The following changes since commit 8c1ecb590497b0349c550607db923972b37f6963: Merge remote-tracking branch 'remotes/stsquad/tags/pull-testing-next-280519-2' into staging (2019-05-28 17:38:32 +0100) are available in the Git repository at: https://github.com/XanClic/qemu.git tags/pull-block-2019-05-28 for you to fetch changes up to a2d665c1bc3624a8375e2f9a7d569f7565cc1358: blockdev: loosen restrictions on drive-backup source node (2019-05-28 20:30:55 +0200) ---------------------------------------------------------------- Block patches: - qcow2: Use threads for encrypted I/O - qemu-img rebase: Optimizations - backup job: Allow any source node, and some refactoring - Some general simplifications in the block layer ---------------------------------------------------------------- Alberto Garcia (2): block: Use bdrv_unref_child() for all children in bdrv_close() block: Make bdrv_root_attach_child() unref child_bs on failure Andrey Shinkevich (1): qcow2-bitmap: initialize bitmap directory alignment Anton Nefedov (1): qcow2: skip writing zero buffers to empty COW areas John Snow (1): blockdev: loosen restrictions on drive-backup source node Sam Eiderman (3): qemu-img: rebase: Reuse parent BlockDriverState qemu-img: rebase: Reduce reads on in-chain rebase qemu-img: rebase: Reuse in-chain BlockDriverState Vladimir Sementsov-Ogievskiy (13): qcow2.h: add missing include qcow2: add separate file for threaded data processing functions qcow2-threads: use thread_pool_submit_co qcow2-threads: qcow2_co_do_compress: protect queuing by mutex qcow2-threads: split out generic path qcow2: qcow2_co_preadv: improve locking qcow2: bdrv_co_pwritev: move encryption code out of the lock qcow2: do encryption in threads block/backup: simplify backup_incremental_init_copy_bitmap block/backup: move to copy_bitmap with granularity block/backup: refactor and tolerate unallocated cluster skipping block/backup: unify different modes code path block/backup: refactor: split out backup_calculate_cluster_size block/Makefile.objs | 2 +- qapi/block-core.json | 4 +- block/qcow2.h | 26 ++- block.c | 46 +++--- block/backup.c | 243 ++++++++++++--------------- block/block-backend.c | 3 +- block/qcow2-bitmap.c | 3 +- block/qcow2-cache.c | 1 - block/qcow2-cluster.c | 10 +- block/qcow2-refcount.c | 1 - block/qcow2-snapshot.c | 1 - block/qcow2-threads.c | 268 ++++++++++++++++++++++++++++++ block/qcow2.c | 320 +++++++++++++----------------------- block/quorum.c | 1 - blockdev.c | 7 +- blockjob.c | 2 +- qemu-img.c | 85 ++++++---- tests/test-bdrv-drain.c | 6 - tests/test-bdrv-graph-mod.c | 1 - block/trace-events | 1 + tests/qemu-iotests/056 | 2 +- tests/qemu-iotests/060 | 7 +- tests/qemu-iotests/060.out | 5 +- 23 files changed, 615 insertions(+), 430 deletions(-) create mode 100644 block/qcow2-threads.c -- 2.21.0 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> qcow2.h depends on block_int.h. Compilation isn't broken currently only due to block_int.h always included before qcow2.h. Though, it seems better to directly include block_int.h in qcow2.h. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 20190506142741.41731-2-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.h | 1 + block/qcow2-bitmap.c | 1 - block/qcow2-cache.c | 1 - block/qcow2-cluster.c | 1 - block/qcow2-refcount.c | 1 - block/qcow2-snapshot.c | 1 - block/qcow2.c | 1 - 7 files changed, 1 insertion(+), 6 deletions(-) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ #include "crypto/block.h" #include "qemu/coroutine.h" #include "qemu/units.h" +#include "block/block_int.h" //#define DEBUG_ALLOC //#define DEBUG_ALLOC2 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 @@ #include "qapi/error.h" #include "qemu/cutils.h" -#include "block/block_int.h" #include "qcow2.h" /* NOTICE: BME here means Bitmaps Extension and used as a namespace for 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 @@ */ #include "qemu/osdep.h" -#include "block/block_int.h" #include "qemu-common.h" #include "qcow2.h" #include "trace.h" 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 @@ #include "qapi/error.h" #include "qemu-common.h" -#include "block/block_int.h" #include "qcow2.h" #include "qemu/bswap.h" #include "trace.h" 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 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qemu-common.h" -#include "block/block_int.h" #include "qcow2.h" #include "qemu/range.h" #include "qemu/bswap.h" 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 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "block/block_int.h" #include "qcow2.h" #include "qemu/bswap.h" #include "qemu/error-report.h" 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 @@ #define ZLIB_CONST #include <zlib.h> -#include "block/block_int.h" #include "block/qdict.h" #include "sysemu/block-backend.h" #include "qemu/module.h" -- 2.21.0 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Move compression-on-threads to separate file. Encryption will be in it too. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 20190506142741.41731-3-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/Makefile.objs | 2 +- block/qcow2.h | 7 ++ block/qcow2-threads.c | 201 ++++++++++++++++++++++++++++++++++++++++++ block/qcow2.c | 169 ----------------------------------- 4 files changed, 209 insertions(+), 170 deletions(-) create mode 100644 block/qcow2-threads.c diff --git a/block/Makefile.objs b/block/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/block/Makefile.objs +++ b/block/Makefile.objs @@ -XXX,XX +XXX,XX @@ block-obj-$(CONFIG_BOCHS) += bochs.o block-obj-$(CONFIG_VVFAT) += vvfat.o block-obj-$(CONFIG_DMG) += dmg.o -block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o qcow2-bitmap.o +block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o qcow2-bitmap.o qcow2-threads.o block-obj-$(CONFIG_QED) += qed.o qed-l2-cache.o qed-table.o qed-cluster.o block-obj-$(CONFIG_QED) += qed-check.o block-obj-y += vhdx.o vhdx-endian.o vhdx-log.o diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ void qcow2_remove_persistent_dirty_bitmap(BlockDriverState *bs, const char *name, Error **errp); +ssize_t coroutine_fn +qcow2_co_compress(BlockDriverState *bs, void *dest, size_t dest_size, + const void *src, size_t src_size); +ssize_t coroutine_fn +qcow2_co_decompress(BlockDriverState *bs, void *dest, size_t dest_size, + const void *src, size_t src_size); + #endif diff --git a/block/qcow2-threads.c b/block/qcow2-threads.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/block/qcow2-threads.c @@ -XXX,XX +XXX,XX @@ +/* + * Threaded data processing for Qcow2: compression, encryption + * + * Copyright (c) 2004-2006 Fabrice Bellard + * Copyright (c) 2018 Virtuozzo International GmbH. All rights reserved. + * + * 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" + +#define ZLIB_CONST +#include <zlib.h> + +#include "qcow2.h" +#include "block/thread-pool.h" + +#define MAX_COMPRESS_THREADS 4 + +typedef ssize_t (*Qcow2CompressFunc)(void *dest, size_t dest_size, + const void *src, size_t src_size); +typedef struct Qcow2CompressData { + void *dest; + size_t dest_size; + const void *src; + size_t src_size; + ssize_t ret; + + Qcow2CompressFunc func; +} Qcow2CompressData; + +/* + * qcow2_compress() + * + * @dest - destination buffer, @dest_size bytes + * @src - source buffer, @src_size bytes + * + * Returns: compressed size on success + * -ENOMEM destination buffer is not enough to store compressed data + * -EIO on any other error + */ +static ssize_t qcow2_compress(void *dest, size_t dest_size, + const void *src, size_t src_size) +{ + ssize_t ret; + z_stream strm; + + /* best compression, small window, no zlib header */ + memset(&strm, 0, sizeof(strm)); + ret = deflateInit2(&strm, Z_DEFAULT_COMPRESSION, Z_DEFLATED, + -12, 9, Z_DEFAULT_STRATEGY); + if (ret != Z_OK) { + return -EIO; + } + + /* + * strm.next_in is not const in old zlib versions, such as those used on + * OpenBSD/NetBSD, so cast the const away + */ + strm.avail_in = src_size; + strm.next_in = (void *) src; + strm.avail_out = dest_size; + strm.next_out = dest; + + ret = deflate(&strm, Z_FINISH); + if (ret == Z_STREAM_END) { + ret = dest_size - strm.avail_out; + } else { + ret = (ret == Z_OK ? -ENOMEM : -EIO); + } + + deflateEnd(&strm); + + return ret; +} + +/* + * qcow2_decompress() + * + * Decompress some data (not more than @src_size bytes) to produce exactly + * @dest_size bytes. + * + * @dest - destination buffer, @dest_size bytes + * @src - source buffer, @src_size bytes + * + * Returns: 0 on success + * -1 on fail + */ +static ssize_t qcow2_decompress(void *dest, size_t dest_size, + const void *src, size_t src_size) +{ + int ret = 0; + z_stream strm; + + memset(&strm, 0, sizeof(strm)); + strm.avail_in = src_size; + strm.next_in = (void *) src; + strm.avail_out = dest_size; + strm.next_out = dest; + + ret = inflateInit2(&strm, -12); + if (ret != Z_OK) { + return -1; + } + + ret = inflate(&strm, Z_FINISH); + if ((ret != Z_STREAM_END && ret != Z_BUF_ERROR) || strm.avail_out != 0) { + /* + * We approve Z_BUF_ERROR because we need @dest buffer to be filled, but + * @src buffer may be processed partly (because in qcow2 we know size of + * compressed data with precision of one sector) + */ + ret = -1; + } + + inflateEnd(&strm); + + return ret; +} + +static int qcow2_compress_pool_func(void *opaque) +{ + Qcow2CompressData *data = opaque; + + data->ret = data->func(data->dest, data->dest_size, + data->src, data->src_size); + + return 0; +} + +static void qcow2_compress_complete(void *opaque, int ret) +{ + qemu_coroutine_enter(opaque); +} + +static ssize_t coroutine_fn +qcow2_co_do_compress(BlockDriverState *bs, void *dest, size_t dest_size, + const void *src, size_t src_size, Qcow2CompressFunc func) +{ + BDRVQcow2State *s = bs->opaque; + BlockAIOCB *acb; + ThreadPool *pool = aio_get_thread_pool(bdrv_get_aio_context(bs)); + Qcow2CompressData arg = { + .dest = dest, + .dest_size = dest_size, + .src = src, + .src_size = src_size, + .func = func, + }; + + while (s->nb_compress_threads >= MAX_COMPRESS_THREADS) { + qemu_co_queue_wait(&s->compress_wait_queue, NULL); + } + + s->nb_compress_threads++; + acb = thread_pool_submit_aio(pool, qcow2_compress_pool_func, &arg, + qcow2_compress_complete, + qemu_coroutine_self()); + + if (!acb) { + s->nb_compress_threads--; + return -EINVAL; + } + qemu_coroutine_yield(); + s->nb_compress_threads--; + qemu_co_queue_next(&s->compress_wait_queue); + + return arg.ret; +} + +ssize_t coroutine_fn +qcow2_co_compress(BlockDriverState *bs, void *dest, size_t dest_size, + const void *src, size_t src_size) +{ + return qcow2_co_do_compress(bs, dest, dest_size, src, src_size, + qcow2_compress); +} + +ssize_t coroutine_fn +qcow2_co_decompress(BlockDriverState *bs, void *dest, size_t dest_size, + const void *src, size_t src_size) +{ + return qcow2_co_do_compress(bs, dest, dest_size, src, src_size, + qcow2_decompress); +} 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 @@ #include "qemu/osdep.h" -#define ZLIB_CONST -#include <zlib.h> - #include "block/qdict.h" #include "sysemu/block-backend.h" #include "qemu/module.h" @@ -XXX,XX +XXX,XX @@ #include "qapi/qobject-input-visitor.h" #include "qapi/qapi-visit-block-core.h" #include "crypto.h" -#include "block/thread-pool.h" /* Differences with QCOW: @@ -XXX,XX +XXX,XX @@ fail: return ret; } -/* - * qcow2_compress() - * - * @dest - destination buffer, @dest_size bytes - * @src - source buffer, @src_size bytes - * - * Returns: compressed size on success - * -ENOMEM destination buffer is not enough to store compressed data - * -EIO on any other error - */ -static ssize_t qcow2_compress(void *dest, size_t dest_size, - const void *src, size_t src_size) -{ - ssize_t ret; - z_stream strm; - - /* best compression, small window, no zlib header */ - memset(&strm, 0, sizeof(strm)); - ret = deflateInit2(&strm, Z_DEFAULT_COMPRESSION, Z_DEFLATED, - -12, 9, Z_DEFAULT_STRATEGY); - if (ret != Z_OK) { - return -EIO; - } - - /* strm.next_in is not const in old zlib versions, such as those used on - * OpenBSD/NetBSD, so cast the const away */ - strm.avail_in = src_size; - strm.next_in = (void *) src; - strm.avail_out = dest_size; - strm.next_out = dest; - - ret = deflate(&strm, Z_FINISH); - if (ret == Z_STREAM_END) { - ret = dest_size - strm.avail_out; - } else { - ret = (ret == Z_OK ? -ENOMEM : -EIO); - } - - deflateEnd(&strm); - - return ret; -} - -/* - * qcow2_decompress() - * - * Decompress some data (not more than @src_size bytes) to produce exactly - * @dest_size bytes. - * - * @dest - destination buffer, @dest_size bytes - * @src - source buffer, @src_size bytes - * - * Returns: 0 on success - * -1 on fail - */ -static ssize_t qcow2_decompress(void *dest, size_t dest_size, - const void *src, size_t src_size) -{ - int ret = 0; - z_stream strm; - - memset(&strm, 0, sizeof(strm)); - strm.avail_in = src_size; - strm.next_in = (void *) src; - strm.avail_out = dest_size; - strm.next_out = dest; - - ret = inflateInit2(&strm, -12); - if (ret != Z_OK) { - return -1; - } - - ret = inflate(&strm, Z_FINISH); - if ((ret != Z_STREAM_END && ret != Z_BUF_ERROR) || strm.avail_out != 0) { - /* We approve Z_BUF_ERROR because we need @dest buffer to be filled, but - * @src buffer may be processed partly (because in qcow2 we know size of - * compressed data with precision of one sector) */ - ret = -1; - } - - inflateEnd(&strm); - - return ret; -} - -#define MAX_COMPRESS_THREADS 4 - -typedef ssize_t (*Qcow2CompressFunc)(void *dest, size_t dest_size, - const void *src, size_t src_size); -typedef struct Qcow2CompressData { - void *dest; - size_t dest_size; - const void *src; - size_t src_size; - ssize_t ret; - - Qcow2CompressFunc func; -} Qcow2CompressData; - -static int qcow2_compress_pool_func(void *opaque) -{ - Qcow2CompressData *data = opaque; - - data->ret = data->func(data->dest, data->dest_size, - data->src, data->src_size); - - return 0; -} - -static void qcow2_compress_complete(void *opaque, int ret) -{ - qemu_coroutine_enter(opaque); -} - -static ssize_t coroutine_fn -qcow2_co_do_compress(BlockDriverState *bs, void *dest, size_t dest_size, - const void *src, size_t src_size, Qcow2CompressFunc func) -{ - BDRVQcow2State *s = bs->opaque; - BlockAIOCB *acb; - ThreadPool *pool = aio_get_thread_pool(bdrv_get_aio_context(bs)); - Qcow2CompressData arg = { - .dest = dest, - .dest_size = dest_size, - .src = src, - .src_size = src_size, - .func = func, - }; - - while (s->nb_compress_threads >= MAX_COMPRESS_THREADS) { - qemu_co_queue_wait(&s->compress_wait_queue, NULL); - } - - s->nb_compress_threads++; - acb = thread_pool_submit_aio(pool, qcow2_compress_pool_func, &arg, - qcow2_compress_complete, - qemu_coroutine_self()); - - if (!acb) { - s->nb_compress_threads--; - return -EINVAL; - } - qemu_coroutine_yield(); - s->nb_compress_threads--; - qemu_co_queue_next(&s->compress_wait_queue); - - return arg.ret; -} - -static ssize_t coroutine_fn -qcow2_co_compress(BlockDriverState *bs, void *dest, size_t dest_size, - const void *src, size_t src_size) -{ - return qcow2_co_do_compress(bs, dest, dest_size, src, src_size, - qcow2_compress); -} - -static ssize_t coroutine_fn -qcow2_co_decompress(BlockDriverState *bs, void *dest, size_t dest_size, - const void *src, size_t src_size) -{ - return qcow2_co_do_compress(bs, dest, dest_size, src, src_size, - qcow2_decompress); -} - /* XXX: put compressed sectors first, then all the cluster aligned tables to avoid losing bytes in alignment */ static coroutine_fn int -- 2.21.0 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Use thread_pool_submit_co, instead of reinventing it here. Note, that thread_pool_submit_aio() never returns NULL, so checking it was an extra thing. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 20190506142741.41731-4-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-threads.c | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) diff --git a/block/qcow2-threads.c b/block/qcow2-threads.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-threads.c +++ b/block/qcow2-threads.c @@ -XXX,XX +XXX,XX @@ static int qcow2_compress_pool_func(void *opaque) return 0; } -static void qcow2_compress_complete(void *opaque, int ret) -{ - qemu_coroutine_enter(opaque); -} - static ssize_t coroutine_fn qcow2_co_do_compress(BlockDriverState *bs, void *dest, size_t dest_size, const void *src, size_t src_size, Qcow2CompressFunc func) { BDRVQcow2State *s = bs->opaque; - BlockAIOCB *acb; ThreadPool *pool = aio_get_thread_pool(bdrv_get_aio_context(bs)); Qcow2CompressData arg = { .dest = dest, @@ -XXX,XX +XXX,XX @@ qcow2_co_do_compress(BlockDriverState *bs, void *dest, size_t dest_size, } s->nb_compress_threads++; - acb = thread_pool_submit_aio(pool, qcow2_compress_pool_func, &arg, - qcow2_compress_complete, - qemu_coroutine_self()); - - if (!acb) { - s->nb_compress_threads--; - return -EINVAL; - } - qemu_coroutine_yield(); + thread_pool_submit_co(pool, qcow2_compress_pool_func, &arg); s->nb_compress_threads--; + qemu_co_queue_next(&s->compress_wait_queue); return arg.ret; -- 2.21.0 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Drop dependence on AioContext lock. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 20190506142741.41731-5-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-threads.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/block/qcow2-threads.c b/block/qcow2-threads.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-threads.c +++ b/block/qcow2-threads.c @@ -XXX,XX +XXX,XX @@ qcow2_co_do_compress(BlockDriverState *bs, void *dest, size_t dest_size, .func = func, }; + qemu_co_mutex_lock(&s->lock); while (s->nb_compress_threads >= MAX_COMPRESS_THREADS) { - qemu_co_queue_wait(&s->compress_wait_queue, NULL); + qemu_co_queue_wait(&s->compress_wait_queue, &s->lock); } - s->nb_compress_threads++; + qemu_co_mutex_unlock(&s->lock); + thread_pool_submit_co(pool, qcow2_compress_pool_func, &arg); - s->nb_compress_threads--; + qemu_co_mutex_lock(&s->lock); + s->nb_compress_threads--; qemu_co_queue_next(&s->compress_wait_queue); + qemu_co_mutex_unlock(&s->lock); return arg.ret; } -- 2.21.0 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Move generic part out of qcow2_co_do_compress, to reuse it for encryption and rename things that would be shared with encryption path. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 20190506142741.41731-6-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.h | 4 ++-- block/qcow2-threads.c | 47 ++++++++++++++++++++++++++++--------------- block/qcow2.c | 2 +- 3 files changed, 34 insertions(+), 19 deletions(-) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ typedef struct BDRVQcow2State { char *image_backing_format; char *image_data_file; - CoQueue compress_wait_queue; - int nb_compress_threads; + CoQueue thread_task_queue; + int nb_threads; BdrvChild *data_file; } BDRVQcow2State; diff --git a/block/qcow2-threads.c b/block/qcow2-threads.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-threads.c +++ b/block/qcow2-threads.c @@ -XXX,XX +XXX,XX @@ #include "qcow2.h" #include "block/thread-pool.h" -#define MAX_COMPRESS_THREADS 4 +#define QCOW2_MAX_THREADS 4 + +static int coroutine_fn +qcow2_co_process(BlockDriverState *bs, ThreadPoolFunc *func, void *arg) +{ + int ret; + BDRVQcow2State *s = bs->opaque; + ThreadPool *pool = aio_get_thread_pool(bdrv_get_aio_context(bs)); + + qemu_co_mutex_lock(&s->lock); + while (s->nb_threads >= QCOW2_MAX_THREADS) { + qemu_co_queue_wait(&s->thread_task_queue, &s->lock); + } + s->nb_threads++; + qemu_co_mutex_unlock(&s->lock); + + ret = thread_pool_submit_co(pool, func, arg); + + qemu_co_mutex_lock(&s->lock); + s->nb_threads--; + qemu_co_queue_next(&s->thread_task_queue); + qemu_co_mutex_unlock(&s->lock); + + return ret; +} + + +/* + * Compression + */ typedef ssize_t (*Qcow2CompressFunc)(void *dest, size_t dest_size, const void *src, size_t src_size); @@ -XXX,XX +XXX,XX @@ static ssize_t coroutine_fn qcow2_co_do_compress(BlockDriverState *bs, void *dest, size_t dest_size, const void *src, size_t src_size, Qcow2CompressFunc func) { - BDRVQcow2State *s = bs->opaque; - ThreadPool *pool = aio_get_thread_pool(bdrv_get_aio_context(bs)); Qcow2CompressData arg = { .dest = dest, .dest_size = dest_size, @@ -XXX,XX +XXX,XX @@ qcow2_co_do_compress(BlockDriverState *bs, void *dest, size_t dest_size, .func = func, }; - qemu_co_mutex_lock(&s->lock); - while (s->nb_compress_threads >= MAX_COMPRESS_THREADS) { - qemu_co_queue_wait(&s->compress_wait_queue, &s->lock); - } - s->nb_compress_threads++; - qemu_co_mutex_unlock(&s->lock); - - thread_pool_submit_co(pool, qcow2_compress_pool_func, &arg); - - qemu_co_mutex_lock(&s->lock); - s->nb_compress_threads--; - qemu_co_queue_next(&s->compress_wait_queue); - qemu_co_mutex_unlock(&s->lock); + qcow2_co_process(bs, qcow2_compress_pool_func, &arg); return arg.ret; } 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_do_open(BlockDriverState *bs, QDict *options, } #endif - qemu_co_queue_init(&s->compress_wait_queue); + qemu_co_queue_init(&s->thread_task_queue); return ret; -- 2.21.0 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Background: decryption will be done in threads, to take benefit of it, we should move it out of the lock first. But let's go further: it turns out, that only qcow2_get_cluster_offset() needs locking, so reduce locking to it. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-id: 20190506142741.41731-7-vsementsov@virtuozzo.com Reviewed-by: Alberto Garcia <berto@igalia.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 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 @@ static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, qemu_iovec_init(&hd_qiov, qiov->niov); - qemu_co_mutex_lock(&s->lock); - while (bytes != 0) { /* prepare next request */ @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size); } + qemu_co_mutex_lock(&s->lock); ret = qcow2_get_cluster_offset(bs, offset, &cur_bytes, &cluster_offset); + qemu_co_mutex_unlock(&s->lock); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, if (bs->backing) { BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO); - qemu_co_mutex_unlock(&s->lock); ret = bdrv_co_preadv(bs->backing, offset, cur_bytes, &hd_qiov, 0); - qemu_co_mutex_lock(&s->lock); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, break; case QCOW2_CLUSTER_COMPRESSED: - qemu_co_mutex_unlock(&s->lock); ret = qcow2_co_preadv_compressed(bs, cluster_offset, offset, cur_bytes, &hd_qiov); - qemu_co_mutex_lock(&s->lock); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, } BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO); - qemu_co_mutex_unlock(&s->lock); ret = bdrv_co_preadv(s->data_file, cluster_offset + offset_in_cluster, cur_bytes, &hd_qiov, 0); - qemu_co_mutex_lock(&s->lock); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, ret = 0; fail: - qemu_co_mutex_unlock(&s->lock); - qemu_iovec_destroy(&hd_qiov); qemu_vfree(cluster_data); -- 2.21.0 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Encryption will be done in threads, to take benefit of it, we should move it out of the lock first. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 20190506142741.41731-8-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.c | 35 +++++++++++++++++++++-------------- 1 file changed, 21 insertions(+), 14 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 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, ret = qcow2_alloc_cluster_offset(bs, offset, &cur_bytes, &cluster_offset, &l2meta); if (ret < 0) { - goto fail; + goto out_locked; } assert((cluster_offset & 511) == 0); + ret = qcow2_pre_write_overlap_check(bs, 0, + cluster_offset + offset_in_cluster, + cur_bytes, true); + if (ret < 0) { + goto out_locked; + } + + qemu_co_mutex_unlock(&s->lock); + qemu_iovec_reset(&hd_qiov); qemu_iovec_concat(&hd_qiov, qiov, bytes_done, cur_bytes); @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, * s->cluster_size); if (cluster_data == NULL) { ret = -ENOMEM; - goto fail; + goto out_unlocked; } } @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, cluster_data, cur_bytes, NULL) < 0) { ret = -EIO; - goto fail; + goto out_unlocked; } qemu_iovec_reset(&hd_qiov); qemu_iovec_add(&hd_qiov, cluster_data, cur_bytes); } - ret = qcow2_pre_write_overlap_check(bs, 0, - cluster_offset + offset_in_cluster, cur_bytes, true); - if (ret < 0) { - goto fail; - } - /* If we need to do COW, check if it's possible to merge the * writing of the guest data together with that of the COW regions. * If it's not possible (or not necessary) then write the * guest data now. */ if (!merge_cow(offset, cur_bytes, &hd_qiov, l2meta)) { - qemu_co_mutex_unlock(&s->lock); BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO); trace_qcow2_writev_data(qemu_coroutine_self(), cluster_offset + offset_in_cluster); ret = bdrv_co_pwritev(s->data_file, cluster_offset + offset_in_cluster, cur_bytes, &hd_qiov, 0); - qemu_co_mutex_lock(&s->lock); if (ret < 0) { - goto fail; + goto out_unlocked; } } + qemu_co_mutex_lock(&s->lock); + ret = qcow2_handle_l2meta(bs, &l2meta, true); if (ret) { - goto fail; + goto out_locked; } bytes -= cur_bytes; @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, trace_qcow2_writev_done_part(qemu_coroutine_self(), cur_bytes); } ret = 0; + goto out_locked; -fail: +out_unlocked: + qemu_co_mutex_lock(&s->lock); + +out_locked: qcow2_handle_l2meta(bs, &l2meta, false); qemu_co_mutex_unlock(&s->lock); -- 2.21.0 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Do encryption/decryption in threads, like it is already done for compression. This improves asynchronous encrypted io. