The following changes since commit 9f55925b8f50a962d1d08d815044db7767ae3838: Merge remote-tracking branch 'remotes/vivier/tags/m68k-for-3.0-pull-request' into staging (2018-06-11 12:46:16 +0100) are available in the Git repository at: git://github.com/XanClic/qemu.git tags/pull-block-2018-06-11 for you to fetch changes up to c50abd175a88cd41c2c08339de91f6f6e4a7b162: iotests: Add case for a corrupted inactive image (2018-06-11 16:18:45 +0200) ---------------------------------------------------------------- Block patches: - Various bug fixes - Removal of qemu-img convert's deprecated -s option - qemu-io now exits with an error when a command failed ---------------------------------------------------------------- Alberto Garcia (1): throttle: Fix crash on reopen Max Reitz (25): block/file-posix: Pass FD to locking helpers block/file-posix: File locking during creation iotests: Add creation test to 153 qemu-img: Amendment support implies create_opts block: Add Error parameter to bdrv_amend_options qemu-option: Pull out "Supported options" print qemu-img: Add print_amend_option_help() qemu-img: Recognize no creation support in -o help iotests: Test help option for unsupporting formats iotests: Rework 113 qcow2: Repair OFLAG_COPIED when fixing leaks iotests: Repairing error during snapshot deletion qemu-io: Drop command functions' return values qemu-io: Let command functions return error code qemu-io: Exit with error when a command failed iotests.py: Add qemu_io_silent iotests: Let 216 make use of qemu-io's exit code qemu-img: Resolve relative backing paths in rebase iotests: Add test for rebasing with relative paths qemu-img: Special post-backing convert handling iotests: Test post-backing convert target behavior iotests: Fix 219's timing block: Make bdrv_is_writable() public qcow2: Do not mark inactive images corrupt iotests: Add case for a corrupted inactive image Thomas Huth (1): qemu-img: Remove deprecated -s snapshot_id_or_name option Vladimir Sementsov-Ogievskiy (2): iotests: improve pause_job block/qcow2-bitmap: fix free_bitmap_clusters include/block/block.h | 4 +- include/block/block_int.h | 3 +- include/qemu-io.h | 9 +- block.c | 25 ++- block/file-posix.c | 64 ++++++-- block/qcow2-bitmap.c | 1 - block/qcow2-refcount.c | 25 ++- block/qcow2.c | 74 +++++---- block/throttle.c | 54 ++++--- qemu-img.c | 108 +++++++++++-- qemu-io-cmds.c | 276 +++++++++++++++++++--------------- qemu-io.c | 62 +++++--- util/qemu-option.c | 1 - qemu-doc.texi | 7 - qemu-img-cmds.hx | 4 +- qemu-img.texi | 7 +- tests/qemu-iotests/024 | 82 +++++++++- tests/qemu-iotests/024.out | 30 ++++ tests/qemu-iotests/029 | 2 +- tests/qemu-iotests/060 | 30 ++++ tests/qemu-iotests/060.out | 18 ++- tests/qemu-iotests/061.out | 7 - tests/qemu-iotests/080 | 4 +- tests/qemu-iotests/080.out | 4 +- tests/qemu-iotests/082 | 9 ++ tests/qemu-iotests/082.out | 53 ++++--- tests/qemu-iotests/112.out | 5 +- tests/qemu-iotests/113 | 19 ++- tests/qemu-iotests/113.out | 7 +- tests/qemu-iotests/122 | 42 ++++++ tests/qemu-iotests/122.out | 18 +++ tests/qemu-iotests/153 | 18 +++ tests/qemu-iotests/153.out | 13 ++ tests/qemu-iotests/216 | 23 +-- tests/qemu-iotests/216.out | 17 +-- tests/qemu-iotests/217 | 90 +++++++++++ tests/qemu-iotests/217.out | 42 ++++++ tests/qemu-iotests/219 | 26 +++- tests/qemu-iotests/219.out | 10 +- tests/qemu-iotests/group | 1 + tests/qemu-iotests/iotests.py | 18 ++- 41 files changed, 970 insertions(+), 342 deletions(-) create mode 100755 tests/qemu-iotests/217 create mode 100644 tests/qemu-iotests/217.out -- 2.17.1 raw_apply_lock_bytes() and raw_check_lock_bytes() currently take a BDRVRawState *, but they only use the lock_fd field. During image creation, we do not have a BDRVRawState, but we do have an FD; so if we want to reuse the functions there, we should modify them to receive only the FD. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20180509215336.31304-2-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/file-posix.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/block/file-posix.c b/block/file-posix.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -XXX,XX +XXX,XX @@ typedef enum { * file; if @unlock == true, also unlock the unneeded bytes. * @shared_perm_lock_bits is the mask of all permissions that are NOT shared. */ -static int raw_apply_lock_bytes(BDRVRawState *s, +static int raw_apply_lock_bytes(int fd, uint64_t perm_lock_bits, uint64_t shared_perm_lock_bits, bool unlock, Error **errp) @@ -XXX,XX +XXX,XX @@ static int raw_apply_lock_bytes(BDRVRawState *s, PERM_FOREACH(i) { int off = RAW_LOCK_PERM_BASE + i; if (perm_lock_bits & (1ULL << i)) { - ret = qemu_lock_fd(s->lock_fd, off, 1, false); + ret = qemu_lock_fd(fd, off, 1, false); if (ret) { error_setg(errp, "Failed to lock byte %d", off); return ret; } } else if (unlock) { - ret = qemu_unlock_fd(s->lock_fd, off, 1); + ret = qemu_unlock_fd(fd, off, 1); if (ret) { error_setg(errp, "Failed to unlock byte %d", off); return ret; @@ -XXX,XX +XXX,XX @@ static int raw_apply_lock_bytes(BDRVRawState *s, PERM_FOREACH(i) { int off = RAW_LOCK_SHARED_BASE + i; if (shared_perm_lock_bits & (1ULL << i)) { - ret = qemu_lock_fd(s->lock_fd, off, 1, false); + ret = qemu_lock_fd(fd, off, 1, false); if (ret) { error_setg(errp, "Failed to lock byte %d", off); return ret; } } else if (unlock) { - ret = qemu_unlock_fd(s->lock_fd, off, 1); + ret = qemu_unlock_fd(fd, off, 1); if (ret) { error_setg(errp, "Failed to unlock byte %d", off); return ret; @@ -XXX,XX +XXX,XX @@ static int raw_apply_lock_bytes(BDRVRawState *s, } /* Check "unshared" bytes implied by @perm and ~@shared_perm in the file. */ -static int raw_check_lock_bytes(BDRVRawState *s, - uint64_t perm, uint64_t shared_perm, +static int raw_check_lock_bytes(int fd, uint64_t perm, uint64_t shared_perm, Error **errp) { int ret; @@ -XXX,XX +XXX,XX @@ static int raw_check_lock_bytes(BDRVRawState *s, int off = RAW_LOCK_SHARED_BASE + i; uint64_t p = 1ULL << i; if (perm & p) { - ret = qemu_lock_fd_test(s->lock_fd, off, 1, true); + ret = qemu_lock_fd_test(fd, off, 1, true); if (ret) { char *perm_name = bdrv_perm_names(p); error_setg(errp, @@ -XXX,XX +XXX,XX @@ static int raw_check_lock_bytes(BDRVRawState *s, int off = RAW_LOCK_PERM_BASE + i; uint64_t p = 1ULL << i; if (!(shared_perm & p)) { - ret = qemu_lock_fd_test(s->lock_fd, off, 1, true); + ret = qemu_lock_fd_test(fd, off, 1, true); if (ret) { char *perm_name = bdrv_perm_names(p); error_setg(errp, @@ -XXX,XX +XXX,XX @@ static int raw_handle_perm_lock(BlockDriverState *bs, switch (op) { case RAW_PL_PREPARE: - ret = raw_apply_lock_bytes(s, s->perm | new_perm, + ret = raw_apply_lock_bytes(s->lock_fd, s->perm | new_perm, ~s->shared_perm | ~new_shared, false, errp); if (!ret) { - ret = raw_check_lock_bytes(s, new_perm, new_shared, errp); + ret = raw_check_lock_bytes(s->lock_fd, new_perm, new_shared, errp); if (!ret) { return 0; } @@ -XXX,XX +XXX,XX @@ static int raw_handle_perm_lock(BlockDriverState *bs, op = RAW_PL_ABORT; /* fall through to unlock bytes. */ case RAW_PL_ABORT: - raw_apply_lock_bytes(s, s->perm, ~s->shared_perm, true, &local_err); + raw_apply_lock_bytes(s->lock_fd, s->perm, ~s->shared_perm, + true, &local_err); if (local_err) { /* Theoretically the above call only unlocks bytes and it cannot * fail. Something weird happened, report it. @@ -XXX,XX +XXX,XX @@ static int raw_handle_perm_lock(BlockDriverState *bs, } break; case RAW_PL_COMMIT: - raw_apply_lock_bytes(s, new_perm, ~new_shared, true, &local_err); + raw_apply_lock_bytes(s->lock_fd, new_perm, ~new_shared, + true, &local_err); if (local_err) { /* Theoretically the above call only unlocks bytes and it cannot * fail. Something weird happened, report it. -- 2.17.1 When creating a file, we should take the WRITE and RESIZE permissions. We do not need either for the creation itself, but we do need them for clearing and resizing it. So we can take the proper permissions by replacing O_TRUNC with an explicit truncation to 0, and by taking the appropriate file locks between those two steps. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20180509215336.31304-3-mreitz@redhat.com Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/file-posix.c | 37 +++++++++++++++++++++++++++++++++++-- 1 file changed, 35 insertions(+), 2 deletions(-) diff --git a/block/file-posix.c b/block/file-posix.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -XXX,XX +XXX,XX @@ static int raw_co_create(BlockdevCreateOptions *options, Error **errp) { BlockdevCreateOptionsFile *file_opts; int fd; + int perm, shared; int result = 0; /* Validate options and set default values */ @@ -XXX,XX +XXX,XX @@ static int raw_co_create(BlockdevCreateOptions *options, Error **errp) } /* Create file */ - fd = qemu_open(file_opts->filename, O_RDWR | O_CREAT | O_TRUNC | O_BINARY, - 0644); + fd = qemu_open(file_opts->filename, O_RDWR | O_CREAT | O_BINARY, 0644); if (fd < 0) { result = -errno; error_setg_errno(errp, -result, "Could not create file"); goto out; } + /* Take permissions: We want to discard everything, so we need + * BLK_PERM_WRITE; and truncation to the desired size requires + * BLK_PERM_RESIZE. + * On the other hand, we cannot share the RESIZE permission + * because we promise that after this function, the file has the + * size given in the options. If someone else were to resize it + * concurrently, we could not guarantee that. + * Note that after this function, we can no longer guarantee that + * the file is not touched by a third party, so it may be resized + * then. */ + perm = BLK_PERM_WRITE | BLK_PERM_RESIZE; + shared = BLK_PERM_ALL & ~BLK_PERM_RESIZE; + + /* Step one: Take locks */ + result = raw_apply_lock_bytes(fd, perm, shared, false, errp); + if (result < 0) { + goto out_close; + } + + /* Step two: Check that nobody else has taken conflicting locks */ + result = raw_check_lock_bytes(fd, perm, shared, errp); + if (result < 0) { + goto out_close; + } + + /* Clear the file by truncating it to 0 */ + result = raw_regular_truncate(fd, 0, PREALLOC_MODE_OFF, errp); + if (result < 0) { + goto out_close; + } + if (file_opts->nocow) { #ifdef __linux__ /* Set NOCOW flag to solve performance issue on fs like btrfs. @@ -XXX,XX +XXX,XX @@ static int raw_co_create(BlockdevCreateOptions *options, Error **errp) #endif } + /* Resize and potentially preallocate the file to the desired + * final size */ result = raw_regular_truncate(fd, file_opts->size, file_opts->preallocation, errp); if (result < 0) { -- 2.17.1 This patch adds a test case to 153 which tries to overwrite an image (using qemu-img create) while it is in use. Without the original user explicitly sharing the necessary permissions (writing and truncation), this should not be allowed. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20180509215336.31304-4-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/153 | 18 ++++++++++++++++++ tests/qemu-iotests/153.out | 13 +++++++++++++ 2 files changed, 31 insertions(+) diff --git a/tests/qemu-iotests/153 b/tests/qemu-iotests/153 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/153 +++ b/tests/qemu-iotests/153 @@ -XXX,XX +XXX,XX @@ for opts1 in "" "read-only=on" "read-only=on,force-share=on"; do _run_cmd $QEMU_IMG dd $L if="${TEST_IMG}" of="${TEST_IMG}.convert" bs=512 count=1 _run_cmd $QEMU_IMG bench $L -c 1 "${TEST_IMG}" _run_cmd $QEMU_IMG bench $L -w -c 1 "${TEST_IMG}" + + # qemu-img create does not support -U + if [ -z "$L" ]; then + _run_cmd $QEMU_IMG create -f $IMGFMT "${TEST_IMG}" \ + -b ${TEST_IMG}.base + # Read the file format. It used to be the case that + # file-posix simply truncated the file, but the qcow2 + # driver then failed to format it because it was unable + # to acquire the necessary WRITE permission. However, the + # truncation was already wrong, and the whole process + # resulted in the file being completely empty and thus its + # format would be detected to be raw. + # So we read it here to see that creation either completed + # successfully (thus the format is qcow2) or it aborted + # before the file was changed at all (thus the format stays + # qcow2). + _img_info -U | grep 'file format' + fi done _send_qemu_cmd $h "{ 'execute': 'quit', }" "" echo diff --git a/tests/qemu-iotests/153.out b/tests/qemu-iotests/153.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/153.out +++ b/tests/qemu-iotests/153.out @@ -XXX,XX +XXX,XX @@ _qemu_img_wrapper bench -w -c 1 TEST_DIR/t.qcow2 qemu-img: Could not open 'TEST_DIR/t.qcow2': Failed to get "write" lock Is another process using the image? +_qemu_img_wrapper create -f qcow2 TEST_DIR/t.qcow2 -b TEST_DIR/t.qcow2.base +qemu-img: TEST_DIR/t.qcow2: Failed to get "write" lock +Is another process using the image? +file format: IMGFMT + == Running utility commands -U == _qemu_io_wrapper -U -c read 0 512 TEST_DIR/t.qcow2 @@ -XXX,XX +XXX,XX @@ _qemu_img_wrapper bench -w -c 1 TEST_DIR/t.qcow2 qemu-img: Could not open 'TEST_DIR/t.qcow2': Failed to get "write" lock Is another process using the image? +_qemu_img_wrapper create -f qcow2 TEST_DIR/t.qcow2 -b TEST_DIR/t.qcow2.base +qemu-img: TEST_DIR/t.qcow2: Failed to get "write" lock +Is another process using the image? +file format: IMGFMT + == Running utility commands -U == _qemu_io_wrapper -U -c read 0 512 TEST_DIR/t.qcow2 @@ -XXX,XX +XXX,XX @@ _qemu_img_wrapper bench -c 1 TEST_DIR/t.qcow2 _qemu_img_wrapper bench -w -c 1 TEST_DIR/t.qcow2 +_qemu_img_wrapper create -f qcow2 TEST_DIR/t.qcow2 -b TEST_DIR/t.qcow2.base +file format: IMGFMT + == Running utility commands -U == _qemu_io_wrapper -U -c read 0 512 TEST_DIR/t.qcow2 -- 2.17.1 Instead of checking whether a driver has a non-NULL create_opts we should check whether it supports image amendment in the first place. If it does, it must have create_opts. On the other hand, if it does not have create_opts (so it does not support amendment either), the error message "does not support any options" is a bit useless. Stating clearly that the driver has no amendment support whatsoever is probably better. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20180509210023.20283-2-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- qemu-img.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int img_amend(int argc, char **argv) goto out; } - if (!bs->drv->create_opts) { - error_report("Format driver '%s' does not support any options to amend", + if (!bs->drv->bdrv_amend_options) { + error_report("Format driver '%s' does not support option amendment", fmt); ret = -1; goto out; } + /* Every driver supporting amendment must have create_opts */ + assert(bs->drv->create_opts); + create_opts = qemu_opts_append(create_opts, bs->drv->create_opts); opts = qemu_opts_create(create_opts, NULL, 0, &error_abort); qemu_opts_do_parse(opts, options, NULL, &err); -- 2.17.1 Looking at the qcow2 code that is riddled with error_report() calls, this is really how it should have been from the start. Along the way, turn the target_version/current_version comparisons at the beginning of qcow2_downgrade() into assertions (the caller has to make sure these conditions are met), and rephrase the error message on using compat=1.1 to get refcount widths other than 16 bits. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20180509210023.20283-3-mreitz@redhat.com Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/block/block.h | 3 +- include/block/block_int.h | 3 +- block.c | 8 +++-- block/qcow2.c | 72 ++++++++++++++++++++++---------------- qemu-img.c | 4 +-- tests/qemu-iotests/060.out | 4 +-- tests/qemu-iotests/061.out | 7 ---- tests/qemu-iotests/080.out | 4 +-- tests/qemu-iotests/112.out | 5 +-- 9 files changed, 58 insertions(+), 52 deletions(-) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ int bdrv_check(BlockDriverState *bs, BdrvCheckResult *res, BdrvCheckMode fix); typedef void BlockDriverAmendStatusCB(BlockDriverState *bs, int64_t offset, int64_t total_work_size, void *opaque); int bdrv_amend_options(BlockDriverState *bs_new, QemuOpts *opts, - BlockDriverAmendStatusCB *status_cb, void *cb_opaque); + BlockDriverAmendStatusCB *status_cb, void *cb_opaque, + Error **errp); /* external snapshots */ bool bdrv_recurse_is_first_non_filter(BlockDriverState *bs, diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ struct BlockDriver { int (*bdrv_amend_options)(BlockDriverState *bs, QemuOpts *opts, BlockDriverAmendStatusCB *status_cb, - void *cb_opaque); + void *cb_opaque, + Error **errp); void (*bdrv_debug_event)(BlockDriverState *bs, BlkdebugEvent event); diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ void bdrv_remove_aio_context_notifier(BlockDriverState *bs, } int bdrv_amend_options(BlockDriverState *bs, QemuOpts *opts, - BlockDriverAmendStatusCB *status_cb, void *cb_opaque) + BlockDriverAmendStatusCB *status_cb, void *cb_opaque, + Error **errp) { if (!bs->drv) { + error_setg(errp, "Node is ejected"); return -ENOMEDIUM; } if (!bs->drv->bdrv_amend_options) { + error_setg(errp, "Block driver '%s' does not support option amendment", + bs->drv->format_name); return -ENOTSUP; } - return bs->drv->bdrv_amend_options(bs, opts, status_cb, cb_opaque); + return bs->drv->bdrv_amend_options(bs, opts, status_cb, cb_opaque, errp); } /* This function will be called by the bdrv_recurse_is_first_non_filter method 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_load_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, * have to be removed. */ static int qcow2_downgrade(BlockDriverState *bs, int target_version, - BlockDriverAmendStatusCB *status_cb, void *cb_opaque) + BlockDriverAmendStatusCB *status_cb, void *cb_opaque, + Error **errp) { BDRVQcow2State *s = bs->opaque; int current_version = s->qcow_version; int ret; - if (target_version == current_version) { - return 0; - } else if (target_version > current_version) { - return -EINVAL; - } else if (target_version != 2) { - return -EINVAL; - } + /* This is qcow2_downgrade(), not qcow2_upgrade() */ + assert(target_version < current_version); + + /* There are no other versions (now) that you can downgrade to */ + assert(target_version == 2); if (s->refcount_order != 4) { - error_report("compat=0.10 requires refcount_bits=16"); + error_setg(errp, "compat=0.10 requires refcount_bits=16"); return -ENOTSUP; } @@ -XXX,XX +XXX,XX @@ static int qcow2_downgrade(BlockDriverState *bs, int target_version, if (s->incompatible_features & QCOW2_INCOMPAT_DIRTY) { ret = qcow2_mark_clean(bs); if (ret < 0) { + error_setg_errno(errp, -ret, "Failed to make the image clean"); return ret; } } @@ -XXX,XX +XXX,XX @@ static int qcow2_downgrade(BlockDriverState *bs, int target_version, * best thing to do anyway */ if (s->incompatible_features) { + error_setg(errp, "Cannot downgrade an image with incompatible features " + "%#" PRIx64 " set", s->incompatible_features); return -ENOTSUP; } @@ -XXX,XX +XXX,XX @@ static int qcow2_downgrade(BlockDriverState *bs, int target_version, ret = qcow2_expand_zero_clusters(bs, status_cb, cb_opaque); if (ret < 0) { + error_setg_errno(errp, -ret, "Failed to turn zero into data clusters"); return ret; } @@ -XXX,XX +XXX,XX @@ static int qcow2_downgrade(BlockDriverState *bs, int target_version, ret = qcow2_update_header(bs); if (ret < 0) { s->qcow_version = current_version; + error_setg_errno(errp, -ret, "Failed to update the image header"); return ret; } return 0; @@ -XXX,XX +XXX,XX @@ static void qcow2_amend_helper_cb(BlockDriverState *bs, static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, BlockDriverAmendStatusCB *status_cb, - void *cb_opaque) + void *cb_opaque, + Error **errp) { BDRVQcow2State *s = bs->opaque; int old_version = s->qcow_version, new_version = old_version; @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, bool encrypt; int encformat; int refcount_bits = s->refcount_bits; - Error *local_err = NULL; int ret; QemuOptDesc *desc = opts->list->desc; Qcow2AmendHelperCBInfo helper_cb_info; @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, } else if (!strcmp(compat, "1.1")) { new_version = 3; } else { - error_report("Unknown compatibility level %s", compat); + error_setg(errp, "Unknown compatibility level %s", compat); return -EINVAL; } } else if (!strcmp(desc->name, BLOCK_OPT_PREALLOC)) { - error_report("Cannot change preallocation mode"); + error_setg(errp, "Cannot change preallocation mode"); return -ENOTSUP; } else if (!strcmp(desc->name, BLOCK_OPT_SIZE)) { new_size = qemu_opt_get_size(opts, BLOCK_OPT_SIZE, 0); @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, !!s->crypto); if (encrypt != !!s->crypto) { - error_report("Changing the encryption flag is not supported"); + error_setg(errp, + "Changing the encryption flag is not supported"); return -ENOTSUP; } } else if (!strcmp(desc->name, BLOCK_OPT_ENCRYPT_FORMAT)) { @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, qemu_opt_get(opts, BLOCK_OPT_ENCRYPT_FORMAT)); if (encformat != s->crypt_method_header) { - error_report("Changing the encryption format is not supported"); + error_setg(errp, + "Changing the encryption format is not supported"); return -ENOTSUP; } } else if (g_str_has_prefix(desc->name, "encrypt.")) { - error_report("Changing the encryption parameters is not supported"); + error_setg(errp, + "Changing the encryption parameters is not supported"); return -ENOTSUP; } else if (!strcmp(desc->name, BLOCK_OPT_CLUSTER_SIZE)) { cluster_size = qemu_opt_get_size(opts, BLOCK_OPT_CLUSTER_SIZE, cluster_size); if (cluster_size != s->cluster_size) { - error_report("Changing the cluster size is not supported"); + error_setg(errp, "Changing the cluster size is not supported"); return -ENOTSUP; } } else if (!strcmp(desc->name, BLOCK_OPT_LAZY_REFCOUNTS)) { @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, if (refcount_bits <= 0 || refcount_bits > 64 || !is_power_of_2(refcount_bits)) { - error_report("Refcount width must be a power of two and may " - "not exceed 64 bits"); + error_setg(errp, "Refcount width must be a power of two and " + "may not exceed 64 bits"); return -EINVAL; } } else { @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, ret = qcow2_update_header(bs); if (ret < 0) { s->qcow_version = old_version; + error_setg_errno(errp, -ret, "Failed to update the image header"); return ret; } } @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, int refcount_order = ctz32(refcount_bits); if (new_version < 3 && refcount_bits != 16) { - error_report("Different refcount widths than 16 bits require " - "compatibility level 1.1 or above (use compat=1.1 or " - "greater)"); + error_setg(errp, "Refcount widths other than 16 bits require " + "compatibility level 1.1 or above (use compat=1.1 or " + "greater)"); return -EINVAL; } helper_cb_info.current_operation = QCOW2_CHANGING_REFCOUNT_ORDER; ret = qcow2_change_refcount_order(bs, refcount_order, &qcow2_amend_helper_cb, - &helper_cb_info, &local_err); + &helper_cb_info, errp); if (ret < 0) { - error_report_err(local_err); return ret; } } @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, backing_file ?: s->image_backing_file, backing_format ?: s->image_backing_format); if (ret < 0) { + error_setg_errno(errp, -ret, "Failed to change the backing file"); return ret; } } @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, if (s->use_lazy_refcounts != lazy_refcounts) { if (lazy_refcounts) { if (new_version < 3) { - error_report("Lazy refcounts only supported with compatibility " - "level 1.1 and above (use compat=1.1 or greater)"); + error_setg(errp, "Lazy refcounts only supported with " + "compatibility level 1.1 and above (use compat=1.1 " + "or greater)"); return -EINVAL; } s->compatible_features |= QCOW2_COMPAT_LAZY_REFCOUNTS; ret = qcow2_update_header(bs); if (ret < 0) { s->compatible_features &= ~QCOW2_COMPAT_LAZY_REFCOUNTS; + error_setg_errno(errp, -ret, "Failed to update the image header"); return ret; } s->use_lazy_refcounts = true; @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, /* make image clean first */ ret = qcow2_mark_clean(bs); if (ret < 0) { + error_setg_errno(errp, -ret, "Failed to make the image clean"); return ret; } /* now disallow lazy refcounts */ @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, ret = qcow2_update_header(bs); if (ret < 0) { s->compatible_features |= QCOW2_COMPAT_LAZY_REFCOUNTS; + error_setg_errno(errp, -ret, "Failed to update the image header"); return ret; } s->use_lazy_refcounts = false; @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, if (new_size) { BlockBackend *blk = blk_new(BLK_PERM_RESIZE, BLK_PERM_ALL); - ret = blk_insert_bs(blk, bs, &local_err); + ret = blk_insert_bs(blk, bs, errp); if (ret < 0) { - error_report_err(local_err); blk_unref(blk); return ret; } - ret = blk_truncate(blk, new_size, PREALLOC_MODE_OFF, &local_err); + ret = blk_truncate(blk, new_size, PREALLOC_MODE_OFF, errp); blk_unref(blk); if (ret < 0) { - error_report_err(local_err); return ret; } } @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, if (new_version < old_version) { helper_cb_info.current_operation = QCOW2_DOWNGRADING; ret = qcow2_downgrade(bs, new_version, &qcow2_amend_helper_cb, - &helper_cb_info); + &helper_cb_info, errp); if (ret < 0) { return ret; } diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int img_amend(int argc, char **argv) /* In case the driver does not call amend_status_cb() */ qemu_progress_print(0.f, 0); - ret = bdrv_amend_options(bs, opts, &amend_status_cb, NULL); + ret = bdrv_amend_options(bs, opts, &amend_status_cb, NULL, &err); qemu_progress_print(100.f, 0); if (ret < 0) { - error_report("Error while amending options: %s", strerror(-ret)); + error_report_err(err); goto out; } 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 @@ 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) qcow2: Marking image as corrupt: L2 table offset 0x42a00 unaligned (L1 index: 0); further corruption events will be suppressed -qemu-img: Error while amending options: Input/output error +qemu-img: Failed to turn zero into data clusters: Input/output error === Testing unaligned L2 entry === @@ -XXX,XX +XXX,XX @@ 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) qcow2: Marking image as corrupt: Cluster allocation offset 0x52a00 unaligned (L2 offset: 0x40000, L2 index: 0); further corruption events will be suppressed -qemu-img: Error while amending options: Input/output error +qemu-img: Failed to turn zero into data clusters: Input/output error === Testing unaligned reftable entry === 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 @@ No errors were found on the image. Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 qemu-img: Lazy refcounts only supported with compatibility level 1.1 and above (use compat=1.1 or greater) -qemu-img: Error while amending options: Invalid argument qemu-img: Lazy refcounts only supported with compatibility level 1.1 and above (use compat=1.1 or greater) -qemu-img: Error while amending options: Invalid argument qemu-img: Unknown compatibility level 0.42 -qemu-img: Error while amending options: Invalid argument qemu-img: Invalid parameter 'foo' qemu-img: Changing the cluster size is not supported -qemu-img: Error while amending options: Operation not supported qemu-img: Changing the encryption flag is not supported -qemu-img: Error while amending options: Operation not supported qemu-img: Cannot change preallocation mode -qemu-img: Error while amending options: Operation not supported === Testing correct handling of unset value === @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 Should work: Should not work: qemu-img: Changing the cluster size is not supported -qemu-img: Error while amending options: Operation not supported === Testing zero expansion on inactive clusters === diff --git a/tests/qemu-iotests/080.out b/tests/qemu-iotests/080.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/080.out +++ b/tests/qemu-iotests/080.out @@ -XXX,XX +XXX,XX @@ wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) qemu-img: Failed to load snapshot: Snapshot L1 table offset invalid qemu-img: Snapshot L1 table offset invalid -qemu-img: Error while amending options: Invalid argument +qemu-img: Failed to turn zero into data clusters: Invalid argument Failed to flush the refcount block cache: Invalid argument write failed: Invalid argument qemu-img: Snapshot L1 table offset invalid @@ -XXX,XX +XXX,XX @@ wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) qemu-img: Failed to load snapshot: Snapshot L1 table too large qemu-img: Snapshot L1 table too large -qemu-img: Error while amending options: File too large +qemu-img: Failed to turn zero into data clusters: File too large Failed to flush the refcount block cache: File too large write failed: File too large qemu-img: Snapshot L1 table too large diff --git a/tests/qemu-iotests/112.out b/tests/qemu-iotests/112.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/112.out +++ b/tests/qemu-iotests/112.out @@ -XXX,XX +XXX,XX @@ refcount bits: 64 === Amend to compat=0.10 === qemu-img: compat=0.10 requires refcount_bits=16 -qemu-img: Error while amending options: Operation not supported refcount bits: 64 No errors were found on the image. refcount bits: 16 refcount bits: 16 -qemu-img: Different refcount widths than 16 bits require compatibility level 1.1 or above (use compat=1.1 or greater) -qemu-img: Error while amending options: Invalid argument +qemu-img: Refcount widths other than 16 bits require compatibility level 1.1 or above (use compat=1.1 or greater) refcount bits: 16 === Amend with snapshot === @@ -XXX,XX +XXX,XX @@ refcount bits: 16 wrote 16777216/16777216 bytes at offset 0 16 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) qemu-img: Cannot decrease refcount entry width to 1 bits: Cluster at offset 0x50000 has a refcount of 2 -qemu-img: Error while amending options: Invalid argument No errors were found on the image. refcount bits: 16 No errors were found on the image. -- 2.17.1 It really is up to the caller to decide what this list of options means. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20180509210023.20283-4-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- qemu-img.c | 1 + util/qemu-option.c | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int print_block_option_help(const char *filename, const char *fmt) create_opts = qemu_opts_append(create_opts, proto_drv->create_opts); } + printf("Supported options:\n"); qemu_opts_print_help(create_opts); qemu_opts_free(create_opts); return 0; diff --git a/util/qemu-option.c b/util/qemu-option.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-option.c +++ b/util/qemu-option.c @@ -XXX,XX +XXX,XX @@ void qemu_opts_print_help(QemuOptsList *list) assert(list); desc = list->desc; - printf("Supported options:\n"); while (desc && desc->name) { printf("%-16s %s\n", desc->name, desc->help ? desc->help : "No description available"); -- 2.17.1 The more generic print_block_option_help() function is not really suitable for qemu-img amend, for a couple of reasons: (1) We do not need to append the protocol-level options, as amendment happens only on one node and does not descend downwards to its children. (2) print_block_option_help() says those options are "supported". For option amendment, we do not really know that. So this new function explicitly says that those options are the creation options, and not all of them may be supported. (3) If the driver does not support option amendment, we should not print anything (except for an error message that amendment is not supported). Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=1537956 Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20180509210023.20283-5-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- qemu-img.c | 30 ++++++++++++++++++++++++-- tests/qemu-iotests/082.out | 44 +++++++++++++++++++++++--------------- 2 files changed, 55 insertions(+), 19 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static void amend_status_cb(BlockDriverState *bs, qemu_progress_print(100.f * offset / total_work_size, 0); } +static int print_amend_option_help(const char *format) +{ + BlockDriver *drv; + + /* Find driver and parse its options */ + drv = bdrv_find_format(format); + if (!drv) { + error_report("Unknown file format '%s'", format); + return 1; + } + + if (!drv->bdrv_amend_options) { + error_report("Format driver '%s' does not support option amendment", + format); + return 1; + } + + /* Every driver supporting amendment must have create_opts */ + assert(drv->create_opts); + + printf("Creation options for '%s':\n", format); + qemu_opts_print_help(drv->create_opts); + printf("\nNote that not all of these options may be amendable.\n"); + return 0; +} + static int img_amend(int argc, char **argv) { Error *err = NULL; @@ -XXX,XX +XXX,XX @@ static int img_amend(int argc, char **argv) if (fmt && has_help_option(options)) { /* If a format is explicitly specified (and possibly no filename is * given), print option help here */ - ret = print_block_option_help(filename, fmt); + ret = print_amend_option_help(fmt); goto out; } @@ -XXX,XX +XXX,XX @@ static int img_amend(int argc, char **argv) if (has_help_option(options)) { /* If the format was auto-detected, print option help here */ - ret = print_block_option_help(filename, fmt); + ret = print_amend_option_help(fmt); goto out; } 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 @@ cluster_size: 65536 === amend: help for -o === Testing: amend -f qcow2 -o help TEST_DIR/t.qcow2 -Supported options: +Creation options for 'qcow2': size Virtual disk size compat Compatibility level (0.10 or 1.1) backing_file File name of a base image @@ -XXX,XX +XXX,XX @@ cluster_size qcow2 cluster size preallocation Preallocation mode (allowed values: off, metadata, falloc, full) lazy_refcounts Postpone refcount updates refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + +Note that not all of these options may be amendable. Testing: amend -f qcow2 -o ? TEST_DIR/t.qcow2 -Supported options: +Creation options for 'qcow2': size Virtual disk size compat Compatibility level (0.10 or 1.1) backing_file File name of a base image @@ -XXX,XX +XXX,XX @@ cluster_size qcow2 cluster size preallocation Preallocation mode (allowed values: off, metadata, falloc, full) lazy_refcounts Postpone refcount updates refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + +Note that not all of these options may be amendable. Testing: amend -f qcow2 -o cluster_size=4k,help TEST_DIR/t.qcow2 -Supported options: +Creation options for 'qcow2': size Virtual disk size compat Compatibility level (0.10 or 1.1) backing_file File name of a base image @@ -XXX,XX +XXX,XX @@ cluster_size qcow2 cluster size preallocation Preallocation mode (allowed values: off, metadata, falloc, full) lazy_refcounts Postpone refcount updates refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + +Note that not all of these options may be amendable. Testing: amend -f qcow2 -o cluster_size=4k,? TEST_DIR/t.qcow2 -Supported options: +Creation options for 'qcow2': size Virtual disk size compat Compatibility level (0.10 or 1.1) backing_file File name of a base image @@ -XXX,XX +XXX,XX @@ cluster_size qcow2 cluster size preallocation Preallocation mode (allowed values: off, metadata, falloc, full) lazy_refcounts Postpone refcount updates refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + +Note that not all of these options may be amendable. Testing: amend -f qcow2 -o help,cluster_size=4k TEST_DIR/t.qcow2 -Supported options: +Creation options for 'qcow2': size Virtual disk size compat Compatibility level (0.10 or 1.1) backing_file File name of a base image @@ -XXX,XX +XXX,XX @@ cluster_size qcow2 cluster size preallocation Preallocation mode (allowed values: off, metadata, falloc, full) lazy_refcounts Postpone refcount updates refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + +Note that not all of these options may be amendable. Testing: amend -f qcow2 -o ?,cluster_size=4k TEST_DIR/t.qcow2 -Supported options: +Creation options for 'qcow2': size Virtual disk size compat Compatibility level (0.10 or 1.1) backing_file File name of a base image @@ -XXX,XX +XXX,XX @@ cluster_size qcow2 cluster size preallocation Preallocation mode (allowed values: off, metadata, falloc, full) lazy_refcounts Postpone refcount updates refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + +Note that not all of these options may be amendable. Testing: amend -f qcow2 -o cluster_size=4k -o help TEST_DIR/t.qcow2 -Supported options: +Creation options for 'qcow2': size Virtual disk size compat Compatibility level (0.10 or 1.1) backing_file File name of a base image @@ -XXX,XX +XXX,XX @@ cluster_size qcow2 cluster size preallocation Preallocation mode (allowed values: off, metadata, falloc, full) lazy_refcounts Postpone refcount updates refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + +Note that not all of these options may be amendable. Testing: amend -f qcow2 -o cluster_size=4k -o ? TEST_DIR/t.qcow2 -Supported options: +Creation options for 'qcow2': size Virtual disk size compat Compatibility level (0.10 or 1.1) backing_file File name of a base image @@ -XXX,XX +XXX,XX @@ cluster_size qcow2 cluster size preallocation Preallocation mode (allowed values: off, metadata, falloc, full) lazy_refcounts Postpone refcount updates refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + +Note that not all of these options may be amendable. Testing: amend -f qcow2 -o backing_file=TEST_DIR/t.qcow2,,help TEST_DIR/t.qcow2 @@ -XXX,XX +XXX,XX @@ Testing: amend -f qcow2 -o backing_file=TEST_DIR/t.qcow2 -o ,, -o help TEST_DIR/ qemu-img: Invalid option list: ,, Testing: amend -f qcow2 -o help -Supported options: +Creation options for 'qcow2': size Virtual disk size compat Compatibility level (0.10 or 1.1) backing_file File name of a base image @@ -XXX,XX +XXX,XX @@ preallocation Preallocation mode (allowed values: off, metadata, falloc, full lazy_refcounts Postpone refcount updates refcount_bits Width of a reference count entry in bits +Note that not all of these options may be amendable. + Testing: convert -o help Supported options: size Virtual disk size -- 2.17.1 The only users of print_block_option_help() are qemu-img create and qemu-img convert for the output image, so this function is always used for image creation (it used to be used for amendment also, but that is no longer the case). So if image creation is not supported by either the format or the protocol, there is no need to print any option description, because the user cannot create an image like this anyway. This also fixes an assertion failure: $ qemu-img create -f bochs -o help Supported options: qemu-img: util/qemu-option.c:219: qemu_opts_print_help: Assertion `list' failed. [1] 24831 abort (core dumped) qemu-img create -f bochs -o help Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20180509210023.20283-6-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- qemu-img.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int print_block_option_help(const char *filename, const char *fmt) return 1; } + if (!drv->create_opts) { + error_report("Format driver '%s' does not support image creation", fmt); + return 1; + } + create_opts = qemu_opts_append(create_opts, drv->create_opts); if (filename) { proto_drv = bdrv_find_protocol(filename, true, &local_err); @@ -XXX,XX +XXX,XX @@ static int print_block_option_help(const char *filename, const char *fmt) qemu_opts_free(create_opts); return 1; } + if (!proto_drv->create_opts) { + error_report("Protocal driver '%s' does not support image creation", + proto_drv->format_name); + return 1; + } create_opts = qemu_opts_append(create_opts, proto_drv->create_opts); } -- 2.17.1 This adds test cases to 082 for qemu-img create/convert/amend "-o help" on formats that do not support creation or amendment, respectively. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20180509210023.20283-7-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/082 | 9 +++++++++ tests/qemu-iotests/082.out | 9 +++++++++ 2 files changed, 18 insertions(+) diff --git a/tests/qemu-iotests/082 b/tests/qemu-iotests/082 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/082 +++ b/tests/qemu-iotests/082 @@ -XXX,XX +XXX,XX @@ run_qemu_img create -f $IMGFMT -o backing_file="$TEST_IMG" -o ,, -o help "$TEST_ run_qemu_img create -f $IMGFMT -o help run_qemu_img create -o help +# Try help option for a format that does not support creation +run_qemu_img create -f bochs -o help + echo echo === convert: Options specified more than once === @@ -XXX,XX +XXX,XX @@ run_qemu_img convert -O $IMGFMT -o backing_file="$TEST_IMG" -o ,, -o help "$TEST run_qemu_img convert -O $IMGFMT -o help run_qemu_img convert -o help +# Try help option for a format that does not support creation +run_qemu_img convert -O bochs -o help + echo echo === amend: Options specified more than once === @@ -XXX,XX +XXX,XX @@ run_qemu_img amend -f $IMGFMT -o backing_file="$TEST_IMG" -o ,, -o help "$TEST_I run_qemu_img amend -f $IMGFMT -o help run_qemu_img convert -o help +# Try help option for a format that does not support amendment +run_qemu_img amend -f bochs -o help + # success, all done echo "*** done" rm -f $seq.full 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 @@ Testing: create -o help Supported options: size Virtual disk size +Testing: create -f bochs -o help +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 @@ -XXX,XX +XXX,XX @@ Testing: convert -o help Supported options: size Virtual disk size +Testing: convert -O bochs -o help +qemu-img: Format driver 'bochs' does not support image creation + === amend: Options specified more than once === Testing: amend -f foo -f qcow2 -o lazy_refcounts=on TEST_DIR/t.qcow2 @@ -XXX,XX +XXX,XX @@ Note that not all of these options may be amendable. Testing: convert -o help Supported options: size Virtual disk size + +Testing: amend -f bochs -o help +qemu-img: Format driver 'bochs' does not support option amendment *** done -- 2.17.1 This test case has been broken since 398e6ad014df261d (roughly half a year). qemu-img amend requires its output image to be R/W, so it opens it as such; the node is then turned into an read-only node automatically which is now accompanied by a warning, however. This warning has not been part of the reference output. For one thing, this warning shows that we cannot keep the test case as it is. We would need a format that has no create_opts but that does have write support -- we do not have such a format, though. Another thing is that qemu now actually checks whether an image format supports amendment instead of whether it has create_opts (since the former always implies the latter). So we can now use any format that does not support amendment (even if it supports creation) and thus test the same code path. The reason nobody has noticed the breakage until now of course is the fact that nobody runs the iotests for nbd+bochs. There actually was never any reason to set the protocol to "nbd" but because that was technically correct; functionally it made no difference. So that is the first thing we are going to change: Make the protocol "file" instead so that people might actually notice breakage here. Secondly, now that bochs no longer works for the amend test case, we have to change the format there anyway. Set let us just bend the truth a bit, declare this test a raw test. In fact, that does not even concern the bochs test cases, other than the output now reading 'bochs' instead of 'IMGFMT'. So with this test now being a raw test, we can rework the amend test case to use raw instead. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Message-id: 20180509210023.20283-8-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/113 | 19 +++++++++---------- tests/qemu-iotests/113.out | 7 ++++--- 2 files changed, 13 insertions(+), 13 deletions(-) diff --git a/tests/qemu-iotests/113 b/tests/qemu-iotests/113 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/113 +++ b/tests/qemu-iotests/113 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 . ./common.rc . ./common.filter -# We can only test one format here because we need its sample file -_supported_fmt bochs -_supported_proto nbd +# Some of these test cases use bochs, but others do use raw, so this +# is only half a lie. +_supported_fmt raw +_supported_proto file _supported_os Linux echo echo '=== Unsupported image creation in qemu-img create ===' echo -$QEMU_IMG create -f $IMGFMT nbd://example.com 2>&1 64M | _filter_imgfmt +$QEMU_IMG create -f bochs nbd://example.com 2>&1 64M echo echo '=== Unsupported image creation in qemu-img convert ===' @@ -XXX,XX +XXX,XX @@ echo # We could use any input image format here, but this is a bochs test, so just # use the bochs image _use_sample_img empty.bochs.bz2 -$QEMU_IMG convert -f $IMGFMT -O $IMGFMT "$TEST_IMG" nbd://example.com 2>&1 \ - | _filter_imgfmt +$QEMU_IMG convert -f bochs -O bochs "$TEST_IMG" nbd://example.com echo echo '=== Unsupported format in qemu-img amend ===' echo -# The protocol does not matter here -_use_sample_img empty.bochs.bz2 -$QEMU_IMG amend -f $IMGFMT -o foo=bar "$TEST_IMG" 2>&1 | _filter_imgfmt - +TEST_IMG="$TEST_DIR/t.$IMGFMT" +_make_test_img 1M +$QEMU_IMG amend -f $IMGFMT -o size=2M "$TEST_IMG" 2>&1 | _filter_imgfmt # success, all done echo diff --git a/tests/qemu-iotests/113.out b/tests/qemu-iotests/113.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/113.out +++ b/tests/qemu-iotests/113.out @@ -XXX,XX +XXX,XX @@ QA output created by 113 === Unsupported image creation in qemu-img create === -qemu-img: nbd://example.com: Format driver 'IMGFMT' does not support image creation +qemu-img: nbd://example.com: Format driver 'bochs' does not support image creation === Unsupported image creation in qemu-img convert === -qemu-img: Format driver 'IMGFMT' does not support image creation +qemu-img: Format driver 'bochs' does not support image creation === Unsupported format in qemu-img amend === -qemu-img: Format driver 'IMGFMT' does not support any options to amend +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 +qemu-img: Format driver 'IMGFMT' does not support option amendment *** done -- 2.17.1 Repairing OFLAG_COPIED is usually safe because it is done after the refcounts have been repaired. Therefore, it we did not find anyone else referencing a data or L2 cluster, it makes no sense to not set OFLAG_COPIED -- and the other direction (clearing OFLAG_COPIED) is always safe, anyway, it may just induce leaks. Furthermore, if OFLAG_COPIED is actually consistent with a wrong (leaky) refcount, we will decrement the refcount with -r leaks, but OFLAG_COPIED will then be wrong. qemu-img check should not produce images that are more corrupted afterwards then they were before. Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=1527085 Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20180509200059.31125-2-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-refcount.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -XXX,XX +XXX,XX @@ static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res, int ret; uint64_t refcount; int i, j; + bool repair; + + if (fix & BDRV_FIX_ERRORS) { + /* Always repair */ + repair = true; + } else if (fix & BDRV_FIX_LEAKS) { + /* Repair only if that seems safe: This function is always + * called after the refcounts have been fixed, so the refcount + * is accurate if that repair was successful */ + repair = !res->check_errors && !res->corruptions && !res->leaks; + } else { + repair = false; + } for (i = 0; i < s->l1_size; i++) { uint64_t l1_entry = s->l1_table[i]; @@ -XXX,XX +XXX,XX @@ static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res, if ((refcount == 1) != ((l1_entry & QCOW_OFLAG_COPIED) != 0)) { fprintf(stderr, "%s OFLAG_COPIED L2 cluster: l1_index=%d " "l1_entry=%" PRIx64 " refcount=%" PRIu64 "\n", - fix & BDRV_FIX_ERRORS ? "Repairing" : - "ERROR", - i, l1_entry, refcount); - if (fix & BDRV_FIX_ERRORS) { + repair ? "Repairing" : "ERROR", i, l1_entry, refcount); + if (repair) { s->l1_table[i] = refcount == 1 ? l1_entry | QCOW_OFLAG_COPIED : l1_entry & ~QCOW_OFLAG_COPIED; @@ -XXX,XX +XXX,XX @@ static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res, if ((refcount == 1) != ((l2_entry & QCOW_OFLAG_COPIED) != 0)) { fprintf(stderr, "%s OFLAG_COPIED data cluster: " "l2_entry=%" PRIx64 " refcount=%" PRIu64 "\n", - fix & BDRV_FIX_ERRORS ? "Repairing" : - "ERROR", - l2_entry, refcount); - if (fix & BDRV_FIX_ERRORS) { + repair ? "Repairing" : "ERROR", l2_entry, refcount); + if (repair) { l2_table[j] = cpu_to_be64(refcount == 1 ? l2_entry | QCOW_OFLAG_COPIED : l2_entry & ~QCOW_OFLAG_COPIED); -- 2.17.1 This adds a test for an I/O error during snapshot deletion, and maybe more importantly, for how to repair the resulting image. If the snapshot has been deleted before the error occurs, the only negative result will be leaked clusters -- and those should be repairable with qemu-img check -r leaks. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20180509200059.31125-3-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/217 | 90 ++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/217.out | 42 ++++++++++++++++++ tests/qemu-iotests/group | 1 + 3 files changed, 133 insertions(+) create mode 100755 tests/qemu-iotests/217 create mode 100644 tests/qemu-iotests/217.out diff --git a/tests/qemu-iotests/217 b/tests/qemu-iotests/217 new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/217 @@ -XXX,XX +XXX,XX @@ +#!/bin/bash +# +# I/O errors when working with internal qcow2 snapshots, and repairing +# the result +# +# Copyright (C) 2018 Red Hat, Inc. +# +# 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/>. + +seq=$(basename $0) +echo "QA output created by $seq" + +status=1 # failure is the default! + +_cleanup() +{ + _cleanup_test_img + rm -f "$TEST_DIR/blkdebug.conf" +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# get standard environment, filters and checks +. ./common.rc +. ./common.filter + +# This test is specific to qcow2 +_supported_fmt qcow2 +_supported_proto file +_supported_os Linux + +# This test needs clusters with at least a refcount of 2 so that +# OFLAG_COPIED is not set. refcount_bits=1 is therefore unsupported. +_unsupported_imgopts 'refcount_bits=1[^0-9]' + +echo +echo '=== Simulating an I/O error during snapshot deletion ===' +echo + +_make_test_img 64M +$QEMU_IO -c 'write 0 64k' "$TEST_IMG" | _filter_qemu_io + +# Create the snapshot +$QEMU_IMG snapshot -c foo "$TEST_IMG" + +# Verify the snapshot is there +echo +_img_info | grep 'Snapshot list' +echo '(Snapshot filtered)' +echo + +# Try to delete the snapshot (with an error happening when freeing the +# then leaked clusters) +cat > "$TEST_DIR/blkdebug.conf" <<EOF +[inject-error] +event = "cluster_free" +errno = "5" +EOF +$QEMU_IMG snapshot -d foo "blkdebug:$TEST_DIR/blkdebug.conf:$TEST_IMG" + +# Verify the snapshot is gone +echo +_img_info | grep 'Snapshot list' + +# Should only show leaks +echo '--- Checking test image ---' +_check_test_img + +echo + +# As there are only leaks, this should be able to fully repair the +# image +echo '--- Repairing test image ---' +_check_test_img -r leaks + + +# success, all done +echo '*** done' +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/217.out b/tests/qemu-iotests/217.out new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/217.out @@ -XXX,XX +XXX,XX @@ +QA output created by 217 + +=== Simulating an I/O error during snapshot deletion === + +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) + +Snapshot list: +(Snapshot filtered) + +qcow2_free_clusters failed: Input/output error +qemu-img: Could not delete snapshot 'foo': Failed to free the cluster and L1 table: Input/output error + +--- Checking test image --- +Leaked cluster 4 refcount=2 reference=1 +Leaked cluster 5 refcount=2 reference=1 +Leaked cluster 6 refcount=1 reference=0 +Leaked cluster 7 refcount=1 reference=0 + +4 leaked clusters were found on the image. +This means waste of disk space, but no harm to data. + +--- Repairing test image --- +Leaked cluster 4 refcount=2 reference=1 +Leaked cluster 5 refcount=2 reference=1 +Leaked cluster 6 refcount=1 reference=0 +Leaked cluster 7 refcount=1 reference=0 +Repairing cluster 4 refcount=2 reference=1 +Repairing cluster 5 refcount=2 reference=1 +Repairing cluster 6 refcount=1 reference=0 +Repairing cluster 7 refcount=1 reference=0 +Repairing OFLAG_COPIED L2 cluster: l1_index=0 l1_entry=40000 refcount=1 +Repairing OFLAG_COPIED data cluster: l2_entry=50000 refcount=1 +The following inconsistencies were found and repaired: + + 4 leaked clusters + 2 corruptions + +Double checking the fixed image now... +No errors were found on the image. +*** 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 @@ 214 rw auto 215 rw auto quick 216 rw auto quick +217 rw auto quick 218 rw auto quick 219 rw auto -- 2.17.1 For qemu-io, a function returns an integer with two possible values: 0 for "qemu-io may continue execution", or 1 for "qemu-io should exit". However, there is only a single command that returns 1, and that is "quit". So let's turn this case into a global variable instead so we can make better use of the return value in a later patch. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20180509194302.21585-2-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/qemu-io.h | 6 +- qemu-io-cmds.c | 294 +++++++++++++++++++++------------------------- qemu-io.c | 36 +++--- 3 files changed, 157 insertions(+), 179 deletions(-) diff --git a/include/qemu-io.h b/include/qemu-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu-io.h +++ b/include/qemu-io.h @@ -XXX,XX +XXX,XX @@ #define CMD_FLAG_GLOBAL ((int)0x80000000) /* don't iterate "args" */ -typedef int (*cfunc_t)(BlockBackend *blk, int argc, char **argv); +typedef void (*cfunc_t)(BlockBackend *blk, int argc, char **argv); typedef void (*helpfunc_t)(void); typedef struct cmdinfo { @@ -XXX,XX +XXX,XX @@ typedef struct cmdinfo { extern bool qemuio_misalign; -bool qemuio_command(BlockBackend *blk, const char *cmd); +void qemuio_command(BlockBackend *blk, const char *cmd); void qemuio_add_command(const cmdinfo_t *ci); -int qemuio_command_usage(const cmdinfo_t *ci); +void qemuio_command_usage(const cmdinfo_t *ci); void qemuio_complete_command(const char *input, void (*fn)(const char *cmd, void *opaque), void *opaque); diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -XXX,XX +XXX,XX @@ void qemuio_add_command(const cmdinfo_t *ci) qsort(cmdtab, ncmds, sizeof(*cmdtab), compare_cmdname); } -int qemuio_command_usage(const cmdinfo_t *ci) +void qemuio_command_usage(const cmdinfo_t *ci) { printf("%s %s -- %s\n", ci->name, ci->args, ci->oneline); - return 0; } static int init_check_command(BlockBackend *blk, const cmdinfo_t *ct) @@ -XXX,XX +XXX,XX @@ static int init_check_command(BlockBackend *blk, const cmdinfo_t *ct) return 1; } -static int command(BlockBackend *blk, const cmdinfo_t *ct, int argc, - char **argv) +static void command(BlockBackend *blk, const cmdinfo_t *ct, int argc, + char **argv) { char *cmd = argv[0]; if (!init_check_command(blk, ct)) { - return 0; + return; } if (argc - 1 < ct->argmin || (ct->argmax != -1 && argc - 1 > ct->argmax)) { @@ -XXX,XX +XXX,XX @@ static int command(BlockBackend *blk, const cmdinfo_t *ct, int argc, "bad argument count %d to %s, expected between %d and %d arguments\n", argc-1, cmd, ct->argmin, ct->argmax); } - return 0; + return; } /* Request additional permissions if necessary for this command. The caller @@ -XXX,XX +XXX,XX @@ static int command(BlockBackend *blk, const cmdinfo_t *ct, int argc, ret = blk_set_perm(blk, new_perm, orig_shared_perm, &local_err); if (ret < 0) { error_report_err(local_err); - return 0; + return; } } } optind = 0; - return ct->cfunc(blk, argc, argv); + ct->cfunc(blk, argc, argv); } static const cmdinfo_t *find_command(const char *cmd) @@ -XXX,XX +XXX,XX @@ static void read_help(void) "\n"); } -static int read_f(BlockBackend *blk, int argc, char **argv); +static void read_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t read_cmd = { .name = "read", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t read_cmd = { .help = read_help, }; -static int read_f(BlockBackend *blk, int argc, char **argv) +static void read_f(BlockBackend *blk, int argc, char **argv) { struct timeval t1, t2; bool Cflag = false, qflag = false, vflag = false; @@ -XXX,XX +XXX,XX @@ static int read_f(BlockBackend *blk, int argc, char **argv) pattern_count = cvtnum(optarg); if (pattern_count < 0) { print_cvtnum_err(pattern_count, optarg); - return 0; + return; } break; case 'p': @@ -XXX,XX +XXX,XX @@ static int read_f(BlockBackend *blk, int argc, char **argv) Pflag = true; pattern = parse_pattern(optarg); if (pattern < 0) { - return 0; + return; } break; case 'q': @@ -XXX,XX +XXX,XX @@ static int read_f(BlockBackend *blk, int argc, char **argv) pattern_offset = cvtnum(optarg); if (pattern_offset < 0) { print_cvtnum_err(pattern_offset, optarg); - return 0; + return; } break; case 'v': vflag = true; break; default: - return qemuio_command_usage(&read_cmd); + qemuio_command_usage(&read_cmd); + return; } } if (optind != argc - 2) { - return qemuio_command_usage(&read_cmd); + qemuio_command_usage(&read_cmd); + return; } offset = cvtnum(argv[optind]); if (offset < 0) { print_cvtnum_err(offset, argv[optind]); - return 0; + return; } optind++; count = cvtnum(argv[optind]); if (count < 0) { print_cvtnum_err(count, argv[optind]); - return 0; + return; } else if (count > BDRV_REQUEST_MAX_BYTES) { printf("length cannot exceed %" PRIu64 ", given %s\n", (uint64_t)BDRV_REQUEST_MAX_BYTES, argv[optind]); - return 0; + return; } if (!Pflag && (lflag || sflag)) { - return qemuio_command_usage(&read_cmd); + qemuio_command_usage(&read_cmd); + return; } if (!lflag) { @@ -XXX,XX +XXX,XX @@ static int read_f(BlockBackend *blk, int argc, char **argv) if ((pattern_count < 0) || (pattern_count + pattern_offset > count)) { printf("pattern verification range exceeds end of read data\n"); - return 0; + return; } if (bflag) { if (!QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)) { printf("%" PRId64 " is not a sector-aligned value for 'offset'\n", offset); - return 0; + return; } if (!QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)) { printf("%"PRId64" is not a sector-aligned value for 'count'\n", count); - return 0; + return; } } @@ -XXX,XX +XXX,XX @@ static int read_f(BlockBackend *blk, int argc, char **argv) out: qemu_io_free(buf); - - return 0; } static void readv_help(void) @@ -XXX,XX +XXX,XX @@ static void readv_help(void) "\n"); } -static int readv_f(BlockBackend *blk, int argc, char **argv); +static void readv_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t readv_cmd = { .name = "readv", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t readv_cmd = { .help = readv_help, }; -static int readv_f(BlockBackend *blk, int argc, char **argv) +static void readv_f(BlockBackend *blk, int argc, char **argv) { struct timeval t1, t2; bool Cflag = false, qflag = false, vflag = false; @@ -XXX,XX +XXX,XX @@ static int readv_f(BlockBackend *blk, int argc, char **argv) Pflag = true; pattern = parse_pattern(optarg); if (pattern < 0) { - return 0; + return; } break; case 'q': @@ -XXX,XX +XXX,XX @@ static int readv_f(BlockBackend *blk, int argc, char **argv) vflag = true; break; default: - return qemuio_command_usage(&readv_cmd); + qemuio_command_usage(&readv_cmd); + return; } } if (optind > argc - 2) { - return qemuio_command_usage(&readv_cmd); + qemuio_command_usage(&readv_cmd); + return; } offset = cvtnum(argv[optind]); if (offset < 0) { print_cvtnum_err(offset, argv[optind]); - return 0; + return; } optind++; nr_iov = argc - optind; buf = create_iovec(blk, &qiov, &argv[optind], nr_iov, 0xab); if (buf == NULL) { - return 0; + return; } gettimeofday(&t1, NULL); @@ -XXX,XX +XXX,XX @@ static int readv_f(BlockBackend *blk, int argc, char **argv) out: qemu_iovec_destroy(&qiov); qemu_io_free(buf); - return 0; } static void write_help(void) @@ -XXX,XX +XXX,XX @@ static void write_help(void) "\n"); } -static int write_f(BlockBackend *blk, int argc, char **argv); +static void write_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t write_cmd = { .name = "write", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t write_cmd = { .help = write_help, }; -static int write_f(BlockBackend *blk, int argc, char **argv) +static void write_f(BlockBackend *blk, int argc, char **argv) { struct timeval t1, t2; bool Cflag = false, qflag = false, bflag = false; @@ -XXX,XX +XXX,XX @@ static int write_f(BlockBackend *blk, int argc, char **argv) Pflag = true; pattern = parse_pattern(optarg); if (pattern < 0) { - return 0; + return; } break; case 'q': @@ -XXX,XX +XXX,XX @@ static int write_f(BlockBackend *blk, int argc, char **argv) zflag = true; break; default: - return qemuio_command_usage(&write_cmd); + qemuio_command_usage(&write_cmd); + return; } } if (optind != argc - 2) { - return qemuio_command_usage(&write_cmd); + qemuio_command_usage(&write_cmd); + return; } if (bflag && zflag) { printf("-b and -z cannot be specified at the same time\n"); - return 0; + return; } if ((flags & BDRV_REQ_FUA) && (bflag || cflag)) { printf("-f and -b or -c cannot be specified at the same time\n"); - return 0; + return; } if ((flags & BDRV_REQ_MAY_UNMAP) && !zflag) { printf("-u requires -z to be specified\n"); - return 0; + return; } if (zflag && Pflag) { printf("-z and -P cannot be specified at the same time\n"); - return 0; + return; } offset = cvtnum(argv[optind]); if (offset < 0) { print_cvtnum_err(offset, argv[optind]); - return 0; + return; } optind++; count = cvtnum(argv[optind]); if (count < 0) { print_cvtnum_err(count, argv[optind]); - return 0; + return; } else if (count > BDRV_REQUEST_MAX_BYTES) { printf("length cannot exceed %" PRIu64 ", given %s\n", (uint64_t)BDRV_REQUEST_MAX_BYTES, argv[optind]); - return 0; + return; } if (bflag || cflag) { if (!QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)) { printf("%" PRId64 " is not a sector-aligned value for 'offset'\n", offset); - return 0; + return; } if (!QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)) { printf("%"PRId64" is not a