if (blk_pread(s->blk, 0, s->fuse, filesize, 0) < 0) { error_setg(errp, "failed to read the initial flash content"); return; } diff --git a/hw/nvram/eeprom_at24c.c b/hw/nvram/eeprom_at24c.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/eeprom_at24c.c +++ b/hw/nvram/eeprom_at24c.c @@ -XXX,XX +XXX,XX @@ void at24c_eeprom_reset(DeviceState *state) memset(ee->mem, 0, ee->rsize); if (ee->blk) { - int ret = blk_pread(ee->blk, 0, ee->mem, ee->rsize); + int ret = blk_pread(ee->blk, 0, ee->mem, ee->rsize, 0); if (ret < 0) { ERR(TYPE_AT24C_EE diff --git a/hw/nvram/spapr_nvram.c b/hw/nvram/spapr_nvram.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/spapr_nvram.c +++ b/hw/nvram/spapr_nvram.c @@ -XXX,XX +XXX,XX @@ static void spapr_nvram_realize(SpaprVioDevice *dev, Error **errp) } if (nvram->blk) { - ret = blk_pread(nvram->blk, 0, nvram->buf, nvram->size); + ret = blk_pread(nvram->blk, 0, nvram->buf, nvram->size, 0); if (ret < 0) { error_setg(errp, "can't read spapr-nvram contents"); diff --git a/hw/nvram/xlnx-bbram.c b/hw/nvram/xlnx-bbram.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/xlnx-bbram.c +++ b/hw/nvram/xlnx-bbram.c @@ -XXX,XX +XXX,XX @@ static void bbram_bdrv_read(XlnxBBRam *s, Error **errp) blk_name(s->blk)); } - if (blk_pread(s->blk, 0, ram, nr) < 0) { + if (blk_pread(s->blk, 0, ram, nr, 0) < 0) { error_setg(errp, "%s: Failed to read %u bytes from BBRAM backstore.", blk_name(s->blk), nr); diff --git a/hw/nvram/xlnx-efuse.c b/hw/nvram/xlnx-efuse.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/xlnx-efuse.c +++ b/hw/nvram/xlnx-efuse.c @@ -XXX,XX +XXX,XX @@ static int efuse_bdrv_read(XlnxEFuse *s, Error **errp) blk_name(s->blk)); } - if (blk_pread(s->blk, 0, ram, nr) < 0) { + if (blk_pread(s->blk, 0, ram, nr, 0) < 0) { error_setg(errp, "%s: Failed to read %u bytes from eFUSE backstore.", blk_name(s->blk), nr); return -1; diff --git a/hw/ppc/pnv_pnor.c b/hw/ppc/pnv_pnor.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ppc/pnv_pnor.c +++ b/hw/ppc/pnv_pnor.c @@ -XXX,XX +XXX,XX @@ static void pnv_pnor_realize(DeviceState *dev, Error **errp) s->storage = blk_blockalign(s->blk, s->size); - if (blk_pread(s->blk, 0, s->storage, s->size) < 0) { + if (blk_pread(s->blk, 0, s->storage, s->size, 0) < 0) { error_setg(errp, "failed to read the initial flash content"); return; } diff --git a/hw/sd/sd.c b/hw/sd/sd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/sd.c +++ b/hw/sd/sd.c @@ -XXX,XX +XXX,XX @@ void sd_set_cb(SDState *sd, qemu_irq readonly, qemu_irq insert) static void sd_blk_read(SDState *sd, uint64_t addr, uint32_t len) { trace_sdcard_read_block(addr, len); - if (!sd->blk || blk_pread(sd->blk, addr, sd->data, len) < 0) { + if (!sd->blk || blk_pread(sd->blk, addr, sd->data, len, 0) < 0) { fprintf(stderr, "sd_blk_read: read error on host side\n"); } } diff --git a/migration/block.c b/migration/block.c index XXXXXXX..XXXXXXX 100644 --- a/migration/block.c +++ b/migration/block.c @@ -XXX,XX +XXX,XX @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds, bmds_set_aio_inflight(bmds, sector, nr_sectors, 1); blk_mig_unlock(); } else { - ret = blk_pread(bmds->blk, sector * BDRV_SECTOR_SIZE, blk->buf, - nr_sectors * BDRV_SECTOR_SIZE); + ret = blk_pread(bmds->blk, sector * BDRV_SECTOR_SIZE, + blk->buf, nr_sectors * BDRV_SECTOR_SIZE, 0); if (ret < 0) { goto error; } diff --git a/nbd/server.c b/nbd/server.c index XXXXXXX..XXXXXXX 100644 --- a/nbd/server.c +++ b/nbd/server.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn nbd_co_send_sparse_read(NBDClient *client, ret = nbd_co_send_iov(client, iov, 1, errp); } else { ret = blk_pread(exp->common.blk, offset + progress, - data + progress, pnum); + data + progress, pnum, 0); if (ret < 0) { error_setg_errno(errp, -ret, "reading from file failed"); break; @@ -XXX,XX +XXX,XX @@ static coroutine_fn int nbd_do_cmd_read(NBDClient *client, NBDRequest *request, data, request->len, errp); } - ret = blk_pread(exp->common.blk, request->from, data, request->len); + ret = blk_pread(exp->common.blk, request->from, data, request->len, 0); if (ret < 0) { return nbd_send_generic_reply(client, request->handle, ret, "reading from file failed", errp); diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int check_empty_sectors(BlockBackend *blk, int64_t offset, int ret = 0; int64_t idx; - ret = blk_pread(blk, offset, buffer, bytes); + ret = blk_pread(blk, offset, buffer, bytes, 0); if (ret < 0) { error_report("Error while reading offset %" PRId64 " of %s: %s", offset, filename, strerror(-ret)); @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) int64_t pnum; chunk = MIN(chunk, IO_BUF_SIZE); - ret = blk_pread(blk1, offset, buf1, chunk); + ret = blk_pread(blk1, offset, buf1, chunk, 0); if (ret < 0) { error_report("Error while reading offset %" PRId64 " of %s: %s", @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) ret = 4; goto out; } - ret = blk_pread(blk2, offset, buf2, chunk); + ret = blk_pread(blk2, offset, buf2, chunk, 0); if (ret < 0) { error_report("Error while reading offset %" PRId64 " of %s: %s", @@ -XXX,XX +XXX,XX @@ static int img_rebase(int argc, char **argv) n = old_backing_size - offset; } - ret = blk_pread(blk_old_backing, offset, buf_old, n); + ret = blk_pread(blk_old_backing, offset, buf_old, n, 0); if (ret < 0) { error_report("error while reading from old backing file"); goto out; @@ -XXX,XX +XXX,XX @@ static int img_rebase(int argc, char **argv) n = new_backing_size - offset; } - ret = blk_pread(blk_new_backing, offset, buf_new, n); + ret = blk_pread(blk_new_backing, offset, buf_new, n, 0); if (ret < 0) { error_report("error while reading from new backing file"); goto out; @@ -XXX,XX +XXX,XX @@ static int img_dd(int argc, char **argv) for (out_pos = 0; in_pos < size; block_count++) { int bytes = (in_pos + in.bsz > size) ? size - in_pos : in.bsz; - ret = blk_pread(blk1, in_pos, in.buf, bytes); + ret = blk_pread(blk1, in_pos, in.buf, bytes, 0); if (ret < 0) { error_report("error while reading from input image file: %s", strerror(-ret)); diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -XXX,XX +XXX,XX @@ static int do_pread(BlockBackend *blk, char *buf, int64_t offset, return -ERANGE; } - ret = blk_pread(blk, offset, (uint8_t *)buf, bytes); + ret = blk_pread(blk, offset, (uint8_t *)buf, bytes, 0); if (ret < 0) { return ret; } diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_sync_op_blk_pread(BlockBackend *blk) int ret; /* Success */ - ret = blk_pread(blk, 0, buf, sizeof(buf)); + ret = blk_pread(blk, 0, buf, sizeof(buf), 0); g_assert_cmpint(ret, ==, 0); /* Early error: Negative offset */ - ret = blk_pread(blk, -2, buf, sizeof(buf)); + ret = blk_pread(blk, -2, buf, sizeof(buf), 0); g_assert_cmpint(ret, ==, -EIO); } -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Swap 'buf' and 'bytes' around for consistency with blk_co_{pread,pwrite}(), and in preparation to implement these functions using generated_co_wrapper. Callers were updated using this Coccinelle script: @@ expression blk, offset, buf, bytes, flags; @@ - blk_pread(blk, offset, buf, bytes, flags) + blk_pread(blk, offset, bytes, buf, flags) @@ expression blk, offset, buf, bytes, flags; @@ - blk_pwrite(blk, offset, buf, bytes, flags) + blk_pwrite(blk, offset, bytes, buf, flags) It had no effect on hw/block/nand.c, presumably due to the #if, so that file was updated manually. Overly-long lines were then fixed by hand. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-4-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/sysemu/block-backend-io.h | 4 +-- block.c | 2 +- block/block-backend.c | 4 +-- block/commit.c | 4 +-- block/crypto.c | 2 +- block/export/fuse.c | 4 +-- block/parallels.c | 2 +- block/qcow.c | 8 +++--- block/qcow2.c | 4 +-- block/qed.c | 8 +++--- block/vdi.c | 4 +-- block/vhdx.c | 20 ++++++------- block/vmdk.c | 10 +++---- block/vpc.c | 12 ++++---- hw/arm/allwinner-h3.c | 2 +- hw/arm/aspeed.c | 2 +- hw/block/block.c | 2 +- hw/block/fdc.c | 20 ++++++------- hw/block/hd-geometry.c | 2 +- hw/block/m25p80.c | 2 +- hw/block/nand.c | 47 ++++++++++++++++--------------- hw/block/onenand.c | 32 ++++++++++----------- hw/block/pflash_cfi01.c | 4 +-- hw/block/pflash_cfi02.c | 4 +-- hw/ide/atapi.c | 4 +-- hw/misc/mac_via.c | 4 +-- hw/misc/sifive_u_otp.c | 14 ++++----- hw/nvram/eeprom_at24c.c | 4 +-- hw/nvram/spapr_nvram.c | 6 ++-- hw/nvram/xlnx-bbram.c | 4 +-- hw/nvram/xlnx-efuse.c | 4 +-- hw/ppc/pnv_pnor.c | 6 ++-- hw/sd/sd.c | 4 +-- migration/block.c | 6 ++-- nbd/server.c | 8 +++--- qemu-img.c | 18 ++++++------ qemu-io-cmds.c | 4 +-- tests/unit/test-block-iothread.c | 8 +++--- 38 files changed, 150 insertions(+), 149 deletions(-) diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in, * the "I/O or GS" API. */ -int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int bytes, +int blk_pread(BlockBackend *blk, int64_t offset, int bytes, void *buf, BdrvRequestFlags flags); -int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int bytes, +int blk_pwrite(BlockBackend *blk, int64_t offset, int bytes, const void *buf, BdrvRequestFlags flags); int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static int find_image_format(BlockBackend *file, const char *filename, return ret; } - ret = blk_pread(file, 0, buf, sizeof(buf), 0); + ret = blk_pread(file, 0, sizeof(buf), buf, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read image for determining its " "format"); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ BlockAIOCB *blk_aio_pwrite_zeroes(BlockBackend *blk, int64_t offset, flags | BDRV_REQ_ZERO_WRITE, cb, opaque); } -int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int bytes, +int blk_pread(BlockBackend *blk, int64_t offset, int bytes, void *buf, BdrvRequestFlags flags) { int ret; @@ -XXX,XX +XXX,XX @@ int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int bytes, return ret; } -int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int bytes, +int blk_pwrite(BlockBackend *blk, int64_t offset, int bytes, const void *buf, BdrvRequestFlags flags) { QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); diff --git a/block/commit.c b/block/commit.c index XXXXXXX..XXXXXXX 100644 --- a/block/commit.c +++ b/block/commit.c @@ -XXX,XX +XXX,XX @@ int bdrv_commit(BlockDriverState *bs) goto ro_cleanup; } if (ret) { - ret = blk_pread(src, offset, buf, n, 0); + ret = blk_pread(src, offset, n, buf, 0); if (ret < 0) { goto ro_cleanup; } - ret = blk_pwrite(backing, offset, buf, n, 0); + ret = blk_pwrite(backing, offset, n, buf, 0); if (ret < 0) { goto ro_cleanup; } diff --git a/block/crypto.c b/block/crypto.c index XXXXXXX..XXXXXXX 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -XXX,XX +XXX,XX @@ static int block_crypto_create_write_func(QCryptoBlock *block, struct BlockCryptoCreateData *data = opaque; ssize_t ret; - ret = blk_pwrite(data->blk, offset, buf, buflen, 0); + ret = blk_pwrite(data->blk, offset, buflen, buf, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not write encryption header"); return ret; diff --git a/block/export/fuse.c b/block/export/fuse.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/fuse.c +++ b/block/export/fuse.c @@ -XXX,XX +XXX,XX @@ static void fuse_read(fuse_req_t req, fuse_ino_t inode, return; } - ret = blk_pread(exp->common.blk, offset, buf, size, 0); + ret = blk_pread(exp->common.blk, offset, size, buf, 0); if (ret >= 0) { fuse_reply_buf(req, buf, size); } else { @@ -XXX,XX +XXX,XX @@ static void fuse_write(fuse_req_t req, fuse_ino_t inode, const char *buf, } } - ret = blk_pwrite(exp->common.blk, offset, buf, size, 0); + ret = blk_pwrite(exp->common.blk, offset, size, buf, 0); if (ret >= 0) { fuse_reply_write(req, size); } else { diff --git a/block/parallels.c b/block/parallels.c index XXXXXXX..XXXXXXX 100644 --- a/block/parallels.c +++ b/block/parallels.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn parallels_co_create(BlockdevCreateOptions* opts, memset(tmp, 0, sizeof(tmp)); memcpy(tmp, &header, sizeof(header)); - ret = blk_pwrite(blk, 0, tmp, BDRV_SECTOR_SIZE, 0); + ret = blk_pwrite(blk, 0, BDRV_SECTOR_SIZE, tmp, 0); if (ret < 0) { goto exit; } diff --git a/block/qcow.c b/block/qcow.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow_co_create(BlockdevCreateOptions *opts, } /* write all the data */ - ret = blk_pwrite(qcow_blk, 0, &header, sizeof(header), 0); + ret = blk_pwrite(qcow_blk, 0, sizeof(header), &header, 0); if (ret < 0) { goto exit; } if (qcow_opts->has_backing_file) { - ret = blk_pwrite(qcow_blk, sizeof(header), - qcow_opts->backing_file, backing_filename_len, 0); + ret = blk_pwrite(qcow_blk, sizeof(header), backing_filename_len, + qcow_opts->backing_file, 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow_co_create(BlockdevCreateOptions *opts, for (i = 0; i < DIV_ROUND_UP(sizeof(uint64_t) * l1_size, BDRV_SECTOR_SIZE); i++) { ret = blk_pwrite(qcow_blk, header_size + BDRV_SECTOR_SIZE * i, - tmp, BDRV_SECTOR_SIZE, 0); + BDRV_SECTOR_SIZE, tmp, 0); if (ret < 0) { g_free(tmp); goto exit; diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ qcow2_co_create(BlockdevCreateOptions *create_options, Error **errp) cpu_to_be64(QCOW2_INCOMPAT_EXTL2); } - ret = blk_pwrite(blk, 0, header, cluster_size, 0); + ret = blk_pwrite(blk, 0, cluster_size, header, 0); g_free(header); if (ret < 0) { error_setg_errno(errp, -ret, "Could not write qcow2 header"); @@ -XXX,XX +XXX,XX @@ qcow2_co_create(BlockdevCreateOptions *create_options, Error **errp) /* Write a refcount table with one refcount block */ refcount_table = g_malloc0(2 * cluster_size); refcount_table[0] = cpu_to_be64(2 * cluster_size); - ret = blk_pwrite(blk, cluster_size, refcount_table, 2 * cluster_size, 0); + ret = blk_pwrite(blk, cluster_size, 2 * cluster_size, refcount_table, 0); g_free(refcount_table); if (ret < 0) { diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_co_create(BlockdevCreateOptions *opts, } qed_header_cpu_to_le(&header, &le_header); - ret = blk_pwrite(blk, 0, &le_header, sizeof(le_header), 0); + ret = blk_pwrite(blk, 0, sizeof(le_header), &le_header, 0); if (ret < 0) { goto out; } - ret = blk_pwrite(blk, sizeof(le_header), qed_opts->backing_file, - header.backing_filename_size, 0); + ret = blk_pwrite(blk, sizeof(le_header), header.backing_filename_size, + qed_opts->backing_file, 0); if (ret < 0) { goto out; } l1_table = g_malloc0(l1_size); - ret = blk_pwrite(blk, header.l1_table_offset, l1_table, l1_size, 0); + ret = blk_pwrite(blk, header.l1_table_offset, l1_size, l1_table, 0); if (ret < 0) { goto out; } diff --git a/block/vdi.c b/block/vdi.c index XXXXXXX..XXXXXXX 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options, vdi_header_print(&header); } vdi_header_to_le(&header); - ret = blk_pwrite(blk, offset, &header, sizeof(header), 0); + ret = blk_pwrite(blk, offset, sizeof(header), &header, 0); if (ret < 0) { error_setg(errp, "Error writing header"); goto exit; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options, bmap[i] = VDI_UNALLOCATED; } } - ret = blk_pwrite(blk, offset, bmap, bmap_size, 0); + ret = blk_pwrite(blk, offset, bmap_size, bmap, 0); if (ret < 0) { error_setg(errp, "Error writing bmap"); goto exit; diff --git a/block/vhdx.c b/block/vhdx.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -XXX,XX +XXX,XX @@ static int vhdx_create_new_metadata(BlockBackend *blk, VHDX_META_FLAGS_IS_VIRTUAL_DISK; vhdx_metadata_entry_le_export(&md_table_entry[4]); - ret = blk_pwrite(blk, metadata_offset, buffer, VHDX_HEADER_BLOCK_SIZE, 0); + ret = blk_pwrite(blk, metadata_offset, VHDX_HEADER_BLOCK_SIZE, buffer, 0); if (ret < 0) { goto exit; } - ret = blk_pwrite(blk, metadata_offset + (64 * KiB), entry_buffer, - VHDX_METADATA_ENTRY_BUFFER_SIZE, 0); + ret = blk_pwrite(blk, metadata_offset + (64 * KiB), + VHDX_METADATA_ENTRY_BUFFER_SIZE, entry_buffer, 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int vhdx_create_bat(BlockBackend *blk, BDRVVHDXState *s, s->bat[sinfo.bat_idx] = cpu_to_le64(s->bat[sinfo.bat_idx]); sector_num += s->sectors_per_block; } - ret = blk_pwrite(blk, file_offset, s->bat, length, 0); + ret = blk_pwrite(blk, file_offset, length, s->bat, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to write the BAT"); goto exit; @@ -XXX,XX +XXX,XX @@ static int vhdx_create_new_region_table(BlockBackend *blk, } /* Now write out the region headers to disk */ - ret = blk_pwrite(blk, VHDX_REGION_TABLE_OFFSET, buffer, - VHDX_HEADER_BLOCK_SIZE, 0); + ret = blk_pwrite(blk, VHDX_REGION_TABLE_OFFSET, VHDX_HEADER_BLOCK_SIZE, + buffer, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to write first region table"); goto exit; } - ret = blk_pwrite(blk, VHDX_REGION_TABLE2_OFFSET, buffer, - VHDX_HEADER_BLOCK_SIZE, 0); + ret = blk_pwrite(blk, VHDX_REGION_TABLE2_OFFSET, VHDX_HEADER_BLOCK_SIZE, + buffer, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to write second region table"); goto exit; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vhdx_co_create(BlockdevCreateOptions *opts, creator = g_utf8_to_utf16("QEMU v" QEMU_VERSION, -1, NULL, &creator_items, NULL); signature = cpu_to_le64(VHDX_FILE_SIGNATURE); - ret = blk_pwrite(blk, VHDX_FILE_ID_OFFSET, &signature, sizeof(signature), + ret = blk_pwrite(blk, VHDX_FILE_ID_OFFSET, sizeof(signature), &signature, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to write file signature"); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vhdx_co_create(BlockdevCreateOptions *opts, } if (creator) { ret = blk_pwrite(blk, VHDX_FILE_ID_OFFSET + sizeof(signature), - creator, creator_items * sizeof(gunichar2), 0); + creator_items * sizeof(gunichar2), creator, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to write creator field"); goto delete_and_exit; diff --git a/block/vmdk.c b/block/vmdk.c index XXXXXXX..XXXXXXX 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -XXX,XX +XXX,XX @@ static int vmdk_init_extent(BlockBackend *blk, header.check_bytes[3] = 0xa; /* write all the data */ - ret = blk_pwrite(blk, 0, &magic, sizeof(magic), 0); + ret = blk_pwrite(blk, 0, sizeof(magic), &magic, 0); if (ret < 0) { error_setg(errp, QERR_IO_ERROR); goto exit; } - ret = blk_pwrite(blk, sizeof(magic), &header, sizeof(header), 0); + ret = blk_pwrite(blk, sizeof(magic), sizeof(header), &header, 0); if (ret < 0) { error_setg(errp, QERR_IO_ERROR); goto exit; @@ -XXX,XX +XXX,XX @@ static int vmdk_init_extent(BlockBackend *blk, gd_buf[i] = cpu_to_le32(tmp); } ret = blk_pwrite(blk, le64_to_cpu(header.rgd_offset) * BDRV_SECTOR_SIZE, - gd_buf, gd_buf_size, 0); + gd_buf_size, gd_buf, 0); if (ret < 0) { error_setg(errp, QERR_IO_ERROR); goto exit; @@ -XXX,XX +XXX,XX @@ static int vmdk_init_extent(BlockBackend *blk, gd_buf[i] = cpu_to_le32(tmp); } ret = blk_pwrite(blk, le64_to_cpu(header.gd_offset) * BDRV_SECTOR_SIZE, - gd_buf, gd_buf_size, 0); + gd_buf_size, gd_buf, 0); if (ret < 0) { error_setg(errp, QERR_IO_ERROR); } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vmdk_co_do_create(int64_t size, desc_offset = 0x200; } - ret = blk_pwrite(blk, desc_offset, desc, desc_len, 0); + ret = blk_pwrite(blk, desc_offset, desc_len, desc, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not write description"); goto exit; diff --git a/block/vpc.c b/block/vpc.c index XXXXXXX..XXXXXXX 100644 --- a/block/vpc.c +++ b/block/vpc.c @@ -XXX,XX +XXX,XX @@ static int create_dynamic_disk(BlockBackend *blk, VHDFooter *footer, block_size = 0x200000; num_bat_entries = DIV_ROUND_UP(total_sectors, block_size / 512); - ret = blk_pwrite(blk, offset, footer, sizeof(*footer), 0); + ret = blk_pwrite(blk, offset, sizeof(*footer), footer, 0); if (ret < 0) { goto fail; } offset = 1536 + ((num_bat_entries * 4 + 511) & ~511); - ret = blk_pwrite(blk, offset, footer, sizeof(*footer), 0); + ret = blk_pwrite(blk, offset, sizeof(*footer), footer, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int create_dynamic_disk(BlockBackend *blk, VHDFooter *footer, memset(bat_sector, 0xFF, 512); for (i = 0; i < DIV_ROUND_UP(num_bat_entries * 4, 512); i++) { - ret = blk_pwrite(blk, offset, bat_sector, 512, 0); + ret = blk_pwrite(blk, offset, 512, bat_sector, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int create_dynamic_disk(BlockBackend *blk, VHDFooter *footer, /* Write the header */ offset = 512; - ret = blk_pwrite(blk, offset, &dyndisk_header, sizeof(dyndisk_header), 0); + ret = blk_pwrite(blk, offset, sizeof(dyndisk_header), &dyndisk_header, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int create_fixed_disk(BlockBackend *blk, VHDFooter *footer, return ret; } - ret = blk_pwrite(blk, total_size - sizeof(*footer), - footer, sizeof(*footer), 0); + ret = blk_pwrite(blk, total_size - sizeof(*footer), sizeof(*footer), + footer, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Unable to write VHD header"); return ret; diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ void allwinner_h3_bootrom_setup(AwH3State *s, BlockBackend *blk) const int64_t rom_size = 32 * KiB; g_autofree uint8_t *buffer = g_new0(uint8_t, rom_size); - if (blk_pread(blk, 8 * KiB, buffer, rom_size, 0) < 0) { + if (blk_pread(blk, 8 * KiB, rom_size, buffer, 0) < 0) { error_setg(&error_fatal, "%s: failed to read BlockBackend data", __func__); return; diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ static void write_boot_rom(DriveInfo *dinfo, hwaddr addr, size_t rom_size, } storage = g_malloc0(rom_size); - if (blk_pread(blk, 0, storage, rom_size, 0) < 0) { + if (blk_pread(blk, 0, rom_size, storage, 0) < 0) { error_setg(errp, "failed to read the initial flash content"); return; } diff --git a/hw/block/block.c b/hw/block/block.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/block.c +++ b/hw/block/block.c @@ -XXX,XX +XXX,XX @@ bool blk_check_size_and_read_all(BlockBackend *blk, void *buf, hwaddr size, * block device and read only on demand. */ assert(size <= BDRV_REQUEST_MAX_BYTES); - ret = blk_pread(blk, 0, buf, size, 0); + ret = blk_pread(blk, 0, size, buf, 0); if (ret < 0) { error_setg_errno(errp, -ret, "can't read block backend"); return false; diff --git a/hw/block/fdc.c b/hw/block/fdc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/fdc.c +++ b/hw/block/fdc.c @@ -XXX,XX +XXX,XX @@ int fdctrl_transfer_handler(void *opaque, int nchan, int dma_pos, int dma_len) if (fdctrl->data_dir != FD_DIR_WRITE || len < FD_SECTOR_LEN || rel_pos != 0) { /* READ & SCAN commands and realign to a sector for WRITE */ - if (blk_pread(cur_drv->blk, fd_offset(cur_drv), fdctrl->fifo, - BDRV_SECTOR_SIZE, 0) < 0) { + if (blk_pread(cur_drv->blk, fd_offset(cur_drv), BDRV_SECTOR_SIZE, + fdctrl->fifo, 0) < 0) { FLOPPY_DPRINTF("Floppy: error getting sector %d\n", fd_sector(cur_drv)); /* Sure, image size is too small... */ @@ -XXX,XX +XXX,XX @@ int fdctrl_transfer_handler(void *opaque, int nchan, int dma_pos, int dma_len) k->read_memory(fdctrl->dma, nchan, fdctrl->fifo + rel_pos, fdctrl->data_pos, len); - if (blk_pwrite(cur_drv->blk, fd_offset(cur_drv), - fdctrl->fifo, BDRV_SECTOR_SIZE, 0) < 0) { + if (blk_pwrite(cur_drv->blk, fd_offset(cur_drv), BDRV_SECTOR_SIZE, + fdctrl->fifo, 0) < 0) { FLOPPY_DPRINTF("error writing sector %d\n", fd_sector(cur_drv)); fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM | FD_SR0_SEEK, 0x00, 0x00); @@ -XXX,XX +XXX,XX @@ static uint32_t fdctrl_read_data(FDCtrl *fdctrl) fd_sector(cur_drv)); return 0; } - if (blk_pread(cur_drv->blk, fd_offset(cur_drv), fdctrl->fifo, - BDRV_SECTOR_SIZE, 0) + if (blk_pread(cur_drv->blk, fd_offset(cur_drv), BDRV_SECTOR_SIZE, + fdctrl->fifo, 0) < 0) { FLOPPY_DPRINTF("error getting sector %d\n", fd_sector(cur_drv)); @@ -XXX,XX +XXX,XX @@ static void fdctrl_format_sector(FDCtrl *fdctrl) } memset(fdctrl->fifo, 0, FD_SECTOR_LEN); if (cur_drv->blk == NULL || - blk_pwrite(cur_drv->blk, fd_offset(cur_drv), fdctrl->fifo, - BDRV_SECTOR_SIZE, 0) < 0) { + blk_pwrite(cur_drv->blk, fd_offset(cur_drv), BDRV_SECTOR_SIZE, + fdctrl->fifo, 0) < 0) { FLOPPY_DPRINTF("error formatting sector %d\n", fd_sector(cur_drv)); fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM | FD_SR0_SEEK, 0x00, 0x00); } else { @@ -XXX,XX +XXX,XX @@ static void fdctrl_write_data(FDCtrl *fdctrl, uint32_t value) if (pos == FD_SECTOR_LEN - 1 || fdctrl->data_pos == fdctrl->data_len) { cur_drv = get_cur_drv(fdctrl); - if (blk_pwrite(cur_drv->blk, fd_offset(cur_drv), fdctrl->fifo, - BDRV_SECTOR_SIZE, 0) < 0) { + if (blk_pwrite(cur_drv->blk, fd_offset(cur_drv), BDRV_SECTOR_SIZE, + fdctrl->fifo, 0) < 0) { FLOPPY_DPRINTF("error writing sector %d\n", fd_sector(cur_drv)); break; diff --git a/hw/block/hd-geometry.c b/hw/block/hd-geometry.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/hd-geometry.c +++ b/hw/block/hd-geometry.c @@ -XXX,XX +XXX,XX @@ static int guess_disk_lchs(BlockBackend *blk, blk_get_geometry(blk, &nb_sectors); - if (blk_pread(blk, 0, buf, BDRV_SECTOR_SIZE, 0) < 0) { + if (blk_pread(blk, 0, BDRV_SECTOR_SIZE, buf, 0) < 0) { return -1; } /* test msdos magic */ diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/m25p80.c +++ b/hw/block/m25p80.c @@ -XXX,XX +XXX,XX @@ static void m25p80_realize(SSIPeripheral *ss, Error **errp) trace_m25p80_binding(s); s->storage = blk_blockalign(s->blk, s->size); - if (blk_pread(s->blk, 0, s->storage, s->size, 0) < 0) { + if (blk_pread(s->blk, 0, s->size, s->storage, 0) < 0) { error_setg(errp, "failed to read the initial flash content"); return; } diff --git a/hw/block/nand.c b/hw/block/nand.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/nand.c +++ b/hw/block/nand.c @@ -XXX,XX +XXX,XX @@ static void glue(nand_blk_write_, NAND_PAGE_SIZE)(NANDFlashState *s) sector = SECTOR(s->addr); off = (s->addr & PAGE_MASK) + s->offset; soff = SECTOR_OFFSET(s->addr); - if (blk_pread(s->blk, sector << BDRV_SECTOR_BITS, iobuf, - PAGE_SECTORS << BDRV_SECTOR_BITS, 0) < 0) { + if (blk_pread(s->blk, sector << BDRV_SECTOR_BITS, + PAGE_SECTORS << BDRV_SECTOR_BITS, iobuf, 0) < 0) { printf("%s: read error in sector %" PRIu64 "\n", __func__, sector); return; } @@ -XXX,XX +XXX,XX @@ static void glue(nand_blk_write_, NAND_PAGE_SIZE)(NANDFlashState *s) MIN(OOB_SIZE, off + s->iolen - NAND_PAGE_SIZE)); } - if (blk_pwrite(s->blk, sector << BDRV_SECTOR_BITS, iobuf, - PAGE_SECTORS << BDRV_SECTOR_BITS, 0) < 0) { + if (blk_pwrite(s->blk, sector << BDRV_SECTOR_BITS, + PAGE_SECTORS << BDRV_SECTOR_BITS, iobuf, 0) < 0) { printf("%s: write error in sector %" PRIu64 "\n", __func__, sector); } } else { off = PAGE_START(s->addr) + (s->addr & PAGE_MASK) + s->offset; sector = off >> 9; soff = off & 0x1ff; - if (blk_pread(s->blk, sector << BDRV_SECTOR_BITS, iobuf, - (PAGE_SECTORS + 2) << BDRV_SECTOR_BITS, 0) < 0) { + if (blk_pread(s->blk, sector << BDRV_SECTOR_BITS, + (PAGE_SECTORS + 2) << BDRV_SECTOR_BITS, iobuf, 0) < 0) { printf("%s: read error in sector %" PRIu64 "\n", __func__, sector); return; } mem_and(iobuf + soff, s->io, s->iolen); - if (blk_pwrite(s->blk, sector << BDRV_SECTOR_BITS, iobuf, - (PAGE_SECTORS + 2) << BDRV_SECTOR_BITS, 0) < 0) { + if (blk_pwrite(s->blk, sector << BDRV_SECTOR_BITS, + (PAGE_SECTORS + 2) << BDRV_SECTOR_BITS, iobuf, 0) < 0) { printf("%s: write error in sector %" PRIu64 "\n", __func__, sector); } } @@ -XXX,XX +XXX,XX @@ static void glue(nand_blk_erase_, NAND_PAGE_SIZE)(NANDFlashState *s) i = SECTOR(addr); page = SECTOR(addr + (1 << (ADDR_SHIFT + s->erase_shift))); for (; i < page; i ++) - if (blk_pwrite(s->blk, i << BDRV_SECTOR_BITS, iobuf, - BDRV_SECTOR_SIZE, 0) < 0) { + if (blk_pwrite(s->blk, i << BDRV_SECTOR_BITS, + BDRV_SECTOR_SIZE, iobuf, 0) < 0) { printf("%s: write error in sector %" PRIu64 "\n", __func__, i); } } else { addr = PAGE_START(addr); page = addr >> 9; - if (blk_pread(s->blk, page << BDRV_SECTOR_BITS, iobuf, - BDRV_SECTOR_SIZE, 0) < 0) { + if (blk_pread(s->blk, page << BDRV_SECTOR_BITS, + BDRV_SECTOR_SIZE, iobuf, 0) < 0) { printf("%s: read error in sector %" PRIu64 "\n", __func__, page); } memset(iobuf + (addr & 0x1ff), 0xff, (~addr & 0x1ff) + 1); - if (blk_pwrite(s->blk, page << BDRV_SECTOR_BITS, iobuf, - BDRV_SECTOR_SIZE, 0) < 0) { + if (blk_pwrite(s->blk, page << BDRV_SECTOR_BITS, + BDRV_SECTOR_SIZE, iobuf, 0) < 0) { printf("%s: write error in sector %" PRIu64 "\n", __func__, page); } @@ -XXX,XX +XXX,XX @@ static void glue(nand_blk_erase_, NAND_PAGE_SIZE)(NANDFlashState *s) i = (addr & ~0x1ff) + 0x200; for (addr += ((NAND_PAGE_SIZE + OOB_SIZE) << s->erase_shift) - 0x200; i < addr; i += 0x200) { - if (blk_pwrite(s->blk, i, iobuf, BDRV_SECTOR_SIZE, 0) < 0) { + if (blk_pwrite(s->blk, i, BDRV_SECTOR_SIZE, iobuf, 0) < 0) { printf("%s: write error in sector %" PRIu64 "\n", __func__, i >> 9); } } page = i >> 9; - if (blk_pread(s->blk, page << BDRV_SECTOR_BITS, iobuf, - BDRV_SECTOR_SIZE, 0) < 0) { + if (blk_pread(s->blk, page << BDRV_SECTOR_BITS, + BDRV_SECTOR_SIZE, iobuf, 0) < 0) { printf("%s: read error in sector %" PRIu64 "\n", __func__, page); } memset(iobuf, 0xff, ((addr - 1) & 0x1ff) + 1); - if (blk_pwrite(s->blk, page << BDRV_SECTOR_BITS, iobuf, - BDRV_SECTOR_SIZE, 0) < 0) { + if (blk_pwrite(s->blk, page << BDRV_SECTOR_BITS, + BDRV_SECTOR_SIZE, iobuf, 0) < 0) { printf("%s: write error in sector %" PRIu64 "\n", __func__, page); } } @@ -XXX,XX +XXX,XX @@ static void glue(nand_blk_load_, NAND_PAGE_SIZE)(NANDFlashState *s, if (s->blk) { if (s->mem_oob) { - if (blk_pread(s->blk, SECTOR(addr) << BDRV_SECTOR_BITS, s->io, - PAGE_SECTORS << BDRV_SECTOR_BITS, 0) < 0) { + if (blk_pread(s->blk, SECTOR(addr) << BDRV_SECTOR_BITS, + PAGE_SECTORS << BDRV_SECTOR_BITS, s->io, 0) < 0) { printf("%s: read error in sector %" PRIu64 "\n", __func__, SECTOR(addr)); } @@ -XXX,XX +XXX,XX @@ static void glue(nand_blk_load_, NAND_PAGE_SIZE)(NANDFlashState *s, OOB_SIZE); s->ioaddr = s->io + SECTOR_OFFSET(s->addr) + offset; } else { - if (blk_pread(s->blk, PAGE_START(addr), s->io, - (PAGE_SECTORS + 2) << BDRV_SECTOR_BITS, 0) < 0) { + if (blk_pread(s->blk, PAGE_START(addr), + (PAGE_SECTORS + 2) << BDRV_SECTOR_BITS, s->io, 0) + < 0) { printf("%s: read error in sector %" PRIu64 "\n", __func__, PAGE_START(addr) >> 9); } diff --git a/hw/block/onenand.c b/hw/block/onenand.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/onenand.c +++ b/hw/block/onenand.c @@ -XXX,XX +XXX,XX @@ static void onenand_reset(OneNANDState *s, int cold) /* Lock the whole flash */ memset(s->blockwp, ONEN_LOCK_LOCKED, s->blocks); - if (s->blk_cur && blk_pread(s->blk_cur, 0, s->boot[0], - 8 << BDRV_SECTOR_BITS, 0) < 0) { + if (s->blk_cur && blk_pread(s->blk_cur, 0, 8 << BDRV_SECTOR_BITS, + s->boot[0], 0) < 0) { hw_error("%s: Loading the BootRAM failed.\n", __func__); } } @@ -XXX,XX +XXX,XX @@ static inline int onenand_load_main(OneNANDState *s, int sec, int secn, assert(UINT32_MAX >> BDRV_SECTOR_BITS > sec); assert(UINT32_MAX >> BDRV_SECTOR_BITS > secn); if (s->blk_cur) { - return blk_pread(s->blk_cur, sec << BDRV_SECTOR_BITS, dest, - secn << BDRV_SECTOR_BITS, 0) < 0; + return blk_pread(s->blk_cur, sec << BDRV_SECTOR_BITS, + secn << BDRV_SECTOR_BITS, dest, 0) < 0; } else if (sec + secn > s->secs_cur) { return 1; } @@ -XXX,XX +XXX,XX @@ static inline int onenand_prog_main(OneNANDState *s, int sec, int secn, uint8_t *dp = 0; if (s->blk_cur) { dp = g_malloc(size); - if (!dp || blk_pread(s->blk_cur, offset, dp, size, 0) < 0) { + if (!dp || blk_pread(s->blk_cur, offset, size, dp, 0) < 0) { result = 1; } } else { @@ -XXX,XX +XXX,XX @@ static inline int onenand_prog_main(OneNANDState *s, int sec, int secn, dp[i] &= sp[i]; } if (s->blk_cur) { - result = blk_pwrite(s->blk_cur, offset, dp, size, 0) < 0; + result = blk_pwrite(s->blk_cur, offset, size, dp, 0) < 0; } } if (dp && s->blk_cur) { @@ -XXX,XX +XXX,XX @@ static inline int onenand_load_spare(OneNANDState *s, int sec, int secn, if (s->blk_cur) { uint32_t offset = (s->secs_cur + (sec >> 5)) << BDRV_SECTOR_BITS; - if (blk_pread(s->blk_cur, offset, buf, BDRV_SECTOR_SIZE, 0) < 0) { + if (blk_pread(s->blk_cur, offset, BDRV_SECTOR_SIZE, buf, 0) < 0) { return 1; } memcpy(dest, buf + ((sec & 31) << 4), secn << 4); @@ -XXX,XX +XXX,XX @@ static inline int onenand_prog_spare(OneNANDState *s, int sec, int secn, if (s->blk_cur) { dp = g_malloc(512); if (!dp - || blk_pread(s->blk_cur, offset, dp, BDRV_SECTOR_SIZE, 0) < 0) { + || blk_pread(s->blk_cur, offset, BDRV_SECTOR_SIZE, dp, 0) < 0) { result = 1; } else { dpp = dp + ((sec & 31) << 4); @@ -XXX,XX +XXX,XX @@ static inline int onenand_prog_spare(OneNANDState *s, int sec, int secn, dpp[i] &= sp[i]; } if (s->blk_cur) { - result = blk_pwrite(s->blk_cur, offset, dp, - BDRV_SECTOR_SIZE, 0) < 0; + result = blk_pwrite(s->blk_cur, offset, BDRV_SECTOR_SIZE, dp, + 0) < 0; } } g_free(dp); @@ -XXX,XX +XXX,XX @@ static inline int onenand_erase(OneNANDState *s, int sec, int num) for (; num > 0; num--, sec++) { if (s->blk_cur) { int erasesec = s->secs_cur + (sec >> 5); - if (blk_pwrite(s->blk_cur, sec << BDRV_SECTOR_BITS, blankbuf, - BDRV_SECTOR_SIZE, 0) < 0) { + if (blk_pwrite(s->blk_cur, sec << BDRV_SECTOR_BITS, + BDRV_SECTOR_SIZE, blankbuf, 0) < 0) { goto fail; } - if (blk_pread(s->blk_cur, erasesec << BDRV_SECTOR_BITS, tmpbuf, - BDRV_SECTOR_SIZE, 0) < 0) { + if (blk_pread(s->blk_cur, erasesec << BDRV_SECTOR_BITS, + BDRV_SECTOR_SIZE, tmpbuf, 0) < 0) { goto fail; } memcpy(tmpbuf + ((sec & 31) << 4), blankbuf, 1 << 4); - if (blk_pwrite(s->blk_cur, erasesec << BDRV_SECTOR_BITS, tmpbuf, - BDRV_SECTOR_SIZE, 0) < 0) { + if (blk_pwrite(s->blk_cur, erasesec << BDRV_SECTOR_BITS, + BDRV_SECTOR_SIZE, tmpbuf, 0) < 0) { goto fail; } } else { diff --git a/hw/block/pflash_cfi01.c b/hw/block/pflash_cfi01.