Add a class that will unify block parents for blockdev-replace functionality we are going to add. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov(a)virtuozzo.com&gt; --- include/block/block-parent.h | 32 +++++++++++++++++ block/block-parent.c | 66 ++++++++++++++++++++++++++++++++++++ block/meson.build | 1 + 3 files changed, 99 insertions(+) create mode 100644 include/block/block-parent.h create mode 100644 block/block-parent.c diff --git a/include/block/block-parent.h b/include/block/block-parent.h new file mode 100644 index 0000000000..bd9c9d91e6 --- /dev/null +++ b/include/block/block-parent.h @@ -0,0 +1,32 @@ +/* + * Block Parent class + * + * Copyright (c) 2021 Virtuozzo International GmbH. + * + * Authors: + * Vladimir Sementsov-Ogievskiy <vsementsov(a)virtuozzo.com&gt; + * + * 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 BLOCK_PARENT_H +#define BLOCK_PARENT_H + +#include "block/block.h" + +typedef struct BlockParentClass { + const char *name; + + int (*find_child)(const char *parent_id, const char *child_name, + BlockDriverState *child_bs, BdrvChild **child, + Error **errp); + QTAILQ_ENTRY(BlockParentClass) next; +} BlockParentClass; + +void block_parent_class_register(BlockParentClass *cls); + +BdrvChild *block_find_child(const char *parent_id, const char *child_name, + BlockDriverState *child_bs, Error **errp); + +#endif /* BLOCK_PARENT_H */ diff --git a/block/block-parent.c b/block/block-parent.c new file mode 100644 index 0000000000..73b6026c42 --- /dev/null +++ b/block/block-parent.c @@ -0,0 +1,66 @@ +/* + * Block Parent class + * + * Copyright (c) 2021 Virtuozzo International GmbH. + * + * Authors: + * Vladimir Sementsov-Ogievskiy <vsementsov(a)virtuozzo.com&gt; + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "block/block-parent.h" +#include "qapi/error.h" + +static QTAILQ_HEAD(, BlockParentClass) block_parent_classes = + QTAILQ_HEAD_INITIALIZER(block_parent_classes); + +void block_parent_class_register(BlockParentClass *cls) +{ + QTAILQ_INSERT_HEAD(&block_parent_classes, cls, next); +} + +BdrvChild *block_find_child(const char *parent_id, const char *child_name, + BlockDriverState *child_bs, Error **errp) +{ + BdrvChild *found_child = NULL; + BlockParentClass *found_cls = NULL, *cls; + + QTAILQ_FOREACH(cls, &block_parent_classes, next) { + int ret; + BdrvChild *c; + + /* + * Note that .find_child must fail if parent is found but doesn't have + * corresponding child. + */ + ret = cls->find_child(parent_id, child_name, child_bs, &c, errp); + if (ret < 0) { + return NULL; + } + if (ret == 0) { + continue; + } + + if (!found_child) { + found_cls = cls; + found_child = c; + continue; + } + + error_setg(errp, "{%s, %s} parent-child pair is ambiguous: it match " + "both %s and %s", parent_id, child_name, found_cls->name, + cls->name); + return NULL; + } + + if (!found_child) { + error_setg(errp, "{%s, %s} parent-child pair not found", parent_id, + child_name); + return NULL; + } + + return found_child; +} diff --git a/block/meson.build b/block/meson.build index 0450914c7a..5200e0ffce 100644 --- a/block/meson.build +++ b/block/meson.build @@ -10,6 +10,7 @@ block_ss.add(files( 'blkverify.c', 'block-backend.c', 'block-copy.c', + 'block-parent.c', 'commit.c', 'copy-on-read.c', 'preallocate.c', -- 2.29.2

16.09.2021 11:34, Markus Armbruster wrote: will add Hmm. Callback returns int. And this block_find_child() function return NULL only together with errp set. -- Best regards, Vladimir

