Merge remote-tracking branch 'remotes/kevin/tags/for-upstream' into staging

Block layer patches

# gpg: Signature made Tue 28 Feb 2017 20:35:32 GMT
# gpg:                using RSA key 0x7F09B272C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74  56FE 7F09 B272 C88F 2FD6

* remotes/kevin/tags/for-upstream: (46 commits)
  block: Add Error parameter to bdrv_append()
  block: Add Error parameter to bdrv_set_backing_hd()
  block: Assertions for resize permission
  block: Assertions for write permissions
  block: Pass BdrvChild to bdrv_aligned_preadv/pwritev and copy-on-read
  tests: Remove FIXME comments
  nbd/server: Use real permissions for NBD exports
  migration/block: Use real permissions
  hmp: Request permissions in qemu-io
  commit: Add filter-node-name to block-commit
  mirror: Add filter-node-name to blockdev-mirror
  stream: Use real permissions in streaming block job
  mirror: Use real permissions in mirror/active commit block job
  blockjob: Factor out block_job_remove_all_bdrv()
  block: Allow backing file links in change_parent_backing_link()
  block: BdrvChildRole.attach/detach() callbacks
  block: Fix pending requests check in bdrv_append()
  backup: Use real permissions in backup block job
  commit: Use real permissions for HMP 'commit'
  commit: Use real permissions in commit block job
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

7 files changed, 192 insertions, 16 deletions

diff --git a/include/block/block.h b/include/block/block.h
index bde5ebda18..c7c4a3ac3a 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -82,6 +82,7 @@ typedef struct HDGeometry {
 } HDGeometry;
 
 #define BDRV_O_RDWR        0x0002
+#define BDRV_O_RESIZE      0x0004 /* request permission for resizing the node */
 #define BDRV_O_SNAPSHOT    0x0008 /* open the file read only and save writes in a snapshot */
 #define BDRV_O_TEMPORARY   0x0010 /* delete the file after use */
 #define BDRV_O_NOCACHE     0x0020 /* do not use the host page cache */
@@ -187,6 +188,42 @@ typedef enum BlockOpType {
     BLOCK_OP_TYPE_MAX,
 } BlockOpType;
 
+/* Block node permission constants */
+enum {
+    /**
+     * A user that has the "permission" of consistent reads is guaranteed that
+     * their view of the contents of the block device is complete and
+     * self-consistent, representing the contents of a disk at a specific
+     * point.
+     *
+     * For most block devices (including their backing files) this is true, but
+     * the property cannot be maintained in a few situations like for
+     * intermediate nodes of a commit block job.
+     */
+    BLK_PERM_CONSISTENT_READ    = 0x01,
+
+    /** This permission is required to change the visible disk contents. */
+    BLK_PERM_WRITE              = 0x02,
+
+    /**
+     * This permission (which is weaker than BLK_PERM_WRITE) is both enough and
+     * required for writes to the block node when the caller promises that
+     * the visible disk content doesn't change.
+     */
+    BLK_PERM_WRITE_UNCHANGED    = 0x04,
+
+    /** This permission is required to change the size of a block node. */
+    BLK_PERM_RESIZE             = 0x08,
+
+    /**
+     * This permission is required to change the node that this BdrvChild
+     * points to.
+     */
+    BLK_PERM_GRAPH_MOD          = 0x10,
+
+    BLK_PERM_ALL                = 0x1f,
+};
+
 /* disk I/O throttling */
 void bdrv_init(void);
 void bdrv_init_with_whitelist(void);
@@ -199,7 +236,8 @@ int bdrv_create(BlockDriver *drv, const char* filename,
                 QemuOpts *opts, Error **errp);
 int bdrv_create_file(const char *filename, QemuOpts *opts, Error **errp);
 BlockDriverState *bdrv_new(void);
-void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top);
+void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
+                 Error **errp);
 void bdrv_replace_in_backing_chain(BlockDriverState *old,
                                    BlockDriverState *new);
 