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 20190506142741.41731-9-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.h | 8 ++++++ block/qcow2-cluster.c | 7 ++--- block/qcow2-threads.c | 65 +++++++++++++++++++++++++++++++++++++++++-- block/qcow2.c | 22 +++++---------- 4 files changed, 81 insertions(+), 21 deletions(-) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ typedef struct Qcow2BitmapHeaderExt { uint64_t bitmap_directory_offset; } QEMU_PACKED Qcow2BitmapHeaderExt; +#define QCOW2_MAX_THREADS 4 + typedef struct BDRVQcow2State { int cluster_bits; int cluster_size; @@ -XXX,XX +XXX,XX @@ qcow2_co_compress(BlockDriverState *bs, void *dest, size_t dest_size, ssize_t coroutine_fn qcow2_co_decompress(BlockDriverState *bs, void *dest, size_t dest_size, const void *src, size_t src_size); +int coroutine_fn +qcow2_co_encrypt(BlockDriverState *bs, uint64_t file_cluster_offset, + uint64_t offset, void *buf, size_t len); +int coroutine_fn +qcow2_co_decrypt(BlockDriverState *bs, uint64_t file_cluster_offset, + uint64_t offset, void *buf, size_t len); #endif 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 bool coroutine_fn do_perform_cow_encrypt(BlockDriverState *bs, { if (bytes && bs->encrypted) { BDRVQcow2State *s = bs->opaque; - int64_t offset = (s->crypt_physical_offset ? - (cluster_offset + offset_in_cluster) : - (src_cluster_offset + offset_in_cluster)); assert((offset_in_cluster & ~BDRV_SECTOR_MASK) == 0); assert((bytes & ~BDRV_SECTOR_MASK) == 0); assert(s->crypto); - if (qcrypto_block_encrypt(s->crypto, offset, buffer, bytes, NULL) < 0) { + if (qcow2_co_encrypt(bs, cluster_offset, + src_cluster_offset + offset_in_cluster, + buffer, bytes) < 0) { return false; } } diff --git a/block/qcow2-threads.c b/block/qcow2-threads.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-threads.c +++ b/block/qcow2-threads.c @@ -XXX,XX +XXX,XX @@ #include "qcow2.h" #include "block/thread-pool.h" - -#define QCOW2_MAX_THREADS 4 +#include "crypto.h" static int coroutine_fn qcow2_co_process(BlockDriverState *bs, ThreadPoolFunc *func, void *arg) @@ -XXX,XX +XXX,XX @@ qcow2_co_decompress(BlockDriverState *bs, void *dest, size_t dest_size, return qcow2_co_do_compress(bs, dest, dest_size, src, src_size, qcow2_decompress); } + + +/* + * Cryptography + */ + +/* + * Qcow2EncDecFunc: common prototype of qcrypto_block_encrypt() and + * qcrypto_block_decrypt() functions. + */ +typedef int (*Qcow2EncDecFunc)(QCryptoBlock *block, uint64_t offset, + uint8_t *buf, size_t len, Error **errp); + +typedef struct Qcow2EncDecData { + QCryptoBlock *block; + uint64_t offset; + uint8_t *buf; + size_t len; + + Qcow2EncDecFunc func; +} Qcow2EncDecData; + +static int qcow2_encdec_pool_func(void *opaque) +{ + Qcow2EncDecData *data = opaque; + + return data->func(data->block, data->offset, data->buf, data->len, NULL); +} + +static int coroutine_fn +qcow2_co_encdec(BlockDriverState *bs, uint64_t file_cluster_offset, + uint64_t offset, void *buf, size_t len, Qcow2EncDecFunc func) +{ + BDRVQcow2State *s = bs->opaque; + Qcow2EncDecData arg = { + .block = s->crypto, + .offset = s->crypt_physical_offset ? + file_cluster_offset + offset_into_cluster(s, offset) : + offset, + .buf = buf, + .len = len, + .func = func, + }; + + return qcow2_co_process(bs, qcow2_encdec_pool_func, &arg); +} + +int coroutine_fn +qcow2_co_encrypt(BlockDriverState *bs, uint64_t file_cluster_offset, + uint64_t offset, void *buf, size_t len) +{ + return qcow2_co_encdec(bs, file_cluster_offset, offset, buf, len, + qcrypto_block_encrypt); +} + +int coroutine_fn +qcow2_co_decrypt(BlockDriverState *bs, uint64_t file_cluster_offset, + uint64_t offset, void *buf, size_t len) +{ + return qcow2_co_encdec(bs, file_cluster_offset, offset, buf, len, + qcrypto_block_decrypt); +} 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_read_extensions(BlockDriverState *bs, uint64_t start_offset, } s->crypto = qcrypto_block_open(s->crypto_opts, "encrypt.", qcow2_crypto_hdr_read_func, - bs, cflags, 1, errp); + bs, cflags, QCOW2_MAX_THREADS, errp); if (!s->crypto) { return -EINVAL; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, cflags |= QCRYPTO_BLOCK_OPEN_NO_IO; } s->crypto = qcrypto_block_open(s->crypto_opts, "encrypt.", - NULL, NULL, cflags, 1, errp); + NULL, NULL, cflags, + QCOW2_MAX_THREADS, errp); if (!s->crypto) { ret = -EINVAL; goto fail; @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, assert(s->crypto); assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0); assert((cur_bytes & (BDRV_SECTOR_SIZE - 1)) == 0); - if (qcrypto_block_decrypt(s->crypto, - (s->crypt_physical_offset ? - cluster_offset + offset_in_cluster : - offset), - cluster_data, - cur_bytes, - NULL) < 0) { + if (qcow2_co_decrypt(bs, cluster_offset, offset, + cluster_data, cur_bytes) < 0) { ret = -EIO; goto fail; } @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size); qemu_iovec_to_buf(&hd_qiov, 0, cluster_data, hd_qiov.size); - if (qcrypto_block_encrypt(s->crypto, - (s->crypt_physical_offset ? - cluster_offset + offset_in_cluster : - offset), - cluster_data, - cur_bytes, NULL) < 0) { + if (qcow2_co_encrypt(bs, cluster_offset, offset, + cluster_data, cur_bytes) < 0) { ret = -EIO; goto out_unlocked; } -- 2.21.0 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Simplify backup_incremental_init_copy_bitmap using the function bdrv_dirty_bitmap_next_dirty_area. Note: move to job->len instead of bitmap size: it should not matter but less code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 20190429090842.57910-2-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/backup.c | 40 ++++++++++++---------------------------- 1 file changed, 12 insertions(+), 28 deletions(-) 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 int coroutine_fn backup_run_incremental(BackupBlockJob *job) /* init copy_bitmap from sync_bitmap */ static void backup_incremental_init_copy_bitmap(BackupBlockJob *job) { - BdrvDirtyBitmapIter *dbi; - int64_t offset; - int64_t end = DIV_ROUND_UP(bdrv_dirty_bitmap_size(job->sync_bitmap), - job->cluster_size); - - dbi = bdrv_dirty_iter_new(job->sync_bitmap); - while ((offset = bdrv_dirty_iter_next(dbi)) != -1) { - int64_t cluster = offset / job->cluster_size; - int64_t next_cluster; - - offset += bdrv_dirty_bitmap_granularity(job->sync_bitmap); - if (offset >= bdrv_dirty_bitmap_size(job->sync_bitmap)) { - hbitmap_set(job->copy_bitmap, cluster, end - cluster); - break; - } + uint64_t offset = 0; + uint64_t bytes = job->len; - offset = bdrv_dirty_bitmap_next_zero(job->sync_bitmap, offset, - UINT64_MAX); - if (offset == -1) { - hbitmap_set(job->copy_bitmap, cluster, end - cluster); - break; - } + while (bdrv_dirty_bitmap_next_dirty_area(job->sync_bitmap, + &offset, &bytes)) + { + uint64_t cluster = offset / job->cluster_size; + uint64_t end_cluster = DIV_ROUND_UP(offset + bytes, job->cluster_size); - next_cluster = DIV_ROUND_UP(offset, job->cluster_size); - hbitmap_set(job->copy_bitmap, cluster, next_cluster - cluster); - if (next_cluster >= end) { + hbitmap_set(job->copy_bitmap, cluster, end_cluster - cluster); + + offset = end_cluster * job->cluster_size; + if (offset >= job->len) { break; } - - bdrv_set_dirty_iter(dbi, next_cluster * job->cluster_size); + bytes = job->len - offset; } /* TODO job_progress_set_remaining() would make more sense */ job_progress_update(&job->common.job, job->len - hbitmap_count(job->copy_bitmap) * job->cluster_size); - - bdrv_dirty_iter_free(dbi); } static int coroutine_fn backup_run(Job *job, Error **errp) -- 2.21.0 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We are going to share this bitmap between backup and backup-top filter driver, so let's share something more meaningful. It also simplifies some calculations. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 20190429090842.57910-3-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/backup.c | 48 +++++++++++++++++++++++------------------------- 1 file changed, 23 insertions(+), 25 deletions(-) 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 int coroutine_fn backup_cow_with_bounce_buffer(BackupBlockJob *job, int read_flags = is_write_notifier ? BDRV_REQ_NO_SERIALISING : 0; int write_flags = job->serialize_target_writes ? BDRV_REQ_SERIALISING : 0; - hbitmap_reset(job->copy_bitmap, start / job->cluster_size, 1); + assert(QEMU_IS_ALIGNED(start, job->cluster_size)); + hbitmap_reset(job->copy_bitmap, start, job->cluster_size); nbytes = MIN(job->cluster_size, job->len - start); if (!*bounce_buffer) { *bounce_buffer = blk_blockalign(blk, job->cluster_size); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_cow_with_bounce_buffer(BackupBlockJob *job, return nbytes; fail: - hbitmap_set(job->copy_bitmap, start / job->cluster_size, 1); + hbitmap_set(job->copy_bitmap, start, job->cluster_size); return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_cow_with_offload(BackupBlockJob *job, int write_flags = job->serialize_target_writes ? BDRV_REQ_SERIALISING : 0; assert(QEMU_IS_ALIGNED(job->copy_range_size, job->cluster_size)); + assert(QEMU_IS_ALIGNED(start, job->cluster_size)); nbytes = MIN(job->copy_range_size, end - start); nr_clusters = DIV_ROUND_UP(nbytes, job->cluster_size); - hbitmap_reset(job->copy_bitmap, start / job->cluster_size, - nr_clusters); + hbitmap_reset(job->copy_bitmap, start, job->cluster_size * nr_clusters); ret = blk_co_copy_range(blk, start, job->target, start, nbytes, read_flags, write_flags); if (ret < 0) { trace_backup_do_cow_copy_range_fail(job, start, ret); - hbitmap_set(job->copy_bitmap, start / job->cluster_size, - nr_clusters); + hbitmap_set(job->copy_bitmap, start, job->cluster_size * nr_clusters); return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_do_cow(BackupBlockJob *job, cow_request_begin(&cow_request, job, start, end); while (start < end) { - if (!hbitmap_get(job->copy_bitmap, start / job->cluster_size)) { + if (!hbitmap_get(job->copy_bitmap, start)) { trace_backup_do_cow_skip(job, start); start += job->cluster_size; continue; /* already copied */ @@ -XXX,XX +XXX,XX @@ static void backup_clean(Job *job) assert(s->target); blk_unref(s->target); s->target = NULL; + + if (s->copy_bitmap) { + hbitmap_free(s->copy_bitmap); + s->copy_bitmap = NULL; + } } void backup_do_checkpoint(BlockJob *job, Error **errp) { BackupBlockJob *backup_job = container_of(job, BackupBlockJob, common); - int64_t len; assert(block_job_driver(job) == &backup_job_driver); @@ -XXX,XX +XXX,XX @@ void backup_do_checkpoint(BlockJob *job, Error **errp) return; } - len = DIV_ROUND_UP(backup_job->len, backup_job->cluster_size); - hbitmap_set(backup_job->copy_bitmap, 0, len); + hbitmap_set(backup_job->copy_bitmap, 0, backup_job->len); } static void backup_drain(BlockJob *job) @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_run_incremental(BackupBlockJob *job) { int ret; bool error_is_read; - int64_t cluster; + int64_t offset; HBitmapIter hbi; hbitmap_iter_init(&hbi, job->copy_bitmap, 0); - while ((cluster = hbitmap_iter_next(&hbi)) != -1) { + while ((offset = hbitmap_iter_next(&hbi)) != -1) { do { if (yield_and_check(job)) { return 0; } - ret = backup_do_cow(job, cluster * job->cluster_size, + ret = backup_do_cow(job, offset, job->cluster_size, &error_is_read, false); if (ret < 0 && backup_error_action(job, error_is_read, -ret) == BLOCK_ERROR_ACTION_REPORT) @@ -XXX,XX +XXX,XX @@ static void backup_incremental_init_copy_bitmap(BackupBlockJob *job) while (bdrv_dirty_bitmap_next_dirty_area(job->sync_bitmap, &offset, &bytes)) { - uint64_t cluster = offset / job->cluster_size; - uint64_t end_cluster = DIV_ROUND_UP(offset + bytes, job->cluster_size); + hbitmap_set(job->copy_bitmap, offset, bytes); - hbitmap_set(job->copy_bitmap, cluster, end_cluster - cluster); - - offset = end_cluster * job->cluster_size; + offset += bytes; if (offset >= job->len) { break; } @@ -XXX,XX +XXX,XX @@ static void backup_incremental_init_copy_bitmap(BackupBlockJob *job) /* TODO job_progress_set_remaining() would make more sense */ job_progress_update(&job->common.job, - job->len - hbitmap_count(job->copy_bitmap) * job->cluster_size); + job->len - hbitmap_count(job->copy_bitmap)); } static int coroutine_fn backup_run(Job *job, Error **errp) { BackupBlockJob *s = container_of(job, BackupBlockJob, common.job); BlockDriverState *bs = blk_bs(s->common.blk); - int64_t offset, nb_clusters; + int64_t offset; int ret = 0; QLIST_INIT(&s->inflight_reqs); qemu_co_rwlock_init(&s->flush_rwlock); - nb_clusters = DIV_ROUND_UP(s->len, s->cluster_size); job_progress_set_remaining(job, s->len); - s->copy_bitmap = hbitmap_alloc(nb_clusters, 0); if (s->sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) { backup_incremental_init_copy_bitmap(s); } else { - hbitmap_set(s->copy_bitmap, 0, nb_clusters); + hbitmap_set(s->copy_bitmap, 0, s->len); } - s->before_write.notify = backup_before_write_notify; bdrv_add_before_write_notifier(bs, &s->before_write); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_run(Job *job, Error **errp) /* wait until pending backup_do_cow() calls have completed */ qemu_co_rwlock_wrlock(&s->flush_rwlock); qemu_co_rwlock_unlock(&s->flush_rwlock); - hbitmap_free(s->copy_bitmap); return ret; } @@ -XXX,XX +XXX,XX @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, } else { job->cluster_size = MAX(BACKUP_CLUSTER_SIZE_DEFAULT, bdi.cluster_size); } + + job->copy_bitmap = hbitmap_alloc(len, ctz32(job->cluster_size)); job->use_copy_range = true; job->copy_range_size = MIN_NON_ZERO(blk_get_max_transfer(job->common.blk), blk_get_max_transfer(job->target)); -- 2.21.0 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Split allocation checking to separate function and reduce nesting. Consider bdrv_is_allocated() fail as allocated area, as copying more than needed is not wrong (and we do it anyway) and seems better than fail the whole job. And, most probably we will fail on the next read, if there are real problem with source. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 20190429090842.57910-4-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/backup.c | 60 +++++++++++++++++++------------------------------- 1 file changed, 23 insertions(+), 37 deletions(-) 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 bool coroutine_fn yield_and_check(BackupBlockJob *job) return false; } +static bool bdrv_is_unallocated_range(BlockDriverState *bs, + int64_t offset, int64_t bytes) +{ + int64_t end = offset + bytes; + + while (offset < end && !bdrv_is_allocated(bs, offset, bytes, &bytes)) { + if (bytes == 0) { + return true; + } + offset += bytes; + bytes = end - offset; + } + + return offset >= end; +} + static int coroutine_fn backup_run_incremental(BackupBlockJob *job) { int ret; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_run(Job *job, Error **errp) for (offset = 0; offset < s->len; offset += s->cluster_size) { bool error_is_read; - int alloced = 0; if (yield_and_check(s)) { break; } - if (s->sync_mode == MIRROR_SYNC_MODE_TOP) { - int i; - int64_t n; - - /* Check to see if these blocks are already in the - * backing file. */ - - for (i = 0; i < s->cluster_size;) { - /* bdrv_is_allocated() only returns true/false based - * on the first set of sectors it comes across that - * are are all in the same state. - * For that reason we must verify each sector in the - * backup cluster length. We end up copying more than - * needed but at some point that is always the case. */ - alloced = - bdrv_is_allocated(bs, offset + i, - s->cluster_size - i, &n); - i += n; - - if (alloced || n == 0) { - break; - } - } - - /* If the above loop never found any sectors that are in - * the topmost image, skip this backup. */ - if (alloced == 0) { - continue; - } - } - /* FULL sync mode we copy the whole drive. */ - if (alloced < 0) { - ret = alloced; - } else { - ret = backup_do_cow(s, offset, s->cluster_size, - &error_is_read, false); + if (s->sync_mode == MIRROR_SYNC_MODE_TOP && + bdrv_is_unallocated_range(bs, offset, s->cluster_size)) + { + continue; } + + ret = backup_do_cow(s, offset, s->cluster_size, + &error_is_read, false); if (ret < 0) { /* Depending on error action, fail now or retry cluster */ BlockErrorAction action = -- 2.21.0 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Do full, top and incremental mode copying all in one place. This unifies the code path and helps further improvements. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 20190429090842.57910-5-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/backup.c | 43 ++++++++++--------------------------------- 1 file changed, 10 insertions(+), 33 deletions(-) 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 bool bdrv_is_unallocated_range(BlockDriverState *bs, return offset >= end; } -static int coroutine_fn backup_run_incremental(BackupBlockJob *job) +static int coroutine_fn backup_loop(BackupBlockJob *job) { int ret; bool error_is_read; int64_t offset; HBitmapIter hbi; + BlockDriverState *bs = blk_bs(job->common.blk); hbitmap_iter_init(&hbi, job->copy_bitmap, 0); while ((offset = hbitmap_iter_next(&hbi)) != -1) { + if (job->sync_mode == MIRROR_SYNC_MODE_TOP && + bdrv_is_unallocated_range(bs, offset, job->cluster_size)) + { + hbitmap_reset(job->copy_bitmap, offset, job->cluster_size); + continue; + } + do { if (yield_and_check(job)) { return 0; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_run(Job *job, Error **errp) { BackupBlockJob *s = container_of(job, BackupBlockJob, common.job); BlockDriverState *bs = blk_bs(s->common.blk); - int64_t offset; int ret = 0; QLIST_INIT(&s->inflight_reqs); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_run(Job *job, Error **errp) * notify callback service CoW requests. */ job_yield(job); } - } else if (s->sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) { - ret = backup_run_incremental(s); } else { - /* Both FULL and TOP SYNC_MODE's require copying.. */ - for (offset = 0; offset < s->len; - offset += s->cluster_size) { - bool error_is_read; - - if (yield_and_check(s)) { - break; - } - - if (s->sync_mode == MIRROR_SYNC_MODE_TOP && - bdrv_is_unallocated_range(bs, offset, s->cluster_size)) - { - continue; - } - - ret = backup_do_cow(s, offset, s->cluster_size, - &error_is_read, false); - if (ret < 0) { - /* Depending on error action, fail now or retry cluster */ - BlockErrorAction action = - backup_error_action(s, error_is_read, -ret); - if (action == BLOCK_ERROR_ACTION_REPORT) { - break; - } else { - offset -= s->cluster_size; - continue; - } - } - } + ret = backup_loop(s); } notifier_with_return_remove(&s->before_write); -- 2.21.0 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Split out cluster_size calculation. Move copy-bitmap creation above block-job creation, as we are going to share it with upcoming backup-top filter, which also should be created before actual block job creation. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-id: 20190429090842.57910-6-vsementsov@virtuozzo.com [mreitz: Dropped a paragraph from the commit message that was left over from a previous version] Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/backup.c | 82 ++++++++++++++++++++++++++++++++------------------ 1 file changed, 52 insertions(+), 30 deletions(-) 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 const BlockJobDriver backup_job_driver = { .drain = backup_drain, }; +static int64_t backup_calculate_cluster_size(BlockDriverState *target, + Error **errp) +{ + int ret; + BlockDriverInfo bdi; + + /* + * If there is no backing file on the target, we cannot rely on COW if our + * backup cluster size is smaller than the target cluster size. Even for + * targets with a backing file, try to avoid COW if possible. + */ + ret = bdrv_get_info(target, &bdi); + if (ret == -ENOTSUP && !target->backing) { + /* Cluster size is not defined */ + warn_report("The target block device doesn't provide " + "information about the block size and it doesn't have a " + "backing file. The default block size of %u bytes is " + "used. If the actual block size of the target exceeds " + "this default, the backup may be unusable", + BACKUP_CLUSTER_SIZE_DEFAULT); + return BACKUP_CLUSTER_SIZE_DEFAULT; + } else if (ret < 0 && !target->backing) { + error_setg_errno(errp, -ret, + "Couldn't determine the cluster size of the target image, " + "which has no backing file"); + error_append_hint(errp, + "Aborting, since this may create an unusable destination image\n"); + return ret; + } else if (ret < 0 && target->backing) { + /* Not fatal; just trudge on ahead. */ + return BACKUP_CLUSTER_SIZE_DEFAULT; + } + + return MAX(BACKUP_CLUSTER_SIZE_DEFAULT, bdi.cluster_size); +} + BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, BlockDriverState *target, int64_t speed, MirrorSyncMode sync_mode, BdrvDirtyBitmap *sync_bitmap, @@ -XXX,XX +XXX,XX @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, JobTxn *txn, Error **errp) { int64_t len; - BlockDriverInfo bdi; BackupBlockJob *job = NULL; int ret; + int64_t cluster_size; + HBitmap *copy_bitmap = NULL; assert(bs); assert(target); @@ -XXX,XX +XXX,XX @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, goto error; } + cluster_size = backup_calculate_cluster_size(target, errp); + if (cluster_size < 0) { + goto error; + } + + copy_bitmap = hbitmap_alloc(len, ctz32(cluster_size)); + /* job->len is fixed, so we can't allow resize */ job = block_job_create(job_id, &backup_job_driver, txn, bs, BLK_PERM_CONSISTENT_READ, @@ -XXX,XX +XXX,XX @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, /* Detect image-fleecing (and similar) schemes */ job->serialize_target_writes = bdrv_chain_contains(target, bs); - - /* If there is no backing file on the target, we cannot rely on COW if our - * backup cluster size is smaller than the target cluster size. Even for - * targets with a backing file, try to avoid COW if possible. */ - ret = bdrv_get_info(target, &bdi); - if (ret == -ENOTSUP && !target->backing) { - /* Cluster size is not defined */ - warn_report("The target block device doesn't provide " - "information about the block size and it doesn't have a " - "backing file. The default block size of %u bytes is " - "used. If the actual block size of the target exceeds " - "this default, the backup may be unusable", - BACKUP_CLUSTER_SIZE_DEFAULT); - job->cluster_size = BACKUP_CLUSTER_SIZE_DEFAULT; - } else if (ret < 0 && !target->backing) { - error_setg_errno(errp, -ret, - "Couldn't determine the cluster size of the target image, " - "which has no backing file"); - error_append_hint(errp, - "Aborting, since this may create an unusable destination image\n"); - goto error; - } else if (ret < 0 && target->backing) { - /* Not fatal; just trudge on ahead. */ - job->cluster_size = BACKUP_CLUSTER_SIZE_DEFAULT; - } else { - job->cluster_size = MAX(BACKUP_CLUSTER_SIZE_DEFAULT, bdi.cluster_size); - } - - job->copy_bitmap = hbitmap_alloc(len, ctz32(job->cluster_size)); + job->cluster_size = cluster_size; + job->copy_bitmap = copy_bitmap; + copy_bitmap = NULL; job->use_copy_range = true; job->copy_range_size = MIN_NON_ZERO(blk_get_max_transfer(job->common.blk), blk_get_max_transfer(job->target)); @@ -XXX,XX +XXX,XX @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, return &job->common; error: + if (copy_bitmap) { + assert(!job || !job->copy_bitmap); + hbitmap_free(copy_bitmap); + } if (sync_bitmap) { bdrv_reclaim_dirty_bitmap(bs, sync_bitmap, NULL); } -- 2.21.0 From: Alberto Garcia <berto@igalia.com> bdrv_unref_child() does the following things: - Updates the child->bs->inherits_from pointer. - Calls bdrv_detach_child() to remove the BdrvChild from bs->children. - Calls bdrv_unref() to unref the child BlockDriverState. When bdrv_unref_child() was introduced in commit 33a604075c it was not used in bdrv_close() because the drivers that had additional children (like quorum or blkverify) had already called bdrv_unref() on their children during their own close functions. This was changed later (in 0bd6e91a7e for quorum, in 3e586be0b2 for blkverify) so there's no reason not to use bdrv_unref_child() in bdrv_close() anymore. After this there's also no need to remove bs->backing and bs->file separately from the rest of the children, so bdrv_close() can be simplified. Now bdrv_close() unrefs all children (before this patch it was only bs->file and bs->backing). As a result, none of the callers of brvd_attach_child() should remove their reference to child_bs (because this function effectively steals that reference). This patch updates a couple of tests that were doing their own bdrv_unref(). Signed-off-by: Alberto Garcia <berto@igalia.com> Message-id: 6d1d5feaa53aa1ab127adb73d605dc4503e3abd5.1557754872.git.berto@igalia.com [mreitz: s/where/were/] Signed-off-by: Max Reitz <mreitz@redhat.com> --- block.c | 16 +++------------- tests/test-bdrv-drain.c | 6 ------ tests/test-bdrv-graph-mod.c | 1 - 3 files changed, 3 insertions(+), 20 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_close(BlockDriverState *bs) bs->drv = NULL; } - bdrv_set_backing_hd(bs, NULL, &error_abort); - - if (bs->file != NULL) { - bdrv_unref_child(bs, bs->file); - bs->file = NULL; - } - QLIST_FOREACH_SAFE(child, &bs->children, next, next) { - /* TODO Remove bdrv_unref() from drivers' close function and use - * bdrv_unref_child() here */ - if (child->bs->inherits_from == bs) { - child->bs->inherits_from = NULL; - } - bdrv_detach_child(child); + bdrv_unref_child(bs, child); } + bs->backing = NULL; + bs->file = NULL; g_free(bs->opaque); bs->opaque = NULL; atomic_set(&bs->copy_on_read, 0); diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_detach_indirect(bool by_parent_cb) bdrv_unref(parent_b); blk_unref(blk); - /* XXX Once bdrv_close() unref's children instead of just detaching them, - * this won't be necessary any more. */ - bdrv_unref(a); - bdrv_unref(a); - bdrv_unref(c); - g_assert_cmpint(a->refcnt, ==, 1); g_assert_cmpint(b->refcnt, ==, 1); g_assert_cmpint(c->refcnt, ==, 1); diff --git a/tests/test-bdrv-graph-mod.c b/tests/test-bdrv-graph-mod.