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov(a)virtuozzo.com&gt; --- block.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) diff --git a/block.c b/block.c index e97ce0b1c8..449f933661 100644 --- a/block.c +++ b/block.c @@ -26,6 +26,7 @@ #include "qemu/osdep.h" #include "block/trace.h" #include "block/block_int.h" +#include "block/block-parent.h" #include "block/blockjob.h" #include "block/fuse.h" #include "block/nbd.h" @@ -7501,6 +7502,47 @@ int bdrv_make_empty(BdrvChild *c, Error **errp) return 0; } +static int bdrv_find_child(const char *parent_id, const char *child_name, + BlockDriverState *child_bs, BdrvChild **child, + Error **errp) +{ + BdrvChild *c, *found = NULL; + BlockDriverState *bs; + + bs = bdrv_find_node(parent_id); + if (!bs) { + return 0; + } + + QLIST_FOREACH(c, &bs->children, next) { + if ((!child_name || strcmp(c->name, child_name) == 0) && + (!child_bs || child_bs == c->bs)) + { + if (found) { + error_setg(errp, "node '%s' has more than one matching child", + parent_id); + return -EINVAL; + } else { + found = c; + } + } + } + + if (!found) { + error_setg(errp, "node '%s' exists but it doesn't have matching child", + parent_id); + return -EINVAL; + } + + *child = found; + return 1; +} + +BlockParentClass block_parent_bdrv = { + .name = "block driver", + .find_child = bdrv_find_child, +}; + /* * Return the child that @bs acts as an overlay for, and from which data may be * copied in COW or COR operations. Usually this is the backing file. @@ -7653,3 +7695,10 @@ BlockDriverState *bdrv_backing_chain_next(BlockDriverState *bs) { return bdrv_skip_filters(bdrv_cow_bs(bdrv_skip_filters(bs))); } + +static void block_c_init(void) +{ + block_parent_class_register(&block_parent_bdrv); +} + +block_init(block_c_init); -- 2.29.2

We'll need this for realizing qdev_find_child() in the next commit. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov(a)virtuozzo.com&gt; --- softmmu/qdev-monitor.c | 48 +++++++++++++++++++++++++++++------------- 1 file changed, 33 insertions(+), 15 deletions(-) diff --git a/softmmu/qdev-monitor.c b/softmmu/qdev-monitor.c index 721dec2d82..0117989009 100644 --- a/softmmu/qdev-monitor.c +++ b/softmmu/qdev-monitor.c @@ -819,7 +819,12 @@ void qmp_device_add(QDict *qdict, QObject **ret_data, Error **errp) object_unref(OBJECT(dev)); } -static DeviceState *find_device_state(const char *id, Error **errp) +/* + * Returns: 1 when found, @dev set + * 0 not found, @dev and @errp untouched + * <0 error, or id is ambiguous, @errp set + */ +static int find_device_state(const char *id, DeviceState **dev, Error **errp) { Object *obj; @@ -835,17 +840,16 @@ static DeviceState *find_device_state(const char *id, Error **errp) } if (!obj) { - error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND, - "Device '%s' not found", id); - return NULL; + return 0; } if (!object_dynamic_cast(obj, TYPE_DEVICE)) { error_setg(errp, "%s is not a hotpluggable device", id); - return NULL; + return -EINVAL; } - return DEVICE(obj); + *dev = DEVICE(obj); + return 1; } void qdev_unplug(DeviceState *dev, Error **errp) @@ -894,16 +898,25 @@ void qdev_unplug(DeviceState *dev, Error **errp) void qmp_device_del(const char *id, Error **errp) { - DeviceState *dev = find_device_state(id, errp); - if (dev != NULL) { - if (dev->pending_deleted_event) { - error_setg(errp, "Device %s is already in the " - "process of unplug", id); - return; + int ret; + DeviceState *dev; + + ret = find_device_state(id, &dev, errp); + if (ret <= 0) { + if (ret == 0) { + error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND, + "Device '%s' not found", id); } + return; + } - qdev_unplug(dev, errp); + if (dev->pending_deleted_event) { + error_setg(errp, "Device %s is already in the " + "process of unplug", id); + return; } + + qdev_unplug(dev, errp); } void hmp_device_add(Monitor *mon, const QDict *qdict) @@ -925,11 +938,16 @@ void hmp_device_del(Monitor *mon, const QDict *qdict) BlockBackend *blk_by_qdev_id(const char *id, Error **errp) { + int ret; DeviceState *dev; BlockBackend *blk; - dev = find_device_state(id, errp); - if (dev == NULL) { + ret = find_device_state(id, &dev, errp); + if (ret <= 0) { + if (ret == 0) { + error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND, + "Device '%s' not found", id); + } return NULL; } -- 2.29.2

16.09.2021 13:48, Markus Armbruster wrote: Looks simpler) Thanks for working that out, I'll go this way in v2 -- Best regards, Vladimir

Vladimir Sementsov-Ogievskiy <vsementsov(a)virtuozzo.com&gt; writes: What is a "root child", and why would a user care? The contract missing in PATCH 2 leaves me floundering.

