The following changes since commit d5c75ec500d96f1d93447f990cd5a4ef5ba27fae: Merge remote-tracking branch 'remotes/stefanberger/tags/pull-tpm-2020-05-08-1' into staging (2020-05-12 17:00:10 +0100) are available in the Git repository at: https://github.com/XanClic/qemu.git tags/pull-block-2020-05-13 for you to fetch changes up to fc9aefc8c0d3c6392656ea661ce72c1583b70bbd: block/block-copy: fix use-after-free of task pointer (2020-05-13 14:20:31 +0200) ---------------------------------------------------------------- Block patches: - zstd compression for qcow2 - Fix use-after-free ---------------------------------------------------------------- Denis Plotnikov (4): qcow2: introduce compression type feature qcow2: rework the cluster compression routine qcow2: add zstd cluster compression iotests: 287: add qcow2 compression type test Vladimir Sementsov-Ogievskiy (1): block/block-copy: fix use-after-free of task pointer docs/interop/qcow2.txt | 1 + configure | 2 +- qapi/block-core.json | 23 ++- block/qcow2.h | 20 ++- include/block/block_int.h | 1 + block/block-copy.c | 2 +- block/qcow2-threads.c | 240 +++++++++++++++++++++++++++++-- block/qcow2.c | 120 ++++++++++++++++ tests/qemu-iotests/031.out | 14 +- tests/qemu-iotests/036.out | 4 +- tests/qemu-iotests/049.out | 102 ++++++------- tests/qemu-iotests/060.out | 1 + tests/qemu-iotests/061.out | 34 +++-- tests/qemu-iotests/065 | 28 ++-- tests/qemu-iotests/080 | 2 +- tests/qemu-iotests/082.out | 48 ++++++- tests/qemu-iotests/085.out | 38 ++--- tests/qemu-iotests/144.out | 4 +- tests/qemu-iotests/182.out | 2 +- tests/qemu-iotests/185.out | 8 +- tests/qemu-iotests/198.out | 2 + tests/qemu-iotests/206.out | 5 + tests/qemu-iotests/242.out | 5 + tests/qemu-iotests/255.out | 8 +- tests/qemu-iotests/274.out | 49 ++++--- tests/qemu-iotests/280.out | 2 +- tests/qemu-iotests/287 | 152 ++++++++++++++++++++ tests/qemu-iotests/287.out | 67 +++++++++ tests/qemu-iotests/common.filter | 3 +- tests/qemu-iotests/group | 1 + 30 files changed, 825 insertions(+), 163 deletions(-) create mode 100755 tests/qemu-iotests/287 create mode 100644 tests/qemu-iotests/287.out -- 2.26.2 From: Denis Plotnikov <dplotnikov@virtuozzo.com> The patch adds some preparation parts for incompatible compression type feature to qcow2 allowing the use different compression methods for image clusters (de)compressing. It is implied that the compression type is set on the image creation and can be changed only later by image conversion, thus compression type defines the only compression algorithm used for the image, and thus, for all image clusters. The goal of the feature is to add support of other compression methods to qcow2. For example, ZSTD which is more effective on compression than ZLIB. The default compression is ZLIB. Images created with ZLIB compression type are backward compatible with older qemu versions. Adding of the compression type breaks a number of tests because now the compression type is reported on image creation and there are some changes in the qcow2 header in size and offsets. The tests are fixed in the following ways: * filter out compression_type for many tests * fix header size, feature table size and backing file offset affected tests: 031, 036, 061, 080 header_size +=8: 1 byte compression type 7 bytes padding feature_table += 48: incompatible feature compression type backing_file_offset += 56 (8 + 48 -> header_change + feature_table_change) * add "compression type" for test output matching when it isn't filtered affected tests: 049, 060, 061, 065, 082, 085, 144, 182, 185, 198, 206, 242, 255, 274, 280 Signed-off-by: Denis Plotnikov <dplotnikov@virtuozzo.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> QAPI part: Acked-by: Markus Armbruster <armbru@redhat.com> Message-Id: <20200507082521.29210-2-dplotnikov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- qapi/block-core.json | 22 +++++- block/qcow2.h | 20 +++++- include/block/block_int.h | 1 + block/qcow2.c | 113 +++++++++++++++++++++++++++++++ tests/qemu-iotests/031.out | 14 ++-- tests/qemu-iotests/036.out | 4 +- tests/qemu-iotests/049.out | 102 ++++++++++++++-------------- tests/qemu-iotests/060.out | 1 + tests/qemu-iotests/061.out | 34 ++++++---- tests/qemu-iotests/065 | 28 +++++--- tests/qemu-iotests/080 | 2 +- tests/qemu-iotests/082.out | 48 +++++++++++-- tests/qemu-iotests/085.out | 38 +++++------ tests/qemu-iotests/144.out | 4 +- tests/qemu-iotests/182.out | 2 +- tests/qemu-iotests/185.out | 8 +-- tests/qemu-iotests/198.out | 2 + tests/qemu-iotests/206.out | 5 ++ tests/qemu-iotests/242.out | 5 ++ tests/qemu-iotests/255.out | 8 +-- tests/qemu-iotests/274.out | 49 +++++++------- tests/qemu-iotests/280.out | 2 +- tests/qemu-iotests/common.filter | 3 +- 23 files changed, 365 insertions(+), 150 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 @@ # # @bitmaps: A list of qcow2 bitmap details (since 4.0) # +# @compression-type: the image cluster compression method (since 5.1) +# # Since: 1.7 ## { 'struct': 'ImageInfoSpecificQCow2', @@ -XXX,XX +XXX,XX @@ '*corrupt': 'bool', 'refcount-bits': 'int', '*encrypt': 'ImageInfoSpecificQCow2Encryption', - '*bitmaps': ['Qcow2BitmapInfo'] + '*bitmaps': ['Qcow2BitmapInfo'], + 'compression-type': 'Qcow2CompressionType' } } ## @@ -XXX,XX +XXX,XX @@ 'data': [ 'v2', 'v3' ] } +## +# @Qcow2CompressionType: +# +# Compression type used in qcow2 image file +# +# @zlib: zlib compression, see <http://zlib.net/> +# +# Since: 5.1 +## +{ 'enum': 'Qcow2CompressionType', + 'data': [ 'zlib' ] } + ## # @BlockdevCreateOptionsQcow2: # @@ -XXX,XX +XXX,XX @@ # allowed values: off, falloc, full, metadata) # @lazy-refcounts: True if refcounts may be updated lazily (default: off) # @refcount-bits: Width of reference counts in bits (default: 16) +# @compression-type: The image cluster compression method +# (default: zlib, since 5.1) # # Since: 2.12 ## @@ -XXX,XX +XXX,XX @@ '*cluster-size': 'size', '*preallocation': 'PreallocMode', '*lazy-refcounts': 'bool', - '*refcount-bits': 'int' } } + '*refcount-bits': 'int', + '*compression-type':'Qcow2CompressionType' } } ## # @BlockdevCreateOptionsQed: 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 QCowHeader { uint32_t refcount_order; uint32_t header_length; + + /* Additional fields */ + uint8_t compression_type; + + /* header must be a multiple of 8 */ + uint8_t padding[7]; } QEMU_PACKED QCowHeader; +QEMU_BUILD_BUG_ON(!QEMU_IS_ALIGNED(sizeof(QCowHeader), 8)); + typedef struct QEMU_PACKED QCowSnapshotHeader { /* header is 8 byte aligned */ uint64_t l1_table_offset; @@ -XXX,XX +XXX,XX @@ enum { QCOW2_INCOMPAT_DIRTY_BITNR = 0, QCOW2_INCOMPAT_CORRUPT_BITNR = 1, QCOW2_INCOMPAT_DATA_FILE_BITNR = 2, + QCOW2_INCOMPAT_COMPRESSION_BITNR = 3, QCOW2_INCOMPAT_DIRTY = 1 << QCOW2_INCOMPAT_DIRTY_BITNR, QCOW2_INCOMPAT_CORRUPT = 1 << QCOW2_INCOMPAT_CORRUPT_BITNR, QCOW2_INCOMPAT_DATA_FILE = 1 << QCOW2_INCOMPAT_DATA_FILE_BITNR, + QCOW2_INCOMPAT_COMPRESSION = 1 << QCOW2_INCOMPAT_COMPRESSION_BITNR, QCOW2_INCOMPAT_MASK = QCOW2_INCOMPAT_DIRTY | QCOW2_INCOMPAT_CORRUPT - | QCOW2_INCOMPAT_DATA_FILE, + | QCOW2_INCOMPAT_DATA_FILE + | QCOW2_INCOMPAT_COMPRESSION, }; /* Compatible feature bits */ @@ -XXX,XX +XXX,XX @@ typedef struct BDRVQcow2State { bool metadata_preallocation_checked; bool metadata_preallocation; + /* + * Compression type used for the image. Default: 0 - ZLIB + * The image compression type is set on image creation. + * For now, the only way to change the compression type + * is to convert the image with the desired compression type set. + */ + Qcow2CompressionType compression_type; } BDRVQcow2State; typedef struct Qcow2COWRegion { diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ #define BLOCK_OPT_REFCOUNT_BITS "refcount_bits" #define BLOCK_OPT_DATA_FILE "data_file" #define BLOCK_OPT_DATA_FILE_RAW "data_file_raw" +#define BLOCK_OPT_COMPRESSION_TYPE "compression_type" #define BLOCK_PROBE_BUF_SIZE 512 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_update_options(BlockDriverState *bs, QDict *options, return ret; } +static int validate_compression_type(BDRVQcow2State *s, Error **errp) +{ + switch (s->compression_type) { + case QCOW2_COMPRESSION_TYPE_ZLIB: + break; + + default: + error_setg(errp, "qcow2: unknown compression type: %u", + s->compression_type); + return -ENOTSUP; + } + + /* + * if the compression type differs from QCOW2_COMPRESSION_TYPE_ZLIB + * the incompatible feature flag must be set + */ + if (s->compression_type == QCOW2_COMPRESSION_TYPE_ZLIB) { + if (s->incompatible_features & QCOW2_INCOMPAT_COMPRESSION) { + error_setg(errp, "qcow2: Compression type incompatible feature " + "bit must not be set"); + return -EINVAL; + } + } else { + if (!(s->incompatible_features & QCOW2_INCOMPAT_COMPRESSION)) { + error_setg(errp, "qcow2: Compression type incompatible feature " + "bit must be set"); + return -EINVAL; + } + } + + return 0; +} + /* Called with s->lock held. */ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, int flags, Error **errp) @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, s->compatible_features = header.compatible_features; s->autoclear_features = header.autoclear_features; + /* + * Handle compression type + * Older qcow2 images don't contain the compression type header. + * Distinguish them by the header length and use + * the only valid (default) compression type in that case + */ + if (header.header_length > offsetof(QCowHeader, compression_type)) { + s->compression_type = header.compression_type; + } else { + s->compression_type = QCOW2_COMPRESSION_TYPE_ZLIB; + } + + ret = validate_compression_type(s, errp); + if (ret) { + goto fail; + } + if (s->incompatible_features & ~QCOW2_INCOMPAT_MASK) { void *feature_table = NULL; qcow2_read_extensions(bs, header.header_length, ext_end, @@ -XXX,XX +XXX,XX @@ int qcow2_update_header(BlockDriverState *bs) total_size = bs->total_sectors * BDRV_SECTOR_SIZE; refcount_table_clusters = s->refcount_table_size >> (s->cluster_bits - 3); + ret = validate_compression_type(s, NULL); + if (ret) { + goto fail; + } + *header = (QCowHeader) { /* Version 2 fields */ .magic = cpu_to_be32(QCOW_MAGIC), @@ -XXX,XX +XXX,XX @@ int qcow2_update_header(BlockDriverState *bs) .autoclear_features = cpu_to_be64(s->autoclear_features), .refcount_order = cpu_to_be32(s->refcount_order), .header_length = cpu_to_be32(header_length), + .compression_type = s->compression_type, }; /* For older versions, write a shorter header */ @@ -XXX,XX +XXX,XX @@ int qcow2_update_header(BlockDriverState *bs) .bit = QCOW2_INCOMPAT_DATA_FILE_BITNR, .name = "external data file", }, + { + .type = QCOW2_FEAT_TYPE_INCOMPATIBLE, + .bit = QCOW2_INCOMPAT_COMPRESSION_BITNR, + .name = "compression type", + }, { .type = QCOW2_FEAT_TYPE_COMPATIBLE, .bit = QCOW2_COMPAT_LAZY_REFCOUNTS_BITNR, @@ -XXX,XX +XXX,XX @@ qcow2_co_create(BlockdevCreateOptions *create_options, Error **errp) uint64_t* refcount_table; Error *local_err = NULL; int ret; + uint8_t compression_type = QCOW2_COMPRESSION_TYPE_ZLIB; assert(create_options->driver == BLOCKDEV_DRIVER_QCOW2); qcow2_opts = &create_options->u.qcow2; @@ -XXX,XX +XXX,XX @@ qcow2_co_create(BlockdevCreateOptions *create_options, Error **errp) } } + if (qcow2_opts->has_compression_type && + qcow2_opts->compression_type != QCOW2_COMPRESSION_TYPE_ZLIB) { + + ret = -EINVAL; + + if (version < 3) { + error_setg(errp, "Non-zlib compression type is only supported with " + "compatibility level 1.1 and above (use version=v3 or " + "greater)"); + goto out; + } + + switch (qcow2_opts->compression_type) { + default: + error_setg(errp, "Unknown compression type"); + goto out; + } + + compression_type = qcow2_opts->compression_type; + } + /* Create BlockBackend to write to the image */ blk = blk_new_with_bs(bs, BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL, errp); @@ -XXX,XX +XXX,XX @@ qcow2_co_create(BlockdevCreateOptions *create_options, Error **errp) .refcount_table_offset = cpu_to_be64(cluster_size), .refcount_table_clusters = cpu_to_be32(1), .refcount_order = cpu_to_be32(refcount_order), + /* don't deal with endianness since compression_type is 1 byte long */ + .compression_type = compression_type, .header_length = cpu_to_be32(sizeof(*header)), }; @@ -XXX,XX +XXX,XX @@ qcow2_co_create(BlockdevCreateOptions *create_options, Error **errp) header->autoclear_features |= cpu_to_be64(QCOW2_AUTOCLEAR_DATA_FILE_RAW); } + if (compression_type != QCOW2_COMPRESSION_TYPE_ZLIB) { + header->incompatible_features |= + cpu_to_be64(QCOW2_INCOMPAT_COMPRESSION); + } ret = blk_pwrite(blk, 0, header, cluster_size, 0); g_free(header); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_co_create_opts(BlockDriver *drv, { BLOCK_OPT_ENCRYPT, BLOCK_OPT_ENCRYPT_FORMAT }, { BLOCK_OPT_COMPAT_LEVEL, "version" }, { BLOCK_OPT_DATA_FILE_RAW, "data-file-raw" }, + { BLOCK_OPT_COMPRESSION_TYPE, "compression-type" }, { NULL, NULL }, }; @@ -XXX,XX +XXX,XX @@ static ImageInfoSpecific *qcow2_get_specific_info(BlockDriverState *bs, .data_file = g_strdup(s->image_data_file), .has_data_file_raw = has_data_file(bs), .data_file_raw = data_file_is_raw(bs), + .compression_type = s->compression_type, }; } else { /* if this assertion fails, this probably means a new version was @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, "images"); return -EINVAL; } + } else if (!strcmp(desc->name, BLOCK_OPT_COMPRESSION_TYPE)) { + const char *ct_name = + qemu_opt_get(opts, BLOCK_OPT_COMPRESSION_TYPE); + int compression_type = + qapi_enum_parse(&Qcow2CompressionType_lookup, ct_name, -1, + NULL); + if (compression_type == -1) { + error_setg(errp, "Unknown compression type: %s", ct_name); + return -ENOTSUP; + } + + if (compression_type != s->compression_type) { + error_setg(errp, "Changing the compression type " + "is not supported"); + return -ENOTSUP; + } } else { /* if this point is reached, this probably means a new option was * added without having it covered here */ @@ -XXX,XX +XXX,XX @@ static QemuOptsList qcow2_create_opts = { .help = "Width of a reference count entry in bits", .def_value_str = "16" }, + { + .name = BLOCK_OPT_COMPRESSION_TYPE, + .type = QEMU_OPT_STRING, + .help = "Compression method used for image cluster compression", + .def_value_str = "zlib" + }, { /* end of list */ } } }; diff --git a/tests/qemu-iotests/031.out b/tests/qemu-iotests/031.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/031.out +++ b/tests/qemu-iotests/031.out @@ -XXX,XX +XXX,XX @@ incompatible_features [] compatible_features [] autoclear_features [] refcount_order 4 -header_length 104 +header_length 112 Header extension: magic 0x6803f857 -length 288 +length 336 data <binary> Header extension: @@ -XXX,XX +XXX,XX @@ incompatible_features [] compatible_features [] autoclear_features [] refcount_order 4 -header_length 104 +header_length 112 Header extension: magic 0x6803f857 -length 288 +length 336 data <binary> Header extension: @@ -XXX,XX +XXX,XX @@ No errors were found on the image. magic 0x514649fb version 3 -backing_file_offset 0x1d8 +backing_file_offset 0x210 backing_file_size 0x17 cluster_bits 16 size 67108864 @@ -XXX,XX +XXX,XX @@ incompatible_features [] compatible_features [] autoclear_features [] refcount_order 4 -header_length 104 +header_length 112 Header extension: magic 0xe2792aca @@ -XXX,XX +XXX,XX @@ data 'host_device' Header extension: magic 0x6803f857 -length 288 +length 336 data <binary> Header extension: diff --git a/tests/qemu-iotests/036.out b/tests/qemu-iotests/036.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/036.out +++ b/tests/qemu-iotests/036.out @@ -XXX,XX +XXX,XX @@ compatible_features [] autoclear_features [63] Header extension: magic 0x6803f857 -length 288 +length 336 data <binary> @@ -XXX,XX +XXX,XX @@ compatible_features [] autoclear_features [] Header extension: magic 0x6803f857 -length 288 +length 336 data <binary> *** done diff --git a/tests/qemu-iotests/049.out b/tests/qemu-iotests/049.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/049.out +++ b/tests/qemu-iotests/049.out @@ -XXX,XX +XXX,XX @@ QA output created by 049 == 1. Traditional size parameter == qemu-img create -f qcow2 TEST_DIR/t.qcow2 1024 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 TEST_DIR/t.qcow2 1024b -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 TEST_DIR/t.qcow2 1k -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 TEST_DIR/t.qcow2 1K -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 TEST_DIR/t.qcow2 1M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1048576 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1048576 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 TEST_DIR/t.qcow2 1G -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1073741824 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1073741824 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 TEST_DIR/t.qcow2 1T -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1099511627776 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1099511627776 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 TEST_DIR/t.qcow2 1024.0 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 TEST_DIR/t.qcow2 1024.0b -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 TEST_DIR/t.qcow2 1.5k -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1536 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1536 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 TEST_DIR/t.qcow2 1.5K -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1536 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1536 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 TEST_DIR/t.qcow2 1.5M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1572864 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1572864 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 TEST_DIR/t.qcow2 1.5G -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1610612736 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1610612736 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 TEST_DIR/t.qcow2 1.5T -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1649267441664 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1649267441664 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib == 2. Specifying size via -o == qemu-img create -f qcow2 -o size=1024 TEST_DIR/t.qcow2 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o size=1024b TEST_DIR/t.qcow2 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o size=1k TEST_DIR/t.qcow2 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o size=1K TEST_DIR/t.qcow2 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o size=1M TEST_DIR/t.qcow2 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1048576 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1048576 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o size=1G TEST_DIR/t.qcow2 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1073741824 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1073741824 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o size=1T TEST_DIR/t.qcow2 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1099511627776 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1099511627776 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o size=1024.0 TEST_DIR/t.qcow2 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o size=1024.0b TEST_DIR/t.qcow2 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1024 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o size=1.5k TEST_DIR/t.qcow2 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1536 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1536 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o size=1.5K TEST_DIR/t.qcow2 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1536 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1536 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o size=1.5M TEST_DIR/t.qcow2 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1572864 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1572864 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o size=1.5G TEST_DIR/t.qcow2 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1610612736 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1610612736 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o size=1.5T TEST_DIR/t.qcow2 -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1649267441664 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=1649267441664 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib == 3. Invalid sizes == @@ -XXX,XX +XXX,XX @@ qemu-img: TEST_DIR/t.qcow2: The image size must be specified only once == Check correct interpretation of suffixes for cluster size == qemu-img create -f qcow2 -o cluster_size=1024 TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o cluster_size=1024b TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o cluster_size=1k TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o cluster_size=1K TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o cluster_size=1M TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1048576 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1048576 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o cluster_size=1024.0 TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o cluster_size=1024.0b TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=1024 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o cluster_size=0.5k TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=512 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=512 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o cluster_size=0.5K TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=512 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=512 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o cluster_size=0.5M TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=524288 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=524288 lazy_refcounts=off refcount_bits=16 compression_type=zlib == Check compat level option == qemu-img create -f qcow2 -o compat=0.10 TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=0.10 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=0.10 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o compat=1.1 TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=1.1 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=1.1 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o compat=0.42 TEST_DIR/t.qcow2 64M qemu-img: TEST_DIR/t.qcow2: Invalid parameter '0.42' -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=0.42 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=0.42 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o compat=foobar TEST_DIR/t.qcow2 64M qemu-img: TEST_DIR/t.qcow2: Invalid parameter 'foobar' -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=foobar cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=foobar cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib == Check preallocation option == qemu-img create -f qcow2 -o preallocation=off TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=65536 preallocation=off lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=65536 preallocation=off lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o preallocation=metadata TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=65536 preallocation=metadata lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=65536 preallocation=metadata lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o preallocation=1234 TEST_DIR/t.qcow2 64M qemu-img: TEST_DIR/t.qcow2: Invalid parameter '1234' -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=65536 preallocation=1234 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 cluster_size=65536 preallocation=1234 lazy_refcounts=off refcount_bits=16 compression_type=zlib == Check encryption option == qemu-img create -f qcow2 -o encryption=off TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 encryption=off cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 encryption=off cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 --object secret,id=sec0,data=123456 -o encryption=on,encrypt.key-secret=sec0 TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 encryption=on encrypt.key-secret=sec0 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 encryption=on encrypt.key-secret=sec0 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib == Check lazy_refcounts option (only with v3) == qemu-img create -f qcow2 -o compat=1.1,lazy_refcounts=off TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=1.1 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=1.1 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o compat=1.1,lazy_refcounts=on TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=1.1 cluster_size=65536 lazy_refcounts=on refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=1.1 cluster_size=65536 lazy_refcounts=on refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o compat=0.10,lazy_refcounts=off TEST_DIR/t.qcow2 64M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=0.10 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=0.10 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib qemu-img create -f qcow2 -o compat=0.10,lazy_refcounts=on TEST_DIR/t.qcow2 64M qemu-img: TEST_DIR/t.qcow2: Lazy refcounts only supported with compatibility level 1.1 and above (use version=v3 or greater) -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=0.10 cluster_size=65536 lazy_refcounts=on refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 compat=0.10 cluster_size=65536 lazy_refcounts=on refcount_bits=16 compression_type=zlib *** done 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 @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false refcount bits: 16 corrupt: true diff --git a/tests/qemu-iotests/061.out b/tests/qemu-iotests/061.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/061.out +++ b/tests/qemu-iotests/061.out @@ -XXX,XX +XXX,XX @@ incompatible_features [] compatible_features [0] autoclear_features [] refcount_order 4 -header_length 104 +header_length 112 Header extension: magic 0x6803f857 -length 288 +length 336 data <binary> magic 0x514649fb @@ -XXX,XX +XXX,XX @@ incompatible_features [] compatible_features [0] autoclear_features [] refcount_order 4 -header_length 104 +header_length 112 Header extension: magic 0x6803f857 -length 288 +length 336 data <binary> magic 0x514649fb @@ -XXX,XX +XXX,XX @@ incompatible_features [0] compatible_features [0] autoclear_features [] refcount_order 4 -header_length 104 +header_length 112 Header extension: magic 0x6803f857 -length 288 +length 336 data <binary> ERROR cluster 5 refcount=0 reference=1 @@ -XXX,XX +XXX,XX @@ incompatible_features [] compatible_features [42] autoclear_features [42] refcount_order 4 -header_length 104 +header_length 112 Header extension: magic 0x6803f857 -length 288 +length 336 data <binary> magic 0x514649fb @@ -XXX,XX +XXX,XX @@ incompatible_features [] compatible_features [0] autoclear_features [] refcount_order 4 -header_length 104 +header_length 112 Header extension: magic 0x6803f857 -length 288 +length 336 data <binary> read 65536/65536 bytes at offset 44040192 @@ -XXX,XX +XXX,XX @@ incompatible_features [0] compatible_features [0] autoclear_features [] refcount_order 4 -header_length 104 +header_length 112 Header extension: magic 0x6803f857 -length 288 +length 336 data <binary> ERROR cluster 5 refcount=0 reference=1 @@ -XXX,XX +XXX,XX @@ incompatible_features [] compatible_features [] autoclear_features [] refcount_order 4 -header_length 104 +header_length 112 Header extension: magic 0x6803f857 -length 288 +length 336 data <binary> read 131072/131072 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false refcount bits: 16 data file: TEST_DIR/t.IMGFMT.data @@ -XXX,XX +XXX,XX @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false refcount bits: 16 data file: foo @@ -XXX,XX +XXX,XX @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false refcount bits: 16 data file raw: false @@ -XXX,XX +XXX,XX @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false refcount bits: 16 data file: TEST_DIR/t.IMGFMT.data @@ -XXX,XX +XXX,XX @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false refcount bits: 16 data file: TEST_DIR/t.IMGFMT.data @@ -XXX,XX +XXX,XX @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false refcount bits: 16 data file: TEST_DIR/t.IMGFMT.data diff --git a/tests/qemu-iotests/065 b/tests/qemu-iotests/065 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/065 +++ b/tests/qemu-iotests/065 @@ -XXX,XX +XXX,XX @@ class TestQMP(TestImageInfoSpecific): class TestQCow2(TestQemuImgInfo): '''Testing a qcow2 version 2 image''' img_options = 'compat=0.10' - json_compare = { 'compat': '0.10', 'refcount-bits': 16 } - human_compare = [ 'compat: 0.10', 'refcount bits: 16' ] + json_compare = { 'compat': '0.10', 'refcount-bits': 16, + 'compression-type': 'zlib' } + human_compare = [ 'compat: 0.10', 'compression type: zlib', + 'refcount bits: 16' ] class TestQCow3NotLazy(TestQemuImgInfo): '''Testing a qcow2 version 3 image with lazy refcounts disabled''' img_options = 'compat=1.1,lazy_refcounts=off' json_compare = { 'compat': '1.1', 'lazy-refcounts': False, - 'refcount-bits': 16, 'corrupt': False } - human_compare = [ 'compat: 1.1', 'lazy refcounts: false', - 'refcount bits: 16', 'corrupt: false' ] + 'refcount-bits': 16, 'corrupt': False, + 'compression-type': 'zlib' } + human_compare = [ 'compat: 1.1', 'compression type: zlib', + 'lazy refcounts: false', 'refcount bits: 16', + 'corrupt: false' ] class TestQCow3Lazy(TestQemuImgInfo): '''Testing a qcow2 version 3 image with lazy refcounts enabled''' img_options = 'compat=1.1,lazy_refcounts=on' json_compare = { 'compat': '1.1', 'lazy-refcounts': True, - 'refcount-bits': 16, 'corrupt': False } - human_compare = [ 'compat: 1.1', 'lazy refcounts: true', - 'refcount bits: 16', 'corrupt: false' ] + 'refcount-bits': 16, 'corrupt': False, + 'compression-type': 'zlib' } + human_compare = [ 'compat: 1.1', 'compression type: zlib', + 'lazy refcounts: true', 'refcount bits: 16', + 'corrupt: false' ] class TestQCow3NotLazyQMP(TestQMP): '''Testing a qcow2 version 3 image with lazy refcounts disabled, opening @@ -XXX,XX +XXX,XX @@ class TestQCow3NotLazyQMP(TestQMP): img_options = 'compat=1.1,lazy_refcounts=off' qemu_options = 'lazy-refcounts=on' compare = { 'compat': '1.1', 'lazy-refcounts': False, - 'refcount-bits': 16, 'corrupt': False } + 'refcount-bits': 16, 'corrupt': False, + 'compression-type': 'zlib' } class TestQCow3LazyQMP(TestQMP): @@ -XXX,XX +XXX,XX @@ class TestQCow3LazyQMP(TestQMP): img_options = 'compat=1.1,lazy_refcounts=on' qemu_options = 'lazy-refcounts=off' compare = { 'compat': '1.1', 'lazy-refcounts': True, - 'refcount-bits': 16, 'corrupt': False } + 'refcount-bits': 16, 'corrupt': False, + 'compression-type': 'zlib' } TestImageInfoSpecific = None TestQemuImgInfo = None diff --git a/tests/qemu-iotests/080 b/tests/qemu-iotests/080 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/080 +++ b/tests/qemu-iotests/080 @@ -XXX,XX +XXX,XX @@ _supported_os Linux # - This is generally a test for compat=1.1 images _unsupported_imgopts 'refcount_bits=1[^0-9]' data_file 'compat=0.10' -header_size=104 +header_size=112 offset_backing_file_offset=8 offset_backing_file_size=16 diff --git a/tests/qemu-iotests/082.out b/tests/qemu-iotests/082.