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-graph-mod.c +++ b/tests/test-bdrv-graph-mod.c @@ -XXX,XX +XXX,XX @@ static void test_update_perm_tree(void) g_assert_nonnull(local_err); error_free(local_err); - bdrv_unref(bs); blk_unref(root); } -- 2.21.0 From: Alberto Garcia <berto@igalia.com> A consequence of the previous patch is that bdrv_attach_child() transfers the reference to child_bs from the caller to parent_bs, which will drop it on bdrv_close() or when someone calls bdrv_unref_child(). But this only happens when bdrv_attach_child() succeeds. If it fails then the caller is responsible for dropping the reference to child_bs. This patch makes bdrv_attach_child() take the reference also when there is an error, freeing the caller for having to do it. A similar situation happens with bdrv_root_attach_child(), so the changes on this patch affect both functions. Signed-off-by: Alberto Garcia <berto@igalia.com> Message-id: 20dfb3d9ccec559cdd1a9690146abad5d204a186.1557754872.git.berto@igalia.com [mreitz: Removed now superfluous BdrvChild * variable in bdrv_open_child()] Signed-off-by: Max Reitz <mreitz@redhat.com> --- block.c | 30 ++++++++++++++++++------------ block/block-backend.c | 3 +-- block/quorum.c | 1 - blockjob.c | 2 +- 4 files changed, 20 insertions(+), 16 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs) } } +/* + * This function steals the reference to child_bs from the caller. + * That reference is later dropped by bdrv_root_unref_child(). + * + * On failure NULL is returned, errp is set and the reference to + * child_bs is also dropped. + */ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs, const char *child_name, const BdrvChildRole *child_role, @@ -XXX,XX +XXX,XX @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs, ret = bdrv_check_update_perm(child_bs, NULL, perm, shared_perm, NULL, errp); if (ret < 0) { bdrv_abort_perm_update(child_bs); + bdrv_unref(child_bs); return NULL; } @@ -XXX,XX +XXX,XX @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs, return child; } +/* + * This function transfers the reference to child_bs from the caller + * to parent_bs. That reference is later dropped by parent_bs on + * bdrv_close() or if someone calls bdrv_unref_child(). + * + * On failure NULL is returned, errp is set and the reference to + * child_bs is also dropped. + */ BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs, BlockDriverState *child_bs, const char *child_name, @@ -XXX,XX +XXX,XX @@ void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd, /* If backing_hd was already part of bs's backing chain, and * inherits_from pointed recursively to bs then let's update it to * point directly to bs (else it will become NULL). */ - if (update_inherits_from) { + if (bs->backing && update_inherits_from) { backing_hd->inherits_from = bs; } - if (!bs->backing) { - bdrv_unref(backing_hd); - } out: bdrv_refresh_limits(bs, NULL); @@ -XXX,XX +XXX,XX @@ BdrvChild *bdrv_open_child(const char *filename, const BdrvChildRole *child_role, bool allow_none, Error **errp) { - BdrvChild *c; BlockDriverState *bs; bs = bdrv_open_child_bs(filename, options, bdref_key, parent, child_role, @@ -XXX,XX +XXX,XX @@ BdrvChild *bdrv_open_child(const char *filename, return NULL; } - c = bdrv_attach_child(parent, bs, bdref_key, child_role, errp); - if (!c) { - bdrv_unref(bs); - return NULL; - } - - return c; + return bdrv_attach_child(parent, bs, bdref_key, child_role, errp); } /* TODO Future callers may need to specify parent/child_role in order for 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 @@ BlockBackend *blk_new_open(const char *filename, const char *reference, blk->root = bdrv_root_attach_child(bs, "root", &child_root, perm, BLK_PERM_ALL, blk, errp); if (!blk->root) { - bdrv_unref(bs); blk_unref(blk); return NULL; } @@ -XXX,XX +XXX,XX @@ void blk_remove_bs(BlockBackend *blk) int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp) { ThrottleGroupMember *tgm = &blk->public.throttle_group_member; + bdrv_ref(bs); blk->root = bdrv_root_attach_child(bs, "root", &child_root, blk->perm, blk->shared_perm, blk, errp); if (blk->root == NULL) { return -EPERM; } - bdrv_ref(bs); notifier_list_notify(&blk->insert_bs_notifiers, blk); if (tgm->throttle_state) { diff --git a/block/quorum.c b/block/quorum.c index XXXXXXX..XXXXXXX 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -XXX,XX +XXX,XX @@ static void quorum_add_child(BlockDriverState *bs, BlockDriverState *child_bs, child = bdrv_attach_child(bs, child_bs, indexstr, &child_format, errp); if (child == NULL) { s->next_child_index--; - bdrv_unref(child_bs); goto out; } s->children = g_renew(BdrvChild *, s->children, s->num_children + 1); diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs, { BdrvChild *c; + bdrv_ref(bs); c = bdrv_root_attach_child(bs, name, &child_job, perm, shared_perm, job, errp); if (c == NULL) { @@ -XXX,XX +XXX,XX @@ int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs, } job->nodes = g_slist_prepend(job->nodes, c); - bdrv_ref(bs); bdrv_op_block_all(bs, job->blocker); return 0; -- 2.21.0 From: Sam Eiderman <shmuel.eiderman@oracle.com> In safe mode we open the entire chain, including the parent backing file of the rebased file. Do not open a new BlockBackend for the parent backing file, which saves opening the rest of the chain twice, which for long chains saves many "pricy" bdrv_open() calls. Permissions for blk_new() were copied from blk_new_open() when flags = 0. Reviewed-by: Karl Heubaum <karl.heubaum@oracle.com> Reviewed-by: Eyal Moscovici <eyal.moscovici@oracle.com> Signed-off-by: Sagi Amit <sagi.amit@oracle.com> Co-developed-by: Sagi Amit <sagi.amit@oracle.com> Signed-off-by: Sam Eiderman <shmuel.eiderman@oracle.com> Message-id: 20190523163337.4497-2-shmuel.eiderman@oracle.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- qemu-img.c | 29 +++++++++-------------------- 1 file changed, 9 insertions(+), 20 deletions(-) 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_rebase(int argc, char **argv) /* For safe rebasing we need to compare old and new backing file */ if (!unsafe) { - char backing_name[PATH_MAX]; QDict *options = NULL; + BlockDriverState *base_bs = backing_bs(bs); - if (bs->backing) { - if (bs->backing_format[0] != '\0') { - options = qdict_new(); - qdict_put_str(options, "driver", bs->backing_format); - } - - if (force_share) { - if (!options) { - options = qdict_new(); - } - qdict_put_bool(options, BDRV_OPT_FORCE_SHARE, true); - } - bdrv_get_backing_filename(bs, backing_name, sizeof(backing_name)); - blk_old_backing = blk_new_open(backing_name, NULL, - options, src_flags, &local_err); - if (!blk_old_backing) { + if (base_bs) { + blk_old_backing = blk_new(BLK_PERM_CONSISTENT_READ, + BLK_PERM_ALL); + ret = blk_insert_bs(blk_old_backing, base_bs, + &local_err); + if (ret < 0) { error_reportf_err(local_err, - "Could not open old backing file '%s': ", - backing_name); - ret = -1; + "Could not reuse old backing file '%s': ", + base_bs->filename); goto out; } } else { -- 2.21.0 From: Sam Eiderman <shmuel.eiderman@oracle.com> In the following case: (base) A <- B <- C (tip) when running: qemu-img rebase -b A C QEMU would read all sectors not allocated in the file being rebased (C) and compare them to the new base image (A), regardless of whether they were changed or even allocated anywhere along the chain between the new base and the top image (B). This causes many unneeded reads when rebasing an image which represents a small diff of a large disk, as it would read most of the disk's sectors. Instead, use bdrv_is_allocated_above() to reduce the number of unnecessary reads. Reviewed-by: Karl Heubaum <karl.heubaum@oracle.com> Signed-off-by: Sam Eiderman <shmuel.eiderman@oracle.com> Signed-off-by: Eyal Moscovici <eyal.moscovici@oracle.com> Message-id: 20190523163337.4497-3-shmuel.eiderman@oracle.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- qemu-img.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) 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_rebase(int argc, char **argv) BlockBackend *blk = NULL, *blk_old_backing = NULL, *blk_new_backing = NULL; uint8_t *buf_old = NULL; uint8_t *buf_new = NULL; - BlockDriverState *bs = NULL; + BlockDriverState *bs = NULL, *prefix_chain_bs = NULL; char *filename; const char *fmt, *cache, *src_cache, *out_basefmt, *out_baseimg; int c, flags, src_flags, ret; @@ -XXX,XX +XXX,XX @@ static int img_rebase(int argc, char **argv) goto out; } + /* + * Find out whether we rebase an image on top of a previous image + * in its chain. + */ + prefix_chain_bs = bdrv_find_backing_image(bs, out_real_path); + blk_new_backing = blk_new_open(out_real_path, NULL, options, src_flags, &local_err); g_free(out_real_path); @@ -XXX,XX +XXX,XX @@ static int img_rebase(int argc, char **argv) continue; } + if (prefix_chain_bs) { + /* + * If cluster wasn't changed since prefix_chain, we don't need + * to take action + */ + ret = bdrv_is_allocated_above(backing_bs(bs), prefix_chain_bs, + offset, n, &n); + if (ret < 0) { + error_report("error while reading image metadata: %s", + strerror(-ret)); + goto out; + } + if (!ret) { + continue; + } + } + /* * Read old and new backing file and take into consideration that * backing files may be smaller than the COW image. -- 2.21.0 From: Sam Eiderman <shmuel.eiderman@oracle.com> If a chain was detected, don't open a new BlockBackend from the target backing file which will create a new BlockDriverState. Instead, create an empty BlockBackend and attach the already open BlockDriverState. Permissions for blk_new() were copied from blk_new_open() when flags = 0. Reviewed-by: Karl Heubaum <karl.heubaum@oracle.com> Reviewed-by: Eyal Moscovici <eyal.moscovici@oracle.com> Signed-off-by: Sagi Amit <sagi.amit@oracle.com> Co-developed-by: Sagi Amit <sagi.amit@oracle.com> Signed-off-by: Sam Eiderman <shmuel.eiderman@oracle.com> Message-id: 20190523163337.4497-4-shmuel.eiderman@oracle.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- qemu-img.c | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) 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_rebase(int argc, char **argv) * in its chain. */ prefix_chain_bs = bdrv_find_backing_image(bs, out_real_path); - - blk_new_backing = blk_new_open(out_real_path, NULL, - options, src_flags, &local_err); - g_free(out_real_path); - if (!blk_new_backing) { - error_reportf_err(local_err, - "Could not open new backing file '%s': ", - out_baseimg); - ret = -1; - goto out; + if (prefix_chain_bs) { + g_free(out_real_path); + blk_new_backing = blk_new(BLK_PERM_CONSISTENT_READ, + BLK_PERM_ALL); + ret = blk_insert_bs(blk_new_backing, prefix_chain_bs, + &local_err); + if (ret < 0) { + error_reportf_err(local_err, + "Could not reuse backing file '%s': ", + out_baseimg); + goto out; + } + } else { + blk_new_backing = blk_new_open(out_real_path, NULL, + options, src_flags, &local_err); + g_free(out_real_path); + if (!blk_new_backing) { + error_reportf_err(local_err, + "Could not open new backing file '%s': ", + out_baseimg); + ret = -1; + goto out; + } } } } -- 2.21.0 From: Anton Nefedov <anton.nefedov@virtuozzo.com> If COW areas of the newly allocated clusters are zeroes on the backing image, efficient bdrv_write_zeroes(flags=BDRV_REQ_NO_FALLBACK) can be used on the whole cluster instead of writing explicit zero buffers later in perform_cow(). iotest 060: write to the discarded cluster does not trigger COW anymore. Use a backing image instead. Signed-off-by: Anton Nefedov <anton.nefedov@virtuozzo.com> Message-id: 20190516142749.81019-2-anton.nefedov@virtuozzo.com Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- qapi/block-core.json | 4 +- block/qcow2.h | 6 +++ block/qcow2-cluster.c | 2 +- block/qcow2.c | 85 ++++++++++++++++++++++++++++++++++++++ block/trace-events | 1 + tests/qemu-iotests/060 | 7 +++- tests/qemu-iotests/060.out | 5 ++- 7 files changed, 106 insertions(+), 4 deletions(-) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ # # @cor_write: a write due to copy-on-read (since 2.11) # +# @cluster_alloc_space: an allocation of file space for a cluster (since 4.1) +# # Since: 2.9 ## { 'enum': 'BlkdebugEvent', 'prefix': 'BLKDBG', @@ -XXX,XX +XXX,XX @@ 'pwritev_rmw_tail', 'pwritev_rmw_after_tail', 'pwritev', 'pwritev_zero', 'pwritev_done', 'empty_image_prepare', 'l1_shrink_write_table', 'l1_shrink_free_l2_clusters', - 'cor_write'] } + 'cor_write', 'cluster_alloc_space'] } ## # @BlkdebugInjectErrorOptions: diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ typedef struct QCowL2Meta */ Qcow2COWRegion cow_end; + /* + * Indicates that COW regions are already handled and do not require + * any more processing. + */ + bool skip_cow; + /** * The I/O vector with the data from the actual guest write request. * If non-NULL, this is meant to be merged together with the data 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 perform_cow(BlockDriverState *bs, QCowL2Meta *m) assert(start->offset + start->nb_bytes <= end->offset); assert(!m->data_qiov || m->data_qiov->size == data_bytes); - if (start->nb_bytes == 0 && end->nb_bytes == 0) { + if ((start->nb_bytes == 0 && end->nb_bytes == 0) || m->skip_cow) { return 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 bool merge_cow(uint64_t offset, unsigned bytes, continue; } + /* If COW regions are handled already, skip this too */ + if (m->skip_cow) { + continue; + } + /* The data (middle) region must be immediately after the * start region */ if (l2meta_cow_start(m) + m->cow_start.nb_bytes != offset) { @@ -XXX,XX +XXX,XX @@ static bool merge_cow(uint64_t offset, unsigned bytes, return false; } +static bool is_unallocated(BlockDriverState *bs, int64_t offset, int64_t bytes) +{ + int64_t nr; + return !bytes || + (!bdrv_is_allocated_above(bs, NULL, offset, bytes, &nr) && nr == bytes); +} + +static bool is_zero_cow(BlockDriverState *bs, QCowL2Meta *m) +{ + /* + * This check is designed for optimization shortcut so it must be + * efficient. + * Instead of is_zero(), use is_unallocated() as it is faster (but not + * as accurate and can result in false negatives). + */ + return is_unallocated(bs, m->offset + m->cow_start.offset, + m->cow_start.nb_bytes) && + is_unallocated(bs, m->offset + m->cow_end.offset, + m->cow_end.nb_bytes); +} + +static int handle_alloc_space(BlockDriverState *bs, QCowL2Meta *l2meta) +{ + BDRVQcow2State *s = bs->opaque; + QCowL2Meta *m; + + if (!(s->data_file->bs->supported_zero_flags & BDRV_REQ_NO_FALLBACK)) { + return 0; + } + + if (bs->encrypted) { + return 0; + } + + for (m = l2meta; m != NULL; m = m->next) { + int ret; + + if (!m->cow_start.nb_bytes && !m->cow_end.nb_bytes) { + continue; + } + + if (!is_zero_cow(bs, m)) { + continue; + } + + /* + * instead of writing zero COW buffers, + * efficiently zero out the whole clusters + */ + + ret = qcow2_pre_write_overlap_check(bs, 0, m->alloc_offset, + m->nb_clusters * s->cluster_size, + true); + if (ret < 0) { + return ret; + } + + BLKDBG_EVENT(bs->file, BLKDBG_CLUSTER_ALLOC_SPACE); + ret = bdrv_co_pwrite_zeroes(s->data_file, m->alloc_offset, + m->nb_clusters * s->cluster_size, + BDRV_REQ_NO_FALLBACK); + if (ret < 0) { + if (ret != -ENOTSUP && ret != -EAGAIN) { + return ret; + } + continue; + } + + trace_qcow2_skip_cow(qemu_coroutine_self(), m->offset, m->nb_clusters); + m->skip_cow = true; + } + return 0; +} + static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags) @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, qemu_iovec_add(&hd_qiov, cluster_data, cur_bytes); } + /* Try to efficiently initialize the physical space with zeroes */ + ret = handle_alloc_space(bs, l2meta); + if (ret < 0) { + goto out_unlocked; + } + /* If we need to do COW, check if it's possible to merge the * writing of the guest data together with that of the COW regions. * If it's not possible (or not necessary) then write the diff --git a/block/trace-events b/block/trace-events index XXXXXXX..XXXXXXX 100644 --- a/block/trace-events +++ b/block/trace-events @@ -XXX,XX +XXX,XX @@ qcow2_writev_done_part(void *co, int cur_bytes) "co %p cur_bytes %d" qcow2_writev_data(void *co, uint64_t offset) "co %p offset 0x%" PRIx64 qcow2_pwrite_zeroes_start_req(void *co, int64_t offset, int count) "co %p offset 0x%" PRIx64 " count %d" qcow2_pwrite_zeroes(void *co, int64_t offset, int count) "co %p offset 0x%" PRIx64 " count %d" +qcow2_skip_cow(void *co, uint64_t offset, int nb_clusters) "co %p offset 0x%" PRIx64 " nb_clusters %d" # qcow2-cluster.c qcow2_alloc_clusters_offset(void *co, uint64_t offset, int bytes) "co %p offset 0x%" PRIx64 " bytes %d" diff --git a/tests/qemu-iotests/060 b/tests/qemu-iotests/060 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/060 +++ b/tests/qemu-iotests/060 @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "$OPEN_RO" -c "read -P 1 0 512" | _filter_qemu_io echo echo "=== Testing overlap while COW is in flight ===" echo +BACKING_IMG=$TEST_IMG.base +TEST_IMG=$BACKING_IMG _make_test_img 1G + +$QEMU_IO -c 'write 0k 64k' "$BACKING_IMG" | _filter_qemu_io + # compat=0.10 is required in order to make the following discard actually # unallocate the sector rather than make it a zero sector - we want COW, after # all. -IMGOPTS='compat=0.10' _make_test_img 1G +IMGOPTS='compat=0.10' _make_test_img -b "$BACKING_IMG" 1G # Write two clusters, the second one enforces creation of an L2 table after # the first data cluster. $QEMU_IO -c 'write 0k 64k' -c 'write 512M 64k' "$TEST_IMG" | _filter_qemu_io diff --git a/tests/qemu-iotests/060.out b/tests/qemu-iotests/060.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/060.out +++ b/tests/qemu-iotests/060.out @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 === Testing overlap while COW is in flight === -Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 +Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=1073741824 +wrote 65536/65536 bytes at offset 0 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 backing_file=TEST_DIR/t.IMGFMT.base wrote 65536/65536 bytes at offset 0 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) wrote 65536/65536 bytes at offset 536870912 -- 2.21.0 From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Valgrind detects multiple issues in QEMU iotests when the memory is used without being initialized. Valgrind may dump lots of unnecessary reports what makes the memory issue analysis harder. Particularly, that is true for the aligned bitmap directory and can be seen while running the iotest #169. Padding the aligned space with zeros eases the pain. Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Message-id: 1558961521-131620-1-git-send-email-andrey.shinkevich@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-bitmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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_list_store(BlockDriverState *bs, Qcow2BitmapList *bm_list, dir_offset = *offset; } - dir = g_try_malloc(dir_size); + dir = g_try_malloc0(dir_size); if (dir == NULL) { return -ENOMEM; } -- 2.21.0 From: John Snow <jsnow@redhat.com> We mandate that the source node must be a root node; but there's no reason I am aware of that it needs to be restricted to such. In some cases, we need to make sure that there's a medium present, but in the general case we can allow the backup job itself to do the graph checking. This patch helps improve the error message when you try to backup from the same node more than once, which is reflected in the change to test 056. For backups with bitmaps, it will also show a better error message that the bitmap is in use instead of giving you something cryptic like "need a root node." Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1707303 Signed-off-by: John Snow <jsnow@redhat.com> Message-id: 20190521210053.8864-1-jsnow@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- blockdev.c | 7 ++++++- tests/qemu-iotests/056 | 2 +- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ static BlockJob *do_drive_backup(DriveBackup *backup, JobTxn *txn, backup->compress = false; } - bs = qmp_get_root_bs(backup->device, errp); + bs = bdrv_lookup_bs(backup->device, backup->device, errp); if (!bs) { return NULL; } + if (!bs->drv) { + error_setg(errp, "Device has no medium"); + return NULL; + } + aio_context = bdrv_get_aio_context(bs); aio_context_acquire(aio_context); diff --git a/tests/qemu-iotests/056 b/tests/qemu-iotests/056 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/056 +++ b/tests/qemu-iotests/056 @@ -XXX,XX +XXX,XX @@ class BackupTest(iotests.QMPTestCase): res = self.vm.qmp('query-block-jobs') self.assert_qmp(res, 'return[0]/status', 'concluded') # Leave zombie job un-dismissed, observe a failure: - res = self.qmp_backup_and_wait(serror='Need a root block node', + res = self.qmp_backup_and_wait(serror="Node 'drive0' is busy: block device is in use by block job: backup", device='drive0', format=iotests.imgfmt, sync='full', target=self.dest_img, auto_dismiss=False) -- 2.21.0 The following changes since commit ac793156f650ae2d77834932d72224175ee69086: Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20201020-1' into staging (2020-10-20 21:11:35 +0100) are available in the Git repository at: https://gitlab.com/stefanha/qemu.git tags/block-pull-request for you to fetch changes up to 32a3fd65e7e3551337fd26bfc0e2f899d70c028c: iotests: add commit top->base cases to 274 (2020-10-22 09:55:39 +0100) ---------------------------------------------------------------- Pull request v2: * Fix format string issues on 32-bit hosts [Peter] * Fix qemu-nbd.c CONFIG_POSIX ifdef issue [Eric] * Fix missing eventfd.h header on macOS [Peter] * Drop unreliable vhost-user-blk test (will send a new patch when ready) [Peter] This pull request contains the vhost-user-blk server by Coiby Xu along with my additions, block/nvme.c alignment and hardware error statistics by Philippe Mathieu-Daudé, and bdrv_co_block_status_above() fixes by Vladimir Sementsov-Ogievskiy. ---------------------------------------------------------------- Coiby Xu (6): libvhost-user: Allow vu_message_read to be replaced libvhost-user: remove watch for kick_fd when de-initialize vu-dev util/vhost-user-server: generic vhost user server block: move logical block size check function to a common utility function block/export: vhost-user block device backend server MAINTAINERS: Add vhost-user block device backend server maintainer Philippe Mathieu-Daudé (1): block/nvme: Add driver statistics for access alignment and hw errors Stefan Hajnoczi (16): util/vhost-user-server: s/fileds/fields/ typo fix util/vhost-user-server: drop unnecessary QOM cast util/vhost-user-server: drop unnecessary watch deletion block/export: consolidate request structs into VuBlockReq util/vhost-user-server: drop unused DevicePanicNotifier util/vhost-user-server: fix memory leak in vu_message_read() util/vhost-user-server: check EOF when reading payload util/vhost-user-server: rework vu_client_trip() coroutine lifecycle block/export: report flush errors block/export: convert vhost-user-blk server to block export API util/vhost-user-server: move header to include/ util/vhost-user-server: use static library in meson.build qemu-storage-daemon: avoid compiling blockdev_ss twice block: move block exports to libblockdev block/export: add iothread and fixed-iothread options block/export: add vhost-user-blk multi-queue support Vladimir Sementsov-Ogievskiy (5): block/io: fix bdrv_co_block_status_above block/io: bdrv_common_block_status_above: support include_base block/io: bdrv_common_block_status_above: support bs == base block/io: fix bdrv_is_allocated_above iotests: add commit top->base cases to 274 MAINTAINERS | 9 + qapi/block-core.json | 24 +- qapi/block-export.json | 36 +- block/coroutines.h | 2 + block/export/vhost-user-blk-server.h | 19 + contrib/libvhost-user/libvhost-user.h | 21 + include/qemu/vhost-user-server.h | 65 +++ util/block-helpers.h | 19 + block/export/export.c | 37 +- block/export/vhost-user-blk-server.c | 431 ++++++++++++++++++++ block/io.c | 132 +++--- block/nvme.c | 27 ++ block/qcow2.c | 16 +- contrib/libvhost-user/libvhost-user-glib.c | 2 +- contrib/libvhost-user/libvhost-user.c | 15 +- hw/core/qdev-properties-system.c | 31 +- nbd/server.c | 2 - qemu-nbd.c | 21 +- softmmu/vl.c | 4 + stubs/blk-exp-close-all.c | 7 + tests/vhost-user-bridge.c | 2 + tools/virtiofsd/fuse_virtio.c | 4 +- util/block-helpers.c | 46 +++ util/vhost-user-server.c | 446 +++++++++++++++++++++ block/export/meson.build | 3 +- contrib/libvhost-user/meson.build | 1 + meson.build | 22 +- nbd/meson.build | 2 + storage-daemon/meson.build | 3 +- stubs/meson.build | 1 + tests/qemu-iotests/274 | 20 + tests/qemu-iotests/274.out | 68 ++++ util/meson.build | 4 + 33 files changed, 1420 insertions(+), 122 deletions(-) create mode 100644 block/export/vhost-user-blk-server.h create mode 100644 include/qemu/vhost-user-server.h create mode 100644 util/block-helpers.h create mode 100644 block/export/vhost-user-blk-server.c create mode 100644 stubs/blk-exp-close-all.c create mode 100644 util/block-helpers.c create mode 100644 util/vhost-user-server.c -- 2.26.2 From: Philippe Mathieu-Daudé <philmd@redhat.com> Keep statistics of some hardware errors, and number of aligned/unaligned I/O accesses. QMP example booting a full RHEL 8.3 aarch64 guest: { "execute": "query-blockstats" } { "return": [ { "device": "", "node-name": "drive0", "stats": { "flush_total_time_ns": 6026948, "wr_highest_offset": 3383991230464, "wr_total_time_ns": 807450995, "failed_wr_operations": 0, "failed_rd_operations": 0, "wr_merged": 3, "wr_bytes": 50133504, "failed_unmap_operations": 0, "failed_flush_operations": 0, "account_invalid": false, "rd_total_time_ns": 1846979900, "flush_operations": 130, "wr_operations": 659, "rd_merged": 1192, "rd_bytes": 218244096, "account_failed": false, "idle_time_ns": 2678641497, "rd_operations": 7406, }, "driver-specific": { "driver": "nvme", "completion-errors": 0, "unaligned-accesses": 2959, "aligned-accesses": 4477 }, "qdev": "/machine/peripheral-anon/device[0]/virtio-backend" } ] } Suggested-by: Stefan Hajnoczi <stefanha@gmail.