Add command that can add and remove filters. Key points of functionality: What the command does is simply replace some BdrvChild.bs by some other nodes. The tricky thing is selecting there BdrvChild objects. To be able to select any kind of BdrvChild we use a generic parent_id, which may be a node-name, or qdev id or block export id. In future we may support block jobs. Any kind of ambiguity leads to error. If we have both device named device0 and block export named device0 and they both point to same BDS, user can't replace root child of one of these parents. So, to be able to do replacements, user should avoid duplicating names in different parent namespaces. So, command allows to replace any single child in the graph. On the other hand we want to realize a kind of bdrv_replace_node(), which works well when we want to replace all parents of some node. For this kind of task @parents-mode argument implemented. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov(a)virtuozzo.com&gt; --- qapi/block-core.json | 78 +++++++++++++++++++++++++++++++++++++++++ block.c | 82 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 160 insertions(+) diff --git a/qapi/block-core.json b/qapi/block-core.json index 675d8265eb..8059b96341 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -5433,3 +5433,81 @@ { 'command': 'blockdev-snapshot-delete-internal-sync', 'data': { 'device': 'str', '*id': 'str', '*name': 'str'}, 'returns': 'SnapshotInfo' } + +## +# @BlockdevReplaceParentsMode: +# +# Alternative (to directly set @parent) way to chose parents in +# @blockdev-replace +# +# @exactly-one: Exactly one parent should match a condition, otherwise +# @blockdev-replace fails. +# +# @all: All matching parents are taken into account. If replacing lead +# to loops in block graph, @blockdev-replace fails. +# +# @auto: Same as @all, but automatically skip replacing parents if it +# leads to loops in block graph. +# +# Since: 6.2 +## +{ 'enum': 'BlockdevReplaceParentsMode', + 'data': ['exactly-one', 'all', 'auto'] } + +## +# @BlockdevReplace: +# +# Declaration of one replacement. +# +# @parent: id of parent. It may be qdev or block export or simple +# node-name. If id is ambiguous (for example node-name of +# some BDS equals to block export name), blockdev-replace +# fails. If not specified, blockdev-replace goes through +# @parents-mode scenario, see below. Note, that @parent and +# @parents-mode can't be specified simultaneously. +# If @parent is specified, only one edge is selected. If +# several edges match the condition, blockdev-replace fails. +# +# @edge: name of the child. If omitted, any child name matches. +# +# @child: node-name of the child. If omitted, any child matches. +# Must be present if @parent is not specified. +# +# @parents-mode: declares how to select edge (or edges) when @parent +# is omitted. Default is 'one'. +# +# Since: 6.2 +# +# Examples: +# +# 1. Change root node of some device. +# +# Note, that @edge name is omitted, as +# devices always has only one child. As well, no need in specifying +# old @child. +# +# -> { "parent": "device0", "new-child": "some-node-name" } +# +# 2. Insert copy-before-write filter. +# +# Assume, after blockdev-add we have block-node 'source', with several +# writing parents and one copy-before-write 'filter' parent. And we want +# to actually insert the filter. We do: +# +# -> { "child": "source", "parent-mode": "auto", "new-child": "filter" } +# +# All parents of source would be switched to 'filter' node, except for +# 'filter' node itself (otherwise, it will make a loop in block-graph). +## +{ 'struct': 'BlockdevReplace', + 'data': { '*parent': 'str', '*edge': 'str', '*child': 'str', + '*parents-mode': 'BlockdevReplaceParentsMode', + 'new-child': 'str' } } + +## +# @blockdev-replace: +# +# Do one or several replacements transactionally. +## +{ 'command': 'blockdev-replace', + 'data': { 'replacements': ['BlockdevReplace'] } } diff --git a/block.c b/block.c index ae8c8c4032..3bcb3152f1 100644 --- a/block.c +++ b/block.c @@ -41,6 +41,7 @@ #include "qapi/qmp/qnull.h" #include "qapi/qmp/qstring.h" #include "qapi/qobject-output-visitor.h" +#include "qapi/qapi-commands-block.h" #include "qapi/qapi-visit-block-core.h" #include "sysemu/block-backend.h" #include "qemu/notify.h" @@ -7717,6 +7718,87 @@ BlockDriverState *bdrv_backing_chain_next(BlockDriverState *bs) return bdrv_skip_filters(bdrv_cow_bs(bdrv_skip_filters(bs))); } +void qmp_blockdev_replace(BlockdevReplaceList *list, Error **errp) +{ + int ret; + Transaction *tran = tran_new(); + g_autoptr(GHashTable) found = NULL; + g_autoptr(GSList) refresh_list = NULL; + g_autoptr(GSList) touched_list = NULL; + GSList *x; + + for ( ; list; list = list->next) { + BlockdevReplace *repl = list->value; + BlockDriverState *child_bs = NULL, *new_child_bs; + BlockdevReplaceParentsMode mode; + BdrvChild *child; + + if (repl->has_child) { + child_bs = bdrv_find_node(repl->child); + if (!child_bs) { + error_setg(errp, "Node '%s' not found", repl->child); + goto fail; + } + } + + new_child_bs = bdrv_find_node(repl->new_child); + if (!new_child_bs) { + error_setg(errp, "Node '%s' not found", repl->new_child); + goto fail; + } + + if (repl->has_parent) { + if (repl->has_parents_mode) { + error_setg(errp, "parent and parents-mode field must " + "not be set simultaneously."); + goto fail; + } + + child = block_find_child(repl->parent, repl->edge, child_bs, errp); + if (!child) { + goto fail; + } + + touched_list = g_slist_prepend(touched_list, child->bs); + touched_list = g_slist_prepend(touched_list, new_child_bs); + bdrv_replace_child_tran(child, new_child_bs, tran); + continue; + } + + if (!repl->has_child) { + error_setg(errp, "At least one of parent and child fields " + "should be specified."); + goto fail; + } + + mode = repl->has_parents_mode ? repl->parents_mode : + BLOCKDEV_REPLACE_PARENTS_MODE_EXACTLY_ONE; + + touched_list = g_slist_prepend(touched_list, child_bs); + touched_list = g_slist_prepend(touched_list, new_child_bs); + ret = bdrv_replace_node_noperm(child_bs, new_child_bs, + mode == BLOCKDEV_REPLACE_PARENTS_MODE_AUTO, + repl->edge, + mode == BLOCKDEV_REPLACE_PARENTS_MODE_EXACTLY_ONE, + tran, errp); + if (ret < 0) { + goto fail; + } + } + + for (x = touched_list; x; x = x->next) { + refresh_list = bdrv_topological_dfs(refresh_list, found, x->data); + } + + ret = bdrv_list_refresh_perms(refresh_list, NULL, tran, errp); + + tran_finalize(tran, ret); + return; + +fail: + tran_abort(tran); +} + static void block_c_init(void) { block_parent_class_register(&block_parent_bdrv); -- 2.29.2

Thanks a lot for reviewing! 20.09.2021 09:44, Markus Armbruster wrote: A specific child node in one or in several edges OK Yes. Alternatively we can also add an enum of node-type [bds, device, export[, job]], and select graph nodes more explicit (by pair of id/path/name and type) But if we have to use these things in one context, it seems good to enforce users use different names for them. And in this way, we can avoid strict typing. In my idea, it's simply impossible. If someone want to use this new interface, he should care to use different names for different things. You may specify @child and @parent, to replace child in specific edge. Or @parent and @edge. Or all three fields: just to be strict. Although we have to deal with different kinds of nodes (BDS, exports, blks, ...), children are always BDS. But, may be in the context, it's better say "id of the child". OK. Now, after some time passed, I see that some additional clarifications are needed. Even for me :) So, the actual modes I have in mind: 1. Replacement for backup: we want to inject copy-before-write filter F above some node X, so that all parents of node X start to access X through filter F. But we want automatically skip parents if modifications leads to loops in the graph (so, we can first carete node F with X as a child, than do replacement, and don't replace child of F by F :). That's parents-mode=auto & parent=None & edge=None & child=X 2. Replacement of any specific edge in the graph. Edge may be specified in different ways: by parent, by child, by edge, and by some combinations of these things. It seems reasonable to allow any combination, if it specifies exactly one field.. Assume we have A -- backing --> B relation in the graph, and want to replace B by filter F in that relation. 2.1 Specify parent: We may specify all information bits, to be sure that we do what we want and for high probability to fail if we have wrong impression about what's going on in the graph: parents-mode=None & parent=A & edge=backing & child=B We can omit edge: parents-mode=None & parent=A & edge=None & child=B - that should fail as ambiguous if B is "double child" of A, with two edges from A to B. But I think, that's unused combination for now) Or we can omit child parents-mode=None & parent=A & edge=backing & child=None - that should work well, as node shouldn't have more than one backing child. and we can omit both edge and child: parents-mode=None & parent=A & edge=None & child=None - that will work only if A has exactly one child and fails otherwise. So, that's bad for format nodes but good for filters and for block devices. 