sector-aligned value for 'count'\n", count); - return 0; + return; } } @@ -XXX,XX +XXX,XX @@ out: if (!zflag) { qemu_io_free(buf); } - - return 0; } static void @@ -XXX,XX +XXX,XX @@ writev_help(void) "\n"); } -static int writev_f(BlockBackend *blk, int argc, char **argv); +static void writev_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t writev_cmd = { .name = "writev", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t writev_cmd = { .help = writev_help, }; -static int writev_f(BlockBackend *blk, int argc, char **argv) +static void writev_f(BlockBackend *blk, int argc, char **argv) { struct timeval t1, t2; bool Cflag = false, qflag = false; @@ -XXX,XX +XXX,XX @@ static int writev_f(BlockBackend *blk, int argc, char **argv) case 'P': pattern = parse_pattern(optarg); if (pattern < 0) { - return 0; + return; } break; default: - return qemuio_command_usage(&writev_cmd); + qemuio_command_usage(&writev_cmd); + return; } } if (optind > argc - 2) { - return qemuio_command_usage(&writev_cmd); + qemuio_command_usage(&writev_cmd); + return; } offset = cvtnum(argv[optind]); if (offset < 0) { print_cvtnum_err(offset, argv[optind]); - return 0; + return; } optind++; nr_iov = argc - optind; buf = create_iovec(blk, &qiov, &argv[optind], nr_iov, pattern); if (buf == NULL) { - return 0; + return; } gettimeofday(&t1, NULL); @@ -XXX,XX +XXX,XX @@ static int writev_f(BlockBackend *blk, int argc, char **argv) out: qemu_iovec_destroy(&qiov); qemu_io_free(buf); - return 0; } struct aio_ctx { @@ -XXX,XX +XXX,XX @@ static void aio_read_help(void) "\n"); } -static int aio_read_f(BlockBackend *blk, int argc, char **argv); +static void aio_read_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t aio_read_cmd = { .name = "aio_read", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t aio_read_cmd = { .help = aio_read_help, }; -static int aio_read_f(BlockBackend *blk, int argc, char **argv) +static void aio_read_f(BlockBackend *blk, int argc, char **argv) { int nr_iov, c; struct aio_ctx *ctx = g_new0(struct aio_ctx, 1); @@ -XXX,XX +XXX,XX @@ static int aio_read_f(BlockBackend *blk, int argc, char **argv) ctx->pattern = parse_pattern(optarg); if (ctx->pattern < 0) { g_free(ctx); - return 0; + return; } break; case 'i': printf("injecting invalid read request\n"); block_acct_invalid(blk_get_stats(blk), BLOCK_ACCT_READ); g_free(ctx); - return 0; + return; case 'q': ctx->qflag = true; break; @@ -XXX,XX +XXX,XX @@ static int aio_read_f(BlockBackend *blk, int argc, char **argv) break; default: g_free(ctx); - return qemuio_command_usage(&aio_read_cmd); + qemuio_command_usage(&aio_read_cmd); + return; } } if (optind > argc - 2) { g_free(ctx); - return qemuio_command_usage(&aio_read_cmd); + qemuio_command_usage(&aio_read_cmd); + return; } ctx->offset = cvtnum(argv[optind]); if (ctx->offset < 0) { print_cvtnum_err(ctx->offset, argv[optind]); g_free(ctx); - return 0; + return; } optind++; @@ -XXX,XX +XXX,XX @@ static int aio_read_f(BlockBackend *blk, int argc, char **argv) if (ctx->buf == NULL) { block_acct_invalid(blk_get_stats(blk), BLOCK_ACCT_READ); g_free(ctx); - return 0; + return; } gettimeofday(&ctx->t1, NULL); block_acct_start(blk_get_stats(blk), &ctx->acct, ctx->qiov.size, BLOCK_ACCT_READ); blk_aio_preadv(blk, ctx->offset, &ctx->qiov, 0, aio_read_done, ctx); - return 0; } static void aio_write_help(void) @@ -XXX,XX +XXX,XX @@ static void aio_write_help(void) "\n"); } -static int aio_write_f(BlockBackend *blk, int argc, char **argv); +static void aio_write_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t aio_write_cmd = { .name = "aio_write", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t aio_write_cmd = { .help = aio_write_help, }; -static int aio_write_f(BlockBackend *blk, int argc, char **argv) +static void aio_write_f(BlockBackend *blk, int argc, char **argv) { int nr_iov, c; int pattern = 0xcd; @@ -XXX,XX +XXX,XX @@ static int aio_write_f(BlockBackend *blk, int argc, char **argv) pattern = parse_pattern(optarg); if (pattern < 0) { g_free(ctx); - return 0; + return; } break; case 'i': printf("injecting invalid write request\n"); block_acct_invalid(blk_get_stats(blk), BLOCK_ACCT_WRITE); g_free(ctx); - return 0; + return; case 'z': ctx->zflag = true; break; default: g_free(ctx); - return qemuio_command_usage(&aio_write_cmd); + qemuio_command_usage(&aio_write_cmd); + return; } } if (optind > argc - 2) { g_free(ctx); - return qemuio_command_usage(&aio_write_cmd); + qemuio_command_usage(&aio_write_cmd); + return; } if (ctx->zflag && optind != argc - 2) { printf("-z supports only a single length parameter\n"); g_free(ctx); - return 0; + return; } if ((flags & BDRV_REQ_MAY_UNMAP) && !ctx->zflag) { printf("-u requires -z to be specified\n"); g_free(ctx); - return 0; + return; } if (ctx->zflag && ctx->Pflag) { printf("-z and -P cannot be specified at the same time\n"); g_free(ctx); - return 0; + return; } ctx->offset = cvtnum(argv[optind]); if (ctx->offset < 0) { print_cvtnum_err(ctx->offset, argv[optind]); g_free(ctx); - return 0; + return; } optind++; @@ -XXX,XX +XXX,XX @@ static int aio_write_f(BlockBackend *blk, int argc, char **argv) if (count < 0) { print_cvtnum_err(count, argv[optind]); g_free(ctx); - return 0; + return; } ctx->qiov.size = count; @@ -XXX,XX +XXX,XX @@ static int aio_write_f(BlockBackend *blk, int argc, char **argv) if (ctx->buf == NULL) { block_acct_invalid(blk_get_stats(blk), BLOCK_ACCT_WRITE); g_free(ctx); - return 0; + return; } gettimeofday(&ctx->t1, NULL); @@ -XXX,XX +XXX,XX @@ static int aio_write_f(BlockBackend *blk, int argc, char **argv) blk_aio_pwritev(blk, ctx->offset, &ctx->qiov, flags, aio_write_done, ctx); } - return 0; } -static int aio_flush_f(BlockBackend *blk, int argc, char **argv) +static void aio_flush_f(BlockBackend *blk, int argc, char **argv) { BlockAcctCookie cookie; block_acct_start(blk_get_stats(blk), &cookie, 0, BLOCK_ACCT_FLUSH); blk_drain_all(); block_acct_done(blk_get_stats(blk), &cookie); - return 0; } static const cmdinfo_t aio_flush_cmd = { @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t aio_flush_cmd = { .oneline = "completes all outstanding aio requests" }; -static int flush_f(BlockBackend *blk, int argc, char **argv) +static void flush_f(BlockBackend *blk, int argc, char **argv) { blk_flush(blk); - return 0; } static const cmdinfo_t flush_cmd = { @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t flush_cmd = { .oneline = "flush all in-core file state to disk", }; -static int truncate_f(BlockBackend *blk, int argc, char **argv) +static void truncate_f(BlockBackend *blk, int argc, char **argv) { Error *local_err = NULL; int64_t offset; @@ -XXX,XX +XXX,XX @@ static int truncate_f(BlockBackend *blk, int argc, char **argv) offset = cvtnum(argv[1]); if (offset < 0) { print_cvtnum_err(offset, argv[1]); - return 0; + return; } ret = blk_truncate(blk, offset, PREALLOC_MODE_OFF, &local_err); if (ret < 0) { error_report_err(local_err); - return 0; + return; } - - return 0; } static const cmdinfo_t truncate_cmd = { @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t truncate_cmd = { .oneline = "truncates the current file at the given offset", }; -static int length_f(BlockBackend *blk, int argc, char **argv) +static void length_f(BlockBackend *blk, int argc, char **argv) { int64_t size; char s1[64]; @@ -XXX,XX +XXX,XX @@ static int length_f(BlockBackend *blk, int argc, char **argv) size = blk_getlength(blk); if (size < 0) { printf("getlength: %s\n", strerror(-size)); - return 0; + return; } cvtstr(size, s1, sizeof(s1)); printf("%s\n", s1); - return 0; } @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t length_cmd = { }; -static int info_f(BlockBackend *blk, int argc, char **argv) +static void info_f(BlockBackend *blk, int argc, char **argv) { BlockDriverState *bs = blk_bs(blk); BlockDriverInfo bdi; @@ -XXX,XX +XXX,XX @@ static int info_f(BlockBackend *blk, int argc, char **argv) ret = bdrv_get_info(bs, &bdi); if (ret) { - return 0; + return; } cvtstr(bdi.cluster_size, s1, sizeof(s1)); @@ -XXX,XX +XXX,XX @@ static int info_f(BlockBackend *blk, int argc, char **argv) bdrv_image_info_specific_dump(fprintf, stdout, spec_info); qapi_free_ImageInfoSpecific(spec_info); } - - return 0; } @@ -XXX,XX +XXX,XX @@ static void discard_help(void) "\n"); } -static int discard_f(BlockBackend *blk, int argc, char **argv); +static void discard_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t discard_cmd = { .name = "discard", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t discard_cmd = { .help = discard_help, }; -static int discard_f(BlockBackend *blk, int argc, char **argv) +static void discard_f(BlockBackend *blk, int argc, char **argv) { struct timeval t1, t2; bool Cflag = false, qflag = false; @@ -XXX,XX +XXX,XX @@ static int discard_f(BlockBackend *blk, int argc, char **argv) qflag = true; break; default: - return qemuio_command_usage(&discard_cmd); + qemuio_command_usage(&discard_cmd); + return; } } if (optind != argc - 2) { - return qemuio_command_usage(&discard_cmd); + qemuio_command_usage(&discard_cmd); + return; } offset = cvtnum(argv[optind]); if (offset < 0) { print_cvtnum_err(offset, argv[optind]); - return 0; + return; } optind++; bytes = cvtnum(argv[optind]); if (bytes < 0) { print_cvtnum_err(bytes, argv[optind]); - return 0; + return; } else if (bytes >> BDRV_SECTOR_BITS > BDRV_REQUEST_MAX_SECTORS) { printf("length cannot exceed %"PRIu64", given %s\n", (uint64_t)BDRV_REQUEST_MAX_SECTORS << BDRV_SECTOR_BITS, argv[optind]); - return 0; + return; } gettimeofday(&t1, NULL); @@ -XXX,XX +XXX,XX @@ static int discard_f(BlockBackend *blk, int argc, char **argv) if (ret < 0) { printf("discard failed: %s\n", strerror(-ret)); - goto out; + return; } /* Finally, report back -- -C gives a parsable format */ @@ -XXX,XX +XXX,XX @@ static int discard_f(BlockBackend *blk, int argc, char **argv) t2 = tsub(t2, t1); print_report("discard", &t2, offset, bytes, bytes, 1, Cflag); } - -out: - return 0; } -static int alloc_f(BlockBackend *blk, int argc, char **argv) +static void alloc_f(BlockBackend *blk, int argc, char **argv) { BlockDriverState *bs = blk_bs(blk); int64_t offset, start, remaining, count; @@ -XXX,XX +XXX,XX @@ static int alloc_f(BlockBackend *blk, int argc, char **argv) start = offset = cvtnum(argv[1]); if (offset < 0) { print_cvtnum_err(offset, argv[1]); - return 0; + return; } if (argc == 3) { count = cvtnum(argv[2]); if (count < 0) { print_cvtnum_err(count, argv[2]); - return 0; + return; } } else { count = BDRV_SECTOR_SIZE; @@ -XXX,XX +XXX,XX @@ static int alloc_f(BlockBackend *blk, int argc, char **argv) ret = bdrv_is_allocated(bs, offset, remaining, &num); if (ret < 0) { printf("is_allocated failed: %s\n", strerror(-ret)); - return 0; + return; } offset += num; remaining -= num; @@ -XXX,XX +XXX,XX @@ static int alloc_f(BlockBackend *blk, int argc, char **argv) printf("%"PRId64"/%"PRId64" bytes allocated at offset %s\n", sum_alloc, count, s1); - return 0; } static const cmdinfo_t alloc_cmd = { @@ -XXX,XX +XXX,XX @@ static int map_is_allocated(BlockDriverState *bs, int64_t offset, return firstret; } -static int map_f(BlockBackend *blk, int argc, char **argv) +static void map_f(BlockBackend *blk, int argc, char **argv) { int64_t offset, bytes; char s1[64], s2[64]; @@ -XXX,XX +XXX,XX @@ static int map_f(BlockBackend *blk, int argc, char **argv) bytes = blk_getlength(blk); if (bytes < 0) { error_report("Failed to query image length: %s", strerror(-bytes)); - return 0; + return; } while (bytes) { ret = map_is_allocated(blk_bs(blk), offset, bytes, &num); if (ret < 0) { error_report("Failed to get allocation status: %s", strerror(-ret)); - return 0; + return; } else if (!num) { error_report("Unexpected end of image"); - return 0; + return; } retstr = ret ? " allocated" : "not allocated"; @@ -XXX,XX +XXX,XX @@ static int map_f(BlockBackend *blk, int argc, char **argv) offset += num; bytes -= num; } - - return 0; } static const cmdinfo_t map_cmd = { @@ -XXX,XX +XXX,XX @@ static void reopen_help(void) "\n"); } -static int reopen_f(BlockBackend *blk, int argc, char **argv); +static void reopen_f(BlockBackend *blk, int argc, char **argv); static QemuOptsList reopen_opts = { .name = "reopen", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t reopen_cmd = { .help = reopen_help, }; -static int reopen_f(BlockBackend *blk, int argc, char **argv) +static void reopen_f(BlockBackend *blk, int argc, char **argv) { BlockDriverState *bs = blk_bs(blk); QemuOpts *qopts; @@ -XXX,XX +XXX,XX @@ static int reopen_f(BlockBackend *blk, int argc, char **argv) case 'c': if (bdrv_parse_cache_mode(optarg, &flags, &writethrough) < 0) { error_report("Invalid cache option: %s", optarg); - return 0; + return; } break; case 'o': if (!qemu_opts_parse_noisily(&reopen_opts, optarg, 0)) { qemu_opts_reset(&reopen_opts); - return 0; + return; } break; case 'r': if (has_rw_option) { error_report("Only one -r/-w option may be given"); - return 0; + return; } flags &= ~BDRV_O_RDWR; has_rw_option = true; @@ -XXX,XX +XXX,XX @@ static int reopen_f(BlockBackend *blk, int argc, char **argv) case 'w': if (has_rw_option) { error_report("Only one -r/-w option may be given"); - return 0; + return; } flags |= BDRV_O_RDWR; has_rw_option = true; break; default: qemu_opts_reset(&reopen_opts); - return qemuio_command_usage(&reopen_cmd); + qemuio_command_usage(&reopen_cmd); + return; } } if (optind != argc) { qemu_opts_reset(&reopen_opts); - return qemuio_command_usage(&reopen_cmd); + qemuio_command_usage(&reopen_cmd); + return; } if (writethrough != blk_enable_write_cache(blk) && @@ -XXX,XX +XXX,XX @@ static int reopen_f(BlockBackend *blk, int argc, char **argv) { error_report("Cannot change cache.writeback: Device attached"); qemu_opts_reset(&reopen_opts); - return 0; + return; } if (!(flags & BDRV_O_RDWR)) { @@ -XXX,XX +XXX,XX @@ static int reopen_f(BlockBackend *blk, int argc, char **argv) } else { blk_set_enable_write_cache(blk, !writethrough); } - - return 0; } -static int break_f(BlockBackend *blk, int argc, char **argv) +static void break_f(BlockBackend *blk, int argc, char **argv) { int ret; @@ -XXX,XX +XXX,XX @@ static int break_f(BlockBackend *blk, int argc, char **argv) if (ret < 0) { printf("Could not set breakpoint: %s\n", strerror(-ret)); } - - return 0; } -static int remove_break_f(BlockBackend *blk, int argc, char **argv) +static void remove_break_f(BlockBackend *blk, int argc, char **argv) { int ret; @@ -XXX,XX +XXX,XX @@ static int remove_break_f(BlockBackend *blk, int argc, char **argv) if (ret < 0) { printf("Could not remove breakpoint %s: %s\n", argv[1], strerror(-ret)); } - - return 0; } static const cmdinfo_t break_cmd = { @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t remove_break_cmd = { .oneline = "remove a breakpoint by tag", }; -static int resume_f(BlockBackend *blk, int argc, char **argv) +static void resume_f(BlockBackend *blk, int argc, char **argv) { int ret; @@ -XXX,XX +XXX,XX @@ static int resume_f(BlockBackend *blk, int argc, char **argv) if (ret < 0) { printf("Could not resume request: %s\n", strerror(-ret)); } - - return 0; } static const cmdinfo_t resume_cmd = { @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t resume_cmd = { .oneline = "resumes the request tagged as tag", }; -static int wait_break_f(BlockBackend *blk, int argc, char **argv) +static void wait_break_f(BlockBackend *blk, int argc, char **argv) { while (!bdrv_debug_is_suspended(blk_bs(blk), argv[1])) { aio_poll(blk_get_aio_context(blk), true); } - - return 0; } static const cmdinfo_t wait_break_cmd = { @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t wait_break_cmd = { .oneline = "waits for the suspension of a request", }; -static int abort_f(BlockBackend *blk, int argc, char **argv) +static void abort_f(BlockBackend *blk, int argc, char **argv) { abort(); } @@ -XXX,XX +XXX,XX @@ static void sigraise_help(void) "\n", SIGTERM); } -static int sigraise_f(BlockBackend *blk, int argc, char **argv); +static void sigraise_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t sigraise_cmd = { .name = "sigraise", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t sigraise_cmd = { .help = sigraise_help, }; -static int sigraise_f(BlockBackend *blk, int argc, char **argv) +static void sigraise_f(BlockBackend *blk, int argc, char **argv) { int64_t sig = cvtnum(argv[1]); if (sig < 0) { print_cvtnum_err(sig, argv[1]); - return 0; + return; } else if (sig > NSIG) { printf("signal argument '%s' is too large to be a valid signal\n", argv[1]); - return 0; + return; } /* Using raise() to kill this process does not necessarily flush all open @@ -XXX,XX +XXX,XX @@ static int sigraise_f(BlockBackend *blk, int argc, char **argv) fflush(stderr); raise(sig); - return 0; } static void sleep_cb(void *opaque) @@ -XXX,XX +XXX,XX @@ static void sleep_cb(void *opaque) *expired = true; } -static int sleep_f(BlockBackend *blk, int argc, char **argv) +static void sleep_f(BlockBackend *blk, int argc, char **argv) { char *endptr; long ms; @@ -XXX,XX +XXX,XX @@ static int sleep_f(BlockBackend *blk, int argc, char **argv) ms = strtol(argv[1], &endptr, 0); if (ms < 0 || *endptr != '\0') { printf("%s is not a valid number\n", argv[1]); - return 0; + return; } timer = timer_new_ns(QEMU_CLOCK_HOST, sleep_cb, &expired); @@ -XXX,XX +XXX,XX @@ static int sleep_f(BlockBackend *blk, int argc, char **argv) } timer_free(timer); - - return 0; } static const cmdinfo_t sleep_cmd = { @@ -XXX,XX +XXX,XX @@ static void help_all(void) printf("\nUse 'help commandname' for extended help.\n"); } -static int help_f(BlockBackend *blk, int argc, char **argv) +static void help_f(BlockBackend *blk, int argc, char **argv) { const cmdinfo_t *ct; if (argc == 1) { help_all(); - return 0; + return; } ct = find_command(argv[1]); if (ct == NULL) { printf("command %s not found\n", argv[1]); - return 0; + return; } help_onecmd(argv[1], ct); - return 0; } static const cmdinfo_t help_cmd = { @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t help_cmd = { .oneline = "help for one or all commands", }; -bool qemuio_command(BlockBackend *blk, const char *cmd) +void qemuio_command(BlockBackend *blk, const char *cmd) { AioContext *ctx; char *input; const cmdinfo_t *ct; char **v; int c; - bool done = false; input = g_strdup(cmd); v = breakline(input, &c); @@ -XXX,XX +XXX,XX @@ bool qemuio_command(BlockBackend *blk, const char *cmd) if (ct) { ctx = blk ? blk_get_aio_context(blk) : qemu_get_aio_context(); aio_context_acquire(ctx); - done = command(blk, ct, c, v); + command(blk, ct, c, v); aio_context_release(ctx); } else { fprintf(stderr, "command \"%s\" not found\n", v[0]); @@ -XXX,XX +XXX,XX @@ bool qemuio_command(BlockBackend *blk, const char *cmd) } g_free(input); g_free(v); - - return done; } static void __attribute((constructor)) init_qemuio_commands(void) diff --git a/qemu-io.c b/qemu-io.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io.c +++ b/qemu-io.c @@ -XXX,XX +XXX,XX @@ static char *progname; static BlockBackend *qemuio_blk; +static bool quit_qemu_io; /* qemu-io commands passed using -c */ static int ncmdline; @@ -XXX,XX +XXX,XX @@ static int get_eof_char(void) #endif } -static int close_f(BlockBackend *blk, int argc, char **argv) +static void close_f(BlockBackend *blk, int argc, char **argv) { blk_unref(qemuio_blk); qemuio_blk = NULL; - return 0; } static const cmdinfo_t close_cmd = { @@ -XXX,XX +XXX,XX @@ static void open_help(void) "\n"); } -static int open_f(BlockBackend *blk, int argc, char **argv); +static void open_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t open_cmd = { .name = "open", @@ -XXX,XX +XXX,XX @@ static QemuOptsList empty_opts = { }, }; -static int open_f(BlockBackend *blk, int argc, char **argv) +static void open_f(BlockBackend *blk, int argc, char **argv) { int flags = BDRV_O_UNMAP; int readonly = 0; @@ -XXX,XX +XXX,XX @@ static int open_f(BlockBackend *blk, int argc, char **argv) if (bdrv_parse_cache_mode(optarg, &flags, &writethrough) < 0) { error_report("Invalid cache option: %s", optarg); qemu_opts_reset(&empty_opts); - return 0; + return; } break; case 'd': if (bdrv_parse_discard_flags(optarg, &flags) < 0) { error_report("Invalid discard option: %s", optarg); qemu_opts_reset(&empty_opts); - return 0; + return; } break; case 'o': if (imageOpts) { printf("--image-opts and 'open -o' are mutually exclusive\n"); qemu_opts_reset(&empty_opts); - return 0; + return; } if (!qemu_opts_parse_noisily(&empty_opts, optarg, false)) { qemu_opts_reset(&empty_opts); - return 0; + return; } break; case 'U': @@ -XXX,XX +XXX,XX @@ static int open_f(BlockBackend *blk, int argc, char **argv) break; default: qemu_opts_reset(&empty_opts); - return qemuio_command_usage(&open_cmd); + qemuio_command_usage(&open_cmd); + return; } } @@ -XXX,XX +XXX,XX @@ static int open_f(BlockBackend *blk, int argc, char **argv) if (imageOpts && (optind == argc - 1)) { if (!qemu_opts_parse_noisily(&empty_opts, argv[optind], false)) { qemu_opts_reset(&empty_opts); - return 0; + return; } optind++; } @@ -XXX,XX +XXX,XX @@ static int open_f(BlockBackend *blk, int argc, char **argv) qobject_unref(opts); qemuio_command_usage(&open_cmd); } - return 0; } -static int quit_f(BlockBackend *blk, int argc, char **argv) +static void quit_f(BlockBackend *blk, int argc, char **argv) { - return 1; + quit_qemu_io = true; } static const cmdinfo_t quit_cmd = { @@ -XXX,XX +XXX,XX @@ static void prep_fetchline(void *opaque) static void command_loop(void) { - int i, done = 0, fetchable = 0, prompted = 0; + int i, fetchable = 0, prompted = 0; char *input; - for (i = 0; !done && i < ncmdline; i++) { - done = qemuio_command(qemuio_blk, cmdline[i]); + for (i = 0; !quit_qemu_io && i < ncmdline; i++) { + qemuio_command(qemuio_blk, cmdline[i]); } if (cmdline) { g_free(cmdline); return; } - while (!done) { + while (!quit_qemu_io) { if (!prompted) { printf("%s", get_prompt()); fflush(stdout); @@ -XXX,XX +XXX,XX @@ static void command_loop(void) if (input == NULL) { break; } - done = qemuio_command(qemuio_blk, input); + qemuio_command(qemuio_blk, input); g_free(input); prompted = 0; -- 2.17.1 This is basically what everything else in the qemu code base does, so we can do it here, too. