Block layer patches

-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQIcBAABAgAGBQJXPdcnAAoJEH8JsnLIjy/WPEoQAK5vlRYqvQrrevMJviT4ZPUX
 cGGbabOcmfTBHGAgGwRLg+vQ043Sgu14JjtNbrsoSsBwAl9eAhAVGOimiieaY3vR
 35OOUxECswArJzK8I4XRx4KhI871Yq+8kHILPoXpF8L7YU38Zqa1D5z2dcOKYrL8
 Oy5IEfd1+Qfpxg/txKIioP5BzKVpz3V9/8GRNo0iAl7c806NoYFpnM0TXsed9Fjr
 YvUn1AdGHUF0/pV6vU46Qxz4yy1Q+cuoh923z6+YvXTcwok7PbjhAQWWA0qvSTuG
 otnPKMPBhYa6g7XOPD9Mra986vs6vBEGiPS5uqXoM5FqxF4Hc9LIeHEr+3hb+m53
 NLOmGqfct0USY9r6rXsOhZQb7nZCDuhaedv33ZfgE0T0cYxIilHs5PhgFAWfthhP
 aNJYlzbJUhqhTi7CJrJcFoGbNQDxux5qtlFo43M4vz/WYYDrwu8P7O3YO+sH0jU1
 EXJnbtztQvwfsiIEbIzvBRQl3XD9QmCfYO3lRbOwdCnd3ZLy47E2bze4gV3DwzK7
 CsBr+sa49xI8LMswPxTms+A+Inndn8O0mGI32Zi4nBKapjpy5Fb4YG6z8+WPfTKp
 Il1PsSgG84wm4YxGWty/UI4DoPY+hqlIIz1CNuRRNQtZTybLgNCK8ZKYbVlRppmf
 pGPpQ8pmqkeFLmx8hecm
 =ntKz
 -----END PGP SIGNATURE-----

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

Block layer patches

# gpg: Signature made Thu 19 May 2016 16:09:27 BST using RSA key ID C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"

* remotes/kevin/tags/for-upstream: (31 commits)
  qemu-iotests: Fix regression in 136 on aio_read invalid
  qemu-iotests: Simplify 109 with unaligned qemu-img compare
  qemu-io: Fix recent UI updates
  block: clarify error message for qmp-eject
  qemu-iotests: Some more write_zeroes tests
  qcow2: Fix write_zeroes with partially allocated backing file cluster
  qcow2: fix condition in is_zero_cluster
  block: Propagate AioContext change to all children
  block: Remove BlockDriverState.blk
  block: Don't return throttling info in query-named-block-nodes
  block: Avoid bs->blk in bdrv_next()
  block: Add bdrv_has_blk()
  block: Remove bdrv_aio_multiwrite()
  blockjob: Don't touch BDS iostatus
  blockjob: Don't set iostatus of target
  block: User BdrvChild callback for device name
  block: Use BdrvChild callbacks for change_media/resize
  block: Don't check throttled reqs in bdrv_requests_pending()
  Revert "block: Forbid I/O throttling on nodes with multiple parents for 2.6"
  block: Remove bdrv_move_feature_fields()
  ...

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

include/block/block.h

@@ -17,6 +17,7 @@ typedef struct BlockJob BlockJob;
 typedef struct BdrvChild BdrvChild;
 typedef struct BdrvChildRole BdrvChildRole;
 typedef struct BlockJobTxn BlockJobTxn;
+typedef struct BdrvNextIterator BdrvNextIterator;
 
 typedef struct BlockDriverInfo {
     /* in bytes, 0 if irrelevant */
@@ -187,10 +188,6 @@ void bdrv_stats_print(Monitor *mon, const QObject *data);
 void bdrv_info_stats(Monitor *mon, QObject **ret_data);
 