@@ -210,7 +248,8 @@ BdrvChild *bdrv_open_child(const char *filename,
                            BlockDriverState* parent,
                            const BdrvChildRole *child_role,
                            bool allow_none, Error **errp);
-void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd);
+void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
+                         Error **errp);
 int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
                            const char *bdref_key, Error **errp);
 BlockDriverState *bdrv_open(const char *filename, const char *reference,
@@ -484,7 +523,8 @@ void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child);
 BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs,
                              BlockDriverState *child_bs,
                              const char *child_name,
-                             const BdrvChildRole *child_role);
+                             const BdrvChildRole *child_role,
+                             Error **errp);
 
 bool bdrv_op_is_blocked(BlockDriverState *bs, BlockOpType op, Error **errp);
 void bdrv_op_block(BlockDriverState *bs, BlockOpType op, Error *reason);
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 1670941da9..a57c0bfb55 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -320,6 +320,59 @@ struct BlockDriver {
     void (*bdrv_del_child)(BlockDriverState *parent, BdrvChild *child,
                            Error **errp);
 
+    /**
+     * Informs the block driver that a permission change is intended. The
+     * driver checks whether the change is permissible and may take other
+     * preparations for the change (e.g. get file system locks). This operation
+     * is always followed either by a call to either .bdrv_set_perm or
+     * .bdrv_abort_perm_update.
+     *
+     * Checks whether the requested set of cumulative permissions in @perm
+     * can be granted for accessing @bs and whether no other users are using
+     * permissions other than those given in @shared (both arguments take
+     * BLK_PERM_* bitmasks).
+     *
+     * If both conditions are met, 0 is returned. Otherwise, -errno is returned
+     * and errp is set to an error describing the conflict.
+     */
+    int (*bdrv_check_perm)(BlockDriverState *bs, uint64_t perm,
+                           uint64_t shared, Error **errp);
+
+    /**
+     * Called to inform the driver that the set of cumulative set of used
+     * permissions for @bs has changed to @perm, and the set of sharable
+     * permission to @shared. The driver can use this to propagate changes to
+     * its children (i.e. request permissions only if a parent actually needs
+     * them).
+     *
+     * This function is only invoked after bdrv_check_perm(), so block drivers
+     * may rely on preparations made in their .bdrv_check_perm implementation.
+     */
+    void (*bdrv_set_perm)(BlockDriverState *bs, uint64_t perm, uint64_t shared);
+
+    /*
+     * Called to inform the driver that after a previous bdrv_check_perm()
+     * call, the permission update is not performed and any preparations made
+     * for it (e.g. taken file locks) need to be undone.
+     *
+     * This function can be called even for nodes that never saw a
+     * bdrv_check_perm() call. It is a no-op then.
+     */
+    void (*bdrv_abort_perm_update)(BlockDriverState *bs);
+
+    /**
+     * Returns in @nperm and @nshared the permissions that the driver for @bs
+     * needs on its child @c, based on the cumulative permissions requested by
+     * the parents in @parent_perm and @parent_shared.
+     *
+     * If @c is NULL, return the permissions for attaching a new child for the
+     * given @role.
+     */
+     void (*bdrv_child_perm)(BlockDriverState *bs, BdrvChild *c,
+                             const BdrvChildRole *role,
+                             uint64_t parent_perm, uint64_t parent_shared,
+                             uint64_t *nperm, uint64_t *nshared);
+
     QLIST_ENTRY(BlockDriver) list;
 };
 
@@ -388,6 +441,10 @@ typedef struct BdrvAioNotifier {
 } BdrvAioNotifier;
 
 struct BdrvChildRole {
+    /* If true, bdrv_replace_in_backing_chain() doesn't change the node this
+     * BdrvChild points to. */
+    bool stay_at_node;
+
     void (*inherit_options)(int *child_flags, QDict *child_options,
                             int parent_flags, QDict *parent_options);
 
@@ -399,6 +456,12 @@ struct BdrvChildRole {
      * name), or NULL if the parent can't provide a better name. */
     const char* (*get_name)(BdrvChild *child);
 