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/pflash_cfi01.c +++ b/hw/block/pflash_cfi01.c @@ -XXX,XX +XXX,XX @@ static void pflash_update(PFlashCFI01 *pfl, int offset, /* widen to sector boundaries */ offset = QEMU_ALIGN_DOWN(offset, BDRV_SECTOR_SIZE); offset_end = QEMU_ALIGN_UP(offset_end, BDRV_SECTOR_SIZE); - ret = blk_pwrite(pfl->blk, offset, pfl->storage + offset, - offset_end - offset, 0); + ret = blk_pwrite(pfl->blk, offset, offset_end - offset, + pfl->storage + offset, 0); if (ret < 0) { /* TODO set error bit in status */ error_report("Could not update PFLASH: %s", strerror(-ret)); diff --git a/hw/block/pflash_cfi02.c b/hw/block/pflash_cfi02.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/pflash_cfi02.c +++ b/hw/block/pflash_cfi02.c @@ -XXX,XX +XXX,XX @@ static void pflash_update(PFlashCFI02 *pfl, int offset, int size) /* widen to sector boundaries */ offset = QEMU_ALIGN_DOWN(offset, BDRV_SECTOR_SIZE); offset_end = QEMU_ALIGN_UP(offset_end, BDRV_SECTOR_SIZE); - ret = blk_pwrite(pfl->blk, offset, pfl->storage + offset, - offset_end - offset, 0); + ret = blk_pwrite(pfl->blk, offset, offset_end - offset, + pfl->storage + offset, 0); if (ret < 0) { /* TODO set error bit in status */ error_report("Could not update PFLASH: %s", strerror(-ret)); diff --git a/hw/ide/atapi.c b/hw/ide/atapi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ide/atapi.c +++ b/hw/ide/atapi.c @@ -XXX,XX +XXX,XX @@ cd_read_sector_sync(IDEState *s) switch (s->cd_sector_size) { case 2048: ret = blk_pread(s->blk, (int64_t)s->lba << ATAPI_SECTOR_BITS, - s->io_buffer, ATAPI_SECTOR_SIZE, 0); + ATAPI_SECTOR_SIZE, s->io_buffer, 0); break; case 2352: ret = blk_pread(s->blk, (int64_t)s->lba << ATAPI_SECTOR_BITS, - s->io_buffer + 16, ATAPI_SECTOR_SIZE, 0); + ATAPI_SECTOR_SIZE, s->io_buffer + 16, 0); if (ret >= 0) { cd_data_to_raw(s->io_buffer, s->lba); } diff --git a/hw/misc/mac_via.c b/hw/misc/mac_via.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mac_via.c +++ b/hw/misc/mac_via.c @@ -XXX,XX +XXX,XX @@ static void via1_one_second(void *opaque) static void pram_update(MOS6522Q800VIA1State *v1s) { if (v1s->blk) { - if (blk_pwrite(v1s->blk, 0, v1s->PRAM, sizeof(v1s->PRAM), 0) < 0) { + if (blk_pwrite(v1s->blk, 0, sizeof(v1s->PRAM), v1s->PRAM, 0) < 0) { qemu_log("pram_update: cannot write to file\n"); } } @@ -XXX,XX +XXX,XX @@ static void mos6522_q800_via1_realize(DeviceState *dev, Error **errp) return; } - ret = blk_pread(v1s->blk, 0, v1s->PRAM, sizeof(v1s->PRAM), 0); + ret = blk_pread(v1s->blk, 0, sizeof(v1s->PRAM), v1s->PRAM, 0); if (ret < 0) { error_setg(errp, "can't read PRAM contents"); return; diff --git a/hw/misc/sifive_u_otp.c b/hw/misc/sifive_u_otp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/sifive_u_otp.c +++ b/hw/misc/sifive_u_otp.c @@ -XXX,XX +XXX,XX @@ static uint64_t sifive_u_otp_read(void *opaque, hwaddr addr, unsigned int size) if (s->blk) { int32_t buf; - if (blk_pread(s->blk, s->pa * SIFIVE_U_OTP_FUSE_WORD, &buf, - SIFIVE_U_OTP_FUSE_WORD, 0) < 0) { + if (blk_pread(s->blk, s->pa * SIFIVE_U_OTP_FUSE_WORD, + SIFIVE_U_OTP_FUSE_WORD, &buf, 0) < 0) { error_report("read error index<%d>", s->pa); return 0xff; } @@ -XXX,XX +XXX,XX @@ static void sifive_u_otp_write(void *opaque, hwaddr addr, /* write to backend */ if (s->blk) { if (blk_pwrite(s->blk, s->pa * SIFIVE_U_OTP_FUSE_WORD, - &s->fuse[s->pa], SIFIVE_U_OTP_FUSE_WORD, - 0) < 0) { + SIFIVE_U_OTP_FUSE_WORD, &s->fuse[s->pa], 0) + < 0) { error_report("write error index<%d>", s->pa); } } @@ -XXX,XX +XXX,XX @@ static void sifive_u_otp_realize(DeviceState *dev, Error **errp) return; } - if (blk_pread(s->blk, 0, s->fuse, filesize, 0) < 0) { + if (blk_pread(s->blk, 0, filesize, s->fuse, 0) < 0) { error_setg(errp, "failed to read the initial flash content"); return; } @@ -XXX,XX +XXX,XX @@ static void sifive_u_otp_realize(DeviceState *dev, Error **errp) serial_data = s->serial; if (blk_pwrite(s->blk, index * SIFIVE_U_OTP_FUSE_WORD, - &serial_data, SIFIVE_U_OTP_FUSE_WORD, 0) < 0) { + SIFIVE_U_OTP_FUSE_WORD, &serial_data, 0) < 0) { error_setg(errp, "failed to write index<%d>", index); return; } serial_data = ~(s->serial); if (blk_pwrite(s->blk, (index + 1) * SIFIVE_U_OTP_FUSE_WORD, - &serial_data, SIFIVE_U_OTP_FUSE_WORD, 0) < 0) { + SIFIVE_U_OTP_FUSE_WORD, &serial_data, 0) < 0) { error_setg(errp, "failed to write index<%d>", index + 1); return; } diff --git a/hw/nvram/eeprom_at24c.c b/hw/nvram/eeprom_at24c.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/eeprom_at24c.c +++ b/hw/nvram/eeprom_at24c.c @@ -XXX,XX +XXX,XX @@ int at24c_eeprom_event(I2CSlave *s, enum i2c_event event) case I2C_START_RECV: DPRINTK("clear\n"); if (ee->blk && ee->changed) { - int ret = blk_pwrite(ee->blk, 0, ee->mem, ee->rsize, 0); + int ret = blk_pwrite(ee->blk, 0, ee->rsize, ee->mem, 0); if (ret < 0) { ERR(TYPE_AT24C_EE " : failed to write backing file\n"); @@ -XXX,XX +XXX,XX @@ void at24c_eeprom_reset(DeviceState *state) memset(ee->mem, 0, ee->rsize); if (ee->blk) { - int ret = blk_pread(ee->blk, 0, ee->mem, ee->rsize, 0); + int ret = blk_pread(ee->blk, 0, ee->rsize, ee->mem, 0); if (ret < 0) { ERR(TYPE_AT24C_EE diff --git a/hw/nvram/spapr_nvram.c b/hw/nvram/spapr_nvram.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/spapr_nvram.c +++ b/hw/nvram/spapr_nvram.c @@ -XXX,XX +XXX,XX @@ static void rtas_nvram_store(PowerPCCPU *cpu, SpaprMachineState *spapr, ret = 0; if (nvram->blk) { - ret = blk_pwrite(nvram->blk, offset, membuf, len, 0); + ret = blk_pwrite(nvram->blk, offset, len, membuf, 0); } assert(nvram->buf); @@ -XXX,XX +XXX,XX @@ static void spapr_nvram_realize(SpaprVioDevice *dev, Error **errp) } if (nvram->blk) { - ret = blk_pread(nvram->blk, 0, nvram->buf, nvram->size, 0); + ret = blk_pread(nvram->blk, 0, nvram->size, nvram->buf, 0); if (ret < 0) { error_setg(errp, "can't read spapr-nvram contents"); @@ -XXX,XX +XXX,XX @@ static void postload_update_cb(void *opaque, bool running, RunState state) qemu_del_vm_change_state_handler(nvram->vmstate); nvram->vmstate = NULL; - blk_pwrite(nvram->blk, 0, nvram->buf, nvram->size, 0); + blk_pwrite(nvram->blk, 0, nvram->size, nvram->buf, 0); } static int spapr_nvram_post_load(void *opaque, int version_id) diff --git a/hw/nvram/xlnx-bbram.c b/hw/nvram/xlnx-bbram.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/xlnx-bbram.c +++ b/hw/nvram/xlnx-bbram.c @@ -XXX,XX +XXX,XX @@ static void bbram_bdrv_read(XlnxBBRam *s, Error **errp) blk_name(s->blk)); } - if (blk_pread(s->blk, 0, ram, nr, 0) < 0) { + if (blk_pread(s->blk, 0, nr, ram, 0) < 0) { error_setg(errp, "%s: Failed to read %u bytes from BBRAM backstore.", blk_name(s->blk), nr); @@ -XXX,XX +XXX,XX @@ static void bbram_bdrv_sync(XlnxBBRam *s, uint64_t hwaddr) } offset = hwaddr - A_BBRAM_0; - rc = blk_pwrite(s->blk, offset, &le32, 4, 0); + rc = blk_pwrite(s->blk, offset, 4, &le32, 0); if (rc < 0) { bbram_bdrv_error(s, rc, g_strdup_printf("write to offset %u", offset)); } diff --git a/hw/nvram/xlnx-efuse.c b/hw/nvram/xlnx-efuse.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/xlnx-efuse.c +++ b/hw/nvram/xlnx-efuse.c @@ -XXX,XX +XXX,XX @@ static int efuse_bdrv_read(XlnxEFuse *s, Error **errp) blk_name(s->blk)); } - if (blk_pread(s->blk, 0, ram, nr, 0) < 0) { + if (blk_pread(s->blk, 0, nr, ram, 0) < 0) { error_setg(errp, "%s: Failed to read %u bytes from eFUSE backstore.", blk_name(s->blk), nr); return -1; @@ -XXX,XX +XXX,XX @@ static void efuse_bdrv_sync(XlnxEFuse *s, unsigned int bit) le32 = cpu_to_le32(xlnx_efuse_get_row(s, bit)); row_offset = (bit / 32) * 4; - if (blk_pwrite(s->blk, row_offset, &le32, 4, 0) < 0) { + if (blk_pwrite(s->blk, row_offset, 4, &le32, 0) < 0) { error_report("%s: Failed to write offset %u of eFUSE backstore.", blk_name(s->blk), row_offset); } diff --git a/hw/ppc/pnv_pnor.c b/hw/ppc/pnv_pnor.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ppc/pnv_pnor.c +++ b/hw/ppc/pnv_pnor.c @@ -XXX,XX +XXX,XX @@ static void pnv_pnor_update(PnvPnor *s, int offset, int size) offset = QEMU_ALIGN_DOWN(offset, BDRV_SECTOR_SIZE); offset_end = QEMU_ALIGN_UP(offset_end, BDRV_SECTOR_SIZE); - ret = blk_pwrite(s->blk, offset, s->storage + offset, - offset_end - offset, 0); + ret = blk_pwrite(s->blk, offset, offset_end - offset, s->storage + offset, + 0); if (ret < 0) { error_report("Could not update PNOR offset=0x%" PRIx32" : %s", offset, strerror(-ret)); @@ -XXX,XX +XXX,XX @@ static void pnv_pnor_realize(DeviceState *dev, Error **errp) s->storage = blk_blockalign(s->blk, s->size); - if (blk_pread(s->blk, 0, s->storage, s->size, 0) < 0) { + if (blk_pread(s->blk, 0, s->size, s->storage, 0) < 0) { error_setg(errp, "failed to read the initial flash content"); return; } diff --git a/hw/sd/sd.c b/hw/sd/sd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/sd.c +++ b/hw/sd/sd.c @@ -XXX,XX +XXX,XX @@ void sd_set_cb(SDState *sd, qemu_irq readonly, qemu_irq insert) static void sd_blk_read(SDState *sd, uint64_t addr, uint32_t len) { trace_sdcard_read_block(addr, len); - if (!sd->blk || blk_pread(sd->blk, addr, sd->data, len, 0) < 0) { + if (!sd->blk || blk_pread(sd->blk, addr, len, sd->data, 0) < 0) { fprintf(stderr, "sd_blk_read: read error on host side\n"); } } @@ -XXX,XX +XXX,XX @@ static void sd_blk_read(SDState *sd, uint64_t addr, uint32_t len) static void sd_blk_write(SDState *sd, uint64_t addr, uint32_t len) { trace_sdcard_write_block(addr, len); - if (!sd->blk || blk_pwrite(sd->blk, addr, sd->data, len, 0) < 0) { + if (!sd->blk || blk_pwrite(sd->blk, addr, len, sd->data, 0) < 0) { fprintf(stderr, "sd_blk_write: write error on host side\n"); } } diff --git a/migration/block.c b/migration/block.c index XXXXXXX..XXXXXXX 100644 --- a/migration/block.c +++ b/migration/block.c @@ -XXX,XX +XXX,XX @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds, blk_mig_unlock(); } else { ret = blk_pread(bmds->blk, sector * BDRV_SECTOR_SIZE, - blk->buf, nr_sectors * BDRV_SECTOR_SIZE, 0); + nr_sectors * BDRV_SECTOR_SIZE, blk->buf, 0); if (ret < 0) { goto error; } @@ -XXX,XX +XXX,XX @@ static int block_load(QEMUFile *f, void *opaque, int version_id) cluster_size, BDRV_REQ_MAY_UNMAP); } else { - ret = blk_pwrite(blk, cur_addr, cur_buf, - cluster_size, 0); + ret = blk_pwrite(blk, cur_addr, cluster_size, cur_buf, + 0); } if (ret < 0) { break; diff --git a/nbd/server.c b/nbd/server.c index XXXXXXX..XXXXXXX 100644 --- a/nbd/server.c +++ b/nbd/server.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn nbd_co_send_sparse_read(NBDClient *client, stl_be_p(&chunk.length, pnum); ret = nbd_co_send_iov(client, iov, 1, errp); } else { - ret = blk_pread(exp->common.blk, offset + progress, - data + progress, pnum, 0); + ret = blk_pread(exp->common.blk, offset + progress, pnum, + data + progress, 0); if (ret < 0) { error_setg_errno(errp, -ret, "reading from file failed"); break; @@ -XXX,XX +XXX,XX @@ static coroutine_fn int nbd_do_cmd_read(NBDClient *client, NBDRequest *request, data, request->len, errp); } - ret = blk_pread(exp->common.blk, request->from, data, request->len, 0); + ret = blk_pread(exp->common.blk, request->from, request->len, data, 0); if (ret < 0) { return nbd_send_generic_reply(client, request->handle, ret, "reading from file failed", errp); @@ -XXX,XX +XXX,XX @@ static coroutine_fn int nbd_handle_request(NBDClient *client, if (request->flags & NBD_CMD_FLAG_FUA) { flags |= BDRV_REQ_FUA; } - ret = blk_pwrite(exp->common.blk, request->from, data, request->len, + ret = blk_pwrite(exp->common.blk, request->from, request->len, data, flags); return nbd_send_generic_reply(client, request->handle, ret, "writing to file failed", errp); diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int check_empty_sectors(BlockBackend *blk, int64_t offset, int ret = 0; int64_t idx; - ret = blk_pread(blk, offset, buffer, bytes, 0); + ret = blk_pread(blk, offset, bytes, buffer, 0); if (ret < 0) { error_report("Error while reading offset %" PRId64 " of %s: %s", offset, filename, strerror(-ret)); @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) int64_t pnum; chunk = MIN(chunk, IO_BUF_SIZE); - ret = blk_pread(blk1, offset, buf1, chunk, 0); + ret = blk_pread(blk1, offset, chunk, buf1, 0); if (ret < 0) { error_report("Error while reading offset %" PRId64 " of %s: %s", @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) ret = 4; goto out; } - ret = blk_pread(blk2, offset, buf2, chunk, 0); + ret = blk_pread(blk2, offset, chunk, buf2, 0); if (ret < 0) { error_report("Error while reading offset %" PRId64 " of %s: %s", @@ -XXX,XX +XXX,XX @@ static int img_rebase(int argc, char **argv) n = old_backing_size - offset; } - ret = blk_pread(blk_old_backing, offset, buf_old, n, 0); + ret = blk_pread(blk_old_backing, offset, n, buf_old, 0); if (ret < 0) { error_report("error while reading from old backing file"); goto out; @@ -XXX,XX +XXX,XX @@ static int img_rebase(int argc, char **argv) n = new_backing_size - offset; } - ret = blk_pread(blk_new_backing, offset, buf_new, n, 0); + ret = blk_pread(blk_new_backing, offset, n, buf_new, 0); if (ret < 0) { error_report("error while reading from new backing file"); goto out; @@ -XXX,XX +XXX,XX @@ static int img_rebase(int argc, char **argv) if (buf_old_is_zero) { ret = blk_pwrite_zeroes(blk, offset + written, pnum, 0); } else { - ret = blk_pwrite(blk, offset + written, - buf_old + written, pnum, 0); + ret = blk_pwrite(blk, offset + written, pnum, + buf_old + written, 0); } if (ret < 0) { error_report("Error while writing to COW image: %s", @@ -XXX,XX +XXX,XX @@ static int img_dd(int argc, char **argv) for (out_pos = 0; in_pos < size; block_count++) { int bytes = (in_pos + in.bsz > size) ? size - in_pos : in.bsz; - ret = blk_pread(blk1, in_pos, in.buf, bytes, 0); + ret = blk_pread(blk1, in_pos, bytes, in.buf, 0); if (ret < 0) { error_report("error while reading from input image file: %s", strerror(-ret)); @@ -XXX,XX +XXX,XX @@ static int img_dd(int argc, char **argv) } in_pos += bytes; - ret = blk_pwrite(blk2, out_pos, in.buf, bytes, 0); + ret = blk_pwrite(blk2, out_pos, bytes, in.buf, 0); if (ret < 0) { error_report("error while writing to output image file: %s", strerror(-ret)); diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -XXX,XX +XXX,XX @@ static int do_pread(BlockBackend *blk, char *buf, int64_t offset, return -ERANGE; } - ret = blk_pread(blk, offset, (uint8_t *)buf, bytes, 0); + ret = blk_pread(blk, offset, bytes, (uint8_t *)buf, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int do_pwrite(BlockBackend *blk, char *buf, int64_t offset, return -ERANGE; } - ret = blk_pwrite(blk, offset, (uint8_t *)buf, bytes, flags); + ret = blk_pwrite(blk, offset, bytes, (uint8_t *)buf, flags); if (ret < 0) { return ret; } diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_sync_op_blk_pread(BlockBackend *blk) int ret; /* Success */ - ret = blk_pread(blk, 0, buf, sizeof(buf), 0); + ret = blk_pread(blk, 0, sizeof(buf), buf, 0); g_assert_cmpint(ret, ==, 0); /* Early error: Negative offset */ - ret = blk_pread(blk, -2, buf, sizeof(buf), 0); + ret = blk_pread(blk, -2, sizeof(buf), buf, 0); g_assert_cmpint(ret, ==, -EIO); } @@ -XXX,XX +XXX,XX @@ static void test_sync_op_blk_pwrite(BlockBackend *blk) int ret; /* Success */ - ret = blk_pwrite(blk, 0, buf, sizeof(buf), 0); + ret = blk_pwrite(blk, 0, sizeof(buf), buf, 0); g_assert_cmpint(ret, ==, 0); /* Early error: Negative offset */ - ret = blk_pwrite(blk, -2, buf, sizeof(buf), 0); + ret = blk_pwrite(blk, -2, sizeof(buf), buf, 0); g_assert_cmpint(ret, ==, -EIO); } -- 2.35.3 From: Alberto Faria <afaria@redhat.com> For consistency with other I/O functions, and in preparation to implement them using generated_co_wrapper. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-5-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/sysemu/block-backend-io.h | 6 +++--- block/block-backend.c | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in, * the "I/O or GS" API. */ -int blk_pread(BlockBackend *blk, int64_t offset, int bytes, void *buf, +int blk_pread(BlockBackend *blk, int64_t offset, int64_t bytes, void *buf, BdrvRequestFlags flags); -int blk_pwrite(BlockBackend *blk, int64_t offset, int bytes, const void *buf, - BdrvRequestFlags flags); +int blk_pwrite(BlockBackend *blk, int64_t offset, int64_t bytes, + const void *buf, BdrvRequestFlags flags); int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ BlockAIOCB *blk_aio_pwrite_zeroes(BlockBackend *blk, int64_t offset, flags | BDRV_REQ_ZERO_WRITE, cb, opaque); } -int blk_pread(BlockBackend *blk, int64_t offset, int bytes, void *buf, +int blk_pread(BlockBackend *blk, int64_t offset, int64_t bytes, void *buf, BdrvRequestFlags flags) { int ret; @@ -XXX,XX +XXX,XX @@ int blk_pread(BlockBackend *blk, int64_t offset, int bytes, void *buf, return ret; } -int blk_pwrite(BlockBackend *blk, int64_t offset, int bytes, const void *buf, - BdrvRequestFlags flags) +int blk_pwrite(BlockBackend *blk, int64_t offset, int64_t bytes, + const void *buf, BdrvRequestFlags flags) { QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); IO_OR_GS_CODE(); -- 2.35.3 From: Alberto Faria <afaria@redhat.com> It does not mutate the buffer. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-6-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/sysemu/block-backend-io.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ static inline int coroutine_fn blk_co_pread(BlockBackend *blk, int64_t offset, } static inline int coroutine_fn blk_co_pwrite(BlockBackend *blk, int64_t offset, - int64_t bytes, void *buf, + int64_t bytes, const void *buf, BdrvRequestFlags flags) { QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); -- 2.35.3 From: Alberto Faria <afaria@redhat.com> We need to add include/sysemu/block-backend-io.h to the inputs of the block-gen.c target defined in block/meson.build. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-7-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- block/coroutines.h | 4 ---- include/sysemu/block-backend-io.h | 10 ++++++---- block/block-backend.c | 23 ----------------------- block/meson.build | 1 + 4 files changed, 7 insertions(+), 31 deletions(-) diff --git a/block/coroutines.h b/block/coroutines.h index XXXXXXX..XXXXXXX 100644 --- a/block/coroutines.h +++ b/block/coroutines.h @@ -XXX,XX +XXX,XX @@ bdrv_common_block_status_above(BlockDriverState *bs, int generated_co_wrapper nbd_do_establish_connection(BlockDriverState *bs, bool blocking, Error **errp); -int generated_co_wrapper -blk_do_preadv(BlockBackend *blk, int64_t offset, int64_t bytes, - QEMUIOVector *qiov, BdrvRequestFlags flags); - int generated_co_wrapper blk_do_pwritev_part(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, size_t qiov_offset, diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in, * the "I/O or GS" API. */ -int blk_pread(BlockBackend *blk, int64_t offset, int64_t bytes, void *buf, - BdrvRequestFlags flags); -int blk_pwrite(BlockBackend *blk, int64_t offset, int64_t bytes, - const void *buf, BdrvRequestFlags flags); +int generated_co_wrapper blk_pread(BlockBackend *blk, int64_t offset, + int64_t bytes, void *buf, + BdrvRequestFlags flags); +int generated_co_wrapper blk_pwrite(BlockBackend *blk, int64_t offset, + int64_t bytes, const void *buf, + BdrvRequestFlags flags); int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ BlockAIOCB *blk_aio_pwrite_zeroes(BlockBackend *blk, int64_t offset, flags | BDRV_REQ_ZERO_WRITE, cb, opaque); } -int blk_pread(BlockBackend *blk, int64_t offset, int64_t bytes, void *buf, - BdrvRequestFlags flags) -{ - int ret; - QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); - IO_OR_GS_CODE(); - - blk_inc_in_flight(blk); - ret = blk_do_preadv(blk, offset, bytes, &qiov, flags); - blk_dec_in_flight(blk); - - return ret; -} - -int blk_pwrite(BlockBackend *blk, int64_t offset, int64_t bytes, - const void *buf, BdrvRequestFlags flags) -{ - QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); - IO_OR_GS_CODE(); - - return blk_pwritev_part(blk, offset, bytes, &qiov, 0, flags); -} - int64_t blk_getlength(BlockBackend *blk) { IO_CODE(); diff --git a/block/meson.build b/block/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/meson.build +++ b/block/meson.build @@ -XXX,XX +XXX,XX @@ block_gen_c = custom_target('block-gen.c', input: files( '../include/block/block-io.h', '../include/block/block-global-state.h', + '../include/sysemu/block-backend-io.h', 'coroutines.h' ), command: [wrapper_py, '@OUTPUT@', '@INPUT@']) -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Implement them using generated_co_wrapper. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-8-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/sysemu/block-backend-io.h | 6 +++++ tests/unit/test-block-iothread.c | 42 ++++++++++++++++++++++++++++++- 2 files changed, 47 insertions(+), 1 deletion(-) diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ int generated_co_wrapper blk_pread(BlockBackend *blk, int64_t offset, int generated_co_wrapper blk_pwrite(BlockBackend *blk, int64_t offset, int64_t bytes, const void *buf, BdrvRequestFlags flags); +int generated_co_wrapper blk_preadv(BlockBackend *blk, int64_t offset, + int64_t bytes, QEMUIOVector *qiov, + BdrvRequestFlags flags); int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_pwritev_part(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, size_t qiov_offset, BdrvRequestFlags flags); +int generated_co_wrapper blk_pwritev(BlockBackend *blk, int64_t offset, + int64_t bytes, QEMUIOVector *qiov, + BdrvRequestFlags flags); int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_sync_op_blk_pwrite(BlockBackend *blk) g_assert_cmpint(ret, ==, -EIO); } +static void test_sync_op_blk_preadv(BlockBackend *blk) +{ + uint8_t buf[512]; + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, sizeof(buf)); + int ret; + + /* Success */ + ret = blk_preadv(blk, 0, sizeof(buf), &qiov, 0); + g_assert_cmpint(ret, ==, 0); + + /* Early error: Negative offset */ + ret = blk_preadv(blk, -2, sizeof(buf), &qiov, 0); + g_assert_cmpint(ret, ==, -EIO); +} + +static void test_sync_op_blk_pwritev(BlockBackend *blk) +{ + uint8_t buf[512] = { 0 }; + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, sizeof(buf)); + int ret; + + /* Success */ + ret = blk_pwritev(blk, 0, sizeof(buf), &qiov, 0); + g_assert_cmpint(ret, ==, 0); + + /* Early error: Negative offset */ + ret = blk_pwritev(blk, -2, sizeof(buf), &qiov, 0); + g_assert_cmpint(ret, ==, -EIO); +} + static void test_sync_op_load_vmstate(BdrvChild *c) { uint8_t buf[512]; @@ -XXX,XX +XXX,XX @@ const SyncOpTest sync_op_tests[] = { .name = "/sync-op/pwrite", .fn = test_sync_op_pwrite, .blkfn = test_sync_op_blk_pwrite, + }, { + .name = "/sync-op/preadv", + .fn = NULL, + .blkfn = test_sync_op_blk_preadv, + }, { + .name = "/sync-op/pwritev", + .fn = NULL, + .blkfn = test_sync_op_blk_pwritev, }, { .name = "/sync-op/load_vmstate", .fn = test_sync_op_load_vmstate, @@ -XXX,XX +XXX,XX @@ static void test_sync_op(const void *opaque) blk_set_aio_context(blk, ctx, &error_abort); aio_context_acquire(ctx); - t->fn(c); + if (t->fn) { + t->fn(c); + } if (t->blkfn) { t->blkfn(blk); } -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Implement blk_preadv_part() using generated_co_wrapper. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-9-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- block/coroutines.h | 5 ----- include/sysemu/block-backend-io.h | 7 +++++++ block/block-backend.c | 30 +++++++++++++++++++++++------- tests/unit/test-block-iothread.c | 19 +++++++++++++++++++ 4 files changed, 49 insertions(+), 12 deletions(-) diff --git a/block/coroutines.h b/block/coroutines.h index XXXXXXX..XXXXXXX 100644 --- a/block/coroutines.h +++ b/block/coroutines.h @@ -XXX,XX +XXX,XX @@ nbd_co_do_establish_connection(BlockDriverState *bs, bool blocking, Error **errp); -int coroutine_fn -blk_co_do_preadv(BlockBackend *blk, int64_t offset, int64_t bytes, - QEMUIOVector *qiov, BdrvRequestFlags flags); - - int coroutine_fn blk_co_do_pwritev_part(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, size_t qiov_offset, diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ int generated_co_wrapper blk_pread(BlockBackend *blk, int64_t offset, int generated_co_wrapper blk_pwrite(BlockBackend *blk, int64_t offset, int64_t bytes, const void *buf, BdrvRequestFlags flags); +int generated_co_wrapper blk_preadv_part(BlockBackend *blk, int64_t offset, + int64_t bytes, QEMUIOVector *qiov, + size_t qiov_offset, + BdrvRequestFlags flags); +int coroutine_fn blk_co_preadv_part(BlockBackend *blk, int64_t offset, + int64_t bytes, QEMUIOVector *qiov, + size_t qiov_offset, BdrvRequestFlags flags); int generated_co_wrapper blk_preadv(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn blk_wait_while_drained(BlockBackend *blk) } /* To be called between exactly one pair of blk_inc/dec_in_flight() */ -int coroutine_fn -blk_co_do_preadv(BlockBackend *blk, int64_t offset, int64_t bytes, - QEMUIOVector *qiov, BdrvRequestFlags flags) +static int coroutine_fn +blk_co_do_preadv_part(BlockBackend *blk, int64_t offset, int64_t bytes, + QEMUIOVector *qiov, size_t qiov_offset, + BdrvRequestFlags flags) { int ret; BlockDriverState *bs; @@ -XXX,XX +XXX,XX @@ blk_co_do_preadv(BlockBackend *blk, int64_t offset, int64_t bytes, bytes, false); } - ret = bdrv_co_preadv(blk->root, offset, bytes, qiov, flags); + ret = bdrv_co_preadv_part(blk->root, offset, bytes, qiov, qiov_offset, + flags); bdrv_dec_in_flight(bs); return ret; } @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset, IO_OR_GS_CODE(); blk_inc_in_flight(blk); - ret = blk_co_do_preadv(blk, offset, bytes, qiov, flags); + ret = blk_co_do_preadv_part(blk, offset, bytes, qiov, 0, flags); + blk_dec_in_flight(blk); + + return ret; +} + +int coroutine_fn blk_co_preadv_part(BlockBackend *blk, int64_t offset, + int64_t bytes, QEMUIOVector *qiov, + size_t qiov_offset, BdrvRequestFlags flags) +{ + int ret; + IO_OR_GS_CODE(); + + blk_inc_in_flight(blk); + ret = blk_co_do_preadv_part(blk, offset, bytes, qiov, qiov_offset, flags); blk_dec_in_flight(blk); return ret; @@ -XXX,XX +XXX,XX @@ static void blk_aio_read_entry(void *opaque) QEMUIOVector *qiov = rwco->iobuf; assert(qiov->size == acb->bytes); - rwco->ret = blk_co_do_preadv(rwco->blk, rwco->offset, acb->bytes, - qiov, rwco->flags); + rwco->ret = blk_co_do_preadv_part(rwco->blk, rwco->offset, acb->bytes, qiov, + 0, rwco->flags); blk_aio_complete(acb); } diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_sync_op_blk_pwritev(BlockBackend *blk) g_assert_cmpint(ret, ==, -EIO); } +static void test_sync_op_blk_preadv_part(BlockBackend *blk) +{ + uint8_t buf[512]; + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, sizeof(buf)); + int ret; + + /* Success */ + ret = blk_preadv_part(blk, 0, sizeof(buf), &qiov, 0, 0); + g_assert_cmpint(ret, ==, 0); + + /* Early error: Negative offset */ + ret = blk_preadv_part(blk, -2, sizeof(buf), &qiov, 0, 0); + g_assert_cmpint(ret, ==, -EIO); +} + static void test_sync_op_load_vmstate(BdrvChild *c) { uint8_t buf[512]; @@ -XXX,XX +XXX,XX @@ const SyncOpTest sync_op_tests[] = { .name = "/sync-op/pwritev", .fn = NULL, .blkfn = test_sync_op_blk_pwritev, + }, { + .name = "/sync-op/preadv_part", + .fn = NULL, + .blkfn = test_sync_op_blk_preadv_part, }, { .name = "/sync-op/load_vmstate", .fn = test_sync_op_load_vmstate, -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Also convert it into a generated_co_wrapper. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-10-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- block/coroutines.h | 5 ----- include/sysemu/block-backend-io.h | 4 ++++ block/block-backend.c | 14 -------------- tests/unit/test-block-iothread.c | 19 +++++++++++++++++++ 4 files changed, 23 insertions(+), 19 deletions(-) diff --git a/block/coroutines.h b/block/coroutines.h index XXXXXXX..XXXXXXX 100644 --- a/block/coroutines.h +++ b/block/coroutines.h @@ -XXX,XX +XXX,XX @@ bdrv_common_block_status_above(BlockDriverState *bs, int generated_co_wrapper nbd_do_establish_connection(BlockDriverState *bs, bool blocking, Error **errp); -int generated_co_wrapper -blk_do_pwritev_part(BlockBackend *blk, int64_t offset, int64_t bytes, - QEMUIOVector *qiov, size_t qiov_offset, - BdrvRequestFlags flags); - int generated_co_wrapper blk_do_ioctl(BlockBackend *blk, unsigned long int req, void *buf); diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ int generated_co_wrapper blk_preadv(BlockBackend *blk, int64_t offset, int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); +int generated_co_wrapper blk_pwritev_part(BlockBackend *blk, int64_t offset, + int64_t bytes, QEMUIOVector *qiov, + size_t qiov_offset, + BdrvRequestFlags flags); int coroutine_fn blk_co_pwritev_part(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, size_t qiov_offset, diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset, return blk_co_pwritev_part(blk, offset, bytes, qiov, 0, flags); } -static int coroutine_fn blk_pwritev_part(BlockBackend *blk, int64_t offset, - int64_t bytes, - QEMUIOVector *qiov, size_t qiov_offset, - BdrvRequestFlags flags) -{ - int ret; - - blk_inc_in_flight(blk); - ret = blk_do_pwritev_part(blk, offset, bytes, qiov, qiov_offset, flags); - blk_dec_in_flight(blk); - - return ret; -} - typedef struct BlkRwCo { BlockBackend *blk; int64_t offset; diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_sync_op_blk_preadv_part(BlockBackend *blk) g_assert_cmpint(ret, ==, -EIO); } +static void test_sync_op_blk_pwritev_part(BlockBackend *blk) +{ + uint8_t buf[512] = { 0 }; + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, sizeof(buf)); + int ret; + + /* Success */ + ret = blk_pwritev_part(blk, 0, sizeof(buf), &qiov, 0, 0); + g_assert_cmpint(ret, ==, 0); + + /* Early error: Negative offset */ + ret = blk_pwritev_part(blk, -2, sizeof(buf), &qiov, 0, 0); + g_assert_cmpint(ret, ==, -EIO); +} + static void test_sync_op_load_vmstate(BdrvChild *c) { uint8_t buf[512]; @@ -XXX,XX +XXX,XX @@ const SyncOpTest sync_op_tests[] = { .name = "/sync-op/preadv_part", .fn = NULL, .blkfn = test_sync_op_blk_preadv_part, + }, { + .name = "/sync-op/pwritev_part", + .fn = NULL, + .blkfn = test_sync_op_blk_pwritev_part, }, { .name = "/sync-op/load_vmstate", .fn = test_sync_op_load_vmstate, -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Swap 'buf' and 'bytes' around for consistency with other I/O functions. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-11-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/sysemu/block-backend-io.h | 4 ++-- block/block-backend.c | 4 ++-- qemu-img.c | 2 +- qemu-io-cmds.c | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ int blk_flush(BlockBackend *blk); int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf); -int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, const void *buf, - int64_t bytes); +int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, int64_t bytes, + const void *buf); int blk_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes); int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset, int64_t bytes, BdrvRequestFlags flags); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset, flags | BDRV_REQ_ZERO_WRITE); } -int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, const void *buf, - int64_t bytes) +int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, int64_t bytes, + const void *buf) { QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); IO_OR_GS_CODE(); diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int convert_do_copy(ImgConvertState *s) if (s->compressed && !s->ret) { /* signal EOF to align */ - ret = blk_pwrite_compressed(s->target, 0, NULL, 0); + ret = blk_pwrite_compressed(s->target, 0, 0, NULL); if (ret < 0) { return ret; } diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -XXX,XX +XXX,XX @@ static int do_write_compressed(BlockBackend *blk, char *buf, int64_t offset, return -ERANGE; } - ret = blk_pwrite_compressed(blk, offset, buf, bytes); + ret = blk_pwrite_compressed(blk, offset, bytes, buf); if (ret < 0) { return ret; } -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Also convert blk_pwrite_compressed() into a generated_co_wrapper. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-12-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/sysemu/block-backend-io.h | 7 +++++-- block/block-backend.c | 8 ++++---- tests/unit/test-block-iothread.c | 18 ++++++++++++++++++ 3 files changed, 27 insertions(+), 6 deletions(-) diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ int blk_flush(BlockBackend *blk); int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf); -int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, int64_t bytes, - const void *buf); +int generated_co_wrapper blk_pwrite_compressed(BlockBackend *blk, + int64_t offset, int64_t bytes, + const void *buf); +int coroutine_fn blk_co_pwrite_compressed(BlockBackend *blk, int64_t offset, + int64_t bytes, const void *buf); int blk_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes); int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset, int64_t bytes, BdrvRequestFlags flags); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset, flags | BDRV_REQ_ZERO_WRITE); } -int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, int64_t bytes, - const void *buf) +int coroutine_fn blk_co_pwrite_compressed(BlockBackend *blk, int64_t offset, + int64_t bytes, const void *buf) { QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); IO_OR_GS_CODE(); - return blk_pwritev_part(blk, offset, bytes, &qiov, 0, - BDRV_REQ_WRITE_COMPRESSED); + return blk_co_pwritev_part(blk, offset, bytes, &qiov, 0, + BDRV_REQ_WRITE_COMPRESSED); } int blk_truncate(BlockBackend *blk, int64_t offset, bool exact, diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_sync_op_blk_pwritev_part(BlockBackend *blk) g_assert_cmpint(ret, ==, -EIO); } +static void test_sync_op_blk_pwrite_compressed(BlockBackend *blk) +{ + uint8_t buf[512] = { 0 }; + int ret; + + /* Late error: Not supported */ + ret = blk_pwrite_compressed(blk, 0, sizeof(buf), buf); + g_assert_cmpint(ret, ==, -ENOTSUP); + + /* Early error: Negative offset */ + ret = blk_pwrite_compressed(blk, -2, sizeof(buf), buf); + g_assert_cmpint(ret, ==, -EIO); +} + static void test_sync_op_load_vmstate(BdrvChild *c) { uint8_t buf[512]; @@ -XXX,XX +XXX,XX @@ const SyncOpTest sync_op_tests[] = { .name = "/sync-op/pwritev_part", .fn = NULL, .blkfn = test_sync_op_blk_pwritev_part, + }, { + .name = "/sync-op/pwrite_compressed", + .fn = NULL, + .blkfn = test_sync_op_blk_pwrite_compressed, }, { .name = "/sync-op/load_vmstate", .fn = test_sync_op_load_vmstate, -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-13-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/sysemu/block-backend-io.h | 5 +++-- block/block-backend.c | 8 -------- tests/unit/test-block-iothread.c | 17 +++++++++++++++++ 3 files changed, 20 insertions(+), 10 deletions(-) diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ int generated_co_wrapper blk_pwrite_compressed(BlockBackend *blk, int coroutine_fn blk_co_pwrite_compressed(BlockBackend *blk, int64_t offset, int64_t bytes, const void *buf); int blk_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes); -int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset, - int64_t bytes, BdrvRequestFlags flags); +int generated_co_wrapper blk_pwrite_zeroes(BlockBackend *blk, int64_t offset, + int64_t bytes, + BdrvRequestFlags flags); int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset, int64_t bytes, BdrvRequestFlags flags); int blk_truncate(BlockBackend *blk, int64_t offset, bool exact, diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ typedef struct BlkRwCo { BdrvRequestFlags flags; } BlkRwCo; -int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset, - int64_t bytes, BdrvRequestFlags flags) -{ - IO_OR_GS_CODE(); - return blk_pwritev_part(blk, offset, bytes, NULL, 0, - flags | BDRV_REQ_ZERO_WRITE); -} - int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags) { GLOBAL_STATE_CODE(); diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_sync_op_blk_pwrite_compressed(BlockBackend *blk) g_assert_cmpint(ret, ==, -EIO); } +static void test_sync_op_blk_pwrite_zeroes(BlockBackend *blk) +{ + int ret; + + /* Success */ + ret = blk_pwrite_zeroes(blk, 0, 512, 0); + g_assert_cmpint(ret, ==, 0); + + /* Early error: Negative offset */ + ret = blk_pwrite_zeroes(blk, -2, 512, 0); + g_assert_cmpint(ret, ==, -EIO); +} + static void test_sync_op_load_vmstate(BdrvChild *c) { uint8_t buf[512]; @@ -XXX,XX +XXX,XX @@ const SyncOpTest sync_op_tests[] = { .name = "/sync-op/pwrite_compressed", .fn = NULL, .blkfn = test_sync_op_blk_pwrite_compressed, + }, { + .name = "/sync-op/pwrite_zeroes", + .fn = NULL, + .blkfn = test_sync_op_blk_pwrite_zeroes, }, { .name = "/sync-op/load_vmstate", .fn = test_sync_op_load_vmstate, -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-14-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- block/coroutines.h | 3 --- include/sysemu/block-backend-io.h | 3 ++- block/block-backend.c | 12 ------------ 3 files changed, 2 insertions(+), 16 deletions(-) diff --git a/block/coroutines.h b/block/coroutines.h index XXXXXXX..XXXXXXX 100644 --- a/block/coroutines.h +++ b/block/coroutines.h @@ -XXX,XX +XXX,XX @@ nbd_do_establish_connection(BlockDriverState *bs, bool blocking, Error **errp); int generated_co_wrapper blk_do_ioctl(BlockBackend *blk, unsigned long int req, void *buf); -int generated_co_wrapper -blk_do_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes); - int generated_co_wrapper blk_do_flush(BlockBackend *blk); #endif /* BLOCK_COROUTINES_H */ diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ static inline int coroutine_fn blk_co_pwrite(BlockBackend *blk, int64_t offset, return blk_co_pwritev(blk, offset, bytes, &qiov, flags); } +int generated_co_wrapper blk_pdiscard(BlockBackend *blk, int64_t offset, + int64_t bytes); int coroutine_fn blk_co_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes); @@ -XXX,XX +XXX,XX @@ int generated_co_wrapper blk_pwrite_compressed(BlockBackend *blk, const void *buf); int coroutine_fn blk_co_pwrite_compressed(BlockBackend *blk, int64_t offset, int64_t bytes, const void *buf); -int blk_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes); int generated_co_wrapper blk_pwrite_zeroes(BlockBackend *blk, int64_t offset, int64_t bytes, BdrvRequestFlags flags); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_pdiscard(BlockBackend *blk, int64_t offset, return ret; } -int blk_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes) -{ - int ret; - IO_OR_GS_CODE(); - - blk_inc_in_flight(blk); - ret = blk_do_pdiscard(blk, offset, bytes); - blk_dec_in_flight(blk); - - return ret; -} - /* To be called between exactly one pair of blk_inc/dec_in_flight() */ int coroutine_fn blk_co_do_flush(BlockBackend *blk) { -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-15-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- block/coroutines.h | 2 -- include/sysemu/block-backend-io.h | 2 +- block/block-backend.c | 11 ----------- 3 files changed, 1 insertion(+), 14 deletions(-) diff --git a/block/coroutines.h b/block/coroutines.h index XXXXXXX..XXXXXXX 100644 --- a/block/coroutines.h +++ b/block/coroutines.h @@ -XXX,XX +XXX,XX @@ nbd_do_establish_connection(BlockDriverState *bs, bool blocking, Error **errp); int generated_co_wrapper blk_do_ioctl(BlockBackend *blk, unsigned long int req, void *buf); -int generated_co_wrapper blk_do_flush(BlockBackend *blk); - #endif /* BLOCK_COROUTINES_H */ diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ int generated_co_wrapper blk_pdiscard(BlockBackend *blk, int64_t offset, int coroutine_fn blk_co_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes); +int generated_co_wrapper blk_flush(BlockBackend *blk); int coroutine_fn blk_co_flush(BlockBackend *blk); -int blk_flush(BlockBackend *blk); int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_flush(BlockBackend *blk) return ret; } -int blk_flush(BlockBackend *blk) -{ - int ret; - - blk_inc_in_flight(blk); - ret = blk_do_flush(blk); - blk_dec_in_flight(blk); - - return ret; -} - void blk_drain(BlockBackend *blk) { BlockDriverState *bs = blk_bs(blk); -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Also convert blk_ioctl() into a generated_co_wrapper. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-16-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- block/coroutines.h | 6 ------ include/sysemu/block-backend-io.h | 5 ++++- block/block-backend.c | 7 ++++--- 3 files changed, 8 insertions(+), 10 deletions(-) diff --git a/block/coroutines.h b/block/coroutines.h index XXXXXXX..XXXXXXX 100644 --- a/block/coroutines.h +++ b/block/coroutines.h @@ -XXX,XX +XXX,XX @@ blk_co_do_pwritev_part(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, size_t qiov_offset, BdrvRequestFlags flags); -int coroutine_fn -blk_co_do_ioctl(BlockBackend *blk, unsigned long int req, void *buf); - int coroutine_fn blk_co_do_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes); @@ -XXX,XX +XXX,XX @@ bdrv_common_block_status_above(BlockDriverState *bs, int generated_co_wrapper nbd_do_establish_connection(BlockDriverState *bs, bool blocking, Error **errp); -int generated_co_wrapper -blk_do_ioctl(BlockBackend *blk, unsigned long int req, void *buf); - #endif /* BLOCK_COROUTINES_H */ diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_pdiscard(BlockBackend *blk, int64_t offset, int generated_co_wrapper blk_flush(BlockBackend *blk); int coroutine_fn blk_co_flush(BlockBackend *blk); -int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf); +int generated_co_wrapper blk_ioctl(BlockBackend *blk, unsigned long int req, + void *buf); +int coroutine_fn blk_co_ioctl(BlockBackend *blk, unsigned long int req, + void *buf); int generated_co_wrapper blk_pwrite_compressed(BlockBackend *blk, int64_t offset, int64_t bytes, diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ void blk_aio_cancel_async(BlockAIOCB *acb) } /* To be called between exactly one pair of blk_inc/dec_in_flight() */ -int coroutine_fn +static int coroutine_fn blk_co_do_ioctl(BlockBackend *blk, unsigned long int req, void *buf) { IO_CODE(); @@ -XXX,XX +XXX,XX @@ blk_co_do_ioctl(BlockBackend *blk, unsigned long int req, void *buf) return bdrv_co_ioctl(blk_bs(blk), req, buf); } -int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf) +int coroutine_fn blk_co_ioctl(BlockBackend *blk, unsigned long int req, + void *buf) { int ret; IO_OR_GS_CODE(); blk_inc_in_flight(blk); - ret = blk_do_ioctl(blk, req, buf); + ret = blk_co_do_ioctl(blk, req, buf); blk_dec_in_flight(blk); return ret; -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Also convert blk_truncate() into a generated_co_wrapper. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-17-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/sysemu/block-backend-io.h | 8 ++++++-- block/block-backend.c | 7 ++++--- tests/unit/test-block-iothread.c | 14 ++++++++++++++ 3 files changed, 24 insertions(+), 5 deletions(-) diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ int generated_co_wrapper blk_pwrite_zeroes(BlockBackend *blk, int64_t offset, BdrvRequestFlags flags); int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset, int64_t bytes, BdrvRequestFlags flags); -int blk_truncate(BlockBackend *blk, int64_t offset, bool exact, - PreallocMode prealloc, BdrvRequestFlags flags, Error **errp); +int generated_co_wrapper blk_truncate(BlockBackend *blk, int64_t offset, + bool exact, PreallocMode prealloc, + BdrvRequestFlags flags, Error **errp); +int coroutine_fn blk_co_truncate(BlockBackend *blk, int64_t offset, bool exact, + PreallocMode prealloc, BdrvRequestFlags flags, + Error **errp); #endif /* BLOCK_BACKEND_IO_H */ diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_pwrite_compressed(BlockBackend *blk, int64_t offset, BDRV_REQ_WRITE_COMPRESSED); } -int blk_truncate(BlockBackend *blk, int64_t offset, bool exact, - PreallocMode prealloc, BdrvRequestFlags flags, Error **errp) +int coroutine_fn blk_co_truncate(BlockBackend *blk, int64_t offset, bool exact, + PreallocMode prealloc, BdrvRequestFlags flags, + Error **errp) { IO_OR_GS_CODE(); if (!blk_is_available(blk)) { @@ -XXX,XX +XXX,XX @@ int blk_truncate(BlockBackend *blk, int64_t offset, bool exact, return -ENOMEDIUM; } - return bdrv_truncate(blk->root, offset, exact, prealloc, flags, errp); + return bdrv_co_truncate(blk->root, offset, exact, prealloc, flags, errp); } int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf, diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_sync_op_truncate(BdrvChild *c) c->bs->open_flags |= BDRV_O_RDWR; } +static void test_sync_op_blk_truncate(BlockBackend *blk) +{ + int ret; + + /* Normal success path */ + ret = blk_truncate(blk, 65536, false, PREALLOC_MODE_OFF, 0, NULL); + g_assert_cmpint(ret, ==, 0); + + /* Early error: Negative offset */ + ret = blk_truncate(blk, -2, false, PREALLOC_MODE_OFF, 0, NULL); + g_assert_cmpint(ret, ==, -EINVAL); +} + static void test_sync_op_block_status(BdrvChild *c) { int ret; @@ -XXX,XX +XXX,XX @@ const SyncOpTest sync_op_tests[] = { }, { .name = "/sync-op/truncate", .fn = test_sync_op_truncate, + .blkfn = test_sync_op_blk_truncate, }, { .name = "/sync-op/block_status", .fn = test_sync_op_block_status, -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Keep generated_co_wrapper and coroutine_fn pairs together. This should make it clear that each I/O function has these two versions. Also move blk_co_{pread,pwrite}()'s implementations out of the header file for consistency. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220705161527.1054072-18-afaria@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- include/sysemu/block-backend-io.h | 77 +++++++++++++------------------ block/block-backend.c | 22 +++++++++ 2 files changed, 54 insertions(+), 45 deletions(-) diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in, int generated_co_wrapper blk_pread(BlockBackend *blk, int64_t offset, int64_t bytes, void *buf, BdrvRequestFlags flags); -int generated_co_wrapper blk_pwrite(BlockBackend *blk, int64_t offset, - int64_t bytes, const void *buf, +int coroutine_fn blk_co_pread(BlockBackend *blk, int64_t offset, int64_t bytes, + void *buf, BdrvRequestFlags flags); + +int generated_co_wrapper blk_preadv(BlockBackend *blk, int64_t offset, + int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); +int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset, + int64_t bytes, QEMUIOVector *qiov, + BdrvRequestFlags flags); + int generated_co_wrapper blk_preadv_part(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, size_t qiov_offset, @@ -XXX,XX +XXX,XX @@ int generated_co_wrapper blk_preadv_part(BlockBackend *blk, int64_t offset, int coroutine_fn blk_co_preadv_part(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, size_t qiov_offset, BdrvRequestFlags flags); -int generated_co_wrapper blk_preadv(BlockBackend *blk, int64_t offset, - int64_t bytes, QEMUIOVector *qiov, + +int generated_co_wrapper blk_pwrite(BlockBackend *blk, int64_t offset, + int64_t bytes, const void *buf, BdrvRequestFlags flags); -int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset, - int64_t bytes, QEMUIOVector *qiov, - BdrvRequestFlags flags); +int coroutine_fn blk_co_pwrite(BlockBackend *blk, int64_t offset, int64_t bytes, + const void *buf, BdrvRequestFlags flags); + +int generated_co_wrapper blk_pwritev(BlockBackend *blk, int64_t offset, + int64_t bytes, QEMUIOVector *qiov, + BdrvRequestFlags flags); +int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset, + int64_t bytes, QEMUIOVector *qiov, + BdrvRequestFlags flags); + int generated_co_wrapper blk_pwritev_part(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, size_t qiov_offset, @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_pwritev_part(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, size_t qiov_offset, BdrvRequestFlags flags); -int generated_co_wrapper blk_pwritev(BlockBackend *blk, int64_t offset, - int64_t bytes, QEMUIOVector *qiov, - BdrvRequestFlags flags); -int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset, - int64_t bytes, QEMUIOVector *qiov, - BdrvRequestFlags flags); - -static inline int coroutine_fn blk_co_pread(BlockBackend *blk, int64_t offset, - int64_t bytes, void *buf, - BdrvRequestFlags flags) -{ - QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); - IO_OR_GS_CODE(); - - assert(bytes <= SIZE_MAX); - - return blk_co_preadv(blk, offset, bytes, &qiov, flags); -} - -static inline int coroutine_fn blk_co_pwrite(BlockBackend *blk, int64_t offset, - int64_t bytes, const void *buf, - BdrvRequestFlags flags) -{ - QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); - IO_OR_GS_CODE(); - assert(bytes <= SIZE_MAX); +int generated_co_wrapper blk_pwrite_compressed(BlockBackend *blk, + int64_t offset, int64_t bytes, + const void *buf); +int coroutine_fn blk_co_pwrite_compressed(BlockBackend *blk, int64_t offset, + int64_t bytes, const void *buf); - return blk_co_pwritev(blk, offset, bytes, &qiov, flags); -} +int generated_co_wrapper blk_pwrite_zeroes(BlockBackend *blk, int64_t offset, + int64_t bytes, + BdrvRequestFlags flags); +int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset, + int64_t bytes, BdrvRequestFlags flags); int generated_co_wrapper blk_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes); @@ -XXX,XX +XXX,XX @@ int generated_co_wrapper blk_ioctl(BlockBackend *blk, unsigned long int req, int coroutine_fn blk_co_ioctl(BlockBackend *blk, unsigned long int req, void *buf); -int generated_co_wrapper blk_pwrite_compressed(BlockBackend *blk, - int64_t offset, int64_t bytes, - const void *buf); -int coroutine_fn blk_co_pwrite_compressed(BlockBackend *blk, int64_t offset, - int64_t bytes, const void *buf); -int generated_co_wrapper blk_pwrite_zeroes(BlockBackend *blk, int64_t offset, - int64_t bytes, - BdrvRequestFlags flags); -int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset, - int64_t bytes, BdrvRequestFlags flags); int generated_co_wrapper blk_truncate(BlockBackend *blk, int64_t offset, bool exact, PreallocMode prealloc, BdrvRequestFlags flags, Error **errp); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ blk_co_do_preadv_part(BlockBackend *blk, int64_t offset, int64_t bytes, return ret; } +int coroutine_fn blk_co_pread(BlockBackend *blk, int64_t offset, int64_t bytes, + void *buf, BdrvRequestFlags flags) +{ + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); + IO_OR_GS_CODE(); + + assert(bytes <= SIZE_MAX); + + return blk_co_preadv(blk, offset, bytes, &qiov, flags); +} + int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags) @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_pwritev_part(BlockBackend *blk, int64_t offset, return ret; } +int coroutine_fn blk_co_pwrite(BlockBackend *blk, int64_t offset, int64_t bytes, + const void *buf, BdrvRequestFlags flags) +{ + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); + IO_OR_GS_CODE(); + + assert(bytes <= SIZE_MAX); + + return blk_co_pwritev(blk, offset, bytes, &qiov, flags); +} + int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags) -- 2.35.3 From: Alberto Faria <afaria@redhat.com> Some can be made static, others are unused generated_co_wrappers. Signed-off-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220705161527.1054072-19-afaria@redhat.com> Signed-off-by: Hanna Reitz <hreitz@redhat.com> --- block/coroutines.h | 19 ------------------- block/block-backend.c | 6 +++--- 2 files changed, 3 insertions(+), 22 deletions(-) diff --git a/block/coroutines.h b/block/coroutines.h index XXXXXXX..XXXXXXX 100644 --- a/block/coroutines.h +++ b/block/coroutines.h @@ -XXX,XX +XXX,XX @@ nbd_co_do_establish_connection(BlockDriverState *bs, bool blocking, Error **errp); -int coroutine_fn -blk_co_do_pwritev_part(BlockBackend *blk, int64_t offset, int64_t bytes, - QEMUIOVector *qiov, size_t qiov_offset, - BdrvRequestFlags flags); - -int coroutine_fn -blk_co_do_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes); - -int coroutine_fn blk_co_do_flush(BlockBackend *blk); - - /* * "I/O or GS" API functions. These functions can run without * the BQL, but only in one specific iothread/main loop. @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_do_flush(BlockBackend *blk); * the "I/O or GS" API. */ -int generated_co_wrapper -bdrv_preadv(BdrvChild *child, int64_t offset, int64_t bytes, - QEMUIOVector *qiov, BdrvRequestFlags flags); - -int generated_co_wrapper -bdrv_pwritev(BdrvChild *child, int64_t offset, int64_t bytes, - QEMUIOVector *qiov, BdrvRequestFlags flags); - int generated_co_wrapper bdrv_common_block_status_above(BlockDriverState *bs, BlockDriverState *base, diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_preadv_part(BlockBackend *blk, int64_t offset, } /* To be called between exactly one pair of blk_inc/dec_in_flight() */ -int coroutine_fn +static int coroutine_fn blk_co_do_pwritev_part(BlockBackend *blk, int64_t offset, int64_t bytes, QEMUIOVector *qiov, size_t qiov_offset, BdrvRequestFlags flags) @@ -XXX,XX +XXX,XX @@ BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf, } /* To be called between exactly one pair of blk_inc/dec_in_flight() */ -int coroutine_fn +static int coroutine_fn blk_co_do_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes) { int ret; @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_pdiscard(BlockBackend *blk, int64_t offset, } /* To be called between exactly one pair of blk_inc/dec_in_flight() */ -int coroutine_fn blk_co_do_flush(BlockBackend *blk) +static int coroutine_fn blk_co_do_flush(BlockBackend *blk) { blk_wait_while_drained(blk); IO_CODE(); -- 2.35.3 error_report() only works once monitor_init_globals_core() has been called, which is not the case when parsing the --daemonize option. Use fprintf(stderr, ...) instead. Fixes: 2525edd85fec53e23fda98974a15e3b3c8957596 ("qsd: Add --daemonize") Signed-off-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220609122852.21140-1-hreitz@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> --- storage-daemon/qemu-storage-daemon.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/storage-daemon/qemu-storage-daemon.c b/storage-daemon/qemu-storage-daemon.c index XXXXXXX..XXXXXXX 100644 --- a/storage-daemon/qemu-storage-daemon.c +++ b/storage-daemon/qemu-storage-daemon.c @@ -XXX,XX +XXX,XX @@ static void process_options(int argc, char *argv[], bool pre_init_pass) } case OPTION_DAEMONIZE: if (os_set_daemonize(true) < 0) { - error_report("--daemonize not supported in this build"); + /* + * --daemonize is parsed before monitor_init_globals_core(), so + * error_report() does not work yet + */ + fprintf(stderr, "--daemonize not supported in this build\n"); exit(EXIT_FAILURE); } break; -- 2.35.3 e7874a50ff3f5b20fb46f36958ad ("python: update for mypy 0.950") has added `warn_unused_ignores = False` to python/setup.cfg, to be able to keep compatibility with both pre- and post-0.950 mypy versions. The iotests' mypy.ini needs the same, or 297 will fail (on both pre- and post-0.950 mypy, as far as I can tell; just for different `ignore` lines). Signed-off-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220621092536.19837-1-hreitz@redhat.com> Acked-by: John Snow <jsnow@redhat.com> --- tests/qemu-iotests/mypy.ini | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/qemu-iotests/mypy.ini b/tests/qemu-iotests/mypy.ini index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/mypy.ini +++ b/tests/qemu-iotests/mypy.ini @@ -XXX,XX +XXX,XX @@ no_implicit_optional = True scripts_are_modules = True warn_redundant_casts = True warn_unused_configs = True -warn_unused_ignores = True +warn_unused_ignores = False -- 2.35.3 After writing the PID file, we register an atexit() handler to unlink it when the process terminates. However, if the process has changed its working directory in the meantime (e.g. in os_setup_post() when daemonizing), this will not work when the PID file path was relative. Therefore, pass the absolute path (created with realpath()) to the unlink() call in the atexit() handler. (realpath() needs a path pointing to an existing file, so we cannot use it before qemu_write_pidfile().) Reproducer: $ cd /tmp $ qemu-storage-daemon --daemonize --pidfile qsd.pid $ file qsd.pid qsd.pid: ASCII text $ kill $(cat qsd.pid) $ file qsd.pid qsd.pid: ASCII text (qsd.pid should be gone after the process has terminated.) Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2092322 Signed-off-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220609122701.17172-2-hreitz@redhat.com> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> --- storage-daemon/qemu-storage-daemon.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/storage-daemon/qemu-storage-daemon.c b/storage-daemon/qemu-storage-daemon.c index XXXXXXX..XXXXXXX 100644 --- a/storage-daemon/qemu-storage-daemon.c +++ b/storage-daemon/qemu-storage-daemon.c @@ -XXX,XX +XXX,XX @@ #include "trace/control.h" static const char *pid_file; +static char *pid_file_realpath; static volatile bool exit_requested = false; void qemu_system_killed(int signal, pid_t pid) @@ -XXX,XX +XXX,XX @@ static void process_options(int argc, char *argv[], bool pre_init_pass) static void pid_file_cleanup(void) { - unlink(pid_file); + unlink(pid_file_realpath); } static void pid_file_init(void) @@ -XXX,XX +XXX,XX @@ static void pid_file_init(void) exit(EXIT_FAILURE); } + pid_file_realpath = g_malloc(PATH_MAX); + if (!realpath(pid_file, pid_file_realpath)) { + error_report("cannot resolve PID file path: %s: %s", + pid_file, strerror(errno)); + unlink(pid_file); + exit(EXIT_FAILURE); + } + atexit(pid_file_cleanup); } -- 2.35.3 Currently, the exit notifier for unlinking the PID file is registered unconditionally. Limit it to only when we actually do create a PID file. Signed-off-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220609122701.17172-3-hreitz@redhat.com> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> --- softmmu/vl.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/softmmu/vl.c b/softmmu/vl.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/vl.c +++ b/softmmu/vl.c @@ -XXX,XX +XXX,XX @@ static Notifier qemu_unlink_pidfile_notifier; static void qemu_unlink_pidfile(Notifier *n, void *data) { - if (pid_file) { - unlink(pid_file); - } + unlink(pid_file); } static const QEMUOption *lookup_opt(int argc, char **argv, @@ -XXX,XX +XXX,XX @@ static void qemu_maybe_daemonize(const char *pid_file) os_daemonize(); rcu_disable_atfork(); - if (pid_file && !qemu_write_pidfile(pid_file, &err)) { - error_reportf_err(err, "cannot create PID file: "); - exit(1); - } + if (pid_file) { + if (!qemu_write_pidfile(pid_file, &err)) { + error_reportf_err(err, "cannot create PID file: "); + exit(1); + } - qemu_unlink_pidfile_notifier.notify = qemu_unlink_pidfile; - qemu_add_exit_notifier(&qemu_unlink_pidfile_notifier); + qemu_unlink_pidfile_notifier.notify = qemu_unlink_pidfile; + qemu_add_exit_notifier(&qemu_unlink_pidfile_notifier); + } } static void qemu_init_displays(void) -- 2.35.3 After writing the PID file, we register an exit notifier to unlink it when the process terminates. However, if the process has changed its working directory in the meantime (e.g. in os_setup_post() when daemonizing), this will not work when the PID file path was relative. Therefore, pass the absolute path (created with realpath()) to the unlink() call in the exit notifier. (realpath() needs a path pointing to an existing file, so we cannot use it before qemu_write_pidfile().) Reproducer: $ cd /tmp $ qemu-system-x86_64 --daemonize --pidfile qemu.pid $ file qemu.pid qemu.pid: ASCII text $ kill $(cat qemu.pid) $ file qemu.pid qemu.pid: ASCII text (qemu.pid should be gone after the process has terminated.) Signed-off-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220609122701.17172-4-hreitz@redhat.com> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> --- softmmu/vl.c | 30 ++++++++++++++++++++++++++---- 1 file changed, 26 insertions(+), 4 deletions(-) diff --git a/softmmu/vl.c b/softmmu/vl.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/vl.c +++ b/softmmu/vl.c @@ -XXX,XX +XXX,XX @@ machine_parse_property_opt(QemuOptsList *opts_list, const char *propname, } static const char *pid_file; -static Notifier qemu_unlink_pidfile_notifier; +struct UnlinkPidfileNotifier { + Notifier notifier; + char *pid_file_realpath; +}; +static struct UnlinkPidfileNotifier qemu_unlink_pidfile_notifier; static void qemu_unlink_pidfile(Notifier *n, void *data) { - unlink(pid_file); + struct UnlinkPidfileNotifier *upn; + + upn = DO_UPCAST(struct UnlinkPidfileNotifier, notifier, n); + unlink(upn->pid_file_realpath); } static const QEMUOption *lookup_opt(int argc, char **argv, @@ -XXX,XX +XXX,XX @@ static void qemu_maybe_daemonize(const char *pid_file) rcu_disable_atfork(); if (pid_file) { + char *pid_file_realpath = NULL; + if (!qemu_write_pidfile(pid_file, &err)) { error_reportf_err(err, "cannot create PID file: "); exit(1); } - qemu_unlink_pidfile_notifier.notify = qemu_unlink_pidfile; - qemu_add_exit_notifier(&qemu_unlink_pidfile_notifier); + pid_file_realpath = g_malloc0(PATH_MAX); + if (!realpath(pid_file, pid_file_realpath)) { + error_report("cannot resolve PID file path: %s: %s", + pid_file, strerror(errno)); + unlink(pid_file); + exit(1); + } + + qemu_unlink_pidfile_notifier = (struct UnlinkPidfileNotifier) { + .notifier = { + .notify = qemu_unlink_pidfile, + }, + .pid_file_realpath = pid_file_realpath, + }; + qemu_add_exit_notifier(&qemu_unlink_pidfile_notifier.notifier); } } -- 2.35.3 The following changes since commit 56f9e46b841c7be478ca038d8d4085d776ab4b0d: Merge remote-tracking branch 'remotes/armbru/tags/pull-qapi-2017-02-20' into staging (2017-02-20 17:42:47 +0000) are available in the git repository at: git://github.com/stefanha/qemu.git tags/block-pull-request for you to fetch changes up to a7b91d35bab97a2d3e779d0c64c9b837b52a6cf7: coroutine-lock: make CoRwlock thread-safe and fair (2017-02-21 11:39:40 +0000) ---------------------------------------------------------------- Pull request v2: * Rebased to resolve scsi conflicts ---------------------------------------------------------------- Paolo Bonzini (24): block: move AioContext, QEMUTimer, main-loop to libqemuutil aio: introduce aio_co_schedule and aio_co_wake block-backend: allow blk_prw from coroutine context test-thread-pool: use generic AioContext infrastructure io: add methods to set I/O handlers on AioContext io: make qio_channel_yield aware of AioContexts nbd: convert to use qio_channel_yield coroutine-lock: reschedule coroutine on the AioContext it was running on blkdebug: reschedule coroutine on the AioContext it is running on qed: introduce qed_aio_start_io and qed_aio_next_io_cb aio: push aio_context_acquire/release down to dispatching block: explicitly acquire aiocontext in timers that need it block: explicitly acquire aiocontext in callbacks that need it block: explicitly acquire aiocontext in bottom halves that need it block: explicitly acquire aiocontext in aio callbacks that need it aio-posix: partially inline aio_dispatch into aio_poll async: remove unnecessary inc/dec pairs block: document fields protected by AioContext lock coroutine-lock: make CoMutex thread-safe coroutine-lock: add limited spinning to CoMutex test-aio-multithread: add performance comparison with thread-based mutexes coroutine-lock: place CoMutex before CoQueue in header coroutine-lock: add mutex argument to CoQueue APIs coroutine-lock: make CoRwlock thread-safe and fair Makefile.objs | 4 - stubs/Makefile.objs | 1 + tests/Makefile.include | 19 +- util/Makefile.objs | 6 +- block/nbd-client.h | 2 +- block/qed.h | 3 + include/block/aio.h | 38 ++- include/block/block_int.h | 64 +++-- include/io/channel.h | 72 +++++- include/qemu/coroutine.h | 84 ++++--- include/qemu/coroutine_int.h | 11 +- include/sysemu/block-backend.h | 14 +- tests/iothread.h | 25 ++ block/backup.c | 2 +- block/blkdebug.c | 9 +- block/blkreplay.c | 2 +- block/block-backend.c | 13 +- block/curl.c | 44 +++- block/gluster.c | 9 +- block/io.c | 42 +--- block/iscsi.c | 15 +- block/linux-aio.c | 10 +- block/mirror.c | 12 +- block/nbd-client.c | 119 +++++---- block/nfs.c | 9 +- block/qcow2-cluster.c | 4 +- block/qed-cluster.c | 2 + block/qed-table.c | 12 +- block/qed.c | 58 +++-- block/sheepdog.c | 31 +-- block/ssh.c | 29 +-- block/throttle-groups.c | 4 +- block/win32-aio.c | 9 +- dma-helpers.c | 2 + hw/9pfs/9p.c | 2 +- hw/block/virtio-blk.c | 19 +- hw/scsi/scsi-bus.c | 2 + hw/scsi/scsi-disk.c | 15 ++ hw/scsi/scsi-generic.c | 20 +- hw/scsi/virtio-scsi.c | 7 + io/channel-command.c | 13 + io/channel-file.c | 11 + io/channel-socket.c | 16 +- io/channel-tls.c | 12 + io/channel-watch.c | 6 + io/channel.c | 97 ++++++-- nbd/client.c | 2 +- nbd/common.c | 9 +- nbd/server.c | 94 +++----- stubs/linux-aio.c | 32 +++ stubs/set-fd-handler.c | 11 - tests/iothread.c | 91 +++++++ tests/test-aio-multithread.c | 463 ++++++++++++++++++++++++++++++++++++ tests/test-thread-pool.c | 12 +- aio-posix.c => util/aio-posix.c | 62 ++--- aio-win32.c => util/aio-win32.c | 30 +-- util/aiocb.c | 55 +++++ async.c => util/async.c | 84 ++++++- iohandler.c => util/iohandler.c | 0 main-loop.c => util/main-loop.c | 0 util/qemu-coroutine-lock.c | 254 ++++++++++++++++++-- util/qemu-coroutine-sleep.c | 2 +- util/qemu-coroutine.c | 8 + qemu-timer.c => util/qemu-timer.c | 0 thread-pool.c => util/thread-pool.c | 8 +- trace-events | 11 - util/trace-events | 17 +- 67 files changed, 1712 insertions(+), 533 deletions(-) create mode 100644 tests/iothread.h create mode 100644 stubs/linux-aio.c create mode 100644 tests/iothread.c create mode 100644 tests/test-aio-multithread.c rename aio-posix.c => util/aio-posix.c (94%) rename aio-win32.c => util/aio-win32.c (95%) create mode 100644 util/aiocb.c rename async.c => util/async.c (82%) rename iohandler.c => util/iohandler.c (100%) rename main-loop.c => util/main-loop.c (100%) rename qemu-timer.c => util/qemu-timer.c (100%) rename thread-pool.c => util/thread-pool.c (97%) -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> AioContext is fairly self contained, the only dependency is QEMUTimer but that in turn doesn't need anything else. So move them out of block-obj-y to avoid