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/082.out +++ b/tests/qemu-iotests/082.out @@ -XXX,XX +XXX,XX @@ QA output created by 082 === create: Options specified more than once === Testing: create -f foo -f qcow2 TEST_DIR/t.qcow2 128M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib image: TEST_DIR/t.IMGFMT file format: IMGFMT virtual size: 128 MiB (134217728 bytes) cluster_size: 65536 Testing: create -f qcow2 -o cluster_size=4k -o lazy_refcounts=on TEST_DIR/t.qcow2 128M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 cluster_size=4096 lazy_refcounts=on refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 cluster_size=4096 lazy_refcounts=on refcount_bits=16 compression_type=zlib image: TEST_DIR/t.IMGFMT file format: IMGFMT virtual size: 128 MiB (134217728 bytes) cluster_size: 4096 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: true refcount bits: 16 corrupt: false Testing: create -f qcow2 -o cluster_size=4k -o lazy_refcounts=on -o cluster_size=8k TEST_DIR/t.qcow2 128M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 cluster_size=8192 lazy_refcounts=on refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 cluster_size=8192 lazy_refcounts=on refcount_bits=16 compression_type=zlib image: TEST_DIR/t.IMGFMT file format: IMGFMT virtual size: 128 MiB (134217728 bytes) cluster_size: 8192 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: true refcount bits: 16 corrupt: false Testing: create -f qcow2 -o cluster_size=4k,cluster_size=8k TEST_DIR/t.qcow2 128M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 cluster_size=8192 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 cluster_size=8192 lazy_refcounts=off refcount_bits=16 compression_type=zlib image: TEST_DIR/t.IMGFMT file format: IMGFMT virtual size: 128 MiB (134217728 bytes) @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported options: size=<size> - Virtual disk size Testing: create -f qcow2 -u -o backing_file=TEST_DIR/t.qcow2,,help TEST_DIR/t.qcow2 128M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/t.qcow2,,help cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/t.qcow2,,help cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib Testing: create -f qcow2 -u -o backing_file=TEST_DIR/t.qcow2,,? TEST_DIR/t.qcow2 128M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/t.qcow2,,? cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/t.qcow2,,? cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib Testing: create -f qcow2 -o backing_file=TEST_DIR/t.qcow2, -o help TEST_DIR/t.qcow2 128M qemu-img: Invalid option list: backing_file=TEST_DIR/t.qcow2, @@ -XXX,XX +XXX,XX @@ Supported qcow2 options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ qemu-img: Format driver 'bochs' does not support image creation === convert: Options specified more than once === Testing: create -f qcow2 TEST_DIR/t.qcow2 128M -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib Testing: convert -f foo -f qcow2 TEST_DIR/t.qcow2 TEST_DIR/t.qcow2.base image: TEST_DIR/t.IMGFMT.base @@ -XXX,XX +XXX,XX @@ virtual size: 128 MiB (134217728 bytes) cluster_size: 4096 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: true refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 128 MiB (134217728 bytes) cluster_size: 8192 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: true refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Supported qcow2 options: backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ virtual size: 128 MiB (134217728 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: true refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 130 MiB (136314880 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 132 MiB (138412032 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: true refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ Creation options for 'qcow2': backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Creation options for 'qcow2': backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Creation options for 'qcow2': backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Creation options for 'qcow2': backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Creation options for 'qcow2': backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Creation options for 'qcow2': backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Creation options for 'qcow2': backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Creation options for 'qcow2': backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm @@ -XXX,XX +XXX,XX @@ Creation options for 'qcow2': backing_fmt=<str> - Image format of the base image cluster_size=<size> - qcow2 cluster size compat=<str> - Compatibility level (v2 [0.10] or v3 [1.1]) + compression_type=<str> - Compression method used for image cluster compression data_file=<str> - File name of an external data file data_file_raw=<bool (on/off)> - The external data file must stay valid as a raw image encrypt.cipher-alg=<str> - Name of encryption cipher algorithm diff --git a/tests/qemu-iotests/085.out b/tests/qemu-iotests/085.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/085.out +++ b/tests/qemu-iotests/085.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT.2', fmt=IMGFMT size=134217728 === Create a single snapshot on virtio0 === { 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'virtio0', 'snapshot-file':'TEST_DIR/1-snapshot-v0.IMGFMT', 'format': 'IMGFMT' } } -Formatting 'TEST_DIR/1-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/t.qcow2.1 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/1-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/t.qcow2.1 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"return": {}} === Invalid command - missing device and nodename === @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/1-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file === Create several transactional group snapshots === { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/2-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/2-snapshot-v1.IMGFMT' } } ] } } -Formatting 'TEST_DIR/2-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/1-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/2-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/t.qcow2.2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/2-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/1-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib +Formatting 'TEST_DIR/2-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/t.qcow2.2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"return": {}} { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/3-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/3-snapshot-v1.IMGFMT' } } ] } } -Formatting 'TEST_DIR/3-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/2-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/3-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/2-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/3-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/2-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib +Formatting 'TEST_DIR/3-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/2-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"return": {}} { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/4-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/4-snapshot-v1.IMGFMT' } } ] } } -Formatting 'TEST_DIR/4-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/3-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/4-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/3-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/4-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/3-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib +Formatting 'TEST_DIR/4-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/3-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"return": {}} { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/5-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/5-snapshot-v1.IMGFMT' } } ] } } -Formatting 'TEST_DIR/5-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/4-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/5-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/4-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/5-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/4-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib +Formatting 'TEST_DIR/5-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/4-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"return": {}} { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/6-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/6-snapshot-v1.IMGFMT' } } ] } } -Formatting 'TEST_DIR/6-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/5-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/6-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/5-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/6-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/5-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib +Formatting 'TEST_DIR/6-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/5-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"return": {}} { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/7-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/7-snapshot-v1.IMGFMT' } } ] } } -Formatting 'TEST_DIR/7-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/6-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/7-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/6-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/7-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/6-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib +Formatting 'TEST_DIR/7-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/6-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"return": {}} { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/8-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/8-snapshot-v1.IMGFMT' } } ] } } -Formatting 'TEST_DIR/8-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/7-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/8-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/7-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/8-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/7-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib +Formatting 'TEST_DIR/8-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/7-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"return": {}} { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/9-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/9-snapshot-v1.IMGFMT' } } ] } } -Formatting 'TEST_DIR/9-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/8-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/9-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/8-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/9-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/8-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib +Formatting 'TEST_DIR/9-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/8-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"return": {}} { 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/10-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/10-snapshot-v1.IMGFMT' } } ] } } -Formatting 'TEST_DIR/10-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/9-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 -Formatting 'TEST_DIR/10-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/9-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/10-snapshot-v0.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/9-snapshot-v0.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib +Formatting 'TEST_DIR/10-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/9-snapshot-v1.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"return": {}} === Create a couple of snapshots using blockdev-snapshot === diff --git a/tests/qemu-iotests/144.out b/tests/qemu-iotests/144.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/144.out +++ b/tests/qemu-iotests/144.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=536870912 { 'execute': 'qmp_capabilities' } {"return": {}} { 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'virtio0', 'snapshot-file':'TEST_DIR/tmp.IMGFMT', 'format': 'IMGFMT' } } -Formatting 'TEST_DIR/tmp.qcow2', fmt=qcow2 size=536870912 backing_file=TEST_DIR/t.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/tmp.qcow2', fmt=qcow2 size=536870912 backing_file=TEST_DIR/t.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"return": {}} === Performing block-commit on active layer === @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/tmp.qcow2', fmt=qcow2 size=536870912 backing_file=TEST_DIR/ === Performing Live Snapshot 2 === { 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'virtio0', 'snapshot-file':'TEST_DIR/tmp2.IMGFMT', 'format': 'IMGFMT' } } -Formatting 'TEST_DIR/tmp2.qcow2', fmt=qcow2 size=536870912 backing_file=TEST_DIR/t.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/tmp2.qcow2', fmt=qcow2 size=536870912 backing_file=TEST_DIR/t.qcow2 backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"return": {}} *** done diff --git a/tests/qemu-iotests/182.out b/tests/qemu-iotests/182.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/182.out +++ b/tests/qemu-iotests/182.out @@ -XXX,XX +XXX,XX @@ Is another process using the image [TEST_DIR/t.qcow2]? {'execute': 'blockdev-add', 'arguments': { 'node-name': 'node0', 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT', 'locking': 'on' } } {"return": {}} {'execute': 'blockdev-snapshot-sync', 'arguments': { 'node-name': 'node0', 'snapshot-file': 'TEST_DIR/t.IMGFMT.overlay', 'snapshot-node-name': 'node1' } } -Formatting 'TEST_DIR/t.qcow2.overlay', fmt=qcow2 size=197120 backing_file=TEST_DIR/t.qcow2 backing_fmt=file cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2.overlay', fmt=qcow2 size=197120 backing_file=TEST_DIR/t.qcow2 backing_fmt=file cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"return": {}} {'execute': 'blockdev-add', 'arguments': { 'node-name': 'node1', 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT', 'locking': 'on' } } {"return": {}} diff --git a/tests/qemu-iotests/185.out b/tests/qemu-iotests/185.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/185.out +++ b/tests/qemu-iotests/185.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864 === Creating backing chain === { 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'disk', 'snapshot-file': 'TEST_DIR/t.IMGFMT.mid', 'format': 'IMGFMT', 'mode': 'absolute-paths' } } -Formatting 'TEST_DIR/t.qcow2.mid', fmt=qcow2 size=67108864 backing_file=TEST_DIR/t.qcow2.base backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2.mid', fmt=qcow2 size=67108864 backing_file=TEST_DIR/t.qcow2.base backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"return": {}} { 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io disk "write 0 4M"' } } wrote 4194304/4194304 bytes at offset 0 4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) {"return": ""} { 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'disk', 'snapshot-file': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'absolute-paths' } } -Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 backing_file=TEST_DIR/t.qcow2.mid backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 backing_file=TEST_DIR/t.qcow2.mid backing_fmt=qcow2 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"return": {}} === Start commit job and exit qemu === @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 backing_file=TEST_DIR/t.q { 'execute': 'qmp_capabilities' } {"return": {}} { 'execute': 'drive-mirror', 'arguments': { 'device': 'disk', 'target': 'TEST_DIR/t.IMGFMT.copy', 'format': 'IMGFMT', 'sync': 'full', 'speed': 65536 } } -Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 size=67108864 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 size=67108864 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "disk"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "disk"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 size=67108864 cluster_size=65536 l { 'execute': 'qmp_capabilities' } {"return": {}} { 'execute': 'drive-backup', 'arguments': { 'device': 'disk', 'target': 'TEST_DIR/t.IMGFMT.copy', 'format': 'IMGFMT', 'sync': 'full', 'speed': 65536 } } -Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 size=67108864 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 size=67108864 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "disk"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "disk"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "paused", "id": "disk"}} diff --git a/tests/qemu-iotests/198.out b/tests/qemu-iotests/198.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/198.out +++ b/tests/qemu-iotests/198.out @@ -XXX,XX +XXX,XX @@ image: json:{ /* filtered */ } file format: IMGFMT virtual size: 16 MiB (16777216 bytes) Format specific information: + compression type: zlib encrypt: ivgen alg: plain64 hash alg: sha256 @@ -XXX,XX +XXX,XX @@ file format: IMGFMT virtual size: 16 MiB (16777216 bytes) backing file: TEST_DIR/t.IMGFMT.base Format specific information: + compression type: zlib encrypt: ivgen alg: plain64 hash alg: sha256 diff --git a/tests/qemu-iotests/206.out b/tests/qemu-iotests/206.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/206.out +++ b/tests/qemu-iotests/206.out @@ -XXX,XX +XXX,XX @@ virtual size: 128 MiB (134217728 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 64 MiB (67108864 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 32 MiB (33554432 bytes) cluster_size: 2097152 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: true refcount bits: 1 corrupt: false @@ -XXX,XX +XXX,XX @@ backing file: TEST_IMG.base backing file format: IMGFMT Format specific information: compat: 0.10 + compression type: zlib refcount bits: 16 === Successful image creation (encrypted) === @@ -XXX,XX +XXX,XX @@ encrypted: yes cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false refcount bits: 16 encrypt: diff --git a/tests/qemu-iotests/242.out b/tests/qemu-iotests/242.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/242.out +++ b/tests/qemu-iotests/242.out @@ -XXX,XX +XXX,XX @@ virtual size: 1 MiB (1048576 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ virtual size: 1 MiB (1048576 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false bitmaps: [0]: @@ -XXX,XX +XXX,XX @@ virtual size: 1 MiB (1048576 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false bitmaps: [0]: @@ -XXX,XX +XXX,XX @@ virtual size: 1 MiB (1048576 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false bitmaps: [0]: @@ -XXX,XX +XXX,XX @@ virtual size: 1 MiB (1048576 bytes) cluster_size: 65536 Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false bitmaps: [0]: diff --git a/tests/qemu-iotests/255.out b/tests/qemu-iotests/255.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/255.out +++ b/tests/qemu-iotests/255.out @@ -XXX,XX +XXX,XX @@ Finishing a commit job with background reads === Create backing chain and start VM === -Formatting 'TEST_DIR/PID-t.qcow2.mid', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-t.qcow2.mid', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib -Formatting 'TEST_DIR/PID-t.qcow2', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-t.qcow2', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib === Start background read requests === @@ -XXX,XX +XXX,XX @@ Closing the VM while a job is being cancelled === Create images and start VM === -Formatting 'TEST_DIR/PID-src.qcow2', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-src.qcow2', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib -Formatting 'TEST_DIR/PID-dst.qcow2', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-dst.qcow2', fmt=qcow2 size=134217728 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib wrote 1048576/1048576 bytes at offset 0 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) 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 @@ == Commit tests == -Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=2097152 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=2097152 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib -Formatting 'TEST_DIR/PID-mid', fmt=qcow2 size=1048576 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-mid', fmt=qcow2 size=1048576 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib -Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=2097152 backing_file=TEST_DIR/PID-mid cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=2097152 backing_file=TEST_DIR/PID-mid cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib wrote 2097152/2097152 bytes at offset 0 2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ cluster_size: 65536 backing file: TEST_DIR/PID-base Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 1048576 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) === Testing HMP commit (top -> mid) === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=2097152 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=2097152 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib -Formatting 'TEST_DIR/PID-mid', fmt=qcow2 size=1048576 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-mid', fmt=qcow2 size=1048576 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib -Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=2097152 backing_file=TEST_DIR/PID-mid cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=2097152 backing_file=TEST_DIR/PID-mid cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib wrote 2097152/2097152 bytes at offset 0 2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ cluster_size: 65536 backing file: TEST_DIR/PID-base Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ 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 -> mid) === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=2097152 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=2097152 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib -Formatting 'TEST_DIR/PID-mid', fmt=qcow2 size=1048576 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-mid', fmt=qcow2 size=1048576 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib -Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=2097152 backing_file=TEST_DIR/PID-mid cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=2097152 backing_file=TEST_DIR/PID-mid cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib wrote 2097152/2097152 bytes at offset 0 2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ cluster_size: 65536 backing file: TEST_DIR/PID-base Format specific information: compat: 1.1 + compression type: zlib lazy refcounts: false refcount bits: 16 corrupt: false @@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 1048576 == Resize tests == === preallocation=off === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=6442450944 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=6442450944 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib -Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=1073741824 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=1073741824 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib wrote 65536/65536 bytes at offset 5368709120 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 5368709120 { "start": 1073741824, "length": 7516192768, "depth": 0, "zero": true, "data": false}] === preallocation=metadata === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=34359738368 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=34359738368 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib -Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=32212254720 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=32212254720 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib wrote 65536/65536 bytes at offset 33285996544 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 33285996544 { "start": 34896609280, "length": 536870912, "depth": 0, "zero": true, "data": false, "offset": 2685075456}] === preallocation=falloc === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=10485760 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=10485760 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib -Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=5242880 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=5242880 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib wrote 65536/65536 bytes at offset 9437184 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 9437184 { "start": 5242880, "length": 10485760, "depth": 0, "zero": false, "data": true, "offset": 327680}] === preallocation=full === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=16777216 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=16777216 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib -Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=8388608 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=8388608 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib wrote 65536/65536 bytes at offset 11534336 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 11534336 { "start": 8388608, "length": 4194304, "depth": 0, "zero": false, "data": true, "offset": 327680}] === preallocation=off === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=393216 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=393216 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib -Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=259072 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=259072 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib wrote 65536/65536 bytes at offset 259072 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 259072 { "start": 262144, "length": 262144, "depth": 0, "zero": true, "data": false}] === preallocation=off === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=409600 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=409600 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib -Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=262144 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=262144 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib wrote 65536/65536 bytes at offset 344064 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 344064 { "start": 262144, "length": 262144, "depth": 0, "zero": true, "data": false}] === preallocation=off === -Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=524288 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=524288 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib -Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=262144 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=262144 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib wrote 65536/65536 bytes at offset 446464 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) diff --git a/tests/qemu-iotests/280.out b/tests/qemu-iotests/280.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/280.out +++ b/tests/qemu-iotests/280.out @@ -XXX,XX +XXX,XX @@ -Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=67108864 cluster_size=65536 lazy_refcounts=off refcount_bits=16 +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=67108864 cluster_size=65536 lazy_refcounts=off refcount_bits=16 compression_type=zlib === Launch VM === Enabling migration QMP events on VM... diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.filter +++ b/tests/qemu-iotests/common.filter @@ -XXX,XX +XXX,XX @@ _filter_img_create() -e "s# refcount_bits=[0-9]\\+##g" \ -e "s# key-secret=[a-zA-Z0-9]\\+##g" \ -e "s# iter-time=[0-9]\\+##g" \ - -e "s# force_size=\\(on\\|off\\)##g" + -e "s# force_size=\\(on\\|off\\)##g" \ + -e "s# compression_type=[a-zA-Z0-9]\\+##g" } _filter_img_info() -- 2.26.2 From: Denis Plotnikov <dplotnikov@virtuozzo.com> The patch enables processing the image compression type defined for the image and chooses an appropriate method for image clusters (de)compression. Signed-off-by: Denis Plotnikov <dplotnikov@virtuozzo.