 /* disk I/O throttling */
-void bdrv_io_limits_enable(BlockDriverState *bs, const char *group);
-void bdrv_io_limits_disable(BlockDriverState *bs);
-void bdrv_io_limits_update_group(BlockDriverState *bs, const char *group);
-
 void bdrv_init(void);
 void bdrv_init_with_whitelist(void);
 bool bdrv_uses_whitelist(void);
@@ -333,7 +330,7 @@ void bdrv_aio_cancel(BlockAIOCB *acb);
 void bdrv_aio_cancel_async(BlockAIOCB *acb);
 
 typedef struct BlockRequest {
-    /* Fields to be filled by multiwrite caller */
+    /* Fields to be filled by caller */
     union {
         struct {
             int64_t sector;
@@ -349,13 +346,10 @@ typedef struct BlockRequest {
     BlockCompletionFunc *cb;
     void *opaque;
 
-    /* Filled by multiwrite implementation */
+    /* Filled by block layer */
     int error;
 } BlockRequest;
 
-int bdrv_aio_multiwrite(BlockDriverState *bs, BlockRequest *reqs,
-    int num_reqs);
-
 /* sg packet commands */
 int bdrv_ioctl(BlockDriverState *bs, unsigned long int req, void *buf);
 BlockAIOCB *bdrv_aio_ioctl(BlockDriverState *bs,
@@ -408,7 +402,7 @@ BlockDriverState *bdrv_lookup_bs(const char *device,
                                  Error **errp);
 bool bdrv_chain_contains(BlockDriverState *top, BlockDriverState *base);
 BlockDriverState *bdrv_next_node(BlockDriverState *bs);
-BlockDriverState *bdrv_next(BlockDriverState *bs);
+BdrvNextIterator *bdrv_next(BdrvNextIterator *it, BlockDriverState **bs);
 BlockDriverState *bdrv_next_monitor_owned(BlockDriverState *bs);
 int bdrv_is_encrypted(BlockDriverState *bs);
 int bdrv_key_required(BlockDriverState *bs);

include/block/block_int.h

@@ -26,7 +26,6 @@
 
 #include "block/accounting.h"
 #include "block/block.h"
-#include "block/throttle-groups.h"
 #include "qemu/option.h"
 #include "qemu/queue.h"
 #include "qemu/coroutine.h"
@@ -365,6 +364,25 @@ typedef struct BdrvAioNotifier {
 struct BdrvChildRole {
     void (*inherit_options)(int *child_flags, QDict *child_options,
                             int parent_flags, QDict *parent_options);
+
+    void (*change_media)(BdrvChild *child, bool load);
+    void (*resize)(BdrvChild *child);
+
+    /* Returns a name that is supposedly more useful for human users than the
+     * node name for identifying the node in question (in particular, a BB
+     * name), or NULL if the parent can't provide a better name. */
+    const char* (*get_name)(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
+     * called.
+     *
+     * Note that this can be nested. If drained_begin() was called twice, new
+     * I/O is allowed only after drained_end() was called twice, too.
+     */
+    void (*drained_begin)(BdrvChild *child);
+    void (*drained_end)(BdrvChild *child);
 };
 
 extern const BdrvChildRole child_file;
@@ -374,6 +392,7 @@ struct BdrvChild {
     BlockDriverState *bs;
     char *name;
     const BdrvChildRole *role;
+    void *opaque;
     QLIST_ENTRY(BdrvChild) next;
     QLIST_ENTRY(BdrvChild) next_parent;
 };
@@ -399,8 +418,6 @@ struct BlockDriverState {
     BlockDriver *drv; /* NULL means no media */
     void *opaque;
 
-    BlockBackend *blk;          /* owning backend, if any */
-
     AioContext *aio_context; /* event loop used for fd handlers, timers, etc */
     /* long-running tasks intended to always use the same AioContext as this
      * BDS may register themselves in this list to be notified of changes
@@ -424,19 +441,6 @@ struct BlockDriverState {
     /* number of in-flight serialising requests */
     unsigned int serialising_in_flight;
 