introducing a dependency from io/ to block-obj-y. main-loop and its dependency iohandler also need to be moved, because later in this series io/ will call iohandler_get_aio_context. [Changed copyright "the QEMU team" to "other QEMU contributors" as suggested by Daniel Berrange and agreed by Paolo. --Stefan] Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213135235.12274-2-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- Makefile.objs | 4 --- stubs/Makefile.objs | 1 + tests/Makefile.include | 11 ++++---- util/Makefile.objs | 6 +++- block/io.c | 29 ------------------- stubs/linux-aio.c | 32 +++++++++++++++++++++ stubs/set-fd-handler.c | 11 -------- aio-posix.c => util/aio-posix.c | 2 +- aio-win32.c => util/aio-win32.c | 0 util/aiocb.c | 55 +++++++++++++++++++++++++++++++++++++ async.c => util/async.c | 3 +- iohandler.c => util/iohandler.c | 0 main-loop.c => util/main-loop.c | 0 qemu-timer.c => util/qemu-timer.c | 0 thread-pool.c => util/thread-pool.c | 2 +- trace-events | 11 -------- util/trace-events | 11 ++++++++ 17 files changed, 114 insertions(+), 64 deletions(-) create mode 100644 stubs/linux-aio.c rename aio-posix.c => util/aio-posix.c (99%) rename aio-win32.c => util/aio-win32.c (100%) create mode 100644 util/aiocb.c rename async.c => util/async.c (99%) rename iohandler.c => util/iohandler.c (100%) rename main-loop.c => util/main-loop.c (100%) rename qemu-timer.c => util/qemu-timer.c (100%) rename thread-pool.c => util/thread-pool.c (99%) diff --git a/Makefile.objs b/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/Makefile.objs +++ b/Makefile.objs @@ -XXX,XX +XXX,XX @@ chardev-obj-y = chardev/ ####################################################################### # block-obj-y is code used by both qemu system emulation and qemu-img -block-obj-y = async.o thread-pool.o block-obj-y += nbd/ block-obj-y += block.o blockjob.o -block-obj-y += main-loop.o iohandler.o qemu-timer.o -block-obj-$(CONFIG_POSIX) += aio-posix.o -block-obj-$(CONFIG_WIN32) += aio-win32.o block-obj-y += block/ block-obj-y += qemu-io-cmds.o block-obj-$(CONFIG_REPLICATION) += replication.o diff --git a/stubs/Makefile.objs b/stubs/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/stubs/Makefile.objs +++ b/stubs/Makefile.objs @@ -XXX,XX +XXX,XX @@ stub-obj-y += get-vm-name.o stub-obj-y += iothread.o stub-obj-y += iothread-lock.o stub-obj-y += is-daemonized.o +stub-obj-$(CONFIG_LINUX_AIO) += linux-aio.o stub-obj-y += machine-init-done.o stub-obj-y += migr-blocker.o stub-obj-y += monitor.o diff --git a/tests/Makefile.include b/tests/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -XXX,XX +XXX,XX @@ check-unit-y += tests/test-visitor-serialization$(EXESUF) check-unit-y += tests/test-iov$(EXESUF) gcov-files-test-iov-y = util/iov.c check-unit-y += tests/test-aio$(EXESUF) +gcov-files-test-aio-y = util/async.c util/qemu-timer.o +gcov-files-test-aio-$(CONFIG_WIN32) += util/aio-win32.c +gcov-files-test-aio-$(CONFIG_POSIX) += util/aio-posix.c check-unit-y += tests/test-throttle$(EXESUF) gcov-files-test-aio-$(CONFIG_WIN32) = aio-win32.c gcov-files-test-aio-$(CONFIG_POSIX) = aio-posix.c @@ -XXX,XX +XXX,XX @@ tests/check-qjson$(EXESUF): tests/check-qjson.o $(test-util-obj-y) tests/check-qom-interface$(EXESUF): tests/check-qom-interface.o $(test-qom-obj-y) tests/check-qom-proplist$(EXESUF): tests/check-qom-proplist.o $(test-qom-obj-y) -tests/test-char$(EXESUF): tests/test-char.o qemu-timer.o \ - $(test-util-obj-y) $(qtest-obj-y) $(test-block-obj-y) $(chardev-obj-y) +tests/test-char$(EXESUF): tests/test-char.o $(test-util-obj-y) $(qtest-obj-y) $(test-io-obj-y) $(chardev-obj-y) tests/test-coroutine$(EXESUF): tests/test-coroutine.o $(test-block-obj-y) tests/test-aio$(EXESUF): tests/test-aio.o $(test-block-obj-y) tests/test-throttle$(EXESUF): tests/test-throttle.o $(test-block-obj-y) @@ -XXX,XX +XXX,XX @@ tests/test-vmstate$(EXESUF): tests/test-vmstate.o \ migration/vmstate.o migration/qemu-file.o \ migration/qemu-file-channel.o migration/qjson.o \ $(test-io-obj-y) -tests/test-timed-average$(EXESUF): tests/test-timed-average.o qemu-timer.o \ - $(test-util-obj-y) +tests/test-timed-average$(EXESUF): tests/test-timed-average.o $(test-util-obj-y) tests/test-base64$(EXESUF): tests/test-base64.o \ libqemuutil.a libqemustub.a tests/ptimer-test$(EXESUF): tests/ptimer-test.o tests/ptimer-test-stubs.o hw/core/ptimer.o libqemustub.a @@ -XXX,XX +XXX,XX @@ tests/usb-hcd-ehci-test$(EXESUF): tests/usb-hcd-ehci-test.o $(libqos-usb-obj-y) tests/usb-hcd-xhci-test$(EXESUF): tests/usb-hcd-xhci-test.o $(libqos-usb-obj-y) tests/pc-cpu-test$(EXESUF): tests/pc-cpu-test.o tests/postcopy-test$(EXESUF): tests/postcopy-test.o -tests/vhost-user-test$(EXESUF): tests/vhost-user-test.o qemu-timer.o \ +tests/vhost-user-test$(EXESUF): tests/vhost-user-test.o $(test-util-obj-y) \ $(qtest-obj-y) $(test-io-obj-y) $(libqos-virtio-obj-y) $(libqos-pc-obj-y) \ $(chardev-obj-y) tests/qemu-iotests/socket_scm_helper$(EXESUF): tests/qemu-iotests/socket_scm_helper.o diff --git a/util/Makefile.objs b/util/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/util/Makefile.objs +++ b/util/Makefile.objs @@ -XXX,XX +XXX,XX @@ util-obj-y = osdep.o cutils.o unicode.o qemu-timer-common.o util-obj-y += bufferiszero.o util-obj-y += lockcnt.o +util-obj-y += aiocb.o async.o thread-pool.o qemu-timer.o +util-obj-y += main-loop.o iohandler.o +util-obj-$(CONFIG_POSIX) += aio-posix.o util-obj-$(CONFIG_POSIX) += compatfd.o util-obj-$(CONFIG_POSIX) += event_notifier-posix.o util-obj-$(CONFIG_POSIX) += mmap-alloc.o util-obj-$(CONFIG_POSIX) += oslib-posix.o util-obj-$(CONFIG_POSIX) += qemu-openpty.o util-obj-$(CONFIG_POSIX) += qemu-thread-posix.o -util-obj-$(CONFIG_WIN32) += event_notifier-win32.o util-obj-$(CONFIG_POSIX) += memfd.o +util-obj-$(CONFIG_WIN32) += aio-win32.o +util-obj-$(CONFIG_WIN32) += event_notifier-win32.o util-obj-$(CONFIG_WIN32) += oslib-win32.o util-obj-$(CONFIG_WIN32) += qemu-thread-win32.o util-obj-y += envlist.o path.o module.o diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ BlockAIOCB *bdrv_aio_flush(BlockDriverState *bs, return &acb->common; } -void *qemu_aio_get(const AIOCBInfo *aiocb_info, BlockDriverState *bs, - BlockCompletionFunc *cb, void *opaque) -{ - BlockAIOCB *acb; - - acb = g_malloc(aiocb_info->aiocb_size); - acb->aiocb_info = aiocb_info; - acb->bs = bs; - acb->cb = cb; - acb->opaque = opaque; - acb->refcnt = 1; - return acb; -} - -void qemu_aio_ref(void *p) -{ - BlockAIOCB *acb = p; - acb->refcnt++; -} - -void qemu_aio_unref(void *p) -{ - BlockAIOCB *acb = p; - assert(acb->refcnt > 0); - if (--acb->refcnt == 0) { - g_free(acb); - } -} - /**************************************************************/ /* Coroutine block device emulation */ diff --git a/stubs/linux-aio.c b/stubs/linux-aio.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/stubs/linux-aio.c @@ -XXX,XX +XXX,XX @@ +/* + * Linux native AIO support. + * + * Copyright (C) 2009 IBM, Corp. + * Copyright (C) 2009 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ +#include "qemu/osdep.h" +#include "block/aio.h" +#include "block/raw-aio.h" + +void laio_detach_aio_context(LinuxAioState *s, AioContext *old_context) +{ + abort(); +} + +void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context) +{ + abort(); +} + +LinuxAioState *laio_init(void) +{ + abort(); +} + +void laio_cleanup(LinuxAioState *s) +{ + abort(); +} diff --git a/stubs/set-fd-handler.c b/stubs/set-fd-handler.c index XXXXXXX..XXXXXXX 100644 --- a/stubs/set-fd-handler.c +++ b/stubs/set-fd-handler.c @@ -XXX,XX +XXX,XX @@ void qemu_set_fd_handler(int fd, { abort(); } - -void aio_set_fd_handler(AioContext *ctx, - int fd, - bool is_external, - IOHandler *io_read, - IOHandler *io_write, - AioPollFn *io_poll, - void *opaque) -{ - abort(); -} diff --git a/aio-posix.c b/util/aio-posix.c similarity index 99% rename from aio-posix.c rename to util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ #include "qemu/rcu_queue.h" #include "qemu/sockets.h" #include "qemu/cutils.h" -#include "trace-root.h" +#include "trace.h" #ifdef CONFIG_EPOLL_CREATE1 #include <sys/epoll.h> #endif diff --git a/aio-win32.c b/util/aio-win32.c similarity index 100% rename from aio-win32.c rename to util/aio-win32.c diff --git a/util/aiocb.c b/util/aiocb.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/util/aiocb.c @@ -XXX,XX +XXX,XX @@ +/* + * BlockAIOCB allocation + * + * Copyright (c) 2003-2017 Fabrice Bellard and other QEMU contributors + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "block/aio.h" + +void *qemu_aio_get(const AIOCBInfo *aiocb_info, BlockDriverState *bs, + BlockCompletionFunc *cb, void *opaque) +{ + BlockAIOCB *acb; + + acb = g_malloc(aiocb_info->aiocb_size); + acb->aiocb_info = aiocb_info; + acb->bs = bs; + acb->cb = cb; + acb->opaque = opaque; + acb->refcnt = 1; + return acb; +} + +void qemu_aio_ref(void *p) +{ + BlockAIOCB *acb = p; + acb->refcnt++; +} + +void qemu_aio_unref(void *p) +{ + BlockAIOCB *acb = p; + assert(acb->refcnt > 0); + if (--acb->refcnt == 0) { + g_free(acb); + } +} diff --git a/async.c b/util/async.c similarity index 99% rename from async.c rename to util/async.c index XXXXXXX..XXXXXXX 100644 --- a/async.c +++ b/util/async.c @@ -XXX,XX +XXX,XX @@ /* - * QEMU System Emulator + * Data plane event loop * * Copyright (c) 2003-2008 Fabrice Bellard + * Copyright (c) 2009-2017 QEMU contributors * * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to deal diff --git a/iohandler.c b/util/iohandler.c similarity index 100% rename from iohandler.c rename to util/iohandler.c diff --git a/main-loop.c b/util/main-loop.c similarity index 100% rename from main-loop.c rename to util/main-loop.c diff --git a/qemu-timer.c b/util/qemu-timer.c similarity index 100% rename from qemu-timer.c rename to util/qemu-timer.c diff --git a/thread-pool.c b/util/thread-pool.c similarity index 99% rename from thread-pool.c rename to util/thread-pool.c index XXXXXXX..XXXXXXX 100644 --- a/thread-pool.c +++ b/util/thread-pool.c @@ -XXX,XX +XXX,XX @@ #include "qemu/queue.h" #include "qemu/thread.h" #include "qemu/coroutine.h" -#include "trace-root.h" +#include "trace.h" #include "block/thread-pool.h" #include "qemu/main-loop.h" diff --git a/trace-events b/trace-events index XXXXXXX..XXXXXXX 100644 --- a/trace-events +++ b/trace-events @@ -XXX,XX +XXX,XX @@ # # The <format-string> should be a sprintf()-compatible format string. -# aio-posix.c -run_poll_handlers_begin(void *ctx, int64_t max_ns) "ctx %p max_ns %"PRId64 -run_poll_handlers_end(void *ctx, bool progress) "ctx %p progress %d" -poll_shrink(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64 -poll_grow(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64 - -# thread-pool.c -thread_pool_submit(void *pool, void *req, void *opaque) "pool %p req %p opaque %p" -thread_pool_complete(void *pool, void *req, void *opaque, int ret) "pool %p req %p opaque %p ret %d" -thread_pool_cancel(void *req, void *opaque) "req %p opaque %p" - # ioport.c cpu_in(unsigned int addr, char size, unsigned int val) "addr %#x(%c) value %u" cpu_out(unsigned int addr, char size, unsigned int val) "addr %#x(%c) value %u" diff --git a/util/trace-events b/util/trace-events index XXXXXXX..XXXXXXX 100644 --- a/util/trace-events +++ b/util/trace-events @@ -XXX,XX +XXX,XX @@ # See docs/tracing.txt for syntax documentation. +# util/aio-posix.c +run_poll_handlers_begin(void *ctx, int64_t max_ns) "ctx %p max_ns %"PRId64 +run_poll_handlers_end(void *ctx, bool progress) "ctx %p progress %d" +poll_shrink(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64 +poll_grow(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64 + +# util/thread-pool.c +thread_pool_submit(void *pool, void *req, void *opaque) "pool %p req %p opaque %p" +thread_pool_complete(void *pool, void *req, void *opaque, int ret) "pool %p req %p opaque %p ret %d" +thread_pool_cancel(void *req, void *opaque) "req %p opaque %p" + # util/buffer.c buffer_resize(const char *buf, size_t olen, size_t len) "%s: old %zd, new %zd" buffer_move_empty(const char *buf, size_t len, const char *from) "%s: %zd bytes from %s" -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> aio_co_wake provides the infrastructure to start a coroutine on a "home" AioContext. It will be used by CoMutex and CoQueue, so that coroutines don't jump from one context to another when they go to sleep on a mutex or waitqueue. However, it can also be used as a more efficient alternative to one-shot bottom halves, and saves the effort of tracking which AioContext a coroutine is running on. aio_co_schedule is the part of aio_co_wake that starts a coroutine on a remove AioContext, but it is also useful to implement e.g. bdrv_set_aio_context callbacks. The implementation of aio_co_schedule is based on a lock-free multiple-producer, single-consumer queue. The multiple producers use cmpxchg to add to a LIFO stack. The consumer (a per-AioContext bottom half) grabs all items added so far, inverts the list to make it FIFO, and goes through it one item at a time until it's empty. The data structure was inspired by OSv, which uses it in the very code we'll "port" to QEMU for the thread-safe CoMutex. Most of the new code is really tests. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213135235.12274-3-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/Makefile.include | 8 +- include/block/aio.h | 32 +++++++ include/qemu/coroutine_int.h | 11 ++- tests/iothread.h | 25 +++++ tests/iothread.c | 91 ++++++++++++++++++ tests/test-aio-multithread.c | 213 +++++++++++++++++++++++++++++++++++++++++++ util/async.c | 65 +++++++++++++ util/qemu-coroutine.c | 8 ++ util/trace-events | 4 + 9 files changed, 453 insertions(+), 4 deletions(-) create mode 100644 tests/iothread.h create mode 100644 tests/iothread.c create mode 100644 tests/test-aio-multithread.c diff --git a/tests/Makefile.include b/tests/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -XXX,XX +XXX,XX @@ check-unit-y += tests/test-aio$(EXESUF) gcov-files-test-aio-y = util/async.c util/qemu-timer.o gcov-files-test-aio-$(CONFIG_WIN32) += util/aio-win32.c gcov-files-test-aio-$(CONFIG_POSIX) += util/aio-posix.c +check-unit-y += tests/test-aio-multithread$(EXESUF) +gcov-files-test-aio-multithread-y = $(gcov-files-test-aio-y) +gcov-files-test-aio-multithread-y += util/qemu-coroutine.c tests/iothread.c check-unit-y += tests/test-throttle$(EXESUF) -gcov-files-test-aio-$(CONFIG_WIN32) = aio-win32.c -gcov-files-test-aio-$(CONFIG_POSIX) = aio-posix.c check-unit-y += tests/test-thread-pool$(EXESUF) gcov-files-test-thread-pool-y = thread-pool.c gcov-files-test-hbitmap-y = util/hbitmap.c @@ -XXX,XX +XXX,XX @@ test-qapi-obj-y = tests/test-qapi-visit.o tests/test-qapi-types.o \ $(test-qom-obj-y) test-crypto-obj-y = $(crypto-obj-y) $(test-qom-obj-y) test-io-obj-y = $(io-obj-y) $(test-crypto-obj-y) -test-block-obj-y = $(block-obj-y) $(test-io-obj-y) +test-block-obj-y = $(block-obj-y) $(test-io-obj-y) tests/iothread.o tests/check-qint$(EXESUF): tests/check-qint.o $(test-util-obj-y) tests/check-qstring$(EXESUF): tests/check-qstring.o $(test-util-obj-y) @@ -XXX,XX +XXX,XX @@ tests/check-qom-proplist$(EXESUF): tests/check-qom-proplist.o $(test-qom-obj-y) tests/test-char$(EXESUF): tests/test-char.o $(test-util-obj-y) $(qtest-obj-y) $(test-io-obj-y) $(chardev-obj-y) tests/test-coroutine$(EXESUF): tests/test-coroutine.o $(test-block-obj-y) tests/test-aio$(EXESUF): tests/test-aio.o $(test-block-obj-y) +tests/test-aio-multithread$(EXESUF): tests/test-aio-multithread.o $(test-block-obj-y) tests/test-throttle$(EXESUF): tests/test-throttle.o $(test-block-obj-y) tests/test-blockjob$(EXESUF): tests/test-blockjob.o $(test-block-obj-y) $(test-util-obj-y) tests/test-blockjob-txn$(EXESUF): tests/test-blockjob-txn.o $(test-block-obj-y) $(test-util-obj-y) diff --git a/include/block/aio.h b/include/block/aio.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/aio.h +++ b/include/block/aio.h @@ -XXX,XX +XXX,XX @@ typedef void QEMUBHFunc(void *opaque); typedef bool AioPollFn(void *opaque); typedef void IOHandler(void *opaque); +struct Coroutine; struct ThreadPool; struct LinuxAioState; @@ -XXX,XX +XXX,XX @@ struct AioContext { bool notified; EventNotifier notifier; + QSLIST_HEAD(, Coroutine) scheduled_coroutines; + QEMUBH *co_schedule_bh; + /* Thread pool for performing work and receiving completion callbacks. * Has its own locking. */ @@ -XXX,XX +XXX,XX @@ static inline bool aio_node_check(AioContext *ctx, bool is_external) } /** + * aio_co_schedule: + * @ctx: the aio context + * @co: the coroutine + * + * Start a coroutine on a remote AioContext. + * + * The coroutine must not be entered by anyone else while aio_co_schedule() + * is active. In addition the coroutine must have yielded unless ctx + * is the context in which the coroutine is running (i.e. the value of + * qemu_get_current_aio_context() from the coroutine itself). + */ +void aio_co_schedule(AioContext *ctx, struct Coroutine *co); + +/** + * aio_co_wake: + * @co: the coroutine + * + * Restart a coroutine on the AioContext where it was running last, thus + * preventing coroutines from jumping from one context to another when they + * go to sleep. + * + * aio_co_wake may be executed either in coroutine or non-coroutine + * context. The coroutine must not be entered by anyone else while + * aio_co_wake() is active. + */ +void aio_co_wake(struct Coroutine *co); + +/** * Return the AioContext whose event loop runs in the current thread. * * If called from an IOThread this will be the IOThread's AioContext. If diff --git a/include/qemu/coroutine_int.h b/include/qemu/coroutine_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine_int.h +++ b/include/qemu/coroutine_int.h @@ -XXX,XX +XXX,XX @@ struct Coroutine { CoroutineEntry *entry; void *entry_arg; Coroutine *caller; + + /* Only used when the coroutine has terminated. */ QSLIST_ENTRY(Coroutine) pool_next; + size_t locks_held; - /* Coroutines that should be woken up when we yield or terminate */ + /* Coroutines that should be woken up when we yield or terminate. + * Only used when the coroutine is running. + */ QSIMPLEQ_HEAD(, Coroutine) co_queue_wakeup; + + /* Only used when the coroutine has yielded. */ + AioContext *ctx; QSIMPLEQ_ENTRY(Coroutine) co_queue_next; + QSLIST_ENTRY(Coroutine) co_scheduled_next; }; Coroutine *qemu_coroutine_new(void); diff --git a/tests/iothread.h b/tests/iothread.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/iothread.h @@ -XXX,XX +XXX,XX @@ +/* + * Event loop thread implementation for unit tests + * + * Copyright Red Hat Inc., 2013, 2016 + * + * Authors: + * Stefan Hajnoczi <stefanha@redhat.com> + * Paolo Bonzini <pbonzini@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ +#ifndef TEST_IOTHREAD_H +#define TEST_IOTHREAD_H + +#include "block/aio.h" +#include "qemu/thread.h" + +typedef struct IOThread IOThread; + +IOThread *iothread_new(void); +void iothread_join(IOThread *iothread); +AioContext *iothread_get_aio_context(IOThread *iothread); + +#endif diff --git a/tests/iothread.c b/tests/iothread.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/iothread.c @@ -XXX,XX +XXX,XX @@ +/* + * Event loop thread implementation for unit tests + * + * Copyright Red Hat Inc., 2013, 2016 + * + * Authors: + * Stefan Hajnoczi <stefanha@redhat.com> + * Paolo Bonzini <pbonzini@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "block/aio.h" +#include "qemu/main-loop.h" +#include "qemu/rcu.h" +#include "iothread.h" + +struct IOThread { + AioContext *ctx; + + QemuThread thread; + QemuMutex init_done_lock; + QemuCond init_done_cond; /* is thread initialization done? */ + bool stopping; +}; + +static __thread IOThread *my_iothread; + +AioContext *qemu_get_current_aio_context(void) +{ + return my_iothread ? my_iothread->ctx : qemu_get_aio_context(); +} + +static void *iothread_run(void *opaque) +{ + IOThread *iothread = opaque; + + rcu_register_thread(); + + my_iothread = iothread; + qemu_mutex_lock(&iothread->init_done_lock); + iothread->ctx = aio_context_new(&error_abort); + qemu_cond_signal(&iothread->init_done_cond); + qemu_mutex_unlock(&iothread->init_done_lock); + + while (!atomic_read(&iothread->stopping)) { + aio_poll(iothread->ctx, true); + } + + rcu_unregister_thread(); + return NULL; +} + +void iothread_join(IOThread *iothread) +{ + iothread->stopping = true; + aio_notify(iothread->ctx); + qemu_thread_join(&iothread->thread); + qemu_cond_destroy(&iothread->init_done_cond); + qemu_mutex_destroy(&iothread->init_done_lock); + aio_context_unref(iothread->ctx); + g_free(iothread); +} + +IOThread *iothread_new(void) +{ + IOThread *iothread = g_new0(IOThread, 1); + + qemu_mutex_init(&iothread->init_done_lock); + qemu_cond_init(&iothread->init_done_cond); + qemu_thread_create(&iothread->thread, NULL, iothread_run, + iothread, QEMU_THREAD_JOINABLE); + + /* Wait for initialization to complete */ + qemu_mutex_lock(&iothread->init_done_lock); + while (iothread->ctx == NULL) { + qemu_cond_wait(&iothread->init_done_cond, + &iothread->init_done_lock); + } + qemu_mutex_unlock(&iothread->init_done_lock); + return iothread; +} + +AioContext *iothread_get_aio_context(IOThread *iothread) +{ + return iothread->ctx; +} diff --git a/tests/test-aio-multithread.c b/tests/test-aio-multithread.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/test-aio-multithread.c @@ -XXX,XX +XXX,XX @@ +/* + * AioContext multithreading tests + * + * Copyright Red Hat, Inc. 2016 + * + * Authors: + * Paolo Bonzini <pbonzini@redhat.com> + * + * This work is licensed under the terms of the GNU LGPL, version 2 or later. + * See the COPYING.LIB file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include <glib.h> +#include "block/aio.h" +#include "qapi/error.h" +#include "qemu/coroutine.h" +#include "qemu/thread.h" +#include "qemu/error-report.h" +#include "iothread.h" + +/* AioContext management */ + +#define NUM_CONTEXTS 5 + +static IOThread *threads[NUM_CONTEXTS]; +static AioContext *ctx[NUM_CONTEXTS]; +static __thread int id = -1; + +static QemuEvent done_event; + +/* Run a function synchronously on a remote iothread. */ + +typedef struct CtxRunData { + QEMUBHFunc *cb; + void *arg; +} CtxRunData; + +static void ctx_run_bh_cb(void *opaque) +{ + CtxRunData *data = opaque; + + data->cb(data->arg); + qemu_event_set(&done_event); +} + +static void ctx_run(int i, QEMUBHFunc *cb, void *opaque) +{ + CtxRunData data = { + .cb = cb, + .arg = opaque + }; + + qemu_event_reset(&done_event); + aio_bh_schedule_oneshot(ctx[i], ctx_run_bh_cb, &data); + qemu_event_wait(&done_event); +} + +/* Starting the iothreads. */ + +static void set_id_cb(void *opaque) +{ + int *i = opaque; + + id = *i; +} + +static void create_aio_contexts(void) +{ + int i; + + for (i = 0; i < NUM_CONTEXTS; i++) { + threads[i] = iothread_new(); + ctx[i] = iothread_get_aio_context(threads[i]); + } + + qemu_event_init(&done_event, false); + for (i = 0; i < NUM_CONTEXTS; i++) { + ctx_run(i, set_id_cb, &i); + } +} + +/* Stopping the iothreads. */ + +static void join_aio_contexts(void) +{ + int i; + + for (i = 0; i < NUM_CONTEXTS; i++) { + aio_context_ref(ctx[i]); + } + for (i = 0; i < NUM_CONTEXTS; i++) { + iothread_join(threads[i]); + } + for (i = 0; i < NUM_CONTEXTS; i++) { + aio_context_unref(ctx[i]); + } + qemu_event_destroy(&done_event); +} + +/* Basic test for the stuff above. */ + +static void test_lifecycle(void) +{ + create_aio_contexts(); + join_aio_contexts(); +} + +/* aio_co_schedule test. */ + +static Coroutine *to_schedule[NUM_CONTEXTS]; + +static bool now_stopping; + +static int count_retry; +static int count_here; +static int count_other; + +static bool schedule_next(int n) +{ + Coroutine *co; + + co = atomic_xchg(&to_schedule[n], NULL); + if (!co) { + atomic_inc(&count_retry); + return false; + } + + if (n == id) { + atomic_inc(&count_here); + } else { + atomic_inc(&count_other); + } + + aio_co_schedule(ctx[n], co); + return true; +} + +static void finish_cb(void *opaque) +{ + schedule_next(id); +} + +static coroutine_fn void test_multi_co_schedule_entry(void *opaque) +{ + g_assert(to_schedule[id] == NULL); + atomic_mb_set(&to_schedule[id], qemu_coroutine_self()); + + while (!atomic_mb_read(&now_stopping)) { + int n; + + n = g_test_rand_int_range(0, NUM_CONTEXTS); + schedule_next(n); + qemu_coroutine_yield(); + + g_assert(to_schedule[id] == NULL); + atomic_mb_set(&to_schedule[id], qemu_coroutine_self()); + } +} + + +static void test_multi_co_schedule(int seconds) +{ + int i; + + count_here = count_other = count_retry = 0; + now_stopping = false; + + create_aio_contexts(); + for (i = 0; i < NUM_CONTEXTS; i++) { + Coroutine *co1 = qemu_coroutine_create(test_multi_co_schedule_entry, NULL); + aio_co_schedule(ctx[i], co1); + } + + g_usleep(seconds * 1000000); + + atomic_mb_set(&now_stopping, true); + for (i = 0; i < NUM_CONTEXTS; i++) { + ctx_run(i, finish_cb, NULL); + to_schedule[i] = NULL; + } + + join_aio_contexts(); + g_test_message("scheduled %d, queued %d, retry %d, total %d\n", + count_other, count_here, count_retry, + count_here + count_other + count_retry); +} + +static void test_multi_co_schedule_1(void) +{ + test_multi_co_schedule(1); +} + +static void test_multi_co_schedule_10(void) +{ + test_multi_co_schedule(10); +} + +/* End of tests. */ + +int main(int argc, char **argv) +{ + init_clocks(); + + g_test_init(&argc, &argv, NULL); + g_test_add_func("/aio/multi/lifecycle", test_lifecycle); + if (g_test_quick()) { + g_test_add_func("/aio/multi/schedule", test_multi_co_schedule_1); + } else { + g_test_add_func("/aio/multi/schedule", test_multi_co_schedule_10); + } + return g_test_run(); +} diff --git a/util/async.c b/util/async.c index XXXXXXX..XXXXXXX 100644 --- a/util/async.c +++ b/util/async.c @@ -XXX,XX +XXX,XX @@ #include "qemu/main-loop.h" #include "qemu/atomic.h" #include "block/raw-aio.h" +#include "qemu/coroutine_int.h" +#include "trace.h" /***********************************************************/ /* bottom halves (can be seen as timers which expire ASAP) */ @@ -XXX,XX +XXX,XX @@ aio_ctx_finalize(GSource *source) } #endif + assert(QSLIST_EMPTY(&ctx->scheduled_coroutines)); + qemu_bh_delete(ctx->co_schedule_bh); + qemu_lockcnt_lock(&ctx->list_lock); assert(!qemu_lockcnt_count(&ctx->list_lock)); while (ctx->first_bh) { @@ -XXX,XX +XXX,XX @@ static bool event_notifier_poll(void *opaque) return atomic_read(&ctx->notified); } +static void co_schedule_bh_cb(void *opaque) +{ + AioContext *ctx = opaque; + QSLIST_HEAD(, Coroutine) straight, reversed; + + QSLIST_MOVE_ATOMIC(&reversed, &ctx->scheduled_coroutines); + QSLIST_INIT(&straight); + + while (!QSLIST_EMPTY(&reversed)) { + Coroutine *co = QSLIST_FIRST(&reversed); + QSLIST_REMOVE_HEAD(&reversed, co_scheduled_next); + QSLIST_INSERT_HEAD(&straight, co, co_scheduled_next); + } + + while (!QSLIST_EMPTY(&straight)) { + Coroutine *co = QSLIST_FIRST(&straight); + QSLIST_REMOVE_HEAD(&straight, co_scheduled_next); + trace_aio_co_schedule_bh_cb(ctx, co); + qemu_coroutine_enter(co); + } +} + AioContext *aio_context_new(Error **errp) { int ret; @@ -XXX,XX +XXX,XX @@ AioContext *aio_context_new(Error **errp) } g_source_set_can_recurse(&ctx->source, true); qemu_lockcnt_init(&ctx->list_lock); + + ctx->co_schedule_bh = aio_bh_new(ctx, co_schedule_bh_cb, ctx); + QSLIST_INIT(&ctx->scheduled_coroutines); + aio_set_event_notifier(ctx, &ctx->notifier, false, (EventNotifierHandler *) @@ -XXX,XX +XXX,XX @@ fail: return NULL; } +void aio_co_schedule(AioContext *ctx, Coroutine *co) +{ + trace_aio_co_schedule(ctx, co); + QSLIST_INSERT_HEAD_ATOMIC(&ctx->scheduled_coroutines, + co, co_scheduled_next); + qemu_bh_schedule(ctx->co_schedule_bh); +} + +void aio_co_wake(struct Coroutine *co) +{ + AioContext *ctx; + + /* Read coroutine before co->ctx. Matches smp_wmb in + * qemu_coroutine_enter. + */ + smp_read_barrier_depends(); + ctx = atomic_read(&co->ctx); + + if (ctx != qemu_get_current_aio_context()) { + aio_co_schedule(ctx, co); + return; + } + + if (qemu_in_coroutine()) { + Coroutine *self = qemu_coroutine_self(); + assert(self != co); + QSIMPLEQ_INSERT_TAIL(&self->co_queue_wakeup, co, co_queue_next); + } else { + aio_context_acquire(ctx); + qemu_coroutine_enter(co); + aio_context_release(ctx); + } +} + void aio_context_ref(AioContext *ctx) { g_source_ref(&ctx->source); diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine.c +++ b/util/qemu-coroutine.c @@ -XXX,XX +XXX,XX @@ #include "qemu/atomic.h" #include "qemu/coroutine.h" #include "qemu/coroutine_int.h" +#include "block/aio.h" enum { POOL_BATCH_SIZE = 64, @@ -XXX,XX +XXX,XX @@ void qemu_coroutine_enter(Coroutine *co) } co->caller = self; + co->ctx = qemu_get_current_aio_context(); + + /* Store co->ctx before anything that stores co. Matches + * barrier in aio_co_wake. + */ + smp_wmb(); + ret = qemu_coroutine_switch(self, co, COROUTINE_ENTER); qemu_co_queue_run_restart(co); diff --git a/util/trace-events b/util/trace-events index XXXXXXX..XXXXXXX 100644 --- a/util/trace-events +++ b/util/trace-events @@ -XXX,XX +XXX,XX @@ run_poll_handlers_end(void *ctx, bool progress) "ctx %p progress %d" poll_shrink(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64 poll_grow(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64 +# util/async.c +aio_co_schedule(void *ctx, void *co) "ctx %p co %p" +aio_co_schedule_bh_cb(void *ctx, void *co) "ctx %p co %p" + # util/thread-pool.c thread_pool_submit(void *pool, void *req, void *opaque) "pool %p req %p opaque %p" thread_pool_complete(void *pool, void *req, void *opaque, int ret) "pool %p req %p opaque %p ret %d" -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> qcow2_create2 calls this. Do not run a nested event loop, as that breaks when aio_co_wake tries to queue the coroutine on the co_queue_wakeup list of the currently running one. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213135235.12274-4-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/block-backend.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf, { QEMUIOVector qiov; struct iovec iov; - Coroutine *co; BlkRwCo rwco; iov = (struct iovec) { @@ -XXX,XX +XXX,XX @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf, .ret = NOT_DONE, }; - co = qemu_coroutine_create(co_entry, &rwco); - qemu_coroutine_enter(co); - BDRV_POLL_WHILE(blk_bs(blk), rwco.ret == NOT_DONE); + if (qemu_in_coroutine()) { + /* Fast-path if already in coroutine context */ + co_entry(&rwco); + } else { + Coroutine *co = qemu_coroutine_create(co_entry, &rwco); + qemu_coroutine_enter(co); + BDRV_POLL_WHILE(blk_bs(blk), rwco.ret == NOT_DONE); + } return rwco.ret; } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Once the thread pool starts using aio_co_wake, it will also need qemu_get_current_aio_context(). Make test-thread-pool create an AioContext with qemu_init_main_loop, so that stubs/iothread.c and tests/iothread.c can provide the rest. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213135235.12274-5-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/test-thread-pool.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/tests/test-thread-pool.c b/tests/test-thread-pool.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-thread-pool.c +++ b/tests/test-thread-pool.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "qemu/timer.h" #include "qemu/error-report.h" +#include "qemu/main-loop.h" static AioContext *ctx; static ThreadPool *pool; @@ -XXX,XX +XXX,XX @@ static void test_cancel_async(void) int main(int argc, char **argv) { int ret; - Error *local_error = NULL; - init_clocks(); - - ctx = aio_context_new(&local_error); - if (!ctx) { - error_reportf_err(local_error, "Failed to create AIO Context: "); - exit(1); - } + qemu_init_main_loop(&error_abort); + ctx = qemu_get_current_aio_context(); pool = aio_get_thread_pool(ctx); g_test_init(&argc, &argv, NULL); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) ret = g_test_run(); - aio_context_unref(ctx); return ret; } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> This is in preparation for making qio_channel_yield work on AioContexts other than the main one. Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213135235.12274-6-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/io/channel.h | 25 +++++++++++++++++++++++++ io/channel-command.c | 13 +++++++++++++ io/channel-file.c | 11 +++++++++++ io/channel-socket.c | 16 +++++++++++----- io/channel-tls.c | 12 ++++++++++++ io/channel-watch.c | 6 ++++++ io/channel.c | 11 +++++++++++ 7 files changed, 89 insertions(+), 5 deletions(-) diff --git a/include/io/channel.h b/include/io/channel.h index XXXXXXX..XXXXXXX 100644 --- a/include/io/channel.h +++ b/include/io/channel.h @@ -XXX,XX +XXX,XX @@ #include "qemu-common.h" #include "qom/object.h" +#include "block/aio.h" #define TYPE_QIO_CHANNEL "qio-channel" #define QIO_CHANNEL(obj) \ @@ -XXX,XX +XXX,XX @@ struct QIOChannelClass { off_t offset, int whence, Error **errp); + void (*io_set_aio_fd_handler)(QIOChannel *ioc, + AioContext *ctx, + IOHandler *io_read, + IOHandler *io_write, + void *opaque); }; /* General I/O handling functions */ @@ -XXX,XX +XXX,XX @@ void qio_channel_yield(QIOChannel *ioc, void qio_channel_wait(QIOChannel *ioc, GIOCondition condition); +/** + * qio_channel_set_aio_fd_handler: + * @ioc: the channel object + * @ctx: the AioContext to set the handlers on + * @io_read: the read handler + * @io_write: the write handler + * @opaque: the opaque value passed to the handler + * + * This is used internally by qio_channel_yield(). It can + * be used by channel implementations to forward the handlers + * to another channel (e.g. from #QIOChannelTLS to the + * underlying socket). + */ +void qio_channel_set_aio_fd_handler(QIOChannel *ioc, + AioContext *ctx, + IOHandler *io_read, + IOHandler *io_write, + void *opaque); + #endif /* QIO_CHANNEL_H */ diff --git a/io/channel-command.c b/io/channel-command.