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20180509194302.21585-3-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/qemu-io.h | 9 +- qemu-io-cmds.c | 346 +++++++++++++++++++++++++++------------------- qemu-io.c | 34 +++-- 3 files changed, 232 insertions(+), 157 deletions(-) diff --git a/include/qemu-io.h b/include/qemu-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu-io.h +++ b/include/qemu-io.h @@ -XXX,XX +XXX,XX @@ #define CMD_FLAG_GLOBAL ((int)0x80000000) /* don't iterate "args" */ -typedef void (*cfunc_t)(BlockBackend *blk, int argc, char **argv); +/* Implement a qemu-io command. + * Operate on @blk using @argc/@argv as the command's arguments, and + * return 0 on success or negative errno on failure. + */ +typedef int (*cfunc_t)(BlockBackend *blk, int argc, char **argv); + typedef void (*helpfunc_t)(void); typedef struct cmdinfo { @@ -XXX,XX +XXX,XX @@ typedef struct cmdinfo { extern bool qemuio_misalign; -void qemuio_command(BlockBackend *blk, const char *cmd); +int qemuio_command(BlockBackend *blk, const char *cmd); void qemuio_add_command(const cmdinfo_t *ci); void qemuio_command_usage(const cmdinfo_t *ci); diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -XXX,XX +XXX,XX @@ static int init_check_command(BlockBackend *blk, const cmdinfo_t *ct) return 1; } -static void command(BlockBackend *blk, const cmdinfo_t *ct, int argc, - char **argv) +static int command(BlockBackend *blk, const cmdinfo_t *ct, int argc, + char **argv) { char *cmd = argv[0]; if (!init_check_command(blk, ct)) { - return; + return -EINVAL; } if (argc - 1 < ct->argmin || (ct->argmax != -1 && argc - 1 > ct->argmax)) { @@ -XXX,XX +XXX,XX @@ static void command(BlockBackend *blk, const cmdinfo_t *ct, int argc, "bad argument count %d to %s, expected between %d and %d arguments\n", argc-1, cmd, ct->argmin, ct->argmax); } - return; + return -EINVAL; } /* Request additional permissions if necessary for this command. The caller @@ -XXX,XX +XXX,XX @@ static void command(BlockBackend *blk, const cmdinfo_t *ct, int argc, ret = blk_set_perm(blk, new_perm, orig_shared_perm, &local_err); if (ret < 0) { error_report_err(local_err); - return; + return ret; } } } optind = 0; - ct->cfunc(blk, argc, argv); + return ct->cfunc(blk, argc, argv); } static const cmdinfo_t *find_command(const char *cmd) @@ -XXX,XX +XXX,XX @@ static void read_help(void) "\n"); } -static void read_f(BlockBackend *blk, int argc, char **argv); +static int read_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t read_cmd = { .name = "read", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t read_cmd = { .help = read_help, }; -static void read_f(BlockBackend *blk, int argc, char **argv) +static int read_f(BlockBackend *blk, int argc, char **argv) { struct timeval t1, t2; bool Cflag = false, qflag = false, vflag = false; bool Pflag = false, sflag = false, lflag = false, bflag = false; - int c, cnt; + int c, cnt, ret; char *buf; int64_t offset; int64_t count; @@ -XXX,XX +XXX,XX @@ static void read_f(BlockBackend *blk, int argc, char **argv) pattern_count = cvtnum(optarg); if (pattern_count < 0) { print_cvtnum_err(pattern_count, optarg); - return; + return pattern_count; } break; case 'p': @@ -XXX,XX +XXX,XX @@ static void read_f(BlockBackend *blk, int argc, char **argv) Pflag = true; pattern = parse_pattern(optarg); if (pattern < 0) { - return; + return -EINVAL; } break; case 'q': @@ -XXX,XX +XXX,XX @@ static void read_f(BlockBackend *blk, int argc, char **argv) pattern_offset = cvtnum(optarg); if (pattern_offset < 0) { print_cvtnum_err(pattern_offset, optarg); - return; + return pattern_offset; } break; case 'v': @@ -XXX,XX +XXX,XX @@ static void read_f(BlockBackend *blk, int argc, char **argv) break; default: qemuio_command_usage(&read_cmd); - return; + return -EINVAL; } } if (optind != argc - 2) { qemuio_command_usage(&read_cmd); - return; + return -EINVAL; } offset = cvtnum(argv[optind]); if (offset < 0) { print_cvtnum_err(offset, argv[optind]); - return; + return offset; } optind++; count = cvtnum(argv[optind]); if (count < 0) { print_cvtnum_err(count, argv[optind]); - return; + return count; } else if (count > BDRV_REQUEST_MAX_BYTES) { printf("length cannot exceed %" PRIu64 ", given %s\n", (uint64_t)BDRV_REQUEST_MAX_BYTES, argv[optind]); - return; + return -EINVAL; } if (!Pflag && (lflag || sflag)) { qemuio_command_usage(&read_cmd); - return; + return -EINVAL; } if (!lflag) { @@ -XXX,XX +XXX,XX @@ static void read_f(BlockBackend *blk, int argc, char **argv) if ((pattern_count < 0) || (pattern_count + pattern_offset > count)) { printf("pattern verification range exceeds end of read data\n"); - return; + return -EINVAL; } if (bflag) { if (!QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)) { printf("%" PRId64 " is not a sector-aligned value for 'offset'\n", offset); - return; + return -EINVAL; } if (!QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)) { printf("%"PRId64" is not a sector-aligned value for 'count'\n", count); - return; + return -EINVAL; } } @@ -XXX,XX +XXX,XX @@ static void read_f(BlockBackend *blk, int argc, char **argv) gettimeofday(&t1, NULL); if (bflag) { - cnt = do_load_vmstate(blk, buf, offset, count, &total); + ret = do_load_vmstate(blk, buf, offset, count, &total); } else { - cnt = do_pread(blk, buf, offset, count, &total); + ret = do_pread(blk, buf, offset, count, &total); } gettimeofday(&t2, NULL); - if (cnt < 0) { - printf("read failed: %s\n", strerror(-cnt)); + if (ret < 0) { + printf("read failed: %s\n", strerror(-ret)); goto out; } + cnt = ret; + + ret = 0; if (Pflag) { void *cmp_buf = g_malloc(pattern_count); @@ -XXX,XX +XXX,XX @@ static void read_f(BlockBackend *blk, int argc, char **argv) printf("Pattern verification failed at offset %" PRId64 ", %"PRId64" bytes\n", offset + pattern_offset, pattern_count); + ret = -EINVAL; } g_free(cmp_buf); } @@ -XXX,XX +XXX,XX @@ static void read_f(BlockBackend *blk, int argc, char **argv) out: qemu_io_free(buf); + return ret; } static void readv_help(void) @@ -XXX,XX +XXX,XX @@ static void readv_help(void) "\n"); } -static void readv_f(BlockBackend *blk, int argc, char **argv); +static int readv_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t readv_cmd = { .name = "readv", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t readv_cmd = { .help = readv_help, }; -static void readv_f(BlockBackend *blk, int argc, char **argv) +static int readv_f(BlockBackend *blk, int argc, char **argv) { struct timeval t1, t2; bool Cflag = false, qflag = false, vflag = false; - int c, cnt; + int c, cnt, ret; char *buf; int64_t offset; /* Some compilers get confused and warn if this is not initialized. */ @@ -XXX,XX +XXX,XX @@ static void readv_f(BlockBackend *blk, int argc, char **argv) Pflag = true; pattern = parse_pattern(optarg); if (pattern < 0) { - return; + return -EINVAL; } break; case 'q': @@ -XXX,XX +XXX,XX @@ static void readv_f(BlockBackend *blk, int argc, char **argv) break; default: qemuio_command_usage(&readv_cmd); - return; + return -EINVAL; } } if (optind > argc - 2) { qemuio_command_usage(&readv_cmd); - return; + return -EINVAL; } offset = cvtnum(argv[optind]); if (offset < 0) { print_cvtnum_err(offset, argv[optind]); - return; + return offset; } optind++; nr_iov = argc - optind; buf = create_iovec(blk, &qiov, &argv[optind], nr_iov, 0xab); if (buf == NULL) { - return; + return -EINVAL; } gettimeofday(&t1, NULL); - cnt = do_aio_readv(blk, &qiov, offset, &total); + ret = do_aio_readv(blk, &qiov, offset, &total); gettimeofday(&t2, NULL); - if (cnt < 0) { - printf("readv failed: %s\n", strerror(-cnt)); + if (ret < 0) { + printf("readv failed: %s\n", strerror(-ret)); goto out; } + cnt = ret; + + ret = 0; if (Pflag) { void *cmp_buf = g_malloc(qiov.size); @@ -XXX,XX +XXX,XX @@ static void readv_f(BlockBackend *blk, int argc, char **argv) if (memcmp(buf, cmp_buf, qiov.size)) { printf("Pattern verification failed at offset %" PRId64 ", %zd bytes\n", offset, qiov.size); + ret = -EINVAL; } g_free(cmp_buf); } @@ -XXX,XX +XXX,XX @@ static void readv_f(BlockBackend *blk, int argc, char **argv) out: qemu_iovec_destroy(&qiov); qemu_io_free(buf); + return ret; } static void write_help(void) @@ -XXX,XX +XXX,XX @@ static void write_help(void) "\n"); } -static void write_f(BlockBackend *blk, int argc, char **argv); +static int write_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t write_cmd = { .name = "write", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t write_cmd = { .help = write_help, }; -static void write_f(BlockBackend *blk, int argc, char **argv) +static int write_f(BlockBackend *blk, int argc, char **argv) { struct timeval t1, t2; bool Cflag = false, qflag = false, bflag = false; bool Pflag = false, zflag = false, cflag = false; int flags = 0; - int c, cnt; + int c, cnt, ret; char *buf = NULL; int64_t offset; int64_t count; @@ -XXX,XX +XXX,XX @@ static void write_f(BlockBackend *blk, int argc, char **argv) Pflag = true; pattern = parse_pattern(optarg); if (pattern < 0) { - return; + return -EINVAL; } break; case 'q': @@ -XXX,XX +XXX,XX @@ static void write_f(BlockBackend *blk, int argc, char **argv) break; default: qemuio_command_usage(&write_cmd); - return; + return -EINVAL; } } if (optind != argc - 2) { qemuio_command_usage(&write_cmd); - return; + return -EINVAL; } if (bflag && zflag) { printf("-b and -z cannot be specified at the same time\n"); - return; + return -EINVAL; } if ((flags & BDRV_REQ_FUA) && (bflag || cflag)) { printf("-f and -b or -c cannot be specified at the same time\n"); - return; + return -EINVAL; } if ((flags & BDRV_REQ_MAY_UNMAP) && !zflag) { printf("-u requires -z to be specified\n"); - return; + return -EINVAL; } if (zflag && Pflag) { printf("-z and -P cannot be specified at the same time\n"); - return; + return -EINVAL; } offset = cvtnum(argv[optind]); if (offset < 0) { print_cvtnum_err(offset, argv[optind]); - return; + return offset; } optind++; count = cvtnum(argv[optind]); if (count < 0) { print_cvtnum_err(count, argv[optind]); - return; + return count; } else if (count > BDRV_REQUEST_MAX_BYTES) { printf("length cannot exceed %" PRIu64 ", given %s\n", (uint64_t)BDRV_REQUEST_MAX_BYTES, argv[optind]); - return; + return -EINVAL; } if (bflag || cflag) { if (!QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)) { printf("%" PRId64 " is not a sector-aligned value for 'offset'\n", offset); - return; + return -EINVAL; } if (!QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)) { printf("%"PRId64" is not a sector-aligned value for 'count'\n", count); - return; + return -EINVAL; } } @@ -XXX,XX +XXX,XX @@ static void write_f(BlockBackend *blk, int argc, char **argv) gettimeofday(&t1, NULL); if (bflag) { - cnt = do_save_vmstate(blk, buf, offset, count, &total); + ret = do_save_vmstate(blk, buf, offset, count, &total); } else if (zflag) { - cnt = do_co_pwrite_zeroes(blk, offset, count, flags, &total); + ret = do_co_pwrite_zeroes(blk, offset, count, flags, &total); } else if (cflag) { - cnt = do_write_compressed(blk, buf, offset, count, &total); + ret = do_write_compressed(blk, buf, offset, count, &total); } else { - cnt = do_pwrite(blk, buf, offset, count, flags, &total); + ret = do_pwrite(blk, buf, offset, count, flags, &total); } gettimeofday(&t2, NULL); - if (cnt < 0) { - printf("write failed: %s\n", strerror(-cnt)); + if (ret < 0) { + printf("write failed: %s\n", strerror(-ret)); goto out; } + cnt = ret; + + ret = 0; if (qflag) { goto out; @@ -XXX,XX +XXX,XX @@ out: if (!zflag) { qemu_io_free(buf); } + return ret; } static void @@ -XXX,XX +XXX,XX @@ writev_help(void) "\n"); } -static void writev_f(BlockBackend *blk, int argc, char **argv); +static int writev_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t writev_cmd = { .name = "writev", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t writev_cmd = { .help = writev_help, }; -static void writev_f(BlockBackend *blk, int argc, char **argv) +static int writev_f(BlockBackend *blk, int argc, char **argv) { struct timeval t1, t2; bool Cflag = false, qflag = false; int flags = 0; - int c, cnt; + int c, cnt, ret; char *buf; int64_t offset; /* Some compilers get confused and warn if this is not initialized. */ @@ -XXX,XX +XXX,XX @@ static void writev_f(BlockBackend *blk, int argc, char **argv) case 'P': pattern = parse_pattern(optarg); if (pattern < 0) { - return; + return -EINVAL; } break; default: qemuio_command_usage(&writev_cmd); - return; + return -EINVAL; } } if (optind > argc - 2) { qemuio_command_usage(&writev_cmd); - return; + return -EINVAL; } offset = cvtnum(argv[optind]); if (offset < 0) { print_cvtnum_err(offset, argv[optind]); - return; + return offset; } optind++; nr_iov = argc - optind; buf = create_iovec(blk, &qiov, &argv[optind], nr_iov, pattern); if (buf == NULL) { - return; + return -EINVAL; } gettimeofday(&t1, NULL); - cnt = do_aio_writev(blk, &qiov, offset, flags, &total); + ret = do_aio_writev(blk, &qiov, offset, flags, &total); gettimeofday(&t2, NULL); - if (cnt < 0) { - printf("writev failed: %s\n", strerror(-cnt)); + if (ret < 0) { + printf("writev failed: %s\n", strerror(-ret)); goto out; } + cnt = ret; + + ret = 0; if (qflag) { goto out; @@ -XXX,XX +XXX,XX @@ static void writev_f(BlockBackend *blk, int argc, char **argv) out: qemu_iovec_destroy(&qiov); qemu_io_free(buf); + return ret; } struct aio_ctx { @@ -XXX,XX +XXX,XX @@ static void aio_read_help(void) " standard output stream (with -v option) for subsequent inspection.\n" " The read is performed asynchronously and the aio_flush command must be\n" " used to ensure all outstanding aio requests have been completed.\n" +" Note that due to its asynchronous nature, this command will be\n" +" considered successful once the request is submitted, independently\n" +" of potential I/O errors or pattern mismatches.\n" " -C, -- report statistics in a machine parsable format\n" " -P, -- use a pattern to verify read data\n" " -i, -- treat request as invalid, for exercising stats\n" @@ -XXX,XX +XXX,XX @@ static void aio_read_help(void) "\n"); } -static void aio_read_f(BlockBackend *blk, int argc, char **argv); +static int aio_read_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t aio_read_cmd = { .name = "aio_read", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t aio_read_cmd = { .help = aio_read_help, }; -static void aio_read_f(BlockBackend *blk, int argc, char **argv) +static int aio_read_f(BlockBackend *blk, int argc, char **argv) { int nr_iov, c; struct aio_ctx *ctx = g_new0(struct aio_ctx, 1); @@ -XXX,XX +XXX,XX @@ static void aio_read_f(BlockBackend *blk, int argc, char **argv) ctx->pattern = parse_pattern(optarg); if (ctx->pattern < 0) { g_free(ctx); - return; + return -EINVAL; } break; case 'i': printf("injecting invalid read request\n"); block_acct_invalid(blk_get_stats(blk), BLOCK_ACCT_READ); g_free(ctx); - return; + return 0; case 'q': ctx->qflag = true; break; @@ -XXX,XX +XXX,XX @@ static void aio_read_f(BlockBackend *blk, int argc, char **argv) default: g_free(ctx); qemuio_command_usage(&aio_read_cmd); - return; + return -EINVAL; } } if (optind > argc - 2) { g_free(ctx); qemuio_command_usage(&aio_read_cmd); - return; + return -EINVAL; } ctx->offset = cvtnum(argv[optind]); if (ctx->offset < 0) { - print_cvtnum_err(ctx->offset, argv[optind]); + int ret = ctx->offset; + print_cvtnum_err(ret, argv[optind]); g_free(ctx); - return; + return ret; } optind++; @@ -XXX,XX +XXX,XX @@ static void aio_read_f(BlockBackend *blk, int argc, char **argv) if (ctx->buf == NULL) { block_acct_invalid(blk_get_stats(blk), BLOCK_ACCT_READ); g_free(ctx); - return; + return -EINVAL; } gettimeofday(&ctx->t1, NULL); block_acct_start(blk_get_stats(blk), &ctx->acct, ctx->qiov.size, BLOCK_ACCT_READ); blk_aio_preadv(blk, ctx->offset, &ctx->qiov, 0, aio_read_done, ctx); + return 0; } static void aio_write_help(void) @@ -XXX,XX +XXX,XX @@ static void aio_write_help(void) " filled with a set pattern (0xcdcdcdcd).\n" " The write is performed asynchronously and the aio_flush command must be\n" " used to ensure all outstanding aio requests have been completed.\n" +" Note that due to its asynchronous nature, this command will be\n" +" considered successful once the request is submitted, independently\n" +" of potential I/O errors or pattern mismatches.