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20200507082521.29210-3-dplotnikov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-threads.c | 71 ++++++++++++++++++++++++++++++++++++------- 1 file changed, 60 insertions(+), 11 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 @@ typedef struct Qcow2CompressData { } Qcow2CompressData; /* - * qcow2_compress() + * qcow2_zlib_compress() + * + * Compress @src_size bytes of data using zlib compression method * * @dest - destination buffer, @dest_size bytes * @src - source buffer, @src_size bytes @@ -XXX,XX +XXX,XX @@ typedef struct Qcow2CompressData { * -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) +static ssize_t qcow2_zlib_compress(void *dest, size_t dest_size, + const void *src, size_t src_size) { ssize_t ret; z_stream strm; @@ -XXX,XX +XXX,XX @@ static ssize_t qcow2_compress(void *dest, size_t dest_size, } /* - * qcow2_decompress() + * qcow2_zlib_decompress() * * Decompress some data (not more than @src_size bytes) to produce exactly - * @dest_size bytes. + * @dest_size bytes using zlib compression method * * @dest - destination buffer, @dest_size bytes * @src - source buffer, @src_size bytes @@ -XXX,XX +XXX,XX @@ static ssize_t qcow2_compress(void *dest, size_t dest_size, * Returns: 0 on success * -EIO on fail */ -static ssize_t qcow2_decompress(void *dest, size_t dest_size, - const void *src, size_t src_size) +static ssize_t qcow2_zlib_decompress(void *dest, size_t dest_size, + const void *src, size_t src_size) { int ret; z_stream strm; @@ -XXX,XX +XXX,XX @@ qcow2_co_do_compress(BlockDriverState *bs, void *dest, size_t dest_size, return arg.ret; } +/* + * qcow2_co_compress() + * + * Compress @src_size bytes of data using the compression + * method defined by the image compression type + * + * @dest - destination buffer, @dest_size bytes + * @src - source buffer, @src_size bytes + * + * Returns: compressed size on success + * a negative error code on failure + */ 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); + BDRVQcow2State *s = bs->opaque; + Qcow2CompressFunc fn; + + switch (s->compression_type) { + case QCOW2_COMPRESSION_TYPE_ZLIB: + fn = qcow2_zlib_compress; + break; + + default: + abort(); + } + + return qcow2_co_do_compress(bs, dest, dest_size, src, src_size, fn); } +/* + * qcow2_co_decompress() + * + * Decompress some data (not more than @src_size bytes) to produce exactly + * @dest_size bytes using the compression method defined by the image + * compression type + * + * @dest - destination buffer, @dest_size bytes + * @src - source buffer, @src_size bytes + * + * Returns: 0 on success + * a negative error code on failure + */ 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); + BDRVQcow2State *s = bs->opaque; + Qcow2CompressFunc fn; + + switch (s->compression_type) { + case QCOW2_COMPRESSION_TYPE_ZLIB: + fn = qcow2_zlib_decompress; + break; + + default: + abort(); + } + + return qcow2_co_do_compress(bs, dest, dest_size, src, src_size, fn); } -- 2.26.2 From: Denis Plotnikov <dplotnikov@virtuozzo.com> zstd significantly reduces cluster compression time. It provides better compression performance maintaining the same level of the compression ratio in comparison with zlib, which, at the moment, is the only compression method available. The performance test results: Test compresses and decompresses qemu qcow2 image with just installed rhel-7.6 guest. Image cluster size: 64K. Image on disk size: 2.2G The test was conducted with brd disk to reduce the influence of disk subsystem to the test results. The results is given in seconds. compress cmd: time ./qemu-img convert -O qcow2 -c -o compression_type=[zlib|zstd] src.img [zlib|zstd]_compressed.img decompress cmd time ./qemu-img convert -O qcow2 [zlib|zstd]_compressed.img uncompressed.img compression decompression zlib zstd zlib zstd ------------------------------------------------------------ real 65.5 16.3 (-75 %) 1.9 1.6 (-16 %) user 65.0 15.8 5.3 2.5 sys 3.3 0.2 2.0 2.0 Both ZLIB and ZSTD gave the same compression ratio: 1.57 compressed image size in both cases: 1.4G Signed-off-by: Denis Plotnikov <dplotnikov@virtuozzo.com> QAPI part: Acked-by: Markus Armbruster <armbru@redhat.com> Message-Id: <20200507082521.29210-4-dplotnikov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- docs/interop/qcow2.txt | 1 + configure | 2 +- qapi/block-core.json | 3 +- block/qcow2-threads.c | 169 +++++++++++++++++++++++++++++++++++++++++ block/qcow2.c | 7 ++ 5 files changed, 180 insertions(+), 2 deletions(-) diff --git a/docs/interop/qcow2.txt b/docs/interop/qcow2.txt index XXXXXXX..XXXXXXX 100644 --- a/docs/interop/qcow2.txt +++ b/docs/interop/qcow2.txt @@ -XXX,XX +XXX,XX @@ version 2. Available compression type values: 0: zlib <https://www.zlib.net/> + 1: zstd <http://github.com/facebook/zstd> === Header padding === diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ disabled with --disable-FEATURE, default is enabled if available: lzfse support of lzfse compression library (for reading lzfse-compressed dmg images) zstd support for zstd compression library - (for migration compression) + (for migration compression and qcow2 cluster compression) seccomp seccomp support coroutine-pool coroutine freelist (better performance) glusterfs GlusterFS backend 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 @@ # Compression type used in qcow2 image file # # @zlib: zlib compression, see <http://zlib.net/> +# @zstd: zstd compression, see <http://github.com/facebook/zstd> # # Since: 5.1 ## { 'enum': 'Qcow2CompressionType', - 'data': [ 'zlib' ] } + 'data': [ 'zlib', { 'name': 'zstd', 'if': 'defined(CONFIG_ZSTD)' } ] } ## # @BlockdevCreateOptionsQcow2: 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 @@ #define ZLIB_CONST #include <zlib.h> +#ifdef CONFIG_ZSTD +#include <zstd.h> +#include <zstd_errors.h> +#endif + #include "qcow2.h" #include "block/thread-pool.h" #include "crypto.h" @@ -XXX,XX +XXX,XX @@ static ssize_t qcow2_zlib_decompress(void *dest, size_t dest_size, return ret; } +#ifdef CONFIG_ZSTD + +/* + * qcow2_zstd_compress() + * + * Compress @src_size bytes of data using zstd compression method + * + * @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_zstd_compress(void *dest, size_t dest_size, + const void *src, size_t src_size) +{ + ssize_t ret; + size_t zstd_ret; + ZSTD_outBuffer output = { + .dst = dest, + .size = dest_size, + .pos = 0 + }; + ZSTD_inBuffer input = { + .src = src, + .size = src_size, + .pos = 0 + }; + ZSTD_CCtx *cctx = ZSTD_createCCtx(); + + if (!cctx) { + return -EIO; + } + /* + * Use the zstd streamed interface for symmetry with decompression, + * where streaming is essential since we don't record the exact + * compressed size. + * + * ZSTD_compressStream2() tries to compress everything it could + * with a single call. Although, ZSTD docs says that: + * "You must continue calling ZSTD_compressStream2() with ZSTD_e_end + * until it returns 0, at which point you are free to start a new frame", + * in out tests we saw the only case when it returned with >0 - + * when the output buffer was too small. In that case, + * ZSTD_compressStream2() expects a bigger buffer on the next call. + * We can't provide a bigger buffer because we are limited with dest_size + * which we pass to the ZSTD_compressStream2() at once. + * So, we don't need any loops and just abort the compression when we + * don't get 0 result on the first call. + */ + zstd_ret = ZSTD_compressStream2(cctx, &output, &input, ZSTD_e_end); + + if (zstd_ret) { + if (zstd_ret > output.size - output.pos) { + ret = -ENOMEM; + } else { + ret = -EIO; + } + goto out; + } + + /* make sure that zstd didn't overflow the dest buffer */ + assert(output.pos <= dest_size); + ret = output.pos; +out: + ZSTD_freeCCtx(cctx); + return ret; +} + +/* + * qcow2_zstd_decompress() + * + * Decompress some data (not more than @src_size bytes) to produce exactly + * @dest_size bytes using zstd compression method + * + * @dest - destination buffer, @dest_size bytes + * @src - source buffer, @src_size bytes + * + * Returns: 0 on success + * -EIO on any error + */ +static ssize_t qcow2_zstd_decompress(void *dest, size_t dest_size, + const void *src, size_t src_size) +{ + size_t zstd_ret = 0; + ssize_t ret = 0; + ZSTD_outBuffer output = { + .dst = dest, + .size = dest_size, + .pos = 0 + }; + ZSTD_inBuffer input = { + .src = src, + .size = src_size, + .pos = 0 + }; + ZSTD_DCtx *dctx = ZSTD_createDCtx(); + + if (!dctx) { + return -EIO; + } + + /* + * The compressed stream from the input buffer may consist of more + * than one zstd frame. So we iterate until we get a fully + * uncompressed cluster. + * From zstd docs related to ZSTD_decompressStream: + * "return : 0 when a frame is completely decoded and fully flushed" + * We suppose that this means: each time ZSTD_decompressStream reads + * only ONE full frame and returns 0 if and only if that frame + * is completely decoded and flushed. Only after returning 0, + * ZSTD_decompressStream reads another ONE full frame. + */ + while (output.pos < output.size) { + size_t last_in_pos = input.pos; + size_t last_out_pos = output.pos; + zstd_ret = ZSTD_decompressStream(dctx, &output, &input); + + if (ZSTD_isError(zstd_ret)) { + ret = -EIO; + break; + } + + /* + * The ZSTD manual is vague about what to do if it reads + * the buffer partially, and we don't want to get stuck + * in an infinite loop where ZSTD_decompressStream + * returns > 0 waiting for another input chunk. So, we add + * a check which ensures that the loop makes some progress + * on each step. + */ + if (last_in_pos >= input.pos && + last_out_pos >= output.pos) { + ret = -EIO; + break; + } + } + /* + * Make sure that we have the frame fully flushed here + * if not, we somehow managed to get uncompressed cluster + * greater then the cluster size, possibly because of its + * damage. + */ + if (zstd_ret > 0) { + ret = -EIO; + } + + ZSTD_freeDCtx(dctx); + assert(ret == 0 || ret == -EIO); + return ret; +} +#endif + static int qcow2_compress_pool_func(void *opaque) { Qcow2CompressData *data = opaque; @@ -XXX,XX +XXX,XX @@ qcow2_co_compress(BlockDriverState *bs, void *dest, size_t dest_size, fn = qcow2_zlib_compress; break; +#ifdef CONFIG_ZSTD + case QCOW2_COMPRESSION_TYPE_ZSTD: + fn = qcow2_zstd_compress; + break; +#endif default: abort(); } @@ -XXX,XX +XXX,XX @@ qcow2_co_decompress(BlockDriverState *bs, void *dest, size_t dest_size, fn = qcow2_zlib_decompress; break; +#ifdef CONFIG_ZSTD + case QCOW2_COMPRESSION_TYPE_ZSTD: + fn = qcow2_zstd_decompress; + break; +#endif default: abort(); } 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 validate_compression_type(BDRVQcow2State *s, Error **errp) { switch (s->compression_type) { case QCOW2_COMPRESSION_TYPE_ZLIB: +#ifdef CONFIG_ZSTD + case QCOW2_COMPRESSION_TYPE_ZSTD: +#endif break; default: @@ -XXX,XX +XXX,XX @@ qcow2_co_create(BlockdevCreateOptions *create_options, Error **errp) } switch (qcow2_opts->compression_type) { +#ifdef CONFIG_ZSTD + case QCOW2_COMPRESSION_TYPE_ZSTD: + break; +#endif default: error_setg(errp, "Unknown compression type"); goto out; -- 2.26.2 From: Denis Plotnikov <dplotnikov@virtuozzo.com> The test checks fulfilling qcow2 requirements for the compression type feature and zstd compression type operability. Signed-off-by: Denis Plotnikov <dplotnikov@virtuozzo.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Tested-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-Id: <20200507082521.29210-5-dplotnikov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/287 | 152 +++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/287.out | 67 ++++++++++++++++ tests/qemu-iotests/group | 1 + 3 files changed, 220 insertions(+) create mode 100755 tests/qemu-iotests/287 create mode 100644 tests/qemu-iotests/287.out diff --git a/tests/qemu-iotests/287 b/tests/qemu-iotests/287 new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/287 @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env bash +# +# Test case for an image using zstd compression +# +# Copyright (c) 2020 Virtuozzo International GmbH +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + +# creator +owner=dplotnikov@virtuozzo.com + +seq="$(basename $0)" +echo "QA output created by $seq" + +status=1 # failure is the default! + +# standard environment +. ./common.rc +. ./common.filter + +# This tests qocw2-specific low-level functionality +_supported_fmt qcow2 +_supported_proto file +_supported_os Linux +_unsupported_imgopts 'compat=0.10' data_file + +COMPR_IMG="$TEST_IMG.compressed" +RAND_FILE="$TEST_DIR/rand_data" + +_cleanup() +{ + _cleanup_test_img + _rm_test_img "$COMPR_IMG" + rm -f "$RAND_FILE" +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# for all the cases +CLUSTER_SIZE=65536 + +# Check if we can run this test. +if IMGOPTS='compression_type=zstd' _make_test_img 64M | + grep "Invalid parameter 'zstd'"; then + _notrun "ZSTD is disabled" +fi + +echo +echo "=== Testing compression type incompatible bit setting for zlib ===" +echo +_make_test_img -o compression_type=zlib 64M +$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features + +echo +echo "=== Testing compression type incompatible bit setting for zstd ===" +echo +_make_test_img -o compression_type=zstd 64M +$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features + +echo +echo "=== Testing zlib with incompatible bit set ===" +echo +_make_test_img -o compression_type=zlib 64M +$PYTHON qcow2.py "$TEST_IMG" set-feature-bit incompatible 3 +# to make sure the bit was actually set +$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features + +if $QEMU_IMG info "$TEST_IMG" >/dev/null 2>&1 ; then + echo "Error: The image opened successfully. The image must not be opened." +fi + +echo +echo "=== Testing zstd with incompatible bit unset ===" +echo +_make_test_img -o compression_type=zstd 64M +$PYTHON qcow2.py "$TEST_IMG" set-header incompatible_features 0 +# to make sure the bit was actually unset +$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features + +if $QEMU_IMG info "$TEST_IMG" >/dev/null 2>&1 ; then + echo "Error: The image opened successfully. The image must not be opened." +fi + +echo +echo "=== Testing compression type values ===" +echo +# zlib=0 +_make_test_img -o compression_type=zlib 64M +peek_file_be "$TEST_IMG" 104 1 +echo + +# zstd=1 +_make_test_img -o compression_type=zstd 64M +peek_file_be "$TEST_IMG" 104 1 +echo + +echo +echo "=== Testing simple reading and writing with zstd ===" +echo +_make_test_img -o compression_type=zstd 64M +$QEMU_IO -c "write -c -P 0xAC 64K 64K " "$TEST_IMG" | _filter_qemu_io +$QEMU_IO -c "read -P 0xAC 64K 64K " "$TEST_IMG" | _filter_qemu_io +# read on the cluster boundaries +$QEMU_IO -c "read -v 131070 8 " "$TEST_IMG" | _filter_qemu_io +$QEMU_IO -c "read -v 65534 8" "$TEST_IMG" | _filter_qemu_io + +echo +echo "=== Testing adjacent clusters reading and writing with zstd ===" +echo +_make_test_img -o compression_type=zstd 64M +$QEMU_IO -c "write -c -P 0xAB 0 64K " "$TEST_IMG" | _filter_qemu_io +$QEMU_IO -c "write -c -P 0xAC 64K 64K " "$TEST_IMG" | _filter_qemu_io +$QEMU_IO -c "write -c -P 0xAD 128K 64K " "$TEST_IMG" | _filter_qemu_io + +$QEMU_IO -c "read -P 0xAB 0 64k " "$TEST_IMG" | _filter_qemu_io +$QEMU_IO -c "read -P 0xAC 64K 64k " "$TEST_IMG" | _filter_qemu_io +$QEMU_IO -c "read -P 0xAD 128K 64k " "$TEST_IMG" | _filter_qemu_io + +echo +echo "=== Testing incompressible cluster processing with zstd ===" +echo +# create a 2M image and fill it with 1M likely incompressible data +# and 1M compressible data +dd if=/dev/urandom of="$RAND_FILE" bs=1M count=1 seek=1 +QEMU_IO_OPTIONS="$QEMU_IO_OPTIONS_NO_FMT" \ +$QEMU_IO -f raw -c "write -P 0xFA 0 1M" "$RAND_FILE" | _filter_qemu_io + +$QEMU_IMG convert -f raw -O $IMGFMT -c \ +-o "$(_optstr_add "$IMGOPTS" "compression_type=zlib")" "$RAND_FILE" \ +"$TEST_IMG" | _filter_qemu_io + +$QEMU_IMG convert -O $IMGFMT -c \ +-o "$(_optstr_add "$IMGOPTS" "compression_type=zstd")" "$TEST_IMG" \ +"$COMPR_IMG" | _filter_qemu_io + +$QEMU_IMG compare "$TEST_IMG" "$COMPR_IMG" + +# success, all done +echo "*** done" +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/287.out b/tests/qemu-iotests/287.out new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/287.out @@ -XXX,XX +XXX,XX @@ +QA output created by 287 + +=== Testing compression type incompatible bit setting for zlib === + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 +incompatible_features [] + +=== Testing compression type incompatible bit setting for zstd === + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 +incompatible_features [3] + +=== Testing zlib with incompatible bit set === + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 +incompatible_features [3] + +=== Testing zstd with incompatible bit unset === + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 +incompatible_features [] + +=== Testing compression type values === + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 + 0 +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 + 1 + +=== Testing simple reading and writing with zstd === + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 +wrote 65536/65536 bytes at offset 65536 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 65536/65536 bytes at offset 65536 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +0001fffe: ac ac 00 00 00 00 00 00 ........ +read 8/8 bytes at offset 131070 +8 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +0000fffe: 00 00 ac ac ac ac ac ac ........ +read 8/8 bytes at offset 65534 +8 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Testing adjacent clusters reading and writing with zstd === + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 +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 65536 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 65536/65536 bytes at offset 131072 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 65536/65536 bytes at offset 0 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 65536/65536 bytes at offset 65536 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 65536/65536 bytes at offset 131072 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Testing incompressible cluster processing with zstd === + +1+0 records in +1+0 records out +wrote 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +Images are identical. +*** done diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/group +++ b/tests/qemu-iotests/group @@ -XXX,XX +XXX,XX @@ 283 auto quick 284 rw 286 rw quick +287 auto quick 288 quick 289 rw quick 290 rw auto quick -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Obviously, we should g_free the task after trace point and offset update. Reported-by: Coverity (CID 1428756) Fixes: 4ce5dd3e9b5ee0fac18625860eb3727399ee965e Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200507183800.22626-1-vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/block-copy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/block-copy.c b/block/block-copy.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-copy.c +++ b/block/block-copy.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn block_copy_dirty_clusters(BlockCopyState *s, } if (s->skip_unallocated && !(ret & BDRV_BLOCK_ALLOCATED)) { block_copy_task_end(task, 0); - g_free(task); progress_set_remaining(s->progress, bdrv_get_dirty_count(s->copy_bitmap) + s->in_flight_bytes); trace_block_copy_skip_range(s, task->offset, task->bytes); offset = task_end(task); bytes = end - offset; + g_free(task); continue; } task->zeroes = ret & BDRV_BLOCK_ZERO; -- 2.26.2 The following changes since commit 1214d55d1c41fbab3a9973a05085b8760647e411: Merge remote-tracking branch 'remotes/nvme/tags/nvme-next-pull-request' into staging (2021-02-09 13:24:37 +0000) are available in the Git repository at: https://gitlab.com/stefanha/qemu.git tags/block-pull-request for you to fetch changes up to eb847c42296497978942f738cd41dc29a35a49b2: docs: fix Parallels Image "dirty bitmap" section (2021-02-10 09:23:28 +0000) ---------------------------------------------------------------- Pull request v4: * Add PCI_EXPRESS Kconfig dependency to fix s390x in "multi-process: setup PCI host bridge for remote device" [Philippe and Thomas] ---------------------------------------------------------------- Denis V. Lunev (1): docs: fix Parallels Image "dirty bitmap" section Elena Ufimtseva (8): multi-process: add configure and usage information io: add qio_channel_writev_full_all helper io: add qio_channel_readv_full_all_eof & qio_channel_readv_full_all helpers multi-process: define MPQemuMsg format and transmission functions multi-process: introduce proxy object multi-process: add proxy communication functions multi-process: Forward PCI config space acceses to the remote process multi-process: perform device reset in the remote process Jagannathan Raman (11): memory: alloc RAM from file at offset multi-process: Add config option for multi-process QEMU multi-process: setup PCI host bridge for remote device multi-process: setup a machine object for remote device process multi-process: Initialize message handler in remote device multi-process: Associate fd of a PCIDevice with its object multi-process: setup memory manager for remote device multi-process: PCI BAR read/write handling for proxy & remote endpoints multi-process: Synchronize remote memory multi-process: create IOHUB object to handle irq multi-process: Retrieve PCI info from remote process John G Johnson (1): multi-process: add the concept description to docs/devel/qemu-multiprocess Stefan Hajnoczi (6): .github: point Repo Lockdown bot to GitLab repo gitmodules: use GitLab repos instead of qemu.org gitlab-ci: remove redundant GitLab repo URL command docs: update README to use GitLab repo URLs pc-bios: update mirror URLs to GitLab get_maintainer: update repo URL to GitLab MAINTAINERS | 24 + README.rst | 4 +- docs/devel/index.rst | 1 + docs/devel/multi-process.rst | 966 ++++++++++++++++++++++ docs/system/index.rst | 1 + docs/system/multi-process.rst | 64 ++ docs/interop/parallels.txt | 2 +- configure | 10 + meson.build | 5 +- hw/remote/trace.h | 1 + include/exec/memory.h | 2 + include/exec/ram_addr.h | 4 +- include/hw/pci-host/remote.h | 30 + include/hw/pci/pci_ids.h | 3 + include/hw/remote/iohub.h | 42 + include/hw/remote/machine.h | 38 + include/hw/remote/memory.h | 19 + include/hw/remote/mpqemu-link.h | 99 +++ include/hw/remote/proxy-memory-listener.h | 28 + include/hw/remote/proxy.h | 48 ++ include/io/channel.h | 78 ++ include/qemu/mmap-alloc.h | 4 +- include/sysemu/iothread.h | 6 + backends/hostmem-memfd.c | 2 +- hw/misc/ivshmem.c | 3 +- hw/pci-host/remote.c | 75 ++ hw/remote/iohub.c | 119 +++ hw/remote/machine.c | 80 ++ hw/remote/memory.c | 65 ++ hw/remote/message.c | 230 ++++++ hw/remote/mpqemu-link.c | 267 ++++++ hw/remote/proxy-memory-listener.c | 227 +++++ hw/remote/proxy.c | 379 +++++++++ hw/remote/remote-obj.c | 203 +++++ io/channel.c | 116 ++- iothread.c | 6 + softmmu/memory.c | 3 +- softmmu/physmem.c | 12 +- util/mmap-alloc.c | 8 +- util/oslib-posix.c | 2 +- .github/lockdown.yml | 8 +- .gitlab-ci.yml | 1 - .gitmodules | 44 +- Kconfig.host | 4 + hw/Kconfig | 1 + hw/meson.build | 1 + hw/pci-host/Kconfig | 3 + hw/pci-host/meson.build | 1 + hw/remote/Kconfig | 4 + hw/remote/meson.build | 13 + hw/remote/trace-events | 4 + pc-bios/README | 4 +- scripts/get_maintainer.pl | 2 +- 53 files changed, 3296 insertions(+), 70 deletions(-) create mode 100644 docs/devel/multi-process.rst create mode 100644 docs/system/multi-process.rst create mode 100644 hw/remote/trace.h create mode 100644 include/hw/pci-host/remote.h create mode 100644 include/hw/remote/iohub.h create mode 100644 include/hw/remote/machine.h create mode 100644 include/hw/remote/memory.h create mode 100644 include/hw/remote/mpqemu-link.h create mode 100644 include/hw/remote/proxy-memory-listener.h create mode 100644 include/hw/remote/proxy.h create mode 100644 hw/pci-host/remote.c create mode 100644 hw/remote/iohub.c create mode 100644 hw/remote/machine.c create mode 100644 hw/remote/memory.c create mode 100644 hw/remote/message.c create mode 100644 hw/remote/mpqemu-link.c create mode 100644 hw/remote/proxy-memory-listener.c create mode 100644 hw/remote/proxy.c create mode 100644 hw/remote/remote-obj.c create mode 100644 hw/remote/Kconfig create mode 100644 hw/remote/meson.build create mode 100644 hw/remote/trace-events -- 2.29.2 Use the GitLab repo URL as the main repo location in order to reduce load on qemu.org. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20210111115017.156802-2-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- .github/lockdown.yml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/.github/lockdown.yml b/.github/lockdown.yml index XXXXXXX..XXXXXXX 100644 --- a/.github/lockdown.yml +++ b/.github/lockdown.yml @@ -XXX,XX +XXX,XX @@ issues: comment: | Thank you for your interest in the QEMU project. - This repository is a read-only mirror of the project's master - repostories hosted on https://git.qemu.org/git/qemu.git. + This repository is a read-only mirror of the project's repostories hosted + at https://gitlab.com/qemu-project/qemu.git. The project does not process issues filed on GitHub. The project issues are tracked on Launchpad: @@ -XXX,XX +XXX,XX @@ pulls: comment: | Thank you for your interest in the QEMU project. - This repository is a read-only mirror of the project's master - repostories hosted on https://git.qemu.org/git/qemu.git. + This repository is a read-only mirror of the project's repostories hosted + on https://gitlab.com/qemu-project/qemu.git. The project does not process merge requests filed on GitHub. QEMU welcomes contributions of code (either fixing bugs or adding new -- 2.29.2 qemu.org is running out of bandwidth and the QEMU project is moving towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org (they will become mirrors). Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20210111115017.156802-3-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- .gitmodules | 44 ++++++++++++++++++++++---------------------- 1 file changed, 22 insertions(+), 22 deletions(-) diff --git a/.gitmodules b/.gitmodules index XXXXXXX..XXXXXXX 100644 --- a/.gitmodules +++ b/.gitmodules @@ -XXX,XX +XXX,XX @@ [submodule "roms/seabios"] path = roms/seabios - url = https://git.qemu.org/git/seabios.git/ + url = https://gitlab.com/qemu-project/seabios.git/ [submodule "roms/SLOF"] path = roms/SLOF - url = https://git.qemu.org/git/SLOF.git + url = https://gitlab.com/qemu-project/SLOF.git [submodule "roms/ipxe"] path = roms/ipxe - url = https://git.qemu.org/git/ipxe.git + url = https://gitlab.com/qemu-project/ipxe.git [submodule "roms/openbios"] path = roms/openbios - url = https://git.qemu.org/git/openbios.git + url = https://gitlab.com/qemu-project/openbios.git [submodule "roms/qemu-palcode"] path = roms/qemu-palcode - url = https://git.qemu.org/git/qemu-palcode.git + url = https://gitlab.com/qemu-project/qemu-palcode.git [submodule "roms/sgabios"] path = roms/sgabios - url = https://git.qemu.org/git/sgabios.git + url = https://gitlab.com/qemu-project/sgabios.git [submodule "dtc"] path = dtc - url = https://git.qemu.org/git/dtc.git + url = https://gitlab.com/qemu-project/dtc.git [submodule "roms/u-boot"] path = roms/u-boot - url = https://git.qemu.org/git/u-boot.git + url = https://gitlab.com/qemu-project/u-boot.git [submodule "roms/skiboot"] path = roms/skiboot - url = https://git.qemu.org/git/skiboot.git + url = https://gitlab.com/qemu-project/skiboot.git [submodule "roms/QemuMacDrivers"] path = roms/QemuMacDrivers - url = https://git.qemu.org/git/QemuMacDrivers.git + url = https://gitlab.com/qemu-project/QemuMacDrivers.git [submodule "ui/keycodemapdb"] path = ui/keycodemapdb - url = https://git.qemu.org/git/keycodemapdb.git + url = https://gitlab.com/qemu-project/keycodemapdb.git [submodule "capstone"] path = capstone - url = https://git.qemu.org/git/capstone.git + url = https://gitlab.com/qemu-project/capstone.git [submodule "roms/seabios-hppa"] path = roms/seabios-hppa - url = https://git.qemu.org/git/seabios-hppa.git + url = https://gitlab.com/qemu-project/seabios-hppa.git [submodule "roms/u-boot-sam460ex"] path = roms/u-boot-sam460ex - url = https://git.qemu.org/git/u-boot-sam460ex.git + url = https://gitlab.com/qemu-project/u-boot-sam460ex.git [submodule "tests/fp/berkeley-testfloat-3"] path = tests/fp/berkeley-testfloat-3 - url = https://git.qemu.org/git/berkeley-testfloat-3.git + url = https://gitlab.com/qemu-project/berkeley-testfloat-3.git [submodule "tests/fp/berkeley-softfloat-3"] path = tests/fp/berkeley-softfloat-3 - url = https://git.qemu.org/git/berkeley-softfloat-3.git + url = https://gitlab.com/qemu-project/berkeley-softfloat-3.git [submodule "roms/edk2"] path = roms/edk2 - url = https://git.qemu.org/git/edk2.git + url = https://gitlab.com/qemu-project/edk2.git [submodule "slirp"] path = slirp - url = https://git.qemu.org/git/libslirp.git + url = https://gitlab.com/qemu-project/libslirp.git [submodule "roms/opensbi"] path = roms/opensbi - url = https://git.qemu.org/git/opensbi.git + url = https://gitlab.com/qemu-project/opensbi.git [submodule "roms/qboot"] path = roms/qboot - url = https://git.qemu.org/git/qboot.git + url = https://gitlab.com/qemu-project/qboot.git [submodule "meson"] path = meson - url = https://git.qemu.org/git/meson.git + url = https://gitlab.com/qemu-project/meson.git [submodule "roms/vbootrom"] path = roms/vbootrom - url = https://git.qemu.org/git/vbootrom.git + url = https://gitlab.com/qemu-project/vbootrom.git -- 2.29.2 It is no longer necessary to point .gitmodules at GitLab repos when running in GitLab CI since they are now used all the time. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20210111115017.156802-4-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- .gitlab-ci.yml | 1 - 1 file changed, 1 deletion(-) diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml index XXXXXXX..XXXXXXX 100644 --- a/.gitlab-ci.yml +++ b/.gitlab-ci.yml @@ -XXX,XX +XXX,XX @@ include: image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest before_script: - JOBS=$(expr $(nproc) + 1) - - sed -i s,git.qemu.org/git,gitlab.com/qemu-project, .gitmodules script: - mkdir build - cd build -- 2.29.2 qemu.org is running out of bandwidth and the QEMU project is moving towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org (they will become mirrors). Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20210111115017.156802-5-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- README.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.rst b/README.rst index XXXXXXX..XXXXXXX 100644 --- a/README.rst +++ b/README.rst @@ -XXX,XX +XXX,XX @@ The QEMU source code is maintained under the GIT version control system. .. code-block:: shell - git clone https://git.qemu.org/git/qemu.git + git clone https://gitlab.com/qemu-project/qemu.git When submitting patches, one common approach is to use 'git format-patch' and/or 'git send-email' to format & send the mail to the @@ -XXX,XX +XXX,XX @@ The QEMU website is also maintained under source control. .. code-block:: shell - git clone https://git.qemu.org/git/qemu-web.git + git clone https://gitlab.com/qemu-project/qemu-web.git * `<https://www.qemu.org/2017/02/04/the-new-qemu-website-is-up/>`_ -- 2.29.2 qemu.org is running out of bandwidth and the QEMU project is moving towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org (they will become mirrors). Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20210111115017.156802-6-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- pc-bios/README | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/pc-bios/README b/pc-bios/README index XXXXXXX..XXXXXXX 100644 --- a/pc-bios/README +++ b/pc-bios/README @@ -XXX,XX +XXX,XX @@ legacy x86 software to communicate with an attached serial console as if a video card were attached. The master sources reside in a subversion repository at http://sgabios.googlecode.com/svn/trunk. A git mirror is - available at https://git.qemu.org/git/sgabios.git. + available at https://gitlab.com/qemu-project/sgabios.git. - The PXE roms come from the iPXE project. Built with BANNER_TIME 0. Sources available at http://ipxe.org. Vendor:Device ID -> ROM mapping: @@ -XXX,XX +XXX,XX @@ - The u-boot binary for e500 comes from the upstream denx u-boot project where it was compiled using the qemu-ppce500 target. - A git mirror is available at: https://git.qemu.org/git/u-boot.git + A git mirror is available at: https://gitlab.com/qemu-project/u-boot.git The hash used to compile the current version is: 2072e72 - Skiboot (https://github.com/open-power/skiboot/) is an OPAL -- 2.29.2 qemu.org is running out of bandwidth and the QEMU project is moving towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org (they will become mirrors). Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20210111115017.156802-7-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- scripts/get_maintainer.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index XXXXXXX..XXXXXXX 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -XXX,XX +XXX,XX @@ sub vcs_exists { warn("$P: No supported VCS found. Add --nogit to options?\n"); warn("Using a git repository produces better results.\n"); warn("Try latest git repository using:\n"); - warn("git clone https://git.qemu.org/git/qemu.git\n"); + warn("git clone https://gitlab.com/qemu-project/qemu.git\n"); $printed_novcs = 1; } return 0; -- 2.29.2 From: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 02a68adef99f5df6a380bf8fd7b90948777e411c.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 7 + docs/devel/index.rst | 1 + docs/devel/multi-process.rst | 966 +++++++++++++++++++++++++++++++++++ 3 files changed, 974 insertions(+) create mode 100644 docs/devel/multi-process.rst diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ S: Maintained F: hw/semihosting/ F: include/hw/semihosting/ +Multi-process QEMU +M: Elena Ufimtseva <elena.ufimtseva@oracle.com> +M: Jagannathan Raman <jag.raman@oracle.com> +M: John G Johnson <john.g.johnson@oracle.com> +S: Maintained +F: docs/devel/multi-process.rst + Build and test automation ------------------------- Build and test automation diff --git a/docs/devel/index.rst b/docs/devel/index.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/index.rst +++ b/docs/devel/index.rst @@ -XXX,XX +XXX,XX @@ Contents: clocks qom block-coroutine-wrapper + multi-process diff --git a/docs/devel/multi-process.rst b/docs/devel/multi-process.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/devel/multi-process.rst @@ -XXX,XX +XXX,XX @@ +This is the design document for multi-process QEMU. It does not +necessarily reflect the status of the current implementation, which +may lack features or be considerably different from what is described +in this document. This document is still useful as a description of +the goals and general direction of this feature. + +Please refer to the following wiki for latest details: +https://wiki.qemu.org/Features/MultiProcessQEMU + +Multi-process QEMU +=================== + +QEMU is often used as the hypervisor for virtual machines running in the +Oracle cloud. Since one of the advantages of cloud computing is the +ability to run many VMs from different tenants in the same cloud +infrastructure, a guest that compromised its hypervisor could +potentially use the hypervisor's access privileges to access data it is +not authorized for. + +QEMU can be susceptible to security attacks because it is a large, +monolithic program that provides many features to the VMs it services. +Many of these features can be configured out of QEMU, but even a reduced +configuration QEMU has a large amount of code a guest can potentially +attack. Separating QEMU reduces the attack surface by aiding to +limit each component in the system to only access the resources that +it needs to perform its job. + +QEMU services +------------- + +QEMU can be broadly described as providing three main services. One is a +VM control point, where VMs can be created, migrated, re-configured, and +destroyed. A second is to emulate the CPU instructions within the VM, +often accelerated by HW virtualization features such as Intel's VT +extensions. Finally, it provides IO services to the VM by emulating HW +IO devices, such as disk and network devices. + +A multi-process QEMU +~~~~~~~~~~~~~~~~~~~~ + +A multi-process QEMU involves separating QEMU services into separate +host processes. Each of these processes can be given only the privileges +it needs to provide its service, e.g., a disk service could be given +access only to the disk images it provides, and not be allowed to +access other files, or any network devices. An attacker who compromised +this service would not be able to use this exploit to access files or +devices beyond what the disk service was given access to. + +A QEMU control process would remain, but in multi-process mode, will +have no direct interfaces to the VM. During VM execution, it would still +provide the user interface to hot-plug devices or live migrate the VM. + +A first step in creating a multi-process QEMU is to separate IO services +from the main QEMU program, which would continue to provide CPU +emulation. i.e., the control process would also be the CPU emulation +process. In a later phase, CPU emulation could be separated from the +control process. + +Separating IO services +---------------------- + +Separating IO services into individual host processes is a good place to +begin for a couple of reasons. One is the sheer number of IO devices QEMU +can emulate provides a large surface of interfaces which could potentially +be exploited, and, indeed, have been a source of exploits in the past. +Another is the modular nature of QEMU device emulation code provides +interface points where the QEMU functions that perform device emulation +can be separated from the QEMU functions that manage the emulation of +guest CPU instructions. The devices emulated in the separate process are +referred to as remote devices. + +QEMU device emulation +~~~~~~~~~~~~~~~~~~~~~ + +QEMU uses an object oriented SW architecture for device emulation code. +Configured objects are all compiled into the QEMU binary, then objects +are instantiated by name when used by the guest VM. For example, the +code to emulate a device named "foo" is always present in QEMU, but its +instantiation code is only run when the device is included in the target +VM. (e.g., via the QEMU command line as *-device foo*) + +The object model is hierarchical, so device emulation code names its +parent object (such as "pci-device" for a PCI device) and QEMU will +instantiate a parent object before calling the device's instantiation +code. + +Current separation models +~~~~~~~~~~~~~~~~~~~~~~~~~ + +In order to separate the device emulation code from the CPU emulation +code, the device object code must run in a different process. There are +a couple of existing QEMU features that can run emulation code +separately from the main QEMU process. These are examined below. + +vhost user model +^^^^^^^^^^^^^^^^ + +Virtio guest device drivers can be connected to vhost user applications +in order to perform their IO operations. This model uses special virtio +device drivers in the guest and vhost user device objects in QEMU, but +once the QEMU vhost user code has configured the vhost user application, +mission-mode IO is performed by the application. The vhost user +application is a daemon process that can be contacted via a known UNIX +domain socket. + +vhost socket +'''''''''''' + +As mentioned above, one of the tasks of the vhost device object within +QEMU is to contact the vhost application and send it configuration +information about this device instance. As part of the configuration +process, the application can also be sent other file descriptors over +the socket, which then can be used by the vhost user application in +various ways, some of which are described below. + +vhost MMIO store acceleration +''''''''''''''''''''''''''''' + +VMs are often run using HW virtualization features via the KVM kernel +driver. This driver allows QEMU to accelerate the emulation of guest CPU +instructions by running the guest in a virtual HW mode. When the guest +executes instructions that cannot be executed by virtual HW mode, +execution returns to the KVM driver so it can inform QEMU to emulate the +instructions in SW. + +One of the events that can cause a return to QEMU is when a guest device +driver accesses an IO location. QEMU then dispatches the memory +operation to the corresponding QEMU device object. In the case of a +vhost user device, the memory operation would need to be sent over a +socket to the vhost application. This path is accelerated by the QEMU +virtio code by setting up an eventfd file descriptor that the vhost +application can directly receive MMIO store notifications from the KVM +driver, instead of needing them to be sent to the QEMU process first. + +vhost interrupt acceleration +'''''''''''''''''''''''''''' + +Another optimization used by the vhost application is the ability to +directly inject interrupts into the VM via the KVM driver, again, +bypassing the need to send the interrupt back to the QEMU process first. +The QEMU virtio setup code configures the KVM driver with an eventfd +that triggers the device interrupt in the guest when the eventfd is +written. This irqfd file descriptor is then passed to the vhost user +application program. + +vhost access to guest memory +'''''''''''''''''''''''''''' + +The vhost application is also allowed to directly access guest memory, +instead of needing to send the data as messages to QEMU. This is also +done with file descriptors sent to the vhost user application by QEMU. +These descriptors can be passed to ``mmap()`` by the vhost application +to map the guest address space into the vhost application. + +IOMMUs introduce another level of complexity, since the address given to +the guest virtio device to DMA to or from is not a guest physical +address. This case is handled by having vhost code within QEMU register +as a listener for IOMMU mapping changes. The vhost application maintains +a cache of IOMMMU translations: sending translation requests back to +QEMU on cache misses, and in turn receiving flush requests from QEMU +when mappings are purged. + +applicability to device separation +'''''''''''''''''''''''''''''''''' + +Much of the vhost model can be re-used by separated device emulation. In +particular, the ideas of using a socket between QEMU and the device +emulation application, using a file descriptor to inject interrupts into +the VM via KVM, and allowing the application to ``mmap()`` the guest +should be re used. + +There are, however, some notable differences between how a vhost +application works and the needs of separated device emulation. The most +basic is that vhost uses custom virtio device drivers which always +trigger IO with MMIO stores. A separated device emulation model must +work with existing IO device models and guest device drivers. MMIO loads +break vhost store acceleration since they are synchronous - guest +progress cannot continue until the load has been emulated. By contrast, +stores are asynchronous, the guest can continue after the store event +has been sent to the vhost application. + +Another difference is that in the vhost user model, a single daemon can +support multiple QEMU instances. This is contrary to the security regime +desired, in which the emulation application should only be allowed to +access the files or devices the VM it's running on behalf of can access. +#### qemu-io model + +Qemu-io is a test harness used to test changes to the QEMU block backend +object code. (e.g., the code that implements disk images for disk driver +emulation) Qemu-io is not a device emulation application per se, but it +does compile the QEMU block objects into a separate binary from the main +QEMU one. This could be useful for disk device emulation, since its +emulation applications will need to include the QEMU block objects. + +New separation model based on proxy objects +------------------------------------------- + +A different model based on proxy objects in the QEMU program +communicating with remote emulation programs could provide separation +while minimizing the changes needed to the device emulation code. The +rest of this section is a discussion of how a proxy object model would +work. + +Remote emulation processes +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The remote emulation process will run the QEMU object hierarchy without +modification. The device emulation objects will be also be based on the +QEMU code, because for anything but the simplest device, it would not be +a tractable to re-implement both the object model and the many device +backends that QEMU has. + +The processes will communicate with the QEMU process over UNIX domain +sockets. The processes can be executed either as standalone processes, +or be executed by QEMU. In both cases, the host backends the emulation +processes will provide are specified on its command line, as they would +be for QEMU. For example: + +:: + + disk-proc -blockdev driver=file,node-name=file0,filename=disk-file0 \ + -blockdev driver=qcow2,node-name=drive0,file=file0 + +would indicate process *disk-proc* uses a qcow2 emulated disk named +*file0* as its backend. + +Emulation processes may emulate more than one guest controller. A common +configuration might be to put all controllers of the same device class +(e.g., disk, network, etc.) in a single process, so that all backends of +the same type can be managed by a single QMP monitor. + +communication with QEMU +^^^^^^^^^^^^^^^^^^^^^^^ + +The first argument to the remote emulation process will be a Unix domain +socket that connects with the Proxy object. This is a required argument. + +:: + + disk-proc <socket number> <backend list> + +remote process QMP monitor +^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Remote emulation processes can be monitored via QMP, similar to QEMU +itself. The QMP monitor socket is specified the same as for a QEMU +process: + +:: + + disk-proc -qmp unix:/tmp/disk-mon,server + +can be monitored over the UNIX socket path */tmp/disk-mon*. + +QEMU command line +~~~~~~~~~~~~~~~~~ + +Each remote device emulated in a remote process on the host is +represented as a *-device* of type *pci-proxy-dev*. A socket +sub-option to this option specifies the Unix socket that connects +to the remote process. An *id* sub-option is required, and it should +be the same id as used in the remote process. + +:: + + qemu-system-x86_64 ... -device pci-proxy-dev,id=lsi0,socket=3 + +can be used to add a device emulated in a remote process + + +QEMU management of remote processes +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +QEMU is not aware of the type of type of the remote PCI device. It is +a pass through device as far as QEMU is concerned. + +communication with emulation process +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +primary channel +''''''''''''''' + +The primary channel (referred to as com in the code) is used to bootstrap +the remote process. It is also used to pass on device-agnostic commands +like reset. + +per-device channels +''''''''''''''''''' + +Each remote device communicates with QEMU using a dedicated communication +channel. The proxy object sets up this channel using the primary +channel during its initialization. + +QEMU device proxy objects +~~~~~~~~~~~~~~~~~~~~~~~~~ + +QEMU has an object model based on sub-classes inherited from the +"object" super-class. The sub-classes that are of interest here are the +"device" and "bus" sub-classes whose child sub-classes make up the +device tree of a QEMU emulated system. + +The proxy object model will use device proxy objects to replace the +device emulation code within the QEMU process. These objects will live +in the same place in the object and bus hierarchies as the objects they +replace. i.e., the proxy object for an LSI SCSI controller will be a +sub-class of the "pci-device" class, and will have the same PCI bus +parent and the same SCSI bus child objects as the LSI controller object +it replaces. + +It is worth noting that the same proxy object is used to mediate with +all types of remote PCI devices. + +object initialization +^^^^^^^^^^^^^^^^^^^^^ + +The Proxy device objects are initialized in the exact same manner in +which any other QEMU device would be initialized. + +In addition, the Proxy objects perform the following two tasks: +- Parses the "socket" sub option and connects to the remote process +using this channel +- Uses the "id" sub-option to connect to the emulated device on the +separate process + +class\_init +''''''''''' + +The ``class_init()`` method of a proxy object will, in general behave +similarly to the object it replaces, including setting any static +properties and methods needed by the proxy. + +instance\_init / realize +'''''''''''''''''''''''' + +The ``instance_init()`` and ``realize()`` functions would only need to +perform tasks related to being a proxy, such are registering its own +MMIO handlers, or creating a child bus that other proxy devices can be +attached to later. + +Other tasks will be device-specific. For example, PCI device objects +will initialize the PCI config space in order to make a valid PCI device +tree within the QEMU process. + +address space registration +^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Most devices are driven by guest device driver accesses to IO addresses +or ports. The QEMU device emulation code uses QEMU's memory region +function calls (such as ``memory_region_init_io()``) to add callback +functions that QEMU will invoke when the guest accesses the device's +areas of the IO address space. When a guest driver does access the +device, the VM will exit HW virtualization mode and return to QEMU, +which will then lookup and execute the corresponding callback function. + +A proxy object would need to mirror the memory region calls the actual +device emulator would perform in its initialization code, but with its +own callbacks. When invoked by QEMU as a result of a guest IO operation, +they will forward the operation to the device emulation process. + +PCI config space +^^^^^^^^^^^^^^^^ + +PCI devices also have a configuration space that can be accessed by the +guest driver. Guest accesses to this space is not handled by the device +emulation object, but by its PCI parent object. Much of this space is +read-only, but certain registers (especially BAR and MSI-related ones) +need to be propagated to the emulation process. + +PCI parent proxy +'''''''''''''''' + +One way to propagate guest PCI config accesses is to create a +"pci-device-proxy" class that can serve as the parent of a PCI device +proxy object. This class's parent would be "pci-device" and it would +override the PCI parent's ``config_read()`` and ``config_write()`` +methods with ones that forward these operations to the emulation +program. + +interrupt receipt +^^^^^^^^^^^^^^^^^ + +A proxy for a device that generates interrupts will need to create a +socket to receive interrupt indications from the emulation process. An +incoming interrupt indication would then be sent up to its bus parent to +be injected into the guest. For example, a PCI device object may use +``pci_set_irq()``. + +live migration +^^^^^^^^^^^^^^ + +The proxy will register to save and restore any *vmstate* it needs over +a live migration event. The device proxy does not need to manage the +remote device's *vmstate*; that will be handled by the remote process +proxy (see below). + +QEMU remote device operation +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Generic device operations, such as DMA, will be performed by the remote +process proxy by sending messages to the remote process. + +DMA operations +^^^^^^^^^^^^^^ + +DMA operations would be handled much like vhost applications do. One of +the initial messages sent to the emulation process is a guest memory +table. Each entry in this table consists of a file descriptor and size +that the emulation process can ``mmap()`` to directly access guest +memory, similar to ``vhost_user_set_mem_table()``. Note guest memory +must be backed by file descriptors, such as when QEMU is given the +*-mem-path* command line option. + +IOMMU operations +^^^^^^^^^^^^^^^^ + +When the emulated system includes an IOMMU, the remote process proxy in +QEMU will need to create a socket for IOMMU requests from the emulation +process. It will handle those requests with an +``address_space_get_iotlb_entry()`` call. In order to handle IOMMU +unmaps, the remote process proxy will also register as a listener on the +device's DMA address space. When an IOMMU memory region is created +within the DMA address space, an IOMMU notifier for unmaps will be added +to the memory region that will forward unmaps to the emulation process +over the IOMMU socket. + +device hot-plug via QMP +^^^^^^^^^^^^^^^^^^^^^^^ + +An QMP "device\_add" command can add a device emulated by a remote +process. It will also have "rid" option to the command, just as the +*-device* command line option does. The remote process may either be one +started at QEMU startup, or be one added by the "add-process" QMP +command described above. In either case, the remote process proxy will +forward the new device's JSON description to the corresponding emulation +process. + +live migration +^^^^^^^^^^^^^^ + +The remote process proxy will also register for live migration +notifications with ``vmstate_register()``. When called to save state, +the proxy will send the remote process a secondary socket file +descriptor to save the remote process's device *vmstate* over. The +incoming byte stream length and data will be saved as the proxy's +*vmstate*. When the proxy is resumed on its new host, this *vmstate* +will be extracted, and a secondary socket file descriptor will be sent +to the new remote process through which it receives the *vmstate* in +order to restore the devices there. + +device emulation in remote process +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The parts of QEMU that the emulation program will need include the +object model; the memory emulation objects; the device emulation objects +of the targeted device, and any dependent devices; and, the device's +backends. It will also need code to setup the machine environment, +handle requests from the QEMU process, and route machine-level requests +(such as interrupts or IOMMU mappings) back to the QEMU process. + +initialization +^^^^^^^^^^^^^^ + +The process initialization sequence will follow the same sequence +followed by QEMU. It will first initialize the backend objects, then +device emulation objects. The JSON descriptions sent by the QEMU process +will drive which objects need to be created. + +- address spaces + +Before the device objects are created, the initial address spaces and +memory regions must be configured with ``memory_map_init()``. This +creates a RAM memory region object (*system\_memory*) and an IO memory +region object (*system\_io*). + +- RAM + +RAM memory region creation will follow how ``pc_memory_init()`` creates +them, but must use ``memory_region_init_ram_from_fd()`` instead of +``memory_region_allocate_system_memory()``. The file descriptors needed +will be supplied by the guest memory table from above. Those RAM regions +would then be added to the *system\_memory* memory region with +``memory_region_add_subregion()``. + +- PCI + +IO initialization will be driven by the JSON descriptions sent from the +QEMU process. For a PCI device, a PCI bus will need to be created with +``pci_root_bus_new()``, and a PCI memory region will need to be created +and added to the *system\_memory* memory region with +``memory_region_add_subregion_overlap()``. The overlap version is +required for architectures where PCI memory overlaps with RAM memory. + +MMIO handling +^^^^^^^^^^^^^ + +The device emulation objects will use ``memory_region_init_io()`` to +install their MMIO handlers, and ``pci_register_bar()`` to associate +those handlers with a PCI BAR, as they do within QEMU currently. + +In order to use ``address_space_rw()`` in the emulation process to +handle MMIO requests from QEMU, the PCI physical addresses must be the +same in the QEMU process and the device emulation process. In order to +accomplish that, guest BAR programming must also be forwarded from QEMU +to the emulation process. + +interrupt injection +^^^^^^^^^^^^^^^^^^^ + +When device emulation wants to inject an interrupt into the VM, the +request climbs the device's bus object hierarchy until the point where a +bus object knows how to signal the interrupt to the guest. The details +depend on the type of interrupt being raised. + +- PCI pin interrupts + +On x86 systems, there is an emulated IOAPIC object attached to the root +PCI bus object, and the root PCI object forwards interrupt requests to +it. The IOAPIC object, in turn, calls the KVM driver to inject the +corresponding interrupt into the VM. The simplest way to handle this in +an emulation process would be to setup the root PCI bus driver (via +``pci_bus_irqs()``) to send a interrupt request back to the QEMU +process, and have the device proxy object reflect it up the PCI tree +there. + +- PCI MSI/X interrupts + +PCI MSI/X interrupts are implemented in HW as DMA writes to a +CPU-specific PCI address. In QEMU on x86, a KVM APIC object receives +these DMA writes, then calls into the KVM driver to inject the interrupt +into the VM. A simple emulation process implementation would be to send +the MSI DMA address from QEMU as a message at initialization, then +install an address space handler at that address which forwards the MSI +message back to QEMU. + +DMA operations +^^^^^^^^^^^^^^ + +When a emulation object wants to DMA into or out of guest memory, it +first must use dma\_memory\_map() to convert the DMA address to a local +virtual address. The emulation process memory region objects setup above +will be used to translate the DMA address to a local virtual address the +device emulation code can access. + +IOMMU +^^^^^ + +When an IOMMU is in use in QEMU, DMA translation uses IOMMU memory +regions to translate the DMA address to a guest physical address before +that physical address can be translated to a local virtual address. The +emulation process will need similar functionality. + +- IOTLB cache + +The emulation process will maintain a cache of recent IOMMU translations +(the IOTLB). When the translate() callback of an IOMMU memory region is +invoked, the IOTLB cache will be searched for an entry that will map the +DMA address to a guest PA. On a cache miss, a message will be sent back +to QEMU requesting the corresponding translation entry, which be both be +used to return a guest address and be added to the cache. + +- IOTLB purge + +The IOMMU emulation will also need to act on unmap requests from QEMU. +These happen when the guest IOMMU driver purges an entry from the +guest's translation table. + +live migration +^^^^^^^^^^^^^^ + +When a remote process receives a live migration indication from QEMU, it +will set up a channel using the received file descriptor with +``qio_channel_socket_new_fd()``. This channel will be used to create a +*QEMUfile* that can be passed to ``qemu_save_device_state()`` to send +the process's device state back to QEMU. This method will be reversed on +restore - the channel will be passed to ``qemu_loadvm_state()`` to +restore the device state. + +Accelerating device emulation +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The messages that are required to be sent between QEMU and the emulation +process can add considerable latency to IO operations. The optimizations +described below attempt to ameliorate this effect by allowing the +emulation process to communicate directly with the kernel KVM driver. +The KVM file descriptors created would be passed to the emulation process +via initialization messages, much like the guest memory table is done. +#### MMIO acceleration + +Vhost user applications can receive guest virtio driver stores directly +from KVM. The issue with the eventfd mechanism used by vhost user is +that it does not pass any data with the event indication, so it cannot +handle guest loads or guest stores that carry store data. This concept +could, however, be expanded to cover more cases. + +The expanded idea would require a new type of KVM device: +*KVM\_DEV\_TYPE\_USER*. This device has two file descriptors: a master +descriptor that QEMU can use for configuration, and a slave descriptor +that the emulation process can use to receive MMIO notifications. QEMU +would create both descriptors using the KVM driver, and pass the slave +descriptor to the emulation process via an initialization message. + +data structures +^^^^^^^^^^^^^^^ + +- guest physical range + +The guest physical range structure describes the address range that a +device will respond to. It includes the base and length of the range, as +well as which bus the range resides on (e.g., on an x86machine, it can +specify whether the range refers to memory or IO addresses). + +A