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel-command.c +++ b/io/channel-command.c @@ -XXX,XX +XXX,XX @@ static int qio_channel_command_close(QIOChannel *ioc, } +static void qio_channel_command_set_aio_fd_handler(QIOChannel *ioc, + AioContext *ctx, + IOHandler *io_read, + IOHandler *io_write, + void *opaque) +{ + QIOChannelCommand *cioc = QIO_CHANNEL_COMMAND(ioc); + aio_set_fd_handler(ctx, cioc->readfd, false, io_read, NULL, NULL, opaque); + aio_set_fd_handler(ctx, cioc->writefd, false, NULL, io_write, NULL, opaque); +} + + static GSource *qio_channel_command_create_watch(QIOChannel *ioc, GIOCondition condition) { @@ -XXX,XX +XXX,XX @@ static void qio_channel_command_class_init(ObjectClass *klass, ioc_klass->io_set_blocking = qio_channel_command_set_blocking; ioc_klass->io_close = qio_channel_command_close; ioc_klass->io_create_watch = qio_channel_command_create_watch; + ioc_klass->io_set_aio_fd_handler = qio_channel_command_set_aio_fd_handler; } static const TypeInfo qio_channel_command_info = { diff --git a/io/channel-file.c b/io/channel-file.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel-file.c +++ b/io/channel-file.c @@ -XXX,XX +XXX,XX @@ static int qio_channel_file_close(QIOChannel *ioc, } +static void qio_channel_file_set_aio_fd_handler(QIOChannel *ioc, + AioContext *ctx, + IOHandler *io_read, + IOHandler *io_write, + void *opaque) +{ + QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc); + aio_set_fd_handler(ctx, fioc->fd, false, io_read, io_write, NULL, opaque); +} + static GSource *qio_channel_file_create_watch(QIOChannel *ioc, GIOCondition condition) { @@ -XXX,XX +XXX,XX @@ static void qio_channel_file_class_init(ObjectClass *klass, ioc_klass->io_seek = qio_channel_file_seek; ioc_klass->io_close = qio_channel_file_close; ioc_klass->io_create_watch = qio_channel_file_create_watch; + ioc_klass->io_set_aio_fd_handler = qio_channel_file_set_aio_fd_handler; } static const TypeInfo qio_channel_file_info = { diff --git a/io/channel-socket.c b/io/channel-socket.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel-socket.c +++ b/io/channel-socket.c @@ -XXX,XX +XXX,XX @@ qio_channel_socket_set_blocking(QIOChannel *ioc, qemu_set_block(sioc->fd); } else { qemu_set_nonblock(sioc->fd); -#ifdef WIN32 - WSAEventSelect(sioc->fd, ioc->event, - FD_READ | FD_ACCEPT | FD_CLOSE | - FD_CONNECT | FD_WRITE | FD_OOB); -#endif } return 0; } @@ -XXX,XX +XXX,XX @@ qio_channel_socket_shutdown(QIOChannel *ioc, return 0; } +static void qio_channel_socket_set_aio_fd_handler(QIOChannel *ioc, + AioContext *ctx, + IOHandler *io_read, + IOHandler *io_write, + void *opaque) +{ + QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc); + aio_set_fd_handler(ctx, sioc->fd, false, io_read, io_write, NULL, opaque); +} + static GSource *qio_channel_socket_create_watch(QIOChannel *ioc, GIOCondition condition) { @@ -XXX,XX +XXX,XX @@ static void qio_channel_socket_class_init(ObjectClass *klass, ioc_klass->io_set_cork = qio_channel_socket_set_cork; ioc_klass->io_set_delay = qio_channel_socket_set_delay; ioc_klass->io_create_watch = qio_channel_socket_create_watch; + ioc_klass->io_set_aio_fd_handler = qio_channel_socket_set_aio_fd_handler; } static const TypeInfo qio_channel_socket_info = { diff --git a/io/channel-tls.c b/io/channel-tls.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel-tls.c +++ b/io/channel-tls.c @@ -XXX,XX +XXX,XX @@ static int qio_channel_tls_close(QIOChannel *ioc, return qio_channel_close(tioc->master, errp); } +static void qio_channel_tls_set_aio_fd_handler(QIOChannel *ioc, + AioContext *ctx, + IOHandler *io_read, + IOHandler *io_write, + void *opaque) +{ + QIOChannelTLS *tioc = QIO_CHANNEL_TLS(ioc); + + qio_channel_set_aio_fd_handler(tioc->master, ctx, io_read, io_write, opaque); +} + static GSource *qio_channel_tls_create_watch(QIOChannel *ioc, GIOCondition condition) { @@ -XXX,XX +XXX,XX @@ static void qio_channel_tls_class_init(ObjectClass *klass, ioc_klass->io_close = qio_channel_tls_close; ioc_klass->io_shutdown = qio_channel_tls_shutdown; ioc_klass->io_create_watch = qio_channel_tls_create_watch; + ioc_klass->io_set_aio_fd_handler = qio_channel_tls_set_aio_fd_handler; } static const TypeInfo qio_channel_tls_info = { diff --git a/io/channel-watch.c b/io/channel-watch.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel-watch.c +++ b/io/channel-watch.c @@ -XXX,XX +XXX,XX @@ GSource *qio_channel_create_socket_watch(QIOChannel *ioc, GSource *source; QIOChannelSocketSource *ssource; +#ifdef WIN32 + WSAEventSelect(socket, ioc->event, + FD_READ | FD_ACCEPT | FD_CLOSE | + FD_CONNECT | FD_WRITE | FD_OOB); +#endif + source = g_source_new(&qio_channel_socket_source_funcs, sizeof(QIOChannelSocketSource)); ssource = (QIOChannelSocketSource *)source; diff --git a/io/channel.c b/io/channel.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel.c +++ b/io/channel.c @@ -XXX,XX +XXX,XX @@ GSource *qio_channel_create_watch(QIOChannel *ioc, } +void qio_channel_set_aio_fd_handler(QIOChannel *ioc, + AioContext *ctx, + IOHandler *io_read, + IOHandler *io_write, + void *opaque) +{ + QIOChannelClass *klass = QIO_CHANNEL_GET_CLASS(ioc); + + klass->io_set_aio_fd_handler(ioc, ctx, io_read, io_write, opaque); +} + guint qio_channel_add_watch(QIOChannel *ioc, GIOCondition condition, QIOChannelFunc func, -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Support separate coroutines for reading and writing, and place the read/write handlers on the AioContext that the QIOChannel is registered with. Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213135235.12274-7-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/io/channel.h | 47 ++++++++++++++++++++++++++-- io/channel.c | 86 +++++++++++++++++++++++++++++++++++++++------------- 2 files changed, 109 insertions(+), 24 deletions(-) diff --git a/include/io/channel.h b/include/io/channel.h index XXXXXXX..XXXXXXX 100644 --- a/include/io/channel.h +++ b/include/io/channel.h @@ -XXX,XX +XXX,XX @@ #include "qemu-common.h" #include "qom/object.h" +#include "qemu/coroutine.h" #include "block/aio.h" #define TYPE_QIO_CHANNEL "qio-channel" @@ -XXX,XX +XXX,XX @@ struct QIOChannel { Object parent; unsigned int features; /* bitmask of QIOChannelFeatures */ char *name; + AioContext *ctx; + Coroutine *read_coroutine; + Coroutine *write_coroutine; #ifdef _WIN32 HANDLE event; /* For use with GSource on Win32 */ #endif @@ -XXX,XX +XXX,XX @@ guint qio_channel_add_watch(QIOChannel *ioc, /** + * qio_channel_attach_aio_context: + * @ioc: the channel object + * @ctx: the #AioContext to set the handlers on + * + * Request that qio_channel_yield() sets I/O handlers on + * the given #AioContext. If @ctx is %NULL, qio_channel_yield() + * uses QEMU's main thread event loop. + * + * You can move a #QIOChannel from one #AioContext to another even if + * I/O handlers are set for a coroutine. However, #QIOChannel provides + * no synchronization between the calls to qio_channel_yield() and + * qio_channel_attach_aio_context(). + * + * Therefore you should first call qio_channel_detach_aio_context() + * to ensure that the coroutine is not entered concurrently. Then, + * while the coroutine has yielded, call qio_channel_attach_aio_context(), + * and then aio_co_schedule() to place the coroutine on the new + * #AioContext. The calls to qio_channel_detach_aio_context() + * and qio_channel_attach_aio_context() should be protected with + * aio_context_acquire() and aio_context_release(). + */ +void qio_channel_attach_aio_context(QIOChannel *ioc, + AioContext *ctx); + +/** + * qio_channel_detach_aio_context: + * @ioc: the channel object + * + * Disable any I/O handlers set by qio_channel_yield(). With the + * help of aio_co_schedule(), this allows moving a coroutine that was + * paused by qio_channel_yield() to another context. + */ +void qio_channel_detach_aio_context(QIOChannel *ioc); + +/** * qio_channel_yield: * @ioc: the channel object * @condition: the I/O condition to wait for * - * Yields execution from the current coroutine until - * the condition indicated by @condition becomes - * available. + * Yields execution from the current coroutine until the condition + * indicated by @condition becomes available. @condition must + * be either %G_IO_IN or %G_IO_OUT; it cannot contain both. In + * addition, no two coroutine can be waiting on the same condition + * and channel at the same time. * * This must only be called from coroutine context */ diff --git a/io/channel.c b/io/channel.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel.c +++ b/io/channel.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "io/channel.h" #include "qapi/error.h" -#include "qemu/coroutine.h" +#include "qemu/main-loop.h" bool qio_channel_has_feature(QIOChannel *ioc, QIOChannelFeature feature) @@ -XXX,XX +XXX,XX @@ off_t qio_channel_io_seek(QIOChannel *ioc, } -typedef struct QIOChannelYieldData QIOChannelYieldData; -struct QIOChannelYieldData { - QIOChannel *ioc; - Coroutine *co; -}; +static void qio_channel_set_aio_fd_handlers(QIOChannel *ioc); +static void qio_channel_restart_read(void *opaque) +{ + QIOChannel *ioc = opaque; + Coroutine *co = ioc->read_coroutine; + + ioc->read_coroutine = NULL; + qio_channel_set_aio_fd_handlers(ioc); + aio_co_wake(co); +} -static gboolean qio_channel_yield_enter(QIOChannel *ioc, - GIOCondition condition, - gpointer opaque) +static void qio_channel_restart_write(void *opaque) { - QIOChannelYieldData *data = opaque; - qemu_coroutine_enter(data->co); - return FALSE; + QIOChannel *ioc = opaque; + Coroutine *co = ioc->write_coroutine; + + ioc->write_coroutine = NULL; + qio_channel_set_aio_fd_handlers(ioc); + aio_co_wake(co); } +static void qio_channel_set_aio_fd_handlers(QIOChannel *ioc) +{ + IOHandler *rd_handler = NULL, *wr_handler = NULL; + AioContext *ctx; + + if (ioc->read_coroutine) { + rd_handler = qio_channel_restart_read; + } + if (ioc->write_coroutine) { + wr_handler = qio_channel_restart_write; + } + + ctx = ioc->ctx ? ioc->ctx : iohandler_get_aio_context(); + qio_channel_set_aio_fd_handler(ioc, ctx, rd_handler, wr_handler, ioc); +} + +void qio_channel_attach_aio_context(QIOChannel *ioc, + AioContext *ctx) +{ + AioContext *old_ctx; + if (ioc->ctx == ctx) { + return; + } + + old_ctx = ioc->ctx ? ioc->ctx : iohandler_get_aio_context(); + qio_channel_set_aio_fd_handler(ioc, old_ctx, NULL, NULL, NULL); + ioc->ctx = ctx; + qio_channel_set_aio_fd_handlers(ioc); +} + +void qio_channel_detach_aio_context(QIOChannel *ioc) +{ + ioc->read_coroutine = NULL; + ioc->write_coroutine = NULL; + qio_channel_set_aio_fd_handlers(ioc); + ioc->ctx = NULL; +} void coroutine_fn qio_channel_yield(QIOChannel *ioc, GIOCondition condition) { - QIOChannelYieldData data; - assert(qemu_in_coroutine()); - data.ioc = ioc; - data.co = qemu_coroutine_self(); - qio_channel_add_watch(ioc, - condition, - qio_channel_yield_enter, - &data, - NULL); + if (condition == G_IO_IN) { + assert(!ioc->read_coroutine); + ioc->read_coroutine = qemu_coroutine_self(); + } else if (condition == G_IO_OUT) { + assert(!ioc->write_coroutine); + ioc->write_coroutine = qemu_coroutine_self(); + } else { + abort(); + } + qio_channel_set_aio_fd_handlers(ioc); qemu_coroutine_yield(); } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> In the client, read the reply headers from a coroutine, switching the read side between the "read header" coroutine and the I/O coroutine that reads the body of the reply. In the server, if the server can read more requests it will create a new "read request" coroutine as soon as a request has been read. Otherwise, the new coroutine is created in nbd_request_put. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-8-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/nbd-client.h | 2 +- block/nbd-client.c | 117 ++++++++++++++++++++++++----------------------------- nbd/client.c | 2 +- nbd/common.c | 9 +---- nbd/server.c | 94 +++++++++++++----------------------------- 5 files changed, 83 insertions(+), 141 deletions(-) diff --git a/block/nbd-client.h b/block/nbd-client.h index XXXXXXX..XXXXXXX 100644 --- a/block/nbd-client.h +++ b/block/nbd-client.h @@ -XXX,XX +XXX,XX @@ typedef struct NBDClientSession { CoMutex send_mutex; CoQueue free_sema; - Coroutine *send_coroutine; + Coroutine *read_reply_co; int in_flight; Coroutine *recv_coroutine[MAX_NBD_REQUESTS]; diff --git a/block/nbd-client.c b/block/nbd-client.c index XXXXXXX..XXXXXXX 100644 --- a/block/nbd-client.c +++ b/block/nbd-client.c @@ -XXX,XX +XXX,XX @@ #define HANDLE_TO_INDEX(bs, handle) ((handle) ^ ((uint64_t)(intptr_t)bs)) #define INDEX_TO_HANDLE(bs, index) ((index) ^ ((uint64_t)(intptr_t)bs)) -static void nbd_recv_coroutines_enter_all(NBDClientSession *s) +static void nbd_recv_coroutines_enter_all(BlockDriverState *bs) { + NBDClientSession *s = nbd_get_client_session(bs); int i; for (i = 0; i < MAX_NBD_REQUESTS; i++) { @@ -XXX,XX +XXX,XX @@ static void nbd_recv_coroutines_enter_all(NBDClientSession *s) qemu_coroutine_enter(s->recv_coroutine[i]); } } + BDRV_POLL_WHILE(bs, s->read_reply_co); } static void nbd_teardown_connection(BlockDriverState *bs) @@ -XXX,XX +XXX,XX @@ static void nbd_teardown_connection(BlockDriverState *bs) qio_channel_shutdown(client->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); - nbd_recv_coroutines_enter_all(client); + nbd_recv_coroutines_enter_all(bs); nbd_client_detach_aio_context(bs); object_unref(OBJECT(client->sioc)); @@ -XXX,XX +XXX,XX @@ static void nbd_teardown_connection(BlockDriverState *bs) client->ioc = NULL; } -static void nbd_reply_ready(void *opaque) +static coroutine_fn void nbd_read_reply_entry(void *opaque) { - BlockDriverState *bs = opaque; - NBDClientSession *s = nbd_get_client_session(bs); + NBDClientSession *s = opaque; uint64_t i; int ret; - if (!s->ioc) { /* Already closed */ - return; - } - - if (s->reply.handle == 0) { - /* No reply already in flight. Fetch a header. It is possible - * that another thread has done the same thing in parallel, so - * the socket is not readable anymore. - */ + for (;;) { + assert(s->reply.handle == 0); ret = nbd_receive_reply(s->ioc, &s->reply); - if (ret == -EAGAIN) { - return; - } if (ret < 0) { - s->reply.handle = 0; - goto fail; + break; } - } - /* There's no need for a mutex on the receive side, because the - * handler acts as a synchronization point and ensures that only - * one coroutine is called until the reply finishes. */ - i = HANDLE_TO_INDEX(s, s->reply.handle); - if (i >= MAX_NBD_REQUESTS) { - goto fail; - } + /* There's no need for a mutex on the receive side, because the + * handler acts as a synchronization point and ensures that only + * one coroutine is called until the reply finishes. + */ + i = HANDLE_TO_INDEX(s, s->reply.handle); + if (i >= MAX_NBD_REQUESTS || !s->recv_coroutine[i]) { + break; + } - if (s->recv_coroutine[i]) { - qemu_coroutine_enter(s->recv_coroutine[i]); - return; + /* We're woken up by the recv_coroutine itself. Note that there + * is no race between yielding and reentering read_reply_co. This + * is because: + * + * - if recv_coroutine[i] runs on the same AioContext, it is only + * entered after we yield + * + * - if recv_coroutine[i] runs on a different AioContext, reentering + * read_reply_co happens through a bottom half, which can only + * run after we yield. + */ + aio_co_wake(s->recv_coroutine[i]); + qemu_coroutine_yield(); } - -fail: - nbd_teardown_connection(bs); -} - -static void nbd_restart_write(void *opaque) -{ - BlockDriverState *bs = opaque; - - qemu_coroutine_enter(nbd_get_client_session(bs)->send_coroutine); + s->read_reply_co = NULL; } static int nbd_co_send_request(BlockDriverState *bs, @@ -XXX,XX +XXX,XX @@ static int nbd_co_send_request(BlockDriverState *bs, QEMUIOVector *qiov) { NBDClientSession *s = nbd_get_client_session(bs); - AioContext *aio_context; int rc, ret, i; qemu_co_mutex_lock(&s->send_mutex); @@ -XXX,XX +XXX,XX @@ static int nbd_co_send_request(BlockDriverState *bs, return -EPIPE; } - s->send_coroutine = qemu_coroutine_self(); - aio_context = bdrv_get_aio_context(bs); - - aio_set_fd_handler(aio_context, s->sioc->fd, false, - nbd_reply_ready, nbd_restart_write, NULL, bs); if (qiov) { qio_channel_set_cork(s->ioc, true); rc = nbd_send_request(s->ioc, request); @@ -XXX,XX +XXX,XX @@ static int nbd_co_send_request(BlockDriverState *bs, } else { rc = nbd_send_request(s->ioc, request); } - aio_set_fd_handler(aio_context, s->sioc->fd, false, - nbd_reply_ready, NULL, NULL, bs); - s->send_coroutine = NULL; qemu_co_mutex_unlock(&s->send_mutex); return rc; } @@ -XXX,XX +XXX,XX @@ static void nbd_co_receive_reply(NBDClientSession *s, { int ret; - /* Wait until we're woken up by the read handler. TODO: perhaps - * peek at the next reply and avoid yielding if it's ours? */ + /* Wait until we're woken up by nbd_read_reply_entry. */ qemu_coroutine_yield(); *reply = s->reply; if (reply->handle != request->handle || @@ -XXX,XX +XXX,XX @@ static void nbd_coroutine_start(NBDClientSession *s, /* s->recv_coroutine[i] is set as soon as we get the send_lock. */ } -static void nbd_coroutine_end(NBDClientSession *s, +static void nbd_coroutine_end(BlockDriverState *bs, NBDRequest *request) { + NBDClientSession *s = nbd_get_client_session(bs); int i = HANDLE_TO_INDEX(s, request->handle); + s->recv_coroutine[i] = NULL; - if (s->in_flight-- == MAX_NBD_REQUESTS) { - qemu_co_queue_next(&s->free_sema); + s->in_flight--; + qemu_co_queue_next(&s->free_sema); + + /* Kick the read_reply_co to get the next reply. */ + if (s->read_reply_co) { + aio_co_wake(s->read_reply_co); } } @@ -XXX,XX +XXX,XX @@ int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset, } else { nbd_co_receive_reply(client, &request, &reply, qiov); } - nbd_coroutine_end(client, &request); + nbd_coroutine_end(bs, &request); return -reply.error; } @@ -XXX,XX +XXX,XX @@ int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset, } else { nbd_co_receive_reply(client, &request, &reply, NULL); } - nbd_coroutine_end(client, &request); + nbd_coroutine_end(bs, &request); return -reply.error; } @@ -XXX,XX +XXX,XX @@ int nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, } else { nbd_co_receive_reply(client, &request, &reply, NULL); } - nbd_coroutine_end(client, &request); + nbd_coroutine_end(bs, &request); return -reply.error; } @@ -XXX,XX +XXX,XX @@ int nbd_client_co_flush(BlockDriverState *bs) } else { nbd_co_receive_reply(client, &request, &reply, NULL); } - nbd_coroutine_end(client, &request); + nbd_coroutine_end(bs, &request); return -reply.error; } @@ -XXX,XX +XXX,XX @@ int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int count) } else { nbd_co_receive_reply(client, &request, &reply, NULL); } - nbd_coroutine_end(client, &request); + nbd_coroutine_end(bs, &request); return -reply.error; } void nbd_client_detach_aio_context(BlockDriverState *bs) { - aio_set_fd_handler(bdrv_get_aio_context(bs), - nbd_get_client_session(bs)->sioc->fd, - false, NULL, NULL, NULL, NULL); + NBDClientSession *client = nbd_get_client_session(bs); + qio_channel_detach_aio_context(QIO_CHANNEL(client->sioc)); } void nbd_client_attach_aio_context(BlockDriverState *bs, AioContext *new_context) { - aio_set_fd_handler(new_context, nbd_get_client_session(bs)->sioc->fd, - false, nbd_reply_ready, NULL, NULL, bs); + NBDClientSession *client = nbd_get_client_session(bs); + qio_channel_attach_aio_context(QIO_CHANNEL(client->sioc), new_context); + aio_co_schedule(new_context, client->read_reply_co); } void nbd_client_close(BlockDriverState *bs) @@ -XXX,XX +XXX,XX @@ int nbd_client_init(BlockDriverState *bs, /* Now that we're connected, set the socket to be non-blocking and * kick the reply mechanism. */ qio_channel_set_blocking(QIO_CHANNEL(sioc), false, NULL); - + client->read_reply_co = qemu_coroutine_create(nbd_read_reply_entry, client); nbd_client_attach_aio_context(bs, bdrv_get_aio_context(bs)); logout("Established connection with NBD server\n"); diff --git a/nbd/client.c b/nbd/client.c index XXXXXXX..XXXXXXX 100644 --- a/nbd/client.c +++ b/nbd/client.c @@ -XXX,XX +XXX,XX @@ ssize_t nbd_receive_reply(QIOChannel *ioc, NBDReply *reply) ssize_t ret; ret = read_sync(ioc, buf, sizeof(buf)); - if (ret < 0) { + if (ret <= 0) { return ret; } diff --git a/nbd/common.c b/nbd/common.c index XXXXXXX..XXXXXXX 100644 --- a/nbd/common.c +++ b/nbd/common.c @@ -XXX,XX +XXX,XX @@ ssize_t nbd_wr_syncv(QIOChannel *ioc, } if (len == QIO_CHANNEL_ERR_BLOCK) { if (qemu_in_coroutine()) { - /* XXX figure out if we can create a variant on - * qio_channel_yield() that works with AIO contexts - * and consider using that in this branch */ - qemu_coroutine_yield(); - } else if (done) { - /* XXX this is needed by nbd_reply_ready. */ - qio_channel_wait(ioc, - do_read ? G_IO_IN : G_IO_OUT); + qio_channel_yield(ioc, do_read ? G_IO_IN : G_IO_OUT); } else { return -EAGAIN; } diff --git a/nbd/server.c b/nbd/server.c index XXXXXXX..XXXXXXX 100644 --- a/nbd/server.c +++ b/nbd/server.c @@ -XXX,XX +XXX,XX @@ struct NBDClient { CoMutex send_lock; Coroutine *send_coroutine; - bool can_read; - QTAILQ_ENTRY(NBDClient) next; int nb_requests; bool closing; @@ -XXX,XX +XXX,XX @@ struct NBDClient { /* That's all folks */ -static void nbd_set_handlers(NBDClient *client); -static void nbd_unset_handlers(NBDClient *client); -static void nbd_update_can_read(NBDClient *client); +static void nbd_client_receive_next_request(NBDClient *client); static gboolean nbd_negotiate_continue(QIOChannel *ioc, GIOCondition condition, @@ -XXX,XX +XXX,XX @@ void nbd_client_put(NBDClient *client) */ assert(client->closing); - nbd_unset_handlers(client); + qio_channel_detach_aio_context(client->ioc); object_unref(OBJECT(client->sioc)); object_unref(OBJECT(client->ioc)); if (client->tlscreds) { @@ -XXX,XX +XXX,XX @@ static NBDRequestData *nbd_request_get(NBDClient *client) assert(client->nb_requests <= MAX_NBD_REQUESTS - 1); client->nb_requests++; - nbd_update_can_read(client); req = g_new0(NBDRequestData, 1); nbd_client_get(client); @@ -XXX,XX +XXX,XX @@ static void nbd_request_put(NBDRequestData *req) g_free(req); client->nb_requests--; - nbd_update_can_read(client); + nbd_client_receive_next_request(client); + nbd_client_put(client); } @@ -XXX,XX +XXX,XX @@ static void blk_aio_attached(AioContext *ctx, void *opaque) exp->ctx = ctx; QTAILQ_FOREACH(client, &exp->clients, next) { - nbd_set_handlers(client); + qio_channel_attach_aio_context(client->ioc, ctx); + if (client->recv_coroutine) { + aio_co_schedule(ctx, client->recv_coroutine); + } + if (client->send_coroutine) { + aio_co_schedule(ctx, client->send_coroutine); + } } } @@ -XXX,XX +XXX,XX @@ static void blk_aio_detach(void *opaque) TRACE("Export %s: Detaching clients from AIO context %p\n", exp->name, exp->ctx); QTAILQ_FOREACH(client, &exp->clients, next) { - nbd_unset_handlers(client); + qio_channel_detach_aio_context(client->ioc); } exp->ctx = NULL; @@ -XXX,XX +XXX,XX @@ static ssize_t nbd_co_send_reply(NBDRequestData *req, NBDReply *reply, g_assert(qemu_in_coroutine()); qemu_co_mutex_lock(&client->send_lock); client->send_coroutine = qemu_coroutine_self(); - nbd_set_handlers(client); if (!len) { rc = nbd_send_reply(client->ioc, reply); @@ -XXX,XX +XXX,XX @@ static ssize_t nbd_co_send_reply(NBDRequestData *req, NBDReply *reply, } client->send_coroutine = NULL; - nbd_set_handlers(client); qemu_co_mutex_unlock(&client->send_lock); return rc; } @@ -XXX,XX +XXX,XX @@ static ssize_t nbd_co_receive_request(NBDRequestData *req, ssize_t rc; g_assert(qemu_in_coroutine()); - client->recv_coroutine = qemu_coroutine_self(); - nbd_update_can_read(client); - + assert(client->recv_coroutine == qemu_coroutine_self()); rc = nbd_receive_request(client->ioc, request); if (rc < 0) { if (rc != -EAGAIN) { @@ -XXX,XX +XXX,XX @@ static ssize_t nbd_co_receive_request(NBDRequestData *req, out: client->recv_coroutine = NULL; - nbd_update_can_read(client); + nbd_client_receive_next_request(client); return rc; } -static void nbd_trip(void *opaque) +/* Owns a reference to the NBDClient passed as opaque. */ +static coroutine_fn void nbd_trip(void *opaque) { NBDClient *client = opaque; NBDExport *exp = client->exp; NBDRequestData *req; - NBDRequest request; + NBDRequest request = { 0 }; /* GCC thinks it can be used uninitialized */ NBDReply reply; ssize_t ret; int flags; TRACE("Reading request."); if (client->closing) { + nbd_client_put(client); return; } @@ -XXX,XX +XXX,XX @@ static void nbd_trip(void *opaque) done: nbd_request_put(req); + nbd_client_put(client); return; out: nbd_request_put(req); client_close(client); + nbd_client_put(client); } -static void nbd_read(void *opaque) +static void nbd_client_receive_next_request(NBDClient *client) { - NBDClient *client = opaque; - - if (client->recv_coroutine) { - qemu_coroutine_enter(client->recv_coroutine); - } else { - qemu_coroutine_enter(qemu_coroutine_create(nbd_trip, client)); - } -} - -static void nbd_restart_write(void *opaque) -{ - NBDClient *client = opaque; - - qemu_coroutine_enter(client->send_coroutine); -} - -static void nbd_set_handlers(NBDClient *client) -{ - if (client->exp && client->exp->ctx) { - aio_set_fd_handler(client->exp->ctx, client->sioc->fd, true, - client->can_read ? nbd_read : NULL, - client->send_coroutine ? nbd_restart_write : NULL, - NULL, client); - } -} - -static void nbd_unset_handlers(NBDClient *client) -{ - if (client->exp && client->exp->ctx) { - aio_set_fd_handler(client->exp->ctx, client->sioc->fd, true, NULL, - NULL, NULL, NULL); - } -} - -static void nbd_update_can_read(NBDClient *client) -{ - bool can_read = client->recv_coroutine || - client->nb_requests < MAX_NBD_REQUESTS; - - if (can_read != client->can_read) { - client->can_read = can_read; - nbd_set_handlers(client); - - /* There is no need to invoke aio_notify(), since aio_set_fd_handler() - * in nbd_set_handlers() will have taken care of that */ + if (!client->recv_coroutine && client->nb_requests < MAX_NBD_REQUESTS) { + nbd_client_get(client); + client->recv_coroutine = qemu_coroutine_create(nbd_trip, client); + aio_co_schedule(client->exp->ctx, client->recv_coroutine); } } @@ -XXX,XX +XXX,XX @@ static coroutine_fn void nbd_co_client_start(void *opaque) goto out; } qemu_co_mutex_init(&client->send_lock); - nbd_set_handlers(client); if (exp) { QTAILQ_INSERT_TAIL(&exp->clients, client, next); } + + nbd_client_receive_next_request(client); + out: g_free(data); } @@ -XXX,XX +XXX,XX @@ void nbd_client_new(NBDExport *exp, object_ref(OBJECT(client->sioc)); client->ioc = QIO_CHANNEL(sioc); object_ref(OBJECT(client->ioc)); - client->can_read = true; client->close = close_fn; data->client = client; -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> As a small step towards the introduction of multiqueue, we want coroutines to remain on the same AioContext that started them, unless they are moved explicitly with e.g. aio_co_schedule. This patch avoids that coroutines switch AioContext when they use a CoMutex. For now it does not make much of a difference, because the CoMutex is not thread-safe and the AioContext itself is used to protect the CoMutex from concurrent access. However, this is going to change. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-9-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/qemu-coroutine-lock.c | 5 ++--- util/trace-events | 1 - 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/util/qemu-coroutine-lock.c b/util/qemu-coroutine-lock.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine-lock.c +++ b/util/qemu-coroutine-lock.c @@ -XXX,XX +XXX,XX @@ #include "qemu/coroutine.h" #include "qemu/coroutine_int.h" #include "qemu/queue.h" +#include "block/aio.h" #include "trace.h" void qemu_co_queue_init(CoQueue *queue) @@ -XXX,XX +XXX,XX @@ void qemu_co_queue_run_restart(Coroutine *co) static bool qemu_co_queue_do_restart(CoQueue *queue, bool single) { - Coroutine *self = qemu_coroutine_self(); Coroutine *next; if (QSIMPLEQ_EMPTY(&queue->entries)) { @@ -XXX,XX +XXX,XX @@ static bool qemu_co_queue_do_restart(CoQueue *queue, bool single) while ((next = QSIMPLEQ_FIRST(&queue->entries)) != NULL) { QSIMPLEQ_REMOVE_HEAD(&queue->entries, co_queue_next); - QSIMPLEQ_INSERT_TAIL(&self->co_queue_wakeup, next, co_queue_next); - trace_qemu_co_queue_next(next); + aio_co_wake(next); if (single) { break; } diff --git a/util/trace-events b/util/trace-events index XXXXXXX..XXXXXXX 100644 --- a/util/trace-events +++ b/util/trace-events @@ -XXX,XX +XXX,XX @@ qemu_coroutine_terminate(void *co) "self %p" # util/qemu-coroutine-lock.c qemu_co_queue_run_restart(void *co) "co %p" -qemu_co_queue_next(void *nxt) "next %p" qemu_co_mutex_lock_entry(void *mutex, void *self) "mutex %p self %p" qemu_co_mutex_lock_return(void *mutex, void *self) "mutex %p self %p" qemu_co_mutex_unlock_entry(void *mutex, void *self) "mutex %p self %p" -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Keep the coroutine on the same AioContext. Without this change, there would be a race between yielding the coroutine and reentering it. While the race cannot happen now, because the code only runs from a single AioContext, this will change with multiqueue support in the block layer. While doing the change, replace custom bottom half with aio_co_schedule. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-10-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/blkdebug.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/block/blkdebug.c b/block/blkdebug.c index XXXXXXX..XXXXXXX 100644 --- a/block/blkdebug.c +++ b/block/blkdebug.c @@ -XXX,XX +XXX,XX @@ out: return ret; } -static void error_callback_bh(void *opaque) -{ - Coroutine *co = opaque; - qemu_coroutine_enter(co); -} - static int inject_error(BlockDriverState *bs, BlkdebugRule *rule) { BDRVBlkdebugState *s = bs->opaque; @@ -XXX,XX +XXX,XX @@ static int inject_error(BlockDriverState *bs, BlkdebugRule *rule) } if (!immediately) { - aio_bh_schedule_oneshot(bdrv_get_aio_context(bs), error_callback_bh, - qemu_coroutine_self()); + aio_co_schedule(qemu_get_current_aio_context(), qemu_coroutine_self()); qemu_coroutine_yield(); } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> qed_aio_start_io and qed_aio_next_io will not have to acquire/release the AioContext, while qed_aio_next_io_cb will. Split the functionality and gain a little type-safety in the process. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-11-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/qed.c | 39 +++++++++++++++++++++++++-------------- 1 file changed, 25 insertions(+), 14 deletions(-) diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static CachedL2Table *qed_new_l2_table(BDRVQEDState *s) return l2_table; } -static void qed_aio_next_io(void *opaque, int ret); +static void qed_aio_next_io(QEDAIOCB *acb, int ret); + +static void qed_aio_start_io(QEDAIOCB *acb) +{ + qed_aio_next_io(acb, 0); +} + +static void qed_aio_next_io_cb(void *opaque, int ret) +{ + QEDAIOCB *acb = opaque; + + qed_aio_next_io(acb, ret); +} static void qed_plug_allocating_write_reqs(BDRVQEDState *s) { @@ -XXX,XX +XXX,XX @@ static void qed_unplug_allocating_write_reqs(BDRVQEDState *s) acb = QSIMPLEQ_FIRST(&s->allocating_write_reqs); if (acb) { - qed_aio_next_io(acb, 0); + qed_aio_start_io(acb); } } @@ -XXX,XX +XXX,XX @@ static void qed_aio_complete(QEDAIOCB *acb, int ret) QSIMPLEQ_REMOVE_HEAD(&s->allocating_write_reqs, next); acb = QSIMPLEQ_FIRST(&s->allocating_write_reqs); if (acb) { - qed_aio_next_io(acb, 0); + qed_aio_start_io(acb); } else if (s->header.features & QED_F_NEED_CHECK) { qed_start_need_check_timer(s); } @@ -XXX,XX +XXX,XX @@ static void qed_commit_l2_update(void *opaque, int ret) acb->request.l2_table = qed_find_l2_cache_entry(&s->l2_cache, l2_offset); assert(acb->request.l2_table != NULL); - qed_aio_next_io(opaque, ret); + qed_aio_next_io(acb, ret); } /** @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_l2_update(QEDAIOCB *acb, int ret, uint64_t offset) if (need_alloc) { /* Write out the whole new L2 table */ qed_write_l2_table(s, &acb->request, 0, s->table_nelems, true, - qed_aio_write_l1_update, acb); + qed_aio_write_l1_update, acb); } else { /* Write out only the updated part of the L2 table */ qed_write_l2_table(s, &acb->request, index, acb->cur_nclusters, false, - qed_aio_next_io, acb); + qed_aio_next_io_cb, acb); } return; @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_main(void *opaque, int ret) } if (acb->find_cluster_ret == QED_CLUSTER_FOUND) { - next_fn = qed_aio_next_io; + next_fn = qed_aio_next_io_cb; } else { if (s->bs->backing) { next_fn = qed_aio_write_flush_before_l2_update; @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len) if (acb->flags & QED_AIOCB_ZERO) { /* Skip ahead if the clusters are already zero */ if (acb->find_cluster_ret == QED_CLUSTER_ZERO) { - qed_aio_next_io(acb, 0); + qed_aio_start_io(acb); return; } @@ -XXX,XX +XXX,XX @@ static void qed_aio_read_data(void *opaque, int ret, /* Handle zero cluster and backing file reads */ if (ret == QED_CLUSTER_ZERO) { qemu_iovec_memset(&acb->cur_qiov, 0, 0, acb->cur_qiov.size); - qed_aio_next_io(acb, 0); + qed_aio_start_io(acb); return; } else if (ret != QED_CLUSTER_FOUND) { qed_read_backing_file(s, acb->cur_pos, &acb->cur_qiov, - &acb->backing_qiov, qed_aio_next_io, acb); + &acb->backing_qiov, qed_aio_next_io_cb, acb); return; } BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO); bdrv_aio_readv(bs->file, offset / BDRV_SECTOR_SIZE, &acb->cur_qiov, acb->cur_qiov.size / BDRV_SECTOR_SIZE, - qed_aio_next_io, acb); + qed_aio_next_io_cb, acb); return; err: @@ -XXX,XX +XXX,XX @@ err: /** * Begin next I/O or complete the request */ -static void qed_aio_next_io(void *opaque, int ret) +static void qed_aio_next_io(QEDAIOCB *acb, int ret) { - QEDAIOCB *acb = opaque; BDRVQEDState *s = acb_to_s(acb); QEDFindClusterFunc *io_fn = (acb->flags & QED_AIOCB_WRITE) ? qed_aio_write_data : qed_aio_read_data; @@ -XXX,XX +XXX,XX @@ static BlockAIOCB *qed_aio_setup(BlockDriverState *bs, qemu_iovec_init(&acb->cur_qiov, qiov->niov); /* Start request */ - qed_aio_next_io(acb, 0); + qed_aio_start_io(acb); return &acb->common; } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> The AioContext data structures are now protected by list_lock and/or they are walked with FOREACH_RCU primitives. There is no need anymore to acquire the AioContext for the entire duration of aio_dispatch. Instead, just acquire it before and after invoking the callbacks. The next step is then to push it further down. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-12-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/aio-posix.c | 25 +++++++++++-------------- util/aio-win32.c | 15 +++++++-------- util/async.c | 2 ++ 3 files changed, 20 insertions(+), 22 deletions(-) diff --git a/util/aio-posix.c b/util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) && aio_node_check(ctx, node->is_external) && node->io_read) { + aio_context_acquire(ctx); node->io_read(node->opaque); + aio_context_release(ctx); /* aio_notify() does not count as progress */ if (node->opaque != &ctx->notifier) { @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) (revents & (G_IO_OUT | G_IO_ERR)) && aio_node_check(ctx, node->is_external) && node->io_write) { + aio_context_acquire(ctx); node->io_write(node->opaque); + aio_context_release(ctx); progress = true; } @@ -XXX,XX +XXX,XX @@ bool aio_dispatch(AioContext *ctx, bool dispatch_fds) } /* Run our timers */ + aio_context_acquire(ctx); progress |= timerlistgroup_run_timers(&ctx->tlg); + aio_context_release(ctx); return progress; } @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) int64_t timeout; int64_t start = 0; - aio_context_acquire(ctx); - progress = false; - /* aio_notify can avoid the expensive event_notifier_set if * everything (file descriptors, bottom halves, timers) will * be re-evaluated before the next blocking poll(). This is @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) start = qemu_clock_get_ns(QEMU_CLOCK_REALTIME); } - if (try_poll_mode(ctx, blocking)) { - progress = true; - } else { + aio_context_acquire(ctx); + progress = try_poll_mode(ctx, blocking); + aio_context_release(ctx); + + if (!progress) { assert(npfd == 0); /* fill pollfds */ @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) timeout = blocking ? aio_compute_timeout(ctx) : 0; /* wait until next event */ - if (timeout) { - aio_context_release(ctx); - } if (aio_epoll_check_poll(ctx, pollfds, npfd, timeout)) { AioHandler epoll_handler; @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) } else { ret = qemu_poll_ns(pollfds, npfd, timeout); } - if (timeout) { - aio_context_acquire(ctx); - } } if (blocking) { @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) progress = true; } - aio_context_release(ctx); - return progress; } diff --git a/util/aio-win32.c b/util/aio-win32.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-win32.c +++ b/util/aio-win32.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event) (revents || event_notifier_get_handle(node->e) == event) && node->io_notify) { node->pfd.revents = 0; + aio_context_acquire(ctx); node->io_notify(node->e); + aio_context_release(ctx); /* aio_notify() does not count as progress */ if (node->e != &ctx->notifier) { @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event) (node->io_read || node->io_write)) { node->pfd.revents = 0; if ((revents & G_IO_IN) && node->io_read) { + aio_context_acquire(ctx); node->io_read(node->opaque); + aio_context_release(ctx); progress = true; } if ((revents & G_IO_OUT) && node->io_write) { + aio_context_acquire(ctx); node->io_write(node->opaque); + aio_context_release(ctx); progress = true; } @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) int count; int timeout; - aio_context_acquire(ctx); progress = false; /* aio_notify can avoid the expensive event_notifier_set if @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) timeout = blocking && !have_select_revents ? qemu_timeout_ns_to_ms(aio_compute_timeout(ctx)) : 0; - if (timeout) { - aio_context_release(ctx); - } ret = WaitForMultipleObjects(count, events, FALSE, timeout); if (blocking) { assert(first); atomic_sub(&ctx->notify_me, 2); } - if (timeout) { - aio_context_acquire(ctx); - } if (first) { aio_notify_accept(ctx); @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) progress |= aio_dispatch_handlers(ctx, event); } while (count > 0); + aio_context_acquire(ctx); progress |= timerlistgroup_run_timers(&ctx->tlg); - aio_context_release(ctx); return progress; } diff --git a/util/async.c b/util/async.c index XXXXXXX..XXXXXXX 100644 --- a/util/async.c +++ b/util/async.c @@ -XXX,XX +XXX,XX @@ int aio_bh_poll(AioContext *ctx) ret = 1; } bh->idle = 0; + aio_context_acquire(ctx); aio_bh_call(bh); + aio_context_release(ctx); } if (bh->deleted) { deleted = true; -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-13-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/qed.h | 3 +++ block/curl.c | 2 ++ block/io.c | 5 +++++ block/iscsi.c | 8 ++++++-- block/null.c | 4 ++++ block/qed.c | 12 ++++++++++++ block/throttle-groups.c | 2 ++ util/aio-posix.c | 2 -- util/aio-win32.c | 2 -- util/qemu-coroutine-sleep.c | 2 +- 10 files changed, 35 insertions(+), 7 deletions(-) diff --git a/block/qed.h b/block/qed.h index XXXXXXX..XXXXXXX 100644 --- a/block/qed.h +++ b/block/qed.h @@ -XXX,XX +XXX,XX @@ enum { */ typedef void QEDFindClusterFunc(void *opaque, int ret, uint64_t offset, size_t len); +void qed_acquire(BDRVQEDState *s); +void qed_release(BDRVQEDState *s); + /** * Generic callback for chaining async callbacks */ diff --git a/block/curl.c b/block/curl.c index XXXXXXX..XXXXXXX 100644 --- a/block/curl.c +++ b/block/curl.c @@ -XXX,XX +XXX,XX @@ static void curl_multi_timeout_do(void *arg) return; } + aio_context_acquire(s->aio_context); curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running); curl_multi_check_completion(s); + aio_context_release(s->aio_context); #else abort(); #endif diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_aio_cancel(BlockAIOCB *acb) if (acb->aiocb_info->get_aio_context) { aio_poll(acb->aiocb_info->get_aio_context(acb), true); } else if (acb->bs) { + /* qemu_aio_ref and qemu_aio_unref are not thread-safe, so + * assert that we're not using an I/O thread. Thread-safe + * code should use bdrv_aio_cancel_async exclusively. + */ + assert(bdrv_get_aio_context(acb->bs) == qemu_get_aio_context()); aio_poll(bdrv_get_aio_context(acb->bs), true); } else { abort(); diff --git a/block/iscsi.c b/block/iscsi.c index XXXXXXX..XXXXXXX 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -XXX,XX +XXX,XX @@ static void iscsi_retry_timer_expired(void *opaque) struct IscsiTask *iTask = opaque; iTask->complete = 1; if (iTask->co) { - qemu_coroutine_enter(iTask->co); + aio_co_wake(iTask->co); } } @@ -XXX,XX +XXX,XX @@ static void iscsi_nop_timed_event(void *opaque) { IscsiLun *iscsilun = opaque; + aio_context_acquire(iscsilun->aio_context); if (iscsi_get_nops_in_flight(iscsilun->iscsi) >= MAX_NOP_FAILURES) { error_report("iSCSI: NOP timeout. Reconnecting..."); iscsilun->request_timed_out = true; } else if (iscsi_nop_out_async(iscsilun->iscsi, NULL, NULL, 0, NULL) != 0) { error_report("iSCSI: failed to sent NOP-Out. Disabling NOP messages."); - return; + goto out; } timer_mod(iscsilun->nop_timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + NOP_INTERVAL); iscsi_set_events(iscsilun); + +out: + aio_context_release(iscsilun->aio_context); } static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp) diff --git a/block/null.c b/block/null.c index XXXXXXX..XXXXXXX 100644 --- a/block/null.c +++ b/block/null.c @@ -XXX,XX +XXX,XX @@ static void null_bh_cb(void *opaque) static void null_timer_cb(void *opaque) { NullAIOCB *acb = opaque; + AioContext *ctx = bdrv_get_aio_context(acb->common.bs); + + aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, 0); + aio_context_release(ctx); timer_deinit(&acb->timer); qemu_aio_unref(acb); } diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static void qed_need_check_timer_cb(void *opaque) trace_qed_need_check_timer_cb(s); + qed_acquire(s); qed_plug_allocating_write_reqs(s); /* Ensure writes are on disk before clearing flag */ bdrv_aio_flush(s->bs->file->bs, qed_clear_need_check, s); + qed_release(s); +} + +void qed_acquire(BDRVQEDState *s) +{ + aio_context_acquire(bdrv_get_aio_context(s->bs)); +} + +void qed_release(BDRVQEDState *s) +{ + aio_context_release(bdrv_get_aio_context(s->bs)); } static void qed_start_need_check_timer(BDRVQEDState *s) diff --git a/block/throttle-groups.c b/block/throttle-groups.c index XXXXXXX..XXXXXXX 100644 --- a/block/throttle-groups.c +++ b/block/throttle-groups.c @@ -XXX,XX +XXX,XX @@ static void timer_cb(BlockBackend *blk, bool is_write) qemu_mutex_unlock(&tg->lock); /* Run the request that was waiting for this timer */ + aio_context_acquire(blk_get_aio_context(blk)); empty_queue = !qemu_co_enter_next(&blkp->throttled_reqs[is_write]); + aio_context_release(blk_get_aio_context(blk)); /* If the request queue was empty then we have to take care of * scheduling the next one */ diff --git a/util/aio-posix.c b/util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ bool aio_dispatch(AioContext *ctx, bool dispatch_fds) } /* Run our timers */ - aio_context_acquire(ctx); progress |= timerlistgroup_run_timers(&ctx->tlg); - aio_context_release(ctx); return progress; } diff --git a/util/aio-win32.c b/util/aio-win32.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-win32.c +++ b/util/aio-win32.c @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) progress |= aio_dispatch_handlers(ctx, event); } while (count > 0); - aio_context_acquire(ctx); progress |= timerlistgroup_run_timers(&ctx->tlg); - aio_context_release(ctx); return progress; } diff --git a/util/qemu-coroutine-sleep.c b/util/qemu-coroutine-sleep.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine-sleep.c +++ b/util/qemu-coroutine-sleep.c @@ -XXX,XX +XXX,XX @@ static void co_sleep_cb(void *opaque) { CoSleepCB *sleep_cb = opaque; - qemu_coroutine_enter(sleep_cb->co); + aio_co_wake(sleep_cb->co); } void coroutine_fn co_aio_sleep_ns(AioContext *ctx, QEMUClockType type, -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> This covers both file descriptor callbacks and polling callbacks, since they execute related code. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-14-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/curl.c | 16 +++++++++++++--- block/iscsi.c | 4 ++++ block/linux-aio.c | 4 ++++ block/nfs.c | 6 ++++++ block/sheepdog.c | 29 +++++++++++++++-------------- block/ssh.c | 29 +++++++++-------------------- block/win32-aio.c | 10 ++++++---- hw/block/virtio-blk.c | 5 ++++- hw/scsi/virtio-scsi.c | 7 +++++++ util/aio-posix.c | 7 ------- util/aio-win32.c | 6 ------ 11 files changed, 68 insertions(+), 55 deletions(-) diff --git a/block/curl.c b/block/curl.c index XXXXXXX..XXXXXXX 100644 --- a/block/curl.c +++ b/block/curl.c @@ -XXX,XX +XXX,XX @@ static void curl_multi_check_completion(BDRVCURLState *s) } } -static void curl_multi_do(void *arg) +static void curl_multi_do_locked(CURLState *s) { - CURLState *s = (CURLState *)arg; CURLSocket *socket, *next_socket; int running; int r; @@ -XXX,XX +XXX,XX @@ static void curl_multi_do(void *arg) } } +static void curl_multi_do(void *arg) +{ + CURLState *s = (CURLState *)arg; + + aio_context_acquire(s->s->aio_context); + curl_multi_do_locked(s); + aio_context_release(s->s->aio_context); +} + static void curl_multi_read(void *arg) { CURLState *s = (CURLState *)arg; - curl_multi_do(arg); + aio_context_acquire(s->s->aio_context); + curl_multi_do_locked(s); curl_multi_check_completion(s->s); + aio_context_release(s->s->aio_context); } static void curl_multi_timeout_do(void *arg) diff --git a/block/iscsi.c b/block/iscsi.c index XXXXXXX..XXXXXXX 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -XXX,XX +XXX,XX @@ iscsi_process_read(void *arg) IscsiLun *iscsilun = arg; struct iscsi_context *iscsi = iscsilun->iscsi; + aio_context_acquire(iscsilun->aio_context); iscsi_service(iscsi, POLLIN); iscsi_set_events(iscsilun); + aio_context_release(iscsilun->aio_context); } static void @@ -XXX,XX +XXX,XX @@ iscsi_process_write(void *arg) IscsiLun *iscsilun = arg; struct iscsi_context *iscsi = iscsilun->iscsi; + aio_context_acquire(iscsilun->aio_context); iscsi_service(iscsi, POLLOUT); iscsi_set_events(iscsilun); + aio_context_release(iscsilun->aio_context); } static int64_t sector_lun2qemu(int64_t sector, IscsiLun *iscsilun) diff --git a/block/linux-aio.c b/block/linux-aio.c index XXXXXXX..XXXXXXX 100644 --- a/block/linux-aio.c +++ b/block/linux-aio.c @@ -XXX,XX +XXX,XX @@ static void qemu_laio_completion_cb(EventNotifier *e) LinuxAioState *s = container_of(e, LinuxAioState, e); if (event_notifier_test_and_clear(&s->e)) { + aio_context_acquire(s->aio_context); qemu_laio_process_completions_and_submit(s); + aio_context_release(s->aio_context); } } @@ -XXX,XX +XXX,XX @@ static bool qemu_laio_poll_cb(void *opaque) return false; } + aio_context_acquire(s->aio_context); qemu_laio_process_completions_and_submit(s); + aio_context_release(s->aio_context); return true; } diff --git a/block/nfs.c b/block/nfs.c index XXXXXXX..XXXXXXX 100644 --- a/block/nfs.c +++ b/block/nfs.c @@ -XXX,XX +XXX,XX @@ static void nfs_set_events(NFSClient *client) static void nfs_process_read(void *arg) { NFSClient *client = arg; + + aio_context_acquire(client->aio_context); nfs_service(client->context, POLLIN); nfs_set_events(client); + aio_context_release(client->aio_context); } static void nfs_process_write(void *arg) { NFSClient *client = arg; + + aio_context_acquire(client->aio_context); nfs_service(client->context, POLLOUT); nfs_set_events(client); + aio_context_release(client->aio_context); } static void nfs_co_init_task(BlockDriverState *bs, NFSRPC *task) diff --git a/block/sheepdog.c b/block/sheepdog.c index XXXXXXX..XXXXXXX 100644 --- a/block/sheepdog.c +++ b/block/sheepdog.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int send_co_req(int sockfd, SheepdogReq *hdr, void *data, return ret; } -static void restart_co_req(void *opaque) -{ - Coroutine *co = opaque; - - qemu_coroutine_enter(co); -} - typedef struct SheepdogReqCo { int sockfd; BlockDriverState *bs; @@ -XXX,XX +XXX,XX @@ typedef struct SheepdogReqCo { unsigned int *rlen; int ret; bool finished; + Coroutine *co; } SheepdogReqCo; +static void restart_co_req(void *opaque) +{ + SheepdogReqCo *srco = opaque; + + aio_co_wake(srco->co); +} + static coroutine_fn void do_co_req(void *opaque) { int ret; - Coroutine *co; SheepdogReqCo *srco = opaque; int sockfd = srco->sockfd; SheepdogReq *hdr = srco->hdr; @@ -XXX,XX +XXX,XX @@ static coroutine_fn void do_co_req(void *opaque) unsigned int *wlen = srco->wlen; unsigned int *rlen = srco->rlen; - co = qemu_coroutine_self(); + srco->co = qemu_coroutine_self(); aio_set_fd_handler(srco->aio_context, sockfd, false, - NULL, restart_co_req, NULL, co); + NULL, restart_co_req, NULL, srco); ret = send_co_req(sockfd, hdr, data, wlen); if (ret < 0) { @@ -XXX,XX +XXX,XX @@ static coroutine_fn void do_co_req(void *opaque) } aio_set_fd_handler(srco->aio_context, sockfd, false, - restart_co_req, NULL, NULL, co); + restart_co_req, NULL, NULL, srco); ret = qemu_co_recv(sockfd, hdr, sizeof(*hdr)); if (ret != sizeof(*hdr)) { @@ -XXX,XX +XXX,XX @@ out: aio_set_fd_handler(srco->aio_context, sockfd, false, NULL, NULL, NULL, NULL); + srco->co = NULL; srco->ret = ret; srco->finished = true; if (srco->bs) { @@ -XXX,XX +XXX,XX @@ static void coroutine_fn aio_read_response(void *opaque) * We've finished all requests which belong to the AIOCB, so * we can switch back to sd_co_readv/writev now. */ - qemu_coroutine_enter(acb->coroutine); + aio_co_wake(acb->coroutine); } return; @@ -XXX,XX +XXX,XX @@ static void co_read_response(void *opaque) s->co_recv = qemu_coroutine_create(aio_read_response, opaque); } - qemu_coroutine_enter(s->co_recv); + aio_co_wake(s->co_recv); } static void co_write_request(void *opaque) { BDRVSheepdogState *s = opaque; - qemu_coroutine_enter(s->co_send); + aio_co_wake(s->co_send); } /* diff --git a/block/ssh.c b/block/ssh.c index XXXXXXX..XXXXXXX 100644 --- a/block/ssh.c +++ b/block/ssh.c @@ -XXX,XX +XXX,XX @@ static void restart_coroutine(void *opaque) DPRINTF("co=%p", co); - qemu_coroutine_enter(co); + aio_co_wake(co); } -static coroutine_fn void set_fd_handler(BDRVSSHState *s, BlockDriverState *bs) +/* A non-blocking call returned EAGAIN, so yield, ensuring the + * handlers are set up so that we'll be rescheduled when there is an + * interesting event on the socket. + */ +static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs) { int r; IOHandler *rd_handler = NULL, *wr_handler = NULL; @@ -XXX,XX +XXX,XX @@ static coroutine_fn void set_fd_handler(BDRVSSHState *s, BlockDriverState *bs) aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock, false, rd_handler, wr_handler, NULL, co); -} - -static coroutine_fn void clear_fd_handler(BDRVSSHState *s, - BlockDriverState *bs) -{ - DPRINTF("s->sock=%d", s->sock); - aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock, - false, NULL, NULL, NULL, NULL); -} - -/* A non-blocking call returned EAGAIN, so yield, ensuring the - * handlers are set up so that we'll be rescheduled when there is an - * interesting event on the socket. - */ -static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs) -{ - set_fd_handler(s, bs); qemu_coroutine_yield(); - clear_fd_handler(s, bs); + DPRINTF("s->sock=%d - back", s->sock); + aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock, false, + NULL, NULL, NULL, NULL); } /* SFTP has a function `libssh2_sftp_seek64' which seeks to a position diff --git a/block/win32-aio.c b/block/win32-aio.c index XXXXXXX..XXXXXXX 100644 --- a/block/win32-aio.c +++ b/block/win32-aio.c @@ -XXX,XX +XXX,XX @@ struct QEMUWin32AIOState { HANDLE hIOCP; EventNotifier e; int count; - bool is_aio_context_attached; + AioContext *aio_ctx; }; typedef struct QEMUWin32AIOCB { @@ -XXX,XX +XXX,XX @@ static void win32_aio_process_completion(QEMUWin32AIOState *s, } + aio_context_acquire(s->aio_ctx); waiocb->common.cb(waiocb->common.opaque, ret); + aio_context_release(s->aio_ctx); qemu_aio_unref(waiocb); } @@ -XXX,XX +XXX,XX @@ void win32_aio_detach_aio_context(QEMUWin32AIOState *aio, AioContext *old_context) { aio_set_event_notifier(old_context, &aio->e, false, NULL, NULL); - aio->is_aio_context_attached = false; + aio->aio_ctx = NULL; } void win32_aio_attach_aio_context(QEMUWin32AIOState *aio, AioContext *new_context) { - aio->is_aio_context_attached = true; + aio->aio_ctx = new_context; aio_set_event_notifier(new_context, &aio->e, false, win32_aio_completion_cb, NULL); } @@ -XXX,XX +XXX,XX @@ out_free_state: void win32_aio_cleanup(QEMUWin32AIOState *aio) { - assert(!aio->is_aio_context_attached); + assert(!aio->aio_ctx); CloseHandle(aio->hIOCP); event_notifier_cleanup(&aio->e); g_free(aio); diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ static void virtio_blk_ioctl_complete(void *opaque, int status) { VirtIOBlockIoctlReq *ioctl_req = opaque; VirtIOBlockReq *req = ioctl_req->req; - VirtIODevice *vdev = VIRTIO_DEVICE(req->dev); + VirtIOBlock *s = req->dev; + VirtIODevice *vdev = VIRTIO_DEVICE(s); struct virtio_scsi_inhdr *scsi; struct sg_io_hdr *hdr; @@ -XXX,XX +XXX,XX @@ bool virtio_blk_handle_vq(VirtIOBlock *s, VirtQueue *vq) MultiReqBuffer mrb = {}; bool progress = false; + aio_context_acquire(blk_get_aio_context(s->blk)); blk_io_plug(s->blk); do { @@ -XXX,XX +XXX,XX @@ bool virtio_blk_handle_vq(VirtIOBlock *s, VirtQueue *vq) } blk_io_unplug(s->blk); + aio_context_release(blk_get_aio_context(s->blk)); return progress; } diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/scsi/virtio-scsi.c +++ b/hw/scsi/virtio-scsi.c @@ -XXX,XX +XXX,XX @@ bool virtio_scsi_handle_ctrl_vq(VirtIOSCSI *s, VirtQueue *vq) VirtIOSCSIReq *req; bool progress = false; + virtio_scsi_acquire(s); while ((req = virtio_scsi_pop_req(s, vq))) { progress = true; virtio_scsi_handle_ctrl_req(s, req); } + virtio_scsi_release(s); return progress; } @@ -XXX,XX +XXX,XX @@ bool virtio_scsi_handle_cmd_vq(VirtIOSCSI *s, VirtQueue *vq) QTAILQ_HEAD(, VirtIOSCSIReq) reqs = QTAILQ_HEAD_INITIALIZER(reqs); + virtio_scsi_acquire(s); do { virtio_queue_set_notification(vq, 0); @@ -XXX,XX +XXX,XX @@ bool virtio_scsi_handle_cmd_vq(VirtIOSCSI *s, VirtQueue *vq) QTAILQ_FOREACH_SAFE(req, &reqs, next, next) { virtio_scsi_handle_cmd_req_submit(s, req); } + virtio_scsi_release(s); return progress; } @@ -XXX,XX +XXX,XX @@ out: bool virtio_scsi_handle_event_vq(VirtIOSCSI *s, VirtQueue *vq) { + virtio_scsi_acquire(s); if (s->events_dropped) { virtio_scsi_push_event(s, NULL, VIRTIO_SCSI_T_NO_EVENT, 0); + virtio_scsi_release(s); return true; } + virtio_scsi_release(s); return false; } diff --git a/util/aio-posix.c b/util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) && aio_node_check(ctx, node->is_external) && node->io_read) { - aio_context_acquire(ctx); node->io_read(node->opaque); - aio_context_release(ctx); /* aio_notify() does not count as progress */ if (node->opaque != &ctx->notifier) { @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) (revents & (G_IO_OUT | G_IO_ERR)) && aio_node_check(ctx, node->is_external) && node->io_write) { - aio_context_acquire(ctx); node->io_write(node->opaque); - aio_context_release(ctx); progress = true; } @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) start = qemu_clock_get_ns(QEMU_CLOCK_REALTIME); } - aio_context_acquire(ctx); progress = try_poll_mode(ctx, blocking); - aio_context_release(ctx); - if (!progress) { assert(npfd == 0); diff --git a/util/aio-win32.c b/util/aio-win32.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-win32.c +++ b/util/aio-win32.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event) (revents || event_notifier_get_handle(node->e) == event) && node->io_notify) { node->pfd.revents = 0; - aio_context_acquire(ctx); node->io_notify(node->e); - aio_context_release(ctx); /* aio_notify() does not count as progress */ if (node->e != &ctx->notifier) { @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event) (node->io_read || node->io_write)) { node->pfd.revents = 0; if ((revents & G_IO_IN) && node->io_read) { - aio_context_acquire(ctx); node->io_read(node->opaque); - aio_context_release(ctx); progress = true; } if ((revents & G_IO_OUT) && node->io_write) { - aio_context_acquire(ctx); node->io_write(node->opaque); - aio_context_release(ctx); progress = true; } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-15-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/archipelago.c | 3 +++ block/blkreplay.c | 2 +- block/block-backend.c | 6 ++++++ block/curl.c | 26 ++++++++++++++++++-------- block/gluster.c | 9 +-------- block/io.c | 6 +++++- block/iscsi.c | 6 +++++- block/linux-aio.c | 15 +++++++++------ block/nfs.c | 3 ++- block/null.c | 4 ++++ block/qed.c | 3 +++ block/rbd.c | 4 ++++ dma-helpers.c | 2 ++ hw/block/virtio-blk.c | 2 ++ hw/scsi/scsi-bus.c | 2 ++ util/async.c | 4 ++-- util/thread-pool.c | 2 ++ 17 files changed, 71 insertions(+), 28 deletions(-) diff --git a/block/archipelago.c b/block/archipelago.c index XXXXXXX..XXXXXXX 100644 --- a/block/archipelago.c +++ b/block/archipelago.c @@ -XXX,XX +XXX,XX @@ static void qemu_archipelago_complete_aio(void *opaque) { AIORequestData *reqdata = (AIORequestData *) opaque; ArchipelagoAIOCB *aio_cb = (ArchipelagoAIOCB *) reqdata->aio_cb; + AioContext *ctx = bdrv_get_aio_context(aio_cb->common.bs); + aio_context_acquire(ctx); aio_cb->common.cb(aio_cb->common.opaque, aio_cb->ret); + aio_context_release(ctx); aio_cb->status = 0; qemu_aio_unref(aio_cb); diff --git a/block/blkreplay.c b/block/blkreplay.c index XXXXXXX..XXXXXXX 100755 --- a/block/blkreplay.c +++ b/block/blkreplay.c @@ -XXX,XX +XXX,XX @@ static int64_t blkreplay_getlength(BlockDriverState *bs) static void blkreplay_bh_cb(void *opaque) { Request *req = opaque; - qemu_coroutine_enter(req->co); + aio_co_wake(req->co); qemu_bh_delete(req->bh); g_free(req); } diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags) static void error_callback_bh(void *opaque) { struct BlockBackendAIOCB *acb = opaque; + AioContext *ctx = bdrv_get_aio_context(acb->common.bs); bdrv_dec_in_flight(acb->common.bs); + aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, acb->ret); + aio_context_release(ctx); qemu_aio_unref(acb); } @@ -XXX,XX +XXX,XX @@ static void blk_aio_complete(BlkAioEmAIOCB *acb) static void blk_aio_complete_bh(void *opaque) { BlkAioEmAIOCB *acb = opaque; + AioContext *ctx = bdrv_get_aio_context(acb->common.bs); assert(acb->has_returned); + aio_context_acquire(ctx); blk_aio_complete(acb); + aio_context_release(ctx); } static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, int bytes, diff --git a/block/curl.c b/block/curl.c index XXXXXXX..XXXXXXX 100644 --- a/block/curl.c +++ b/block/curl.c @@ -XXX,XX +XXX,XX @@ static void curl_readv_bh_cb(void *p) { CURLState *state; int running; + int ret = -EINPROGRESS; CURLAIOCB *acb = p; - BDRVCURLState *s = acb->common.bs->opaque; + BlockDriverState *bs = acb->common.bs; + BDRVCURLState *s = bs->opaque; + AioContext *ctx = bdrv_get_aio_context(bs); size_t start = acb->sector_num * BDRV_SECTOR_SIZE; size_t end; + aio_context_acquire(ctx); + // In case we have the requested data already (e.g. read-ahead), // we can just call the callback and be done. switch (curl_find_buf(s, start, acb->nb_sectors * BDRV_SECTOR_SIZE, acb)) { @@ -XXX,XX +XXX,XX @@ static void curl_readv_bh_cb(void *p) qemu_aio_unref(acb); // fall through case FIND_RET_WAIT: - return; + goto out; default: break; } @@ -XXX,XX +XXX,XX @@ static void curl_readv_bh_cb(void *p) // No cache found, so let's start a new request state = curl_init_state(acb->common.bs, s); if (!state) { - acb->common.cb(acb->common.opaque, -EIO); - qemu_aio_unref(acb); - return; + ret = -EIO; + goto out; } acb->start = 0; @@ -XXX,XX +XXX,XX @@ static void curl_readv_bh_cb(void *p) state->orig_buf = g_try_malloc(state->buf_len); if (state->buf_len && state->orig_buf == NULL) { curl_clean_state(state); - acb->common.cb(acb->common.opaque, -ENOMEM); - qemu_aio_unref(acb); - return; + ret = -ENOMEM; + goto out; } state->acb[0] = acb; @@ -XXX,XX +XXX,XX @@ static void curl_readv_bh_cb(void *p) /* Tell curl it needs to kick things off */ curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running); + +out: + if (ret != -EINPROGRESS) { + acb->common.cb(acb->common.opaque, ret); + qemu_aio_unref(acb); + } + aio_context_release(ctx); } static BlockAIOCB *curl_aio_readv(BlockDriverState *bs, diff --git a/block/gluster.c b/block/gluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/gluster.c +++ b/block/gluster.c @@ -XXX,XX +XXX,XX @@ static struct glfs *qemu_gluster_init(BlockdevOptionsGluster *gconf, return qemu_gluster_glfs_init(gconf, errp); } -static void qemu_gluster_complete_aio(void *opaque) -{ - GlusterAIOCB *acb = (GlusterAIOCB *)opaque; - - qemu_coroutine_enter(acb->coroutine); -} - /* * AIO callback routine called from GlusterFS thread. */ @@ -XXX,XX +XXX,XX @@ static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg) acb->ret = -EIO; /* Partial read/write - fail it */ } - aio_bh_schedule_oneshot(acb->aio_context, qemu_gluster_complete_aio, acb); + aio_co_schedule(acb->aio_context, acb->coroutine); } static void qemu_gluster_parse_flags(int bdrv_flags, int *open_flags) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void bdrv_co_drain_bh_cb(void *opaque) bdrv_dec_in_flight(bs); bdrv_drained_begin(bs); data->done = true; - qemu_coroutine_enter(co); + aio_co_wake(co); } static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs) @@ -XXX,XX +XXX,XX @@ static void bdrv_co_complete(BlockAIOCBCoroutine *acb) static void bdrv_co_em_bh(void *opaque) { BlockAIOCBCoroutine *acb = opaque; + BlockDriverState *bs = acb->common.bs; + AioContext *ctx = bdrv_get_aio_context(bs); assert(!acb->need_bh); + aio_context_acquire(ctx); bdrv_co_complete(acb); + aio_context_release(ctx); } static void bdrv_co_maybe_schedule_bh(BlockAIOCBCoroutine *acb) diff --git a/block/iscsi.c b/block/iscsi.c index XXXXXXX..XXXXXXX 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -XXX,XX +XXX,XX @@ static void iscsi_bh_cb(void *p) { IscsiAIOCB *acb = p; + AioContext *ctx = bdrv_get_aio_context(acb->common.bs); qemu_bh_delete(acb->bh); g_free(acb->buf); acb->buf = NULL; + aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, acb->status); + aio_context_release(ctx); if (acb->task != NULL) { scsi_free_scsi_task(acb->task); @@ -XXX,XX +XXX,XX @@ iscsi_schedule_bh(IscsiAIOCB *acb) static void iscsi_co_generic_bh_cb(void *opaque) { struct IscsiTask *iTask = opaque; + iTask->complete = 1; - qemu_coroutine_enter(iTask->co); + aio_co_wake(iTask->co); } static void iscsi_retry_timer_expired(void *opaque) diff --git a/block/linux-aio.c b/block/linux-aio.c index XXXXXXX..XXXXXXX 100644 --- a/block/linux-aio.c +++ b/block/linux-aio.c @@ -XXX,XX +XXX,XX @@ struct LinuxAioState { io_context_t ctx; EventNotifier e; - /* io queue for submit at batch */ + /* io queue for submit at batch. Protected by AioContext lock. */ LaioQueue io_q; - /* I/O completion processing */ + /* I/O completion processing. Only runs in I/O thread. */ QEMUBH *completion_bh; int event_idx; int event_max; @@ -XXX,XX +XXX,XX @@ static inline ssize_t io_event_ret(struct io_event *ev) */ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb) { + LinuxAioState *s = laiocb->ctx; int ret; ret = laiocb->ret; @@ -XXX,XX +XXX,XX @@ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb) } laiocb->ret = ret; + aio_context_acquire(s->aio_context); if (laiocb->co) { /* If the coroutine is already entered it must be in ioq_submit() and * will notice laio->ret has been filled in when it eventually runs @@ -XXX,XX +XXX,XX @@ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb) laiocb->common.cb(laiocb->common.opaque, ret); qemu_aio_unref(laiocb); } + aio_context_release(s->aio_context); } /** @@ -XXX,XX +XXX,XX @@ static void qemu_laio_process_completions(LinuxAioState *s) static void qemu_laio_process_completions_and_submit(LinuxAioState *s) { qemu_laio_process_completions(s); + + aio_context_acquire(s->aio_context); if (!s->io_q.plugged && !QSIMPLEQ_EMPTY(&s->io_q.pending)) { ioq_submit(s); } + aio_context_release(s->aio_context); } static void qemu_laio_completion_bh(void *opaque) @@ -XXX,XX +XXX,XX @@ static void qemu_laio_completion_cb(EventNotifier *e) LinuxAioState *s = container_of(e, LinuxAioState, e); if (event_notifier_test_and_clear(&s->e)) { - aio_context_acquire(s->aio_context); qemu_laio_process_completions_and_submit(s); - aio_context_release(s->aio_context); } } @@ -XXX,XX +XXX,XX @@ static bool qemu_laio_poll_cb(void *opaque) return false; } - aio_context_acquire(s->aio_context); qemu_laio_process_completions_and_submit(s); - aio_context_release(s->aio_context); return true; } @@ -XXX,XX +XXX,XX @@ void laio_detach_aio_context(LinuxAioState *s, AioContext *old_context) { aio_set_event_notifier(old_context, &s->e, false, NULL, NULL); qemu_bh_delete(s->completion_bh); + s->aio_context = NULL; } void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context) diff --git a/block/nfs.c b/block/nfs.c index XXXXXXX..XXXXXXX 100644 --- a/block/nfs.c +++ b/block/nfs.c @@ -XXX,XX +XXX,XX @@ static void nfs_co_init_task(BlockDriverState *bs, NFSRPC *task) static void nfs_co_generic_bh_cb(void *opaque) { NFSRPC *task = opaque; + task->complete = 1; - qemu_coroutine_enter(task->co); + aio_co_wake(task->co); } static void diff --git a/block/null.c b/block/null.c index XXXXXXX..XXXXXXX 100644 --- a/block/null.c +++ b/block/null.c @@ -XXX,XX +XXX,XX @@ static const AIOCBInfo null_aiocb_info = { static void null_bh_cb(void *opaque) { NullAIOCB *acb = opaque; + AioContext *ctx = bdrv_get_aio_context(acb->common.bs); + + aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, 