2.2 Don't specify parent but specify child: parents-mode=exactly-one & parent=None & edge=backing & child=B - works if B has only one parent with B as backing child parents-mode=exactly-one & parent=None & edge=None & child=B - works if B has only one parent ====================== Now, what's more? parents-mode=auto & parent=None & edge=root & child=X - replace only child only for root parents of X - may make sense And all other combinations are parents-mode=ANY & parent=None & edge=ANY & child=None - don't specify neither parent nor child. That works bad with any mode.. Theoretically, we still can support it by looking through the whole graph. If edge=backing and we only only one backing edge in the whole graph we can serve the request.. But we can simply fail and not care. ===================== What's bad, is that 2.1 and 2.2 are not symmetrical. So, right, it seems better to turn it into union: 1. mode = auto Replace child in all it's parents where edge match to @edge and avoiding creating loops in the graph child: required, specify child edge: optional, if specified, do replacement only in such edges 2. mode = one-edge Replace child in exactly one edge. If more than one edge matches - re[ace nothing and fail. parent: optional edge: optional child: optional - all fields optional, but user is responsible to not be ambiguous. Still, we can enforce that at least one of @parent and @child should be specified. Recently we allowed do several reopens in one blockdev-reopen. So, it's reasonable to behave same way in blockdev-replace. Still, I think combination of different commands in a transaction make sense too. So, in my thought, transaction support for blockdev-* graph modification commands is a TODO. -- Best regards, Vladimir

23.09.2021 13:09, Markus Armbruster wrote: Hmm, I didn't see neither of it. I'm not sure.. Of course node can't have several backing children.. Quorum cares to name children differently. But for example, block-stream job may have several children named simply "intermediate node". But block-jobs children is so internal feature, that I'm not sure we can allow user simply replace them. That's why this series doesn't allow select jobs as parents. Still, I have never seen such a use case) I don't know) That just what come into my mind. It's simple enough to restrict the flexibility for now and add it in future if needed. The reason was that to remove filter, we should do two replacements in one transaction, otherwise filter may conflict with original parent after replacement.. But finally, I had to add "if (!QLIST_EMPTY(&bs->parents))" hack to cbw_child_perm() of copy-before-write filter, so it should be possible to remove the filter in two steps: 1. replace child in original parent 2. remove the filter. (and filter will not conflict, thanks to the hack). And that time we thought blockdev-reopen is good for manipulation with filters. Now it's obvious that it is not. Oh, that's all makes more questions than answers :) 1. It's OK to use one BlockdevReplace instead of a list and concentrate on transaction support. That's a mission I keep in mind: moving qapi transactions to use util/transactions.c engine for native integration with modern block modifications. 2. It's OK to limit "one-edge" flexibility, anyway, I don't know do we need it or not. Still, are use sure that for user it will be simpler to replace root node by qdev path then by node-name? Both variants allow to determine the edge in the graph : qdiv --root--> node-name. But node-name may be preferable in graph operations. Hmm, on the other hand, if user rely on possibility to specify edge by child, he'll make implementation which will fail to support several qdev parents for one driver node. So, maybe you are right, better not allow it. 3. I'm not sure that we can avoid "auto" mode. It makes inserting copy-before-write filter rather simple. If we force user to specify all parents by hand, it may complicate implementation in libvirt. Note also that we don't have a good way to query all parents of the node.. 4. And I'm not sure about id namespaces merging, how much is it bad. Now I tend to agree that it seems unsafe. Do we want force users use different names globally, or instead use pairs (type, id) to identify them? Like ("qdev", "<qdev_id>"), ("export", "<export-name>"), ("driver", "node-name").. Peter, Kevin, what do you think about this all? -- Best regards, Vladimir