device can have multiple physical address ranges it responds to (e.g., +a PCI device can have multiple BARs), so the structure will also include +an enumerated identifier to specify which of the device's ranges is +being referred to. + ++--------+----------------------------+ +| Name | Description | ++========+============================+ +| addr | range base address | ++--------+----------------------------+ +| len | range length | ++--------+----------------------------+ +| bus | addr type (memory or IO) | ++--------+----------------------------+ +| id | range ID (e.g., PCI BAR) | ++--------+----------------------------+ + +- MMIO request structure + +This structure describes an MMIO operation. It includes which guest +physical range the MMIO was within, the offset within that range, the +MMIO type (e.g., load or store), and its length and data. It also +includes a sequence number that can be used to reply to the MMIO, and +the CPU that issued the MMIO. + ++----------+------------------------+ +| Name | Description | ++==========+========================+ +| rid | range MMIO is within | ++----------+------------------------+ +| offset | offset withing *rid* | ++----------+------------------------+ +| type | e.g., load or store | ++----------+------------------------+ +| len | MMIO length | ++----------+------------------------+ +| data | store data | ++----------+------------------------+ +| seq | sequence ID | ++----------+------------------------+ + +- MMIO request queues + +MMIO request queues are FIFO arrays of MMIO request structures. There +are two queues: pending queue is for MMIOs that haven't been read by the +emulation program, and the sent queue is for MMIOs that haven't been +acknowledged. The main use of the second queue is to validate MMIO +replies from the emulation program. + +- scoreboard + +Each CPU in the VM is emulated in QEMU by a separate thread, so multiple +MMIOs may be waiting to be consumed by an emulation program and multiple +threads may be waiting for MMIO replies. The scoreboard would contain a +wait queue and sequence number for the per-CPU threads, allowing them to +be individually woken when the MMIO reply is received from the emulation +program. It also tracks the number of posted MMIO stores to the device +that haven't been replied to, in order to satisfy the PCI constraint +that a load to a device will not complete until all previous stores to +that device have been completed. + +- device shadow memory + +Some MMIO loads do not have device side-effects. These MMIOs can be +completed without sending a MMIO request to the emulation program if the +emulation program shares a shadow image of the device's memory image +with the KVM driver. + +The emulation program will ask the KVM driver to allocate memory for the +shadow image, and will then use ``mmap()`` to directly access it. The +emulation program can control KVM access to the shadow image by sending +KVM an access map telling it which areas of the image have no +side-effects (and can be completed immediately), and which require a +MMIO request to the emulation program. The access map can also inform +the KVM drive which size accesses are allowed to the image. + +master descriptor +^^^^^^^^^^^^^^^^^ + +The master descriptor is used by QEMU to configure the new KVM device. +The descriptor would be returned by the KVM driver when QEMU issues a +*KVM\_CREATE\_DEVICE* ``ioctl()`` with a *KVM\_DEV\_TYPE\_USER* type. + +KVM\_DEV\_TYPE\_USER device ops + + +The *KVM\_DEV\_TYPE\_USER* operations vector will be registered by a +``kvm_register_device_ops()`` call when the KVM system in initialized by +``kvm_init()``. These device ops are called by the KVM driver when QEMU +executes certain ``ioctl()`` operations on its KVM file descriptor. They +include: + +- create + +This routine is called when QEMU issues a *KVM\_CREATE\_DEVICE* +``ioctl()`` on its per-VM file descriptor. It will allocate and +initialize a KVM user device specific data structure, and assign the +*kvm\_device* private field to it. + +- ioctl + +This routine is invoked when QEMU issues an ``ioctl()`` on the master +descriptor. The ``ioctl()`` commands supported are defined by the KVM +device type. *KVM\_DEV\_TYPE\_USER* ones will need several commands: + +*KVM\_DEV\_USER\_SLAVE\_FD* creates the slave file descriptor that will +be passed to the device emulation program. Only one slave can be created +by each master descriptor. The file operations performed by this +descriptor are described below. + +The *KVM\_DEV\_USER\_PA\_RANGE* command configures a guest physical +address range that the slave descriptor will receive MMIO notifications +for. The range is specified by a guest physical range structure +argument. For buses that assign addresses to devices dynamically, this +command can be executed while the guest is running, such as the case +when a guest changes a device's PCI BAR registers. + +*KVM\_DEV\_USER\_PA\_RANGE* will use ``kvm_io_bus_register_dev()`` to +register *kvm\_io\_device\_ops* callbacks to be invoked when the guest +performs a MMIO operation within the range. When a range is changed, +``kvm_io_bus_unregister_dev()`` is used to remove the previous +instantiation. + +*KVM\_DEV\_USER\_TIMEOUT* will configure a timeout value that specifies +how long KVM will wait for the emulation process to respond to a MMIO +indication. + +- destroy + +This routine is called when the VM instance is destroyed. It will need +to destroy the slave descriptor; and free any memory allocated by the +driver, as well as the *kvm\_device* structure itself. + +slave descriptor +^^^^^^^^^^^^^^^^ + +The slave descriptor will have its own file operations vector, which +responds to system calls on the descriptor performed by the device +emulation program. + +- read + +A read returns any pending MMIO requests from the KVM driver as MMIO +request structures. Multiple structures can be returned if there are +multiple MMIO operations pending. The MMIO requests are moved from the +pending queue to the sent queue, and if there are threads waiting for +space in the pending to add new MMIO operations, they will be woken +here. + +- write + +A write also consists of a set of MMIO requests. They are compared to +the MMIO requests in the sent queue. Matches are removed from the sent +queue, and any threads waiting for the reply are woken. If a store is +removed, then the number of posted stores in the per-CPU scoreboard is +decremented. When the number is zero, and a non side-effect load was +waiting for posted stores to complete, the load is continued. + +- ioctl + +There are several ioctl()s that can be performed on the slave +descriptor. + +A *KVM\_DEV\_USER\_SHADOW\_SIZE* ``ioctl()`` causes the KVM driver to +allocate memory for the shadow image. This memory can later be +``mmap()``\ ed by the emulation process to share the emulation's view of +device memory with the KVM driver. + +A *KVM\_DEV\_USER\_SHADOW\_CTRL* ``ioctl()`` controls access to the +shadow image. It will send the KVM driver a shadow control map, which +specifies which areas of the image can complete guest loads without +sending the load request to the emulation program. It will also specify +the size of load operations that are allowed. + +- poll + +An emulation program will use the ``poll()`` call with a *POLLIN* flag +to determine if there are MMIO requests waiting to be read. It will +return if the pending MMIO request queue is not empty. + +- mmap + +This call allows the emulation program to directly access the shadow +image allocated by the KVM driver. As device emulation updates device +memory, changes with no side-effects will be reflected in the shadow, +and the KVM driver can satisfy guest loads from the shadow image without +needing to wait for the emulation program. + +kvm\_io\_device ops +^^^^^^^^^^^^^^^^^^^ + +Each KVM per-CPU thread can handle MMIO operation on behalf of the guest +VM. KVM will use the MMIO's guest physical address to search for a +matching *kvm\_io\_device* to see if the MMIO can be handled by the KVM +driver instead of exiting back to QEMU. If a match is found, the +corresponding callback will be invoked. + +- read + +This callback is invoked when the guest performs a load to the device. +Loads with side-effects must be handled synchronously, with the KVM +driver putting the QEMU thread to sleep waiting for the emulation +process reply before re-starting the guest. Loads that do not have +side-effects may be optimized by satisfying them from the shadow image, +if there are no outstanding stores to the device by this CPU. PCI memory +ordering demands that a load cannot complete before all older stores to +the same device have been completed. + +- write + +Stores can be handled asynchronously unless the pending MMIO request +queue is full. In this case, the QEMU thread must sleep waiting for +space in the queue. Stores will increment the number of posted stores in +the per-CPU scoreboard, in order to implement the PCI ordering +constraint above. + +interrupt acceleration +^^^^^^^^^^^^^^^^^^^^^^ + +This performance optimization would work much like a vhost user +application does, where the QEMU process sets up *eventfds* that cause +the device's corresponding interrupt to be triggered by the KVM driver. +These irq file descriptors are sent to the emulation process at +initialization, and are used when the emulation code raises a device +interrupt. + +intx acceleration +''''''''''''''''' + +Traditional PCI pin interrupts are level based, so, in addition to an +irq file descriptor, a re-sampling file descriptor needs to be sent to +the emulation program. This second file descriptor allows multiple +devices sharing an irq to be notified when the interrupt has been +acknowledged by the guest, so they can re-trigger the interrupt if their +device has not de-asserted its interrupt. + +intx irq descriptor + + +The irq descriptors are created by the proxy object +``using event_notifier_init()`` to create the irq and re-sampling +*eventds*, and ``kvm_vm_ioctl(KVM_IRQFD)`` to bind them to an interrupt. +The interrupt route can be found with +``pci_device_route_intx_to_irq()``. + +intx routing changes + + +Intx routing can be changed when the guest programs the APIC the device +pin is connected to. The proxy object in QEMU will use +``pci_device_set_intx_routing_notifier()`` to be informed of any guest +changes to the route. This handler will broadly follow the VFIO +interrupt logic to change the route: de-assigning the existing irq +descriptor from its route, then assigning it the new route. (see +``vfio_intx_update()``) + +MSI/X acceleration +'''''''''''''''''' + +MSI/X interrupts are sent as DMA transactions to the host. The interrupt +data contains a vector that is programmed by the guest, A device may have +multiple MSI interrupts associated with it, so multiple irq descriptors +may need to be sent to the emulation program. + +MSI/X irq descriptor + + +This case will also follow the VFIO example. For each MSI/X interrupt, +an *eventfd* is created, a virtual interrupt is allocated by +``kvm_irqchip_add_msi_route()``, and the virtual interrupt is bound to +the eventfd with ``kvm_irqchip_add_irqfd_notifier()``. + +MSI/X config space changes + + +The guest may dynamically update several MSI-related tables in the +device's PCI config space. These include per-MSI interrupt enables and +vector data. Additionally, MSIX tables exist in device memory space, not +config space. Much like the BAR case above, the proxy object must look +at guest config space programming to keep the MSI interrupt state +consistent between QEMU and the emulation program. + +-------------- + +Disaggregated CPU emulation +--------------------------- + +After IO services have been disaggregated, a second phase would be to +separate a process to handle CPU instruction emulation from the main +QEMU control function. There are no object separation points for this +code, so the first task would be to create one. + +Host access controls +-------------------- + +Separating QEMU relies on the host OS's access restriction mechanisms to +enforce that the differing processes can only access the objects they +are entitled to. There are a couple types of mechanisms usually provided +by general purpose OSs. + +Discretionary access control +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Discretionary access control allows each user to control who can access +their files. In Linux, this type of control is usually too coarse for +QEMU separation, since it only provides three separate access controls: +one for the same user ID, the second for users IDs with the same group +ID, and the third for all other user IDs. Each device instance would +need a separate user ID to provide access control, which is likely to be +unwieldy for dynamically created VMs. + +Mandatory access control +~~~~~~~~~~~~~~~~~~~~~~~~ + +Mandatory access control allows the OS to add an additional set of +controls on top of discretionary access for the OS to control. It also +adds other attributes to processes and files such as types, roles, and +categories, and can establish rules for how processes and files can +interact. + +Type enforcement +^^^^^^^^^^^^^^^^ + +Type enforcement assigns a *type* attribute to processes and files, and +allows rules to be written on what operations a process with a given +type can perform on a file with a given type. QEMU separation could take +advantage of type enforcement by running the emulation processes with +different types, both from the main QEMU process, and from the emulation +processes of different classes of devices. + +For example, guest disk images and disk emulation processes could have +types separate from the main QEMU process and non-disk emulation +processes, and the type rules could prevent processes other than disk +emulation ones from accessing guest disk images. Similarly, network +emulation processes can have a type separate from the main QEMU process +and non-network emulation process, and only that type can access the +host tun/tap device used to provide guest networking. + +Category enforcement +^^^^^^^^^^^^^^^^^^^^ + +Category enforcement assigns a set of numbers within a given range to +the process or file. The process is granted access to the file if the +process's set is a superset of the file's set. This enforcement can be +used to separate multiple instances of devices in the same class. + +For example, if there are multiple disk devices provides to a guest, +each device emulation process could be provisioned with a separate +category. The different device emulation processes would not be able to +access each other's backing disk images. + +Alternatively, categories could be used in lieu of the type enforcement +scheme described above. In this scenario, different categories would be +used to prevent device emulation processes in different classes from +accessing resources assigned to other classes. -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> Adds documentation explaining the command-line arguments needed to use multi-process. Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 49f757a84e5dd6fae14b22544897d1124c5fdbad.1611938319.git.jag.raman@oracle.com [Move orphan docs/multi-process.rst document into docs/system/ and add it to index.rst to prevent Sphinx "document isn't included in any toctree" error. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 1 + docs/system/index.rst | 1 + docs/system/multi-process.rst | 64 +++++++++++++++++++++++++++++++++++ 3 files changed, 66 insertions(+) create mode 100644 docs/system/multi-process.rst diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Jagannathan Raman <jag.raman@oracle.com> M: John G Johnson <john.g.johnson@oracle.com> S: Maintained F: docs/devel/multi-process.rst +F: docs/system/multi-process.rst Build and test automation ------------------------- diff --git a/docs/system/index.rst b/docs/system/index.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/index.rst +++ b/docs/system/index.rst @@ -XXX,XX +XXX,XX @@ Contents: pr-manager targets security + multi-process deprecated removed-features build-platforms diff --git a/docs/system/multi-process.rst b/docs/system/multi-process.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/system/multi-process.rst @@ -XXX,XX +XXX,XX @@ +Multi-process QEMU +================== + +This document describes how to configure and use multi-process qemu. +For the design document refer to docs/devel/qemu-multiprocess. + +1) Configuration +---------------- + +multi-process is enabled by default for targets that enable KVM + + +2) Usage +-------- + +Multi-process QEMU requires an orchestrator to launch. + +Following is a description of command-line used to launch mpqemu. + +* Orchestrator: + + - The Orchestrator creates a unix socketpair + + - It launches the remote process and passes one of the + sockets to it via command-line. + + - It then launches QEMU and specifies the other socket as an option + to the Proxy device object + +* Remote Process: + + - QEMU can enter remote process mode by using the "remote" machine + option. + + - The orchestrator creates a "remote-object" with details about + the device and the file descriptor for the device + + - The remaining options are no different from how one launches QEMU with + devices. + + - Example command-line for the remote process is as follows: + + /usr/bin/qemu-system-x86_64 \ + -machine x-remote \ + -device lsi53c895a,id=lsi0 \ + -drive id=drive_image2,file=/build/ol7-nvme-test-1.qcow2 \ + -device scsi-hd,id=drive2,drive=drive_image2,bus=lsi0.0,scsi-id=0 \ + -object x-remote-object,id=robj1,devid=lsi1,fd=4, + +* QEMU: + + - Since parts of the RAM are shared between QEMU & remote process, a + memory-backend-memfd is required to facilitate this, as follows: + + -object memory-backend-memfd,id=mem,size=2G + + - A "x-pci-proxy-dev" device is created for each of the PCI devices emulated + in the remote process. A "socket" sub-option specifies the other end of + unix channel created by orchestrator. The "id" sub-option must be specified + and should be the same as the "id" specified for the remote PCI device + + - Example commandline for QEMU is as follows: + + -device x-pci-proxy-dev,id=lsi0,socket=3 -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> Allow RAM MemoryRegion to be created from an offset in a file, instead of allocating at offset of 0 by default. This is needed to synchronize RAM between QEMU & remote process. Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 609996697ad8617e3b01df38accc5c208c24d74e.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/exec/memory.h | 2 ++ include/exec/ram_addr.h | 4 ++-- include/qemu/mmap-alloc.h | 4 +++- backends/hostmem-memfd.c | 2 +- hw/misc/ivshmem.c | 3 ++- softmmu/memory.c | 3 ++- softmmu/physmem.c | 12 +++++++----- util/mmap-alloc.c | 8 +++++--- util/oslib-posix.c | 2 +- 9 files changed, 25 insertions(+), 15 deletions(-) diff --git a/include/exec/memory.h b/include/exec/memory.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_file(MemoryRegion *mr, * @size: size of the region. * @share: %true if memory must be mmaped with the MAP_SHARED flag * @fd: the fd to mmap. + * @offset: offset within the file referenced by fd * @errp: pointer to Error*, to store an error if it happens. * * Note that this function does not do anything to cause the data in the @@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_fd(MemoryRegion *mr, uint64_t size, bool share, int fd, + ram_addr_t offset, Error **errp); #endif diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/ram_addr.h +++ b/include/exec/ram_addr.h @@ -XXX,XX +XXX,XX @@ RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr, uint32_t ram_flags, const char *mem_path, bool readonly, Error **errp); RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, - uint32_t ram_flags, int fd, bool readonly, - Error **errp); + uint32_t ram_flags, int fd, off_t offset, + bool readonly, Error **errp); RAMBlock *qemu_ram_alloc_from_ptr(ram_addr_t size, void *host, MemoryRegion *mr, Error **errp); diff --git a/include/qemu/mmap-alloc.h b/include/qemu/mmap-alloc.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/mmap-alloc.h +++ b/include/qemu/mmap-alloc.h @@ -XXX,XX +XXX,XX @@ size_t qemu_mempath_getpagesize(const char *mem_path); * @readonly: true for a read-only mapping, false for read/write. * @shared: map has RAM_SHARED flag. * @is_pmem: map has RAM_PMEM flag. + * @map_offset: map starts at offset of map_offset from the start of fd * * Return: * On success, return a pointer to the mapped area. @@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd, size_t align, bool readonly, bool shared, - bool is_pmem); + bool is_pmem, + off_t map_offset); void qemu_ram_munmap(int fd, void *ptr, size_t size); diff --git a/backends/hostmem-memfd.c b/backends/hostmem-memfd.c index XXXXXXX..XXXXXXX 100644 --- a/backends/hostmem-memfd.c +++ b/backends/hostmem-memfd.c @@ -XXX,XX +XXX,XX @@ memfd_backend_memory_alloc(HostMemoryBackend *backend, Error **errp) name = host_memory_backend_get_name(backend); memory_region_init_ram_from_fd(&backend->mr, OBJECT(backend), name, backend->size, - backend->share, fd, errp); + backend->share, fd, 0, errp); g_free(name); } diff --git a/hw/misc/ivshmem.c b/hw/misc/ivshmem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/ivshmem.c +++ b/hw/misc/ivshmem.c @@ -XXX,XX +XXX,XX @@ static void process_msg_shmem(IVShmemState *s, int fd, Error **errp) /* mmap the region and map into the BAR2 */ memory_region_init_ram_from_fd(&s->server_bar2, OBJECT(s), - "ivshmem.bar2", size, true, fd, &local_err); + "ivshmem.bar2", size, true, fd, 0, + &local_err); if (local_err) { error_propagate(errp, local_err); return; diff --git a/softmmu/memory.c b/softmmu/memory.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/memory.c +++ b/softmmu/memory.c @@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_fd(MemoryRegion *mr, uint64_t size, bool share, int fd, + ram_addr_t offset, Error **errp) { Error *err = NULL; @@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_fd(MemoryRegion *mr, mr->destructor = memory_region_destructor_ram; mr->ram_block = qemu_ram_alloc_from_fd(size, mr, share ? RAM_SHARED : 0, - fd, false, &err); + fd, offset, false, &err); if (err) { mr->size = int128_zero(); object_unparent(OBJECT(mr)); diff --git a/softmmu/physmem.c b/softmmu/physmem.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/physmem.c +++ b/softmmu/physmem.c @@ -XXX,XX +XXX,XX @@ static void *file_ram_alloc(RAMBlock *block, int fd, bool readonly, bool truncate, + off_t offset, Error **errp) { void *area; @@ -XXX,XX +XXX,XX @@ static void *file_ram_alloc(RAMBlock *block, } area = qemu_ram_mmap(fd, memory, block->mr->align, readonly, - block->flags & RAM_SHARED, block->flags & RAM_PMEM); + block->flags & RAM_SHARED, block->flags & RAM_PMEM, + offset); if (area == MAP_FAILED) { error_setg_errno(errp, errno, "unable to map backing store for guest RAM"); @@ -XXX,XX +XXX,XX @@ static void ram_block_add(RAMBlock *new_block, Error **errp, bool shared) #ifdef CONFIG_POSIX RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, - uint32_t ram_flags, int fd, bool readonly, - Error **errp) + uint32_t ram_flags, int fd, off_t offset, + bool readonly, Error **errp) { RAMBlock *new_block; Error *local_err = NULL; @@ -XXX,XX +XXX,XX @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, new_block->max_length = size; new_block->flags = ram_flags; new_block->host = file_ram_alloc(new_block, size, fd, readonly, - !file_size, errp); + !file_size, offset, errp); if (!new_block->host) { g_free(new_block); return NULL; @@ -XXX,XX +XXX,XX @@ RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr, return NULL; } - block = qemu_ram_alloc_from_fd(size, mr, ram_flags, fd, readonly, errp); + block = qemu_ram_alloc_from_fd(size, mr, ram_flags, fd, 0, readonly, errp); if (!block) { if (created) { unlink(mem_path); diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c index XXXXXXX..XXXXXXX 100644 --- a/util/mmap-alloc.c +++ b/util/mmap-alloc.c @@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd, size_t align, bool readonly, bool shared, - bool is_pmem) + bool is_pmem, + off_t map_offset) { int prot; int flags; @@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd, prot = PROT_READ | (readonly ? 0 : PROT_WRITE); - ptr = mmap(guardptr + offset, size, prot, flags | map_sync_flags, fd, 0); + ptr = mmap(guardptr + offset, size, prot, + flags | map_sync_flags, fd, map_offset); if (ptr == MAP_FAILED && map_sync_flags) { if (errno == ENOTSUP) { @@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd, * if map failed with MAP_SHARED_VALIDATE | MAP_SYNC, * we will remove these flags to handle compatibility. */ - ptr = mmap(guardptr + offset, size, prot, flags, fd, 0); + ptr = mmap(guardptr + offset, size, prot, flags, fd, map_offset); } if (ptr == MAP_FAILED) { diff --git a/util/oslib-posix.c b/util/oslib-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/oslib-posix.c +++ b/util/oslib-posix.c @@ -XXX,XX +XXX,XX @@ void *qemu_memalign(size_t alignment, size_t size) void *qemu_anon_ram_alloc(size_t size, uint64_t *alignment, bool shared) { size_t align = QEMU_VMALLOC_ALIGN; - void *ptr = qemu_ram_mmap(-1, size, align, false, shared, false); + void *ptr = qemu_ram_mmap(-1, size, align, false, shared, false, 0); if (ptr == MAP_FAILED) { return NULL; -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> Add configuration options to enable or disable multiprocess QEMU code Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 6cc37253e35418ebd7b675a31a3df6e3c7a12dc1.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- configure | 10 ++++++++++ meson.build | 4 +++- Kconfig.host | 4 ++++ hw/Kconfig | 1 + hw/remote/Kconfig | 3 +++ 5 files changed, 21 insertions(+), 1 deletion(-) create mode 100644 hw/remote/Kconfig diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ skip_meson=no gettext="auto" fuse="auto" fuse_lseek="auto" +multiprocess="no" malloc_trim="auto" @@ -XXX,XX +XXX,XX @@ Linux) linux="yes" linux_user="yes" vhost_user=${default_feature:-yes} + multiprocess=${default_feature:-yes} ;; esac @@ -XXX,XX +XXX,XX @@ for opt do ;; --disable-fuse-lseek) fuse_lseek="disabled" ;; + --enable-multiprocess) multiprocess="yes" + ;; + --disable-multiprocess) multiprocess="no" + ;; *) echo "ERROR: unknown option $opt" echo "Try '$0 --help' for more information" @@ -XXX,XX +XXX,XX @@ disabled with --disable-FEATURE, default is enabled if available libdaxctl libdaxctl support fuse FUSE block device export fuse-lseek SEEK_HOLE/SEEK_DATA support for FUSE exports + multiprocess Multiprocess QEMU support NOTE: The object files are built at the place where configure is launched EOF @@ -XXX,XX +XXX,XX @@ fi if test "$have_mlockall" = "yes" ; then echo "HAVE_MLOCKALL=y" >> $config_host_mak fi +if test "$multiprocess" = "yes" ; then + echo "CONFIG_MULTIPROCESS_ALLOWED=y" >> $config_host_mak +fi if test "$fuzzing" = "yes" ; then # If LIB_FUZZING_ENGINE is set, assume we are running on OSS-Fuzz, and the # needed CFLAGS have already been provided diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ host_kconfig = \ ('CONFIG_VHOST_KERNEL' in config_host ? ['CONFIG_VHOST_KERNEL=y'] : []) + \ (have_virtfs ? ['CONFIG_VIRTFS=y'] : []) + \ ('CONFIG_LINUX' in config_host ? ['CONFIG_LINUX=y'] : []) + \ - ('CONFIG_PVRDMA' in config_host ? ['CONFIG_PVRDMA=y'] : []) + ('CONFIG_PVRDMA' in config_host ? ['CONFIG_PVRDMA=y'] : []) + \ + ('CONFIG_MULTIPROCESS_ALLOWED' in config_host ? ['CONFIG_MULTIPROCESS_ALLOWED=y'] : []) ignored = [ 'TARGET_XML_FILES', 'TARGET_ABI_DIR', 'TARGET_ARCH' ] @@ -XXX,XX +XXX,XX @@ summary_info += {'libpmem support': config_host.has_key('CONFIG_LIBPMEM')} summary_info += {'libdaxctl support': config_host.has_key('CONFIG_LIBDAXCTL')} summary_info += {'libudev': libudev.found()} summary_info += {'FUSE lseek': fuse_lseek.found()} +summary_info += {'Multiprocess QEMU': config_host.has_key('CONFIG_MULTIPROCESS_ALLOWED')} summary(summary_info, bool_yn: true, section: 'Dependencies') if not supported_cpus.contains(cpu) diff --git a/Kconfig.host b/Kconfig.host index XXXXXXX..XXXXXXX 100644 --- a/Kconfig.host +++ b/Kconfig.host @@ -XXX,XX +XXX,XX @@ config VIRTFS config PVRDMA bool + +config MULTIPROCESS_ALLOWED + bool + imply MULTIPROCESS diff --git a/hw/Kconfig b/hw/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/Kconfig +++ b/hw/Kconfig @@ -XXX,XX +XXX,XX @@ source pci-host/Kconfig source pcmcia/Kconfig source pci/Kconfig source rdma/Kconfig +source remote/Kconfig source rtc/Kconfig source scsi/Kconfig source sd/Kconfig diff --git a/hw/remote/Kconfig b/hw/remote/Kconfig new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/Kconfig @@ -XXX,XX +XXX,XX @@ +config MULTIPROCESS + bool + depends on PCI && KVM -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> PCI host bridge is setup for the remote device process. It is implemented using remote-pcihost object. It is an extension of the PCI host bridge setup by QEMU. Remote-pcihost configures a PCI bus which could be used by the remote PCI device to latch on to. Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 0871ba857abb2eafacde07e7fe66a3f12415bfb2.1611938319.git.jag.raman@oracle.com [Added PCI_EXPRESS condition in hw/remote/Kconfig since remote-pcihost needs PCIe. This solves "make check" failure on s390x. Fix suggested by Philippe Mathieu-Daudé <philmd@redhat.com> and Thomas Huth <thuth@redhat.com>. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 2 + include/hw/pci-host/remote.h | 29 ++++++++++++++ hw/pci-host/remote.c | 75 ++++++++++++++++++++++++++++++++++++ hw/pci-host/Kconfig | 3 ++ hw/pci-host/meson.build | 1 + hw/remote/Kconfig | 3 +- 6 files changed, 112 insertions(+), 1 deletion(-) create mode 100644 include/hw/pci-host/remote.h create mode 100644 hw/pci-host/remote.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: John G Johnson <john.g.johnson@oracle.com> S: Maintained F: docs/devel/multi-process.rst F: docs/system/multi-process.rst +F: hw/pci-host/remote.c +F: include/hw/pci-host/remote.h Build and test automation ------------------------- diff --git a/include/hw/pci-host/remote.h b/include/hw/pci-host/remote.