0); + aio_context_release(ctx); qemu_aio_unref(acb); } diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static void qed_update_l2_table(BDRVQEDState *s, QEDTable *table, int index, static void qed_aio_complete_bh(void *opaque) { QEDAIOCB *acb = opaque; + BDRVQEDState *s = acb_to_s(acb); BlockCompletionFunc *cb = acb->common.cb; void *user_opaque = acb->common.opaque; int ret = acb->bh_ret; @@ -XXX,XX +XXX,XX @@ static void qed_aio_complete_bh(void *opaque) qemu_aio_unref(acb); /* Invoke callback */ + qed_acquire(s); cb(user_opaque, ret); + qed_release(s); } static void qed_aio_complete(QEDAIOCB *acb, int ret) diff --git a/block/rbd.c b/block/rbd.c index XXXXXXX..XXXXXXX 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -XXX,XX +XXX,XX @@ shutdown: static void qemu_rbd_complete_aio(RADOSCB *rcb) { RBDAIOCB *acb = rcb->acb; + AioContext *ctx = bdrv_get_aio_context(acb->common.bs); int64_t r; r = rcb->ret; @@ -XXX,XX +XXX,XX @@ static void qemu_rbd_complete_aio(RADOSCB *rcb) qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size); } qemu_vfree(acb->bounce); + + aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret)); + aio_context_release(ctx); qemu_aio_unref(acb); } diff --git a/dma-helpers.c b/dma-helpers.c index XXXXXXX..XXXXXXX 100644 --- a/dma-helpers.c +++ b/dma-helpers.c @@ -XXX,XX +XXX,XX @@ static void dma_blk_cb(void *opaque, int ret) QEMU_ALIGN_DOWN(dbs->iov.size, dbs->align)); } + aio_context_acquire(dbs->ctx); dbs->acb = dbs->io_func(dbs->offset, &dbs->iov, dma_blk_cb, dbs, dbs->io_func_opaque); + aio_context_release(dbs->ctx); assert(dbs->acb); } diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ static void virtio_blk_dma_restart_bh(void *opaque) s->rq = NULL; + aio_context_acquire(blk_get_aio_context(s->conf.conf.blk)); while (req) { VirtIOBlockReq *next = req->next; if (virtio_blk_handle_request(req, &mrb)) { @@ -XXX,XX +XXX,XX @@ static void virtio_blk_dma_restart_bh(void *opaque) if (mrb.num_reqs) { virtio_blk_submit_multireq(s->blk, &mrb); } + aio_context_release(blk_get_aio_context(s->conf.conf.blk)); } static void virtio_blk_dma_restart_cb(void *opaque, int running, diff --git a/hw/scsi/scsi-bus.c b/hw/scsi/scsi-bus.c index XXXXXXX..XXXXXXX 100644 --- a/hw/scsi/scsi-bus.c +++ b/hw/scsi/scsi-bus.c @@ -XXX,XX +XXX,XX @@ static void scsi_dma_restart_bh(void *opaque) qemu_bh_delete(s->bh); s->bh = NULL; + aio_context_acquire(blk_get_aio_context(s->conf.blk)); QTAILQ_FOREACH_SAFE(req, &s->requests, next, next) { scsi_req_ref(req); if (req->retry) { @@ -XXX,XX +XXX,XX @@ static void scsi_dma_restart_bh(void *opaque) } scsi_req_unref(req); } + aio_context_release(blk_get_aio_context(s->conf.blk)); } void scsi_req_retry(SCSIRequest *req) diff --git a/util/async.c b/util/async.c index XXXXXXX..XXXXXXX 100644 --- a/util/async.c +++ b/util/async.c @@ -XXX,XX +XXX,XX @@ int aio_bh_poll(AioContext *ctx) ret = 1; } bh->idle = 0; - aio_context_acquire(ctx); aio_bh_call(bh); - aio_context_release(ctx); } if (bh->deleted) { deleted = true; @@ -XXX,XX +XXX,XX @@ static void co_schedule_bh_cb(void *opaque) Coroutine *co = QSLIST_FIRST(&straight); QSLIST_REMOVE_HEAD(&straight, co_scheduled_next); trace_aio_co_schedule_bh_cb(ctx, co); + aio_context_acquire(ctx); qemu_coroutine_enter(co); + aio_context_release(ctx); } } diff --git a/util/thread-pool.c b/util/thread-pool.c index XXXXXXX..XXXXXXX 100644 --- a/util/thread-pool.c +++ b/util/thread-pool.c @@ -XXX,XX +XXX,XX @@ static void thread_pool_completion_bh(void *opaque) ThreadPool *pool = opaque; ThreadPoolElement *elem, *next; + aio_context_acquire(pool->ctx); restart: QLIST_FOREACH_SAFE(elem, &pool->head, all, next) { if (elem->state != THREAD_DONE) { @@ -XXX,XX +XXX,XX @@ restart: qemu_aio_unref(elem); } } + aio_context_release(pool->ctx); } static void thread_pool_cancel(BlockAIOCB *acb) -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-16-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/archipelago.c | 3 --- block/block-backend.c | 7 ------- block/curl.c | 2 +- block/io.c | 6 +----- block/iscsi.c | 3 --- block/linux-aio.c | 5 +---- block/mirror.c | 12 +++++++++--- block/null.c | 8 -------- block/qed-cluster.c | 2 ++ block/qed-table.c | 12 ++++++++++-- block/qed.c | 4 ++-- block/rbd.c | 4 ---- block/win32-aio.c | 3 --- hw/block/virtio-blk.c | 12 +++++++++++- hw/scsi/scsi-disk.c | 15 +++++++++++++++ hw/scsi/scsi-generic.c | 20 +++++++++++++++++--- util/thread-pool.c | 4 +++- 17 files changed, 72 insertions(+), 50 deletions(-) diff --git a/block/archipelago.c b/block/archipelago.c index XXXXXXX..XXXXXXX 100644 --- a/block/archipelago.c +++ b/block/archipelago.c @@ -XXX,XX +XXX,XX @@ static void qemu_archipelago_complete_aio(void *opaque) { AIORequestData *reqdata = (AIORequestData *) opaque; ArchipelagoAIOCB *aio_cb = (ArchipelagoAIOCB *) reqdata->aio_cb; - AioContext *ctx = bdrv_get_aio_context(aio_cb->common.bs); - aio_context_acquire(ctx); aio_cb->common.cb(aio_cb->common.opaque, aio_cb->ret); - aio_context_release(ctx); aio_cb->status = 0; qemu_aio_unref(aio_cb); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags) static void error_callback_bh(void *opaque) { struct BlockBackendAIOCB *acb = opaque; - AioContext *ctx = bdrv_get_aio_context(acb->common.bs); bdrv_dec_in_flight(acb->common.bs); - aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, acb->ret); - aio_context_release(ctx); qemu_aio_unref(acb); } @@ -XXX,XX +XXX,XX @@ static void blk_aio_complete(BlkAioEmAIOCB *acb) static void blk_aio_complete_bh(void *opaque) { BlkAioEmAIOCB *acb = opaque; - AioContext *ctx = bdrv_get_aio_context(acb->common.bs); - assert(acb->has_returned); - aio_context_acquire(ctx); blk_aio_complete(acb); - aio_context_release(ctx); } static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, int bytes, diff --git a/block/curl.c b/block/curl.c index XXXXXXX..XXXXXXX 100644 --- a/block/curl.c +++ b/block/curl.c @@ -XXX,XX +XXX,XX @@ static void curl_readv_bh_cb(void *p) curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running); out: + aio_context_release(ctx); if (ret != -EINPROGRESS) { acb->common.cb(acb->common.opaque, ret); qemu_aio_unref(acb); } - aio_context_release(ctx); } static BlockAIOCB *curl_aio_readv(BlockDriverState *bs, diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void bdrv_co_io_em_complete(void *opaque, int ret) CoroutineIOCompletion *co = opaque; co->ret = ret; - qemu_coroutine_enter(co->coroutine); + aio_co_wake(co->coroutine); } static int coroutine_fn bdrv_driver_preadv(BlockDriverState *bs, @@ -XXX,XX +XXX,XX @@ static void bdrv_co_complete(BlockAIOCBCoroutine *acb) static void bdrv_co_em_bh(void *opaque) { BlockAIOCBCoroutine *acb = opaque; - BlockDriverState *bs = acb->common.bs; - AioContext *ctx = bdrv_get_aio_context(bs); assert(!acb->need_bh); - aio_context_acquire(ctx); bdrv_co_complete(acb); - aio_context_release(ctx); } static void bdrv_co_maybe_schedule_bh(BlockAIOCBCoroutine *acb) diff --git a/block/iscsi.c b/block/iscsi.c index XXXXXXX..XXXXXXX 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -XXX,XX +XXX,XX @@ static void iscsi_bh_cb(void *p) { IscsiAIOCB *acb = p; - AioContext *ctx = bdrv_get_aio_context(acb->common.bs); qemu_bh_delete(acb->bh); g_free(acb->buf); acb->buf = NULL; - aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, acb->status); - aio_context_release(ctx); if (acb->task != NULL) { scsi_free_scsi_task(acb->task); diff --git a/block/linux-aio.c b/block/linux-aio.c index XXXXXXX..XXXXXXX 100644 --- a/block/linux-aio.c +++ b/block/linux-aio.c @@ -XXX,XX +XXX,XX @@ static inline ssize_t io_event_ret(struct io_event *ev) */ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb) { - LinuxAioState *s = laiocb->ctx; int ret; ret = laiocb->ret; @@ -XXX,XX +XXX,XX @@ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb) } laiocb->ret = ret; - aio_context_acquire(s->aio_context); if (laiocb->co) { /* If the coroutine is already entered it must be in ioq_submit() and * will notice laio->ret has been filled in when it eventually runs @@ -XXX,XX +XXX,XX @@ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb) * that! */ if (!qemu_coroutine_entered(laiocb->co)) { - qemu_coroutine_enter(laiocb->co); + aio_co_wake(laiocb->co); } } else { laiocb->common.cb(laiocb->common.opaque, ret); qemu_aio_unref(laiocb); } - aio_context_release(s->aio_context); } /** diff --git a/block/mirror.c b/block/mirror.c index XXXXXXX..XXXXXXX 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -XXX,XX +XXX,XX @@ static void mirror_write_complete(void *opaque, int ret) { MirrorOp *op = opaque; MirrorBlockJob *s = op->s; + + aio_context_acquire(blk_get_aio_context(s->common.blk)); if (ret < 0) { BlockErrorAction action; @@ -XXX,XX +XXX,XX @@ static void mirror_write_complete(void *opaque, int ret) } } mirror_iteration_done(op, ret); + aio_context_release(blk_get_aio_context(s->common.blk)); } static void mirror_read_complete(void *opaque, int ret) { MirrorOp *op = opaque; MirrorBlockJob *s = op->s; + + aio_context_acquire(blk_get_aio_context(s->common.blk)); if (ret < 0) { BlockErrorAction action; @@ -XXX,XX +XXX,XX @@ static void mirror_read_complete(void *opaque, int ret) } mirror_iteration_done(op, ret); - return; + } else { + blk_aio_pwritev(s->target, op->sector_num * BDRV_SECTOR_SIZE, &op->qiov, + 0, mirror_write_complete, op); } - blk_aio_pwritev(s->target, op->sector_num * BDRV_SECTOR_SIZE, &op->qiov, - 0, mirror_write_complete, op); + aio_context_release(blk_get_aio_context(s->common.blk)); } static inline void mirror_clip_sectors(MirrorBlockJob *s, diff --git a/block/null.c b/block/null.c index XXXXXXX..XXXXXXX 100644 --- a/block/null.c +++ b/block/null.c @@ -XXX,XX +XXX,XX @@ static const AIOCBInfo null_aiocb_info = { static void null_bh_cb(void *opaque) { NullAIOCB *acb = opaque; - AioContext *ctx = bdrv_get_aio_context(acb->common.bs); - - aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, 0); - aio_context_release(ctx); qemu_aio_unref(acb); } static void null_timer_cb(void *opaque) { NullAIOCB *acb = opaque; - AioContext *ctx = bdrv_get_aio_context(acb->common.bs); - - aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, 0); - aio_context_release(ctx); timer_deinit(&acb->timer); qemu_aio_unref(acb); } diff --git a/block/qed-cluster.c b/block/qed-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed-cluster.c +++ b/block/qed-cluster.c @@ -XXX,XX +XXX,XX @@ static void qed_find_cluster_cb(void *opaque, int ret) unsigned int index; unsigned int n; + qed_acquire(s); if (ret) { goto out; } @@ -XXX,XX +XXX,XX @@ static void qed_find_cluster_cb(void *opaque, int ret) out: find_cluster_cb->cb(find_cluster_cb->opaque, ret, offset, len); + qed_release(s); g_free(find_cluster_cb); } diff --git a/block/qed-table.c b/block/qed-table.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed-table.c +++ b/block/qed-table.c @@ -XXX,XX +XXX,XX @@ static void qed_read_table_cb(void *opaque, int ret) { QEDReadTableCB *read_table_cb = opaque; QEDTable *table = read_table_cb->table; + BDRVQEDState *s = read_table_cb->s; int noffsets = read_table_cb->qiov.size / sizeof(uint64_t); int i; @@ -XXX,XX +XXX,XX @@ static void qed_read_table_cb(void *opaque, int ret) } /* Byteswap offsets */ + qed_acquire(s); for (i = 0; i < noffsets; i++) { table->offsets[i] = le64_to_cpu(table->offsets[i]); } + qed_release(s); out: /* Completion */ - trace_qed_read_table_cb(read_table_cb->s, read_table_cb->table, ret); + trace_qed_read_table_cb(s, read_table_cb->table, ret); gencb_complete(&read_table_cb->gencb, ret); } @@ -XXX,XX +XXX,XX @@ typedef struct { static void qed_write_table_cb(void *opaque, int ret) { QEDWriteTableCB *write_table_cb = opaque; + BDRVQEDState *s = write_table_cb->s; - trace_qed_write_table_cb(write_table_cb->s, + trace_qed_write_table_cb(s, write_table_cb->orig_table, write_table_cb->flush, ret); @@ -XXX,XX +XXX,XX @@ static void qed_write_table_cb(void *opaque, int ret) if (write_table_cb->flush) { /* We still need to flush first */ write_table_cb->flush = false; + qed_acquire(s); bdrv_aio_flush(write_table_cb->s->bs, qed_write_table_cb, write_table_cb); + qed_release(s); return; } @@ -XXX,XX +XXX,XX @@ static void qed_read_l2_table_cb(void *opaque, int ret) CachedL2Table *l2_table = request->l2_table; uint64_t l2_offset = read_l2_table_cb->l2_offset; + qed_acquire(s); if (ret) { /* can't trust loaded L2 table anymore */ qed_unref_l2_cache_entry(l2_table); @@ -XXX,XX +XXX,XX @@ static void qed_read_l2_table_cb(void *opaque, int ret) request->l2_table = qed_find_l2_cache_entry(&s->l2_cache, l2_offset); assert(request->l2_table != NULL); } + qed_release(s); gencb_complete(&read_l2_table_cb->gencb, ret); } diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static void qed_is_allocated_cb(void *opaque, int ret, uint64_t offset, size_t l } if (cb->co) { - qemu_coroutine_enter(cb->co); + aio_co_wake(cb->co); } } @@ -XXX,XX +XXX,XX @@ static void coroutine_fn qed_co_pwrite_zeroes_cb(void *opaque, int ret) cb->done = true; cb->ret = ret; if (cb->co) { - qemu_coroutine_enter(cb->co); + aio_co_wake(cb->co); } } diff --git a/block/rbd.c b/block/rbd.c index XXXXXXX..XXXXXXX 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -XXX,XX +XXX,XX @@ shutdown: static void qemu_rbd_complete_aio(RADOSCB *rcb) { RBDAIOCB *acb = rcb->acb; - AioContext *ctx = bdrv_get_aio_context(acb->common.bs); int64_t r; r = rcb->ret; @@ -XXX,XX +XXX,XX @@ static void qemu_rbd_complete_aio(RADOSCB *rcb) qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size); } qemu_vfree(acb->bounce); - - aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret)); - aio_context_release(ctx); qemu_aio_unref(acb); } diff --git a/block/win32-aio.c b/block/win32-aio.c index XXXXXXX..XXXXXXX 100644 --- a/block/win32-aio.c +++ b/block/win32-aio.c @@ -XXX,XX +XXX,XX @@ static void win32_aio_process_completion(QEMUWin32AIOState *s, qemu_vfree(waiocb->buf); } - - aio_context_acquire(s->aio_ctx); waiocb->common.cb(waiocb->common.opaque, ret); - aio_context_release(s->aio_ctx); qemu_aio_unref(waiocb); } diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error, static void virtio_blk_rw_complete(void *opaque, int ret) { VirtIOBlockReq *next = opaque; + VirtIOBlock *s = next->dev; + aio_context_acquire(blk_get_aio_context(s->conf.conf.blk)); while (next) { VirtIOBlockReq *req = next; next = req->mr_next; @@ -XXX,XX +XXX,XX @@ static void virtio_blk_rw_complete(void *opaque, int ret) block_acct_done(blk_get_stats(req->dev->blk), &req->acct); virtio_blk_free_request(req); } + aio_context_release(blk_get_aio_context(s->conf.conf.blk)); } static void virtio_blk_flush_complete(void *opaque, int ret) { VirtIOBlockReq *req = opaque; + VirtIOBlock *s = req->dev; + aio_context_acquire(blk_get_aio_context(s->conf.conf.blk)); if (ret) { if (virtio_blk_handle_rw_error(req, -ret, 0)) { - return; + goto out; } } virtio_blk_req_complete(req, VIRTIO_BLK_S_OK); block_acct_done(blk_get_stats(req->dev->blk), &req->acct); virtio_blk_free_request(req); + +out: + aio_context_release(blk_get_aio_context(s->conf.conf.blk)); } #ifdef __linux__ @@ -XXX,XX +XXX,XX @@ static void virtio_blk_ioctl_complete(void *opaque, int status) virtio_stl_p(vdev, &scsi->data_len, hdr->dxfer_len); out: + aio_context_acquire(blk_get_aio_context(s->conf.conf.blk)); virtio_blk_req_complete(req, status); virtio_blk_free_request(req); + aio_context_release(blk_get_aio_context(s->conf.conf.blk)); g_free(ioctl_req); } diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/scsi/scsi-disk.c +++ b/hw/scsi/scsi-disk.c @@ -XXX,XX +XXX,XX @@ static void scsi_aio_complete(void *opaque, int ret) assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); if (scsi_disk_req_check_error(r, ret, true)) { goto done; } @@ -XXX,XX +XXX,XX @@ static void scsi_aio_complete(void *opaque, int ret) scsi_req_complete(&r->req, GOOD); done: + aio_context_release(blk_get_aio_context(s->qdev.conf.blk)); scsi_req_unref(&r->req); } @@ -XXX,XX +XXX,XX @@ static void scsi_dma_complete(void *opaque, int ret) assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); if (ret < 0) { block_acct_failed(blk_get_stats(s->qdev.conf.blk), &r->acct); } else { block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct); } scsi_dma_complete_noio(r, ret); + aio_context_release(blk_get_aio_context(s->qdev.conf.blk)); } static void scsi_read_complete(void * opaque, int ret) @@ -XXX,XX +XXX,XX @@ static void scsi_read_complete(void * opaque, int ret) assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); if (scsi_disk_req_check_error(r, ret, true)) { goto done; } @@ -XXX,XX +XXX,XX @@ static void scsi_read_complete(void * opaque, int ret) done: scsi_req_unref(&r->req); + aio_context_release(blk_get_aio_context(s->qdev.conf.blk)); } /* Actually issue a read to the block device. */ @@ -XXX,XX +XXX,XX @@ static void scsi_do_read_cb(void *opaque, int ret) assert (r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); if (ret < 0) { block_acct_failed(blk_get_stats(s->qdev.conf.blk), &r->acct); } else { block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct); } scsi_do_read(opaque, ret); + aio_context_release(blk_get_aio_context(s->qdev.conf.blk)); } /* Read more data from scsi device into buffer. */ @@ -XXX,XX +XXX,XX @@ static void scsi_write_complete(void * opaque, int ret) assert (r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); if (ret < 0) { block_acct_failed(blk_get_stats(s->qdev.conf.blk), &r->acct); } else { block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct); } scsi_write_complete_noio(r, ret); + aio_context_release(blk_get_aio_context(s->qdev.conf.blk)); } static void scsi_write_data(SCSIRequest *req) @@ -XXX,XX +XXX,XX @@ static void scsi_unmap_complete(void *opaque, int ret) { UnmapCBData *data = opaque; SCSIDiskReq *r = data->r; + SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev); assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); scsi_unmap_complete_noio(data, ret); + aio_context_release(blk_get_aio_context(s->qdev.conf.blk)); } static void scsi_disk_emulate_unmap(SCSIDiskReq *r, uint8_t *inbuf) @@ -XXX,XX +XXX,XX @@ static void scsi_write_same_complete(void *opaque, int ret) assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); if (scsi_disk_req_check_error(r, ret, true)) { goto done; } @@ -XXX,XX +XXX,XX @@ done: scsi_req_unref(&r->req); qemu_vfree(data->iov.iov_base); g_free(data); + aio_context_release(blk_get_aio_context(s->qdev.conf.blk)); } static void scsi_disk_emulate_write_same(SCSIDiskReq *r, uint8_t *inbuf) diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/scsi/scsi-generic.c +++ b/hw/scsi/scsi-generic.c @@ -XXX,XX +XXX,XX @@ done: static void scsi_command_complete(void *opaque, int ret) { SCSIGenericReq *r = (SCSIGenericReq *)opaque; + SCSIDevice *s = r->req.dev; assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + + aio_context_acquire(blk_get_aio_context(s->conf.blk)); scsi_command_complete_noio(r, ret); + aio_context_release(blk_get_aio_context(s->conf.blk)); } static int execute_command(BlockBackend *blk, @@ -XXX,XX +XXX,XX @@ static void scsi_read_complete(void * opaque, int ret) assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->conf.blk)); + if (ret || r->req.io_canceled) { scsi_command_complete_noio(r, ret); - return; + goto done; } len = r->io_header.dxfer_len - r->io_header.resid; @@ -XXX,XX +XXX,XX @@ static void scsi_read_complete(void * opaque, int ret) r->len = -1; if (len == 0) { scsi_command_complete_noio(r, 0); - return; + goto done; } /* Snoop READ CAPACITY output to set the blocksize. */ @@ -XXX,XX +XXX,XX @@ static void scsi_read_complete(void * opaque, int ret) } scsi_req_data(&r->req, len); scsi_req_unref(&r->req); + +done: + aio_context_release(blk_get_aio_context(s->conf.blk)); } /* Read more data from scsi device into buffer. */ @@ -XXX,XX +XXX,XX @@ static void scsi_write_complete(void * opaque, int ret) assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->conf.blk)); + if (ret || r->req.io_canceled) { scsi_command_complete_noio(r, ret); - return; + goto done; } if (r->req.cmd.buf[0] == MODE_SELECT && r->req.cmd.buf[4] == 12 && @@ -XXX,XX +XXX,XX @@ static void scsi_write_complete(void * opaque, int ret) } scsi_command_complete_noio(r, ret); + +done: + aio_context_release(blk_get_aio_context(s->conf.blk)); } /* Write data to a scsi device. Returns nonzero on failure. diff --git a/util/thread-pool.c b/util/thread-pool.c index XXXXXXX..XXXXXXX 100644 --- a/util/thread-pool.c +++ b/util/thread-pool.c @@ -XXX,XX +XXX,XX @@ restart: */ qemu_bh_schedule(pool->completion_bh); + aio_context_release(pool->ctx); elem->common.cb(elem->common.opaque, elem->ret); + aio_context_acquire(pool->ctx); qemu_aio_unref(elem); goto restart; } else { @@ -XXX,XX +XXX,XX @@ static void thread_pool_co_cb(void *opaque, int ret) ThreadPoolCo *co = opaque; co->ret = ret; - qemu_coroutine_enter(co->co); + aio_co_wake(co->co); } int coroutine_fn thread_pool_submit_co(ThreadPool *pool, ThreadPoolFunc *func, -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> This patch prepares for the removal of unnecessary lockcnt inc/dec pairs. Extract the dispatching loop for file descriptor handlers into a new function aio_dispatch_handlers, and then inline aio_dispatch into aio_poll. aio_dispatch can now become void. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-17-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/block/aio.h | 6 +----- util/aio-posix.c | 44 ++++++++++++++------------------------------ util/aio-win32.c | 13 ++++--------- util/async.c | 2 +- 4 files changed, 20 insertions(+), 45 deletions(-) diff --git a/include/block/aio.h b/include/block/aio.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/aio.h +++ b/include/block/aio.h @@ -XXX,XX +XXX,XX @@ bool aio_pending(AioContext *ctx); /* Dispatch any pending callbacks from the GSource attached to the AioContext. * * This is used internally in the implementation of the GSource. - * - * @dispatch_fds: true to process fds, false to skip them - * (can be used as an optimization by callers that know there - * are no fds ready) */ -bool aio_dispatch(AioContext *ctx, bool dispatch_fds); +void aio_dispatch(AioContext *ctx); /* Progress in completing AIO work to occur. This can issue new pending * aio as a result of executing I/O completion or bh callbacks. diff --git a/util/aio-posix.c b/util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) AioHandler *node, *tmp; bool progress = false; - /* - * We have to walk very carefully in case aio_set_fd_handler is - * called while we're walking. - */ - qemu_lockcnt_inc(&ctx->list_lock); - QLIST_FOREACH_SAFE_RCU(node, &ctx->aio_handlers, node, tmp) { int revents; @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) } } - qemu_lockcnt_dec(&ctx->list_lock); return progress; } -/* - * Note that dispatch_fds == false has the side-effect of post-poning the - * freeing of deleted handlers. - */ -bool aio_dispatch(AioContext *ctx, bool dispatch_fds) +void aio_dispatch(AioContext *ctx) { - bool progress; + aio_bh_poll(ctx); - /* - * If there are callbacks left that have been queued, we need to call them. - * Do not call select in this case, because it is possible that the caller - * does not need a complete flush (as is the case for aio_poll loops). - */ - progress = aio_bh_poll(ctx); + qemu_lockcnt_inc(&ctx->list_lock); + aio_dispatch_handlers(ctx); + qemu_lockcnt_dec(&ctx->list_lock); - if (dispatch_fds) { - progress |= aio_dispatch_handlers(ctx); - } - - /* Run our timers */ - progress |= timerlistgroup_run_timers(&ctx->tlg); - - return progress; + timerlistgroup_run_timers(&ctx->tlg); } /* These thread-local variables are used only in a small part of aio_poll @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) npfd = 0; qemu_lockcnt_dec(&ctx->list_lock); - /* Run dispatch even if there were no readable fds to run timers */ - if (aio_dispatch(ctx, ret > 0)) { - progress = true; + progress |= aio_bh_poll(ctx); + + if (ret > 0) { + qemu_lockcnt_inc(&ctx->list_lock); + progress |= aio_dispatch_handlers(ctx); + qemu_lockcnt_dec(&ctx->list_lock); } + progress |= timerlistgroup_run_timers(&ctx->tlg); + return progress; } diff --git a/util/aio-win32.c b/util/aio-win32.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-win32.c +++ b/util/aio-win32.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event) return progress; } -bool aio_dispatch(AioContext *ctx, bool dispatch_fds) +void aio_dispatch(AioContext *ctx) { - bool progress; - - progress = aio_bh_poll(ctx); - if (dispatch_fds) { - progress |= aio_dispatch_handlers(ctx, INVALID_HANDLE_VALUE); - } - progress |= timerlistgroup_run_timers(&ctx->tlg); - return progress; + aio_bh_poll(ctx); + aio_dispatch_handlers(ctx, INVALID_HANDLE_VALUE); + timerlistgroup_run_timers(&ctx->tlg); } bool aio_poll(AioContext *ctx, bool blocking) diff --git a/util/async.c b/util/async.c index XXXXXXX..XXXXXXX 100644 --- a/util/async.c +++ b/util/async.c @@ -XXX,XX +XXX,XX @@ aio_ctx_dispatch(GSource *source, AioContext *ctx = (AioContext *) source; assert(callback == NULL); - aio_dispatch(ctx, true); + aio_dispatch(ctx); return true; } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Pull the increment/decrement pair out of aio_bh_poll and into the callers. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-18-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/aio-posix.c | 8 +++----- util/aio-win32.c | 8 ++++---- util/async.c | 12 ++++++------ 3 files changed, 13 insertions(+), 15 deletions(-) diff --git a/util/aio-posix.c b/util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) void aio_dispatch(AioContext *ctx) { + qemu_lockcnt_inc(&ctx->list_lock); aio_bh_poll(ctx); - - qemu_lockcnt_inc(&ctx->list_lock); aio_dispatch_handlers(ctx); qemu_lockcnt_dec(&ctx->list_lock); @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) } npfd = 0; - qemu_lockcnt_dec(&ctx->list_lock); progress |= aio_bh_poll(ctx); if (ret > 0) { - qemu_lockcnt_inc(&ctx->list_lock); progress |= aio_dispatch_handlers(ctx); - qemu_lockcnt_dec(&ctx->list_lock); } + qemu_lockcnt_dec(&ctx->list_lock); + progress |= timerlistgroup_run_timers(&ctx->tlg); return progress; diff --git a/util/aio-win32.c b/util/aio-win32.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-win32.c +++ b/util/aio-win32.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event) bool progress = false; AioHandler *tmp; - qemu_lockcnt_inc(&ctx->list_lock); - /* * We have to walk very carefully in case aio_set_fd_handler is * called while we're walking. @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event) } } - qemu_lockcnt_dec(&ctx->list_lock); return progress; } void aio_dispatch(AioContext *ctx) { + qemu_lockcnt_inc(&ctx->list_lock); aio_bh_poll(ctx); aio_dispatch_handlers(ctx, INVALID_HANDLE_VALUE); + qemu_lockcnt_dec(&ctx->list_lock); timerlistgroup_run_timers(&ctx->tlg); } @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) } } - qemu_lockcnt_dec(&ctx->list_lock); first = true; /* ctx->notifier is always registered. */ @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) progress |= aio_dispatch_handlers(ctx, event); } while (count > 0); + qemu_lockcnt_dec(&ctx->list_lock); + progress |= timerlistgroup_run_timers(&ctx->tlg); return progress; } diff --git a/util/async.c b/util/async.c index XXXXXXX..XXXXXXX 100644 --- a/util/async.c +++ b/util/async.c @@ -XXX,XX +XXX,XX @@ void aio_bh_call(QEMUBH *bh) bh->cb(bh->opaque); } -/* Multiple occurrences of aio_bh_poll cannot be called concurrently */ +/* Multiple occurrences of aio_bh_poll cannot be called concurrently. + * The count in ctx->list_lock is incremented before the call, and is + * not affected by the call. + */ int aio_bh_poll(AioContext *ctx) { QEMUBH *bh, **bhp, *next; int ret; bool deleted = false; - qemu_lockcnt_inc(&ctx->list_lock); - ret = 0; for (bh = atomic_rcu_read(&ctx->first_bh); bh; bh = next) { next = atomic_rcu_read(&bh->next); @@ -XXX,XX +XXX,XX @@ int aio_bh_poll(AioContext *ctx) /* remove deleted bhs */ if (!deleted) { - qemu_lockcnt_dec(&ctx->list_lock); return ret; } - if (qemu_lockcnt_dec_and_lock(&ctx->list_lock)) { + if (qemu_lockcnt_dec_if_lock(&ctx->list_lock)) { bhp = &ctx->first_bh; while (*bhp) { bh = *bhp; @@ -XXX,XX +XXX,XX @@ int aio_bh_poll(AioContext *ctx) bhp = &bh->next; } } - qemu_lockcnt_unlock(&ctx->list_lock); + qemu_lockcnt_inc_and_unlock(&ctx->list_lock); } return ret; } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-19-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/block/block_int.h | 64 +++++++++++++++++++++++++----------------- include/sysemu/block-backend.h | 14 ++++++--- 2 files changed, 49 insertions(+), 29 deletions(-) diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ struct BdrvChild { * copied as well. */ struct BlockDriverState { - int64_t total_sectors; /* if we are reading a disk image, give its - size in sectors */ + /* Protected by big QEMU lock or read-only after opening. No special + * locking needed during I/O... + */ int open_flags; /* flags used to open the file, re-used for re-open */ bool read_only; /* if true, the media is read only */ bool encrypted; /* if true, the media is encrypted */ @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { bool sg; /* if true, the device is a /dev/sg* */ bool probed; /* if true, format was probed rather than specified */ - int copy_on_read; /* if nonzero, copy read backing sectors into image. - note this is a reference count */ - - CoQueue flush_queue; /* Serializing flush queue */ - bool active_flush_req; /* Flush request in flight? */ - unsigned int write_gen; /* Current data generation */ - unsigned int flushed_gen; /* Flushed write generation */ - BlockDriver *drv; /* NULL means no media */ void *opaque; @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { BdrvChild *backing; BdrvChild *file; - /* Callback before write request is processed */ - NotifierWithReturnList before_write_notifiers; - - /* number of in-flight requests; overall and serialising */ - unsigned int in_flight; - unsigned int serialising_in_flight; - - bool wakeup; - - /* Offset after the highest byte written to */ - uint64_t wr_highest_offset; - /* I/O Limits */ BlockLimits bl; @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { QTAILQ_ENTRY(BlockDriverState) bs_list; /* element of the list of monitor-owned BDS */ QTAILQ_ENTRY(BlockDriverState) monitor_list; - QLIST_HEAD(, BdrvDirtyBitmap) dirty_bitmaps; int refcnt; - QLIST_HEAD(, BdrvTrackedRequest) tracked_requests; - /* operation blockers */ QLIST_HEAD(, BdrvOpBlocker) op_blockers[BLOCK_OP_TYPE_MAX]; @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { /* The error object in use for blocking operations on backing_hd */ Error *backing_blocker; + /* Protected by AioContext lock */ + + /* If true, copy read backing sectors into image. Can be >1 if more + * than one client has requested copy-on-read. + */ + int copy_on_read; + + /* If we are reading a disk image, give its size in sectors. + * Generally read-only; it is written to by load_vmstate and save_vmstate, + * but the block layer is quiescent during those. + */ + int64_t total_sectors; + + /* Callback before write request is processed */ + NotifierWithReturnList before_write_notifiers; + + /* number of in-flight requests; overall and serialising */ + unsigned int in_flight; + unsigned int serialising_in_flight; + + bool wakeup; + + /* Offset after the highest byte written to */ + uint64_t wr_highest_offset; + /* threshold limit for writes, in bytes. "High water mark". */ uint64_t write_threshold_offset; NotifierWithReturn write_threshold_notifier; @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { /* counter for nested bdrv_io_plug */ unsigned io_plugged; + QLIST_HEAD(, BdrvTrackedRequest) tracked_requests; + CoQueue flush_queue; /* Serializing flush queue */ + bool active_flush_req; /* Flush request in flight? */ + unsigned int write_gen; /* Current data generation */ + unsigned int flushed_gen; /* Flushed write generation */ + + QLIST_HEAD(, BdrvDirtyBitmap) dirty_bitmaps; + + /* do we need to tell the quest if we have a volatile write cache? */ + int enable_write_cache; + int quiesce_counter; }; diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend.h +++ b/include/sysemu/block-backend.h @@ -XXX,XX +XXX,XX @@ typedef struct BlockDevOps { * fields that must be public. This is in particular for QLIST_ENTRY() and * friends so that BlockBackends can be kept in lists outside block-backend.c */ typedef struct BlockBackendPublic { - /* I/O throttling. - * throttle_state tells us if this BlockBackend has I/O limits configured. - * io_limits_disabled tells us if they are currently being enforced */ + /* I/O throttling has its own locking, but also some fields are + * protected by the AioContext lock. + */ + + /* Protected by AioContext lock. */ CoQueue throttled_reqs[2]; + + /* Nonzero if the I/O limits are currently being ignored; generally + * it is zero. */ unsigned int io_limits_disabled; /* The following fields are protected by the ThrottleGroup lock. - * See the ThrottleGroup documentation for details. */ + * See the ThrottleGroup documentation for details. + * throttle_state tells us if I/O limits are configured. */ ThrottleState *throttle_state; ThrottleTimers throttle_timers; unsigned pending_reqs[2]; -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> This uses the lock-free mutex described in the paper '"Blocking without Locking", or LFTHREADS: A lock-free thread library' by Gidenstam and Papatriantafilou. The same technique is used in OSv, and in fact the code is essentially a conversion to C of OSv's code. [Added missing coroutine_fn in tests/test-aio-multithread.c. --Stefan] Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213181244.16297-2-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/qemu/coroutine.h | 17 ++++- tests/test-aio-multithread.c | 86 ++++++++++++++++++++++++ util/qemu-coroutine-lock.c | 155 ++++++++++++++++++++++++++++++++++++++++--- util/trace-events | 1 + 4 files changed, 246 insertions(+), 13 deletions(-) diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -XXX,XX +XXX,XX @@ bool qemu_co_queue_empty(CoQueue *queue); /** * Provides a mutex that can be used to synchronise coroutines */ +struct CoWaitRecord; typedef struct CoMutex { - bool locked; + /* Count of pending lockers; 0 for a free mutex, 1 for an + * uncontended mutex. + */ + unsigned locked; + + /* A queue of waiters. Elements are added atomically in front of + * from_push. to_pop is only populated, and popped from, by whoever + * is in charge of the next wakeup. This can be an unlocker or, + * through the handoff protocol, a locker that is about to go to sleep. + */ + QSLIST_HEAD(, CoWaitRecord) from_push, to_pop; + + unsigned handoff, sequence; + Coroutine *holder; - CoQueue queue; } CoMutex; /** diff --git a/tests/test-aio-multithread.c b/tests/test-aio-multithread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-aio-multithread.c +++ b/tests/test-aio-multithread.c @@ -XXX,XX +XXX,XX @@ static void test_multi_co_schedule_10(void) test_multi_co_schedule(10); } +/* CoMutex thread-safety. */ + +static uint32_t atomic_counter; +static uint32_t running; +static uint32_t counter; +static CoMutex comutex; + +static void coroutine_fn test_multi_co_mutex_entry(void *opaque) +{ + while (!atomic_mb_read(&now_stopping)) { + qemu_co_mutex_lock(&comutex); + counter++; + qemu_co_mutex_unlock(&comutex); + + /* Increase atomic_counter *after* releasing the mutex. Otherwise + * there is a chance (it happens about 1 in 3 runs) that the iothread + * exits before the coroutine is woken up, causing a spurious + * assertion failure. + */ + atomic_inc(&atomic_counter); + } + atomic_dec(&running); +} + +static void test_multi_co_mutex(int threads, int seconds) +{ + int i; + + qemu_co_mutex_init(&comutex); + counter = 0; + atomic_counter = 0; + now_stopping = false; + + create_aio_contexts(); + assert(threads <= NUM_CONTEXTS); + running = threads; + for (i = 0; i < threads; i++) { + Coroutine *co1 = qemu_coroutine_create(test_multi_co_mutex_entry, NULL); + aio_co_schedule(ctx[i], co1); + } + + g_usleep(seconds * 1000000); + + atomic_mb_set(&now_stopping, true); + while (running > 0) { + g_usleep(100000); + } + + join_aio_contexts(); + g_test_message("%d iterations/second\n", counter / seconds); + g_assert_cmpint(counter, ==, atomic_counter); +} + +/* Testing with NUM_CONTEXTS threads focuses on the queue. The mutex however + * is too contended (and the threads spend too much time in aio_poll) + * to actually stress the handoff protocol. + */ +static void test_multi_co_mutex_1(void) +{ + test_multi_co_mutex(NUM_CONTEXTS, 1); +} + +static void test_multi_co_mutex_10(void) +{ + test_multi_co_mutex(NUM_CONTEXTS, 10); +} + +/* Testing with fewer threads stresses the handoff protocol too. Still, the + * case where the locker _can_ pick up a handoff is very rare, happening + * about 10 times in 1 million, so increase the runtime a bit compared to + * other "quick" testcases that only run for 1 second. + */ +static void test_multi_co_mutex_2_3(void) +{ + test_multi_co_mutex(2, 3); +} + +static void test_multi_co_mutex_2_30(void) +{ + test_multi_co_mutex(2, 30); +} + /* End of tests. */ int main(int argc, char **argv) @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/aio/multi/lifecycle", test_lifecycle); if (g_test_quick()) { g_test_add_func("/aio/multi/schedule", test_multi_co_schedule_1); + g_test_add_func("/aio/multi/mutex/contended", test_multi_co_mutex_1); + g_test_add_func("/aio/multi/mutex/handoff", test_multi_co_mutex_2_3); } else { g_test_add_func("/aio/multi/schedule", test_multi_co_schedule_10); + g_test_add_func("/aio/multi/mutex/contended", test_multi_co_mutex_10); + g_test_add_func("/aio/multi/mutex/handoff", test_multi_co_mutex_2_30); } return g_test_run(); } diff --git a/util/qemu-coroutine-lock.c b/util/qemu-coroutine-lock.