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Acked-by: Markus Armbruster <armbru@redhat.com> Message-id: 20201001162939.1567915-1-philmd@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qapi/block-core.json | 24 +++++++++++++++++++++++- block/nvme.c | 27 +++++++++++++++++++++++++++ 2 files changed, 50 insertions(+), 1 deletion(-) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ 'discard-nb-failed': 'uint64', 'discard-bytes-ok': 'uint64' } } +## +# @BlockStatsSpecificNvme: +# +# NVMe driver statistics +# +# @completion-errors: The number of completion errors. +# +# @aligned-accesses: The number of aligned accesses performed by +# the driver. +# +# @unaligned-accesses: The number of unaligned accesses performed by +# the driver. +# +# Since: 5.2 +## +{ 'struct': 'BlockStatsSpecificNvme', + 'data': { + 'completion-errors': 'uint64', + 'aligned-accesses': 'uint64', + 'unaligned-accesses': 'uint64' } } + ## # @BlockStatsSpecific: # @@ -XXX,XX +XXX,XX @@ 'discriminator': 'driver', 'data': { 'file': 'BlockStatsSpecificFile', - 'host_device': 'BlockStatsSpecificFile' } } + 'host_device': 'BlockStatsSpecificFile', + 'nvme': 'BlockStatsSpecificNvme' } } ## # @BlockStats: diff --git a/block/nvme.c b/block/nvme.c index XXXXXXX..XXXXXXX 100644 --- a/block/nvme.c +++ b/block/nvme.c @@ -XXX,XX +XXX,XX @@ struct BDRVNVMeState { /* PCI address (required for nvme_refresh_filename()) */ char *device; + + struct { + uint64_t completion_errors; + uint64_t aligned_accesses; + uint64_t unaligned_accesses; + } stats; }; #define NVME_BLOCK_OPT_DEVICE "device" @@ -XXX,XX +XXX,XX @@ static bool nvme_process_completion(NVMeQueuePair *q) break; } ret = nvme_translate_error(c); + if (ret) { + s->stats.completion_errors++; + } q->cq.head = (q->cq.head + 1) % NVME_QUEUE_SIZE; if (!q->cq.head) { q->cq_phase = !q->cq_phase; @@ -XXX,XX +XXX,XX @@ static int nvme_co_prw(BlockDriverState *bs, uint64_t offset, uint64_t bytes, assert(QEMU_IS_ALIGNED(bytes, s->page_size)); assert(bytes <= s->max_transfer); if (nvme_qiov_aligned(bs, qiov)) { + s->stats.aligned_accesses++; return nvme_co_prw_aligned(bs, offset, bytes, qiov, is_write, flags); } + s->stats.unaligned_accesses++; trace_nvme_prw_buffered(s, offset, bytes, qiov->niov, is_write); buf = qemu_try_memalign(s->page_size, bytes); @@ -XXX,XX +XXX,XX @@ static void nvme_unregister_buf(BlockDriverState *bs, void *host) qemu_vfio_dma_unmap(s->vfio, host); } +static BlockStatsSpecific *nvme_get_specific_stats(BlockDriverState *bs) +{ + BlockStatsSpecific *stats = g_new(BlockStatsSpecific, 1); + BDRVNVMeState *s = bs->opaque; + + stats->driver = BLOCKDEV_DRIVER_NVME; + stats->u.nvme = (BlockStatsSpecificNvme) { + .completion_errors = s->stats.completion_errors, + .aligned_accesses = s->stats.aligned_accesses, + .unaligned_accesses = s->stats.unaligned_accesses, + }; + + return stats; +} + static const char *const nvme_strong_runtime_opts[] = { NVME_BLOCK_OPT_DEVICE, NVME_BLOCK_OPT_NAMESPACE, @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_nvme = { .bdrv_refresh_filename = nvme_refresh_filename, .bdrv_refresh_limits = nvme_refresh_limits, .strong_runtime_opts = nvme_strong_runtime_opts, + .bdrv_get_specific_stats = nvme_get_specific_stats, .bdrv_detach_aio_context = nvme_detach_aio_context, .bdrv_attach_aio_context = nvme_attach_aio_context, -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> Allow vu_message_read to be replaced by one which will make use of the QIOChannel functions. Thus reading vhost-user message won't stall the guest. For slave channel, we still use the default vu_message_read. Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200918080912.321299-2-coiby.xu@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- contrib/libvhost-user/libvhost-user.h | 21 +++++++++++++++++++++ contrib/libvhost-user/libvhost-user-glib.c | 2 +- contrib/libvhost-user/libvhost-user.c | 14 +++++++------- tests/vhost-user-bridge.c | 2 ++ tools/virtiofsd/fuse_virtio.c | 4 ++-- 5 files changed, 33 insertions(+), 10 deletions(-) diff --git a/contrib/libvhost-user/libvhost-user.h b/contrib/libvhost-user/libvhost-user.h index XXXXXXX..XXXXXXX 100644 --- a/contrib/libvhost-user/libvhost-user.h +++ b/contrib/libvhost-user/libvhost-user.h @@ -XXX,XX +XXX,XX @@ */ #define VHOST_USER_MAX_RAM_SLOTS 32 +#define VHOST_USER_HDR_SIZE offsetof(VhostUserMsg, payload.u64) + typedef enum VhostSetConfigType { VHOST_SET_CONFIG_TYPE_MASTER = 0, VHOST_SET_CONFIG_TYPE_MIGRATION = 1, @@ -XXX,XX +XXX,XX @@ typedef uint64_t (*vu_get_features_cb) (VuDev *dev); typedef void (*vu_set_features_cb) (VuDev *dev, uint64_t features); typedef int (*vu_process_msg_cb) (VuDev *dev, VhostUserMsg *vmsg, int *do_reply); +typedef bool (*vu_read_msg_cb) (VuDev *dev, int sock, VhostUserMsg *vmsg); typedef void (*vu_queue_set_started_cb) (VuDev *dev, int qidx, bool started); typedef bool (*vu_queue_is_processed_in_order_cb) (VuDev *dev, int qidx); typedef int (*vu_get_config_cb) (VuDev *dev, uint8_t *config, uint32_t len); @@ -XXX,XX +XXX,XX @@ struct VuDev { bool broken; uint16_t max_queues; + /* @read_msg: custom method to read vhost-user message + * + * Read data from vhost_user socket fd and fill up + * the passed VhostUserMsg *vmsg struct. + * + * If reading fails, it should close the received set of file + * descriptors as socket message's auxiliary data. + * + * For the details, please refer to vu_message_read in libvhost-user.c + * which will be used by default if not custom method is provided when + * calling vu_init + * + * Returns: true if vhost-user message successfully received, + * otherwise return false. + * + */ + vu_read_msg_cb read_msg; /* @set_watch: add or update the given fd to the watch set, * call cb when condition is met */ vu_set_watch_cb set_watch; @@ -XXX,XX +XXX,XX @@ bool vu_init(VuDev *dev, uint16_t max_queues, int socket, vu_panic_cb panic, + vu_read_msg_cb read_msg, vu_set_watch_cb set_watch, vu_remove_watch_cb remove_watch, const VuDevIface *iface); diff --git a/contrib/libvhost-user/libvhost-user-glib.c b/contrib/libvhost-user/libvhost-user-glib.c index XXXXXXX..XXXXXXX 100644 --- a/contrib/libvhost-user/libvhost-user-glib.c +++ b/contrib/libvhost-user/libvhost-user-glib.c @@ -XXX,XX +XXX,XX @@ vug_init(VugDev *dev, uint16_t max_queues, int socket, g_assert(dev); g_assert(iface); - if (!vu_init(&dev->parent, max_queues, socket, panic, set_watch, + if (!vu_init(&dev->parent, max_queues, socket, panic, NULL, set_watch, remove_watch, iface)) { return false; } diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c index XXXXXXX..XXXXXXX 100644 --- a/contrib/libvhost-user/libvhost-user.c +++ b/contrib/libvhost-user/libvhost-user.c @@ -XXX,XX +XXX,XX @@ /* The version of inflight buffer */ #define INFLIGHT_VERSION 1 -#define VHOST_USER_HDR_SIZE offsetof(VhostUserMsg, payload.u64) - /* The version of the protocol we support */ #define VHOST_USER_VERSION 1 #define LIBVHOST_USER_DEBUG 0 @@ -XXX,XX +XXX,XX @@ have_userfault(void) } static bool -vu_message_read(VuDev *dev, int conn_fd, VhostUserMsg *vmsg) +vu_message_read_default(VuDev *dev, int conn_fd, VhostUserMsg *vmsg) { char control[CMSG_SPACE(VHOST_MEMORY_BASELINE_NREGIONS * sizeof(int))] = {}; struct iovec iov = { @@ -XXX,XX +XXX,XX @@ vu_process_message_reply(VuDev *dev, const VhostUserMsg *vmsg) goto out; } - if (!vu_message_read(dev, dev->slave_fd, &msg_reply)) { + if (!vu_message_read_default(dev, dev->slave_fd, &msg_reply)) { goto out; } @@ -XXX,XX +XXX,XX @@ vu_set_mem_table_exec_postcopy(VuDev *dev, VhostUserMsg *vmsg) /* Wait for QEMU to confirm that it's registered the handler for the * faults. */ - if (!vu_message_read(dev, dev->sock, vmsg) || + if (!dev->read_msg(dev, dev->sock, vmsg) || vmsg->size != sizeof(vmsg->payload.u64) || vmsg->payload.u64 != 0) { vu_panic(dev, "failed to receive valid ack for postcopy set-mem-table"); @@ -XXX,XX +XXX,XX @@ vu_dispatch(VuDev *dev) int reply_requested; bool need_reply, success = false; - if (!vu_message_read(dev, dev->sock, &vmsg)) { + if (!dev->read_msg(dev, dev->sock, &vmsg)) { goto end; } @@ -XXX,XX +XXX,XX @@ vu_init(VuDev *dev, uint16_t max_queues, int socket, vu_panic_cb panic, + vu_read_msg_cb read_msg, vu_set_watch_cb set_watch, vu_remove_watch_cb remove_watch, const VuDevIface *iface) @@ -XXX,XX +XXX,XX @@ vu_init(VuDev *dev, dev->sock = socket; dev->panic = panic; + dev->read_msg = read_msg ? read_msg : vu_message_read_default; dev->set_watch = set_watch; dev->remove_watch = remove_watch; dev->iface = iface; @@ -XXX,XX +XXX,XX @@ static void _vu_queue_notify(VuDev *dev, VuVirtq *vq, bool sync) vu_message_write(dev, dev->slave_fd, &vmsg); if (ack) { - vu_message_read(dev, dev->slave_fd, &vmsg); + vu_message_read_default(dev, dev->slave_fd, &vmsg); } return; } diff --git a/tests/vhost-user-bridge.c b/tests/vhost-user-bridge.c index XXXXXXX..XXXXXXX 100644 --- a/tests/vhost-user-bridge.c +++ b/tests/vhost-user-bridge.c @@ -XXX,XX +XXX,XX @@ vubr_accept_cb(int sock, void *ctx) VHOST_USER_BRIDGE_MAX_QUEUES, conn_fd, vubr_panic, + NULL, vubr_set_watch, vubr_remove_watch, &vuiface)) { @@ -XXX,XX +XXX,XX @@ vubr_new(const char *path, bool client) VHOST_USER_BRIDGE_MAX_QUEUES, dev->sock, vubr_panic, + NULL, vubr_set_watch, vubr_remove_watch, &vuiface)) { diff --git a/tools/virtiofsd/fuse_virtio.c b/tools/virtiofsd/fuse_virtio.c index XXXXXXX..XXXXXXX 100644 --- a/tools/virtiofsd/fuse_virtio.c +++ b/tools/virtiofsd/fuse_virtio.c @@ -XXX,XX +XXX,XX @@ int virtio_session_mount(struct fuse_session *se) se->vu_socketfd = data_sock; se->virtio_dev->se = se; pthread_rwlock_init(&se->virtio_dev->vu_dispatch_rwlock, NULL); - vu_init(&se->virtio_dev->dev, 2, se->vu_socketfd, fv_panic, fv_set_watch, - fv_remove_watch, &fv_iface); + vu_init(&se->virtio_dev->dev, 2, se->vu_socketfd, fv_panic, NULL, + fv_set_watch, fv_remove_watch, &fv_iface); return 0; } -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> When the client is running in gdb and quit command is run in gdb, QEMU will still dispatch the event which will cause segment fault in the callback function. Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-id: 20200918080912.321299-3-coiby.xu@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- contrib/libvhost-user/libvhost-user.c | 1 + 1 file changed, 1 insertion(+) diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c index XXXXXXX..XXXXXXX 100644 --- a/contrib/libvhost-user/libvhost-user.c +++ b/contrib/libvhost-user/libvhost-user.c @@ -XXX,XX +XXX,XX @@ vu_deinit(VuDev *dev) } if (vq->kick_fd != -1) { + dev->remove_watch(dev, vq->kick_fd); close(vq->kick_fd); vq->kick_fd = -1; } -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> Sharing QEMU devices via vhost-user protocol. Only one vhost-user client can connect to the server one time. Suggested-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-id: 20200918080912.321299-4-coiby.xu@gmail.com [Fixed size_t %lu -> %zu format string compiler error. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.h | 65 ++++++ util/vhost-user-server.c | 428 +++++++++++++++++++++++++++++++++++++++ util/meson.build | 1 + 3 files changed, 494 insertions(+) create mode 100644 util/vhost-user-server.h create mode 100644 util/vhost-user-server.c diff --git a/util/vhost-user-server.h b/util/vhost-user-server.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/util/vhost-user-server.h @@ -XXX,XX +XXX,XX @@ +/* + * Sharing QEMU devices via vhost-user protocol + * + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. + * Copyright (c) 2020 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. + */ + +#ifndef VHOST_USER_SERVER_H +#define VHOST_USER_SERVER_H + +#include "contrib/libvhost-user/libvhost-user.h" +#include "io/channel-socket.h" +#include "io/channel-file.h" +#include "io/net-listener.h" +#include "qemu/error-report.h" +#include "qapi/error.h" +#include "standard-headers/linux/virtio_blk.h" + +typedef struct VuFdWatch { + VuDev *vu_dev; + int fd; /*kick fd*/ + void *pvt; + vu_watch_cb cb; + bool processing; + QTAILQ_ENTRY(VuFdWatch) next; +} VuFdWatch; + +typedef struct VuServer VuServer; +typedef void DevicePanicNotifierFn(VuServer *server); + +struct VuServer { + QIONetListener *listener; + AioContext *ctx; + DevicePanicNotifierFn *device_panic_notifier; + int max_queues; + const VuDevIface *vu_iface; + VuDev vu_dev; + QIOChannel *ioc; /* The I/O channel with the client */ + QIOChannelSocket *sioc; /* The underlying data channel with the client */ + /* IOChannel for fd provided via VHOST_USER_SET_SLAVE_REQ_FD */ + QIOChannel *ioc_slave; + QIOChannelSocket *sioc_slave; + Coroutine *co_trip; /* coroutine for processing VhostUserMsg */ + QTAILQ_HEAD(, VuFdWatch) vu_fd_watches; + /* restart coroutine co_trip if AIOContext is changed */ + bool aio_context_changed; + bool processing_msg; +}; + +bool vhost_user_server_start(VuServer *server, + SocketAddress *unix_socket, + AioContext *ctx, + uint16_t max_queues, + DevicePanicNotifierFn *device_panic_notifier, + const VuDevIface *vu_iface, + Error **errp); + +void vhost_user_server_stop(VuServer *server); + +void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx); + +#endif /* VHOST_USER_SERVER_H */ diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ +/* + * Sharing QEMU devices via vhost-user protocol + * + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. + * Copyright (c) 2020 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 "qemu/main-loop.h" +#include "vhost-user-server.h" + +static void vmsg_close_fds(VhostUserMsg *vmsg) +{ + int i; + for (i = 0; i < vmsg->fd_num; i++) { + close(vmsg->fds[i]); + } +} + +static void vmsg_unblock_fds(VhostUserMsg *vmsg) +{ + int i; + for (i = 0; i < vmsg->fd_num; i++) { + qemu_set_nonblock(vmsg->fds[i]); + } +} + +static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, + gpointer opaque); + +static void close_client(VuServer *server) +{ + /* + * Before closing the client + * + * 1. Let vu_client_trip stop processing new vhost-user msg + * + * 2. remove kick_handler + * + * 3. wait for the kick handler to be finished + * + * 4. wait for the current vhost-user msg to be finished processing + */ + + QIOChannelSocket *sioc = server->sioc; + /* When this is set vu_client_trip will stop new processing vhost-user message */ + server->sioc = NULL; + + VuFdWatch *vu_fd_watch, *next; + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { + aio_set_fd_handler(server->ioc->ctx, vu_fd_watch->fd, true, NULL, + NULL, NULL, NULL); + } + + while (!QTAILQ_EMPTY(&server->vu_fd_watches)) { + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { + if (!vu_fd_watch->processing) { + QTAILQ_REMOVE(&server->vu_fd_watches, vu_fd_watch, next); + g_free(vu_fd_watch); + } + } + } + + while (server->processing_msg) { + if (server->ioc->read_coroutine) { + server->ioc->read_coroutine = NULL; + qio_channel_set_aio_fd_handler(server->ioc, server->ioc->ctx, NULL, + NULL, server->ioc); + server->processing_msg = false; + } + } + + vu_deinit(&server->vu_dev); + object_unref(OBJECT(sioc)); + object_unref(OBJECT(server->ioc)); +} + +static void panic_cb(VuDev *vu_dev, const char *buf) +{ + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + + /* avoid while loop in close_client */ + server->processing_msg = false; + + if (buf) { + error_report("vu_panic: %s", buf); + } + + if (server->sioc) { + close_client(server); + } + + if (server->device_panic_notifier) { + server->device_panic_notifier(server); + } + + /* + * Set the callback function for network listener so another + * vhost-user client can connect to this server + */ + qio_net_listener_set_client_func(server->listener, + vu_accept, + server, + NULL); +} + +static bool coroutine_fn +vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) +{ + struct iovec iov = { + .iov_base = (char *)vmsg, + .iov_len = VHOST_USER_HDR_SIZE, + }; + int rc, read_bytes = 0; + Error *local_err = NULL; + /* + * Store fds/nfds returned from qio_channel_readv_full into + * temporary variables. + * + * VhostUserMsg is a packed structure, gcc will complain about passing + * pointer to a packed structure member if we pass &VhostUserMsg.fd_num + * and &VhostUserMsg.fds directly when calling qio_channel_readv_full, + * thus two temporary variables nfds and fds are used here. + */ + size_t nfds = 0, nfds_t = 0; + const size_t max_fds = G_N_ELEMENTS(vmsg->fds); + int *fds_t = NULL; + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + QIOChannel *ioc = server->ioc; + + if (!ioc) { + error_report_err(local_err); + goto fail; + } + + assert(qemu_in_coroutine()); + do { + /* + * qio_channel_readv_full may have short reads, keeping calling it + * until getting VHOST_USER_HDR_SIZE or 0 bytes in total + */ + rc = qio_channel_readv_full(ioc, &iov, 1, &fds_t, &nfds_t, &local_err); + if (rc < 0) { + if (rc == QIO_CHANNEL_ERR_BLOCK) { + qio_channel_yield(ioc, G_IO_IN); + continue; + } else { + error_report_err(local_err); + return false; + } + } + read_bytes += rc; + if (nfds_t > 0) { + if (nfds + nfds_t > max_fds) { + error_report("A maximum of %zu fds are allowed, " + "however got %zu fds now", + max_fds, nfds + nfds_t); + goto fail; + } + memcpy(vmsg->fds + nfds, fds_t, + nfds_t *sizeof(vmsg->fds[0])); + nfds += nfds_t; + g_free(fds_t); + } + if (read_bytes == VHOST_USER_HDR_SIZE || rc == 0) { + break; + } + iov.iov_base = (char *)vmsg + read_bytes; + iov.iov_len = VHOST_USER_HDR_SIZE - read_bytes; + } while (true); + + vmsg->fd_num = nfds; + /* qio_channel_readv_full will make socket fds blocking, unblock them */ + vmsg_unblock_fds(vmsg); + if (vmsg->size > sizeof(vmsg->payload)) { + error_report("Error: too big message request: %d, " + "size: vmsg->size: %u, " + "while sizeof(vmsg->payload) = %zu", + vmsg->request, vmsg->size, sizeof(vmsg->payload)); + goto fail; + } + + struct iovec iov_payload = { + .iov_base = (char *)&vmsg->payload, + .iov_len = vmsg->size, + }; + if (vmsg->size) { + rc = qio_channel_readv_all_eof(ioc, &iov_payload, 1, &local_err); + if (rc == -1) { + error_report_err(local_err); + goto fail; + } + } + + return true; + +fail: + vmsg_close_fds(vmsg); + + return false; +} + + +static void vu_client_start(VuServer *server); +static coroutine_fn void vu_client_trip(void *opaque) +{ + VuServer *server = opaque; + + while (!server->aio_context_changed && server->sioc) { + server->processing_msg = true; + vu_dispatch(&server->vu_dev); + server->processing_msg = false; + } + + if (server->aio_context_changed && server->sioc) { + server->aio_context_changed = false; + vu_client_start(server); + } +} + +static void vu_client_start(VuServer *server) +{ + server->co_trip = qemu_coroutine_create(vu_client_trip, server); + aio_co_enter(server->ctx, server->co_trip); +} + +/* + * a wrapper for vu_kick_cb + * + * since aio_dispatch can only pass one user data pointer to the + * callback function, pack VuDev and pvt into a struct. Then unpack it + * and pass them to vu_kick_cb + */ +static void kick_handler(void *opaque) +{ + VuFdWatch *vu_fd_watch = opaque; + vu_fd_watch->processing = true; + vu_fd_watch->cb(vu_fd_watch->vu_dev, 0, vu_fd_watch->pvt); + vu_fd_watch->processing = false; +} + + +static VuFdWatch *find_vu_fd_watch(VuServer *server, int fd) +{ + + VuFdWatch *vu_fd_watch, *next; + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { + if (vu_fd_watch->fd == fd) { + return vu_fd_watch; + } + } + return NULL; +} + +static void +set_watch(VuDev *vu_dev, int fd, int vu_evt, + vu_watch_cb cb, void *pvt) +{ + + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + g_assert(vu_dev); + g_assert(fd >= 0); + g_assert(cb); + + VuFdWatch *vu_fd_watch = find_vu_fd_watch(server, fd); + + if (!vu_fd_watch) { + VuFdWatch *vu_fd_watch = g_new0(VuFdWatch, 1); + + QTAILQ_INSERT_TAIL(&server->vu_fd_watches, vu_fd_watch, next); + + vu_fd_watch->fd = fd; + vu_fd_watch->cb = cb; + qemu_set_nonblock(fd); + aio_set_fd_handler(server->ioc->ctx, fd, true, kick_handler, + NULL, NULL, vu_fd_watch); + vu_fd_watch->vu_dev = vu_dev; + vu_fd_watch->pvt = pvt; + } +} + + +static void remove_watch(VuDev *vu_dev, int fd) +{ + VuServer *server; + g_assert(vu_dev); + g_assert(fd >= 0); + + server = container_of(vu_dev, VuServer, vu_dev); + + VuFdWatch *vu_fd_watch = find_vu_fd_watch(server, fd); + + if (!vu_fd_watch) { + return; + } + aio_set_fd_handler(server->ioc->ctx, fd, true, NULL, NULL, NULL, NULL); + + QTAILQ_REMOVE(&server->vu_fd_watches, vu_fd_watch, next); + g_free(vu_fd_watch); +} + + +static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, + gpointer opaque) +{ + VuServer *server = opaque; + + if (server->sioc) { + warn_report("Only one vhost-user client is allowed to " + "connect the server one time"); + return; + } + + if (!vu_init(&server->vu_dev, server->max_queues, sioc->fd, panic_cb, + vu_message_read, set_watch, remove_watch, server->vu_iface)) { + error_report("Failed to initialize libvhost-user"); + return; + } + + /* + * Unset the callback function for network listener to make another + * vhost-user client keeping waiting until this client disconnects + */ + qio_net_listener_set_client_func(server->listener, + NULL, + NULL, + NULL); + server->sioc = sioc; + /* + * Increase the object reference, so sioc will not freed by + * qio_net_listener_channel_func which will call object_unref(OBJECT(sioc)) + */ + object_ref(OBJECT(server->sioc)); + qio_channel_set_name(QIO_CHANNEL(sioc), "vhost-user client"); + server->ioc = QIO_CHANNEL(sioc); + object_ref(OBJECT(server->ioc)); + qio_channel_attach_aio_context(server->ioc, server->ctx); + qio_channel_set_blocking(QIO_CHANNEL(server->sioc), false, NULL); + vu_client_start(server); +} + + +void vhost_user_server_stop(VuServer *server) +{ + if (server->sioc) { + close_client(server); + } + + if (server->listener) { + qio_net_listener_disconnect(server->listener); + object_unref(OBJECT(server->listener)); + } + +} + +void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx) +{ + VuFdWatch *vu_fd_watch, *next; + void *opaque = NULL; + IOHandler *io_read = NULL; + bool attach; + + server->ctx = ctx ? ctx : qemu_get_aio_context(); + + if (!server->sioc) { + /* not yet serving any client*/ + return; + } + + if (ctx) { + qio_channel_attach_aio_context(server->ioc, ctx); + server->aio_context_changed = true; + io_read = kick_handler; + attach = true; + } else { + qio_channel_detach_aio_context(server->ioc); + /* server->ioc->ctx keeps the old AioConext */ + ctx = server->ioc->ctx; + attach = false; + } + + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { + if (vu_fd_watch->cb) { + opaque = attach ? vu_fd_watch : NULL; + aio_set_fd_handler(ctx, vu_fd_watch->fd, true, + io_read, NULL, NULL, + opaque); + } + } +} + + +bool vhost_user_server_start(VuServer *server, + SocketAddress *socket_addr, + AioContext *ctx, + uint16_t max_queues, + DevicePanicNotifierFn *device_panic_notifier, + const VuDevIface *vu_iface, + Error **errp) +{ + QIONetListener *listener = qio_net_listener_new(); + if (qio_net_listener_open_sync(listener, socket_addr, 1, + errp) < 0) { + object_unref(OBJECT(listener)); + return false; + } + + /* zero out unspecified fileds */ + *server = (VuServer) { + .listener = listener, + .vu_iface = vu_iface, + .max_queues = max_queues, + .ctx = ctx, + .device_panic_notifier = device_panic_notifier, + }; + + qio_net_listener_set_name(server->listener, "vhost-user-backend-listener"); + + qio_net_listener_set_client_func(server->listener, + vu_accept, + server, + NULL); + + QTAILQ_INIT(&server->vu_fd_watches); + return true; +} diff --git a/util/meson.build b/util/meson.build index XXXXXXX..XXXXXXX 100644 --- a/util/meson.build +++ b/util/meson.build @@ -XXX,XX +XXX,XX @@ if have_block util_ss.add(files('main-loop.c')) util_ss.add(files('nvdimm-utils.c')) util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c')) + util_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-server.c')) util_ss.add(files('qemu-coroutine-sleep.c')) util_ss.add(files('qemu-co-shared-resource.c')) util_ss.add(files('thread-pool.c', 'qemu-timer.c')) -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> Move the constants from hw/core/qdev-properties.c to util/block-helpers.h so that knowledge of the min/max values is Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Acked-by: Eduardo Habkost <ehabkost@redhat.com> Message-id: 20200918080912.321299-5-coiby.xu@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/block-helpers.h | 19 +++++++++++++ hw/core/qdev-properties-system.c | 31 ++++----------------- util/block-helpers.c | 46 ++++++++++++++++++++++++++++++++ util/meson.build | 1 + 4 files changed, 71 insertions(+), 26 deletions(-) create mode 100644 util/block-helpers.h create mode 100644 util/block-helpers.c diff --git a/util/block-helpers.h b/util/block-helpers.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/util/block-helpers.h @@ -XXX,XX +XXX,XX @@ +#ifndef BLOCK_HELPERS_H +#define BLOCK_HELPERS_H + +#include "qemu/units.h" + +/* lower limit is sector size */ +#define MIN_BLOCK_SIZE INT64_C(512) +#define MIN_BLOCK_SIZE_STR "512 B" +/* + * upper limit is arbitrary, 2 MiB looks sufficient for all sensible uses, and + * matches qcow2 cluster size limit + */ +#define MAX_BLOCK_SIZE (2 * MiB) +#define MAX_BLOCK_SIZE_STR "2 MiB" + +void check_block_size(const char *id, const char *name, int64_t value, + Error **errp); + +#endif /* BLOCK_HELPERS_H */ diff --git a/hw/core/qdev-properties-system.c b/hw/core/qdev-properties-system.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/qdev-properties-system.c +++ b/hw/core/qdev-properties-system.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/blockdev.h" #include "net/net.h" #include "hw/pci/pci.h" +#include "util/block-helpers.h" static bool check_prop_still_unset(DeviceState *dev, const char *name, const void *old_val, const char *new_val, @@ -XXX,XX +XXX,XX @@ const PropertyInfo qdev_prop_losttickpolicy = { /* --- blocksize --- */ -/* lower limit is sector size */ -#define MIN_BLOCK_SIZE 512 -#define MIN_BLOCK_SIZE_STR "512 B" -/* - * upper limit is arbitrary, 2 MiB looks sufficient for all sensible uses, and - * matches qcow2 cluster size limit - */ -#define MAX_BLOCK_SIZE (2 * MiB) -#define MAX_BLOCK_SIZE_STR "2 MiB" - static void set_blocksize(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void set_blocksize(Object *obj, Visitor *v, const char *name, Property *prop = opaque; uint32_t *ptr = qdev_get_prop_ptr(dev, prop); uint64_t value; + Error *local_err = NULL; if (dev->realized) { qdev_prop_set_after_realize(dev, name, errp); @@ -XXX,XX +XXX,XX @@ static void set_blocksize(Object *obj, Visitor *v, const char *name, if (!visit_type_size(v, name, &value, errp)) { return; } - /* value of 0 means "unset" */ - if (value && (value < MIN_BLOCK_SIZE || value > MAX_BLOCK_SIZE)) { - error_setg(errp, - "Property %s.%s doesn't take value %" PRIu64 - " (minimum: " MIN_BLOCK_SIZE_STR - ", maximum: " MAX_BLOCK_SIZE_STR ")", - dev->id ? : "", name, value); + check_block_size(dev->id ? : "", name, value, &local_err); + if (local_err) { + error_propagate(errp, local_err); return; } - - /* We rely on power-of-2 blocksizes for bitmasks */ - if ((value & (value - 1)) != 0) { - error_setg(errp, - "Property %s.