-    /* I/O throttling.
-     * throttle_state tells us if this BDS has I/O limits configured.
-     * io_limits_disabled tells us if they are currently being enforced */
-    CoQueue      throttled_reqs[2];
-    unsigned int io_limits_disabled;
-
-    /* The following fields are protected by the ThrottleGroup lock.
-     * See the ThrottleGroup documentation for details. */
-    ThrottleState *throttle_state;
-    ThrottleTimers throttle_timers;
-    unsigned       pending_reqs[2];
-    QLIST_ENTRY(BlockDriverState) round_robin;
-
     /* Offset after the highest byte written to */
     uint64_t wr_highest_offset;
 
@@ -502,9 +506,6 @@ struct BlockBackendRootState {
     int open_flags;
     bool read_only;
     BlockdevDetectZeroesOptions detect_zeroes;
-
-    char *throttle_group;
-    ThrottleState *throttle_state;
 };
 
 static inline BlockDriverState *backing_bs(BlockDriverState *bs)
@@ -539,9 +540,6 @@ int get_tmp_filename(char *filename, int size);
 BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size,
                             const char *filename);
 
-void bdrv_set_io_limits(BlockDriverState *bs,
-                        ThrottleConfig *cfg);
-
 
 /**
  * bdrv_add_before_write_notifier:
@@ -724,16 +722,13 @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
                                   const BdrvChildRole *child_role);
 void bdrv_root_unref_child(BdrvChild *child);
 
-void bdrv_no_throttling_begin(BlockDriverState *bs);
-void bdrv_no_throttling_end(BlockDriverState *bs);
-
+const char *bdrv_get_parent_name(const BlockDriverState *bs);
 void blk_dev_change_media_cb(BlockBackend *blk, bool load);
 bool blk_dev_has_removable_media(BlockBackend *blk);
 bool blk_dev_has_tray(BlockBackend *blk);
 void blk_dev_eject_request(BlockBackend *blk, bool force);
 bool blk_dev_is_tray_open(BlockBackend *blk);
 bool blk_dev_is_medium_locked(BlockBackend *blk);
-void blk_dev_resize_cb(BlockBackend *blk);
 
 void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector, int nr_sectors);
 bool bdrv_requests_pending(BlockDriverState *bs);

include/block/blockjob.h

@@ -383,7 +383,6 @@ void block_job_iostatus_reset(BlockJob *job);
 /**
  * block_job_error_action:
  * @job: The job to signal an error for.
- * @bs: The block device on which to set an I/O error.
  * @on_err: The error action setting.
  * @is_read: Whether the operation was a read.
  * @error: The error that was reported.
@@ -391,8 +390,7 @@ void block_job_iostatus_reset(BlockJob *job);
  * Report an I/O error for a block job and possibly stop the VM.  Return the
  * action that was selected based on @on_err and @error.
  */
-BlockErrorAction block_job_error_action(BlockJob *job, BlockDriverState *bs,
-                                        BlockdevOnError on_err,
+BlockErrorAction block_job_error_action(BlockJob *job, BlockdevOnError on_err,
                                         int is_read, int error);
 
 typedef void BlockJobDeferToMainLoopFn(BlockJob *job, void *opaque);

include/block/throttle-groups.h

@@ -28,19 +28,19 @@
 #include "qemu/throttle.h"
 #include "block/block_int.h"
 
-const char *throttle_group_get_name(BlockDriverState *bs);
+const char *throttle_group_get_name(BlockBackend *blk);
 
 ThrottleState *throttle_group_incref(const char *name);
 void throttle_group_unref(ThrottleState *ts);
 
-void throttle_group_config(BlockDriverState *bs, ThrottleConfig *cfg);
-void throttle_group_get_config(BlockDriverState *bs, ThrottleConfig *cfg);
+void throttle_group_config(BlockBackend *blk, ThrottleConfig *cfg);
+void throttle_group_get_config(BlockBackend *blk, ThrottleConfig *cfg);
 