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine-lock.c +++ b/util/qemu-coroutine-lock.c @@ -XXX,XX +XXX,XX @@ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN * THE SOFTWARE. + * + * The lock-free mutex implementation is based on OSv + * (core/lfmutex.cc, include/lockfree/mutex.hh). + * Copyright (C) 2013 Cloudius Systems, Ltd. */ #include "qemu/osdep.h" @@ -XXX,XX +XXX,XX @@ bool qemu_co_queue_empty(CoQueue *queue) return QSIMPLEQ_FIRST(&queue->entries) == NULL; } +/* The wait records are handled with a multiple-producer, single-consumer + * lock-free queue. There cannot be two concurrent pop_waiter() calls + * because pop_waiter() can only be called while mutex->handoff is zero. + * This can happen in three cases: + * - in qemu_co_mutex_unlock, before the hand-off protocol has started. + * In this case, qemu_co_mutex_lock will see mutex->handoff == 0 and + * not take part in the handoff. + * - in qemu_co_mutex_lock, if it steals the hand-off responsibility from + * qemu_co_mutex_unlock. In this case, qemu_co_mutex_unlock will fail + * the cmpxchg (it will see either 0 or the next sequence value) and + * exit. The next hand-off cannot begin until qemu_co_mutex_lock has + * woken up someone. + * - in qemu_co_mutex_unlock, if it takes the hand-off token itself. + * In this case another iteration starts with mutex->handoff == 0; + * a concurrent qemu_co_mutex_lock will fail the cmpxchg, and + * qemu_co_mutex_unlock will go back to case (1). + * + * The following functions manage this queue. + */ +typedef struct CoWaitRecord { + Coroutine *co; + QSLIST_ENTRY(CoWaitRecord) next; +} CoWaitRecord; + +static void push_waiter(CoMutex *mutex, CoWaitRecord *w) +{ + w->co = qemu_coroutine_self(); + QSLIST_INSERT_HEAD_ATOMIC(&mutex->from_push, w, next); +} + +static void move_waiters(CoMutex *mutex) +{ + QSLIST_HEAD(, CoWaitRecord) reversed; + QSLIST_MOVE_ATOMIC(&reversed, &mutex->from_push); + while (!QSLIST_EMPTY(&reversed)) { + CoWaitRecord *w = QSLIST_FIRST(&reversed); + QSLIST_REMOVE_HEAD(&reversed, next); + QSLIST_INSERT_HEAD(&mutex->to_pop, w, next); + } +} + +static CoWaitRecord *pop_waiter(CoMutex *mutex) +{ + CoWaitRecord *w; + + if (QSLIST_EMPTY(&mutex->to_pop)) { + move_waiters(mutex); + if (QSLIST_EMPTY(&mutex->to_pop)) { + return NULL; + } + } + w = QSLIST_FIRST(&mutex->to_pop); + QSLIST_REMOVE_HEAD(&mutex->to_pop, next); + return w; +} + +static bool has_waiters(CoMutex *mutex) +{ + return QSLIST_EMPTY(&mutex->to_pop) || QSLIST_EMPTY(&mutex->from_push); +} + void qemu_co_mutex_init(CoMutex *mutex) { memset(mutex, 0, sizeof(*mutex)); - qemu_co_queue_init(&mutex->queue); } -void coroutine_fn qemu_co_mutex_lock(CoMutex *mutex) +static void coroutine_fn qemu_co_mutex_lock_slowpath(CoMutex *mutex) { Coroutine *self = qemu_coroutine_self(); + CoWaitRecord w; + unsigned old_handoff; trace_qemu_co_mutex_lock_entry(mutex, self); + w.co = self; + push_waiter(mutex, &w); - while (mutex->locked) { - qemu_co_queue_wait(&mutex->queue); + /* This is the "Responsibility Hand-Off" protocol; a lock() picks from + * a concurrent unlock() the responsibility of waking somebody up. + */ + old_handoff = atomic_mb_read(&mutex->handoff); + if (old_handoff && + has_waiters(mutex) && + atomic_cmpxchg(&mutex->handoff, old_handoff, 0) == old_handoff) { + /* There can be no concurrent pops, because there can be only + * one active handoff at a time. + */ + CoWaitRecord *to_wake = pop_waiter(mutex); + Coroutine *co = to_wake->co; + if (co == self) { + /* We got the lock ourselves! */ + assert(to_wake == &w); + return; + } + + aio_co_wake(co); } - mutex->locked = true; - mutex->holder = self; - self->locks_held++; - + qemu_coroutine_yield(); trace_qemu_co_mutex_lock_return(mutex, self); } +void coroutine_fn qemu_co_mutex_lock(CoMutex *mutex) +{ + Coroutine *self = qemu_coroutine_self(); + + if (atomic_fetch_inc(&mutex->locked) == 0) { + /* Uncontended. */ + trace_qemu_co_mutex_lock_uncontended(mutex, self); + } else { + qemu_co_mutex_lock_slowpath(mutex); + } + mutex->holder = self; + self->locks_held++; +} + void coroutine_fn qemu_co_mutex_unlock(CoMutex *mutex) { Coroutine *self = qemu_coroutine_self(); trace_qemu_co_mutex_unlock_entry(mutex, self); - assert(mutex->locked == true); + assert(mutex->locked); assert(mutex->holder == self); assert(qemu_in_coroutine()); - mutex->locked = false; mutex->holder = NULL; self->locks_held--; - qemu_co_queue_next(&mutex->queue); + if (atomic_fetch_dec(&mutex->locked) == 1) { + /* No waiting qemu_co_mutex_lock(). Pfew, that was easy! */ + return; + } + + for (;;) { + CoWaitRecord *to_wake = pop_waiter(mutex); + unsigned our_handoff; + + if (to_wake) { + Coroutine *co = to_wake->co; + aio_co_wake(co); + break; + } + + /* Some concurrent lock() is in progress (we know this because + * mutex->locked was >1) but it hasn't yet put itself on the wait + * queue. Pick a sequence number for the handoff protocol (not 0). + */ + if (++mutex->sequence == 0) { + mutex->sequence = 1; + } + + our_handoff = mutex->sequence; + atomic_mb_set(&mutex->handoff, our_handoff); + if (!has_waiters(mutex)) { + /* The concurrent lock has not added itself yet, so it + * will be able to pick our handoff. + */ + break; + } + + /* Try to do the handoff protocol ourselves; if somebody else has + * already taken it, however, we're done and they're responsible. + */ + if (atomic_cmpxchg(&mutex->handoff, our_handoff, 0) != our_handoff) { + break; + } + } trace_qemu_co_mutex_unlock_return(mutex, self); } diff --git a/util/trace-events b/util/trace-events index XXXXXXX..XXXXXXX 100644 --- a/util/trace-events +++ b/util/trace-events @@ -XXX,XX +XXX,XX @@ qemu_coroutine_terminate(void *co) "self %p" # util/qemu-coroutine-lock.c qemu_co_queue_run_restart(void *co) "co %p" +qemu_co_mutex_lock_uncontended(void *mutex, void *self) "mutex %p self %p" qemu_co_mutex_lock_entry(void *mutex, void *self) "mutex %p self %p" qemu_co_mutex_lock_return(void *mutex, void *self) "mutex %p self %p" qemu_co_mutex_unlock_entry(void *mutex, void *self) "mutex %p self %p" -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Running a very small critical section on pthread_mutex_t and CoMutex shows that pthread_mutex_t is much faster because it doesn't actually go to sleep. What happens is that the critical section is shorter than the latency of entering the kernel and thus FUTEX_WAIT always fails. With CoMutex there is no such latency but you still want to avoid wait and wakeup. So introduce it artificially. This only works with one waiters; because CoMutex is fair, it will always have more waits and wakeups than a pthread_mutex_t. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213181244.16297-3-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/qemu/coroutine.h | 5 +++++ util/qemu-coroutine-lock.c | 51 ++++++++++++++++++++++++++++++++++++++++------ util/qemu-coroutine.c | 2 +- 3 files changed, 51 insertions(+), 7 deletions(-) diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -XXX,XX +XXX,XX @@ typedef struct CoMutex { */ unsigned locked; + /* Context that is holding the lock. Useful to avoid spinning + * when two coroutines on the same AioContext try to get the lock. :) + */ + AioContext *ctx; + /* A queue of waiters. Elements are added atomically in front of * from_push. to_pop is only populated, and popped from, by whoever * is in charge of the next wakeup. This can be an unlocker or, diff --git a/util/qemu-coroutine-lock.c b/util/qemu-coroutine-lock.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine-lock.c +++ b/util/qemu-coroutine-lock.c @@ -XXX,XX +XXX,XX @@ #include "qemu-common.h" #include "qemu/coroutine.h" #include "qemu/coroutine_int.h" +#include "qemu/processor.h" #include "qemu/queue.h" #include "block/aio.h" #include "trace.h" @@ -XXX,XX +XXX,XX @@ void qemu_co_mutex_init(CoMutex *mutex) memset(mutex, 0, sizeof(*mutex)); } -static void coroutine_fn qemu_co_mutex_lock_slowpath(CoMutex *mutex) +static void coroutine_fn qemu_co_mutex_wake(CoMutex *mutex, Coroutine *co) +{ + /* Read co before co->ctx; pairs with smp_wmb() in + * qemu_coroutine_enter(). + */ + smp_read_barrier_depends(); + mutex->ctx = co->ctx; + aio_co_wake(co); +} + +static void coroutine_fn qemu_co_mutex_lock_slowpath(AioContext *ctx, + CoMutex *mutex) { Coroutine *self = qemu_coroutine_self(); CoWaitRecord w; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn qemu_co_mutex_lock_slowpath(CoMutex *mutex) if (co == self) { /* We got the lock ourselves! */ assert(to_wake == &w); + mutex->ctx = ctx; return; } - aio_co_wake(co); + qemu_co_mutex_wake(mutex, co); } qemu_coroutine_yield(); @@ -XXX,XX +XXX,XX @@ static void coroutine_fn qemu_co_mutex_lock_slowpath(CoMutex *mutex) void coroutine_fn qemu_co_mutex_lock(CoMutex *mutex) { + AioContext *ctx = qemu_get_current_aio_context(); Coroutine *self = qemu_coroutine_self(); + int waiters, i; - if (atomic_fetch_inc(&mutex->locked) == 0) { + /* Running a very small critical section on pthread_mutex_t and CoMutex + * shows that pthread_mutex_t is much faster because it doesn't actually + * go to sleep. What happens is that the critical section is shorter + * than the latency of entering the kernel and thus FUTEX_WAIT always + * fails. With CoMutex there is no such latency but you still want to + * avoid wait and wakeup. So introduce it artificially. + */ + i = 0; +retry_fast_path: + waiters = atomic_cmpxchg(&mutex->locked, 0, 1); + if (waiters != 0) { + while (waiters == 1 && ++i < 1000) { + if (atomic_read(&mutex->ctx) == ctx) { + break; + } + if (atomic_read(&mutex->locked) == 0) { + goto retry_fast_path; + } + cpu_relax(); + } + waiters = atomic_fetch_inc(&mutex->locked); + } + + if (waiters == 0) { /* Uncontended. */ trace_qemu_co_mutex_lock_uncontended(mutex, self); + mutex->ctx = ctx; } else { - qemu_co_mutex_lock_slowpath(mutex); + qemu_co_mutex_lock_slowpath(ctx, mutex); } mutex->holder = self; self->locks_held++; @@ -XXX,XX +XXX,XX @@ void coroutine_fn qemu_co_mutex_unlock(CoMutex *mutex) assert(mutex->holder == self); assert(qemu_in_coroutine()); + mutex->ctx = NULL; mutex->holder = NULL; self->locks_held--; if (atomic_fetch_dec(&mutex->locked) == 1) { @@ -XXX,XX +XXX,XX @@ void coroutine_fn qemu_co_mutex_unlock(CoMutex *mutex) unsigned our_handoff; if (to_wake) { - Coroutine *co = to_wake->co; - aio_co_wake(co); + qemu_co_mutex_wake(mutex, to_wake->co); break; } diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine.c +++ b/util/qemu-coroutine.c @@ -XXX,XX +XXX,XX @@ void qemu_coroutine_enter(Coroutine *co) co->ctx = qemu_get_current_aio_context(); /* Store co->ctx before anything that stores co. Matches - * barrier in aio_co_wake. + * barrier in aio_co_wake and qemu_co_mutex_wake. */ smp_wmb(); -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Add two implementations of the same benchmark as the previous patch, but using pthreads. One uses a normal QemuMutex, the other is Linux only and implements a fair mutex based on MCS locks and futexes. This shows that the slower performance of the 5-thread case is due to the fairness of CoMutex, rather than to coroutines. If fairness does not matter, as is the case with two threads, CoMutex can actually be faster than pthreads. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213181244.16297-4-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/test-aio-multithread.c | 164 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 164 insertions(+) diff --git a/tests/test-aio-multithread.c b/tests/test-aio-multithread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-aio-multithread.c +++ b/tests/test-aio-multithread.c @@ -XXX,XX +XXX,XX @@ static void test_multi_co_mutex_2_30(void) test_multi_co_mutex(2, 30); } +/* Same test with fair mutexes, for performance comparison. */ + +#ifdef CONFIG_LINUX +#include "qemu/futex.h" + +/* The nodes for the mutex reside in this structure (on which we try to avoid + * false sharing). The head of the mutex is in the "mutex_head" variable. + */ +static struct { + int next, locked; + int padding[14]; +} nodes[NUM_CONTEXTS] __attribute__((__aligned__(64))); + +static int mutex_head = -1; + +static void mcs_mutex_lock(void) +{ + int prev; + + nodes[id].next = -1; + nodes[id].locked = 1; + prev = atomic_xchg(&mutex_head, id); + if (prev != -1) { + atomic_set(&nodes[prev].next, id); + qemu_futex_wait(&nodes[id].locked, 1); + } +} + +static void mcs_mutex_unlock(void) +{ + int next; + if (nodes[id].next == -1) { + if (atomic_read(&mutex_head) == id && + atomic_cmpxchg(&mutex_head, id, -1) == id) { + /* Last item in the list, exit. */ + return; + } + while (atomic_read(&nodes[id].next) == -1) { + /* mcs_mutex_lock did the xchg, but has not updated + * nodes[prev].next yet. + */ + } + } + + /* Wake up the next in line. */ + next = nodes[id].next; + nodes[next].locked = 0; + qemu_futex_wake(&nodes[next].locked, 1); +} + +static void test_multi_fair_mutex_entry(void *opaque) +{ + while (!atomic_mb_read(&now_stopping)) { + mcs_mutex_lock(); + counter++; + mcs_mutex_unlock(); + atomic_inc(&atomic_counter); + } + atomic_dec(&running); +} + +static void test_multi_fair_mutex(int threads, int seconds) +{ + int i; + + assert(mutex_head == -1); + counter = 0; + atomic_counter = 0; + now_stopping = false; + + create_aio_contexts(); + assert(threads <= NUM_CONTEXTS); + running = threads; + for (i = 0; i < threads; i++) { + Coroutine *co1 = qemu_coroutine_create(test_multi_fair_mutex_entry, NULL); + aio_co_schedule(ctx[i], co1); + } + + g_usleep(seconds * 1000000); + + atomic_mb_set(&now_stopping, true); + while (running > 0) { + g_usleep(100000); + } + + join_aio_contexts(); + g_test_message("%d iterations/second\n", counter / seconds); + g_assert_cmpint(counter, ==, atomic_counter); +} + +static void test_multi_fair_mutex_1(void) +{ + test_multi_fair_mutex(NUM_CONTEXTS, 1); +} + +static void test_multi_fair_mutex_10(void) +{ + test_multi_fair_mutex(NUM_CONTEXTS, 10); +} +#endif + +/* Same test with pthread mutexes, for performance comparison and + * portability. */ + +static QemuMutex mutex; + +static void test_multi_mutex_entry(void *opaque) +{ + while (!atomic_mb_read(&now_stopping)) { + qemu_mutex_lock(&mutex); + counter++; + qemu_mutex_unlock(&mutex); + atomic_inc(&atomic_counter); + } + atomic_dec(&running); +} + +static void test_multi_mutex(int threads, int seconds) +{ + int i; + + qemu_mutex_init(&mutex); + counter = 0; + atomic_counter = 0; + now_stopping = false; + + create_aio_contexts(); + assert(threads <= NUM_CONTEXTS); + running = threads; + for (i = 0; i < threads; i++) { + Coroutine *co1 = qemu_coroutine_create(test_multi_mutex_entry, NULL); + aio_co_schedule(ctx[i], co1); + } + + g_usleep(seconds * 1000000); + + atomic_mb_set(&now_stopping, true); + while (running > 0) { + g_usleep(100000); + } + + join_aio_contexts(); + g_test_message("%d iterations/second\n", counter / seconds); + g_assert_cmpint(counter, ==, atomic_counter); +} + +static void test_multi_mutex_1(void) +{ + test_multi_mutex(NUM_CONTEXTS, 1); +} + +static void test_multi_mutex_10(void) +{ + test_multi_mutex(NUM_CONTEXTS, 10); +} + /* End of tests. */ int main(int argc, char **argv) @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/aio/multi/schedule", test_multi_co_schedule_1); g_test_add_func("/aio/multi/mutex/contended", test_multi_co_mutex_1); g_test_add_func("/aio/multi/mutex/handoff", test_multi_co_mutex_2_3); +#ifdef CONFIG_LINUX + g_test_add_func("/aio/multi/mutex/mcs", test_multi_fair_mutex_1); +#endif + g_test_add_func("/aio/multi/mutex/pthread", test_multi_mutex_1); } else { g_test_add_func("/aio/multi/schedule", test_multi_co_schedule_10); g_test_add_func("/aio/multi/mutex/contended", test_multi_co_mutex_10); g_test_add_func("/aio/multi/mutex/handoff", test_multi_co_mutex_2_30); +#ifdef CONFIG_LINUX + g_test_add_func("/aio/multi/mutex/mcs", test_multi_fair_mutex_10); +#endif + g_test_add_func("/aio/multi/mutex/pthread", test_multi_mutex_10); } return g_test_run(); } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> This will avoid forward references in the next patch. It is also more logical because CoQueue is not anymore the basic primitive. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213181244.16297-5-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/qemu/coroutine.h | 89 ++++++++++++++++++++++++------------------------ 1 file changed, 44 insertions(+), 45 deletions(-) diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -XXX,XX +XXX,XX @@ bool qemu_in_coroutine(void); */ bool qemu_coroutine_entered(Coroutine *co); - -/** - * CoQueues are a mechanism to queue coroutines in order to continue executing - * them later. They provide the fundamental primitives on which coroutine locks - * are built. - */ -typedef struct CoQueue { - QSIMPLEQ_HEAD(, Coroutine) entries; -} CoQueue; - -/** - * Initialise a CoQueue. This must be called before any other operation is used - * on the CoQueue. - */ -void qemu_co_queue_init(CoQueue *queue); - -/** - * Adds the current coroutine to the CoQueue and transfers control to the - * caller of the coroutine. - */ -void coroutine_fn qemu_co_queue_wait(CoQueue *queue); - -/** - * Restarts the next coroutine in the CoQueue and removes it from the queue. - * - * Returns true if a coroutine was restarted, false if the queue is empty. - */ -bool coroutine_fn qemu_co_queue_next(CoQueue *queue); - -/** - * Restarts all coroutines in the CoQueue and leaves the queue empty. - */ -void coroutine_fn qemu_co_queue_restart_all(CoQueue *queue); - -/** - * Enter the next coroutine in the queue - */ -bool qemu_co_enter_next(CoQueue *queue); - -/** - * Checks if the CoQueue is empty. - */ -bool qemu_co_queue_empty(CoQueue *queue); - - /** * Provides a mutex that can be used to synchronise coroutines */ @@ -XXX,XX +XXX,XX @@ void coroutine_fn qemu_co_mutex_lock(CoMutex *mutex); */ void coroutine_fn qemu_co_mutex_unlock(CoMutex *mutex); + +/** + * CoQueues are a mechanism to queue coroutines in order to continue executing + * them later. + */ +typedef struct CoQueue { + QSIMPLEQ_HEAD(, Coroutine) entries; +} CoQueue; + +/** + * Initialise a CoQueue. This must be called before any other operation is used + * on the CoQueue. + */ +void qemu_co_queue_init(CoQueue *queue); + +/** + * Adds the current coroutine to the CoQueue and transfers control to the + * caller of the coroutine. + */ +void coroutine_fn qemu_co_queue_wait(CoQueue *queue); + +/** + * Restarts the next coroutine in the CoQueue and removes it from the queue. + * + * Returns true if a coroutine was restarted, false if the queue is empty. + */ +bool coroutine_fn qemu_co_queue_next(CoQueue *queue); + +/** + * Restarts all coroutines in the CoQueue and leaves the queue empty. + */ +void coroutine_fn qemu_co_queue_restart_all(CoQueue *queue); + +/** + * Enter the next coroutine in the queue + */ +bool qemu_co_enter_next(CoQueue *queue); + +/** + * Checks if the CoQueue is empty. + */ +bool qemu_co_queue_empty(CoQueue *queue); + + typedef struct CoRwlock { bool writer; int reader; -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> All that CoQueue needs in order to become thread-safe is help from an external mutex. Add this to the API. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213181244.16297-6-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/qemu/coroutine.h | 8 +++++--- block/backup.c | 2 +- block/io.c | 4 ++-- block/nbd-client.c | 2 +- block/qcow2-cluster.c | 4 +--- block/sheepdog.c | 2 +- block/throttle-groups.c | 2 +- hw/9pfs/9p.c | 2 +- util/qemu-coroutine-lock.c | 24 +++++++++++++++++++++--- 9 files changed, 34 insertions(+), 16 deletions(-) diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -XXX,XX +XXX,XX @@ void coroutine_fn qemu_co_mutex_unlock(CoMutex *mutex); /** * CoQueues are a mechanism to queue coroutines in order to continue executing - * them later. + * them later. They are similar to condition variables, but they need help + * from an external mutex in order to maintain thread-safety. */ typedef struct CoQueue { QSIMPLEQ_HEAD(, Coroutine) entries; @@ -XXX,XX +XXX,XX @@ void qemu_co_queue_init(CoQueue *queue); /** * Adds the current coroutine to the CoQueue and transfers control to the - * caller of the coroutine. + * caller of the coroutine. The mutex is unlocked during the wait and + * locked again afterwards. */ -void coroutine_fn qemu_co_queue_wait(CoQueue *queue); +void coroutine_fn qemu_co_queue_wait(CoQueue *queue, CoMutex *mutex); /** * Restarts the next coroutine in the CoQueue and removes it from the queue. diff --git a/block/backup.c b/block/backup.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup.c +++ b/block/backup.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn wait_for_overlapping_requests(BackupBlockJob *job, retry = false; QLIST_FOREACH(req, &job->inflight_reqs, list) { if (end > req->start && start < req->end) { - qemu_co_queue_wait(&req->wait_queue); + qemu_co_queue_wait(&req->wait_queue, NULL); retry = true; break; } diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static bool coroutine_fn wait_serialising_requests(BdrvTrackedRequest *self) * (instead of producing a deadlock in the former case). */ if (!req->waiting_for) { self->waiting_for = req; - qemu_co_queue_wait(&req->wait_queue); + qemu_co_queue_wait(&req->wait_queue, NULL); self->waiting_for = NULL; retry = true; waited = true; @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_flush(BlockDriverState *bs) /* Wait until any previous flushes are completed */ while (bs->active_flush_req) { - qemu_co_queue_wait(&bs->flush_queue); + qemu_co_queue_wait(&bs->flush_queue, NULL); } bs->active_flush_req = true; diff --git a/block/nbd-client.c b/block/nbd-client.c index XXXXXXX..XXXXXXX 100644 --- a/block/nbd-client.c +++ b/block/nbd-client.c @@ -XXX,XX +XXX,XX @@ static void nbd_coroutine_start(NBDClientSession *s, /* Poor man semaphore. The free_sema is locked when no other request * can be accepted, and unlocked after receiving one reply. */ if (s->in_flight == MAX_NBD_REQUESTS) { - qemu_co_queue_wait(&s->free_sema); + qemu_co_queue_wait(&s->free_sema, NULL); assert(s->in_flight < MAX_NBD_REQUESTS); } s->in_flight++; diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ static int handle_dependencies(BlockDriverState *bs, uint64_t guest_offset, if (bytes == 0) { /* Wait for the dependency to complete. We need to recheck * the free/allocated clusters when we continue. */ - qemu_co_mutex_unlock(&s->lock); - qemu_co_queue_wait(&old_alloc->dependent_requests); - qemu_co_mutex_lock(&s->lock); + qemu_co_queue_wait(&old_alloc->dependent_requests, &s->lock); return -EAGAIN; } } diff --git a/block/sheepdog.c b/block/sheepdog.c index XXXXXXX..XXXXXXX 100644 --- a/block/sheepdog.c +++ b/block/sheepdog.c @@ -XXX,XX +XXX,XX @@ static void wait_for_overlapping_aiocb(BDRVSheepdogState *s, SheepdogAIOCB *acb) retry: QLIST_FOREACH(cb, &s->inflight_aiocb_head, aiocb_siblings) { if (AIOCBOverlapping(acb, cb)) { - qemu_co_queue_wait(&s->overlapping_queue); + qemu_co_queue_wait(&s->overlapping_queue, NULL); goto retry; } } diff --git a/block/throttle-groups.c b/block/throttle-groups.c index XXXXXXX..XXXXXXX 100644 --- a/block/throttle-groups.c +++ b/block/throttle-groups.c @@ -XXX,XX +XXX,XX @@ void coroutine_fn throttle_group_co_io_limits_intercept(BlockBackend *blk, if (must_wait || blkp->pending_reqs[is_write]) { blkp->pending_reqs[is_write]++; qemu_mutex_unlock(&tg->lock); - qemu_co_queue_wait(&blkp->throttled_reqs[is_write]); + qemu_co_queue_wait(&blkp->throttled_reqs[is_write], NULL); qemu_mutex_lock(&tg->lock); blkp->pending_reqs[is_write]--; } diff --git a/hw/9pfs/9p.c b/hw/9pfs/9p.c index XXXXXXX..XXXXXXX 100644 --- a/hw/9pfs/9p.c +++ b/hw/9pfs/9p.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn v9fs_flush(void *opaque) /* * Wait for pdu to complete. */ - qemu_co_queue_wait(&cancel_pdu->complete); + qemu_co_queue_wait(&cancel_pdu->complete, NULL); cancel_pdu->cancelled = 0; pdu_free(cancel_pdu); } diff --git a/util/qemu-coroutine-lock.c b/util/qemu-coroutine-lock.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine-lock.c +++ b/util/qemu-coroutine-lock.c @@ -XXX,XX +XXX,XX @@ void qemu_co_queue_init(CoQueue *queue) QSIMPLEQ_INIT(&queue->entries); } -void coroutine_fn qemu_co_queue_wait(CoQueue *queue) +void coroutine_fn qemu_co_queue_wait(CoQueue *queue, CoMutex *mutex) { Coroutine *self = qemu_coroutine_self(); QSIMPLEQ_INSERT_TAIL(&queue->entries, self, co_queue_next); + + if (mutex) { + qemu_co_mutex_unlock(mutex); + } + + /* There is no race condition here. Other threads will call + * aio_co_schedule on our AioContext, which can reenter this + * coroutine but only after this yield and after the main loop + * has gone through the next iteration. + */ qemu_coroutine_yield(); assert(qemu_in_coroutine()); + + /* TODO: OSv implements wait morphing here, where the wakeup + * primitive automatically places the woken coroutine on the + * mutex's queue. This avoids the thundering herd effect. + */ + if (mutex) { + qemu_co_mutex_lock(mutex); + } } /** @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_rdlock(CoRwlock *lock) Coroutine *self = qemu_coroutine_self(); while (lock->writer) { - qemu_co_queue_wait(&lock->queue); + qemu_co_queue_wait(&lock->queue, NULL); } lock->reader++; self->locks_held++; @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_wrlock(CoRwlock *lock) Coroutine *self = qemu_coroutine_self(); while (lock->writer || lock->reader) { - qemu_co_queue_wait(&lock->queue); + qemu_co_queue_wait(&lock->queue, NULL); } lock->writer = true; self->locks_held++; -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> This adds a CoMutex around the existing CoQueue. Because the write-side can just take CoMutex, the old "writer" field is not necessary anymore. Instead of removing it altogether, count the number of pending writers during a read-side critical section and forbid further readers from entering. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213181244.16297-7-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/qemu/coroutine.h | 3 ++- util/qemu-coroutine-lock.c | 35 ++++++++++++++++++++++++----------- 2 files changed, 26 insertions(+), 12 deletions(-) diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -XXX,XX +XXX,XX @@ bool qemu_co_queue_empty(CoQueue *queue); typedef struct CoRwlock { - bool writer; + int pending_writer; int reader; + CoMutex mutex; CoQueue queue; } CoRwlock; diff --git a/util/qemu-coroutine-lock.c b/util/qemu-coroutine-lock.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine-lock.c +++ b/util/qemu-coroutine-lock.c @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_init(CoRwlock *lock) { memset(lock, 0, sizeof(*lock)); qemu_co_queue_init(&lock->queue); + qemu_co_mutex_init(&lock->mutex); } void qemu_co_rwlock_rdlock(CoRwlock *lock) { Coroutine *self = qemu_coroutine_self(); - while (lock->writer) { - qemu_co_queue_wait(&lock->queue, NULL); + qemu_co_mutex_lock(&lock->mutex); + /* For fairness, wait if a writer is in line. */ + while (lock->pending_writer) { + qemu_co_queue_wait(&lock->queue, &lock->mutex); } lock->reader++; + qemu_co_mutex_unlock(&lock->mutex); + + /* The rest of the read-side critical section is run without the mutex. */ self->locks_held++; } @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_unlock(CoRwlock *lock) Coroutine *self = qemu_coroutine_self(); assert(qemu_in_coroutine()); - if (lock->writer) { - lock->writer = false; + if (!lock->reader) { + /* The critical section started in qemu_co_rwlock_wrlock. */ qemu_co_queue_restart_all(&lock->queue); } else { + self->locks_held--; + + qemu_co_mutex_lock(&lock->mutex); lock->reader--; assert(lock->reader >= 0); /* Wakeup only one waiting writer */ @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_unlock(CoRwlock *lock) qemu_co_queue_next(&lock->queue); } } - self->locks_held--; + qemu_co_mutex_unlock(&lock->mutex); } void qemu_co_rwlock_wrlock(CoRwlock *lock) { - Coroutine *self = qemu_coroutine_self(); - - while (lock->writer || lock->reader) { - qemu_co_queue_wait(&lock->queue, NULL); + qemu_co_mutex_lock(&lock->mutex); + lock->pending_writer++; + while (lock->reader) { + qemu_co_queue_wait(&lock->queue, &lock->mutex); } - lock->writer = true; - self->locks_held++; + lock->pending_writer--; + + /* The rest of the write-side critical section is run with + * the mutex taken, so that lock->reader remains zero. + * There is no need to update self->locks_held. + */ } -- 2.9.3