%s doesn't take value '%" PRId64 "', " - "it's not a power of 2", dev->id ?: "", name, (int64_t)value); - return; - } - *ptr = value; } diff --git a/util/block-helpers.c b/util/block-helpers.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/util/block-helpers.c @@ -XXX,XX +XXX,XX @@ +/* + * Block utility functions + * + * Copyright IBM, Corp. 2011 + * Copyright (c) 2020 Coiby Xu <coiby.xu@gmail.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 "qapi/qmp/qerror.h" +#include "block-helpers.h" + +/** + * check_block_size: + * @id: The unique ID of the object + * @name: The name of the property being validated + * @value: The block size in bytes + * @errp: A pointer to an area to store an error + * + * This function checks that the block size meets the following conditions: + * 1. At least MIN_BLOCK_SIZE + * 2. No larger than MAX_BLOCK_SIZE + * 3. A power of 2 + */ +void check_block_size(const char *id, const char *name, int64_t value, + Error **errp) +{ + /* value of 0 means "unset" */ + if (value && (value < MIN_BLOCK_SIZE || value > MAX_BLOCK_SIZE)) { + error_setg(errp, QERR_PROPERTY_VALUE_OUT_OF_RANGE, + id, name, value, MIN_BLOCK_SIZE, MAX_BLOCK_SIZE); + return; + } + + /* We rely on power-of-2 blocksizes for bitmasks */ + if ((value & (value - 1)) != 0) { + error_setg(errp, + "Property %s.%s doesn't take value '%" PRId64 + "', it's not a power of 2", + id, name, value); + return; + } +} diff --git a/util/meson.build b/util/meson.build index XXXXXXX..XXXXXXX 100644 --- a/util/meson.build +++ b/util/meson.build @@ -XXX,XX +XXX,XX @@ if have_block util_ss.add(files('nvdimm-utils.c')) util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c')) util_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-server.c')) + util_ss.add(files('block-helpers.c')) util_ss.add(files('qemu-coroutine-sleep.c')) util_ss.add(files('qemu-co-shared-resource.c')) util_ss.add(files('thread-pool.c', 'qemu-timer.c')) -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> By making use of libvhost-user, block device drive can be shared to the connected vhost-user client. Only one client can connect to the server one time. Since vhost-user-server needs a block drive to be created first, delay the creation of this object. Suggested-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-id: 20200918080912.321299-6-coiby.xu@gmail.com [Shorten "vhost_user_blk_server" string to "vhost_user_blk" to avoid the following compiler warning: ../block/export/vhost-user-blk-server.c:178:50: error: ‘%s’ directive output truncated writing 21 bytes into a region of size 20 [-Werror=format-truncation=] and fix "Invalid size %ld ..." ssize_t format string arguments for 32-bit hosts. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/export/vhost-user-blk-server.h | 36 ++ block/export/vhost-user-blk-server.c | 661 +++++++++++++++++++++++++++ softmmu/vl.c | 4 + block/meson.build | 1 + 4 files changed, 702 insertions(+) create mode 100644 block/export/vhost-user-blk-server.h create mode 100644 block/export/vhost-user-blk-server.c diff --git a/block/export/vhost-user-blk-server.h b/block/export/vhost-user-blk-server.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/block/export/vhost-user-blk-server.h @@ -XXX,XX +XXX,XX @@ +/* + * Sharing QEMU block devices via vhost-user protocal + * + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. + * Copyright (c) 2020 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. + */ + +#ifndef VHOST_USER_BLK_SERVER_H +#define VHOST_USER_BLK_SERVER_H +#include "util/vhost-user-server.h" + +typedef struct VuBlockDev VuBlockDev; +#define TYPE_VHOST_USER_BLK_SERVER "vhost-user-blk-server" +#define VHOST_USER_BLK_SERVER(obj) \ + OBJECT_CHECK(VuBlockDev, obj, TYPE_VHOST_USER_BLK_SERVER) + +/* vhost user block device */ +struct VuBlockDev { + Object parent_obj; + char *node_name; + SocketAddress *addr; + AioContext *ctx; + VuServer vu_server; + bool running; + uint32_t blk_size; + BlockBackend *backend; + QIOChannelSocket *sioc; + QTAILQ_ENTRY(VuBlockDev) next; + struct virtio_blk_config blkcfg; + bool writable; +}; + +#endif /* VHOST_USER_BLK_SERVER_H */ diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ +/* + * Sharing QEMU block devices via vhost-user protocal + * + * Parts of the code based on nbd/server.c. + * + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. + * Copyright (c) 2020 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/block.h" +#include "vhost-user-blk-server.h" +#include "qapi/error.h" +#include "qom/object_interfaces.h" +#include "sysemu/block-backend.h" +#include "util/block-helpers.h" + +enum { + VHOST_USER_BLK_MAX_QUEUES = 1, +}; +struct virtio_blk_inhdr { + unsigned char status; +}; + +typedef struct VuBlockReq { + VuVirtqElement *elem; + int64_t sector_num; + size_t size; + struct virtio_blk_inhdr *in; + struct virtio_blk_outhdr out; + VuServer *server; + struct VuVirtq *vq; +} VuBlockReq; + +static void vu_block_req_complete(VuBlockReq *req) +{ + VuDev *vu_dev = &req->server->vu_dev; + + /* IO size with 1 extra status byte */ + vu_queue_push(vu_dev, req->vq, req->elem, req->size + 1); + vu_queue_notify(vu_dev, req->vq); + + if (req->elem) { + free(req->elem); + } + + g_free(req); +} + +static VuBlockDev *get_vu_block_device_by_server(VuServer *server) +{ + return container_of(server, VuBlockDev, vu_server); +} + +static int coroutine_fn +vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, + uint32_t iovcnt, uint32_t type) +{ + struct virtio_blk_discard_write_zeroes desc; + ssize_t size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc)); + if (unlikely(size != sizeof(desc))) { + error_report("Invalid size %zd, expect %zu", size, sizeof(desc)); + return -EINVAL; + } + + VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); + uint64_t range[2] = { le64_to_cpu(desc.sector) << 9, + le32_to_cpu(desc.num_sectors) << 9 }; + if (type == VIRTIO_BLK_T_DISCARD) { + if (blk_co_pdiscard(vdev_blk->backend, range[0], range[1]) == 0) { + return 0; + } + } else if (type == VIRTIO_BLK_T_WRITE_ZEROES) { + if (blk_co_pwrite_zeroes(vdev_blk->backend, + range[0], range[1], 0) == 0) { + return 0; + } + } + + return -EINVAL; +} + +static void coroutine_fn vu_block_flush(VuBlockReq *req) +{ + VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); + BlockBackend *backend = vdev_blk->backend; + blk_co_flush(backend); +} + +struct req_data { + VuServer *server; + VuVirtq *vq; + VuVirtqElement *elem; +}; + +static void coroutine_fn vu_block_virtio_process_req(void *opaque) +{ + struct req_data *data = opaque; + VuServer *server = data->server; + VuVirtq *vq = data->vq; + VuVirtqElement *elem = data->elem; + uint32_t type; + VuBlockReq *req; + + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + BlockBackend *backend = vdev_blk->backend; + + struct iovec *in_iov = elem->in_sg; + struct iovec *out_iov = elem->out_sg; + unsigned in_num = elem->in_num; + unsigned out_num = elem->out_num; + /* refer to hw/block/virtio_blk.c */ + if (elem->out_num < 1 || elem->in_num < 1) { + error_report("virtio-blk request missing headers"); + free(elem); + return; + } + + req = g_new0(VuBlockReq, 1); + req->server = server; + req->vq = vq; + req->elem = elem; + + if (unlikely(iov_to_buf(out_iov, out_num, 0, &req->out, + sizeof(req->out)) != sizeof(req->out))) { + error_report("virtio-blk request outhdr too short"); + goto err; + } + + iov_discard_front(&out_iov, &out_num, sizeof(req->out)); + + if (in_iov[in_num - 1].iov_len < sizeof(struct virtio_blk_inhdr)) { + error_report("virtio-blk request inhdr too short"); + goto err; + } + + /* We always touch the last byte, so just see how big in_iov is. */ + req->in = (void *)in_iov[in_num - 1].iov_base + + in_iov[in_num - 1].iov_len + - sizeof(struct virtio_blk_inhdr); + iov_discard_back(in_iov, &in_num, sizeof(struct virtio_blk_inhdr)); + + type = le32_to_cpu(req->out.type); + switch (type & ~VIRTIO_BLK_T_BARRIER) { + case VIRTIO_BLK_T_IN: + case VIRTIO_BLK_T_OUT: { + ssize_t ret = 0; + bool is_write = type & VIRTIO_BLK_T_OUT; + req->sector_num = le64_to_cpu(req->out.sector); + + int64_t offset = req->sector_num * vdev_blk->blk_size; + QEMUIOVector qiov; + if (is_write) { + qemu_iovec_init_external(&qiov, out_iov, out_num); + ret = blk_co_pwritev(backend, offset, qiov.size, + &qiov, 0); + } else { + qemu_iovec_init_external(&qiov, in_iov, in_num); + ret = blk_co_preadv(backend, offset, qiov.size, + &qiov, 0); + } + if (ret >= 0) { + req->in->status = VIRTIO_BLK_S_OK; + } else { + req->in->status = VIRTIO_BLK_S_IOERR; + } + break; + } + case VIRTIO_BLK_T_FLUSH: + vu_block_flush(req); + req->in->status = VIRTIO_BLK_S_OK; + break; + case VIRTIO_BLK_T_GET_ID: { + size_t size = MIN(iov_size(&elem->in_sg[0], in_num), + VIRTIO_BLK_ID_BYTES); + snprintf(elem->in_sg[0].iov_base, size, "%s", "vhost_user_blk"); + req->in->status = VIRTIO_BLK_S_OK; + req->size = elem->in_sg[0].iov_len; + break; + } + case VIRTIO_BLK_T_DISCARD: + case VIRTIO_BLK_T_WRITE_ZEROES: { + int rc; + rc = vu_block_discard_write_zeroes(req, &elem->out_sg[1], + out_num, type); + if (rc == 0) { + req->in->status = VIRTIO_BLK_S_OK; + } else { + req->in->status = VIRTIO_BLK_S_IOERR; + } + break; + } + default: + req->in->status = VIRTIO_BLK_S_UNSUPP; + break; + } + + vu_block_req_complete(req); + return; + +err: + free(elem); + g_free(req); + return; +} + +static void vu_block_process_vq(VuDev *vu_dev, int idx) +{ + VuServer *server; + VuVirtq *vq; + struct req_data *req_data; + + server = container_of(vu_dev, VuServer, vu_dev); + assert(server); + + vq = vu_get_queue(vu_dev, idx); + assert(vq); + VuVirtqElement *elem; + while (1) { + elem = vu_queue_pop(vu_dev, vq, sizeof(VuVirtqElement) + + sizeof(VuBlockReq)); + if (elem) { + req_data = g_new0(struct req_data, 1); + req_data->server = server; + req_data->vq = vq; + req_data->elem = elem; + Coroutine *co = qemu_coroutine_create(vu_block_virtio_process_req, + req_data); + aio_co_enter(server->ioc->ctx, co); + } else { + break; + } + } +} + +static void vu_block_queue_set_started(VuDev *vu_dev, int idx, bool started) +{ + VuVirtq *vq; + + assert(vu_dev); + + vq = vu_get_queue(vu_dev, idx); + vu_set_queue_handler(vu_dev, vq, started ? vu_block_process_vq : NULL); +} + +static uint64_t vu_block_get_features(VuDev *dev) +{ + uint64_t features; + VuServer *server = container_of(dev, VuServer, vu_dev); + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + features = 1ull << VIRTIO_BLK_F_SIZE_MAX | + 1ull << VIRTIO_BLK_F_SEG_MAX | + 1ull << VIRTIO_BLK_F_TOPOLOGY | + 1ull << VIRTIO_BLK_F_BLK_SIZE | + 1ull << VIRTIO_BLK_F_FLUSH | + 1ull << VIRTIO_BLK_F_DISCARD | + 1ull << VIRTIO_BLK_F_WRITE_ZEROES | + 1ull << VIRTIO_BLK_F_CONFIG_WCE | + 1ull << VIRTIO_F_VERSION_1 | + 1ull << VIRTIO_RING_F_INDIRECT_DESC | + 1ull << VIRTIO_RING_F_EVENT_IDX | + 1ull << VHOST_USER_F_PROTOCOL_FEATURES; + + if (!vdev_blk->writable) { + features |= 1ull << VIRTIO_BLK_F_RO; + } + + return features; +} + +static uint64_t vu_block_get_protocol_features(VuDev *dev) +{ + return 1ull << VHOST_USER_PROTOCOL_F_CONFIG | + 1ull << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD; +} + +static int +vu_block_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len) +{ + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + memcpy(config, &vdev_blk->blkcfg, len); + + return 0; +} + +static int +vu_block_set_config(VuDev *vu_dev, const uint8_t *data, + uint32_t offset, uint32_t size, uint32_t flags) +{ + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + uint8_t wce; + + /* don't support live migration */ + if (flags != VHOST_SET_CONFIG_TYPE_MASTER) { + return -EINVAL; + } + + if (offset != offsetof(struct virtio_blk_config, wce) || + size != 1) { + return -EINVAL; + } + + wce = *data; + vdev_blk->blkcfg.wce = wce; + blk_set_enable_write_cache(vdev_blk->backend, wce); + return 0; +} + +/* + * When the client disconnects, it sends a VHOST_USER_NONE request + * and vu_process_message will simple call exit which cause the VM + * to exit abruptly. + * To avoid this issue, process VHOST_USER_NONE request ahead + * of vu_process_message. + * + */ +static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) +{ + if (vmsg->request == VHOST_USER_NONE) { + dev->panic(dev, "disconnect"); + return true; + } + return false; +} + +static const VuDevIface vu_block_iface = { + .get_features = vu_block_get_features, + .queue_set_started = vu_block_queue_set_started, + .get_protocol_features = vu_block_get_protocol_features, + .get_config = vu_block_get_config, + .set_config = vu_block_set_config, + .process_msg = vu_block_process_msg, +}; + +static void blk_aio_attached(AioContext *ctx, void *opaque) +{ + VuBlockDev *vub_dev = opaque; + aio_context_acquire(ctx); + vhost_user_server_set_aio_context(&vub_dev->vu_server, ctx); + aio_context_release(ctx); +} + +static void blk_aio_detach(void *opaque) +{ + VuBlockDev *vub_dev = opaque; + AioContext *ctx = vub_dev->vu_server.ctx; + aio_context_acquire(ctx); + vhost_user_server_set_aio_context(&vub_dev->vu_server, NULL); + aio_context_release(ctx); +} + +static void +vu_block_initialize_config(BlockDriverState *bs, + struct virtio_blk_config *config, uint32_t blk_size) +{ + config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS; + config->blk_size = blk_size; + config->size_max = 0; + config->seg_max = 128 - 2; + config->min_io_size = 1; + config->opt_io_size = 1; + config->num_queues = VHOST_USER_BLK_MAX_QUEUES; + config->max_discard_sectors = 32768; + config->max_discard_seg = 1; + config->discard_sector_alignment = config->blk_size >> 9; + config->max_write_zeroes_sectors = 32768; + config->max_write_zeroes_seg = 1; +} + +static VuBlockDev *vu_block_init(VuBlockDev *vu_block_device, Error **errp) +{ + + BlockBackend *blk; + Error *local_error = NULL; + const char *node_name = vu_block_device->node_name; + bool writable = vu_block_device->writable; + uint64_t perm = BLK_PERM_CONSISTENT_READ; + int ret; + + AioContext *ctx; + + BlockDriverState *bs = bdrv_lookup_bs(node_name, node_name, &local_error); + + if (!bs) { + error_propagate(errp, local_error); + return NULL; + } + + if (bdrv_is_read_only(bs)) { + writable = false; + } + + if (writable) { + perm |= BLK_PERM_WRITE; + } + + ctx = bdrv_get_aio_context(bs); + aio_context_acquire(ctx); + bdrv_invalidate_cache(bs, NULL); + aio_context_release(ctx); + + /* + * Don't allow resize while the vhost user server is running, + * otherwise we don't care what happens with the node. + */ + blk = blk_new(bdrv_get_aio_context(bs), perm, + BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED | + BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD); + ret = blk_insert_bs(blk, bs, errp); + + if (ret < 0) { + goto fail; + } + + blk_set_enable_write_cache(blk, false); + + blk_set_allow_aio_context_change(blk, true); + + vu_block_device->blkcfg.wce = 0; + vu_block_device->backend = blk; + if (!vu_block_device->blk_size) { + vu_block_device->blk_size = BDRV_SECTOR_SIZE; + } + vu_block_device->blkcfg.blk_size = vu_block_device->blk_size; + blk_set_guest_block_size(blk, vu_block_device->blk_size); + vu_block_initialize_config(bs, &vu_block_device->blkcfg, + vu_block_device->blk_size); + return vu_block_device; + +fail: + blk_unref(blk); + return NULL; +} + +static void vu_block_deinit(VuBlockDev *vu_block_device) +{ + if (vu_block_device->backend) { + blk_remove_aio_context_notifier(vu_block_device->backend, blk_aio_attached, + blk_aio_detach, vu_block_device); + } + + blk_unref(vu_block_device->backend); +} + +static void vhost_user_blk_server_stop(VuBlockDev *vu_block_device) +{ + vhost_user_server_stop(&vu_block_device->vu_server); + vu_block_deinit(vu_block_device); +} + +static void vhost_user_blk_server_start(VuBlockDev *vu_block_device, + Error **errp) +{ + AioContext *ctx; + SocketAddress *addr = vu_block_device->addr; + + if (!vu_block_init(vu_block_device, errp)) { + return; + } + + ctx = bdrv_get_aio_context(blk_bs(vu_block_device->backend)); + + if (!vhost_user_server_start(&vu_block_device->vu_server, addr, ctx, + VHOST_USER_BLK_MAX_QUEUES, + NULL, &vu_block_iface, + errp)) { + goto error; + } + + blk_add_aio_context_notifier(vu_block_device->backend, blk_aio_attached, + blk_aio_detach, vu_block_device); + vu_block_device->running = true; + return; + + error: + vu_block_deinit(vu_block_device); +} + +static bool vu_prop_modifiable(VuBlockDev *vus, Error **errp) +{ + if (vus->running) { + error_setg(errp, "The property can't be modified " + "while the server is running"); + return false; + } + return true; +} + +static void vu_set_node_name(Object *obj, const char *value, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + + if (!vu_prop_modifiable(vus, errp)) { + return; + } + + if (vus->node_name) { + g_free(vus->node_name); + } + + vus->node_name = g_strdup(value); +} + +static char *vu_get_node_name(Object *obj, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + return g_strdup(vus->node_name); +} + +static void free_socket_addr(SocketAddress *addr) +{ + g_free(addr->u.q_unix.path); + g_free(addr); +} + +static void vu_set_unix_socket(Object *obj, const char *value, + Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + + if (!vu_prop_modifiable(vus, errp)) { + return; + } + + if (vus->addr) { + free_socket_addr(vus->addr); + } + + SocketAddress *addr = g_new0(SocketAddress, 1); + addr->type = SOCKET_ADDRESS_TYPE_UNIX; + addr->u.q_unix.path = g_strdup(value); + vus->addr = addr; +} + +static char *vu_get_unix_socket(Object *obj, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + return g_strdup(vus->addr->u.q_unix.path); +} + +static bool vu_get_block_writable(Object *obj, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + return vus->writable; +} + +static void vu_set_block_writable(Object *obj, bool value, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + + if (!vu_prop_modifiable(vus, errp)) { + return; + } + + vus->writable = value; +} + +static void vu_get_blk_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + uint32_t value = vus->blk_size; + + visit_type_uint32(v, name, &value, errp); +} + +static void vu_set_blk_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + + Error *local_err = NULL; + uint32_t value; + + if (!vu_prop_modifiable(vus, errp)) { + return; + } + + visit_type_uint32(v, name, &value, &local_err); + if (local_err) { + goto out; + } + + check_block_size(object_get_typename(obj), name, value, &local_err); + if (local_err) { + goto out; + } + + vus->blk_size = value; + +out: + error_propagate(errp, local_err); +} + +static void vhost_user_blk_server_instance_finalize(Object *obj) +{ + VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); + + vhost_user_blk_server_stop(vub); + + /* + * Unlike object_property_add_str, object_class_property_add_str + * doesn't have a release method. Thus manual memory freeing is + * needed. + */ + free_socket_addr(vub->addr); + g_free(vub->node_name); +} + +static void vhost_user_blk_server_complete(UserCreatable *obj, Error **errp) +{ + VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); + + vhost_user_blk_server_start(vub, errp); +} + +static void vhost_user_blk_server_class_init(ObjectClass *klass, + void *class_data) +{ + UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass); + ucc->complete = vhost_user_blk_server_complete; + + object_class_property_add_bool(klass, "writable", + vu_get_block_writable, + vu_set_block_writable); + + object_class_property_add_str(klass, "node-name", + vu_get_node_name, + vu_set_node_name); + + object_class_property_add_str(klass, "unix-socket", + vu_get_unix_socket, + vu_set_unix_socket); + + object_class_property_add(klass, "logical-block-size", "uint32", + vu_get_blk_size, vu_set_blk_size, + NULL, NULL); +} + +static const TypeInfo vhost_user_blk_server_info = { + .name = TYPE_VHOST_USER_BLK_SERVER, + .parent = TYPE_OBJECT, + .instance_size = sizeof(VuBlockDev), + .instance_finalize = vhost_user_blk_server_instance_finalize, + .class_init = vhost_user_blk_server_class_init, + .interfaces = (InterfaceInfo[]) { + {TYPE_USER_CREATABLE}, + {} + }, +}; + +static void vhost_user_blk_server_register_types(void) +{ + type_register_static(&vhost_user_blk_server_info); +} + +type_init(vhost_user_blk_server_register_types) 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 bool object_create_initial(const char *type, QemuOpts *opts) } #endif + /* Reason: vhost-user-blk-server property "node-name" */ + if (g_str_equal(type, "vhost-user-blk-server")) { + return false; + } /* * Reason: filter-* property "netdev" etc. */ 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_ss.add(when: 'CONFIG_WIN32', if_true: files('file-win32.c', 'win32-aio.c') block_ss.add(when: 'CONFIG_POSIX', if_true: [files('file-posix.c'), coref, iokit]) block_ss.add(when: 'CONFIG_LIBISCSI', if_true: files('iscsi-opts.c')) block_ss.add(when: 'CONFIG_LINUX', if_true: files('nvme.c')) +block_ss.add(when: 'CONFIG_LINUX', if_true: files('export/vhost-user-blk-server.c', '../contrib/libvhost-user/libvhost-user.c')) block_ss.add(when: 'CONFIG_REPLICATION', if_true: files('replication.c')) block_ss.add(when: 'CONFIG_SHEEPDOG', if_true: files('sheepdog.c')) block_ss.add(when: ['CONFIG_LINUX_AIO', libaio], if_true: files('linux-aio.c')) -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> Suggested-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-id: 20200918080912.321299-8-coiby.xu@gmail.com [Removed reference to vhost-user-blk-test.c, it will be sent in a separate pull request. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ L: qemu-block@nongnu.org S: Supported F: tests/image-fuzzer/ +Vhost-user block device backend server +M: Coiby Xu <Coiby.Xu@gmail.com> +S: Maintained +F: block/export/vhost-user-blk-server.c +F: util/vhost-user-server.c +F: tests/qtest/libqos/vhost-user-blk.c + Replication M: Wen Congyang <wencongyang2@huawei.com> M: Xie Changlong <xiechanglong.d@gmail.com> -- 2.26.2 Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-3-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, return false; } - /* zero out unspecified fileds */ + /* zero out unspecified fields */ *server = (VuServer) { .listener = listener, .vu_iface = vu_iface, -- 2.26.2 We already have access to the value with the correct type (ioc and sioc are the same QIOChannel). Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-4-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, server->ioc = QIO_CHANNEL(sioc); object_ref(OBJECT(server->ioc)); qio_channel_attach_aio_context(server->ioc, server->ctx); - qio_channel_set_blocking(QIO_CHANNEL(server->sioc), false, NULL); + qio_channel_set_blocking(server->ioc, false, NULL); vu_client_start(server); } -- 2.26.2 Explicitly deleting watches is not necessary since libvhost-user calls remove_watch() during vu_deinit(). Add an assertion to check this though. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-5-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.c | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ static void close_client(VuServer *server) /* When this is set vu_client_trip will stop new processing vhost-user message */ server->sioc = NULL; - VuFdWatch *vu_fd_watch, *next; - QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { - aio_set_fd_handler(server->ioc->ctx, vu_fd_watch->fd, true, NULL, - NULL, NULL, NULL); - } - - while (!QTAILQ_EMPTY(&server->vu_fd_watches)) { - QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { - if (!vu_fd_watch->processing) { - QTAILQ_REMOVE(&server->vu_fd_watches, vu_fd_watch, next); - g_free(vu_fd_watch); - } - } - } - while (server->processing_msg) { if (server->ioc->read_coroutine) { server->ioc->read_coroutine = NULL; @@ -XXX,XX +XXX,XX @@ static void close_client(VuServer *server) } vu_deinit(&server->vu_dev); + + /* vu_deinit() should have called remove_watch() */ + assert(QTAILQ_EMPTY(&server->vu_fd_watches)); + object_unref(OBJECT(sioc)); object_unref(OBJECT(server->ioc)); } -- 2.26.2 Only one struct is needed per request. Drop req_data and the separate VuBlockReq instance. Instead let vu_queue_pop() allocate everything at once. This fixes the req_data memory leak in vu_block_virtio_process_req(). Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-6-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/export/vhost-user-blk-server.c | 68 +++++++++------------------- 1 file changed, 21 insertions(+), 47 deletions(-) diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ struct virtio_blk_inhdr { }; typedef struct VuBlockReq { - VuVirtqElement *elem; + VuVirtqElement elem; int64_t sector_num; size_t size; struct virtio_blk_inhdr *in; @@ -XXX,XX +XXX,XX @@ static void vu_block_req_complete(VuBlockReq *req) VuDev *vu_dev = &req->server->vu_dev; /* IO size with 1 extra status byte */ - vu_queue_push(vu_dev, req->vq, req->elem, req->size + 1); + vu_queue_push(vu_dev, req->vq, &req->elem, req->size + 1); vu_queue_notify(vu_dev, req->vq); - if (req->elem) { - free(req->elem); - } - - g_free(req); + free(req); } static VuBlockDev *get_vu_block_device_by_server(VuServer *server) @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_flush(VuBlockReq *req) blk_co_flush(backend); } -struct req_data { - VuServer *server; - VuVirtq *vq; - VuVirtqElement *elem; -}; - static void coroutine_fn vu_block_virtio_process_req(void *opaque) { - struct req_data *data = opaque; - VuServer *server = data->server; - VuVirtq *vq = data->vq; - VuVirtqElement *elem = data->elem; + VuBlockReq *req = opaque; + VuServer *server = req->server; + VuVirtqElement *elem = &req->elem; uint32_t type; - VuBlockReq *req; VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); BlockBackend *backend = vdev_blk->backend; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) struct iovec *out_iov = elem->out_sg; unsigned in_num = elem->in_num; unsigned out_num = elem->out_num; + /* refer to hw/block/virtio_blk.c */ if (elem->out_num < 1 || elem->in_num < 1) { error_report("virtio-blk request missing headers"); - free(elem); - return; + goto err; } - req = g_new0(VuBlockReq, 1); - req->server = server; - req->vq = vq; - req->elem = elem; - if (unlikely(iov_to_buf(out_iov, out_num, 0, &req->out, sizeof(req->out)) != sizeof(req->out))) { error_report("virtio-blk request outhdr too short"); @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) err: free(elem); - g_free(req); - return; } static void vu_block_process_vq(VuDev *vu_dev, int idx) { - VuServer *server; - VuVirtq *vq; - struct req_data *req_data; + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + VuVirtq *vq = vu_get_queue(vu_dev, idx); - server = container_of(vu_dev, VuServer, vu_dev); - assert(server); - - vq = vu_get_queue(vu_dev, idx); - assert(vq); - VuVirtqElement *elem; while (1) { - elem = vu_queue_pop(vu_dev, vq, sizeof(VuVirtqElement) + - sizeof(VuBlockReq)); - if (elem) { - req_data = g_new0(struct req_data, 1); - req_data->server = server; - req_data->vq = vq; - req_data->elem = elem; - Coroutine *co = qemu_coroutine_create(vu_block_virtio_process_req, - req_data); - aio_co_enter(server->ioc->ctx, co); - } else { + VuBlockReq *req; + + req = vu_queue_pop(vu_dev, vq, sizeof(VuBlockReq)); + if (!req) { break; } + + req->server = server; + req->vq = vq; + + Coroutine *co = + qemu_coroutine_create(vu_block_virtio_process_req, req); + qemu_coroutine_enter(co); } } -- 2.26.2 The device panic notifier callback is not used. Drop it. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-7-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.h | 3 --- block/export/vhost-user-blk-server.c | 3 +-- util/vhost-user-server.c | 6 ------ 3 files changed, 1 insertion(+), 11 deletions(-) diff --git a/util/vhost-user-server.h b/util/vhost-user-server.h index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.h +++ b/util/vhost-user-server.h @@ -XXX,XX +XXX,XX @@ typedef struct VuFdWatch { } VuFdWatch; typedef struct VuServer VuServer; -typedef void DevicePanicNotifierFn(VuServer *server); struct VuServer { QIONetListener *listener; AioContext *ctx; - DevicePanicNotifierFn *device_panic_notifier; int max_queues; const VuDevIface *vu_iface; VuDev vu_dev; @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, SocketAddress *unix_socket, AioContext *ctx, uint16_t max_queues, - DevicePanicNotifierFn *device_panic_notifier, const VuDevIface *vu_iface, Error **errp); diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ static void vhost_user_blk_server_start(VuBlockDev *vu_block_device, ctx = bdrv_get_aio_context(blk_bs(vu_block_device->backend)); if (!vhost_user_server_start(&vu_block_device->vu_server, addr, ctx, - VHOST_USER_BLK_MAX_QUEUES, - NULL, &vu_block_iface, + VHOST_USER_BLK_MAX_QUEUES, &vu_block_iface, errp)) { goto error; } diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ static void panic_cb(VuDev *vu_dev, const char *buf) close_client(server); } - if (server->device_panic_notifier) { - server->device_panic_notifier(server); - } - /* * Set the callback function for network listener so another * vhost-user client can connect to this server @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, SocketAddress *socket_addr, AioContext *ctx, uint16_t max_queues, - DevicePanicNotifierFn *device_panic_notifier, const VuDevIface *vu_iface, Error **errp) { @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, .vu_iface = vu_iface, .max_queues = max_queues, .ctx = ctx, - .device_panic_notifier = device_panic_notifier, }; qio_net_listener_set_name(server->listener, "vhost-user-backend-listener"); -- 2.26.2 fds[] is leaked when qio_channel_readv_full() fails. Use vmsg->fds[] instead of keeping a local fds[] array. Then we can reuse goto fail to clean up fds. vmsg->fd_num must be zeroed before the loop to make this safe. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-8-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.c | 50 ++++++++++++++++++---------------------- 1 file changed, 23 insertions(+), 27 deletions(-) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) }; int rc, read_bytes = 0; Error *local_err = NULL; - /* - * Store fds/nfds returned from qio_channel_readv_full into - * temporary variables. - * - * VhostUserMsg is a packed structure, gcc will complain about passing - * pointer to a packed structure member if we pass &VhostUserMsg.fd_num - * and &VhostUserMsg.fds directly when calling qio_channel_readv_full, - * thus two temporary variables nfds and fds are used here. - */ - size_t nfds = 0, nfds_t = 0; const size_t max_fds = G_N_ELEMENTS(vmsg->fds); - int *fds_t = NULL; VuServer *server = container_of(vu_dev, VuServer, vu_dev); QIOChannel *ioc = server->ioc; + vmsg->fd_num = 0; if (!ioc) { error_report_err(local_err); goto fail; @@ -XXX,XX +XXX,XX @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) assert(qemu_in_coroutine()); do { + size_t nfds = 0; + int *fds = NULL; + /* * qio_channel_readv_full may have short reads, keeping calling it * until getting VHOST_USER_HDR_SIZE or 0 bytes in total */ - rc = qio_channel_readv_full(ioc, &iov, 1, &fds_t, &nfds_t, &local_err); + rc = qio_channel_readv_full(ioc, &iov, 1, &fds, &nfds, &local_err); if (rc < 0) { if (rc == QIO_CHANNEL_ERR_BLOCK) { + assert(local_err == NULL); qio_channel_yield(ioc, G_IO_IN); continue; } else { error_report_err(local_err); - return false; + goto fail; } } - read_bytes += rc; - if (nfds_t > 0) { - if (nfds + nfds_t > max_fds) { + + if (nfds > 0) { + if (vmsg->fd_num + nfds > max_fds) { error_report("A maximum of %zu fds are allowed, " "however got %zu fds now", - max_fds, nfds + nfds_t); + max_fds, vmsg->fd_num + nfds); + g_free(fds); goto fail; } - memcpy(vmsg->fds + nfds, fds_t, - nfds_t *sizeof(vmsg->fds[0])); - nfds += nfds_t; - g_free(fds_t); + memcpy(vmsg->fds + vmsg->fd_num, fds, nfds * sizeof(vmsg->fds[0])); + vmsg->fd_num += nfds; + g_free(fds); } - if (read_bytes == VHOST_USER_HDR_SIZE || rc == 0) { - break; + + if (rc == 0) { /* socket closed */ + goto fail; } - iov.iov_base = (char *)vmsg + read_bytes; - iov.iov_len = VHOST_USER_HDR_SIZE - read_bytes; - } while (true); - vmsg->fd_num = nfds; + iov.iov_base += rc; + iov.iov_len -= rc; + read_bytes += rc; + } while (read_bytes != VHOST_USER_HDR_SIZE); + /* qio_channel_readv_full will make socket fds blocking, unblock them */ vmsg_unblock_fds(vmsg); if (vmsg->size > sizeof(vmsg->payload)) { -- 2.26.2 Unexpected EOF is an error that must be reported. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-9-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) }; if (vmsg->size) { rc = qio_channel_readv_all_eof(ioc, &iov_payload, 1, &local_err); - if (rc == -1) { - error_report_err(local_err); + if (rc != 1) { + if (local_err) { + error_report_err(local_err); + } goto fail; } } -- 2.26.2 The vu_client_trip() coroutine is leaked during AioContext switching. It is also unsafe to destroy the vu_dev in panic_cb() since its callers still access it in some cases. Rework the lifecycle to solve these safety issues. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-10-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.h | 29 ++-- block/export/vhost-user-blk-server.c | 9 +- util/vhost-user-server.c | 245 +++++++++++++++------------ 3 files changed, 155 insertions(+), 128 deletions(-) diff --git a/util/vhost-user-server.h b/util/vhost-user-server.h index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.h +++ b/util/vhost-user-server.h @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "standard-headers/linux/virtio_blk.h" +/* A kick fd that we monitor on behalf of libvhost-user */ typedef struct VuFdWatch { VuDev *vu_dev; int fd; /*kick fd*/ void *pvt; vu_watch_cb cb; - bool processing; QTAILQ_ENTRY(VuFdWatch) next; } VuFdWatch; -typedef struct VuServer VuServer; - -struct VuServer { +/** + * VuServer: + * A vhost-user server instance with user-defined VuDevIface callbacks. + * Vhost-user device backends can be implemented using VuServer. VuDevIface + * callbacks and virtqueue kicks run in the given AioContext. + */ +typedef struct { QIONetListener *listener; + QEMUBH *restart_listener_bh; AioContext *ctx; int max_queues; const VuDevIface *vu_iface; + + /* Protected by ctx lock */ VuDev vu_dev; QIOChannel *ioc; /* The I/O channel with the client */ QIOChannelSocket *sioc; /* The underlying data channel with the client */ - /* IOChannel for fd provided via VHOST_USER_SET_SLAVE_REQ_FD */ - QIOChannel *ioc_slave; - QIOChannelSocket *sioc_slave; - Coroutine *co_trip; /* coroutine for processing VhostUserMsg */ QTAILQ_HEAD(, VuFdWatch) vu_fd_watches; - /* restart coroutine co_trip if AIOContext is changed */ - bool aio_context_changed; - bool processing_msg; -}; + + Coroutine *co_trip; /* coroutine for processing VhostUserMsg */ +} VuServer; bool vhost_user_server_start(VuServer *server, SocketAddress *unix_socket, @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, void vhost_user_server_stop(VuServer *server); -void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx); +void vhost_user_server_attach_aio_context(VuServer *server, AioContext *ctx); +void vhost_user_server_detach_aio_context(VuServer *server); #endif /* VHOST_USER_SERVER_H */ diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ static const VuDevIface vu_block_iface = { static void blk_aio_attached(AioContext *ctx, void *opaque) { VuBlockDev *vub_dev = opaque; - aio_context_acquire(ctx); - vhost_user_server_set_aio_context(&vub_dev->vu_server, ctx); - aio_context_release(ctx); + vhost_user_server_attach_aio_context(&vub_dev->vu_server, ctx); } static void blk_aio_detach(void *opaque) { VuBlockDev *vub_dev = opaque; - AioContext *ctx = vub_dev->vu_server.ctx; - aio_context_acquire(ctx); - vhost_user_server_set_aio_context(&vub_dev->vu_server, NULL); - aio_context_release(ctx); + vhost_user_server_detach_aio_context(&vub_dev->vu_server); } static void diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" #include "qemu/main-loop.h" +#include "block/aio-wait.h" #include "vhost-user-server.h" +/* + * Theory of operation: + * + * VuServer is started and stopped by vhost_user_server_start() and + * vhost_user_server_stop() from the main loop thread. Starting the server + * opens a vhost-user UNIX domain socket and listens for incoming connections. + * Only one connection is allowed at a time. + * + * The connection is handled by the vu_client_trip() coroutine in the + * VuServer->ctx AioContext. The coroutine consists of a vu_dispatch() loop + * where libvhost-user calls vu_message_read() to receive the next vhost-user + * protocol messages over the UNIX domain socket. + * + * When virtqueues are set up libvhost-user calls set_watch() to monitor kick + * fds. These fds are also handled in the VuServer->ctx AioContext. + * + * Both vu_client_trip() and kick fd monitoring can be stopped by shutting down + * the socket connection. Shutting down the socket connection causes + * vu_message_read() to fail since no more data can be received from the socket. + * After vu_dispatch() fails, vu_client_trip() calls vu_deinit() to stop + * libvhost-user before terminating the coroutine. vu_deinit() calls + * remove_watch() to stop monitoring kick fds and this stops virtqueue + * processing. + * + * When vu_client_trip() has finished cleaning up it schedules a BH in the main + * loop thread to accept the next client connection. + * + * When libvhost-user detects an error it calls panic_cb() and sets the + * dev->broken flag. Both vu_client_trip() and kick fd processing stop when + * the dev->broken flag is set. + * + * It is possible to switch AioContexts using + * vhost_user_server_detach_aio_context() and + * vhost_user_server_attach_aio_context(). They stop monitoring fds in the old + * AioContext and resume monitoring in the new AioContext. The vu_client_trip() + * coroutine remains in a yielded state during the switch. This is made + * possible by QIOChannel's support for spurious coroutine re-entry in + * qio_channel_yield(). The coroutine will restart I/O when re-entered from the + * new AioContext. + */ + static void vmsg_close_fds(VhostUserMsg *vmsg) { int i; @@ -XXX,XX +XXX,XX @@ static void vmsg_unblock_fds(VhostUserMsg *vmsg) } } -static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, - gpointer opaque); - -static void close_client(VuServer *server) -{ - /* - * Before closing the client - * - * 1. Let vu_client_trip stop processing new vhost-user msg - * - * 2. remove kick_handler - * - * 3. wait for the kick handler to be finished - * - * 4. wait for the current vhost-user msg to be finished processing - */ - - QIOChannelSocket *sioc = server->sioc; - /* When this is set vu_client_trip will stop new processing vhost-user message */ - server->sioc = NULL; - - while (server->processing_msg) { - if (server->ioc->read_coroutine) { - server->ioc->read_coroutine = NULL; - qio_channel_set_aio_fd_handler(server->ioc, server->ioc->ctx, NULL, - NULL, server->ioc); - server->processing_msg = false; - } - } - - vu_deinit(&server->vu_dev); - - /* vu_deinit() should have called remove_watch() */ - assert(QTAILQ_EMPTY(&server->vu_fd_watches)); - - object_unref(OBJECT(sioc)); - object_unref(OBJECT(server->ioc)); -} - static void panic_cb(VuDev *vu_dev, const char *buf) { - VuServer *server = container_of(vu_dev, VuServer, vu_dev); - - /* avoid while loop in close_client */ - server->processing_msg = false; - - if (buf) { - error_report("vu_panic: %s", buf); - } - - if (server->sioc) { - close_client(server); - } - - /* - * Set the callback function for network listener so another - * vhost-user client can connect to this server - */ - qio_net_listener_set_client_func(server->listener, - vu_accept, - server, - NULL); + error_report("vu_panic: %s", buf); } static bool coroutine_fn @@ -XXX,XX +XXX,XX @@ fail: return false; } - -static void vu_client_start(VuServer *server); static coroutine_fn void vu_client_trip(void *opaque) { VuServer *server = opaque; + VuDev *vu_dev = &server->vu_dev; - while (!server->aio_context_changed && server->sioc) { - server->processing_msg = true; - vu_dispatch(&server->vu_dev); - server->processing_msg = false; + while (!vu_dev->broken && vu_dispatch(vu_dev)) { + /* Keep running */ } - if (server->aio_context_changed && server->sioc) { - server->aio_context_changed = false; - vu_client_start(server); - } -} + vu_deinit(vu_dev); + + /* vu_deinit() should have called remove_watch() */ + assert(QTAILQ_EMPTY(&server->vu_fd_watches)); + + object_unref(OBJECT(server->sioc)); + server->sioc = NULL; -static void vu_client_start(VuServer *server) -{ - server->co_trip = qemu_coroutine_create(vu_client_trip, server); - aio_co_enter(server->ctx, server->co_trip); + object_unref(OBJECT(server->ioc)); + server->ioc = NULL; + + server->co_trip = NULL; + if (server->restart_listener_bh) { + qemu_bh_schedule(server->restart_listener_bh); + } + aio_wait_kick(); } /* @@ -XXX,XX +XXX,XX @@ static void vu_client_start(VuServer *server) static void kick_handler(void *opaque) { VuFdWatch *vu_fd_watch = opaque; - vu_fd_watch->processing = true; - vu_fd_watch->cb(vu_fd_watch->vu_dev, 0, vu_fd_watch->pvt); - vu_fd_watch->processing = false; + VuDev *vu_dev = vu_fd_watch->vu_dev; + + vu_fd_watch->cb(vu_dev, 0, vu_fd_watch->pvt); + + /* Stop vu_client_trip() if an error occurred in vu_fd_watch->cb() */ + if (vu_dev->broken) { + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + + qio_channel_shutdown(server->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); + } } - static VuFdWatch *find_vu_fd_watch(VuServer *server, int fd) { @@ -XXX,XX +XXX,XX @@ static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, qio_channel_set_name(QIO_CHANNEL(sioc), "vhost-user client"); server->ioc = QIO_CHANNEL(sioc); object_ref(OBJECT(server->ioc)); - qio_channel_attach_aio_context(server->ioc, server->ctx); + + /* TODO vu_message_write() spins if non-blocking! */ qio_channel_set_blocking(server->ioc, false, NULL); - vu_client_start(server); + + server->co_trip = qemu_coroutine_create(vu_client_trip, server); + + aio_context_acquire(server->ctx); + vhost_user_server_attach_aio_context(server, server->ctx); + aio_context_release(server->ctx); } - void vhost_user_server_stop(VuServer *server) { + aio_context_acquire(server->ctx); + + qemu_bh_delete(server->restart_listener_bh); + server->restart_listener_bh = NULL; + if (server->sioc) { - close_client(server); + VuFdWatch *vu_fd_watch; + + QTAILQ_FOREACH(vu_fd_watch, &server->vu_fd_watches, next) { + aio_set_fd_handler(server->ctx, vu_fd_watch->fd, true, + NULL, NULL, NULL, vu_fd_watch); + } + + qio_channel_shutdown(server->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); + + AIO_WAIT_WHILE(server->ctx, server->co_trip); } + aio_context_release(server->ctx); + if (server->listener) { qio_net_listener_disconnect(server->listener); object_unref(OBJECT(server->listener)); } +} + +/* + * Allow the next client to connect to the server. Called from a BH in the main + * loop. + */ +static void restart_listener_bh(void *opaque) +{ + VuServer *server = opaque; + qio_net_listener_set_client_func(server->listener, vu_accept, server, + NULL); } -void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx) +/* Called with ctx acquired */ +void vhost_user_server_attach_aio_context(VuServer *server, AioContext *ctx) { - VuFdWatch *vu_fd_watch, *next; - void *opaque = NULL; - IOHandler *io_read = NULL; - bool attach; + VuFdWatch *vu_fd_watch; - server->ctx = ctx ? ctx : qemu_get_aio_context(); + server->ctx = ctx; if (!server->sioc) { - /* not yet serving any client*/ return; } - if (ctx) { - qio_channel_attach_aio_context(server->ioc, ctx); - server->aio_context_changed = true; - io_read = kick_handler; - attach = true; - } else { + qio_channel_attach_aio_context(server->ioc, ctx); + + QTAILQ_FOREACH(vu_fd_watch, &server->vu_fd_watches, next) { + aio_set_fd_handler(ctx, vu_fd_watch->fd, true, kick_handler, NULL, + NULL, vu_fd_watch); + } + + aio_co_schedule(ctx, server->co_trip); +} + +/* Called with server->ctx acquired */ +void vhost_user_server_detach_aio_context(VuServer *server) +{ + if (server->sioc) { + VuFdWatch *vu_fd_watch; + + QTAILQ_FOREACH(vu_fd_watch, &server->vu_fd_watches, next) { + aio_set_fd_handler(server->ctx, vu_fd_watch->fd, true, + NULL, NULL, NULL, vu_fd_watch); + } + qio_channel_detach_aio_context(server->ioc); - /* server->ioc->ctx keeps the old AioConext */ - ctx = server->ioc->ctx; - attach = false; } - QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { - if (vu_fd_watch->cb) { - opaque = attach ? vu_fd_watch : NULL; - aio_set_fd_handler(ctx, vu_fd_watch->fd, true, - io_read, NULL, NULL, - opaque); - } - } + server->ctx = NULL; } - bool vhost_user_server_start(VuServer *server, SocketAddress *socket_addr, AioContext *ctx, @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, const VuDevIface *vu_iface, Error **errp) { + QEMUBH *bh; QIONetListener *listener = qio_net_listener_new(); if (qio_net_listener_open_sync(listener, socket_addr, 1, errp) < 0) { @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, return false; } + bh = qemu_bh_new(restart_listener_bh, server); + /* zero out unspecified fields */ *server = (VuServer) { .listener = listener, + .restart_listener_bh = bh, .vu_iface = vu_iface, .max_queues = max_queues, .ctx = ctx, -- 2.26.2 Propagate the flush return value since errors are possible. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-11-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/export/vhost-user-blk-server.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, return -EINVAL; } -static void coroutine_fn vu_block_flush(VuBlockReq *req) +static int coroutine_fn vu_block_flush(VuBlockReq *req) { VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); BlockBackend *backend = vdev_blk->backend; - blk_co_flush(backend); + return blk_co_flush(backend); } static void coroutine_fn vu_block_virtio_process_req(void *opaque) @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) break; } case VIRTIO_BLK_T_FLUSH: - vu_block_flush(req); - req->in->status = VIRTIO_BLK_S_OK; + if (vu_block_flush(req) == 0) { + req->in->status = VIRTIO_BLK_S_OK; + } else { + req->in->status = VIRTIO_BLK_S_IOERR; + } break; case VIRTIO_BLK_T_GET_ID: { size_t size = MIN(iov_size(&elem->in_sg[0], in_num), -- 2.26.2 Use the new QAPI block exports API instead of defining our own QOM objects. This is a large change because the lifecycle of VuBlockDev needs to follow BlockExportDriver. QOM properties are replaced by QAPI options objects. VuBlockDev is renamed VuBlkExport and contains a BlockExport field. Several fields can be dropped since BlockExport already has equivalents. The file names and meson build integration will be adjusted in a future patch. libvhost-user should probably be built as a static library that is linked into QEMU instead of as a .c file that results in duplicate compilation. The new command-line syntax is: $ qemu-storage-daemon \ --blockdev file,node-name=drive0,filename=test.img \ --export vhost-user-blk,node-name=drive0,id=export0,unix-socket=/tmp/vhost-user-blk.sock Note that unix-socket is optional because we may wish to accept chardevs too in the future. Markus noted that supported address families are not explicit in the QAPI schema. It is unlikely that support for more address families will be added since file descriptor passing is required and few address families support it. If a new address family needs to be added, then the QAPI 'features' syntax can be used to advertize them. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Markus Armbruster <armbru@redhat.com> Message-id: 20200924151549.913737-12-stefanha@redhat.com [Skip test on big-endian host architectures because this device doesn't support them yet (as already mentioned in a code comment). --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qapi/block-export.json | 21 +- block/export/vhost-user-blk-server.h | 23 +- block/export/export.c | 6 + block/export/vhost-user-blk-server.c | 452 +++++++-------------------- util/vhost-user-server.c | 10 +- block/export/meson.build | 1 + block/meson.build | 1 - 7 files changed, 156 insertions(+), 358 deletions(-) diff --git a/qapi/block-export.json b/qapi/block-export.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-export.json +++ b/qapi/block-export.json @@ -XXX,XX +XXX,XX @@ 'data': { '*name': 'str', '*description': 'str', '*bitmap': 'str' } } +## +# @BlockExportOptionsVhostUserBlk: +# +# A vhost-user-blk block export. +# +# @addr: The vhost-user socket on which to listen. Both 'unix' and 'fd' +# SocketAddress types are supported. Passed fds must be UNIX domain +# sockets. +# @logical-block-size: Logical block size in bytes. Defaults to 512 bytes. +# +# Since: 5.2 +## +{ 'struct': 'BlockExportOptionsVhostUserBlk', + 'data': { 'addr': 'SocketAddress', '*logical-block-size': 'size' } } + ## # @NbdServerAddOptions: # @@ -XXX,XX +XXX,XX @@ # An enumeration of block export types # # @nbd: NBD export +# @vhost-user-blk: vhost-user-blk export (since 5.2) # # Since: 4.2 ## { 'enum': 'BlockExportType', - 'data': [ 'nbd' ] } + 'data': [ 'nbd', 'vhost-user-blk' ] } ## # @BlockExportOptions: @@ -XXX,XX +XXX,XX @@ '*writethrough': 'bool' }, 'discriminator': 'type', 'data': { - 'nbd': 'BlockExportOptionsNbd' + 'nbd': 'BlockExportOptionsNbd', + 'vhost-user-blk': 'BlockExportOptionsVhostUserBlk' } } ## diff --git a/block/export/vhost-user-blk-server.h b/block/export/vhost-user-blk-server.h index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.h +++ b/block/export/vhost-user-blk-server.h @@ -XXX,XX +XXX,XX @@ #ifndef VHOST_USER_BLK_SERVER_H #define VHOST_USER_BLK_SERVER_H -#include "util/vhost-user-server.h" -typedef struct VuBlockDev VuBlockDev; -#define TYPE_VHOST_USER_BLK_SERVER "vhost-user-blk-server" -#define VHOST_USER_BLK_SERVER(obj) \ - OBJECT_CHECK(VuBlockDev, obj, TYPE_VHOST_USER_BLK_SERVER) +#include "block/export.h" -/* vhost user block device */ -struct VuBlockDev { - Object parent_obj; - char *node_name; - SocketAddress *addr; - AioContext *ctx; - VuServer vu_server; - bool running; - uint32_t blk_size; - BlockBackend *backend; - QIOChannelSocket *sioc; - QTAILQ_ENTRY(VuBlockDev) next; - struct virtio_blk_config blkcfg; - bool writable; -}; +/* For block/export/export.c */ +extern const BlockExportDriver blk_exp_vhost_user_blk; #endif /* VHOST_USER_BLK_SERVER_H */ diff --git a/block/export/export.c b/block/export/export.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/export.c +++ b/block/export/export.