\n" " -P, -- use different pattern to fill file\n" " -C, -- report statistics in a machine parsable format\n" " -f, -- use Force Unit Access semantics\n" @@ -XXX,XX +XXX,XX @@ static void aio_write_help(void) "\n"); } -static void aio_write_f(BlockBackend *blk, int argc, char **argv); +static int aio_write_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t aio_write_cmd = { .name = "aio_write", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t aio_write_cmd = { .help = aio_write_help, }; -static void aio_write_f(BlockBackend *blk, int argc, char **argv) +static int aio_write_f(BlockBackend *blk, int argc, char **argv) { int nr_iov, c; int pattern = 0xcd; @@ -XXX,XX +XXX,XX @@ static void aio_write_f(BlockBackend *blk, int argc, char **argv) pattern = parse_pattern(optarg); if (pattern < 0) { g_free(ctx); - return; + return -EINVAL; } break; case 'i': printf("injecting invalid write request\n"); block_acct_invalid(blk_get_stats(blk), BLOCK_ACCT_WRITE); g_free(ctx); - return; + return 0; case 'z': ctx->zflag = true; break; default: g_free(ctx); qemuio_command_usage(&aio_write_cmd); - return; + return -EINVAL; } } if (optind > argc - 2) { g_free(ctx); qemuio_command_usage(&aio_write_cmd); - return; + return -EINVAL; } if (ctx->zflag && optind != argc - 2) { printf("-z supports only a single length parameter\n"); g_free(ctx); - return; + return -EINVAL; } if ((flags & BDRV_REQ_MAY_UNMAP) && !ctx->zflag) { printf("-u requires -z to be specified\n"); g_free(ctx); - return; + return -EINVAL; } if (ctx->zflag && ctx->Pflag) { printf("-z and -P cannot be specified at the same time\n"); g_free(ctx); - return; + return -EINVAL; } ctx->offset = cvtnum(argv[optind]); if (ctx->offset < 0) { - print_cvtnum_err(ctx->offset, argv[optind]); + int ret = ctx->offset; + print_cvtnum_err(ret, argv[optind]); g_free(ctx); - return; + return ret; } optind++; @@ -XXX,XX +XXX,XX @@ static void aio_write_f(BlockBackend *blk, int argc, char **argv) if (count < 0) { print_cvtnum_err(count, argv[optind]); g_free(ctx); - return; + return count; } ctx->qiov.size = count; @@ -XXX,XX +XXX,XX @@ static void aio_write_f(BlockBackend *blk, int argc, char **argv) if (ctx->buf == NULL) { block_acct_invalid(blk_get_stats(blk), BLOCK_ACCT_WRITE); g_free(ctx); - return; + return -EINVAL; } gettimeofday(&ctx->t1, NULL); @@ -XXX,XX +XXX,XX @@ static void aio_write_f(BlockBackend *blk, int argc, char **argv) blk_aio_pwritev(blk, ctx->offset, &ctx->qiov, flags, aio_write_done, ctx); } + + return 0; } -static void aio_flush_f(BlockBackend *blk, int argc, char **argv) +static int aio_flush_f(BlockBackend *blk, int argc, char **argv) { BlockAcctCookie cookie; block_acct_start(blk_get_stats(blk), &cookie, 0, BLOCK_ACCT_FLUSH); blk_drain_all(); block_acct_done(blk_get_stats(blk), &cookie); + return 0; } static const cmdinfo_t aio_flush_cmd = { @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t aio_flush_cmd = { .oneline = "completes all outstanding aio requests" }; -static void flush_f(BlockBackend *blk, int argc, char **argv) +static int flush_f(BlockBackend *blk, int argc, char **argv) { - blk_flush(blk); + return blk_flush(blk); } static const cmdinfo_t flush_cmd = { @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t flush_cmd = { .oneline = "flush all in-core file state to disk", }; -static void truncate_f(BlockBackend *blk, int argc, char **argv) +static int truncate_f(BlockBackend *blk, int argc, char **argv) { Error *local_err = NULL; int64_t offset; @@ -XXX,XX +XXX,XX @@ static void truncate_f(BlockBackend *blk, int argc, char **argv) offset = cvtnum(argv[1]); if (offset < 0) { print_cvtnum_err(offset, argv[1]); - return; + return offset; } ret = blk_truncate(blk, offset, PREALLOC_MODE_OFF, &local_err); if (ret < 0) { error_report_err(local_err); - return; + return ret; } + + return 0; } static const cmdinfo_t truncate_cmd = { @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t truncate_cmd = { .oneline = "truncates the current file at the given offset", }; -static void length_f(BlockBackend *blk, int argc, char **argv) +static int length_f(BlockBackend *blk, int argc, char **argv) { int64_t size; char s1[64]; @@ -XXX,XX +XXX,XX @@ static void length_f(BlockBackend *blk, int argc, char **argv) size = blk_getlength(blk); if (size < 0) { printf("getlength: %s\n", strerror(-size)); - return; + return size; } cvtstr(size, s1, sizeof(s1)); printf("%s\n", s1); + return 0; } @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t length_cmd = { }; -static void info_f(BlockBackend *blk, int argc, char **argv) +static int info_f(BlockBackend *blk, int argc, char **argv) { BlockDriverState *bs = blk_bs(blk); BlockDriverInfo bdi; @@ -XXX,XX +XXX,XX @@ static void info_f(BlockBackend *blk, int argc, char **argv) ret = bdrv_get_info(bs, &bdi); if (ret) { - return; + return ret; } cvtstr(bdi.cluster_size, s1, sizeof(s1)); @@ -XXX,XX +XXX,XX @@ static void info_f(BlockBackend *blk, int argc, char **argv) bdrv_image_info_specific_dump(fprintf, stdout, spec_info); qapi_free_ImageInfoSpecific(spec_info); } + + return 0; } @@ -XXX,XX +XXX,XX @@ static void discard_help(void) "\n"); } -static void discard_f(BlockBackend *blk, int argc, char **argv); +static int discard_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t discard_cmd = { .name = "discard", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t discard_cmd = { .help = discard_help, }; -static void discard_f(BlockBackend *blk, int argc, char **argv) +static int discard_f(BlockBackend *blk, int argc, char **argv) { struct timeval t1, t2; bool Cflag = false, qflag = false; @@ -XXX,XX +XXX,XX @@ static void discard_f(BlockBackend *blk, int argc, char **argv) break; default: qemuio_command_usage(&discard_cmd); - return; + return -EINVAL; } } if (optind != argc - 2) { qemuio_command_usage(&discard_cmd); - return; + return -EINVAL; } offset = cvtnum(argv[optind]); if (offset < 0) { print_cvtnum_err(offset, argv[optind]); - return; + return offset; } optind++; bytes = cvtnum(argv[optind]); if (bytes < 0) { print_cvtnum_err(bytes, argv[optind]); - return; + return bytes; } else if (bytes >> BDRV_SECTOR_BITS > BDRV_REQUEST_MAX_SECTORS) { printf("length cannot exceed %"PRIu64", given %s\n", (uint64_t)BDRV_REQUEST_MAX_SECTORS << BDRV_SECTOR_BITS, argv[optind]); - return; + return -EINVAL; } gettimeofday(&t1, NULL); @@ -XXX,XX +XXX,XX @@ static void discard_f(BlockBackend *blk, int argc, char **argv) if (ret < 0) { printf("discard failed: %s\n", strerror(-ret)); - return; + return ret; } /* Finally, report back -- -C gives a parsable format */ @@ -XXX,XX +XXX,XX @@ static void discard_f(BlockBackend *blk, int argc, char **argv) t2 = tsub(t2, t1); print_report("discard", &t2, offset, bytes, bytes, 1, Cflag); } + + return 0; } -static void alloc_f(BlockBackend *blk, int argc, char **argv) +static int alloc_f(BlockBackend *blk, int argc, char **argv) { BlockDriverState *bs = blk_bs(blk); int64_t offset, start, remaining, count; @@ -XXX,XX +XXX,XX @@ static void alloc_f(BlockBackend *blk, int argc, char **argv) start = offset = cvtnum(argv[1]); if (offset < 0) { print_cvtnum_err(offset, argv[1]); - return; + return offset; } if (argc == 3) { count = cvtnum(argv[2]); if (count < 0) { print_cvtnum_err(count, argv[2]); - return; + return count; } } else { count = BDRV_SECTOR_SIZE; @@ -XXX,XX +XXX,XX @@ static void alloc_f(BlockBackend *blk, int argc, char **argv) ret = bdrv_is_allocated(bs, offset, remaining, &num); if (ret < 0) { printf("is_allocated failed: %s\n", strerror(-ret)); - return; + return ret; } offset += num; remaining -= num; @@ -XXX,XX +XXX,XX @@ static void alloc_f(BlockBackend *blk, int argc, char **argv) printf("%"PRId64"/%"PRId64" bytes allocated at offset %s\n", sum_alloc, count, s1); + return 0; } static const cmdinfo_t alloc_cmd = { @@ -XXX,XX +XXX,XX @@ static int map_is_allocated(BlockDriverState *bs, int64_t offset, return firstret; } -static void map_f(BlockBackend *blk, int argc, char **argv) +static int map_f(BlockBackend *blk, int argc, char **argv) { int64_t offset, bytes; char s1[64], s2[64]; @@ -XXX,XX +XXX,XX @@ static void map_f(BlockBackend *blk, int argc, char **argv) bytes = blk_getlength(blk); if (bytes < 0) { error_report("Failed to query image length: %s", strerror(-bytes)); - return; + return bytes; } while (bytes) { ret = map_is_allocated(blk_bs(blk), offset, bytes, &num); if (ret < 0) { error_report("Failed to get allocation status: %s", strerror(-ret)); - return; + return ret; } else if (!num) { error_report("Unexpected end of image"); - return; + return -EIO; } retstr = ret ? " allocated" : "not allocated"; @@ -XXX,XX +XXX,XX @@ static void map_f(BlockBackend *blk, int argc, char **argv) offset += num; bytes -= num; } + + return 0; } static const cmdinfo_t map_cmd = { @@ -XXX,XX +XXX,XX @@ static void reopen_help(void) "\n"); } -static void reopen_f(BlockBackend *blk, int argc, char **argv); +static int reopen_f(BlockBackend *blk, int argc, char **argv); static QemuOptsList reopen_opts = { .name = "reopen", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t reopen_cmd = { .help = reopen_help, }; -static void reopen_f(BlockBackend *blk, int argc, char **argv) +static int reopen_f(BlockBackend *blk, int argc, char **argv) { BlockDriverState *bs = blk_bs(blk); QemuOpts *qopts; @@ -XXX,XX +XXX,XX @@ static void reopen_f(BlockBackend *blk, int argc, char **argv) case 'c': if (bdrv_parse_cache_mode(optarg, &flags, &writethrough) < 0) { error_report("Invalid cache option: %s", optarg); - return; + return -EINVAL; } break; case 'o': if (!qemu_opts_parse_noisily(&reopen_opts, optarg, 0)) { qemu_opts_reset(&reopen_opts); - return; + return -EINVAL; } break; case 'r': if (has_rw_option) { error_report("Only one -r/-w option may be given"); - return; + return -EINVAL; } flags &= ~BDRV_O_RDWR; has_rw_option = true; @@ -XXX,XX +XXX,XX @@ static void reopen_f(BlockBackend *blk, int argc, char **argv) case 'w': if (has_rw_option) { error_report("Only one -r/-w option may be given"); - return; + return -EINVAL; } flags |= BDRV_O_RDWR; has_rw_option = true; @@ -XXX,XX +XXX,XX @@ static void reopen_f(BlockBackend *blk, int argc, char **argv) default: qemu_opts_reset(&reopen_opts); qemuio_command_usage(&reopen_cmd); - return; + return -EINVAL; } } if (optind != argc) { qemu_opts_reset(&reopen_opts); qemuio_command_usage(&reopen_cmd); - return; + return -EINVAL; } if (writethrough != blk_enable_write_cache(blk) && @@ -XXX,XX +XXX,XX @@ static void reopen_f(BlockBackend *blk, int argc, char **argv) { error_report("Cannot change cache.writeback: Device attached"); qemu_opts_reset(&reopen_opts); - return; + return -EBUSY; } if (!(flags & BDRV_O_RDWR)) { @@ -XXX,XX +XXX,XX @@ static void reopen_f(BlockBackend *blk, int argc, char **argv) if (local_err) { error_report_err(local_err); - } else { - blk_set_enable_write_cache(blk, !writethrough); + return -EINVAL; } + + blk_set_enable_write_cache(blk, !writethrough); + return 0; } -static void break_f(BlockBackend *blk, int argc, char **argv) +static int break_f(BlockBackend *blk, int argc, char **argv) { int ret; ret = bdrv_debug_breakpoint(blk_bs(blk), argv[1], argv[2]); if (ret < 0) { printf("Could not set breakpoint: %s\n", strerror(-ret)); + return ret; } + + return 0; } -static void remove_break_f(BlockBackend *blk, int argc, char **argv) +static int remove_break_f(BlockBackend *blk, int argc, char **argv) { int ret; ret = bdrv_debug_remove_breakpoint(blk_bs(blk), argv[1]); if (ret < 0) { printf("Could not remove breakpoint %s: %s\n", argv[1], strerror(-ret)); + return ret; } + + return 0; } static const cmdinfo_t break_cmd = { @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t remove_break_cmd = { .oneline = "remove a breakpoint by tag", }; -static void resume_f(BlockBackend *blk, int argc, char **argv) +static int resume_f(BlockBackend *blk, int argc, char **argv) { int ret; ret = bdrv_debug_resume(blk_bs(blk), argv[1]); if (ret < 0) { printf("Could not resume request: %s\n", strerror(-ret)); + return ret; } + + return 0; } static const cmdinfo_t resume_cmd = { @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t resume_cmd = { .oneline = "resumes the request tagged as tag", }; -static void wait_break_f(BlockBackend *blk, int argc, char **argv) +static int wait_break_f(BlockBackend *blk, int argc, char **argv) { while (!bdrv_debug_is_suspended(blk_bs(blk), argv[1])) { aio_poll(blk_get_aio_context(blk), true); } + return 0; } static const cmdinfo_t wait_break_cmd = { @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t wait_break_cmd = { .oneline = "waits for the suspension of a request", }; -static void abort_f(BlockBackend *blk, int argc, char **argv) +static int abort_f(BlockBackend *blk, int argc, char **argv) { abort(); } @@ -XXX,XX +XXX,XX @@ static void sigraise_help(void) "\n", SIGTERM); } -static void sigraise_f(BlockBackend *blk, int argc, char **argv); +static int sigraise_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t sigraise_cmd = { .name = "sigraise", @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t sigraise_cmd = { .help = sigraise_help, }; -static void sigraise_f(BlockBackend *blk, int argc, char **argv) +static int sigraise_f(BlockBackend *blk, int argc, char **argv) { int64_t sig = cvtnum(argv[1]); if (sig < 0) { print_cvtnum_err(sig, argv[1]); - return; + return sig; } else if (sig > NSIG) { printf("signal argument '%s' is too large to be a valid signal\n", argv[1]); - return; + return -EINVAL; } /* Using raise() to kill this process does not necessarily flush all open @@ -XXX,XX +XXX,XX @@ static void sigraise_f(BlockBackend *blk, int argc, char **argv) fflush(stderr); raise(sig); + + return 0; } static void sleep_cb(void *opaque) @@ -XXX,XX +XXX,XX @@ static void sleep_cb(void *opaque) *expired = true; } -static void sleep_f(BlockBackend *blk, int argc, char **argv) +static int sleep_f(BlockBackend *blk, int argc, char **argv) { char *endptr; long ms; @@ -XXX,XX +XXX,XX @@ static void sleep_f(BlockBackend *blk, int argc, char **argv) ms = strtol(argv[1], &endptr, 0); if (ms < 0 || *endptr != '\0') { printf("%s is not a valid number\n", argv[1]); - return; + return -EINVAL; } timer = timer_new_ns(QEMU_CLOCK_HOST, sleep_cb, &expired); @@ -XXX,XX +XXX,XX @@ static void sleep_f(BlockBackend *blk, int argc, char **argv) } timer_free(timer); + return 0; } static const cmdinfo_t sleep_cmd = { @@ -XXX,XX +XXX,XX @@ static void help_all(void) printf("\nUse 'help commandname' for extended help.\n"); } -static void help_f(BlockBackend *blk, int argc, char **argv) +static int help_f(BlockBackend *blk, int argc, char **argv) { const cmdinfo_t *ct; if (argc == 1) { help_all(); - return; + return 0; } ct = find_command(argv[1]); if (ct == NULL) { printf("command %s not found\n", argv[1]); - return; + return -EINVAL; } help_onecmd(argv[1], ct); + return 0; } static const cmdinfo_t help_cmd = { @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t help_cmd = { .oneline = "help for one or all commands", }; -void qemuio_command(BlockBackend *blk, const char *cmd) +int qemuio_command(BlockBackend *blk, const char *cmd) { AioContext *ctx; char *input; const cmdinfo_t *ct; char **v; int c; + int ret = 0; input = g_strdup(cmd); v = breakline(input, &c); @@ -XXX,XX +XXX,XX @@ void qemuio_command(BlockBackend *blk, const char *cmd) if (ct) { ctx = blk ? blk_get_aio_context(blk) : qemu_get_aio_context(); aio_context_acquire(ctx); - command(blk, ct, c, v); + ret = command(blk, ct, c, v); aio_context_release(ctx); } else { fprintf(stderr, "command \"%s\" not found\n", v[0]); + ret = -EINVAL; } } g_free(input); g_free(v); + + return ret; } static void __attribute((constructor)) init_qemuio_commands(void) diff --git a/qemu-io.c b/qemu-io.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io.c +++ b/qemu-io.c @@ -XXX,XX +XXX,XX @@ static int get_eof_char(void) #endif } -static void close_f(BlockBackend *blk, int argc, char **argv) +static int close_f(BlockBackend *blk, int argc, char **argv) { blk_unref(qemuio_blk); qemuio_blk = NULL; + return 0; } static const cmdinfo_t close_cmd = { @@ -XXX,XX +XXX,XX @@ static void open_help(void) "\n"); } -static void open_f(BlockBackend *blk, int argc, char **argv); +static int open_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t open_cmd = { .name = "open", @@ -XXX,XX +XXX,XX @@ static QemuOptsList empty_opts = { }, }; -static void open_f(BlockBackend *blk, int argc, char **argv) +static int open_f(BlockBackend *blk, int argc, char **argv) { int flags = BDRV_O_UNMAP; int readonly = 0; bool writethrough = true; int c; + int ret; QemuOpts *qopts; QDict *opts; bool force_share = false; @@ -XXX,XX +XXX,XX @@ static void open_f(BlockBackend *blk, int argc, char **argv) if (bdrv_parse_cache_mode(optarg, &flags, &writethrough) < 0) { error_report("Invalid cache option: %s", optarg); qemu_opts_reset(&empty_opts); - return; + return -EINVAL; } break; case 'd': if (bdrv_parse_discard_flags(optarg, &flags) < 0) { error_report("Invalid discard option: %s", optarg); qemu_opts_reset(&empty_opts); - return; + return -EINVAL; } break; case 'o': if (imageOpts) { printf("--image-opts and 'open -o' are mutually exclusive\n"); qemu_opts_reset(&empty_opts); - return; + return -EINVAL; } if (!qemu_opts_parse_noisily(&empty_opts, optarg, false)) { qemu_opts_reset(&empty_opts); - return; + return -EINVAL; } break; case 'U': @@ -XXX,XX +XXX,XX @@ static void open_f(BlockBackend *blk, int argc, char **argv) default: qemu_opts_reset(&empty_opts); qemuio_command_usage(&open_cmd); - return; + return -EINVAL; } } @@ -XXX,XX +XXX,XX @@ static void open_f(BlockBackend *blk, int argc, char **argv) if (imageOpts && (optind == argc - 1)) { if (!qemu_opts_parse_noisily(&empty_opts, argv[optind], false)) { qemu_opts_reset(&empty_opts); - return; + return -EINVAL; } optind++; } @@ -XXX,XX +XXX,XX @@ static void open_f(BlockBackend *blk, int argc, char **argv) qemu_opts_reset(&empty_opts); if (optind == argc - 1) { - openfile(argv[optind], flags, writethrough, force_share, opts); + ret = openfile(argv[optind], flags, writethrough, force_share, opts); } else if (optind == argc) { - openfile(NULL, flags, writethrough, force_share, opts); + ret = openfile(NULL, flags, writethrough, force_share, opts); } else { qobject_unref(opts); qemuio_command_usage(&open_cmd); + return -EINVAL; + } + + if (ret) { + return -EINVAL; } + + return 0; } -static void quit_f(BlockBackend *blk, int argc, char **argv) +static int quit_f(BlockBackend *blk, int argc, char **argv) { quit_qemu_io = true; + return 0; } static const cmdinfo_t quit_cmd = { -- 2.17.1 Currently, qemu-io basically always returns success when it gets to interactive mode (so once the whole command line has been parsed; even before the commands on the command line are interpreted). That is not very useful. This patch makes qemu-io return failure when any of the executed commands failed. Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=1519617 Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20180509194302.21585-4-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- qemu-io.c | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) diff --git a/qemu-io.c b/qemu-io.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io.c +++ b/qemu-io.c @@ -XXX,XX +XXX,XX @@ static void prep_fetchline(void *opaque) *fetchable= 1; } -static void command_loop(void) +static int command_loop(void) { int i, fetchable = 0, prompted = 0; + int ret, last_error = 0; char *input; for (i = 0; !quit_qemu_io && i < ncmdline; i++) { - qemuio_command(qemuio_blk, cmdline[i]); + ret = qemuio_command(qemuio_blk, cmdline[i]); + if (ret < 0) { + last_error = ret; + } } if (cmdline) { g_free(cmdline); - return; + return last_error; } while (!quit_qemu_io) { @@ -XXX,XX +XXX,XX @@ static void command_loop(void) if (input == NULL) { break; } - qemuio_command(qemuio_blk, input); + ret = qemuio_command(qemuio_blk, input); g_free(input); + if (ret < 0) { + last_error = ret; + } + prompted = 0; fetchable = 0; } qemu_set_fd_handler(STDIN_FILENO, NULL, NULL, NULL); + + return last_error; } static void add_user_command(char *optarg) @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) int c; int opt_index = 0; int flags = BDRV_O_UNMAP; + int ret; bool writethrough = true; Error *local_error = NULL; QDict *opts = NULL; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) } } } - command_loop(); + ret = command_loop(); /* * Make sure all outstanding requests complete before the program exits. @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) blk_unref(qemuio_blk); g_free(readline_state); - return 0; + + if (ret < 0) { + return 1; + } else { + return 0; + } } -- 2.17.1 With qemu-io now returning a useful exit code, some tests may find it sufficient to just query that instead of logging (and filtering) the whole output. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20180509194302.21585-5-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/iotests.py | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ def qemu_io(*args): sys.stderr.write('qemu-io received signal %i: %s\n' % (-exitcode, ' '.join(args))) return subp.communicate()[0] +def qemu_io_silent(*args): + '''Run qemu-io and return the exit code, suppressing stdout''' + args = qemu_io_args + list(args) + exitcode = subprocess.call(args, stdout=open('/dev/null', 'w')) + if exitcode < 0: + sys.stderr.write('qemu-io received signal %i: %s\n' % + (-exitcode, ' '.join(args))) + return exitcode + class QemuIoInteractive: def __init__(self, *args): -- 2.17.1 As a showcase of how you can use qemu-io's exit code to determine success or failure (same for qemu-img), this test is changed to use qemu_io_silent() instead of qemu_io(), and to assert the exit code instead of logging the filtered result. One real advantage of this is that in case of an error, you get a backtrace that helps you locate the issue in the test file quickly. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20180509194302.21585-6-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/216 | 23 ++++++++++++----------- tests/qemu-iotests/216.out | 17 ++--------------- 2 files changed, 14 insertions(+), 26 deletions(-) diff --git a/tests/qemu-iotests/216 b/tests/qemu-iotests/216 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/216 +++ b/tests/qemu-iotests/216 @@ -XXX,XX +XXX,XX @@ # Creator/Owner: Max Reitz <mreitz@redhat.com> import iotests -from iotests import log, qemu_img_pipe, qemu_io, filter_qemu_io +from iotests import log, qemu_img, qemu_io_silent # Need backing file support iotests.verify_image_format(supported_fmts=['qcow2', 'qcow', 'qed', 'vmdk']) @@ -XXX,XX +XXX,XX @@ with iotests.FilePath('base.img') as base_img_path, \ log('--- Setting up images ---') log('') - qemu_img_pipe('create', '-f', iotests.imgfmt, base_img_path, '64M') + assert qemu_img('create', '-f', iotests.imgfmt, base_img_path, '64M') == 0 + assert qemu_io_silent(base_img_path, '-c', 'write -P 1 0M 1M') == 0 + assert qemu_img('create', '-f', iotests.imgfmt, '-b', base_img_path, + top_img_path) == 0 + assert qemu_io_silent(top_img_path, '-c', 'write -P 2 1M 1M') == 0 - log(filter_qemu_io(qemu_io(base_img_path, '-c', 'write -P 1 0M 1M'))) - - qemu_img_pipe('create', '-f', iotests.imgfmt, '-b', base_img_path, - top_img_path) - - log(filter_qemu_io(qemu_io(top_img_path, '-c', 'write -P 2 1M 1M'))) + log('Done') log('') log('--- Doing COR ---') @@ -XXX,XX +XXX,XX @@ with iotests.FilePath('base.img') as base_img_path, \ log('--- Checking COR result ---') log('') - log(filter_qemu_io(qemu_io(base_img_path, '-c', 'discard 0 64M'))) - log(filter_qemu_io(qemu_io(top_img_path, '-c', 'read -P 1 0M 1M'))) - log(filter_qemu_io(qemu_io(top_img_path, '-c', 'read -P 2 1M 1M'))) + assert qemu_io_silent(base_img_path, '-c', 'discard 0 64M') == 0 + assert qemu_io_silent(top_img_path, '-c', 'read -P 1 0M 1M') == 0 + assert qemu_io_silent(top_img_path, '-c', 'read -P 2 1M 1M') == 0 + + log('Done') diff --git a/tests/qemu-iotests/216.out b/tests/qemu-iotests/216.