+    /* Returns a malloced string that describes the parent of the child for a
+     * human reader. This could be a node-name, BlockBackend name, qdev ID or
+     * QOM path of the device owning the BlockBackend, job type and ID etc. The
+     * caller is responsible for freeing the memory. */
+    char* (*get_parent_desc)(BdrvChild *child);
+
     /*
      * If this pair of functions is implemented, the parent doesn't issue new
      * requests after returning from .drained_begin() until .drained_end() is
@@ -409,16 +472,32 @@ struct BdrvChildRole {
      */
     void (*drained_begin)(BdrvChild *child);
     void (*drained_end)(BdrvChild *child);
+
+    void (*attach)(BdrvChild *child);
+    void (*detach)(BdrvChild *child);
 };
 
 extern const BdrvChildRole child_file;
 extern const BdrvChildRole child_format;
+extern const BdrvChildRole child_backing;
 
 struct BdrvChild {
     BlockDriverState *bs;
     char *name;
     const BdrvChildRole *role;
     void *opaque;
+
+    /**
+     * Granted permissions for operating on this BdrvChild (BLK_PERM_* bitmask)
+     */
+    uint64_t perm;
+
+    /**
+     * Permissions that can still be granted to other users of @bs while this
+     * BdrvChild is still attached to it. (BLK_PERM_* bitmask)
+     */
+    uint64_t shared_perm;
+
     QLIST_ENTRY(BdrvChild) next;
     QLIST_ENTRY(BdrvChild) next_parent;
 };
@@ -701,13 +780,16 @@ void stream_start(const char *job_id, BlockDriverState *bs,
  * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
  * @on_error: The action to take upon error.
  * @backing_file_str: String to use as the backing file in @top's overlay
+ * @filter_node_name: The node name that should be assigned to the filter
+ * driver that the commit job inserts into the graph above @top. NULL means
+ * that a node name should be autogenerated.
  * @errp: Error object.
  *
  */
 void commit_start(const char *job_id, BlockDriverState *bs,
                   BlockDriverState *base, BlockDriverState *top, int64_t speed,
                   BlockdevOnError on_error, const char *backing_file_str,
-                  Error **errp);
+                  const char *filter_node_name, Error **errp);
 /**
  * commit_active_start:
  * @job_id: The id of the newly-created job, or %NULL to use the
@@ -718,6 +800,9 @@ void commit_start(const char *job_id, BlockDriverState *bs,
  *                  See @BlockJobCreateFlags
  * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
  * @on_error: The action to take upon error.
+ * @filter_node_name: The node name that should be assigned to the filter
+ * driver that the commit job inserts into the graph above @bs. NULL means that
+ * a node name should be autogenerated.
  * @cb: Completion function for the job.
  * @opaque: Opaque pointer value passed to @cb.
  * @errp: Error object.
@@ -727,8 +812,9 @@ void commit_start(const char *job_id, BlockDriverState *bs,
 void commit_active_start(const char *job_id, BlockDriverState *bs,
                          BlockDriverState *base, int creation_flags,
                          int64_t speed, BlockdevOnError on_error,
-                         BlockCompletionFunc *cb,
-                         void *opaque, Error **errp, bool auto_complete);
+                         const char *filter_node_name,
+                         BlockCompletionFunc *cb, void *opaque, Error **errp,
+                         bool auto_complete);
 /*
  * mirror_start:
  * @job_id: The id of the newly-created job, or %NULL to use the
@@ -745,6 +831,9 @@ void commit_active_start(const char *job_id, BlockDriverState *bs,
  * @on_source_error: The action to take upon error reading from the source.
  * @on_target_error: The action to take upon error writing to the target.
  * @unmap: Whether to unmap target where source sectors only contain zeroes.
+ * @filter_node_name: The node name that should be assigned to the filter
+ * driver that the mirror job inserts into the graph above @bs. NULL means that
+ * a node name should be autogenerated.
  * @errp: Error object.
  *
  * Start a mirroring operation on @bs.  Clusters that are allocated
@@ -758,7 +847,7 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
                   MirrorSyncMode mode, BlockMirrorBackingMode backing_mode,
                   BlockdevOnError on_source_error,
                   BlockdevOnError on_target_error,
-                  bool unmap, Error **errp);
+                  bool unmap, const char *filter_node_name, Error **errp);
 