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/block-backend.h" #include "block/export.h" #include "block/nbd.h" +#if CONFIG_LINUX +#include "block/export/vhost-user-blk-server.h" +#endif #include "qapi/error.h" #include "qapi/qapi-commands-block-export.h" #include "qapi/qapi-events-block-export.h" @@ -XXX,XX +XXX,XX @@ static const BlockExportDriver *blk_exp_drivers[] = { &blk_exp_nbd, +#if CONFIG_LINUX + &blk_exp_vhost_user_blk, +#endif }; /* Only accessed from the main thread */ diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" #include "block/block.h" +#include "contrib/libvhost-user/libvhost-user.h" +#include "standard-headers/linux/virtio_blk.h" +#include "util/vhost-user-server.h" #include "vhost-user-blk-server.h" #include "qapi/error.h" #include "qom/object_interfaces.h" @@ -XXX,XX +XXX,XX @@ struct virtio_blk_inhdr { unsigned char status; }; -typedef struct VuBlockReq { +typedef struct VuBlkReq { VuVirtqElement elem; int64_t sector_num; size_t size; @@ -XXX,XX +XXX,XX @@ typedef struct VuBlockReq { struct virtio_blk_outhdr out; VuServer *server; struct VuVirtq *vq; -} VuBlockReq; +} VuBlkReq; -static void vu_block_req_complete(VuBlockReq *req) +/* vhost user block device */ +typedef struct { + BlockExport export; + VuServer vu_server; + uint32_t blk_size; + QIOChannelSocket *sioc; + struct virtio_blk_config blkcfg; + bool writable; +} VuBlkExport; + +static void vu_blk_req_complete(VuBlkReq *req) { VuDev *vu_dev = &req->server->vu_dev; @@ -XXX,XX +XXX,XX @@ static void vu_block_req_complete(VuBlockReq *req) free(req); } -static VuBlockDev *get_vu_block_device_by_server(VuServer *server) -{ - return container_of(server, VuBlockDev, vu_server); -} - static int coroutine_fn -vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, - uint32_t iovcnt, uint32_t type) +vu_blk_discard_write_zeroes(BlockBackend *blk, struct iovec *iov, + uint32_t iovcnt, uint32_t type) { struct virtio_blk_discard_write_zeroes desc; ssize_t size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc)); @@ -XXX,XX +XXX,XX @@ vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, return -EINVAL; } - VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); uint64_t range[2] = { le64_to_cpu(desc.sector) << 9, le32_to_cpu(desc.num_sectors) << 9 }; if (type == VIRTIO_BLK_T_DISCARD) { - if (blk_co_pdiscard(vdev_blk->backend, range[0], range[1]) == 0) { + if (blk_co_pdiscard(blk, range[0], range[1]) == 0) { return 0; } } else if (type == VIRTIO_BLK_T_WRITE_ZEROES) { - if (blk_co_pwrite_zeroes(vdev_blk->backend, - range[0], range[1], 0) == 0) { + if (blk_co_pwrite_zeroes(blk, range[0], range[1], 0) == 0) { return 0; } } @@ -XXX,XX +XXX,XX @@ vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, return -EINVAL; } -static int coroutine_fn vu_block_flush(VuBlockReq *req) +static void coroutine_fn vu_blk_virtio_process_req(void *opaque) { - VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); - BlockBackend *backend = vdev_blk->backend; - return blk_co_flush(backend); -} - -static void coroutine_fn vu_block_virtio_process_req(void *opaque) -{ - VuBlockReq *req = opaque; + VuBlkReq *req = opaque; VuServer *server = req->server; VuVirtqElement *elem = &req->elem; uint32_t type; - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); - BlockBackend *backend = vdev_blk->backend; + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); + BlockBackend *blk = vexp->export.blk; struct iovec *in_iov = elem->in_sg; struct iovec *out_iov = elem->out_sg; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) bool is_write = type & VIRTIO_BLK_T_OUT; req->sector_num = le64_to_cpu(req->out.sector); - int64_t offset = req->sector_num * vdev_blk->blk_size; + if (is_write && !vexp->writable) { + req->in->status = VIRTIO_BLK_S_IOERR; + break; + } + + int64_t offset = req->sector_num * vexp->blk_size; QEMUIOVector qiov; if (is_write) { qemu_iovec_init_external(&qiov, out_iov, out_num); - ret = blk_co_pwritev(backend, offset, qiov.size, - &qiov, 0); + ret = blk_co_pwritev(blk, offset, qiov.size, &qiov, 0); } else { qemu_iovec_init_external(&qiov, in_iov, in_num); - ret = blk_co_preadv(backend, offset, qiov.size, - &qiov, 0); + ret = blk_co_preadv(blk, offset, qiov.size, &qiov, 0); } if (ret >= 0) { req->in->status = VIRTIO_BLK_S_OK; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) break; } case VIRTIO_BLK_T_FLUSH: - if (vu_block_flush(req) == 0) { + if (blk_co_flush(blk) == 0) { req->in->status = VIRTIO_BLK_S_OK; } else { req->in->status = VIRTIO_BLK_S_IOERR; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) case VIRTIO_BLK_T_DISCARD: case VIRTIO_BLK_T_WRITE_ZEROES: { int rc; - rc = vu_block_discard_write_zeroes(req, &elem->out_sg[1], - out_num, type); + + if (!vexp->writable) { + req->in->status = VIRTIO_BLK_S_IOERR; + break; + } + + rc = vu_blk_discard_write_zeroes(blk, &elem->out_sg[1], out_num, type); if (rc == 0) { req->in->status = VIRTIO_BLK_S_OK; } else { @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) break; } - vu_block_req_complete(req); + vu_blk_req_complete(req); return; err: - free(elem); + free(req); } -static void vu_block_process_vq(VuDev *vu_dev, int idx) +static void vu_blk_process_vq(VuDev *vu_dev, int idx) { VuServer *server = container_of(vu_dev, VuServer, vu_dev); VuVirtq *vq = vu_get_queue(vu_dev, idx); while (1) { - VuBlockReq *req; + VuBlkReq *req; - req = vu_queue_pop(vu_dev, vq, sizeof(VuBlockReq)); + req = vu_queue_pop(vu_dev, vq, sizeof(VuBlkReq)); if (!req) { break; } @@ -XXX,XX +XXX,XX @@ static void vu_block_process_vq(VuDev *vu_dev, int idx) req->vq = vq; Coroutine *co = - qemu_coroutine_create(vu_block_virtio_process_req, req); + qemu_coroutine_create(vu_blk_virtio_process_req, req); qemu_coroutine_enter(co); } } -static void vu_block_queue_set_started(VuDev *vu_dev, int idx, bool started) +static void vu_blk_queue_set_started(VuDev *vu_dev, int idx, bool started) { VuVirtq *vq; assert(vu_dev); vq = vu_get_queue(vu_dev, idx); - vu_set_queue_handler(vu_dev, vq, started ? vu_block_process_vq : NULL); + vu_set_queue_handler(vu_dev, vq, started ? vu_blk_process_vq : NULL); } -static uint64_t vu_block_get_features(VuDev *dev) +static uint64_t vu_blk_get_features(VuDev *dev) { uint64_t features; VuServer *server = container_of(dev, VuServer, vu_dev); - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); features = 1ull << VIRTIO_BLK_F_SIZE_MAX | 1ull << VIRTIO_BLK_F_SEG_MAX | 1ull << VIRTIO_BLK_F_TOPOLOGY | @@ -XXX,XX +XXX,XX @@ static uint64_t vu_block_get_features(VuDev *dev) 1ull << VIRTIO_RING_F_EVENT_IDX | 1ull << VHOST_USER_F_PROTOCOL_FEATURES; - if (!vdev_blk->writable) { + if (!vexp->writable) { features |= 1ull << VIRTIO_BLK_F_RO; } return features; } -static uint64_t vu_block_get_protocol_features(VuDev *dev) +static uint64_t vu_blk_get_protocol_features(VuDev *dev) { return 1ull << VHOST_USER_PROTOCOL_F_CONFIG | 1ull << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD; } static int -vu_block_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len) +vu_blk_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len) { + /* TODO blkcfg must be little-endian for VIRTIO 1.0 */ VuServer *server = container_of(vu_dev, VuServer, vu_dev); - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); - memcpy(config, &vdev_blk->blkcfg, len); - + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); + memcpy(config, &vexp->blkcfg, len); return 0; } static int -vu_block_set_config(VuDev *vu_dev, const uint8_t *data, +vu_blk_set_config(VuDev *vu_dev, const uint8_t *data, uint32_t offset, uint32_t size, uint32_t flags) { VuServer *server = container_of(vu_dev, VuServer, vu_dev); - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); uint8_t wce; /* don't support live migration */ @@ -XXX,XX +XXX,XX @@ vu_block_set_config(VuDev *vu_dev, const uint8_t *data, } wce = *data; - vdev_blk->blkcfg.wce = wce; - blk_set_enable_write_cache(vdev_blk->backend, wce); + vexp->blkcfg.wce = wce; + blk_set_enable_write_cache(vexp->export.blk, wce); return 0; } @@ -XXX,XX +XXX,XX @@ vu_block_set_config(VuDev *vu_dev, const uint8_t *data, * of vu_process_message. * */ -static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) +static int vu_blk_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) { if (vmsg->request == VHOST_USER_NONE) { dev->panic(dev, "disconnect"); @@ -XXX,XX +XXX,XX @@ static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) return false; } -static const VuDevIface vu_block_iface = { - .get_features = vu_block_get_features, - .queue_set_started = vu_block_queue_set_started, - .get_protocol_features = vu_block_get_protocol_features, - .get_config = vu_block_get_config, - .set_config = vu_block_set_config, - .process_msg = vu_block_process_msg, +static const VuDevIface vu_blk_iface = { + .get_features = vu_blk_get_features, + .queue_set_started = vu_blk_queue_set_started, + .get_protocol_features = vu_blk_get_protocol_features, + .get_config = vu_blk_get_config, + .set_config = vu_blk_set_config, + .process_msg = vu_blk_process_msg, }; static void blk_aio_attached(AioContext *ctx, void *opaque) { - VuBlockDev *vub_dev = opaque; - vhost_user_server_attach_aio_context(&vub_dev->vu_server, ctx); + VuBlkExport *vexp = opaque; + vhost_user_server_attach_aio_context(&vexp->vu_server, ctx); } static void blk_aio_detach(void *opaque) { - VuBlockDev *vub_dev = opaque; - vhost_user_server_detach_aio_context(&vub_dev->vu_server); + VuBlkExport *vexp = opaque; + vhost_user_server_detach_aio_context(&vexp->vu_server); } static void -vu_block_initialize_config(BlockDriverState *bs, +vu_blk_initialize_config(BlockDriverState *bs, struct virtio_blk_config *config, uint32_t blk_size) { config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS; @@ -XXX,XX +XXX,XX @@ vu_block_initialize_config(BlockDriverState *bs, config->max_write_zeroes_seg = 1; } -static VuBlockDev *vu_block_init(VuBlockDev *vu_block_device, Error **errp) +static void vu_blk_exp_request_shutdown(BlockExport *exp) { + VuBlkExport *vexp = container_of(exp, VuBlkExport, export); - BlockBackend *blk; - Error *local_error = NULL; - const char *node_name = vu_block_device->node_name; - bool writable = vu_block_device->writable; - uint64_t perm = BLK_PERM_CONSISTENT_READ; - int ret; - - AioContext *ctx; - - BlockDriverState *bs = bdrv_lookup_bs(node_name, node_name, &local_error); - - if (!bs) { - error_propagate(errp, local_error); - return NULL; - } - - if (bdrv_is_read_only(bs)) { - writable = false; - } - - if (writable) { - perm |= BLK_PERM_WRITE; - } - - ctx = bdrv_get_aio_context(bs); - aio_context_acquire(ctx); - bdrv_invalidate_cache(bs, NULL); - aio_context_release(ctx); - - /* - * Don't allow resize while the vhost user server is running, - * otherwise we don't care what happens with the node. - */ - blk = blk_new(bdrv_get_aio_context(bs), perm, - BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED | - BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD); - ret = blk_insert_bs(blk, bs, errp); - - if (ret < 0) { - goto fail; - } - - blk_set_enable_write_cache(blk, false); - - blk_set_allow_aio_context_change(blk, true); - - vu_block_device->blkcfg.wce = 0; - vu_block_device->backend = blk; - if (!vu_block_device->blk_size) { - vu_block_device->blk_size = BDRV_SECTOR_SIZE; - } - vu_block_device->blkcfg.blk_size = vu_block_device->blk_size; - blk_set_guest_block_size(blk, vu_block_device->blk_size); - vu_block_initialize_config(bs, &vu_block_device->blkcfg, - vu_block_device->blk_size); - return vu_block_device; - -fail: - blk_unref(blk); - return NULL; -} - -static void vu_block_deinit(VuBlockDev *vu_block_device) -{ - if (vu_block_device->backend) { - blk_remove_aio_context_notifier(vu_block_device->backend, blk_aio_attached, - blk_aio_detach, vu_block_device); - } - - blk_unref(vu_block_device->backend); -} - -static void vhost_user_blk_server_stop(VuBlockDev *vu_block_device) -{ - vhost_user_server_stop(&vu_block_device->vu_server); - vu_block_deinit(vu_block_device); -} - -static void vhost_user_blk_server_start(VuBlockDev *vu_block_device, - Error **errp) -{ - AioContext *ctx; - SocketAddress *addr = vu_block_device->addr; - - if (!vu_block_init(vu_block_device, errp)) { - return; - } - - ctx = bdrv_get_aio_context(blk_bs(vu_block_device->backend)); - - if (!vhost_user_server_start(&vu_block_device->vu_server, addr, ctx, - VHOST_USER_BLK_MAX_QUEUES, &vu_block_iface, - errp)) { - goto error; - } - - blk_add_aio_context_notifier(vu_block_device->backend, blk_aio_attached, - blk_aio_detach, vu_block_device); - vu_block_device->running = true; - return; - - error: - vu_block_deinit(vu_block_device); -} - -static bool vu_prop_modifiable(VuBlockDev *vus, Error **errp) -{ - if (vus->running) { - error_setg(errp, "The property can't be modified " - "while the server is running"); - return false; - } - return true; -} - -static void vu_set_node_name(Object *obj, const char *value, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - - if (!vu_prop_modifiable(vus, errp)) { - return; - } - - if (vus->node_name) { - g_free(vus->node_name); - } - - vus->node_name = g_strdup(value); -} - -static char *vu_get_node_name(Object *obj, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - return g_strdup(vus->node_name); -} - -static void free_socket_addr(SocketAddress *addr) -{ - g_free(addr->u.q_unix.path); - g_free(addr); -} - -static void vu_set_unix_socket(Object *obj, const char *value, - Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - - if (!vu_prop_modifiable(vus, errp)) { - return; - } - - if (vus->addr) { - free_socket_addr(vus->addr); - } - - SocketAddress *addr = g_new0(SocketAddress, 1); - addr->type = SOCKET_ADDRESS_TYPE_UNIX; - addr->u.q_unix.path = g_strdup(value); - vus->addr = addr; + vhost_user_server_stop(&vexp->vu_server); } -static char *vu_get_unix_socket(Object *obj, Error **errp) +static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, + Error **errp) { - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - return g_strdup(vus->addr->u.q_unix.path); -} - -static bool vu_get_block_writable(Object *obj, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - return vus->writable; -} - -static void vu_set_block_writable(Object *obj, bool value, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - - if (!vu_prop_modifiable(vus, errp)) { - return; - } - - vus->writable = value; -} - -static void vu_get_blk_size(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - uint32_t value = vus->blk_size; - - visit_type_uint32(v, name, &value, errp); -} - -static void vu_set_blk_size(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - + VuBlkExport *vexp = container_of(exp, VuBlkExport, export); + BlockExportOptionsVhostUserBlk *vu_opts = &opts->u.vhost_user_blk; Error *local_err = NULL; - uint32_t value; + uint64_t logical_block_size; - if (!vu_prop_modifiable(vus, errp)) { - return; - } + vexp->writable = opts->writable; + vexp->blkcfg.wce = 0; - visit_type_uint32(v, name, &value, &local_err); - if (local_err) { - goto out; + if (vu_opts->has_logical_block_size) { + logical_block_size = vu_opts->logical_block_size; + } else { + logical_block_size = BDRV_SECTOR_SIZE; } - - check_block_size(object_get_typename(obj), name, value, &local_err); + check_block_size(exp->id, "logical-block-size", logical_block_size, + &local_err); if (local_err) { - goto out; + error_propagate(errp, local_err); + return -EINVAL; + } + vexp->blk_size = logical_block_size; + blk_set_guest_block_size(exp->blk, logical_block_size); + vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg, + logical_block_size); + + blk_set_allow_aio_context_change(exp->blk, true); + blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, + vexp); + + if (!vhost_user_server_start(&vexp->vu_server, vu_opts->addr, exp->ctx, + VHOST_USER_BLK_MAX_QUEUES, &vu_blk_iface, + errp)) { + blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, + blk_aio_detach, vexp); + return -EADDRNOTAVAIL; } - vus->blk_size = value; - -out: - error_propagate(errp, local_err); -} - -static void vhost_user_blk_server_instance_finalize(Object *obj) -{ - VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); - - vhost_user_blk_server_stop(vub); - - /* - * Unlike object_property_add_str, object_class_property_add_str - * doesn't have a release method. Thus manual memory freeing is - * needed. - */ - free_socket_addr(vub->addr); - g_free(vub->node_name); -} - -static void vhost_user_blk_server_complete(UserCreatable *obj, Error **errp) -{ - VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); - - vhost_user_blk_server_start(vub, errp); + return 0; } -static void vhost_user_blk_server_class_init(ObjectClass *klass, - void *class_data) +static void vu_blk_exp_delete(BlockExport *exp) { - UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass); - ucc->complete = vhost_user_blk_server_complete; - - object_class_property_add_bool(klass, "writable", - vu_get_block_writable, - vu_set_block_writable); - - object_class_property_add_str(klass, "node-name", - vu_get_node_name, - vu_set_node_name); - - object_class_property_add_str(klass, "unix-socket", - vu_get_unix_socket, - vu_set_unix_socket); + VuBlkExport *vexp = container_of(exp, VuBlkExport, export); - object_class_property_add(klass, "logical-block-size", "uint32", - vu_get_blk_size, vu_set_blk_size, - NULL, NULL); + blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, + vexp); } -static const TypeInfo vhost_user_blk_server_info = { - .name = TYPE_VHOST_USER_BLK_SERVER, - .parent = TYPE_OBJECT, - .instance_size = sizeof(VuBlockDev), - .instance_finalize = vhost_user_blk_server_instance_finalize, - .class_init = vhost_user_blk_server_class_init, - .interfaces = (InterfaceInfo[]) { - {TYPE_USER_CREATABLE}, - {} - }, +const BlockExportDriver blk_exp_vhost_user_blk = { + .type = BLOCK_EXPORT_TYPE_VHOST_USER_BLK, + .instance_size = sizeof(VuBlkExport), + .create = vu_blk_exp_create, + .delete = vu_blk_exp_delete, + .request_shutdown = vu_blk_exp_request_shutdown, }; - -static void vhost_user_blk_server_register_types(void) -{ - type_register_static(&vhost_user_blk_server_info); -} - -type_init(vhost_user_blk_server_register_types) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, Error **errp) { QEMUBH *bh; - QIONetListener *listener = qio_net_listener_new(); + QIONetListener *listener; + + if (socket_addr->type != SOCKET_ADDRESS_TYPE_UNIX && + socket_addr->type != SOCKET_ADDRESS_TYPE_FD) { + error_setg(errp, "Only socket address types 'unix' and 'fd' are supported"); + return false; + } + + listener = qio_net_listener_new(); if (qio_net_listener_open_sync(listener, socket_addr, 1, errp) < 0) { object_unref(OBJECT(listener)); diff --git a/block/export/meson.build b/block/export/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/export/meson.build +++ b/block/export/meson.build @@ -1 +1,2 @@ block_ss.add(files('export.c')) +block_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-blk-server.c', '../../contrib/libvhost-user/libvhost-user.c')) 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_ss.add(when: 'CONFIG_WIN32', if_true: files('file-win32.c', 'win32-aio.c') block_ss.add(when: 'CONFIG_POSIX', if_true: [files('file-posix.c'), coref, iokit]) block_ss.add(when: 'CONFIG_LIBISCSI', if_true: files('iscsi-opts.c')) block_ss.add(when: 'CONFIG_LINUX', if_true: files('nvme.c')) -block_ss.add(when: 'CONFIG_LINUX', if_true: files('export/vhost-user-blk-server.c', '../contrib/libvhost-user/libvhost-user.c')) block_ss.add(when: 'CONFIG_REPLICATION', if_true: files('replication.c')) block_ss.add(when: 'CONFIG_SHEEPDOG', if_true: files('sheepdog.c')) block_ss.add(when: ['CONFIG_LINUX_AIO', libaio], if_true: files('linux-aio.c')) -- 2.26.2 Headers used by other subsystems are located in include/. Also add the vhost-user-server and vhost-user-blk-server headers to MAINTAINERS. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-13-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 4 +++- {util => include/qemu}/vhost-user-server.h | 0 block/export/vhost-user-blk-server.c | 2 +- util/vhost-user-server.c | 2 +- 4 files changed, 5 insertions(+), 3 deletions(-) rename {util => include/qemu}/vhost-user-server.h (100%) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ Vhost-user block device backend server M: Coiby Xu <Coiby.Xu@gmail.com> S: Maintained F: block/export/vhost-user-blk-server.c -F: util/vhost-user-server.c +F: block/export/vhost-user-blk-server.h +F: include/qemu/vhost-user-server.h F: tests/qtest/libqos/vhost-user-blk.c +F: util/vhost-user-server.c Replication M: Wen Congyang <wencongyang2@huawei.com> diff --git a/util/vhost-user-server.h b/include/qemu/vhost-user-server.h similarity index 100% rename from util/vhost-user-server.h rename to include/qemu/vhost-user-server.h diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ #include "block/block.h" #include "contrib/libvhost-user/libvhost-user.h" #include "standard-headers/linux/virtio_blk.h" -#include "util/vhost-user-server.h" +#include "qemu/vhost-user-server.h" #include "vhost-user-blk-server.h" #include "qapi/error.h" #include "qom/object_interfaces.h" diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" #include "qemu/main-loop.h" +#include "qemu/vhost-user-server.h" #include "block/aio-wait.h" -#include "vhost-user-server.h" /* * Theory of operation: -- 2.26.2 Don't compile contrib/libvhost-user/libvhost-user.c again. Instead build the static library once and then reuse it throughout QEMU. Also switch from CONFIG_LINUX to CONFIG_VHOST_USER, which is what the vhost-user tools (vhost-user-gpu, etc) do. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-14-stefanha@redhat.com [Added CONFIG_LINUX again because libvhost-user doesn't build on macOS. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/export/export.c | 8 ++++---- block/export/meson.build | 2 +- contrib/libvhost-user/meson.build | 1 + meson.build | 6 +++++- util/meson.build | 4 +++- 5 files changed, 14 insertions(+), 7 deletions(-) diff --git a/block/export/export.c b/block/export/export.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/export.c +++ b/block/export/export.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/block-backend.h" #include "block/export.h" #include "block/nbd.h" -#if CONFIG_LINUX -#include "block/export/vhost-user-blk-server.h" -#endif #include "qapi/error.h" #include "qapi/qapi-commands-block-export.h" #include "qapi/qapi-events-block-export.h" #include "qemu/id.h" +#ifdef CONFIG_VHOST_USER +#include "vhost-user-blk-server.h" +#endif static const BlockExportDriver *blk_exp_drivers[] = { &blk_exp_nbd, -#if CONFIG_LINUX +#ifdef CONFIG_VHOST_USER &blk_exp_vhost_user_blk, #endif }; diff --git a/block/export/meson.build b/block/export/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/export/meson.build +++ b/block/export/meson.build @@ -XXX,XX +XXX,XX @@ block_ss.add(files('export.c')) -block_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-blk-server.c', '../../contrib/libvhost-user/libvhost-user.c')) +block_ss.add(when: ['CONFIG_LINUX', 'CONFIG_VHOST_USER'], if_true: files('vhost-user-blk-server.c')) diff --git a/contrib/libvhost-user/meson.build b/contrib/libvhost-user/meson.build index XXXXXXX..XXXXXXX 100644 --- a/contrib/libvhost-user/meson.build +++ b/contrib/libvhost-user/meson.build @@ -XXX,XX +XXX,XX @@ libvhost_user = static_library('vhost-user', files('libvhost-user.c', 'libvhost-user-glib.c'), build_by_default: false) +vhost_user = declare_dependency(link_with: libvhost_user) diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ trace_events_subdirs += [ 'util', ] +vhost_user = not_found +if 'CONFIG_VHOST_USER' in config_host + subdir('contrib/libvhost-user') +endif + subdir('qapi') subdir('qobject') subdir('stubs') @@ -XXX,XX +XXX,XX @@ if have_tools install: true) if 'CONFIG_VHOST_USER' in config_host - subdir('contrib/libvhost-user') subdir('contrib/vhost-user-blk') subdir('contrib/vhost-user-gpu') subdir('contrib/vhost-user-input') diff --git a/util/meson.build b/util/meson.build index XXXXXXX..XXXXXXX 100644 --- a/util/meson.build +++ b/util/meson.build @@ -XXX,XX +XXX,XX @@ if have_block util_ss.add(files('main-loop.c')) util_ss.add(files('nvdimm-utils.c')) util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c')) - util_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-server.c')) + util_ss.add(when: ['CONFIG_LINUX', 'CONFIG_VHOST_USER'], if_true: [ + files('vhost-user-server.c'), vhost_user + ]) util_ss.add(files('block-helpers.c')) util_ss.add(files('qemu-coroutine-sleep.c')) util_ss.add(files('qemu-co-shared-resource.c')) -- 2.26.2 Introduce libblkdev.fa to avoid recompiling blockdev_ss twice. Suggested-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200929125516.186715-3-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- meson.build | 12 ++++++++++-- storage-daemon/meson.build | 3 +-- 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ blockdev_ss.add(files( # os-win32.c does not blockdev_ss.add(when: 'CONFIG_POSIX', if_true: files('os-posix.c')) softmmu_ss.add(when: 'CONFIG_WIN32', if_true: [files('os-win32.c')]) -softmmu_ss.add_all(blockdev_ss) common_ss.add(files('cpus-common.c')) @@ -XXX,XX +XXX,XX @@ block = declare_dependency(link_whole: [libblock], link_args: '@block.syms', dependencies: [crypto, io]) +blockdev_ss = blockdev_ss.apply(config_host, strict: false) +libblockdev = static_library('blockdev', blockdev_ss.sources() + genh, + dependencies: blockdev_ss.dependencies(), + name_suffix: 'fa', + build_by_default: false) + +blockdev = declare_dependency(link_whole: [libblockdev], + dependencies: [block]) + qmp_ss = qmp_ss.apply(config_host, strict: false) libqmp = static_library('qmp', qmp_ss.sources() + genh, dependencies: qmp_ss.dependencies(), @@ -XXX,XX +XXX,XX @@ foreach m : block_mods + softmmu_mods install_dir: config_host['qemu_moddir']) endforeach -softmmu_ss.add(authz, block, chardev, crypto, io, qmp) +softmmu_ss.add(authz, blockdev, chardev, crypto, io, qmp) common_ss.add(qom, qemuutil) common_ss.add_all(when: 'CONFIG_SOFTMMU', if_true: [softmmu_ss]) diff --git a/storage-daemon/meson.build b/storage-daemon/meson.build index XXXXXXX..XXXXXXX 100644 --- a/storage-daemon/meson.build +++ b/storage-daemon/meson.build @@ -XXX,XX +XXX,XX @@ qsd_ss = ss.source_set() qsd_ss.add(files('qemu-storage-daemon.c')) -qsd_ss.add(block, chardev, qmp, qom, qemuutil) -qsd_ss.add_all(blockdev_ss) +qsd_ss.add(blockdev, chardev, qmp, qom, qemuutil) subdir('qapi') -- 2.26.2 Block exports are used by softmmu, qemu-storage-daemon, and qemu-nbd. They are not used by other programs and are not otherwise needed in libblock. Undo the recent move of blockdev-nbd.c from blockdev_ss into block_ss. Since bdrv_close_all() (libblock) calls blk_exp_close_all() (libblockdev) a stub function is required.. Make qemu-nbd.c use signal handling utility functions instead of duplicating the code. This helps because os-posix.c is in libblockdev and it depends on a qemu_system_killed() symbol that qemu-nbd.c lacks. Once we use the signal handling utility functions we also end up providing the necessary symbol. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20200929125516.186715-4-stefanha@redhat.com [Fixed s/ndb/nbd/ typo in commit description as suggested by Eric Blake --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qemu-nbd.c | 21 ++++++++------------- stubs/blk-exp-close-all.c | 7 +++++++ block/export/meson.build | 4 ++-- meson.build | 4 ++-- nbd/meson.build | 2 ++ stubs/meson.build | 1 + 6 files changed, 22 insertions(+), 17 deletions(-) create mode 100644 stubs/blk-exp-close-all.c diff --git a/qemu-nbd.c b/qemu-nbd.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-nbd.c +++ b/qemu-nbd.