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/216.out +++ b/tests/qemu-iotests/216.out @@ -XXX,XX +XXX,XX @@ --- Setting up images --- -wrote 1048576/1048576 bytes at offset 0 -1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) - -wrote 1048576/1048576 bytes at offset 1048576 -1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) - +Done --- Doing COR --- @@ -XXX,XX +XXX,XX @@ wrote 1048576/1048576 bytes at offset 1048576 --- Checking COR result --- -discard 67108864/67108864 bytes at offset 0 -64 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) - -read 1048576/1048576 bytes at offset 0 -1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) - -read 1048576/1048576 bytes at offset 1048576 -1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) - +Done -- 2.17.1 Currently, rebase interprets a relative path for the new backing image as follows: (1) Open the new backing image with the given relative path (thus relative to qemu-img's working directory). (2) Write it directly into the overlay's backing path field (thus relative to the overlay). If the overlay is not in qemu-img's working directory, both will be different interpretations, which may either lead to an error somewhere (either rebase fails because it cannot open the new backing image, or your overlay becomes unusable because its backing path does not point to a file), or, even worse, it may result in your rebase being performed for a different backing file than what your overlay will point to after the rebase. Fix this by interpreting the target backing path as relative to the overlay, like qemu-img does everywhere else. Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=1569835 Cc: qemu-stable@nongnu.org Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20180509182002.8044-2-mreitz@redhat.com Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- qemu-img.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int img_rebase(int argc, char **argv) } if (out_baseimg[0]) { + const char *overlay_filename; + char *out_real_path; + options = qdict_new(); if (out_basefmt) { qdict_put_str(options, "driver", out_basefmt); @@ -XXX,XX +XXX,XX @@ static int img_rebase(int argc, char **argv) qdict_put_bool(options, BDRV_OPT_FORCE_SHARE, true); } - blk_new_backing = blk_new_open(out_baseimg, NULL, + overlay_filename = bs->exact_filename[0] ? bs->exact_filename + : bs->filename; + out_real_path = g_malloc(PATH_MAX); + + bdrv_get_full_backing_filename_from_filename(overlay_filename, + out_baseimg, + out_real_path, + PATH_MAX, + &local_err); + if (local_err) { + error_reportf_err(local_err, + "Could not resolve backing filename: "); + ret = -1; + g_free(out_real_path); + goto out; + } + + blk_new_backing = blk_new_open(out_real_path, NULL, options, src_flags, &local_err); + g_free(out_real_path); if (!blk_new_backing) { error_reportf_err(local_err, "Could not open new backing file '%s': ", -- 2.17.1 Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20180509182002.8044-3-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/024 | 82 ++++++++++++++++++++++++++++++++++++-- tests/qemu-iotests/024.out | 30 ++++++++++++++ 2 files changed, 109 insertions(+), 3 deletions(-) diff --git a/tests/qemu-iotests/024 b/tests/qemu-iotests/024 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/024 +++ b/tests/qemu-iotests/024 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - _cleanup_test_img - rm -f "$TEST_DIR/t.$IMGFMT.base_old" - rm -f "$TEST_DIR/t.$IMGFMT.base_new" + _cleanup_test_img + rm -f "$TEST_DIR/t.$IMGFMT.base_old" + rm -f "$TEST_DIR/t.$IMGFMT.base_new" + + rm -f "$TEST_DIR/subdir/t.$IMGFMT" + rm -f "$TEST_DIR/subdir/t.$IMGFMT.base_old" + rm -f "$TEST_DIR/subdir/t.$IMGFMT.base_new" + rmdir "$TEST_DIR/subdir" 2> /dev/null } trap "_cleanup; exit \$status" 0 1 2 3 15 @@ -XXX,XX +XXX,XX @@ io_pattern readv $((13 * CLUSTER_SIZE)) $CLUSTER_SIZE 0 1 0x00 io_pattern readv $((14 * CLUSTER_SIZE)) $CLUSTER_SIZE 0 1 0x11 io_pattern readv $((15 * CLUSTER_SIZE)) $CLUSTER_SIZE 0 1 0x00 +echo +echo "=== Test rebase in a subdirectory of the working directory ===" +echo + +# Clean up the old images beforehand so they do not interfere with +# this test +_cleanup + +mkdir "$TEST_DIR/subdir" + +# Relative to the overlay +BASE_OLD_OREL="t.$IMGFMT.base_old" +BASE_NEW_OREL="t.$IMGFMT.base_new" + +# Relative to $TEST_DIR (which is going to be our working directory) +OVERLAY_WREL="subdir/t.$IMGFMT" + +BASE_OLD="$TEST_DIR/subdir/$BASE_OLD_OREL" +BASE_NEW="$TEST_DIR/subdir/$BASE_NEW_OREL" +OVERLAY="$TEST_DIR/$OVERLAY_WREL" + +# Test done here: +# +# Backing (old): 11 11 -- 11 +# Backing (new): -- 22 22 11 +# Overlay: -- -- -- -- +# +# Rebasing works, we have verified that above. Here, we just want to +# see that rebasing is done for the correct target backing file. + +TEST_IMG=$BASE_OLD _make_test_img 1M +TEST_IMG=$BASE_NEW _make_test_img 1M +TEST_IMG=$OVERLAY _make_test_img -b "$BASE_OLD_OREL" 1M + +echo + +$QEMU_IO "$BASE_OLD" \ + -c "write -P 0x11 $((0 * CLUSTER_SIZE)) $((2 * CLUSTER_SIZE))" \ + -c "write -P 0x11 $((3 * CLUSTER_SIZE)) $((1 * CLUSTER_SIZE))" \ + | _filter_qemu_io + +$QEMU_IO "$BASE_NEW" \ + -c "write -P 0x22 $((1 * CLUSTER_SIZE)) $((2 * CLUSTER_SIZE))" \ + -c "write -P 0x11 $((3 * CLUSTER_SIZE)) $((1 * CLUSTER_SIZE))" \ + | _filter_qemu_io + +echo + +pushd "$TEST_DIR" >/dev/null +$QEMU_IMG rebase -f "$IMGFMT" -b "$BASE_NEW_OREL" "$OVERLAY_WREL" +popd >/dev/null + +# Verify the backing path is correct +TEST_IMG=$OVERLAY _img_info | grep '^backing file' + +echo + +# Verify the data is correct +$QEMU_IO "$OVERLAY" \ + -c "read -P 0x11 $((0 * CLUSTER_SIZE)) $CLUSTER_SIZE" \ + -c "read -P 0x11 $((1 * CLUSTER_SIZE)) $CLUSTER_SIZE" \ + -c "read -P 0x00 $((2 * CLUSTER_SIZE)) $CLUSTER_SIZE" \ + -c "read -P 0x11 $((3 * CLUSTER_SIZE)) $CLUSTER_SIZE" \ + | _filter_qemu_io + +echo + +# Verify that cluster #3 is not allocated (because it is the same in +# $BASE_OLD and $BASE_NEW) +$QEMU_IMG map "$OVERLAY" | _filter_qemu_img_map + # success, all done echo "*** done" diff --git a/tests/qemu-iotests/024.out b/tests/qemu-iotests/024.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/024.out +++ b/tests/qemu-iotests/024.out @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 917504 === IO: pattern 0x00 read 65536/65536 bytes at offset 983040 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Test rebase in a subdirectory of the working directory === + +Formatting 'TEST_DIR/subdir/t.IMGFMT.base_old', fmt=IMGFMT size=1048576 +Formatting 'TEST_DIR/subdir/t.IMGFMT.base_new', fmt=IMGFMT size=1048576 +Formatting 'TEST_DIR/subdir/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=t.IMGFMT.base_old + +wrote 131072/131072 bytes at offset 0 +128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 65536/65536 bytes at offset 196608 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 131072/131072 bytes at offset 65536 +128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 65536/65536 bytes at offset 196608 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +backing file: t.IMGFMT.base_new (actual path: TEST_DIR/subdir/t.IMGFMT.base_new) + +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) +read 65536/65536 bytes at offset 196608 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Offset Length File +0 0x30000 TEST_DIR/subdir/t.IMGFMT +0x30000 0x10000 TEST_DIR/subdir/t.IMGFMT.base_new *** done -- 2.17.1 Currently, qemu-img convert writes zeroes when it reads zeroes. Sometimes it does not because the target is initialized to zeroes anyway, so we do not need to overwrite (and thus potentially allocate) it. This is never the case for targets with backing files, though. But even they may have an area that is initialized to zeroes, and that is the area past the end of the backing file (if that is shorter than the overlay). So if the target format's unallocated blocks are zero and there is a gap between the target's backing file's end and the target's end, we do not have to explicitly write zeroes there. Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=1527898 Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20180501165750.19242-2-mreitz@redhat.com Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- qemu-img.c | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ typedef struct ImgConvertState { BlockBackend *target; bool has_zero_init; bool compressed; + bool unallocated_blocks_are_zero; bool target_has_backing; + int64_t target_backing_sectors; /* negative if unknown */ bool wr_in_order; bool copy_range; int min_sparse; @@ -XXX,XX +XXX,XX @@ static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num) { int64_t src_cur_offset; int ret, n, src_cur; + bool post_backing_zero = false; convert_select_part(s, sector_num, &src_cur, &src_cur_offset); assert(s->total_sectors > sector_num); n = MIN(s->total_sectors - sector_num, BDRV_REQUEST_MAX_SECTORS); + if (s->target_backing_sectors >= 0) { + if (sector_num >= s->target_backing_sectors) { + post_backing_zero = s->unallocated_blocks_are_zero; + } else if (sector_num + n > s->target_backing_sectors) { + /* Split requests around target_backing_sectors (because + * starting from there, zeros are handled differently) */ + n = s->target_backing_sectors - sector_num; + } + } + if (s->sector_next_status <= sector_num) { int64_t count = n * BDRV_SECTOR_SIZE; @@ -XXX,XX +XXX,XX @@ static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num) n = DIV_ROUND_UP(count, BDRV_SECTOR_SIZE); if (ret & BDRV_BLOCK_ZERO) { - s->status = BLK_ZERO; + s->status = post_backing_zero ? BLK_BACKING_FILE : BLK_ZERO; } else if (ret & BDRV_BLOCK_DATA) { s->status = BLK_DATA; } else { @@ -XXX,XX +XXX,XX @@ static int img_convert(int argc, char **argv) } } + if (s.target_has_backing) { + /* Errors are treated as "backing length unknown" (which means + * s.target_backing_sectors has to be negative, which it will + * be automatically). The backing file length is used only + * for optimizations, so such a case is not fatal. */ + s.target_backing_sectors = bdrv_nb_sectors(out_bs->backing->bs); + } else { + s.target_backing_sectors = -1; + } + ret = bdrv_get_info(out_bs, &bdi); if (ret < 0) { if (s.compressed) { @@ -XXX,XX +XXX,XX @@ static int img_convert(int argc, char **argv) } else { s.compressed = s.compressed || bdi.needs_compressed_writes; s.cluster_sectors = bdi.cluster_size / BDRV_SECTOR_SIZE; + s.unallocated_blocks_are_zero = bdi.unallocated_blocks_are_zero; } ret = convert_do_copy(&s); -- 2.17.1 This adds a test case to 122 for what happens when you convert to a target with a backing file that is shorter than the target, and the image format does not support efficient zero writes (as is the case with qcow2 v2). Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20180501165750.19242-3-mreitz@redhat.com Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/122 | 42 ++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/122.out | 18 ++++++++++++++++ 2 files changed, 60 insertions(+) diff --git a/tests/qemu-iotests/122 b/tests/qemu-iotests/122 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/122 +++ b/tests/qemu-iotests/122 @@ -XXX,XX +XXX,XX @@ $QEMU_IMG convert -O $IMGFMT -c -B "$TEST_IMG".base "$TEST_IMG" "$TEST_IMG".orig $QEMU_IO -c "read -P 0 0 3M" "$TEST_IMG".orig 2>&1 | _filter_qemu_io | _filter_testdir +echo +echo "=== Converting to an overlay larger than its backing file ===" +echo + +TEST_IMG="$TEST_IMG".base _make_test_img 256M +# Needs to be at least how much an L2 table covers +# (64 kB/entry * 64 kB / 8 B/entry = 512 MB) +# That way, qcow2 will yield at least two status request responses. +# With just a single response, it would always say "Allocated in the +# backing file", so the optimization qemu-img convert tries to do is +# done automatically. Once it has to be queried twice, however (and +# one of the queries is completely after the end of the backing file), +# the block layer will automatically add a ZERO flag that qemu-img +# convert used to follow up with a zero write to the target. +# We do not want such a zero write, however, because we are past the +# end of the backing file on the target as well, so we do not need to +# write anything there. +_make_test_img -b "$TEST_IMG".base 768M + +# Use compat=0.10 as the output so there is no zero cluster support +$QEMU_IMG convert -O $IMGFMT -B "$TEST_IMG".base -o compat=0.10 \ + "$TEST_IMG" "$TEST_IMG".orig +# See that nothing has been allocated past 64M +$QEMU_IMG map "$TEST_IMG".orig | _filter_qemu_img_map + +echo + +# Just before the end of the backing file +$QEMU_IO -c 'write -P 0x11 255M 1M' "$TEST_IMG".base 2>&1 | _filter_qemu_io +# Somewhere in the second L2 table +$QEMU_IO -c 'write -P 0x22 600M 1M' "$TEST_IMG" 2>&1 | _filter_qemu_io + +$QEMU_IMG convert -O $IMGFMT -B "$TEST_IMG".base -o compat=0.10 \ + "$TEST_IMG" "$TEST_IMG".orig + +$QEMU_IMG map "$TEST_IMG".orig | _filter_qemu_img_map +$QEMU_IO -c 'read -P 0x11 255M 1M' \ + -c 'read -P 0x22 600M 1M' \ + "$TEST_IMG".orig \ + | _filter_qemu_io + + echo echo "=== Concatenate multiple source images ===" echo diff --git a/tests/qemu-iotests/122.out b/tests/qemu-iotests/122.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/122.out +++ b/tests/qemu-iotests/122.out @@ -XXX,XX +XXX,XX @@ read 3145728/3145728 bytes at offset 0 read 3145728/3145728 bytes at offset 0 3 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +=== Converting to an overlay larger than its backing file === + +Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=268435456 +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=805306368 backing_file=TEST_DIR/t.IMGFMT.base +Offset Length File + +wrote 1048576/1048576 bytes at offset 267386880 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 1048576/1048576 bytes at offset 629145600 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +Offset Length File +0xff00000 0x100000 TEST_DIR/t.IMGFMT.base +0x25800000 0x100000 TEST_DIR/t.IMGFMT.orig +read 1048576/1048576 bytes at offset 267386880 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 1048576/1048576 bytes at offset 629145600 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + === Concatenate multiple source images === Formatting 'TEST_DIR/t.IMGFMT.1', fmt=IMGFMT size=4194304 -- 2.17.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> It's possible, that job was finished during waiting. In this case we will see error message "Timeout waiting for job to pause" which is not very informative. So, let's check during waiting iteration that the job exists. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-id: 20180601115923.17159-1-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/iotests.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ class QMPTestCase(unittest.TestCase): with Timeout(1, "Timeout waiting for job to pause"): while True: result = self.vm.qmp('query-block-jobs') + found = False for job in result['return']: - if job['device'] == job_id and job['paused'] == True and job['busy'] == False: - return job + if job['device'] == job_id: + found = True + if job['paused'] == True and job['busy'] == False: + return job + break + assert found def pause_job(self, job_id='job0', wait=True): result = self.vm.qmp('block-job-pause', device=job_id) -- 2.17.1 219 has two issues that may lead to sporadic failure, both of which are the result of issuing query-jobs too early after a job has been modified. This can then lead to different results based on whether the modification has taken effect already or not. First, query-jobs is issued right after the job has been created. Besides its current progress possibly being in any random state (which has already been taken care of), its total progress too is basically arbitrary, because the job may not yet have been able to determine it. This patch addresses this by just filtering the total progress, like what has been done for the current progress already. However, for more clarity, the filtering is changed to replace the values by a string 'FILTERED' instead of deleting them. Secondly, query-jobs is issued right after a job has been resumed. The job may or may not yet have had the time to actually perform any I/O, and thus its current progress may or may not have advanced. To make sure it has indeed advanced (which is what the reference output already assumes), keep querying it until it has. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20180606190628.8170-1-mreitz@redhat.com Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/219 | 26 ++++++++++++++++++++------ tests/qemu-iotests/219.out | 10 +++++----- 2 files changed, 25 insertions(+), 11 deletions(-) diff --git a/tests/qemu-iotests/219 b/tests/qemu-iotests/219 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/219 +++ b/tests/qemu-iotests/219 @@ -XXX,XX +XXX,XX @@ def test_pause_resume(vm): iotests.log(vm.qmp(pause_cmd, **{pause_arg: 'job0'})) pause_wait(vm, 'job0') iotests.log(iotests.filter_qmp_event(vm.event_wait('JOB_STATUS_CHANGE'))) - iotests.log(vm.qmp('query-jobs')) + result = vm.qmp('query-jobs') + iotests.log(result) + + old_progress = result['return'][0]['current-progress'] + total_progress = result['return'][0]['total-progress'] iotests.log(vm.qmp(resume_cmd, **{resume_arg: 'job0'})) iotests.log(iotests.filter_qmp_event(vm.event_wait('JOB_STATUS_CHANGE'))) - iotests.log(vm.qmp('query-jobs')) + if old_progress < total_progress: + # Wait for the job to advance + while result['return'][0]['current-progress'] == old_progress: + result = vm.qmp('query-jobs') + iotests.log(result) + else: + # Already reached the end, so the job cannot advance + # any further; therefore, the query-jobs result can be + # logged immediately + iotests.log(vm.qmp('query-jobs')) def test_job_lifecycle(vm, job, job_args, has_ready=False): iotests.log('') @@ -XXX,XX +XXX,XX @@ def test_job_lifecycle(vm, job, job_args, has_ready=False): iotests.log(vm.qmp(job, job_id='job0', **job_args)) # Depending on the storage, the first request may or may not have completed - # yet, so filter out the progress. Later query-job calls don't need the - # filtering because the progress is made deterministic by the block job - # speed + # yet (and the total progress may not have been fully determined yet), so + # filter out the progress. Later query-job calls don't need the filtering + # because the progress is made deterministic by the block job speed result = vm.qmp('query-jobs') for j in result['return']: - del j['current-progress'] + j['current-progress'] = 'FILTERED' + j['total-progress'] = 'FILTERED' iotests.log(result) # undefined -> created -> running diff --git a/tests/qemu-iotests/219.out b/tests/qemu-iotests/219.