 /*
  * backup_job_create:
@@ -796,11 +885,36 @@ void hmp_drive_add_node(Monitor *mon, const char *optstr);
 BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
                                   const char *child_name,
                                   const BdrvChildRole *child_role,
-                                  void *opaque);
+                                  uint64_t perm, uint64_t shared_perm,
+                                  void *opaque, Error **errp);
 void bdrv_root_unref_child(BdrvChild *child);
 
+int bdrv_child_check_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
+                          Error **errp);
+void bdrv_child_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared);
+void bdrv_child_abort_perm_update(BdrvChild *c);
+int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
+                            Error **errp);
+
+/* Default implementation for BlockDriver.bdrv_child_perm() that can be used by
+ * block filters: Forward CONSISTENT_READ, WRITE, WRITE_UNCHANGED and RESIZE to
+ * all children */
+void bdrv_filter_default_perms(BlockDriverState *bs, BdrvChild *c,
+                               const BdrvChildRole *role,
+                               uint64_t perm, uint64_t shared,
+                               uint64_t *nperm, uint64_t *nshared);
+
+/* Default implementation for BlockDriver.bdrv_child_perm() that can be used by
+ * (non-raw) image formats: Like above for bs->backing, but for bs->file it
+ * requires WRITE | RESIZE for read-write images, always requires
+ * CONSISTENT_READ and doesn't share WRITE. */
+void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c,
+                               const BdrvChildRole *role,
+                               uint64_t perm, uint64_t shared,
+                               uint64_t *nperm, uint64_t *nshared);
+
 const char *bdrv_get_parent_name(const BlockDriverState *bs);
-void blk_dev_change_media_cb(BlockBackend *blk, bool load);
+void blk_dev_change_media_cb(BlockBackend *blk, bool load, Error **errp);
 bool blk_dev_has_removable_media(BlockBackend *blk);
 bool blk_dev_has_tray(BlockBackend *blk);
 void blk_dev_eject_request(BlockBackend *blk, bool force);
diff --git a/include/block/blockjob.h b/include/block/blockjob.h
index 1acb256223..9e906f7d7e 100644
--- a/include/block/blockjob.h
+++ b/include/block/blockjob.h
@@ -169,13 +169,25 @@ BlockJob *block_job_get(const char *id);
 /**
  * block_job_add_bdrv:
  * @job: A block job
+ * @name: The name to assign to the new BdrvChild
  * @bs: A BlockDriverState that is involved in @job
+ * @perm, @shared_perm: Permissions to request on the node
  *
  * Add @bs to the list of BlockDriverState that are involved in
  * @job. This means that all operations will be blocked on @bs while
  * @job exists.
  */
-void block_job_add_bdrv(BlockJob *job, BlockDriverState *bs);
+int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs,
+                       uint64_t perm, uint64_t shared_perm, Error **errp);
+
+/**
+ * block_job_remove_all_bdrv:
+ * @job: The block job
+ *
+ * Remove all BlockDriverStates from the list of nodes that are involved in the
+ * job. This removes the blockers added with block_job_add_bdrv().
+ */
+void block_job_remove_all_bdrv(BlockJob *job);
 
 /**
  * block_job_set_speed:
diff --git a/include/block/blockjob_int.h b/include/block/blockjob_int.h
index 82238229c6..3f86cc5acc 100644
--- a/include/block/blockjob_int.h
+++ b/include/block/blockjob_int.h
@@ -119,6 +119,7 @@ struct BlockJobDriver {
  * generated automatically.
  * @job_type: The class object for the newly-created job.
  * @bs: The block
+ * @perm, @shared_perm: Permissions to request for @bs
  * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
  * @cb: Completion function for the job.
  * @opaque: Opaque pointer value passed to @cb.
@@ -134,7 +135,8 @@ struct BlockJobDriver {
  * called from a wrapper that is specific to the job type.
  */
 void *block_job_create(const char *job_id, const BlockJobDriver *driver,
-                       BlockDriverState *bs, int64_t speed, int flags,
+                       BlockDriverState *bs, uint64_t perm,
+                       uint64_t shared_perm, int64_t speed, int flags,
                        BlockCompletionFunc *cb, void *opaque, Error **errp);
 