-void throttle_group_register_bs(BlockDriverState *bs, const char *groupname);
-void throttle_group_unregister_bs(BlockDriverState *bs);
-void throttle_group_restart_bs(BlockDriverState *bs);
+void throttle_group_register_blk(BlockBackend *blk, const char *groupname);
+void throttle_group_unregister_blk(BlockBackend *blk);
+void throttle_group_restart_blk(BlockBackend *blk);
 
-void coroutine_fn throttle_group_co_io_limits_intercept(BlockDriverState *bs,
+void coroutine_fn throttle_group_co_io_limits_intercept(BlockBackend *blk,
                                                         unsigned int bytes,
                                                         bool is_write);
 

include/sysemu/block-backend.h

@@ -14,6 +14,7 @@
 #define BLOCK_BACKEND_H
 
 #include "qemu/iov.h"
+#include "block/throttle-groups.h"
 
 /*
  * TODO Have to include block/block.h for a bunch of block layer
@@ -59,6 +60,24 @@ typedef struct BlockDevOps {
     void (*resize_cb)(void *opaque);
 } BlockDevOps;
 
+/* This struct is embedded in (the private) BlockBackend struct and contains
+ * fields that must be public. This is in particular for QLIST_ENTRY() and
+ * friends so that BlockBackends can be kept in lists outside block-backend.c */
+typedef struct BlockBackendPublic {
+    /* I/O throttling.
+     * throttle_state tells us if this BlockBackend has I/O limits configured.
+     * io_limits_disabled tells us if they are currently being enforced */
+    CoQueue      throttled_reqs[2];
+    unsigned int io_limits_disabled;
+
+    /* The following fields are protected by the ThrottleGroup lock.
+     * See the ThrottleGroup documentation for details. */
+    ThrottleState *throttle_state;
+    ThrottleTimers throttle_timers;
+    unsigned       pending_reqs[2];
+    QLIST_ENTRY(BlockBackendPublic) round_robin;
+} BlockBackendPublic;
+
 BlockBackend *blk_new(Error **errp);
 BlockBackend *blk_new_with_bs(Error **errp);
 BlockBackend *blk_new_open(const char *filename, const char *reference,
@@ -70,13 +89,16 @@ void blk_remove_all_bs(void);
 const char *blk_name(BlockBackend *blk);
 BlockBackend *blk_by_name(const char *name);
 BlockBackend *blk_next(BlockBackend *blk);
-BlockDriverState *blk_next_root_bs(BlockDriverState *bs);
 bool monitor_add_blk(BlockBackend *blk, const char *name, Error **errp);
 void monitor_remove_blk(BlockBackend *blk);
 
+BlockBackendPublic *blk_get_public(BlockBackend *blk);
+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);
+bool bdrv_has_blk(BlockDriverState *bs);
 
 void blk_set_allow_write_beyond_eof(BlockBackend *blk, bool allow);
 void blk_iostatus_enable(BlockBackend *blk);
@@ -116,7 +138,6 @@ BlockAIOCB *blk_aio_discard(BlockBackend *blk,
                             BlockCompletionFunc *cb, void *opaque);
 void blk_aio_cancel(BlockAIOCB *acb);
 void blk_aio_cancel_async(BlockAIOCB *acb);
-int blk_aio_multiwrite(BlockBackend *blk, BlockRequest *reqs, int num_reqs);
 int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf);
 BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
                           BlockCompletionFunc *cb, void *opaque);
@@ -190,4 +211,9 @@ BlockAIOCB *blk_abort_aio_request(BlockBackend *blk,
                                   BlockCompletionFunc *cb,
                                   void *opaque, int ret);
 
+void blk_set_io_limits(BlockBackend *blk, ThrottleConfig *cfg);
+void blk_io_limits_disable(BlockBackend *blk);
+void blk_io_limits_enable(BlockBackend *blk, const char *group);
+void blk_io_limits_update_group(BlockBackend *blk, const char *group);
+
 #endif