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/pci-host/remote.h @@ -XXX,XX +XXX,XX @@ +/* + * PCI Host for remote device + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * 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 REMOTE_PCIHOST_H +#define REMOTE_PCIHOST_H + +#include "exec/memory.h" +#include "hw/pci/pcie_host.h" + +#define TYPE_REMOTE_PCIHOST "remote-pcihost" +OBJECT_DECLARE_SIMPLE_TYPE(RemotePCIHost, REMOTE_PCIHOST) + +struct RemotePCIHost { + /*< private >*/ + PCIExpressHost parent_obj; + /*< public >*/ + + MemoryRegion *mr_pci_mem; + MemoryRegion *mr_sys_io; +}; + +#endif diff --git a/hw/pci-host/remote.c b/hw/pci-host/remote.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/pci-host/remote.c @@ -XXX,XX +XXX,XX @@ +/* + * Remote PCI host device + * + * Unlike PCI host devices that model physical hardware, the purpose + * of this PCI host is to host multi-process QEMU devices. + * + * Multi-process QEMU extends the PCI host of a QEMU machine into a + * remote process. Any PCI device attached to the remote process is + * visible in the QEMU guest. This allows existing QEMU device models + * to be reused in the remote process. + * + * This PCI host is purely a container for PCI devices. It's fake in the + * sense that the guest never sees this PCI host and has no way of + * accessing it. Its job is just to provide the environment that QEMU + * PCI device models need when running in a remote process. + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * 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-common.h" + +#include "hw/pci/pci.h" +#include "hw/pci/pci_host.h" +#include "hw/pci/pcie_host.h" +#include "hw/qdev-properties.h" +#include "hw/pci-host/remote.h" +#include "exec/memory.h" + +static const char *remote_pcihost_root_bus_path(PCIHostState *host_bridge, + PCIBus *rootbus) +{ + return "0000:00"; +} + +static void remote_pcihost_realize(DeviceState *dev, Error **errp) +{ + PCIHostState *pci = PCI_HOST_BRIDGE(dev); + RemotePCIHost *s = REMOTE_PCIHOST(dev); + + pci->bus = pci_root_bus_new(DEVICE(s), "remote-pci", + s->mr_pci_mem, s->mr_sys_io, + 0, TYPE_PCIE_BUS); +} + +static void remote_pcihost_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + PCIHostBridgeClass *hc = PCI_HOST_BRIDGE_CLASS(klass); + + hc->root_bus_path = remote_pcihost_root_bus_path; + dc->realize = remote_pcihost_realize; + + dc->user_creatable = false; + set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories); + dc->fw_name = "pci"; +} + +static const TypeInfo remote_pcihost_info = { + .name = TYPE_REMOTE_PCIHOST, + .parent = TYPE_PCIE_HOST_BRIDGE, + .instance_size = sizeof(RemotePCIHost), + .class_init = remote_pcihost_class_init, +}; + +static void remote_pcihost_register(void) +{ + type_register_static(&remote_pcihost_info); +} + +type_init(remote_pcihost_register) diff --git a/hw/pci-host/Kconfig b/hw/pci-host/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/pci-host/Kconfig +++ b/hw/pci-host/Kconfig @@ -XXX,XX +XXX,XX @@ config PCI_POWERNV select PCI_EXPRESS select MSI_NONBROKEN select PCIE_PORT + +config REMOTE_PCIHOST + bool diff --git a/hw/pci-host/meson.build b/hw/pci-host/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/pci-host/meson.build +++ b/hw/pci-host/meson.build @@ -XXX,XX +XXX,XX @@ pci_ss.add(when: 'CONFIG_PCI_EXPRESS_XILINX', if_true: files('xilinx-pcie.c')) pci_ss.add(when: 'CONFIG_PCI_I440FX', if_true: files('i440fx.c')) pci_ss.add(when: 'CONFIG_PCI_SABRE', if_true: files('sabre.c')) pci_ss.add(when: 'CONFIG_XEN_IGD_PASSTHROUGH', if_true: files('xen_igd_pt.c')) +pci_ss.add(when: 'CONFIG_REMOTE_PCIHOST', if_true: files('remote.c')) # PPC devices pci_ss.add(when: 'CONFIG_PREP_PCI', if_true: files('prep.c')) diff --git a/hw/remote/Kconfig b/hw/remote/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/Kconfig +++ b/hw/remote/Kconfig @@ -XXX,XX +XXX,XX @@ config MULTIPROCESS bool - depends on PCI && KVM + depends on PCI && PCI_EXPRESS && KVM + select REMOTE_PCIHOST -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> x-remote-machine object sets up various subsystems of the remote device process. Instantiate PCI host bridge object and initialize RAM, IO & PCI memory regions. Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: c537f38d17f90453ca610c6b70cf3480274e0ba1.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 2 ++ include/hw/pci-host/remote.h | 1 + include/hw/remote/machine.h | 27 ++++++++++++++ hw/remote/machine.c | 70 ++++++++++++++++++++++++++++++++++++ hw/meson.build | 1 + hw/remote/meson.build | 5 +++ 6 files changed, 106 insertions(+) create mode 100644 include/hw/remote/machine.h create mode 100644 hw/remote/machine.c create mode 100644 hw/remote/meson.build diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: docs/devel/multi-process.rst F: docs/system/multi-process.rst F: hw/pci-host/remote.c F: include/hw/pci-host/remote.h +F: hw/remote/machine.c +F: include/hw/remote/machine.h Build and test automation ------------------------- diff --git a/include/hw/pci-host/remote.h b/include/hw/pci-host/remote.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/pci-host/remote.h +++ b/include/hw/pci-host/remote.h @@ -XXX,XX +XXX,XX @@ struct RemotePCIHost { MemoryRegion *mr_pci_mem; MemoryRegion *mr_sys_io; + MemoryRegion *mr_sys_mem; }; #endif diff --git a/include/hw/remote/machine.h b/include/hw/remote/machine.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/remote/machine.h @@ -XXX,XX +XXX,XX @@ +/* + * Remote machine configuration + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * 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 REMOTE_MACHINE_H +#define REMOTE_MACHINE_H + +#include "qom/object.h" +#include "hw/boards.h" +#include "hw/pci-host/remote.h" + +struct RemoteMachineState { + MachineState parent_obj; + + RemotePCIHost *host; +}; + +#define TYPE_REMOTE_MACHINE "x-remote-machine" +OBJECT_DECLARE_SIMPLE_TYPE(RemoteMachineState, REMOTE_MACHINE) + +#endif diff --git a/hw/remote/machine.c b/hw/remote/machine.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/machine.c @@ -XXX,XX +XXX,XX @@ +/* + * Machine for remote device + * + * This machine type is used by the remote device process in multi-process + * QEMU. QEMU device models depend on parent busses, interrupt controllers, + * memory regions, etc. The remote machine type offers this environment so + * that QEMU device models can be used as remote devices. + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * 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-common.h" + +#include "hw/remote/machine.h" +#include "exec/address-spaces.h" +#include "exec/memory.h" +#include "qapi/error.h" + +static void remote_machine_init(MachineState *machine) +{ + MemoryRegion *system_memory, *system_io, *pci_memory; + RemoteMachineState *s = REMOTE_MACHINE(machine); + RemotePCIHost *rem_host; + + system_memory = get_system_memory(); + system_io = get_system_io(); + + pci_memory = g_new(MemoryRegion, 1); + memory_region_init(pci_memory, NULL, "pci", UINT64_MAX); + + rem_host = REMOTE_PCIHOST(qdev_new(TYPE_REMOTE_PCIHOST)); + + rem_host->mr_pci_mem = pci_memory; + rem_host->mr_sys_mem = system_memory; + rem_host->mr_sys_io = system_io; + + s->host = rem_host; + + object_property_add_child(OBJECT(s), "remote-pcihost", OBJECT(rem_host)); + memory_region_add_subregion_overlap(system_memory, 0x0, pci_memory, -1); + + qdev_realize(DEVICE(rem_host), sysbus_get_default(), &error_fatal); +} + +static void remote_machine_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + + mc->init = remote_machine_init; + mc->desc = "Experimental remote machine"; +} + +static const TypeInfo remote_machine = { + .name = TYPE_REMOTE_MACHINE, + .parent = TYPE_MACHINE, + .instance_size = sizeof(RemoteMachineState), + .class_init = remote_machine_class_init, +}; + +static void remote_machine_register_types(void) +{ + type_register_static(&remote_machine); +} + +type_init(remote_machine_register_types); diff --git a/hw/meson.build b/hw/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/meson.build +++ b/hw/meson.build @@ -XXX,XX +XXX,XX @@ subdir('moxie') subdir('nios2') subdir('openrisc') subdir('ppc') +subdir('remote') subdir('riscv') subdir('rx') subdir('s390x') diff --git a/hw/remote/meson.build b/hw/remote/meson.build new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ +remote_ss = ss.source_set() + +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c')) + +softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss) -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> Adds qio_channel_writev_full_all() to transmit both data and FDs. Refactors existing code to use this helper. Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Daniel P. Berrangé <berrange@redhat.com> Message-id: 480fbf1fe4152495d60596c9b665124549b426a5.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/io/channel.h | 25 +++++++++++++++++++++++++ io/channel.c | 15 ++++++++++++++- 2 files changed, 39 insertions(+), 1 deletion(-) diff --git a/include/io/channel.h b/include/io/channel.h index XXXXXXX..XXXXXXX 100644 --- a/include/io/channel.h +++ b/include/io/channel.h @@ -XXX,XX +XXX,XX @@ void qio_channel_set_aio_fd_handler(QIOChannel *ioc, IOHandler *io_write, void *opaque); +/** + * qio_channel_writev_full_all: + * @ioc: the channel object + * @iov: the array of memory regions to write data from + * @niov: the length of the @iov array + * @fds: an array of file handles to send + * @nfds: number of file handles in @fds + * @errp: pointer to a NULL-initialized error object + * + * + * Behaves like qio_channel_writev_full but will attempt + * to send all data passed (file handles and memory regions). + * The function will wait for all requested data + * to be written, yielding from the current coroutine + * if required. + * + * Returns: 0 if all bytes were written, or -1 on error + */ + +int qio_channel_writev_full_all(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int *fds, size_t nfds, + Error **errp); + #endif /* QIO_CHANNEL_H */ diff --git a/io/channel.c b/io/channel.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel.c +++ b/io/channel.c @@ -XXX,XX +XXX,XX @@ int qio_channel_writev_all(QIOChannel *ioc, const struct iovec *iov, size_t niov, Error **errp) +{ + return qio_channel_writev_full_all(ioc, iov, niov, NULL, 0, errp); +} + +int qio_channel_writev_full_all(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int *fds, size_t nfds, + Error **errp) { int ret = -1; struct iovec *local_iov = g_new(struct iovec, niov); @@ -XXX,XX +XXX,XX @@ int qio_channel_writev_all(QIOChannel *ioc, while (nlocal_iov > 0) { ssize_t len; - len = qio_channel_writev(ioc, local_iov, nlocal_iov, errp); + len = qio_channel_writev_full(ioc, local_iov, nlocal_iov, fds, nfds, + errp); if (len == QIO_CHANNEL_ERR_BLOCK) { if (qemu_in_coroutine()) { qio_channel_yield(ioc, G_IO_OUT); @@ -XXX,XX +XXX,XX @@ int qio_channel_writev_all(QIOChannel *ioc, } iov_discard_front(&local_iov, &nlocal_iov, len); + + fds = NULL; + nfds = 0; } ret = 0; -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> Adds qio_channel_readv_full_all_eof() and qio_channel_readv_full_all() to read both data and FDs. Refactors existing code to use these helpers. Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Acked-by: Daniel P. Berrangé <berrange@redhat.com> Message-id: b059c4cc0fb741e794d644c144cc21372cad877d.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/io/channel.h | 53 +++++++++++++++++++++++ io/channel.c | 101 ++++++++++++++++++++++++++++++++++--------- 2 files changed, 134 insertions(+), 20 deletions(-) diff --git a/include/io/channel.h b/include/io/channel.h index XXXXXXX..XXXXXXX 100644 --- a/include/io/channel.h +++ b/include/io/channel.h @@ -XXX,XX +XXX,XX @@ void qio_channel_set_aio_fd_handler(QIOChannel *ioc, IOHandler *io_write, void *opaque); +/** + * qio_channel_readv_full_all_eof: + * @ioc: the channel object + * @iov: the array of memory regions to read data to + * @niov: the length of the @iov array + * @fds: an array of file handles to read + * @nfds: number of file handles in @fds + * @errp: pointer to a NULL-initialized error object + * + * + * Performs same function as qio_channel_readv_all_eof. + * Additionally, attempts to read file descriptors shared + * over the channel. The function will wait for all + * requested data to be read, yielding from the current + * coroutine if required. data refers to both file + * descriptors and the iovs. + * + * Returns: 1 if all bytes were read, 0 if end-of-file + * occurs without data, or -1 on error + */ + +int qio_channel_readv_full_all_eof(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int **fds, size_t *nfds, + Error **errp); + +/** + * qio_channel_readv_full_all: + * @ioc: the channel object + * @iov: the array of memory regions to read data to + * @niov: the length of the @iov array + * @fds: an array of file handles to read + * @nfds: number of file handles in @fds + * @errp: pointer to a NULL-initialized error object + * + * + * Performs same function as qio_channel_readv_all_eof. + * Additionally, attempts to read file descriptors shared + * over the channel. The function will wait for all + * requested data to be read, yielding from the current + * coroutine if required. data refers to both file + * descriptors and the iovs. + * + * Returns: 0 if all bytes were read, or -1 on error + */ + +int qio_channel_readv_full_all(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int **fds, size_t *nfds, + Error **errp); + /** * qio_channel_writev_full_all: * @ioc: the channel object diff --git a/io/channel.c b/io/channel.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel.c +++ b/io/channel.c @@ -XXX,XX +XXX,XX @@ int qio_channel_readv_all_eof(QIOChannel *ioc, const struct iovec *iov, size_t niov, Error **errp) +{ + return qio_channel_readv_full_all_eof(ioc, iov, niov, NULL, NULL, errp); +} + +int qio_channel_readv_all(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + Error **errp) +{ + return qio_channel_readv_full_all(ioc, iov, niov, NULL, NULL, errp); +} + +int qio_channel_readv_full_all_eof(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int **fds, size_t *nfds, + Error **errp) { int ret = -1; struct iovec *local_iov = g_new(struct iovec, niov); struct iovec *local_iov_head = local_iov; unsigned int nlocal_iov = niov; + int **local_fds = fds; + size_t *local_nfds = nfds; bool partial = false; + if (nfds) { + *nfds = 0; + } + + if (fds) { + *fds = NULL; + } + nlocal_iov = iov_copy(local_iov, nlocal_iov, iov, niov, 0, iov_size(iov, niov)); - while (nlocal_iov > 0) { + while ((nlocal_iov > 0) || local_fds) { ssize_t len; - len = qio_channel_readv(ioc, local_iov, nlocal_iov, errp); + len = qio_channel_readv_full(ioc, local_iov, nlocal_iov, local_fds, + local_nfds, errp); if (len == QIO_CHANNEL_ERR_BLOCK) { if (qemu_in_coroutine()) { qio_channel_yield(ioc, G_IO_IN); @@ -XXX,XX +XXX,XX @@ int qio_channel_readv_all_eof(QIOChannel *ioc, qio_channel_wait(ioc, G_IO_IN); } continue; - } else if (len < 0) { - goto cleanup; - } else if (len == 0) { - if (partial) { - error_setg(errp, - "Unexpected end-of-file before all bytes were read"); - } else { + } + + if (len == 0) { + if (local_nfds && *local_nfds) { + /* + * Got some FDs, but no data yet. This isn't an EOF + * scenario (yet), so carry on to try to read data + * on next loop iteration + */ + goto next_iter; + } else if (!partial) { + /* No fds and no data - EOF before any data read */ ret = 0; + goto cleanup; + } else { + len = -1; + error_setg(errp, + "Unexpected end-of-file before all data were read"); + /* Fallthrough into len < 0 handling */ + } + } + + if (len < 0) { + /* Close any FDs we previously received */ + if (nfds && fds) { + size_t i; + for (i = 0; i < (*nfds); i++) { + close((*fds)[i]); + } + g_free(*fds); + *fds = NULL; + *nfds = 0; } goto cleanup; } + if (nlocal_iov) { + iov_discard_front(&local_iov, &nlocal_iov, len); + } + +next_iter: partial = true; - iov_discard_front(&local_iov, &nlocal_iov, len); + local_fds = NULL; + local_nfds = NULL; } ret = 1; @@ -XXX,XX +XXX,XX @@ int qio_channel_readv_all_eof(QIOChannel *ioc, return ret; } -int qio_channel_readv_all(QIOChannel *ioc, - const struct iovec *iov, - size_t niov, - Error **errp) +int qio_channel_readv_full_all(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int **fds, size_t *nfds, + Error **errp) { - int ret = qio_channel_readv_all_eof(ioc, iov, niov, errp); + int ret = qio_channel_readv_full_all_eof(ioc, iov, niov, fds, nfds, errp); if (ret == 0) { - ret = -1; - error_setg(errp, - "Unexpected end-of-file before all bytes were read"); - } else if (ret == 1) { - ret = 0; + error_prepend(errp, + "Unexpected end-of-file before all data were read."); + return -1; } + if (ret == 1) { + return 0; + } + return ret; } -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> Defines MPQemuMsg, which is the message that is sent to the remote process. This message is sent over QIOChannel and is used to command the remote process to perform various tasks. Define transmission functions used by proxy and by remote. Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 56ca8bcf95195b2b195b08f6b9565b6d7410bce5.1611938319.git.jag.raman@oracle.com [Replace struct iovec send[2] = {0} with {} to make clang happy as suggested by Peter Maydell <peter.maydell@linaro.org>. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 2 + meson.build | 1 + hw/remote/trace.h | 1 + include/hw/remote/mpqemu-link.h | 63 ++++++++++ include/sysemu/iothread.h | 6 + hw/remote/mpqemu-link.c | 205 ++++++++++++++++++++++++++++++++ iothread.c | 6 + hw/remote/meson.build | 1 + hw/remote/trace-events | 4 + 9 files changed, 289 insertions(+) create mode 100644 hw/remote/trace.h create mode 100644 include/hw/remote/mpqemu-link.h create mode 100644 hw/remote/mpqemu-link.c create mode 100644 hw/remote/trace-events diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/pci-host/remote.c F: include/hw/pci-host/remote.h F: hw/remote/machine.c F: include/hw/remote/machine.h +F: hw/remote/mpqemu-link.c +F: include/hw/remote/mpqemu-link.h Build and test automation ------------------------- diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ if have_system 'net', 'softmmu', 'ui', + 'hw/remote', ] endif if have_system or have_user diff --git a/hw/remote/trace.h b/hw/remote/trace.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/trace.h @@ -0,0 +1 @@ +#include "trace/trace-hw_remote.h" diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/remote/mpqemu-link.h @@ -XXX,XX +XXX,XX @@ +/* + * Communication channel between QEMU and remote device process + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * 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 MPQEMU_LINK_H +#define MPQEMU_LINK_H + +#include "qom/object.h" +#include "qemu/thread.h" +#include "io/channel.h" + +#define REMOTE_MAX_FDS 8 + +#define MPQEMU_MSG_HDR_SIZE offsetof(MPQemuMsg, data.u64) + +/** + * MPQemuCmd: + * + * MPQemuCmd enum type to specify the command to be executed on the remote + * device. + * + * This uses a private protocol between QEMU and the remote process. vfio-user + * protocol would supersede this in the future. + * + */ +typedef enum { + MPQEMU_CMD_MAX, +} MPQemuCmd; + +/** + * MPQemuMsg: + * @cmd: The remote command + * @size: Size of the data to be shared + * @data: Structured data + * @fds: File descriptors to be shared with remote device + * + * MPQemuMsg Format of the message sent to the remote device from QEMU. + * + */ +typedef struct { + int cmd; + size_t size; + + union { + uint64_t u64; + } data; + + int fds[REMOTE_MAX_FDS]; + int num_fds; +} MPQemuMsg; + +bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp); +bool mpqemu_msg_recv(MPQemuMsg *msg, QIOChannel *ioc, Error **errp); + +bool mpqemu_msg_valid(MPQemuMsg *msg); + +#endif diff --git a/include/sysemu/iothread.h b/include/sysemu/iothread.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/iothread.h +++ b/include/sysemu/iothread.h @@ -XXX,XX +XXX,XX @@ IOThread *iothread_create(const char *id, Error **errp); void iothread_stop(IOThread *iothread); void iothread_destroy(IOThread *iothread); +/* + * Returns true if executing withing IOThread context, + * false otherwise. + */ +bool qemu_in_iothread(void); + #endif /* IOTHREAD_H */ diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/mpqemu-link.c @@ -XXX,XX +XXX,XX @@ +/* + * Communication channel between QEMU and remote device process + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * 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-common.h" + +#include "qemu/module.h" +#include "hw/remote/mpqemu-link.h" +#include "qapi/error.h" +#include "qemu/iov.h" +#include "qemu/error-report.h" +#include "qemu/main-loop.h" +#include "io/channel.h" +#include "sysemu/iothread.h" +#include "trace.h" + +/* + * Send message over the ioc QIOChannel. + * This function is safe to call from: + * - main loop in co-routine context. Will block the main loop if not in + * co-routine context; + * - vCPU thread with no co-routine context and if the channel is not part + * of the main loop handling; + * - IOThread within co-routine context, outside of co-routine context + * will block IOThread; + * Returns true if no errors were encountered, false otherwise. + */ +bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp) +{ + ERRP_GUARD(); + bool iolock = qemu_mutex_iothread_locked(); + bool iothread = qemu_in_iothread(); + struct iovec send[2] = {}; + int *fds = NULL; + size_t nfds = 0; + bool ret = false; + + send[0].iov_base = msg; + send[0].iov_len = MPQEMU_MSG_HDR_SIZE; + + send[1].iov_base = (void *)&msg->data; + send[1].iov_len = msg->size; + + if (msg->num_fds) { + nfds = msg->num_fds; + fds = msg->fds; + } + + /* + * Dont use in IOThread out of co-routine context as + * it will block IOThread. + */ + assert(qemu_in_coroutine() || !iothread); + + /* + * Skip unlocking/locking iothread lock when the IOThread is running + * in co-routine context. Co-routine context is asserted above + * for IOThread case. + * Also skip lock handling while in a co-routine in the main context. + */ + if (iolock && !iothread && !qemu_in_coroutine()) { + qemu_mutex_unlock_iothread(); + } + + if (!qio_channel_writev_full_all(ioc, send, G_N_ELEMENTS(send), + fds, nfds, errp)) { + ret = true; + } else { + trace_mpqemu_send_io_error(msg->cmd, msg->size, nfds); + } + + if (iolock && !iothread && !qemu_in_coroutine()) { + /* See above comment why skip locking here. */ + qemu_mutex_lock_iothread(); + } + + return ret; +} + +/* + * Read message from the ioc QIOChannel. + * This function is safe to call from: + * - From main loop in co-routine context. Will block the main loop if not in + * co-routine context; + * - From vCPU thread with no co-routine context and if the channel is not part + * of the main loop handling; + * - From IOThread within co-routine context, outside of co-routine context + * will block IOThread; + */ +static ssize_t mpqemu_read(QIOChannel *ioc, void *buf, size_t len, int **fds, + size_t *nfds, Error **errp) +{ + ERRP_GUARD(); + struct iovec iov = { .iov_base = buf, .iov_len = len }; + bool iolock = qemu_mutex_iothread_locked(); + bool iothread = qemu_in_iothread(); + int ret = -1; + + /* + * Dont use in IOThread out of co-routine context as + * it will block IOThread. + */ + assert(qemu_in_coroutine() || !iothread); + + if (iolock && !iothread && !qemu_in_coroutine()) { + qemu_mutex_unlock_iothread(); + } + + ret = qio_channel_readv_full_all_eof(ioc, &iov, 1, fds, nfds, errp); + + if (iolock && !iothread && !qemu_in_coroutine()) { + qemu_mutex_lock_iothread(); + } + + return (ret <= 0) ? ret : iov.iov_len; +} + +bool mpqemu_msg_recv(MPQemuMsg *msg, QIOChannel *ioc, Error **errp) +{ + ERRP_GUARD(); + g_autofree int *fds = NULL; + size_t nfds = 0; + ssize_t len; + bool ret = false; + + len = mpqemu_read(ioc, msg, MPQEMU_MSG_HDR_SIZE, &fds, &nfds, errp); + if (len <= 0) { + goto fail; + } else if (len != MPQEMU_MSG_HDR_SIZE) { + error_setg(errp, "Message header corrupted"); + goto fail; + } + + if (msg->size > sizeof(msg->data)) { + error_setg(errp, "Invalid size for message"); + goto fail; + } + + if (!msg->size) { + goto copy_fds; + } + + len = mpqemu_read(ioc, &msg->data, msg->size, NULL, NULL, errp); + if (len <= 0) { + goto fail; + } + if (len != msg->size) { + error_setg(errp, "Unable to read full message"); + goto fail; + } + +copy_fds: + msg->num_fds = nfds; + if (nfds > G_N_ELEMENTS(msg->fds)) { + error_setg(errp, + "Overflow error: received %zu fds, more than max of %d fds", + nfds, REMOTE_MAX_FDS); + goto fail; + } + if (nfds) { + memcpy(msg->fds, fds, nfds * sizeof(int)); + } + + ret = true; + +fail: + if (*errp) { + trace_mpqemu_recv_io_error(msg->cmd, msg->size, nfds); + } + while (*errp && nfds) { + close(fds[nfds - 1]); + nfds--; + } + + return ret; +} + +bool mpqemu_msg_valid(MPQemuMsg *msg) +{ + if (msg->cmd >= MPQEMU_CMD_MAX && msg->cmd < 0) { + return false; + } + + /* Verify FDs. */ + if (msg->num_fds >= REMOTE_MAX_FDS) { + return false; + } + + if (msg->num_fds > 0) { + for (int i = 0; i < msg->num_fds; i++) { + if (fcntl(msg->fds[i], F_GETFL) == -1) { + return false; + } + } + } + + return true; +} diff --git a/iothread.c b/iothread.c index XXXXXXX..XXXXXXX 100644 --- a/iothread.c +++ b/iothread.c @@ -XXX,XX +XXX,XX @@ IOThread *iothread_by_id(const char *id) { return IOTHREAD(object_resolve_path_type(id, TYPE_IOTHREAD, NULL)); } + +bool qemu_in_iothread(void) +{ + return qemu_get_current_aio_context() == qemu_get_aio_context() ? + false : true; +} diff --git a/hw/remote/meson.build b/hw/remote/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/meson.build +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ remote_ss = ss.source_set() remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c')) +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c')) softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss) diff --git a/hw/remote/trace-events b/hw/remote/trace-events new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/trace-events @@ -XXX,XX +XXX,XX @@ +# multi-process trace events + +mpqemu_send_io_error(int cmd, int size, int nfds) "send command %d size %d, %d file descriptors to remote process" +mpqemu_recv_io_error(int cmd, int size, int nfds) "failed to receive %d size %d, %d file descriptors to remote process" -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> Initializes the message handler function in the remote process. It is called whenever there's an event pending on QIOChannel that registers this function. Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 99d38d8b93753a6409ac2340e858858cda59ab1b.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 1 + include/hw/remote/machine.h | 9 ++++++ hw/remote/message.c | 57 +++++++++++++++++++++++++++++++++++++ hw/remote/meson.build | 1 + 4 files changed, 68 insertions(+) create mode 100644 hw/remote/message.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/remote/machine.c F: include/hw/remote/machine.h F: hw/remote/mpqemu-link.c F: include/hw/remote/mpqemu-link.h +F: hw/remote/message.c Build and test automation ------------------------- diff --git a/include/hw/remote/machine.h b/include/hw/remote/machine.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/machine.h +++ b/include/hw/remote/machine.h @@ -XXX,XX +XXX,XX @@ #include "qom/object.h" #include "hw/boards.h" #include "hw/pci-host/remote.h" +#include "io/channel.h" struct RemoteMachineState { MachineState parent_obj; @@ -XXX,XX +XXX,XX @@ struct RemoteMachineState { RemotePCIHost *host; }; +/* Used to pass to co-routine device and ioc. */ +typedef struct RemoteCommDev { + PCIDevice *dev; + QIOChannel *ioc; +} RemoteCommDev; + #define TYPE_REMOTE_MACHINE "x-remote-machine" OBJECT_DECLARE_SIMPLE_TYPE(RemoteMachineState, REMOTE_MACHINE) +void coroutine_fn mpqemu_remote_msg_loop_co(void *data); + #endif diff --git a/hw/remote/message.c b/hw/remote/message.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/message.c @@ -XXX,XX +XXX,XX @@ +/* + * Copyright © 2020, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL-v2, version 2 or later. + * + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "hw/remote/machine.h" +#include "io/channel.h" +#include "hw/remote/mpqemu-link.h" +#include "qapi/error.h" +#include "sysemu/runstate.h" + +void coroutine_fn mpqemu_remote_msg_loop_co(void *data) +{ + g_autofree RemoteCommDev *com = (RemoteCommDev *)data; + PCIDevice *pci_dev = NULL; + Error *local_err = NULL; + + assert(com->ioc); + + pci_dev = com->dev; + for (; !local_err;) { + MPQemuMsg msg = {0}; + + if (!mpqemu_msg_recv(&msg, com->ioc, &local_err)) { + break; + } + + if (!mpqemu_msg_valid(&msg)) { + error_setg(&local_err, "Received invalid message from proxy" + "in remote process pid="FMT_pid"", + getpid()); + break; + } + + switch (msg.cmd) { + default: + error_setg(&local_err, + "Unknown command (%d) received for device %s" + " (pid="FMT_pid")", + msg.cmd, DEVICE(pci_dev)->id, getpid()); + } + } + + if (local_err) { + error_report_err(local_err); + qemu_system_shutdown_request(SHUTDOWN_CAUSE_HOST_ERROR); + } else { + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + } +} diff --git a/hw/remote/meson.build b/hw/remote/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/meson.build +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ remote_ss = ss.source_set() remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c')) +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c')) softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss) -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> Associate the file descriptor for a PCIDevice in remote process with DeviceState object. Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: f405a2ed5d7518b87bea7c59cfdf334d67e5ee51.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 1 + hw/remote/remote-obj.c | 203 +++++++++++++++++++++++++++++++++++++++++ hw/remote/meson.build | 1 + 3 files changed, 205 insertions(+) create mode 100644 hw/remote/remote-obj.