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/219.out +++ b/tests/qemu-iotests/219.out @@ -XXX,XX +XXX,XX @@ Launching VM... Starting block job: drive-mirror (auto-finalize: True; auto-dismiss: True) {u'return': {}} -{u'return': [{u'status': u'running', u'total-progress': 4194304, u'id': u'job0', u'type': u'mirror'}]} +{u'return': [{u'status': u'running', u'current-progress': 'FILTERED', u'total-progress': 'FILTERED', u'id': u'job0', u'type': u'mirror'}]} {u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'status': u'created', u'id': u'job0'}, u'event': u'JOB_STATUS_CHANGE'} {u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'status': u'running', u'id': u'job0'}, u'event': u'JOB_STATUS_CHANGE'} @@ -XXX,XX +XXX,XX @@ Waiting for PENDING state... Starting block job: drive-backup (auto-finalize: True; auto-dismiss: True) {u'return': {}} -{u'return': [{u'status': u'running', u'total-progress': 4194304, u'id': u'job0', u'type': u'backup'}]} +{u'return': [{u'status': u'running', u'current-progress': 'FILTERED', u'total-progress': 'FILTERED', u'id': u'job0', u'type': u'backup'}]} {u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'status': u'created', u'id': u'job0'}, u'event': u'JOB_STATUS_CHANGE'} {u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'status': u'running', u'id': u'job0'}, u'event': u'JOB_STATUS_CHANGE'} @@ -XXX,XX +XXX,XX @@ Waiting for PENDING state... Starting block job: drive-backup (auto-finalize: True; auto-dismiss: False) {u'return': {}} -{u'return': [{u'status': u'running', u'total-progress': 4194304, u'id': u'job0', u'type': u'backup'}]} +{u'return': [{u'status': u'running', u'current-progress': 'FILTERED', u'total-progress': 'FILTERED', u'id': u'job0', u'type': u'backup'}]} {u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'status': u'created', u'id': u'job0'}, u'event': u'JOB_STATUS_CHANGE'} {u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'status': u'running', u'id': u'job0'}, u'event': u'JOB_STATUS_CHANGE'} @@ -XXX,XX +XXX,XX @@ Waiting for PENDING state... Starting block job: drive-backup (auto-finalize: False; auto-dismiss: True) {u'return': {}} -{u'return': [{u'status': u'running', u'total-progress': 4194304, u'id': u'job0', u'type': u'backup'}]} +{u'return': [{u'status': u'running', u'current-progress': 'FILTERED', u'total-progress': 'FILTERED', u'id': u'job0', u'type': u'backup'}]} {u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'status': u'created', u'id': u'job0'}, u'event': u'JOB_STATUS_CHANGE'} {u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'status': u'running', u'id': u'job0'}, u'event': u'JOB_STATUS_CHANGE'} @@ -XXX,XX +XXX,XX @@ Waiting for PENDING state... Starting block job: drive-backup (auto-finalize: False; auto-dismiss: False) {u'return': {}} -{u'return': [{u'status': u'running', u'total-progress': 4194304, u'id': u'job0', u'type': u'backup'}]} +{u'return': [{u'status': u'running', u'current-progress': 'FILTERED', u'total-progress': 'FILTERED', u'id': u'job0', u'type': u'backup'}]} {u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'status': u'created', u'id': u'job0'}, u'event': u'JOB_STATUS_CHANGE'} {u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'status': u'running', u'id': u'job0'}, u'event': u'JOB_STATUS_CHANGE'} -- 2.17.1 From: Thomas Huth <thuth@redhat.com> It has been marked as deprecated since QEMU v2.0 already, so it is time now to finally remove it. Signed-off-by: Thomas Huth <thuth@redhat.com> Message-id: 1528288551-31641-1-git-send-email-thuth@redhat.com Reviewed-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- qemu-img.c | 7 +------ qemu-doc.texi | 7 ------- qemu-img-cmds.hx | 4 ++-- qemu-img.texi | 7 ++----- tests/qemu-iotests/029 | 2 +- tests/qemu-iotests/080 | 4 ++-- 6 files changed, 8 insertions(+), 23 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static void QEMU_NORETURN help(void) " 'snapshot_param' is param used for internal snapshot, format\n" " is 'snapshot.id=[ID],snapshot.name=[NAME]', or\n" " '[ID_OR_NAME]'\n" - " 'snapshot_id_or_name' is deprecated, use 'snapshot_param'\n" - " instead\n" " '-c' indicates that target image must be compressed (qcow format only)\n" " '-u' allows unsafe backing chains. For rebasing, it is assumed that old and\n" " new backing file match exactly. The image doesn't need a working\n" @@ -XXX,XX +XXX,XX @@ static int img_convert(int argc, char **argv) {"target-image-opts", no_argument, 0, OPTION_TARGET_IMAGE_OPTS}, {0, 0, 0, 0} }; - c = getopt_long(argc, argv, ":hf:O:B:co:s:l:S:pt:T:qnm:WU", + c = getopt_long(argc, argv, ":hf:O:B:co:l:S:pt:T:qnm:WU", long_options, NULL); if (c == -1) { break; @@ -XXX,XX +XXX,XX @@ static int img_convert(int argc, char **argv) g_free(old_options); } break; - case 's': - snapshot_name = optarg; - break; case 'l': if (strstart(optarg, SNAPSHOT_OPT_BASE, NULL)) { sn_opts = qemu_opts_parse_noisily(&internal_snapshot_opts, diff --git a/qemu-doc.texi b/qemu-doc.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-doc.texi +++ b/qemu-doc.texi @@ -XXX,XX +XXX,XX @@ Option @option{-virtioconsole} has been replaced by The @code{-clock} option is ignored since QEMU version 1.7.0. There is no replacement since it is not needed anymore. -@section qemu-img command line arguments - -@subsection convert -s (since 2.0.0) - -The ``convert -s snapshot_id_or_name'' argument is obsoleted -by the ``convert -l snapshot_param'' argument instead. - @section QEMU Machine Protocol (QMP) commands @subsection block-dirty-bitmap-add "autoload" parameter (since 2.12.0) diff --git a/qemu-img-cmds.hx b/qemu-img-cmds.hx index XXXXXXX..XXXXXXX 100644 --- a/qemu-img-cmds.hx +++ b/qemu-img-cmds.hx @@ -XXX,XX +XXX,XX @@ STEXI ETEXI DEF("convert", img_convert, - "convert [--object objectdef] [--image-opts] [--target-image-opts] [-U] [-c] [-p] [-q] [-n] [-f fmt] [-t cache] [-T src_cache] [-O output_fmt] [-B backing_file] [-o options] [-s snapshot_id_or_name] [-l snapshot_param] [-S sparse_size] [-m num_coroutines] [-W] filename [filename2 [...]] output_filename") + "convert [--object objectdef] [--image-opts] [--target-image-opts] [-U] [-c] [-p] [-q] [-n] [-f fmt] [-t cache] [-T src_cache] [-O output_fmt] [-B backing_file] [-o options] [-l snapshot_param] [-S sparse_size] [-m num_coroutines] [-W] filename [filename2 [...]] output_filename") STEXI -@item convert [--object @var{objectdef}] [--image-opts] [--target-image-opts] [-U] [-c] [-p] [-q] [-n] [-f @var{fmt}] [-t @var{cache}] [-T @var{src_cache}] [-O @var{output_fmt}] [-B @var{backing_file}] [-o @var{options}] [-s @var{snapshot_id_or_name}] [-l @var{snapshot_param}] [-S @var{sparse_size}] [-m @var{num_coroutines}] [-W] @var{filename} [@var{filename2} [...]] @var{output_filename} +@item convert [--object @var{objectdef}] [--image-opts] [--target-image-opts] [-U] [-c] [-p] [-q] [-n] [-f @var{fmt}] [-t @var{cache}] [-T @var{src_cache}] [-O @var{output_fmt}] [-B @var{backing_file}] [-o @var{options}] [-l @var{snapshot_param}] [-S @var{sparse_size}] [-m @var{num_coroutines}] [-W] @var{filename} [@var{filename2} [...]] @var{output_filename} ETEXI DEF("create", img_create, diff --git a/qemu-img.texi b/qemu-img.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.texi +++ b/qemu-img.texi @@ -XXX,XX +XXX,XX @@ by the used format or see the format descriptions below for details. is param used for internal snapshot, format is 'snapshot.id=[ID],snapshot.name=[NAME]' or '[ID_OR_NAME]' -@item snapshot_id_or_name -is deprecated, use snapshot_param instead - @end table @table @option @@ -XXX,XX +XXX,XX @@ Error on reading data @end table -@item convert [--object @var{objectdef}] [--image-opts] [--target-image-opts] [-U] [-c] [-p] [-q] [-n] [-f @var{fmt}] [-t @var{cache}] [-T @var{src_cache}] [-O @var{output_fmt}] [-B @var{backing_file}] [-o @var{options}] [-s @var{snapshot_id_or_name}] [-l @var{snapshot_param}] [-S @var{sparse_size}] [-m @var{num_coroutines}] [-W] @var{filename} [@var{filename2} [...]] @var{output_filename} +@item convert [--object @var{objectdef}] [--image-opts] [--target-image-opts] [-U] [-c] [-p] [-q] [-n] [-f @var{fmt}] [-t @var{cache}] [-T @var{src_cache}] [-O @var{output_fmt}] [-B @var{backing_file}] [-o @var{options}] [-l @var{snapshot_param}] [-S @var{sparse_size}] [-m @var{num_coroutines}] [-W] @var{filename} [@var{filename2} [...]] @var{output_filename} -Convert the disk image @var{filename} or a snapshot @var{snapshot_param}(@var{snapshot_id_or_name} is deprecated) +Convert the disk image @var{filename} or a snapshot @var{snapshot_param} to disk image @var{output_filename} using format @var{output_fmt}. It can be optionally compressed (@code{-c} option) or use any format specific options like encryption (@code{-o} option). diff --git a/tests/qemu-iotests/029 b/tests/qemu-iotests/029 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/029 +++ b/tests/qemu-iotests/029 @@ -XXX,XX +XXX,XX @@ _make_test_img 64M { $QEMU_IMG snapshot -c foo $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir poke_file "$TEST_IMG" "$offset_size" "\x00\x00\x00\x00\x00\x00\x02\x00" poke_file "$TEST_IMG" "$offset_l1_size" "\x00\x00\x00\x01" -{ $QEMU_IMG convert -s foo $TEST_IMG $TEST_IMG.snap; } 2>&1 | _filter_qemu_io | _filter_testdir +{ $QEMU_IMG convert -l foo $TEST_IMG $TEST_IMG.snap; } 2>&1 | _filter_qemu_io | _filter_testdir # success, all done 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 @@ _make_test_img 64M { $QEMU_IO -c "write 0 512" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir { $QEMU_IMG snapshot -c test $TEST_IMG; } 2>&1 | _filter_testdir poke_file "$TEST_IMG" "$offset_snap1_l1_offset" "\x00\x00\x00\x00\x00\x40\x02\x00" -{ $QEMU_IMG convert -s test $TEST_IMG $TEST_IMG.snap; } 2>&1 | _filter_testdir +{ $QEMU_IMG convert -l test $TEST_IMG $TEST_IMG.snap; } 2>&1 | _filter_testdir { $QEMU_IMG amend -o compat=0.10 $TEST_IMG; } 2>&1 | _filter_testdir { $QEMU_IO -c "open -o overlap-check.inactive-l2=on $TEST_IMG" \ -c 'write 0 4k'; } 2>&1 | _filter_qemu_io | _filter_testdir @@ -XXX,XX +XXX,XX @@ _make_test_img 64M { $QEMU_IO -c "write 0 512" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir { $QEMU_IMG snapshot -c test $TEST_IMG; } 2>&1 | _filter_testdir poke_file "$TEST_IMG" "$offset_snap1_l1_size" "\x10\x00\x00\x00" -{ $QEMU_IMG convert -s test $TEST_IMG $TEST_IMG.snap; } 2>&1 | _filter_testdir +{ $QEMU_IMG convert -l test $TEST_IMG $TEST_IMG.snap; } 2>&1 | _filter_testdir { $QEMU_IMG amend -o compat=0.10 $TEST_IMG; } 2>&1 | _filter_testdir { $QEMU_IO -c "open -o overlap-check.inactive-l2=on $TEST_IMG" \ -c 'write 0 4k'; } 2>&1 | _filter_qemu_io | _filter_testdir -- 2.17.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> This assert may fail, because bitmap_table is not initialized. Just drop it, as it's obvious, that bitmap_table_load sets bitmap_table parameter only when returning zero. Reported-by: Pavel Butsykin <pbutsykin@virtuozzo.com> Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-id: 20180608101225.2575-1-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-bitmap.c | 1 - 1 file changed, 1 deletion(-) diff --git a/block/qcow2-bitmap.c b/block/qcow2-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-bitmap.c +++ b/block/qcow2-bitmap.c @@ -XXX,XX +XXX,XX @@ static int free_bitmap_clusters(BlockDriverState *bs, Qcow2BitmapTable *tb) ret = bitmap_table_load(bs, tb, &bitmap_table); if (ret < 0) { - assert(bitmap_table == NULL); return ret; } -- 2.17.1 From: Alberto Garcia <berto@igalia.com> The throttle block filter can be reopened, and with this it is possible to change the throttle group that the filter belongs to. The way the code does that is the following: - On throttle_reopen_prepare(): create a new ThrottleGroupMember and attach it to the new throttle group. - On throttle_reopen_commit(): detach the old ThrottleGroupMember, delete it and replace it with the new one. The problem with this is that by replacing the ThrottleGroupMember the previous value of io_limits_disabled is lost, causing an assertion failure in throttle_co_drain_end(). This problem can be reproduced by reopening a throttle node: $QEMU -monitor stdio -object throttle-group,id=tg0,x-iops-total=1000 \ -blockdev node-name=hd0,driver=qcow2,file.driver=file,file.filename=hd.qcow2 \ -blockdev node-name=root,driver=throttle,throttle-group=tg0,file=hd0,read-only=on (qemu) block_stream root block/throttle.c:214: throttle_co_drain_end: Assertion `tgm->io_limits_disabled' failed. Since we only want to change the throttle group on reopen there's no need to create a ThrottleGroupMember and discard the old one. It's easier if we simply detach it from its current group and attach it to the new one. Signed-off-by: Alberto Garcia <berto@igalia.com> Message-id: 20180608151536.7378-1-berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/throttle.c | 54 +++++++++++++++++++++++++++++------------------- 1 file changed, 33 insertions(+), 21 deletions(-) diff --git a/block/throttle.c b/block/throttle.c index XXXXXXX..XXXXXXX 100644 --- a/block/throttle.c +++ b/block/throttle.c @@ -XXX,XX +XXX,XX @@ static QemuOptsList throttle_opts = { }, }; -static int throttle_configure_tgm(BlockDriverState *bs, - ThrottleGroupMember *tgm, - QDict *options, Error **errp) +/* + * If this function succeeds then the throttle group name is stored in + * @group and must be freed by the caller. + * If there's an error then @group remains unmodified. + */ +static int throttle_parse_options(QDict *options, char **group, Error **errp) { int ret; const char *group_name; @@ -XXX,XX +XXX,XX @@ static int throttle_configure_tgm(BlockDriverState *bs, goto fin; } - /* Register membership to group with name group_name */ - throttle_group_register_tgm(tgm, group_name, bdrv_get_aio_context(bs)); + *group = g_strdup(group_name); ret = 0; fin: qemu_opts_del(opts); @@ -XXX,XX +XXX,XX @@ static int throttle_open(BlockDriverState *bs, QDict *options, int flags, Error **errp) { ThrottleGroupMember *tgm = bs->opaque; + char *group; + int ret; bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, false, errp); @@ -XXX,XX +XXX,XX @@ static int throttle_open(BlockDriverState *bs, QDict *options, bs->supported_zero_flags = bs->file->bs->supported_zero_flags | BDRV_REQ_WRITE_UNCHANGED; - return throttle_configure_tgm(bs, tgm, options, errp); + ret = throttle_parse_options(options, &group, errp); + if (ret == 0) { + /* Register membership to group with name group_name */ + throttle_group_register_tgm(tgm, group, bdrv_get_aio_context(bs)); + g_free(group); + } + + return ret; } static void throttle_close(BlockDriverState *bs) @@ -XXX,XX +XXX,XX @@ static void throttle_attach_aio_context(BlockDriverState *bs, static int throttle_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue, Error **errp) { - ThrottleGroupMember *tgm; + int ret; + char *group = NULL; assert(reopen_state != NULL); assert(reopen_state->bs != NULL); - reopen_state->opaque = g_new0(ThrottleGroupMember, 1); - tgm = reopen_state->opaque; - - return throttle_configure_tgm(reopen_state->bs, tgm, reopen_state->options, - errp); + ret = throttle_parse_options(reopen_state->options, &group, errp); + reopen_state->opaque = group; + return ret; } static void throttle_reopen_commit(BDRVReopenState *reopen_state) { - ThrottleGroupMember *old_tgm = reopen_state->bs->opaque; - ThrottleGroupMember *new_tgm = reopen_state->opaque; + BlockDriverState *bs = reopen_state->bs; + ThrottleGroupMember *tgm = bs->opaque; + char *group = reopen_state->opaque; + + assert(group); - throttle_group_unregister_tgm(old_tgm); - g_free(old_tgm); - reopen_state->bs->opaque = new_tgm; + if (strcmp(group, throttle_group_get_name(tgm))) { + throttle_group_unregister_tgm(tgm); + throttle_group_register_tgm(tgm, group, bdrv_get_aio_context(bs)); + } + g_free(reopen_state->opaque); reopen_state->opaque = NULL; } static void throttle_reopen_abort(BDRVReopenState *reopen_state) { - ThrottleGroupMember *tgm = reopen_state->opaque; - - throttle_group_unregister_tgm(tgm); - g_free(tgm); + g_free(reopen_state->opaque); reopen_state->opaque = NULL; } -- 2.17.1 This is a useful function for the whole block layer, so make it public. At the same time, users outside of block.c probably do not need to make use of the reopen functionality, so rename the current function to bdrv_is_writable_after_reopen() create a new bdrv_is_writable() function that just passes NULL to it for the reopen queue. Cc: qemu-stable@nongnu.org Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20180606193702.7113-2-mreitz@redhat.com Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/block/block.h | 1 + block.c | 17 ++++++++++++++--- 2 files changed, 15 insertions(+), 3 deletions(-) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ bool bdrv_is_read_only(BlockDriverState *bs); int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only, bool ignore_allow_rdw, Error **errp); int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp); +bool bdrv_is_writable(BlockDriverState *bs); bool bdrv_is_sg(BlockDriverState *bs); bool bdrv_is_inserted(BlockDriverState *bs); void bdrv_lock_medium(BlockDriverState *bs, bool locked); diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static int bdrv_reopen_get_flags(BlockReopenQueue *q, BlockDriverState *bs) /* Returns whether the image file can be written to after the reopen queue @q * has been successfully applied, or right now if @q is NULL. */ -static bool bdrv_is_writable(BlockDriverState *bs, BlockReopenQueue *q) +static bool bdrv_is_writable_after_reopen(BlockDriverState *bs, + BlockReopenQueue *q) { int flags = bdrv_reopen_get_flags(q, bs); return (flags & (BDRV_O_RDWR | BDRV_O_INACTIVE)) == BDRV_O_RDWR; } +/* + * Return whether the BDS can be written to. This is not necessarily + * the same as !bdrv_is_read_only(bs), as inactivated images may not + * be written to but do not count as read-only images. + */ +bool bdrv_is_writable(BlockDriverState *bs) +{ + return bdrv_is_writable_after_reopen(bs, NULL); +} + static void bdrv_child_perm(BlockDriverState *bs, BlockDriverState *child_bs, BdrvChild *c, const BdrvChildRole *role, BlockReopenQueue *reopen_queue, @@ -XXX,XX +XXX,XX @@ static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q, /* Write permissions never work with read-only images */ if ((cumulative_perms & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED)) && - !bdrv_is_writable(bs, q)) + !bdrv_is_writable_after_reopen(bs, q)) { error_setg(errp, "Block node is read-only"); return -EPERM; @@ -XXX,XX +XXX,XX @@ void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c, &perm, &shared); /* Format drivers may touch metadata even if the guest doesn't write */ - if (bdrv_is_writable(bs, reopen_queue)) { + if (bdrv_is_writable_after_reopen(bs, reopen_queue)) { perm |= BLK_PERM_WRITE | BLK_PERM_RESIZE; } -- 2.17.1 When signaling a corruption on a read-only image, qcow2 already makes fatal events non-fatal (i.e., they will not result in the image being closed, and the image header's corrupt flag will not be set). This is necessary because we cannot set the corrupt flag on read-only images, and it is possible because further corruption of read-only images is impossible. Inactive images are effectively read-only, too, so we should do the same for them. bdrv_is_writable() can tell us whether an image can actually be written to, so use its result instead of !bs->read_only. (Otherwise, the assert(!(bs->open_flags & BDRV_O_INACTIVE)) in bdrv_co_pwritev() will fail, crashing qemu.) Cc: qemu-stable@nongnu.org Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20180606193702.7113-3-mreitz@redhat.com Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 @@ void qcow2_signal_corruption(BlockDriverState *bs, bool fatal, int64_t offset, char *message; va_list ap; - fatal = fatal && !bs->read_only; + fatal = fatal && bdrv_is_writable(bs); if (s->signaled_corruption && (!fatal || (s->incompatible_features & QCOW2_INCOMPAT_CORRUPT))) -- 2.17.1 Reviewed-by: John Snow <jsnow@redhat.com> Tested-by: Jeff Cody <jcody@redhat.com> Reviewed-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20180606193702.7113-4-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/060 | 30 ++++++++++++++++++++++++++++++ tests/qemu-iotests/060.out | 14 ++++++++++++++ 2 files changed, 44 insertions(+) diff --git a/tests/qemu-iotests/060 b/tests/qemu-iotests/060 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/060 +++ b/tests/qemu-iotests/060 @@ -XXX,XX +XXX,XX @@ echo "{'execute': 'qmp_capabilities'} -drive if=none,node-name=drive,file="$TEST_IMG",driver=qcow2 \ | _filter_qmp | _filter_qemu_io +echo +echo "=== Testing incoming inactive corrupted image ===" +echo + +_make_test_img 64M +# Create an unaligned L1 entry, so qemu will signal a corruption when +# reading from the covered area +poke_file "$TEST_IMG" "$l1_offset" "\x00\x00\x00\x00\x2a\x2a\x2a\x2a" + +# Inactive images are effectively read-only images, so this should be a +# non-fatal corruption (which does not modify the image) +echo "{'execute': 'qmp_capabilities'} + {'execute': 'human-monitor-command', + 'arguments': {'command-line': 'qemu-io drive \"read 0 512\"'}} + {'execute': 'quit'}" \ + | $QEMU -qmp stdio -nographic -nodefaults \ + -blockdev "{'node-name': 'drive', + 'driver': 'qcow2', + 'file': { + 'driver': 'file', + 'filename': '$TEST_IMG' + }}" \ + -incoming exec:'cat /dev/null' \ + 2>&1 \ + | _filter_qmp | _filter_qemu_io + +echo +# Image should not have been marked corrupt +_img_info --format-specific | grep 'corrupt:' + # success, all done echo "*** done" rm -f $seq.full 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 @@ write failed: Input/output error {"return": ""} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} + +=== Testing incoming inactive corrupted image === + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 +QMP_VERSION +{"return": {}} +qcow2: Image is corrupt: L2 table offset 0x2a2a2a00 unaligned (L1 index: 0); further non-fatal corruption events will be suppressed +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_IMAGE_CORRUPTED", "data": {"device": "", "msg": "L2 table offset 0x2a2a2a00 unaligned (L1 index: 0)", "node-name": "drive", "fatal": false}} +read failed: Input/output error +{"return": ""} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} + + corrupt: false *** done -- 2.17.1 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