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "qemu/cutils.h" #include "sysemu/block-backend.h" +#include "sysemu/runstate.h" /* for qemu_system_killed() prototype */ #include "block/block_int.h" #include "block/nbd.h" #include "qemu/main-loop.h" @@ -XXX,XX +XXX,XX @@ QEMU_COPYRIGHT "\n" } #ifdef CONFIG_POSIX -static void termsig_handler(int signum) +/* + * The client thread uses SIGTERM to interrupt the server. A signal + * handler ensures that "qemu-nbd -v -c" exits with a nice status code. + */ +void qemu_system_killed(int signum, pid_t pid) { qatomic_cmpxchg(&state, RUNNING, TERMINATE); qemu_notify_event(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) BlockExportOptions *export_opts; #ifdef CONFIG_POSIX - /* - * Exit gracefully on various signals, which includes SIGTERM used - * by 'qemu-nbd -v -c'. - */ - struct sigaction sa_sigterm; - memset(&sa_sigterm, 0, sizeof(sa_sigterm)); - sa_sigterm.sa_handler = termsig_handler; - sigaction(SIGTERM, &sa_sigterm, NULL); - sigaction(SIGINT, &sa_sigterm, NULL); - sigaction(SIGHUP, &sa_sigterm, NULL); - - signal(SIGPIPE, SIG_IGN); + os_setup_early_signal_handling(); + os_setup_signal_handling(); #endif socket_init(); diff --git a/stubs/blk-exp-close-all.c b/stubs/blk-exp-close-all.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/stubs/blk-exp-close-all.c @@ -XXX,XX +XXX,XX @@ +#include "qemu/osdep.h" +#include "block/export.h" + +/* Only used in programs that support block exports (libblockdev.fa) */ +void blk_exp_close_all(void) +{ +} diff --git a/block/export/meson.build b/block/export/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/export/meson.build +++ b/block/export/meson.build @@ -XXX,XX +XXX,XX @@ -block_ss.add(files('export.c')) -block_ss.add(when: ['CONFIG_LINUX', 'CONFIG_VHOST_USER'], if_true: files('vhost-user-blk-server.c')) +blockdev_ss.add(files('export.c')) +blockdev_ss.add(when: ['CONFIG_LINUX', 'CONFIG_VHOST_USER'], if_true: files('vhost-user-blk-server.c')) diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ subdir('dump') block_ss.add(files( 'block.c', - 'blockdev-nbd.c', 'blockjob.c', 'job.c', 'qemu-io-cmds.c', @@ -XXX,XX +XXX,XX @@ subdir('block') blockdev_ss.add(files( 'blockdev.c', + 'blockdev-nbd.c', 'iothread.c', 'job-qmp.c', )) @@ -XXX,XX +XXX,XX @@ if have_tools qemu_io = executable('qemu-io', files('qemu-io.c'), dependencies: [block, qemuutil], install: true) qemu_nbd = executable('qemu-nbd', files('qemu-nbd.c'), - dependencies: [block, qemuutil], install: true) + dependencies: [blockdev, qemuutil], install: true) subdir('storage-daemon') subdir('contrib/rdmacm-mux') diff --git a/nbd/meson.build b/nbd/meson.build index XXXXXXX..XXXXXXX 100644 --- a/nbd/meson.build +++ b/nbd/meson.build @@ -XXX,XX +XXX,XX @@ block_ss.add(files( 'client.c', 'common.c', +)) +blockdev_ss.add(files( 'server.c', )) diff --git a/stubs/meson.build b/stubs/meson.build index XXXXXXX..XXXXXXX 100644 --- a/stubs/meson.build +++ b/stubs/meson.build @@ -XXX,XX +XXX,XX @@ stub_ss.add(files('arch_type.c')) stub_ss.add(files('bdrv-next-monitor-owned.c')) stub_ss.add(files('blk-commit-all.c')) +stub_ss.add(files('blk-exp-close-all.c')) stub_ss.add(files('blockdev-close-all-bdrv-states.c')) stub_ss.add(files('change-state-handler.c')) stub_ss.add(files('cmos.c')) -- 2.26.2 Make it possible to specify the iothread where the export will run. By default the block node can be moved to other AioContexts later and the export will follow. The fixed-iothread option forces strict behavior that prevents changing AioContext while the export is active. See the QAPI docs for details. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200929125516.186715-5-stefanha@redhat.com [Fix stray '#' character in block-export.json and add missing "(since: 5.2)" as suggested by Eric Blake. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qapi/block-export.json | 11 ++++++++++ block/export/export.c | 31 +++++++++++++++++++++++++++- block/export/vhost-user-blk-server.c | 5 ++++- nbd/server.c | 2 -- 4 files changed, 45 insertions(+), 4 deletions(-) diff --git a/qapi/block-export.json b/qapi/block-export.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-export.json +++ b/qapi/block-export.json @@ -XXX,XX +XXX,XX @@ # export before completion is signalled. (since: 5.2; # default: false) # +# @iothread: The name of the iothread object where the export will run. The +# default is to use the thread currently associated with the +# block node. (since: 5.2) +# +# @fixed-iothread: True prevents the block node from being moved to another +# thread while the export is active. If true and @iothread is +# given, export creation fails if the block node cannot be +# moved to the iothread. The default is false. (since: 5.2) +# # Since: 4.2 ## { 'union': 'BlockExportOptions', 'base': { 'type': 'BlockExportType', 'id': 'str', + '*fixed-iothread': 'bool', + '*iothread': 'str', 'node-name': 'str', '*writable': 'bool', '*writethrough': 'bool' }, diff --git a/block/export/export.c b/block/export/export.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/export.c +++ b/block/export/export.c @@ -XXX,XX +XXX,XX @@ #include "block/block.h" #include "sysemu/block-backend.h" +#include "sysemu/iothread.h" #include "block/export.h" #include "block/nbd.h" #include "qapi/error.h" @@ -XXX,XX +XXX,XX @@ static const BlockExportDriver *blk_exp_find_driver(BlockExportType type) BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) { + bool fixed_iothread = export->has_fixed_iothread && export->fixed_iothread; const BlockExportDriver *drv; BlockExport *exp = NULL; BlockDriverState *bs; - BlockBackend *blk; + BlockBackend *blk = NULL; AioContext *ctx; uint64_t perm; int ret; @@ -XXX,XX +XXX,XX @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) ctx = bdrv_get_aio_context(bs); aio_context_acquire(ctx); + if (export->has_iothread) { + IOThread *iothread; + AioContext *new_ctx; + + iothread = iothread_by_id(export->iothread); + if (!iothread) { + error_setg(errp, "iothread \"%s\" not found", export->iothread); + goto fail; + } + + new_ctx = iothread_get_aio_context(iothread); + + ret = bdrv_try_set_aio_context(bs, new_ctx, errp); + if (ret == 0) { + aio_context_release(ctx); + aio_context_acquire(new_ctx); + ctx = new_ctx; + } else if (fixed_iothread) { + goto fail; + } + } + /* * Block exports are used for non-shared storage migration. Make sure * that BDRV_O_INACTIVE is cleared and the image is ready for write @@ -XXX,XX +XXX,XX @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) } blk = blk_new(ctx, perm, BLK_PERM_ALL); + + if (!fixed_iothread) { + blk_set_allow_aio_context_change(blk, true); + } + ret = blk_insert_bs(blk, bs, errp); if (ret < 0) { goto fail; diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ static const VuDevIface vu_blk_iface = { static void blk_aio_attached(AioContext *ctx, void *opaque) { VuBlkExport *vexp = opaque; + + vexp->export.ctx = ctx; vhost_user_server_attach_aio_context(&vexp->vu_server, ctx); } static void blk_aio_detach(void *opaque) { VuBlkExport *vexp = opaque; + vhost_user_server_detach_aio_context(&vexp->vu_server); + vexp->export.ctx = NULL; } static void @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg, logical_block_size); - blk_set_allow_aio_context_change(exp->blk, true); blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, vexp); 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 nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args, return ret; } - blk_set_allow_aio_context_change(blk, true); - QTAILQ_INIT(&exp->clients); exp->name = g_strdup(arg->name); exp->description = g_strdup(arg->description); -- 2.26.2 Allow the number of queues to be configured using --export vhost-user-blk,num-queues=N. This setting should match the QEMU --device vhost-user-blk-pci,num-queues=N setting but QEMU vhost-user-blk.c lowers its own value if the vhost-user-blk backend offers fewer queues than QEMU. The vhost-user-blk-server.c code is already capable of multi-queue. All virtqueue processing runs in the same AioContext. No new locking is needed. Add the num-queues=N option and set the VIRTIO_BLK_F_MQ feature bit. Note that the feature bit only announces the presence of the num_queues configuration space field. It does not promise that there is more than 1 virtqueue, so we can set it unconditionally. I tested multi-queue by running a random read fio test with numjobs=4 on an -smp 4 guest. After the benchmark finished the guest /proc/interrupts file showed activity on all 4 virtio-blk MSI-X. The /sys/block/vda/mq/ directory shows that Linux blk-mq has 4 queues configured. An automated test is included in the next commit. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Markus Armbruster <armbru@redhat.com> Message-id: 20201001144604.559733-2-stefanha@redhat.com [Fixed accidental tab characters as suggested by Markus Armbruster --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qapi/block-export.json | 10 +++++++--- block/export/vhost-user-blk-server.c | 24 ++++++++++++++++++------ 2 files changed, 25 insertions(+), 9 deletions(-) diff --git a/qapi/block-export.json b/qapi/block-export.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-export.json +++ b/qapi/block-export.json @@ -XXX,XX +XXX,XX @@ # SocketAddress types are supported. Passed fds must be UNIX domain # sockets. # @logical-block-size: Logical block size in bytes. Defaults to 512 bytes. +# @num-queues: Number of request virtqueues. Must be greater than 0. Defaults +# to 1. # # Since: 5.2 ## { 'struct': 'BlockExportOptionsVhostUserBlk', - 'data': { 'addr': 'SocketAddress', '*logical-block-size': 'size' } } + 'data': { 'addr': 'SocketAddress', + '*logical-block-size': 'size', + '*num-queues': 'uint16'} } ## # @NbdServerAddOptions: @@ -XXX,XX +XXX,XX @@ { 'union': 'BlockExportOptions', 'base': { 'type': 'BlockExportType', 'id': 'str', - '*fixed-iothread': 'bool', - '*iothread': 'str', + '*fixed-iothread': 'bool', + '*iothread': 'str', 'node-name': 'str', '*writable': 'bool', '*writethrough': 'bool' }, diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ #include "util/block-helpers.h" enum { - VHOST_USER_BLK_MAX_QUEUES = 1, + VHOST_USER_BLK_NUM_QUEUES_DEFAULT = 1, }; struct virtio_blk_inhdr { unsigned char status; @@ -XXX,XX +XXX,XX @@ static uint64_t vu_blk_get_features(VuDev *dev) 1ull << VIRTIO_BLK_F_DISCARD | 1ull << VIRTIO_BLK_F_WRITE_ZEROES | 1ull << VIRTIO_BLK_F_CONFIG_WCE | + 1ull << VIRTIO_BLK_F_MQ | 1ull << VIRTIO_F_VERSION_1 | 1ull << VIRTIO_RING_F_INDIRECT_DESC | 1ull << VIRTIO_RING_F_EVENT_IDX | @@ -XXX,XX +XXX,XX @@ static void blk_aio_detach(void *opaque) static void vu_blk_initialize_config(BlockDriverState *bs, - struct virtio_blk_config *config, uint32_t blk_size) + struct virtio_blk_config *config, + uint32_t blk_size, + uint16_t num_queues) { config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS; config->blk_size = blk_size; @@ -XXX,XX +XXX,XX @@ vu_blk_initialize_config(BlockDriverState *bs, config->seg_max = 128 - 2; config->min_io_size = 1; config->opt_io_size = 1; - config->num_queues = VHOST_USER_BLK_MAX_QUEUES; + config->num_queues = num_queues; config->max_discard_sectors = 32768; config->max_discard_seg = 1; config->discard_sector_alignment = config->blk_size >> 9; @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, BlockExportOptionsVhostUserBlk *vu_opts = &opts->u.vhost_user_blk; Error *local_err = NULL; uint64_t logical_block_size; + uint16_t num_queues = VHOST_USER_BLK_NUM_QUEUES_DEFAULT; vexp->writable = opts->writable; vexp->blkcfg.wce = 0; @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, } vexp->blk_size = logical_block_size; blk_set_guest_block_size(exp->blk, logical_block_size); + + if (vu_opts->has_num_queues) { + num_queues = vu_opts->num_queues; + } + if (num_queues == 0) { + error_setg(errp, "num-queues must be greater than 0"); + return -EINVAL; + } + vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg, - logical_block_size); + logical_block_size, num_queues); blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, vexp); if (!vhost_user_server_start(&vexp->vu_server, vu_opts->addr, exp->ctx, - VHOST_USER_BLK_MAX_QUEUES, &vu_blk_iface, - errp)) { + num_queues, &vu_blk_iface, errp)) { blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, vexp); return -EADDRNOTAVAIL; -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> bdrv_co_block_status_above has several design problems with handling short backing files: 1. With want_zeros=true, it may return ret with BDRV_BLOCK_ZERO but without BDRV_BLOCK_ALLOCATED flag, when actually short backing file which produces these after-EOF zeros is inside requested backing sequence. 2. With want_zero=false, it may return pnum=0 prior to actual EOF, because of EOF of short backing file. Fix these things, making logic about short backing files clearer. With fixed bdrv_block_status_above we also have to improve is_zero in qcow2 code, otherwise iotest 154 will fail, because with this patch we stop to merge zeros of different types (produced by fully unallocated in the whole backing chain regions vs produced by short backing files). Note also, that this patch leaves for another day the general problem around block-status: misuse of BDRV_BLOCK_ALLOCATED as is-fs-allocated vs go-to-backing. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20200924194003.22080-2-vsementsov@virtuozzo.com [Fix s/comes/come/ as suggested by Eric Blake --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 68 ++++++++++++++++++++++++++++++++++++++++----------- block/qcow2.c | 16 ++++++++++-- 2 files changed, 68 insertions(+), 16 deletions(-) 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 @@ bdrv_co_common_block_status_above(BlockDriverState *bs, int64_t *map, BlockDriverState **file) { + int ret; BlockDriverState *p; - int ret = 0; - bool first = true; + int64_t eof = 0; assert(bs != base); - for (p = bs; p != base; p = bdrv_filter_or_cow_bs(p)) { + + ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); + if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED) { + return ret; + } + + if (ret & BDRV_BLOCK_EOF) { + eof = offset + *pnum; + } + + assert(*pnum <= bytes); + bytes = *pnum; + + for (p = bdrv_filter_or_cow_bs(bs); p != base; + p = bdrv_filter_or_cow_bs(p)) + { ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map, file); if (ret < 0) { - break; + return ret; } - if (ret & BDRV_BLOCK_ZERO && ret & BDRV_BLOCK_EOF && !first) { + if (*pnum == 0) { /* - * Reading beyond the end of the file continues to read - * zeroes, but we can only widen the result to the - * unallocated length we learned from an earlier - * iteration. + * The top layer deferred to this layer, and because this layer is + * short, any zeroes that we synthesize beyond EOF behave as if they + * were allocated at this layer. + * + * We don't include BDRV_BLOCK_EOF into ret, as upper layer may be + * larger. We'll add BDRV_BLOCK_EOF if needed at function end, see + * below. */ + assert(ret & BDRV_BLOCK_EOF); *pnum = bytes; + if (file) { + *file = p; + } + ret = BDRV_BLOCK_ZERO | BDRV_BLOCK_ALLOCATED; + break; } - if (ret & (BDRV_BLOCK_ZERO | BDRV_BLOCK_DATA)) { + if (ret & BDRV_BLOCK_ALLOCATED) { + /* + * We've found the node and the status, we must break. + * + * Drop BDRV_BLOCK_EOF, as it's not for upper layer, which may be + * larger. We'll add BDRV_BLOCK_EOF if needed at function end, see + * below. + */ + ret &= ~BDRV_BLOCK_EOF; break; } - /* [offset, pnum] unallocated on this layer, which could be only - * the first part of [offset, bytes]. */ - bytes = MIN(bytes, *pnum); - first = false; + + /* + * OK, [offset, offset + *pnum) region is unallocated on this layer, + * let's continue the diving. + */ + assert(*pnum <= bytes); + bytes = *pnum; + } + + if (offset + *pnum == eof) { + ret |= BDRV_BLOCK_EOF; } + return ret; } 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 bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) if (!bytes) { return true; } - res = bdrv_block_status_above(bs, NULL, offset, bytes, &nr, NULL, NULL); - return res >= 0 && (res & BDRV_BLOCK_ZERO) && nr == bytes; + + /* + * bdrv_block_status_above doesn't merge different types of zeros, for + * example, zeros which come from the region which is unallocated in + * the whole backing chain, and zeros which come because of a short + * backing file. So, we need a loop. + */ + do { + res = bdrv_block_status_above(bs, NULL, offset, bytes, &nr, NULL, NULL); + offset += nr; + bytes -= nr; + } while (res >= 0 && (res & BDRV_BLOCK_ZERO) && nr && bytes); + + return res >= 0 && (res & BDRV_BLOCK_ZERO) && bytes == 0; } static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs, -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> In order to reuse bdrv_common_block_status_above in bdrv_is_allocated_above, let's support include_base parameter. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20200924194003.22080-3-vsementsov@virtuozzo.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/coroutines.h | 2 ++ block/io.c | 21 ++++++++++++++------- 2 files changed, 16 insertions(+), 7 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_pwritev(BdrvChild *child, int64_t offset, unsigned int bytes, int coroutine_fn bdrv_co_common_block_status_above(BlockDriverState *bs, BlockDriverState *base, + bool include_base, bool want_zero, int64_t offset, int64_t bytes, @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, int generated_co_wrapper bdrv_common_block_status_above(BlockDriverState *bs, BlockDriverState *base, + bool include_base, bool want_zero, int64_t offset, int64_t bytes, 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 @@ early_out: int coroutine_fn bdrv_co_common_block_status_above(BlockDriverState *bs, BlockDriverState *base, + bool include_base, bool want_zero, int64_t offset, int64_t bytes, @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, BlockDriverState *p; int64_t eof = 0; - assert(bs != base); + assert(include_base || bs != base); + assert(!include_base || base); /* Can't include NULL base */ ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); - if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED) { + if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED || bs == base) { return ret; } @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, assert(*pnum <= bytes); bytes = *pnum; - for (p = bdrv_filter_or_cow_bs(bs); p != base; + for (p = bdrv_filter_or_cow_bs(bs); include_base || p != base; p = bdrv_filter_or_cow_bs(p)) { ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map, @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, break; } + if (p == base) { + assert(include_base); + break; + } + /* * OK, [offset, offset + *pnum) region is unallocated on this layer, * let's continue the diving. @@ -XXX,XX +XXX,XX @@ int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base, int64_t offset, int64_t bytes, int64_t *pnum, int64_t *map, BlockDriverState **file) { - return bdrv_common_block_status_above(bs, base, true, offset, bytes, + return bdrv_common_block_status_above(bs, base, false, true, offset, bytes, pnum, map, file); } @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int ret; int64_t dummy; - ret = bdrv_common_block_status_above(bs, bdrv_filter_or_cow_bs(bs), false, - offset, bytes, pnum ? pnum : &dummy, - NULL, NULL); + ret = bdrv_common_block_status_above(bs, bs, true, false, offset, + bytes, pnum ? pnum : &dummy, NULL, + NULL); if (ret < 0) { return ret; } -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We are going to reuse bdrv_common_block_status_above in bdrv_is_allocated_above. bdrv_is_allocated_above may be called with include_base == false and still bs == base (for ex. from img_rebase()). So, support this corner case. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Message-id: 20200924194003.22080-4-vsementsov@virtuozzo.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) 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 @@ bdrv_co_common_block_status_above(BlockDriverState *bs, BlockDriverState *p; int64_t eof = 0; - assert(include_base || bs != base); assert(!include_base || base); /* Can't include NULL base */ + if (!include_base && bs == base) { + *pnum = bytes; + return 0; + } + ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED || bs == base) { return ret; -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> bdrv_is_allocated_above wrongly handles short backing files: it reports after-EOF space as UNALLOCATED which is wrong, as on read the data is generated on the level of short backing file (if all overlays have unallocated areas at that place). Reusing bdrv_common_block_status_above fixes the issue and unifies code path. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Message-id: 20200924194003.22080-5-vsementsov@virtuozzo.com [Fix s/has/have/ as suggested by Eric Blake. Fix s/area/areas/. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 43 +++++-------------------------------------- 1 file changed, 5 insertions(+), 38 deletions(-) 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 coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, * at 'offset + *pnum' may return the same allocation status (in other * words, the result is not necessarily the maximum possible range); * but 'pnum' will only be 0 when end of file is reached. - * */ int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base, bool include_base, int64_t offset, int64_t bytes, int64_t *pnum) { - BlockDriverState *intermediate; - int ret; - int64_t n = bytes; - - assert(base || !include_base); - - intermediate = top; - while (include_base || intermediate != base) { - int64_t pnum_inter; - int64_t size_inter; - - assert(intermediate); - ret = bdrv_is_allocated(intermediate, offset, bytes, &pnum_inter); - if (ret < 0) { - return ret; - } - if (ret) { - *pnum = pnum_inter; - return 1; - } - - size_inter = bdrv_getlength(intermediate); - if (size_inter < 0) { - return size_inter; - } - if (n > pnum_inter && - (intermediate == top || offset + pnum_inter < size_inter)) { - n = pnum_inter; - } - - if (intermediate == base) { - break; - } - - intermediate = bdrv_filter_or_cow_bs(intermediate); + int ret = bdrv_common_block_status_above(top, base, include_base, false, + offset, bytes, pnum, NULL, NULL); + if (ret < 0) { + return ret; } - *pnum = n; - return 0; + return !!(ret & BDRV_BLOCK_ALLOCATED); } int coroutine_fn -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> These cases are fixed by previous patches around block_status and is_allocated. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Message-id: 20200924194003.22080-6-vsementsov@virtuozzo.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qemu-iotests/274 | 20 +++++++++++ tests/qemu-iotests/274.out | 68 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 88 insertions(+) diff --git a/tests/qemu-iotests/274 b/tests/qemu-iotests/274 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/274 +++ b/tests/qemu-iotests/274 @@ -XXX,XX +XXX,XX @@ with iotests.FilePath('base') as base, \ iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, mid) iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), mid) + iotests.log('=== Testing qemu-img commit (top -> base) ===') + + create_chain() + iotests.qemu_img_log('commit', '-b', base, top) + iotests.img_info_log(base) + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, base) + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), base) + + iotests.log('=== Testing QMP active commit (top -> base) ===') + + create_chain() + with create_vm() as vm: + vm.launch() + vm.qmp_log('block-commit', device='top', base_node='base', + job_id='job0', auto_dismiss=False) + vm.run_job('job0', wait=5) + + iotests.img_info_log(mid) + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, base) + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), base) iotests.log('== Resize tests ==') diff --git a/tests/qemu-iotests/274.out b/tests/qemu-iotests/274.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/274.out +++ b/tests/qemu-iotests/274.out @@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 0 read 1048576/1048576 bytes at offset 1048576 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +=== Testing qemu-img commit (top -> base) === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-mid', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=1048576 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 backing_file=TEST_DIR/PID-mid backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 + +wrote 2097152/2097152 bytes at offset 0 +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image committed. + +image: TEST_IMG +file format: IMGFMT +virtual size: 2 MiB (2097152 bytes) +cluster_size: 65536 +Format specific information: + compat: 1.1 + compression type: zlib + lazy refcounts: false + refcount bits: 16 + corrupt: false + extended l2: false + +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Testing QMP active commit (top -> base) === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-mid', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=1048576 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 backing_file=TEST_DIR/PID-mid backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 + +wrote 2097152/2097152 bytes at offset 0 +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +{"execute": "block-commit", "arguments": {"auto-dismiss": false, "base-node": "base", "device": "top", "job-id": "job0"}} +{"return": {}} +{"execute": "job-complete", "arguments": {"id": "job0"}} +{"return": {}} +{"data": {"device": "job0", "len": 1048576, "offset": 1048576, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_READY", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} +{"data": {"device": "job0", "len": 1048576, "offset": 1048576, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} +{"execute": "job-dismiss", "arguments": {"id": "job0"}} +{"return": {}} +image: TEST_IMG +file format: IMGFMT +virtual size: 1 MiB (1048576 bytes) +cluster_size: 65536 +backing file: TEST_DIR/PID-base +backing file format: IMGFMT +Format specific information: + compat: 1.1 + compression type: zlib + lazy refcounts: false + refcount bits: 16 + corrupt: false + extended l2: false + +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + == Resize tests == === preallocation=off === Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=6442450944 lazy_refcounts=off refcount_bits=16 -- 2.26.2