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/hw/remote/machine.h F: hw/remote/mpqemu-link.c F: include/hw/remote/mpqemu-link.h F: hw/remote/message.c +F: hw/remote/remote-obj.c Build and test automation ------------------------- diff --git a/hw/remote/remote-obj.c b/hw/remote/remote-obj.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/remote-obj.c @@ -XXX,XX +XXX,XX @@ +/* + * Copyright © 2020, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL-v2, version 2 or later. + * + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "qemu/error-report.h" +#include "qemu/notify.h" +#include "qom/object_interfaces.h" +#include "hw/qdev-core.h" +#include "io/channel.h" +#include "hw/qdev-core.h" +#include "hw/remote/machine.h" +#include "io/channel-util.h" +#include "qapi/error.h" +#include "sysemu/sysemu.h" +#include "hw/pci/pci.h" +#include "qemu/sockets.h" +#include "monitor/monitor.h" + +#define TYPE_REMOTE_OBJECT "x-remote-object" +OBJECT_DECLARE_TYPE(RemoteObject, RemoteObjectClass, REMOTE_OBJECT) + +struct RemoteObjectClass { + ObjectClass parent_class; + + unsigned int nr_devs; + unsigned int max_devs; +}; + +struct RemoteObject { + /* private */ + Object parent; + + Notifier machine_done; + + int32_t fd; + char *devid; + + QIOChannel *ioc; + + DeviceState *dev; + DeviceListener listener; +}; + +static void remote_object_set_fd(Object *obj, const char *str, Error **errp) +{ + RemoteObject *o = REMOTE_OBJECT(obj); + int fd = -1; + + fd = monitor_fd_param(monitor_cur(), str, errp); + if (fd == -1) { + error_prepend(errp, "Could not parse remote object fd %s:", str); + return; + } + + if (!fd_is_socket(fd)) { + error_setg(errp, "File descriptor '%s' is not a socket", str); + close(fd); + return; + } + + o->fd = fd; +} + +static void remote_object_set_devid(Object *obj, const char *str, Error **errp) +{ + RemoteObject *o = REMOTE_OBJECT(obj); + + g_free(o->devid); + + o->devid = g_strdup(str); +} + +static void remote_object_unrealize_listener(DeviceListener *listener, + DeviceState *dev) +{ + RemoteObject *o = container_of(listener, RemoteObject, listener); + + if (o->dev == dev) { + object_unref(OBJECT(o)); + } +} + +static void remote_object_machine_done(Notifier *notifier, void *data) +{ + RemoteObject *o = container_of(notifier, RemoteObject, machine_done); + DeviceState *dev = NULL; + QIOChannel *ioc = NULL; + Coroutine *co = NULL; + RemoteCommDev *comdev = NULL; + Error *err = NULL; + + dev = qdev_find_recursive(sysbus_get_default(), o->devid); + if (!dev || !object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { + error_report("%s is not a PCI device", o->devid); + return; + } + + ioc = qio_channel_new_fd(o->fd, &err); + if (!ioc) { + error_report_err(err); + return; + } + qio_channel_set_blocking(ioc, false, NULL); + + o->dev = dev; + + o->listener.unrealize = remote_object_unrealize_listener; + device_listener_register(&o->listener); + + /* co-routine should free this. */ + comdev = g_new0(RemoteCommDev, 1); + *comdev = (RemoteCommDev) { + .ioc = ioc, + .dev = PCI_DEVICE(dev), + }; + + co = qemu_coroutine_create(mpqemu_remote_msg_loop_co, comdev); + qemu_coroutine_enter(co); +} + +static void remote_object_init(Object *obj) +{ + RemoteObjectClass *k = REMOTE_OBJECT_GET_CLASS(obj); + RemoteObject *o = REMOTE_OBJECT(obj); + + if (k->nr_devs >= k->max_devs) { + error_report("Reached maximum number of devices: %u", k->max_devs); + return; + } + + o->ioc = NULL; + o->fd = -1; + o->devid = NULL; + + k->nr_devs++; + + o->machine_done.notify = remote_object_machine_done; + qemu_add_machine_init_done_notifier(&o->machine_done); +} + +static void remote_object_finalize(Object *obj) +{ + RemoteObjectClass *k = REMOTE_OBJECT_GET_CLASS(obj); + RemoteObject *o = REMOTE_OBJECT(obj); + + device_listener_unregister(&o->listener); + + if (o->ioc) { + qio_channel_shutdown(o->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); + qio_channel_close(o->ioc, NULL); + } + + object_unref(OBJECT(o->ioc)); + + k->nr_devs--; + g_free(o->devid); +} + +static void remote_object_class_init(ObjectClass *klass, void *data) +{ + RemoteObjectClass *k = REMOTE_OBJECT_CLASS(klass); + + /* + * Limit number of supported devices to 1. This is done to avoid devices + * from one VM accessing the RAM of another VM. This is done until we + * start using separate address spaces for individual devices. + */ + k->max_devs = 1; + k->nr_devs = 0; + + object_class_property_add_str(klass, "fd", NULL, remote_object_set_fd); + object_class_property_add_str(klass, "devid", NULL, + remote_object_set_devid); +} + +static const TypeInfo remote_object_info = { + .name = TYPE_REMOTE_OBJECT, + .parent = TYPE_OBJECT, + .instance_size = sizeof(RemoteObject), + .instance_init = remote_object_init, + .instance_finalize = remote_object_finalize, + .class_size = sizeof(RemoteObjectClass), + .class_init = remote_object_class_init, + .interfaces = (InterfaceInfo[]) { + { TYPE_USER_CREATABLE }, + { } + } +}; + +static void register_types(void) +{ + type_register_static(&remote_object_info); +} + +type_init(register_types); diff --git a/hw/remote/meson.build b/hw/remote/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/meson.build +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ remote_ss = ss.source_set() remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c')) +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c')) softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss) -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> SyncSysMemMsg message format is defined. It is used to send file descriptors of the RAM regions to remote device. RAM on the remote device is configured with a set of file descriptors. Old RAM regions are deleted and new regions, each with an fd, is added to the RAM. Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 7d2d1831d812e85f681e7a8ab99e032cf4704689.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 2 + include/hw/remote/memory.h | 19 ++++++++++ include/hw/remote/mpqemu-link.h | 10 +++++ hw/remote/memory.c | 65 +++++++++++++++++++++++++++++++++ hw/remote/mpqemu-link.c | 11 ++++++ hw/remote/meson.build | 2 + 6 files changed, 109 insertions(+) create mode 100644 include/hw/remote/memory.h create mode 100644 hw/remote/memory.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/remote/mpqemu-link.c F: include/hw/remote/mpqemu-link.h F: hw/remote/message.c F: hw/remote/remote-obj.c +F: include/hw/remote/memory.h +F: hw/remote/memory.c Build and test automation ------------------------- diff --git a/include/hw/remote/memory.h b/include/hw/remote/memory.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/remote/memory.h @@ -XXX,XX +XXX,XX @@ +/* + * Memory manager for remote device + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * 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 REMOTE_MEMORY_H +#define REMOTE_MEMORY_H + +#include "exec/hwaddr.h" +#include "hw/remote/mpqemu-link.h" + +void remote_sysmem_reconfig(MPQemuMsg *msg, Error **errp); + +#endif diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/mpqemu-link.h +++ b/include/hw/remote/mpqemu-link.h @@ -XXX,XX +XXX,XX @@ #include "qom/object.h" #include "qemu/thread.h" #include "io/channel.h" +#include "exec/hwaddr.h" #define REMOTE_MAX_FDS 8 @@ -XXX,XX +XXX,XX @@ * */ typedef enum { + MPQEMU_CMD_SYNC_SYSMEM, MPQEMU_CMD_MAX, } MPQemuCmd; +typedef struct { + hwaddr gpas[REMOTE_MAX_FDS]; + uint64_t sizes[REMOTE_MAX_FDS]; + off_t offsets[REMOTE_MAX_FDS]; +} SyncSysmemMsg; + /** * MPQemuMsg: * @cmd: The remote command @@ -XXX,XX +XXX,XX @@ typedef enum { * MPQemuMsg Format of the message sent to the remote device from QEMU. * */ + typedef struct { int cmd; size_t size; union { uint64_t u64; + SyncSysmemMsg sync_sysmem; } data; int fds[REMOTE_MAX_FDS]; diff --git a/hw/remote/memory.c b/hw/remote/memory.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/memory.c @@ -XXX,XX +XXX,XX @@ +/* + * Memory manager for remote device + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * 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-common.h" + +#include "hw/remote/memory.h" +#include "exec/address-spaces.h" +#include "exec/ram_addr.h" +#include "qapi/error.h" + +static void remote_sysmem_reset(void) +{ + MemoryRegion *sysmem, *subregion, *next; + + sysmem = get_system_memory(); + + QTAILQ_FOREACH_SAFE(subregion, &sysmem->subregions, subregions_link, next) { + if (subregion->ram) { + memory_region_del_subregion(sysmem, subregion); + object_unparent(OBJECT(subregion)); + } + } +} + +void remote_sysmem_reconfig(MPQemuMsg *msg, Error **errp) +{ + ERRP_GUARD(); + SyncSysmemMsg *sysmem_info = &msg->data.sync_sysmem; + MemoryRegion *sysmem, *subregion; + static unsigned int suffix; + int region; + + sysmem = get_system_memory(); + + remote_sysmem_reset(); + + for (region = 0; region < msg->num_fds; region++) { + g_autofree char *name; + subregion = g_new(MemoryRegion, 1); + name = g_strdup_printf("remote-mem-%u", suffix++); + memory_region_init_ram_from_fd(subregion, NULL, + name, sysmem_info->sizes[region], + true, msg->fds[region], + sysmem_info->offsets[region], + errp); + + if (*errp) { + g_free(subregion); + remote_sysmem_reset(); + return; + } + + memory_region_add_subregion(sysmem, sysmem_info->gpas[region], + subregion); + + } +} diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/mpqemu-link.c +++ b/hw/remote/mpqemu-link.c @@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg) } } + /* Verify message specific fields. */ + switch (msg->cmd) { + case MPQEMU_CMD_SYNC_SYSMEM: + if (msg->num_fds == 0 || msg->size != sizeof(SyncSysmemMsg)) { + return false; + } + break; + default: + break; + } + return true; } diff --git a/hw/remote/meson.build b/hw/remote/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/meson.build +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c')) +specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c')) + softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss) -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> Defines a PCI Device proxy object as a child of TYPE_PCI_DEVICE. Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: b5186ebfedf8e557044d09a768846c59230ad3a7.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 2 + include/hw/remote/proxy.h | 33 +++++++++++++ hw/remote/proxy.c | 99 +++++++++++++++++++++++++++++++++++++++ hw/remote/meson.build | 1 + 4 files changed, 135 insertions(+) create mode 100644 include/hw/remote/proxy.h create mode 100644 hw/remote/proxy.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/remote/message.c F: hw/remote/remote-obj.c F: include/hw/remote/memory.h F: hw/remote/memory.c +F: hw/remote/proxy.c +F: include/hw/remote/proxy.h Build and test automation ------------------------- diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/remote/proxy.h @@ -XXX,XX +XXX,XX @@ +/* + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * 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 PROXY_H +#define PROXY_H + +#include "hw/pci/pci.h" +#include "io/channel.h" + +#define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev" +OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV) + +struct PCIProxyDev { + PCIDevice parent_dev; + char *fd; + + /* + * Mutex used to protect the QIOChannel fd from + * the concurrent access by the VCPUs since proxy + * blocks while awaiting for the replies from the + * process remote. + */ + QemuMutex io_mutex; + QIOChannel *ioc; + Error *migration_blocker; +}; + +#endif /* PROXY_H */ diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/proxy.c @@ -XXX,XX +XXX,XX @@ +/* + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * 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-common.h" + +#include "hw/remote/proxy.h" +#include "hw/pci/pci.h" +#include "qapi/error.h" +#include "io/channel-util.h" +#include "hw/qdev-properties.h" +#include "monitor/monitor.h" +#include "migration/blocker.h" +#include "qemu/sockets.h" + +static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) +{ + ERRP_GUARD(); + PCIProxyDev *dev = PCI_PROXY_DEV(device); + int fd; + + if (!dev->fd) { + error_setg(errp, "fd parameter not specified for %s", + DEVICE(device)->id); + return; + } + + fd = monitor_fd_param(monitor_cur(), dev->fd, errp); + if (fd == -1) { + error_prepend(errp, "proxy: unable to parse fd %s: ", dev->fd); + return; + } + + if (!fd_is_socket(fd)) { + error_setg(errp, "proxy: fd %d is not a socket", fd); + close(fd); + return; + } + + dev->ioc = qio_channel_new_fd(fd, errp); + + error_setg(&dev->migration_blocker, "%s does not support migration", + TYPE_PCI_PROXY_DEV); + migrate_add_blocker(dev->migration_blocker, errp); + + qemu_mutex_init(&dev->io_mutex); + qio_channel_set_blocking(dev->ioc, true, NULL); +} + +static void pci_proxy_dev_exit(PCIDevice *pdev) +{ + PCIProxyDev *dev = PCI_PROXY_DEV(pdev); + + if (dev->ioc) { + qio_channel_close(dev->ioc, NULL); + } + + migrate_del_blocker(dev->migration_blocker); + + error_free(dev->migration_blocker); +} + +static Property proxy_properties[] = { + DEFINE_PROP_STRING("fd", PCIProxyDev, fd), + DEFINE_PROP_END_OF_LIST(), +}; + +static void pci_proxy_dev_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); + + k->realize = pci_proxy_dev_realize; + k->exit = pci_proxy_dev_exit; + device_class_set_props(dc, proxy_properties); +} + +static const TypeInfo pci_proxy_dev_type_info = { + .name = TYPE_PCI_PROXY_DEV, + .parent = TYPE_PCI_DEVICE, + .instance_size = sizeof(PCIProxyDev), + .class_init = pci_proxy_dev_class_init, + .interfaces = (InterfaceInfo[]) { + { INTERFACE_CONVENTIONAL_PCI_DEVICE }, + { }, + }, +}; + +static void pci_proxy_dev_register_types(void) +{ + type_register_static(&pci_proxy_dev_type_info); +} + +type_init(pci_proxy_dev_register_types) diff --git a/hw/remote/meson.build b/hw/remote/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/meson.build +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c')) +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c')) specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c')) -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: d54edb4176361eed86b903e8f27058363b6c83b3.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/hw/remote/mpqemu-link.h | 4 ++++ hw/remote/mpqemu-link.c | 34 +++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/mpqemu-link.h +++ b/include/hw/remote/mpqemu-link.h @@ -XXX,XX +XXX,XX @@ #include "qemu/thread.h" #include "io/channel.h" #include "exec/hwaddr.h" +#include "io/channel-socket.h" +#include "hw/remote/proxy.h" #define REMOTE_MAX_FDS 8 @@ -XXX,XX +XXX,XX @@ typedef struct { bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp); bool mpqemu_msg_recv(MPQemuMsg *msg, QIOChannel *ioc, Error **errp); +uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev, + Error **errp); bool mpqemu_msg_valid(MPQemuMsg *msg); #endif diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/mpqemu-link.c +++ b/hw/remote/mpqemu-link.c @@ -XXX,XX +XXX,XX @@ fail: return ret; } +/* + * Send msg and wait for a reply with command code RET_MSG. + * Returns the message received of size u64 or UINT64_MAX + * on error. + * Called from VCPU thread in non-coroutine context. + * Used by the Proxy object to communicate to remote processes. + */ +uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev, + Error **errp) +{ + ERRP_GUARD(); + MPQemuMsg msg_reply = {0}; + uint64_t ret = UINT64_MAX; + + assert(!qemu_in_coroutine()); + + QEMU_LOCK_GUARD(&pdev->io_mutex); + if (!mpqemu_msg_send(msg, pdev->ioc, errp)) { + return ret; + } + + if (!mpqemu_msg_recv(&msg_reply, pdev->ioc, errp)) { + return ret; + } + + if (!mpqemu_msg_valid(&msg_reply)) { + error_setg(errp, "ERROR: Invalid reply received for command %d", + msg->cmd); + return ret; + } + + return msg_reply.data.u64; +} + bool mpqemu_msg_valid(MPQemuMsg *msg) { if (msg->cmd >= MPQEMU_CMD_MAX && msg->cmd < 0) { -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> The Proxy Object sends the PCI config space accesses as messages to the remote process over the communication channel Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: d3c94f4618813234655356c60e6f0d0362ff42d6.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/hw/remote/mpqemu-link.h | 10 ++++++ hw/remote/message.c | 60 +++++++++++++++++++++++++++++++++ hw/remote/mpqemu-link.c | 8 ++++- hw/remote/proxy.c | 55 ++++++++++++++++++++++++++++++ 4 files changed, 132 insertions(+), 1 deletion(-) diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/mpqemu-link.h +++ b/include/hw/remote/mpqemu-link.h @@ -XXX,XX +XXX,XX @@ */ typedef enum { MPQEMU_CMD_SYNC_SYSMEM, + MPQEMU_CMD_RET, + MPQEMU_CMD_PCI_CFGWRITE, + MPQEMU_CMD_PCI_CFGREAD, MPQEMU_CMD_MAX, } MPQemuCmd; @@ -XXX,XX +XXX,XX @@ typedef struct { off_t offsets[REMOTE_MAX_FDS]; } SyncSysmemMsg; +typedef struct { + uint32_t addr; + uint32_t val; + int len; +} PciConfDataMsg; + /** * MPQemuMsg: * @cmd: The remote command @@ -XXX,XX +XXX,XX @@ typedef struct { union { uint64_t u64; + PciConfDataMsg pci_conf_data; SyncSysmemMsg sync_sysmem; } data; diff --git a/hw/remote/message.c b/hw/remote/message.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/message.c +++ b/hw/remote/message.c @@ -XXX,XX +XXX,XX @@ #include "hw/remote/mpqemu-link.h" #include "qapi/error.h" #include "sysemu/runstate.h" +#include "hw/pci/pci.h" + +static void process_config_write(QIOChannel *ioc, PCIDevice *dev, + MPQemuMsg *msg, Error **errp); +static void process_config_read(QIOChannel *ioc, PCIDevice *dev, + MPQemuMsg *msg, Error **errp); void coroutine_fn mpqemu_remote_msg_loop_co(void *data) { @@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data) } switch (msg.cmd) { + case MPQEMU_CMD_PCI_CFGWRITE: + process_config_write(com->ioc, pci_dev, &msg, &local_err); + break; + case MPQEMU_CMD_PCI_CFGREAD: + process_config_read(com->ioc, pci_dev, &msg, &local_err); + break; default: error_setg(&local_err, "Unknown command (%d) received for device %s" @@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data) qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); } } + +static void process_config_write(QIOChannel *ioc, PCIDevice *dev, + MPQemuMsg *msg, Error **errp) +{ + ERRP_GUARD(); + PciConfDataMsg *conf = (PciConfDataMsg *)&msg->data.pci_conf_data; + MPQemuMsg ret = { 0 }; + + if ((conf->addr + sizeof(conf->val)) > pci_config_size(dev)) { + error_setg(errp, "Bad address for PCI config write, pid "FMT_pid".", + getpid()); + ret.data.u64 = UINT64_MAX; + } else { + pci_default_write_config(dev, conf->addr, conf->val, conf->len); + } + + ret.cmd = MPQEMU_CMD_RET; + ret.size = sizeof(ret.data.u64); + + if (!mpqemu_msg_send(&ret, ioc, NULL)) { + error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ", + getpid()); + } +} + +static void process_config_read(QIOChannel *ioc, PCIDevice *dev, + MPQemuMsg *msg, Error **errp) +{ + ERRP_GUARD(); + PciConfDataMsg *conf = (PciConfDataMsg *)&msg->data.pci_conf_data; + MPQemuMsg ret = { 0 }; + + if ((conf->addr + sizeof(conf->val)) > pci_config_size(dev)) { + error_setg(errp, "Bad address for PCI config read, pid "FMT_pid".", + getpid()); + ret.data.u64 = UINT64_MAX; + } else { + ret.data.u64 = pci_default_read_config(dev, conf->addr, conf->len); + } + + ret.cmd = MPQEMU_CMD_RET; + ret.size = sizeof(ret.data.u64); + + if (!mpqemu_msg_send(&ret, ioc, NULL)) { + error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ", + getpid()); + } +} diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/mpqemu-link.c +++ b/hw/remote/mpqemu-link.c @@ -XXX,XX +XXX,XX @@ uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev, return ret; } - if (!mpqemu_msg_valid(&msg_reply)) { + if (!mpqemu_msg_valid(&msg_reply) || msg_reply.cmd != MPQEMU_CMD_RET) { error_setg(errp, "ERROR: Invalid reply received for command %d", msg->cmd); return ret; @@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg) return false; } break; + case MPQEMU_CMD_PCI_CFGWRITE: + case MPQEMU_CMD_PCI_CFGREAD: + if (msg->size != sizeof(PciConfDataMsg)) { + return false; + } + break; default: break; } diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/proxy.c +++ b/hw/remote/proxy.c @@ -XXX,XX +XXX,XX @@ #include "monitor/monitor.h" #include "migration/blocker.h" #include "qemu/sockets.h" +#include "hw/remote/mpqemu-link.h" +#include "qemu/error-report.h" static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_exit(PCIDevice *pdev) error_free(dev->migration_blocker); } +static void config_op_send(PCIProxyDev *pdev, uint32_t addr, uint32_t *val, + int len, unsigned int op) +{ + MPQemuMsg msg = { 0 }; + uint64_t ret = -EINVAL; + Error *local_err = NULL; + + msg.cmd = op; + msg.data.pci_conf_data.addr = addr; + msg.data.pci_conf_data.val = (op == MPQEMU_CMD_PCI_CFGWRITE) ? *val : 0; + msg.data.pci_conf_data.len = len; + msg.size = sizeof(PciConfDataMsg); + + ret = mpqemu_msg_send_and_await_reply(&msg, pdev, &local_err); + if (local_err) { + error_report_err(local_err); + } + + if (ret == UINT64_MAX) { + error_report("Failed to perform PCI config %s operation", + (op == MPQEMU_CMD_PCI_CFGREAD) ? "READ" : "WRITE"); + } + + if (op == MPQEMU_CMD_PCI_CFGREAD) { + *val = (uint32_t)ret; + } +} + +static uint32_t pci_proxy_read_config(PCIDevice *d, uint32_t addr, int len) +{ + uint32_t val; + + config_op_send(PCI_PROXY_DEV(d), addr, &val, len, MPQEMU_CMD_PCI_CFGREAD); + + return val; +} + +static void pci_proxy_write_config(PCIDevice *d, uint32_t addr, uint32_t val, + int len) +{ + /* + * Some of the functions access the copy of remote device's PCI config + * space which is cached in the proxy device. Therefore, maintain + * it updated. + */ + pci_default_write_config(d, addr, val, len); + + config_op_send(PCI_PROXY_DEV(d), addr, &val, len, MPQEMU_CMD_PCI_CFGWRITE); +} + static Property proxy_properties[] = { DEFINE_PROP_STRING("fd", PCIProxyDev, fd), DEFINE_PROP_END_OF_LIST(), @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_class_init(ObjectClass *klass, void *data) k->realize = pci_proxy_dev_realize; k->exit = pci_proxy_dev_exit; + k->config_read = pci_proxy_read_config; + k->config_write = pci_proxy_write_config; + device_class_set_props(dc, proxy_properties); } -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> Proxy device object implements handler for PCI BAR writes and reads. The handler uses BAR_WRITE/BAR_READ message to communicate to the remote process with the BAR address and value to be written/read. The remote process implements handler for BAR_WRITE/BAR_READ message. Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: a8b76714a9688be5552c4c92d089bc9e8a4707ff.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/hw/remote/mpqemu-link.h | 10 ++++ include/hw/remote/proxy.h | 9 ++++ hw/remote/message.c | 83 +++++++++++++++++++++++++++++++++ hw/remote/mpqemu-link.c | 6 +++ hw/remote/proxy.c | 60 ++++++++++++++++++++++++ 5 files changed, 168 insertions(+) diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/mpqemu-link.h +++ b/include/hw/remote/mpqemu-link.h @@ -XXX,XX +XXX,XX @@ typedef enum { MPQEMU_CMD_RET, MPQEMU_CMD_PCI_CFGWRITE, MPQEMU_CMD_PCI_CFGREAD, + MPQEMU_CMD_BAR_WRITE, + MPQEMU_CMD_BAR_READ, MPQEMU_CMD_MAX, } MPQemuCmd; @@ -XXX,XX +XXX,XX @@ typedef struct { int len; } PciConfDataMsg; +typedef struct { + hwaddr addr; + uint64_t val; + unsigned size; + bool memory; +} BarAccessMsg; + /** * MPQemuMsg: * @cmd: The remote command @@ -XXX,XX +XXX,XX @@ typedef struct { uint64_t u64; PciConfDataMsg pci_conf_data; SyncSysmemMsg sync_sysmem; + BarAccessMsg bar_access; } data; int fds[REMOTE_MAX_FDS]; diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/proxy.h +++ b/include/hw/remote/proxy.h @@ -XXX,XX +XXX,XX @@ #define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev" OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV) +typedef struct ProxyMemoryRegion { + PCIProxyDev *dev; + MemoryRegion mr; + bool memory; + bool present; + uint8_t type; +} ProxyMemoryRegion; + struct PCIProxyDev { PCIDevice parent_dev; char *fd; @@ -XXX,XX +XXX,XX @@ struct PCIProxyDev { QemuMutex io_mutex; QIOChannel *ioc; Error *migration_blocker; + ProxyMemoryRegion region[PCI_NUM_REGIONS]; }; #endif /* PROXY_H */ diff --git a/hw/remote/message.c b/hw/remote/message.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/message.c +++ b/hw/remote/message.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "sysemu/runstate.h" #include "hw/pci/pci.h" +#include "exec/memattrs.h" static void process_config_write(QIOChannel *ioc, PCIDevice *dev, MPQemuMsg *msg, Error **errp); static void process_config_read(QIOChannel *ioc, PCIDevice *dev, MPQemuMsg *msg, Error **errp); +static void process_bar_write(QIOChannel *ioc, MPQemuMsg *msg, Error **errp); +static void process_bar_read(QIOChannel *ioc, MPQemuMsg *msg, Error **errp); void coroutine_fn mpqemu_remote_msg_loop_co(void *data) { @@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data) case MPQEMU_CMD_PCI_CFGREAD: process_config_read(com->ioc, pci_dev, &msg, &local_err); break; + case MPQEMU_CMD_BAR_WRITE: + process_bar_write(com->ioc, &msg, &local_err); + break; + case MPQEMU_CMD_BAR_READ: + process_bar_read(com->ioc, &msg, &local_err); + break; default: error_setg(&local_err, "Unknown command (%d) received for device %s" @@ -XXX,XX +XXX,XX @@ static void process_config_read(QIOChannel *ioc, PCIDevice *dev, getpid()); } } + +static void process_bar_write(QIOChannel *ioc, MPQemuMsg *msg, Error **errp) +{ + ERRP_GUARD(); + BarAccessMsg *bar_access = &msg->data.bar_access; + AddressSpace *as = + bar_access->memory ? &address_space_memory : &address_space_io; + MPQemuMsg ret = { 0 }; + MemTxResult res; + uint64_t val; + + if (!is_power_of_2(bar_access->size) || + (bar_access->size > sizeof(uint64_t))) { + ret.data.u64 = UINT64_MAX; + goto fail; + } + + val = cpu_to_le64(bar_access->val); + + res = address_space_rw(as, bar_access->addr, MEMTXATTRS_UNSPECIFIED, + (void *)&val, bar_access->size, true); + + if (res != MEMTX_OK) { + error_setg(errp, "Bad address %"PRIx64" for mem write, pid "FMT_pid".", + bar_access->addr, getpid()); + ret.data.u64 = -1; + } + +fail: + ret.cmd = MPQEMU_CMD_RET; + ret.size = sizeof(ret.data.u64); + + if (!mpqemu_msg_send(&ret, ioc, NULL)) { + error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ", + getpid()); + } +} + +static void process_bar_read(QIOChannel *ioc, MPQemuMsg *msg, Error **errp) +{ + ERRP_GUARD(); + BarAccessMsg *bar_access = &msg->data.bar_access; + MPQemuMsg ret = { 0 }; + AddressSpace *as; + MemTxResult res; + uint64_t val = 0; + + as = bar_access->memory ? &address_space_memory : &address_space_io; + + if (!is_power_of_2(bar_access->size) || + (bar_access->size > sizeof(uint64_t))) { + val = UINT64_MAX; + goto fail; + } + + res = address_space_rw(as, bar_access->addr, MEMTXATTRS_UNSPECIFIED, + (void *)&val, bar_access->size, false); + + if (res != MEMTX_OK) { + error_setg(errp, "Bad address %"PRIx64" for mem read, pid "FMT_pid".", + bar_access->addr, getpid()); + val = UINT64_MAX; + } + +fail: + ret.cmd = MPQEMU_CMD_RET; + ret.data.u64 = le64_to_cpu(val); + ret.size = sizeof(ret.data.u64); + + if (!mpqemu_msg_send(&ret, ioc, NULL)) { + error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ", + getpid()); + } +} diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/mpqemu-link.c +++ b/hw/remote/mpqemu-link.c @@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg) return false; } break; + case MPQEMU_CMD_BAR_WRITE: + case MPQEMU_CMD_BAR_READ: + if ((msg->size != sizeof(BarAccessMsg)) || (msg->num_fds != 0)) { + return false; + } + break; default: break; } diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/proxy.c +++ b/hw/remote/proxy.c @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_register_types(void) } type_init(pci_proxy_dev_register_types) + +static void send_bar_access_msg(PCIProxyDev *pdev, MemoryRegion *mr, + bool write, hwaddr addr, uint64_t *val, + unsigned size, bool memory) +{ + MPQemuMsg msg = { 0 }; + long ret = -EINVAL; + Error *local_err = NULL; + + msg.size = sizeof(BarAccessMsg); + msg.data.bar_access.addr = mr->addr + addr; + msg.data.bar_access.size = size; + msg.data.bar_access.memory = memory; + + if (write) { + msg.cmd = MPQEMU_CMD_BAR_WRITE; + msg.data.bar_access.val = *val; + } else { + msg.cmd = MPQEMU_CMD_BAR_READ; + } + + ret = mpqemu_msg_send_and_await_reply(&msg, pdev, &local_err); + if (local_err) { + error_report_err(local_err); + } + + if (!write) { + *val = ret; + } +} + +static void proxy_bar_write(void *opaque, hwaddr addr, uint64_t val, + unsigned size) +{ + ProxyMemoryRegion *pmr = opaque; + + send_bar_access_msg(pmr->dev, &pmr->mr, true, addr, &val, size, + pmr->memory); +} + +static uint64_t proxy_bar_read(void *opaque, hwaddr addr, unsigned size) +{ + ProxyMemoryRegion *pmr = opaque; + uint64_t val; + + send_bar_access_msg(pmr->dev, &pmr->mr, false, addr, &val, size, + pmr->memory); + + return val; +} + +const MemoryRegionOps proxy_mr_ops = { + .read = proxy_bar_read, + .write = proxy_bar_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + .min_access_size = 1, + .max_access_size = 8, + }, +}; -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> Add ProxyMemoryListener object which is used to keep the view of the RAM in sync between QEMU and remote process. A MemoryListener is registered for system-memory AddressSpace. The listener sends SYNC_SYSMEM message to the remote process when memory listener commits the changes to memory, the remote process receives the message and processes it in the handler for SYNC_SYSMEM message. Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 04fe4e6a9ca90d4f11ab6f59be7652f5b086a071.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 2 + include/hw/remote/proxy-memory-listener.h | 28 +++ include/hw/remote/proxy.h | 2 + hw/remote/message.c | 4 + hw/remote/proxy-memory-listener.c | 227 ++++++++++++++++++++++ hw/remote/proxy.c | 6 + hw/remote/meson.build | 1 + 7 files changed, 270 insertions(+) create mode 100644 include/hw/remote/proxy-memory-listener.h create mode 100644 hw/remote/proxy-memory-listener.