 /**
diff --git a/include/hw/block/block.h b/include/hw/block/block.h
index df9d207d81..f3f6e8ef02 100644
--- a/include/hw/block/block.h
+++ b/include/hw/block/block.h
@@ -26,6 +26,7 @@ typedef struct BlockConf {
     /* geometry, not all devices use this */
     uint32_t cyls, heads, secs;
     OnOffAuto wce;
+    bool share_rw;
     BlockdevOnError rerror;
     BlockdevOnError werror;
 } BlockConf;
@@ -53,7 +54,9 @@ static inline unsigned int get_physical_block_exp(BlockConf *conf)
     DEFINE_PROP_UINT32("opt_io_size", _state, _conf.opt_io_size, 0),    \
     DEFINE_PROP_UINT32("discard_granularity", _state, \
                        _conf.discard_granularity, -1), \
-    DEFINE_PROP_ON_OFF_AUTO("write-cache", _state, _conf.wce, ON_OFF_AUTO_AUTO)
+    DEFINE_PROP_ON_OFF_AUTO("write-cache", _state, _conf.wce, \
+                            ON_OFF_AUTO_AUTO), \
+    DEFINE_PROP_BOOL("share-rw", _state, _conf.share_rw, false)
 
 #define DEFINE_BLOCK_CHS_PROPERTIES(_state, _conf)      \
     DEFINE_PROP_UINT32("cyls", _state, _conf.cyls, 0),  \
@@ -73,7 +76,8 @@ void blkconf_geometry(BlockConf *conf, int *trans,
                       unsigned cyls_max, unsigned heads_max, unsigned secs_max,
                       Error **errp);
 void blkconf_blocksizes(BlockConf *conf);
-void blkconf_apply_backend_options(BlockConf *conf);
+void blkconf_apply_backend_options(BlockConf *conf, bool readonly,
+                                   bool resizable, Error **errp);
 
 /* Hard disk geometry */
 
diff --git a/include/qemu-io.h b/include/qemu-io.h
index 4d402b9b01..196fde0f3a 100644
--- a/include/qemu-io.h
+++ b/include/qemu-io.h
@@ -36,6 +36,7 @@ typedef struct cmdinfo {
     const char  *args;
     const char  *oneline;
     helpfunc_t  help;
+    uint64_t    perm;
 } cmdinfo_t;
 
 extern bool qemuio_misalign;
diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h
index f365a51acf..096c17fce0 100644
--- a/include/sysemu/block-backend.h
+++ b/include/sysemu/block-backend.h
@@ -34,7 +34,7 @@ typedef struct BlockDevOps {
      * changes.  Sure would be useful if it did.
      * Device models with removable media must implement this callback.
      */
-    void (*change_media_cb)(void *opaque, bool load);
+    void (*change_media_cb)(void *opaque, bool load, Error **errp);
     /*
      * Runs when an eject request is issued from the monitor, the tray
      * is closed, and the medium is locked.
@@ -84,7 +84,7 @@ typedef struct BlockBackendPublic {
     QLIST_ENTRY(BlockBackendPublic) round_robin;
 } BlockBackendPublic;
 
-BlockBackend *blk_new(void);
+BlockBackend *blk_new(uint64_t perm, uint64_t shared_perm);
 BlockBackend *blk_new_open(const char *filename, const char *reference,
                            QDict *options, int flags, Error **errp);
 int blk_get_refcnt(BlockBackend *blk);
@@ -102,9 +102,12 @@ BlockBackend *blk_by_public(BlockBackendPublic *public);
 
 BlockDriverState *blk_bs(BlockBackend *blk);
 void blk_remove_bs(BlockBackend *blk);
-void blk_insert_bs(BlockBackend *blk, BlockDriverState *bs);
+int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp);
 bool bdrv_has_blk(BlockDriverState *bs);
 bool bdrv_is_root_node(BlockDriverState *bs);
+int blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
+                 Error **errp);
+void blk_get_perm(BlockBackend *blk, uint64_t *perm, uint64_t *shared_perm);
 
 void blk_set_allow_write_beyond_eof(BlockBackend *blk, bool allow);
 void blk_iostatus_enable(BlockBackend *blk);