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/hw/remote/memory.h F: hw/remote/memory.c F: hw/remote/proxy.c F: include/hw/remote/proxy.h +F: hw/remote/proxy-memory-listener.c +F: include/hw/remote/proxy-memory-listener.h Build and test automation ------------------------- diff --git a/include/hw/remote/proxy-memory-listener.h b/include/hw/remote/proxy-memory-listener.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/remote/proxy-memory-listener.h @@ -XXX,XX +XXX,XX @@ +/* + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * 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 PROXY_MEMORY_LISTENER_H +#define PROXY_MEMORY_LISTENER_H + +#include "exec/memory.h" +#include "io/channel.h" + +typedef struct ProxyMemoryListener { + MemoryListener listener; + + int n_mr_sections; + MemoryRegionSection *mr_sections; + + QIOChannel *ioc; +} ProxyMemoryListener; + +void proxy_memory_listener_configure(ProxyMemoryListener *proxy_listener, + QIOChannel *ioc); +void proxy_memory_listener_deconfigure(ProxyMemoryListener *proxy_listener); + +#endif diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/proxy.h +++ b/include/hw/remote/proxy.h @@ -XXX,XX +XXX,XX @@ #include "hw/pci/pci.h" #include "io/channel.h" +#include "hw/remote/proxy-memory-listener.h" #define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev" OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV) @@ -XXX,XX +XXX,XX @@ struct PCIProxyDev { QemuMutex io_mutex; QIOChannel *ioc; Error *migration_blocker; + ProxyMemoryListener proxy_listener; ProxyMemoryRegion region[PCI_NUM_REGIONS]; }; diff --git a/hw/remote/message.c b/hw/remote/message.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/message.c +++ b/hw/remote/message.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/runstate.h" #include "hw/pci/pci.h" #include "exec/memattrs.h" +#include "hw/remote/memory.h" static void process_config_write(QIOChannel *ioc, PCIDevice *dev, MPQemuMsg *msg, Error **errp); @@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data) case MPQEMU_CMD_BAR_READ: process_bar_read(com->ioc, &msg, &local_err); break; + case MPQEMU_CMD_SYNC_SYSMEM: + remote_sysmem_reconfig(&msg, &local_err); + break; default: error_setg(&local_err, "Unknown command (%d) received for device %s" diff --git a/hw/remote/proxy-memory-listener.c b/hw/remote/proxy-memory-listener.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/proxy-memory-listener.c @@ -XXX,XX +XXX,XX @@ +/* + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * 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-common.h" + +#include "qemu/compiler.h" +#include "qemu/int128.h" +#include "qemu/range.h" +#include "exec/memory.h" +#include "exec/cpu-common.h" +#include "cpu.h" +#include "exec/ram_addr.h" +#include "exec/address-spaces.h" +#include "qapi/error.h" +#include "hw/remote/mpqemu-link.h" +#include "hw/remote/proxy-memory-listener.h" + +/* + * TODO: get_fd_from_hostaddr(), proxy_mrs_can_merge() and + * proxy_memory_listener_commit() defined below perform tasks similar to the + * functions defined in vhost-user.c. These functions are good candidates + * for refactoring. + * + */ + +static void proxy_memory_listener_reset(MemoryListener *listener) +{ + ProxyMemoryListener *proxy_listener = container_of(listener, + ProxyMemoryListener, + listener); + int mrs; + + for (mrs = 0; mrs < proxy_listener->n_mr_sections; mrs++) { + memory_region_unref(proxy_listener->mr_sections[mrs].mr); + } + + g_free(proxy_listener->mr_sections); + proxy_listener->mr_sections = NULL; + proxy_listener->n_mr_sections = 0; +} + +static int get_fd_from_hostaddr(uint64_t host, ram_addr_t *offset) +{ + MemoryRegion *mr; + ram_addr_t off; + + /** + * Assumes that the host address is a valid address as it's + * coming from the MemoryListener system. In the case host + * address is not valid, the following call would return + * the default subregion of "system_memory" region, and + * not NULL. So it's not possible to check for NULL here. + */ + mr = memory_region_from_host((void *)(uintptr_t)host, &off); + + if (offset) { + *offset = off; + } + + return memory_region_get_fd(mr); +} + +static bool proxy_mrs_can_merge(uint64_t host, uint64_t prev_host, size_t size) +{ + if (((prev_host + size) != host)) { + return false; + } + + if (get_fd_from_hostaddr(host, NULL) != + get_fd_from_hostaddr(prev_host, NULL)) { + return false; + } + + return true; +} + +static bool try_merge(ProxyMemoryListener *proxy_listener, + MemoryRegionSection *section) +{ + uint64_t mrs_size, mrs_gpa, mrs_page; + MemoryRegionSection *prev_sec; + bool merged = false; + uintptr_t mrs_host; + RAMBlock *mrs_rb; + + if (!proxy_listener->n_mr_sections) { + return false; + } + + mrs_rb = section->mr->ram_block; + mrs_page = (uint64_t)qemu_ram_pagesize(mrs_rb); + mrs_size = int128_get64(section->size); + mrs_gpa = section->offset_within_address_space; + mrs_host = (uintptr_t)memory_region_get_ram_ptr(section->mr) + + section->offset_within_region; + + if (get_fd_from_hostaddr(mrs_host, NULL) < 0) { + return true; + } + + mrs_host = mrs_host & ~(mrs_page - 1); + mrs_gpa = mrs_gpa & ~(mrs_page - 1); + mrs_size = ROUND_UP(mrs_size, mrs_page); + + prev_sec = proxy_listener->mr_sections + + (proxy_listener->n_mr_sections - 1); + uint64_t prev_gpa_start = prev_sec->offset_within_address_space; + uint64_t prev_size = int128_get64(prev_sec->size); + uint64_t prev_gpa_end = range_get_last(prev_gpa_start, prev_size); + uint64_t prev_host_start = + (uintptr_t)memory_region_get_ram_ptr(prev_sec->mr) + + prev_sec->offset_within_region; + uint64_t prev_host_end = range_get_last(prev_host_start, prev_size); + + if (mrs_gpa <= (prev_gpa_end + 1)) { + g_assert(mrs_gpa > prev_gpa_start); + + if ((section->mr == prev_sec->mr) && + proxy_mrs_can_merge(mrs_host, prev_host_start, + (mrs_gpa - prev_gpa_start))) { + uint64_t max_end = MAX(prev_host_end, mrs_host + mrs_size); + merged = true; + prev_sec->offset_within_address_space = + MIN(prev_gpa_start, mrs_gpa); + prev_sec->offset_within_region = + MIN(prev_host_start, mrs_host) - + (uintptr_t)memory_region_get_ram_ptr(prev_sec->mr); + prev_sec->size = int128_make64(max_end - MIN(prev_host_start, + mrs_host)); + } + } + + return merged; +} + +static void proxy_memory_listener_region_addnop(MemoryListener *listener, + MemoryRegionSection *section) +{ + ProxyMemoryListener *proxy_listener = container_of(listener, + ProxyMemoryListener, + listener); + + if (!memory_region_is_ram(section->mr) || + memory_region_is_rom(section->mr)) { + return; + } + + if (try_merge(proxy_listener, section)) { + return; + } + + ++proxy_listener->n_mr_sections; + proxy_listener->mr_sections = g_renew(MemoryRegionSection, + proxy_listener->mr_sections, + proxy_listener->n_mr_sections); + proxy_listener->mr_sections[proxy_listener->n_mr_sections - 1] = *section; + proxy_listener->mr_sections[proxy_listener->n_mr_sections - 1].fv = NULL; + memory_region_ref(section->mr); +} + +static void proxy_memory_listener_commit(MemoryListener *listener) +{ + ProxyMemoryListener *proxy_listener = container_of(listener, + ProxyMemoryListener, + listener); + MPQemuMsg msg; + MemoryRegionSection *section; + ram_addr_t offset; + uintptr_t host_addr; + int region; + Error *local_err = NULL; + + memset(&msg, 0, sizeof(MPQemuMsg)); + + msg.cmd = MPQEMU_CMD_SYNC_SYSMEM; + msg.num_fds = proxy_listener->n_mr_sections; + msg.size = sizeof(SyncSysmemMsg); + if (msg.num_fds > REMOTE_MAX_FDS) { + error_report("Number of fds is more than %d", REMOTE_MAX_FDS); + return; + } + + for (region = 0; region < proxy_listener->n_mr_sections; region++) { + section = &proxy_listener->mr_sections[region]; + msg.data.sync_sysmem.gpas[region] = + section->offset_within_address_space; + msg.data.sync_sysmem.sizes[region] = int128_get64(section->size); + host_addr = (uintptr_t)memory_region_get_ram_ptr(section->mr) + + section->offset_within_region; + msg.fds[region] = get_fd_from_hostaddr(host_addr, &offset); + msg.data.sync_sysmem.offsets[region] = offset; + } + if (!mpqemu_msg_send(&msg, proxy_listener->ioc, &local_err)) { + error_report_err(local_err); + } +} + +void proxy_memory_listener_deconfigure(ProxyMemoryListener *proxy_listener) +{ + memory_listener_unregister(&proxy_listener->listener); + + proxy_memory_listener_reset(&proxy_listener->listener); +} + +void proxy_memory_listener_configure(ProxyMemoryListener *proxy_listener, + QIOChannel *ioc) +{ + proxy_listener->n_mr_sections = 0; + proxy_listener->mr_sections = NULL; + + proxy_listener->ioc = ioc; + + proxy_listener->listener.begin = proxy_memory_listener_reset; + proxy_listener->listener.commit = proxy_memory_listener_commit; + proxy_listener->listener.region_add = proxy_memory_listener_region_addnop; + proxy_listener->listener.region_nop = proxy_memory_listener_region_addnop; + proxy_listener->listener.priority = 10; + + memory_listener_register(&proxy_listener->listener, + &address_space_memory); +} diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/proxy.c +++ b/hw/remote/proxy.c @@ -XXX,XX +XXX,XX @@ #include "qemu/sockets.h" #include "hw/remote/mpqemu-link.h" #include "qemu/error-report.h" +#include "hw/remote/proxy-memory-listener.h" +#include "qom/object.h" static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) qemu_mutex_init(&dev->io_mutex); qio_channel_set_blocking(dev->ioc, true, NULL); + + proxy_memory_listener_configure(&dev->proxy_listener, dev->ioc); } static void pci_proxy_dev_exit(PCIDevice *pdev) @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_exit(PCIDevice *pdev) migrate_del_blocker(dev->migration_blocker); error_free(dev->migration_blocker); + + proxy_memory_listener_deconfigure(&dev->proxy_listener); } static void config_op_send(PCIProxyDev *pdev, uint32_t addr, uint32_t *val, diff --git a/hw/remote/meson.build b/hw/remote/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/meson.build +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c')) specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c')) +specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy-memory-listener.c')) softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss) -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> IOHUB object is added to manage PCI IRQs. It uses KVM_IRQFD ioctl to create irqfd to injecting PCI interrupts to the guest. IOHUB object forwards the irqfd to the remote process. Remote process uses this fd to directly send interrupts to the guest, bypassing QEMU. Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 51d5c3d54e28a68b002e3875c59599c9f5a424a1.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 2 + include/hw/pci/pci_ids.h | 3 + include/hw/remote/iohub.h | 42 +++++++++++ include/hw/remote/machine.h | 2 + include/hw/remote/mpqemu-link.h | 1 + include/hw/remote/proxy.h | 4 ++ hw/remote/iohub.c | 119 ++++++++++++++++++++++++++++++++ hw/remote/machine.c | 10 +++ hw/remote/message.c | 4 ++ hw/remote/mpqemu-link.c | 5 ++ hw/remote/proxy.c | 56 +++++++++++++++ hw/remote/meson.build | 1 + 12 files changed, 249 insertions(+) create mode 100644 include/hw/remote/iohub.h create mode 100644 hw/remote/iohub.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/remote/proxy.c F: include/hw/remote/proxy.h F: hw/remote/proxy-memory-listener.c F: include/hw/remote/proxy-memory-listener.h +F: hw/remote/iohub.c +F: include/hw/remote/iohub.h Build and test automation ------------------------- diff --git a/include/hw/pci/pci_ids.h b/include/hw/pci/pci_ids.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/pci/pci_ids.h +++ b/include/hw/pci/pci_ids.h @@ -XXX,XX +XXX,XX @@ #define PCI_DEVICE_ID_SUN_SIMBA 0x5000 #define PCI_DEVICE_ID_SUN_SABRE 0xa000 +#define PCI_VENDOR_ID_ORACLE 0x108e +#define PCI_DEVICE_ID_REMOTE_IOHUB 0xb000 + #define PCI_VENDOR_ID_CMD 0x1095 #define PCI_DEVICE_ID_CMD_646 0x0646 diff --git a/include/hw/remote/iohub.h b/include/hw/remote/iohub.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/remote/iohub.h @@ -XXX,XX +XXX,XX @@ +/* + * IO Hub for remote device + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * 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 REMOTE_IOHUB_H +#define REMOTE_IOHUB_H + +#include "hw/pci/pci.h" +#include "qemu/event_notifier.h" +#include "qemu/thread-posix.h" +#include "hw/remote/mpqemu-link.h" + +#define REMOTE_IOHUB_NB_PIRQS PCI_DEVFN_MAX + +typedef struct ResampleToken { + void *iohub; + int pirq; +} ResampleToken; + +typedef struct RemoteIOHubState { + PCIDevice d; + EventNotifier irqfds[REMOTE_IOHUB_NB_PIRQS]; + EventNotifier resamplefds[REMOTE_IOHUB_NB_PIRQS]; + unsigned int irq_level[REMOTE_IOHUB_NB_PIRQS]; + ResampleToken token[REMOTE_IOHUB_NB_PIRQS]; + QemuMutex irq_level_lock[REMOTE_IOHUB_NB_PIRQS]; +} RemoteIOHubState; + +int remote_iohub_map_irq(PCIDevice *pci_dev, int intx); +void remote_iohub_set_irq(void *opaque, int pirq, int level); +void process_set_irqfd_msg(PCIDevice *pci_dev, MPQemuMsg *msg); + +void remote_iohub_init(RemoteIOHubState *iohub); +void remote_iohub_finalize(RemoteIOHubState *iohub); + +#endif diff --git a/include/hw/remote/machine.h b/include/hw/remote/machine.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/machine.h +++ b/include/hw/remote/machine.h @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/pci-host/remote.h" #include "io/channel.h" +#include "hw/remote/iohub.h" struct RemoteMachineState { MachineState parent_obj; RemotePCIHost *host; + RemoteIOHubState iohub; }; /* Used to pass to co-routine device and ioc. */ diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/mpqemu-link.h +++ b/include/hw/remote/mpqemu-link.h @@ -XXX,XX +XXX,XX @@ typedef enum { MPQEMU_CMD_PCI_CFGREAD, MPQEMU_CMD_BAR_WRITE, MPQEMU_CMD_BAR_READ, + MPQEMU_CMD_SET_IRQFD, MPQEMU_CMD_MAX, } MPQemuCmd; diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/proxy.h +++ b/include/hw/remote/proxy.h @@ -XXX,XX +XXX,XX @@ #include "hw/pci/pci.h" #include "io/channel.h" #include "hw/remote/proxy-memory-listener.h" +#include "qemu/event_notifier.h" #define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev" OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV) @@ -XXX,XX +XXX,XX @@ struct PCIProxyDev { QIOChannel *ioc; Error *migration_blocker; ProxyMemoryListener proxy_listener; + int virq; + EventNotifier intr; + EventNotifier resample; ProxyMemoryRegion region[PCI_NUM_REGIONS]; }; diff --git a/hw/remote/iohub.c b/hw/remote/iohub.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/iohub.c @@ -XXX,XX +XXX,XX @@ +/* + * Remote IO Hub + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * 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-common.h" + +#include "hw/pci/pci.h" +#include "hw/pci/pci_ids.h" +#include "hw/pci/pci_bus.h" +#include "qemu/thread.h" +#include "hw/boards.h" +#include "hw/remote/machine.h" +#include "hw/remote/iohub.h" +#include "qemu/main-loop.h" + +void remote_iohub_init(RemoteIOHubState *iohub) +{ + int pirq; + + memset(&iohub->irqfds, 0, sizeof(iohub->irqfds)); + memset(&iohub->resamplefds, 0, sizeof(iohub->resamplefds)); + + for (pirq = 0; pirq < REMOTE_IOHUB_NB_PIRQS; pirq++) { + qemu_mutex_init(&iohub->irq_level_lock[pirq]); + iohub->irq_level[pirq] = 0; + event_notifier_init_fd(&iohub->irqfds[pirq], -1); + event_notifier_init_fd(&iohub->resamplefds[pirq], -1); + } +} + +void remote_iohub_finalize(RemoteIOHubState *iohub) +{ + int pirq; + + for (pirq = 0; pirq < REMOTE_IOHUB_NB_PIRQS; pirq++) { + qemu_set_fd_handler(event_notifier_get_fd(&iohub->resamplefds[pirq]), + NULL, NULL, NULL); + event_notifier_cleanup(&iohub->irqfds[pirq]); + event_notifier_cleanup(&iohub->resamplefds[pirq]); + qemu_mutex_destroy(&iohub->irq_level_lock[pirq]); + } +} + +int remote_iohub_map_irq(PCIDevice *pci_dev, int intx) +{ + return pci_dev->devfn; +} + +void remote_iohub_set_irq(void *opaque, int pirq, int level) +{ + RemoteIOHubState *iohub = opaque; + + assert(pirq >= 0); + assert(pirq < PCI_DEVFN_MAX); + + QEMU_LOCK_GUARD(&iohub->irq_level_lock[pirq]); + + if (level) { + if (++iohub->irq_level[pirq] == 1) { + event_notifier_set(&iohub->irqfds[pirq]); + } + } else if (iohub->irq_level[pirq] > 0) { + iohub->irq_level[pirq]--; + } +} + +static void intr_resample_handler(void *opaque) +{ + ResampleToken *token = opaque; + RemoteIOHubState *iohub = token->iohub; + int pirq, s; + + pirq = token->pirq; + + s = event_notifier_test_and_clear(&iohub->resamplefds[pirq]); + + assert(s >= 0); + + QEMU_LOCK_GUARD(&iohub->irq_level_lock[pirq]); + + if (iohub->irq_level[pirq]) { + event_notifier_set(&iohub->irqfds[pirq]); + } +} + +void process_set_irqfd_msg(PCIDevice *pci_dev, MPQemuMsg *msg) +{ + RemoteMachineState *machine = REMOTE_MACHINE(current_machine); + RemoteIOHubState *iohub = &machine->iohub; + int pirq, intx; + + intx = pci_get_byte(pci_dev->config + PCI_INTERRUPT_PIN) - 1; + + pirq = remote_iohub_map_irq(pci_dev, intx); + + if (event_notifier_get_fd(&iohub->irqfds[pirq]) != -1) { + qemu_set_fd_handler(event_notifier_get_fd(&iohub->resamplefds[pirq]), + NULL, NULL, NULL); + event_notifier_cleanup(&iohub->irqfds[pirq]); + event_notifier_cleanup(&iohub->resamplefds[pirq]); + memset(&iohub->token[pirq], 0, sizeof(ResampleToken)); + } + + event_notifier_init_fd(&iohub->irqfds[pirq], msg->fds[0]); + event_notifier_init_fd(&iohub->resamplefds[pirq], msg->fds[1]); + + iohub->token[pirq].iohub = iohub; + iohub->token[pirq].pirq = pirq; + + qemu_set_fd_handler(msg->fds[1], intr_resample_handler, NULL, + &iohub->token[pirq]); +} diff --git a/hw/remote/machine.c b/hw/remote/machine.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/machine.c +++ b/hw/remote/machine.c @@ -XXX,XX +XXX,XX @@ #include "exec/address-spaces.h" #include "exec/memory.h" #include "qapi/error.h" +#include "hw/pci/pci_host.h" +#include "hw/remote/iohub.h" static void remote_machine_init(MachineState *machine) { MemoryRegion *system_memory, *system_io, *pci_memory; RemoteMachineState *s = REMOTE_MACHINE(machine); RemotePCIHost *rem_host; + PCIHostState *pci_host; system_memory = get_system_memory(); system_io = get_system_io(); @@ -XXX,XX +XXX,XX @@ static void remote_machine_init(MachineState *machine) memory_region_add_subregion_overlap(system_memory, 0x0, pci_memory, -1); qdev_realize(DEVICE(rem_host), sysbus_get_default(), &error_fatal); + + pci_host = PCI_HOST_BRIDGE(rem_host); + + remote_iohub_init(&s->iohub); + + pci_bus_irqs(pci_host->bus, remote_iohub_set_irq, remote_iohub_map_irq, + &s->iohub, REMOTE_IOHUB_NB_PIRQS); } static void remote_machine_class_init(ObjectClass *oc, void *data) diff --git a/hw/remote/message.c b/hw/remote/message.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/message.c +++ b/hw/remote/message.c @@ -XXX,XX +XXX,XX @@ #include "hw/pci/pci.h" #include "exec/memattrs.h" #include "hw/remote/memory.h" +#include "hw/remote/iohub.h" static void process_config_write(QIOChannel *ioc, PCIDevice *dev, MPQemuMsg *msg, Error **errp); @@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data) case MPQEMU_CMD_SYNC_SYSMEM: remote_sysmem_reconfig(&msg, &local_err); break; + case MPQEMU_CMD_SET_IRQFD: + process_set_irqfd_msg(pci_dev, &msg); + break; default: error_setg(&local_err, "Unknown command (%d) received for device %s" diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/mpqemu-link.c +++ b/hw/remote/mpqemu-link.c @@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg) return false; } break; + case MPQEMU_CMD_SET_IRQFD: + if (msg->size || (msg->num_fds != 2)) { + return false; + } + break; default: break; } diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/proxy.c +++ b/hw/remote/proxy.c @@ -XXX,XX +XXX,XX @@ #include "qemu/error-report.h" #include "hw/remote/proxy-memory-listener.h" #include "qom/object.h" +#include "qemu/event_notifier.h" +#include "sysemu/kvm.h" +#include "util/event_notifier-posix.c" + +static void proxy_intx_update(PCIDevice *pci_dev) +{ + PCIProxyDev *dev = PCI_PROXY_DEV(pci_dev); + PCIINTxRoute route; + int pin = pci_get_byte(pci_dev->config + PCI_INTERRUPT_PIN) - 1; + + if (dev->virq != -1) { + kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, &dev->intr, dev->virq); + dev->virq = -1; + } + + route = pci_device_route_intx_to_irq(pci_dev, pin); + + dev->virq = route.irq; + + if (dev->virq != -1) { + kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, &dev->intr, + &dev->resample, dev->virq); + } +} + +static void setup_irqfd(PCIProxyDev *dev) +{ + PCIDevice *pci_dev = PCI_DEVICE(dev); + MPQemuMsg msg; + Error *local_err = NULL; + + event_notifier_init(&dev->intr, 0); + event_notifier_init(&dev->resample, 0); + + memset(&msg, 0, sizeof(MPQemuMsg)); + msg.cmd = MPQEMU_CMD_SET_IRQFD; + msg.num_fds = 2; + msg.fds[0] = event_notifier_get_fd(&dev->intr); + msg.fds[1] = event_notifier_get_fd(&dev->resample); + msg.size = 0; + + if (!mpqemu_msg_send(&msg, dev->ioc, &local_err)) { + error_report_err(local_err); + } + + dev->virq = -1; + + proxy_intx_update(pci_dev); + + pci_device_set_intx_routing_notifier(pci_dev, proxy_intx_update); +} static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) qio_channel_set_blocking(dev->ioc, true, NULL); proxy_memory_listener_configure(&dev->proxy_listener, dev->ioc); + + setup_irqfd(dev); } static void pci_proxy_dev_exit(PCIDevice *pdev) @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_exit(PCIDevice *pdev) error_free(dev->migration_blocker); proxy_memory_listener_deconfigure(&dev->proxy_listener); + + event_notifier_cleanup(&dev->intr); + event_notifier_cleanup(&dev->resample); } static void config_op_send(PCIProxyDev *pdev, uint32_t addr, uint32_t *val, diff --git a/hw/remote/meson.build b/hw/remote/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/meson.build +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c')) +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('iohub.c')) specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c')) specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy-memory-listener.c')) -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> Retrieve PCI configuration info about the remote device and configure the Proxy PCI object based on the returned information Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 85ee367bbb993aa23699b44cfedd83b4ea6d5221.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- hw/remote/proxy.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/proxy.c +++ b/hw/remote/proxy.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/kvm.h" #include "util/event_notifier-posix.c" +static void probe_pci_info(PCIDevice *dev, Error **errp); + static void proxy_intx_update(PCIDevice *pci_dev) { PCIProxyDev *dev = PCI_PROXY_DEV(pci_dev); @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) { ERRP_GUARD(); PCIProxyDev *dev = PCI_PROXY_DEV(device); + uint8_t *pci_conf = device->config; int fd; if (!dev->fd) { @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) qemu_mutex_init(&dev->io_mutex); qio_channel_set_blocking(dev->ioc, true, NULL); + pci_conf[PCI_LATENCY_TIMER] = 0xff; + pci_conf[PCI_INTERRUPT_PIN] = 0x01; + proxy_memory_listener_configure(&dev->proxy_listener, dev->ioc); setup_irqfd(dev); + + probe_pci_info(PCI_DEVICE(dev), errp); } static void pci_proxy_dev_exit(PCIDevice *pdev) @@ -XXX,XX +XXX,XX @@ const MemoryRegionOps proxy_mr_ops = { .max_access_size = 8, }, }; + +static void probe_pci_info(PCIDevice *dev, Error **errp) +{ + PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(dev); + uint32_t orig_val, new_val, base_class, val; + PCIProxyDev *pdev = PCI_PROXY_DEV(dev); + DeviceClass *dc = DEVICE_CLASS(pc); + uint8_t type; + int i, size; + + config_op_send(pdev, PCI_VENDOR_ID, &val, 2, MPQEMU_CMD_PCI_CFGREAD); + pc->vendor_id = (uint16_t)val; + + config_op_send(pdev, PCI_DEVICE_ID, &val, 2, MPQEMU_CMD_PCI_CFGREAD); + pc->device_id = (uint16_t)val; + + config_op_send(pdev, PCI_CLASS_DEVICE, &val, 2, MPQEMU_CMD_PCI_CFGREAD); + pc->class_id = (uint16_t)val; + + config_op_send(pdev, PCI_SUBSYSTEM_ID, &val, 2, MPQEMU_CMD_PCI_CFGREAD); + pc->subsystem_id = (uint16_t)val; + + base_class = pc->class_id >> 4; + switch (base_class) { + case PCI_BASE_CLASS_BRIDGE: + set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories); + break; + case PCI_BASE_CLASS_STORAGE: + set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); + break; + case PCI_BASE_CLASS_NETWORK: + set_bit(DEVICE_CATEGORY_NETWORK, dc->categories); + break; + case PCI_BASE_CLASS_INPUT: + set_bit(DEVICE_CATEGORY_INPUT, dc->categories); + break; + case PCI_BASE_CLASS_DISPLAY: + set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories); + break; + case PCI_BASE_CLASS_PROCESSOR: + set_bit(DEVICE_CATEGORY_CPU, dc->categories); + break; + default: + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + break; + } + + for (i = 0; i < PCI_NUM_REGIONS; i++) { + config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &orig_val, 4, + MPQEMU_CMD_PCI_CFGREAD); + new_val = 0xffffffff; + config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &new_val, 4, + MPQEMU_CMD_PCI_CFGWRITE); + config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &new_val, 4, + MPQEMU_CMD_PCI_CFGREAD); + size = (~(new_val & 0xFFFFFFF0)) + 1; + config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &orig_val, 4, + MPQEMU_CMD_PCI_CFGWRITE); + type = (new_val & 0x1) ? + PCI_BASE_ADDRESS_SPACE_IO : PCI_BASE_ADDRESS_SPACE_MEMORY; + + if (size) { + g_autofree char *name; + pdev->region[i].dev = pdev; + pdev->region[i].present = true; + if (type == PCI_BASE_ADDRESS_SPACE_MEMORY) { + pdev->region[i].memory = true; + } + name = g_strdup_printf("bar-region-%d", i); + memory_region_init_io(&pdev->region[i].mr, OBJECT(pdev), + &proxy_mr_ops, &pdev->region[i], + name, size); + pci_register_bar(dev, i, type, &pdev->region[i].mr); + } + } +} -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> Perform device reset in the remote process when QEMU performs device reset. This is required to reset the internal state (like registers, etc...) of emulated devices Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 7cb220a51f565dc0817bd76e2f540e89c2d2b850.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/hw/remote/mpqemu-link.h | 1 + hw/remote/message.c | 22 ++++++++++++++++++++++ hw/remote/proxy.c | 19 +++++++++++++++++++ 3 files changed, 42 insertions(+) diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/mpqemu-link.h +++ b/include/hw/remote/mpqemu-link.h @@ -XXX,XX +XXX,XX @@ typedef enum { MPQEMU_CMD_BAR_WRITE, MPQEMU_CMD_BAR_READ, MPQEMU_CMD_SET_IRQFD, + MPQEMU_CMD_DEVICE_RESET, MPQEMU_CMD_MAX, } MPQemuCmd; diff --git a/hw/remote/message.c b/hw/remote/message.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/message.c +++ b/hw/remote/message.c @@ -XXX,XX +XXX,XX @@ #include "exec/memattrs.h" #include "hw/remote/memory.h" #include "hw/remote/iohub.h" +#include "sysemu/reset.h" static void process_config_write(QIOChannel *ioc, PCIDevice *dev, MPQemuMsg *msg, Error **errp); @@ -XXX,XX +XXX,XX @@ static void process_config_read(QIOChannel *ioc, PCIDevice *dev, MPQemuMsg *msg, Error **errp); static void process_bar_write(QIOChannel *ioc, MPQemuMsg *msg, Error **errp); static void process_bar_read(QIOChannel *ioc, MPQemuMsg *msg, Error **errp); +static void process_device_reset_msg(QIOChannel *ioc, PCIDevice *dev, + Error **errp); void coroutine_fn mpqemu_remote_msg_loop_co(void *data) { @@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data) case MPQEMU_CMD_SET_IRQFD: process_set_irqfd_msg(pci_dev, &msg); break; + case MPQEMU_CMD_DEVICE_RESET: + process_device_reset_msg(com->ioc, pci_dev, &local_err); + break; default: error_setg(&local_err, "Unknown command (%d) received for device %s" @@ -XXX,XX +XXX,XX @@ fail: getpid()); } } + +static void process_device_reset_msg(QIOChannel *ioc, PCIDevice *dev, + Error **errp) +{ + DeviceClass *dc = DEVICE_GET_CLASS(dev); + DeviceState *s = DEVICE(dev); + MPQemuMsg ret = { 0 }; + + if (dc->reset) { + dc->reset(s); + } + + ret.cmd = MPQEMU_CMD_RET; + + mpqemu_msg_send(&ret, ioc, errp); +} diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/proxy.c +++ b/hw/remote/proxy.c @@ -XXX,XX +XXX,XX @@ #include "util/event_notifier-posix.c" static void probe_pci_info(PCIDevice *dev, Error **errp); +static void proxy_device_reset(DeviceState *dev); static void proxy_intx_update(PCIDevice *pci_dev) { @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_class_init(ObjectClass *klass, void *data) k->config_read = pci_proxy_read_config; k->config_write = pci_proxy_write_config; + dc->reset = proxy_device_reset; + device_class_set_props(dc, proxy_properties); } @@ -XXX,XX +XXX,XX @@ static void probe_pci_info(PCIDevice *dev, Error **errp) } } } + +static void proxy_device_reset(DeviceState *dev) +{ + PCIProxyDev *pdev = PCI_PROXY_DEV(dev); + MPQemuMsg msg = { 0 }; + Error *local_err = NULL; + + msg.cmd = MPQEMU_CMD_DEVICE_RESET; + msg.size = 0; + + mpqemu_msg_send_and_await_reply(&msg, pdev, &local_err); + if (local_err) { + error_report_err(local_err); + } + +} -- 2.29.2 From: "Denis V. Lunev" <den@openvz.org> Original specification says that l1 table size if 64 * l1_size, which is obviously wrong. The size of the l1 entry is 64 _bits_, not bytes. Thus 64 is to be replaces with 8 as specification says about bytes. There is also minor tweak, field name is renamed from l1 to l1_table, which matches with the later text. Signed-off-by: Denis V. Lunev <den@openvz.org> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-id: 20210128171313.2210947-1-den@openvz.org CC: Stefan Hajnoczi <stefanha@redhat.com> CC: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> [Replace the original commit message "docs: fix mistake in dirty bitmap feature description" as suggested by Eric Blake. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- docs/interop/parallels.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/interop/parallels.txt b/docs/interop/parallels.txt index XXXXXXX..XXXXXXX 100644 --- a/docs/interop/parallels.txt +++ b/docs/interop/parallels.txt @@ -XXX,XX +XXX,XX @@ of its data area are: 28 - 31: l1_size The number of entries in the L1 table of the bitmap. - variable: l1 (64 * l1_size bytes) + variable: l1_table (8 * l1_size bytes) L1 offset table (in bytes) A dirty bitmap is stored using a one-level structure for the mapping to host -- 2.29.2